From: DongHun Kwak Date: Tue, 8 Dec 2020 04:45:06 +0000 (+0900) Subject: Imported Upstream version 3.7.5 X-Git-Tag: upstream/3.7.5^0 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=aa2fdd096dd249005a9211bdad5df72cf0024144;p=platform%2Fupstream%2Fpython3.git Imported Upstream version 3.7.5 --- diff --git a/.azure-pipelines/ci.yml b/.azure-pipelines/ci.yml index fcfac85e..38d0cc3e 100644 --- a/.azure-pipelines/ci.yml +++ b/.azure-pipelines/ci.yml @@ -42,7 +42,7 @@ jobs: testRunPlatform: macos pool: - vmImage: xcode9-macos10.13 + vmImage: macos-10.14 steps: - template: ./macos-steps.yml @@ -59,7 +59,7 @@ jobs: variables: testRunTitle: '$(build.sourceBranchName)-linux' testRunPlatform: linux - openssl_version: 1.1.1c + openssl_version: 1.1.1d steps: - template: ./posix-steps.yml @@ -116,7 +116,7 @@ jobs: variables: testRunTitle: '$(Build.SourceBranchName)-linux-coverage' testRunPlatform: linux-coverage - openssl_version: 1.1.1c + openssl_version: 1.1.1d steps: - template: ./posix-steps.yml diff --git a/.azure-pipelines/macos-steps.yml b/.azure-pipelines/macos-steps.yml index 64708168..d2ca580a 100644 --- a/.azure-pipelines/macos-steps.yml +++ b/.azure-pipelines/macos-steps.yml @@ -14,6 +14,8 @@ steps: - script: make buildbottest TESTOPTS="-j4 -uall,-cpu --junit-xml=$(build.binariesDirectory)/test-results.xml" displayName: 'Tests' + continueOnError: true + timeoutInMinutes: 30 - task: PublishTestResults@2 displayName: 'Publish Test Results' diff --git a/.azure-pipelines/pr.yml b/.azure-pipelines/pr.yml index 2486f88a..8661da93 100644 --- a/.azure-pipelines/pr.yml +++ b/.azure-pipelines/pr.yml @@ -40,7 +40,7 @@ jobs: testRunPlatform: macos pool: - vmImage: xcode9-macos10.13 + vmImage: macos-10.14 steps: - template: ./macos-steps.yml @@ -59,7 +59,7 @@ jobs: variables: testRunTitle: '$(system.pullRequest.TargetBranch)-linux' testRunPlatform: linux - openssl_version: 1.1.1c + openssl_version: 1.1.1d steps: - template: ./posix-steps.yml @@ -116,7 +116,7 @@ jobs: variables: testRunTitle: '$(Build.SourceBranchName)-linux-coverage' testRunPlatform: linux-coverage - openssl_version: 1.1.1c + openssl_version: 1.1.1d steps: - template: ./posix-steps.yml diff --git a/Doc/Makefile b/Doc/Makefile index 307d1e0e..08013c0e 100644 --- a/Doc/Makefile +++ b/Doc/Makefile @@ -12,7 +12,11 @@ PAPER = SOURCES = DISTVERSION = $(shell $(PYTHON) tools/extensions/patchlevel.py) -ALLSPHINXOPTS = -b $(BUILDER) -d build/doctrees -D latex_elements.papersize=$(PAPER) \ +# Internal variables. +PAPEROPT_a4 = -D latex_elements.papersize=a4paper +PAPEROPT_letter = -D latex_elements.papersize=letterpaper + +ALLSPHINXOPTS = -b $(BUILDER) -d build/doctrees $(PAPEROPT_$(PAPER)) \ $(SPHINXOPTS) . build/$(BUILDER) $(SOURCES) .PHONY: help build html htmlhelp latex text changes linkcheck \ diff --git a/Doc/bugs.rst b/Doc/bugs.rst index c449ba2e..1dbfadbf 100644 --- a/Doc/bugs.rst +++ b/Doc/bugs.rst @@ -72,7 +72,7 @@ taken on the bug. Article which goes into some detail about how to create a useful bug report. This describes what kind of information is useful and why it is useful. - `Bug Writing Guidelines `_ + `Bug Report Writing Guidelines `_ Information about writing a good bug report. Some of this is specific to the Mozilla project, but describes general good practices. diff --git a/Doc/c-api/allocation.rst b/Doc/c-api/allocation.rst index 25a867f1..c5e548d2 100644 --- a/Doc/c-api/allocation.rst +++ b/Doc/c-api/allocation.rst @@ -48,7 +48,7 @@ Allocating Objects on the Heap improving the memory management efficiency. -.. c:function:: void PyObject_Del(PyObject *op) +.. c:function:: void PyObject_Del(void *op) Releases memory allocated to an object using :c:func:`PyObject_New` or :c:func:`PyObject_NewVar`. This is normally called from the diff --git a/Doc/c-api/buffer.rst b/Doc/c-api/buffer.rst index c7c1e3cc..b639ba6f 100644 --- a/Doc/c-api/buffer.rst +++ b/Doc/c-api/buffer.rst @@ -355,8 +355,10 @@ If :c:member:`~Py_buffer.strides` is *NULL*, the array is interpreted as a standard n-dimensional C-array. Otherwise, the consumer must access an n-dimensional array as follows: - ``ptr = (char *)buf + indices[0] * strides[0] + ... + indices[n-1] * strides[n-1]`` - ``item = *((typeof(item) *)ptr);`` +.. code-block:: c + + ptr = (char *)buf + indices[0] * strides[0] + ... + indices[n-1] * strides[n-1]; + item = *((typeof(item) *)ptr); As noted above, :c:member:`~Py_buffer.buf` can point to any location within @@ -473,11 +475,24 @@ Buffer-related functions (*order* is ``'A'``). Return ``0`` otherwise. This function always succeeds. +.. c:function:: void* PyBuffer_GetPointer(Py_buffer *view, Py_ssize_t *indices) + + Get the memory area pointed to by the *indices* inside the given *view*. + *indices* must point to an array of ``view->ndim`` indices. + + +.. c:function:: int PyBuffer_FromContiguous(Py_buffer *view, void *buf, Py_ssize_t len, char fort) + + Copy contiguous *len* bytes from *buf* to *view*. + *fort* can be ``'C'`` or ``'F'`` (for C-style or Fortran-style ordering). + ``0`` is returned on success, ``-1`` on error. + + .. c:function:: int PyBuffer_ToContiguous(void *buf, Py_buffer *src, Py_ssize_t len, char order) Copy *len* bytes from *src* to its contiguous representation in *buf*. - *order* can be ``'C'`` or ``'F'`` (for C-style or Fortran-style ordering). - ``0`` is returned on success, ``-1`` on error. + *order* can be ``'C'`` or ``'F'`` or ``'A'`` (for C-style or Fortran-style + ordering or either one). ``0`` is returned on success, ``-1`` on error. This function fails if *len* != *src->len*. diff --git a/Doc/c-api/exceptions.rst b/Doc/c-api/exceptions.rst index 13e00b54..14ca2b40 100644 --- a/Doc/c-api/exceptions.rst +++ b/Doc/c-api/exceptions.rst @@ -317,7 +317,7 @@ an error value). :mod:`warnings` module and the :option:`-W` option in the command line documentation. There is no C API for warning control. -.. c:function:: PyObject* PyErr_SetImportErrorSubclass(PyObject *msg, PyObject *name, PyObject *path) +.. c:function:: PyObject* PyErr_SetImportErrorSubclass(PyObject *exception, PyObject *msg, PyObject *name, PyObject *path) Much like :c:func:`PyErr_SetImportError` but this function allows for specifying a subclass of :exc:`ImportError` to raise. diff --git a/Doc/c-api/intro.rst b/Doc/c-api/intro.rst index 330871bc..964d348c 100644 --- a/Doc/c-api/intro.rst +++ b/Doc/c-api/intro.rst @@ -69,10 +69,12 @@ standard headers) have one of the prefixes ``Py`` or ``_Py``. Names beginning with ``_Py`` are for internal use by the Python implementation and should not be used by extension writers. Structure member names do not have a reserved prefix. -**Important:** user code should never define names that begin with ``Py`` or -``_Py``. This confuses the reader, and jeopardizes the portability of the user -code to future Python versions, which may define additional names beginning with -one of these prefixes. +.. note:: + + User code should never define names that begin with ``Py`` or ``_Py``. This + confuses the reader, and jeopardizes the portability of the user code to + future Python versions, which may define additional names beginning with one + of these prefixes. The header files are typically installed with Python. On Unix, these are located in the directories :file:`{prefix}/include/pythonversion/` and @@ -90,9 +92,9 @@ multi-platform builds since the platform independent headers under :envvar:`prefix` include the platform specific headers from :envvar:`exec_prefix`. -C++ users should note that though the API is defined entirely using C, the -header files do properly declare the entry points to be ``extern "C"``, so there -is no need to do anything special to use the API from C++. +C++ users should note that although the API is defined entirely using C, the +header files properly declare the entry points to be ``extern "C"``. As a result, +there is no need to do anything special to use the API from C++. Useful macros diff --git a/Doc/c-api/list.rst b/Doc/c-api/list.rst index 5b263a7b..a5cd634a 100644 --- a/Doc/c-api/list.rst +++ b/Doc/c-api/list.rst @@ -59,9 +59,9 @@ List Objects .. c:function:: PyObject* PyList_GetItem(PyObject *list, Py_ssize_t index) Return the object at position *index* in the list pointed to by *list*. The - position must be positive, indexing from the end of the list is not - supported. If *index* is out of bounds, return *NULL* and set an - :exc:`IndexError` exception. + position must be non-negative; indexing from the end of the list is not + supported. If *index* is out of bounds (<0 or >=len(list)), + return *NULL* and set an :exc:`IndexError` exception. .. c:function:: PyObject* PyList_GET_ITEM(PyObject *list, Py_ssize_t i) diff --git a/Doc/c-api/memory.rst b/Doc/c-api/memory.rst index 9b42900b..01f7f420 100644 --- a/Doc/c-api/memory.rst +++ b/Doc/c-api/memory.rst @@ -67,7 +67,7 @@ example:: In this example, the memory request for the I/O buffer is handled by the C library allocator. The Python memory manager is involved only in the allocation -of the string object returned as a result. +of the bytes object returned as a result. In most situations, however, it is recommended to allocate memory from the Python heap specifically because the latter is under control of the Python diff --git a/Doc/c-api/module.rst b/Doc/c-api/module.rst index 017b6568..7168dc73 100644 --- a/Doc/c-api/module.rst +++ b/Doc/c-api/module.rst @@ -417,7 +417,22 @@ state: Add an object to *module* as *name*. This is a convenience function which can be used from the module's initialization function. This steals a reference to - *value*. Return ``-1`` on error, ``0`` on success. + *value* on success. Return ``-1`` on error, ``0`` on success. + + .. note:: + + Unlike other functions that steal references, ``PyModule_AddObject()`` only + decrements the reference count of *value* **on success**. + + This means that its return value must be checked, and calling code must + :c:func:`Py_DECREF` *value* manually on error. Example usage:: + + Py_INCREF(spam); + if (PyModule_AddObject(module, "spam", spam) < 0) { + Py_DECREF(module); + Py_DECREF(spam); + return NULL; + } .. c:function:: int PyModule_AddIntConstant(PyObject *module, const char *name, long value) diff --git a/Doc/c-api/sequence.rst b/Doc/c-api/sequence.rst index 6d22f35e..d653319f 100644 --- a/Doc/c-api/sequence.rst +++ b/Doc/c-api/sequence.rst @@ -130,10 +130,17 @@ Sequence Protocol .. c:function:: PyObject* PySequence_Fast(PyObject *o, const char *m) - Return the sequence or iterable *o* as a list, unless it is already a tuple or list, in - which case *o* is returned. Use :c:func:`PySequence_Fast_GET_ITEM` to access - the members of the result. Returns *NULL* on failure. If the object is not - a sequence or iterable, raises :exc:`TypeError` with *m* as the message text. + Return the sequence or iterable *o* as an object usable by the other + ``PySequence_Fast*`` family of functions. If the object is not a sequence or + iterable, raises :exc:`TypeError` with *m* as the message text. Returns + *NULL* on failure. + + The ``PySequence_Fast*`` functions are thus named because they assume + *o* is a :c:type:`PyTupleObject` or a :c:type:`PyListObject` and access + the data fields of *o* directly. + + As a CPython implementation detail, if *o* is already a sequence or list, it + will be returned. .. c:function:: Py_ssize_t PySequence_Fast_GET_SIZE(PyObject *o) @@ -141,8 +148,8 @@ Sequence Protocol Returns the length of *o*, assuming that *o* was returned by :c:func:`PySequence_Fast` and that *o* is not *NULL*. The size can also be gotten by calling :c:func:`PySequence_Size` on *o*, but - :c:func:`PySequence_Fast_GET_SIZE` is faster because it can assume *o* is a list - or tuple. + :c:func:`PySequence_Fast_GET_SIZE` is faster because it can assume *o* is a + list or tuple. .. c:function:: PyObject* PySequence_Fast_GET_ITEM(PyObject *o, Py_ssize_t i) @@ -163,7 +170,7 @@ Sequence Protocol .. c:function:: PyObject* PySequence_ITEM(PyObject *o, Py_ssize_t i) - Return the *i*\ th element of *o* or *NULL* on failure. Macro form of + Return the *i*\ th element of *o* or *NULL* on failure. Faster form of :c:func:`PySequence_GetItem` but without checking that :c:func:`PySequence_Check` on *o* is true and without adjustment for negative indices. diff --git a/Doc/conf.py b/Doc/conf.py index da8b9d7b..ce2d47f5 100644 --- a/Doc/conf.py +++ b/Doc/conf.py @@ -38,8 +38,10 @@ highlight_language = 'python3' needs_sphinx = "1.6.6" # Ignore any .rst files in the venv/ directory. -venvdir = os.getenv('VENVDIR', 'venv') -exclude_patterns = [venvdir+'/*', 'README.rst'] +exclude_patterns = ['venv/*', 'README.rst'] +venvdir = os.getenv('VENVDIR') +if venvdir is not None: + exclude_patterns.append(venvdir + '/*') # Disable Docutils smartquotes for several translations smartquotes_excludes = { diff --git a/Doc/data/refcounts.dat b/Doc/data/refcounts.dat index 213ddcb6..ec8094ef 100644 --- a/Doc/data/refcounts.dat +++ b/Doc/data/refcounts.dat @@ -2444,7 +2444,7 @@ PyUnicode_FromWideChar:Py_ssize_t:size:: PyUnicode_AsWideChar:Py_ssize_t::: PyUnicode_AsWideChar:PyObject*:*unicode:0: PyUnicode_AsWideChar:wchar_t*:w:: -PyUnicode_AsWideChar:Pyssize_t:size:: +PyUnicode_AsWideChar:Py_ssize_t:size:: PyUnicode_AsWideCharString:wchar_t*::: PyUnicode_AsWideCharString:PyObject*:unicode:0: diff --git a/Doc/distutils/builtdist.rst b/Doc/distutils/builtdist.rst index f1f34712..0a83f8bd 100644 --- a/Doc/distutils/builtdist.rst +++ b/Doc/distutils/builtdist.rst @@ -313,8 +313,8 @@ or the :command:`bdist` command with the :option:`!--formats` option:: If you have a pure module distribution (only containing pure Python modules and packages), the resulting installer will be version independent and have a name -like :file:`foo-1.0.win32.exe`. These installers can even be created on Unix -platforms or Mac OS X. +like :file:`foo-1.0.win32.exe`. Note that creating ``wininst`` binary +distributions in only supported on Windows systems. If you have a non-pure distribution, the extensions can only be created on a Windows platform, and will be Python version dependent. The installer filename diff --git a/Doc/extending/extending.rst b/Doc/extending/extending.rst index afed3aab..73a77c78 100644 --- a/Doc/extending/extending.rst +++ b/Doc/extending/extending.rst @@ -209,7 +209,7 @@ usually declare a static object variable at the beginning of your file:: static PyObject *SpamError; and initialize it in your module's initialization function (:c:func:`PyInit_spam`) -with an exception object (leaving out the error checking for now):: +with an exception object:: PyMODINIT_FUNC PyInit_spam(void) @@ -221,8 +221,14 @@ with an exception object (leaving out the error checking for now):: return NULL; SpamError = PyErr_NewException("spam.error", NULL, NULL); - Py_INCREF(SpamError); - PyModule_AddObject(m, "error", SpamError); + Py_XINCREF(SpamError); + if (PyModule_AddObject(m, "error", SpamError) < 0) { + Py_XDECREF(SpamError); + Py_CLEAR(SpamError); + Py_DECREF(m); + return NULL; + } + return m; } @@ -1261,8 +1267,12 @@ function must take care of initializing the C API pointer array:: /* Create a Capsule containing the API pointer array's address */ c_api_object = PyCapsule_New((void *)PySpam_API, "spam._C_API", NULL); - if (c_api_object != NULL) - PyModule_AddObject(m, "_C_API", c_api_object); + if (PyModule_AddObject(m, "_C_API", c_api_object) < 0) { + Py_XDECREF(c_api_object); + Py_DECREF(m); + return NULL; + } + return m; } diff --git a/Doc/extending/newtypes_tutorial.rst b/Doc/extending/newtypes_tutorial.rst index 07c2ef71..50be28fb 100644 --- a/Doc/extending/newtypes_tutorial.rst +++ b/Doc/extending/newtypes_tutorial.rst @@ -179,7 +179,12 @@ This initializes the :class:`Custom` type, filling in a number of members to the appropriate default values, including :attr:`ob_type` that we initially set to *NULL*. :: - PyModule_AddObject(m, "Custom", (PyObject *) &CustomType); + Py_INCREF(&CustomType); + if (PyModule_AddObject(m, "Custom", (PyObject *) &CustomType) < 0) { + Py_DECREF(&CustomType); + Py_DECREF(m); + return NULL; + } This adds the type to the module dictionary. This allows us to create :class:`Custom` instances by calling the :class:`Custom` class: @@ -864,7 +869,12 @@ function:: return NULL; Py_INCREF(&SubListType); - PyModule_AddObject(m, "SubList", (PyObject *) &SubListType); + if (PyModule_AddObject(m, "SubList", (PyObject *) &SubListType) < 0) { + Py_DECREF(&SubListType); + Py_DECREF(m); + return NULL; + } + return m; } diff --git a/Doc/faq/programming.rst b/Doc/faq/programming.rst index f14e8cc8..a8aaebf7 100644 --- a/Doc/faq/programming.rst +++ b/Doc/faq/programming.rst @@ -659,7 +659,7 @@ How can my code discover the name of an object? ----------------------------------------------- Generally speaking, it can't, because objects don't really have names. -Essentially, assignment always binds a name to a value; The same is true of +Essentially, assignment always binds a name to a value; the same is true of ``def`` and ``class`` statements, but in that case the value is a callable. Consider the following code:: diff --git a/Doc/glossary.rst b/Doc/glossary.rst index df6f6b64..ed588612 100644 --- a/Doc/glossary.rst +++ b/Doc/glossary.rst @@ -243,7 +243,7 @@ Glossary Fortran contiguous arrays, the first index varies the fastest. coroutine - Coroutines is a more generalized form of subroutines. Subroutines are + Coroutines are a more generalized form of subroutines. Subroutines are entered at one point and exited at another point. Coroutines can be entered, exited, and resumed at many different points. They can be implemented with the :keyword:`async def` statement. See also @@ -735,17 +735,28 @@ Glossary also :term:`immutable`. named tuple - Any tuple-like class whose indexable elements are also accessible using - named attributes (for example, :func:`time.localtime` returns a - tuple-like object where the *year* is accessible either with an - index such as ``t[0]`` or with a named attribute like ``t.tm_year``). - - A named tuple can be a built-in type such as :class:`time.struct_time`, - or it can be created with a regular class definition. A full featured - named tuple can also be created with the factory function - :func:`collections.namedtuple`. The latter approach automatically - provides extra features such as a self-documenting representation like - ``Employee(name='jones', title='programmer')``. + The term "named tuple" applies to any type or class that inherits from + tuple and whose indexable elements are also accessible using named + attributes. The type or class may have other features as well. + + Several built-in types are named tuples, including the values returned + by :func:`time.localtime` and :func:`os.stat`. Another example is + :data:`sys.float_info`:: + + >>> sys.float_info[1] # indexed access + 1024 + >>> sys.float_info.max_exp # named field access + 1024 + >>> isinstance(sys.float_info, tuple) # kind of tuple + True + + Some named tuples are built-in types (such as the above examples). + Alternatively, a named tuple can be created from a regular class + definition that inherits from :class:`tuple` and that defines named + fields. Such a class can be written by hand or it can be created with + the factory function :func:`collections.namedtuple`. The latter + technique also adds some extra methods that may not be found in + hand-written or built-in named tuples. namespace The place where a variable is stored. Namespaces are implemented as @@ -1028,14 +1039,6 @@ Glossary an :term:`expression` or one of several constructs with a keyword, such as :keyword:`if`, :keyword:`while` or :keyword:`for`. - struct sequence - A tuple with named elements. Struct sequences expose an interface similar - to :term:`named tuple` in that elements can be accessed either by - index or as an attribute. However, they do not have any of the named tuple - methods like :meth:`~collections.somenamedtuple._make` or - :meth:`~collections.somenamedtuple._asdict`. Examples of struct sequences - include :data:`sys.float_info` and the return value of :func:`os.stat`. - text encoding A codec which encodes Unicode strings to bytes. diff --git a/Doc/howto/logging-cookbook.rst b/Doc/howto/logging-cookbook.rst index e391506c..a9222ab6 100644 --- a/Doc/howto/logging-cookbook.rst +++ b/Doc/howto/logging-cookbook.rst @@ -949,6 +949,41 @@ This variant shows how you can e.g. apply configuration for particular loggers machinery in the main process (even though the logging events are generated in the worker processes) to direct the messages to the appropriate destinations. +Using concurrent.futures.ProcessPoolExecutor +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If you want to use :class:`concurrent.futures.ProcessPoolExecutor` to start +your worker processes, you need to create the queue slightly differently. +Instead of + +.. code-block:: python + + queue = multiprocessing.Queue(-1) + +you should use + +.. code-block:: python + + queue = multiprocessing.Manager().Queue(-1) # also works with the examples above + +and you can then replace the worker creation from this:: + + workers = [] + for i in range(10): + worker = multiprocessing.Process(target=worker_process, + args=(queue, worker_configurer)) + workers.append(worker) + worker.start() + for w in workers: + w.join() + +to this (remembering to first import :mod:`concurrent.futures`):: + + with concurrent.futures.ProcessPoolExecutor(max_workers=10) as executor: + for i in range(10): + executor.submit(worker_process, queue, worker_configurer) + + Using file rotation ------------------- @@ -2267,9 +2302,9 @@ The script just arranges to decorate ``foo`` with a decorator which will do the conditional logging that's required. The decorator takes a logger as a parameter and attaches a memory handler for the duration of the call to the decorated function. The decorator can be additionally parameterised using a target handler, -a level at which flushing should occur, and a capacity for the buffer. These -default to a :class:`~logging.StreamHandler` which writes to ``sys.stderr``, -``logging.ERROR`` and ``100`` respectively. +a level at which flushing should occur, and a capacity for the buffer (number of +records buffered). These default to a :class:`~logging.StreamHandler` which +writes to ``sys.stderr``, ``logging.ERROR`` and ``100`` respectively. Here's the script:: diff --git a/Doc/howto/unicode.rst b/Doc/howto/unicode.rst index d4b1b2a7..1ac41020 100644 --- a/Doc/howto/unicode.rst +++ b/Doc/howto/unicode.rst @@ -57,14 +57,14 @@ their corresponding code points: ... 007B '{'; LEFT CURLY BRACKET ... - 2167 'Ⅶ': ROMAN NUMERAL EIGHT - 2168 'Ⅸ': ROMAN NUMERAL NINE + 2167 'Ⅷ'; ROMAN NUMERAL EIGHT + 2168 'Ⅸ'; ROMAN NUMERAL NINE ... - 265E '♞': BLACK CHESS KNIGHT - 265F '♟': BLACK CHESS PAWN + 265E '♞'; BLACK CHESS KNIGHT + 265F '♟'; BLACK CHESS PAWN ... - 1F600 '😀': GRINNING FACE - 1F609 '😉': WINKING FACE + 1F600 '😀'; GRINNING FACE + 1F609 '😉'; WINKING FACE ... Strictly, these definitions imply that it's meaningless to say 'this is diff --git a/Doc/includes/custom.c b/Doc/includes/custom.c index 13d16f54..bda32e2a 100644 --- a/Doc/includes/custom.c +++ b/Doc/includes/custom.c @@ -35,6 +35,11 @@ PyInit_custom(void) return NULL; Py_INCREF(&CustomType); - PyModule_AddObject(m, "Custom", (PyObject *) &CustomType); + if (PyModule_AddObject(m, "Custom", (PyObject *) &CustomType) < 0) { + Py_DECREF(&CustomType); + PY_DECREF(m); + return NULL; + } + return m; } diff --git a/Doc/includes/custom2.c b/Doc/includes/custom2.c index 6477a19d..5bacab7a 100644 --- a/Doc/includes/custom2.c +++ b/Doc/includes/custom2.c @@ -128,6 +128,11 @@ PyInit_custom2(void) return NULL; Py_INCREF(&CustomType); - PyModule_AddObject(m, "Custom", (PyObject *) &CustomType); + if (PyModule_AddObject(m, "Custom", (PyObject *) &CustomType) < 0) { + Py_DECREF(&CustomType); + Py_DECREF(m); + return NULL; + } + return m; } diff --git a/Doc/includes/custom3.c b/Doc/includes/custom3.c index 213d0864..2b7a99ec 100644 --- a/Doc/includes/custom3.c +++ b/Doc/includes/custom3.c @@ -179,6 +179,11 @@ PyInit_custom3(void) return NULL; Py_INCREF(&CustomType); - PyModule_AddObject(m, "Custom", (PyObject *) &CustomType); + if (PyModule_AddObject(m, "Custom", (PyObject *) &CustomType) < 0) { + Py_DECREF(&CustomType); + Py_DECREF(m); + return NULL; + } + return m; } diff --git a/Doc/includes/custom4.c b/Doc/includes/custom4.c index b0b2906d..584992fc 100644 --- a/Doc/includes/custom4.c +++ b/Doc/includes/custom4.c @@ -193,6 +193,11 @@ PyInit_custom4(void) return NULL; Py_INCREF(&CustomType); - PyModule_AddObject(m, "Custom", (PyObject *) &CustomType); + if (PyModule_AddObject(m, "Custom", (PyObject *) &CustomType) < 0) { + Py_DECREF(&CustomType); + Py_DECREF(m); + return NULL; + } + return m; } diff --git a/Doc/includes/email-mime.py b/Doc/includes/email-mime.py index c610242f..6af2be0b 100644 --- a/Doc/includes/email-mime.py +++ b/Doc/includes/email-mime.py @@ -14,7 +14,7 @@ msg['Subject'] = 'Our family reunion' # family = the list of all recipients' email addresses msg['From'] = me msg['To'] = ', '.join(family) -msg.preamble = 'Our family reunion' +msg.preamble = 'You will not see this in a MIME-aware mail reader.\n' # Open the files in binary mode. Use imghdr to figure out the # MIME subtype for each specific image. diff --git a/Doc/includes/sublist.c b/Doc/includes/sublist.c index 76ff9394..b2c26e73 100644 --- a/Doc/includes/sublist.c +++ b/Doc/includes/sublist.c @@ -59,6 +59,11 @@ PyInit_sublist(void) return NULL; Py_INCREF(&SubListType); - PyModule_AddObject(m, "SubList", (PyObject *) &SubListType); + if (PyModule_AddObject(m, "SubList", (PyObject *) &SubListType) < 0) { + Py_DECREF(&SubListType); + Py_DECREF(m); + return NULL; + } + return m; } diff --git a/Doc/library/argparse.rst b/Doc/library/argparse.rst index cef197f3..a2baa077 100644 --- a/Doc/library/argparse.rst +++ b/Doc/library/argparse.rst @@ -1583,7 +1583,7 @@ Sub-commands stored; by default ``None`` and no value is stored * required_ - Whether or not a subcommand must be provided, by default - ``False``. + ``False`` (added in 3.7) * help_ - help for sub-parser group in help output, by default ``None`` @@ -1739,6 +1739,9 @@ Sub-commands >>> parser.parse_args(['2', 'frobble']) Namespace(subparser_name='2', y='frobble') + .. versionchanged:: 3.7 + New *required* keyword argument. + FileType objects ^^^^^^^^^^^^^^^^ diff --git a/Doc/library/array.rst b/Doc/library/array.rst index 4ac7bb53..0da6b487 100644 --- a/Doc/library/array.rst +++ b/Doc/library/array.rst @@ -36,9 +36,9 @@ defined: +-----------+--------------------+-------------------+-----------------------+-------+ | ``'L'`` | unsigned long | int | 4 | | +-----------+--------------------+-------------------+-----------------------+-------+ -| ``'q'`` | signed long long | int | 8 | \(2) | +| ``'q'`` | signed long long | int | 8 | | +-----------+--------------------+-------------------+-----------------------+-------+ -| ``'Q'`` | unsigned long long | int | 8 | \(2) | +| ``'Q'`` | unsigned long long | int | 8 | | +-----------+--------------------+-------------------+-----------------------+-------+ | ``'f'`` | float | float | 4 | | +-----------+--------------------+-------------------+-----------------------+-------+ @@ -57,13 +57,6 @@ Notes: .. deprecated-removed:: 3.3 4.0 -(2) - The ``'q'`` and ``'Q'`` type codes are available only if - the platform C compiler used to build Python supports C :c:type:`long long`, - or, on Windows, :c:type:`__int64`. - - .. versionadded:: 3.3 - The actual representation of values is determined by the machine architecture (strictly speaking, by the C implementation). The actual size can be accessed through the :attr:`itemsize` attribute. diff --git a/Doc/library/ast.rst b/Doc/library/ast.rst index 3c73f748..699ad045 100644 --- a/Doc/library/ast.rst +++ b/Doc/library/ast.rst @@ -262,11 +262,12 @@ and classes for traversing abstract syntax trees: .. function:: dump(node, annotate_fields=True, include_attributes=False) Return a formatted dump of the tree in *node*. This is mainly useful for - debugging purposes. The returned string will show the names and the values - for fields. This makes the code impossible to evaluate, so if evaluation is - wanted *annotate_fields* must be set to ``False``. Attributes such as line + debugging purposes. If *annotate_fields* is true (by default), + the returned string will show the names and the values for fields. + If *annotate_fields* is false, the result string will be more compact by + omitting unambiguous field names. Attributes such as line numbers and column offsets are not dumped by default. If this is wanted, - *include_attributes* can be set to ``True``. + *include_attributes* can be set to true. .. seealso:: diff --git a/Doc/library/asyncio-dev.rst b/Doc/library/asyncio-dev.rst index b7288036..101e7817 100644 --- a/Doc/library/asyncio-dev.rst +++ b/Doc/library/asyncio-dev.rst @@ -119,7 +119,7 @@ all concurrent asyncio Tasks and IO operations would be delayed by 1 second. An executor can be used to run a task in a different thread or even in -a different process to avoid blocking block the OS thread with the +a different process to avoid blocking the OS thread with the event loop. See the :meth:`loop.run_in_executor` method for more details. diff --git a/Doc/library/asyncio-future.rst b/Doc/library/asyncio-future.rst index 6e6e0137..c069471b 100644 --- a/Doc/library/asyncio-future.rst +++ b/Doc/library/asyncio-future.rst @@ -35,7 +35,9 @@ Future Functions is used for the test.) * a :class:`Task` object wrapping *obj*, if *obj* is a - coroutine (:func:`iscoroutine` is used for the test.) + coroutine (:func:`iscoroutine` is used for the test); + in this case the coroutine will be scheduled by + ``ensure_future()``. * a :class:`Task` object that would await on *obj*, if *obj* is an awaitable (:func:`inspect.isawaitable` is used for the test.) diff --git a/Doc/library/asyncio-protocol.rst b/Doc/library/asyncio-protocol.rst index d8d7947c..1a7794e2 100644 --- a/Doc/library/asyncio-protocol.rst +++ b/Doc/library/asyncio-protocol.rst @@ -767,9 +767,8 @@ data, and waits until the connection is closed:: class EchoClientProtocol(asyncio.Protocol): - def __init__(self, message, on_con_lost, loop): + def __init__(self, message, on_con_lost): self.message = message - self.loop = loop self.on_con_lost = on_con_lost def connection_made(self, transport): @@ -793,7 +792,7 @@ data, and waits until the connection is closed:: message = 'Hello World!' transport, protocol = await loop.create_connection( - lambda: EchoClientProtocol(message, on_con_lost, loop), + lambda: EchoClientProtocol(message, on_con_lost), '127.0.0.1', 8888) # Wait until the protocol signals that the connection @@ -869,11 +868,10 @@ method, sends data and closes the transport when it receives the answer:: class EchoClientProtocol: - def __init__(self, message, loop): + def __init__(self, message, on_con_lost): self.message = message - self.loop = loop + self.on_con_lost = on_con_lost self.transport = None - self.on_con_lost = loop.create_future() def connection_made(self, transport): self.transport = transport @@ -899,13 +897,15 @@ method, sends data and closes the transport when it receives the answer:: # low-level APIs. loop = asyncio.get_running_loop() + on_con_lost = loop.create_future() message = "Hello World!" + transport, protocol = await loop.create_datagram_endpoint( - lambda: EchoClientProtocol(message, loop), + lambda: EchoClientProtocol(message, on_con_lost), remote_addr=('127.0.0.1', 9999)) try: - await protocol.on_con_lost + await on_con_lost finally: transport.close() @@ -927,9 +927,9 @@ Wait until a socket receives data using the class MyProtocol(asyncio.Protocol): - def __init__(self, loop): + def __init__(self, on_con_lost): self.transport = None - self.on_con_lost = loop.create_future() + self.on_con_lost = on_con_lost def connection_made(self, transport): self.transport = transport @@ -950,13 +950,14 @@ Wait until a socket receives data using the # Get a reference to the event loop as we plan to use # low-level APIs. loop = asyncio.get_running_loop() + on_con_lost = loop.create_future() # Create a pair of connected sockets rsock, wsock = socket.socketpair() # Register the socket to wait for data. transport, protocol = await loop.create_connection( - lambda: MyProtocol(loop), sock=rsock) + lambda: MyProtocol(on_con_lost), sock=rsock) # Simulate the reception of data from the network. loop.call_soon(wsock.send, 'abc'.encode()) diff --git a/Doc/library/asyncio-sync.rst b/Doc/library/asyncio-sync.rst index 993bd13f..79f6b02d 100644 --- a/Doc/library/asyncio-sync.rst +++ b/Doc/library/asyncio-sync.rst @@ -187,11 +187,11 @@ Condition cond = asyncio.Condition() # ... later - await lock.acquire() + await cond.acquire() try: await cond.wait() finally: - lock.release() + cond.release() .. coroutinemethod:: acquire() diff --git a/Doc/library/asyncio-task.rst b/Doc/library/asyncio-task.rst index 29ccafee..9a4cda18 100644 --- a/Doc/library/asyncio-task.rst +++ b/Doc/library/asyncio-task.rst @@ -212,6 +212,8 @@ Running an asyncio Program .. function:: run(coro, \*, debug=False) + Execute the :term:`coroutine` *coro* and return the result. + This function runs the passed coroutine, taking care of managing the asyncio event loop and *finalizing asynchronous generators*. @@ -225,6 +227,14 @@ Running an asyncio Program the end. It should be used as a main entry point for asyncio programs, and should ideally only be called once. + Example:: + + async def main(): + await asyncio.sleep(1) + print('hello') + + asyncio.run(main()) + .. versionadded:: 3.7 **Important:** this function has been added to asyncio in Python 3.7 on a :term:`provisional basis `. diff --git a/Doc/library/codecs.rst b/Doc/library/codecs.rst index ff4f4933..5c418282 100644 --- a/Doc/library/codecs.rst +++ b/Doc/library/codecs.rst @@ -292,7 +292,7 @@ Error Handlers To simplify and standardize error handling, codecs may implement different error handling schemes by -accepting the *errors* string argument. The following string values are +accepting the *errors* string argument. The following string values are defined and implemented by all standard Python codecs: .. tabularcolumns:: |l|L| @@ -301,11 +301,11 @@ defined and implemented by all standard Python codecs: | Value | Meaning | +=========================+===============================================+ | ``'strict'`` | Raise :exc:`UnicodeError` (or a subclass); | -| | this is the default. Implemented in | +| | this is the default. Implemented in | | | :func:`strict_errors`. | +-------------------------+-----------------------------------------------+ | ``'ignore'`` | Ignore the malformed data and continue | -| | without further notice. Implemented in | +| | without further notice. Implemented in | | | :func:`ignore_errors`. | +-------------------------+-----------------------------------------------+ @@ -327,11 +327,11 @@ The following error handlers are only applicable to | | marker; Python will use the official | | | ``U+FFFD`` REPLACEMENT CHARACTER for the | | | built-in codecs on decoding, and '?' on | -| | encoding. Implemented in | +| | encoding. Implemented in | | | :func:`replace_errors`. | +-------------------------+-----------------------------------------------+ | ``'xmlcharrefreplace'`` | Replace with the appropriate XML character | -| | reference (only for encoding). Implemented | +| | reference (only for encoding). Implemented | | | in :func:`xmlcharrefreplace_errors`. | +-------------------------+-----------------------------------------------+ | ``'backslashreplace'`` | Replace with backslashed escape sequences. | @@ -339,15 +339,15 @@ The following error handlers are only applicable to | | :func:`backslashreplace_errors`. | +-------------------------+-----------------------------------------------+ | ``'namereplace'`` | Replace with ``\N{...}`` escape sequences | -| | (only for encoding). Implemented in | +| | (only for encoding). Implemented in | | | :func:`namereplace_errors`. | +-------------------------+-----------------------------------------------+ | ``'surrogateescape'`` | On decoding, replace byte with individual | | | surrogate code ranging from ``U+DC80`` to | -| | ``U+DCFF``. This code will then be turned | +| | ``U+DCFF``. This code will then be turned | | | back into the same byte when the | | | ``'surrogateescape'`` error handler is used | -| | when encoding the data. (See :pep:`383` for | +| | when encoding the data. (See :pep:`383` for | | | more.) | +-------------------------+-----------------------------------------------+ @@ -357,7 +357,7 @@ In addition, the following error handler is specific to the given codecs: | Value | Codecs | Meaning | +===================+========================+===========================================+ |``'surrogatepass'``| utf-8, utf-16, utf-32, | Allow encoding and decoding of surrogate | -| | utf-16-be, utf-16-le, | codes. These codecs normally treat the | +| | utf-16-be, utf-16-le, | codes. These codecs normally treat the | | | utf-32-be, utf-32-le | presence of surrogates as an error. | +-------------------+------------------------+-------------------------------------------+ @@ -388,9 +388,9 @@ handler: error handler must either raise this or a different exception, or return a tuple with a replacement for the unencodable part of the input and a position where encoding should continue. The replacement may be either :class:`str` or - :class:`bytes`. If the replacement is bytes, the encoder will simply copy + :class:`bytes`. If the replacement is bytes, the encoder will simply copy them into the output buffer. If the replacement is a string, the encoder will - encode the replacement. Encoding continues on original input at the + encode the replacement. Encoding continues on original input at the specified position. Negative position values will be treated as being relative to the end of the input string. If the resulting position is out of bound an :exc:`IndexError` will be raised. @@ -484,7 +484,7 @@ function interfaces of the stateless encoder and decoder: .. method:: Codec.decode(input[, errors]) Decodes the object *input* and returns a tuple (output object, length - consumed). For instance, for a :term:`text encoding`, decoding converts + consumed). For instance, for a :term:`text encoding`, decoding converts a bytes object encoded using a particular character set encoding to a string object. @@ -568,7 +568,7 @@ define in order to be compatible with the Python codec registry. implementation should make sure that ``0`` is the most common state. (States that are more complicated than integers can be converted into an integer by marshaling/pickling the state and encoding the bytes - of the resulting string into an integer). + of the resulting string into an integer.) .. method:: setstate(state) @@ -751,7 +751,7 @@ compatible with the Python codec registry. number of encoded bytes or code points to read for decoding. The decoder can modify this setting as appropriate. The default value -1 indicates to read and decode as much as - possible. This parameter is intended to + possible. This parameter is intended to prevent having to decode huge files in one step. The *firstline* flag indicates that @@ -780,8 +780,8 @@ compatible with the Python codec registry. Read all lines available on the input stream and return them as a list of lines. - Line-endings are implemented using the codec's decoder method and are - included in the list entries if *keepends* is true. + Line-endings are implemented using the codec's :meth:`decode` method and + are included in the list entries if *keepends* is true. *sizehint*, if given, is passed as the *size* argument to the stream's :meth:`read` method. @@ -791,7 +791,7 @@ compatible with the Python codec registry. Resets the codec buffers used for keeping state. - Note that no stream repositioning should take place. This method is + Note that no stream repositioning should take place. This method is primarily intended to be able to recover from decoding errors. @@ -841,7 +841,7 @@ The design is such that one can use the factory functions returned by the code calling :meth:`read` and :meth:`write`, while *Reader* and *Writer* work on the backend — the data in *stream*. - You can use these objects to do transparent transcodings from e.g. Latin-1 + You can use these objects to do transparent transcodings, e.g., from Latin-1 to UTF-8 and back. The *stream* argument must be a file-like object. @@ -866,10 +866,10 @@ Encodings and Unicode --------------------- Strings are stored internally as sequences of code points in -range ``0x0``--``0x10FFFF``. (See :pep:`393` for +range ``0x0``--``0x10FFFF``. (See :pep:`393` for more details about the implementation.) Once a string object is used outside of CPU and memory, endianness -and how these arrays are stored as bytes become an issue. As with other +and how these arrays are stored as bytes become an issue. As with other codecs, serialising a string into a sequence of bytes is known as *encoding*, and recreating the string from the sequence of bytes is known as *decoding*. There are a variety of different text serialisation codecs, which are @@ -964,7 +964,7 @@ to determine the byte order used for generating the byte sequence, but as a signature that helps in guessing the encoding. On encoding the utf-8-sig codec will write ``0xef``, ``0xbb``, ``0xbf`` as the first three bytes to the file. On decoding ``utf-8-sig`` will skip those three bytes if they appear as the first -three bytes in the file. In UTF-8, the use of the BOM is discouraged and +three bytes in the file. In UTF-8, the use of the BOM is discouraged and should generally be avoided. @@ -984,7 +984,7 @@ e.g. ``'utf-8'`` is a valid alias for the ``'utf_8'`` codec. .. impl-detail:: Some common encodings can bypass the codecs lookup machinery to - improve performance. These optimization opportunities are only + improve performance. These optimization opportunities are only recognized by CPython for a limited set of (case insensitive) aliases: utf-8, utf8, latin-1, latin1, iso-8859-1, iso8859-1, mbcs (Windows only), ascii, us-ascii, utf-16, utf16, utf-32, utf32, and @@ -1150,7 +1150,7 @@ particular, the following variants typically exist: | iso2022_kr | csiso2022kr, iso2022kr, | Korean | | | iso-2022-kr | | +-----------------+--------------------------------+--------------------------------+ -| latin_1 | iso-8859-1, iso8859-1, 8859, | West Europe | +| latin_1 | iso-8859-1, iso8859-1, 8859, | Western Europe | | | cp819, latin, latin1, L1 | | +-----------------+--------------------------------+--------------------------------+ | iso8859_2 | iso-8859-2, latin2, L2 | Central and Eastern Europe | @@ -1251,11 +1251,11 @@ Python Specific Encodings ------------------------- A number of predefined codecs are specific to Python, so their codec names have -no meaning outside Python. These are listed in the tables below based on the +no meaning outside Python. These are listed in the tables below based on the expected input and output types (note that while text encodings are the most common use case for codecs, the underlying codec infrastructure supports -arbitrary data transforms rather than just text encodings). For asymmetric -codecs, the stated purpose describes the encoding direction. +arbitrary data transforms rather than just text encodings). For asymmetric +codecs, the stated meaning describes the encoding direction. Text Encodings ^^^^^^^^^^^^^^ @@ -1267,27 +1267,27 @@ encodings. .. tabularcolumns:: |l|p{0.3\linewidth}|p{0.3\linewidth}| +--------------------+---------+---------------------------+ -| Codec | Aliases | Purpose | +| Codec | Aliases | Meaning | +====================+=========+===========================+ -| idna | | Implements :rfc:`3490`, | +| idna | | Implement :rfc:`3490`, | | | | see also | | | | :mod:`encodings.idna`. | | | | Only ``errors='strict'`` | | | | is supported. | +--------------------+---------+---------------------------+ -| mbcs | ansi, | Windows only: Encode | +| mbcs | ansi, | Windows only: Encode the | | | dbcs | operand according to the | -| | | ANSI codepage (CP_ACP) | +| | | ANSI codepage (CP_ACP). | +--------------------+---------+---------------------------+ -| oem | | Windows only: Encode | +| oem | | Windows only: Encode the | | | | operand according to the | -| | | OEM codepage (CP_OEMCP) | +| | | OEM codepage (CP_OEMCP). | | | | | | | | .. versionadded:: 3.6 | +--------------------+---------+---------------------------+ -| palmos | | Encoding of PalmOS 3.5 | +| palmos | | Encoding of PalmOS 3.5. | +--------------------+---------+---------------------------+ -| punycode | | Implements :rfc:`3492`. | +| punycode | | Implement :rfc:`3492`. | | | | Stateful codecs are not | | | | supported. | +--------------------+---------+---------------------------+ @@ -1310,8 +1310,8 @@ encodings. | | | literal in ASCII-encoded | | | | Python source code, | | | | except that quotes are | -| | | not escaped. Decodes from | -| | | Latin-1 source code. | +| | | not escaped. Decode | +| | | from Latin-1 source code. | | | | Beware that Python source | | | | code actually uses UTF-8 | | | | by default. | @@ -1333,19 +1333,19 @@ Binary Transforms ^^^^^^^^^^^^^^^^^ The following codecs provide binary transforms: :term:`bytes-like object` -to :class:`bytes` mappings. They are not supported by :meth:`bytes.decode` +to :class:`bytes` mappings. They are not supported by :meth:`bytes.decode` (which only produces :class:`str` output). .. tabularcolumns:: |l|L|L|L| +----------------------+------------------+------------------------------+------------------------------+ -| Codec | Aliases | Purpose | Encoder / decoder | +| Codec | Aliases | Meaning | Encoder / decoder | +======================+==================+==============================+==============================+ -| base64_codec [#b64]_ | base64, base_64 | Convert operand to multiline | :meth:`base64.encodebytes` / | -| | | MIME base64 (the result | :meth:`base64.decodebytes` | -| | | always includes a trailing | | -| | | ``'\n'``) | | +| base64_codec [#b64]_ | base64, base_64 | Convert the operand to | :meth:`base64.encodebytes` / | +| | | multiline MIME base64 (the | :meth:`base64.decodebytes` | +| | | result always includes a | | +| | | trailing ``'\n'``). | | | | | | | | | | .. versionchanged:: 3.4 | | | | | accepts any | | @@ -1353,23 +1353,23 @@ to :class:`bytes` mappings. They are not supported by :meth:`bytes.decode` | | | as input for encoding and | | | | | decoding | | +----------------------+------------------+------------------------------+------------------------------+ -| bz2_codec | bz2 | Compress the operand | :meth:`bz2.compress` / | -| | | using bz2 | :meth:`bz2.decompress` | +| bz2_codec | bz2 | Compress the operand using | :meth:`bz2.compress` / | +| | | bz2. | :meth:`bz2.decompress` | +----------------------+------------------+------------------------------+------------------------------+ -| hex_codec | hex | Convert operand to | :meth:`binascii.b2a_hex` / | +| hex_codec | hex | Convert the operand to | :meth:`binascii.b2a_hex` / | | | | hexadecimal | :meth:`binascii.a2b_hex` | | | | representation, with two | | -| | | digits per byte | | +| | | digits per byte. | | +----------------------+------------------+------------------------------+------------------------------+ -| quopri_codec | quopri, | Convert operand to MIME | :meth:`quopri.encode` with | -| | quotedprintable, | quoted printable | ``quotetabs=True`` / | +| quopri_codec | quopri, | Convert the operand to MIME | :meth:`quopri.encode` with | +| | quotedprintable, | quoted printable. | ``quotetabs=True`` / | | | quoted_printable | | :meth:`quopri.decode` | +----------------------+------------------+------------------------------+------------------------------+ | uu_codec | uu | Convert the operand using | :meth:`uu.encode` / | -| | | uuencode | :meth:`uu.decode` | +| | | uuencode. | :meth:`uu.decode` | +----------------------+------------------+------------------------------+------------------------------+ -| zlib_codec | zip, zlib | Compress the operand | :meth:`zlib.compress` / | -| | | using gzip | :meth:`zlib.decompress` | +| zlib_codec | zip, zlib | Compress the operand using | :meth:`zlib.compress` / | +| | | gzip. | :meth:`zlib.decompress` | +----------------------+------------------+------------------------------+------------------------------+ .. [#b64] In addition to :term:`bytes-like objects `, @@ -1389,16 +1389,17 @@ Text Transforms ^^^^^^^^^^^^^^^ The following codec provides a text transform: a :class:`str` to :class:`str` -mapping. It is not supported by :meth:`str.encode` (which only produces +mapping. It is not supported by :meth:`str.encode` (which only produces :class:`bytes` output). .. tabularcolumns:: |l|l|L| +--------------------+---------+---------------------------+ -| Codec | Aliases | Purpose | +| Codec | Aliases | Meaning | +====================+=========+===========================+ -| rot_13 | rot13 | Returns the Caesar-cypher | -| | | encryption of the operand | +| rot_13 | rot13 | Return the Caesar-cypher | +| | | encryption of the | +| | | operand. | +--------------------+---------+---------------------------+ .. versionadded:: 3.2 @@ -1436,7 +1437,7 @@ conversion between Unicode and ACE, separating an input string into labels based on the separator characters defined in :rfc:`section 3.1 of RFC 3490 <3490#section-3.1>` and converting each label to ACE as required, and conversely separating an input byte string into labels based on the ``.`` separator and converting any ACE -labels found into unicode. Furthermore, the :mod:`socket` module +labels found into unicode. Furthermore, the :mod:`socket` module transparently converts Unicode host names to ACE, so that applications need not be concerned about converting host names themselves when they pass them to the socket module. On top of that, modules that have host names as function @@ -1445,7 +1446,7 @@ names (:mod:`http.client` then also transparently sends an IDNA hostname in the :mailheader:`Host` field if it sends that field at all). When receiving host names from the wire (such as in reverse name lookup), no -automatic conversion to Unicode is performed: Applications wishing to present +automatic conversion to Unicode is performed: applications wishing to present such host names to the user should decode them to Unicode. The module :mod:`encodings.idna` also implements the nameprep procedure, which @@ -1477,7 +1478,7 @@ functions can be used directly if desired. .. module:: encodings.mbcs :synopsis: Windows ANSI codepage -Encode operand according to the ANSI codepage (CP_ACP). +This module implements the ANSI codepage (CP_ACP). .. availability:: Windows only. @@ -1496,7 +1497,7 @@ Encode operand according to the ANSI codepage (CP_ACP). :synopsis: UTF-8 codec with BOM signature .. moduleauthor:: Walter Dörwald -This module implements a variant of the UTF-8 codec: On encoding a UTF-8 encoded +This module implements a variant of the UTF-8 codec. On encoding, a UTF-8 encoded BOM will be prepended to the UTF-8 encoded bytes. For the stateful encoder this -is only done once (on the first write to the byte stream). For decoding an +is only done once (on the first write to the byte stream). On decoding, an optional UTF-8 encoded BOM at the start of the data will be skipped. diff --git a/Doc/library/collections.rst b/Doc/library/collections.rst index 9f47e897..e9dbd094 100644 --- a/Doc/library/collections.rst +++ b/Doc/library/collections.rst @@ -33,10 +33,10 @@ Python's general purpose built-in containers, :class:`dict`, :class:`list`, :class:`UserString` wrapper around string objects for easier string subclassing ===================== ==================================================================== -.. versionchanged:: 3.3 +.. deprecated-removed:: 3.3 3.9 Moved :ref:`collections-abstract-base-classes` to the :mod:`collections.abc` module. For backwards compatibility, they continue to be visible in this module through - Python 3.7. Subsequently, they will be removed entirely. + Python 3.8. :class:`ChainMap` objects diff --git a/Doc/library/configparser.rst b/Doc/library/configparser.rst index 68b663ff..6ab85857 100644 --- a/Doc/library/configparser.rst +++ b/Doc/library/configparser.rst @@ -313,6 +313,8 @@ from ``get()`` calls. my_dir: %(home_dir)s/lumberjack my_pictures: %(my_dir)s/Pictures + [Escape] + gain: 80%% # use a %% to escape the % sign (% is the only character that needs to be escaped) In the example above, :class:`ConfigParser` with *interpolation* set to ``BasicInterpolation()`` would resolve ``%(home_dir)s`` to the value of @@ -346,6 +348,9 @@ from ``get()`` calls. my_dir: ${home_dir}/lumberjack my_pictures: ${my_dir}/Pictures + [Escape] + cost: $$80 # use a $$ to escape the $ sign ($ is the only character that needs to be escaped) + Values from other sections can be fetched as well: .. code-block:: ini diff --git a/Doc/library/ctypes.rst b/Doc/library/ctypes.rst index 60a2ec1c..2eafa654 100644 --- a/Doc/library/ctypes.rst +++ b/Doc/library/ctypes.rst @@ -576,7 +576,7 @@ Here is a simple example of a POINT structure, which contains two integers named >>> POINT(1, 2, 3) Traceback (most recent call last): File "", line 1, in - ValueError: too many initializers + TypeError: too many initializers >>> You can, however, build much more complicated structures. A structure can @@ -1175,16 +1175,21 @@ Keep in mind that retrieving sub-objects from Structure, Unions, and Arrays doesn't *copy* the sub-object, instead it retrieves a wrapper object accessing the root-object's underlying buffer. -Another example that may behave different from what one would expect is this:: +Another example that may behave differently from what one would expect is this:: >>> s = c_char_p() - >>> s.value = "abc def ghi" + >>> s.value = b"abc def ghi" >>> s.value - 'abc def ghi' + b'abc def ghi' >>> s.value is s.value False >>> +.. note:: + + Objects instantiated from :class:`c_char_p` can only have their value set to bytes + or integers. + Why is it printing ``False``? ctypes instances are objects containing a memory block plus some :term:`descriptor`\s accessing the contents of the memory. Storing a Python object in the memory block does not store the object itself, diff --git a/Doc/library/curses.rst b/Doc/library/curses.rst index 2a2ee2be..3e4856e1 100644 --- a/Doc/library/curses.rst +++ b/Doc/library/curses.rst @@ -1276,7 +1276,7 @@ The :mod:`curses` module defines the following data members: .. data:: ERR - Some curses routines that return an integer, such as :func:`getch`, return + Some curses routines that return an integer, such as :meth:`~window.getch`, return :const:`ERR` upon failure. diff --git a/Doc/library/datatypes.rst b/Doc/library/datatypes.rst index 48af0823..94010c0e 100644 --- a/Doc/library/datatypes.rst +++ b/Doc/library/datatypes.rst @@ -5,13 +5,14 @@ Data Types ********** The modules described in this chapter provide a variety of specialized data -types such as dates and times, fixed-type arrays, heap queues, synchronized -queues, and sets. +types such as dates and times, fixed-type arrays, heap queues, double-ended +queues, and enumerations. Python also provides some built-in data types, in particular, :class:`dict`, :class:`list`, :class:`set` and :class:`frozenset`, and :class:`tuple`. The :class:`str` class is used to hold -Unicode strings, and the :class:`bytes` class is used to hold binary data. +Unicode strings, and the :class:`bytes` and :class:`bytearray` classes are used +to hold binary data. The following modules are documented in this chapter: diff --git a/Doc/library/datetime.rst b/Doc/library/datetime.rst index 270b2386..342dc2b8 100644 --- a/Doc/library/datetime.rst +++ b/Doc/library/datetime.rst @@ -401,7 +401,7 @@ systems. .. class:: date(year, month, day) - All arguments are required. Arguments may be integers, in the following + All arguments are required. Arguments must be integers in the following ranges: * ``MINYEAR <= year <= MAXYEAR`` @@ -707,7 +707,7 @@ Constructor: .. class:: datetime(year, month, day, hour=0, minute=0, second=0, microsecond=0, tzinfo=None, *, fold=0) The year, month and day arguments are required. *tzinfo* may be ``None``, or an - instance of a :class:`tzinfo` subclass. The remaining arguments may be integers, + instance of a :class:`tzinfo` subclass. The remaining arguments must be integers in the following ranges: * ``MINYEAR <= year <= MAXYEAR``, @@ -850,7 +850,9 @@ Other constructors, all class methods: .. caution:: This does not support parsing arbitrary ISO 8601 strings - it is only intended - as the inverse operation of :meth:`datetime.isoformat`. + as the inverse operation of :meth:`datetime.isoformat`. A more full-featured + ISO 8601 parser, ``dateutil.parser.isoparse`` is available in the third-party package + `dateutil `_. .. versionadded:: 3.7 @@ -1422,7 +1424,7 @@ day, and subject to adjustment via a :class:`tzinfo` object. .. class:: time(hour=0, minute=0, second=0, microsecond=0, tzinfo=None, *, fold=0) All arguments are optional. *tzinfo* may be ``None``, or an instance of a - :class:`tzinfo` subclass. The remaining arguments may be integers, in the + :class:`tzinfo` subclass. The remaining arguments must be integers in the following ranges: * ``0 <= hour < 24``, diff --git a/Doc/library/difflib.rst b/Doc/library/difflib.rst index f044cb2d..e245ab81 100644 --- a/Doc/library/difflib.rst +++ b/Doc/library/difflib.rst @@ -543,6 +543,16 @@ The :class:`SequenceMatcher` class has this constructor: to try :meth:`quick_ratio` or :meth:`real_quick_ratio` first to get an upper bound. + .. note:: + + Caution: The result of a :meth:`ratio` call may depend on the order of + the arguments. For instance:: + + >>> SequenceMatcher(None, 'tide', 'diet').ratio() + 0.25 + >>> SequenceMatcher(None, 'diet', 'tide').ratio() + 0.5 + .. method:: quick_ratio() diff --git a/Doc/library/faulthandler.rst b/Doc/library/faulthandler.rst index 94ebd876..b588dfa1 100644 --- a/Doc/library/faulthandler.rst +++ b/Doc/library/faulthandler.rst @@ -100,8 +100,10 @@ Dumping the tracebacks after a timeout :func:`cancel_dump_traceback_later` is called: see :ref:`issue with file descriptors `. - This function is implemented using a watchdog thread and therefore is not - available if Python is compiled with threads disabled. + This function is implemented using a watchdog thread. + + .. versionchanged:: 3.7 + This function is now always available. .. versionchanged:: 3.5 Added support for passing file descriptor to this function. diff --git a/Doc/library/ftplib.rst b/Doc/library/ftplib.rst index 6c39f9a5..d9701f48 100644 --- a/Doc/library/ftplib.rst +++ b/Doc/library/ftplib.rst @@ -33,7 +33,8 @@ Here's a sample session using the :mod:`ftplib` module:: drwxr-sr-x 4 1176 1176 4096 Nov 17 2008 project drwxr-xr-x 3 1176 1176 4096 Oct 10 2012 tools '226 Directory send OK.' - >>> ftp.retrbinary('RETR README', open('README', 'wb').write) + >>> with open('README', 'wb') as fp: + >>> ftp.retrbinary('RETR README', fp.write) '226 Transfer complete.' >>> ftp.quit() diff --git a/Doc/library/functions.rst b/Doc/library/functions.rst index 11147525..06ba323c 100644 --- a/Doc/library/functions.rst +++ b/Doc/library/functions.rst @@ -426,7 +426,7 @@ are always available. They are listed here in alphabetical order. n += 1 -.. function:: eval(expression, globals=None, locals=None) +.. function:: eval(expression[, globals[, locals]]) The arguments are a string and optional globals and locals. If provided, *globals* must be a dictionary. If provided, *locals* can be any mapping @@ -1532,6 +1532,10 @@ are always available. They are listed here in alphabetical order. super().method(arg) # This does the same thing as: # super(C, self).method(arg) + In addition to method lookups, :func:`super` also works for attribute + lookups. One possible use case for this is calling :term:`descriptor`\s + in a parent or sibling class. + Note that :func:`super` is implemented as part of the binding process for explicit dotted attribute lookups such as ``super().__getitem__(name)``. It does so by implementing its own :meth:`__getattribute__` method for searching diff --git a/Doc/library/glob.rst b/Doc/library/glob.rst index 0db10b5e..9ab79d7a 100644 --- a/Doc/library/glob.rst +++ b/Doc/library/glob.rst @@ -48,8 +48,9 @@ For example, ``'[?]'`` matches the character ``'?'``. single: **; in glob-style wildcards If *recursive* is true, the pattern "``**``" will match any files and zero or - more directories and subdirectories. If the pattern is followed by an - ``os.sep``, only directories and subdirectories match. + more directories, subdirectories and symbolic links to directories. If the + pattern is followed by an :data:`os.sep` or :data:`os.altsep` then files will not + match. .. note:: Using the "``**``" pattern in large directory trees may consume diff --git a/Doc/library/http.client.rst b/Doc/library/http.client.rst index 3ebeb10a..bc73c7a9 100644 --- a/Doc/library/http.client.rst +++ b/Doc/library/http.client.rst @@ -497,8 +497,11 @@ Here is an example session that uses the ``GET`` method:: >>> # The following example demonstrates reading data in chunks. >>> conn.request("GET", "/") >>> r1 = conn.getresponse() - >>> while not r1.closed: - ... print(r1.read(200)) # 200 bytes + >>> while True: + ... chunk = r1.read(200) # 200 bytes + ... if not chunk: + ... break + ... print(repr(chunk)) b'\n 0x%0*lx (%lu bytes)\n", - label, - (int)sizeof(entropy) * 2, entropy, - (unsigned long)sizeof(entropy)); + fprintf(stderr, "Entropy: %s --> 0x%0*lx (%lu bytes)\n", label, + (int)sizeof(entropy) * 2, entropy, (unsigned long)sizeof(entropy)); } return entropy; } static unsigned long -generate_hash_secret_salt(XML_Parser parser) -{ +generate_hash_secret_salt(XML_Parser parser) { unsigned long entropy; (void)parser; @@ -848,20 +811,20 @@ generate_hash_secret_salt(XML_Parser parser) return ENTROPY_DEBUG("arc4random", entropy); #else /* Try high quality providers first .. */ -#ifdef _WIN32 - if (writeRandomBytes_RtlGenRandom((void *)&entropy, sizeof(entropy))) { - return ENTROPY_DEBUG("RtlGenRandom", entropy); +# ifdef _WIN32 + if (writeRandomBytes_rand_s((void *)&entropy, sizeof(entropy))) { + return ENTROPY_DEBUG("rand_s", entropy); } -#elif defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) +# elif defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) if (writeRandomBytes_getrandom_nonblock((void *)&entropy, sizeof(entropy))) { return ENTROPY_DEBUG("getrandom", entropy); } -#endif -#if ! defined(_WIN32) && defined(XML_DEV_URANDOM) +# endif +# if ! defined(_WIN32) && defined(XML_DEV_URANDOM) if (writeRandomBytes_dev_urandom((void *)&entropy, sizeof(entropy))) { return ENTROPY_DEBUG("/dev/urandom", entropy); } -#endif /* ! defined(_WIN32) && defined(XML_DEV_URANDOM) */ +# endif /* ! defined(_WIN32) && defined(XML_DEV_URANDOM) */ /* .. and self-made low quality for backup: */ /* Process ID is 0 bits entropy if attacker has local access */ @@ -872,7 +835,7 @@ generate_hash_secret_salt(XML_Parser parser) return ENTROPY_DEBUG("fallback(4)", entropy * 2147483647); } else { return ENTROPY_DEBUG("fallback(8)", - entropy * (unsigned long)2305843009213693951ULL); + entropy * (unsigned long)2305843009213693951ULL); } #endif } @@ -884,49 +847,43 @@ get_hash_secret_salt(XML_Parser parser) { return parser->m_hash_secret_salt; } -static XML_Bool /* only valid for root parser */ -startParsing(XML_Parser parser) -{ - /* hash functions must be initialized before setContext() is called */ - if (parser->m_hash_secret_salt == 0) - parser->m_hash_secret_salt = generate_hash_secret_salt(parser); - if (parser->m_ns) { - /* implicit context only set for root parser, since child - parsers (i.e. external entity parsers) will inherit it - */ - return setContext(parser, implicitContext); - } - return XML_TRUE; +static XML_Bool /* only valid for root parser */ +startParsing(XML_Parser parser) { + /* hash functions must be initialized before setContext() is called */ + if (parser->m_hash_secret_salt == 0) + parser->m_hash_secret_salt = generate_hash_secret_salt(parser); + if (parser->m_ns) { + /* implicit context only set for root parser, since child + parsers (i.e. external entity parsers) will inherit it + */ + return setContext(parser, implicitContext); + } + return XML_TRUE; } XML_Parser XMLCALL XML_ParserCreate_MM(const XML_Char *encodingName, const XML_Memory_Handling_Suite *memsuite, - const XML_Char *nameSep) -{ + const XML_Char *nameSep) { return parserCreate(encodingName, memsuite, nameSep, NULL); } static XML_Parser parserCreate(const XML_Char *encodingName, - const XML_Memory_Handling_Suite *memsuite, - const XML_Char *nameSep, - DTD *dtd) -{ + const XML_Memory_Handling_Suite *memsuite, const XML_Char *nameSep, + DTD *dtd) { XML_Parser parser; if (memsuite) { XML_Memory_Handling_Suite *mtemp; - parser = (XML_Parser) - memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); + parser = (XML_Parser)memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); if (parser != NULL) { mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); mtemp->malloc_fcn = memsuite->malloc_fcn; mtemp->realloc_fcn = memsuite->realloc_fcn; mtemp->free_fcn = memsuite->free_fcn; } - } - else { + } else { XML_Memory_Handling_Suite *mtemp; parser = (XML_Parser)malloc(sizeof(struct XML_ParserStruct)); if (parser != NULL) { @@ -937,27 +894,30 @@ parserCreate(const XML_Char *encodingName, } } - if (!parser) + if (! parser) return parser; parser->m_buffer = NULL; parser->m_bufferLim = NULL; parser->m_attsSize = INIT_ATTS_SIZE; - parser->m_atts = (ATTRIBUTE *)MALLOC(parser, parser->m_attsSize * sizeof(ATTRIBUTE)); + parser->m_atts + = (ATTRIBUTE *)MALLOC(parser, parser->m_attsSize * sizeof(ATTRIBUTE)); if (parser->m_atts == NULL) { FREE(parser, parser); return NULL; } #ifdef XML_ATTR_INFO - parser->m_attInfo = (XML_AttrInfo*)MALLOC(parser, parser->m_attsSize * sizeof(XML_AttrInfo)); + parser->m_attInfo = (XML_AttrInfo *)MALLOC( + parser, parser->m_attsSize * sizeof(XML_AttrInfo)); if (parser->m_attInfo == NULL) { FREE(parser, parser->m_atts); FREE(parser, parser); return NULL; } #endif - parser->m_dataBuf = (XML_Char *)MALLOC(parser, INIT_DATA_BUF_SIZE * sizeof(XML_Char)); + parser->m_dataBuf + = (XML_Char *)MALLOC(parser, INIT_DATA_BUF_SIZE * sizeof(XML_Char)); if (parser->m_dataBuf == NULL) { FREE(parser, parser->m_atts); #ifdef XML_ATTR_INFO @@ -1007,7 +967,7 @@ parserCreate(const XML_Char *encodingName, poolInit(&parser->m_temp2Pool, &(parser->m_mem)); parserInit(parser, encodingName); - if (encodingName && !parser->m_protocolEncodingName) { + if (encodingName && ! parser->m_protocolEncodingName) { XML_ParserFree(parser); return NULL; } @@ -1016,8 +976,7 @@ parserCreate(const XML_Char *encodingName, parser->m_ns = XML_TRUE; parser->m_internalEncoding = XmlGetInternalEncodingNS(); parser->m_namespaceSeparator = *nameSep; - } - else { + } else { parser->m_internalEncoding = XmlGetInternalEncoding(); } @@ -1025,8 +984,7 @@ parserCreate(const XML_Char *encodingName, } static void -parserInit(XML_Parser parser, const XML_Char *encodingName) -{ +parserInit(XML_Parser parser, const XML_Char *encodingName) { parser->m_processor = prologInitProcessor; XmlPrologStateInit(&parser->m_prologState); if (encodingName != NULL) { @@ -1099,8 +1057,7 @@ parserInit(XML_Parser parser, const XML_Char *encodingName) /* moves list of bindings to m_freeBindingList */ static void FASTCALL -moveToFreeBindingList(XML_Parser parser, BINDING *bindings) -{ +moveToFreeBindingList(XML_Parser parser, BINDING *bindings) { while (bindings) { BINDING *b = bindings; bindings = bindings->nextTagBinding; @@ -1110,13 +1067,12 @@ moveToFreeBindingList(XML_Parser parser, BINDING *bindings) } XML_Bool XMLCALL -XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) -{ +XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) { TAG *tStk; OPEN_INTERNAL_ENTITY *openEntityList; if (parser == NULL) - return XML_FALSE; + return XML_FALSE; if (parser->m_parentParser) return XML_FALSE; @@ -1152,15 +1108,15 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) } enum XML_Status XMLCALL -XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) -{ +XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) { if (parser == NULL) - return XML_STATUS_ERROR; + return XML_STATUS_ERROR; /* Block after XML_Parse()/XML_ParseBuffer() has been called. XXX There's no way for the caller to determine which of the XXX possible error cases caused the XML_STATUS_ERROR return. */ - if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return XML_STATUS_ERROR; /* Get rid of any previous encoding name */ @@ -1172,17 +1128,15 @@ XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) else { /* Copy the new encoding name into allocated memory */ parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem)); - if (!parser->m_protocolEncodingName) + if (! parser->m_protocolEncodingName) return XML_STATUS_ERROR; } return XML_STATUS_OK; } XML_Parser XMLCALL -XML_ExternalEntityParserCreate(XML_Parser oldParser, - const XML_Char *context, - const XML_Char *encodingName) -{ +XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context, + const XML_Char *encodingName) { XML_Parser parser = oldParser; DTD *newDtd = NULL; DTD *oldDtd; @@ -1206,7 +1160,7 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, XML_AttlistDeclHandler oldAttlistDeclHandler; XML_EntityDeclHandler oldEntityDeclHandler; XML_XmlDeclHandler oldXmlDeclHandler; - ELEMENT_TYPE * oldDeclElementType; + ELEMENT_TYPE *oldDeclElementType; void *oldUserData; void *oldHandlerArg; @@ -1269,7 +1223,7 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, oldhash_secret_salt = parser->m_hash_secret_salt; #ifdef XML_DTD - if (!context) + if (! context) newDtd = oldDtd; #endif /* XML_DTD */ @@ -1282,12 +1236,11 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, XML_Char tmp[2]; *tmp = parser->m_namespaceSeparator; parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd); - } - else { + } else { parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd); } - if (!parser) + if (! parser) return NULL; parser->m_startElementHandler = oldStartElementHandler; @@ -1327,21 +1280,20 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, parser->m_prologState.inEntityValue = oldInEntityValue; if (context) { #endif /* XML_DTD */ - if (!dtdCopy(oldParser, parser->m_dtd, oldDtd, &parser->m_mem) - || !setContext(parser, context)) { + if (! dtdCopy(oldParser, parser->m_dtd, oldDtd, &parser->m_mem) + || ! setContext(parser, context)) { XML_ParserFree(parser); return NULL; } parser->m_processor = externalEntityInitProcessor; #ifdef XML_DTD - } - else { - /* The DTD instance referenced by parser->m_dtd is shared between the document's - root parser and external PE parsers, therefore one does not need to - call setContext. In addition, one also *must* not call setContext, - because this would overwrite existing prefix->binding pointers in - parser->m_dtd with ones that get destroyed with the external PE parser. - This would leave those prefixes with dangling pointers. + } else { + /* The DTD instance referenced by parser->m_dtd is shared between the + document's root parser and external PE parsers, therefore one does not + need to call setContext. In addition, one also *must* not call + setContext, because this would overwrite existing prefix->binding + pointers in parser->m_dtd with ones that get destroyed with the external + PE parser. This would leave those prefixes with dangling pointers. */ parser->m_isParamEntity = XML_TRUE; XmlPrologStateInitExternalEntity(&parser->m_prologState); @@ -1352,11 +1304,10 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, } static void FASTCALL -destroyBindings(BINDING *bindings, XML_Parser parser) -{ +destroyBindings(BINDING *bindings, XML_Parser parser) { for (;;) { BINDING *b = bindings; - if (!b) + if (! b) break; bindings = b->nextTagBinding; FREE(parser, b->uri); @@ -1365,8 +1316,7 @@ destroyBindings(BINDING *bindings, XML_Parser parser) } void XMLCALL -XML_ParserFree(XML_Parser parser) -{ +XML_ParserFree(XML_Parser parser) { TAG *tagList; OPEN_INTERNAL_ENTITY *entityList; if (parser == NULL) @@ -1411,11 +1361,12 @@ XML_ParserFree(XML_Parser parser) /* external parameter entity parsers share the DTD structure parser->m_dtd with the root parser, so we must not destroy it */ - if (!parser->m_isParamEntity && parser->m_dtd) + if (! parser->m_isParamEntity && parser->m_dtd) #else if (parser->m_dtd) #endif /* XML_DTD */ - dtdDestroy(parser->m_dtd, (XML_Bool)!parser->m_parentParser, &parser->m_mem); + dtdDestroy(parser->m_dtd, (XML_Bool)! parser->m_parentParser, + &parser->m_mem); FREE(parser, (void *)parser->m_atts); #ifdef XML_ATTR_INFO FREE(parser, (void *)parser->m_attInfo); @@ -1431,20 +1382,19 @@ XML_ParserFree(XML_Parser parser) } void XMLCALL -XML_UseParserAsHandlerArg(XML_Parser parser) -{ +XML_UseParserAsHandlerArg(XML_Parser parser) { if (parser != NULL) parser->m_handlerArg = parser; } enum XML_Error XMLCALL -XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) -{ +XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) { if (parser == NULL) return XML_ERROR_INVALID_ARGUMENT; #ifdef XML_DTD /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING; parser->m_useForeignDTD = useDTD; return XML_ERROR_NONE; @@ -1454,19 +1404,18 @@ XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) } void XMLCALL -XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) -{ +XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) { if (parser == NULL) return; /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return; parser->m_ns_triplets = do_nst ? XML_TRUE : XML_FALSE; } void XMLCALL -XML_SetUserData(XML_Parser parser, void *p) -{ +XML_SetUserData(XML_Parser parser, void *p) { if (parser == NULL) return; if (parser->m_handlerArg == parser->m_userData) @@ -1476,49 +1425,43 @@ XML_SetUserData(XML_Parser parser, void *p) } enum XML_Status XMLCALL -XML_SetBase(XML_Parser parser, const XML_Char *p) -{ +XML_SetBase(XML_Parser parser, const XML_Char *p) { if (parser == NULL) return XML_STATUS_ERROR; if (p) { p = poolCopyString(&parser->m_dtd->pool, p); - if (!p) + if (! p) return XML_STATUS_ERROR; parser->m_curBase = p; - } - else + } else parser->m_curBase = NULL; return XML_STATUS_OK; } -const XML_Char * XMLCALL -XML_GetBase(XML_Parser parser) -{ +const XML_Char *XMLCALL +XML_GetBase(XML_Parser parser) { if (parser == NULL) return NULL; return parser->m_curBase; } int XMLCALL -XML_GetSpecifiedAttributeCount(XML_Parser parser) -{ +XML_GetSpecifiedAttributeCount(XML_Parser parser) { if (parser == NULL) return -1; return parser->m_nSpecifiedAtts; } int XMLCALL -XML_GetIdAttributeIndex(XML_Parser parser) -{ +XML_GetIdAttributeIndex(XML_Parser parser) { if (parser == NULL) return -1; return parser->m_idAttIndex; } #ifdef XML_ATTR_INFO -const XML_AttrInfo * XMLCALL -XML_GetAttributeInfo(XML_Parser parser) -{ +const XML_AttrInfo *XMLCALL +XML_GetAttributeInfo(XML_Parser parser) { if (parser == NULL) return NULL; return parser->m_attInfo; @@ -1526,10 +1469,8 @@ XML_GetAttributeInfo(XML_Parser parser) #endif void XMLCALL -XML_SetElementHandler(XML_Parser parser, - XML_StartElementHandler start, - XML_EndElementHandler end) -{ +XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, + XML_EndElementHandler end) { if (parser == NULL) return; parser->m_startElementHandler = start; @@ -1537,39 +1478,33 @@ XML_SetElementHandler(XML_Parser parser, } void XMLCALL -XML_SetStartElementHandler(XML_Parser parser, - XML_StartElementHandler start) { +XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler start) { if (parser != NULL) parser->m_startElementHandler = start; } void XMLCALL -XML_SetEndElementHandler(XML_Parser parser, - XML_EndElementHandler end) { +XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler end) { if (parser != NULL) parser->m_endElementHandler = end; } void XMLCALL XML_SetCharacterDataHandler(XML_Parser parser, - XML_CharacterDataHandler handler) -{ + XML_CharacterDataHandler handler) { if (parser != NULL) parser->m_characterDataHandler = handler; } void XMLCALL XML_SetProcessingInstructionHandler(XML_Parser parser, - XML_ProcessingInstructionHandler handler) -{ + XML_ProcessingInstructionHandler handler) { if (parser != NULL) parser->m_processingInstructionHandler = handler; } void XMLCALL -XML_SetCommentHandler(XML_Parser parser, - XML_CommentHandler handler) -{ +XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler) { if (parser != NULL) parser->m_commentHandler = handler; } @@ -1577,8 +1512,7 @@ XML_SetCommentHandler(XML_Parser parser, void XMLCALL XML_SetCdataSectionHandler(XML_Parser parser, XML_StartCdataSectionHandler start, - XML_EndCdataSectionHandler end) -{ + XML_EndCdataSectionHandler end) { if (parser == NULL) return; parser->m_startCdataSectionHandler = start; @@ -1600,9 +1534,7 @@ XML_SetEndCdataSectionHandler(XML_Parser parser, } void XMLCALL -XML_SetDefaultHandler(XML_Parser parser, - XML_DefaultHandler handler) -{ +XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler) { if (parser == NULL) return; parser->m_defaultHandler = handler; @@ -1610,9 +1542,7 @@ XML_SetDefaultHandler(XML_Parser parser, } void XMLCALL -XML_SetDefaultHandlerExpand(XML_Parser parser, - XML_DefaultHandler handler) -{ +XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler) { if (parser == NULL) return; parser->m_defaultHandler = handler; @@ -1620,10 +1550,8 @@ XML_SetDefaultHandlerExpand(XML_Parser parser, } void XMLCALL -XML_SetDoctypeDeclHandler(XML_Parser parser, - XML_StartDoctypeDeclHandler start, - XML_EndDoctypeDeclHandler end) -{ +XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end) { if (parser == NULL) return; parser->m_startDoctypeDeclHandler = start; @@ -1638,24 +1566,20 @@ XML_SetStartDoctypeDeclHandler(XML_Parser parser, } void XMLCALL -XML_SetEndDoctypeDeclHandler(XML_Parser parser, - XML_EndDoctypeDeclHandler end) { +XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end) { if (parser != NULL) parser->m_endDoctypeDeclHandler = end; } void XMLCALL XML_SetUnparsedEntityDeclHandler(XML_Parser parser, - XML_UnparsedEntityDeclHandler handler) -{ + XML_UnparsedEntityDeclHandler handler) { if (parser != NULL) parser->m_unparsedEntityDeclHandler = handler; } void XMLCALL -XML_SetNotationDeclHandler(XML_Parser parser, - XML_NotationDeclHandler handler) -{ +XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler) { if (parser != NULL) parser->m_notationDeclHandler = handler; } @@ -1663,8 +1587,7 @@ XML_SetNotationDeclHandler(XML_Parser parser, void XMLCALL XML_SetNamespaceDeclHandler(XML_Parser parser, XML_StartNamespaceDeclHandler start, - XML_EndNamespaceDeclHandler end) -{ + XML_EndNamespaceDeclHandler end) { if (parser == NULL) return; parser->m_startNamespaceDeclHandler = start; @@ -1687,23 +1610,20 @@ XML_SetEndNamespaceDeclHandler(XML_Parser parser, void XMLCALL XML_SetNotStandaloneHandler(XML_Parser parser, - XML_NotStandaloneHandler handler) -{ + XML_NotStandaloneHandler handler) { if (parser != NULL) parser->m_notStandaloneHandler = handler; } void XMLCALL XML_SetExternalEntityRefHandler(XML_Parser parser, - XML_ExternalEntityRefHandler handler) -{ + XML_ExternalEntityRefHandler handler) { if (parser != NULL) parser->m_externalEntityRefHandler = handler; } void XMLCALL -XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) -{ +XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) { if (parser == NULL) return; if (arg) @@ -1714,17 +1634,14 @@ XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) void XMLCALL XML_SetSkippedEntityHandler(XML_Parser parser, - XML_SkippedEntityHandler handler) -{ + XML_SkippedEntityHandler handler) { if (parser != NULL) parser->m_skippedEntityHandler = handler; } void XMLCALL XML_SetUnknownEncodingHandler(XML_Parser parser, - XML_UnknownEncodingHandler handler, - void *data) -{ + XML_UnknownEncodingHandler handler, void *data) { if (parser == NULL) return; parser->m_unknownEncodingHandler = handler; @@ -1732,44 +1649,37 @@ XML_SetUnknownEncodingHandler(XML_Parser parser, } void XMLCALL -XML_SetElementDeclHandler(XML_Parser parser, - XML_ElementDeclHandler eldecl) -{ +XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl) { if (parser != NULL) parser->m_elementDeclHandler = eldecl; } void XMLCALL -XML_SetAttlistDeclHandler(XML_Parser parser, - XML_AttlistDeclHandler attdecl) -{ +XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl) { if (parser != NULL) parser->m_attlistDeclHandler = attdecl; } void XMLCALL -XML_SetEntityDeclHandler(XML_Parser parser, - XML_EntityDeclHandler handler) -{ +XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler) { if (parser != NULL) parser->m_entityDeclHandler = handler; } void XMLCALL -XML_SetXmlDeclHandler(XML_Parser parser, - XML_XmlDeclHandler handler) { +XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler handler) { if (parser != NULL) parser->m_xmlDeclHandler = handler; } int XMLCALL XML_SetParamEntityParsing(XML_Parser parser, - enum XML_ParamEntityParsing peParsing) -{ + enum XML_ParamEntityParsing peParsing) { if (parser == NULL) return 0; /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return 0; #ifdef XML_DTD parser->m_paramEntityParsing = peParsing; @@ -1780,23 +1690,21 @@ XML_SetParamEntityParsing(XML_Parser parser, } int XMLCALL -XML_SetHashSalt(XML_Parser parser, - unsigned long hash_salt) -{ +XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt) { if (parser == NULL) return 0; if (parser->m_parentParser) return XML_SetHashSalt(parser->m_parentParser, hash_salt); /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (parser->m_parsingStatus.parsing == XML_PARSING || parser->m_parsingStatus.parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return 0; parser->m_hash_secret_salt = hash_salt; return 1; } enum XML_Status XMLCALL -XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) -{ +XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { if ((parser == NULL) || (len < 0) || ((s == NULL) && (len != 0))) { if (parser != NULL) parser->m_errorCode = XML_ERROR_INVALID_ARGUMENT; @@ -1810,7 +1718,7 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) parser->m_errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; case XML_INITIALIZED: - if (parser->m_parentParser == NULL && !startParsing(parser)) { + if (parser->m_parentParser == NULL && ! startParsing(parser)) { parser->m_errorCode = XML_ERROR_NO_MEMORY; return XML_STATUS_ERROR; } @@ -1821,7 +1729,7 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) if (len == 0) { parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; - if (!isFinal) + if (! isFinal) return XML_STATUS_OK; parser->m_positionPtr = parser->m_bufferPtr; parser->m_parseEndPtr = parser->m_bufferEnd; @@ -1830,7 +1738,9 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) data are the final chunk of input, then we have to check them again to detect errors based on that fact. */ - parser->m_errorCode = parser->m_processor(parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr); + parser->m_errorCode + = parser->m_processor(parser, parser->m_bufferPtr, + parser->m_parseEndPtr, &parser->m_bufferPtr); if (parser->m_errorCode == XML_ERROR_NONE) { switch (parser->m_parsingStatus.parsing) { @@ -1847,7 +1757,8 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) * * LCOV_EXCL_START */ - XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position); + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); parser->m_positionPtr = parser->m_bufferPtr; return XML_STATUS_SUSPENDED; /* LCOV_EXCL_STOP */ @@ -1870,23 +1781,23 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) enum XML_Status result; /* Detect overflow (a+b > MAX <==> b > MAX-a) */ if (len > ((XML_Size)-1) / 2 - parser->m_parseEndByteIndex) { - parser->m_errorCode = XML_ERROR_NO_MEMORY; - parser->m_eventPtr = parser->m_eventEndPtr = NULL; - parser->m_processor = errorProcessor; - return XML_STATUS_ERROR; + parser->m_errorCode = XML_ERROR_NO_MEMORY; + parser->m_eventPtr = parser->m_eventEndPtr = NULL; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; } parser->m_parseEndByteIndex += len; parser->m_positionPtr = s; parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; - parser->m_errorCode = parser->m_processor(parser, s, parser->m_parseEndPtr = s + len, &end); + parser->m_errorCode + = parser->m_processor(parser, s, parser->m_parseEndPtr = s + len, &end); if (parser->m_errorCode != XML_ERROR_NONE) { parser->m_eventEndPtr = parser->m_eventPtr; parser->m_processor = errorProcessor; return XML_STATUS_ERROR; - } - else { + } else { switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; @@ -1903,10 +1814,12 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) } } - XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, end, &parser->m_position); + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, end, + &parser->m_position); nLeftOver = s + len - end; if (nLeftOver) { - if (parser->m_buffer == NULL || nLeftOver > parser->m_bufferLim - parser->m_buffer) { + if (parser->m_buffer == NULL + || nLeftOver > parser->m_bufferLim - parser->m_buffer) { /* avoid _signed_ integer overflow */ char *temp = NULL; const int bytesToAllocate = (int)((unsigned)len * 2U); @@ -1932,7 +1845,7 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) parser->m_eventEndPtr = parser->m_bufferPtr; return result; } -#endif /* not defined XML_CONTEXT_BYTES */ +#endif /* not defined XML_CONTEXT_BYTES */ else { void *buff = XML_GetBuffer(parser, len); if (buff == NULL) @@ -1945,8 +1858,7 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) } enum XML_Status XMLCALL -XML_ParseBuffer(XML_Parser parser, int len, int isFinal) -{ +XML_ParseBuffer(XML_Parser parser, int len, int isFinal) { const char *start; enum XML_Status result = XML_STATUS_OK; @@ -1960,7 +1872,7 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) parser->m_errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; case XML_INITIALIZED: - if (parser->m_parentParser == NULL && !startParsing(parser)) { + if (parser->m_parentParser == NULL && ! startParsing(parser)) { parser->m_errorCode = XML_ERROR_NO_MEMORY; return XML_STATUS_ERROR; } @@ -1976,14 +1888,14 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) parser->m_parseEndByteIndex += len; parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; - parser->m_errorCode = parser->m_processor(parser, start, parser->m_parseEndPtr, &parser->m_bufferPtr); + parser->m_errorCode = parser->m_processor( + parser, start, parser->m_parseEndPtr, &parser->m_bufferPtr); if (parser->m_errorCode != XML_ERROR_NONE) { parser->m_eventEndPtr = parser->m_eventPtr; parser->m_processor = errorProcessor; return XML_STATUS_ERROR; - } - else { + } else { switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; @@ -1994,18 +1906,18 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal) parser->m_parsingStatus.parsing = XML_FINISHED; return result; } - default: ; /* should not happen */ + default:; /* should not happen */ } } - XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position); + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); parser->m_positionPtr = parser->m_bufferPtr; return result; } -void * XMLCALL -XML_GetBuffer(XML_Parser parser, int len) -{ +void *XMLCALL +XML_GetBuffer(XML_Parser parser, int len) { if (parser == NULL) return NULL; if (len < 0) { @@ -2019,17 +1931,17 @@ XML_GetBuffer(XML_Parser parser, int len) case XML_FINISHED: parser->m_errorCode = XML_ERROR_FINISHED; return NULL; - default: ; + default:; } if (len > EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferEnd)) { #ifdef XML_CONTEXT_BYTES int keep; -#endif /* defined XML_CONTEXT_BYTES */ +#endif /* defined XML_CONTEXT_BYTES */ /* Do not invoke signed arithmetic overflow: */ - int neededSize = (int) ((unsigned)len + - (unsigned)EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, - parser->m_bufferPtr)); + int neededSize = (int)((unsigned)len + + (unsigned)EXPAT_SAFE_PTR_DIFF( + parser->m_bufferEnd, parser->m_bufferPtr)); if (neededSize < 0) { parser->m_errorCode = XML_ERROR_NO_MEMORY; return NULL; @@ -2039,13 +1951,18 @@ XML_GetBuffer(XML_Parser parser, int len) if (keep > XML_CONTEXT_BYTES) keep = XML_CONTEXT_BYTES; neededSize += keep; -#endif /* defined XML_CONTEXT_BYTES */ - if (neededSize <= EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_buffer)) { +#endif /* defined XML_CONTEXT_BYTES */ + if (neededSize + <= EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_buffer)) { #ifdef XML_CONTEXT_BYTES if (keep < EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer)) { - int offset = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer) - keep; - /* The buffer pointers cannot be NULL here; we have at least some bytes in the buffer */ - memmove(parser->m_buffer, &parser->m_buffer[offset], parser->m_bufferEnd - parser->m_bufferPtr + keep); + int offset + = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer) + - keep; + /* The buffer pointers cannot be NULL here; we have at least some bytes + * in the buffer */ + memmove(parser->m_buffer, &parser->m_buffer[offset], + parser->m_bufferEnd - parser->m_bufferPtr + keep); parser->m_bufferEnd -= offset; parser->m_bufferPtr -= offset; } @@ -2053,20 +1970,21 @@ XML_GetBuffer(XML_Parser parser, int len) if (parser->m_buffer && parser->m_bufferPtr) { memmove(parser->m_buffer, parser->m_bufferPtr, EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr)); - parser->m_bufferEnd = parser->m_buffer + - EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); + parser->m_bufferEnd + = parser->m_buffer + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); parser->m_bufferPtr = parser->m_buffer; } -#endif /* not defined XML_CONTEXT_BYTES */ - } - else { +#endif /* not defined XML_CONTEXT_BYTES */ + } else { char *newBuf; - int bufferSize = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferPtr); + int bufferSize + = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferPtr); if (bufferSize == 0) bufferSize = INIT_BUFFER_SIZE; do { /* Do not invoke signed arithmetic overflow: */ - bufferSize = (int) (2U * (unsigned) bufferSize); + bufferSize = (int)(2U * (unsigned)bufferSize); } while (bufferSize < neededSize && bufferSize > 0); if (bufferSize <= 0) { parser->m_errorCode = XML_ERROR_NO_MEMORY; @@ -2080,18 +1998,17 @@ XML_GetBuffer(XML_Parser parser, int len) parser->m_bufferLim = newBuf + bufferSize; #ifdef XML_CONTEXT_BYTES if (parser->m_bufferPtr) { - int keep = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer); - if (keep > XML_CONTEXT_BYTES) - keep = XML_CONTEXT_BYTES; memcpy(newBuf, &parser->m_bufferPtr[-keep], - EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) + keep); + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) + + keep); FREE(parser, parser->m_buffer); parser->m_buffer = newBuf; - parser->m_bufferEnd = parser->m_buffer + - EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) + keep; + parser->m_bufferEnd + = parser->m_buffer + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) + + keep; parser->m_bufferPtr = parser->m_buffer + keep; - } - else { + } else { /* This must be a brand new buffer with no data in it yet */ parser->m_bufferEnd = newBuf; parser->m_bufferPtr = parser->m_buffer = newBuf; @@ -2101,15 +2018,15 @@ XML_GetBuffer(XML_Parser parser, int len) memcpy(newBuf, parser->m_bufferPtr, EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr)); FREE(parser, parser->m_buffer); - parser->m_bufferEnd = newBuf + - EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); - } - else { + parser->m_bufferEnd + = newBuf + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); + } else { /* This must be a brand new buffer with no data in it yet */ parser->m_bufferEnd = newBuf; } parser->m_bufferPtr = parser->m_buffer = newBuf; -#endif /* not defined XML_CONTEXT_BYTES */ +#endif /* not defined XML_CONTEXT_BYTES */ } parser->m_eventPtr = parser->m_eventEndPtr = NULL; parser->m_positionPtr = NULL; @@ -2118,8 +2035,7 @@ XML_GetBuffer(XML_Parser parser, int len) } enum XML_Status XMLCALL -XML_StopParser(XML_Parser parser, XML_Bool resumable) -{ +XML_StopParser(XML_Parser parser, XML_Bool resumable) { if (parser == NULL) return XML_STATUS_ERROR; switch (parser->m_parsingStatus.parsing) { @@ -2142,16 +2058,14 @@ XML_StopParser(XML_Parser parser, XML_Bool resumable) } #endif parser->m_parsingStatus.parsing = XML_SUSPENDED; - } - else + } else parser->m_parsingStatus.parsing = XML_FINISHED; } return XML_STATUS_OK; } enum XML_Status XMLCALL -XML_ResumeParser(XML_Parser parser) -{ +XML_ResumeParser(XML_Parser parser) { enum XML_Status result = XML_STATUS_OK; if (parser == NULL) @@ -2162,14 +2076,14 @@ XML_ResumeParser(XML_Parser parser) } parser->m_parsingStatus.parsing = XML_PARSING; - parser->m_errorCode = parser->m_processor(parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr); + parser->m_errorCode = parser->m_processor( + parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr); if (parser->m_errorCode != XML_ERROR_NONE) { parser->m_eventEndPtr = parser->m_eventPtr; parser->m_processor = errorProcessor; return XML_STATUS_ERROR; - } - else { + } else { switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; @@ -2180,18 +2094,18 @@ XML_ResumeParser(XML_Parser parser) parser->m_parsingStatus.parsing = XML_FINISHED; return result; } - default: ; + default:; } } - XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_bufferPtr, &parser->m_position); + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); parser->m_positionPtr = parser->m_bufferPtr; return result; } void XMLCALL -XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status) -{ +XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status) { if (parser == NULL) return; assert(status != NULL); @@ -2199,26 +2113,24 @@ XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status) } enum XML_Error XMLCALL -XML_GetErrorCode(XML_Parser parser) -{ +XML_GetErrorCode(XML_Parser parser) { if (parser == NULL) return XML_ERROR_INVALID_ARGUMENT; return parser->m_errorCode; } XML_Index XMLCALL -XML_GetCurrentByteIndex(XML_Parser parser) -{ +XML_GetCurrentByteIndex(XML_Parser parser) { if (parser == NULL) return -1; if (parser->m_eventPtr) - return (XML_Index)(parser->m_parseEndByteIndex - (parser->m_parseEndPtr - parser->m_eventPtr)); + return (XML_Index)(parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - parser->m_eventPtr)); return -1; } int XMLCALL -XML_GetCurrentByteCount(XML_Parser parser) -{ +XML_GetCurrentByteCount(XML_Parser parser) { if (parser == NULL) return 0; if (parser->m_eventEndPtr && parser->m_eventPtr) @@ -2226,9 +2138,8 @@ XML_GetCurrentByteCount(XML_Parser parser) return 0; } -const char * XMLCALL -XML_GetInputContext(XML_Parser parser, int *offset, int *size) -{ +const char *XMLCALL +XML_GetInputContext(XML_Parser parser, int *offset, int *size) { #ifdef XML_CONTEXT_BYTES if (parser == NULL) return NULL; @@ -2236,7 +2147,7 @@ XML_GetInputContext(XML_Parser parser, int *offset, int *size) if (offset != NULL) *offset = (int)(parser->m_eventPtr - parser->m_buffer); if (size != NULL) - *size = (int)(parser->m_bufferEnd - parser->m_buffer); + *size = (int)(parser->m_bufferEnd - parser->m_buffer); return parser->m_buffer; } #else @@ -2244,82 +2155,76 @@ XML_GetInputContext(XML_Parser parser, int *offset, int *size) (void)offset; (void)size; #endif /* defined XML_CONTEXT_BYTES */ - return (char *) 0; + return (char *)0; } XML_Size XMLCALL -XML_GetCurrentLineNumber(XML_Parser parser) -{ +XML_GetCurrentLineNumber(XML_Parser parser) { if (parser == NULL) return 0; if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) { - XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_eventPtr, &parser->m_position); + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_eventPtr, &parser->m_position); parser->m_positionPtr = parser->m_eventPtr; } return parser->m_position.lineNumber + 1; } XML_Size XMLCALL -XML_GetCurrentColumnNumber(XML_Parser parser) -{ +XML_GetCurrentColumnNumber(XML_Parser parser) { if (parser == NULL) return 0; if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) { - XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, parser->m_eventPtr, &parser->m_position); + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_eventPtr, &parser->m_position); parser->m_positionPtr = parser->m_eventPtr; } return parser->m_position.columnNumber; } void XMLCALL -XML_FreeContentModel(XML_Parser parser, XML_Content *model) -{ +XML_FreeContentModel(XML_Parser parser, XML_Content *model) { if (parser != NULL) FREE(parser, model); } -void * XMLCALL -XML_MemMalloc(XML_Parser parser, size_t size) -{ +void *XMLCALL +XML_MemMalloc(XML_Parser parser, size_t size) { if (parser == NULL) return NULL; return MALLOC(parser, size); } -void * XMLCALL -XML_MemRealloc(XML_Parser parser, void *ptr, size_t size) -{ +void *XMLCALL +XML_MemRealloc(XML_Parser parser, void *ptr, size_t size) { if (parser == NULL) return NULL; return REALLOC(parser, ptr, size); } void XMLCALL -XML_MemFree(XML_Parser parser, void *ptr) -{ +XML_MemFree(XML_Parser parser, void *ptr) { if (parser != NULL) FREE(parser, ptr); } void XMLCALL -XML_DefaultCurrent(XML_Parser parser) -{ +XML_DefaultCurrent(XML_Parser parser) { if (parser == NULL) return; if (parser->m_defaultHandler) { if (parser->m_openInternalEntities) - reportDefault(parser, - parser->m_internalEncoding, + reportDefault(parser, parser->m_internalEncoding, parser->m_openInternalEntities->internalEventPtr, parser->m_openInternalEntities->internalEventEndPtr); else - reportDefault(parser, parser->m_encoding, parser->m_eventPtr, parser->m_eventEndPtr); + reportDefault(parser, parser->m_encoding, parser->m_eventPtr, + parser->m_eventEndPtr); } } -const XML_LChar * XMLCALL -XML_ErrorString(enum XML_Error code) -{ +const XML_LChar *XMLCALL +XML_ErrorString(enum XML_Error code) { switch (code) { case XML_ERROR_NONE: return NULL; @@ -2401,21 +2306,22 @@ XML_ErrorString(enum XML_Error code) return XML_L("cannot suspend in external parameter entity"); /* Added in 2.0.0. */ case XML_ERROR_RESERVED_PREFIX_XML: - return XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name"); + return XML_L( + "reserved prefix (xml) must not be undeclared or bound to another namespace name"); case XML_ERROR_RESERVED_PREFIX_XMLNS: return XML_L("reserved prefix (xmlns) must not be declared or undeclared"); case XML_ERROR_RESERVED_NAMESPACE_URI: - return XML_L("prefix must not be bound to one of the reserved namespace names"); + return XML_L( + "prefix must not be bound to one of the reserved namespace names"); /* Added in 2.2.5. */ - case XML_ERROR_INVALID_ARGUMENT: /* Constant added in 2.2.1, already */ + case XML_ERROR_INVALID_ARGUMENT: /* Constant added in 2.2.1, already */ return XML_L("invalid argument"); } return NULL; } -const XML_LChar * XMLCALL +const XML_LChar *XMLCALL XML_ExpatVersion(void) { - /* V1 is used to string-ize the version number. However, it would string-ize the actual version macro *names* unless we get them substituted before being passed to V1. CPP is defined to expand @@ -2424,8 +2330,8 @@ XML_ExpatVersion(void) { with the correct numerals. */ /* ### I'm assuming cpp is portable in this respect... */ -#define V1(a,b,c) XML_L(#a)XML_L(".")XML_L(#b)XML_L(".")XML_L(#c) -#define V2(a,b,c) XML_L("expat_")V1(a,b,c) +#define V1(a, b, c) XML_L(#a) XML_L(".") XML_L(#b) XML_L(".") XML_L(#c) +#define V2(a, b, c) XML_L("expat_") V1(a, b, c) return V2(XML_MAJOR_VERSION, XML_MINOR_VERSION, XML_MICRO_VERSION); @@ -2434,8 +2340,7 @@ XML_ExpatVersion(void) { } XML_Expat_Version XMLCALL -XML_ExpatVersionInfo(void) -{ +XML_ExpatVersionInfo(void) { XML_Expat_Version version; version.major = XML_MAJOR_VERSION; @@ -2445,41 +2350,39 @@ XML_ExpatVersionInfo(void) return version; } -const XML_Feature * XMLCALL -XML_GetFeatureList(void) -{ - static const XML_Feature features[] = { - {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), - sizeof(XML_Char)}, - {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), - sizeof(XML_LChar)}, +const XML_Feature *XMLCALL +XML_GetFeatureList(void) { + static const XML_Feature features[] + = {{XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), + sizeof(XML_Char)}, + {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), + sizeof(XML_LChar)}, #ifdef XML_UNICODE - {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, + {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, #endif #ifdef XML_UNICODE_WCHAR_T - {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, + {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, #endif #ifdef XML_DTD - {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, + {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, #endif #ifdef XML_CONTEXT_BYTES - {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), - XML_CONTEXT_BYTES}, + {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), + XML_CONTEXT_BYTES}, #endif #ifdef XML_MIN_SIZE - {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, + {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, #endif #ifdef XML_NS - {XML_FEATURE_NS, XML_L("XML_NS"), 0}, + {XML_FEATURE_NS, XML_L("XML_NS"), 0}, #endif #ifdef XML_LARGE_SIZE - {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, + {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, #endif #ifdef XML_ATTR_INFO - {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, + {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, #endif - {XML_FEATURE_END, NULL, 0} - }; + {XML_FEATURE_END, NULL, 0}}; return features; } @@ -2490,8 +2393,7 @@ XML_GetFeatureList(void) permanent location, since the parse buffer is about to be discarded. */ static XML_Bool -storeRawNames(XML_Parser parser) -{ +storeRawNames(XML_Parser parser) { TAG *tag = parser->m_tagStack; while (tag) { int bufSize; @@ -2521,8 +2423,8 @@ storeRawNames(XML_Parser parser) then update it as well, since it will always point into tag->buf */ if (tag->name.localPart) - tag->name.localPart = (XML_Char *)temp + (tag->name.localPart - - (XML_Char *)tag->buf); + tag->name.localPart + = (XML_Char *)temp + (tag->name.localPart - (XML_Char *)tag->buf); tag->buf = temp; tag->bufEnd = temp + bufSize; rawNameBuf = temp + nameLen; @@ -2535,26 +2437,21 @@ storeRawNames(XML_Parser parser) } static enum XML_Error PTRCALL -contentProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doContent(parser, 0, parser->m_encoding, start, end, - endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer); +contentProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result + = doContent(parser, 0, parser->m_encoding, start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); if (result == XML_ERROR_NONE) { - if (!storeRawNames(parser)) + if (! storeRawNames(parser)) return XML_ERROR_NO_MEMORY; } return result; } static enum XML_Error PTRCALL -externalEntityInitProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ +externalEntityInitProcessor(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { enum XML_Error result = initializeEncoding(parser); if (result != XML_ERROR_NONE) return result; @@ -2563,11 +2460,8 @@ externalEntityInitProcessor(XML_Parser parser, } static enum XML_Error PTRCALL -externalEntityInitProcessor2(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ +externalEntityInitProcessor2(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { const char *next = start; /* XmlContentTok doesn't always set the last arg */ int tok = XmlContentTok(parser->m_encoding, start, end, &next); switch (tok) { @@ -2577,21 +2471,21 @@ externalEntityInitProcessor2(XML_Parser parser, doContent (by detecting XML_TOK_NONE) without processing any xml text declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent. */ - if (next == end && !parser->m_parsingStatus.finalBuffer) { + if (next == end && ! parser->m_parsingStatus.finalBuffer) { *endPtr = next; return XML_ERROR_NONE; } start = next; break; case XML_TOK_PARTIAL: - if (!parser->m_parsingStatus.finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } parser->m_eventPtr = start; return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!parser->m_parsingStatus.finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } @@ -2603,11 +2497,8 @@ externalEntityInitProcessor2(XML_Parser parser, } static enum XML_Error PTRCALL -externalEntityInitProcessor3(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ +externalEntityInitProcessor3(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { int tok; const char *next = start; /* XmlContentTok doesn't always set the last arg */ parser->m_eventPtr = start; @@ -2615,31 +2506,29 @@ externalEntityInitProcessor3(XML_Parser parser, parser->m_eventEndPtr = next; switch (tok) { - case XML_TOK_XML_DECL: - { - enum XML_Error result; - result = processXmlDecl(parser, 1, start, next); - if (result != XML_ERROR_NONE) - return result; - switch (parser->m_parsingStatus.parsing) { - case XML_SUSPENDED: - *endPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: - return XML_ERROR_ABORTED; - default: - start = next; - } + case XML_TOK_XML_DECL: { + enum XML_Error result; + result = processXmlDecl(parser, 1, start, next); + if (result != XML_ERROR_NONE) + return result; + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + *endPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: + start = next; } - break; + } break; case XML_TOK_PARTIAL: - if (!parser->m_parsingStatus.finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!parser->m_parsingStatus.finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } @@ -2651,39 +2540,31 @@ externalEntityInitProcessor3(XML_Parser parser, } static enum XML_Error PTRCALL -externalEntityContentProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doContent(parser, 1, parser->m_encoding, start, end, - endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer); +externalEntityContentProcessor(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { + enum XML_Error result + = doContent(parser, 1, parser->m_encoding, start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); if (result == XML_ERROR_NONE) { - if (!storeRawNames(parser)) + if (! storeRawNames(parser)) return XML_ERROR_NO_MEMORY; } return result; } static enum XML_Error -doContent(XML_Parser parser, - int startTagLevel, - const ENCODING *enc, - const char *s, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ +doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, + const char *s, const char *end, const char **nextPtr, + XML_Bool haveMore) { /* save one level of indirection */ - DTD * const dtd = parser->m_dtd; + DTD *const dtd = parser->m_dtd; const char **eventPP; const char **eventEndPP; if (enc == parser->m_encoding) { eventPP = &parser->m_eventPtr; eventEndPP = &parser->m_eventEndPtr; - } - else { + } else { eventPP = &(parser->m_openInternalEntities->internalEventPtr); eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); } @@ -2703,8 +2584,7 @@ doContent(XML_Parser parser, if (parser->m_characterDataHandler) { XML_Char c = 0xA; parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); - } - else if (parser->m_defaultHandler) + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, end); /* We are at the end of the final buffer, should we check for XML_SUSPENDED, XML_FINISHED? @@ -2742,185 +2622,178 @@ doContent(XML_Parser parser, return XML_ERROR_NONE; } return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_ENTITY_REF: - { - const XML_Char *name; - ENTITY *entity; - XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (ch) { - if (parser->m_characterDataHandler) - parser->m_characterDataHandler(parser->m_handlerArg, &ch, 1); - else if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - name = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) - return XML_ERROR_NO_MEMORY; - entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); - poolDiscard(&dtd->pool); - /* First, determine if a check for an existing declaration is needed; - if yes, check that the entity exists, and that it is internal, - otherwise call the skipped entity or default handler. - */ - if (!dtd->hasParamEntityRefs || dtd->standalone) { - if (!entity) - return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) - return XML_ERROR_ENTITY_DECLARED_IN_PE; - } - else if (!entity) { + case XML_TOK_ENTITY_REF: { + const XML_Char *name; + ENTITY *entity; + XML_Char ch = (XML_Char)XmlPredefinedEntityName( + enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); + if (ch) { + if (parser->m_characterDataHandler) + parser->m_characterDataHandler(parser->m_handlerArg, &ch, 1); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + name = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); + poolDiscard(&dtd->pool); + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal, + otherwise call the skipped entity or default handler. + */ + if (! dtd->hasParamEntityRefs || dtd->standalone) { + if (! entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (! entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } else if (! entity) { + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + if (entity->open) + return XML_ERROR_RECURSIVE_ENTITY_REF; + if (entity->notation) + return XML_ERROR_BINARY_ENTITY_REF; + if (entity->textPtr) { + enum XML_Error result; + if (! parser->m_defaultExpandInternalEntities) { if (parser->m_skippedEntityHandler) - parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); + parser->m_skippedEntityHandler(parser->m_handlerArg, entity->name, + 0); else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); break; } - if (entity->open) - return XML_ERROR_RECURSIVE_ENTITY_REF; - if (entity->notation) - return XML_ERROR_BINARY_ENTITY_REF; - if (entity->textPtr) { - enum XML_Error result; - if (!parser->m_defaultExpandInternalEntities) { - if (parser->m_skippedEntityHandler) - parser->m_skippedEntityHandler(parser->m_handlerArg, entity->name, 0); - else if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - result = processInternalEntity(parser, entity, XML_FALSE); - if (result != XML_ERROR_NONE) - return result; - } - else if (parser->m_externalEntityRefHandler) { - const XML_Char *context; - entity->open = XML_TRUE; - context = getContext(parser); - entity->open = XML_FALSE; - if (!context) - return XML_ERROR_NO_MEMORY; - if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg, - context, - entity->base, - entity->systemId, - entity->publicId)) - return XML_ERROR_EXTERNAL_ENTITY_HANDLING; - poolDiscard(&parser->m_tempPool); - } - else if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - break; - } + result = processInternalEntity(parser, entity, XML_FALSE); + if (result != XML_ERROR_NONE) + return result; + } else if (parser->m_externalEntityRefHandler) { + const XML_Char *context; + entity->open = XML_TRUE; + context = getContext(parser); + entity->open = XML_FALSE; + if (! context) + return XML_ERROR_NO_MEMORY; + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, context, entity->base, + entity->systemId, entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + poolDiscard(&parser->m_tempPool); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } case XML_TOK_START_TAG_NO_ATTS: /* fall through */ - case XML_TOK_START_TAG_WITH_ATTS: - { - TAG *tag; - enum XML_Error result; - XML_Char *toPtr; - if (parser->m_freeTagList) { - tag = parser->m_freeTagList; - parser->m_freeTagList = parser->m_freeTagList->parent; + case XML_TOK_START_TAG_WITH_ATTS: { + TAG *tag; + enum XML_Error result; + XML_Char *toPtr; + if (parser->m_freeTagList) { + tag = parser->m_freeTagList; + parser->m_freeTagList = parser->m_freeTagList->parent; + } else { + tag = (TAG *)MALLOC(parser, sizeof(TAG)); + if (! tag) + return XML_ERROR_NO_MEMORY; + tag->buf = (char *)MALLOC(parser, INIT_TAG_BUF_SIZE); + if (! tag->buf) { + FREE(parser, tag); + return XML_ERROR_NO_MEMORY; } - else { - tag = (TAG *)MALLOC(parser, sizeof(TAG)); - if (!tag) - return XML_ERROR_NO_MEMORY; - tag->buf = (char *)MALLOC(parser, INIT_TAG_BUF_SIZE); - if (!tag->buf) { - FREE(parser, tag); - return XML_ERROR_NO_MEMORY; + tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; + } + tag->bindings = NULL; + tag->parent = parser->m_tagStack; + parser->m_tagStack = tag; + tag->name.localPart = NULL; + tag->name.prefix = NULL; + tag->rawName = s + enc->minBytesPerChar; + tag->rawNameLength = XmlNameLength(enc, tag->rawName); + ++parser->m_tagLevel; + { + const char *rawNameEnd = tag->rawName + tag->rawNameLength; + const char *fromPtr = tag->rawName; + toPtr = (XML_Char *)tag->buf; + for (;;) { + int bufSize; + int convLen; + const enum XML_Convert_Result convert_res + = XmlConvert(enc, &fromPtr, rawNameEnd, (ICHAR **)&toPtr, + (ICHAR *)tag->bufEnd - 1); + convLen = (int)(toPtr - (XML_Char *)tag->buf); + if ((fromPtr >= rawNameEnd) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) { + tag->name.strLen = convLen; + break; } - tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; - } - tag->bindings = NULL; - tag->parent = parser->m_tagStack; - parser->m_tagStack = tag; - tag->name.localPart = NULL; - tag->name.prefix = NULL; - tag->rawName = s + enc->minBytesPerChar; - tag->rawNameLength = XmlNameLength(enc, tag->rawName); - ++parser->m_tagLevel; - { - const char *rawNameEnd = tag->rawName + tag->rawNameLength; - const char *fromPtr = tag->rawName; - toPtr = (XML_Char *)tag->buf; - for (;;) { - int bufSize; - int convLen; - const enum XML_Convert_Result convert_res = XmlConvert(enc, - &fromPtr, rawNameEnd, - (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1); - convLen = (int)(toPtr - (XML_Char *)tag->buf); - if ((fromPtr >= rawNameEnd) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) { - tag->name.strLen = convLen; - break; - } - bufSize = (int)(tag->bufEnd - tag->buf) << 1; - { - char *temp = (char *)REALLOC(parser, tag->buf, bufSize); - if (temp == NULL) - return XML_ERROR_NO_MEMORY; - tag->buf = temp; - tag->bufEnd = temp + bufSize; - toPtr = (XML_Char *)temp + convLen; - } + bufSize = (int)(tag->bufEnd - tag->buf) << 1; + { + char *temp = (char *)REALLOC(parser, tag->buf, bufSize); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + tag->buf = temp; + tag->bufEnd = temp + bufSize; + toPtr = (XML_Char *)temp + convLen; } } - tag->name.str = (XML_Char *)tag->buf; - *toPtr = XML_T('\0'); - result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings)); - if (result) - return result; - if (parser->m_startElementHandler) - parser->m_startElementHandler(parser->m_handlerArg, tag->name.str, - (const XML_Char **)parser->m_atts); - else if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - poolClear(&parser->m_tempPool); - break; } + tag->name.str = (XML_Char *)tag->buf; + *toPtr = XML_T('\0'); + result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings)); + if (result) + return result; + if (parser->m_startElementHandler) + parser->m_startElementHandler(parser->m_handlerArg, tag->name.str, + (const XML_Char **)parser->m_atts); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + poolClear(&parser->m_tempPool); + break; + } case XML_TOK_EMPTY_ELEMENT_NO_ATTS: /* fall through */ - case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: - { - const char *rawName = s + enc->minBytesPerChar; - enum XML_Error result; - BINDING *bindings = NULL; - XML_Bool noElmHandlers = XML_TRUE; - TAG_NAME name; - name.str = poolStoreString(&parser->m_tempPool, enc, rawName, - rawName + XmlNameLength(enc, rawName)); - if (!name.str) - return XML_ERROR_NO_MEMORY; - poolFinish(&parser->m_tempPool); - result = storeAtts(parser, enc, s, &name, &bindings); - if (result != XML_ERROR_NONE) { - freeBindings(parser, bindings); - return result; - } - poolFinish(&parser->m_tempPool); - if (parser->m_startElementHandler) { - parser->m_startElementHandler(parser->m_handlerArg, name.str, (const XML_Char **)parser->m_atts); - noElmHandlers = XML_FALSE; - } - if (parser->m_endElementHandler) { - if (parser->m_startElementHandler) - *eventPP = *eventEndPP; - parser->m_endElementHandler(parser->m_handlerArg, name.str); - noElmHandlers = XML_FALSE; - } - if (noElmHandlers && parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - poolClear(&parser->m_tempPool); + case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: { + const char *rawName = s + enc->minBytesPerChar; + enum XML_Error result; + BINDING *bindings = NULL; + XML_Bool noElmHandlers = XML_TRUE; + TAG_NAME name; + name.str = poolStoreString(&parser->m_tempPool, enc, rawName, + rawName + XmlNameLength(enc, rawName)); + if (! name.str) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_tempPool); + result = storeAtts(parser, enc, s, &name, &bindings); + if (result != XML_ERROR_NONE) { freeBindings(parser, bindings); + return result; + } + poolFinish(&parser->m_tempPool); + if (parser->m_startElementHandler) { + parser->m_startElementHandler(parser->m_handlerArg, name.str, + (const XML_Char **)parser->m_atts); + noElmHandlers = XML_FALSE; + } + if (parser->m_endElementHandler) { + if (parser->m_startElementHandler) + *eventPP = *eventEndPP; + parser->m_endElementHandler(parser->m_handlerArg, name.str); + noElmHandlers = XML_FALSE; } - if ((parser->m_tagLevel == 0) && (parser->m_parsingStatus.parsing != XML_FINISHED)) { + if (noElmHandlers && parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + poolClear(&parser->m_tempPool); + freeBindings(parser, bindings); + } + if ((parser->m_tagLevel == 0) + && (parser->m_parsingStatus.parsing != XML_FINISHED)) { if (parser->m_parsingStatus.parsing == XML_SUSPENDED) parser->m_processor = epilogProcessor; else @@ -2937,7 +2810,7 @@ doContent(XML_Parser parser, parser->m_tagStack = tag->parent; tag->parent = parser->m_freeTagList; parser->m_freeTagList = tag; - rawName = s + enc->minBytesPerChar*2; + rawName = s + enc->minBytesPerChar * 2; len = XmlNameLength(enc, rawName); if (len != tag->rawNameLength || memcmp(tag->rawName, rawName, len) != 0) { @@ -2957,86 +2830,89 @@ doContent(XML_Parser parser, */ uri = (XML_Char *)tag->name.str + tag->name.uriLen; /* don't need to check for space - already done in storeAtts() */ - while (*localPart) *uri++ = *localPart++; + while (*localPart) + *uri++ = *localPart++; prefix = (XML_Char *)tag->name.prefix; if (parser->m_ns_triplets && prefix) { *uri++ = parser->m_namespaceSeparator; - while (*prefix) *uri++ = *prefix++; - } + while (*prefix) + *uri++ = *prefix++; + } *uri = XML_T('\0'); } parser->m_endElementHandler(parser->m_handlerArg, tag->name.str); - } - else if (parser->m_defaultHandler) + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); while (tag->bindings) { BINDING *b = tag->bindings; if (parser->m_endNamespaceDeclHandler) - parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name); + parser->m_endNamespaceDeclHandler(parser->m_handlerArg, + b->prefix->name); tag->bindings = tag->bindings->nextTagBinding; b->nextTagBinding = parser->m_freeBindingList; parser->m_freeBindingList = b; b->prefix->binding = b->prevPrefixBinding; } - if (parser->m_tagLevel == 0) - return epilogProcessor(parser, next, end, nextPtr); - } - break; - case XML_TOK_CHAR_REF: - { - int n = XmlCharRefNumber(enc, s); - if (n < 0) - return XML_ERROR_BAD_CHAR_REF; - if (parser->m_characterDataHandler) { - XML_Char buf[XML_ENCODE_MAX]; - parser->m_characterDataHandler(parser->m_handlerArg, buf, XmlEncode(n, (ICHAR *)buf)); + if ((parser->m_tagLevel == 0) + && (parser->m_parsingStatus.parsing != XML_FINISHED)) { + if (parser->m_parsingStatus.parsing == XML_SUSPENDED) + parser->m_processor = epilogProcessor; + else + return epilogProcessor(parser, next, end, nextPtr); } - else if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); } break; + case XML_TOK_CHAR_REF: { + int n = XmlCharRefNumber(enc, s); + if (n < 0) + return XML_ERROR_BAD_CHAR_REF; + if (parser->m_characterDataHandler) { + XML_Char buf[XML_ENCODE_MAX]; + parser->m_characterDataHandler(parser->m_handlerArg, buf, + XmlEncode(n, (ICHAR *)buf)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; case XML_TOK_XML_DECL: return XML_ERROR_MISPLACED_XML_PI; case XML_TOK_DATA_NEWLINE: if (parser->m_characterDataHandler) { XML_Char c = 0xA; parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); - } - else if (parser->m_defaultHandler) + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); break; - case XML_TOK_CDATA_SECT_OPEN: - { - enum XML_Error result; - if (parser->m_startCdataSectionHandler) - parser->m_startCdataSectionHandler(parser->m_handlerArg); -/* BEGIN disabled code */ - /* Suppose you doing a transformation on a document that involves - changing only the character data. You set up a defaultHandler - and a characterDataHandler. The defaultHandler simply copies - characters through. The characterDataHandler does the - transformation and writes the characters out escaping them as - necessary. This case will fail to work if we leave out the - following two lines (because & and < inside CDATA sections will - be incorrectly escaped). - - However, now we have a start/endCdataSectionHandler, so it seems - easier to let the user deal with this. - */ - else if (0 && parser->m_characterDataHandler) - parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, 0); -/* END disabled code */ - else if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore); - if (result != XML_ERROR_NONE) - return result; - else if (!next) { - parser->m_processor = cdataSectionProcessor; - return result; - } + case XML_TOK_CDATA_SECT_OPEN: { + enum XML_Error result; + if (parser->m_startCdataSectionHandler) + parser->m_startCdataSectionHandler(parser->m_handlerArg); + /* BEGIN disabled code */ + /* Suppose you doing a transformation on a document that involves + changing only the character data. You set up a defaultHandler + and a characterDataHandler. The defaultHandler simply copies + characters through. The characterDataHandler does the + transformation and writes the characters out escaping them as + necessary. This case will fail to work if we leave out the + following two lines (because & and < inside CDATA sections will + be incorrectly escaped). + + However, now we have a start/endCdataSectionHandler, so it seems + easier to let the user deal with this. + */ + else if (0 && parser->m_characterDataHandler) + parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, + 0); + /* END disabled code */ + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore); + if (result != XML_ERROR_NONE) + return result; + else if (! next) { + parser->m_processor = cdataSectionProcessor; + return result; } - break; + } break; case XML_TOK_TRAILING_RSQB: if (haveMore) { *nextPtr = s; @@ -3046,15 +2922,14 @@ doContent(XML_Parser parser, if (MUST_CONVERT(enc, s)) { ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd); - parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, - (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); - } - else - parser->m_characterDataHandler(parser->m_handlerArg, - (XML_Char *)s, - (int)((XML_Char *)end - (XML_Char *)s)); - } - else if (parser->m_defaultHandler) + parser->m_characterDataHandler( + parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + } else + parser->m_characterDataHandler( + parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)end - (XML_Char *)s)); + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, end); /* We are at the end of the final buffer, should we check for XML_SUSPENDED, XML_FINISHED? @@ -3069,37 +2944,34 @@ doContent(XML_Parser parser, } *nextPtr = end; return XML_ERROR_NONE; - case XML_TOK_DATA_CHARS: - { - XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler; - if (charDataHandler) { - if (MUST_CONVERT(enc, s)) { - for (;;) { - ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; - const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd); - *eventEndPP = s; - charDataHandler(parser->m_handlerArg, parser->m_dataBuf, - (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) - break; - *eventPP = s; - } + case XML_TOK_DATA_CHARS: { + XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler; + if (charDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + *eventEndPP = s; + charDataHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + break; + *eventPP = s; } - else - charDataHandler(parser->m_handlerArg, - (XML_Char *)s, - (int)((XML_Char *)next - (XML_Char *)s)); - } - else if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - } - break; + } else + charDataHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)next - (XML_Char *)s)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; case XML_TOK_PI: - if (!reportProcessingInstruction(parser, enc, s, next)) + if (! reportProcessingInstruction(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_COMMENT: - if (!reportComment(parser, enc, s, next)) + if (! reportComment(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; break; default: @@ -3122,7 +2994,7 @@ doContent(XML_Parser parser, return XML_ERROR_NONE; case XML_FINISHED: return XML_ERROR_ABORTED; - default: ; + default:; } } /* not reached */ @@ -3133,8 +3005,7 @@ doContent(XML_Parser parser, * reused as appropriate. */ static void -freeBindings(XML_Parser parser, BINDING *bindings) -{ +freeBindings(XML_Parser parser, BINDING *bindings) { while (bindings) { BINDING *b = bindings; @@ -3142,7 +3013,7 @@ freeBindings(XML_Parser parser, BINDING *bindings) * binding in addBindings(), so call the end handler now. */ if (parser->m_endNamespaceDeclHandler) - parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name); + parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name); bindings = bindings->nextTagBinding; b->nextTagBinding = parser->m_freeBindingList; @@ -3162,14 +3033,12 @@ freeBindings(XML_Parser parser, BINDING *bindings) - generate namespace aware element name (URI, prefix) */ static enum XML_Error -storeAtts(XML_Parser parser, const ENCODING *enc, - const char *attStr, TAG_NAME *tagNamePtr, - BINDING **bindingsPtr) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, + TAG_NAME *tagNamePtr, BINDING **bindingsPtr) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ ELEMENT_TYPE *elementType; int nDefaultAtts; - const XML_Char **appAtts; /* the attribute list for the application */ + const XML_Char **appAtts; /* the attribute list for the application */ int attIndex = 0; int prefixLen; int i; @@ -3180,16 +3049,17 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const XML_Char *localPart; /* lookup the element type name */ - elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, tagNamePtr->str,0); - if (!elementType) { + elementType + = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, tagNamePtr->str, 0); + if (! elementType) { const XML_Char *name = poolCopyString(&dtd->pool, tagNamePtr->str); - if (!name) + if (! name) return XML_ERROR_NO_MEMORY; elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, name, sizeof(ELEMENT_TYPE)); - if (!elementType) + if (! elementType) return XML_ERROR_NO_MEMORY; - if (parser->m_ns && !setElementTypePrefix(parser, elementType)) + if (parser->m_ns && ! setElementTypePrefix(parser, elementType)) return XML_ERROR_NO_MEMORY; } nDefaultAtts = elementType->nDefaultAtts; @@ -3203,14 +3073,16 @@ storeAtts(XML_Parser parser, const ENCODING *enc, XML_AttrInfo *temp2; #endif parser->m_attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; - temp = (ATTRIBUTE *)REALLOC(parser, (void *)parser->m_atts, parser->m_attsSize * sizeof(ATTRIBUTE)); + temp = (ATTRIBUTE *)REALLOC(parser, (void *)parser->m_atts, + parser->m_attsSize * sizeof(ATTRIBUTE)); if (temp == NULL) { parser->m_attsSize = oldAttsSize; return XML_ERROR_NO_MEMORY; } parser->m_atts = temp; #ifdef XML_ATTR_INFO - temp2 = (XML_AttrInfo *)REALLOC(parser, (void *)parser->m_attInfo, parser->m_attsSize * sizeof(XML_AttrInfo)); + temp2 = (XML_AttrInfo *)REALLOC(parser, (void *)parser->m_attInfo, + parser->m_attsSize * sizeof(XML_AttrInfo)); if (temp2 == NULL) { parser->m_attsSize = oldAttsSize; return XML_ERROR_NO_MEMORY; @@ -3228,18 +3100,20 @@ storeAtts(XML_Parser parser, const ENCODING *enc, XML_AttrInfo *currAttInfo = &parser->m_attInfo[i]; #endif /* add the name and value to the attribute list */ - ATTRIBUTE_ID *attId = getAttributeId(parser, enc, currAtt->name, - currAtt->name - + XmlNameLength(enc, currAtt->name)); - if (!attId) + ATTRIBUTE_ID *attId + = getAttributeId(parser, enc, currAtt->name, + currAtt->name + XmlNameLength(enc, currAtt->name)); + if (! attId) return XML_ERROR_NO_MEMORY; #ifdef XML_ATTR_INFO - currAttInfo->nameStart = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->name); - currAttInfo->nameEnd = currAttInfo->nameStart + - XmlNameLength(enc, currAtt->name); - currAttInfo->valueStart = parser->m_parseEndByteIndex - - (parser->m_parseEndPtr - currAtt->valuePtr); - currAttInfo->valueEnd = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->valueEnd); + currAttInfo->nameStart + = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->name); + currAttInfo->nameEnd + = currAttInfo->nameStart + XmlNameLength(enc, currAtt->name); + currAttInfo->valueStart = parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - currAtt->valuePtr); + currAttInfo->valueEnd = parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - currAtt->valueEnd); #endif /* Detect duplicate attributes by their QNames. This does not work when namespace processing is turned on and different prefixes for the same @@ -3252,7 +3126,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc, } (attId->name)[-1] = 1; appAtts[attIndex++] = attId->name; - if (!parser->m_atts[i].normalized) { + if (! parser->m_atts[i].normalized) { enum XML_Error result; XML_Bool isCdata = XML_TRUE; @@ -3268,17 +3142,17 @@ storeAtts(XML_Parser parser, const ENCODING *enc, } /* normalize the attribute value */ - result = storeAttributeValue(parser, enc, isCdata, - parser->m_atts[i].valuePtr, parser->m_atts[i].valueEnd, - &parser->m_tempPool); + result = storeAttributeValue( + parser, enc, isCdata, parser->m_atts[i].valuePtr, + parser->m_atts[i].valueEnd, &parser->m_tempPool); if (result) return result; appAtts[attIndex] = poolStart(&parser->m_tempPool); poolFinish(&parser->m_tempPool); - } - else { + } else { /* the value did not need normalizing */ - appAtts[attIndex] = poolStoreString(&parser->m_tempPool, enc, parser->m_atts[i].valuePtr, + appAtts[attIndex] = poolStoreString(&parser->m_tempPool, enc, + parser->m_atts[i].valuePtr, parser->m_atts[i].valueEnd); if (appAtts[attIndex] == 0) return XML_ERROR_NO_MEMORY; @@ -3293,15 +3167,13 @@ storeAtts(XML_Parser parser, const ENCODING *enc, if (result) return result; --attIndex; - } - else { + } else { /* deal with other prefixed names later */ attIndex++; nPrefixes++; (attId->name)[-1] = 2; } - } - else + } else attIndex++; } @@ -3313,29 +3185,26 @@ storeAtts(XML_Parser parser, const ENCODING *enc, parser->m_idAttIndex = i; break; } - } - else + } else parser->m_idAttIndex = -1; /* do attribute defaulting */ for (i = 0; i < nDefaultAtts; i++) { const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + i; - if (!(da->id->name)[-1] && da->value) { + if (! (da->id->name)[-1] && da->value) { if (da->id->prefix) { if (da->id->xmlns) { enum XML_Error result = addBinding(parser, da->id->prefix, da->id, da->value, bindingsPtr); if (result) return result; - } - else { + } else { (da->id->name)[-1] = 2; nPrefixes++; appAtts[attIndex++] = da->id->name; appAtts[attIndex++] = da->value; } - } - else { + } else { (da->id->name)[-1] = 1; appAtts[attIndex++] = da->id->name; appAtts[attIndex++] = da->value; @@ -3348,31 +3217,34 @@ storeAtts(XML_Parser parser, const ENCODING *enc, and clear flags that say whether attributes were specified */ i = 0; if (nPrefixes) { - int j; /* hash table index */ + int j; /* hash table index */ unsigned long version = parser->m_nsAttsVersion; int nsAttsSize = (int)1 << parser->m_nsAttsPower; unsigned char oldNsAttsPower = parser->m_nsAttsPower; /* size of hash table must be at least 2 * (# of prefixed attributes) */ - if ((nPrefixes << 1) >> parser->m_nsAttsPower) { /* true for m_nsAttsPower = 0 */ + if ((nPrefixes << 1) + >> parser->m_nsAttsPower) { /* true for m_nsAttsPower = 0 */ NS_ATT *temp; /* hash table size must also be a power of 2 and >= 8 */ - while (nPrefixes >> parser->m_nsAttsPower++); + while (nPrefixes >> parser->m_nsAttsPower++) + ; if (parser->m_nsAttsPower < 3) parser->m_nsAttsPower = 3; nsAttsSize = (int)1 << parser->m_nsAttsPower; - temp = (NS_ATT *)REALLOC(parser, parser->m_nsAtts, nsAttsSize * sizeof(NS_ATT)); - if (!temp) { + temp = (NS_ATT *)REALLOC(parser, parser->m_nsAtts, + nsAttsSize * sizeof(NS_ATT)); + if (! temp) { /* Restore actual size of memory in m_nsAtts */ parser->m_nsAttsPower = oldNsAttsPower; return XML_ERROR_NO_MEMORY; } parser->m_nsAtts = temp; - version = 0; /* force re-initialization of m_nsAtts hash table */ + version = 0; /* force re-initialization of m_nsAtts hash table */ } /* using a version flag saves us from initializing m_nsAtts every time */ - if (!version) { /* initialize version flags when version wraps around */ + if (! version) { /* initialize version flags when version wraps around */ version = INIT_ATTS_VERSION; - for (j = nsAttsSize; j != 0; ) + for (j = nsAttsSize; j != 0;) parser->m_nsAtts[--j].version = version; } parser->m_nsAttsVersion = --version; @@ -3380,7 +3252,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc, /* expand prefixed names and check for duplicates */ for (; i < attIndex; i += 2) { const XML_Char *s = appAtts[i]; - if (s[-1] == 2) { /* prefixed */ + if (s[-1] == 2) { /* prefixed */ ATTRIBUTE_ID *id; const BINDING *b; unsigned long uriHash; @@ -3390,9 +3262,9 @@ storeAtts(XML_Parser parser, const ENCODING *enc, copy_salt_to_sipkey(parser, &sip_key); sip24_init(&sip_state, &sip_key); - ((XML_Char *)s)[-1] = 0; /* clear flag */ + ((XML_Char *)s)[-1] = 0; /* clear flag */ id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, s, 0); - if (!id || !id->prefix) { + if (! id || ! id->prefix) { /* This code is walking through the appAtts array, dealing * with (in this case) a prefixed attribute name. To be in * the array, the attribute must have already been bound, so @@ -3410,12 +3282,12 @@ storeAtts(XML_Parser parser, const ENCODING *enc, return XML_ERROR_NO_MEMORY; /* LCOV_EXCL_LINE */ } b = id->prefix->binding; - if (!b) + if (! b) return XML_ERROR_UNBOUND_PREFIX; for (j = 0; j < b->uriLen; j++) { const XML_Char c = b->uri[j]; - if (!poolAppendChar(&parser->m_tempPool, c)) + if (! poolAppendChar(&parser->m_tempPool, c)) return XML_ERROR_NO_MEMORY; } @@ -3426,8 +3298,8 @@ storeAtts(XML_Parser parser, const ENCODING *enc, sip24_update(&sip_state, s, keylen(s) * sizeof(XML_Char)); - do { /* copies null terminator */ - if (!poolAppendChar(&parser->m_tempPool, *s)) + do { /* copies null terminator */ + if (! poolAppendChar(&parser->m_tempPool, *s)) return XML_ERROR_NO_MEMORY; } while (*s++); @@ -3438,28 +3310,29 @@ storeAtts(XML_Parser parser, const ENCODING *enc, */ unsigned char step = 0; unsigned long mask = nsAttsSize - 1; - j = uriHash & mask; /* index into hash table */ + j = uriHash & mask; /* index into hash table */ while (parser->m_nsAtts[j].version == version) { /* for speed we compare stored hash values first */ if (uriHash == parser->m_nsAtts[j].hash) { const XML_Char *s1 = poolStart(&parser->m_tempPool); const XML_Char *s2 = parser->m_nsAtts[j].uriName; /* s1 is null terminated, but not s2 */ - for (; *s1 == *s2 && *s1 != 0; s1++, s2++); + for (; *s1 == *s2 && *s1 != 0; s1++, s2++) + ; if (*s1 == 0) return XML_ERROR_DUPLICATE_ATTRIBUTE; } - if (!step) + if (! step) step = PROBE_STEP(uriHash, mask, parser->m_nsAttsPower); j < step ? (j += nsAttsSize - step) : (j -= step); } } - if (parser->m_ns_triplets) { /* append namespace separator and prefix */ + if (parser->m_ns_triplets) { /* append namespace separator and prefix */ parser->m_tempPool.ptr[-1] = parser->m_namespaceSeparator; s = b->prefix->name; do { - if (!poolAppendChar(&parser->m_tempPool, *s)) + if (! poolAppendChar(&parser->m_tempPool, *s)) return XML_ERROR_NO_MEMORY; } while (*s++); } @@ -3474,13 +3347,12 @@ storeAtts(XML_Parser parser, const ENCODING *enc, parser->m_nsAtts[j].hash = uriHash; parser->m_nsAtts[j].uriName = s; - if (!--nPrefixes) { + if (! --nPrefixes) { i += 2; break; } - } - else /* not prefixed */ - ((XML_Char *)s)[-1] = 0; /* clear flag */ + } else /* not prefixed */ + ((XML_Char *)s)[-1] = 0; /* clear flag */ } } /* clear flags for the remaining attributes */ @@ -3489,40 +3361,38 @@ storeAtts(XML_Parser parser, const ENCODING *enc, for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding) binding->attId->name[-1] = 0; - if (!parser->m_ns) + if (! parser->m_ns) return XML_ERROR_NONE; /* expand the element type name */ if (elementType->prefix) { binding = elementType->prefix->binding; - if (!binding) + if (! binding) return XML_ERROR_UNBOUND_PREFIX; localPart = tagNamePtr->str; while (*localPart++ != XML_T(ASCII_COLON)) ; - } - else if (dtd->defaultPrefix.binding) { + } else if (dtd->defaultPrefix.binding) { binding = dtd->defaultPrefix.binding; localPart = tagNamePtr->str; - } - else + } else return XML_ERROR_NONE; prefixLen = 0; if (parser->m_ns_triplets && binding->prefix->name) { for (; binding->prefix->name[prefixLen++];) - ; /* prefixLen includes null terminator */ + ; /* prefixLen includes null terminator */ } tagNamePtr->localPart = localPart; tagNamePtr->uriLen = binding->uriLen; tagNamePtr->prefix = binding->prefix->name; tagNamePtr->prefixLen = prefixLen; for (i = 0; localPart[i++];) - ; /* i includes null terminator */ + ; /* i includes null terminator */ n = i + binding->uriLen + prefixLen; if (n > binding->uriAlloc) { TAG *p; uri = (XML_Char *)MALLOC(parser, (n + EXPAND_SPARE) * sizeof(XML_Char)); - if (!uri) + if (! uri) return XML_ERROR_NO_MEMORY; binding->uriAlloc = n + EXPAND_SPARE; memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char)); @@ -3538,7 +3408,7 @@ storeAtts(XML_Parser parser, const ENCODING *enc, /* we always have a namespace separator between localPart and prefix */ if (prefixLen) { uri += i - 1; - *uri = parser->m_namespaceSeparator; /* replace null terminator */ + *uri = parser->m_namespaceSeparator; /* replace null terminator */ memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char)); } tagNamePtr->str = binding->uri; @@ -3550,27 +3420,25 @@ storeAtts(XML_Parser parser, const ENCODING *enc, */ static enum XML_Error addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, - const XML_Char *uri, BINDING **bindingsPtr) -{ - static const XML_Char xmlNamespace[] = { - ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, - ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, - ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, - ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, ASCII_8, ASCII_SLASH, - ASCII_n, ASCII_a, ASCII_m, ASCII_e, ASCII_s, ASCII_p, ASCII_a, ASCII_c, - ASCII_e, '\0' - }; - static const int xmlLen = - (int)sizeof(xmlNamespace)/sizeof(XML_Char) - 1; - static const XML_Char xmlnsNamespace[] = { - ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, - ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, - ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, ASCII_2, ASCII_0, ASCII_0, - ASCII_0, ASCII_SLASH, ASCII_x, ASCII_m, ASCII_l, ASCII_n, ASCII_s, - ASCII_SLASH, '\0' - }; - static const int xmlnsLen = - (int)sizeof(xmlnsNamespace)/sizeof(XML_Char) - 1; + const XML_Char *uri, BINDING **bindingsPtr) { + static const XML_Char xmlNamespace[] + = {ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, + ASCII_SLASH, ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, + ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, ASCII_o, + ASCII_r, ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, + ASCII_L, ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, + ASCII_8, ASCII_SLASH, ASCII_n, ASCII_a, ASCII_m, + ASCII_e, ASCII_s, ASCII_p, ASCII_a, ASCII_c, + ASCII_e, '\0'}; + static const int xmlLen = (int)sizeof(xmlNamespace) / sizeof(XML_Char) - 1; + static const XML_Char xmlnsNamespace[] + = {ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, + ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, + ASCII_3, ASCII_PERIOD, ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, + ASCII_2, ASCII_0, ASCII_0, ASCII_0, ASCII_SLASH, ASCII_x, + ASCII_m, ASCII_l, ASCII_n, ASCII_s, ASCII_SLASH, '\0'}; + static const int xmlnsLen + = (int)sizeof(xmlnsNamespace) / sizeof(XML_Char) - 1; XML_Bool mustBeXML = XML_FALSE; XML_Bool isXML = XML_TRUE; @@ -3583,14 +3451,11 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (*uri == XML_T('\0') && prefix->name) return XML_ERROR_UNDECLARING_PREFIX; - if (prefix->name - && prefix->name[0] == XML_T(ASCII_x) + if (prefix->name && prefix->name[0] == XML_T(ASCII_x) && prefix->name[1] == XML_T(ASCII_m) && prefix->name[2] == XML_T(ASCII_l)) { - /* Not allowed to bind xmlns */ - if (prefix->name[3] == XML_T(ASCII_n) - && prefix->name[4] == XML_T(ASCII_s) + if (prefix->name[3] == XML_T(ASCII_n) && prefix->name[4] == XML_T(ASCII_s) && prefix->name[5] == XML_T('\0')) return XML_ERROR_RESERVED_PREFIX_XMLNS; @@ -3602,7 +3467,7 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (isXML && (len > xmlLen || uri[len] != xmlNamespace[len])) isXML = XML_FALSE; - if (!mustBeXML && isXMLNS + if (! mustBeXML && isXMLNS && (len > xmlnsLen || uri[len] != xmlnsNamespace[len])) isXMLNS = XML_FALSE; } @@ -3621,21 +3486,21 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (parser->m_freeBindingList) { b = parser->m_freeBindingList; if (len > b->uriAlloc) { - XML_Char *temp = (XML_Char *)REALLOC(parser, b->uri, - sizeof(XML_Char) * (len + EXPAND_SPARE)); + XML_Char *temp = (XML_Char *)REALLOC( + parser, b->uri, sizeof(XML_Char) * (len + EXPAND_SPARE)); if (temp == NULL) return XML_ERROR_NO_MEMORY; b->uri = temp; b->uriAlloc = len + EXPAND_SPARE; } parser->m_freeBindingList = b->nextTagBinding; - } - else { + } else { b = (BINDING *)MALLOC(parser, sizeof(BINDING)); - if (!b) + if (! b) return XML_ERROR_NO_MEMORY; - b->uri = (XML_Char *)MALLOC(parser, sizeof(XML_Char) * (len + EXPAND_SPARE)); - if (!b->uri) { + b->uri + = (XML_Char *)MALLOC(parser, sizeof(XML_Char) * (len + EXPAND_SPARE)); + if (! b->uri) { FREE(parser, b); return XML_ERROR_NO_MEMORY; } @@ -3658,7 +3523,7 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, /* if attId == NULL then we are not starting a namespace scope */ if (attId && parser->m_startNamespaceDeclHandler) parser->m_startNamespaceDeclHandler(parser->m_handlerArg, prefix->name, - prefix->binding ? uri : 0); + prefix->binding ? uri : 0); return XML_ERROR_NONE; } @@ -3666,21 +3531,18 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, the whole file is parsed with one call. */ static enum XML_Error PTRCALL -cdataSectionProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doCdataSection(parser, parser->m_encoding, &start, end, - endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer); +cdataSectionProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result + = doCdataSection(parser, parser->m_encoding, &start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); if (result != XML_ERROR_NONE) return result; if (start) { - if (parser->m_parentParser) { /* we are parsing an external entity */ + if (parser->m_parentParser) { /* we are parsing an external entity */ parser->m_processor = externalEntityContentProcessor; return externalEntityContentProcessor(parser, start, end, endPtr); - } - else { + } else { parser->m_processor = contentProcessor; return contentProcessor(parser, start, end, endPtr); } @@ -3692,13 +3554,8 @@ cdataSectionProcessor(XML_Parser parser, the section is not yet closed. */ static enum XML_Error -doCdataSection(XML_Parser parser, - const ENCODING *enc, - const char **startPtr, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ +doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, + const char *end, const char **nextPtr, XML_Bool haveMore) { const char *s = *startPtr; const char **eventPP; const char **eventEndPP; @@ -3706,8 +3563,7 @@ doCdataSection(XML_Parser parser, eventPP = &parser->m_eventPtr; *eventPP = s; eventEndPP = &parser->m_eventEndPtr; - } - else { + } else { eventPP = &(parser->m_openInternalEntities->internalEventPtr); eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); } @@ -3722,11 +3578,12 @@ doCdataSection(XML_Parser parser, case XML_TOK_CDATA_SECT_CLOSE: if (parser->m_endCdataSectionHandler) parser->m_endCdataSectionHandler(parser->m_handlerArg); -/* BEGIN disabled code */ + /* BEGIN disabled code */ /* see comment under XML_TOK_CDATA_SECT_OPEN */ else if (0 && parser->m_characterDataHandler) - parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, 0); -/* END disabled code */ + parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, + 0); + /* END disabled code */ else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); *startPtr = next; @@ -3739,35 +3596,31 @@ doCdataSection(XML_Parser parser, if (parser->m_characterDataHandler) { XML_Char c = 0xA; parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); - } - else if (parser->m_defaultHandler) + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); break; - case XML_TOK_DATA_CHARS: - { - XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler; - if (charDataHandler) { - if (MUST_CONVERT(enc, s)) { - for (;;) { - ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; - const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd); - *eventEndPP = next; - charDataHandler(parser->m_handlerArg, parser->m_dataBuf, - (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) - break; - *eventPP = s; - } + case XML_TOK_DATA_CHARS: { + XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler; + if (charDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + *eventEndPP = next; + charDataHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + break; + *eventPP = s; } - else - charDataHandler(parser->m_handlerArg, - (XML_Char *)s, - (int)((XML_Char *)next - (XML_Char *)s)); - } - else if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - } - break; + } else + charDataHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)next - (XML_Char *)s)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; case XML_TOK_INVALID: *eventPP = next; return XML_ERROR_INVALID_TOKEN; @@ -3791,7 +3644,7 @@ doCdataSection(XML_Parser parser, * statistics. * * LCOV_EXCL_START - */ + */ *eventPP = next; return XML_ERROR_UNEXPECTED_STATE; /* LCOV_EXCL_STOP */ @@ -3804,7 +3657,7 @@ doCdataSection(XML_Parser parser, return XML_ERROR_NONE; case XML_FINISHED: return XML_ERROR_ABORTED; - default: ; + default:; } } /* not reached */ @@ -3816,13 +3669,11 @@ doCdataSection(XML_Parser parser, the whole file is parsed with one call. */ static enum XML_Error PTRCALL -ignoreSectionProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doIgnoreSection(parser, parser->m_encoding, &start, end, - endPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer); +ignoreSectionProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result + = doIgnoreSection(parser, parser->m_encoding, &start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); if (result != XML_ERROR_NONE) return result; if (start) { @@ -3836,13 +3687,8 @@ ignoreSectionProcessor(XML_Parser parser, if the section is not yet closed. */ static enum XML_Error -doIgnoreSection(XML_Parser parser, - const ENCODING *enc, - const char **startPtr, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ +doIgnoreSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, + const char *end, const char **nextPtr, XML_Bool haveMore) { const char *next; int tok; const char *s = *startPtr; @@ -3852,8 +3698,7 @@ doIgnoreSection(XML_Parser parser, eventPP = &parser->m_eventPtr; *eventPP = s; eventEndPP = &parser->m_eventEndPtr; - } - else { + } else { /* It's not entirely clear, but it seems the following two lines * of code cannot be executed. The only occasions on which 'enc' * is not 'encoding' are when this function is called @@ -3917,13 +3762,12 @@ doIgnoreSection(XML_Parser parser, #endif /* XML_DTD */ static enum XML_Error -initializeEncoding(XML_Parser parser) -{ +initializeEncoding(XML_Parser parser) { const char *s; #ifdef XML_UNICODE char encodingBuf[128]; /* See comments abount `protoclEncodingName` in parserInit() */ - if (!parser->m_protocolEncodingName) + if (! parser->m_protocolEncodingName) s = NULL; else { int i; @@ -3941,15 +3785,15 @@ initializeEncoding(XML_Parser parser) #else s = parser->m_protocolEncodingName; #endif - if ((parser->m_ns ? XmlInitEncodingNS : XmlInitEncoding)(&parser->m_initEncoding, &parser->m_encoding, s)) + if ((parser->m_ns ? XmlInitEncodingNS : XmlInitEncoding)( + &parser->m_initEncoding, &parser->m_encoding, s)) return XML_ERROR_NONE; return handleUnknownEncoding(parser, parser->m_protocolEncodingName); } static enum XML_Error -processXmlDecl(XML_Parser parser, int isGeneralTextEntity, - const char *s, const char *next) -{ +processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *s, + const char *next) { const char *encodingName = NULL; const XML_Char *storedEncName = NULL; const ENCODING *newEncoding = NULL; @@ -3957,52 +3801,41 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *versionend; const XML_Char *storedversion = NULL; int standalone = -1; - if (!(parser->m_ns - ? XmlParseXmlDeclNS - : XmlParseXmlDecl)(isGeneralTextEntity, - parser->m_encoding, - s, - next, - &parser->m_eventPtr, - &version, - &versionend, - &encodingName, - &newEncoding, - &standalone)) { + if (! (parser->m_ns ? XmlParseXmlDeclNS : XmlParseXmlDecl)( + isGeneralTextEntity, parser->m_encoding, s, next, &parser->m_eventPtr, + &version, &versionend, &encodingName, &newEncoding, &standalone)) { if (isGeneralTextEntity) return XML_ERROR_TEXT_DECL; else return XML_ERROR_XML_DECL; } - if (!isGeneralTextEntity && standalone == 1) { + if (! isGeneralTextEntity && standalone == 1) { parser->m_dtd->standalone = XML_TRUE; #ifdef XML_DTD - if (parser->m_paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE) + if (parser->m_paramEntityParsing + == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE) parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; #endif /* XML_DTD */ } if (parser->m_xmlDeclHandler) { if (encodingName != NULL) { - storedEncName = poolStoreString(&parser->m_temp2Pool, - parser->m_encoding, - encodingName, - encodingName - + XmlNameLength(parser->m_encoding, encodingName)); - if (!storedEncName) - return XML_ERROR_NO_MEMORY; + storedEncName = poolStoreString( + &parser->m_temp2Pool, parser->m_encoding, encodingName, + encodingName + XmlNameLength(parser->m_encoding, encodingName)); + if (! storedEncName) + return XML_ERROR_NO_MEMORY; poolFinish(&parser->m_temp2Pool); } if (version) { - storedversion = poolStoreString(&parser->m_temp2Pool, - parser->m_encoding, - version, - versionend - parser->m_encoding->minBytesPerChar); - if (!storedversion) + storedversion + = poolStoreString(&parser->m_temp2Pool, parser->m_encoding, version, + versionend - parser->m_encoding->minBytesPerChar); + if (! storedversion) return XML_ERROR_NO_MEMORY; } - parser->m_xmlDeclHandler(parser->m_handlerArg, storedversion, storedEncName, standalone); - } - else if (parser->m_defaultHandler) + parser->m_xmlDeclHandler(parser->m_handlerArg, storedversion, storedEncName, + standalone); + } else if (parser->m_defaultHandler) reportDefault(parser, parser->m_encoding, s, next); if (parser->m_protocolEncodingName == NULL) { if (newEncoding) { @@ -4012,20 +3845,19 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity, * this is UTF-16, is it the same endianness? */ if (newEncoding->minBytesPerChar != parser->m_encoding->minBytesPerChar - || (newEncoding->minBytesPerChar == 2 && - newEncoding != parser->m_encoding)) { + || (newEncoding->minBytesPerChar == 2 + && newEncoding != parser->m_encoding)) { parser->m_eventPtr = encodingName; return XML_ERROR_INCORRECT_ENCODING; } parser->m_encoding = newEncoding; - } - else if (encodingName) { + } else if (encodingName) { enum XML_Error result; - if (!storedEncName) { + if (! storedEncName) { storedEncName = poolStoreString( - &parser->m_temp2Pool, parser->m_encoding, encodingName, - encodingName + XmlNameLength(parser->m_encoding, encodingName)); - if (!storedEncName) + &parser->m_temp2Pool, parser->m_encoding, encodingName, + encodingName + XmlNameLength(parser->m_encoding, encodingName)); + if (! storedEncName) return XML_ERROR_NO_MEMORY; } result = handleUnknownEncoding(parser, storedEncName); @@ -4043,8 +3875,7 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity, } static enum XML_Error -handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) -{ +handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) { if (parser->m_unknownEncodingHandler) { XML_Encoding info; int i; @@ -4053,21 +3884,17 @@ handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) info.convert = NULL; info.data = NULL; info.release = NULL; - if (parser->m_unknownEncodingHandler(parser->m_unknownEncodingHandlerData, encodingName, - &info)) { + if (parser->m_unknownEncodingHandler(parser->m_unknownEncodingHandlerData, + encodingName, &info)) { ENCODING *enc; parser->m_unknownEncodingMem = MALLOC(parser, XmlSizeOfUnknownEncoding()); - if (!parser->m_unknownEncodingMem) { + if (! parser->m_unknownEncodingMem) { if (info.release) info.release(info.data); return XML_ERROR_NO_MEMORY; } - enc = (parser->m_ns - ? XmlInitUnknownEncodingNS - : XmlInitUnknownEncoding)(parser->m_unknownEncodingMem, - info.map, - info.convert, - info.data); + enc = (parser->m_ns ? XmlInitUnknownEncodingNS : XmlInitUnknownEncoding)( + parser->m_unknownEncodingMem, info.map, info.convert, info.data); if (enc) { parser->m_unknownEncodingData = info.data; parser->m_unknownEncodingRelease = info.release; @@ -4082,11 +3909,8 @@ handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) } static enum XML_Error PTRCALL -prologInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +prologInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { enum XML_Error result = initializeEncoding(parser); if (result != XML_ERROR_NONE) return result; @@ -4097,11 +3921,8 @@ prologInitProcessor(XML_Parser parser, #ifdef XML_DTD static enum XML_Error PTRCALL -externalParEntInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +externalParEntInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { enum XML_Error result = initializeEncoding(parser); if (result != XML_ERROR_NONE) return result; @@ -4113,19 +3934,15 @@ externalParEntInitProcessor(XML_Parser parser, if (parser->m_prologState.inEntityValue) { parser->m_processor = entityValueInitProcessor; return entityValueInitProcessor(parser, s, end, nextPtr); - } - else { + } else { parser->m_processor = externalParEntProcessor; return externalParEntProcessor(parser, s, end, nextPtr); } } static enum XML_Error PTRCALL -entityValueInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +entityValueInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { int tok; const char *start = s; const char *next = start; @@ -4135,7 +3952,7 @@ entityValueInitProcessor(XML_Parser parser, tok = XmlPrologTok(parser->m_encoding, start, end, &next); parser->m_eventEndPtr = next; if (tok <= 0) { - if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -4146,22 +3963,21 @@ entityValueInitProcessor(XML_Parser parser, return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ + case XML_TOK_NONE: /* start == end */ default: break; } /* found end of entity value - can store it now */ return storeEntityValue(parser, parser->m_encoding, s, end); - } - else if (tok == XML_TOK_XML_DECL) { + } else if (tok == XML_TOK_XML_DECL) { enum XML_Error result; result = processXmlDecl(parser, 0, start, next); if (result != XML_ERROR_NONE) return result; - /* At this point, m_parsingStatus.parsing cannot be XML_SUSPENDED. For that - * to happen, a parameter entity parsing handler must have - * attempted to suspend the parser, which fails and raises an - * error. The parser can be aborted, but can't be suspended. + /* At this point, m_parsingStatus.parsing cannot be XML_SUSPENDED. For + * that to happen, a parameter entity parsing handler must have attempted + * to suspend the parser, which fails and raises an error. The parser can + * be aborted, but can't be suspended. */ if (parser->m_parsingStatus.parsing == XML_FINISHED) return XML_ERROR_ABORTED; @@ -4177,7 +3993,8 @@ entityValueInitProcessor(XML_Parser parser, then, when this routine is entered the next time, XmlPrologTok will return XML_TOK_INVALID, since the BOM is still in the buffer */ - else if (tok == XML_TOK_BOM && next == end && !parser->m_parsingStatus.finalBuffer) { + else if (tok == XML_TOK_BOM && next == end + && ! parser->m_parsingStatus.finalBuffer) { *nextPtr = next; return XML_ERROR_NONE; } @@ -4195,17 +4012,14 @@ entityValueInitProcessor(XML_Parser parser, } static enum XML_Error PTRCALL -externalParEntProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +externalParEntProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { const char *next = s; int tok; tok = XmlPrologTok(parser->m_encoding, s, end, &next); if (tok <= 0) { - if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -4216,7 +4030,7 @@ externalParEntProcessor(XML_Parser parser, return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ + case XML_TOK_NONE: /* start == end */ default: break; } @@ -4231,16 +4045,13 @@ externalParEntProcessor(XML_Parser parser, } parser->m_processor = prologProcessor; - return doProlog(parser, parser->m_encoding, s, end, tok, next, - nextPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer); + return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); } static enum XML_Error PTRCALL -entityValueProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +entityValueProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { const char *start = s; const char *next = s; const ENCODING *enc = parser->m_encoding; @@ -4249,7 +4060,7 @@ entityValueProcessor(XML_Parser parser, for (;;) { tok = XmlPrologTok(enc, start, end, &next); if (tok <= 0) { - if (!parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -4260,7 +4071,7 @@ entityValueProcessor(XML_Parser parser, return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ + case XML_TOK_NONE: /* start == end */ default: break; } @@ -4274,52 +4085,46 @@ entityValueProcessor(XML_Parser parser, #endif /* XML_DTD */ static enum XML_Error PTRCALL -prologProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +prologProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { const char *next = s; int tok = XmlPrologTok(parser->m_encoding, s, end, &next); - return doProlog(parser, parser->m_encoding, s, end, tok, next, - nextPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer); + return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); } static enum XML_Error -doProlog(XML_Parser parser, - const ENCODING *enc, - const char *s, - const char *end, - int tok, - const char *next, - const char **nextPtr, - XML_Bool haveMore) -{ +doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, + int tok, const char *next, const char **nextPtr, XML_Bool haveMore, + XML_Bool allowClosingDoctype) { #ifdef XML_DTD - static const XML_Char externalSubsetName[] = { ASCII_HASH , '\0' }; + static const XML_Char externalSubsetName[] = {ASCII_HASH, '\0'}; #endif /* XML_DTD */ - static const XML_Char atypeCDATA[] = - { ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; - static const XML_Char atypeID[] = { ASCII_I, ASCII_D, '\0' }; - static const XML_Char atypeIDREF[] = - { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' }; - static const XML_Char atypeIDREFS[] = - { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' }; - static const XML_Char atypeENTITY[] = - { ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' }; - static const XML_Char atypeENTITIES[] = { ASCII_E, ASCII_N, - ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, '\0' }; - static const XML_Char atypeNMTOKEN[] = { - ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' }; - static const XML_Char atypeNMTOKENS[] = { ASCII_N, ASCII_M, ASCII_T, - ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, '\0' }; - static const XML_Char notationPrefix[] = { ASCII_N, ASCII_O, ASCII_T, - ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, ASCII_LPAREN, '\0' }; - static const XML_Char enumValueSep[] = { ASCII_PIPE, '\0' }; - static const XML_Char enumValueStart[] = { ASCII_LPAREN, '\0' }; + static const XML_Char atypeCDATA[] + = {ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; + static const XML_Char atypeID[] = {ASCII_I, ASCII_D, '\0'}; + static const XML_Char atypeIDREF[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0'}; + static const XML_Char atypeIDREFS[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0'}; + static const XML_Char atypeENTITY[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0'}; + static const XML_Char atypeENTITIES[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, + ASCII_I, ASCII_E, ASCII_S, '\0'}; + static const XML_Char atypeNMTOKEN[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0'}; + static const XML_Char atypeNMTOKENS[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, + ASCII_E, ASCII_N, ASCII_S, '\0'}; + static const XML_Char notationPrefix[] + = {ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, + ASCII_I, ASCII_O, ASCII_N, ASCII_LPAREN, '\0'}; + static const XML_Char enumValueSep[] = {ASCII_PIPE, '\0'}; + static const XML_Char enumValueStart[] = {ASCII_LPAREN, '\0'}; /* save one level of indirection */ - DTD * const dtd = parser->m_dtd; + DTD *const dtd = parser->m_dtd; const char **eventPP; const char **eventEndPP; @@ -4328,8 +4133,7 @@ doProlog(XML_Parser parser, if (enc == parser->m_encoding) { eventPP = &parser->m_eventPtr; eventEndPP = &parser->m_eventEndPtr; - } - else { + } else { eventPP = &(parser->m_openInternalEntities->internalEventPtr); eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); } @@ -4358,7 +4162,8 @@ doProlog(XML_Parser parser, case XML_TOK_NONE: #ifdef XML_DTD /* for internal PE NOT referenced between declarations */ - if (enc != parser->m_encoding && !parser->m_openInternalEntities->betweenDecl) { + if (enc != parser->m_encoding + && ! parser->m_openInternalEntities->betweenDecl) { *nextPtr = s; return XML_ERROR_NONE; } @@ -4383,19 +4188,18 @@ doProlog(XML_Parser parser, } role = XmlTokenRole(&parser->m_prologState, tok, s, next, enc); switch (role) { - case XML_ROLE_XML_DECL: - { - enum XML_Error result = processXmlDecl(parser, 0, s, next); - if (result != XML_ERROR_NONE) - return result; - enc = parser->m_encoding; - handleDefault = XML_FALSE; - } - break; + case XML_ROLE_XML_DECL: { + enum XML_Error result = processXmlDecl(parser, 0, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = parser->m_encoding; + handleDefault = XML_FALSE; + } break; case XML_ROLE_DOCTYPE_NAME: if (parser->m_startDoctypeDeclHandler) { - parser->m_doctypeName = poolStoreString(&parser->m_tempPool, enc, s, next); - if (!parser->m_doctypeName) + parser->m_doctypeName + = poolStoreString(&parser->m_tempPool, enc, s, next); + if (! parser->m_doctypeName) return XML_ERROR_NO_MEMORY; poolFinish(&parser->m_tempPool); parser->m_doctypePubid = NULL; @@ -4405,43 +4209,40 @@ doProlog(XML_Parser parser, break; case XML_ROLE_DOCTYPE_INTERNAL_SUBSET: if (parser->m_startDoctypeDeclHandler) { - parser->m_startDoctypeDeclHandler(parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid, - parser->m_doctypePubid, 1); + parser->m_startDoctypeDeclHandler( + parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid, + parser->m_doctypePubid, 1); parser->m_doctypeName = NULL; poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } break; #ifdef XML_DTD - case XML_ROLE_TEXT_DECL: - { - enum XML_Error result = processXmlDecl(parser, 1, s, next); - if (result != XML_ERROR_NONE) - return result; - enc = parser->m_encoding; - handleDefault = XML_FALSE; - } - break; + case XML_ROLE_TEXT_DECL: { + enum XML_Error result = processXmlDecl(parser, 1, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = parser->m_encoding; + handleDefault = XML_FALSE; + } break; #endif /* XML_DTD */ case XML_ROLE_DOCTYPE_PUBLIC_ID: #ifdef XML_DTD parser->m_useForeignDTD = XML_FALSE; - parser->m_declEntity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!parser->m_declEntity) + parser->m_declEntity = (ENTITY *)lookup( + parser, &dtd->paramEntities, externalSubsetName, sizeof(ENTITY)); + if (! parser->m_declEntity) return XML_ERROR_NO_MEMORY; #endif /* XML_DTD */ dtd->hasParamEntityRefs = XML_TRUE; if (parser->m_startDoctypeDeclHandler) { XML_Char *pubId; - if (!XmlIsPublicId(enc, s, next, eventPP)) + if (! XmlIsPublicId(enc, s, next, eventPP)) return XML_ERROR_PUBLICID; pubId = poolStoreString(&parser->m_tempPool, enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); - if (!pubId) + if (! pubId) return XML_ERROR_NO_MEMORY; normalizePublicId(pubId); poolFinish(&parser->m_tempPool); @@ -4451,15 +4252,14 @@ doProlog(XML_Parser parser, } /* fall through */ case XML_ROLE_ENTITY_PUBLIC_ID: - if (!XmlIsPublicId(enc, s, next, eventPP)) + if (! XmlIsPublicId(enc, s, next, eventPP)) return XML_ERROR_PUBLICID; alreadyChecked: if (dtd->keepProcessing && parser->m_declEntity) { - XML_Char *tem = poolStoreString(&dtd->pool, - enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!tem) + XML_Char *tem + = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! tem) return XML_ERROR_NO_MEMORY; normalizePublicId(tem); parser->m_declEntity->publicId = tem; @@ -4472,9 +4272,15 @@ doProlog(XML_Parser parser, } break; case XML_ROLE_DOCTYPE_CLOSE: + if (allowClosingDoctype != XML_TRUE) { + /* Must not close doctype from within expanded parameter entities */ + return XML_ERROR_INVALID_TOKEN; + } + if (parser->m_doctypeName) { - parser->m_startDoctypeDeclHandler(parser->m_handlerArg, parser->m_doctypeName, - parser->m_doctypeSysid, parser->m_doctypePubid, 0); + parser->m_startDoctypeDeclHandler( + parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid, + parser->m_doctypePubid, 0); poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } @@ -4486,12 +4292,11 @@ doProlog(XML_Parser parser, if (parser->m_doctypeSysid || parser->m_useForeignDTD) { XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; dtd->hasParamEntityRefs = XML_TRUE; - if (parser->m_paramEntityParsing && parser->m_externalEntityRefHandler) { - ENTITY *entity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!entity) { + if (parser->m_paramEntityParsing + && parser->m_externalEntityRefHandler) { + ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities, + externalSubsetName, sizeof(ENTITY)); + if (! entity) { /* The external subset name "#" will have already been * inserted into the hash table at the start of the * external entity parsing, so no allocation will happen @@ -4502,22 +4307,19 @@ doProlog(XML_Parser parser, if (parser->m_useForeignDTD) entity->base = parser->m_curBase; dtd->paramEntityRead = XML_FALSE; - if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) return XML_ERROR_EXTERNAL_ENTITY_HANDLING; if (dtd->paramEntityRead) { - if (!dtd->standalone && - parser->m_notStandaloneHandler && - !parser->m_notStandaloneHandler(parser->m_handlerArg)) + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) return XML_ERROR_NOT_STANDALONE; } /* if we didn't read the foreign DTD then this means that there is no external subset and we must reset dtd->hasParamEntityRefs */ - else if (!parser->m_doctypeSysid) + else if (! parser->m_doctypeSysid) dtd->hasParamEntityRefs = hadParamEntityRefs; /* end of DTD - no need to update dtd->keepProcessing */ } @@ -4537,24 +4339,21 @@ doProlog(XML_Parser parser, if (parser->m_useForeignDTD) { XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; dtd->hasParamEntityRefs = XML_TRUE; - if (parser->m_paramEntityParsing && parser->m_externalEntityRefHandler) { + if (parser->m_paramEntityParsing + && parser->m_externalEntityRefHandler) { ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!entity) + externalSubsetName, sizeof(ENTITY)); + if (! entity) return XML_ERROR_NO_MEMORY; entity->base = parser->m_curBase; dtd->paramEntityRead = XML_FALSE; - if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) return XML_ERROR_EXTERNAL_ENTITY_HANDLING; if (dtd->paramEntityRead) { - if (!dtd->standalone && - parser->m_notStandaloneHandler && - !parser->m_notStandaloneHandler(parser->m_handlerArg)) + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) return XML_ERROR_NOT_STANDALONE; } /* if we didn't read the foreign DTD then this means that there @@ -4570,12 +4369,12 @@ doProlog(XML_Parser parser, return contentProcessor(parser, s, end, nextPtr); case XML_ROLE_ATTLIST_ELEMENT_NAME: parser->m_declElementType = getElementType(parser, enc, s, next); - if (!parser->m_declElementType) + if (! parser->m_declElementType) return XML_ERROR_NO_MEMORY; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_NAME: parser->m_declAttributeId = getAttributeId(parser, enc, s, next); - if (!parser->m_declAttributeId) + if (! parser->m_declAttributeId) return XML_ERROR_NO_MEMORY; parser->m_declAttributeIsCdata = XML_FALSE; parser->m_declAttributeType = NULL; @@ -4616,15 +4415,13 @@ doProlog(XML_Parser parser, const XML_Char *prefix; if (parser->m_declAttributeType) { prefix = enumValueSep; + } else { + prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE ? notationPrefix + : enumValueStart); } - else { - prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE - ? notationPrefix - : enumValueStart); - } - if (!poolAppendString(&parser->m_tempPool, prefix)) + if (! poolAppendString(&parser->m_tempPool, prefix)) return XML_ERROR_NO_MEMORY; - if (!poolAppend(&parser->m_tempPool, enc, s, next)) + if (! poolAppend(&parser->m_tempPool, enc, s, next)) return XML_ERROR_NO_MEMORY; parser->m_declAttributeType = parser->m_tempPool.start; handleDefault = XML_FALSE; @@ -4633,25 +4430,27 @@ doProlog(XML_Parser parser, case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE: case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE: if (dtd->keepProcessing) { - if (!defineAttribute(parser->m_declElementType, parser->m_declAttributeId, - parser->m_declAttributeIsCdata, parser->m_declAttributeIsId, - 0, parser)) + if (! defineAttribute(parser->m_declElementType, + parser->m_declAttributeId, + parser->m_declAttributeIsCdata, + parser->m_declAttributeIsId, 0, parser)) return XML_ERROR_NO_MEMORY; if (parser->m_attlistDeclHandler && parser->m_declAttributeType) { if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN) || (*parser->m_declAttributeType == XML_T(ASCII_N) && parser->m_declAttributeType[1] == XML_T(ASCII_O))) { /* Enumerated or Notation type */ - if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN)) - || !poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN)) + || ! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_ERROR_NO_MEMORY; parser->m_declAttributeType = parser->m_tempPool.start; poolFinish(&parser->m_tempPool); } *eventEndPP = s; - parser->m_attlistDeclHandler(parser->m_handlerArg, parser->m_declElementType->name, - parser->m_declAttributeId->name, parser->m_declAttributeType, - 0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); + parser->m_attlistDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, + parser->m_declAttributeId->name, parser->m_declAttributeType, 0, + role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } @@ -4661,35 +4460,34 @@ doProlog(XML_Parser parser, case XML_ROLE_FIXED_ATTRIBUTE_VALUE: if (dtd->keepProcessing) { const XML_Char *attVal; - enum XML_Error result = - storeAttributeValue(parser, enc, parser->m_declAttributeIsCdata, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar, - &dtd->pool); + enum XML_Error result = storeAttributeValue( + parser, enc, parser->m_declAttributeIsCdata, + s + enc->minBytesPerChar, next - enc->minBytesPerChar, &dtd->pool); if (result) return result; attVal = poolStart(&dtd->pool); poolFinish(&dtd->pool); /* ID attributes aren't allowed to have a default */ - if (!defineAttribute(parser->m_declElementType, parser->m_declAttributeId, - parser->m_declAttributeIsCdata, XML_FALSE, attVal, parser)) + if (! defineAttribute( + parser->m_declElementType, parser->m_declAttributeId, + parser->m_declAttributeIsCdata, XML_FALSE, attVal, parser)) return XML_ERROR_NO_MEMORY; if (parser->m_attlistDeclHandler && parser->m_declAttributeType) { if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN) || (*parser->m_declAttributeType == XML_T(ASCII_N) && parser->m_declAttributeType[1] == XML_T(ASCII_O))) { /* Enumerated or Notation type */ - if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN)) - || !poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN)) + || ! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_ERROR_NO_MEMORY; parser->m_declAttributeType = parser->m_tempPool.start; poolFinish(&parser->m_tempPool); } *eventEndPP = s; - parser->m_attlistDeclHandler(parser->m_handlerArg, parser->m_declElementType->name, - parser->m_declAttributeId->name, parser->m_declAttributeType, - attVal, - role == XML_ROLE_FIXED_ATTRIBUTE_VALUE); + parser->m_attlistDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, + parser->m_declAttributeId->name, parser->m_declAttributeType, + attVal, role == XML_ROLE_FIXED_ATTRIBUTE_VALUE); poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } @@ -4697,25 +4495,22 @@ doProlog(XML_Parser parser, break; case XML_ROLE_ENTITY_VALUE: if (dtd->keepProcessing) { - enum XML_Error result = storeEntityValue(parser, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); + enum XML_Error result = storeEntityValue( + parser, enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); if (parser->m_declEntity) { parser->m_declEntity->textPtr = poolStart(&dtd->entityValuePool); - parser->m_declEntity->textLen = (int)(poolLength(&dtd->entityValuePool)); + parser->m_declEntity->textLen + = (int)(poolLength(&dtd->entityValuePool)); poolFinish(&dtd->entityValuePool); if (parser->m_entityDeclHandler) { *eventEndPP = s; - parser->m_entityDeclHandler(parser->m_handlerArg, - parser->m_declEntity->name, - parser->m_declEntity->is_param, - parser->m_declEntity->textPtr, - parser->m_declEntity->textLen, - parser->m_curBase, 0, 0, 0); + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->is_param, parser->m_declEntity->textPtr, + parser->m_declEntity->textLen, parser->m_curBase, 0, 0, 0); handleDefault = XML_FALSE; } - } - else + } else poolDiscard(&dtd->entityValuePool); if (result != XML_ERROR_NONE) return result; @@ -4728,8 +4523,8 @@ doProlog(XML_Parser parser, dtd->hasParamEntityRefs = XML_TRUE; if (parser->m_startDoctypeDeclHandler) { parser->m_doctypeSysid = poolStoreString(&parser->m_tempPool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); if (parser->m_doctypeSysid == NULL) return XML_ERROR_NO_MEMORY; poolFinish(&parser->m_tempPool); @@ -4741,22 +4536,20 @@ doProlog(XML_Parser parser, for the case where no parser->m_startDoctypeDeclHandler is set */ parser->m_doctypeSysid = externalSubsetName; #endif /* XML_DTD */ - if (!dtd->standalone + if (! dtd->standalone #ifdef XML_DTD - && !parser->m_paramEntityParsing + && ! parser->m_paramEntityParsing #endif /* XML_DTD */ && parser->m_notStandaloneHandler - && !parser->m_notStandaloneHandler(parser->m_handlerArg)) + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) return XML_ERROR_NOT_STANDALONE; #ifndef XML_DTD break; -#else /* XML_DTD */ - if (!parser->m_declEntity) { - parser->m_declEntity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!parser->m_declEntity) +#else /* XML_DTD */ + if (! parser->m_declEntity) { + parser->m_declEntity = (ENTITY *)lookup( + parser, &dtd->paramEntities, externalSubsetName, sizeof(ENTITY)); + if (! parser->m_declEntity) return XML_ERROR_NO_MEMORY; parser->m_declEntity->publicId = NULL; } @@ -4764,10 +4557,10 @@ doProlog(XML_Parser parser, /* fall through */ case XML_ROLE_ENTITY_SYSTEM_ID: if (dtd->keepProcessing && parser->m_declEntity) { - parser->m_declEntity->systemId = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!parser->m_declEntity->systemId) + parser->m_declEntity->systemId + = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! parser->m_declEntity->systemId) return XML_ERROR_NO_MEMORY; parser->m_declEntity->base = parser->m_curBase; poolFinish(&dtd->pool); @@ -4779,115 +4572,103 @@ doProlog(XML_Parser parser, } break; case XML_ROLE_ENTITY_COMPLETE: - if (dtd->keepProcessing && parser->m_declEntity && parser->m_entityDeclHandler) { + if (dtd->keepProcessing && parser->m_declEntity + && parser->m_entityDeclHandler) { *eventEndPP = s; - parser->m_entityDeclHandler(parser->m_handlerArg, - parser->m_declEntity->name, - parser->m_declEntity->is_param, - 0,0, - parser->m_declEntity->base, - parser->m_declEntity->systemId, - parser->m_declEntity->publicId, - 0); + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->is_param, 0, 0, parser->m_declEntity->base, + parser->m_declEntity->systemId, parser->m_declEntity->publicId, 0); handleDefault = XML_FALSE; } break; case XML_ROLE_ENTITY_NOTATION_NAME: if (dtd->keepProcessing && parser->m_declEntity) { - parser->m_declEntity->notation = poolStoreString(&dtd->pool, enc, s, next); - if (!parser->m_declEntity->notation) + parser->m_declEntity->notation + = poolStoreString(&dtd->pool, enc, s, next); + if (! parser->m_declEntity->notation) return XML_ERROR_NO_MEMORY; poolFinish(&dtd->pool); if (parser->m_unparsedEntityDeclHandler) { *eventEndPP = s; - parser->m_unparsedEntityDeclHandler(parser->m_handlerArg, - parser->m_declEntity->name, - parser->m_declEntity->base, - parser->m_declEntity->systemId, - parser->m_declEntity->publicId, - parser->m_declEntity->notation); + parser->m_unparsedEntityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->base, parser->m_declEntity->systemId, + parser->m_declEntity->publicId, parser->m_declEntity->notation); handleDefault = XML_FALSE; - } - else if (parser->m_entityDeclHandler) { + } else if (parser->m_entityDeclHandler) { *eventEndPP = s; - parser->m_entityDeclHandler(parser->m_handlerArg, - parser->m_declEntity->name, - 0,0,0, - parser->m_declEntity->base, - parser->m_declEntity->systemId, - parser->m_declEntity->publicId, - parser->m_declEntity->notation); + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, 0, 0, 0, + parser->m_declEntity->base, parser->m_declEntity->systemId, + parser->m_declEntity->publicId, parser->m_declEntity->notation); handleDefault = XML_FALSE; } } break; - case XML_ROLE_GENERAL_ENTITY_NAME: - { - if (XmlPredefinedEntityName(enc, s, next)) { - parser->m_declEntity = NULL; - break; - } - if (dtd->keepProcessing) { - const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); - if (!name) - return XML_ERROR_NO_MEMORY; - parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, - sizeof(ENTITY)); - if (!parser->m_declEntity) - return XML_ERROR_NO_MEMORY; - if (parser->m_declEntity->name != name) { - poolDiscard(&dtd->pool); - parser->m_declEntity = NULL; - } - else { - poolFinish(&dtd->pool); - parser->m_declEntity->publicId = NULL; - parser->m_declEntity->is_param = XML_FALSE; - /* if we have a parent parser or are reading an internal parameter - entity, then the entity declaration is not considered "internal" - */ - parser->m_declEntity->is_internal = !(parser->m_parentParser || parser->m_openInternalEntities); - if (parser->m_entityDeclHandler) - handleDefault = XML_FALSE; - } - } - else { + case XML_ROLE_GENERAL_ENTITY_NAME: { + if (XmlPredefinedEntityName(enc, s, next)) { + parser->m_declEntity = NULL; + break; + } + if (dtd->keepProcessing) { + const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); + if (! name) + return XML_ERROR_NO_MEMORY; + parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, + name, sizeof(ENTITY)); + if (! parser->m_declEntity) + return XML_ERROR_NO_MEMORY; + if (parser->m_declEntity->name != name) { poolDiscard(&dtd->pool); parser->m_declEntity = NULL; + } else { + poolFinish(&dtd->pool); + parser->m_declEntity->publicId = NULL; + parser->m_declEntity->is_param = XML_FALSE; + /* if we have a parent parser or are reading an internal parameter + entity, then the entity declaration is not considered "internal" + */ + parser->m_declEntity->is_internal + = ! (parser->m_parentParser || parser->m_openInternalEntities); + if (parser->m_entityDeclHandler) + handleDefault = XML_FALSE; } + } else { + poolDiscard(&dtd->pool); + parser->m_declEntity = NULL; } - break; + } break; case XML_ROLE_PARAM_ENTITY_NAME: #ifdef XML_DTD if (dtd->keepProcessing) { const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); - if (!name) + if (! name) return XML_ERROR_NO_MEMORY; parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities, - name, sizeof(ENTITY)); - if (!parser->m_declEntity) + name, sizeof(ENTITY)); + if (! parser->m_declEntity) return XML_ERROR_NO_MEMORY; if (parser->m_declEntity->name != name) { poolDiscard(&dtd->pool); parser->m_declEntity = NULL; - } - else { + } else { poolFinish(&dtd->pool); parser->m_declEntity->publicId = NULL; parser->m_declEntity->is_param = XML_TRUE; /* if we have a parent parser or are reading an internal parameter entity, then the entity declaration is not considered "internal" */ - parser->m_declEntity->is_internal = !(parser->m_parentParser || parser->m_openInternalEntities); + parser->m_declEntity->is_internal + = ! (parser->m_parentParser || parser->m_openInternalEntities); if (parser->m_entityDeclHandler) handleDefault = XML_FALSE; } - } - else { + } else { poolDiscard(&dtd->pool); parser->m_declEntity = NULL; } -#else /* not XML_DTD */ +#else /* not XML_DTD */ parser->m_declEntity = NULL; #endif /* XML_DTD */ break; @@ -4895,22 +4676,23 @@ doProlog(XML_Parser parser, parser->m_declNotationPublicId = NULL; parser->m_declNotationName = NULL; if (parser->m_notationDeclHandler) { - parser->m_declNotationName = poolStoreString(&parser->m_tempPool, enc, s, next); - if (!parser->m_declNotationName) + parser->m_declNotationName + = poolStoreString(&parser->m_tempPool, enc, s, next); + if (! parser->m_declNotationName) return XML_ERROR_NO_MEMORY; poolFinish(&parser->m_tempPool); handleDefault = XML_FALSE; } break; case XML_ROLE_NOTATION_PUBLIC_ID: - if (!XmlIsPublicId(enc, s, next, eventPP)) + if (! XmlIsPublicId(enc, s, next, eventPP)) return XML_ERROR_PUBLICID; - if (parser->m_declNotationName) { /* means m_notationDeclHandler != NULL */ - XML_Char *tem = poolStoreString(&parser->m_tempPool, - enc, + if (parser + ->m_declNotationName) { /* means m_notationDeclHandler != NULL */ + XML_Char *tem = poolStoreString(&parser->m_tempPool, enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); - if (!tem) + if (! tem) return XML_ERROR_NO_MEMORY; normalizePublicId(tem); parser->m_declNotationPublicId = tem; @@ -4920,18 +4702,15 @@ doProlog(XML_Parser parser, break; case XML_ROLE_NOTATION_SYSTEM_ID: if (parser->m_declNotationName && parser->m_notationDeclHandler) { - const XML_Char *systemId - = poolStoreString(&parser->m_tempPool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!systemId) + const XML_Char *systemId = poolStoreString(&parser->m_tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! systemId) return XML_ERROR_NO_MEMORY; *eventEndPP = s; - parser->m_notationDeclHandler(parser->m_handlerArg, - parser->m_declNotationName, - parser->m_curBase, - systemId, - parser->m_declNotationPublicId); + parser->m_notationDeclHandler( + parser->m_handlerArg, parser->m_declNotationName, parser->m_curBase, + systemId, parser->m_declNotationPublicId); handleDefault = XML_FALSE; } poolClear(&parser->m_tempPool); @@ -4939,11 +4718,9 @@ doProlog(XML_Parser parser, case XML_ROLE_NOTATION_NO_SYSTEM_ID: if (parser->m_declNotationPublicId && parser->m_notationDeclHandler) { *eventEndPP = s; - parser->m_notationDeclHandler(parser->m_handlerArg, - parser->m_declNotationName, - parser->m_curBase, - 0, - parser->m_declNotationPublicId); + parser->m_notationDeclHandler( + parser->m_handlerArg, parser->m_declNotationName, parser->m_curBase, + 0, parser->m_declNotationPublicId); handleDefault = XML_FALSE; } poolClear(&parser->m_tempPool); @@ -4960,42 +4737,44 @@ doProlog(XML_Parser parser, return XML_ERROR_SYNTAX; } #ifdef XML_DTD - case XML_ROLE_IGNORE_SECT: - { - enum XML_Error result; - if (parser->m_defaultHandler) - reportDefault(parser, enc, s, next); - handleDefault = XML_FALSE; - result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore); - if (result != XML_ERROR_NONE) - return result; - else if (!next) { - parser->m_processor = ignoreSectionProcessor; - return result; - } + case XML_ROLE_IGNORE_SECT: { + enum XML_Error result; + if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + handleDefault = XML_FALSE; + result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore); + if (result != XML_ERROR_NONE) + return result; + else if (! next) { + parser->m_processor = ignoreSectionProcessor; + return result; } - break; + } break; #endif /* XML_DTD */ case XML_ROLE_GROUP_OPEN: if (parser->m_prologState.level >= parser->m_groupSize) { if (parser->m_groupSize) { - char *temp = (char *)REALLOC(parser, parser->m_groupConnector, parser->m_groupSize *= 2); - if (temp == NULL) { - parser->m_groupSize /= 2; - return XML_ERROR_NO_MEMORY; + { + char *const new_connector = (char *)REALLOC( + parser, parser->m_groupConnector, parser->m_groupSize *= 2); + if (new_connector == NULL) { + parser->m_groupSize /= 2; + return XML_ERROR_NO_MEMORY; + } + parser->m_groupConnector = new_connector; } - parser->m_groupConnector = temp; + if (dtd->scaffIndex) { - int *temp = (int *)REALLOC(parser, dtd->scaffIndex, - parser->m_groupSize * sizeof(int)); - if (temp == NULL) + int *const new_scaff_index = (int *)REALLOC( + parser, dtd->scaffIndex, parser->m_groupSize * sizeof(int)); + if (new_scaff_index == NULL) return XML_ERROR_NO_MEMORY; - dtd->scaffIndex = temp; + dtd->scaffIndex = new_scaff_index; } - } - else { - parser->m_groupConnector = (char *)MALLOC(parser, parser->m_groupSize = 32); - if (!parser->m_groupConnector) { + } else { + parser->m_groupConnector + = (char *)MALLOC(parser, parser->m_groupSize = 32); + if (! parser->m_groupConnector) { parser->m_groupSize = 0; return XML_ERROR_NO_MEMORY; } @@ -5006,6 +4785,7 @@ doProlog(XML_Parser parser, int myindex = nextScaffoldPart(parser); if (myindex < 0) return XML_ERROR_NO_MEMORY; + assert(dtd->scaffIndex != NULL); dtd->scaffIndex[dtd->scaffLevel] = myindex; dtd->scaffLevel++; dtd->scaffold[myindex].type = XML_CTYPE_SEQ; @@ -5024,10 +4804,9 @@ doProlog(XML_Parser parser, if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_COMMA) return XML_ERROR_SYNTAX; if (dtd->in_eldecl - && !parser->m_groupConnector[parser->m_prologState.level] + && ! parser->m_groupConnector[parser->m_prologState.level] && (dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type - != XML_CTYPE_MIXED) - ) { + != XML_CTYPE_MIXED)) { dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type = XML_CTYPE_CHOICE; if (parser->m_elementDeclHandler) @@ -5039,15 +4818,14 @@ doProlog(XML_Parser parser, #ifdef XML_DTD case XML_ROLE_INNER_PARAM_ENTITY_REF: dtd->hasParamEntityRefs = XML_TRUE; - if (!parser->m_paramEntityParsing) + if (! parser->m_paramEntityParsing) dtd->keepProcessing = dtd->standalone; else { const XML_Char *name; ENTITY *entity; - name = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) + name = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) return XML_ERROR_NO_MEMORY; entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); poolDiscard(&dtd->pool); @@ -5055,13 +4833,12 @@ doProlog(XML_Parser parser, if yes, check that the entity exists, and that it is internal, otherwise call the skipped entity handler */ - if (parser->m_prologState.documentEntity && - (dtd->standalone - ? !parser->m_openInternalEntities - : !dtd->hasParamEntityRefs)) { - if (!entity) + if (parser->m_prologState.documentEntity + && (dtd->standalone ? ! parser->m_openInternalEntities + : ! dtd->hasParamEntityRefs)) { + if (! entity) return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) { + else if (! entity->is_internal) { /* It's hard to exhaustively search the code to be sure, * but there doesn't seem to be a way of executing the * following line. There are two cases: @@ -5084,11 +4861,11 @@ doProlog(XML_Parser parser, */ return XML_ERROR_ENTITY_DECLARED_IN_PE; /* LCOV_EXCL_LINE */ } - } - else if (!entity) { + } else if (! entity) { dtd->keepProcessing = dtd->standalone; /* cannot report skipped entities in declarations */ - if ((role == XML_ROLE_PARAM_ENTITY_REF) && parser->m_skippedEntityHandler) { + if ((role == XML_ROLE_PARAM_ENTITY_REF) + && parser->m_skippedEntityHandler) { parser->m_skippedEntityHandler(parser->m_handlerArg, name, 1); handleDefault = XML_FALSE; } @@ -5098,8 +4875,8 @@ doProlog(XML_Parser parser, return XML_ERROR_RECURSIVE_ENTITY_REF; if (entity->textPtr) { enum XML_Error result; - XML_Bool betweenDecl = - (role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE); + XML_Bool betweenDecl + = (role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE); result = processInternalEntity(parser, entity, betweenDecl); if (result != XML_ERROR_NONE) return result; @@ -5109,39 +4886,35 @@ doProlog(XML_Parser parser, if (parser->m_externalEntityRefHandler) { dtd->paramEntityRead = XML_FALSE; entity->open = XML_TRUE; - if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) { + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) { entity->open = XML_FALSE; return XML_ERROR_EXTERNAL_ENTITY_HANDLING; } entity->open = XML_FALSE; handleDefault = XML_FALSE; - if (!dtd->paramEntityRead) { + if (! dtd->paramEntityRead) { dtd->keepProcessing = dtd->standalone; break; } - } - else { + } else { dtd->keepProcessing = dtd->standalone; break; } } #endif /* XML_DTD */ - if (!dtd->standalone && - parser->m_notStandaloneHandler && - !parser->m_notStandaloneHandler(parser->m_handlerArg)) + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) return XML_ERROR_NOT_STANDALONE; break; - /* Element declaration stuff */ + /* Element declaration stuff */ case XML_ROLE_ELEMENT_NAME: if (parser->m_elementDeclHandler) { parser->m_declElementType = getElementType(parser, enc, s, next); - if (!parser->m_declElementType) + if (! parser->m_declElementType) return XML_ERROR_NO_MEMORY; dtd->scaffLevel = 0; dtd->scaffCount = 0; @@ -5154,18 +4927,19 @@ doProlog(XML_Parser parser, case XML_ROLE_CONTENT_EMPTY: if (dtd->in_eldecl) { if (parser->m_elementDeclHandler) { - XML_Content * content = (XML_Content *) MALLOC(parser, sizeof(XML_Content)); - if (!content) + XML_Content *content + = (XML_Content *)MALLOC(parser, sizeof(XML_Content)); + if (! content) return XML_ERROR_NO_MEMORY; content->quant = XML_CQUANT_NONE; content->name = NULL; content->numchildren = 0; content->children = NULL; - content->type = ((role == XML_ROLE_CONTENT_ANY) ? - XML_CTYPE_ANY : - XML_CTYPE_EMPTY); + content->type = ((role == XML_ROLE_CONTENT_ANY) ? XML_CTYPE_ANY + : XML_CTYPE_EMPTY); *eventEndPP = s; - parser->m_elementDeclHandler(parser->m_handlerArg, parser->m_declElementType->name, content); + parser->m_elementDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, content); handleDefault = XML_FALSE; } dtd->in_eldecl = XML_FALSE; @@ -5197,22 +4971,22 @@ doProlog(XML_Parser parser, ELEMENT_TYPE *el; const XML_Char *name; int nameLen; - const char *nxt = (quant == XML_CQUANT_NONE - ? next - : next - enc->minBytesPerChar); + const char *nxt + = (quant == XML_CQUANT_NONE ? next : next - enc->minBytesPerChar); int myindex = nextScaffoldPart(parser); if (myindex < 0) return XML_ERROR_NO_MEMORY; dtd->scaffold[myindex].type = XML_CTYPE_NAME; dtd->scaffold[myindex].quant = quant; el = getElementType(parser, enc, s, nxt); - if (!el) + if (! el) return XML_ERROR_NO_MEMORY; name = el->name; dtd->scaffold[myindex].name = name; nameLen = 0; - for (; name[nameLen++]; ); - dtd->contentStringLen += nameLen; + for (; name[nameLen++];) + ; + dtd->contentStringLen += nameLen; if (parser->m_elementDeclHandler) handleDefault = XML_FALSE; } @@ -5236,12 +5010,13 @@ doProlog(XML_Parser parser, dtd->scaffLevel--; dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel]].quant = quant; if (dtd->scaffLevel == 0) { - if (!handleDefault) { + if (! handleDefault) { XML_Content *model = build_model(parser); - if (!model) + if (! model) return XML_ERROR_NO_MEMORY; *eventEndPP = s; - parser->m_elementDeclHandler(parser->m_handlerArg, parser->m_declElementType->name, model); + parser->m_elementDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, model); } dtd->in_eldecl = XML_FALSE; dtd->contentStringLen = 0; @@ -5251,12 +5026,12 @@ doProlog(XML_Parser parser, /* End element declaration stuff */ case XML_ROLE_PI: - if (!reportProcessingInstruction(parser, enc, s, next)) + if (! reportProcessingInstruction(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; handleDefault = XML_FALSE; break; case XML_ROLE_COMMENT: - if (!reportComment(parser, enc, s, next)) + if (! reportComment(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; handleDefault = XML_FALSE; break; @@ -5307,11 +5082,8 @@ doProlog(XML_Parser parser, } static enum XML_Error PTRCALL -epilogProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +epilogProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { parser->m_processor = epilogProcessor; parser->m_eventPtr = s; for (;;) { @@ -5336,24 +5108,24 @@ epilogProcessor(XML_Parser parser, reportDefault(parser, parser->m_encoding, s, next); break; case XML_TOK_PI: - if (!reportProcessingInstruction(parser, parser->m_encoding, s, next)) + if (! reportProcessingInstruction(parser, parser->m_encoding, s, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_COMMENT: - if (!reportComment(parser, parser->m_encoding, s, next)) + if (! reportComment(parser, parser->m_encoding, s, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_INVALID: parser->m_eventPtr = next; return XML_ERROR_INVALID_TOKEN; case XML_TOK_PARTIAL: - if (!parser->m_parsingStatus.finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *nextPtr = s; return XML_ERROR_NONE; } return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!parser->m_parsingStatus.finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *nextPtr = s; return XML_ERROR_NONE; } @@ -5368,15 +5140,13 @@ epilogProcessor(XML_Parser parser, return XML_ERROR_NONE; case XML_FINISHED: return XML_ERROR_ABORTED; - default: ; + default:; } } } static enum XML_Error -processInternalEntity(XML_Parser parser, ENTITY *entity, - XML_Bool betweenDecl) -{ +processInternalEntity(XML_Parser parser, ENTITY *entity, XML_Bool betweenDecl) { const char *textStart, *textEnd; const char *next; enum XML_Error result; @@ -5385,10 +5155,10 @@ processInternalEntity(XML_Parser parser, ENTITY *entity, if (parser->m_freeInternalEntities) { openEntity = parser->m_freeInternalEntities; parser->m_freeInternalEntities = openEntity->next; - } - else { - openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(parser, sizeof(OPEN_INTERNAL_ENTITY)); - if (!openEntity) + } else { + openEntity + = (OPEN_INTERNAL_ENTITY *)MALLOC(parser, sizeof(OPEN_INTERNAL_ENTITY)); + if (! openEntity) return XML_ERROR_NO_MEMORY; } entity->open = XML_TRUE; @@ -5407,21 +5177,20 @@ processInternalEntity(XML_Parser parser, ENTITY *entity, #ifdef XML_DTD if (entity->is_param) { - int tok = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); - result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, tok, - next, &next, XML_FALSE); - } - else + int tok + = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, + tok, next, &next, XML_FALSE, XML_FALSE); + } else #endif /* XML_DTD */ - result = doContent(parser, parser->m_tagLevel, parser->m_internalEncoding, textStart, - textEnd, &next, XML_FALSE); + result = doContent(parser, parser->m_tagLevel, parser->m_internalEncoding, + textStart, textEnd, &next, XML_FALSE); if (result == XML_ERROR_NONE) { if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) { entity->processed = (int)(next - textStart); parser->m_processor = internalEntityProcessor; - } - else { + } else { entity->open = XML_FALSE; parser->m_openInternalEntities = openEntity->next; /* put openEntity back in list of free instances */ @@ -5433,17 +5202,14 @@ processInternalEntity(XML_Parser parser, ENTITY *entity, } static enum XML_Error PTRCALL -internalEntityProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +internalEntityProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { ENTITY *entity; const char *textStart, *textEnd; const char *next; enum XML_Error result; OPEN_INTERNAL_ENTITY *openEntity = parser->m_openInternalEntities; - if (!openEntity) + if (! openEntity) return XML_ERROR_UNEXPECTED_STATE; entity = openEntity->entity; @@ -5454,22 +5220,23 @@ internalEntityProcessor(XML_Parser parser, #ifdef XML_DTD if (entity->is_param) { - int tok = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); - result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, tok, - next, &next, XML_FALSE); - } - else + int tok + = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, + tok, next, &next, XML_FALSE, XML_TRUE); + } else #endif /* XML_DTD */ - result = doContent(parser, openEntity->startTagLevel, parser->m_internalEncoding, - textStart, textEnd, &next, XML_FALSE); + result = doContent(parser, openEntity->startTagLevel, + parser->m_internalEncoding, textStart, textEnd, &next, + XML_FALSE); if (result != XML_ERROR_NONE) return result; - else if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) { + else if (textEnd != next + && parser->m_parsingStatus.parsing == XML_SUSPENDED) { entity->processed = (int)(next - (char *)entity->textPtr); return result; - } - else { + } else { entity->open = XML_FALSE; parser->m_openInternalEntities = openEntity->next; /* put openEntity back in list of free instances */ @@ -5483,49 +5250,45 @@ internalEntityProcessor(XML_Parser parser, parser->m_processor = prologProcessor; tok = XmlPrologTok(parser->m_encoding, s, end, &next); return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, - (XML_Bool)!parser->m_parsingStatus.finalBuffer); - } - else + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); + } else #endif /* XML_DTD */ { parser->m_processor = contentProcessor; /* see externalEntityContentProcessor vs contentProcessor */ - return doContent(parser, parser->m_parentParser ? 1 : 0, parser->m_encoding, s, end, - nextPtr, (XML_Bool)!parser->m_parsingStatus.finalBuffer); + return doContent(parser, parser->m_parentParser ? 1 : 0, parser->m_encoding, + s, end, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); } } static enum XML_Error PTRCALL -errorProcessor(XML_Parser parser, - const char *UNUSED_P(s), - const char *UNUSED_P(end), - const char **UNUSED_P(nextPtr)) -{ +errorProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + UNUSED_P(s); + UNUSED_P(end); + UNUSED_P(nextPtr); return parser->m_errorCode; } static enum XML_Error storeAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, - const char *ptr, const char *end, - STRING_POOL *pool) -{ - enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr, - end, pool); + const char *ptr, const char *end, STRING_POOL *pool) { + enum XML_Error result + = appendAttributeValue(parser, enc, isCdata, ptr, end, pool); if (result) return result; - if (!isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) + if (! isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) poolChop(pool); - if (!poolAppendChar(pool, XML_T('\0'))) + if (! poolAppendChar(pool, XML_T('\0'))) return XML_ERROR_NO_MEMORY; return XML_ERROR_NONE; } static enum XML_Error appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, - const char *ptr, const char *end, - STRING_POOL *pool) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ + const char *ptr, const char *end, STRING_POOL *pool) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ for (;;) { const char *next; int tok = XmlAttributeValueTok(enc, ptr, end, &next); @@ -5540,38 +5303,35 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, if (enc == parser->m_encoding) parser->m_eventPtr = ptr; return XML_ERROR_INVALID_TOKEN; - case XML_TOK_CHAR_REF: - { - XML_Char buf[XML_ENCODE_MAX]; - int i; - int n = XmlCharRefNumber(enc, ptr); - if (n < 0) { - if (enc == parser->m_encoding) - parser->m_eventPtr = ptr; - return XML_ERROR_BAD_CHAR_REF; - } - if (!isCdata - && n == 0x20 /* space */ - && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) - break; - n = XmlEncode(n, (ICHAR *)buf); - /* The XmlEncode() functions can never return 0 here. That - * error return happens if the code point passed in is either - * negative or greater than or equal to 0x110000. The - * XmlCharRefNumber() functions will all return a number - * strictly less than 0x110000 or a negative value if an error - * occurred. The negative value is intercepted above, so - * XmlEncode() is never passed a value it might return an - * error for. - */ - for (i = 0; i < n; i++) { - if (!poolAppendChar(pool, buf[i])) - return XML_ERROR_NO_MEMORY; - } + case XML_TOK_CHAR_REF: { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, ptr); + if (n < 0) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_BAD_CHAR_REF; } - break; + if (! isCdata && n == 0x20 /* space */ + && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + break; + n = XmlEncode(n, (ICHAR *)buf); + /* The XmlEncode() functions can never return 0 here. That + * error return happens if the code point passed in is either + * negative or greater than or equal to 0x110000. The + * XmlCharRefNumber() functions will all return a number + * strictly less than 0x110000 or a negative value if an error + * occurred. The negative value is intercepted above, so + * XmlEncode() is never passed a value it might return an + * error for. + */ + for (i = 0; i < n; i++) { + if (! poolAppendChar(pool, buf[i])) + return XML_ERROR_NO_MEMORY; + } + } break; case XML_TOK_DATA_CHARS: - if (!poolAppend(pool, enc, ptr, next)) + if (! poolAppend(pool, enc, ptr, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_TRAILING_CR: @@ -5579,109 +5339,103 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, /* fall through */ case XML_TOK_ATTRIBUTE_VALUE_S: case XML_TOK_DATA_NEWLINE: - if (!isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + if (! isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) break; - if (!poolAppendChar(pool, 0x20)) + if (! poolAppendChar(pool, 0x20)) return XML_ERROR_NO_MEMORY; break; - case XML_TOK_ENTITY_REF: - { - const XML_Char *name; - ENTITY *entity; - char checkEntityDecl; - XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc, - ptr + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (ch) { - if (!poolAppendChar(pool, ch)) - return XML_ERROR_NO_MEMORY; - break; - } - name = poolStoreString(&parser->m_temp2Pool, enc, - ptr + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) + case XML_TOK_ENTITY_REF: { + const XML_Char *name; + ENTITY *entity; + char checkEntityDecl; + XML_Char ch = (XML_Char)XmlPredefinedEntityName( + enc, ptr + enc->minBytesPerChar, next - enc->minBytesPerChar); + if (ch) { + if (! poolAppendChar(pool, ch)) return XML_ERROR_NO_MEMORY; - entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); - poolDiscard(&parser->m_temp2Pool); - /* First, determine if a check for an existing declaration is needed; - if yes, check that the entity exists, and that it is internal. - */ - if (pool == &dtd->pool) /* are we called from prolog? */ - checkEntityDecl = + break; + } + name = poolStoreString(&parser->m_temp2Pool, enc, + ptr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); + poolDiscard(&parser->m_temp2Pool); + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal. + */ + if (pool == &dtd->pool) /* are we called from prolog? */ + checkEntityDecl = #ifdef XML_DTD - parser->m_prologState.documentEntity && + parser->m_prologState.documentEntity && #endif /* XML_DTD */ - (dtd->standalone - ? !parser->m_openInternalEntities - : !dtd->hasParamEntityRefs); - else /* if (pool == &parser->m_tempPool): we are called from content */ - checkEntityDecl = !dtd->hasParamEntityRefs || dtd->standalone; - if (checkEntityDecl) { - if (!entity) - return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) - return XML_ERROR_ENTITY_DECLARED_IN_PE; - } - else if (!entity) { - /* Cannot report skipped entity here - see comments on - parser->m_skippedEntityHandler. - if (parser->m_skippedEntityHandler) - parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); - */ - /* Cannot call the default handler because this would be - out of sync with the call to the startElementHandler. - if ((pool == &parser->m_tempPool) && parser->m_defaultHandler) - reportDefault(parser, enc, ptr, next); - */ - break; - } - if (entity->open) { - if (enc == parser->m_encoding) { - /* It does not appear that this line can be executed. - * - * The "if (entity->open)" check catches recursive entity - * definitions. In order to be called with an open - * entity, it must have gone through this code before and - * been through the recursive call to - * appendAttributeValue() some lines below. That call - * sets the local encoding ("enc") to the parser's - * internal encoding (internal_utf8 or internal_utf16), - * which can never be the same as the principle encoding. - * It doesn't appear there is another code path that gets - * here with entity->open being TRUE. - * - * Since it is not certain that this logic is watertight, - * we keep the line and merely exclude it from coverage - * tests. - */ - parser->m_eventPtr = ptr; /* LCOV_EXCL_LINE */ - } - return XML_ERROR_RECURSIVE_ENTITY_REF; - } - if (entity->notation) { - if (enc == parser->m_encoding) - parser->m_eventPtr = ptr; - return XML_ERROR_BINARY_ENTITY_REF; - } - if (!entity->textPtr) { - if (enc == parser->m_encoding) - parser->m_eventPtr = ptr; - return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; - } - else { - enum XML_Error result; - const XML_Char *textEnd = entity->textPtr + entity->textLen; - entity->open = XML_TRUE; - result = appendAttributeValue(parser, parser->m_internalEncoding, isCdata, - (char *)entity->textPtr, - (char *)textEnd, pool); - entity->open = XML_FALSE; - if (result) - return result; + (dtd->standalone ? ! parser->m_openInternalEntities + : ! dtd->hasParamEntityRefs); + else /* if (pool == &parser->m_tempPool): we are called from content */ + checkEntityDecl = ! dtd->hasParamEntityRefs || dtd->standalone; + if (checkEntityDecl) { + if (! entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (! entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } else if (! entity) { + /* Cannot report skipped entity here - see comments on + parser->m_skippedEntityHandler. + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); + */ + /* Cannot call the default handler because this would be + out of sync with the call to the startElementHandler. + if ((pool == &parser->m_tempPool) && parser->m_defaultHandler) + reportDefault(parser, enc, ptr, next); + */ + break; + } + if (entity->open) { + if (enc == parser->m_encoding) { + /* It does not appear that this line can be executed. + * + * The "if (entity->open)" check catches recursive entity + * definitions. In order to be called with an open + * entity, it must have gone through this code before and + * been through the recursive call to + * appendAttributeValue() some lines below. That call + * sets the local encoding ("enc") to the parser's + * internal encoding (internal_utf8 or internal_utf16), + * which can never be the same as the principle encoding. + * It doesn't appear there is another code path that gets + * here with entity->open being TRUE. + * + * Since it is not certain that this logic is watertight, + * we keep the line and merely exclude it from coverage + * tests. + */ + parser->m_eventPtr = ptr; /* LCOV_EXCL_LINE */ } + return XML_ERROR_RECURSIVE_ENTITY_REF; } - break; + if (entity->notation) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_BINARY_ENTITY_REF; + } + if (! entity->textPtr) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; + } else { + enum XML_Error result; + const XML_Char *textEnd = entity->textPtr + entity->textLen; + entity->open = XML_TRUE; + result = appendAttributeValue(parser, parser->m_internalEncoding, + isCdata, (char *)entity->textPtr, + (char *)textEnd, pool); + entity->open = XML_FALSE; + if (result) + return result; + } + } break; default: /* The only token returned by XmlAttributeValueTok() that does * not have an explicit case here is XML_TOK_PARTIAL_CHAR. @@ -5705,12 +5459,9 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, } static enum XML_Error -storeEntityValue(XML_Parser parser, - const ENCODING *enc, - const char *entityTextPtr, - const char *entityTextEnd) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +storeEntityValue(XML_Parser parser, const ENCODING *enc, + const char *entityTextPtr, const char *entityTextEnd) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ STRING_POOL *pool = &(dtd->entityValuePool); enum XML_Error result = XML_ERROR_NONE; #ifdef XML_DTD @@ -5720,8 +5471,8 @@ storeEntityValue(XML_Parser parser, /* never return Null for the value argument in EntityDeclHandler, since this would indicate an external entity; therefore we have to make sure that entityValuePool.start is not null */ - if (!pool->blocks) { - if (!poolGrow(pool)) + if (! pool->blocks) { + if (! poolGrow(pool)) return XML_ERROR_NO_MEMORY; } @@ -5737,13 +5488,13 @@ storeEntityValue(XML_Parser parser, name = poolStoreString(&parser->m_tempPool, enc, entityTextPtr + enc->minBytesPerChar, next - enc->minBytesPerChar); - if (!name) { + if (! name) { result = XML_ERROR_NO_MEMORY; goto endEntityValue; } entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); poolDiscard(&parser->m_tempPool); - if (!entity) { + if (! entity) { /* not a well-formedness error - see XML 1.0: WFC Entity Declared */ /* cannot report skipped entity here - see comments on parser->m_skippedEntityHandler @@ -5763,29 +5514,23 @@ storeEntityValue(XML_Parser parser, if (parser->m_externalEntityRefHandler) { dtd->paramEntityRead = XML_FALSE; entity->open = XML_TRUE; - if (!parser->m_externalEntityRefHandler(parser->m_externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) { + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) { entity->open = XML_FALSE; result = XML_ERROR_EXTERNAL_ENTITY_HANDLING; goto endEntityValue; } entity->open = XML_FALSE; - if (!dtd->paramEntityRead) + if (! dtd->paramEntityRead) dtd->keepProcessing = dtd->standalone; - } - else + } else dtd->keepProcessing = dtd->standalone; - } - else { + } else { entity->open = XML_TRUE; - result = storeEntityValue(parser, - parser->m_internalEncoding, - (char *)entity->textPtr, - (char *)(entity->textPtr - + entity->textLen)); + result = storeEntityValue( + parser, parser->m_internalEncoding, (char *)entity->textPtr, + (char *)(entity->textPtr + entity->textLen)); entity->open = XML_FALSE; if (result) goto endEntityValue; @@ -5803,7 +5548,7 @@ storeEntityValue(XML_Parser parser, goto endEntityValue; case XML_TOK_ENTITY_REF: case XML_TOK_DATA_CHARS: - if (!poolAppend(pool, enc, entityTextPtr, next)) { + if (! poolAppend(pool, enc, entityTextPtr, next)) { result = XML_ERROR_NO_MEMORY; goto endEntityValue; } @@ -5812,42 +5557,40 @@ storeEntityValue(XML_Parser parser, next = entityTextPtr + enc->minBytesPerChar; /* fall through */ case XML_TOK_DATA_NEWLINE: - if (pool->end == pool->ptr && !poolGrow(pool)) { - result = XML_ERROR_NO_MEMORY; + if (pool->end == pool->ptr && ! poolGrow(pool)) { + result = XML_ERROR_NO_MEMORY; goto endEntityValue; } *(pool->ptr)++ = 0xA; break; - case XML_TOK_CHAR_REF: - { - XML_Char buf[XML_ENCODE_MAX]; - int i; - int n = XmlCharRefNumber(enc, entityTextPtr); - if (n < 0) { - if (enc == parser->m_encoding) - parser->m_eventPtr = entityTextPtr; - result = XML_ERROR_BAD_CHAR_REF; + case XML_TOK_CHAR_REF: { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, entityTextPtr); + if (n < 0) { + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; + result = XML_ERROR_BAD_CHAR_REF; + goto endEntityValue; + } + n = XmlEncode(n, (ICHAR *)buf); + /* The XmlEncode() functions can never return 0 here. That + * error return happens if the code point passed in is either + * negative or greater than or equal to 0x110000. The + * XmlCharRefNumber() functions will all return a number + * strictly less than 0x110000 or a negative value if an error + * occurred. The negative value is intercepted above, so + * XmlEncode() is never passed a value it might return an + * error for. + */ + for (i = 0; i < n; i++) { + if (pool->end == pool->ptr && ! poolGrow(pool)) { + result = XML_ERROR_NO_MEMORY; goto endEntityValue; } - n = XmlEncode(n, (ICHAR *)buf); - /* The XmlEncode() functions can never return 0 here. That - * error return happens if the code point passed in is either - * negative or greater than or equal to 0x110000. The - * XmlCharRefNumber() functions will all return a number - * strictly less than 0x110000 or a negative value if an error - * occurred. The negative value is intercepted above, so - * XmlEncode() is never passed a value it might return an - * error for. - */ - for (i = 0; i < n; i++) { - if (pool->end == pool->ptr && !poolGrow(pool)) { - result = XML_ERROR_NO_MEMORY; - goto endEntityValue; - } - *(pool->ptr)++ = buf[i]; - } + *(pool->ptr)++ = buf[i]; } - break; + } break; case XML_TOK_PARTIAL: if (enc == parser->m_encoding) parser->m_eventPtr = entityTextPtr; @@ -5882,8 +5625,7 @@ endEntityValue: } static void FASTCALL -normalizeLines(XML_Char *s) -{ +normalizeLines(XML_Char *s) { XML_Char *p; for (;; s++) { if (*s == XML_T('\0')) @@ -5897,8 +5639,7 @@ normalizeLines(XML_Char *s) *p++ = 0xA; if (*++s == 0xA) s++; - } - else + } else *p++ = *s++; } while (*s); *p = XML_T('\0'); @@ -5906,12 +5647,11 @@ normalizeLines(XML_Char *s) static int reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ + const char *start, const char *end) { const XML_Char *target; XML_Char *data; const char *tem; - if (!parser->m_processingInstructionHandler) { + if (! parser->m_processingInstructionHandler) { if (parser->m_defaultHandler) reportDefault(parser, enc, start, end); return 1; @@ -5919,13 +5659,12 @@ reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, start += enc->minBytesPerChar * 2; tem = start + XmlNameLength(enc, start); target = poolStoreString(&parser->m_tempPool, enc, start, tem); - if (!target) + if (! target) return 0; poolFinish(&parser->m_tempPool); - data = poolStoreString(&parser->m_tempPool, enc, - XmlSkipS(enc, tem), - end - enc->minBytesPerChar*2); - if (!data) + data = poolStoreString(&parser->m_tempPool, enc, XmlSkipS(enc, tem), + end - enc->minBytesPerChar * 2); + if (! data) return 0; normalizeLines(data); parser->m_processingInstructionHandler(parser->m_handlerArg, target, data); @@ -5934,20 +5673,18 @@ reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, } static int -reportComment(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ +reportComment(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end) { XML_Char *data; - if (!parser->m_commentHandler) { + if (! parser->m_commentHandler) { if (parser->m_defaultHandler) reportDefault(parser, enc, start, end); return 1; } - data = poolStoreString(&parser->m_tempPool, - enc, + data = poolStoreString(&parser->m_tempPool, enc, start + enc->minBytesPerChar * 4, end - enc->minBytesPerChar * 3); - if (!data) + if (! data) return 0; normalizeLines(data); parser->m_commentHandler(parser->m_handlerArg, data); @@ -5956,9 +5693,8 @@ reportComment(XML_Parser parser, const ENCODING *enc, } static void -reportDefault(XML_Parser parser, const ENCODING *enc, - const char *s, const char *end) -{ +reportDefault(XML_Parser parser, const ENCODING *enc, const char *s, + const char *end) { if (MUST_CONVERT(enc, s)) { enum XML_Convert_Result convert_res; const char **eventPP; @@ -5966,8 +5702,7 @@ reportDefault(XML_Parser parser, const ENCODING *enc, if (enc == parser->m_encoding) { eventPP = &parser->m_eventPtr; eventEndPP = &parser->m_eventEndPtr; - } - else { + } else { /* To get here, two things must be true; the parser must be * using a character encoding that is not the same as the * encoding passed in, and the encoding passed in must need @@ -5990,21 +5725,22 @@ reportDefault(XML_Parser parser, const ENCODING *enc, } do { ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; - convert_res = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + convert_res + = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd); *eventEndPP = s; - parser->m_defaultHandler(parser->m_handlerArg, parser->m_dataBuf, (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + parser->m_defaultHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); *eventPP = s; - } while ((convert_res != XML_CONVERT_COMPLETED) && (convert_res != XML_CONVERT_INPUT_INCOMPLETE)); - } - else - parser->m_defaultHandler(parser->m_handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s)); + } while ((convert_res != XML_CONVERT_COMPLETED) + && (convert_res != XML_CONVERT_INPUT_INCOMPLETE)); + } else + parser->m_defaultHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)end - (XML_Char *)s)); } - static int defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, - XML_Bool isId, const XML_Char *value, XML_Parser parser) -{ + XML_Bool isId, const XML_Char *value, XML_Parser parser) { DEFAULT_ATTRIBUTE *att; if (value || isId) { /* The handling of default attributes gets messed up if we have @@ -6013,24 +5749,23 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, for (i = 0; i < type->nDefaultAtts; i++) if (attId == type->defaultAtts[i].id) return 1; - if (isId && !type->idAtt && !attId->xmlns) + if (isId && ! type->idAtt && ! attId->xmlns) type->idAtt = attId; } if (type->nDefaultAtts == type->allocDefaultAtts) { if (type->allocDefaultAtts == 0) { type->allocDefaultAtts = 8; - type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(parser, type->allocDefaultAtts - * sizeof(DEFAULT_ATTRIBUTE)); - if (!type->defaultAtts) { + type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC( + parser, type->allocDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + if (! type->defaultAtts) { type->allocDefaultAtts = 0; return 0; } - } - else { + } else { DEFAULT_ATTRIBUTE *temp; int count = type->allocDefaultAtts * 2; - temp = (DEFAULT_ATTRIBUTE *) - REALLOC(parser, type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE))); + temp = (DEFAULT_ATTRIBUTE *)REALLOC(parser, type->defaultAtts, + (count * sizeof(DEFAULT_ATTRIBUTE))); if (temp == NULL) return 0; type->allocDefaultAtts = count; @@ -6041,30 +5776,29 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, att->id = attId; att->value = value; att->isCdata = isCdata; - if (!isCdata) + if (! isCdata) attId->maybeTokenized = XML_TRUE; type->nDefaultAtts += 1; return 1; } static int -setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ const XML_Char *name; for (name = elementType->name; *name; name++) { if (*name == XML_T(ASCII_COLON)) { PREFIX *prefix; const XML_Char *s; for (s = elementType->name; s != name; s++) { - if (!poolAppendChar(&dtd->pool, *s)) + if (! poolAppendChar(&dtd->pool, *s)) return 0; } - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) return 0; prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), sizeof(PREFIX)); - if (!prefix) + if (! prefix) return 0; if (prefix->name == poolStart(&dtd->pool)) poolFinish(&dtd->pool); @@ -6078,55 +5812,53 @@ setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) } static ATTRIBUTE_ID * -getAttributeId(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ ATTRIBUTE_ID *id; const XML_Char *name; - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) return NULL; name = poolStoreString(&dtd->pool, enc, start, end); - if (!name) + if (! name) return NULL; /* skip quotation mark - its storage will be re-used (like in name[-1]) */ ++name; - id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, name, sizeof(ATTRIBUTE_ID)); - if (!id) + id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, name, + sizeof(ATTRIBUTE_ID)); + if (! id) return NULL; if (id->name != name) poolDiscard(&dtd->pool); else { poolFinish(&dtd->pool); - if (!parser->m_ns) + if (! parser->m_ns) ; - else if (name[0] == XML_T(ASCII_x) - && name[1] == XML_T(ASCII_m) - && name[2] == XML_T(ASCII_l) - && name[3] == XML_T(ASCII_n) - && name[4] == XML_T(ASCII_s) - && (name[5] == XML_T('\0') || name[5] == XML_T(ASCII_COLON))) { + else if (name[0] == XML_T(ASCII_x) && name[1] == XML_T(ASCII_m) + && name[2] == XML_T(ASCII_l) && name[3] == XML_T(ASCII_n) + && name[4] == XML_T(ASCII_s) + && (name[5] == XML_T('\0') || name[5] == XML_T(ASCII_COLON))) { if (name[5] == XML_T('\0')) id->prefix = &dtd->defaultPrefix; else - id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, name + 6, sizeof(PREFIX)); + id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, name + 6, + sizeof(PREFIX)); id->xmlns = XML_TRUE; - } - else { + } else { int i; for (i = 0; name[i]; i++) { /* attributes without prefix are *not* in the default namespace */ if (name[i] == XML_T(ASCII_COLON)) { int j; for (j = 0; j < i; j++) { - if (!poolAppendChar(&dtd->pool, name[j])) + if (! poolAppendChar(&dtd->pool, name[j])) return NULL; } - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) return NULL; - id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), - sizeof(PREFIX)); - if (!id->prefix) + id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, + poolStart(&dtd->pool), sizeof(PREFIX)); + if (! id->prefix) return NULL; if (id->prefix->name == poolStart(&dtd->pool)) poolFinish(&dtd->pool); @@ -6143,22 +5875,22 @@ getAttributeId(XML_Parser parser, const ENCODING *enc, #define CONTEXT_SEP XML_T(ASCII_FF) static const XML_Char * -getContext(XML_Parser parser) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +getContext(XML_Parser parser) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ HASH_TABLE_ITER iter; XML_Bool needSep = XML_FALSE; if (dtd->defaultPrefix.binding) { int i; int len; - if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS))) + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS))) return NULL; len = dtd->defaultPrefix.binding->uriLen; if (parser->m_namespaceSeparator) len--; for (i = 0; i < len; i++) { - if (!poolAppendChar(&parser->m_tempPool, dtd->defaultPrefix.binding->uri[i])) { + if (! poolAppendChar(&parser->m_tempPool, + dtd->defaultPrefix.binding->uri[i])) { /* Because of memory caching, I don't believe this line can be * executed. * @@ -6190,9 +5922,9 @@ getContext(XML_Parser parser) int len; const XML_Char *s; PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter); - if (!prefix) + if (! prefix) break; - if (!prefix->binding) { + if (! prefix->binding) { /* This test appears to be (justifiable) paranoia. There does * not seem to be a way of injecting a prefix without a binding * that doesn't get errored long before this function is called. @@ -6201,98 +5933,96 @@ getContext(XML_Parser parser) */ continue; /* LCOV_EXCL_LINE */ } - if (needSep && !poolAppendChar(&parser->m_tempPool, CONTEXT_SEP)) + if (needSep && ! poolAppendChar(&parser->m_tempPool, CONTEXT_SEP)) return NULL; for (s = prefix->name; *s; s++) - if (!poolAppendChar(&parser->m_tempPool, *s)) + if (! poolAppendChar(&parser->m_tempPool, *s)) return NULL; - if (!poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS))) + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS))) return NULL; len = prefix->binding->uriLen; if (parser->m_namespaceSeparator) len--; for (i = 0; i < len; i++) - if (!poolAppendChar(&parser->m_tempPool, prefix->binding->uri[i])) + if (! poolAppendChar(&parser->m_tempPool, prefix->binding->uri[i])) return NULL; needSep = XML_TRUE; } - hashTableIterInit(&iter, &(dtd->generalEntities)); for (;;) { const XML_Char *s; ENTITY *e = (ENTITY *)hashTableIterNext(&iter); - if (!e) + if (! e) break; - if (!e->open) + if (! e->open) continue; - if (needSep && !poolAppendChar(&parser->m_tempPool, CONTEXT_SEP)) + if (needSep && ! poolAppendChar(&parser->m_tempPool, CONTEXT_SEP)) return NULL; for (s = e->name; *s; s++) - if (!poolAppendChar(&parser->m_tempPool, *s)) + if (! poolAppendChar(&parser->m_tempPool, *s)) return 0; needSep = XML_TRUE; } - if (!poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return NULL; return parser->m_tempPool.start; } static XML_Bool -setContext(XML_Parser parser, const XML_Char *context) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +setContext(XML_Parser parser, const XML_Char *context) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ const XML_Char *s = context; while (*context != XML_T('\0')) { if (*s == CONTEXT_SEP || *s == XML_T('\0')) { ENTITY *e; - if (!poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_FALSE; - e = (ENTITY *)lookup(parser, &dtd->generalEntities, poolStart(&parser->m_tempPool), 0); + e = (ENTITY *)lookup(parser, &dtd->generalEntities, + poolStart(&parser->m_tempPool), 0); if (e) e->open = XML_TRUE; if (*s != XML_T('\0')) s++; context = s; poolDiscard(&parser->m_tempPool); - } - else if (*s == XML_T(ASCII_EQUALS)) { + } else if (*s == XML_T(ASCII_EQUALS)) { PREFIX *prefix; if (poolLength(&parser->m_tempPool) == 0) prefix = &dtd->defaultPrefix; else { - if (!poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_FALSE; - prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&parser->m_tempPool), - sizeof(PREFIX)); - if (!prefix) + prefix + = (PREFIX *)lookup(parser, &dtd->prefixes, + poolStart(&parser->m_tempPool), sizeof(PREFIX)); + if (! prefix) return XML_FALSE; if (prefix->name == poolStart(&parser->m_tempPool)) { prefix->name = poolCopyString(&dtd->pool, prefix->name); - if (!prefix->name) + if (! prefix->name) return XML_FALSE; } poolDiscard(&parser->m_tempPool); } - for (context = s + 1; - *context != CONTEXT_SEP && *context != XML_T('\0'); + for (context = s + 1; *context != CONTEXT_SEP && *context != XML_T('\0'); context++) - if (!poolAppendChar(&parser->m_tempPool, *context)) + if (! poolAppendChar(&parser->m_tempPool, *context)) return XML_FALSE; - if (!poolAppendChar(&parser->m_tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_FALSE; if (addBinding(parser, prefix, NULL, poolStart(&parser->m_tempPool), - &parser->m_inheritedBindings) != XML_ERROR_NONE) + &parser->m_inheritedBindings) + != XML_ERROR_NONE) return XML_FALSE; poolDiscard(&parser->m_tempPool); if (*context != XML_T('\0')) ++context; s = context; - } - else { - if (!poolAppendChar(&parser->m_tempPool, *s)) + } else { + if (! poolAppendChar(&parser->m_tempPool, *s)) return XML_FALSE; s++; } @@ -6301,8 +6031,7 @@ setContext(XML_Parser parser, const XML_Char *context) } static void FASTCALL -normalizePublicId(XML_Char *publicId) -{ +normalizePublicId(XML_Char *publicId) { XML_Char *p = publicId; XML_Char *s; for (s = publicId; *s; s++) { @@ -6323,8 +6052,7 @@ normalizePublicId(XML_Char *publicId) } static DTD * -dtdCreate(const XML_Memory_Handling_Suite *ms) -{ +dtdCreate(const XML_Memory_Handling_Suite *ms) { DTD *p = (DTD *)ms->malloc_fcn(sizeof(DTD)); if (p == NULL) return p; @@ -6356,13 +6084,12 @@ dtdCreate(const XML_Memory_Handling_Suite *ms) } static void -dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) -{ +dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) { HASH_TABLE_ITER iter; hashTableIterInit(&iter, &(p->elementTypes)); for (;;) { ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!e) + if (! e) break; if (e->allocDefaultAtts != 0) ms->free_fcn(e->defaultAtts); @@ -6398,13 +6125,12 @@ dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) } static void -dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) -{ +dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) { HASH_TABLE_ITER iter; hashTableIterInit(&iter, &(p->elementTypes)); for (;;) { ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!e) + if (! e) break; if (e->allocDefaultAtts != 0) ms->free_fcn(e->defaultAtts); @@ -6429,8 +6155,8 @@ dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) The new DTD has already been initialized. */ static int -dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms) -{ +dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, + const XML_Memory_Handling_Suite *ms) { HASH_TABLE_ITER iter; /* Copy the prefix table. */ @@ -6439,12 +6165,12 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H for (;;) { const XML_Char *name; const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter); - if (!oldP) + if (! oldP) break; name = poolCopyString(&(newDtd->pool), oldP->name); - if (!name) + if (! name) return 0; - if (!lookup(oldParser, &(newDtd->prefixes), name, sizeof(PREFIX))) + if (! lookup(oldParser, &(newDtd->prefixes), name, sizeof(PREFIX))) return 0; } @@ -6457,18 +6183,18 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H const XML_Char *name; const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter); - if (!oldA) + if (! oldA) break; /* Remember to allocate the scratch byte before the name. */ - if (!poolAppendChar(&(newDtd->pool), XML_T('\0'))) + if (! poolAppendChar(&(newDtd->pool), XML_T('\0'))) return 0; name = poolCopyString(&(newDtd->pool), oldA->name); - if (!name) + if (! name) return 0; ++name; newA = (ATTRIBUTE_ID *)lookup(oldParser, &(newDtd->attributeIds), name, sizeof(ATTRIBUTE_ID)); - if (!newA) + if (! newA) return 0; newA->maybeTokenized = oldA->maybeTokenized; if (oldA->prefix) { @@ -6490,57 +6216,52 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H ELEMENT_TYPE *newE; const XML_Char *name; const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!oldE) + if (! oldE) break; name = poolCopyString(&(newDtd->pool), oldE->name); - if (!name) + if (! name) return 0; newE = (ELEMENT_TYPE *)lookup(oldParser, &(newDtd->elementTypes), name, sizeof(ELEMENT_TYPE)); - if (!newE) + if (! newE) return 0; if (oldE->nDefaultAtts) { - newE->defaultAtts = (DEFAULT_ATTRIBUTE *) - ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); - if (!newE->defaultAtts) { + newE->defaultAtts = (DEFAULT_ATTRIBUTE *)ms->malloc_fcn( + oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + if (! newE->defaultAtts) { return 0; } } if (oldE->idAtt) - newE->idAtt = (ATTRIBUTE_ID *) - lookup(oldParser, &(newDtd->attributeIds), oldE->idAtt->name, 0); + newE->idAtt = (ATTRIBUTE_ID *)lookup(oldParser, &(newDtd->attributeIds), + oldE->idAtt->name, 0); newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts; if (oldE->prefix) newE->prefix = (PREFIX *)lookup(oldParser, &(newDtd->prefixes), oldE->prefix->name, 0); for (i = 0; i < newE->nDefaultAtts; i++) { - newE->defaultAtts[i].id = (ATTRIBUTE_ID *) - lookup(oldParser, &(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0); + newE->defaultAtts[i].id = (ATTRIBUTE_ID *)lookup( + oldParser, &(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0); newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata; if (oldE->defaultAtts[i].value) { newE->defaultAtts[i].value = poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value); - if (!newE->defaultAtts[i].value) + if (! newE->defaultAtts[i].value) return 0; - } - else + } else newE->defaultAtts[i].value = NULL; } } /* Copy the entity tables. */ - if (!copyEntityTable(oldParser, - &(newDtd->generalEntities), - &(newDtd->pool), - &(oldDtd->generalEntities))) - return 0; + if (! copyEntityTable(oldParser, &(newDtd->generalEntities), &(newDtd->pool), + &(oldDtd->generalEntities))) + return 0; #ifdef XML_DTD - if (!copyEntityTable(oldParser, - &(newDtd->paramEntities), - &(newDtd->pool), - &(oldDtd->paramEntities))) - return 0; + if (! copyEntityTable(oldParser, &(newDtd->paramEntities), &(newDtd->pool), + &(oldDtd->paramEntities))) + return 0; newDtd->paramEntityRead = oldDtd->paramEntityRead; #endif /* XML_DTD */ @@ -6557,14 +6278,11 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H newDtd->scaffIndex = oldDtd->scaffIndex; return 1; -} /* End dtdCopy */ +} /* End dtdCopy */ static int -copyEntityTable(XML_Parser oldParser, - HASH_TABLE *newTable, - STRING_POOL *newPool, - const HASH_TABLE *oldTable) -{ +copyEntityTable(XML_Parser oldParser, HASH_TABLE *newTable, + STRING_POOL *newPool, const HASH_TABLE *oldTable) { HASH_TABLE_ITER iter; const XML_Char *cachedOldBase = NULL; const XML_Char *cachedNewBase = NULL; @@ -6575,17 +6293,17 @@ copyEntityTable(XML_Parser oldParser, ENTITY *newE; const XML_Char *name; const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter); - if (!oldE) + if (! oldE) break; name = poolCopyString(newPool, oldE->name); - if (!name) + if (! name) return 0; newE = (ENTITY *)lookup(oldParser, newTable, name, sizeof(ENTITY)); - if (!newE) + if (! newE) return 0; if (oldE->systemId) { const XML_Char *tem = poolCopyString(newPool, oldE->systemId); - if (!tem) + if (! tem) return 0; newE->systemId = tem; if (oldE->base) { @@ -6594,29 +6312,28 @@ copyEntityTable(XML_Parser oldParser, else { cachedOldBase = oldE->base; tem = poolCopyString(newPool, cachedOldBase); - if (!tem) + if (! tem) return 0; cachedNewBase = newE->base = tem; } } if (oldE->publicId) { tem = poolCopyString(newPool, oldE->publicId); - if (!tem) + if (! tem) return 0; newE->publicId = tem; } - } - else { - const XML_Char *tem = poolCopyStringN(newPool, oldE->textPtr, - oldE->textLen); - if (!tem) + } else { + const XML_Char *tem + = poolCopyStringN(newPool, oldE->textPtr, oldE->textLen); + if (! tem) return 0; newE->textPtr = tem; newE->textLen = oldE->textLen; } if (oldE->notation) { const XML_Char *tem = poolCopyString(newPool, oldE->notation); - if (!tem) + if (! tem) return 0; newE->notation = tem; } @@ -6629,8 +6346,7 @@ copyEntityTable(XML_Parser oldParser, #define INIT_POWER 6 static XML_Bool FASTCALL -keyeq(KEY s1, KEY s2) -{ +keyeq(KEY s1, KEY s2) { for (; *s1 == *s2; s1++, s2++) if (*s1 == 0) return XML_TRUE; @@ -6638,23 +6354,21 @@ keyeq(KEY s1, KEY s2) } static size_t -keylen(KEY s) -{ +keylen(KEY s) { size_t len = 0; - for (; *s; s++, len++); + for (; *s; s++, len++) + ; return len; } static void -copy_salt_to_sipkey(XML_Parser parser, struct sipkey * key) -{ +copy_salt_to_sipkey(XML_Parser parser, struct sipkey *key) { key->k[0] = 0; key->k[1] = get_hash_secret_salt(parser); } static unsigned long FASTCALL -hash(XML_Parser parser, KEY s) -{ +hash(XML_Parser parser, KEY s) { struct siphash state; struct sipkey key; (void)sip24_valid; @@ -6665,26 +6379,24 @@ hash(XML_Parser parser, KEY s) } static NAMED * -lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) -{ +lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) { size_t i; if (table->size == 0) { size_t tsize; - if (!createSize) + if (! createSize) return NULL; table->power = INIT_POWER; /* table->size is a power of 2 */ table->size = (size_t)1 << INIT_POWER; tsize = table->size * sizeof(NAMED *); table->v = (NAMED **)table->mem->malloc_fcn(tsize); - if (!table->v) { + if (! table->v) { table->size = 0; return NULL; } memset(table->v, 0, tsize); i = hash(parser, name) & ((unsigned long)table->size - 1); - } - else { + } else { unsigned long h = hash(parser, name); unsigned long mask = (unsigned long)table->size - 1; unsigned char step = 0; @@ -6692,11 +6404,11 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) while (table->v[i]) { if (keyeq(name, table->v[i]->name)) return table->v[i]; - if (!step) + if (! step) step = PROBE_STEP(h, mask, table->power); i < step ? (i += table->size - step) : (i -= step); } - if (!createSize) + if (! createSize) return NULL; /* check for overflow (table is half full) */ @@ -6706,7 +6418,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) unsigned long newMask = (unsigned long)newSize - 1; size_t tsize = newSize * sizeof(NAMED *); NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize); - if (!newV) + if (! newV) return NULL; memset(newV, 0, tsize); for (i = 0; i < table->size; i++) @@ -6715,7 +6427,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) size_t j = newHash & newMask; step = 0; while (newV[j]) { - if (!step) + if (! step) step = PROBE_STEP(newHash, newMask, newPower); j < step ? (j += newSize - step) : (j -= step); } @@ -6728,14 +6440,14 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) i = h & newMask; step = 0; while (table->v[i]) { - if (!step) + if (! step) step = PROBE_STEP(h, newMask, newPower); i < step ? (i += newSize - step) : (i -= step); } } } table->v[i] = (NAMED *)table->mem->malloc_fcn(createSize); - if (!table->v[i]) + if (! table->v[i]) return NULL; memset(table->v[i], 0, createSize); table->v[i]->name = name; @@ -6744,8 +6456,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) } static void FASTCALL -hashTableClear(HASH_TABLE *table) -{ +hashTableClear(HASH_TABLE *table) { size_t i; for (i = 0; i < table->size; i++) { table->mem->free_fcn(table->v[i]); @@ -6755,8 +6466,7 @@ hashTableClear(HASH_TABLE *table) } static void FASTCALL -hashTableDestroy(HASH_TABLE *table) -{ +hashTableDestroy(HASH_TABLE *table) { size_t i; for (i = 0; i < table->size; i++) table->mem->free_fcn(table->v[i]); @@ -6764,8 +6474,7 @@ hashTableDestroy(HASH_TABLE *table) } static void FASTCALL -hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) -{ +hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) { p->power = 0; p->size = 0; p->used = 0; @@ -6774,15 +6483,13 @@ hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) } static void FASTCALL -hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table) -{ +hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table) { iter->p = table->v; iter->end = iter->p + table->size; } -static NAMED * FASTCALL -hashTableIterNext(HASH_TABLE_ITER *iter) -{ +static NAMED *FASTCALL +hashTableIterNext(HASH_TABLE_ITER *iter) { while (iter->p != iter->end) { NAMED *tem = *(iter->p)++; if (tem) @@ -6792,8 +6499,7 @@ hashTableIterNext(HASH_TABLE_ITER *iter) } static void FASTCALL -poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) -{ +poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) { pool->blocks = NULL; pool->freeBlocks = NULL; pool->start = NULL; @@ -6803,9 +6509,8 @@ poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) } static void FASTCALL -poolClear(STRING_POOL *pool) -{ - if (!pool->freeBlocks) +poolClear(STRING_POOL *pool) { + if (! pool->freeBlocks) pool->freeBlocks = pool->blocks; else { BLOCK *p = pool->blocks; @@ -6823,8 +6528,7 @@ poolClear(STRING_POOL *pool) } static void FASTCALL -poolDestroy(STRING_POOL *pool) -{ +poolDestroy(STRING_POOL *pool) { BLOCK *p = pool->blocks; while (p) { BLOCK *tem = p->next; @@ -6840,26 +6544,26 @@ poolDestroy(STRING_POOL *pool) } static XML_Char * -poolAppend(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end) -{ - if (!pool->ptr && !poolGrow(pool)) +poolAppend(STRING_POOL *pool, const ENCODING *enc, const char *ptr, + const char *end) { + if (! pool->ptr && ! poolGrow(pool)) return NULL; for (;;) { - const enum XML_Convert_Result convert_res = XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) break; - if (!poolGrow(pool)) + if (! poolGrow(pool)) return NULL; } return pool->start; } -static const XML_Char * FASTCALL -poolCopyString(STRING_POOL *pool, const XML_Char *s) -{ +static const XML_Char *FASTCALL +poolCopyString(STRING_POOL *pool, const XML_Char *s) { do { - if (!poolAppendChar(pool, *s)) + if (! poolAppendChar(pool, *s)) return NULL; } while (*s++); s = pool->start; @@ -6868,9 +6572,8 @@ poolCopyString(STRING_POOL *pool, const XML_Char *s) } static const XML_Char * -poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) -{ - if (!pool->ptr && !poolGrow(pool)) { +poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) { + if (! pool->ptr && ! poolGrow(pool)) { /* The following line is unreachable given the current usage of * poolCopyStringN(). Currently it is called from exactly one * place to copy the text of a simple general entity. By that @@ -6885,7 +6588,7 @@ poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) return NULL; /* LCOV_EXCL_LINE */ } for (; n > 0; --n, s++) { - if (!poolAppendChar(pool, *s)) + if (! poolAppendChar(pool, *s)) return NULL; } s = pool->start; @@ -6893,11 +6596,10 @@ poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) return s; } -static const XML_Char * FASTCALL -poolAppendString(STRING_POOL *pool, const XML_Char *s) -{ +static const XML_Char *FASTCALL +poolAppendString(STRING_POOL *pool, const XML_Char *s) { while (*s) { - if (!poolAppendChar(pool, *s)) + if (! poolAppendChar(pool, *s)) return NULL; s++; } @@ -6905,20 +6607,18 @@ poolAppendString(STRING_POOL *pool, const XML_Char *s) } static XML_Char * -poolStoreString(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end) -{ - if (!poolAppend(pool, enc, ptr, end)) +poolStoreString(STRING_POOL *pool, const ENCODING *enc, const char *ptr, + const char *end) { + if (! poolAppend(pool, enc, ptr, end)) return NULL; - if (pool->ptr == pool->end && !poolGrow(pool)) + if (pool->ptr == pool->end && ! poolGrow(pool)) return NULL; *(pool->ptr)++ = 0; return pool->start; } static size_t -poolBytesToAllocateFor(int blockSize) -{ +poolBytesToAllocateFor(int blockSize) { /* Unprotected math would be: ** return offsetof(BLOCK, s) + blockSize * sizeof(XML_Char); ** @@ -6926,7 +6626,7 @@ poolBytesToAllocateFor(int blockSize) ** For a + b * c we check b * c in isolation first, so that addition of a ** on top has no chance of making us accept a small non-negative number */ - const size_t stretch = sizeof(XML_Char); /* can be 4 bytes */ + const size_t stretch = sizeof(XML_Char); /* can be 4 bytes */ if (blockSize <= 0) return 0; @@ -6936,8 +6636,8 @@ poolBytesToAllocateFor(int blockSize) { const int stretchedBlockSize = blockSize * (int)stretch; - const int bytesToAllocate = (int)( - offsetof(BLOCK, s) + (unsigned)stretchedBlockSize); + const int bytesToAllocate + = (int)(offsetof(BLOCK, s) + (unsigned)stretchedBlockSize); if (bytesToAllocate < 0) return 0; @@ -6946,8 +6646,7 @@ poolBytesToAllocateFor(int blockSize) } static XML_Bool FASTCALL -poolGrow(STRING_POOL *pool) -{ +poolGrow(STRING_POOL *pool) { if (pool->freeBlocks) { if (pool->start == 0) { pool->blocks = pool->freeBlocks; @@ -6973,7 +6672,7 @@ poolGrow(STRING_POOL *pool) } if (pool->blocks && pool->start == pool->blocks->s) { BLOCK *temp; - int blockSize = (int)((unsigned)(pool->end - pool->start)*2U); + int blockSize = (int)((unsigned)(pool->end - pool->start) * 2U); size_t bytesToAllocate; /* NOTE: Needs to be calculated prior to calling `realloc` @@ -6994,8 +6693,8 @@ poolGrow(STRING_POOL *pool) if (bytesToAllocate == 0) return XML_FALSE; - temp = (BLOCK *) - pool->mem->realloc_fcn(pool->blocks, (unsigned)bytesToAllocate); + temp = (BLOCK *)pool->mem->realloc_fcn(pool->blocks, + (unsigned)bytesToAllocate); if (temp == NULL) return XML_FALSE; pool->blocks = temp; @@ -7003,8 +6702,7 @@ poolGrow(STRING_POOL *pool) pool->ptr = pool->blocks->s + offsetInsideBlock; pool->start = pool->blocks->s; pool->end = pool->start + blockSize; - } - else { + } else { BLOCK *tem; int blockSize = (int)(pool->end - pool->start); size_t bytesToAllocate; @@ -7019,7 +6717,7 @@ poolGrow(STRING_POOL *pool) * function). Either way it isn't readily testable, so we * exclude it from the coverage statistics. */ - return XML_FALSE; /* LCOV_EXCL_LINE */ + return XML_FALSE; /* LCOV_EXCL_LINE */ } if (blockSize < INIT_BLOCK_SIZE) @@ -7037,14 +6735,13 @@ poolGrow(STRING_POOL *pool) return XML_FALSE; tem = (BLOCK *)pool->mem->malloc_fcn(bytesToAllocate); - if (!tem) + if (! tem) return XML_FALSE; tem->size = blockSize; tem->next = pool->blocks; pool->blocks = tem; if (pool->ptr != pool->start) - memcpy(tem->s, pool->start, - (pool->ptr - pool->start) * sizeof(XML_Char)); + memcpy(tem->s, pool->start, (pool->ptr - pool->start) * sizeof(XML_Char)); pool->ptr = tem->s + (pool->ptr - pool->start); pool->start = tem->s; pool->end = tem->s + blockSize; @@ -7053,15 +6750,14 @@ poolGrow(STRING_POOL *pool) } static int FASTCALL -nextScaffoldPart(XML_Parser parser) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ - CONTENT_SCAFFOLD * me; +nextScaffoldPart(XML_Parser parser) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + CONTENT_SCAFFOLD *me; int next; - if (!dtd->scaffIndex) { + if (! dtd->scaffIndex) { dtd->scaffIndex = (int *)MALLOC(parser, parser->m_groupSize * sizeof(int)); - if (!dtd->scaffIndex) + if (! dtd->scaffIndex) return -1; dtd->scaffIndex[0] = 0; } @@ -7069,15 +6765,14 @@ nextScaffoldPart(XML_Parser parser) if (dtd->scaffCount >= dtd->scaffSize) { CONTENT_SCAFFOLD *temp; if (dtd->scaffold) { - temp = (CONTENT_SCAFFOLD *) - REALLOC(parser, dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD)); + temp = (CONTENT_SCAFFOLD *)REALLOC( + parser, dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD)); if (temp == NULL) return -1; dtd->scaffSize *= 2; - } - else { + } else { temp = (CONTENT_SCAFFOLD *)MALLOC(parser, INIT_SCAFFOLD_ELEMENTS - * sizeof(CONTENT_SCAFFOLD)); + * sizeof(CONTENT_SCAFFOLD)); if (temp == NULL) return -1; dtd->scaffSize = INIT_SCAFFOLD_ELEMENTS; @@ -7087,11 +6782,12 @@ nextScaffoldPart(XML_Parser parser) next = dtd->scaffCount++; me = &dtd->scaffold[next]; if (dtd->scaffLevel) { - CONTENT_SCAFFOLD *parent = &dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel-1]]; + CONTENT_SCAFFOLD *parent + = &dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]]; if (parent->lastchild) { dtd->scaffold[parent->lastchild].nextsib = next; } - if (!parent->childcnt) + if (! parent->childcnt) parent->firstchild = next; parent->lastchild = next; parent->childcnt++; @@ -7101,13 +6797,9 @@ nextScaffoldPart(XML_Parser parser) } static void -build_node(XML_Parser parser, - int src_node, - XML_Content *dest, - XML_Content **contpos, - XML_Char **strpos) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +build_node(XML_Parser parser, int src_node, XML_Content *dest, + XML_Content **contpos, XML_Char **strpos) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ dest->type = dtd->scaffold[src_node].type; dest->quant = dtd->scaffold[src_node].quant; if (dest->type == XML_CTYPE_NAME) { @@ -7116,21 +6808,19 @@ build_node(XML_Parser parser, src = dtd->scaffold[src_node].name; for (;;) { *(*strpos)++ = *src; - if (!*src) + if (! *src) break; src++; } dest->numchildren = 0; dest->children = NULL; - } - else { + } else { unsigned int i; int cn; dest->numchildren = dtd->scaffold[src_node].childcnt; dest->children = *contpos; *contpos += dest->numchildren; - for (i = 0, cn = dtd->scaffold[src_node].firstchild; - i < dest->numchildren; + for (i = 0, cn = dtd->scaffold[src_node].firstchild; i < dest->numchildren; i++, cn = dtd->scaffold[cn].nextsib) { build_node(parser, cn, &(dest->children[i]), contpos, strpos); } @@ -7139,20 +6829,19 @@ build_node(XML_Parser parser, } static XML_Content * -build_model (XML_Parser parser) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +build_model(XML_Parser parser) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ XML_Content *ret; XML_Content *cpos; - XML_Char * str; + XML_Char *str; int allocsize = (dtd->scaffCount * sizeof(XML_Content) + (dtd->contentStringLen * sizeof(XML_Char))); ret = (XML_Content *)MALLOC(parser, allocsize); - if (!ret) + if (! ret) return NULL; - str = (XML_Char *) (&ret[dtd->scaffCount]); + str = (XML_Char *)(&ret[dtd->scaffCount]); cpos = &ret[1]; build_node(parser, 0, ret, &cpos, &str); @@ -7160,49 +6849,45 @@ build_model (XML_Parser parser) } static ELEMENT_TYPE * -getElementType(XML_Parser parser, - const ENCODING *enc, - const char *ptr, - const char *end) -{ - DTD * const dtd = parser->m_dtd; /* save one level of indirection */ +getElementType(XML_Parser parser, const ENCODING *enc, const char *ptr, + const char *end) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ const XML_Char *name = poolStoreString(&dtd->pool, enc, ptr, end); ELEMENT_TYPE *ret; - if (!name) + if (! name) return NULL; - ret = (ELEMENT_TYPE *) lookup(parser, &dtd->elementTypes, name, sizeof(ELEMENT_TYPE)); - if (!ret) + ret = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, name, + sizeof(ELEMENT_TYPE)); + if (! ret) return NULL; if (ret->name != name) poolDiscard(&dtd->pool); else { poolFinish(&dtd->pool); - if (!setElementTypePrefix(parser, ret)) + if (! setElementTypePrefix(parser, ret)) return NULL; } return ret; } static XML_Char * -copyString(const XML_Char *s, - const XML_Memory_Handling_Suite *memsuite) -{ - int charsRequired = 0; - XML_Char *result; - - /* First determine how long the string is */ - while (s[charsRequired] != 0) { - charsRequired++; - } - /* Include the terminator */ +copyString(const XML_Char *s, const XML_Memory_Handling_Suite *memsuite) { + int charsRequired = 0; + XML_Char *result; + + /* First determine how long the string is */ + while (s[charsRequired] != 0) { charsRequired++; + } + /* Include the terminator */ + charsRequired++; - /* Now allocate space for the copy */ - result = memsuite->malloc_fcn(charsRequired * sizeof(XML_Char)); - if (result == NULL) - return NULL; - /* Copy the original into place */ - memcpy(result, s, charsRequired * sizeof(XML_Char)); - return result; + /* Now allocate space for the copy */ + result = memsuite->malloc_fcn(charsRequired * sizeof(XML_Char)); + if (result == NULL) + return NULL; + /* Copy the original into place */ + memcpy(result, s, charsRequired * sizeof(XML_Char)); + return result; } diff --git a/Modules/expat/xmlrole.c b/Modules/expat/xmlrole.c index 708507d5..4d3e3e86 100644 --- a/Modules/expat/xmlrole.c +++ b/Modules/expat/xmlrole.c @@ -33,11 +33,11 @@ #include #ifdef _WIN32 -#include "winconfig.h" +# include "winconfig.h" #else -#ifdef HAVE_EXPAT_CONFIG_H -#include -#endif +# ifdef HAVE_EXPAT_CONFIG_H +# include +# endif #endif /* ndef _WIN32 */ #include "expat_external.h" @@ -52,107 +52,88 @@ */ -static const char KW_ANY[] = { - ASCII_A, ASCII_N, ASCII_Y, '\0' }; -static const char KW_ATTLIST[] = { - ASCII_A, ASCII_T, ASCII_T, ASCII_L, ASCII_I, ASCII_S, ASCII_T, '\0' }; -static const char KW_CDATA[] = { - ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; -static const char KW_DOCTYPE[] = { - ASCII_D, ASCII_O, ASCII_C, ASCII_T, ASCII_Y, ASCII_P, ASCII_E, '\0' }; -static const char KW_ELEMENT[] = { - ASCII_E, ASCII_L, ASCII_E, ASCII_M, ASCII_E, ASCII_N, ASCII_T, '\0' }; -static const char KW_EMPTY[] = { - ASCII_E, ASCII_M, ASCII_P, ASCII_T, ASCII_Y, '\0' }; -static const char KW_ENTITIES[] = { - ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, - '\0' }; -static const char KW_ENTITY[] = { - ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' }; -static const char KW_FIXED[] = { - ASCII_F, ASCII_I, ASCII_X, ASCII_E, ASCII_D, '\0' }; -static const char KW_ID[] = { - ASCII_I, ASCII_D, '\0' }; -static const char KW_IDREF[] = { - ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' }; -static const char KW_IDREFS[] = { - ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' }; +static const char KW_ANY[] = {ASCII_A, ASCII_N, ASCII_Y, '\0'}; +static const char KW_ATTLIST[] + = {ASCII_A, ASCII_T, ASCII_T, ASCII_L, ASCII_I, ASCII_S, ASCII_T, '\0'}; +static const char KW_CDATA[] + = {ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_DOCTYPE[] + = {ASCII_D, ASCII_O, ASCII_C, ASCII_T, ASCII_Y, ASCII_P, ASCII_E, '\0'}; +static const char KW_ELEMENT[] + = {ASCII_E, ASCII_L, ASCII_E, ASCII_M, ASCII_E, ASCII_N, ASCII_T, '\0'}; +static const char KW_EMPTY[] + = {ASCII_E, ASCII_M, ASCII_P, ASCII_T, ASCII_Y, '\0'}; +static const char KW_ENTITIES[] = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, + ASCII_I, ASCII_E, ASCII_S, '\0'}; +static const char KW_ENTITY[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0'}; +static const char KW_FIXED[] + = {ASCII_F, ASCII_I, ASCII_X, ASCII_E, ASCII_D, '\0'}; +static const char KW_ID[] = {ASCII_I, ASCII_D, '\0'}; +static const char KW_IDREF[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0'}; +static const char KW_IDREFS[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0'}; #ifdef XML_DTD -static const char KW_IGNORE[] = { - ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0' }; +static const char KW_IGNORE[] + = {ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0'}; #endif -static const char KW_IMPLIED[] = { - ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0' }; +static const char KW_IMPLIED[] + = {ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0'}; #ifdef XML_DTD -static const char KW_INCLUDE[] = { - ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0' }; +static const char KW_INCLUDE[] + = {ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0'}; #endif -static const char KW_NDATA[] = { - ASCII_N, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; -static const char KW_NMTOKEN[] = { - ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' }; -static const char KW_NMTOKENS[] = { - ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, - '\0' }; -static const char KW_NOTATION[] = - { ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, - '\0' }; -static const char KW_PCDATA[] = { - ASCII_P, ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; -static const char KW_PUBLIC[] = { - ASCII_P, ASCII_U, ASCII_B, ASCII_L, ASCII_I, ASCII_C, '\0' }; -static const char KW_REQUIRED[] = { - ASCII_R, ASCII_E, ASCII_Q, ASCII_U, ASCII_I, ASCII_R, ASCII_E, ASCII_D, - '\0' }; -static const char KW_SYSTEM[] = { - ASCII_S, ASCII_Y, ASCII_S, ASCII_T, ASCII_E, ASCII_M, '\0' }; +static const char KW_NDATA[] + = {ASCII_N, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_NMTOKEN[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0'}; +static const char KW_NMTOKENS[] = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, + ASCII_E, ASCII_N, ASCII_S, '\0'}; +static const char KW_NOTATION[] = {ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, + ASCII_I, ASCII_O, ASCII_N, '\0'}; +static const char KW_PCDATA[] + = {ASCII_P, ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_PUBLIC[] + = {ASCII_P, ASCII_U, ASCII_B, ASCII_L, ASCII_I, ASCII_C, '\0'}; +static const char KW_REQUIRED[] = {ASCII_R, ASCII_E, ASCII_Q, ASCII_U, ASCII_I, + ASCII_R, ASCII_E, ASCII_D, '\0'}; +static const char KW_SYSTEM[] + = {ASCII_S, ASCII_Y, ASCII_S, ASCII_T, ASCII_E, ASCII_M, '\0'}; #ifndef MIN_BYTES_PER_CHAR -#define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar) +# define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar) #endif #ifdef XML_DTD -#define setTopLevel(state) \ - ((state)->handler = ((state)->documentEntity \ - ? internalSubset \ - : externalSubset1)) +# define setTopLevel(state) \ + ((state)->handler \ + = ((state)->documentEntity ? internalSubset : externalSubset1)) #else /* not XML_DTD */ -#define setTopLevel(state) ((state)->handler = internalSubset) +# define setTopLevel(state) ((state)->handler = internalSubset) #endif /* not XML_DTD */ -typedef int PTRCALL PROLOG_HANDLER(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, +typedef int PTRCALL PROLOG_HANDLER(PROLOG_STATE *state, int tok, + const char *ptr, const char *end, const ENCODING *enc); -static PROLOG_HANDLER - prolog0, prolog1, prolog2, - doctype0, doctype1, doctype2, doctype3, doctype4, doctype5, - internalSubset, - entity0, entity1, entity2, entity3, entity4, entity5, entity6, - entity7, entity8, entity9, entity10, - notation0, notation1, notation2, notation3, notation4, - attlist0, attlist1, attlist2, attlist3, attlist4, attlist5, attlist6, - attlist7, attlist8, attlist9, - element0, element1, element2, element3, element4, element5, element6, - element7, +static PROLOG_HANDLER prolog0, prolog1, prolog2, doctype0, doctype1, doctype2, + doctype3, doctype4, doctype5, internalSubset, entity0, entity1, entity2, + entity3, entity4, entity5, entity6, entity7, entity8, entity9, entity10, + notation0, notation1, notation2, notation3, notation4, attlist0, attlist1, + attlist2, attlist3, attlist4, attlist5, attlist6, attlist7, attlist8, + attlist9, element0, element1, element2, element3, element4, element5, + element6, element7, #ifdef XML_DTD - externalSubset0, externalSubset1, - condSect0, condSect1, condSect2, + externalSubset0, externalSubset1, condSect0, condSect1, condSect2, #endif /* XML_DTD */ - declClose, - error; + declClose, error; static int FASTCALL common(PROLOG_STATE *state, int tok); static int PTRCALL -prolog0(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +prolog0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: state->handler = prolog1; @@ -169,10 +150,8 @@ prolog0(PROLOG_STATE *state, case XML_TOK_BOM: return XML_ROLE_NONE; case XML_TOK_DECL_OPEN: - if (!XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, - KW_DOCTYPE)) + if (! XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_DOCTYPE)) break; state->handler = doctype0; return XML_ROLE_DOCTYPE_NONE; @@ -184,12 +163,8 @@ prolog0(PROLOG_STATE *state, } static int PTRCALL -prolog1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +prolog1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -207,10 +182,8 @@ prolog1(PROLOG_STATE *state, */ return XML_ROLE_NONE; /* LCOV_EXCL_LINE */ case XML_TOK_DECL_OPEN: - if (!XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, - KW_DOCTYPE)) + if (! XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_DOCTYPE)) break; state->handler = doctype0; return XML_ROLE_DOCTYPE_NONE; @@ -222,12 +195,11 @@ prolog1(PROLOG_STATE *state, } static int PTRCALL -prolog2(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +prolog2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -243,12 +215,11 @@ prolog2(PROLOG_STATE *state, } static int PTRCALL -doctype0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -261,12 +232,8 @@ doctype0(PROLOG_STATE *state, } static int PTRCALL -doctype1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +doctype1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -291,12 +258,11 @@ doctype1(PROLOG_STATE *state, } static int PTRCALL -doctype2(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -308,12 +274,11 @@ doctype2(PROLOG_STATE *state, } static int PTRCALL -doctype3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -325,12 +290,11 @@ doctype3(PROLOG_STATE *state, } static int PTRCALL -doctype4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -345,12 +309,11 @@ doctype4(PROLOG_STATE *state, } static int PTRCALL -doctype5(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -362,40 +325,28 @@ doctype5(PROLOG_STATE *state, } static int PTRCALL -internalSubset(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +internalSubset(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; case XML_TOK_DECL_OPEN: - if (XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, KW_ENTITY)) { state->handler = entity0; return XML_ROLE_ENTITY_NONE; } - if (XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, KW_ATTLIST)) { state->handler = attlist0; return XML_ROLE_ATTLIST_NONE; } - if (XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, KW_ELEMENT)) { state->handler = element0; return XML_ROLE_ELEMENT_NONE; } - if (XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, KW_NOTATION)) { state->handler = notation0; return XML_ROLE_NOTATION_NONE; @@ -419,12 +370,8 @@ internalSubset(PROLOG_STATE *state, #ifdef XML_DTD static int PTRCALL -externalSubset0(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +externalSubset0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { state->handler = externalSubset1; if (tok == XML_TOK_XML_DECL) return XML_ROLE_TEXT_DECL; @@ -432,12 +379,8 @@ externalSubset0(PROLOG_STATE *state, } static int PTRCALL -externalSubset1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +externalSubset1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_COND_SECT_OPEN: state->handler = condSect0; @@ -464,12 +407,11 @@ externalSubset1(PROLOG_STATE *state, #endif /* XML_DTD */ static int PTRCALL -entity0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -484,12 +426,11 @@ entity0(PROLOG_STATE *state, } static int PTRCALL -entity1(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -501,12 +442,8 @@ entity1(PROLOG_STATE *state, } static int PTRCALL -entity2(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +entity2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -529,12 +466,11 @@ entity2(PROLOG_STATE *state, } static int PTRCALL -entity3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -546,12 +482,11 @@ entity3(PROLOG_STATE *state, } static int PTRCALL -entity4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -563,12 +498,8 @@ entity4(PROLOG_STATE *state, } static int PTRCALL -entity5(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +entity5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -586,12 +517,11 @@ entity5(PROLOG_STATE *state, } static int PTRCALL -entity6(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -604,12 +534,8 @@ entity6(PROLOG_STATE *state, } static int PTRCALL -entity7(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +entity7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -632,12 +558,11 @@ entity7(PROLOG_STATE *state, } static int PTRCALL -entity8(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity8(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -649,12 +574,11 @@ entity8(PROLOG_STATE *state, } static int PTRCALL -entity9(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity9(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -666,12 +590,11 @@ entity9(PROLOG_STATE *state, } static int PTRCALL -entity10(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity10(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -683,12 +606,11 @@ entity10(PROLOG_STATE *state, } static int PTRCALL -notation0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +notation0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -700,12 +622,8 @@ notation0(PROLOG_STATE *state, } static int PTRCALL -notation1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +notation1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -724,12 +642,11 @@ notation1(PROLOG_STATE *state, } static int PTRCALL -notation2(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +notation2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -741,12 +658,11 @@ notation2(PROLOG_STATE *state, } static int PTRCALL -notation3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +notation3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -759,12 +675,11 @@ notation3(PROLOG_STATE *state, } static int PTRCALL -notation4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +notation4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -780,12 +695,11 @@ notation4(PROLOG_STATE *state, } static int PTRCALL -attlist0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -798,12 +712,11 @@ attlist0(PROLOG_STATE *state, } static int PTRCALL -attlist1(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -819,34 +732,23 @@ attlist1(PROLOG_STATE *state, } static int PTRCALL -attlist2(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +attlist2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; - case XML_TOK_NAME: - { - static const char * const types[] = { - KW_CDATA, - KW_ID, - KW_IDREF, - KW_IDREFS, - KW_ENTITY, - KW_ENTITIES, - KW_NMTOKEN, - KW_NMTOKENS, - }; - int i; - for (i = 0; i < (int)(sizeof(types)/sizeof(types[0])); i++) - if (XmlNameMatchesAscii(enc, ptr, end, types[i])) { - state->handler = attlist8; - return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i; - } - } + case XML_TOK_NAME: { + static const char *const types[] = { + KW_CDATA, KW_ID, KW_IDREF, KW_IDREFS, + KW_ENTITY, KW_ENTITIES, KW_NMTOKEN, KW_NMTOKENS, + }; + int i; + for (i = 0; i < (int)(sizeof(types) / sizeof(types[0])); i++) + if (XmlNameMatchesAscii(enc, ptr, end, types[i])) { + state->handler = attlist8; + return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i; + } + } if (XmlNameMatchesAscii(enc, ptr, end, KW_NOTATION)) { state->handler = attlist5; return XML_ROLE_ATTLIST_NONE; @@ -860,12 +762,11 @@ attlist2(PROLOG_STATE *state, } static int PTRCALL -attlist3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -879,12 +780,11 @@ attlist3(PROLOG_STATE *state, } static int PTRCALL -attlist4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -899,12 +799,11 @@ attlist4(PROLOG_STATE *state, } static int PTRCALL -attlist5(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -916,12 +815,11 @@ attlist5(PROLOG_STATE *state, } static int PTRCALL -attlist6(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -933,12 +831,11 @@ attlist6(PROLOG_STATE *state, } static int PTRCALL -attlist7(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -954,33 +851,23 @@ attlist7(PROLOG_STATE *state, /* default value */ static int PTRCALL -attlist8(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +attlist8(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; case XML_TOK_POUND_NAME: - if (XmlNameMatchesAscii(enc, - ptr + MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, KW_IMPLIED)) { state->handler = attlist1; return XML_ROLE_IMPLIED_ATTRIBUTE_VALUE; } - if (XmlNameMatchesAscii(enc, - ptr + MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, KW_REQUIRED)) { state->handler = attlist1; return XML_ROLE_REQUIRED_ATTRIBUTE_VALUE; } - if (XmlNameMatchesAscii(enc, - ptr + MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, KW_FIXED)) { state->handler = attlist9; return XML_ROLE_ATTLIST_NONE; @@ -994,12 +881,11 @@ attlist8(PROLOG_STATE *state, } static int PTRCALL -attlist9(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist9(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -1011,12 +897,11 @@ attlist9(PROLOG_STATE *state, } static int PTRCALL -element0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1029,12 +914,8 @@ element0(PROLOG_STATE *state, } static int PTRCALL -element1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +element1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1059,19 +940,13 @@ element1(PROLOG_STATE *state, } static int PTRCALL -element2(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +element2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; case XML_TOK_POUND_NAME: - if (XmlNameMatchesAscii(enc, - ptr + MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, KW_PCDATA)) { state->handler = element3; return XML_ROLE_CONTENT_PCDATA; @@ -1099,12 +974,11 @@ element2(PROLOG_STATE *state, } static int PTRCALL -element3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1124,12 +998,11 @@ element3(PROLOG_STATE *state, } static int PTRCALL -element4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1142,12 +1015,11 @@ element4(PROLOG_STATE *state, } static int PTRCALL -element5(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1163,12 +1035,11 @@ element5(PROLOG_STATE *state, } static int PTRCALL -element6(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1193,12 +1064,11 @@ element6(PROLOG_STATE *state, } static int PTRCALL -element7(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1243,12 +1113,8 @@ element7(PROLOG_STATE *state, #ifdef XML_DTD static int PTRCALL -condSect0(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +condSect0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -1267,12 +1133,11 @@ condSect0(PROLOG_STATE *state, } static int PTRCALL -condSect1(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +condSect1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -1285,12 +1150,11 @@ condSect1(PROLOG_STATE *state, } static int PTRCALL -condSect2(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +condSect2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -1304,12 +1168,11 @@ condSect2(PROLOG_STATE *state, #endif /* XML_DTD */ static int PTRCALL -declClose(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +declClose(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return state->role_none; @@ -1341,21 +1204,21 @@ declClose(PROLOG_STATE *state, * LCOV_EXCL_START */ static int PTRCALL -error(PROLOG_STATE *UNUSED_P(state), - int UNUSED_P(tok), - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +error(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(state); + UNUSED_P(tok); + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); return XML_ROLE_NONE; } /* LCOV_EXCL_STOP */ static int FASTCALL -common(PROLOG_STATE *state, int tok) -{ +common(PROLOG_STATE *state, int tok) { #ifdef XML_DTD - if (!state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF) + if (! state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF) return XML_ROLE_INNER_PARAM_ENTITY_REF; #endif state->handler = error; @@ -1363,8 +1226,7 @@ common(PROLOG_STATE *state, int tok) } void -XmlPrologStateInit(PROLOG_STATE *state) -{ +XmlPrologStateInit(PROLOG_STATE *state) { state->handler = prolog0; #ifdef XML_DTD state->documentEntity = 1; @@ -1376,8 +1238,7 @@ XmlPrologStateInit(PROLOG_STATE *state) #ifdef XML_DTD void -XmlPrologStateInitExternalEntity(PROLOG_STATE *state) -{ +XmlPrologStateInitExternalEntity(PROLOG_STATE *state) { state->handler = externalSubset0; state->documentEntity = 0; state->includeLevel = 0; diff --git a/Modules/expat/xmlrole.h b/Modules/expat/xmlrole.h index e5f048ea..036aba64 100644 --- a/Modules/expat/xmlrole.h +++ b/Modules/expat/xmlrole.h @@ -36,7 +36,7 @@ #ifdef __VMS /* 0 1 2 3 0 1 2 3 1234567890123456789012345678901 1234567890123456789012345678901 */ -#define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt +# define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt #endif #include "xmltok.h" @@ -113,11 +113,8 @@ enum { }; typedef struct prolog_state { - int (PTRCALL *handler) (struct prolog_state *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc); + int(PTRCALL *handler)(struct prolog_state *state, int tok, const char *ptr, + const char *end, const ENCODING *enc); unsigned level; int role_none; #ifdef XML_DTD @@ -132,8 +129,8 @@ void XmlPrologStateInit(PROLOG_STATE *); void XmlPrologStateInitExternalEntity(PROLOG_STATE *); #endif /* XML_DTD */ -#define XmlTokenRole(state, tok, ptr, end, enc) \ - (((state)->handler)(state, tok, ptr, end, enc)) +#define XmlTokenRole(state, tok, ptr, end, enc) \ + (((state)->handler)(state, tok, ptr, end, enc)) #ifdef __cplusplus } diff --git a/Modules/expat/xmltok.c b/Modules/expat/xmltok.c index 6b415d83..11e9d1cc 100644 --- a/Modules/expat/xmltok.c +++ b/Modules/expat/xmltok.c @@ -31,24 +31,23 @@ */ #include -#include /* memcpy */ +#include /* memcpy */ #if defined(_MSC_VER) && (_MSC_VER <= 1700) - /* for vs2012/11.0/1700 and earlier Visual Studio compilers */ -# define bool int -# define false 0 -# define true 1 +/* for vs2012/11.0/1700 and earlier Visual Studio compilers */ +# define bool int +# define false 0 +# define true 1 #else -# include +# include #endif - #ifdef _WIN32 -#include "winconfig.h" +# include "winconfig.h" #else -#ifdef HAVE_EXPAT_CONFIG_H -#include -#endif +# ifdef HAVE_EXPAT_CONFIG_H +# include +# endif #endif /* ndef _WIN32 */ #include "expat_external.h" @@ -57,58 +56,49 @@ #include "nametab.h" #ifdef XML_DTD -#define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok) +# define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok) #else -#define IGNORE_SECTION_TOK_VTABLE /* as nothing */ +# define IGNORE_SECTION_TOK_VTABLE /* as nothing */ #endif -#define VTABLE1 \ - { PREFIX(prologTok), PREFIX(contentTok), \ - PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE }, \ - { PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \ - PREFIX(nameMatchesAscii), \ - PREFIX(nameLength), \ - PREFIX(skipS), \ - PREFIX(getAtts), \ - PREFIX(charRefNumber), \ - PREFIX(predefinedEntityName), \ - PREFIX(updatePosition), \ - PREFIX(isPublicId) +#define VTABLE1 \ + {PREFIX(prologTok), PREFIX(contentTok), \ + PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE}, \ + {PREFIX(attributeValueTok), PREFIX(entityValueTok)}, \ + PREFIX(nameMatchesAscii), PREFIX(nameLength), PREFIX(skipS), \ + PREFIX(getAtts), PREFIX(charRefNumber), PREFIX(predefinedEntityName), \ + PREFIX(updatePosition), PREFIX(isPublicId) #define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16) -#define UCS2_GET_NAMING(pages, hi, lo) \ - (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((lo) & 0x1F))) +#define UCS2_GET_NAMING(pages, hi, lo) \ + (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((lo)&0x1F))) /* A 2 byte UTF-8 representation splits the characters 11 bits between the bottom 5 and 6 bits of the bytes. We need 8 bits to index into pages, 3 bits to add to that index and 5 bits to generate the mask. */ -#define UTF8_GET_NAMING2(pages, byte) \ - (namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \ - + ((((byte)[0]) & 3) << 1) \ - + ((((byte)[1]) >> 5) & 1)] \ - & (1u << (((byte)[1]) & 0x1F))) +#define UTF8_GET_NAMING2(pages, byte) \ + (namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \ + + ((((byte)[0]) & 3) << 1) + ((((byte)[1]) >> 5) & 1)] \ + & (1u << (((byte)[1]) & 0x1F))) /* A 3 byte UTF-8 representation splits the characters 16 bits between the bottom 4, 6 and 6 bits of the bytes. We need 8 bits to index into pages, 3 bits to add to that index and 5 bits to generate the mask. */ -#define UTF8_GET_NAMING3(pages, byte) \ - (namingBitmap[((pages)[((((byte)[0]) & 0xF) << 4) \ - + ((((byte)[1]) >> 2) & 0xF)] \ - << 3) \ - + ((((byte)[1]) & 3) << 1) \ - + ((((byte)[2]) >> 5) & 1)] \ - & (1u << (((byte)[2]) & 0x1F))) - -#define UTF8_GET_NAMING(pages, p, n) \ - ((n) == 2 \ - ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \ - : ((n) == 3 \ - ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) \ - : 0)) +#define UTF8_GET_NAMING3(pages, byte) \ + (namingBitmap \ + [((pages)[((((byte)[0]) & 0xF) << 4) + ((((byte)[1]) >> 2) & 0xF)] \ + << 3) \ + + ((((byte)[1]) & 3) << 1) + ((((byte)[2]) >> 5) & 1)] \ + & (1u << (((byte)[2]) & 0x1F))) + +#define UTF8_GET_NAMING(pages, p, n) \ + ((n) == 2 \ + ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \ + : ((n) == 3 ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) : 0)) /* Detection of invalid UTF-8 sequences is based on Table 3.1B of Unicode 3.2: http://www.unicode.org/unicode/reports/tr28/ @@ -120,88 +110,76 @@ (A & 0xC0) == 0xC0 means A > 0xBF */ -#define UTF8_INVALID2(p) \ +#define UTF8_INVALID2(p) \ ((*p) < 0xC2 || ((p)[1] & 0x80) == 0 || ((p)[1] & 0xC0) == 0xC0) -#define UTF8_INVALID3(p) \ - (((p)[2] & 0x80) == 0 \ - || \ - ((*p) == 0xEF && (p)[1] == 0xBF \ - ? \ - (p)[2] > 0xBD \ - : \ - ((p)[2] & 0xC0) == 0xC0) \ - || \ - ((*p) == 0xE0 \ - ? \ - (p)[1] < 0xA0 || ((p)[1] & 0xC0) == 0xC0 \ - : \ - ((p)[1] & 0x80) == 0 \ - || \ - ((*p) == 0xED ? (p)[1] > 0x9F : ((p)[1] & 0xC0) == 0xC0))) - -#define UTF8_INVALID4(p) \ - (((p)[3] & 0x80) == 0 || ((p)[3] & 0xC0) == 0xC0 \ - || \ - ((p)[2] & 0x80) == 0 || ((p)[2] & 0xC0) == 0xC0 \ - || \ - ((*p) == 0xF0 \ - ? \ - (p)[1] < 0x90 || ((p)[1] & 0xC0) == 0xC0 \ - : \ - ((p)[1] & 0x80) == 0 \ - || \ - ((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0))) +#define UTF8_INVALID3(p) \ + (((p)[2] & 0x80) == 0 \ + || ((*p) == 0xEF && (p)[1] == 0xBF ? (p)[2] > 0xBD \ + : ((p)[2] & 0xC0) == 0xC0) \ + || ((*p) == 0xE0 \ + ? (p)[1] < 0xA0 || ((p)[1] & 0xC0) == 0xC0 \ + : ((p)[1] & 0x80) == 0 \ + || ((*p) == 0xED ? (p)[1] > 0x9F : ((p)[1] & 0xC0) == 0xC0))) + +#define UTF8_INVALID4(p) \ + (((p)[3] & 0x80) == 0 || ((p)[3] & 0xC0) == 0xC0 || ((p)[2] & 0x80) == 0 \ + || ((p)[2] & 0xC0) == 0xC0 \ + || ((*p) == 0xF0 \ + ? (p)[1] < 0x90 || ((p)[1] & 0xC0) == 0xC0 \ + : ((p)[1] & 0x80) == 0 \ + || ((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0))) static int PTRFASTCALL -isNever(const ENCODING *UNUSED_P(enc), const char *UNUSED_P(p)) -{ +isNever(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + UNUSED_P(p); return 0; } static int PTRFASTCALL -utf8_isName2(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isName2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_GET_NAMING2(namePages, (const unsigned char *)p); } static int PTRFASTCALL -utf8_isName3(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isName3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_GET_NAMING3(namePages, (const unsigned char *)p); } #define utf8_isName4 isNever static int PTRFASTCALL -utf8_isNmstrt2(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isNmstrt2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p); } static int PTRFASTCALL -utf8_isNmstrt3(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isNmstrt3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p); } #define utf8_isNmstrt4 isNever static int PTRFASTCALL -utf8_isInvalid2(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isInvalid2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_INVALID2((const unsigned char *)p); } static int PTRFASTCALL -utf8_isInvalid3(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isInvalid3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_INVALID3((const unsigned char *)p); } static int PTRFASTCALL -utf8_isInvalid4(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isInvalid4(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_INVALID4((const unsigned char *)p); } @@ -209,61 +187,44 @@ struct normal_encoding { ENCODING enc; unsigned char type[256]; #ifdef XML_MIN_SIZE - int (PTRFASTCALL *byteType)(const ENCODING *, const char *); - int (PTRFASTCALL *isNameMin)(const ENCODING *, const char *); - int (PTRFASTCALL *isNmstrtMin)(const ENCODING *, const char *); - int (PTRFASTCALL *byteToAscii)(const ENCODING *, const char *); - int (PTRCALL *charMatches)(const ENCODING *, const char *, int); + int(PTRFASTCALL *byteType)(const ENCODING *, const char *); + int(PTRFASTCALL *isNameMin)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrtMin)(const ENCODING *, const char *); + int(PTRFASTCALL *byteToAscii)(const ENCODING *, const char *); + int(PTRCALL *charMatches)(const ENCODING *, const char *, int); #endif /* XML_MIN_SIZE */ - int (PTRFASTCALL *isName2)(const ENCODING *, const char *); - int (PTRFASTCALL *isName3)(const ENCODING *, const char *); - int (PTRFASTCALL *isName4)(const ENCODING *, const char *); - int (PTRFASTCALL *isNmstrt2)(const ENCODING *, const char *); - int (PTRFASTCALL *isNmstrt3)(const ENCODING *, const char *); - int (PTRFASTCALL *isNmstrt4)(const ENCODING *, const char *); - int (PTRFASTCALL *isInvalid2)(const ENCODING *, const char *); - int (PTRFASTCALL *isInvalid3)(const ENCODING *, const char *); - int (PTRFASTCALL *isInvalid4)(const ENCODING *, const char *); + int(PTRFASTCALL *isName2)(const ENCODING *, const char *); + int(PTRFASTCALL *isName3)(const ENCODING *, const char *); + int(PTRFASTCALL *isName4)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt2)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt3)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt4)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid2)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid3)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid4)(const ENCODING *, const char *); }; -#define AS_NORMAL_ENCODING(enc) ((const struct normal_encoding *) (enc)) +#define AS_NORMAL_ENCODING(enc) ((const struct normal_encoding *)(enc)) #ifdef XML_MIN_SIZE -#define STANDARD_VTABLE(E) \ - E ## byteType, \ - E ## isNameMin, \ - E ## isNmstrtMin, \ - E ## byteToAscii, \ - E ## charMatches, +# define STANDARD_VTABLE(E) \ + E##byteType, E##isNameMin, E##isNmstrtMin, E##byteToAscii, E##charMatches, #else -#define STANDARD_VTABLE(E) /* as nothing */ +# define STANDARD_VTABLE(E) /* as nothing */ #endif -#define NORMAL_VTABLE(E) \ - E ## isName2, \ - E ## isName3, \ - E ## isName4, \ - E ## isNmstrt2, \ - E ## isNmstrt3, \ - E ## isNmstrt4, \ - E ## isInvalid2, \ - E ## isInvalid3, \ - E ## isInvalid4 - -#define NULL_VTABLE \ - /* isName2 */ NULL, \ - /* isName3 */ NULL, \ - /* isName4 */ NULL, \ - /* isNmstrt2 */ NULL, \ - /* isNmstrt3 */ NULL, \ - /* isNmstrt4 */ NULL, \ - /* isInvalid2 */ NULL, \ - /* isInvalid3 */ NULL, \ - /* isInvalid4 */ NULL +#define NORMAL_VTABLE(E) \ + E##isName2, E##isName3, E##isName4, E##isNmstrt2, E##isNmstrt3, \ + E##isNmstrt4, E##isInvalid2, E##isInvalid3, E##isInvalid4 + +#define NULL_VTABLE \ + /* isName2 */ NULL, /* isName3 */ NULL, /* isName4 */ NULL, \ + /* isNmstrt2 */ NULL, /* isNmstrt3 */ NULL, /* isNmstrt4 */ NULL, \ + /* isInvalid2 */ NULL, /* isInvalid3 */ NULL, /* isInvalid4 */ NULL static int FASTCALL checkCharRefNumber(int); @@ -271,75 +232,70 @@ static int FASTCALL checkCharRefNumber(int); #include "ascii.h" #ifdef XML_MIN_SIZE -#define sb_isNameMin isNever -#define sb_isNmstrtMin isNever +# define sb_isNameMin isNever +# define sb_isNmstrtMin isNever #endif #ifdef XML_MIN_SIZE -#define MINBPC(enc) ((enc)->minBytesPerChar) +# define MINBPC(enc) ((enc)->minBytesPerChar) #else /* minimum bytes per character */ -#define MINBPC(enc) 1 +# define MINBPC(enc) 1 #endif -#define SB_BYTE_TYPE(enc, p) \ +#define SB_BYTE_TYPE(enc, p) \ (((struct normal_encoding *)(enc))->type[(unsigned char)*(p)]) #ifdef XML_MIN_SIZE static int PTRFASTCALL -sb_byteType(const ENCODING *enc, const char *p) -{ +sb_byteType(const ENCODING *enc, const char *p) { return SB_BYTE_TYPE(enc, p); } -#define BYTE_TYPE(enc, p) \ - (AS_NORMAL_ENCODING(enc)->byteType(enc, p)) +# define BYTE_TYPE(enc, p) (AS_NORMAL_ENCODING(enc)->byteType(enc, p)) #else -#define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p) +# define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p) #endif #ifdef XML_MIN_SIZE -#define BYTE_TO_ASCII(enc, p) \ - (AS_NORMAL_ENCODING(enc)->byteToAscii(enc, p)) +# define BYTE_TO_ASCII(enc, p) (AS_NORMAL_ENCODING(enc)->byteToAscii(enc, p)) static int PTRFASTCALL -sb_byteToAscii(const ENCODING *enc, const char *p) -{ +sb_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return *p; } #else -#define BYTE_TO_ASCII(enc, p) (*(p)) +# define BYTE_TO_ASCII(enc, p) (*(p)) #endif -#define IS_NAME_CHAR(enc, p, n) \ - (AS_NORMAL_ENCODING(enc)->isName ## n(enc, p)) -#define IS_NMSTRT_CHAR(enc, p, n) \ - (AS_NORMAL_ENCODING(enc)->isNmstrt ## n(enc, p)) -#define IS_INVALID_CHAR(enc, p, n) \ - (AS_NORMAL_ENCODING(enc)->isInvalid ## n(enc, p)) +#define IS_NAME_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isName##n(enc, p)) +#define IS_NMSTRT_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isNmstrt##n(enc, p)) +#define IS_INVALID_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isInvalid##n(enc, p)) #ifdef XML_MIN_SIZE -#define IS_NAME_CHAR_MINBPC(enc, p) \ - (AS_NORMAL_ENCODING(enc)->isNameMin(enc, p)) -#define IS_NMSTRT_CHAR_MINBPC(enc, p) \ - (AS_NORMAL_ENCODING(enc)->isNmstrtMin(enc, p)) +# define IS_NAME_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNameMin(enc, p)) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNmstrtMin(enc, p)) #else -#define IS_NAME_CHAR_MINBPC(enc, p) (0) -#define IS_NMSTRT_CHAR_MINBPC(enc, p) (0) +# define IS_NAME_CHAR_MINBPC(enc, p) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) (0) #endif #ifdef XML_MIN_SIZE -#define CHAR_MATCHES(enc, p, c) \ - (AS_NORMAL_ENCODING(enc)->charMatches(enc, p, c)) +# define CHAR_MATCHES(enc, p, c) \ + (AS_NORMAL_ENCODING(enc)->charMatches(enc, p, c)) static int PTRCALL -sb_charMatches(const ENCODING *enc, const char *p, int c) -{ +sb_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); return *p == c; } #else /* c is an ASCII character */ -#define CHAR_MATCHES(enc, p, c) (*(p) == c) +# define CHAR_MATCHES(enc, p, c) (*(p) == c) #endif -#define PREFIX(ident) normal_ ## ident +#define PREFIX(ident) normal_##ident #define XML_TOK_IMPL_C #include "xmltok_impl.c" #undef XML_TOK_IMPL_C @@ -354,42 +310,46 @@ sb_charMatches(const ENCODING *enc, const char *p, int c) #undef IS_NMSTRT_CHAR_MINBPC #undef IS_INVALID_CHAR -enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */ - UTF8_cval1 = 0x00, - UTF8_cval2 = 0xc0, - UTF8_cval3 = 0xe0, - UTF8_cval4 = 0xf0 +enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */ + UTF8_cval1 = 0x00, + UTF8_cval2 = 0xc0, + UTF8_cval3 = 0xe0, + UTF8_cval4 = 0xf0 }; void -_INTERNAL_trim_to_complete_utf8_characters(const char * from, const char ** fromLimRef) -{ - const char * fromLim = *fromLimRef; +_INTERNAL_trim_to_complete_utf8_characters(const char *from, + const char **fromLimRef) { + const char *fromLim = *fromLimRef; size_t walked = 0; for (; fromLim > from; fromLim--, walked++) { const unsigned char prev = (unsigned char)fromLim[-1]; - if ((prev & 0xf8u) == 0xf0u) { /* 4-byte character, lead by 0b11110xxx byte */ + if ((prev & 0xf8u) + == 0xf0u) { /* 4-byte character, lead by 0b11110xxx byte */ if (walked + 1 >= 4) { fromLim += 4 - 1; break; } else { walked = 0; } - } else if ((prev & 0xf0u) == 0xe0u) { /* 3-byte character, lead by 0b1110xxxx byte */ + } else if ((prev & 0xf0u) + == 0xe0u) { /* 3-byte character, lead by 0b1110xxxx byte */ if (walked + 1 >= 3) { fromLim += 3 - 1; break; } else { walked = 0; } - } else if ((prev & 0xe0u) == 0xc0u) { /* 2-byte character, lead by 0b110xxxxx byte */ + } else if ((prev & 0xe0u) + == 0xc0u) { /* 2-byte character, lead by 0b110xxxxx byte */ if (walked + 1 >= 2) { fromLim += 2 - 1; break; } else { walked = 0; } - } else if ((prev & 0x80u) == 0x00u) { /* 1-byte character, matching 0b0xxxxxxx */ + } else if ((prev & 0x80u) + == 0x00u) { /* 1-byte character, matching 0b0xxxxxxx */ break; } } @@ -397,16 +357,15 @@ _INTERNAL_trim_to_complete_utf8_characters(const char * from, const char ** from } static enum XML_Convert_Result PTRCALL -utf8_toUtf8(const ENCODING *UNUSED_P(enc), - const char **fromP, const char *fromLim, - char **toP, const char *toLim) -{ +utf8_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { bool input_incomplete = false; bool output_exhausted = false; /* Avoid copying partial characters (due to limited space). */ const ptrdiff_t bytesAvailable = fromLim - *fromP; const ptrdiff_t bytesStorable = toLim - *toP; + UNUSED_P(enc); if (bytesAvailable > bytesStorable) { fromLim = *fromP + bytesStorable; output_exhausted = true; @@ -414,7 +373,7 @@ utf8_toUtf8(const ENCODING *UNUSED_P(enc), /* Avoid copying partial characters (from incomplete input). */ { - const char * const fromLimBefore = fromLim; + const char *const fromLimBefore = fromLim; _INTERNAL_trim_to_complete_utf8_characters(*fromP, &fromLim); if (fromLim < fromLimBefore) { input_incomplete = true; @@ -428,7 +387,7 @@ utf8_toUtf8(const ENCODING *UNUSED_P(enc), *toP += bytesToCopy; } - if (output_exhausted) /* needs to go first */ + if (output_exhausted) /* needs to go first */ return XML_CONVERT_OUTPUT_EXHAUSTED; else if (input_incomplete) return XML_CONVERT_INPUT_INCOMPLETE; @@ -437,10 +396,8 @@ utf8_toUtf8(const ENCODING *UNUSED_P(enc), } static enum XML_Convert_Result PTRCALL -utf8_toUtf16(const ENCODING *enc, - const char **fromP, const char *fromLim, - unsigned short **toP, const unsigned short *toLim) -{ +utf8_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { enum XML_Convert_Result res = XML_CONVERT_COMPLETED; unsigned short *to = *toP; const char *from = *fromP; @@ -459,30 +416,28 @@ utf8_toUtf16(const ENCODING *enc, res = XML_CONVERT_INPUT_INCOMPLETE; goto after; } - *to++ = (unsigned short)(((from[0] & 0xf) << 12) - | ((from[1] & 0x3f) << 6) | (from[2] & 0x3f)); + *to++ = (unsigned short)(((from[0] & 0xf) << 12) | ((from[1] & 0x3f) << 6) + | (from[2] & 0x3f)); from += 3; break; - case BT_LEAD4: - { - unsigned long n; - if (toLim - to < 2) { - res = XML_CONVERT_OUTPUT_EXHAUSTED; - goto after; - } - if (fromLim - from < 4) { - res = XML_CONVERT_INPUT_INCOMPLETE; - goto after; - } - n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) - | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f); - n -= 0x10000; - to[0] = (unsigned short)((n >> 10) | 0xD800); - to[1] = (unsigned short)((n & 0x3FF) | 0xDC00); - to += 2; - from += 4; + case BT_LEAD4: { + unsigned long n; + if (toLim - to < 2) { + res = XML_CONVERT_OUTPUT_EXHAUSTED; + goto after; } - break; + if (fromLim - from < 4) { + res = XML_CONVERT_INPUT_INCOMPLETE; + goto after; + } + n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) + | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f); + n -= 0x10000; + to[0] = (unsigned short)((n >> 10) | 0xD800); + to[1] = (unsigned short)((n & 0x3FF) | 0xDC00); + to += 2; + from += 4; + } break; default: *to++ = *from++; break; @@ -497,56 +452,51 @@ after: } #ifdef XML_NS -static const struct normal_encoding utf8_encoding_ns = { - { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, - { -#include "asciitab.h" -#include "utf8tab.h" - }, - STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) -}; +static const struct normal_encoding utf8_encoding_ns + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { +# include "asciitab.h" +# include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; #endif -static const struct normal_encoding utf8_encoding = { - { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, - { +static const struct normal_encoding utf8_encoding + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON #include "utf8tab.h" - }, - STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) -}; + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; #ifdef XML_NS -static const struct normal_encoding internal_utf8_encoding_ns = { - { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, - { -#include "iasciitab.h" -#include "utf8tab.h" - }, - STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) -}; +static const struct normal_encoding internal_utf8_encoding_ns + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { +# include "iasciitab.h" +# include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; #endif -static const struct normal_encoding internal_utf8_encoding = { - { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, - { +static const struct normal_encoding internal_utf8_encoding + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { #define BT_COLON BT_NMSTRT #include "iasciitab.h" #undef BT_COLON #include "utf8tab.h" - }, - STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) -}; + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; static enum XML_Convert_Result PTRCALL -latin1_toUtf8(const ENCODING *UNUSED_P(enc), - const char **fromP, const char *fromLim, - char **toP, const char *toLim) -{ +latin1_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + UNUSED_P(enc); for (;;) { unsigned char c; if (*fromP == fromLim) @@ -558,8 +508,7 @@ latin1_toUtf8(const ENCODING *UNUSED_P(enc), *(*toP)++ = (char)((c >> 6) | UTF8_cval2); *(*toP)++ = (char)((c & 0x3f) | 0x80); (*fromP)++; - } - else { + } else { if (*toP == toLim) return XML_CONVERT_OUTPUT_EXHAUSTED; *(*toP)++ = *(*fromP)++; @@ -568,10 +517,9 @@ latin1_toUtf8(const ENCODING *UNUSED_P(enc), } static enum XML_Convert_Result PTRCALL -latin1_toUtf16(const ENCODING *UNUSED_P(enc), - const char **fromP, const char *fromLim, - unsigned short **toP, const unsigned short *toLim) -{ +latin1_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { + UNUSED_P(enc); while (*fromP < fromLim && *toP < toLim) *(*toP)++ = (unsigned char)*(*fromP)++; @@ -583,33 +531,30 @@ latin1_toUtf16(const ENCODING *UNUSED_P(enc), #ifdef XML_NS -static const struct normal_encoding latin1_encoding_ns = { - { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 }, - { -#include "asciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(sb_) NULL_VTABLE -}; +static const struct normal_encoding latin1_encoding_ns + = {{VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0}, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; #endif -static const struct normal_encoding latin1_encoding = { - { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 }, - { +static const struct normal_encoding latin1_encoding + = {{VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0}, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON #include "latin1tab.h" - }, - STANDARD_VTABLE(sb_) NULL_VTABLE -}; + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; static enum XML_Convert_Result PTRCALL -ascii_toUtf8(const ENCODING *UNUSED_P(enc), - const char **fromP, const char *fromLim, - char **toP, const char *toLim) -{ +ascii_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + UNUSED_P(enc); while (*fromP < fromLim && *toP < toLim) *(*toP)++ = *(*fromP)++; @@ -621,40 +566,45 @@ ascii_toUtf8(const ENCODING *UNUSED_P(enc), #ifdef XML_NS -static const struct normal_encoding ascii_encoding_ns = { - { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 }, - { -#include "asciitab.h" -/* BT_NONXML == 0 */ - }, - STANDARD_VTABLE(sb_) NULL_VTABLE -}; +static const struct normal_encoding ascii_encoding_ns + = {{VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0}, + { +# include "asciitab.h" + /* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; #endif -static const struct normal_encoding ascii_encoding = { - { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 }, - { +static const struct normal_encoding ascii_encoding + = {{VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0}, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON -/* BT_NONXML == 0 */ - }, - STANDARD_VTABLE(sb_) NULL_VTABLE -}; + /* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; static int PTRFASTCALL -unicode_byte_type(char hi, char lo) -{ +unicode_byte_type(char hi, char lo) { switch ((unsigned char)hi) { - case 0xD8: case 0xD9: case 0xDA: case 0xDB: + /* 0xD800–0xDBFF first 16-bit code unit or high surrogate (W1) */ + case 0xD8: + case 0xD9: + case 0xDA: + case 0xDB: return BT_LEAD4; - case 0xDC: case 0xDD: case 0xDE: case 0xDF: + /* 0xDC00–0xDFFF second 16-bit code unit or low surrogate (W2) */ + case 0xDC: + case 0xDD: + case 0xDE: + case 0xDF: return BT_TRAIL; case 0xFF: switch ((unsigned char)lo) { - case 0xFF: - case 0xFE: + case 0xFF: /* noncharacter-FFFF */ + case 0xFE: /* noncharacter-FFFE */ return BT_NONXML; } break; @@ -662,102 +612,105 @@ unicode_byte_type(char hi, char lo) return BT_NONASCII; } -#define DEFINE_UTF16_TO_UTF8(E) \ -static enum XML_Convert_Result PTRCALL \ -E ## toUtf8(const ENCODING *UNUSED_P(enc), \ - const char **fromP, const char *fromLim, \ - char **toP, const char *toLim) \ -{ \ - const char *from = *fromP; \ - fromLim = from + (((fromLim - from) >> 1) << 1); /* shrink to even */ \ - for (; from < fromLim; from += 2) { \ - int plane; \ - unsigned char lo2; \ - unsigned char lo = GET_LO(from); \ - unsigned char hi = GET_HI(from); \ - switch (hi) { \ - case 0: \ - if (lo < 0x80) { \ - if (*toP == toLim) { \ - *fromP = from; \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - } \ - *(*toP)++ = lo; \ - break; \ - } \ - /* fall through */ \ - case 0x1: case 0x2: case 0x3: \ - case 0x4: case 0x5: case 0x6: case 0x7: \ - if (toLim - *toP < 2) { \ - *fromP = from; \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - } \ - *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \ - *(*toP)++ = ((lo & 0x3f) | 0x80); \ - break; \ - default: \ - if (toLim - *toP < 3) { \ - *fromP = from; \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - } \ - /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \ - *(*toP)++ = ((hi >> 4) | UTF8_cval3); \ - *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \ - *(*toP)++ = ((lo & 0x3f) | 0x80); \ - break; \ - case 0xD8: case 0xD9: case 0xDA: case 0xDB: \ - if (toLim - *toP < 4) { \ - *fromP = from; \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - } \ - if (fromLim - from < 4) { \ - *fromP = from; \ - return XML_CONVERT_INPUT_INCOMPLETE; \ - } \ - plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \ - *(*toP)++ = ((plane >> 2) | UTF8_cval4); \ - *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \ - from += 2; \ - lo2 = GET_LO(from); \ - *(*toP)++ = (((lo & 0x3) << 4) \ - | ((GET_HI(from) & 0x3) << 2) \ - | (lo2 >> 6) \ - | 0x80); \ - *(*toP)++ = ((lo2 & 0x3f) | 0x80); \ - break; \ - } \ - } \ - *fromP = from; \ - if (from < fromLim) \ - return XML_CONVERT_INPUT_INCOMPLETE; \ - else \ - return XML_CONVERT_COMPLETED; \ -} +#define DEFINE_UTF16_TO_UTF8(E) \ + static enum XML_Convert_Result PTRCALL E##toUtf8( \ + const ENCODING *enc, const char **fromP, const char *fromLim, \ + char **toP, const char *toLim) { \ + const char *from = *fromP; \ + UNUSED_P(enc); \ + fromLim = from + (((fromLim - from) >> 1) << 1); /* shrink to even */ \ + for (; from < fromLim; from += 2) { \ + int plane; \ + unsigned char lo2; \ + unsigned char lo = GET_LO(from); \ + unsigned char hi = GET_HI(from); \ + switch (hi) { \ + case 0: \ + if (lo < 0x80) { \ + if (*toP == toLim) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + *(*toP)++ = lo; \ + break; \ + } \ + /* fall through */ \ + case 0x1: \ + case 0x2: \ + case 0x3: \ + case 0x4: \ + case 0x5: \ + case 0x6: \ + case 0x7: \ + if (toLim - *toP < 2) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + default: \ + if (toLim - *toP < 3) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \ + *(*toP)++ = ((hi >> 4) | UTF8_cval3); \ + *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + case 0xD8: \ + case 0xD9: \ + case 0xDA: \ + case 0xDB: \ + if (toLim - *toP < 4) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + if (fromLim - from < 4) { \ + *fromP = from; \ + return XML_CONVERT_INPUT_INCOMPLETE; \ + } \ + plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \ + *(*toP)++ = (char)((plane >> 2) | UTF8_cval4); \ + *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \ + from += 2; \ + lo2 = GET_LO(from); \ + *(*toP)++ = (((lo & 0x3) << 4) | ((GET_HI(from) & 0x3) << 2) \ + | (lo2 >> 6) | 0x80); \ + *(*toP)++ = ((lo2 & 0x3f) | 0x80); \ + break; \ + } \ + } \ + *fromP = from; \ + if (from < fromLim) \ + return XML_CONVERT_INPUT_INCOMPLETE; \ + else \ + return XML_CONVERT_COMPLETED; \ + } -#define DEFINE_UTF16_TO_UTF16(E) \ -static enum XML_Convert_Result PTRCALL \ -E ## toUtf16(const ENCODING *UNUSED_P(enc), \ - const char **fromP, const char *fromLim, \ - unsigned short **toP, const unsigned short *toLim) \ -{ \ - enum XML_Convert_Result res = XML_CONVERT_COMPLETED; \ - fromLim = *fromP + (((fromLim - *fromP) >> 1) << 1); /* shrink to even */ \ - /* Avoid copying first half only of surrogate */ \ - if (fromLim - *fromP > ((toLim - *toP) << 1) \ - && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) { \ - fromLim -= 2; \ - res = XML_CONVERT_INPUT_INCOMPLETE; \ - } \ - for (; *fromP < fromLim && *toP < toLim; *fromP += 2) \ - *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \ - if ((*toP == toLim) && (*fromP < fromLim)) \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - else \ - return res; \ -} +#define DEFINE_UTF16_TO_UTF16(E) \ + static enum XML_Convert_Result PTRCALL E##toUtf16( \ + const ENCODING *enc, const char **fromP, const char *fromLim, \ + unsigned short **toP, const unsigned short *toLim) { \ + enum XML_Convert_Result res = XML_CONVERT_COMPLETED; \ + UNUSED_P(enc); \ + fromLim = *fromP + (((fromLim - *fromP) >> 1) << 1); /* shrink to even */ \ + /* Avoid copying first half only of surrogate */ \ + if (fromLim - *fromP > ((toLim - *toP) << 1) \ + && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) { \ + fromLim -= 2; \ + res = XML_CONVERT_INPUT_INCOMPLETE; \ + } \ + for (; *fromP < fromLim && *toP < toLim; *fromP += 2) \ + *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \ + if ((*toP == toLim) && (*fromP < fromLim)) \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + else \ + return res; \ + } -#define SET2(ptr, ch) \ - (((ptr)[0] = ((ch) & 0xff)), ((ptr)[1] = ((ch) >> 8))) +#define SET2(ptr, ch) (((ptr)[0] = ((ch)&0xff)), ((ptr)[1] = ((ch) >> 8))) #define GET_LO(ptr) ((unsigned char)(ptr)[0]) #define GET_HI(ptr) ((unsigned char)(ptr)[1]) @@ -768,8 +721,7 @@ DEFINE_UTF16_TO_UTF16(little2_) #undef GET_LO #undef GET_HI -#define SET2(ptr, ch) \ - (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch) & 0xFF))) +#define SET2(ptr, ch) (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch)&0xFF))) #define GET_LO(ptr) ((unsigned char)(ptr)[1]) #define GET_HI(ptr) ((unsigned char)(ptr)[0]) @@ -780,292 +732,279 @@ DEFINE_UTF16_TO_UTF16(big2_) #undef GET_LO #undef GET_HI -#define LITTLE2_BYTE_TYPE(enc, p) \ - ((p)[1] == 0 \ - ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \ - : unicode_byte_type((p)[1], (p)[0])) -#define LITTLE2_BYTE_TO_ASCII(enc, p) ((p)[1] == 0 ? (p)[0] : -1) -#define LITTLE2_CHAR_MATCHES(enc, p, c) ((p)[1] == 0 && (p)[0] == c) -#define LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) \ +#define LITTLE2_BYTE_TYPE(enc, p) \ + ((p)[1] == 0 ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \ + : unicode_byte_type((p)[1], (p)[0])) +#define LITTLE2_BYTE_TO_ASCII(p) ((p)[1] == 0 ? (p)[0] : -1) +#define LITTLE2_CHAR_MATCHES(p, c) ((p)[1] == 0 && (p)[0] == c) +#define LITTLE2_IS_NAME_CHAR_MINBPC(p) \ UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0]) -#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) \ +#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) \ UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0]) #ifdef XML_MIN_SIZE static int PTRFASTCALL -little2_byteType(const ENCODING *enc, const char *p) -{ +little2_byteType(const ENCODING *enc, const char *p) { return LITTLE2_BYTE_TYPE(enc, p); } static int PTRFASTCALL -little2_byteToAscii(const ENCODING *enc, const char *p) -{ - return LITTLE2_BYTE_TO_ASCII(enc, p); +little2_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_BYTE_TO_ASCII(p); } static int PTRCALL -little2_charMatches(const ENCODING *enc, const char *p, int c) -{ - return LITTLE2_CHAR_MATCHES(enc, p, c); +little2_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); + return LITTLE2_CHAR_MATCHES(p, c); } static int PTRFASTCALL -little2_isNameMin(const ENCODING *enc, const char *p) -{ - return LITTLE2_IS_NAME_CHAR_MINBPC(enc, p); +little2_isNameMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_IS_NAME_CHAR_MINBPC(p); } static int PTRFASTCALL -little2_isNmstrtMin(const ENCODING *enc, const char *p) -{ - return LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p); +little2_isNmstrtMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_IS_NMSTRT_CHAR_MINBPC(p); } -#undef VTABLE -#define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16 +# undef VTABLE +# define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16 #else /* not XML_MIN_SIZE */ -#undef PREFIX -#define PREFIX(ident) little2_ ## ident -#define MINBPC(enc) 2 +# undef PREFIX +# define PREFIX(ident) little2_##ident +# define MINBPC(enc) 2 /* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ -#define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p) -#define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(enc, p) -#define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(enc, p, c) -#define IS_NAME_CHAR(enc, p, n) 0 -#define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) -#define IS_NMSTRT_CHAR(enc, p, n) (0) -#define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) - -#define XML_TOK_IMPL_C -#include "xmltok_impl.c" -#undef XML_TOK_IMPL_C - -#undef MINBPC -#undef BYTE_TYPE -#undef BYTE_TO_ASCII -#undef CHAR_MATCHES -#undef IS_NAME_CHAR -#undef IS_NAME_CHAR_MINBPC -#undef IS_NMSTRT_CHAR -#undef IS_NMSTRT_CHAR_MINBPC -#undef IS_INVALID_CHAR +# define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p) +# define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(p) +# define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(p, c) +# define IS_NAME_CHAR(enc, p, n) 0 +# define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(p) +# define IS_NMSTRT_CHAR(enc, p, n) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) + +# define XML_TOK_IMPL_C +# include "xmltok_impl.c" +# undef XML_TOK_IMPL_C + +# undef MINBPC +# undef BYTE_TYPE +# undef BYTE_TO_ASCII +# undef CHAR_MATCHES +# undef IS_NAME_CHAR +# undef IS_NAME_CHAR_MINBPC +# undef IS_NMSTRT_CHAR +# undef IS_NMSTRT_CHAR_MINBPC +# undef IS_INVALID_CHAR #endif /* not XML_MIN_SIZE */ #ifdef XML_NS -static const struct normal_encoding little2_encoding_ns = { - { VTABLE, 2, 0, -#if BYTEORDER == 1234 - 1 -#else - 0 -#endif - }, - { -#include "asciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(little2_) NULL_VTABLE -}; +static const struct normal_encoding little2_encoding_ns + = {{VTABLE, 2, 0, +# if BYTEORDER == 1234 + 1 +# else + 0 +# endif + }, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; #endif -static const struct normal_encoding little2_encoding = { - { VTABLE, 2, 0, +static const struct normal_encoding little2_encoding + = {{VTABLE, 2, 0, #if BYTEORDER == 1234 - 1 + 1 #else - 0 + 0 #endif - }, - { + }, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON #include "latin1tab.h" - }, - STANDARD_VTABLE(little2_) NULL_VTABLE -}; + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; #if BYTEORDER != 4321 -#ifdef XML_NS +# ifdef XML_NS -static const struct normal_encoding internal_little2_encoding_ns = { - { VTABLE, 2, 0, 1 }, - { -#include "iasciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(little2_) NULL_VTABLE -}; +static const struct normal_encoding internal_little2_encoding_ns + = {{VTABLE, 2, 0, 1}, + { +# include "iasciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; -#endif +# endif -static const struct normal_encoding internal_little2_encoding = { - { VTABLE, 2, 0, 1 }, - { -#define BT_COLON BT_NMSTRT -#include "iasciitab.h" -#undef BT_COLON -#include "latin1tab.h" - }, - STANDARD_VTABLE(little2_) NULL_VTABLE -}; +static const struct normal_encoding internal_little2_encoding + = {{VTABLE, 2, 0, 1}, + { +# define BT_COLON BT_NMSTRT +# include "iasciitab.h" +# undef BT_COLON +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; #endif - -#define BIG2_BYTE_TYPE(enc, p) \ - ((p)[0] == 0 \ - ? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \ - : unicode_byte_type((p)[0], (p)[1])) -#define BIG2_BYTE_TO_ASCII(enc, p) ((p)[0] == 0 ? (p)[1] : -1) -#define BIG2_CHAR_MATCHES(enc, p, c) ((p)[0] == 0 && (p)[1] == c) -#define BIG2_IS_NAME_CHAR_MINBPC(enc, p) \ +#define BIG2_BYTE_TYPE(enc, p) \ + ((p)[0] == 0 \ + ? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \ + : unicode_byte_type((p)[0], (p)[1])) +#define BIG2_BYTE_TO_ASCII(p) ((p)[0] == 0 ? (p)[1] : -1) +#define BIG2_CHAR_MATCHES(p, c) ((p)[0] == 0 && (p)[1] == c) +#define BIG2_IS_NAME_CHAR_MINBPC(p) \ UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1]) -#define BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) \ +#define BIG2_IS_NMSTRT_CHAR_MINBPC(p) \ UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1]) #ifdef XML_MIN_SIZE static int PTRFASTCALL -big2_byteType(const ENCODING *enc, const char *p) -{ +big2_byteType(const ENCODING *enc, const char *p) { return BIG2_BYTE_TYPE(enc, p); } static int PTRFASTCALL -big2_byteToAscii(const ENCODING *enc, const char *p) -{ - return BIG2_BYTE_TO_ASCII(enc, p); +big2_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_BYTE_TO_ASCII(p); } static int PTRCALL -big2_charMatches(const ENCODING *enc, const char *p, int c) -{ - return BIG2_CHAR_MATCHES(enc, p, c); +big2_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); + return BIG2_CHAR_MATCHES(p, c); } static int PTRFASTCALL -big2_isNameMin(const ENCODING *enc, const char *p) -{ - return BIG2_IS_NAME_CHAR_MINBPC(enc, p); +big2_isNameMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_IS_NAME_CHAR_MINBPC(p); } static int PTRFASTCALL -big2_isNmstrtMin(const ENCODING *enc, const char *p) -{ - return BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p); +big2_isNmstrtMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_IS_NMSTRT_CHAR_MINBPC(p); } -#undef VTABLE -#define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16 +# undef VTABLE +# define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16 #else /* not XML_MIN_SIZE */ -#undef PREFIX -#define PREFIX(ident) big2_ ## ident -#define MINBPC(enc) 2 +# undef PREFIX +# define PREFIX(ident) big2_##ident +# define MINBPC(enc) 2 /* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ -#define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p) -#define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(enc, p) -#define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(enc, p, c) -#define IS_NAME_CHAR(enc, p, n) 0 -#define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(enc, p) -#define IS_NMSTRT_CHAR(enc, p, n) (0) -#define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) - -#define XML_TOK_IMPL_C -#include "xmltok_impl.c" -#undef XML_TOK_IMPL_C - -#undef MINBPC -#undef BYTE_TYPE -#undef BYTE_TO_ASCII -#undef CHAR_MATCHES -#undef IS_NAME_CHAR -#undef IS_NAME_CHAR_MINBPC -#undef IS_NMSTRT_CHAR -#undef IS_NMSTRT_CHAR_MINBPC -#undef IS_INVALID_CHAR +# define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p) +# define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(p) +# define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(p, c) +# define IS_NAME_CHAR(enc, p, n) 0 +# define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(p) +# define IS_NMSTRT_CHAR(enc, p, n) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(p) + +# define XML_TOK_IMPL_C +# include "xmltok_impl.c" +# undef XML_TOK_IMPL_C + +# undef MINBPC +# undef BYTE_TYPE +# undef BYTE_TO_ASCII +# undef CHAR_MATCHES +# undef IS_NAME_CHAR +# undef IS_NAME_CHAR_MINBPC +# undef IS_NMSTRT_CHAR +# undef IS_NMSTRT_CHAR_MINBPC +# undef IS_INVALID_CHAR #endif /* not XML_MIN_SIZE */ #ifdef XML_NS -static const struct normal_encoding big2_encoding_ns = { - { VTABLE, 2, 0, -#if BYTEORDER == 4321 - 1 -#else - 0 -#endif - }, - { -#include "asciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(big2_) NULL_VTABLE -}; +static const struct normal_encoding big2_encoding_ns + = {{VTABLE, 2, 0, +# if BYTEORDER == 4321 + 1 +# else + 0 +# endif + }, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; #endif -static const struct normal_encoding big2_encoding = { - { VTABLE, 2, 0, +static const struct normal_encoding big2_encoding + = {{VTABLE, 2, 0, #if BYTEORDER == 4321 - 1 + 1 #else - 0 + 0 #endif - }, - { + }, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON #include "latin1tab.h" - }, - STANDARD_VTABLE(big2_) NULL_VTABLE -}; + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; #if BYTEORDER != 1234 -#ifdef XML_NS +# ifdef XML_NS -static const struct normal_encoding internal_big2_encoding_ns = { - { VTABLE, 2, 0, 1 }, - { -#include "iasciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(big2_) NULL_VTABLE -}; +static const struct normal_encoding internal_big2_encoding_ns + = {{VTABLE, 2, 0, 1}, + { +# include "iasciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; -#endif +# endif -static const struct normal_encoding internal_big2_encoding = { - { VTABLE, 2, 0, 1 }, - { -#define BT_COLON BT_NMSTRT -#include "iasciitab.h" -#undef BT_COLON -#include "latin1tab.h" - }, - STANDARD_VTABLE(big2_) NULL_VTABLE -}; +static const struct normal_encoding internal_big2_encoding + = {{VTABLE, 2, 0, 1}, + { +# define BT_COLON BT_NMSTRT +# include "iasciitab.h" +# undef BT_COLON +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; #endif #undef PREFIX static int FASTCALL -streqci(const char *s1, const char *s2) -{ +streqci(const char *s1, const char *s2) { for (;;) { char c1 = *s1++; char c2 = *s2++; @@ -1079,22 +1018,21 @@ streqci(const char *s1, const char *s2) c2 += ASCII_A - ASCII_a; /* LCOV_EXCL_LINE */ if (c1 != c2) return 0; - if (!c1) + if (! c1) break; } return 1; } static void PTRCALL -initUpdatePosition(const ENCODING *UNUSED_P(enc), const char *ptr, - const char *end, POSITION *pos) -{ +initUpdatePosition(const ENCODING *enc, const char *ptr, const char *end, + POSITION *pos) { + UNUSED_P(enc); normal_updatePosition(&utf8_encoding.enc, ptr, end, pos); } static int -toAscii(const ENCODING *enc, const char *ptr, const char *end) -{ +toAscii(const ENCODING *enc, const char *ptr, const char *end) { char buf[1]; char *p = buf; XmlUtf8Convert(enc, &ptr, end, &p, p + 1); @@ -1105,8 +1043,7 @@ toAscii(const ENCODING *enc, const char *ptr, const char *end) } static int FASTCALL -isSpace(int c) -{ +isSpace(int c) { switch (c) { case 0x20: case 0xD: @@ -1121,21 +1058,16 @@ isSpace(int c) followed by name=val. */ static int -parsePseudoAttribute(const ENCODING *enc, - const char *ptr, - const char *end, - const char **namePtr, - const char **nameEndPtr, - const char **valPtr, - const char **nextTokPtr) -{ +parsePseudoAttribute(const ENCODING *enc, const char *ptr, const char *end, + const char **namePtr, const char **nameEndPtr, + const char **valPtr, const char **nextTokPtr) { int c; char open; if (ptr == end) { *namePtr = NULL; return 1; } - if (!isSpace(toAscii(enc, ptr, end))) { + if (! isSpace(toAscii(enc, ptr, end))) { *nextTokPtr = ptr; return 0; } @@ -1191,12 +1123,9 @@ parsePseudoAttribute(const ENCODING *enc, c = toAscii(enc, ptr, end); if (c == open) break; - if (!(ASCII_a <= c && c <= ASCII_z) - && !(ASCII_A <= c && c <= ASCII_Z) - && !(ASCII_0 <= c && c <= ASCII_9) - && c != ASCII_PERIOD - && c != ASCII_MINUS - && c != ASCII_UNDERSCORE) { + if (! (ASCII_a <= c && c <= ASCII_z) && ! (ASCII_A <= c && c <= ASCII_Z) + && ! (ASCII_0 <= c && c <= ASCII_9) && c != ASCII_PERIOD + && c != ASCII_MINUS && c != ASCII_UNDERSCORE) { *nextTokPtr = ptr; return 0; } @@ -1205,68 +1134,52 @@ parsePseudoAttribute(const ENCODING *enc, return 1; } -static const char KW_version[] = { - ASCII_v, ASCII_e, ASCII_r, ASCII_s, ASCII_i, ASCII_o, ASCII_n, '\0' -}; +static const char KW_version[] + = {ASCII_v, ASCII_e, ASCII_r, ASCII_s, ASCII_i, ASCII_o, ASCII_n, '\0'}; -static const char KW_encoding[] = { - ASCII_e, ASCII_n, ASCII_c, ASCII_o, ASCII_d, ASCII_i, ASCII_n, ASCII_g, '\0' -}; +static const char KW_encoding[] = {ASCII_e, ASCII_n, ASCII_c, ASCII_o, ASCII_d, + ASCII_i, ASCII_n, ASCII_g, '\0'}; -static const char KW_standalone[] = { - ASCII_s, ASCII_t, ASCII_a, ASCII_n, ASCII_d, ASCII_a, ASCII_l, ASCII_o, - ASCII_n, ASCII_e, '\0' -}; +static const char KW_standalone[] + = {ASCII_s, ASCII_t, ASCII_a, ASCII_n, ASCII_d, ASCII_a, + ASCII_l, ASCII_o, ASCII_n, ASCII_e, '\0'}; -static const char KW_yes[] = { - ASCII_y, ASCII_e, ASCII_s, '\0' -}; +static const char KW_yes[] = {ASCII_y, ASCII_e, ASCII_s, '\0'}; -static const char KW_no[] = { - ASCII_n, ASCII_o, '\0' -}; +static const char KW_no[] = {ASCII_n, ASCII_o, '\0'}; static int -doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, - const char *, +doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, const char *, const char *), - int isGeneralTextEntity, - const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr, - const char **versionPtr, - const char **versionEndPtr, - const char **encodingName, - const ENCODING **encoding, - int *standalone) -{ + int isGeneralTextEntity, const ENCODING *enc, const char *ptr, + const char *end, const char **badPtr, const char **versionPtr, + const char **versionEndPtr, const char **encodingName, + const ENCODING **encoding, int *standalone) { const char *val = NULL; const char *name = NULL; const char *nameEnd = NULL; ptr += 5 * enc->minBytesPerChar; end -= 2 * enc->minBytesPerChar; - if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) - || !name) { + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) + || ! name) { *badPtr = ptr; return 0; } - if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_version)) { - if (!isGeneralTextEntity) { + if (! XmlNameMatchesAscii(enc, name, nameEnd, KW_version)) { + if (! isGeneralTextEntity) { *badPtr = name; return 0; } - } - else { + } else { if (versionPtr) *versionPtr = val; if (versionEndPtr) *versionEndPtr = ptr; - if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { *badPtr = ptr; return 0; } - if (!name) { + if (! name) { if (isGeneralTextEntity) { /* a TextDecl must have an EncodingDecl */ *badPtr = ptr; @@ -1277,7 +1190,7 @@ doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, } if (XmlNameMatchesAscii(enc, name, nameEnd, KW_encoding)) { int c = toAscii(enc, val, end); - if (!(ASCII_a <= c && c <= ASCII_z) && !(ASCII_A <= c && c <= ASCII_Z)) { + if (! (ASCII_a <= c && c <= ASCII_z) && ! (ASCII_A <= c && c <= ASCII_Z)) { *badPtr = val; return 0; } @@ -1285,14 +1198,14 @@ doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, *encodingName = val; if (encoding) *encoding = encodingFinder(enc, val, ptr - enc->minBytesPerChar); - if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { *badPtr = ptr; return 0; } - if (!name) + if (! name) return 1; } - if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_standalone) + if (! XmlNameMatchesAscii(enc, name, nameEnd, KW_standalone) || isGeneralTextEntity) { *badPtr = name; return 0; @@ -1300,12 +1213,10 @@ doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_yes)) { if (standalone) *standalone = 1; - } - else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_no)) { + } else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_no)) { if (standalone) *standalone = 0; - } - else { + } else { *badPtr = val; return 0; } @@ -1319,11 +1230,16 @@ doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, } static int FASTCALL -checkCharRefNumber(int result) -{ +checkCharRefNumber(int result) { switch (result >> 8) { - case 0xD8: case 0xD9: case 0xDA: case 0xDB: - case 0xDC: case 0xDD: case 0xDE: case 0xDF: + case 0xD8: + case 0xD9: + case 0xDA: + case 0xDB: + case 0xDC: + case 0xDD: + case 0xDE: + case 0xDF: return -1; case 0: if (latin1_encoding.type[result] == BT_NONXML) @@ -1338,8 +1254,7 @@ checkCharRefNumber(int result) } int FASTCALL -XmlUtf8Encode(int c, char *buf) -{ +XmlUtf8Encode(int c, char *buf) { enum { /* minN is minimum legal resulting value for N byte sequence */ min2 = 0x80, @@ -1375,8 +1290,7 @@ XmlUtf8Encode(int c, char *buf) } int FASTCALL -XmlUtf16Encode(int charNum, unsigned short *buf) -{ +XmlUtf16Encode(int charNum, unsigned short *buf) { if (charNum < 0) return 0; if (charNum < 0x10000) { @@ -1400,17 +1314,15 @@ struct unknown_encoding { char utf8[256][4]; }; -#define AS_UNKNOWN_ENCODING(enc) ((const struct unknown_encoding *) (enc)) +#define AS_UNKNOWN_ENCODING(enc) ((const struct unknown_encoding *)(enc)) int -XmlSizeOfUnknownEncoding(void) -{ +XmlSizeOfUnknownEncoding(void) { return sizeof(struct unknown_encoding); } static int PTRFASTCALL -unknown_isName(const ENCODING *enc, const char *p) -{ +unknown_isName(const ENCODING *enc, const char *p) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); int c = uenc->convert(uenc->userData, p); if (c & ~0xFFFF) @@ -1419,8 +1331,7 @@ unknown_isName(const ENCODING *enc, const char *p) } static int PTRFASTCALL -unknown_isNmstrt(const ENCODING *enc, const char *p) -{ +unknown_isNmstrt(const ENCODING *enc, const char *p) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); int c = uenc->convert(uenc->userData, p); if (c & ~0xFFFF) @@ -1429,18 +1340,15 @@ unknown_isNmstrt(const ENCODING *enc, const char *p) } static int PTRFASTCALL -unknown_isInvalid(const ENCODING *enc, const char *p) -{ +unknown_isInvalid(const ENCODING *enc, const char *p) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); int c = uenc->convert(uenc->userData, p); return (c & ~0xFFFF) || checkCharRefNumber(c) < 0; } static enum XML_Convert_Result PTRCALL -unknown_toUtf8(const ENCODING *enc, - const char **fromP, const char *fromLim, - char **toP, const char *toLim) -{ +unknown_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); char buf[XML_UTF8_ENCODE_MAX]; for (;;) { @@ -1458,8 +1366,7 @@ unknown_toUtf8(const ENCODING *enc, utf8 = buf; *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] - (BT_LEAD2 - 2)); - } - else { + } else { if (n > toLim - *toP) return XML_CONVERT_OUTPUT_EXHAUSTED; (*fromP)++; @@ -1470,20 +1377,16 @@ unknown_toUtf8(const ENCODING *enc, } static enum XML_Convert_Result PTRCALL -unknown_toUtf16(const ENCODING *enc, - const char **fromP, const char *fromLim, - unsigned short **toP, const unsigned short *toLim) -{ +unknown_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); while (*fromP < fromLim && *toP < toLim) { unsigned short c = uenc->utf16[(unsigned char)**fromP]; if (c == 0) { - c = (unsigned short) - uenc->convert(uenc->userData, *fromP); + c = (unsigned short)uenc->convert(uenc->userData, *fromP); *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] - (BT_LEAD2 - 2)); - } - else + } else (*fromP)++; *(*toP)++ = c; } @@ -1495,19 +1398,14 @@ unknown_toUtf16(const ENCODING *enc, } ENCODING * -XmlInitUnknownEncoding(void *mem, - int *table, - CONVERTER convert, - void *userData) -{ +XmlInitUnknownEncoding(void *mem, int *table, CONVERTER convert, + void *userData) { int i; struct unknown_encoding *e = (struct unknown_encoding *)mem; - for (i = 0; i < (int)sizeof(struct normal_encoding); i++) - ((char *)mem)[i] = ((char *)&latin1_encoding)[i]; + memcpy(mem, &latin1_encoding, sizeof(struct normal_encoding)); for (i = 0; i < 128; i++) if (latin1_encoding.type[i] != BT_OTHER - && latin1_encoding.type[i] != BT_NONXML - && table[i] != i) + && latin1_encoding.type[i] != BT_NONXML && table[i] != i) return 0; for (i = 0; i < 256; i++) { int c = table[i]; @@ -1517,35 +1415,30 @@ XmlInitUnknownEncoding(void *mem, e->utf16[i] = 0xFFFF; e->utf8[i][0] = 1; e->utf8[i][1] = 0; - } - else if (c < 0) { + } else if (c < 0) { if (c < -4) return 0; /* Multi-byte sequences need a converter function */ - if (!convert) + if (! convert) return 0; e->normal.type[i] = (unsigned char)(BT_LEAD2 - (c + 2)); e->utf8[i][0] = 0; e->utf16[i] = 0; - } - else if (c < 0x80) { + } else if (c < 0x80) { if (latin1_encoding.type[c] != BT_OTHER - && latin1_encoding.type[c] != BT_NONXML - && c != i) + && latin1_encoding.type[c] != BT_NONXML && c != i) return 0; e->normal.type[i] = latin1_encoding.type[c]; e->utf8[i][0] = 1; e->utf8[i][1] = (char)c; e->utf16[i] = (unsigned short)(c == 0 ? 0xFFFF : c); - } - else if (checkCharRefNumber(c) < 0) { + } else if (checkCharRefNumber(c) < 0) { e->normal.type[i] = BT_NONXML; /* This shouldn't really get used. */ e->utf16[i] = 0xFFFF; e->utf8[i][0] = 1; e->utf8[i][1] = 0; - } - else { + } else { if (c > 0xFFFF) return 0; if (UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xff)) @@ -1590,44 +1483,32 @@ enum { NO_ENC }; -static const char KW_ISO_8859_1[] = { - ASCII_I, ASCII_S, ASCII_O, ASCII_MINUS, ASCII_8, ASCII_8, ASCII_5, ASCII_9, - ASCII_MINUS, ASCII_1, '\0' -}; -static const char KW_US_ASCII[] = { - ASCII_U, ASCII_S, ASCII_MINUS, ASCII_A, ASCII_S, ASCII_C, ASCII_I, ASCII_I, - '\0' -}; -static const char KW_UTF_8[] = { - ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_8, '\0' -}; -static const char KW_UTF_16[] = { - ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, '\0' -}; -static const char KW_UTF_16BE[] = { - ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_B, ASCII_E, - '\0' -}; -static const char KW_UTF_16LE[] = { - ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_L, ASCII_E, - '\0' -}; +static const char KW_ISO_8859_1[] + = {ASCII_I, ASCII_S, ASCII_O, ASCII_MINUS, ASCII_8, ASCII_8, + ASCII_5, ASCII_9, ASCII_MINUS, ASCII_1, '\0'}; +static const char KW_US_ASCII[] + = {ASCII_U, ASCII_S, ASCII_MINUS, ASCII_A, ASCII_S, + ASCII_C, ASCII_I, ASCII_I, '\0'}; +static const char KW_UTF_8[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_8, '\0'}; +static const char KW_UTF_16[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, '\0'}; +static const char KW_UTF_16BE[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, + ASCII_6, ASCII_B, ASCII_E, '\0'}; +static const char KW_UTF_16LE[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, + ASCII_6, ASCII_L, ASCII_E, '\0'}; static int FASTCALL -getEncodingIndex(const char *name) -{ - static const char * const encodingNames[] = { - KW_ISO_8859_1, - KW_US_ASCII, - KW_UTF_8, - KW_UTF_16, - KW_UTF_16BE, - KW_UTF_16LE, +getEncodingIndex(const char *name) { + static const char *const encodingNames[] = { + KW_ISO_8859_1, KW_US_ASCII, KW_UTF_8, KW_UTF_16, KW_UTF_16BE, KW_UTF_16LE, }; int i; if (name == NULL) return NO_ENC; - for (i = 0; i < (int)(sizeof(encodingNames)/sizeof(encodingNames[0])); i++) + for (i = 0; i < (int)(sizeof(encodingNames) / sizeof(encodingNames[0])); i++) if (streqci(name, encodingNames[i])) return i; return UNKNOWN_ENC; @@ -1647,15 +1528,9 @@ getEncodingIndex(const char *name) XML_PROLOG_STATE otherwise. */ - static int -initScan(const ENCODING * const *encodingTable, - const INIT_ENCODING *enc, - int state, - const char *ptr, - const char *end, - const char **nextTokPtr) -{ +initScan(const ENCODING *const *encodingTable, const INIT_ENCODING *enc, + int state, const char *ptr, const char *end, const char **nextTokPtr) { const ENCODING **encPtr; if (ptr >= end) @@ -1680,20 +1555,17 @@ initScan(const ENCODING * const *encodingTable, case 0xFE: case 0xFF: case 0xEF: /* possibly first byte of UTF-8 BOM */ - if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC - && state == XML_CONTENT_STATE) + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) break; /* fall through */ case 0x00: case 0x3C: return XML_TOK_PARTIAL; } - } - else { + } else { switch (((unsigned char)ptr[0] << 8) | (unsigned char)ptr[1]) { case 0xFEFF: - if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC - && state == XML_CONTENT_STATE) + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) break; *nextTokPtr = ptr + 2; *encPtr = encodingTable[UTF_16BE_ENC]; @@ -1707,8 +1579,7 @@ initScan(const ENCODING * const *encodingTable, *encPtr = encodingTable[UTF_16LE_ENC]; return XmlTok(*encPtr, state, ptr, end, nextTokPtr); case 0xFFFE: - if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC - && state == XML_CONTENT_STATE) + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) break; *nextTokPtr = ptr + 2; *encPtr = encodingTable[UTF_16LE_ENC]; @@ -1723,8 +1594,8 @@ initScan(const ENCODING * const *encodingTable, */ if (state == XML_CONTENT_STATE) { int e = INIT_ENC_INDEX(enc); - if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC - || e == UTF_16LE_ENC || e == UTF_16_ENC) + if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC || e == UTF_16LE_ENC + || e == UTF_16_ENC) break; } if (ptr + 2 == end) @@ -1747,8 +1618,7 @@ initScan(const ENCODING * const *encodingTable, break; *encPtr = encodingTable[UTF_16BE_ENC]; return XmlTok(*encPtr, state, ptr, end, nextTokPtr); - } - else if (ptr[1] == '\0') { + } else if (ptr[1] == '\0') { /* We could recover here in the case: - parsing an external entity - second byte is 0 @@ -1770,7 +1640,6 @@ initScan(const ENCODING * const *encodingTable, return XmlTok(*encPtr, state, ptr, end, nextTokPtr); } - #define NS(x) x #define ns(x) x #define XML_TOK_NS_C @@ -1781,22 +1650,19 @@ initScan(const ENCODING * const *encodingTable, #ifdef XML_NS -#define NS(x) x ## NS -#define ns(x) x ## _ns +# define NS(x) x##NS +# define ns(x) x##_ns -#define XML_TOK_NS_C -#include "xmltok_ns.c" -#undef XML_TOK_NS_C +# define XML_TOK_NS_C +# include "xmltok_ns.c" +# undef XML_TOK_NS_C -#undef NS -#undef ns +# undef NS +# undef ns ENCODING * -XmlInitUnknownEncodingNS(void *mem, - int *table, - CONVERTER convert, - void *userData) -{ +XmlInitUnknownEncodingNS(void *mem, int *table, CONVERTER convert, + void *userData) { ENCODING *enc = XmlInitUnknownEncoding(mem, table, convert, userData); if (enc) ((struct normal_encoding *)enc)->type[ASCII_COLON] = BT_COLON; diff --git a/Modules/expat/xmltok.h b/Modules/expat/xmltok.h index 50926f38..2adbf530 100644 --- a/Modules/expat/xmltok.h +++ b/Modules/expat/xmltok.h @@ -38,16 +38,18 @@ extern "C" { #endif /* The following token may be returned by XmlContentTok */ -#define XML_TOK_TRAILING_RSQB -5 /* ] or ]] at the end of the scan; might be - start of illegal ]]> sequence */ +#define XML_TOK_TRAILING_RSQB \ + -5 /* ] or ]] at the end of the scan; might be \ + start of illegal ]]> sequence */ /* The following tokens may be returned by both XmlPrologTok and XmlContentTok. */ -#define XML_TOK_NONE -4 /* The string to be scanned is empty */ -#define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan; - might be part of CRLF sequence */ -#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */ -#define XML_TOK_PARTIAL -1 /* only part of a token */ +#define XML_TOK_NONE -4 /* The string to be scanned is empty */ +#define XML_TOK_TRAILING_CR \ + -3 /* A CR at the end of the scan; \ + might be part of CRLF sequence */ +#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */ +#define XML_TOK_PARTIAL -1 /* only part of a token */ #define XML_TOK_INVALID 0 /* The following tokens are returned by XmlContentTok; some are also @@ -62,24 +64,24 @@ extern "C" { #define XML_TOK_DATA_NEWLINE 7 #define XML_TOK_CDATA_SECT_OPEN 8 #define XML_TOK_ENTITY_REF 9 -#define XML_TOK_CHAR_REF 10 /* numeric character reference */ +#define XML_TOK_CHAR_REF 10 /* numeric character reference */ /* The following tokens may be returned by both XmlPrologTok and XmlContentTok. */ -#define XML_TOK_PI 11 /* processing instruction */ -#define XML_TOK_XML_DECL 12 /* XML decl or text decl */ +#define XML_TOK_PI 11 /* processing instruction */ +#define XML_TOK_XML_DECL 12 /* XML decl or text decl */ #define XML_TOK_COMMENT 13 -#define XML_TOK_BOM 14 /* Byte order mark */ +#define XML_TOK_BOM 14 /* Byte order mark */ /* The following tokens are returned only by XmlPrologTok */ #define XML_TOK_PROLOG_S 15 -#define XML_TOK_DECL_OPEN 16 /* */ +#define XML_TOK_DECL_OPEN 16 /* */ #define XML_TOK_NAME 18 #define XML_TOK_NMTOKEN 19 -#define XML_TOK_POUND_NAME 20 /* #name */ -#define XML_TOK_OR 21 /* | */ +#define XML_TOK_POUND_NAME 20 /* #name */ +#define XML_TOK_OR 21 /* | */ #define XML_TOK_PERCENT 22 #define XML_TOK_OPEN_PAREN 23 #define XML_TOK_CLOSE_PAREN 24 @@ -90,14 +92,14 @@ extern "C" { #define XML_TOK_INSTANCE_START 29 /* The following occur only in element type declarations */ -#define XML_TOK_NAME_QUESTION 30 /* name? */ -#define XML_TOK_NAME_ASTERISK 31 /* name* */ -#define XML_TOK_NAME_PLUS 32 /* name+ */ -#define XML_TOK_COND_SECT_OPEN 33 /* */ -#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */ -#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */ -#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */ +#define XML_TOK_NAME_QUESTION 30 /* name? */ +#define XML_TOK_NAME_ASTERISK 31 /* name* */ +#define XML_TOK_NAME_PLUS 32 /* name+ */ +#define XML_TOK_COND_SECT_OPEN 33 /* */ +#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */ +#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */ +#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */ #define XML_TOK_COMMA 38 /* The following token is returned only by XmlAttributeValueTok */ @@ -112,20 +114,20 @@ extern "C" { #define XML_TOK_PREFIXED_NAME 41 #ifdef XML_DTD -#define XML_TOK_IGNORE_SECT 42 +# define XML_TOK_IGNORE_SECT 42 #endif /* XML_DTD */ #ifdef XML_DTD -#define XML_N_STATES 4 +# define XML_N_STATES 4 #else /* not XML_DTD */ -#define XML_N_STATES 3 +# define XML_N_STATES 3 #endif /* not XML_DTD */ #define XML_PROLOG_STATE 0 #define XML_CONTENT_STATE 1 #define XML_CDATA_SECTION_STATE 2 #ifdef XML_DTD -#define XML_IGNORE_SECTION_STATE 3 +# define XML_IGNORE_SECTION_STATE 3 #endif /* XML_DTD */ #define XML_N_LITERAL_TYPES 2 @@ -153,52 +155,41 @@ typedef struct { struct encoding; typedef struct encoding ENCODING; -typedef int (PTRCALL *SCANNER)(const ENCODING *, - const char *, - const char *, - const char **); +typedef int(PTRCALL *SCANNER)(const ENCODING *, const char *, const char *, + const char **); enum XML_Convert_Result { XML_CONVERT_COMPLETED = 0, XML_CONVERT_INPUT_INCOMPLETE = 1, - XML_CONVERT_OUTPUT_EXHAUSTED = 2 /* and therefore potentially input remaining as well */ + XML_CONVERT_OUTPUT_EXHAUSTED + = 2 /* and therefore potentially input remaining as well */ }; struct encoding { SCANNER scanners[XML_N_STATES]; SCANNER literalScanners[XML_N_LITERAL_TYPES]; - int (PTRCALL *nameMatchesAscii)(const ENCODING *, - const char *, - const char *, - const char *); - int (PTRFASTCALL *nameLength)(const ENCODING *, const char *); + int(PTRCALL *nameMatchesAscii)(const ENCODING *, const char *, const char *, + const char *); + int(PTRFASTCALL *nameLength)(const ENCODING *, const char *); const char *(PTRFASTCALL *skipS)(const ENCODING *, const char *); - int (PTRCALL *getAtts)(const ENCODING *enc, - const char *ptr, - int attsMax, - ATTRIBUTE *atts); - int (PTRFASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr); - int (PTRCALL *predefinedEntityName)(const ENCODING *, - const char *, - const char *); - void (PTRCALL *updatePosition)(const ENCODING *, - const char *ptr, - const char *end, - POSITION *); - int (PTRCALL *isPublicId)(const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr); - enum XML_Convert_Result (PTRCALL *utf8Convert)(const ENCODING *enc, - const char **fromP, - const char *fromLim, - char **toP, - const char *toLim); - enum XML_Convert_Result (PTRCALL *utf16Convert)(const ENCODING *enc, - const char **fromP, - const char *fromLim, - unsigned short **toP, - const unsigned short *toLim); + int(PTRCALL *getAtts)(const ENCODING *enc, const char *ptr, int attsMax, + ATTRIBUTE *atts); + int(PTRFASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr); + int(PTRCALL *predefinedEntityName)(const ENCODING *, const char *, + const char *); + void(PTRCALL *updatePosition)(const ENCODING *, const char *ptr, + const char *end, POSITION *); + int(PTRCALL *isPublicId)(const ENCODING *enc, const char *ptr, + const char *end, const char **badPtr); + enum XML_Convert_Result(PTRCALL *utf8Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, char **toP, + const char *toLim); + enum XML_Convert_Result(PTRCALL *utf16Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, + unsigned short **toP, + const unsigned short *toLim); int minBytesPerChar; char isUtf8; char isUtf16; @@ -225,66 +216,62 @@ struct encoding { the prolog outside literals, comments and processing instructions. */ - -#define XmlTok(enc, state, ptr, end, nextTokPtr) \ +#define XmlTok(enc, state, ptr, end, nextTokPtr) \ (((enc)->scanners[state])(enc, ptr, end, nextTokPtr)) -#define XmlPrologTok(enc, ptr, end, nextTokPtr) \ - XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr) +#define XmlPrologTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr) -#define XmlContentTok(enc, ptr, end, nextTokPtr) \ - XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr) +#define XmlContentTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr) -#define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \ - XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr) +#define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr) #ifdef XML_DTD -#define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \ - XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr) +# define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr) #endif /* XML_DTD */ /* This is used for performing a 2nd-level tokenization on the content of a literal that has already been returned by XmlTok. */ -#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \ +#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \ (((enc)->literalScanners[literalType])(enc, ptr, end, nextTokPtr)) -#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \ - XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr) +#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr) -#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \ - XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr) +#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr) -#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \ +#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \ (((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2)) -#define XmlNameLength(enc, ptr) \ - (((enc)->nameLength)(enc, ptr)) +#define XmlNameLength(enc, ptr) (((enc)->nameLength)(enc, ptr)) -#define XmlSkipS(enc, ptr) \ - (((enc)->skipS)(enc, ptr)) +#define XmlSkipS(enc, ptr) (((enc)->skipS)(enc, ptr)) -#define XmlGetAttributes(enc, ptr, attsMax, atts) \ +#define XmlGetAttributes(enc, ptr, attsMax, atts) \ (((enc)->getAtts)(enc, ptr, attsMax, atts)) -#define XmlCharRefNumber(enc, ptr) \ - (((enc)->charRefNumber)(enc, ptr)) +#define XmlCharRefNumber(enc, ptr) (((enc)->charRefNumber)(enc, ptr)) -#define XmlPredefinedEntityName(enc, ptr, end) \ +#define XmlPredefinedEntityName(enc, ptr, end) \ (((enc)->predefinedEntityName)(enc, ptr, end)) -#define XmlUpdatePosition(enc, ptr, end, pos) \ +#define XmlUpdatePosition(enc, ptr, end, pos) \ (((enc)->updatePosition)(enc, ptr, end, pos)) -#define XmlIsPublicId(enc, ptr, end, badPtr) \ +#define XmlIsPublicId(enc, ptr, end, badPtr) \ (((enc)->isPublicId)(enc, ptr, end, badPtr)) -#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \ +#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \ (((enc)->utf8Convert)(enc, fromP, fromLim, toP, toLim)) -#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \ +#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \ (((enc)->utf16Convert)(enc, fromP, fromLim, toP, toLim)) typedef struct { @@ -292,16 +279,11 @@ typedef struct { const ENCODING **encPtr; } INIT_ENCODING; -int XmlParseXmlDecl(int isGeneralTextEntity, - const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr, - const char **versionPtr, - const char **versionEndPtr, +int XmlParseXmlDecl(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, const char **encodingNamePtr, - const ENCODING **namedEncodingPtr, - int *standalonePtr); + const ENCODING **namedEncodingPtr, int *standalonePtr); int XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name); const ENCODING *XmlGetUtf8InternalEncoding(void); @@ -310,34 +292,22 @@ int FASTCALL XmlUtf8Encode(int charNumber, char *buf); int FASTCALL XmlUtf16Encode(int charNumber, unsigned short *buf); int XmlSizeOfUnknownEncoding(void); +typedef int(XMLCALL *CONVERTER)(void *userData, const char *p); -typedef int (XMLCALL *CONVERTER) (void *userData, const char *p); - -ENCODING * -XmlInitUnknownEncoding(void *mem, - int *table, - CONVERTER convert, - void *userData); +ENCODING *XmlInitUnknownEncoding(void *mem, int *table, CONVERTER convert, + void *userData); -int XmlParseXmlDeclNS(int isGeneralTextEntity, - const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr, - const char **versionPtr, - const char **versionEndPtr, +int XmlParseXmlDeclNS(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, const char **encodingNamePtr, - const ENCODING **namedEncodingPtr, - int *standalonePtr); + const ENCODING **namedEncodingPtr, int *standalonePtr); int XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name); const ENCODING *XmlGetUtf8InternalEncodingNS(void); const ENCODING *XmlGetUtf16InternalEncodingNS(void); -ENCODING * -XmlInitUnknownEncodingNS(void *mem, - int *table, - CONVERTER convert, - void *userData); +ENCODING *XmlInitUnknownEncodingNS(void *mem, int *table, CONVERTER convert, + void *userData); #ifdef __cplusplus } #endif diff --git a/Modules/expat/xmltok_impl.c b/Modules/expat/xmltok_impl.c index 4d9ae7dc..c209221c 100644 --- a/Modules/expat/xmltok_impl.c +++ b/Modules/expat/xmltok_impl.c @@ -32,130 +32,124 @@ #ifdef XML_TOK_IMPL_C -#ifndef IS_INVALID_CHAR -#define IS_INVALID_CHAR(enc, ptr, n) (0) -#endif - -#define INVALID_LEAD_CASE(n, ptr, nextTokPtr) \ - case BT_LEAD ## n: \ - if (end - ptr < n) \ - return XML_TOK_PARTIAL_CHAR; \ - if (IS_INVALID_CHAR(enc, ptr, n)) { \ - *(nextTokPtr) = (ptr); \ - return XML_TOK_INVALID; \ - } \ - ptr += n; \ - break; +# ifndef IS_INVALID_CHAR +# define IS_INVALID_CHAR(enc, ptr, n) (0) +# endif + +# define INVALID_LEAD_CASE(n, ptr, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n)) { \ + *(nextTokPtr) = (ptr); \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; -#define INVALID_CASES(ptr, nextTokPtr) \ - INVALID_LEAD_CASE(2, ptr, nextTokPtr) \ - INVALID_LEAD_CASE(3, ptr, nextTokPtr) \ - INVALID_LEAD_CASE(4, ptr, nextTokPtr) \ - case BT_NONXML: \ - case BT_MALFORM: \ - case BT_TRAIL: \ - *(nextTokPtr) = (ptr); \ +# define INVALID_CASES(ptr, nextTokPtr) \ + INVALID_LEAD_CASE(2, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(3, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(4, ptr, nextTokPtr) \ + case BT_NONXML: \ + case BT_MALFORM: \ + case BT_TRAIL: \ + *(nextTokPtr) = (ptr); \ return XML_TOK_INVALID; -#define CHECK_NAME_CASE(n, enc, ptr, end, nextTokPtr) \ - case BT_LEAD ## n: \ - if (end - ptr < n) \ - return XML_TOK_PARTIAL_CHAR; \ - if (!IS_NAME_CHAR(enc, ptr, n)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_INVALID; \ - } \ - ptr += n; \ - break; - -#define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \ - case BT_NONASCII: \ - if (!IS_NAME_CHAR_MINBPC(enc, ptr)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_INVALID; \ - } \ - /* fall through */ \ - case BT_NMSTRT: \ - case BT_HEX: \ - case BT_DIGIT: \ - case BT_NAME: \ - case BT_MINUS: \ - ptr += MINBPC(enc); \ - break; \ - CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \ - CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \ - CHECK_NAME_CASE(4, enc, ptr, end, nextTokPtr) - -#define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \ - case BT_LEAD ## n: \ - if (end - ptr < n) \ - return XML_TOK_PARTIAL_CHAR; \ - if (!IS_NMSTRT_CHAR(enc, ptr, n)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_INVALID; \ - } \ - ptr += n; \ - break; - -#define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \ - case BT_NONASCII: \ - if (!IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_INVALID; \ - } \ - /* fall through */ \ - case BT_NMSTRT: \ - case BT_HEX: \ - ptr += MINBPC(enc); \ - break; \ - CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \ - CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \ - CHECK_NMSTRT_CASE(4, enc, ptr, end, nextTokPtr) - -#ifndef PREFIX -#define PREFIX(ident) ident -#endif - - -#define HAS_CHARS(enc, ptr, end, count) \ - (end - ptr >= count * MINBPC(enc)) +# define CHECK_NAME_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (! IS_NAME_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; -#define HAS_CHAR(enc, ptr, end) \ - HAS_CHARS(enc, ptr, end, 1) +# define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (! IS_NAME_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + /* fall through */ \ + case BT_NMSTRT: \ + case BT_HEX: \ + case BT_DIGIT: \ + case BT_NAME: \ + case BT_MINUS: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(4, enc, ptr, end, nextTokPtr) + +# define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (! IS_NMSTRT_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; -#define REQUIRE_CHARS(enc, ptr, end, count) \ - { \ - if (! HAS_CHARS(enc, ptr, end, count)) { \ - return XML_TOK_PARTIAL; \ - } \ +# define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (! IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + /* fall through */ \ + case BT_NMSTRT: \ + case BT_HEX: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(4, enc, ptr, end, nextTokPtr) + +# ifndef PREFIX +# define PREFIX(ident) ident +# endif + +# define HAS_CHARS(enc, ptr, end, count) (end - ptr >= count * MINBPC(enc)) + +# define HAS_CHAR(enc, ptr, end) HAS_CHARS(enc, ptr, end, 1) + +# define REQUIRE_CHARS(enc, ptr, end, count) \ + { \ + if (! HAS_CHARS(enc, ptr, end, count)) { \ + return XML_TOK_PARTIAL; \ + } \ } -#define REQUIRE_CHAR(enc, ptr, end) \ - REQUIRE_CHARS(enc, ptr, end, 1) - +# define REQUIRE_CHAR(enc, ptr, end) REQUIRE_CHARS(enc, ptr, end, 1) /* ptr points to character following " */ switch (BYTE_TYPE(enc, ptr + MINBPC(enc))) { - case BT_S: case BT_CR: case BT_LF: case BT_PERCNT: + case BT_S: + case BT_CR: + case BT_LF: + case BT_PERCNT: *nextTokPtr = ptr; return XML_TOK_INVALID; } /* fall through */ - case BT_S: case BT_CR: case BT_LF: + case BT_S: + case BT_CR: + case BT_LF: *nextTokPtr = ptr; return XML_TOK_DECL_OPEN; case BT_NMSTRT: @@ -220,12 +218,12 @@ PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, } static int PTRCALL -PREFIX(checkPiTarget)(const ENCODING *UNUSED_P(enc), const char *ptr, - const char *end, int *tokPtr) -{ +PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end, + int *tokPtr) { int upper = 0; + UNUSED_P(enc); *tokPtr = XML_TOK_PI; - if (end - ptr != MINBPC(enc)*3) + if (end - ptr != MINBPC(enc) * 3) return 1; switch (BYTE_TO_ASCII(enc, ptr)) { case ASCII_x: @@ -265,30 +263,31 @@ PREFIX(checkPiTarget)(const ENCODING *UNUSED_P(enc), const char *ptr, /* ptr points to character following "= end) return XML_TOK_NONE; if (MINBPC(enc) > 1) { @@ -361,11 +359,11 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, case BT_RSQB: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); - if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + if (! CHAR_MATCHES(enc, ptr, ASCII_RSQB)) break; ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); - if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { ptr -= MINBPC(enc); break; } @@ -381,23 +379,25 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, case BT_LF: *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_DATA_NEWLINE; - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) default: ptr += MINBPC(enc); break; } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_DATA_CHARS; \ - } \ - ptr += n; \ - break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_NONXML: case BT_MALFORM: case BT_TRAIL: @@ -418,23 +418,26 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, /* ptr points to character following "= end) return XML_TOK_NONE; if (MINBPC(enc) > 1) { @@ -842,48 +843,50 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, ptr += MINBPC(enc); if (! HAS_CHAR(enc, ptr, end)) return XML_TOK_TRAILING_RSQB; - if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + if (! CHAR_MATCHES(enc, ptr, ASCII_RSQB)) break; ptr += MINBPC(enc); if (! HAS_CHAR(enc, ptr, end)) return XML_TOK_TRAILING_RSQB; - if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { ptr -= MINBPC(enc); break; } *nextTokPtr = ptr; return XML_TOK_INVALID; - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) default: ptr += MINBPC(enc); break; } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_DATA_CHARS; \ - } \ - ptr += n; \ - break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_RSQB: if (HAS_CHARS(enc, ptr, end, 2)) { - if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) { - ptr += MINBPC(enc); - break; - } - if (HAS_CHARS(enc, ptr, end, 3)) { - if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), ASCII_GT)) { - ptr += MINBPC(enc); - break; - } - *nextTokPtr = ptr + 2*MINBPC(enc); - return XML_TOK_INVALID; - } + if (! CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) { + ptr += MINBPC(enc); + break; + } + if (HAS_CHARS(enc, ptr, end, 3)) { + if (! CHAR_MATCHES(enc, ptr + 2 * MINBPC(enc), ASCII_GT)) { + ptr += MINBPC(enc); + break; + } + *nextTokPtr = ptr + 2 * MINBPC(enc); + return XML_TOK_INVALID; + } } /* fall through */ case BT_AMP: @@ -908,12 +911,14 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, static int PTRCALL PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ + const char **nextTokPtr) { REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) - case BT_S: case BT_LF: case BT_CR: case BT_PERCNT: + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_S: + case BT_LF: + case BT_CR: + case BT_PERCNT: *nextTokPtr = ptr; return XML_TOK_PERCENT; default: @@ -922,7 +927,7 @@ PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) case BT_SEMI: *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_PARAM_ENTITY_REF; @@ -936,20 +941,24 @@ PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, static int PTRCALL PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ + const char **nextTokPtr) { REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) default: *nextTokPtr = ptr; return XML_TOK_INVALID; } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) - case BT_CR: case BT_LF: case BT_S: - case BT_RPAR: case BT_GT: case BT_PERCNT: case BT_VERBAR: + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_CR: + case BT_LF: + case BT_S: + case BT_RPAR: + case BT_GT: + case BT_PERCNT: + case BT_VERBAR: *nextTokPtr = ptr; return XML_TOK_POUND_NAME; default: @@ -961,14 +970,12 @@ PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end, } static int PTRCALL -PREFIX(scanLit)(int open, const ENCODING *enc, - const char *ptr, const char *end, - const char **nextTokPtr) -{ +PREFIX(scanLit)(int open, const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { while (HAS_CHAR(enc, ptr, end)) { int t = BYTE_TYPE(enc, ptr); switch (t) { - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) case BT_QUOT: case BT_APOS: ptr += MINBPC(enc); @@ -978,8 +985,12 @@ PREFIX(scanLit)(int open, const ENCODING *enc, return -XML_TOK_LITERAL; *nextTokPtr = ptr; switch (BYTE_TYPE(enc, ptr)) { - case BT_S: case BT_CR: case BT_LF: - case BT_GT: case BT_PERCNT: case BT_LSQB: + case BT_S: + case BT_CR: + case BT_LF: + case BT_GT: + case BT_PERCNT: + case BT_LSQB: return XML_TOK_LITERAL; default: return XML_TOK_INVALID; @@ -994,8 +1005,7 @@ PREFIX(scanLit)(int open, const ENCODING *enc, static int PTRCALL PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ + const char **nextTokPtr) { int tok; if (ptr >= end) return XML_TOK_NONE; @@ -1013,27 +1023,26 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, return PREFIX(scanLit)(BT_QUOT, enc, ptr + MINBPC(enc), end, nextTokPtr); case BT_APOS: return PREFIX(scanLit)(BT_APOS, enc, ptr + MINBPC(enc), end, nextTokPtr); - case BT_LT: - { - ptr += MINBPC(enc); - REQUIRE_CHAR(enc, ptr, end); - switch (BYTE_TYPE(enc, ptr)) { - case BT_EXCL: - return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr); - case BT_QUEST: - return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); - case BT_NMSTRT: - case BT_HEX: - case BT_NONASCII: - case BT_LEAD2: - case BT_LEAD3: - case BT_LEAD4: - *nextTokPtr = ptr - MINBPC(enc); - return XML_TOK_INSTANCE_START; - } - *nextTokPtr = ptr; - return XML_TOK_INVALID; + case BT_LT: { + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + case BT_EXCL: + return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_QUEST: + return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_NMSTRT: + case BT_HEX: + case BT_NONASCII: + case BT_LEAD2: + case BT_LEAD3: + case BT_LEAD4: + *nextTokPtr = ptr - MINBPC(enc); + return XML_TOK_INSTANCE_START; } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } case BT_CR: if (ptr + MINBPC(enc) == end) { *nextTokPtr = end; @@ -1041,13 +1050,15 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, return -XML_TOK_PROLOG_S; } /* fall through */ - case BT_S: case BT_LF: + case BT_S: + case BT_LF: for (;;) { ptr += MINBPC(enc); if (! HAS_CHAR(enc, ptr, end)) break; switch (BYTE_TYPE(enc, ptr)) { - case BT_S: case BT_LF: + case BT_S: + case BT_LF: break; case BT_CR: /* don't split CR/LF pair */ @@ -1076,7 +1087,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) { REQUIRE_CHARS(enc, ptr, end, 2); if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_GT)) { - *nextTokPtr = ptr + 2*MINBPC(enc); + *nextTokPtr = ptr + 2 * MINBPC(enc); return XML_TOK_COND_SECT_CLOSE; } } @@ -1099,8 +1110,12 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, case BT_PLUS: *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_CLOSE_PAREN_PLUS; - case BT_CR: case BT_LF: case BT_S: - case BT_GT: case BT_COMMA: case BT_VERBAR: + case BT_CR: + case BT_LF: + case BT_S: + case BT_GT: + case BT_COMMA: + case BT_VERBAR: case BT_RPAR: *nextTokPtr = ptr; return XML_TOK_CLOSE_PAREN; @@ -1115,24 +1130,26 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, return XML_TOK_DECL_CLOSE; case BT_NUM: return PREFIX(scanPoundName)(enc, ptr + MINBPC(enc), end, nextTokPtr); -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - if (end - ptr < n) \ - return XML_TOK_PARTIAL_CHAR; \ - if (IS_NMSTRT_CHAR(enc, ptr, n)) { \ - ptr += n; \ - tok = XML_TOK_NAME; \ - break; \ - } \ - if (IS_NAME_CHAR(enc, ptr, n)) { \ - ptr += n; \ - tok = XML_TOK_NMTOKEN; \ - break; \ - } \ - *nextTokPtr = ptr; \ +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_NMSTRT_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NAME; \ + break; \ + } \ + if (IS_NAME_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NMTOKEN; \ + break; \ + } \ + *nextTokPtr = ptr; \ return XML_TOK_INVALID; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_NMSTRT: case BT_HEX: tok = XML_TOK_NAME; @@ -1141,9 +1158,9 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, case BT_DIGIT: case BT_NAME: case BT_MINUS: -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: -#endif +# endif tok = XML_TOK_NMTOKEN; ptr += MINBPC(enc); break; @@ -1165,13 +1182,19 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) - case BT_GT: case BT_RPAR: case BT_COMMA: - case BT_VERBAR: case BT_LSQB: case BT_PERCNT: - case BT_S: case BT_CR: case BT_LF: + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_GT: + case BT_RPAR: + case BT_COMMA: + case BT_VERBAR: + case BT_LSQB: + case BT_PERCNT: + case BT_S: + case BT_CR: + case BT_LF: *nextTokPtr = ptr; return tok; -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: ptr += MINBPC(enc); switch (tok) { @@ -1179,7 +1202,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, REQUIRE_CHAR(enc, ptr, end); tok = XML_TOK_PREFIXED_NAME; switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) default: tok = XML_TOK_NMTOKEN; break; @@ -1190,23 +1213,23 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, break; } break; -#endif +# endif case BT_PLUS: - if (tok == XML_TOK_NMTOKEN) { + if (tok == XML_TOK_NMTOKEN) { *nextTokPtr = ptr; return XML_TOK_INVALID; } *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_NAME_PLUS; case BT_AST: - if (tok == XML_TOK_NMTOKEN) { + if (tok == XML_TOK_NMTOKEN) { *nextTokPtr = ptr; return XML_TOK_INVALID; } *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_NAME_ASTERISK; case BT_QUEST: - if (tok == XML_TOK_NMTOKEN) { + if (tok == XML_TOK_NMTOKEN) { *nextTokPtr = ptr; return XML_TOK_INVALID; } @@ -1221,9 +1244,8 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, } static int PTRCALL -PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { const char *start; if (ptr >= end) return XML_TOK_NONE; @@ -1238,10 +1260,14 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, start = ptr; while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: ptr += n; break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_AMP: if (ptr == start) return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); @@ -1287,9 +1313,8 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, } static int PTRCALL -PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { const char *start; if (ptr >= end) return XML_TOK_NONE; @@ -1304,10 +1329,14 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, start = ptr; while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: ptr += n; break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_AMP: if (ptr == start) return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); @@ -1315,8 +1344,7 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, return XML_TOK_DATA_CHARS; case BT_PERCNT: if (ptr == start) { - int tok = PREFIX(scanPercent)(enc, ptr + MINBPC(enc), - end, nextTokPtr); + int tok = PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr); return (tok == XML_TOK_PERCENT) ? XML_TOK_INVALID : tok; } *nextTokPtr = ptr; @@ -1349,12 +1377,11 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, return XML_TOK_DATA_CHARS; } -#ifdef XML_DTD +# ifdef XML_DTD static int PTRCALL -PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { int level = 0; if (MINBPC(enc) > 1) { size_t n = end - ptr; @@ -1365,7 +1392,7 @@ PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) case BT_LT: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); @@ -1402,12 +1429,11 @@ PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, return XML_TOK_PARTIAL; } -#endif /* XML_DTD */ +# endif /* XML_DTD */ static int PTRCALL PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, - const char **badPtr) -{ + const char **badPtr) { ptr += MINBPC(enc); end -= MINBPC(enc); for (; HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) { @@ -1430,9 +1456,9 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, case BT_AST: case BT_PERCNT: case BT_NUM: -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: -#endif +# endif break; case BT_S: if (CHAR_MATCHES(enc, ptr, ASCII_TAB)) { @@ -1442,7 +1468,7 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, break; case BT_NAME: case BT_NMSTRT: - if (!(BYTE_TO_ASCII(enc, ptr) & ~0x7f)) + if (! (BYTE_TO_ASCII(enc, ptr) & ~0x7f)) break; /* fall through */ default: @@ -1466,9 +1492,8 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, */ static int PTRCALL -PREFIX(getAtts)(const ENCODING *enc, const char *ptr, - int attsMax, ATTRIBUTE *atts) -{ +PREFIX(getAtts)(const ENCODING *enc, const char *ptr, int attsMax, + ATTRIBUTE *atts) { enum { other, inName, inValue } state = inName; int nAtts = 0; int open = 0; /* defined when state == inValue; @@ -1476,32 +1501,35 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, for (ptr += MINBPC(enc);; ptr += MINBPC(enc)) { switch (BYTE_TYPE(enc, ptr)) { -#define START_NAME \ - if (state == other) { \ - if (nAtts < attsMax) { \ - atts[nAtts].name = ptr; \ - atts[nAtts].normalized = 1; \ - } \ - state = inName; \ - } -#define LEAD_CASE(n) \ - case BT_LEAD ## n: START_NAME ptr += (n - MINBPC(enc)); break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define START_NAME \ + if (state == other) { \ + if (nAtts < attsMax) { \ + atts[nAtts].name = ptr; \ + atts[nAtts].normalized = 1; \ + } \ + state = inName; \ + } +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + START_NAME ptr += (n - MINBPC(enc)); \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_NONASCII: case BT_NMSTRT: case BT_HEX: START_NAME break; -#undef START_NAME +# undef START_NAME case BT_QUOT: if (state != inValue) { if (nAtts < attsMax) atts[nAtts].valuePtr = ptr + MINBPC(enc); state = inValue; open = BT_QUOT; - } - else if (open == BT_QUOT) { + } else if (open == BT_QUOT) { state = other; if (nAtts < attsMax) atts[nAtts].valueEnd = ptr; @@ -1514,8 +1542,7 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, atts[nAtts].valuePtr = ptr + MINBPC(enc); state = inValue; open = BT_APOS; - } - else if (open == BT_APOS) { + } else if (open == BT_APOS) { state = other; if (nAtts < attsMax) atts[nAtts].valueEnd = ptr; @@ -1529,16 +1556,15 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, case BT_S: if (state == inName) state = other; - else if (state == inValue - && nAtts < attsMax - && atts[nAtts].normalized + else if (state == inValue && nAtts < attsMax && atts[nAtts].normalized && (ptr == atts[nAtts].valuePtr || BYTE_TO_ASCII(enc, ptr) != ASCII_SPACE || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ASCII_SPACE || BYTE_TYPE(enc, ptr + MINBPC(enc)) == open)) atts[nAtts].normalized = 0; break; - case BT_CR: case BT_LF: + case BT_CR: + case BT_LF: /* This case ensures that the first attribute name is counted Apart from that we could just change state on the quote. */ if (state == inName) @@ -1559,29 +1585,44 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, } static int PTRFASTCALL -PREFIX(charRefNumber)(const ENCODING *UNUSED_P(enc), const char *ptr) -{ +PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr) { int result = 0; /* skip &# */ - ptr += 2*MINBPC(enc); + UNUSED_P(enc); + ptr += 2 * MINBPC(enc); if (CHAR_MATCHES(enc, ptr, ASCII_x)) { - for (ptr += MINBPC(enc); - !CHAR_MATCHES(enc, ptr, ASCII_SEMI); + for (ptr += MINBPC(enc); ! CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { int c = BYTE_TO_ASCII(enc, ptr); switch (c) { - case ASCII_0: case ASCII_1: case ASCII_2: case ASCII_3: case ASCII_4: - case ASCII_5: case ASCII_6: case ASCII_7: case ASCII_8: case ASCII_9: + case ASCII_0: + case ASCII_1: + case ASCII_2: + case ASCII_3: + case ASCII_4: + case ASCII_5: + case ASCII_6: + case ASCII_7: + case ASCII_8: + case ASCII_9: result <<= 4; result |= (c - ASCII_0); break; - case ASCII_A: case ASCII_B: case ASCII_C: - case ASCII_D: case ASCII_E: case ASCII_F: + case ASCII_A: + case ASCII_B: + case ASCII_C: + case ASCII_D: + case ASCII_E: + case ASCII_F: result <<= 4; result += 10 + (c - ASCII_A); break; - case ASCII_a: case ASCII_b: case ASCII_c: - case ASCII_d: case ASCII_e: case ASCII_f: + case ASCII_a: + case ASCII_b: + case ASCII_c: + case ASCII_d: + case ASCII_e: + case ASCII_f: result <<= 4; result += 10 + (c - ASCII_a); break; @@ -1589,9 +1630,8 @@ PREFIX(charRefNumber)(const ENCODING *UNUSED_P(enc), const char *ptr) if (result >= 0x110000) return -1; } - } - else { - for (; !CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { + } else { + for (; ! CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { int c = BYTE_TO_ASCII(enc, ptr); result *= 10; result += (c - ASCII_0); @@ -1603,10 +1643,10 @@ PREFIX(charRefNumber)(const ENCODING *UNUSED_P(enc), const char *ptr) } static int PTRCALL -PREFIX(predefinedEntityName)(const ENCODING *UNUSED_P(enc), const char *ptr, - const char *end) -{ - switch ((end - ptr)/MINBPC(enc)) { +PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, + const char *end) { + UNUSED_P(enc); + switch ((end - ptr) / MINBPC(enc)) { case 2: if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_t)) { switch (BYTE_TO_ASCII(enc, ptr)) { @@ -1657,9 +1697,9 @@ PREFIX(predefinedEntityName)(const ENCODING *UNUSED_P(enc), const char *ptr, } static int PTRCALL -PREFIX(nameMatchesAscii)(const ENCODING *UNUSED_P(enc), const char *ptr1, - const char *end1, const char *ptr2) -{ +PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, + const char *end1, const char *ptr2) { + UNUSED_P(enc); for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) { if (end1 - ptr1 < MINBPC(enc)) { /* This line cannot be executed. The incoming data has already @@ -1669,27 +1709,30 @@ PREFIX(nameMatchesAscii)(const ENCODING *UNUSED_P(enc), const char *ptr1, */ return 0; /* LCOV_EXCL_LINE */ } - if (!CHAR_MATCHES(enc, ptr1, *ptr2)) + if (! CHAR_MATCHES(enc, ptr1, *ptr2)) return 0; } return ptr1 == end1; } static int PTRFASTCALL -PREFIX(nameLength)(const ENCODING *enc, const char *ptr) -{ +PREFIX(nameLength)(const ENCODING *enc, const char *ptr) { const char *start = ptr; for (;;) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: ptr += n; break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_NONASCII: case BT_NMSTRT: -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: -#endif +# endif case BT_HEX: case BT_DIGIT: case BT_NAME: @@ -1702,9 +1745,8 @@ PREFIX(nameLength)(const ENCODING *enc, const char *ptr) } } -static const char * PTRFASTCALL -PREFIX(skipS)(const ENCODING *enc, const char *ptr) -{ +static const char *PTRFASTCALL +PREFIX(skipS)(const ENCODING *enc, const char *ptr) { for (;;) { switch (BYTE_TYPE(enc, ptr)) { case BT_LF: @@ -1719,19 +1761,18 @@ PREFIX(skipS)(const ENCODING *enc, const char *ptr) } static void PTRCALL -PREFIX(updatePosition)(const ENCODING *enc, - const char *ptr, - const char *end, - POSITION *pos) -{ +PREFIX(updatePosition)(const ENCODING *enc, const char *ptr, const char *end, + POSITION *pos) { while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - ptr += n; \ - break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_LF: pos->columnNumber = (XML_Size)-1; pos->lineNumber++; @@ -1752,12 +1793,12 @@ PREFIX(updatePosition)(const ENCODING *enc, } } -#undef DO_LEAD_CASE -#undef MULTIBYTE_CASES -#undef INVALID_CASES -#undef CHECK_NAME_CASE -#undef CHECK_NAME_CASES -#undef CHECK_NMSTRT_CASE -#undef CHECK_NMSTRT_CASES +# undef DO_LEAD_CASE +# undef MULTIBYTE_CASES +# undef INVALID_CASES +# undef CHECK_NAME_CASE +# undef CHECK_NAME_CASES +# undef CHECK_NMSTRT_CASE +# undef CHECK_NMSTRT_CASES #endif /* XML_TOK_IMPL_C */ diff --git a/Modules/expat/xmltok_impl.h b/Modules/expat/xmltok_impl.h index a6420f48..e925dbc7 100644 --- a/Modules/expat/xmltok_impl.h +++ b/Modules/expat/xmltok_impl.h @@ -31,43 +31,43 @@ */ enum { - BT_NONXML, - BT_MALFORM, - BT_LT, - BT_AMP, - BT_RSQB, - BT_LEAD2, - BT_LEAD3, - BT_LEAD4, - BT_TRAIL, - BT_CR, - BT_LF, - BT_GT, - BT_QUOT, - BT_APOS, - BT_EQUALS, - BT_QUEST, - BT_EXCL, - BT_SOL, - BT_SEMI, - BT_NUM, - BT_LSQB, - BT_S, - BT_NMSTRT, - BT_COLON, - BT_HEX, - BT_DIGIT, - BT_NAME, - BT_MINUS, - BT_OTHER, /* known not to be a name or name start character */ + BT_NONXML, /* e.g. noncharacter-FFFF */ + BT_MALFORM, /* illegal, with regard to encoding */ + BT_LT, /* less than = "<" */ + BT_AMP, /* ampersand = "&" */ + BT_RSQB, /* right square bracket = "[" */ + BT_LEAD2, /* lead byte of a 2-byte UTF-8 character */ + BT_LEAD3, /* lead byte of a 3-byte UTF-8 character */ + BT_LEAD4, /* lead byte of a 4-byte UTF-8 character */ + BT_TRAIL, /* trailing unit, e.g. second 16-bit unit of a 4-byte char. */ + BT_CR, /* carriage return = "\r" */ + BT_LF, /* line feed = "\n" */ + BT_GT, /* greater than = ">" */ + BT_QUOT, /* quotation character = "\"" */ + BT_APOS, /* aposthrophe = "'" */ + BT_EQUALS, /* equal sign = "=" */ + BT_QUEST, /* question mark = "?" */ + BT_EXCL, /* exclamation mark = "!" */ + BT_SOL, /* solidus, slash = "/" */ + BT_SEMI, /* semicolon = ";" */ + BT_NUM, /* number sign = "#" */ + BT_LSQB, /* left square bracket = "[" */ + BT_S, /* white space, e.g. "\t", " "[, "\r"] */ + BT_NMSTRT, /* non-hex name start letter = "G".."Z" + "g".."z" + "_" */ + BT_COLON, /* colon = ":" */ + BT_HEX, /* hex letter = "A".."F" + "a".."f" */ + BT_DIGIT, /* digit = "0".."9" */ + BT_NAME, /* dot and middle dot = "." + chr(0xb7) */ + BT_MINUS, /* minus = "-" */ + BT_OTHER, /* known not to be a name or name start character */ BT_NONASCII, /* might be a name or name start character */ - BT_PERCNT, - BT_LPAR, - BT_RPAR, - BT_AST, - BT_PLUS, - BT_COMMA, - BT_VERBAR + BT_PERCNT, /* percent sign = "%" */ + BT_LPAR, /* left parenthesis = "(" */ + BT_RPAR, /* right parenthesis = "(" */ + BT_AST, /* asterisk = "*" */ + BT_PLUS, /* plus sign = "+" */ + BT_COMMA, /* comma = "," */ + BT_VERBAR /* vertical bar = "|" */ }; #include diff --git a/Modules/expat/xmltok_ns.c b/Modules/expat/xmltok_ns.c index 23d31e8e..919c74e9 100644 --- a/Modules/expat/xmltok_ns.c +++ b/Modules/expat/xmltok_ns.c @@ -33,56 +33,47 @@ #ifdef XML_TOK_NS_C const ENCODING * -NS(XmlGetUtf8InternalEncoding)(void) -{ +NS(XmlGetUtf8InternalEncoding)(void) { return &ns(internal_utf8_encoding).enc; } const ENCODING * -NS(XmlGetUtf16InternalEncoding)(void) -{ -#if BYTEORDER == 1234 +NS(XmlGetUtf16InternalEncoding)(void) { +# if BYTEORDER == 1234 return &ns(internal_little2_encoding).enc; -#elif BYTEORDER == 4321 +# elif BYTEORDER == 4321 return &ns(internal_big2_encoding).enc; -#else +# else const short n = 1; - return (*(const char *)&n - ? &ns(internal_little2_encoding).enc - : &ns(internal_big2_encoding).enc); -#endif + return (*(const char *)&n ? &ns(internal_little2_encoding).enc + : &ns(internal_big2_encoding).enc); +# endif } -static const ENCODING * const NS(encodings)[] = { - &ns(latin1_encoding).enc, - &ns(ascii_encoding).enc, - &ns(utf8_encoding).enc, - &ns(big2_encoding).enc, - &ns(big2_encoding).enc, - &ns(little2_encoding).enc, - &ns(utf8_encoding).enc /* NO_ENC */ +static const ENCODING *const NS(encodings)[] = { + &ns(latin1_encoding).enc, &ns(ascii_encoding).enc, + &ns(utf8_encoding).enc, &ns(big2_encoding).enc, + &ns(big2_encoding).enc, &ns(little2_encoding).enc, + &ns(utf8_encoding).enc /* NO_ENC */ }; static int PTRCALL NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ - return initScan(NS(encodings), (const INIT_ENCODING *)enc, - XML_PROLOG_STATE, ptr, end, nextTokPtr); + const char **nextTokPtr) { + return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_PROLOG_STATE, + ptr, end, nextTokPtr); } static int PTRCALL NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ - return initScan(NS(encodings), (const INIT_ENCODING *)enc, - XML_CONTENT_STATE, ptr, end, nextTokPtr); + const char **nextTokPtr) { + return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_CONTENT_STATE, + ptr, end, nextTokPtr); } int NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, - const char *name) -{ + const char *name) { int i = getEncodingIndex(name); if (i == UNKNOWN_ENC) return 0; @@ -96,9 +87,8 @@ NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, } static const ENCODING * -NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) -{ -#define ENCODING_MAX 128 +NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) { +# define ENCODING_MAX 128 char buf[ENCODING_MAX]; char *p = buf; int i; @@ -115,28 +105,14 @@ NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) } int -NS(XmlParseXmlDecl)(int isGeneralTextEntity, - const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr, - const char **versionPtr, - const char **versionEndPtr, - const char **encodingName, - const ENCODING **encoding, - int *standalone) -{ - return doParseXmlDecl(NS(findEncoding), - isGeneralTextEntity, - enc, - ptr, - end, - badPtr, - versionPtr, - versionEndPtr, - encodingName, - encoding, - standalone); +NS(XmlParseXmlDecl)(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, + const char **encodingName, const ENCODING **encoding, + int *standalone) { + return doParseXmlDecl(NS(findEncoding), isGeneralTextEntity, enc, ptr, end, + badPtr, versionPtr, versionEndPtr, encodingName, + encoding, standalone); } #endif /* XML_TOK_NS_C */ diff --git a/Modules/faulthandler.c b/Modules/faulthandler.c index 0dbd5a33..97c64f63 100644 --- a/Modules/faulthandler.c +++ b/Modules/faulthandler.c @@ -1322,7 +1322,11 @@ _PyFaulthandler_Init(int enable) * be able to allocate memory on the stack, even on a stack overflow. If it * fails, ignore the error. */ stack.ss_flags = 0; - stack.ss_size = SIGSTKSZ; + /* bpo-21131: allocate dedicated stack of SIGSTKSZ*2 bytes, instead of just + SIGSTKSZ bytes. Calling the previous signal handler in faulthandler + signal handler uses more than SIGSTKSZ bytes of stack memory on some + platforms. */ + stack.ss_size = SIGSTKSZ * 2; stack.ss_sp = PyMem_Malloc(stack.ss_size); if (stack.ss_sp != NULL) { err = sigaltstack(&stack, &old_stack); diff --git a/Modules/getpath.c b/Modules/getpath.c index bfb33316..ba8d74b4 100644 --- a/Modules/getpath.c +++ b/Modules/getpath.c @@ -909,7 +909,7 @@ calculate_init(PyCalculatePath *calculate, return DECODE_LOCALE_ERR("PREFIX define", len); } calculate->exec_prefix = Py_DecodeLocale(EXEC_PREFIX, &len); - if (!calculate->prefix) { + if (!calculate->exec_prefix) { return DECODE_LOCALE_ERR("EXEC_PREFIX define", len); } calculate->lib_python = Py_DecodeLocale("lib/python" VERSION, &len); diff --git a/Modules/itertoolsmodule.c b/Modules/itertoolsmodule.c index bff9df60..0ddd98de 100644 --- a/Modules/itertoolsmodule.c +++ b/Modules/itertoolsmodule.c @@ -395,6 +395,7 @@ typedef struct { PyObject_HEAD PyObject *it; int numread; /* 0 <= numread <= LINKCELLS */ + int running; PyObject *nextlink; PyObject *(values[LINKCELLS]); } teedataobject; @@ -417,6 +418,7 @@ teedataobject_newinternal(PyObject *it) if (tdo == NULL) return NULL; + tdo->running = 0; tdo->numread = 0; tdo->nextlink = NULL; Py_INCREF(it); @@ -445,7 +447,14 @@ teedataobject_getitem(teedataobject *tdo, int i) else { /* this is the lead iterator, so fetch more data */ assert(i == tdo->numread); + if (tdo->running) { + PyErr_SetString(PyExc_RuntimeError, + "cannot re-enter the tee iterator"); + return NULL; + } + tdo->running = 1; value = PyIter_Next(tdo->it); + tdo->running = 0; if (value == NULL) return NULL; tdo->numread++; diff --git a/Modules/mmapmodule.c b/Modules/mmapmodule.c index 223afacf..37a5c3da 100644 --- a/Modules/mmapmodule.c +++ b/Modules/mmapmodule.c @@ -1392,7 +1392,8 @@ static void setint(PyObject *d, const char *name, long value) { PyObject *o = PyLong_FromLong(value); - if (o && PyDict_SetItemString(d, name, o) == 0) { + if (o) { + PyDict_SetItemString(d, name, o); Py_DECREF(o); } } diff --git a/Modules/overlapped.c b/Modules/overlapped.c index 7798856b..596ee330 100644 --- a/Modules/overlapped.c +++ b/Modules/overlapped.c @@ -486,7 +486,8 @@ overlapped_FormatMessage(PyObject *ignore, PyObject *args) return NULL; n = FormatMessageW(FORMAT_MESSAGE_ALLOCATE_BUFFER | - FORMAT_MESSAGE_FROM_SYSTEM, + FORMAT_MESSAGE_FROM_SYSTEM | + FORMAT_MESSAGE_IGNORE_INSERTS, NULL, code, MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT), diff --git a/Modules/posixmodule.c b/Modules/posixmodule.c index b758e766..58cb9b0d 100644 --- a/Modules/posixmodule.c +++ b/Modules/posixmodule.c @@ -5809,6 +5809,9 @@ os_sched_setaffinity_impl(PyObject *module, pid_t pid, PyObject *mask) } CPU_SET_S(cpu, setsize, cpu_set); } + if (PyErr_Occurred()) { + goto error; + } Py_CLEAR(iterator); if (sched_setaffinity(pid, setsize, cpu_set)) { diff --git a/Modules/socketmodule.c b/Modules/socketmodule.c index 65385e89..a9ef7e20 100644 --- a/Modules/socketmodule.c +++ b/Modules/socketmodule.c @@ -741,6 +741,17 @@ internal_select(PySocketSockObject *s, int writing, _PyTime_t interval, ms = _PyTime_AsMilliseconds(interval, _PyTime_ROUND_CEILING); assert(ms <= INT_MAX); + /* On some OSes, typically BSD-based ones, the timeout parameter of the + poll() syscall, when negative, must be exactly INFTIM, where defined, + or -1. See issue 37811. */ + if (ms < 0) { +#ifdef INFTIM + ms = INFTIM; +#else + ms = -1; +#endif + } + Py_BEGIN_ALLOW_THREADS; n = poll(&pollfd, 1, (int)ms); Py_END_ALLOW_THREADS; diff --git a/Modules/timemodule.c b/Modules/timemodule.c index 4c8e2cb2..0ae4fcc3 100644 --- a/Modules/timemodule.c +++ b/Modules/timemodule.c @@ -1189,7 +1189,7 @@ _PyTime_GetProcessTimeWithInfo(_PyTime_t *tp, _Py_clock_info_t *info) return -1; } - _PyTime_t total = utime + utime; + _PyTime_t total = utime + stime; *tp = total; return 0; } diff --git a/Objects/bytearrayobject.c b/Objects/bytearrayobject.c index 8a0994ff..41de28d5 100644 --- a/Objects/bytearrayobject.c +++ b/Objects/bytearrayobject.c @@ -1689,6 +1689,10 @@ bytearray_extend(PyByteArrayObject *self, PyObject *iterable_of_ints) } Py_DECREF(bytearray_obj); + if (PyErr_Occurred()) { + return NULL; + } + Py_RETURN_NONE; } diff --git a/Objects/dictobject.c b/Objects/dictobject.c index eb635263..94374488 100644 --- a/Objects/dictobject.c +++ b/Objects/dictobject.c @@ -39,7 +39,7 @@ Size of indices is dk_size. Type of each index in indices is vary on dk_size: * int32 for 2**16 <= dk_size <= 2**31 * int64 for 2**32 <= dk_size -dk_entries is array of PyDictKeyEntry. It's size is USABLE_FRACTION(dk_size). +dk_entries is array of PyDictKeyEntry. Its size is USABLE_FRACTION(dk_size). DK_ENTRIES(dk) can be used to get pointer to entries. NOTE: Since negative value is used for DKIX_EMPTY and DKIX_DUMMY, type of diff --git a/Objects/floatobject.c b/Objects/floatobject.c index 67f9e5d5..b4b1e5cf 100644 --- a/Objects/floatobject.c +++ b/Objects/floatobject.c @@ -43,7 +43,7 @@ static PyTypeObject FloatInfoType; PyDoc_STRVAR(floatinfo__doc__, "sys.float_info\n\ \n\ -A structseq holding information about the float type. It contains low level\n\ +A named tuple holding information about the float type. It contains low level\n\ information about the precision and internal representation. Please study\n\ your system's :file:`float.h` for more information."); diff --git a/Objects/genobject.c b/Objects/genobject.c index b0e87707..8a978b1a 100644 --- a/Objects/genobject.c +++ b/Objects/genobject.c @@ -1905,11 +1905,6 @@ async_gen_athrow_throw(PyAsyncGenAThrow *o, PyObject *args) { PyObject *retval; - if (o->agt_state == AWAITABLE_STATE_INIT) { - PyErr_SetString(PyExc_RuntimeError, NON_INIT_CORO_MSG); - return NULL; - } - if (o->agt_state == AWAITABLE_STATE_CLOSED) { PyErr_SetNone(PyExc_StopIteration); return NULL; diff --git a/Objects/listobject.c b/Objects/listobject.c index 78aa8dea..c5e7553e 100644 --- a/Objects/listobject.c +++ b/Objects/listobject.c @@ -2729,7 +2729,8 @@ list_subscript(PyListObject* self, PyObject* item) return list_item(self, i); } else if (PySlice_Check(item)) { - Py_ssize_t start, stop, step, slicelength, cur, i; + Py_ssize_t start, stop, step, slicelength, i; + size_t cur; PyObject* result; PyObject* it; PyObject **src, **dest; @@ -2865,7 +2866,8 @@ list_ass_subscript(PyListObject* self, PyObject* item, PyObject* value) /* assign slice */ PyObject *ins, *seq; PyObject **garbage, **seqitems, **selfitems; - Py_ssize_t cur, i; + Py_ssize_t i; + size_t cur; /* protect against a[::-1] = a */ if (self == (PyListObject*)value) { diff --git a/Objects/longobject.c b/Objects/longobject.c index 7628a114..202f652f 100644 --- a/Objects/longobject.c +++ b/Objects/longobject.c @@ -5424,7 +5424,7 @@ static PyTypeObject Int_InfoType; PyDoc_STRVAR(int_info__doc__, "sys.int_info\n\ \n\ -A struct sequence that holds information about Python's\n\ +A named tuple that holds information about Python's\n\ internal representation of integers. The attributes are read only."); static PyStructSequence_Field int_info_fields[] = { diff --git a/Objects/obmalloc.c b/Objects/obmalloc.c index 885ad537..1248a393 100644 --- a/Objects/obmalloc.c +++ b/Objects/obmalloc.c @@ -44,9 +44,9 @@ static void _PyMem_SetupDebugHooksDomain(PyMemAllocatorDomain domain); # define _Py_NO_ADDRESS_SAFETY_ANALYSIS \ __attribute__((no_address_safety_analysis)) # endif - // TSAN is supported since GCC 4.8, but __SANITIZE_THREAD__ macro + // TSAN is supported since GCC 5.1, but __SANITIZE_THREAD__ macro // is provided only since GCC 7. -# if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8) +# if __GNUC__ > 5 || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1) # define _Py_NO_SANITIZE_THREAD __attribute__((no_sanitize_thread)) # endif #endif @@ -1377,13 +1377,13 @@ address_in_range(void *p, poolp pool) block allocations typically result in a couple of instructions). Unless the optimizer reorders everything, being too smart... - Return 1 if pymalloc allocated memory and wrote the pointer into *ptr_p. + Return a pointer to newly allocated memory if pymalloc allocated memory. - Return 0 if pymalloc failed to allocate the memory block: on bigger + Return NULL if pymalloc failed to allocate the memory block: on bigger requests, on error in the code below (as a last chance to serve the request) or when the max memory limit has been reached. */ -static int -pymalloc_alloc(void *ctx, void **ptr_p, size_t nbytes) +static void* +pymalloc_alloc(void *ctx, size_t nbytes) { block *bp; poolp pool; @@ -1395,15 +1395,15 @@ pymalloc_alloc(void *ctx, void **ptr_p, size_t nbytes) running_on_valgrind = RUNNING_ON_VALGRIND; } if (UNLIKELY(running_on_valgrind)) { - return 0; + return NULL; } #endif if (nbytes == 0) { - return 0; + return NULL; } if (nbytes > SMALL_REQUEST_THRESHOLD) { - return 0; + return NULL; } LOCK(); @@ -1564,20 +1564,19 @@ pymalloc_alloc(void *ctx, void **ptr_p, size_t nbytes) success: UNLOCK(); assert(bp != NULL); - *ptr_p = (void *)bp; - return 1; + return (void *)bp; failed: UNLOCK(); - return 0; + return NULL; } static void * _PyObject_Malloc(void *ctx, size_t nbytes) { - void* ptr; - if (pymalloc_alloc(ctx, &ptr, nbytes)) { + void* ptr = pymalloc_alloc(ctx, nbytes); + if (ptr != NULL) { _Py_AllocatedBlocks++; return ptr; } @@ -1593,12 +1592,11 @@ _PyObject_Malloc(void *ctx, size_t nbytes) static void * _PyObject_Calloc(void *ctx, size_t nelem, size_t elsize) { - void* ptr; - assert(elsize == 0 || nelem <= (size_t)PY_SSIZE_T_MAX / elsize); size_t nbytes = nelem * elsize; - if (pymalloc_alloc(ctx, &ptr, nbytes)) { + void *ptr = pymalloc_alloc(ctx, nbytes); + if (ptr != NULL) { memset(ptr, 0, nbytes); _Py_AllocatedBlocks++; return ptr; diff --git a/Objects/structseq.c b/Objects/structseq.c index e48165dc..c71898fd 100644 --- a/Objects/structseq.c +++ b/Objects/structseq.c @@ -1,5 +1,11 @@ -/* Implementation helper: a struct that looks like a tuple. See timemodule - and posixmodule for example uses. */ +/* Implementation helper: a struct that looks like a tuple. + See timemodule and posixmodule for example uses. + + The structseq helper is considered an internal CPython implementation + detail. Docs for modules using structseqs should call them + "named tuples" (be sure to include a space between the two + words and add a link back to the term in Docs/glossary.rst). +*/ #include "Python.h" #include "structmember.h" diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index c0e9c2d1..9e0731bf 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -7085,6 +7085,12 @@ PyUnicode_AsASCIIString(PyObject *unicode) #define NEED_RETRY #endif +/* INT_MAX is the theoretical largest chunk (or INT_MAX / 2 when + transcoding from UTF-16), but INT_MAX / 4 perfoms better in + both cases also and avoids partial characters overrunning the + length limit in MultiByteToWideChar on Windows */ +#define DECODING_CHUNK_SIZE (INT_MAX/4) + #ifndef WC_ERR_INVALID_CHARS # define WC_ERR_INVALID_CHARS 0x0080 #endif @@ -7345,8 +7351,8 @@ decode_code_page_stateful(int code_page, do { #ifdef NEED_RETRY - if (size > INT_MAX) { - chunk_size = INT_MAX; + if (size > DECODING_CHUNK_SIZE) { + chunk_size = DECODING_CHUNK_SIZE; final = 0; done = 0; } @@ -7748,10 +7754,8 @@ encode_code_page(int code_page, do { #ifdef NEED_RETRY - /* UTF-16 encoding may double the size, so use only INT_MAX/2 - chunks. */ - if (len > INT_MAX/2) { - chunk_len = INT_MAX/2; + if (len > DECODING_CHUNK_SIZE) { + chunk_len = DECODING_CHUNK_SIZE; done = 0; } else diff --git a/PC/bdist_wininst/install.c b/PC/bdist_wininst/install.c index 04323ebd..7a0e2e8c 100644 --- a/PC/bdist_wininst/install.c +++ b/PC/bdist_wininst/install.c @@ -939,7 +939,8 @@ static BOOL SystemError(int error, char *msg) LPVOID lpMsgBuf; FormatMessage( FORMAT_MESSAGE_ALLOCATE_BUFFER | - FORMAT_MESSAGE_FROM_SYSTEM, + FORMAT_MESSAGE_FROM_SYSTEM | + FORMAT_MESSAGE_IGNORE_INSERTS, NULL, error, MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT), diff --git a/PC/clinic/winreg.c.h b/PC/clinic/winreg.c.h index 6a5f6138..e9df3675 100644 --- a/PC/clinic/winreg.c.h +++ b/PC/clinic/winreg.c.h @@ -1003,7 +1003,7 @@ PyDoc_STRVAR(winreg_DisableReflectionKey__doc__, " key\n" " An already open key, or any one of the predefined HKEY_* constants.\n" "\n" -"Will generally raise NotImplemented if executed on a 32bit OS.\n" +"Will generally raise NotImplementedError if executed on a 32bit OS.\n" "\n" "If the key is not on the reflection list, the function succeeds but has\n" "no effect. Disabling reflection for a key does not affect reflection\n" @@ -1039,7 +1039,7 @@ PyDoc_STRVAR(winreg_EnableReflectionKey__doc__, " key\n" " An already open key, or any one of the predefined HKEY_* constants.\n" "\n" -"Will generally raise NotImplemented if executed on a 32bit OS.\n" +"Will generally raise NotImplementedError if executed on a 32bit OS.\n" "Restoring reflection for a key does not affect reflection of any\n" "subkeys."); @@ -1073,7 +1073,7 @@ PyDoc_STRVAR(winreg_QueryReflectionKey__doc__, " key\n" " An already open key, or any one of the predefined HKEY_* constants.\n" "\n" -"Will generally raise NotImplemented if executed on a 32bit OS."); +"Will generally raise NotImplementedError if executed on a 32bit OS."); #define WINREG_QUERYREFLECTIONKEY_METHODDEF \ {"QueryReflectionKey", (PyCFunction)winreg_QueryReflectionKey, METH_O, winreg_QueryReflectionKey__doc__}, @@ -1095,4 +1095,4 @@ winreg_QueryReflectionKey(PyObject *module, PyObject *arg) exit: return return_value; } -/*[clinic end generated code: output=60c92ffc7438f8cf input=a9049054013a1b77]*/ +/*[clinic end generated code: output=696f627d310ac599 input=a9049054013a1b77]*/ diff --git a/PC/errmap.h b/PC/errmap.h index 985f673a..a7489ab7 100644 --- a/PC/errmap.h +++ b/PC/errmap.h @@ -1,80 +1,140 @@ -/* Generated file. Do not edit. */ -int winerror_to_errno(int winerror) +int +winerror_to_errno(int winerror) { - switch(winerror) { - case 2: return 2; - case 3: return 2; - case 4: return 24; - case 5: return 13; - case 6: return 9; - case 7: return 12; - case 8: return 12; - case 9: return 12; - case 10: return 7; - case 11: return 8; - case 15: return 2; - case 16: return 13; - case 17: return 18; - case 18: return 2; - case 19: return 13; - case 20: return 13; - case 21: return 13; - case 22: return 13; - case 23: return 13; - case 24: return 13; - case 25: return 13; - case 26: return 13; - case 27: return 13; - case 28: return 13; - case 29: return 13; - case 30: return 13; - case 31: return 13; - case 32: return 13; - case 33: return 13; - case 34: return 13; - case 35: return 13; - case 36: return 13; - case 53: return 2; - case 65: return 13; - case 67: return 2; - case 80: return 17; - case 82: return 13; - case 83: return 13; - case 89: return 11; - case 108: return 13; - case 109: return 32; - case 112: return 28; - case 114: return 9; - case 128: return 10; - case 129: return 10; - case 130: return 9; - case 132: return 13; - case 145: return 41; - case 158: return 13; - case 161: return 2; - case 164: return 11; - case 167: return 13; - case 183: return 17; - case 188: return 8; - case 189: return 8; - case 190: return 8; - case 191: return 8; - case 192: return 8; - case 193: return 8; - case 194: return 8; - case 195: return 8; - case 196: return 8; - case 197: return 8; - case 198: return 8; - case 199: return 8; - case 200: return 8; - case 201: return 8; - case 202: return 8; - case 206: return 2; - case 215: return 11; - case 232: return 32; - case 267: return 20; - case 1816: return 12; - default: return EINVAL; + // Unwrap FACILITY_WIN32 HRESULT errors. + if ((winerror & 0xFFFF0000) == 0x80070000) { + winerror &= 0x0000FFFF; + } + + // Winsock error codes (10000-11999) are errno values. + if (winerror >= 10000 && winerror < 12000) { + switch (winerror) { + case WSAEINTR: + case WSAEBADF: + case WSAEACCES: + case WSAEFAULT: + case WSAEINVAL: + case WSAEMFILE: + // Winsock definitions of errno values. See WinSock2.h + return winerror - 10000; + default: + return winerror; + } + } + + switch (winerror) { + case ERROR_FILE_NOT_FOUND: // 2 + case ERROR_PATH_NOT_FOUND: // 3 + case ERROR_INVALID_DRIVE: // 15 + case ERROR_NO_MORE_FILES: // 18 + case ERROR_BAD_NETPATH: // 53 + case ERROR_BAD_NET_NAME: // 67 + case ERROR_BAD_PATHNAME: // 161 + case ERROR_FILENAME_EXCED_RANGE: // 206 + return ENOENT; + + case ERROR_BAD_ENVIRONMENT: // 10 + return E2BIG; + + case ERROR_BAD_FORMAT: // 11 + case ERROR_INVALID_STARTING_CODESEG: // 188 + case ERROR_INVALID_STACKSEG: // 189 + case ERROR_INVALID_MODULETYPE: // 190 + case ERROR_INVALID_EXE_SIGNATURE: // 191 + case ERROR_EXE_MARKED_INVALID: // 192 + case ERROR_BAD_EXE_FORMAT: // 193 + case ERROR_ITERATED_DATA_EXCEEDS_64k: // 194 + case ERROR_INVALID_MINALLOCSIZE: // 195 + case ERROR_DYNLINK_FROM_INVALID_RING: // 196 + case ERROR_IOPL_NOT_ENABLED: // 197 + case ERROR_INVALID_SEGDPL: // 198 + case ERROR_AUTODATASEG_EXCEEDS_64k: // 199 + case ERROR_RING2SEG_MUST_BE_MOVABLE: // 200 + case ERROR_RELOC_CHAIN_XEEDS_SEGLIM: // 201 + case ERROR_INFLOOP_IN_RELOC_CHAIN: // 202 + return ENOEXEC; + + case ERROR_INVALID_HANDLE: // 6 + case ERROR_INVALID_TARGET_HANDLE: // 114 + case ERROR_DIRECT_ACCESS_HANDLE: // 130 + return EBADF; + + case ERROR_WAIT_NO_CHILDREN: // 128 + case ERROR_CHILD_NOT_COMPLETE: // 129 + return ECHILD; + + case ERROR_NO_PROC_SLOTS: // 89 + case ERROR_MAX_THRDS_REACHED: // 164 + case ERROR_NESTING_NOT_ALLOWED: // 215 + return EAGAIN; + + case ERROR_ARENA_TRASHED: // 7 + case ERROR_NOT_ENOUGH_MEMORY: // 8 + case ERROR_INVALID_BLOCK: // 9 + case ERROR_NOT_ENOUGH_QUOTA: // 1816 + return ENOMEM; + + case ERROR_ACCESS_DENIED: // 5 + case ERROR_CURRENT_DIRECTORY: // 16 + case ERROR_WRITE_PROTECT: // 19 + case ERROR_BAD_UNIT: // 20 + case ERROR_NOT_READY: // 21 + case ERROR_BAD_COMMAND: // 22 + case ERROR_CRC: // 23 + case ERROR_BAD_LENGTH: // 24 + case ERROR_SEEK: // 25 + case ERROR_NOT_DOS_DISK: // 26 + case ERROR_SECTOR_NOT_FOUND: // 27 + case ERROR_OUT_OF_PAPER: // 28 + case ERROR_WRITE_FAULT: // 29 + case ERROR_READ_FAULT: // 30 + case ERROR_GEN_FAILURE: // 31 + case ERROR_SHARING_VIOLATION: // 32 + case ERROR_LOCK_VIOLATION: // 33 + case ERROR_WRONG_DISK: // 34 + case ERROR_SHARING_BUFFER_EXCEEDED: // 36 + case ERROR_NETWORK_ACCESS_DENIED: // 65 + case ERROR_CANNOT_MAKE: // 82 + case ERROR_FAIL_I24: // 83 + case ERROR_DRIVE_LOCKED: // 108 + case ERROR_SEEK_ON_DEVICE: // 132 + case ERROR_NOT_LOCKED: // 158 + case ERROR_LOCK_FAILED: // 167 + case 35: // 35 (undefined) + return EACCES; + + case ERROR_FILE_EXISTS: // 80 + case ERROR_ALREADY_EXISTS: // 183 + return EEXIST; + + case ERROR_NOT_SAME_DEVICE: // 17 + return EXDEV; + + case ERROR_DIRECTORY: // 267 (bpo-12802) + return ENOTDIR; + + case ERROR_TOO_MANY_OPEN_FILES: // 4 + return EMFILE; + + case ERROR_DISK_FULL: // 112 + return ENOSPC; + + case ERROR_BROKEN_PIPE: // 109 + case ERROR_NO_DATA: // 232 (bpo-13063) + return EPIPE; + + case ERROR_DIR_NOT_EMPTY: // 145 + return ENOTEMPTY; + + case ERROR_NO_UNICODE_TRANSLATION: // 1113 + return EILSEQ; + + case ERROR_INVALID_FUNCTION: // 1 + case ERROR_INVALID_ACCESS: // 12 + case ERROR_INVALID_DATA: // 13 + case ERROR_INVALID_PARAMETER: // 87 + case ERROR_NEGATIVE_SEEK: // 131 + default: + return EINVAL; } } diff --git a/PC/generrmap.c b/PC/generrmap.c deleted file mode 100644 index 953344c0..00000000 --- a/PC/generrmap.c +++ /dev/null @@ -1,32 +0,0 @@ -#include -#include -#include -#include -#include - -/* Extract the mapping of Win32 error codes to errno */ - -int main() -{ - int i; - _setmode(fileno(stdout), O_BINARY); - printf("/* Generated file. Do not edit. */\n"); - printf("int winerror_to_errno(int winerror)\n"); - printf("{\n switch(winerror) {\n"); - for(i=1; i < 65000; i++) { - _dosmaperr(i); - if (errno == EINVAL) { - /* Issue #12802 */ - if (i == ERROR_DIRECTORY) - errno = ENOTDIR; - /* Issue #13063 */ - else if (i == ERROR_NO_DATA) - errno = EPIPE; - else - continue; - } - printf(" case %d: return %d;\n", i, errno); - } - printf(" default: return EINVAL;\n"); - printf(" }\n}\n"); -} diff --git a/PC/pyconfig.h b/PC/pyconfig.h index 46fc84e9..6e33f12e 100644 --- a/PC/pyconfig.h +++ b/PC/pyconfig.h @@ -292,7 +292,7 @@ Py_NO_ENABLE_SHARED to find out. Also support MS_NO_COREDLL for b/w compat */ # define SIZEOF_FPOS_T 8 # define SIZEOF_HKEY 8 # define SIZEOF_SIZE_T 8 -/* configure.ac defines HAVE_LARGEFILE_SUPPORT iff HAVE_LONG_LONG, +/* configure.ac defines HAVE_LARGEFILE_SUPPORT iff sizeof(off_t) > sizeof(long), and sizeof(PY_LONG_LONG) >= sizeof(off_t). On Win64 the second condition is not true, but if fpos_t replaces off_t then this is true. The uses of HAVE_LARGEFILE_SUPPORT imply that Win64 diff --git a/PC/winreg.c b/PC/winreg.c index 1021609e..16a10c72 100644 --- a/PC/winreg.c +++ b/PC/winreg.c @@ -517,11 +517,18 @@ fixupMultiSZ(wchar_t **str, wchar_t *data, int len) int i; wchar_t *Q; - Q = data + len; - for (P = data, i = 0; P < Q && *P != '\0'; P++, i++) { + if (len > 0 && data[len - 1] == '\0') { + Q = data + len - 1; + } + else { + Q = data + len; + } + + for (P = data, i = 0; P < Q; P++, i++) { str[i] = P; - for (; P < Q && *P != '\0'; P++) + for (; P < Q && *P != '\0'; P++) { ; + } } } @@ -529,12 +536,20 @@ static int countStrings(wchar_t *data, int len) { int strings; - wchar_t *P; - wchar_t *Q = data + len; + wchar_t *P, *Q; + + if (len > 0 && data[len - 1] == '\0') { + Q = data + len - 1; + } + else { + Q = data + len; + } - for (P = data, strings = 0; P < Q && *P != '\0'; P++, strings++) - for (; P < Q && *P != '\0'; P++) + for (P = data, strings = 0; P < Q; P++, strings++) { + for (; P < Q && *P != '\0'; P++) { ; + } + } return strings; } @@ -749,21 +764,15 @@ Reg2Py(BYTE *retDataBuf, DWORD retDataSize, DWORD typ) } for (index = 0; index < s; index++) { - size_t len = wcslen(str[index]); - if (len > INT_MAX) { - PyErr_SetString(PyExc_OverflowError, - "registry string is too long for a Python string"); - Py_DECREF(obData); - PyMem_Free(str); - return NULL; - } - PyObject *uni = PyUnicode_FromWideChar(str[index], len); + size_t slen = wcsnlen(str[index], len); + PyObject *uni = PyUnicode_FromWideChar(str[index], slen); if (uni == NULL) { Py_DECREF(obData); PyMem_Free(str); return NULL; } PyList_SET_ITEM(obData, index, uni); + len -= Py_SAFE_DOWNCAST(slen + 1, size_t, int); } PyMem_Free(str); @@ -1697,7 +1706,7 @@ winreg.DisableReflectionKey Disables registry reflection for 32bit processes running on a 64bit OS. -Will generally raise NotImplemented if executed on a 32bit OS. +Will generally raise NotImplementedError if executed on a 32bit OS. If the key is not on the reflection list, the function succeeds but has no effect. Disabling reflection for a key does not affect reflection @@ -1706,7 +1715,7 @@ of any subkeys. static PyObject * winreg_DisableReflectionKey_impl(PyObject *module, HKEY key) -/*[clinic end generated code: output=830cce504cc764b4 input=a6c9e5ca5410193c]*/ +/*[clinic end generated code: output=830cce504cc764b4 input=70bece2dee02e073]*/ { HMODULE hMod; typedef LONG (WINAPI *RDRKFunc)(HKEY); @@ -1742,14 +1751,14 @@ winreg.EnableReflectionKey Restores registry reflection for the specified disabled key. -Will generally raise NotImplemented if executed on a 32bit OS. +Will generally raise NotImplementedError if executed on a 32bit OS. Restoring reflection for a key does not affect reflection of any subkeys. [clinic start generated code]*/ static PyObject * winreg_EnableReflectionKey_impl(PyObject *module, HKEY key) -/*[clinic end generated code: output=86fa1385fdd9ce57 input=7748abbacd1e166a]*/ +/*[clinic end generated code: output=86fa1385fdd9ce57 input=eeae770c6eb9f559]*/ { HMODULE hMod; typedef LONG (WINAPI *RERKFunc)(HKEY); @@ -1785,12 +1794,12 @@ winreg.QueryReflectionKey Returns the reflection state for the specified key as a bool. -Will generally raise NotImplemented if executed on a 32bit OS. +Will generally raise NotImplementedError if executed on a 32bit OS. [clinic start generated code]*/ static PyObject * winreg_QueryReflectionKey_impl(PyObject *module, HKEY key) -/*[clinic end generated code: output=4e774af288c3ebb9 input=9f325eacb5a65d88]*/ +/*[clinic end generated code: output=4e774af288c3ebb9 input=a98fa51d55ade186]*/ { HMODULE hMod; typedef LONG (WINAPI *RQRKFunc)(HKEY, BOOL *); diff --git a/PCbuild/_elementtree.vcxproj b/PCbuild/_elementtree.vcxproj index 310458d5..4e054d85 100644 --- a/PCbuild/_elementtree.vcxproj +++ b/PCbuild/_elementtree.vcxproj @@ -84,7 +84,6 @@ - diff --git a/PCbuild/_elementtree.vcxproj.filters b/PCbuild/_elementtree.vcxproj.filters index 14fa4175..48cb2492 100644 --- a/PCbuild/_elementtree.vcxproj.filters +++ b/PCbuild/_elementtree.vcxproj.filters @@ -33,9 +33,6 @@ Header Files - - Header Files - Header Files diff --git a/PCbuild/get_externals.bat b/PCbuild/get_externals.bat index 4b4ccf1b..0414bc22 100644 --- a/PCbuild/get_externals.bat +++ b/PCbuild/get_externals.bat @@ -49,7 +49,7 @@ echo.Fetching external libraries... set libraries= set libraries=%libraries% bzip2-1.0.6 -if NOT "%IncludeSSLSrc%"=="false" set libraries=%libraries% openssl-1.1.1c +if NOT "%IncludeSSLSrc%"=="false" set libraries=%libraries% openssl-1.1.1d set libraries=%libraries% sqlite-3.28.0.0 if NOT "%IncludeTkinterSrc%"=="false" set libraries=%libraries% tcl-core-8.6.9.0 if NOT "%IncludeTkinterSrc%"=="false" set libraries=%libraries% tk-8.6.9.0 @@ -72,7 +72,7 @@ for %%e in (%libraries%) do ( echo.Fetching external binaries... set binaries= -if NOT "%IncludeSSL%"=="false" set binaries=%binaries% openssl-bin-1.1.1c +if NOT "%IncludeSSL%"=="false" set binaries=%binaries% openssl-bin-1.1.1d if NOT "%IncludeTkinter%"=="false" set binaries=%binaries% tcltk-8.6.9.0 if NOT "%IncludeSSLSrc%"=="false" set binaries=%binaries% nasm-2.11.06 diff --git a/PCbuild/pyexpat.vcxproj b/PCbuild/pyexpat.vcxproj index cd3f6d17..d49f61d8 100644 --- a/PCbuild/pyexpat.vcxproj +++ b/PCbuild/pyexpat.vcxproj @@ -68,7 +68,6 @@ - diff --git a/PCbuild/pyexpat.vcxproj.filters b/PCbuild/pyexpat.vcxproj.filters index 2d415219..d48df6ec 100644 --- a/PCbuild/pyexpat.vcxproj.filters +++ b/PCbuild/pyexpat.vcxproj.filters @@ -20,9 +20,6 @@ Source Files - - Source Files - Source Files diff --git a/PCbuild/python.props b/PCbuild/python.props index 617f4029..bf9a438b 100644 --- a/PCbuild/python.props +++ b/PCbuild/python.props @@ -49,8 +49,8 @@ $(ExternalsDir)sqlite-3.28.0.0\ $(ExternalsDir)bzip2-1.0.6\ $(ExternalsDir)xz-5.2.2\ - $(ExternalsDir)openssl-1.1.1c\ - $(ExternalsDir)openssl-bin-1.1.1c\$(ArchName)\ + $(ExternalsDir)openssl-1.1.1d\ + $(ExternalsDir)openssl-bin-1.1.1d\$(ArchName)\ $(opensslOutDir)include $(ExternalsDir)\nasm-2.11.06\ $(ExternalsDir)\zlib-1.2.11\ diff --git a/PCbuild/python_uwp.vcxproj b/PCbuild/python_uwp.vcxproj index 7b3842a7..fb4e78a6 100644 --- a/PCbuild/python_uwp.vcxproj +++ b/PCbuild/python_uwp.vcxproj @@ -65,6 +65,15 @@ Console + + + Multithreaded + + + ucrt.lib;%(AdditionalDependencies) + libucrt;%(IgnoreSpecificDefaultLibraries) + + diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c index e374c5a4..d720f19e 100644 --- a/Parser/tokenizer.c +++ b/Parser/tokenizer.c @@ -1890,7 +1890,7 @@ PyTokenizer_FindEncodingFilename(int fd, PyObject *filename) if (tok->encoding) { encoding = (char *)PyMem_MALLOC(strlen(tok->encoding) + 1); if (encoding) - strcpy(encoding, tok->encoding); + strcpy(encoding, tok->encoding); } PyTokenizer_Free(tok); return encoding; diff --git a/Python/_warnings.c b/Python/_warnings.c index 80dca65f..e86a582a 100644 --- a/Python/_warnings.c +++ b/Python/_warnings.c @@ -1213,7 +1213,7 @@ _PyErr_WarnUnawaitedCoroutine(PyObject *coro) } PyDoc_STRVAR(warn_explicit_doc, -"Low-level inferface to warnings functionality."); +"Low-level interface to warnings functionality."); static PyMethodDef warnings_functions[] = { WARNINGS_WARN_METHODDEF diff --git a/Python/bltinmodule.c b/Python/bltinmodule.c index 8083ac96..12def959 100644 --- a/Python/bltinmodule.c +++ b/Python/bltinmodule.c @@ -2675,7 +2675,7 @@ static PyMethodDef zip_methods[] = { }; PyDoc_STRVAR(zip_doc, -"zip(iter1 [,iter2 [...]]) --> zip object\n\ +"zip(*iterables) --> zip object\n\ \n\ Return a zip object whose .__next__() method returns a tuple where\n\ the i-th element comes from the i-th iterable argument. The .__next__()\n\ diff --git a/Python/compile.c b/Python/compile.c index 5688ef84..32884be3 100644 --- a/Python/compile.c +++ b/Python/compile.c @@ -1482,7 +1482,7 @@ compiler_body(struct compiler *c, asdl_seq *stmts) /* Set current line number to the line number of first statement. This way line number for SETUP_ANNOTATIONS will always coincide with the line number of first "real" statement in module. - If body is empy, then lineno will be set later in assemble. */ + If body is empty, then lineno will be set later in assemble. */ if (c->u->u_scope_type == COMPILER_SCOPE_MODULE && !c->u->u_lineno && asdl_seq_LEN(stmts)) { st = (stmt_ty)asdl_seq_GET(stmts, 0); diff --git a/Python/condvar.h b/Python/condvar.h index 951b8ad4..802d53fb 100644 --- a/Python/condvar.h +++ b/Python/condvar.h @@ -194,7 +194,7 @@ _PyCOND_WAIT_MS(PyCOND_T *cv, PyMUTEX_T *cs, DWORD ms) * just means an extra spurious wakeup for a waiting thread. * ('waiting' corresponds to the semaphore's "negative" count and * we may end up with e.g. (waiting == -1 && sem.count == 1). When - * a new thread comes along, it will pass right throuhgh, having + * a new thread comes along, it will pass right through, having * adjusted it to (waiting == 0 && sem.count == 0). */ diff --git a/Python/fileutils.c b/Python/fileutils.c index 868fbf91..b2c634db 100644 --- a/Python/fileutils.c +++ b/Python/fileutils.c @@ -1037,11 +1037,18 @@ set_inheritable(int fd, int inheritable, int raise, int *atomic_flag_works) flags = HANDLE_FLAG_INHERIT; else flags = 0; - if (!SetHandleInformation(handle, HANDLE_FLAG_INHERIT, flags)) { + + /* This check can be removed once support for Windows 7 ends. */ +#define CONSOLE_PSEUDOHANDLE(handle) (((ULONG_PTR)(handle) & 0x3) == 0x3 && \ + GetFileType(handle) == FILE_TYPE_CHAR) + + if (!CONSOLE_PSEUDOHANDLE(handle) && + !SetHandleInformation(handle, HANDLE_FLAG_INHERIT, flags)) { if (raise) PyErr_SetFromWindowsErr(0); return -1; } +#undef CONSOLE_PSEUDOHANDLE return 0; #else diff --git a/Python/import.c b/Python/import.c index 63c99ea5..edc59249 100644 --- a/Python/import.c +++ b/Python/import.c @@ -1563,22 +1563,20 @@ resolve_name(PyObject *name, PyObject *globals, int level) if (dot == -2) { goto error; } - - if (dot >= 0) { - PyObject *substr = PyUnicode_Substring(package, 0, dot); - if (substr == NULL) { - goto error; - } - Py_SETREF(package, substr); + else if (dot == -1) { + goto no_parent_error; } + PyObject *substr = PyUnicode_Substring(package, 0, dot); + if (substr == NULL) { + goto error; + } + Py_SETREF(package, substr); } } last_dot = PyUnicode_GET_LENGTH(package); if (last_dot == 0) { - PyErr_SetString(PyExc_ImportError, - "attempted relative import with no known parent package"); - goto error; + goto no_parent_error; } for (level_up = 1; level_up < level; level_up += 1) { @@ -1604,6 +1602,11 @@ resolve_name(PyObject *name, PyObject *globals, int level) Py_DECREF(base); return abs_name; + no_parent_error: + PyErr_SetString(PyExc_ImportError, + "attempted relative import " + "with no known parent package"); + error: Py_XDECREF(package); return NULL; diff --git a/Python/pystate.c b/Python/pystate.c index fc695c62..90cd56bb 100644 --- a/Python/pystate.c +++ b/Python/pystate.c @@ -484,7 +484,7 @@ _PyState_AddModule(PyObject* module, struct PyModuleDef* def) if (!state->modules_by_index) return -1; } - while(PyList_GET_SIZE(state->modules_by_index) <= def->m_base.m_index) + while (PyList_GET_SIZE(state->modules_by_index) <= def->m_base.m_index) if (PyList_Append(state->modules_by_index, Py_None) < 0) return -1; Py_INCREF(module); @@ -502,13 +502,11 @@ PyState_AddModule(PyObject* module, struct PyModuleDef* def) return -1; } index = def->m_base.m_index; - if (state->modules_by_index) { - if(PyList_GET_SIZE(state->modules_by_index) >= index) { - if(module == PyList_GET_ITEM(state->modules_by_index, index)) { - Py_FatalError("PyState_AddModule: Module already added!"); - return -1; - } - } + if (state->modules_by_index && + index < PyList_GET_SIZE(state->modules_by_index) && + module == PyList_GET_ITEM(state->modules_by_index, index)) { + Py_FatalError("PyState_AddModule: Module already added!"); + return -1; } return _PyState_AddModule(module, def); } diff --git a/Python/pythonrun.c b/Python/pythonrun.c index c4ec5ac6..4c974cef 100644 --- a/Python/pythonrun.c +++ b/Python/pythonrun.c @@ -750,7 +750,7 @@ print_exception(PyObject *f, PyObject *value) Py_DECREF(value); value = message; - line = PyUnicode_FromFormat(" File \"%U\", line %d\n", + line = PyUnicode_FromFormat(" File \"%S\", line %d\n", filename, lineno); Py_DECREF(filename); if (line != NULL) { diff --git a/Python/sysmodule.c b/Python/sysmodule.c index 942a8b6b..b953a000 100644 --- a/Python/sysmodule.c +++ b/Python/sysmodule.c @@ -836,7 +836,7 @@ static PyTypeObject AsyncGenHooksType; PyDoc_STRVAR(asyncgen_hooks_doc, "asyncgen_hooks\n\ \n\ -A struct sequence providing information about asynhronous\n\ +A named tuple providing information about asynchronous\n\ generators hooks. The attributes are read only."); static PyStructSequence_Field asyncgen_hooks_fields[] = { @@ -943,7 +943,7 @@ static PyTypeObject Hash_InfoType; PyDoc_STRVAR(hash_info_doc, "hash_info\n\ \n\ -A struct sequence providing parameters used for computing\n\ +A named tuple providing parameters used for computing\n\ hashes. The attributes are read only."); static PyStructSequence_Field hash_info_fields[] = { @@ -1967,17 +1967,17 @@ builtin_module_names -- tuple of module names built into this interpreter\n\ copyright -- copyright notice pertaining to this interpreter\n\ exec_prefix -- prefix used to find the machine-specific Python library\n\ executable -- absolute path of the executable binary of the Python interpreter\n\ -float_info -- a struct sequence with information about the float implementation.\n\ +float_info -- a named tuple with information about the float implementation.\n\ float_repr_style -- string indicating the style of repr() output for floats\n\ -hash_info -- a struct sequence with information about the hash algorithm.\n\ +hash_info -- a named tuple with information about the hash algorithm.\n\ hexversion -- version information encoded as a single integer\n\ implementation -- Python implementation information.\n\ -int_info -- a struct sequence with information about the int implementation.\n\ +int_info -- a named tuple with information about the int implementation.\n\ maxsize -- the largest supported length of containers.\n\ maxunicode -- the value of the largest Unicode code point\n\ platform -- platform identifier\n\ prefix -- prefix used to find the Python library\n\ -thread_info -- a struct sequence with information about the thread implementation.\n\ +thread_info -- a named tuple with information about the thread implementation.\n\ version -- the version of this interpreter as a string\n\ version_info -- version information as a named tuple\n\ " diff --git a/Python/thread.c b/Python/thread.c index 07743840..e0cbdeef 100644 --- a/Python/thread.c +++ b/Python/thread.c @@ -147,7 +147,7 @@ PyThread_tss_is_created(Py_tss_t *key) PyDoc_STRVAR(threadinfo__doc__, "sys.thread_info\n\ \n\ -A struct sequence holding information about the thread implementation."); +A named tuple holding information about the thread implementation."); static PyStructSequence_Field threadinfo_fields[] = { {"name", "name of the thread implementation"}, diff --git a/README.rst b/README.rst index b891925f..795b821d 100644 --- a/README.rst +++ b/README.rst @@ -1,21 +1,17 @@ -This is Python version 3.7.4 +This is Python version 3.7.5 ============================ -.. image:: https://travis-ci.org/python/cpython.svg?branch=master +.. image:: https://travis-ci.org/python/cpython.svg?branch=3.7 :alt: CPython build status on Travis CI - :target: https://travis-ci.org/python/cpython - -.. image:: https://ci.appveyor.com/api/projects/status/4mew1a93xdkbf5ua/branch/master?svg=true - :alt: CPython build status on Appveyor - :target: https://ci.appveyor.com/project/python/cpython/branch/master + :target: https://travis-ci.org/python/cpython/branches .. image:: https://dev.azure.com/python/cpython/_apis/build/status/Azure%20Pipelines%20CI?branchName=3.7 :alt: CPython build status on Azure Pipelines :target: https://dev.azure.com/python/cpython/_build/latest?definitionId=4&branchName=3.7 -.. image:: https://codecov.io/gh/python/cpython/branch/master/graph/badge.svg +.. image:: https://codecov.io/gh/python/cpython/branch/3.7/graph/badge.svg :alt: CPython code coverage on Codecov - :target: https://codecov.io/gh/python/cpython + :target: https://codecov.io/gh/python/cpython/branch/3.7 Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019 Python Software Foundation. All @@ -63,21 +59,23 @@ On Unix, Linux, BSD, macOS, and Cygwin:: This will install Python as ``python3``. You can pass many options to the configure script; run ``./configure --help`` -to find out more. On macOS and Cygwin, the executable is called ``python.exe``; -elsewhere it's just ``python``. +to find out more. On macOS case-insensitive file systems and on Cygwin, +the executable is called ``python.exe``; elsewhere it's just ``python``. -If you are running on macOS with the latest updates installed, make sure to install -openSSL or some other SSL software along with Homebrew or another package manager. -If issues persist, see https://devguide.python.org/setup/#macos-and-os-x for more -information. +Building a complete Python installation requires the use of various +additional third-party libraries, depending on your build platform and +configure options. Not all standard library modules are buildable or +useable on all platforms. Refer to the +`Install dependencies `_ +section of the `Developer Guide`_ for current detailed information on +dependencies for various Linux distributions and macOS. -On macOS, if you have configured Python with ``--enable-framework``, you -should use ``make frameworkinstall`` to do the installation. Note that this -installs the Python executable in a place that is not normally on your PATH, -you may want to set up a symlink in ``/usr/local/bin``. +On macOS, there are additional configure and build options related +to macOS framework and universal builds. Refer to `Mac/README.rst +`_. On Windows, see `PCbuild/readme.txt -`_. +`_. If you wish, you can create a subdirectory and invoke configure from there. For example:: @@ -139,9 +137,9 @@ What's New We have a comprehensive overview of the changes in the `What's New in Python 3.7 `_ document. For a more detailed change log, read `Misc/NEWS -`_, but a full +`_, but a full accounting of changes can only be gleaned from the `commit history -`_. +`_. If you want to install multiple versions of Python see the section below entitled "Installing multiple versions". @@ -159,7 +157,7 @@ is primarily for documentation authors, translators, and people with special formatting requirements. For information about building Python's documentation, refer to `Doc/README.rst -`_. +`_. Converting From Python 2.x to 3.x diff --git a/Tools/msi/bundle/bootstrap/PythonBootstrapperApplication.cpp b/Tools/msi/bundle/bootstrap/PythonBootstrapperApplication.cpp index 2e468b7e..cd4a1f8f 100644 --- a/Tools/msi/bundle/bootstrap/PythonBootstrapperApplication.cpp +++ b/Tools/msi/bundle/bootstrap/PythonBootstrapperApplication.cpp @@ -727,9 +727,13 @@ public: // IBootstrapperApplication BalLog(BOOTSTRAPPER_LOG_LEVEL_ERROR, "Failed to load AssociateFiles state: error code 0x%08X", hr); } - _engine->SetVariableNumeric(L"Include_launcher", 1); + LONGLONG includeLauncher; + if (FAILED(BalGetNumericVariable(L"Include_launcher", &includeLauncher)) + || includeLauncher == -1) { + _engine->SetVariableNumeric(L"Include_launcher", 1); + _engine->SetVariableNumeric(L"InstallLauncherAllUsers", fPerMachine ? 1 : 0); + } _engine->SetVariableNumeric(L"DetectedOldLauncher", 1); - _engine->SetVariableNumeric(L"InstallLauncherAllUsers", fPerMachine ? 1 : 0); } return CheckCanceled() ? IDCANCEL : IDNOACTION; } @@ -796,6 +800,12 @@ public: // IBootstrapperApplication } } + LONGLONG includeLauncher; + if (SUCCEEDED(BalGetNumericVariable(L"Include_launcher", &includeLauncher)) + && includeLauncher != -1) { + detectedLauncher = FALSE; + } + if (detectedLauncher) { /* When we detect the current version of the launcher. */ _engine->SetVariableNumeric(L"Include_launcher", 1); @@ -819,6 +829,14 @@ public: // IBootstrapperApplication _baFunction->OnDetectComplete(); } + if (SUCCEEDED(hrStatus)) { + LONGLONG includeLauncher; + if (SUCCEEDED(BalGetNumericVariable(L"Include_launcher", &includeLauncher)) + && includeLauncher == -1) { + _engine->SetVariableNumeric(L"Include_launcher", 1); + } + } + if (SUCCEEDED(hrStatus)) { hrStatus = EvaluateConditions(); } @@ -1451,6 +1469,10 @@ private: hr = ParseOverridableVariablesFromXml(pixdManifest); BalExitOnFailure(hr, "Failed to read overridable variables."); + if (_command.action == BOOTSTRAPPER_ACTION_MODIFY) { + LoadOptionalFeatureStates(_engine); + } + hr = ParseVariablesFromUnattendXml(); ExitOnFailure(hr, "Failed to read unattend.ini file."); @@ -1478,10 +1500,6 @@ private: hr = UpdateUIStrings(_command.action); BalExitOnFailure(hr, "Failed to load UI strings."); - if (_command.action == BOOTSTRAPPER_ACTION_MODIFY) { - LoadOptionalFeatureStates(_engine); - } - GetBundleFileVersion(); // don't fail if we couldn't get the version info; best-effort only LExit: diff --git a/Tools/msi/bundle/bundle.wxs b/Tools/msi/bundle/bundle.wxs index f6cff6fc..ddd6870f 100644 --- a/Tools/msi/bundle/bundle.wxs +++ b/Tools/msi/bundle/bundle.wxs @@ -71,11 +71,10 @@ + - - diff --git a/Tools/ssl/multissltests.py b/Tools/ssl/multissltests.py index 07bd9b01..d816810d 100755 --- a/Tools/ssl/multissltests.py +++ b/Tools/ssl/multissltests.py @@ -45,16 +45,16 @@ OPENSSL_OLD_VERSIONS = [ ] OPENSSL_RECENT_VERSIONS = [ - "1.0.2s", - "1.1.0k", - "1.1.1c", + "1.0.2t", + "1.1.0l", + "1.1.1d", ] LIBRESSL_OLD_VERSIONS = [ ] LIBRESSL_RECENT_VERSIONS = [ - "2.7.4", + "2.9.2", ] # store files in ../multissl diff --git a/configure b/configure index 2db11e6e..0f466db4 100755 --- a/configure +++ b/configure @@ -680,10 +680,6 @@ LLVM_PROF_MERGER PGO_PROF_USE_FLAG PGO_PROF_GEN_FLAG LLVM_AR_FOUND -target_os -target_vendor -target_cpu -target LLVM_AR DEF_MAKE_RULE DEF_MAKE_ALL_RULE @@ -1459,7 +1455,6 @@ _ACEOF System types: --build=BUILD configure for building on BUILD [guessed] --host=HOST cross-compile to build programs to run on HOST [BUILD] - --target=TARGET configure for building compilers for TARGET [HOST] _ACEOF fi @@ -6486,47 +6481,9 @@ if test "$Py_LTO" = 'true' ; then case $CC in *clang*) - { $as_echo "$as_me:${as_lineno-$LINENO}: checking target system type" >&5 -$as_echo_n "checking target system type... " >&6; } -if ${ac_cv_target+:} false; then : - $as_echo_n "(cached) " >&6 -else - if test "x$target_alias" = x; then - ac_cv_target=$ac_cv_host -else - ac_cv_target=`$SHELL "$ac_aux_dir/config.sub" $target_alias` || - as_fn_error $? "$SHELL $ac_aux_dir/config.sub $target_alias failed" "$LINENO" 5 -fi - -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_target" >&5 -$as_echo "$ac_cv_target" >&6; } -case $ac_cv_target in -*-*-*) ;; -*) as_fn_error $? "invalid value of canonical target" "$LINENO" 5;; -esac -target=$ac_cv_target -ac_save_IFS=$IFS; IFS='-' -set x $ac_cv_target -shift -target_cpu=$1 -target_vendor=$2 -shift; shift -# Remember, the first character of IFS is used to create $*, -# except with old shells: -target_os=$* -IFS=$ac_save_IFS -case $target_os in *\ *) target_os=`echo "$target_os" | sed 's/ /-/g'`;; esac - - -# The aliases save the names the user supplied, while $host etc. -# will get canonicalized. -test -n "$target_alias" && - test "$program_prefix$program_suffix$program_transform_name" = \ - NONENONEs,x,x, && - program_prefix=${target_alias}- -# Extract the first word of "$target_alias-llvm-ar", so it can be a program name with args. -set dummy $target_alias-llvm-ar; ac_word=$2 + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}llvm-ar", so it can be a program name with args. +set dummy ${ac_tool_prefix}llvm-ar; ac_word=$2 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 $as_echo_n "checking for $ac_word... " >&6; } if ${ac_cv_path_LLVM_AR+:} false; then : @@ -6565,10 +6522,10 @@ $as_echo "no" >&6; } fi +fi if test -z "$ac_cv_path_LLVM_AR"; then - if test "$build" = "$target"; then - ac_pt_LLVM_AR=$LLVM_AR - # Extract the first word of "llvm-ar", so it can be a program name with args. + ac_pt_LLVM_AR=$LLVM_AR + # Extract the first word of "llvm-ar", so it can be a program name with args. set dummy llvm-ar; ac_word=$2 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 $as_echo_n "checking for $ac_word... " >&6; } @@ -6595,7 +6552,6 @@ done done IFS=$as_save_IFS - test -z "$ac_cv_path_ac_pt_LLVM_AR" && ac_cv_path_ac_pt_LLVM_AR="''" ;; esac fi @@ -6608,9 +6564,16 @@ else $as_echo "no" >&6; } fi - LLVM_AR=$ac_pt_LLVM_AR - else + if test "x$ac_pt_LLVM_AR" = x; then LLVM_AR="''" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + LLVM_AR=$ac_pt_LLVM_AR fi else LLVM_AR="$ac_cv_path_LLVM_AR" @@ -6682,8 +6645,9 @@ fi -# Extract the first word of "$target_alias-llvm-profdata", so it can be a program name with args. -set dummy $target_alias-llvm-profdata; ac_word=$2 +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}llvm-profdata", so it can be a program name with args. +set dummy ${ac_tool_prefix}llvm-profdata; ac_word=$2 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 $as_echo_n "checking for $ac_word... " >&6; } if ${ac_cv_path_LLVM_PROFDATA+:} false; then : @@ -6722,10 +6686,10 @@ $as_echo "no" >&6; } fi +fi if test -z "$ac_cv_path_LLVM_PROFDATA"; then - if test "$build" = "$target"; then - ac_pt_LLVM_PROFDATA=$LLVM_PROFDATA - # Extract the first word of "llvm-profdata", so it can be a program name with args. + ac_pt_LLVM_PROFDATA=$LLVM_PROFDATA + # Extract the first word of "llvm-profdata", so it can be a program name with args. set dummy llvm-profdata; ac_word=$2 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 $as_echo_n "checking for $ac_word... " >&6; } @@ -6752,7 +6716,6 @@ done done IFS=$as_save_IFS - test -z "$ac_cv_path_ac_pt_LLVM_PROFDATA" && ac_cv_path_ac_pt_LLVM_PROFDATA="''" ;; esac fi @@ -6765,9 +6728,16 @@ else $as_echo "no" >&6; } fi - LLVM_PROFDATA=$ac_pt_LLVM_PROFDATA - else + if test "x$ac_pt_LLVM_PROFDATA" = x; then LLVM_PROFDATA="''" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + LLVM_PROFDATA=$ac_pt_LLVM_PROFDATA fi else LLVM_PROFDATA="$ac_cv_path_LLVM_PROFDATA" @@ -10519,6 +10489,9 @@ then $as_echo "#define _REENTRANT 1" >>confdefs.h posix_threads=yes + if test "$ac_sys_system" = "SunOS"; then + CFLAGS="$CFLAGS -D_REENTRANT" + fi elif test "$ac_cv_kpthread" = "yes" then CC="$CC -Kpthread" diff --git a/configure.ac b/configure.ac index e5fb7e7b..1ef0df70 100644 --- a/configure.ac +++ b/configure.ac @@ -1339,7 +1339,7 @@ if test "$Py_LTO" = 'true' ; then case $CC in *clang*) AC_SUBST(LLVM_AR) - AC_PATH_TARGET_TOOL(LLVM_AR, llvm-ar, '', ${llvm_path}) + AC_PATH_TOOL(LLVM_AR, llvm-ar, '', ${llvm_path}) AC_SUBST(LLVM_AR_FOUND) if test -n "${LLVM_AR}" -a -x "${LLVM_AR}" then @@ -1405,7 +1405,7 @@ AC_SUBST(LLVM_PROF_MERGER) AC_SUBST(LLVM_PROF_FILE) AC_SUBST(LLVM_PROF_ERR) AC_SUBST(LLVM_PROFDATA) -AC_PATH_TARGET_TOOL(LLVM_PROFDATA, llvm-profdata, '', ${llvm_path}) +AC_PATH_TOOL(LLVM_PROFDATA, llvm-profdata, '', ${llvm_path}) AC_SUBST(LLVM_PROF_FOUND) if test -n "${LLVM_PROFDATA}" -a -x "${LLVM_PROFDATA}" then @@ -2333,7 +2333,7 @@ if test "$ac_cv_sizeof_off_t" -gt "$ac_cv_sizeof_long" -a \ "$ac_cv_sizeof_long_long" -ge "$ac_cv_sizeof_off_t"; then AC_DEFINE(HAVE_LARGEFILE_SUPPORT, 1, [Defined to enable large file support when an off_t is bigger than a long - and long long is available and at least as big as an off_t. You may need + and long long is at least as big as an off_t. You may need to add some flags for configuration and compilation to enable this mode. (For Solaris and Linux, the necessary defines are already defined.)]) AC_MSG_RESULT(yes) @@ -3079,6 +3079,9 @@ then # Defining _REENTRANT on system with POSIX threads should not hurt. AC_DEFINE(_REENTRANT) posix_threads=yes + if test "$ac_sys_system" = "SunOS"; then + CFLAGS="$CFLAGS -D_REENTRANT" + fi elif test "$ac_cv_kpthread" = "yes" then CC="$CC -Kpthread" diff --git a/pyconfig.h.in b/pyconfig.h.in index 4032fa51..d36fc933 100644 --- a/pyconfig.h.in +++ b/pyconfig.h.in @@ -540,9 +540,9 @@ #undef HAVE_LANGINFO_H /* Defined to enable large file support when an off_t is bigger than a long - and long long is available and at least as big as an off_t. You may need to - add some flags for configuration and compilation to enable this mode. (For - Solaris and Linux, the necessary defines are already defined.) */ + and long long is at least as big as an off_t. You may need to add some + flags for configuration and compilation to enable this mode. (For Solaris + and Linux, the necessary defines are already defined.) */ #undef HAVE_LARGEFILE_SUPPORT /* Define to 1 if you have the 'lchflags' function. */