lxml changelog

127 return s.encode(120 unichr_escape = re.compile(r'\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}') +121 +122 if sys.version_info[0] >= 3: +123 # Python 3 +124 from builtins import str as unicode +125 from codecs import unicode_escape_decode +126 _chr = chr +127 - def _str(s, encoding="UTF-8"): + 128 return unichr_escape.sub(lambda x: unicode_escape_decode(x.group(0))[0], s) + 129 - def _bytes(s, encoding="UTF-8"): + 130 return s.encode(encoding) - 128 from io import BytesIO as _BytesIO -129 - def BytesIO(*args): - 130 if args and isinstance(args[0], str): -131 args = (args[0].encode("UTF-8"),) -132 return _BytesIO(*args) - 133 -134 doctest_parser = doctest.DocTestParser() -135 _fix_unicode = re.compile(r'(\s+)u(["\'])').sub -136 _fix_exceptions = re.compile(r'(.*except [^(]*),\s*(.*:)').sub -137 - def make_doctest(filename): - 138 filename = _get_caller_relative_path(filename) -139 doctests = read_file(filename) -140 doctests = _fix_unicode(r'\1\2', doctests) -141 doctests = _fix_exceptions(r'\1 as \2', doctests) -142 return doctest.DocTestCase( -143 doctest_parser.get_doctest( -144 doctests, {}, os.path.basename(filename), filename, 0)) - 145 else: -146 # Python 2 -147 unichr_escape = re.compile(r'\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}') -148 -149 from __builtin__ import unicode -150 _chr = unichr -151 - def _str(s, encoding="UTF-8"): - 152 s = unicode(s, encoding) + 131 from io import BytesIO as _BytesIO +132 - def BytesIO(*args): + 133 if args and isinstance(args[0], str): +134 args = (args[0].encode("UTF-8"),) +135 return _BytesIO(*args) + 136 +137 doctest_parser = doctest.DocTestParser() +138 _fix_unicode = re.compile(r'(\s+)u(["\'])').sub +139 _fix_exceptions = re.compile(r'(.*except [^(]*),\s*(.*:)').sub +140 - def make_doctest(filename): + 141 filename = _get_caller_relative_path(filename) +142 doctests = read_file(filename) +143 doctests = _fix_unicode(r'\1\2', doctests) +144 doctests = _fix_exceptions(r'\1 as \2', doctests) +145 return doctest.DocTestCase( +146 doctest_parser.get_doctest( +147 doctests, {}, os.path.basename(filename), filename, 0)) + 148 else: +149 # Python 2 +150 from __builtin__ import unicode +151 _chr = unichr +152 - def _str(s, encoding="UTF-8"): + 153 s = unicode(s, encoding=encoding=encoding) -153 return unichr_escape.sub(lambda x: -154 x.group(0).decode('unicode-escape'), -155 s) - 156 - def _bytes(s, encoding="UTF-8"): - 157 return s - 158 from io import BytesIO -159 -160 doctest_parser = doctest.DocTestParser() -161 _fix_traceback = re.compile(r'^(\s*)(?:\w+\.)+(\w*(?:Error|Exception|Invalid):)', re.M).sub -162 _fix_exceptions = re.compile(r'(.*except [^(]*)\s+as\s+(.*:)').sub -163 _fix_bytes = re.compile(r'(\s+)b(["\'])').sub -164 - def make_doctest(filename): - 165 filename = _get_caller_relative_path(filename) -166 doctests = read_file(filename) -167 doctests = _fix_traceback(r'\1\2', doctests) -168 doctests = _fix_exceptions(r'\1, \2', doctests) -169 doctests = _fix_bytes(r'\1\2', doctests) -170 return doctest.DocTestCase( -171 doctest_parser.get_doctest( -172 doctests, {}, os.path.basename(filename), filename, 0)) - 173 -174 try: -175 skipIf = unittest.skipIf -176 except AttributeError: -177 - def skipIf(condition, why, -178 _skip=lambda test_method: None, -179 _keep=lambda test_method: test_method): - 180 if condition: -181 return _skip -182 return _keep - 183 -184 -185 -class HelperTestCase(unittest.TestCase): -

186 - def tearDown(self): -

187 gc.collect() +lxml.tests.selftest2.encoding" class="py-name" href="#" onclick="return doclink('link-70', 'encoding', 'link-52');">encoding) +154 return unichr_escape.sub(lambda x: +155 x.group(0).decode('unicode-escape'), +156 s) +

157 - def _bytes(s, encoding="UTF-8"): +

158 return s +

159 from io import BytesIO +160 +161 doctest_parser = doctest.DocTestParser() +162 _fix_traceback = re.compile(r'^(\s*)(?:\w+\.)+(\w*(?:Error|Exception|Invalid):)', re.M).sub +163 _fix_exceptions = re.compile(r'(.*except [^(]*)\s+as\s+(.*:)').sub +164 _fix_bytes = re.compile(r'(\s+)b(["\'])').sub +

165 - def make_doctest(filename): +

166 filename = _get_caller_relative_path(filename) +167 doctests = read_file(filename) +168 doctests = _fix_traceback(r'\1\2', doctests) +169 doctests = _fix_exceptions(r'\1, \2', doctests) +170 doctests = _fix_bytes(r'\1\2', doctests) +171 return doctest.DocTestCase( +172 doctest_parser.get_doctest( +173 doctests, {}, os.path.basename(filename), filename, 0)) +

174 +175 try: +176 skipIf = unittest.skipIf +177 except AttributeError: +

178 - def skipIf(condition, why): +

179 def _skip(thing): +180 import types +181 if isinstance(thing, (type, types.ClassType)): +182 return type(thing.__name__, (object,), {}) +183 else: +184 return None +

185 if condition: +186 return _skip +187 return lambda thing: thing

188 -

189 - def parse(self, text, parser=None): -

190 f = BytesIO(189 +190 -class HelperTestCase(unittest.TestCase): + 191 - def tearDown(self): + 192 gc.collect() + 193 +194 - def parse(self, text, parser=None): + 195 f = BytesIO(text) if isinstance(text) if isinstance(text, bytes) else StringIO(text, bytes) else StringIO(text) -191 return text) +196 return etree.etree.parse(f, parser=parser) - 192 -193 - def _rootstring(self, tree): - 194 return parse(f, parser=parser) + 197 +198 - def _rootstring(self, tree): + 199 return etree.tostring(tree.getroot()).replace( -195 _bytes(' '), _bytes('')).replace(_bytes('\n'), _bytes('')) - 196 -197 # assertFalse doesn't exist in Python 2.3 -198 try: -199 unittest.TestCase.assertFalse -200 except AttributeError: -201 assertFalse = unittest.TestCase.failIf - 202 -203 -204 -class SillyFileLike: - 205 - def __init__(self, xml_data=_bytes('<foo><bar/></foo>')): - 206 self.xml_data = xml_data - 207 -208 - def read(self, amount=None): - 209 if self.xml_data: -210 if amount: -211 data = self.xml_data[:amount] -212 self.xml_data = self.xml_data[amount:] -213 else: -214 data = self.xml_data -215 self.xml_data = _bytes('') -216 return data -217 return _bytes('') - 218 -219 -class LargeFileLike: - 220 - def __init__(self, charlen=100, depth=4, children=5): - 221 self.data = BytesIO() -222 self.chars = _bytes('a') * charlen -223 self.children = range(children) -224 self.more = self.etree.tostring(tree.getroot()).replace( +200 _bytes(' '), _bytes('')).replace(_bytes('\n'), _bytes('')) + 201 +202 # assertFalse doesn't exist in Python 2.3 +203 try: +204 unittest.TestCase.assertFalse +205 except AttributeError: +206 assertFalse = unittest.TestCase.failIf + 207 +208 +209 -class SillyFileLike: + 210 - def __init__(self, xml_data=_bytes('<foo><bar/></foo>')): + 211 self.xml_data = xml_data + 212 +213 - def read(self, amount=None): + 214 if self.xml_data: +215 if amount: +216 data = self.xml_data[:amount] +217 self.xml_data = self.xml_data[amount:] +218 else: +219 data = self.xml_data +220 self.xml_data = _bytes('') +221 return data +222 return _bytes('') + 223 +224 -class LargeFileLike: + 225 - def __init__(self, charlen=100, depth=4, children=5): + 226 self.data = BytesIO() +227 self.chars = _bytes('a') * charlen +228 self.children = range(children) +229 self.more = self.iterelements(depth) - 225 -226 - def iterelements(self, depth): - 227 yield _bytes('<root>') -228 depth -= 1 -229 if depth > 0: -230 for child in self.children: -231 for element in self.iterelements(depth) + 230 +231 - def iterelements(self, depth): + 232 yield _bytes('<root>') +233 depth -= 1 +234 if depth > 0: +235 for child in self.children: +236 for element in self.iterelements(depth): -232 yield element -233 yield self.chars -234 else: -235 yield self.chars -236 yield _bytes('</root>') - 237 -238 - def read(self, amount=None): - 239 data = self.data -240 append = data.write -241 if amount: -242 for element in self.more: -243 append(element) -244 if data.tell() >= amount: -245 break -246 else: -247 for element in self.more: -248 append(element) -249 result = data.getvalue() -250 data.seek(0) -251 data.truncate() -252 if amount: -253 append(result[amount:]) -254 result = result[:amount] -255 return result - 256 -257 -class LargeFileLikeUnicode(LargeFileLike): - 258 - def __init__(self, charlen=100, depth=4, children=5): - 259 LargeFileLike.iterelements(depth): +237 yield element +238 yield self.chars +239 else: +240 yield self.chars +241 yield _bytes('</root>') + 242 +243 - def read(self, amount=None): + 244 data = self.data +245 append = data.write +246 if amount: +247 for element in self.more: +248 append(element) +249 if data.tell() >= amount: +250 break +251 else: +252 for element in self.more: +253 append(element) +254 result = data.getvalue() +255 data.seek(0) +256 data.truncate() +257 if amount: +258 append(result[amount:]) +259 result = result[:amount] +260 return result + 261 +262 -class LargeFileLikeUnicode(LargeFileLike): + 263 - def __init__(self, charlen=100, depth=4, children=5): + 264 LargeFileLike.__init__(self, charlen, depth, children) -260 self.data = StringIO() -261 self.chars = _str('a') * charlen -262 self.more = self.__init__(self, charlen, depth, children) +265 self.data = StringIO() +266 self.chars = _str('a') * charlen +267 self.more = self.iterelements(depth) - 263 -264 - def iterelements(self, depth): - 265 yield _str('<root>') -266 depth -= 1 -267 if depth > 0: -268 for child in self.children: -269 for element in self.iterelements(depth) + 268 +269 - def iterelements(self, depth): + 270 yield _str('<root>') +271 depth -= 1 +272 if depth > 0: +273 for child in self.children: +274 for element in self.iterelements(depth): -270 yield element -271 yield self.chars -272 else: -273 yield self.chars -274 yield _str('</root>') - 275 -276 -def fileInTestDir(name): - 277 _testdir = os.path.dirname(__file__) -278 return os.path.join(_testdir, iterelements(depth): +275 yield element +276 yield self.chars +277 else: +278 yield self.chars +279 yield _str('</root>') +

280 +281 -def fileInTestDir(name): + 282 _testdir = os.path.dirname(__file__) +283 return os.path.join(_testdir, name) - 279 -280 -def path2url(path): - 281 return urlparse.urljoin( -282 'file:', pathname2url(path)) - 283 -284 -def fileUrlInTestDir(name): - 285 return path2url(fileInTestDir(name) + 284 +285 -def path2url(path): + 286 return urlparse.urljoin( +287 'file:', pathname2url(path)) + 288 +289 -def fileUrlInTestDir(name): + 290 return path2url(fileInTestDir(name)) - 286 -287 -def read_file(name, mode='r'): - 288 f = open(name)) + 291 +292 -def read_file(name, mode='r'): + 293 f = open(name, mode) -289 try: -290 data = f.read() -291 finally: -292 f.name, mode) +294 try: +295 data = f.read() +296 finally: +297 f.close() -293 return data - 294 -295 -def write_to_file(name, data, mode='w'): - 296 f = open(close() +298 return data + 299 +300 -def write_to_file(name, data, mode='w'): + 301 f = open(name, mode) -297 try: -298 data = f.write(data) -299 finally: -300 f.name, mode) +302 try: +303 data = f.write(data) +304 finally: +305 f.close() - 301 -302 -def readFileInTestDir(name, mode='r'): - 303 return read_file(fileInTestDir(close() + 306 +307 -def readFileInTestDir(name, mode='r'): + 308 return read_file(fileInTestDir(name), mode) - 304 -305 -def canonicalize(xml): - 306 tree = name), mode) + 309 +310 -def canonicalize(xml): + 311 tree = etree.etree.parse(BytesIO(xml) if isinstance(xml, bytes) else StringIO(xml)) -307 f = BytesIO() -308 tree.write_c14n(f) -309 return f.getvalue() - 310 -311 -def unentitify(xml): - 312 for entity_name, parse(BytesIO(xml) if isinstance(xml, bytes) else StringIO(xml)) +312 f = BytesIO() +313 tree.write_c14n(f) +314 return f.getvalue() + 315 +316 -def unentitify(xml): + 317 for entity_name, value in re.findall("(&#([0-9]+);)", xml): -313 xml = xml.replace(entity_name, unichr(int(value in re.findall("(&#([0-9]+);)", xml): +318 xml = xml.replace(entity_name, unichr(int(value))) -314 return xml - 315 -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap How to build lxml from source +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap How to build lxml from source To build lxml from source, you need libxml2 and libxslt properly installed, including the header files. These are likely shipped in @@ -303,7 +303,7 @@ installed using dpkg -i -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/capi.html b/doc/html/capi.html index 733cd09f..e3369fc5 100644 --- a/doc/html/capi.html +++ b/doc/html/capi.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap The public C-API of lxml.etree +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap The public C-API of lxml.etree As of version 1.1, lxml.etree provides a public C-API. This allows external C extensions to efficiently access public functions and classes of lxml, @@ -110,7 +110,7 @@ includes may not be sufficient. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/changes-3.7.2.html b/doc/html/changes-3.7.2.html deleted file mode 100644 index 7b0a6aa3..00000000 --- a/doc/html/changes-3.7.2.html +++ /dev/null @@ -1,3165 +0,0 @@ - - - - - - -lxml changelog - - - - -lxml changelog - - -3.7.2 (2017-01-08) - -Bugs fixed - -Work around installation problems in recent Python 2.7 versions -due to FTP download failures. -GH#219: xmlfile.element() was not properly quoting attribute values. -Patch by Burak Arslan. -GH#218: xmlfile.element() was not properly escaping text content of -script/style tags. Patch by Burak Arslan. - - - - -3.7.1 (2016-12-23) - -No source changes, issued only to solve problems with the -binary packages released for 3.7.0. - - - -3.7.0 (2016-12-10) - -Features added - -GH#217: XMLSyntaxError now behaves more like its SyntaxError -baseclass. Patch by Philipp A. -GH#216: HTMLParser() now supports the same collect_ids parameter -as XMLParser(). Patch by Burak Arslan. -GH#210: Allow specifying a serialisation method in xmlfile.write(). -Patch by Burak Arslan. -GH#203: New option default_doctype in HTMLParser that allows -disabling the automatic doctype creation. Patch by Shadab Zafar. -GH#201: Calling the method .set('attrname') without value argument -(or None) on HTML elements creates an attribute without value that -serialises like <div attrname></div>. Patch by Daniel Holth. -GH#197: Ignore form input fields in form_values() when they are -marked as disabled in HTML. Patch by Kristian Klemon. - - - -Bugs fixed - -GH#206: File name and line number were missing from XSLT error messages. -Patch by Marcus Brinkmann. - - - -Other changes - -Log entries no longer allow anything but plain string objects as message text -and file name. -zlib is included in the list of statically built libraries. - - - - -3.6.4 (2016-08-20) - -GH#204, LP#1614693: build fix for MacOS-X. - - - -3.6.3 (2016-08-18) - -LP#1614603: change linker flags to build multi-linux wheels - - - -3.6.2 (2016-08-18) - -LP#1614603: release without source changes to provide cleanly built Linux wheels - - - -3.6.1 (2016-07-24) - -Features added - -GH#180: Separate option inline_style for Cleaner that only removes style -attributes instead of all styles. Patch by Christian Pedersen. -GH#196: Windows build support for Python 3.5. Contribution by Maximilian Hils. - - - -Bugs fixed - -GH#199: Exclude file fields from FormElement.form_values (as browsers do). -Patch by Tomas Divis. -GH#198, LP#1568167: Try to provide base URL from Resolver.resolve_string(). -Patch by Michael van Tellingen. -GH#191: More accurate float serialisation in objectify.FloatElement. -Patch by Holger Joukl. -LP#1551797: Repair XSLT error logging. Patch by Marcus Brinkmann. - - - - -3.6.0 (2016-03-17) - -Features added - -GH#187: Now supports (only) version 5.x and later of PyPy. -Patch by Armin Rigo. -GH#181: Direct support for .rnc files in RelaxNG() if rnc2rng -is installed. Patch by Dirkjan Ochtman. - - - -Bugs fixed - -GH#189: Static builds honour FTP proxy configurations when downloading -the external libs. Patch by Youhei Sakurai. -GH#186: Soupparser failed to process entities in Python 3.x. -Patch by Duncan Morris. -GH#185: Rare encoding related TypeError on import was fixed. -Patch by Petr Demin. - - - - -3.5.0 (2015-11-13) - -Bugs fixed - -Unicode string results failed XPath queries in PyPy. -LP#1497051: HTML target parser failed to terminate on exceptions -and continued parsing instead. -Deprecated API usage in doctestcompare. - - - - -3.5.0b1 (2015-09-18) - -Features added - -cleanup_namespaces() accepts a new argument keep_ns_prefixes -that does not remove definitions of the provided prefix-namespace -mapping from the tree. -cleanup_namespaces() accepts a new argument top_nsmap that -moves definitions of the provided prefix-namespace mapping to the -top of the tree. -LP#1490451: Element objects gained a cssselect() method as -known from lxml.html. Patch by Simon Sapin. -API functions and methods behave and look more like Python functions, -which allows introspection on them etc. One side effect to be aware of -is that the functions now bind as methods when assigned to a class -variable. A quick fix is to wrap them in staticmethod() (as for -normal Python functions). -ISO-Schematron support gained an option error_finder that allows -passing a filter function for picking validation errors from reports. -LP#1243600: Elements in lxml.html gained a classes property -that provides a set-like interface to the class attribute. -Original patch by masklinn. -LP#1341964: The soupparser now handles DOCTYPE declarations, comments -and processing instructions outside of the root element. -Patch by Olli Pottonen. -LP#1421512: The docinfo of a tree was made editable to allow -setting and removing the public ID and system ID of the DOCTYPE. -Patch by Olli Pottonen. -LP#1442427: More work-arounds for quirks and bugs in pypy and pypy3. -lxml.html.soupparser now uses BeautifulSoup version 4 instead -of version 3 if available. - - - -Bugs fixed - -Memory errors that occur during tree adaptations (e.g. moving subtrees -to foreign documents) could leave the tree in a crash prone state. -Calling process_children() in an XSLT extension element without -an output_parent argument failed with a TypeError. -Fix by Jens TrÃ¶ger. -GH#162: Image data in HTML data URLs is considered safe and -no longer removed by lxml.html.clean JavaScript cleaner. -GH#166: Static build could link libraries in wrong order. -GH#172: Rely a bit more on libxml2 for encoding detection rather than -rolling our own in some cases. Patch by Olli Pottonen. -GH#159: Validity checks for names and string content were tightened -to detect the use of illegal characters early. Patch by Olli Pottonen. -LP#1421921: Comments/PIs before the DOCTYPE declaration were not -serialised. Patch by Olli Pottonen. -LP#659367: Some HTML DOCTYPE declarations were not serialised. -Patch by Olli Pottonen. -LP#1238503: lxml.doctestcompare is now consistent with stdlib's doctest -in how it uses + and - to refer to unexpected and missing output. -Empty prefixes are explicitly rejected when a namespace mapping is used -with ElementPath to avoid hiding bugs in user code. -Several problems with PyPy were fixed by switching to Cython 0.23. - - - - -3.4.4 (2015-04-25) - -Bugs fixed - -An ElementTree compatibility test added in lxml 3.4.3 that failed in -Python 3.4+ was removed again. - - - - -3.4.3 (2015-04-15) - -Bugs fixed - -Expression cache in ElementPath was ignored. Fix by Changaco. -LP#1426868: Passing a default namespace and a prefixed namespace mapping -as nsmap into xmlfile.element() raised a TypeError. -LP#1421927: DOCTYPE system URLs were incorrectly quoted when containing -double quotes. Patch by Olli Pottonen. -LP#1419354: meta-redirect URLs were incorrectly processed by -iterlinks() if preceded by whitespace. - - - - -3.4.2 (2015-02-07) - -Bugs fixed - -LP#1415907: Crash when creating an XMLSchema from a non-root element -of an XML document. -LP#1369362: HTML cleaning failed when hitting processing instructions -with pseudo-attributes. -CDATA() wrapped content was rejected for tail text. -CDATA sections were not serialised as tail text of the top-level element. - - - - -3.4.1 (2014-11-20) - -Features added - -New htmlfile HTML generator to accompany the incremental xmlfile -serialisation API. Patch by Burak Arslan. - - - -Bugs fixed - -lxml.sax.ElementTreeContentHandler did not initialise its superclass. - - - - -3.4.0 (2014-09-10) - -Features added - -xmlfile(buffered=False) disables output buffering and flushes the -content after each API operation (starting/ending element blocks or writes). -A new method xf.flush() can alternatively be used to explicitly flush -the output. -lxml.html.document_fromstring has a new option ensure_head_body=True -which will add an empty head and/or body element to the result document if -missing. -lxml.html.iterlinks now returns links inside meta refresh tags. -New XMLParser option collect_ids=False to disable ID hash table -creation. This can substantially speed up parsing of documents with many -different IDs that are not used. -The parser uses per-document hash tables for XML IDs. This reduces the -load of the global parser dict and speeds up parsing for documents with -many different IDs. -ElementTree.getelementpath(element) returns a structural ElementPath -expression for the given element, which can be used for lookups later. -xmlfile() accepts a new argument close=True to close file(-like) -objects after writing to them. Before, xmlfile() only closed the file -if it had opened it internally. -Allow "bytearray" type for ASCII text input. - - - -Bugs fixed - - -Other changes - -LP#400588: decoding errors have become hard errors even in recovery mode. -Previously, they could lead to an internal tree representation in a mixed -encoding state, which lead to very late errors or even silently incorrect -behaviour during tree traversal or serialisation. -Requires Python 2.6, 2.7, 3.2 or later. No longer supports -Python 2.4, 2.5 and 3.1, use lxml 3.3.x for those. -Requires libxml2 2.7.0 or later and libxslt 1.1.23 or later, -use lxml 3.3.x with older versions. - - - - -3.3.6 (2014-08-28) - -Bugs fixed - -Prevent tree cycle creation when adding Elements as siblings. -LP#1361948: crash when deallocating Element siblings without parent. -LP#1354652: crash when traversing internally loaded documents in XSLT -extension functions. - - - - -3.3.5 (2014-04-18) - -Bugs fixed - -HTML cleaning could fail to strip javascript links that mix control -characters into the link scheme. - - - - -3.3.4 (2014-04-03) - -Features added - -Source line numbers above 65535 are available on Elements when -using libxml2 2.9 or later. - - - -Bugs fixed - -lxml.html.fragment_fromstring() failed for bytes input in Py3. - - - -Other changes - - - -3.3.3 (2014-03-04) - -Bugs fixed - -LP#1287118: Crash when using Element subtypes with __slots__. - - - -Other changes - -The internal classes _LogEntry and _Attrib can no longer be -subclassed from Python code. - - - - -3.3.2 (2014-02-26) - -Bugs fixed - -The properties resolvers and version, as well as the methods -set_element_class_lookup() and makeelement(), were lost from -iterparse objects in 3.3.0. -LP#1222132: instances of XMLSchema, Schematron and RelaxNG -did not clear their local error_log before running a validation. -LP#1238500: lxml.doctestcompare mixed up "expected" and "actual" in -attribute values. -Some file I/O tests were failing in MS-Windows due to non-portable temp -file usage. Initial patch by Gabi Davar. -LP#910014: duplicate IDs in a document were not reported by DTD validation. -LP#1185332: tostring(method="html") did not use HTML serialisation -semantics for trailing tail text. Initial patch by Sylvain Viollon. -LP#1281139: .attrib value of Comments lost its mutation methods -in 3.3.0. Even though it is empty and immutable, it should still -provide the same interface as that returned for Elements. - - - - -3.3.1 (2014-02-12) - -Features added - - -Bugs fixed - -LP#1014290: HTML documents parsed with parser.feed() failed to find -elements during tag iteration. -LP#1273709: Building in PyPy failed due to missing support for -PyUnicode_Compare() and PyByteArray_*() in PyPy's C-API. -LP#1274413: Compilation in MSVC failed due to missing "stdint.h" standard -header file. -LP#1274118: iterparse() failed to parse BOM prefixed files. - - - -Other changes - - - -3.3.0 (2014-01-26) - -Features added - - -Bugs fixed - -The heuristic that distinguishes file paths from URLs was tightened -to produce less false negatives. - - - -Other changes - - - -3.3.0beta5 (2014-01-18) - -Features added - -The PEP 393 unicode parsing support gained a fallback for wchar strings -which might still be somewhat common on Windows systems. - - - -Bugs fixed - -Several error handling problems were fixed throughout the code base that -could previously lead to exceptions being silently swallowed or not -properly reported. -The C-API function appendChild() is now deprecated as it does not -propagate exceptions (its return type is void). The new function -appendChildToElement() was added as a safe replacement. -Passing a string into fromstringlist() raises an exception instead of -parsing the string character by character. - - - -Other changes - -Document cleanup code was simplified using the new GC features in -Cython 0.20. - - - - -3.3.0beta4 (2014-01-12) - -Features added - - -Bugs fixed - -The (empty) value returned by the attrib property of Entity and Comment -objects was mutable. -Element class lookup wasn't available for the new pull parsers or when using -a custom parser target. -Setting Element attributes on instantiation with both the attrib argument -and keyword arguments could modify the mapping passed as attrib. -LP#1266171: DTDs instantiated from internal/external subsets (i.e. through -the docinfo property) lost their attribute declarations. - - - -Other changes - -Built with Cython 0.20pre (gitrev 012ae82eb) to prepare support for -Python 3.4. - - - - -3.3.0beta3 (2014-01-02) - -Features added - -Unicode string parsing was optimised for Python 3.3 (PEP 393). - - - -Bugs fixed - -HTML parsing of Unicode strings could misdecode the input on some platforms. -Crash in xmlfile() when closing open elements out of order in an error case. - - - -Other changes - - - -3.3.0beta2 (2013-12-20) - -Features added - -iterparse() supports the recover option. - - - -Bugs fixed - -Crash in iterparse() for HTML parsing. -Crash in target parsing with attributes. - - - -Other changes - -The safety check in the read-only tree implementation (e.g. used by -PythonElementClassLookup) raises a more appropriate ReferenceError -for illegal access after tree disposal instead of an AssertionError. -This should only impact test code that specifically checks the original -behaviour. - - - - -3.3.0beta1 (2013-12-12) - -Features added - -New option handle_failures in make_links_absolute() and -resolve_base_href() (lxml.html) that enables ignoring or -discarding links that fail to parse as URLs. -New parser classes XMLPullParser and HTMLPullParser for -incremental parsing, as implemented for ElementTree in Python 3.4. -iterparse() enables recovery mode by default for HTML parsing -(html=True). - - - -Bugs fixed - -LP#1255132: crash when trying to run validation over non-Element (e.g. -comment or PI). -Error messages in the log and in exception messages that originated -from libxml2 could accidentally be picked up from preceding warnings -instead of the actual error. -The ElementMaker in lxml.objectify did not accept a dict as -argument for adding attributes to the element it's building. This -works as in lxml.builder now. -LP#1228881: repr(XSLTAccessControl) failed in Python 3. -Raise ValueError when trying to append an Element to itself or -to one of its own descendants, instead of running into an infinite -loop. -LP#1206077: htmldiff discarded whitespace from the output. -Compressed plain-text serialisation to file-like objects was broken. -lxml.html.formfill: Fix textarea form filling. -The textarea used to be cleared before the new content was set, -which removed the name attribute. - - - -Other changes - -Some basic API classes use freelists internally for faster -instantiation. This can speed up some iterparse() scenarios, -for example. -iterparse() was rewritten to use the new *PullParser -classes internally instead of being a parser itself. - - - - -3.2.5 (2014-01-02) - -Features added - - -Bugs fixed - -Crash in xmlfile() when closing open elements out of order in an error case. -Crash in target parsing with attributes. -LP#1255132: crash when trying to run validation over non-Element (e.g. -comment or PI). - - - -Other changes - - - -3.2.4 (2013-11-07) - -Features added - - -Bugs fixed - -Memory leak when creating an XPath evaluator in a thread. -LP#1228881: repr(XSLTAccessControl) failed in Python 3. -Raise ValueError when trying to append an Element to itself or -to one of its own descendants. -LP#1206077: htmldiff discarded whitespace from the output. -Compressed plain-text serialisation to file-like objects was broken. - - - -Other changes - - - -3.2.3 (2013-07-28) - -Bugs fixed - -Fix support for Python 2.4 which was lost in 3.2.2. - - - - -3.2.2 (2013-07-28) - -Features added - - -Bugs fixed - -LP#1185701: spurious XMLSyntaxError after finishing iterparse(). -Crash in lxml.objectify during xsi annotation. - - - -Other changes - -Return values of user provided element class lookup methods are now -validated against the type of the XML node they represent to prevent -API class mismatches. - - - - -3.2.1 (2013-05-11) - -Features added - -The methods apply_templates() and process_children() of XSLT -extension elements have gained two new boolean options elements_only -and remove_blank_text that discard either all strings or whitespace-only -strings from the result list. - - - -Bugs fixed - -When moving Elements to another tree, the namespace cleanup mechanism -no longer drops namespace prefixes from attributes for which it finds -a default namespace declaration, to prevent them from appearing as -unnamespaced attributes after serialisation. -Returning non-type objects from a custom class lookup method could lead -to a crash. -Instantiating and using subtypes of Comments and ProcessingInstructions -crashed. - - - -Other changes - - - -3.2.0 (2013-04-28) - -Features added - - -Bugs fixed - -LP#690319: Leading whitespace could change the behaviour of the string -parsing functions in lxml.html. -LP#599318: The string parsing functions in lxml.html are more robust -in the face of uncommon HTML content like framesets or missing body tags. -Patch by Stefan Seelmann. -LP#712941: I/O errors while trying to access files with paths that contain -non-ASCII characters could raise UnicodeDecodeError instead of properly -reporting the IOError. -LP#673205: Parsing from in-memory strings disabled network access in the -default parser and made subsequent attempts to parse from a URL fail. -LP#971754: lxml.html.clean appends 'nofollow' to 'rel' attributes instead -of overwriting the current value. -LP#715687: lxml.html.clean no longer discards scripts that are explicitly -allowed by the user provided whitelist. Patch by Christine Koppelt. - - - -Other changes - - - -3.1.2 (2013-04-12) - -Features added - - -Bugs fixed - -LP#1136509: Passing attributes through the namespace-unaware API of -the sax bridge (i.e. the handler.startElement() method) failed -with a TypeError. Patch by Mike Bayer. -LP#1123074: Fix serialisation error in XSLT output when converting -the result tree to a Unicode string. -GH#105: Replace illegal usage of xmlBufLength() in libxml2 2.9.0 -by properly exported API function xmlBufUse(). - - - -Other changes - - - -3.1.1 (2013-03-29) - -Features added - - -Bugs fixed - -LP#1160386: Write access to lxml.html.FormElement.fields raised -an AttributeError in Py3. -Illegal memory access during cleanup in incremental xmlfile writer. - - - -Other changes - -The externally useless class lxml.etree._BaseParser was removed -from the module dict. - - - - -3.1.0 (2013-02-10) - -Features added - -GH#89: lxml.html.clean allows overriding the set of attributes that it -considers 'safe'. Patch by Francis Devereux. - - - -Bugs fixed - -LP#1104370: copy.copy(el.attrib) raised an exception. It now returns -a copy of the attributes as a plain Python dict. -GH#95: When used with namespace prefixes, the el.find*() methods -always used the first namespace mapping that was provided for each -path expression instead of using the one that was actually passed -in for the current run. -LP#1092521, GH#91: Fix undefined C symbol in Python runtimes compiled -without threading support. Patch by Ulrich Seidl. - - - -Other changes - - - -3.1beta1 (2012-12-21) - -Features added - -New build-time option --with-unicode-strings for Python 2 that -makes the API always return Unicode strings for names and text -instead of byte strings for plain ASCII content. -New incremental XML file writing API etree.xmlfile(). -E factory in lxml.objectify is callable to simplify the creation of -tags with non-identifier names without having to resort to getattr(). - - - -Bugs fixed - -When starting from a non-namespaced element in lxml.objectify, searching -for a child without explicitly specifying a namespace incorrectly found -namespaced elements with the requested local name, instead of restricting -the search to non-namespaced children. -GH#85: Deprecation warnings were fixed for Python 3.x. -GH#33: lxml.html.fromstring() failed to accept bytes input in Py3. -LP#1080792: Static build of libxml2 2.9.0 failed due to missing file. - - - -Other changes - -The externally useless class _ObjectifyElementMakerCaller was -removed from the module API of lxml.objectify. -LP#1075622: lxml.builder is faster for adding text to elements with -many children. Patch by Anders Hammarquist. - - - - -3.0.2 (2012-12-14) - -Features added - - -Bugs fixed - -Fix crash during interpreter shutdown by switching to Cython 0.17.3 for building. - - - -Other changes - - - -3.0.1 (2012-10-14) - -Features added - - -Bugs fixed - -LP#1065924: Element proxies could disappear during garbage collection -in PyPy without proper cleanup. -GH#71: Failure to work with libxml2 2.6.x. -LP#1065139: static MacOS-X build failed in Py3. - - - -Other changes - - - -3.0 (2012-10-08) - -Features added - - -Bugs fixed - -End-of-file handling was incorrect in iterparse() when reading from -a low-level C file stream and failed in libxml2 2.9.0 due to its -improved consistency checks. - - - -Other changes - -The build no longer uses Cython by default unless the generated C files -are missing. To use Cython, pass the option "--with-cython". To ignore -the fatal build error when Cython is required but not available (e.g. to -run special setup.py commands that do not actually run a build), pass -"--without-cython". - - - - -3.0beta1 (2012-09-26) - -Features added - -Python level access to (optional) libxml2 memory debugging features -to simplify debugging of memory leaks etc. - - - -Bugs fixed - -Fix a memory leak in XPath by switching to Cython 0.17.1. -Some tests were adapted to work with PyPy. - - - -Other changes - -The code was adapted to work with the upcoming libxml2 2.9.0 release. - - - - -3.0alpha2 (2012-08-23) - -Features added - -The .iter() method of elements now accepts tag arguments like -"{*}name" to search for elements with a given local name in any -namespace. With this addition, all combinations of wildcards now work -as expected: -"{ns}name", "{}name", "{*}name", "{ns}*", "{}*" -and "{*}*". Note that "name" is equivalent to "{}name", -but "*" is "{*}*". -The same change applies to the .getiterator(), .itersiblings(), -.iterancestors(), .iterdescendants(), .iterchildren() -and .itertext() methods;the strip_attributes(), -strip_elements() and strip_tags() functions as well as the -iterparse() class. Patch by Simon Sapin. -C14N allows specifying the inclusive prefixes to be promoted -to top-level during exclusive serialisation. - - - -Bugs fixed - -Passing long Unicode strings into the feed() parser interface -failed to read the entire string. - - - -Other changes - - - -3.0alpha1 (2012-07-31) - -Features added - -Initial support for building in PyPy (through cpyext). -DTD objects gained an API that allows read access to their -declarations. -xpathgrep.py gained support for parsing line-by-line (e.g. -from grep output) and for surrounding the output with a new root -tag. -E-factory in lxml.builder accepts subtypes of known data -types (such as string subtypes) when building elements around them. -Tree iteration and iterparse() with a selective tag -argument supports passing a set of tags. Tree nodes will be -returned by the iterators if they match any of the tags. - - - -Bugs fixed - -The .find*() methods in lxml.objectify no longer use XPath -internally, which makes them faster in many cases (especially when -short circuiting after a single or couple of elements) and fixes -some behavioural differences compared to lxml.etree. Note that -this means that they no longer support arbitrary XPath expressions -but only the subset that the ElementPath language supports. -The previous implementation was also redundant with the normal -XPath support, which can be used as a replacement. -el.find('*') could accidentally return a comment or processing -instruction that happened to be in the wrong spot. (Same for the -other .find*() methods.) -The error logging is less intrusive and avoids a global setup where -possible. -Fixed undefined names in html5lib parser. -xpathgrep.py did not work in Python 3. -Element.attrib.update() did not accept an attrib of -another Element as parameter. -For subtypes of ElementBase that make the .text or .tail -properties immutable (as in objectify, for example), inserting text -when creating Elements through the E-Factory feature of the class -constructor would fail with an exception, stating that the text -cannot be modified. - - - -Other changes - -The code base was overhauled to properly use 'const' where the API -of libxml2 and libxslt requests it. This also has an impact on the -public C-API of lxml itself, as defined in etreepublic.pxd, as -well as the provided declarations in the lxml/includes/ directory. -Code that uses these declarations may have to be adapted. On the -plus side, this fixes several C compiler warnings, also for user -code, thus making it easier to spot real problems again. -The functionality of "lxml.cssselect" was moved into a separate PyPI -package called "cssselect". To continue using it, you must install -that package separately. The "lxml.cssselect" module is still -available and provides the same interface, provided the "cssselect" -package can be imported at runtime. -Element attributes passed in as an attrib dict or as keyword -arguments are now sorted by (namespaced) name before being created -to make their order predictable for serialisation and iteration. -Note that adding or deleting attributes afterwards does not take -that order into account, i.e. setting a new attribute appends it -after the existing ones. -Several classes that are for internal use only were removed -from the lxml.etree module dict: -_InputDocument, _ResolverRegistry, _ResolverContext, _BaseContext, -_ExsltRegExp, _IterparseContext, _TempStore, _ExceptionContext, -__ContentOnlyElement, _AttribIterator, _NamespaceRegistry, -_ClassNamespaceRegistry, _FunctionNamespaceRegistry, -_XPathFunctionNamespaceRegistry, _ParserDictionaryContext, -_FileReaderContext, _ParserContext, _PythonSaxParserTarget, -_TargetParserContext, _ReadOnlyProxy, _ReadOnlyPIProxy, -_ReadOnlyEntityProxy, _ReadOnlyElementProxy, _OpaqueNodeWrapper, -_OpaqueDocumentWrapper, _ModifyContentOnlyProxy, -_ModifyContentOnlyPIProxy, _ModifyContentOnlyEntityProxy, -_AppendOnlyElementProxy, _SaxParserContext, _FilelikeWriter, -_ParserSchemaValidationContext, _XPathContext, -_XSLTResolverContext, _XSLTContext, _XSLTQuotedStringParam -Several internal classes can no longer be inherited from: -_InputDocument, _ResolverRegistry, _ExsltRegExp, _ElementUnicodeResult, -_IterparseContext, _TempStore, _AttribIterator, _ClassNamespaceRegistry, -_XPathFunctionNamespaceRegistry, _ParserDictionaryContext, -_FileReaderContext, _PythonSaxParserTarget, _TargetParserContext, -_ReadOnlyPIProxy, _ReadOnlyEntityProxy, _OpaqueDocumentWrapper, -_ModifyContentOnlyPIProxy, _ModifyContentOnlyEntityProxy, -_AppendOnlyElementProxy, _FilelikeWriter, _ParserSchemaValidationContext, -_XPathContext, _XSLTResolverContext, _XSLTContext, _XSLTQuotedStringParam, -_XSLTResultTree, _XSLTProcessingInstruction - - - - -2.3.6 (2012-09-28) - -Features added - - -Bugs fixed - -Passing long Unicode strings into the feed() parser interface -failed to read the entire string. - - - -Other changes - - - -2.3.5 (2012-07-31) - -Features added - - -Bugs fixed - -Crash when merging text nodes in element.remove(). -Crash in sax/target parser when reporting empty doctype. - - - -Other changes - - - -2.3.4 (2012-03-26) - -Features added - - -Bugs fixed - -Crash when building an nsmap (Element property) with empty -namespace URIs. -Crash due to race condition when errors (or user messages) occur -during threaded XSLT processing. -XSLT stylesheet compilation could ignore compilation errors. - - - -Other changes - - - -2.3.3 (2012-01-04) - -Features added - -lxml.html.tostring() gained new serialisation options -with_tail and doctype. - - - -Bugs fixed - -Fixed a crash when using iterparse() for HTML parsing and -requesting start events. -Fixed parsing of more selectors in cssselect. Whitespace before -pseudo-elements and pseudo-classes is significant as it is a -descendant combinator. -"E :pseudo" should parse the same as "E *:pseudo", not "E:pseudo". -Patch by Simon Sapin. -lxml.html.diff no longer raises an exception when hitting -'img' tags without 'src' attribute. - - - -Other changes - - - -2.3.2 (2011-11-11) - -Features added - -lxml.objectify.deannotate() has a new boolean option -cleanup_namespaces to remove the objectify namespace -declarations (and generally clean up the namespace declarations) -after removing the type annotations. -lxml.objectify gained its own SubElement() function as a -copy of etree.SubElement to avoid an otherwise redundant import -of lxml.etree on the user side. - - - -Bugs fixed - -Fixed the "descendant" bug in cssselect a second time (after a first -fix in lxml 2.3.1). The previous change resulted in a serious -performance regression for the XPath based evaluation of the -translated expression. Note that this breaks the usage of some of -the generated XPath expressions as XSLT location paths that -previously worked in 2.3.1. -Fixed parsing of some selectors in cssselect. Whitespace after combinators -">", "+" and "~" is now correctly ignored. Previously is was parsed as -a descendant combinator. For example, "div> .foo" was parsed the same as -"div>* .foo" instead of "div>.foo". Patch by Simon Sapin. - - - -Other changes - - - -2.3.1 (2011-09-25) - -Features added - -New option kill_tags in lxml.html.clean to remove specific -tags and their content (i.e. their whole subtree). -pi.get() and pi.attrib on processing instructions to parse -pseudo-attributes from the text content of processing instructions. -lxml.get_include() returns a list of include paths that can be -used to compile external C code against lxml.etree. This is -specifically required for statically linked lxml builds when code -needs to compile against the exact same header file versions as lxml -itself. -Resolver.resolve_file() takes an additional option -close_file that configures if the file(-like) object will be -closed after reading or not. By default, the file will be closed, -as the user is not expected to keep a reference to it. - - - -Bugs fixed - -HTML cleaning didn't remove 'data:' links. -The html5lib parser integration now uses the 'official' -implementation in html5lib itself, which makes it work with newer -releases of the library. -In lxml.sax, endElementNS() could incorrectly reject a plain -tag name when the corresponding start event inferred the same plain -tag name to be in the default namespace. -When an open file-like object is passed into parse() or -iterparse(), the parser will no longer close it after use. This -reverts a change in lxml 2.3 where all files would be closed. It is -the users responsibility to properly close the file(-like) object, -also in error cases. -Assertion error in lxml.html.cleaner when discarding top-level elements. -In lxml.cssselect, use the xpath 'A//B' (short for -'A/descendant-or-self::node()/B') instead of 'A/descendant::B' for -the css descendant selector ('A B'). This makes a few edge cases -like "div *:last-child" consistent with the selector behavior in -WebKit and Firefox, and makes more css expressions valid location -paths (for use in xsl:template match). -In lxml.html, non-selected <option> tags no longer show up in the -collected form values. -Adding/removing <option> values to/from a multiple select form -field properly selects them and unselects them. - - - -Other changes - -Static builds can specify the download directory with the ---download-dir option. - - - - -2.3 (2011-02-06) - -Features added - -When looking for children, lxml.objectify takes '{}tag' as -meaning an empty namespace, as opposed to the parent namespace. - - - -Bugs fixed - -When finished reading from a file-like object, the parser -immediately calls its .close() method. -When finished parsing, iterparse() immediately closes the input -file. -Work-around for libxml2 bug that can leave the HTML parser in a -non-functional state after parsing a severely broken document (fixed -in libxml2 2.7.8). -marque tag in HTML cleanup code is correctly named marquee. - - - -Other changes - -Some public functions in the Cython-level C-API have more explicit -return types. - - - - -2.3beta1 (2010-09-06) - -Features added - - -Bugs fixed - -Crash in newer libxml2 versions when moving elements between -documents that had attributes on replaced XInclude nodes. -XMLID() function was missing the optional parser and -base_url parameters. -Searching for wildcard tags in iterparse() was broken in Py3. -lxml.html.open_in_browser() didn't work in Python 3 due to the -use of os.tempnam. It now takes an optional 'encoding' parameter. - - - -Other changes - - - -2.3alpha2 (2010-07-24) - -Features added - - -Bugs fixed - -Crash in XSLT when generating text-only result documents with a -stylesheet created in a different thread. - - - -Other changes - -repr() of Element objects shows the hex ID with leading 0x -(following ElementTree 1.3). - - - - -2.3alpha1 (2010-06-19) - -Features added - -Keyword argument namespaces in lxml.cssselect.CSSSelector() -to pass a prefix-to-namespace mapping for the selector. -New function lxml.etree.register_namespace(prefix, uri) that -globally registers a namespace prefix for a namespace that newly -created Elements in that namespace will use automatically. Follows -ElementTree 1.3. -Support 'unicode' string name as encoding parameter in -tostring(), following ElementTree 1.3. -Support 'c14n' serialisation method in ElementTree.write() and -tostring(), following ElementTree 1.3. -The ElementPath expression syntax (el.find*()) was extended to -match the upcoming ElementTree 1.3 that will ship in the standard -library of Python 3.2/2.7. This includes extended support for -predicates as well as namespace prefixes (as known from XPath). -During regular XPath evaluation, various ESXLT functions are -available within their namespace when using libxslt 1.1.26 or later. -Support passing a readily configured logger instance into -PyErrorLog, instead of a logger name. -On serialisation, the new doctype parameter can be used to -override the DOCTYPE (internal subset) of the document. -New parameter output_parent to XSLTExtension.apply_templates() -to append the resulting content directly to an output element. -XSLTExtension.process_children() to process the content of the -XSLT extension element itself. -ISO-Schematron support based on the de-facto Schematron reference -'skeleton implementation'. -XSLT objects now take XPath object as __call__ stylesheet -parameters. -Enable path caching in ElementPath (el.find*()) to avoid parsing -overhead. -Setting the value of a namespaced attribute always uses a prefixed -namespace instead of the default namespace even if both declare the -same namespace URI. This avoids serialisation problems when an -attribute from a default namespace is set on an element from a -different namespace. -XSLT extension elements: support for XSLT context nodes other than -elements: document root, comments, processing instructions. -Support for strings (in addition to Elements) in node-sets returned -by extension functions. -Forms that lack an action attribute default to the base URL of -the document on submit. -XPath attribute result strings have an attrname property. -Namespace URIs get validated against RFC 3986 at the API level -(required by the XML namespace specification). -Target parsers show their target object in the .target property -(compatible with ElementTree). - - - -Bugs fixed - -API is hardened against invalid proxy instances to prevent crashes -due to incorrectly instantiated Element instances. -Prevent crash when instantiating CommentBase and friends. -Export ElementTree compatible XML parser class as -XMLTreeBuilder, as it is called in ET 1.2. -ObjectifiedDataElements in lxml.objectify were not hashable. They -now use the hash value of the underlying Python value (string, -number, etc.) to which they compare equal. -Parsing broken fragments in lxml.html could fail if the fragment -contained an orphaned closing '</div>' tag. -Using XSLT extension elements around the root of the output document -crashed. -lxml.cssselect did not distinguish between x[attr="val"] and -x [attr="val"] (with a space). The latter now matches the -attribute independent of the element. -Rewriting multiple links inside of HTML text content could end up -replacing unrelated content as replacements could impact the -reported position of subsequent matches. Modifications are now -simplified by letting the iterlinks() generator in lxml.html -return links in reversed order if they appear inside the same text -node. Thus, replacements and link-internal modifications no longer -change the position of links reported afterwards. -The .value attribute of textarea elements in lxml.html did -not represent the complete raw value (including child tags etc.). It -now serialises the complete content on read and replaces the -complete content by a string on write. -Target parser didn't call .close() on the target object if -parsing failed. Now it is guaranteed that .close() will be -called after parsing, regardless of the outcome. - - - -Other changes - -Official support for Python 3.1.2 and later. -Static MS Windows builds can now download their dependencies -themselves. -Element.attrib no longer uses a cyclic reference back to its -Element object. It therefore no longer requires the garbage -collector to clean up. -Static builds include libiconv, in addition to libxml2 and libxslt. - - - - -2.2.8 (2010-09-02) - -Bugs fixed - -Crash in newer libxml2 versions when moving elements between -documents that had attributes on replaced XInclude nodes. -Import fix for urljoin in Python 3.1+. - - - - -2.2.7 (2010-07-24) - -Bugs fixed - -Crash in XSLT when generating text-only result documents with a -stylesheet created in a different thread. - - - - -2.2.6 (2010-03-02) - -Bugs fixed - -Fixed several Python 3 regressions by building with Cython 0.11.3. - - - - -2.2.5 (2010-02-28) - -Features added - -Support for running XSLT extension elements on the input root node -(e.g. in a template matching on "/"). - - - -Bugs fixed - -Crash in XPath evaluation when reading smart strings from a document -other than the original context document. -Support recent versions of html5lib by not requiring its -XHTMLParser in htmlparser.py anymore. -Manually instantiating the custom element classes in -lxml.objectify could crash. -Invalid XML text characters were not rejected by the API when they -appeared in unicode strings directly after non-ASCII characters. -lxml.html.open_http_urllib() did not work in Python 3. -The functions strip_tags() and strip_elements() in -lxml.etree did not remove all occurrences of a tag in all cases. -Crash in XSLT extension elements when the XSLT context node is not -an element. - - - - -2.2.4 (2009-11-11) - -Bugs fixed - -Static build of libxml2/libxslt was broken. - - - - -2.2.3 (2009-10-30) - -Features added - - -Bugs fixed - -The resolve_entities option did not work in the incremental feed -parser. -Looking up and deleting attributes without a namespace could hit a -namespaced attribute of the same name instead. -Late errors during calls to SubElement() (e.g. attribute related -ones) could leave a partially initialised element in the tree. -Modifying trees that contain parsed entity references could result -in an infinite loop. -ObjectifiedElement.__setattr__ created an empty-string child element when the -attribute value was rejected as a non-unicode/non-ascii string -Syntax errors in lxml.cssselect could result in misleading error -messages. -Invalid syntax in CSS expressions could lead to an infinite loop in -the parser of lxml.cssselect. -CSS special character escapes were not properly handled in -lxml.cssselect. -CSS Unicode escapes were not properly decoded in lxml.cssselect. -Select options in HTML forms that had no explicit value -attribute were not handled correctly. The HTML standard dictates -that their value is defined by their text content. This is now -supported by lxml.html. -XPath raised a TypeError when finding CDATA sections. This is now -fully supported. -Calling help(lxml.objectify) didn't work at the prompt. -The ElementMaker in lxml.objectify no longer defines the default -namespaces when annotation is disabled. -Feed parser failed to honour the 'recover' option on parse errors. -Diverting the error logging to Python's logging system was broken. - - - -Other changes - - - -2.2.2 (2009-06-21) - -Features added - -New helper functions strip_attributes(), strip_elements(), -strip_tags() in lxml.etree to remove attributes/subtrees/tags -from a subtree. - - - -Bugs fixed - -Namespace cleanup on subtree insertions could result in missing -namespace declarations (and potentially crashes) if the element -defining a namespace was deleted and the namespace was not used by -the top element of the inserted subtree but only in deeper subtrees. -Raising an exception from a parser target callback didn't always -terminate the parser. -Only {true, false, 1, 0} are accepted as the lexical representation for -BoolElement ({True, False, T, F, t, f} not any more), restoring lxml <= 2.0 -behaviour. - - - -Other changes - - - -2.2.1 (2009-06-02) - -Features added - -Injecting default attributes into a document during XML Schema -validation (also at parse time). -Pass huge_tree parser option to disable parser security -restrictions imposed by libxml2 2.7. - - - -Bugs fixed - -The script for statically building libxml2 and libxslt didn't work -in Py3. -XMLSchema() also passes invalid schema documents on to libxml2 -for parsing (which could lead to a crash before release 2.6.24). - - - -Other changes - - - -2.2 (2009-03-21) - -Features added - -Support for standalone flag in XML declaration through -tree.docinfo.standalone and by passing standalone=True/False -on serialisation. - - - -Bugs fixed - -Crash when parsing an XML Schema with external imports from a -filename. - - - - -2.2beta4 (2009-02-27) - -Features added - -Support strings and instantiable Element classes as child arguments -to the constructor of custom Element classes. -GZip compression support for serialisation to files and file-like -objects. - - - -Bugs fixed - -Deep-copying an ElementTree copied neither its sibling PIs and -comments nor its internal/external DTD subsets. -Soupparser failed on broken attributes without values. -Crash in XSLT when overwriting an already defined attribute using -xsl:attribute. -Crash bug in exception handling code under Python 3. This was due -to a problem in Cython, not lxml itself. -lxml.html.FormElement._name() failed for non top-level forms. -TAG special attribute in constructor of custom Element classes -was evaluated incorrectly. - - - -Other changes - -Official support for Python 3.0.1. -Element.findtext() now returns an empty string instead of None -for Elements without text content. - - - - -2.2beta3 (2009-02-17) - -Features added - -XSLT.strparam() class method to wrap quoted string parameters -that require escaping. - - - -Bugs fixed - -Memory leak in XPath evaluators. -Crash when parsing indented XML in one thread and merging it with -other documents parsed in another thread. -Setting the base attribute in lxml.objectify from a unicode -string failed. -Fixes following changes in Python 3.0.1. -Minor fixes for Python 3. - - - -Other changes - -The global error log (which is copied into the exception log) is now -local to a thread, which fixes some race conditions. -More robust error handling on serialisation. - - - - -2.2beta2 (2009-01-25) - -Bugs fixed - -Potential memory leak on exception handling. This was due to a -problem in Cython, not lxml itself. -iter_links (and related link-rewriting functions) in -lxml.html would interpret CSS like url("link") incorrectly -(treating the quotation marks as part of the link). -Failing import on systems that have an io module. - - - - -2.1.5 (2009-01-06) - -Bugs fixed - -Potential memory leak on exception handling. This was due to a -problem in Cython, not lxml itself. -Failing import on systems that have an io module. - - - - -2.2beta1 (2008-12-12) - -Features added - -Allow lxml.html.diff.htmldiff to accept Element objects, not -just HTML strings. - - - -Bugs fixed - -Crash when using an XPath evaluator in multiple threads. -Fixed missing whitespace before Link:... in lxml.html.diff. - - - -Other changes - -Export lxml.html.parse. - - - - -2.1.4 (2008-12-12) - -Bugs fixed - -Crash when using an XPath evaluator in multiple threads. - - - - -2.0.11 (2008-12-12) - -Bugs fixed - -Crash when using an XPath evaluator in multiple threads. - - - - -2.2alpha1 (2008-11-23) - -Features added - -Support for XSLT result tree fragments in XPath/XSLT extension -functions. -QName objects have new properties namespace and localname. -New options for exclusive C14N and C14N without comments. -Instantiating a custom Element classes creates a new Element. - - - -Bugs fixed - -XSLT didn't inherit the parse options of the input document. -0-bytes could slip through the API when used inside of Unicode -strings. -With lxml.html.clean.autolink, links with balanced parenthesis, -that end in a parenthesis, will be linked in their entirety (typical -with Wikipedia links). - - - -Other changes - - - -2.1.3 (2008-11-17) - -Features added - - -Bugs fixed - -Ref-count leaks when lxml enters a try-except statement while an -outside exception lives in sys.exc_*(). This was due to a problem in -Cython, not lxml itself. -Parser Unicode decoding errors could get swallowed by other -exceptions. -Name/import errors in some Python modules. -Internal DTD subsets that did not specify a system or public ID were -not serialised and did not appear in the docinfo property of -ElementTrees. -Fix a pre-Py3k warning when parsing from a gzip file in Py2.6. -Test suite fixes for libxml2 2.7. -Resolver.resolve_string() did not work for non-ASCII byte strings. -Resolver.resolve_file() was broken. -Overriding the parser encoding didn't work for many encodings. - - - -Other changes - - - -2.0.10 (2008-11-17) - -Bugs fixed - -Ref-count leaks when lxml enters a try-except statement while an -outside exception lives in sys.exc_*(). This was due to a problem in -Cython, not lxml itself. - - - - -2.1.2 (2008-09-05) - -Features added - -lxml.etree now tries to find the absolute path name of files when -parsing from a file-like object. This helps custom resolvers when -resolving relative URLs, as lixbml2 can prepend them with the path -of the source document. - - - -Bugs fixed - -Memory problem when passing documents between threads. -Target parser did not honour the recover option and raised an -exception instead of calling .close() on the target. - - - -Other changes - - - -2.0.9 (2008-09-05) - -Bugs fixed - -Memory problem when passing documents between threads. -Target parser did not honour the recover option and raised an -exception instead of calling .close() on the target. - - - - -2.1.1 (2008-07-24) - -Features added - - -Bugs fixed - -Crash when parsing XSLT stylesheets in a thread and using them in -another. -Encoding problem when including text with ElementInclude under -Python 3. - - - -Other changes - - - -2.0.8 (2008-07-24) - -Features added - -lxml.html.rewrite_links() strips links to work around documents -with whitespace in URL attributes. - - - -Bugs fixed - -Crash when parsing XSLT stylesheets in a thread and using them in -another. -CSS selector parser dropped remaining expression after a function -with parameters. - - - -Other changes - - - -2.1 (2008-07-09) - -Features added - -Smart strings can be switched off in XPath (smart_strings -keyword option). -lxml.html.rewrite_links() strips links to work around documents -with whitespace in URL attributes. - - - -Bugs fixed - -Custom resolvers were not used for XMLSchema includes/imports and -XInclude processing. -CSS selector parser dropped remaining expression after a function -with parameters. - - - -Other changes - -objectify.enableRecursiveStr() was removed, use -objectify.enable_recursive_str() instead -Speed-up when running XSLTs on documents from other threads - - - - -2.0.7 (2008-06-20) - -Features added - -Pickling ElementTree objects in lxml.objectify. - - - -Bugs fixed - -Descending dot-separated classes in CSS selectors were not resolved -correctly. -ElementTree.parse() didn't handle target parser result. -Potential threading problem in XInclude. -Crash in Element class lookup classes when the __init__() method of -the super class is not called from Python subclasses. - - - -Other changes - -Non-ASCII characters in attribute values are no longer escaped on -serialisation. - - - - -2.1beta3 (2008-06-19) - -Features added - -Major overhaul of tools/xpathgrep.py script. -Pickling ElementTree objects in lxml.objectify. -Support for parsing from file-like objects that return unicode -strings. -New function etree.cleanup_namespaces(el) that removes unused -namespace declarations from a (sub)tree (experimental). -XSLT results support the buffer protocol in Python 3. -Polymorphic functions in lxml.html that accept either a tree or -a parsable string will return either a UTF-8 encoded byte string, a -unicode string or a tree, based on the type of the input. -Previously, the result was always a byte string or a tree. -Support for Python 2.6 and 3.0 beta. -File name handling now uses a heuristic to convert between byte -strings (usually filenames) and unicode strings (usually URLs). -Parsing from a plain file object frees the GIL under Python 2.x. -Running iterparse() on a plain file (or filename) frees the GIL -on reading under Python 2.x. -Conversion functions html_to_xhtml() and xhtml_to_html() in -lxml.html (experimental). -Most features in lxml.html work for XHTML namespaced tag names -(experimental). - - - -Bugs fixed - -ElementTree.parse() didn't handle target parser result. -Crash in Element class lookup classes when the __init__() method of -the super class is not called from Python subclasses. -A number of problems related to unicode/byte string conversion of -filenames and error messages were fixed. -Building on MacOS-X now passes the "flat_namespace" option to the C -compiler, which reportedly prevents build quirks and crashes on this -platform. -Windows build was broken. -Rare crash when serialising to a file object with certain encodings. - - - -Other changes - -Non-ASCII characters in attribute values are no longer escaped on -serialisation. -Passing non-ASCII byte strings or invalid unicode strings as .tag, -namespaces, etc. will result in a ValueError instead of an -AssertionError (just like the tag well-formedness check). -Up to several times faster attribute access (i.e. tree traversal) in -lxml.objectify. - - - - -2.0.6 (2008-05-31) - -Features added - - -Bugs fixed - -Incorrect evaluation of el.find("tag[child]"). -Windows build was broken. -Moving a subtree from a document created in one thread into a -document of another thread could crash when the rest of the source -document is deleted while the subtree is still in use. -Rare crash when serialising to a file object with certain encodings. - - - -Other changes - -lxml should now build without problems on MacOS-X. - - - - -2.1beta2 (2008-05-02) - -Features added - -All parse functions in lxml.html take a parser keyword argument. -lxml.html has a new parser class XHTMLParser and a module -attribute xhtml_parser that provide XML parsers that are -pre-configured for the lxml.html package. - - - -Bugs fixed - -Moving a subtree from a document created in one thread into a -document of another thread could crash when the rest of the source -document is deleted while the subtree is still in use. -Passing an nsmap when creating an Element will no longer strip -redundantly defined namespace URIs. This prevented the definition -of more than one prefix for a namespace on the same Element. - - - -Other changes - -If the default namespace is redundantly defined with a prefix on the -same Element, the prefix will now be preferred for subelements and -attributes. This allows users to work around a problem in libxml2 -where attributes from the default namespace could serialise without -a prefix even when they appear on an Element with a different -namespace (i.e. they would end up in the wrong namespace). - - - - -2.0.5 (2008-05-01) - -Features added - - -Bugs fixed - -Resolving to a filename in custom resolvers didn't work. -lxml did not honour libxslt's second error state "STOPPED", which -let some XSLT errors pass silently. -Memory leak in Schematron with libxml2 >= 2.6.31. - - - -Other changes - - - -2.1beta1 (2008-04-15) - -Features added - -Error logging in Schematron (requires libxml2 2.6.32 or later). -Parser option strip_cdata for normalising or keeping CDATA -sections. Defaults to True as before, thus replacing CDATA -sections by their text content. -CDATA() factory to wrap string content as CDATA section. - - - -Bugs fixed - -Resolving to a filename in custom resolvers didn't work. -lxml did not honour libxslt's second error state "STOPPED", which -let some XSLT errors pass silently. -Memory leak in Schematron with libxml2 >= 2.6.31. -lxml.etree accepted non well-formed namespace prefix names. - - - -Other changes - -Major cleanup in internal moveNodeToDocument() function, which -takes care of namespace cleanup when moving elements between -different namespace contexts. -New Elements created through the makeelement() method of an HTML -parser or through lxml.html now end up in a new HTML document -(doctype HTML 4.01 Transitional) instead of a generic XML document. -This mostly impacts the serialisation and the availability of a DTD -context. - - - - -2.0.4 (2008-04-13) - -Features added - - -Bugs fixed - -Hanging thread in conjunction with GTK threading. -Crash bug in iterparse when moving elements into other documents. -HTML elements' .cssselect() method was broken. -ElementTree.find*() didn't accept QName objects. - - - -Other changes - - - -2.1alpha1 (2008-03-27) - -Features added - -New event types 'comment' and 'pi' in iterparse(). -XSLTAccessControl instances have a property options that -returns a dict of access configuration options. -Constant instances DENY_ALL and DENY_WRITE on -XSLTAccessControl class. -Extension elements for XSLT (experimental!) -Element.base property returns the xml:base or HTML base URL of -an Element. -docinfo.URL property is writable. - - - -Bugs fixed - -Default encoding for plain text serialisation was different from -that of XML serialisation (UTF-8 instead of ASCII). - - - -Other changes - -Minor API speed-ups. -The benchmark suite now uses tail text in the trees, which makes the -absolute numbers incomparable to previous results. -Generating the HTML documentation now requires Pygments, which is -used to enable syntax highlighting for the doctest examples. - -Most long-time deprecated functions and methods were removed: - -etree.clearErrorLog(), use etree.clear_error_log() - -etree.useGlobalPythonLog(), use -etree.use_global_python_log() - -etree.ElementClassLookup.setFallback(), use -etree.ElementClassLookup.set_fallback() - -etree.getDefaultParser(), use etree.get_default_parser() - -etree.setDefaultParser(), use etree.set_default_parser() - -etree.setElementClassLookup(), use -etree.set_element_class_lookup() -Note that parser.setElementClassLookup() has not been removed -yet, although parser.set_element_class_lookup() should be used -instead. - -xpath_evaluator.registerNamespace(), use -xpath_evaluator.register_namespace() - -xpath_evaluator.registerNamespaces(), use -xpath_evaluator.register_namespaces() - -objectify.setPytypeAttributeTag, use -objectify.set_pytype_attribute_tag - -objectify.setDefaultParser(), use -objectify.set_default_parser() - - - - - -2.0.3 (2008-03-26) - -Features added - -soupparser.parse() allows passing keyword arguments on to -BeautifulSoup. -fromstring() method in lxml.html.soupparser. - - - -Bugs fixed - -lxml.html.diff didn't treat empty tags properly (e.g., -<br>). -Handle entity replacements correctly in target parser. -Crash when using iterparse() with XML Schema validation. -The BeautifulSoup parser (soupparser.py) did not replace entities, -which made them turn up in text content. -Attribute assignment of custom PyTypes in objectify could fail to -correctly serialise the value to a string. - - - -Other changes - -lxml.html.ElementSoup was replaced by a new module -lxml.html.soupparser with a more consistent API. The old module -remains for compatibility with ElementTree's own ElementSoup module. -Setting the XSLT_CONFIG and XML2_CONFIG environment variables at -build time will let setup.py pick up the xml2-config and -xslt-config scripts from the supplied path name. -Passing --with-xml2-config=/path/to/xml2-config to setup.py will -override the xml2-config script that is used to determine the C -compiler options. The same applies for the --with-xslt-config -option. - - - - -2.0.2 (2008-02-22) - -Features added - -Support passing base_url to file parser functions to override -the filename of the file(-like) object. - - - -Bugs fixed - -The prefix for objectify's pytype namespace was missing from the set -of default prefixes. -Memory leak in Schematron (fixed only for libxml2 2.6.31+). -Error type names in RelaxNG were reported incorrectly. -Slice deletion bug fixed in objectify. - - - -Other changes - -Enabled doctests for some Python modules (especially lxml.html). -Add a method argument to lxml.html.tostring() -(method="xml" for XHTML output). -Make it clearer that methods like lxml.html.fromstring() take a -base_url argument. - - - - -2.0.1 (2008-02-13) - -Features added - -Child iteration in lxml.pyclasslookup. -Loads of new docstrings reflect the signature of functions and -methods to make them visible in API docs and help() - - - -Bugs fixed - -The module lxml.html.builder was duplicated as -lxml.htmlbuilder -Form elements would return None for form.fields.keys() if there -was an unnamed input field. Now unnamed input fields are completely -ignored. -Setting an element slice in objectify could insert slice-overlapping -elements at the wrong position. - - - -Other changes - -The generated API documentation was cleaned up and disburdened from -non-public classes etc. -The previously public module lxml.html.setmixin was renamed to -lxml.html._setmixin as it is not an official part of lxml. If -you want to use it, feel free to copy it over to your own source -base. -Passing --with-xslt-config=/path/to/xslt-config to setup.py will -override the xslt-config script that is used to determine the C -compiler options. - - - - -2.0 (2008-02-01) - -Features added - -Passing the unicode type as encoding to tostring() will -serialise to unicode. The tounicode() function is now -deprecated. -XMLSchema() and RelaxNG() can parse from StringIO. -makeparser() function in lxml.objectify to create a new -parser with the usual objectify setup. -Plain ASCII XPath string results are no longer forced into unicode -objects as in 2.0beta1, but are returned as plain strings as before. -All XPath string results are 'smart' objects that have a -getparent() method to retrieve their parent Element. -with_tail option in serialiser functions. -More accurate exception messages in validator creation. -Parse-time XML schema validation (schema parser keyword). -XPath string results of the text() function and attribute -selection make their Element container accessible through a -getparent() method. As a side-effect, they are now always -unicode objects (even ASCII strings). -XSLT objects are usable in any thread - at the cost of a deep -copy if they were not created in that thread. -Invalid entity names and character references will be rejected by -the Entity() factory. -entity.text returns the textual representation of the entity, -e.g. &. -New properties position and code on ParseError exception (as -in ET 1.3) -Rich comparison of element.attrib proxies. -ElementTree compatible TreeBuilder class. -Use default prefixes for some common XML namespaces. -lxml.html.clean.Cleaner now allows for a host_whitelist, and -two overridable methods: allow_embedded_url(el, url) and the -more general allow_element(el). -Extended slicing of Elements as in element[1:-1:2], both in -etree and in objectify -Resolvers can now provide a base_url keyword argument when -resolving a document as string data. -When using lxml.doctestcompare you can give the doctest option -NOPARSE_MARKUP (like # doctest: +NOPARSE_MARKUP) to suppress -the special checking for one test. -Separate feed_error_log property for the feed parser interface. -The normal parser interface and iterparse continue to use -error_log. -The normal parsers and the feed parser interface are now separated -and can be used concurrently on the same parser instance. -fromstringlist() and tostringlist() functions as in -ElementTree 1.3 -iterparse() accepts an html boolean keyword argument for -parsing with the HTML parser (note that this interface may be -subject to change) -Parsers accept an encoding keyword argument that overrides the encoding -of the parsed documents. -New C-API function hasChild() to test for children -annotate() function in objectify can annotate with Python types and XSI -types in one step. Accompanied by xsiannotate() and pyannotate(). -ET.write(), tostring() and tounicode() now accept a keyword -argument method that can be one of 'xml' (or None), 'html' or 'text' to -serialise as XML, HTML or plain text content. -iterfind() method on Elements returns an iterator equivalent to -findall() -itertext() method on Elements -Setting a QName object as value of the .text property or as an attribute -will resolve its prefix in the respective context -ElementTree-like parser target interface as described in -http://effbot.org/elementtree/elementtree-xmlparser.htm -ElementTree-like feed parser interface on XMLParser and HTMLParser -(feed() and close() methods) -Reimplemented objectify.E for better performance and improved -integration with objectify. Provides extended type support based on -registered PyTypes. -XSLT objects now support deep copying -New makeSubElement() C-API function that allows creating a new -subelement straight with text, tail and attributes. -XPath extension functions can now access the current context node -(context.context_node) and use a context dictionary -(context.eval_context) from the context provided in their first -parameter -HTML tag soup parser based on BeautifulSoup in lxml.html.ElementSoup -New module lxml.doctestcompare by Ian Bicking for writing simplified -doctests based on XML/HTML output. Use by importing lxml.usedoctest or -lxml.html.usedoctest from within a doctest. -New module lxml.cssselect by Ian Bicking for selecting Elements with CSS -selectors. -New package lxml.html written by Ian Bicking for advanced HTML -treatment. -Namespace class setup is now local to the ElementNamespaceClassLookup -instance and no longer global. -Schematron validation (incomplete in libxml2) -Additional stringify argument to objectify.PyType() takes a -conversion function to strings to support setting text values from arbitrary -types. -Entity support through an Entity factory and element classes. XML -parsers now have a resolve_entities keyword argument that can be set to -False to keep entities in the document. -column field on error log entries to accompany the line field -Error specific messages in XPath parsing and evaluation -NOTE: for evaluation errors, you will now get an XPathEvalError instead of -an XPathSyntaxError. To catch both, you can except on XPathError -The regular expression functions in XPath now support passing a node-set -instead of a string -Extended type annotation in objectify: new xsiannotate() function -EXSLT RegExp support in standard XPath (not only XSLT) - - - -Bugs fixed - -Missing import in lxml.html.clean. -Some Python 2.4-isms prevented lxml from building/running under -Python 2.3. -XPath on ElementTrees could crash when selecting the virtual root -node of the ElementTree. -Compilation --without-threading was buggy in alpha5/6. -Memory leak in the parse() function. -Minor bugs in XSLT error message formatting. -Result document memory leak in target parser. -Target parser failed to report comments. -In the lxml.html iter_links method, links in <object> -tags weren't recognized. (Note: plugin-specific link parameters -still aren't recognized.) Also, the <embed> tag, though not -standard, is now included in lxml.html.defs.special_inline_tags. -Using custom resolvers on XSLT stylesheets parsed from a string -could request ill-formed URLs. -With lxml.doctestcompare if you do <tag xmlns="..."> in your -output, it will then be namespace-neutral (before the ellipsis was -treated as a real namespace). -AttributeError in feed parser on parse errors -XML feed parser setup problem -Type annotation for unicode strings in DataElement() -lxml failed to serialise namespace declarations of elements other than the -root node of a tree -Race condition in XSLT where the resolver context leaked between concurrent -XSLT calls -lxml.etree did not check tag/attribute names -The XML parser did not report undefined entities as error -The text in exceptions raised by XML parsers, validators and XPath -evaluators now reports the first error that occurred instead of the last -Passing '' as XPath namespace prefix did not raise an error -Thread safety in XPath evaluators - - - -Other changes - -Exceptions carry only the part of the error log that is related to -the operation that caused the error. -XMLSchema() and RelaxNG() now enforce passing the source -file/filename through the file keyword argument. -The test suite now skips most doctests under Python 2.3. -make clean no longer removes the .c files (use make -realclean instead) -Minor performance tweaks for Element instantiation and subelement -creation -Various places in the XPath, XSLT and iteration APIs now require -keyword-only arguments. -The argument order in element.itersiblings() was changed to -match the order used in all other iteration methods. The second -argument ('preceding') is now a keyword-only argument. -The getiterator() method on Elements and ElementTrees was -reverted to return an iterator as it did in lxml 1.x. The ET API -specification allows it to return either a sequence or an iterator, -and it traditionally returned a sequence in ET and an iterator in -lxml. However, it is now deprecated in favour of the iter() -method, which should be used in new code wherever possible. -The 'pretty printed' serialisation of ElementTree objects now -inserts newlines at the root level between processing instructions, -comments and the root tag. -A 'pretty printed' serialisation is now terminated with a newline. -Second argument to lxml.etree.Extension() helper is no longer -required, third argument is now a keyword-only argument ns. -lxml.html.tostring takes an encoding argument. -The module source files were renamed to "lxml.*.pyx", such as -"lxml.etree.pyx". This was changed for consistency with the way -Pyrex commonly handles package imports. The main effect is that -classes now know about their fully qualified class name, including -the package name of their module. -Keyword-only arguments in some API functions, especially in the -parsers and serialisers. -Tag name validation in lxml.etree (and lxml.html) now distinguishes -between HTML tags and XML tags based on the parser that was used to -parse or create them. HTML tags no longer reject any non-ASCII -characters in tag names but only spaces and the special characters -<>&/"'. -lxml.etree now emits a warning if you use XPath with libxml2 2.6.27 -(which can crash on certain XPath errors) -Type annotation in objectify now preserves the already annotated type by -default to prevent losing type information that is already there. -element.getiterator() returns a list, use element.iter() to retrieve -an iterator (ElementTree 1.3 compatible behaviour) -objectify.PyType for None is now called "NoneType" -el.getiterator() renamed to el.iter(), following ElementTree 1.3 - -original name is still available as alias -In the public C-API, findOrBuildNodeNs() was replaced by the more -generic findOrBuildNodeNsPrefix -Major refactoring in XPath/XSLT extension function code -Network access in parsers disabled by default - - - - -1.3.6 (2007-10-29) - -Bugs fixed - -Backported decref crash fix from 2.0 -Well hidden free-while-in-use crash bug in ObjectPath - - - -Other changes - -The test suites now run gc.collect() in the tearDown() -methods. While this makes them take a lot longer to run, it also -makes it easier to link a specific test to garbage collection -problems that would otherwise appear in later tests. - - - - -1.3.5 (2007-10-22) - -Features added - - -Bugs fixed - -lxml.etree could crash when adding more than 10000 namespaces to a -document -lxml failed to serialise namespace declarations of elements other -than the root node of a tree - - - - -1.3.4 (2007-08-30) - -Features added - -The ElementMaker in lxml.builder now accepts the keyword arguments -namespace and nsmap to set a namespace and nsmap for the Elements it -creates. -The docinfo on ElementTree objects has new properties internalDTD -and externalDTD that return a DTD object for the internal or external -subset of the document respectively. -Serialising an ElementTree now includes any internal DTD subsets that are -part of the document, as well as comments and PIs that are siblings of the -root node. - - - -Bugs fixed - -Parsing with the no_network option could fail - - - -Other changes - -lxml now raises a TagNameWarning about tag names containing ':' instead of -an Error as 1.3.3 did. The reason is that a number of projects currently -misuse the previous lack of tag name validation to generate namespace -prefixes without declaring namespaces. Apart from the danger of generating -broken XML this way, it also breaks most of the namespace-aware tools in -XML, including XPath, XSLT and validation. lxml 1.3.x will continue to -support this bug with a Warning, while lxml 2.0 will be strict about -well-formed tag names (not only regarding ':'). -Serialising an Element no longer includes its comment and PI siblings (only -ElementTree serialisation includes them). - - - - -1.3.3 (2007-07-26) - -Features added - -ElementTree compatible parser ETCompatXMLParser strips processing -instructions and comments while parsing XML -Parsers now support stripping PIs (keyword argument 'remove_pis') -etree.fromstring() now supports parsing both HTML and XML, depending on -the parser you pass. -Support base_url keyword argument in HTML() and XML() - - - -Bugs fixed - -Parsing from Python Unicode strings failed on some platforms -Element() did not raise an exception on tag names containing ':' -Element.getiterator(tag) did not accept Comment and -ProcessingInstruction as tags. It also accepts Element now. - - - - -1.3.2 (2007-07-03) - -Features added - - -Bugs fixed - -"deallocating None" crash bug - - - - -1.3.1 (2007-07-02) - -Features added - -objectify.DataElement now supports setting values from existing data -elements (not just plain Python types) and reuses defined namespaces etc. -E-factory support for lxml.objectify (objectify.E) - - - -Bugs fixed - -Better way to prevent crashes in Element proxy cleanup code -objectify.DataElement didn't set up None value correctly -objectify.DataElement didn't check the value against the provided type hints -Reference-counting bug in Element.attrib.pop() - - - - -1.3 (2007-06-24) - -Features added - -Module lxml.pyclasslookup module implements an Element class lookup -scheme that can access the entire tree in read-only mode to help determining -a suitable Element class -Parsers take a remove_comments keyword argument that skips over comments -parse() function in objectify, corresponding to XML() etc. -Element.addnext(el) and Element.addprevious(el) methods to support -adding processing instructions and comments around the root node -Element.attrib was missing clear() and pop() methods -Extended type annotation in objectify: cleaner annotation namespace setup -plus new deannotate() function -Support for custom Element class instantiation in lxml.sax: passing a -makeelement function to the ElementTreeContentHandler will reuse the -lookup context of that function -'.' represents empty ObjectPath (identity) -Element.values() to accompany the existing .keys() and .items() -collectAttributes() C-function to build a list of attribute -keys/values/items for a libxml2 node -DTD validator class (like RelaxNG and XMLSchema) -HTML generator helpers by Fredrik Lundh in lxml.htmlbuilder -ElementMaker XML generator by Fredrik Lundh in lxml.builder.E -Support for pickeling objectify.ObjectifiedElement objects to XML -update() method on Element.attrib -Optimised replacement for libxml2's _xmlReconsiliateNs(). This allows lxml -a better handling of namespaces when moving elements between documents. - - - -Bugs fixed - -Removing Elements from a tree could make them lose their namespace -declarations -ElementInclude didn't honour base URL of original document -Replacing the children slice of an Element would cut off the tails of the -original children -Element.getiterator(tag) did not accept Comment and -ProcessingInstruction as tags -API functions now check incoming strings for XML conformity. Zero bytes or -low ASCII characters are no longer accepted (AssertionError). -XSLT parsing failed to pass resolver context on to imported documents -passing '' as namespace prefix in nsmap could be passed through to libxml2 -Objectify couldn't handle prefixed XSD type names in xsi:type -More ET compatible behaviour when writing out XML declarations or not -More robust error handling in iterparse() -Documents lost their top-level PIs and comments on serialisation -lxml.sax failed on comments and PIs. Comments are now properly ignored and -PIs are copied. -Possible memory leaks in namespace handling when moving elements between -documents - - - -Other changes - -major restructuring in the documentation - - - - -1.2.1 (2007-02-27) - -Bugs fixed - -Build fixes for MS compiler -Item assignments to special names like element["text"] failed -Renamed ObjectifiedDataElement.__setText() to _setText() to make it easier -to access -The pattern for attribute names in ObjectPath was too restrictive - - - - -1.2 (2007-02-20) - -Features added - -Rich comparison of QName objects -Support for regular expressions in benchmark selection -get/set emulation (not .attrib!) for attributes on processing instructions -ElementInclude Python module for ElementTree compatible XInclude processing -that honours custom resolvers registered with the source document -ElementTree.parser property holds the parser used to parse the document -setup.py has been refactored for greater readability and flexibility ---rpath flag to setup.py to induce automatic linking-in of dynamic library -runtime search paths has been renamed to --auto-rpath. This makes it -possible to pass an --rpath directly to distutils; previously this was being -shadowed. - - - -Bugs fixed - -Element instantiation now uses locks to prevent race conditions with threads -ElementTree.write() did not raise an exception when the file was not writable -Error handling could crash under Python <= 2.4.1 - fixed by disabling thread -support in these environments -Element.find*() did not accept QName objects as path - - - -Other changes - -code cleanup: redundant _NodeBase super class merged into _Element class -Note: although the impact should be zero in most cases, this change breaks -the compatibility of the public C-API - - - - -1.1.2 (2006-10-30) - -Features added - -Data elements in objectify support repr(), which is now used by dump() -Source distribution now ships with a patched Pyrex -New C-API function makeElement() to create new elements with text, -tail, attributes and namespaces -Reuse original parser flags for XInclude -Simplified support for handling XSLT processing instructions - - - -Bugs fixed - -Parser resources were not freed before the next parser run -Open files and XML strings returned by Python resolvers were not -closed/freed -Crash in the IDDict returned by XMLDTDID -Copying Comments and ProcessingInstructions failed -Memory leak for external URLs in _XSLTProcessingInstruction.parseXSL() -Memory leak when garbage collecting tailed root elements -HTML script/style content was not propagated to .text -Show text xincluded between text nodes correctly in .text and .tail -'integer * objectify.StringElement' operation was not supported - - - - -1.1.1 (2006-09-21) - -Features added - -XSLT profiling support (profile_run keyword) -countchildren() method on objectify.ObjectifiedElement -Support custom elements for tree nodes in lxml.objectify - - - -Bugs fixed - -lxml.objectify failed to support long data values (e.g., "123L") -Error messages from XSLT did not reach XSLT.error_log -Factories objectify.Element() and objectify.DataElement() were missing -attrib and nsmap keyword arguments -Changing the default parser in lxml.objectify did not update the factories -Element() and DataElement() -Let lxml.objectify.Element() always generate tree elements (not data -elements) -Build under Windows failed ('0' bug in patched Pyrex version) - - - - -1.1 (2006-09-13) - -Features added - -Comments and processing instructions return '' and -'<?pi-target content?>' for repr() -Parsers are now the preferred (and default) place where element class lookup -schemes should be registered. Namespace lookup is no longer supported by -default. -Support for Python 2.5 beta -Unlock the GIL for deep copying documents and for XPath() -New compact keyword argument for parsing read-only documents -Support for parser options in iterparse() -The namespace axis is supported in XPath and returns (prefix, URI) -tuples -The XPath expression "/" now returns an empty list instead of raising an -exception -XML-Object API on top of lxml (lxml.objectify) -Customizable Element class lookup: -different pre-implemented lookup mechanisms -support for externally provided lookup functions - - -Support for processing instructions (ET-like, not compatible) -Public C-level API for independent extension modules -Module level iterwalk() function as 'iterparse' for trees -Module level iterparse() function similar to ElementTree (see -documentation for differences) -Element.nsmap property returns a mapping of all namespace prefixes known at -the Element to their namespace URI -Reentrant threading support in RelaxNG, XMLSchema and XSLT -Threading support in parsers and serializers: -All in-memory operations (tostring, parse(StringIO), etc.) free the GIL -File operations (on file names) free the GIL -Reading from file-like objects frees the GIL and reacquires it for reading -Serialisation to file-like objects is single-threaded (high lock overhead) - - -Element iteration over XPath axes: -Element.iterdescendants() iterates over the descendants of an element -Element.iterancestors() iterates over the ancestors of an element (from -parent to parent) -Element.itersiblings() iterates over either the following or preceding -siblings of an element -Element.iterchildren() iterates over the children of an element in either -direction -All iterators support the tag keyword argument to restrict the -generated elements - - -Element.getnext() and Element.getprevious() return the direct siblings of an -element - - - -Bugs fixed - -filenames with local 8-bit encoding were not supported -1.1beta did not compile under Python 2.3 -ignore unknown 'pyval' attribute values in objectify -objectify.ObjectifiedElement.addattr() failed to accept Elements and Lists -objectify.ObjectPath.setattr() failed to accept Elements and Lists -XPathSyntaxError now inherits from XPathError -Threading race conditions in RelaxNG and XMLSchema -Crash when mixing elements from XSLT results into other trees, concurrent -XSLT is only allowed when the stylesheet was parsed in the main thread -The EXSLT regexp:match function now works as defined (except for some -differences in the regular expression syntax) -Setting element.text to '' returned None on request, not the empty string -iterparse() could crash on long XML files -Creating documents no longer copies the parser for later URL resolving. For -performance reasons, only a reference is kept. Resolver updates on the -parser will now be reflected by documents that were parsed before the -change. Although this should rarely become visible, it is a behavioral -change from 1.0. - - - - -1.0.4 (2006-09-09) - -Features added - -List-like Element.extend() method - - - -Bugs fixed - -Crash in tail handling in Element.replace() - - - - -1.0.3 (2006-08-08) - -Features added - -Element.replace(old, new) method to replace a subelement by another one - - - -Bugs fixed - -Crash when mixing elements from XSLT results into other trees -Copying/deepcopying did not work for ElementTree objects -Setting an attribute to a non-string value did not raise an exception -Element.remove() deleted the tail text from the removed Element - - - - -1.0.2 (2006-06-27) - -Features added - -Support for setting a custom default Element class as opposed to namespace -specific classes (which still override the default class) - - - -Bugs fixed - -Rare exceptions in Python list functions were not handled -Parsing accepted unicode strings with XML encoding declaration in certain -cases -Parsing 8-bit encoded strings from StringIO objects raised an exception -Module function initThread() was removed - useless (and never worked) -XSLT and parser exception messages include the error line number - - - - -1.0.1 (2006-06-09) - -Features added - -Repeated calls to Element.attrib now efficiently return the same instance - - - -Bugs fixed - -Document deallocation could crash in certain garbage collection scenarios -Extension function calls in XSLT variable declarations could break the -stylesheet and crash on repeated calls -Deep copying Elements could lose namespaces declared in parents -Deep copying Elements did not copy tail -Parsing file(-like) objects failed to load external entities -Parsing 8-bit strings from file(-like) objects raised an exception -xsl:include failed when the stylesheet was parsed from a file-like object -lxml.sax.ElementTreeProducer did not call startDocument() / endDocument() -MSVC compiler complained about long strings (supports only 2048 bytes) - - - - -1.0 (2006-06-01) - -Features added - -Element.getiterator() and the findall() methods support finding arbitrary -elements from a namespace (pattern {namespace}*) -Another speedup in tree iteration code -General speedup of Python Element object creation and deallocation -Writing C14N no longer serializes in memory (reduced memory footprint) -PyErrorLog for error logging through the Python logging module -Element.getroottree() returns an ElementTree for the root node of the -document that contains the element. -ElementTree.getpath(element) returns a simple, absolute XPath expression to -find the element in the tree structure -Error logs have a last_error attribute for convenience -Comment texts can be changed through the API -Formatted output via pretty_print keyword in serialization functions -XSLT can block access to file system and network via XSLTAccessControl -ElementTree.write() no longer serializes in memory (reduced memory -footprint) -Speedup of Element.findall(tag) and Element.getiterator(tag) -Support for writing the XML representation of Elements and ElementTrees to -Python unicode strings via etree.tounicode() -Support for writing XSLT results to Python unicode strings via unicode() -Parsing a unicode string no longer copies the string (reduced memory -footprint) -Parsing file-like objects reads chunks rather than the whole file (reduced -memory footprint) -Parsing StringIO objects from the start avoids copying the string (reduced -memory footprint) -Read-only 'docinfo' attribute in ElementTree class holds DOCTYPE -information, original encoding and XML version as seen by the parser -etree module can be compiled without libxslt by commenting out the line -include "xslt.pxi" near the end of the etree.pyx source file -Better error messages in parser exceptions -Error reporting also works in XSLT -Support for custom document loaders (URI resolvers) in parsers and XSLT, -resolvers are registered at parser level -Implementation of exslt:regexp for XSLT based on the Python 're' module, -enabled by default, can be switched off with 'regexp=False' keyword argument -Support for exslt extensions (libexslt) and libxslt extra functions -(node-set, document, write, output) -Substantial speedup in XPath.evaluate() -HTMLParser for parsing (broken) HTML -XMLDTDID function parses XML into tuple (root node, ID dict) based on xml:id -implementation of libxml2 (as opposed to ET compatible XMLID) - - - -Bugs fixed - -Memory leak in Element.__setitem__ -Memory leak in Element.attrib.items() and Element.attrib.values() -Memory leak in XPath extension functions -Memory leak in unicode related setup code -Element now raises ValueError on empty tag names -Namespace fixing after moving elements between documents could fail if the -source document was freed too early -Setting namespace-less tag names on namespaced elements ('{ns}t' -> 't') -didn't reset the namespace -Unknown constants from newer libxml2 versions could raise exceptions in the -error handlers -lxml.etree compiles much faster -On libxml2 <= 2.6.22, parsing strings with encoding declaration could fail -in certain cases -Document reference in ElementTree objects was not updated when the root -element was moved to a different document -Running absolute XPath expressions on an Element now evaluates against the -root tree -Evaluating absolute XPath expressions (/*) on an ElementTree could fail -Crashes when calling XSLT, RelaxNG, etc. with uninitialized ElementTree -objects -Removed public function initThreadLogging(), replaced by more general -initThread() which fixes a number of setup problems in threads -Memory leak when using iconv encoders in tostring/write -Deep copying Elements and ElementTrees maintains the document information -Serialization functions raise LookupError for unknown encodings -Memory deallocation crash resulting from deep copying elements -Some ElementTree methods could crash if the root node was not initialized -(neither file nor element passed to the constructor) -Element/SubElement failed to set attribute namespaces from passed attrib -dictionary -tostring() adds an XML declaration for non-ASCII encodings -tostring() failed to serialize encodings that contain 0-bytes -ElementTree.xpath() and XPathDocumentEvaluator were not using the -ElementTree root node as reference point -Calling document('') in XSLT failed to return the stylesheet - - - - -0.9.2 (2006-05-10) - -Features added - -Speedup for Element.makeelement(): the new element reuses the original -libxml2 document instead of creating a new empty one -Speedup for reversed() iteration over element children (Py2.4+ only) -ElementTree compatible QName class -RelaxNG and XMLSchema accept any Element, not only ElementTrees - - - -Bugs fixed - -str(xslt_result) was broken for XSLT output other than UTF-8 -Memory leak if write_c14n fails to write the file after conversion -Crash in XMLSchema and RelaxNG when passing non-schema documents -Memory leak in RelaxNG() when RelaxNGParseError is raised - - - - -0.9.1 (2006-03-30) - -Features added - -lxml.sax.ElementTreeContentHandler checks closing elements and raises -SaxError on mismatch -lxml.sax.ElementTreeContentHandler supports namespace-less SAX events -(startElement, endElement) and defaults to empty attributes (keyword -argument) -Speedup for repeatedly accessing element tag names -Minor API performance improvements - - - -Bugs fixed - -Memory deallocation bug when using XSLT output method "html" -sax.py was handling UTF-8 encoded tag names where it shouldn't -lxml.tests package will no longer be installed (is still in source tar) - - - - -0.9 (2006-03-20) - -Features added - -Error logging API for libxml2 error messages -Various performance improvements -Benchmark script for lxml, ElementTree and cElementTree -Support for registering extension functions through new FunctionNamespace -class (see doc/extensions.txt) -ETXPath class for XPath expressions in ElementTree notation ('//{ns}tag') -Support for variables in XPath expressions (also in XPath class) -XPath class for compiled XPath expressions -XMLID module level function (ElementTree compatible) -XMLParser API for customized libxml2 parser configuration -Support for custom Element classes through new Namespace API (see -doc/namespace_extensions.txt) -Common exception base class LxmlError for module exceptions -real iterator support in iter(Element), Element.getiterator() -XSLT objects are callable, result trees support str() -Added MANIFEST.in for easier creation of RPM files. -'getparent' method on elements allows navigation to an element's -parent element. -Python core compatible SAX tree builder and SAX event generator. See -doc/sax.txt for more information. - - - -Bugs fixed - -Segfaults and memory leaks in various API functions of Element -Segfault in XSLT.tostring() -ElementTree objects no longer interfere, Elements can be root of different -ElementTrees at the same time -document('') works in XSLT documents read from files (in-memory documents -cannot support this due to libxslt deficiencies) - - - - -0.8 (2005-11-03) - -Features added - -Support for copy.deepcopy() on elements. copy.copy() works also, but -does the same thing, and does not create a shallow copy, as that -makes no sense in the context of libxml2 trees. This means a -potential incompatibility with ElementTree, but there's more chance -that it works than if copy.copy() isn't supported at all. -Increased compatibility with (c)ElementTree; .parse() on ElementTree is -supported and parsing of gzipped XML files works. -implemented index() on elements, allowing one to find the index of a -SubElement. - - - -Bugs fixed - -Use xslt-config instead of xml2-config to find out libxml2 -directories to take into account a case where libxslt is installed -in a different directory than libxslt. -Eliminate crash condition in iteration when text nodes are changed. -Passing 'None' to tostring() does not result in a segfault anymore, -but an AssertionError. -Some test fixes for Windows. -Raise XMLSyntaxError and XPathSyntaxError instead of plain python -syntax errors. This should be less confusing. -Fixed error with uncaught exception in Pyrex code. -Calling lxml.etree.fromstring('') throws XMLSyntaxError instead of a -segfault. -has_key() works on attrib. 'in' tests also work correctly on attrib. -INSTALL.txt was saying 2.2.16 instead of 2.6.16 as a supported -libxml2 version, as it should. -Passing a UTF-8 encoded string to the XML() function would fail; -fixed. - - - - -0.7 (2005-06-15) - -Features added - -parameters (XPath expressions) can be passed to XSLT using keyword -parameters. -Simple XInclude support. Calling the xinclude() method on a tree -will process any XInclude statements in the document. -XMLSchema support. Use the XMLSchema class or the convenience -xmlschema() method on a tree to do XML Schema (XSD) validation. -Added convenience xslt() method on tree. This is less efficient -than the XSLT object, but makes it easier to write quick code. -Added convenience relaxng() method on tree. This is less efficient -than the RelaxNG object, but makes it easier to write quick code. -Make it possible to use XPathEvaluator with elements as well. The -XPathEvaluator in this case will retain the element so multiple -XPath queries can be made against one element efficiently. This -replaces the second argument to the .evaluate() method that existed -previously. -Allow registerNamespace() to be called on an XPathEvaluator, after -creation, to add additional namespaces. Also allow registerNamespaces(), -which does the same for a namespace dictionary. -Add 'prefix' attribute to element to be able to read prefix information. -This is entirely read-only. -It is possible to supply an extra nsmap keyword parameter to -the Element() and SubElement() constructors, which supplies a -prefix to namespace URI mapping. This will create namespace -prefix declarations on these elements and these prefixes will show up -in XML serialization. - - - -Bugs fixed - -Killed yet another memory management related bug: trees created -using newDoc would not get a libxml2-level dictionary, which caused -problems when deallocating these documents later if they contained a -node that came from a document with a dictionary. -Moving namespaced elements between documents was problematic as -references to the original document would remain. This has been fixed -by applying xmlReconciliateNs() after each move operation. -Can pass None to 'dump()' without segfaults. -tostring() works properly for non-root elements as well. -Cleaned out the tostring() method so it should handle encoding -correctly. -Cleaned out the ElementTree.write() method so it should handle encoding -correctly. Writing directly to a file should also be faster, as there is no -need to go through a Python string in that case. Made sure the test cases -test both serializing to StringIO as well as serializing to a real file. - - - - -0.6 (2005-05-14) - -Features added - -Changed setup.py so that library_dirs is also guessed. This should -help with compilation on the Mac OS X platform, where otherwise the -wrong library (shipping with the OS) could be picked up. -Tweaked setup.py so that it picks up the version from version.txt. - - - -Bugs fixed - -Do the right thing when handling namespaced attributes. -fix bug where tostring() moved nodes into new documents. tostring() -had very nasty side-effects before this fix, sorry! - - - - -0.5.1 (2005-04-09) - -Python 2.2 compatibility fixes. -unicode fixes in Element() and Comment() as well as XML(); unicode -input wasn't properly being UTF-8 encoded. - - - -0.5 (2005-04-08) -Initial public release. - - - - -Generated on: 2017-01-08. - - - - diff --git a/doc/html/changes-3.7.3.html b/doc/html/changes-3.7.3.html new file mode 100644 index 00000000..d05174b0 --- /dev/null +++ b/doc/html/changes-3.7.3.html @@ -0,0 +1,3180 @@ + + + + + + +lxml changelog + + + + +lxml changelog + + +3.7.3 (2017-02-18) + +Bugs fixed + +GH#218 was ineffective in Python 3. +GH#222: lxml.html.submit_form() failed in Python 3. +Patch by Jakub Wilk. + + + + +3.7.2 (2017-01-08) + +GH#220: xmlfile allows switching output methods at an element level. +Patch by Burak Arslan. + + +Bugs fixed + +Work around installation problems in recent Python 2.7 versions +due to FTP download failures. +GH#219: xmlfile.element() was not properly quoting attribute values. +Patch by Burak Arslan. +GH#218: xmlfile.element() was not properly escaping text content of +script/style tags. Patch by Burak Arslan. + + + + +3.7.1 (2016-12-23) + +No source changes, issued only to solve problems with the +binary packages released for 3.7.0. + + + +3.7.0 (2016-12-10) + +Features added + +GH#217: XMLSyntaxError now behaves more like its SyntaxError +baseclass. Patch by Philipp A. +GH#216: HTMLParser() now supports the same collect_ids parameter +as XMLParser(). Patch by Burak Arslan. +GH#210: Allow specifying a serialisation method in xmlfile.write(). +Patch by Burak Arslan. +GH#203: New option default_doctype in HTMLParser that allows +disabling the automatic doctype creation. Patch by Shadab Zafar. +GH#201: Calling the method .set('attrname') without value argument +(or None) on HTML elements creates an attribute without value that +serialises like <div attrname></div>. Patch by Daniel Holth. +GH#197: Ignore form input fields in form_values() when they are +marked as disabled in HTML. Patch by Kristian Klemon. + + + +Bugs fixed + +GH#206: File name and line number were missing from XSLT error messages. +Patch by Marcus Brinkmann. + + + +Other changes + +Log entries no longer allow anything but plain string objects as message text +and file name. +zlib is included in the list of statically built libraries. + + + + +3.6.4 (2016-08-20) + +GH#204, LP#1614693: build fix for MacOS-X. + + + +3.6.3 (2016-08-18) + +LP#1614603: change linker flags to build multi-linux wheels + + + +3.6.2 (2016-08-18) + +LP#1614603: release without source changes to provide cleanly built Linux wheels + + + +3.6.1 (2016-07-24) + +Features added + +GH#180: Separate option inline_style for Cleaner that only removes style +attributes instead of all styles. Patch by Christian Pedersen. +GH#196: Windows build support for Python 3.5. Contribution by Maximilian Hils. + + + +Bugs fixed + +GH#199: Exclude file fields from FormElement.form_values (as browsers do). +Patch by Tomas Divis. +GH#198, LP#1568167: Try to provide base URL from Resolver.resolve_string(). +Patch by Michael van Tellingen. +GH#191: More accurate float serialisation in objectify.FloatElement. +Patch by Holger Joukl. +LP#1551797: Repair XSLT error logging. Patch by Marcus Brinkmann. + + + + +3.6.0 (2016-03-17) + +Features added + +GH#187: Now supports (only) version 5.x and later of PyPy. +Patch by Armin Rigo. +GH#181: Direct support for .rnc files in RelaxNG() if rnc2rng +is installed. Patch by Dirkjan Ochtman. + + + +Bugs fixed + +GH#189: Static builds honour FTP proxy configurations when downloading +the external libs. Patch by Youhei Sakurai. +GH#186: Soupparser failed to process entities in Python 3.x. +Patch by Duncan Morris. +GH#185: Rare encoding related TypeError on import was fixed. +Patch by Petr Demin. + + + + +3.5.0 (2015-11-13) + +Bugs fixed + +Unicode string results failed XPath queries in PyPy. +LP#1497051: HTML target parser failed to terminate on exceptions +and continued parsing instead. +Deprecated API usage in doctestcompare. + + + + +3.5.0b1 (2015-09-18) + +Features added + +cleanup_namespaces() accepts a new argument keep_ns_prefixes +that does not remove definitions of the provided prefix-namespace +mapping from the tree. +cleanup_namespaces() accepts a new argument top_nsmap that +moves definitions of the provided prefix-namespace mapping to the +top of the tree. +LP#1490451: Element objects gained a cssselect() method as +known from lxml.html. Patch by Simon Sapin. +API functions and methods behave and look more like Python functions, +which allows introspection on them etc. One side effect to be aware of +is that the functions now bind as methods when assigned to a class +variable. A quick fix is to wrap them in staticmethod() (as for +normal Python functions). +ISO-Schematron support gained an option error_finder that allows +passing a filter function for picking validation errors from reports. +LP#1243600: Elements in lxml.html gained a classes property +that provides a set-like interface to the class attribute. +Original patch by masklinn. +LP#1341964: The soupparser now handles DOCTYPE declarations, comments +and processing instructions outside of the root element. +Patch by Olli Pottonen. +LP#1421512: The docinfo of a tree was made editable to allow +setting and removing the public ID and system ID of the DOCTYPE. +Patch by Olli Pottonen. +LP#1442427: More work-arounds for quirks and bugs in pypy and pypy3. +lxml.html.soupparser now uses BeautifulSoup version 4 instead +of version 3 if available. + + + +Bugs fixed + +Memory errors that occur during tree adaptations (e.g. moving subtrees +to foreign documents) could leave the tree in a crash prone state. +Calling process_children() in an XSLT extension element without +an output_parent argument failed with a TypeError. +Fix by Jens TrÃ¶ger. +GH#162: Image data in HTML data URLs is considered safe and +no longer removed by lxml.html.clean JavaScript cleaner. +GH#166: Static build could link libraries in wrong order. +GH#172: Rely a bit more on libxml2 for encoding detection rather than +rolling our own in some cases. Patch by Olli Pottonen. +GH#159: Validity checks for names and string content were tightened +to detect the use of illegal characters early. Patch by Olli Pottonen. +LP#1421921: Comments/PIs before the DOCTYPE declaration were not +serialised. Patch by Olli Pottonen. +LP#659367: Some HTML DOCTYPE declarations were not serialised. +Patch by Olli Pottonen. +LP#1238503: lxml.doctestcompare is now consistent with stdlib's doctest +in how it uses + and - to refer to unexpected and missing output. +Empty prefixes are explicitly rejected when a namespace mapping is used +with ElementPath to avoid hiding bugs in user code. +Several problems with PyPy were fixed by switching to Cython 0.23. + + + + +3.4.4 (2015-04-25) + +Bugs fixed + +An ElementTree compatibility test added in lxml 3.4.3 that failed in +Python 3.4+ was removed again. + + + + +3.4.3 (2015-04-15) + +Bugs fixed + +Expression cache in ElementPath was ignored. Fix by Changaco. +LP#1426868: Passing a default namespace and a prefixed namespace mapping +as nsmap into xmlfile.element() raised a TypeError. +LP#1421927: DOCTYPE system URLs were incorrectly quoted when containing +double quotes. Patch by Olli Pottonen. +LP#1419354: meta-redirect URLs were incorrectly processed by +iterlinks() if preceded by whitespace. + + + + +3.4.2 (2015-02-07) + +Bugs fixed + +LP#1415907: Crash when creating an XMLSchema from a non-root element +of an XML document. +LP#1369362: HTML cleaning failed when hitting processing instructions +with pseudo-attributes. +CDATA() wrapped content was rejected for tail text. +CDATA sections were not serialised as tail text of the top-level element. + + + + +3.4.1 (2014-11-20) + +Features added + +New htmlfile HTML generator to accompany the incremental xmlfile +serialisation API. Patch by Burak Arslan. + + + +Bugs fixed + +lxml.sax.ElementTreeContentHandler did not initialise its superclass. + + + + +3.4.0 (2014-09-10) + +Features added + +xmlfile(buffered=False) disables output buffering and flushes the +content after each API operation (starting/ending element blocks or writes). +A new method xf.flush() can alternatively be used to explicitly flush +the output. +lxml.html.document_fromstring has a new option ensure_head_body=True +which will add an empty head and/or body element to the result document if +missing. +lxml.html.iterlinks now returns links inside meta refresh tags. +New XMLParser option collect_ids=False to disable ID hash table +creation. This can substantially speed up parsing of documents with many +different IDs that are not used. +The parser uses per-document hash tables for XML IDs. This reduces the +load of the global parser dict and speeds up parsing for documents with +many different IDs. +ElementTree.getelementpath(element) returns a structural ElementPath +expression for the given element, which can be used for lookups later. +xmlfile() accepts a new argument close=True to close file(-like) +objects after writing to them. Before, xmlfile() only closed the file +if it had opened it internally. +Allow "bytearray" type for ASCII text input. + + + +Bugs fixed + + +Other changes + +LP#400588: decoding errors have become hard errors even in recovery mode. +Previously, they could lead to an internal tree representation in a mixed +encoding state, which lead to very late errors or even silently incorrect +behaviour during tree traversal or serialisation. +Requires Python 2.6, 2.7, 3.2 or later. No longer supports +Python 2.4, 2.5 and 3.1, use lxml 3.3.x for those. +Requires libxml2 2.7.0 or later and libxslt 1.1.23 or later, +use lxml 3.3.x with older versions. + + + + +3.3.6 (2014-08-28) + +Bugs fixed + +Prevent tree cycle creation when adding Elements as siblings. +LP#1361948: crash when deallocating Element siblings without parent. +LP#1354652: crash when traversing internally loaded documents in XSLT +extension functions. + + + + +3.3.5 (2014-04-18) + +Bugs fixed + +HTML cleaning could fail to strip javascript links that mix control +characters into the link scheme. + + + + +3.3.4 (2014-04-03) + +Features added + +Source line numbers above 65535 are available on Elements when +using libxml2 2.9 or later. + + + +Bugs fixed + +lxml.html.fragment_fromstring() failed for bytes input in Py3. + + + +Other changes + + + +3.3.3 (2014-03-04) + +Bugs fixed + +LP#1287118: Crash when using Element subtypes with __slots__. + + + +Other changes + +The internal classes _LogEntry and _Attrib can no longer be +subclassed from Python code. + + + + +3.3.2 (2014-02-26) + +Bugs fixed + +The properties resolvers and version, as well as the methods +set_element_class_lookup() and makeelement(), were lost from +iterparse objects in 3.3.0. +LP#1222132: instances of XMLSchema, Schematron and RelaxNG +did not clear their local error_log before running a validation. +LP#1238500: lxml.doctestcompare mixed up "expected" and "actual" in +attribute values. +Some file I/O tests were failing in MS-Windows due to non-portable temp +file usage. Initial patch by Gabi Davar. +LP#910014: duplicate IDs in a document were not reported by DTD validation. +LP#1185332: tostring(method="html") did not use HTML serialisation +semantics for trailing tail text. Initial patch by Sylvain Viollon. +LP#1281139: .attrib value of Comments lost its mutation methods +in 3.3.0. Even though it is empty and immutable, it should still +provide the same interface as that returned for Elements. + + + + +3.3.1 (2014-02-12) + +Features added + + +Bugs fixed + +LP#1014290: HTML documents parsed with parser.feed() failed to find +elements during tag iteration. +LP#1273709: Building in PyPy failed due to missing support for +PyUnicode_Compare() and PyByteArray_*() in PyPy's C-API. +LP#1274413: Compilation in MSVC failed due to missing "stdint.h" standard +header file. +LP#1274118: iterparse() failed to parse BOM prefixed files. + + + +Other changes + + + +3.3.0 (2014-01-26) + +Features added + + +Bugs fixed + +The heuristic that distinguishes file paths from URLs was tightened +to produce less false negatives. + + + +Other changes + + + +3.3.0beta5 (2014-01-18) + +Features added + +The PEP 393 unicode parsing support gained a fallback for wchar strings +which might still be somewhat common on Windows systems. + + + +Bugs fixed + +Several error handling problems were fixed throughout the code base that +could previously lead to exceptions being silently swallowed or not +properly reported. +The C-API function appendChild() is now deprecated as it does not +propagate exceptions (its return type is void). The new function +appendChildToElement() was added as a safe replacement. +Passing a string into fromstringlist() raises an exception instead of +parsing the string character by character. + + + +Other changes + +Document cleanup code was simplified using the new GC features in +Cython 0.20. + + + + +3.3.0beta4 (2014-01-12) + +Features added + + +Bugs fixed + +The (empty) value returned by the attrib property of Entity and Comment +objects was mutable. +Element class lookup wasn't available for the new pull parsers or when using +a custom parser target. +Setting Element attributes on instantiation with both the attrib argument +and keyword arguments could modify the mapping passed as attrib. +LP#1266171: DTDs instantiated from internal/external subsets (i.e. through +the docinfo property) lost their attribute declarations. + + + +Other changes + +Built with Cython 0.20pre (gitrev 012ae82eb) to prepare support for +Python 3.4. + + + + +3.3.0beta3 (2014-01-02) + +Features added + +Unicode string parsing was optimised for Python 3.3 (PEP 393). + + + +Bugs fixed + +HTML parsing of Unicode strings could misdecode the input on some platforms. +Crash in xmlfile() when closing open elements out of order in an error case. + + + +Other changes + + + +3.3.0beta2 (2013-12-20) + +Features added + +iterparse() supports the recover option. + + + +Bugs fixed + +Crash in iterparse() for HTML parsing. +Crash in target parsing with attributes. + + + +Other changes + +The safety check in the read-only tree implementation (e.g. used by +PythonElementClassLookup) raises a more appropriate ReferenceError +for illegal access after tree disposal instead of an AssertionError. +This should only impact test code that specifically checks the original +behaviour. + + + + +3.3.0beta1 (2013-12-12) + +Features added + +New option handle_failures in make_links_absolute() and +resolve_base_href() (lxml.html) that enables ignoring or +discarding links that fail to parse as URLs. +New parser classes XMLPullParser and HTMLPullParser for +incremental parsing, as implemented for ElementTree in Python 3.4. +iterparse() enables recovery mode by default for HTML parsing +(html=True). + + + +Bugs fixed + +LP#1255132: crash when trying to run validation over non-Element (e.g. +comment or PI). +Error messages in the log and in exception messages that originated +from libxml2 could accidentally be picked up from preceding warnings +instead of the actual error. +The ElementMaker in lxml.objectify did not accept a dict as +argument for adding attributes to the element it's building. This +works as in lxml.builder now. +LP#1228881: repr(XSLTAccessControl) failed in Python 3. +Raise ValueError when trying to append an Element to itself or +to one of its own descendants, instead of running into an infinite +loop. +LP#1206077: htmldiff discarded whitespace from the output. +Compressed plain-text serialisation to file-like objects was broken. +lxml.html.formfill: Fix textarea form filling. +The textarea used to be cleared before the new content was set, +which removed the name attribute. + + + +Other changes + +Some basic API classes use freelists internally for faster +instantiation. This can speed up some iterparse() scenarios, +for example. +iterparse() was rewritten to use the new *PullParser +classes internally instead of being a parser itself. + + + + +3.2.5 (2014-01-02) + +Features added + + +Bugs fixed + +Crash in xmlfile() when closing open elements out of order in an error case. +Crash in target parsing with attributes. +LP#1255132: crash when trying to run validation over non-Element (e.g. +comment or PI). + + + +Other changes + + + +3.2.4 (2013-11-07) + +Features added + + +Bugs fixed + +Memory leak when creating an XPath evaluator in a thread. +LP#1228881: repr(XSLTAccessControl) failed in Python 3. +Raise ValueError when trying to append an Element to itself or +to one of its own descendants. +LP#1206077: htmldiff discarded whitespace from the output. +Compressed plain-text serialisation to file-like objects was broken. + + + +Other changes + + + +3.2.3 (2013-07-28) + +Bugs fixed + +Fix support for Python 2.4 which was lost in 3.2.2. + + + + +3.2.2 (2013-07-28) + +Features added + + +Bugs fixed + +LP#1185701: spurious XMLSyntaxError after finishing iterparse(). +Crash in lxml.objectify during xsi annotation. + + + +Other changes + +Return values of user provided element class lookup methods are now +validated against the type of the XML node they represent to prevent +API class mismatches. + + + + +3.2.1 (2013-05-11) + +Features added + +The methods apply_templates() and process_children() of XSLT +extension elements have gained two new boolean options elements_only +and remove_blank_text that discard either all strings or whitespace-only +strings from the result list. + + + +Bugs fixed + +When moving Elements to another tree, the namespace cleanup mechanism +no longer drops namespace prefixes from attributes for which it finds +a default namespace declaration, to prevent them from appearing as +unnamespaced attributes after serialisation. +Returning non-type objects from a custom class lookup method could lead +to a crash. +Instantiating and using subtypes of Comments and ProcessingInstructions +crashed. + + + +Other changes + + + +3.2.0 (2013-04-28) + +Features added + + +Bugs fixed + +LP#690319: Leading whitespace could change the behaviour of the string +parsing functions in lxml.html. +LP#599318: The string parsing functions in lxml.html are more robust +in the face of uncommon HTML content like framesets or missing body tags. +Patch by Stefan Seelmann. +LP#712941: I/O errors while trying to access files with paths that contain +non-ASCII characters could raise UnicodeDecodeError instead of properly +reporting the IOError. +LP#673205: Parsing from in-memory strings disabled network access in the +default parser and made subsequent attempts to parse from a URL fail. +LP#971754: lxml.html.clean appends 'nofollow' to 'rel' attributes instead +of overwriting the current value. +LP#715687: lxml.html.clean no longer discards scripts that are explicitly +allowed by the user provided whitelist. Patch by Christine Koppelt. + + + +Other changes + + + +3.1.2 (2013-04-12) + +Features added + + +Bugs fixed + +LP#1136509: Passing attributes through the namespace-unaware API of +the sax bridge (i.e. the handler.startElement() method) failed +with a TypeError. Patch by Mike Bayer. +LP#1123074: Fix serialisation error in XSLT output when converting +the result tree to a Unicode string. +GH#105: Replace illegal usage of xmlBufLength() in libxml2 2.9.0 +by properly exported API function xmlBufUse(). + + + +Other changes + + + +3.1.1 (2013-03-29) + +Features added + + +Bugs fixed + +LP#1160386: Write access to lxml.html.FormElement.fields raised +an AttributeError in Py3. +Illegal memory access during cleanup in incremental xmlfile writer. + + + +Other changes + +The externally useless class lxml.etree._BaseParser was removed +from the module dict. + + + + +3.1.0 (2013-02-10) + +Features added + +GH#89: lxml.html.clean allows overriding the set of attributes that it +considers 'safe'. Patch by Francis Devereux. + + + +Bugs fixed + +LP#1104370: copy.copy(el.attrib) raised an exception. It now returns +a copy of the attributes as a plain Python dict. +GH#95: When used with namespace prefixes, the el.find*() methods +always used the first namespace mapping that was provided for each +path expression instead of using the one that was actually passed +in for the current run. +LP#1092521, GH#91: Fix undefined C symbol in Python runtimes compiled +without threading support. Patch by Ulrich Seidl. + + + +Other changes + + + +3.1beta1 (2012-12-21) + +Features added + +New build-time option --with-unicode-strings for Python 2 that +makes the API always return Unicode strings for names and text +instead of byte strings for plain ASCII content. +New incremental XML file writing API etree.xmlfile(). +E factory in lxml.objectify is callable to simplify the creation of +tags with non-identifier names without having to resort to getattr(). + + + +Bugs fixed + +When starting from a non-namespaced element in lxml.objectify, searching +for a child without explicitly specifying a namespace incorrectly found +namespaced elements with the requested local name, instead of restricting +the search to non-namespaced children. +GH#85: Deprecation warnings were fixed for Python 3.x. +GH#33: lxml.html.fromstring() failed to accept bytes input in Py3. +LP#1080792: Static build of libxml2 2.9.0 failed due to missing file. + + + +Other changes + +The externally useless class _ObjectifyElementMakerCaller was +removed from the module API of lxml.objectify. +LP#1075622: lxml.builder is faster for adding text to elements with +many children. Patch by Anders Hammarquist. + + + + +3.0.2 (2012-12-14) + +Features added + + +Bugs fixed + +Fix crash during interpreter shutdown by switching to Cython 0.17.3 for building. + + + +Other changes + + + +3.0.1 (2012-10-14) + +Features added + + +Bugs fixed + +LP#1065924: Element proxies could disappear during garbage collection +in PyPy without proper cleanup. +GH#71: Failure to work with libxml2 2.6.x. +LP#1065139: static MacOS-X build failed in Py3. + + + +Other changes + + + +3.0 (2012-10-08) + +Features added + + +Bugs fixed + +End-of-file handling was incorrect in iterparse() when reading from +a low-level C file stream and failed in libxml2 2.9.0 due to its +improved consistency checks. + + + +Other changes + +The build no longer uses Cython by default unless the generated C files +are missing. To use Cython, pass the option "--with-cython". To ignore +the fatal build error when Cython is required but not available (e.g. to +run special setup.py commands that do not actually run a build), pass +"--without-cython". + + + + +3.0beta1 (2012-09-26) + +Features added + +Python level access to (optional) libxml2 memory debugging features +to simplify debugging of memory leaks etc. + + + +Bugs fixed + +Fix a memory leak in XPath by switching to Cython 0.17.1. +Some tests were adapted to work with PyPy. + + + +Other changes + +The code was adapted to work with the upcoming libxml2 2.9.0 release. + + + + +3.0alpha2 (2012-08-23) + +Features added + +The .iter() method of elements now accepts tag arguments like +"{*}name" to search for elements with a given local name in any +namespace. With this addition, all combinations of wildcards now work +as expected: +"{ns}name", "{}name", "{*}name", "{ns}*", "{}*" +and "{*}*". Note that "name" is equivalent to "{}name", +but "*" is "{*}*". +The same change applies to the .getiterator(), .itersiblings(), +.iterancestors(), .iterdescendants(), .iterchildren() +and .itertext() methods;the strip_attributes(), +strip_elements() and strip_tags() functions as well as the +iterparse() class. Patch by Simon Sapin. +C14N allows specifying the inclusive prefixes to be promoted +to top-level during exclusive serialisation. + + + +Bugs fixed + +Passing long Unicode strings into the feed() parser interface +failed to read the entire string. + + + +Other changes + + + +3.0alpha1 (2012-07-31) + +Features added + +Initial support for building in PyPy (through cpyext). +DTD objects gained an API that allows read access to their +declarations. +xpathgrep.py gained support for parsing line-by-line (e.g. +from grep output) and for surrounding the output with a new root +tag. +E-factory in lxml.builder accepts subtypes of known data +types (such as string subtypes) when building elements around them. +Tree iteration and iterparse() with a selective tag +argument supports passing a set of tags. Tree nodes will be +returned by the iterators if they match any of the tags. + + + +Bugs fixed + +The .find*() methods in lxml.objectify no longer use XPath +internally, which makes them faster in many cases (especially when +short circuiting after a single or couple of elements) and fixes +some behavioural differences compared to lxml.etree. Note that +this means that they no longer support arbitrary XPath expressions +but only the subset that the ElementPath language supports. +The previous implementation was also redundant with the normal +XPath support, which can be used as a replacement. +el.find('*') could accidentally return a comment or processing +instruction that happened to be in the wrong spot. (Same for the +other .find*() methods.) +The error logging is less intrusive and avoids a global setup where +possible. +Fixed undefined names in html5lib parser. +xpathgrep.py did not work in Python 3. +Element.attrib.update() did not accept an attrib of +another Element as parameter. +For subtypes of ElementBase that make the .text or .tail +properties immutable (as in objectify, for example), inserting text +when creating Elements through the E-Factory feature of the class +constructor would fail with an exception, stating that the text +cannot be modified. + + + +Other changes + +The code base was overhauled to properly use 'const' where the API +of libxml2 and libxslt requests it. This also has an impact on the +public C-API of lxml itself, as defined in etreepublic.pxd, as +well as the provided declarations in the lxml/includes/ directory. +Code that uses these declarations may have to be adapted. On the +plus side, this fixes several C compiler warnings, also for user +code, thus making it easier to spot real problems again. +The functionality of "lxml.cssselect" was moved into a separate PyPI +package called "cssselect". To continue using it, you must install +that package separately. The "lxml.cssselect" module is still +available and provides the same interface, provided the "cssselect" +package can be imported at runtime. +Element attributes passed in as an attrib dict or as keyword +arguments are now sorted by (namespaced) name before being created +to make their order predictable for serialisation and iteration. +Note that adding or deleting attributes afterwards does not take +that order into account, i.e. setting a new attribute appends it +after the existing ones. +Several classes that are for internal use only were removed +from the lxml.etree module dict: +_InputDocument, _ResolverRegistry, _ResolverContext, _BaseContext, +_ExsltRegExp, _IterparseContext, _TempStore, _ExceptionContext, +__ContentOnlyElement, _AttribIterator, _NamespaceRegistry, +_ClassNamespaceRegistry, _FunctionNamespaceRegistry, +_XPathFunctionNamespaceRegistry, _ParserDictionaryContext, +_FileReaderContext, _ParserContext, _PythonSaxParserTarget, +_TargetParserContext, _ReadOnlyProxy, _ReadOnlyPIProxy, +_ReadOnlyEntityProxy, _ReadOnlyElementProxy, _OpaqueNodeWrapper, +_OpaqueDocumentWrapper, _ModifyContentOnlyProxy, +_ModifyContentOnlyPIProxy, _ModifyContentOnlyEntityProxy, +_AppendOnlyElementProxy, _SaxParserContext, _FilelikeWriter, +_ParserSchemaValidationContext, _XPathContext, +_XSLTResolverContext, _XSLTContext, _XSLTQuotedStringParam +Several internal classes can no longer be inherited from: +_InputDocument, _ResolverRegistry, _ExsltRegExp, _ElementUnicodeResult, +_IterparseContext, _TempStore, _AttribIterator, _ClassNamespaceRegistry, +_XPathFunctionNamespaceRegistry, _ParserDictionaryContext, +_FileReaderContext, _PythonSaxParserTarget, _TargetParserContext, +_ReadOnlyPIProxy, _ReadOnlyEntityProxy, _OpaqueDocumentWrapper, +_ModifyContentOnlyPIProxy, _ModifyContentOnlyEntityProxy, +_AppendOnlyElementProxy, _FilelikeWriter, _ParserSchemaValidationContext, +_XPathContext, _XSLTResolverContext, _XSLTContext, _XSLTQuotedStringParam, +_XSLTResultTree, _XSLTProcessingInstruction + + + + +2.3.6 (2012-09-28) + +Features added + + +Bugs fixed + +Passing long Unicode strings into the feed() parser interface +failed to read the entire string. + + + +Other changes + + + +2.3.5 (2012-07-31) + +Features added + + +Bugs fixed + +Crash when merging text nodes in element.remove(). +Crash in sax/target parser when reporting empty doctype. + + + +Other changes + + + +2.3.4 (2012-03-26) + +Features added + + +Bugs fixed + +Crash when building an nsmap (Element property) with empty +namespace URIs. +Crash due to race condition when errors (or user messages) occur +during threaded XSLT processing. +XSLT stylesheet compilation could ignore compilation errors. + + + +Other changes + + + +2.3.3 (2012-01-04) + +Features added + +lxml.html.tostring() gained new serialisation options +with_tail and doctype. + + + +Bugs fixed + +Fixed a crash when using iterparse() for HTML parsing and +requesting start events. +Fixed parsing of more selectors in cssselect. Whitespace before +pseudo-elements and pseudo-classes is significant as it is a +descendant combinator. +"E :pseudo" should parse the same as "E *:pseudo", not "E:pseudo". +Patch by Simon Sapin. +lxml.html.diff no longer raises an exception when hitting +'img' tags without 'src' attribute. + + + +Other changes + + + +2.3.2 (2011-11-11) + +Features added + +lxml.objectify.deannotate() has a new boolean option +cleanup_namespaces to remove the objectify namespace +declarations (and generally clean up the namespace declarations) +after removing the type annotations. +lxml.objectify gained its own SubElement() function as a +copy of etree.SubElement to avoid an otherwise redundant import +of lxml.etree on the user side. + + + +Bugs fixed + +Fixed the "descendant" bug in cssselect a second time (after a first +fix in lxml 2.3.1). The previous change resulted in a serious +performance regression for the XPath based evaluation of the +translated expression. Note that this breaks the usage of some of +the generated XPath expressions as XSLT location paths that +previously worked in 2.3.1. +Fixed parsing of some selectors in cssselect. Whitespace after combinators +">", "+" and "~" is now correctly ignored. Previously it was parsed as +a descendant combinator. For example, "div> .foo" was parsed the same as +"div>* .foo" instead of "div>.foo". Patch by Simon Sapin. + + + +Other changes + + + +2.3.1 (2011-09-25) + +Features added + +New option kill_tags in lxml.html.clean to remove specific +tags and their content (i.e. their whole subtree). +pi.get() and pi.attrib on processing instructions to parse +pseudo-attributes from the text content of processing instructions. +lxml.get_include() returns a list of include paths that can be +used to compile external C code against lxml.etree. This is +specifically required for statically linked lxml builds when code +needs to compile against the exact same header file versions as lxml +itself. +Resolver.resolve_file() takes an additional option +close_file that configures if the file(-like) object will be +closed after reading or not. By default, the file will be closed, +as the user is not expected to keep a reference to it. + + + +Bugs fixed + +HTML cleaning didn't remove 'data:' links. +The html5lib parser integration now uses the 'official' +implementation in html5lib itself, which makes it work with newer +releases of the library. +In lxml.sax, endElementNS() could incorrectly reject a plain +tag name when the corresponding start event inferred the same plain +tag name to be in the default namespace. +When an open file-like object is passed into parse() or +iterparse(), the parser will no longer close it after use. This +reverts a change in lxml 2.3 where all files would be closed. It is +the users responsibility to properly close the file(-like) object, +also in error cases. +Assertion error in lxml.html.cleaner when discarding top-level elements. +In lxml.cssselect, use the xpath 'A//B' (short for +'A/descendant-or-self::node()/B') instead of 'A/descendant::B' for +the css descendant selector ('A B'). This makes a few edge cases +like "div *:last-child" consistent with the selector behavior in +WebKit and Firefox, and makes more css expressions valid location +paths (for use in xsl:template match). +In lxml.html, non-selected <option> tags no longer show up in the +collected form values. +Adding/removing <option> values to/from a multiple select form +field properly selects them and unselects them. + + + +Other changes + +Static builds can specify the download directory with the +--download-dir option. + + + + +2.3 (2011-02-06) + +Features added + +When looking for children, lxml.objectify takes '{}tag' as +meaning an empty namespace, as opposed to the parent namespace. + + + +Bugs fixed + +When finished reading from a file-like object, the parser +immediately calls its .close() method. +When finished parsing, iterparse() immediately closes the input +file. +Work-around for libxml2 bug that can leave the HTML parser in a +non-functional state after parsing a severely broken document (fixed +in libxml2 2.7.8). +marque tag in HTML cleanup code is correctly named marquee. + + + +Other changes + +Some public functions in the Cython-level C-API have more explicit +return types. + + + + +2.3beta1 (2010-09-06) + +Features added + + +Bugs fixed + +Crash in newer libxml2 versions when moving elements between +documents that had attributes on replaced XInclude nodes. +XMLID() function was missing the optional parser and +base_url parameters. +Searching for wildcard tags in iterparse() was broken in Py3. +lxml.html.open_in_browser() didn't work in Python 3 due to the +use of os.tempnam. It now takes an optional 'encoding' parameter. + + + +Other changes + + + +2.3alpha2 (2010-07-24) + +Features added + + +Bugs fixed + +Crash in XSLT when generating text-only result documents with a +stylesheet created in a different thread. + + + +Other changes + +repr() of Element objects shows the hex ID with leading 0x +(following ElementTree 1.3). + + + + +2.3alpha1 (2010-06-19) + +Features added + +Keyword argument namespaces in lxml.cssselect.CSSSelector() +to pass a prefix-to-namespace mapping for the selector. +New function lxml.etree.register_namespace(prefix, uri) that +globally registers a namespace prefix for a namespace that newly +created Elements in that namespace will use automatically. Follows +ElementTree 1.3. +Support 'unicode' string name as encoding parameter in +tostring(), following ElementTree 1.3. +Support 'c14n' serialisation method in ElementTree.write() and +tostring(), following ElementTree 1.3. +The ElementPath expression syntax (el.find*()) was extended to +match the upcoming ElementTree 1.3 that will ship in the standard +library of Python 3.2/2.7. This includes extended support for +predicates as well as namespace prefixes (as known from XPath). +During regular XPath evaluation, various ESXLT functions are +available within their namespace when using libxslt 1.1.26 or later. +Support passing a readily configured logger instance into +PyErrorLog, instead of a logger name. +On serialisation, the new doctype parameter can be used to +override the DOCTYPE (internal subset) of the document. +New parameter output_parent to XSLTExtension.apply_templates() +to append the resulting content directly to an output element. +XSLTExtension.process_children() to process the content of the +XSLT extension element itself. +ISO-Schematron support based on the de-facto Schematron reference +'skeleton implementation'. +XSLT objects now take XPath object as __call__ stylesheet +parameters. +Enable path caching in ElementPath (el.find*()) to avoid parsing +overhead. +Setting the value of a namespaced attribute always uses a prefixed +namespace instead of the default namespace even if both declare the +same namespace URI. This avoids serialisation problems when an +attribute from a default namespace is set on an element from a +different namespace. +XSLT extension elements: support for XSLT context nodes other than +elements: document root, comments, processing instructions. +Support for strings (in addition to Elements) in node-sets returned +by extension functions. +Forms that lack an action attribute default to the base URL of +the document on submit. +XPath attribute result strings have an attrname property. +Namespace URIs get validated against RFC 3986 at the API level +(required by the XML namespace specification). +Target parsers show their target object in the .target property +(compatible with ElementTree). + + + +Bugs fixed + +API is hardened against invalid proxy instances to prevent crashes +due to incorrectly instantiated Element instances. +Prevent crash when instantiating CommentBase and friends. +Export ElementTree compatible XML parser class as +XMLTreeBuilder, as it is called in ET 1.2. +ObjectifiedDataElements in lxml.objectify were not hashable. They +now use the hash value of the underlying Python value (string, +number, etc.) to which they compare equal. +Parsing broken fragments in lxml.html could fail if the fragment +contained an orphaned closing '</div>' tag. +Using XSLT extension elements around the root of the output document +crashed. +lxml.cssselect did not distinguish between x[attr="val"] and +x [attr="val"] (with a space). The latter now matches the +attribute independent of the element. +Rewriting multiple links inside of HTML text content could end up +replacing unrelated content as replacements could impact the +reported position of subsequent matches. Modifications are now +simplified by letting the iterlinks() generator in lxml.html +return links in reversed order if they appear inside the same text +node. Thus, replacements and link-internal modifications no longer +change the position of links reported afterwards. +The .value attribute of textarea elements in lxml.html did +not represent the complete raw value (including child tags etc.). It +now serialises the complete content on read and replaces the +complete content by a string on write. +Target parser didn't call .close() on the target object if +parsing failed. Now it is guaranteed that .close() will be +called after parsing, regardless of the outcome. + + + +Other changes + +Official support for Python 3.1.2 and later. +Static MS Windows builds can now download their dependencies +themselves. +Element.attrib no longer uses a cyclic reference back to its +Element object. It therefore no longer requires the garbage +collector to clean up. +Static builds include libiconv, in addition to libxml2 and libxslt. + + + + +2.2.8 (2010-09-02) + +Bugs fixed + +Crash in newer libxml2 versions when moving elements between +documents that had attributes on replaced XInclude nodes. +Import fix for urljoin in Python 3.1+. + + + + +2.2.7 (2010-07-24) + +Bugs fixed + +Crash in XSLT when generating text-only result documents with a +stylesheet created in a different thread. + + + + +2.2.6 (2010-03-02) + +Bugs fixed + +Fixed several Python 3 regressions by building with Cython 0.11.3. + + + + +2.2.5 (2010-02-28) + +Features added + +Support for running XSLT extension elements on the input root node +(e.g. in a template matching on "/"). + + + +Bugs fixed + +Crash in XPath evaluation when reading smart strings from a document +other than the original context document. +Support recent versions of html5lib by not requiring its +XHTMLParser in htmlparser.py anymore. +Manually instantiating the custom element classes in +lxml.objectify could crash. +Invalid XML text characters were not rejected by the API when they +appeared in unicode strings directly after non-ASCII characters. +lxml.html.open_http_urllib() did not work in Python 3. +The functions strip_tags() and strip_elements() in +lxml.etree did not remove all occurrences of a tag in all cases. +Crash in XSLT extension elements when the XSLT context node is not +an element. + + + + +2.2.4 (2009-11-11) + +Bugs fixed + +Static build of libxml2/libxslt was broken. + + + + +2.2.3 (2009-10-30) + +Features added + + +Bugs fixed + +The resolve_entities option did not work in the incremental feed +parser. +Looking up and deleting attributes without a namespace could hit a +namespaced attribute of the same name instead. +Late errors during calls to SubElement() (e.g. attribute related +ones) could leave a partially initialised element in the tree. +Modifying trees that contain parsed entity references could result +in an infinite loop. +ObjectifiedElement.__setattr__ created an empty-string child element when the +attribute value was rejected as a non-unicode/non-ascii string +Syntax errors in lxml.cssselect could result in misleading error +messages. +Invalid syntax in CSS expressions could lead to an infinite loop in +the parser of lxml.cssselect. +CSS special character escapes were not properly handled in +lxml.cssselect. +CSS Unicode escapes were not properly decoded in lxml.cssselect. +Select options in HTML forms that had no explicit value +attribute were not handled correctly. The HTML standard dictates +that their value is defined by their text content. This is now +supported by lxml.html. +XPath raised a TypeError when finding CDATA sections. This is now +fully supported. +Calling help(lxml.objectify) didn't work at the prompt. +The ElementMaker in lxml.objectify no longer defines the default +namespaces when annotation is disabled. +Feed parser failed to honour the 'recover' option on parse errors. +Diverting the error logging to Python's logging system was broken. + + + +Other changes + + + +2.2.2 (2009-06-21) + +Features added + +New helper functions strip_attributes(), strip_elements(), +strip_tags() in lxml.etree to remove attributes/subtrees/tags +from a subtree. + + + +Bugs fixed + +Namespace cleanup on subtree insertions could result in missing +namespace declarations (and potentially crashes) if the element +defining a namespace was deleted and the namespace was not used by +the top element of the inserted subtree but only in deeper subtrees. +Raising an exception from a parser target callback didn't always +terminate the parser. +Only {true, false, 1, 0} are accepted as the lexical representation for +BoolElement ({True, False, T, F, t, f} not any more), restoring lxml <= 2.0 +behaviour. + + + +Other changes + + + +2.2.1 (2009-06-02) + +Features added + +Injecting default attributes into a document during XML Schema +validation (also at parse time). +Pass huge_tree parser option to disable parser security +restrictions imposed by libxml2 2.7. + + + +Bugs fixed + +The script for statically building libxml2 and libxslt didn't work +in Py3. +XMLSchema() also passes invalid schema documents on to libxml2 +for parsing (which could lead to a crash before release 2.6.24). + + + +Other changes + + + +2.2 (2009-03-21) + +Features added + +Support for standalone flag in XML declaration through +tree.docinfo.standalone and by passing standalone=True/False +on serialisation. + + + +Bugs fixed + +Crash when parsing an XML Schema with external imports from a +filename. + + + + +2.2beta4 (2009-02-27) + +Features added + +Support strings and instantiable Element classes as child arguments +to the constructor of custom Element classes. +GZip compression support for serialisation to files and file-like +objects. + + + +Bugs fixed + +Deep-copying an ElementTree copied neither its sibling PIs and +comments nor its internal/external DTD subsets. +Soupparser failed on broken attributes without values. +Crash in XSLT when overwriting an already defined attribute using +xsl:attribute. +Crash bug in exception handling code under Python 3. This was due +to a problem in Cython, not lxml itself. +lxml.html.FormElement._name() failed for non top-level forms. +TAG special attribute in constructor of custom Element classes +was evaluated incorrectly. + + + +Other changes + +Official support for Python 3.0.1. +Element.findtext() now returns an empty string instead of None +for Elements without text content. + + + + +2.2beta3 (2009-02-17) + +Features added + +XSLT.strparam() class method to wrap quoted string parameters +that require escaping. + + + +Bugs fixed + +Memory leak in XPath evaluators. +Crash when parsing indented XML in one thread and merging it with +other documents parsed in another thread. +Setting the base attribute in lxml.objectify from a unicode +string failed. +Fixes following changes in Python 3.0.1. +Minor fixes for Python 3. + + + +Other changes + +The global error log (which is copied into the exception log) is now +local to a thread, which fixes some race conditions. +More robust error handling on serialisation. + + + + +2.2beta2 (2009-01-25) + +Bugs fixed + +Potential memory leak on exception handling. This was due to a +problem in Cython, not lxml itself. +iter_links (and related link-rewriting functions) in +lxml.html would interpret CSS like url("link") incorrectly +(treating the quotation marks as part of the link). +Failing import on systems that have an io module. + + + + +2.1.5 (2009-01-06) + +Bugs fixed + +Potential memory leak on exception handling. This was due to a +problem in Cython, not lxml itself. +Failing import on systems that have an io module. + + + + +2.2beta1 (2008-12-12) + +Features added + +Allow lxml.html.diff.htmldiff to accept Element objects, not +just HTML strings. + + + +Bugs fixed + +Crash when using an XPath evaluator in multiple threads. +Fixed missing whitespace before Link:... in lxml.html.diff. + + + +Other changes + +Export lxml.html.parse. + + + + +2.1.4 (2008-12-12) + +Bugs fixed + +Crash when using an XPath evaluator in multiple threads. + + + + +2.0.11 (2008-12-12) + +Bugs fixed + +Crash when using an XPath evaluator in multiple threads. + + + + +2.2alpha1 (2008-11-23) + +Features added + +Support for XSLT result tree fragments in XPath/XSLT extension +functions. +QName objects have new properties namespace and localname. +New options for exclusive C14N and C14N without comments. +Instantiating a custom Element classes creates a new Element. + + + +Bugs fixed + +XSLT didn't inherit the parse options of the input document. +0-bytes could slip through the API when used inside of Unicode +strings. +With lxml.html.clean.autolink, links with balanced parenthesis, +that end in a parenthesis, will be linked in their entirety (typical +with Wikipedia links). + + + +Other changes + + + +2.1.3 (2008-11-17) + +Features added + + +Bugs fixed + +Ref-count leaks when lxml enters a try-except statement while an +outside exception lives in sys.exc_*(). This was due to a problem in +Cython, not lxml itself. +Parser Unicode decoding errors could get swallowed by other +exceptions. +Name/import errors in some Python modules. +Internal DTD subsets that did not specify a system or public ID were +not serialised and did not appear in the docinfo property of +ElementTrees. +Fix a pre-Py3k warning when parsing from a gzip file in Py2.6. +Test suite fixes for libxml2 2.7. +Resolver.resolve_string() did not work for non-ASCII byte strings. +Resolver.resolve_file() was broken. +Overriding the parser encoding didn't work for many encodings. + + + +Other changes + + + +2.0.10 (2008-11-17) + +Bugs fixed + +Ref-count leaks when lxml enters a try-except statement while an +outside exception lives in sys.exc_*(). This was due to a problem in +Cython, not lxml itself. + + + + +2.1.2 (2008-09-05) + +Features added + +lxml.etree now tries to find the absolute path name of files when +parsing from a file-like object. This helps custom resolvers when +resolving relative URLs, as lixbml2 can prepend them with the path +of the source document. + + + +Bugs fixed + +Memory problem when passing documents between threads. +Target parser did not honour the recover option and raised an +exception instead of calling .close() on the target. + + + +Other changes + + + +2.0.9 (2008-09-05) + +Bugs fixed + +Memory problem when passing documents between threads. +Target parser did not honour the recover option and raised an +exception instead of calling .close() on the target. + + + + +2.1.1 (2008-07-24) + +Features added + + +Bugs fixed + +Crash when parsing XSLT stylesheets in a thread and using them in +another. +Encoding problem when including text with ElementInclude under +Python 3. + + + +Other changes + + + +2.0.8 (2008-07-24) + +Features added + +lxml.html.rewrite_links() strips links to work around documents +with whitespace in URL attributes. + + + +Bugs fixed + +Crash when parsing XSLT stylesheets in a thread and using them in +another. +CSS selector parser dropped remaining expression after a function +with parameters. + + + +Other changes + + + +2.1 (2008-07-09) + +Features added + +Smart strings can be switched off in XPath (smart_strings +keyword option). +lxml.html.rewrite_links() strips links to work around documents +with whitespace in URL attributes. + + + +Bugs fixed + +Custom resolvers were not used for XMLSchema includes/imports and +XInclude processing. +CSS selector parser dropped remaining expression after a function +with parameters. + + + +Other changes + +objectify.enableRecursiveStr() was removed, use +objectify.enable_recursive_str() instead +Speed-up when running XSLTs on documents from other threads + + + + +2.0.7 (2008-06-20) + +Features added + +Pickling ElementTree objects in lxml.objectify. + + + +Bugs fixed + +Descending dot-separated classes in CSS selectors were not resolved +correctly. +ElementTree.parse() didn't handle target parser result. +Potential threading problem in XInclude. +Crash in Element class lookup classes when the __init__() method of +the super class is not called from Python subclasses. + + + +Other changes + +Non-ASCII characters in attribute values are no longer escaped on +serialisation. + + + + +2.1beta3 (2008-06-19) + +Features added + +Major overhaul of tools/xpathgrep.py script. +Pickling ElementTree objects in lxml.objectify. +Support for parsing from file-like objects that return unicode +strings. +New function etree.cleanup_namespaces(el) that removes unused +namespace declarations from a (sub)tree (experimental). +XSLT results support the buffer protocol in Python 3. +Polymorphic functions in lxml.html that accept either a tree or +a parsable string will return either a UTF-8 encoded byte string, a +unicode string or a tree, based on the type of the input. +Previously, the result was always a byte string or a tree. +Support for Python 2.6 and 3.0 beta. +File name handling now uses a heuristic to convert between byte +strings (usually filenames) and unicode strings (usually URLs). +Parsing from a plain file object frees the GIL under Python 2.x. +Running iterparse() on a plain file (or filename) frees the GIL +on reading under Python 2.x. +Conversion functions html_to_xhtml() and xhtml_to_html() in +lxml.html (experimental). +Most features in lxml.html work for XHTML namespaced tag names +(experimental). + + + +Bugs fixed + +ElementTree.parse() didn't handle target parser result. +Crash in Element class lookup classes when the __init__() method of +the super class is not called from Python subclasses. +A number of problems related to unicode/byte string conversion of +filenames and error messages were fixed. +Building on MacOS-X now passes the "flat_namespace" option to the C +compiler, which reportedly prevents build quirks and crashes on this +platform. +Windows build was broken. +Rare crash when serialising to a file object with certain encodings. + + + +Other changes + +Non-ASCII characters in attribute values are no longer escaped on +serialisation. +Passing non-ASCII byte strings or invalid unicode strings as .tag, +namespaces, etc. will result in a ValueError instead of an +AssertionError (just like the tag well-formedness check). +Up to several times faster attribute access (i.e. tree traversal) in +lxml.objectify. + + + + +2.0.6 (2008-05-31) + +Features added + + +Bugs fixed + +Incorrect evaluation of el.find("tag[child]"). +Windows build was broken. +Moving a subtree from a document created in one thread into a +document of another thread could crash when the rest of the source +document is deleted while the subtree is still in use. +Rare crash when serialising to a file object with certain encodings. + + + +Other changes + +lxml should now build without problems on MacOS-X. + + + + +2.1beta2 (2008-05-02) + +Features added + +All parse functions in lxml.html take a parser keyword argument. +lxml.html has a new parser class XHTMLParser and a module +attribute xhtml_parser that provide XML parsers that are +pre-configured for the lxml.html package. + + + +Bugs fixed + +Moving a subtree from a document created in one thread into a +document of another thread could crash when the rest of the source +document is deleted while the subtree is still in use. +Passing an nsmap when creating an Element will no longer strip +redundantly defined namespace URIs. This prevented the definition +of more than one prefix for a namespace on the same Element. + + + +Other changes + +If the default namespace is redundantly defined with a prefix on the +same Element, the prefix will now be preferred for subelements and +attributes. This allows users to work around a problem in libxml2 +where attributes from the default namespace could serialise without +a prefix even when they appear on an Element with a different +namespace (i.e. they would end up in the wrong namespace). + + + + +2.0.5 (2008-05-01) + +Features added + + +Bugs fixed + +Resolving to a filename in custom resolvers didn't work. +lxml did not honour libxslt's second error state "STOPPED", which +let some XSLT errors pass silently. +Memory leak in Schematron with libxml2 >= 2.6.31. + + + +Other changes + + + +2.1beta1 (2008-04-15) + +Features added + +Error logging in Schematron (requires libxml2 2.6.32 or later). +Parser option strip_cdata for normalising or keeping CDATA +sections. Defaults to True as before, thus replacing CDATA +sections by their text content. +CDATA() factory to wrap string content as CDATA section. + + + +Bugs fixed + +Resolving to a filename in custom resolvers didn't work. +lxml did not honour libxslt's second error state "STOPPED", which +let some XSLT errors pass silently. +Memory leak in Schematron with libxml2 >= 2.6.31. +lxml.etree accepted non well-formed namespace prefix names. + + + +Other changes + +Major cleanup in internal moveNodeToDocument() function, which +takes care of namespace cleanup when moving elements between +different namespace contexts. +New Elements created through the makeelement() method of an HTML +parser or through lxml.html now end up in a new HTML document +(doctype HTML 4.01 Transitional) instead of a generic XML document. +This mostly impacts the serialisation and the availability of a DTD +context. + + + + +2.0.4 (2008-04-13) + +Features added + + +Bugs fixed + +Hanging thread in conjunction with GTK threading. +Crash bug in iterparse when moving elements into other documents. +HTML elements' .cssselect() method was broken. +ElementTree.find*() didn't accept QName objects. + + + +Other changes + + + +2.1alpha1 (2008-03-27) + +Features added + +New event types 'comment' and 'pi' in iterparse(). +XSLTAccessControl instances have a property options that +returns a dict of access configuration options. +Constant instances DENY_ALL and DENY_WRITE on +XSLTAccessControl class. +Extension elements for XSLT (experimental!) +Element.base property returns the xml:base or HTML base URL of +an Element. +docinfo.URL property is writable. + + + +Bugs fixed + +Default encoding for plain text serialisation was different from +that of XML serialisation (UTF-8 instead of ASCII). + + + +Other changes + +Minor API speed-ups. +The benchmark suite now uses tail text in the trees, which makes the +absolute numbers incomparable to previous results. +Generating the HTML documentation now requires Pygments, which is +used to enable syntax highlighting for the doctest examples. + +Most long-time deprecated functions and methods were removed: + +etree.clearErrorLog(), use etree.clear_error_log() + +etree.useGlobalPythonLog(), use +etree.use_global_python_log() + +etree.ElementClassLookup.setFallback(), use +etree.ElementClassLookup.set_fallback() + +etree.getDefaultParser(), use etree.get_default_parser() + +etree.setDefaultParser(), use etree.set_default_parser() + +etree.setElementClassLookup(), use +etree.set_element_class_lookup() +Note that parser.setElementClassLookup() has not been removed +yet, although parser.set_element_class_lookup() should be used +instead. + +xpath_evaluator.registerNamespace(), use +xpath_evaluator.register_namespace() + +xpath_evaluator.registerNamespaces(), use +xpath_evaluator.register_namespaces() + +objectify.setPytypeAttributeTag, use +objectify.set_pytype_attribute_tag + +objectify.setDefaultParser(), use +objectify.set_default_parser() + + + + + +2.0.3 (2008-03-26) + +Features added + +soupparser.parse() allows passing keyword arguments on to +BeautifulSoup. +fromstring() method in lxml.html.soupparser. + + + +Bugs fixed + +lxml.html.diff didn't treat empty tags properly (e.g., +<br>). +Handle entity replacements correctly in target parser. +Crash when using iterparse() with XML Schema validation. +The BeautifulSoup parser (soupparser.py) did not replace entities, +which made them turn up in text content. +Attribute assignment of custom PyTypes in objectify could fail to +correctly serialise the value to a string. + + + +Other changes + +lxml.html.ElementSoup was replaced by a new module +lxml.html.soupparser with a more consistent API. The old module +remains for compatibility with ElementTree's own ElementSoup module. +Setting the XSLT_CONFIG and XML2_CONFIG environment variables at +build time will let setup.py pick up the xml2-config and +xslt-config scripts from the supplied path name. +Passing --with-xml2-config=/path/to/xml2-config to setup.py will +override the xml2-config script that is used to determine the C +compiler options. The same applies for the --with-xslt-config +option. + + + + +2.0.2 (2008-02-22) + +Features added + +Support passing base_url to file parser functions to override +the filename of the file(-like) object. + + + +Bugs fixed + +The prefix for objectify's pytype namespace was missing from the set +of default prefixes. +Memory leak in Schematron (fixed only for libxml2 2.6.31+). +Error type names in RelaxNG were reported incorrectly. +Slice deletion bug fixed in objectify. + + + +Other changes + +Enabled doctests for some Python modules (especially lxml.html). +Add a method argument to lxml.html.tostring() +(method="xml" for XHTML output). +Make it clearer that methods like lxml.html.fromstring() take a +base_url argument. + + + + +2.0.1 (2008-02-13) + +Features added + +Child iteration in lxml.pyclasslookup. +Loads of new docstrings reflect the signature of functions and +methods to make them visible in API docs and help() + + + +Bugs fixed + +The module lxml.html.builder was duplicated as +lxml.htmlbuilder +Form elements would return None for form.fields.keys() if there +was an unnamed input field. Now unnamed input fields are completely +ignored. +Setting an element slice in objectify could insert slice-overlapping +elements at the wrong position. + + + +Other changes + +The generated API documentation was cleaned up and disburdened from +non-public classes etc. +The previously public module lxml.html.setmixin was renamed to +lxml.html._setmixin as it is not an official part of lxml. If +you want to use it, feel free to copy it over to your own source +base. +Passing --with-xslt-config=/path/to/xslt-config to setup.py will +override the xslt-config script that is used to determine the C +compiler options. + + + + +2.0 (2008-02-01) + +Features added + +Passing the unicode type as encoding to tostring() will +serialise to unicode. The tounicode() function is now +deprecated. +XMLSchema() and RelaxNG() can parse from StringIO. +makeparser() function in lxml.objectify to create a new +parser with the usual objectify setup. +Plain ASCII XPath string results are no longer forced into unicode +objects as in 2.0beta1, but are returned as plain strings as before. +All XPath string results are 'smart' objects that have a +getparent() method to retrieve their parent Element. +with_tail option in serialiser functions. +More accurate exception messages in validator creation. +Parse-time XML schema validation (schema parser keyword). +XPath string results of the text() function and attribute +selection make their Element container accessible through a +getparent() method. As a side-effect, they are now always +unicode objects (even ASCII strings). +XSLT objects are usable in any thread - at the cost of a deep +copy if they were not created in that thread. +Invalid entity names and character references will be rejected by +the Entity() factory. +entity.text returns the textual representation of the entity, +e.g. &. +New properties position and code on ParseError exception (as +in ET 1.3) +Rich comparison of element.attrib proxies. +ElementTree compatible TreeBuilder class. +Use default prefixes for some common XML namespaces. +lxml.html.clean.Cleaner now allows for a host_whitelist, and +two overridable methods: allow_embedded_url(el, url) and the +more general allow_element(el). +Extended slicing of Elements as in element[1:-1:2], both in +etree and in objectify +Resolvers can now provide a base_url keyword argument when +resolving a document as string data. +When using lxml.doctestcompare you can give the doctest option +NOPARSE_MARKUP (like # doctest: +NOPARSE_MARKUP) to suppress +the special checking for one test. +Separate feed_error_log property for the feed parser interface. +The normal parser interface and iterparse continue to use +error_log. +The normal parsers and the feed parser interface are now separated +and can be used concurrently on the same parser instance. +fromstringlist() and tostringlist() functions as in +ElementTree 1.3 +iterparse() accepts an html boolean keyword argument for +parsing with the HTML parser (note that this interface may be +subject to change) +Parsers accept an encoding keyword argument that overrides the encoding +of the parsed documents. +New C-API function hasChild() to test for children +annotate() function in objectify can annotate with Python types and XSI +types in one step. Accompanied by xsiannotate() and pyannotate(). +ET.write(), tostring() and tounicode() now accept a keyword +argument method that can be one of 'xml' (or None), 'html' or 'text' to +serialise as XML, HTML or plain text content. +iterfind() method on Elements returns an iterator equivalent to +findall() +itertext() method on Elements +Setting a QName object as value of the .text property or as an attribute +will resolve its prefix in the respective context +ElementTree-like parser target interface as described in +http://effbot.org/elementtree/elementtree-xmlparser.htm +ElementTree-like feed parser interface on XMLParser and HTMLParser +(feed() and close() methods) +Reimplemented objectify.E for better performance and improved +integration with objectify. Provides extended type support based on +registered PyTypes. +XSLT objects now support deep copying +New makeSubElement() C-API function that allows creating a new +subelement straight with text, tail and attributes. +XPath extension functions can now access the current context node +(context.context_node) and use a context dictionary +(context.eval_context) from the context provided in their first +parameter +HTML tag soup parser based on BeautifulSoup in lxml.html.ElementSoup +New module lxml.doctestcompare by Ian Bicking for writing simplified +doctests based on XML/HTML output. Use by importing lxml.usedoctest or +lxml.html.usedoctest from within a doctest. +New module lxml.cssselect by Ian Bicking for selecting Elements with CSS +selectors. +New package lxml.html written by Ian Bicking for advanced HTML +treatment. +Namespace class setup is now local to the ElementNamespaceClassLookup +instance and no longer global. +Schematron validation (incomplete in libxml2) +Additional stringify argument to objectify.PyType() takes a +conversion function to strings to support setting text values from arbitrary +types. +Entity support through an Entity factory and element classes. XML +parsers now have a resolve_entities keyword argument that can be set to +False to keep entities in the document. +column field on error log entries to accompany the line field +Error specific messages in XPath parsing and evaluation +NOTE: for evaluation errors, you will now get an XPathEvalError instead of +an XPathSyntaxError. To catch both, you can except on XPathError +The regular expression functions in XPath now support passing a node-set +instead of a string +Extended type annotation in objectify: new xsiannotate() function +EXSLT RegExp support in standard XPath (not only XSLT) + + + +Bugs fixed + +Missing import in lxml.html.clean. +Some Python 2.4-isms prevented lxml from building/running under +Python 2.3. +XPath on ElementTrees could crash when selecting the virtual root +node of the ElementTree. +Compilation --without-threading was buggy in alpha5/6. +Memory leak in the parse() function. +Minor bugs in XSLT error message formatting. +Result document memory leak in target parser. +Target parser failed to report comments. +In the lxml.html iter_links method, links in <object> +tags weren't recognized. (Note: plugin-specific link parameters +still aren't recognized.) Also, the <embed> tag, though not +standard, is now included in lxml.html.defs.special_inline_tags. +Using custom resolvers on XSLT stylesheets parsed from a string +could request ill-formed URLs. +With lxml.doctestcompare if you do <tag xmlns="..."> in your +output, it will then be namespace-neutral (before the ellipsis was +treated as a real namespace). +AttributeError in feed parser on parse errors +XML feed parser setup problem +Type annotation for unicode strings in DataElement() +lxml failed to serialise namespace declarations of elements other than the +root node of a tree +Race condition in XSLT where the resolver context leaked between concurrent +XSLT calls +lxml.etree did not check tag/attribute names +The XML parser did not report undefined entities as error +The text in exceptions raised by XML parsers, validators and XPath +evaluators now reports the first error that occurred instead of the last +Passing '' as XPath namespace prefix did not raise an error +Thread safety in XPath evaluators + + + +Other changes + +Exceptions carry only the part of the error log that is related to +the operation that caused the error. +XMLSchema() and RelaxNG() now enforce passing the source +file/filename through the file keyword argument. +The test suite now skips most doctests under Python 2.3. +make clean no longer removes the .c files (use make +realclean instead) +Minor performance tweaks for Element instantiation and subelement +creation +Various places in the XPath, XSLT and iteration APIs now require +keyword-only arguments. +The argument order in element.itersiblings() was changed to +match the order used in all other iteration methods. The second +argument ('preceding') is now a keyword-only argument. +The getiterator() method on Elements and ElementTrees was +reverted to return an iterator as it did in lxml 1.x. The ET API +specification allows it to return either a sequence or an iterator, +and it traditionally returned a sequence in ET and an iterator in +lxml. However, it is now deprecated in favour of the iter() +method, which should be used in new code wherever possible. +The 'pretty printed' serialisation of ElementTree objects now +inserts newlines at the root level between processing instructions, +comments and the root tag. +A 'pretty printed' serialisation is now terminated with a newline. +Second argument to lxml.etree.Extension() helper is no longer +required, third argument is now a keyword-only argument ns. +lxml.html.tostring takes an encoding argument. +The module source files were renamed to "lxml.*.pyx", such as +"lxml.etree.pyx". This was changed for consistency with the way +Pyrex commonly handles package imports. The main effect is that +classes now know about their fully qualified class name, including +the package name of their module. +Keyword-only arguments in some API functions, especially in the +parsers and serialisers. +Tag name validation in lxml.etree (and lxml.html) now distinguishes +between HTML tags and XML tags based on the parser that was used to +parse or create them. HTML tags no longer reject any non-ASCII +characters in tag names but only spaces and the special characters +<>&/"'. +lxml.etree now emits a warning if you use XPath with libxml2 2.6.27 +(which can crash on certain XPath errors) +Type annotation in objectify now preserves the already annotated type by +default to prevent losing type information that is already there. +element.getiterator() returns a list, use element.iter() to retrieve +an iterator (ElementTree 1.3 compatible behaviour) +objectify.PyType for None is now called "NoneType" +el.getiterator() renamed to el.iter(), following ElementTree 1.3 - +original name is still available as alias +In the public C-API, findOrBuildNodeNs() was replaced by the more +generic findOrBuildNodeNsPrefix +Major refactoring in XPath/XSLT extension function code +Network access in parsers disabled by default + + + + +1.3.6 (2007-10-29) + +Bugs fixed + +Backported decref crash fix from 2.0 +Well hidden free-while-in-use crash bug in ObjectPath + + + +Other changes + +The test suites now run gc.collect() in the tearDown() +methods. While this makes them take a lot longer to run, it also +makes it easier to link a specific test to garbage collection +problems that would otherwise appear in later tests. + + + + +1.3.5 (2007-10-22) + +Features added + + +Bugs fixed + +lxml.etree could crash when adding more than 10000 namespaces to a +document +lxml failed to serialise namespace declarations of elements other +than the root node of a tree + + + + +1.3.4 (2007-08-30) + +Features added + +The ElementMaker in lxml.builder now accepts the keyword arguments +namespace and nsmap to set a namespace and nsmap for the Elements it +creates. +The docinfo on ElementTree objects has new properties internalDTD +and externalDTD that return a DTD object for the internal or external +subset of the document respectively. +Serialising an ElementTree now includes any internal DTD subsets that are +part of the document, as well as comments and PIs that are siblings of the +root node. + + + +Bugs fixed + +Parsing with the no_network option could fail + + + +Other changes + +lxml now raises a TagNameWarning about tag names containing ':' instead of +an Error as 1.3.3 did. The reason is that a number of projects currently +misuse the previous lack of tag name validation to generate namespace +prefixes without declaring namespaces. Apart from the danger of generating +broken XML this way, it also breaks most of the namespace-aware tools in +XML, including XPath, XSLT and validation. lxml 1.3.x will continue to +support this bug with a Warning, while lxml 2.0 will be strict about +well-formed tag names (not only regarding ':'). +Serialising an Element no longer includes its comment and PI siblings (only +ElementTree serialisation includes them). + + + + +1.3.3 (2007-07-26) + +Features added + +ElementTree compatible parser ETCompatXMLParser strips processing +instructions and comments while parsing XML +Parsers now support stripping PIs (keyword argument 'remove_pis') +etree.fromstring() now supports parsing both HTML and XML, depending on +the parser you pass. +Support base_url keyword argument in HTML() and XML() + + + +Bugs fixed + +Parsing from Python Unicode strings failed on some platforms +Element() did not raise an exception on tag names containing ':' +Element.getiterator(tag) did not accept Comment and +ProcessingInstruction as tags. It also accepts Element now. + + + + +1.3.2 (2007-07-03) + +Features added + + +Bugs fixed + +"deallocating None" crash bug + + + + +1.3.1 (2007-07-02) + +Features added + +objectify.DataElement now supports setting values from existing data +elements (not just plain Python types) and reuses defined namespaces etc. +E-factory support for lxml.objectify (objectify.E) + + + +Bugs fixed + +Better way to prevent crashes in Element proxy cleanup code +objectify.DataElement didn't set up None value correctly +objectify.DataElement didn't check the value against the provided type hints +Reference-counting bug in Element.attrib.pop() + + + + +1.3 (2007-06-24) + +Features added + +Module lxml.pyclasslookup module implements an Element class lookup +scheme that can access the entire tree in read-only mode to help determining +a suitable Element class +Parsers take a remove_comments keyword argument that skips over comments +parse() function in objectify, corresponding to XML() etc. +Element.addnext(el) and Element.addprevious(el) methods to support +adding processing instructions and comments around the root node +Element.attrib was missing clear() and pop() methods +Extended type annotation in objectify: cleaner annotation namespace setup +plus new deannotate() function +Support for custom Element class instantiation in lxml.sax: passing a +makeelement function to the ElementTreeContentHandler will reuse the +lookup context of that function +'.' represents empty ObjectPath (identity) +Element.values() to accompany the existing .keys() and .items() +collectAttributes() C-function to build a list of attribute +keys/values/items for a libxml2 node +DTD validator class (like RelaxNG and XMLSchema) +HTML generator helpers by Fredrik Lundh in lxml.htmlbuilder +ElementMaker XML generator by Fredrik Lundh in lxml.builder.E +Support for pickling objectify.ObjectifiedElement objects to XML +update() method on Element.attrib +Optimised replacement for libxml2's _xmlReconsiliateNs(). This allows lxml +a better handling of namespaces when moving elements between documents. + + + +Bugs fixed + +Removing Elements from a tree could make them lose their namespace +declarations +ElementInclude didn't honour base URL of original document +Replacing the children slice of an Element would cut off the tails of the +original children +Element.getiterator(tag) did not accept Comment and +ProcessingInstruction as tags +API functions now check incoming strings for XML conformity. Zero bytes or +low ASCII characters are no longer accepted (AssertionError). +XSLT parsing failed to pass resolver context on to imported documents +passing '' as namespace prefix in nsmap could be passed through to libxml2 +Objectify couldn't handle prefixed XSD type names in xsi:type +More ET compatible behaviour when writing out XML declarations or not +More robust error handling in iterparse() +Documents lost their top-level PIs and comments on serialisation +lxml.sax failed on comments and PIs. Comments are now properly ignored and +PIs are copied. +Possible memory leaks in namespace handling when moving elements between +documents + + + +Other changes + +major restructuring in the documentation + + + + +1.2.1 (2007-02-27) + +Bugs fixed + +Build fixes for MS compiler +Item assignments to special names like element["text"] failed +Renamed ObjectifiedDataElement.__setText() to _setText() to make it easier +to access +The pattern for attribute names in ObjectPath was too restrictive + + + + +1.2 (2007-02-20) + +Features added + +Rich comparison of QName objects +Support for regular expressions in benchmark selection +get/set emulation (not .attrib!) for attributes on processing instructions +ElementInclude Python module for ElementTree compatible XInclude processing +that honours custom resolvers registered with the source document +ElementTree.parser property holds the parser used to parse the document +setup.py has been refactored for greater readability and flexibility +--rpath flag to setup.py to induce automatic linking-in of dynamic library +runtime search paths has been renamed to --auto-rpath. This makes it +possible to pass an --rpath directly to distutils; previously this was being +shadowed. + + + +Bugs fixed + +Element instantiation now uses locks to prevent race conditions with threads +ElementTree.write() did not raise an exception when the file was not writable +Error handling could crash under Python <= 2.4.1 - fixed by disabling thread +support in these environments +Element.find*() did not accept QName objects as path + + + +Other changes + +code cleanup: redundant _NodeBase super class merged into _Element class +Note: although the impact should be zero in most cases, this change breaks +the compatibility of the public C-API + + + + +1.1.2 (2006-10-30) + +Features added + +Data elements in objectify support repr(), which is now used by dump() +Source distribution now ships with a patched Pyrex +New C-API function makeElement() to create new elements with text, +tail, attributes and namespaces +Reuse original parser flags for XInclude +Simplified support for handling XSLT processing instructions + + + +Bugs fixed + +Parser resources were not freed before the next parser run +Open files and XML strings returned by Python resolvers were not +closed/freed +Crash in the IDDict returned by XMLDTDID +Copying Comments and ProcessingInstructions failed +Memory leak for external URLs in _XSLTProcessingInstruction.parseXSL() +Memory leak when garbage collecting tailed root elements +HTML script/style content was not propagated to .text +Show text xincluded between text nodes correctly in .text and .tail +'integer * objectify.StringElement' operation was not supported + + + + +1.1.1 (2006-09-21) + +Features added + +XSLT profiling support (profile_run keyword) +countchildren() method on objectify.ObjectifiedElement +Support custom elements for tree nodes in lxml.objectify + + + +Bugs fixed + +lxml.objectify failed to support long data values (e.g., "123L") +Error messages from XSLT did not reach XSLT.error_log +Factories objectify.Element() and objectify.DataElement() were missing +attrib and nsmap keyword arguments +Changing the default parser in lxml.objectify did not update the factories +Element() and DataElement() +Let lxml.objectify.Element() always generate tree elements (not data +elements) +Build under Windows failed ('0' bug in patched Pyrex version) + + + + +1.1 (2006-09-13) + +Features added + +Comments and processing instructions return '' and +'<?pi-target content?>' for repr() +Parsers are now the preferred (and default) place where element class lookup +schemes should be registered. Namespace lookup is no longer supported by +default. +Support for Python 2.5 beta +Unlock the GIL for deep copying documents and for XPath() +New compact keyword argument for parsing read-only documents +Support for parser options in iterparse() +The namespace axis is supported in XPath and returns (prefix, URI) +tuples +The XPath expression "/" now returns an empty list instead of raising an +exception +XML-Object API on top of lxml (lxml.objectify) +Customizable Element class lookup: +different pre-implemented lookup mechanisms +support for externally provided lookup functions + + +Support for processing instructions (ET-like, not compatible) +Public C-level API for independent extension modules +Module level iterwalk() function as 'iterparse' for trees +Module level iterparse() function similar to ElementTree (see +documentation for differences) +Element.nsmap property returns a mapping of all namespace prefixes known at +the Element to their namespace URI +Reentrant threading support in RelaxNG, XMLSchema and XSLT +Threading support in parsers and serializers: +All in-memory operations (tostring, parse(StringIO), etc.) free the GIL +File operations (on file names) free the GIL +Reading from file-like objects frees the GIL and reacquires it for reading +Serialisation to file-like objects is single-threaded (high lock overhead) + + +Element iteration over XPath axes: +Element.iterdescendants() iterates over the descendants of an element +Element.iterancestors() iterates over the ancestors of an element (from +parent to parent) +Element.itersiblings() iterates over either the following or preceding +siblings of an element +Element.iterchildren() iterates over the children of an element in either +direction +All iterators support the tag keyword argument to restrict the +generated elements + + +Element.getnext() and Element.getprevious() return the direct siblings of an +element + + + +Bugs fixed + +filenames with local 8-bit encoding were not supported +1.1beta did not compile under Python 2.3 +ignore unknown 'pyval' attribute values in objectify +objectify.ObjectifiedElement.addattr() failed to accept Elements and Lists +objectify.ObjectPath.setattr() failed to accept Elements and Lists +XPathSyntaxError now inherits from XPathError +Threading race conditions in RelaxNG and XMLSchema +Crash when mixing elements from XSLT results into other trees, concurrent +XSLT is only allowed when the stylesheet was parsed in the main thread +The EXSLT regexp:match function now works as defined (except for some +differences in the regular expression syntax) +Setting element.text to '' returned None on request, not the empty string +iterparse() could crash on long XML files +Creating documents no longer copies the parser for later URL resolving. For +performance reasons, only a reference is kept. Resolver updates on the +parser will now be reflected by documents that were parsed before the +change. Although this should rarely become visible, it is a behavioral +change from 1.0. + + + + +1.0.4 (2006-09-09) + +Features added + +List-like Element.extend() method + + + +Bugs fixed + +Crash in tail handling in Element.replace() + + + + +1.0.3 (2006-08-08) + +Features added + +Element.replace(old, new) method to replace a subelement by another one + + + +Bugs fixed + +Crash when mixing elements from XSLT results into other trees +Copying/deepcopying did not work for ElementTree objects +Setting an attribute to a non-string value did not raise an exception +Element.remove() deleted the tail text from the removed Element + + + + +1.0.2 (2006-06-27) + +Features added + +Support for setting a custom default Element class as opposed to namespace +specific classes (which still override the default class) + + + +Bugs fixed + +Rare exceptions in Python list functions were not handled +Parsing accepted unicode strings with XML encoding declaration in certain +cases +Parsing 8-bit encoded strings from StringIO objects raised an exception +Module function initThread() was removed - useless (and never worked) +XSLT and parser exception messages include the error line number + + + + +1.0.1 (2006-06-09) + +Features added + +Repeated calls to Element.attrib now efficiently return the same instance + + + +Bugs fixed + +Document deallocation could crash in certain garbage collection scenarios +Extension function calls in XSLT variable declarations could break the +stylesheet and crash on repeated calls +Deep copying Elements could lose namespaces declared in parents +Deep copying Elements did not copy tail +Parsing file(-like) objects failed to load external entities +Parsing 8-bit strings from file(-like) objects raised an exception +xsl:include failed when the stylesheet was parsed from a file-like object +lxml.sax.ElementTreeProducer did not call startDocument() / endDocument() +MSVC compiler complained about long strings (supports only 2048 bytes) + + + + +1.0 (2006-06-01) + +Features added + +Element.getiterator() and the findall() methods support finding arbitrary +elements from a namespace (pattern {namespace}*) +Another speedup in tree iteration code +General speedup of Python Element object creation and deallocation +Writing C14N no longer serializes in memory (reduced memory footprint) +PyErrorLog for error logging through the Python logging module +Element.getroottree() returns an ElementTree for the root node of the +document that contains the element. +ElementTree.getpath(element) returns a simple, absolute XPath expression to +find the element in the tree structure +Error logs have a last_error attribute for convenience +Comment texts can be changed through the API +Formatted output via pretty_print keyword in serialization functions +XSLT can block access to file system and network via XSLTAccessControl +ElementTree.write() no longer serializes in memory (reduced memory +footprint) +Speedup of Element.findall(tag) and Element.getiterator(tag) +Support for writing the XML representation of Elements and ElementTrees to +Python unicode strings via etree.tounicode() +Support for writing XSLT results to Python unicode strings via unicode() +Parsing a unicode string no longer copies the string (reduced memory +footprint) +Parsing file-like objects reads chunks rather than the whole file (reduced +memory footprint) +Parsing StringIO objects from the start avoids copying the string (reduced +memory footprint) +Read-only 'docinfo' attribute in ElementTree class holds DOCTYPE +information, original encoding and XML version as seen by the parser +etree module can be compiled without libxslt by commenting out the line +include "xslt.pxi" near the end of the etree.pyx source file +Better error messages in parser exceptions +Error reporting also works in XSLT +Support for custom document loaders (URI resolvers) in parsers and XSLT, +resolvers are registered at parser level +Implementation of exslt:regexp for XSLT based on the Python 're' module, +enabled by default, can be switched off with 'regexp=False' keyword argument +Support for exslt extensions (libexslt) and libxslt extra functions +(node-set, document, write, output) +Substantial speedup in XPath.evaluate() +HTMLParser for parsing (broken) HTML +XMLDTDID function parses XML into tuple (root node, ID dict) based on xml:id +implementation of libxml2 (as opposed to ET compatible XMLID) + + + +Bugs fixed + +Memory leak in Element.__setitem__ +Memory leak in Element.attrib.items() and Element.attrib.values() +Memory leak in XPath extension functions +Memory leak in unicode related setup code +Element now raises ValueError on empty tag names +Namespace fixing after moving elements between documents could fail if the +source document was freed too early +Setting namespace-less tag names on namespaced elements ('{ns}t' -> 't') +didn't reset the namespace +Unknown constants from newer libxml2 versions could raise exceptions in the +error handlers +lxml.etree compiles much faster +On libxml2 <= 2.6.22, parsing strings with encoding declaration could fail +in certain cases +Document reference in ElementTree objects was not updated when the root +element was moved to a different document +Running absolute XPath expressions on an Element now evaluates against the +root tree +Evaluating absolute XPath expressions (/*) on an ElementTree could fail +Crashes when calling XSLT, RelaxNG, etc. with uninitialized ElementTree +objects +Removed public function initThreadLogging(), replaced by more general +initThread() which fixes a number of setup problems in threads +Memory leak when using iconv encoders in tostring/write +Deep copying Elements and ElementTrees maintains the document information +Serialization functions raise LookupError for unknown encodings +Memory deallocation crash resulting from deep copying elements +Some ElementTree methods could crash if the root node was not initialized +(neither file nor element passed to the constructor) +Element/SubElement failed to set attribute namespaces from passed attrib +dictionary +tostring() adds an XML declaration for non-ASCII encodings +tostring() failed to serialize encodings that contain 0-bytes +ElementTree.xpath() and XPathDocumentEvaluator were not using the +ElementTree root node as reference point +Calling document('') in XSLT failed to return the stylesheet + + + + +0.9.2 (2006-05-10) + +Features added + +Speedup for Element.makeelement(): the new element reuses the original +libxml2 document instead of creating a new empty one +Speedup for reversed() iteration over element children (Py2.4+ only) +ElementTree compatible QName class +RelaxNG and XMLSchema accept any Element, not only ElementTrees + + + +Bugs fixed + +str(xslt_result) was broken for XSLT output other than UTF-8 +Memory leak if write_c14n fails to write the file after conversion +Crash in XMLSchema and RelaxNG when passing non-schema documents +Memory leak in RelaxNG() when RelaxNGParseError is raised + + + + +0.9.1 (2006-03-30) + +Features added + +lxml.sax.ElementTreeContentHandler checks closing elements and raises +SaxError on mismatch +lxml.sax.ElementTreeContentHandler supports namespace-less SAX events +(startElement, endElement) and defaults to empty attributes (keyword +argument) +Speedup for repeatedly accessing element tag names +Minor API performance improvements + + + +Bugs fixed + +Memory deallocation bug when using XSLT output method "html" +sax.py was handling UTF-8 encoded tag names where it shouldn't +lxml.tests package will no longer be installed (is still in source tar) + + + + +0.9 (2006-03-20) + +Features added + +Error logging API for libxml2 error messages +Various performance improvements +Benchmark script for lxml, ElementTree and cElementTree +Support for registering extension functions through new FunctionNamespace +class (see doc/extensions.txt) +ETXPath class for XPath expressions in ElementTree notation ('//{ns}tag') +Support for variables in XPath expressions (also in XPath class) +XPath class for compiled XPath expressions +XMLID module level function (ElementTree compatible) +XMLParser API for customized libxml2 parser configuration +Support for custom Element classes through new Namespace API (see +doc/namespace_extensions.txt) +Common exception base class LxmlError for module exceptions +real iterator support in iter(Element), Element.getiterator() +XSLT objects are callable, result trees support str() +Added MANIFEST.in for easier creation of RPM files. +'getparent' method on elements allows navigation to an element's +parent element. +Python core compatible SAX tree builder and SAX event generator. See +doc/sax.txt for more information. + + + +Bugs fixed + +Segfaults and memory leaks in various API functions of Element +Segfault in XSLT.tostring() +ElementTree objects no longer interfere, Elements can be root of different +ElementTrees at the same time +document('') works in XSLT documents read from files (in-memory documents +cannot support this due to libxslt deficiencies) + + + + +0.8 (2005-11-03) + +Features added + +Support for copy.deepcopy() on elements. copy.copy() works also, but +does the same thing, and does not create a shallow copy, as that +makes no sense in the context of libxml2 trees. This means a +potential incompatibility with ElementTree, but there's more chance +that it works than if copy.copy() isn't supported at all. +Increased compatibility with (c)ElementTree; .parse() on ElementTree is +supported and parsing of gzipped XML files works. +implemented index() on elements, allowing one to find the index of a +SubElement. + + + +Bugs fixed + +Use xslt-config instead of xml2-config to find out libxml2 +directories to take into account a case where libxslt is installed +in a different directory than libxslt. +Eliminate crash condition in iteration when text nodes are changed. +Passing 'None' to tostring() does not result in a segfault anymore, +but an AssertionError. +Some test fixes for Windows. +Raise XMLSyntaxError and XPathSyntaxError instead of plain python +syntax errors. This should be less confusing. +Fixed error with uncaught exception in Pyrex code. +Calling lxml.etree.fromstring('') throws XMLSyntaxError instead of a +segfault. +has_key() works on attrib. 'in' tests also work correctly on attrib. +INSTALL.txt was saying 2.2.16 instead of 2.6.16 as a supported +libxml2 version, as it should. +Passing a UTF-8 encoded string to the XML() function would fail; +fixed. + + + + +0.7 (2005-06-15) + +Features added + +parameters (XPath expressions) can be passed to XSLT using keyword +parameters. +Simple XInclude support. Calling the xinclude() method on a tree +will process any XInclude statements in the document. +XMLSchema support. Use the XMLSchema class or the convenience +xmlschema() method on a tree to do XML Schema (XSD) validation. +Added convenience xslt() method on tree. This is less efficient +than the XSLT object, but makes it easier to write quick code. +Added convenience relaxng() method on tree. This is less efficient +than the RelaxNG object, but makes it easier to write quick code. +Make it possible to use XPathEvaluator with elements as well. The +XPathEvaluator in this case will retain the element so multiple +XPath queries can be made against one element efficiently. This +replaces the second argument to the .evaluate() method that existed +previously. +Allow registerNamespace() to be called on an XPathEvaluator, after +creation, to add additional namespaces. Also allow registerNamespaces(), +which does the same for a namespace dictionary. +Add 'prefix' attribute to element to be able to read prefix information. +This is entirely read-only. +It is possible to supply an extra nsmap keyword parameter to +the Element() and SubElement() constructors, which supplies a +prefix to namespace URI mapping. This will create namespace +prefix declarations on these elements and these prefixes will show up +in XML serialization. + + + +Bugs fixed + +Killed yet another memory management related bug: trees created +using newDoc would not get a libxml2-level dictionary, which caused +problems when deallocating these documents later if they contained a +node that came from a document with a dictionary. +Moving namespaced elements between documents was problematic as +references to the original document would remain. This has been fixed +by applying xmlReconciliateNs() after each move operation. +Can pass None to 'dump()' without segfaults. +tostring() works properly for non-root elements as well. +Cleaned out the tostring() method so it should handle encoding +correctly. +Cleaned out the ElementTree.write() method so it should handle encoding +correctly. Writing directly to a file should also be faster, as there is no +need to go through a Python string in that case. Made sure the test cases +test both serializing to StringIO as well as serializing to a real file. + + + + +0.6 (2005-05-14) + +Features added + +Changed setup.py so that library_dirs is also guessed. This should +help with compilation on the Mac OS X platform, where otherwise the +wrong library (shipping with the OS) could be picked up. +Tweaked setup.py so that it picks up the version from version.txt. + + + +Bugs fixed + +Do the right thing when handling namespaced attributes. +fix bug where tostring() moved nodes into new documents. tostring() +had very nasty side-effects before this fix, sorry! + + + + +0.5.1 (2005-04-09) + +Python 2.2 compatibility fixes. +unicode fixes in Element() and Comment() as well as XML(); unicode +input wasn't properly being UTF-8 encoded. + + + +0.5 (2005-04-08) +Initial public release. + + + + +Generated on: 2017-02-18. + + + + diff --git a/doc/html/compatibility.html b/doc/html/compatibility.html index 6514cc1e..b90dd1bf 100644 --- a/doc/html/compatibility.html +++ b/doc/html/compatibility.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap ElementTree compatibility of lxml.etree +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap ElementTree compatibility of lxml.etree A lot of care has been taken to ensure compatibility between etree and ElementTree. Nonetheless, some differences and incompatibilities exist: @@ -199,7 +199,7 @@ enough to replace a shallow copy in your case. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/credits.html b/doc/html/credits.html index 5246e6ff..5d8b92c9 100644 --- a/doc/html/credits.html +++ b/doc/html/credits.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Credits +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Credits Main contributors @@ -88,7 +88,7 @@ Holger Krekel for originally hosting lxml on codespeak.net -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/cssselect.html b/doc/html/cssselect.html index 7c656aec..7d6aa452 100644 --- a/doc/html/cssselect.html +++ b/doc/html/cssselect.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap lxml.cssselect +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap lxml.cssselect lxml supports a number of interesting languages for tree traversal and element selection. The most important is obviously XPath, but there is also @@ -108,7 +108,7 @@ namespace URIs: the CSSSelector class accepts -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/element_classes.html b/doc/html/element_classes.html index f372bfce..0adca657 100644 --- a/doc/html/element_classes.html +++ b/doc/html/element_classes.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Using custom Element classes in lxml +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Using custom Element classes in lxml lxml has very sophisticated support for custom Element classes. You can provide your own classes for Elements and have lxml use them by @@ -459,7 +459,7 @@ subclasses for elements of this namespace: -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/elementsoup.html b/doc/html/elementsoup.html index 10b9906e..dd2e4c3b 100644 --- a/doc/html/elementsoup.html +++ b/doc/html/elementsoup.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap BeautifulSoup Parser +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap BeautifulSoup Parser BeautifulSoup is a Python package for working with real-world and broken HTML, just like lxml.html. As of version 4.x, it can use @@ -203,7 +203,7 @@ you can simply pass the resulting Unicode string into lxml's parser. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/extensions.html b/doc/html/extensions.html index fd1255a0..a343df3e 100644 --- a/doc/html/extensions.html +++ b/doc/html/extensions.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Python extensions for XPath and XSLT +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Python extensions for XPath and XSLT This document describes how to use Python extension functions in XPath and XSLT like this: @@ -521,7 +521,7 @@ will work: -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/html5parser.html b/doc/html/html5parser.html index 80a6eb6d..b681b42f 100644 --- a/doc/html/html5parser.html +++ b/doc/html/html5parser.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap html5lib Parser +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap html5lib Parser html5lib is a Python package that implements the HTML5 parsing algorithm which is heavily influenced by current browsers and based on the WHATWG @@ -90,7 +90,7 @@ module. Note that these are the parser classes provided by html5lib. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/index.html b/doc/html/index.html index b7305de3..fd95ec6b 100644 --- a/doc/html/index.html +++ b/doc/html/index.html @@ -26,7 +26,7 @@ function hide_menu() { -MenulxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap lxml - XML and HTML with Python +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap lxml - XML and HTML with Python » lxml takes all the pain out of XML. « @@ -67,7 +67,7 @@ fast Python XML processing. Documentation -The complete lxml documentation is available for download as PDF + The complete lxml documentation is available for download as PDF documentation. The HTML documentation from this web site is part of the normal source download. @@ -130,8 +130,8 @@ external C modules, including fast custom element class support. Index (PyPI). It has the source that compiles on various platforms. The source distribution is signed with this key. -The latest version is lxml 3.7.2, released 2017-01-08 -(changes for 3.7.2). Older versions + The latest version is lxml 3.7.3, released 2017-02-18 +(changes for 3.7.3). Older versions are listed below. Please take a look at the installation instructions ! @@ -139,7 +139,7 @@ are listed below. part of the source distribution, so if you want to download the documentation for offline use, take the source archive and copy the doc/html directory out of the source tree, or use the -PDF documentation. +PDF documentation. The latest installable developer sources should usually be available from the build server. It's also possible to check out the latest development version of lxml from github directly, using a command @@ -192,6 +192,7 @@ obstacle to using lxml in your codebase. 3.5, 3.6 +lxml 3.7.3, released 2017-02-18 (changes for 3.7.3) lxml 3.7.2, released 2017-01-08 (changes for 3.7.2) lxml 3.7.1, released 2016-12-22 (changes for 3.7.1) lxml 3.7.0, released 2016-12-10 (changes for 3.7.0) @@ -223,7 +224,7 @@ donation is non-refundable. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/installation.html b/doc/html/installation.html index fdb45379..73763033 100644 --- a/doc/html/installation.html +++ b/doc/html/installation.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Installing lxml +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Installing lxml Contents @@ -215,7 +215,7 @@ read the -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/intro.html b/doc/html/intro.html index da661791..a9bcd942 100644 --- a/doc/html/intro.html +++ b/doc/html/intro.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Why lxml? +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Why lxml? Contents @@ -82,7 +82,7 @@ having to learn new things -- XML is complicated enough. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/lxml-source-howto.html b/doc/html/lxml-source-howto.html index b1727002..eab30246 100644 --- a/doc/html/lxml-source-howto.html +++ b/doc/html/lxml-source-howto.html @@ -27,7 +27,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap How to read the source of lxml +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap How to read the source of lxml @@ -286,7 +286,7 @@ implemented in pure Python. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/lxmlhtml.html b/doc/html/lxmlhtml.html index f303d40f..9b990b63 100644 --- a/doc/html/lxmlhtml.html +++ b/doc/html/lxmlhtml.html @@ -25,7 +25,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap lxml.html +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap lxml.html @@ -190,7 +190,7 @@ readable diff in the output when a test fails. The HTML comparison is most easily used by importing the usedoctest module in a doctest: >>> import lxml.html.usedoctest -Now, if you have a HTML document and want to compare it to an expected result + Now, if you have an HTML document and want to compare it to an expected result document in a doctest, you can do the following: >>> import lxml.html >>> html = lxml.html.fromstring('''\ @@ -696,7 +696,7 @@ microformat. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/objectify.html b/doc/html/objectify.html index b39de75f..d6de43b6 100644 --- a/doc/html/objectify.html +++ b/doc/html/objectify.html @@ -25,7 +25,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap lxml.objectify +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap lxml.objectify @@ -1165,7 +1165,7 @@ support any XPath expression. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/parsing.html b/doc/html/parsing.html index fe44ccfe..8bd30ffa 100644 --- a/doc/html/parsing.html +++ b/doc/html/parsing.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Parsing XML and HTML with lxml +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Parsing XML and HTML with lxml lxml provides a very simple and powerful API for parsing XML and HTML. It supports one-step parsing as well as step-by-step parsing using an @@ -867,7 +867,7 @@ with UTF-8 is also considerably faster in most cases. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/performance.html b/doc/html/performance.html index d893141b..54dcfe40 100644 --- a/doc/html/performance.html +++ b/doc/html/performance.html @@ -27,7 +27,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Benchmarks and Speed +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Benchmarks and Speed @@ -798,7 +798,7 @@ random. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/resolvers.html b/doc/html/resolvers.html index 0212132c..779610c8 100644 --- a/doc/html/resolvers.html +++ b/doc/html/resolvers.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Document loading and URL resolving +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Document loading and URL resolving Contents @@ -250,7 +250,7 @@ documents or raises exceptions if access is denied. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/sax.html b/doc/html/sax.html index 2f9fc781..70aa62e2 100644 --- a/doc/html/sax.html +++ b/doc/html/sax.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Sax support +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Sax support In this document we'll describe lxml's SAX support. lxml has support for producing SAX events for an ElementTree or Element. lxml can also turn SAX @@ -124,7 +124,7 @@ DOM implementation cannot generate SAX events from a DOM tree. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/sitemap.html b/doc/html/sitemap.html index 430965cf..07328db1 100644 --- a/doc/html/sitemap.html +++ b/doc/html/sitemap.html @@ -8,5 +8,5 @@ Sitemap of lxml.de - Processing XML and HTML with Python - Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Download files + Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Download files \ No newline at end of file diff --git a/doc/html/tutorial.html b/doc/html/tutorial.html index b58951dd..e303aebe 100644 --- a/doc/html/tutorial.html +++ b/doc/html/tutorial.html @@ -27,7 +27,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap The lxml.etree Tutorial +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap The lxml.etree Tutorial @@ -1184,7 +1184,7 @@ whereas the other two examples would raise a StopIt -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/validation.html b/doc/html/validation.html index 620f5537..2a59ddc5 100644 --- a/doc/html/validation.html +++ b/doc/html/validation.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Validation with lxml +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap Validation with lxml Apart from the built-in DTD support in parsers, lxml currently supports three schema languages: DTD, Relax NG and XML Schema. All three provide @@ -556,7 +556,7 @@ reporting during validation. -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/html/xpathxslt.html b/doc/html/xpathxslt.html index bd3fdf5e..86681ec5 100644 --- a/doc/html/xpathxslt.html +++ b/doc/html/xpathxslt.html @@ -24,7 +24,7 @@ function hide_menu() { -Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap XPath and XSLT with lxml +Menu lxmllxmlIntroduction Support the project Documentation Download Mailing list Bug tracker License Old Versions Legal Notice for Donations Why lxml?Motto Aims Installing lxmlWhere to get it Requirements Installation Building lxml from dev sources Using lxml with python-libxml2 Source builds on MS Windows Source builds on MacOS-X Benchmarks and SpeedGeneral notes How to read the timings Parsing and Serialising The ElementTree API XPath A longer example lxml.objectify ElementTree compatibility of lxml.etree lxml FAQ - Frequently Asked QuestionsGeneral Questions Installation Contributing Bugs Threading Parsing and Serialisation XPath and Document Traversal Developing with lxmlThe lxml.etree TutorialThe Element class The ElementTree class Parsing from strings and files Namespaces The E-factory ElementPath API reference APIs specific to lxml.etreelxml.etree Other Element APIs Trees and Documents Iteration Error handling on exceptions Error logging Serialisation Incremental XML generation CDATA XInclude and ElementInclude write_c14n on ElementTree Parsing XML and HTML with lxmlParsers The target parser interface The feed parser interface Incremental event parsing iterparse and iterwalk Python unicode strings Validation with lxmlValidation at parse time DTD RelaxNG XMLSchema Schematron (Pre-ISO-Schematron) XPath and XSLT with lxmlXPath XSLT lxml.objectifyThe lxml.objectify API Asserting a Schema ObjectPath Python data types How data types are matched What is different from lxml.etree? lxml.htmlParsing HTML HTML Element Methods Running HTML doctests Creating HTML with the E-factory Working with links Forms Cleaning up HTML HTML Diff Examples lxml.cssselectThe CSSSelector class The cssselect method Supported Selectors Namespaces BeautifulSoup ParserParsing with the soupparser Entity handling Using soupparser as a fallback Using only the encoding detection html5lib ParserDifferences to regular HTML parsing Function Reference Extending lxmlDocument loading and URL resolvingXML Catalogs URI Resolvers Document loading in context I/O access control in XSLT Python extensions for XPath and XSLTXPath Extension functions XSLT extension elements Using custom Element classes in lxmlBackground on Element proxies Element initialization Setting up a class lookup scheme Generating XML with custom classes Implementing namespaces Sax supportBuilding a tree from SAX events Producing SAX events from an ElementTree or Element Interfacing with pulldom/minidom The public C-API of lxml.etreeWriting external modules in Cython Writing external modules in C Developing lxmlHow to build lxml from sourceCython Github, git and hg Building the sources Running the tests and reporting errors Building an egg or wheel Building lxml on MacOS-X Static linking on Windows Building Debian packages from SVN sources How to read the source of lxmlWhat is Cython? Where to start? lxml.etree Python modules lxml.objectify lxml.html Release Changelog CreditsMain contributors Special thanks goes to: Sitemap XPath and XSLT with lxml lxml supports XPath 1.0, XSLT 1.0 and the EXSLT extensions through libxml2 and libxslt in a standards compliant way. @@ -605,7 +605,7 @@ If you want to free it from memory, just do: -Generated on: 2017-01-08. +Generated on: 2017-02-18. diff --git a/doc/lxmlhtml.txt b/doc/lxmlhtml.txt index 93bb0c27..cc59d97a 100644 --- a/doc/lxmlhtml.txt +++ b/doc/lxmlhtml.txt @@ -178,7 +178,7 @@ most easily used by importing the ``usedoctest`` module in a doctest: >>> import lxml.html.usedoctest -Now, if you have a HTML document and want to compare it to an expected result +Now, if you have an HTML document and want to compare it to an expected result document in a doctest, you can do the following: .. sourcecode:: pycon diff --git a/doc/main.txt b/doc/main.txt index c9ca624b..fe42c6be 100644 --- a/doc/main.txt +++ b/doc/main.txt @@ -157,8 +157,8 @@ Index `_ (PyPI). It has the source that compiles on various platforms. The source distribution is signed with `this key `_. -The latest version is `lxml 3.7.2`_, released 2017-01-08 -(`changes for 3.7.2`_). `Older versions <#old-versions>`_ +The latest version is `lxml 3.7.3`_, released 2017-02-18 +(`changes for 3.7.3`_). `Older versions <#old-versions>`_ are listed below. Please take a look at the @@ -246,7 +246,9 @@ See the websites of lxml .. and the `latest in-development version `_. -.. _`PDF documentation`: lxmldoc-3.7.2.pdf +.. _`PDF documentation`: lxmldoc-3.7.3.pdf + +* `lxml 3.7.3`_, released 2017-02-18 (`changes for 3.7.3`_) * `lxml 3.7.2`_, released 2017-01-08 (`changes for 3.7.2`_) @@ -266,6 +268,7 @@ See the websites of lxml * `older releases `_ +.. _`lxml 3.7.3`: /files/lxml-3.7.3.tgz .. _`lxml 3.7.2`: /files/lxml-3.7.2.tgz .. _`lxml 3.7.1`: /files/lxml-3.7.1.tgz .. _`lxml 3.7.0`: /files/lxml-3.7.0.tgz @@ -275,6 +278,7 @@ See the websites of lxml .. _`lxml 3.6.1`: /files/lxml-3.6.1.tgz .. _`lxml 3.6.0`: /files/lxml-3.6.0.tgz +.. _`changes for 3.7.3`: /changes-3.7.3.html .. _`changes for 3.7.2`: /changes-3.7.2.html .. _`changes for 3.7.1`: /changes-3.7.1.html .. _`changes for 3.7.0`: /changes-3.7.0.html diff --git a/src/lxml.egg-info/PKG-INFO b/src/lxml.egg-info/PKG-INFO index d876caa7..22b03bea 100644 --- a/src/lxml.egg-info/PKG-INFO +++ b/src/lxml.egg-info/PKG-INFO @@ -1,6 +1,6 @@ Metadata-Version: 1.1 Name: lxml -Version: 3.7.2 +Version: 3.7.3 Summary: Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API. Home-page: http://lxml.de/ Author: lxml dev team @@ -36,20 +36,16 @@ Description: lxml is a Pythonic, mature binding for the libxml2 and libxslt libr as soon as a maintenance branch has been established. Note that this requires Cython to be installed at an appropriate version for the build. - 3.7.2 (2017-01-08) + 3.7.3 (2017-02-18) ================== Bugs fixed ---------- - * Work around installation problems in recent Python 2.7 versions - due to FTP download failures. + * GH#218 was ineffective in Python 3. - * GH#219: ``xmlfile.element()`` was not properly quoting attribute values. - Patch by Burak Arslan. - - * GH#218: ``xmlfile.element()`` was not properly escaping text content of - script/style tags. Patch by Burak Arslan. + * GH#222: ``lxml.html.submit_form()`` failed in Python 3. + Patch by Jakub Wilk. diff --git a/src/lxml.egg-info/SOURCES.txt b/src/lxml.egg-info/SOURCES.txt index 252a1fce..fdcc3c31 100644 --- a/src/lxml.egg-info/SOURCES.txt +++ b/src/lxml.egg-info/SOURCES.txt @@ -58,7 +58,7 @@ doc/html/FAQ.html doc/html/api.html doc/html/build.html doc/html/capi.html -doc/html/changes-3.7.2.html +doc/html/changes-3.7.3.html doc/html/compatibility.html doc/html/credits.html doc/html/cssselect.html diff --git a/src/lxml/includes/lxml-version.h b/src/lxml/includes/lxml-version.h index 7e4c152c..ae99a477 100644 --- a/src/lxml/includes/lxml-version.h +++ b/src/lxml/includes/lxml-version.h @@ -1,3 +1,3 @@ #ifndef LXML_VERSION_STRING -#define LXML_VERSION_STRING "3.7.2" +#define LXML_VERSION_STRING "3.7.3" #endif diff --git a/src/lxml/lxml.etree.c b/src/lxml/lxml.etree.c index 0ea8f16c..d4820919 100644 --- a/src/lxml/lxml.etree.c +++ b/src/lxml/lxml.etree.c @@ -2257,7 +2257,7 @@ struct __pyx_obj_4lxml_5etree__IncrementalFileWriter { }; -/* "src/lxml/serializer.pxi":1219 +/* "src/lxml/serializer.pxi":1220 * @cython.internal * @cython.freelist(8) * cdef class _FileWriterElement: # <<<<<<<<<<<<<< @@ -8071,7 +8071,6 @@ static PyObject *__pyx_kp_b_http_www_w3_org_1999_02_22_rdf_s; static PyObject *__pyx_kp_b_http_www_w3_org_1999_XSL_Transfo; static PyObject *__pyx_kp_u_http_www_w3_org_1999_XSL_Transfo; static PyObject *__pyx_kp_b_http_www_w3_org_1999_xhtml; -static PyObject *__pyx_kp_s_http_www_w3_org_1999_xhtml; static PyObject *__pyx_kp_b_http_www_w3_org_2001_XMLSchema; static PyObject *__pyx_kp_u_http_www_w3_org_2001_XMLSchema; static PyObject *__pyx_kp_b_http_www_w3_org_2001_XMLSchema_i; @@ -8353,7 +8352,7 @@ static PyObject *__pyx_kp_s_s_s_object_name_r_prefix_r_type; static PyObject *__pyx_kp_s_s_s_object_name_r_type_r_occur; static PyObject *__pyx_kp_u_s_w_s_s; static PyObject *__pyx_n_s_schema; -static PyObject *__pyx_n_s_script; +static PyObject *__pyx_n_b_script; static PyObject *__pyx_n_s_search; static PyObject *__pyx_n_s_self; static PyObject *__pyx_n_s_self_node; @@ -8398,6 +8397,7 @@ static PyObject *__pyx_n_s_strip_elements; static PyObject *__pyx_n_s_strip_tags; static PyObject *__pyx_n_s_strparam; static PyObject *__pyx_n_s_strval; +static PyObject *__pyx_n_b_style; static PyObject *__pyx_n_s_style; static PyObject *__pyx_n_s_sub; static PyObject *__pyx_n_s_super; @@ -144902,7 +144902,6 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ PyObject *(*__pyx_t_13)(PyObject *); int __pyx_t_14; Py_ssize_t __pyx_t_15; - const char *__pyx_t_16; __Pyx_RefNannySetupContext("write", 0); /* "src/lxml/serializer.pxi":1151 @@ -145065,8 +145064,8 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ * content = _utf8(content) * * ns, name, _, _ = self._element_stack[-1] # <<<<<<<<<<<<<< - * if c_method == OUTPUT_METHOD_HTML and \ - * ns in (None, 'http://www.w3.org/1999/xhtml') and name in ('script', 'style'): + * if (c_method == OUTPUT_METHOD_HTML and + * ns in (None, b'http://www.w3.org/1999/xhtml') and */ if (unlikely(__pyx_v_self->_element_stack == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); @@ -145149,9 +145148,9 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ /* "src/lxml/serializer.pxi":1162 * * ns, name, _, _ = self._element_stack[-1] - * if c_method == OUTPUT_METHOD_HTML and \ # <<<<<<<<<<<<<< - * ns in (None, 'http://www.w3.org/1999/xhtml') and name in ('script', 'style'): - * tree.xmlOutputBufferWrite(self._c_out, len(content), content) + * if (c_method == OUTPUT_METHOD_HTML and # <<<<<<<<<<<<<< + * ns in (None, b'http://www.w3.org/1999/xhtml') and + * name in (b'script', b'style')): */ __pyx_t_7 = ((__pyx_v_c_method == __pyx_e_4lxml_5etree_OUTPUT_METHOD_HTML) != 0); if (__pyx_t_7) { @@ -145162,10 +145161,10 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ /* "src/lxml/serializer.pxi":1163 * ns, name, _, _ = self._element_stack[-1] - * if c_method == OUTPUT_METHOD_HTML and \ - * ns in (None, 'http://www.w3.org/1999/xhtml') and name in ('script', 'style'): # <<<<<<<<<<<<<< - * tree.xmlOutputBufferWrite(self._c_out, len(content), content) - * else: + * if (c_method == OUTPUT_METHOD_HTML and + * ns in (None, b'http://www.w3.org/1999/xhtml') and # <<<<<<<<<<<<<< + * name in (b'script', b'style')): + * tree.xmlOutputBufferWrite(self._c_out, len(content), _cstr(content)) */ __Pyx_INCREF(__pyx_v_ns); __pyx_t_8 = __pyx_v_ns; @@ -145177,7 +145176,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ __pyx_t_7 = __pyx_t_14; goto __pyx_L16_bool_binop_done; } - __pyx_t_14 = (__Pyx_PyString_Equals(__pyx_t_8, __pyx_kp_s_http_www_w3_org_1999_xhtml, Py_EQ)); if (unlikely(__pyx_t_14 < 0)) __PYX_ERR(7, 1163, __pyx_L1_error) + __pyx_t_14 = (__Pyx_PyBytes_Equals(__pyx_t_8, __pyx_kp_b_http_www_w3_org_1999_xhtml, Py_EQ)); if (unlikely(__pyx_t_14 < 0)) __PYX_ERR(7, 1163, __pyx_L1_error) __pyx_t_7 = __pyx_t_14; __pyx_L16_bool_binop_done:; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; @@ -145187,15 +145186,23 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ __pyx_t_2 = __pyx_t_14; goto __pyx_L13_bool_binop_done; } + + /* "src/lxml/serializer.pxi":1164 + * if (c_method == OUTPUT_METHOD_HTML and + * ns in (None, b'http://www.w3.org/1999/xhtml') and + * name in (b'script', b'style')): # <<<<<<<<<<<<<< + * tree.xmlOutputBufferWrite(self._c_out, len(content), _cstr(content)) + * else: + */ __Pyx_INCREF(__pyx_v_name); __pyx_t_8 = __pyx_v_name; - __pyx_t_7 = (__Pyx_PyString_Equals(__pyx_t_8, __pyx_n_s_script, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(7, 1163, __pyx_L1_error) + __pyx_t_7 = (__Pyx_PyBytes_Equals(__pyx_t_8, __pyx_n_b_script, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(7, 1164, __pyx_L1_error) if (!__pyx_t_7) { } else { __pyx_t_14 = __pyx_t_7; goto __pyx_L18_bool_binop_done; } - __pyx_t_7 = (__Pyx_PyString_Equals(__pyx_t_8, __pyx_n_s_style, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(7, 1163, __pyx_L1_error) + __pyx_t_7 = (__Pyx_PyBytes_Equals(__pyx_t_8, __pyx_n_b_style, Py_EQ)); if (unlikely(__pyx_t_7 < 0)) __PYX_ERR(7, 1164, __pyx_L1_error) __pyx_t_14 = __pyx_t_7; __pyx_L18_bool_binop_done:; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; @@ -145206,35 +145213,34 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ /* "src/lxml/serializer.pxi":1162 * * ns, name, _, _ = self._element_stack[-1] - * if c_method == OUTPUT_METHOD_HTML and \ # <<<<<<<<<<<<<< - * ns in (None, 'http://www.w3.org/1999/xhtml') and name in ('script', 'style'): - * tree.xmlOutputBufferWrite(self._c_out, len(content), content) + * if (c_method == OUTPUT_METHOD_HTML and # <<<<<<<<<<<<<< + * ns in (None, b'http://www.w3.org/1999/xhtml') and + * name in (b'script', b'style')): */ if (__pyx_t_2) { - /* "src/lxml/serializer.pxi":1164 - * if c_method == OUTPUT_METHOD_HTML and \ - * ns in (None, 'http://www.w3.org/1999/xhtml') and name in ('script', 'style'): - * tree.xmlOutputBufferWrite(self._c_out, len(content), content) # <<<<<<<<<<<<<< + /* "src/lxml/serializer.pxi":1165 + * ns in (None, b'http://www.w3.org/1999/xhtml') and + * name in (b'script', b'style')): + * tree.xmlOutputBufferWrite(self._c_out, len(content), _cstr(content)) # <<<<<<<<<<<<<< * else: * tree.xmlOutputBufferWriteEscape(self._c_out, _xcstr(content), NULL) */ - __pyx_t_15 = PyObject_Length(__pyx_v_content); if (unlikely(__pyx_t_15 == -1)) __PYX_ERR(7, 1164, __pyx_L1_error) - __pyx_t_16 = __Pyx_PyObject_AsString(__pyx_v_content); if (unlikely((!__pyx_t_16) && PyErr_Occurred())) __PYX_ERR(7, 1164, __pyx_L1_error) - xmlOutputBufferWrite(__pyx_v_self->_c_out, __pyx_t_15, __pyx_t_16); + __pyx_t_15 = PyObject_Length(__pyx_v_content); if (unlikely(__pyx_t_15 == -1)) __PYX_ERR(7, 1165, __pyx_L1_error) + xmlOutputBufferWrite(__pyx_v_self->_c_out, __pyx_t_15, PyBytes_AS_STRING(__pyx_v_content)); /* "src/lxml/serializer.pxi":1162 * * ns, name, _, _ = self._element_stack[-1] - * if c_method == OUTPUT_METHOD_HTML and \ # <<<<<<<<<<<<<< - * ns in (None, 'http://www.w3.org/1999/xhtml') and name in ('script', 'style'): - * tree.xmlOutputBufferWrite(self._c_out, len(content), content) + * if (c_method == OUTPUT_METHOD_HTML and # <<<<<<<<<<<<<< + * ns in (None, b'http://www.w3.org/1999/xhtml') and + * name in (b'script', b'style')): */ goto __pyx_L12; } - /* "src/lxml/serializer.pxi":1166 - * tree.xmlOutputBufferWrite(self._c_out, len(content), content) + /* "src/lxml/serializer.pxi":1167 + * tree.xmlOutputBufferWrite(self._c_out, len(content), _cstr(content)) * else: * tree.xmlOutputBufferWriteEscape(self._c_out, _xcstr(content), NULL) # <<<<<<<<<<<<<< * @@ -145255,14 +145261,14 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ goto __pyx_L5; } - /* "src/lxml/serializer.pxi":1168 + /* "src/lxml/serializer.pxi":1169 * tree.xmlOutputBufferWriteEscape(self._c_out, _xcstr(content), NULL) * * elif iselement(content): # <<<<<<<<<<<<<< * if self._status > WRITER_IN_ELEMENT: * raise LxmlSyntaxError("cannot append trailing element to complete XML document") */ - __pyx_t_11 = __Pyx_GetModuleGlobalName(__pyx_n_s_iselement); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1168, __pyx_L1_error) + __pyx_t_11 = __Pyx_GetModuleGlobalName(__pyx_n_s_iselement); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1169, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); __pyx_t_10 = NULL; if (CYTHON_UNPACK_METHODS && unlikely(PyMethod_Check(__pyx_t_11))) { @@ -145275,13 +145281,13 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ } } if (!__pyx_t_10) { - __pyx_t_8 = __Pyx_PyObject_CallOneArg(__pyx_t_11, __pyx_v_content); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1168, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_CallOneArg(__pyx_t_11, __pyx_v_content); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1169, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); } else { #if CYTHON_FAST_PYCALL if (PyFunction_Check(__pyx_t_11)) { PyObject *__pyx_temp[2] = {__pyx_t_10, __pyx_v_content}; - __pyx_t_8 = __Pyx_PyFunction_FastCall(__pyx_t_11, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1168, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyFunction_FastCall(__pyx_t_11, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1169, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_10); __pyx_t_10 = 0; __Pyx_GOTREF(__pyx_t_8); } else @@ -145289,29 +145295,29 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ #if CYTHON_FAST_PYCCALL if (__Pyx_PyFastCFunction_Check(__pyx_t_11)) { PyObject *__pyx_temp[2] = {__pyx_t_10, __pyx_v_content}; - __pyx_t_8 = __Pyx_PyCFunction_FastCall(__pyx_t_11, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1168, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyCFunction_FastCall(__pyx_t_11, __pyx_temp+1-1, 1+1); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1169, __pyx_L1_error) __Pyx_XDECREF(__pyx_t_10); __pyx_t_10 = 0; __Pyx_GOTREF(__pyx_t_8); } else #endif { - __pyx_t_9 = PyTuple_New(1+1); if (unlikely(!__pyx_t_9)) __PYX_ERR(7, 1168, __pyx_L1_error) + __pyx_t_9 = PyTuple_New(1+1); if (unlikely(!__pyx_t_9)) __PYX_ERR(7, 1169, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); __Pyx_GIVEREF(__pyx_t_10); PyTuple_SET_ITEM(__pyx_t_9, 0, __pyx_t_10); __pyx_t_10 = NULL; __Pyx_INCREF(__pyx_v_content); __Pyx_GIVEREF(__pyx_v_content); PyTuple_SET_ITEM(__pyx_t_9, 0+1, __pyx_v_content); - __pyx_t_8 = __Pyx_PyObject_Call(__pyx_t_11, __pyx_t_9, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1168, __pyx_L1_error) + __pyx_t_8 = __Pyx_PyObject_Call(__pyx_t_11, __pyx_t_9, NULL); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1169, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; } } __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; - __pyx_t_2 = __Pyx_PyObject_IsTrue(__pyx_t_8); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(7, 1168, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_IsTrue(__pyx_t_8); if (unlikely(__pyx_t_2 < 0)) __PYX_ERR(7, 1169, __pyx_L1_error) __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; if (__pyx_t_2) { - /* "src/lxml/serializer.pxi":1169 + /* "src/lxml/serializer.pxi":1170 * * elif iselement(content): * if self._status > WRITER_IN_ELEMENT: # <<<<<<<<<<<<<< @@ -145321,23 +145327,23 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ __pyx_t_2 = ((__pyx_v_self->_status > __pyx_e_4lxml_5etree_WRITER_IN_ELEMENT) != 0); if (__pyx_t_2) { - /* "src/lxml/serializer.pxi":1170 + /* "src/lxml/serializer.pxi":1171 * elif iselement(content): * if self._status > WRITER_IN_ELEMENT: * raise LxmlSyntaxError("cannot append trailing element to complete XML document") # <<<<<<<<<<<<<< * _writeNodeToBuffer(self._c_out, (<_Element>content)._c_node, * self._c_encoding, NULL, c_method, */ - __pyx_t_8 = __Pyx_GetModuleGlobalName(__pyx_n_s_LxmlSyntaxError); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1170, __pyx_L1_error) + __pyx_t_8 = __Pyx_GetModuleGlobalName(__pyx_n_s_LxmlSyntaxError); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1171, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); - __pyx_t_11 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__77, NULL); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1170, __pyx_L1_error) + __pyx_t_11 = __Pyx_PyObject_Call(__pyx_t_8, __pyx_tuple__77, NULL); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1171, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_Raise(__pyx_t_11, 0, 0, 0); __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; - __PYX_ERR(7, 1170, __pyx_L1_error) + __PYX_ERR(7, 1171, __pyx_L1_error) - /* "src/lxml/serializer.pxi":1169 + /* "src/lxml/serializer.pxi":1170 * * elif iselement(content): * if self._status > WRITER_IN_ELEMENT: # <<<<<<<<<<<<<< @@ -145346,7 +145352,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ */ } - /* "src/lxml/serializer.pxi":1171 + /* "src/lxml/serializer.pxi":1172 * if self._status > WRITER_IN_ELEMENT: * raise LxmlSyntaxError("cannot append trailing element to complete XML document") * _writeNodeToBuffer(self._c_out, (<_Element>content)._c_node, # <<<<<<<<<<<<<< @@ -145355,7 +145361,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ */ __pyx_f_4lxml_5etree__writeNodeToBuffer(__pyx_v_self->_c_out, ((struct LxmlElement *)__pyx_v_content)->_c_node, __pyx_v_self->_c_encoding, NULL, __pyx_v_c_method, 0, 0, __pyx_v_pretty_print, __pyx_v_with_tail, 0); - /* "src/lxml/serializer.pxi":1174 + /* "src/lxml/serializer.pxi":1175 * self._c_encoding, NULL, c_method, * False, False, pretty_print, with_tail, False) * if (<_Element>content)._c_node.type == tree.XML_ELEMENT_NODE: # <<<<<<<<<<<<<< @@ -145365,7 +145371,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ __pyx_t_2 = ((((struct LxmlElement *)__pyx_v_content)->_c_node->type == XML_ELEMENT_NODE) != 0); if (__pyx_t_2) { - /* "src/lxml/serializer.pxi":1175 + /* "src/lxml/serializer.pxi":1176 * False, False, pretty_print, with_tail, False) * if (<_Element>content)._c_node.type == tree.XML_ELEMENT_NODE: * if not self._element_stack: # <<<<<<<<<<<<<< @@ -145376,7 +145382,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ __pyx_t_7 = ((!__pyx_t_2) != 0); if (__pyx_t_7) { - /* "src/lxml/serializer.pxi":1176 + /* "src/lxml/serializer.pxi":1177 * if (<_Element>content)._c_node.type == tree.XML_ELEMENT_NODE: * if not self._element_stack: * self._status = WRITER_FINISHED # <<<<<<<<<<<<<< @@ -145385,7 +145391,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ */ __pyx_v_self->_status = __pyx_e_4lxml_5etree_WRITER_FINISHED; - /* "src/lxml/serializer.pxi":1175 + /* "src/lxml/serializer.pxi":1176 * False, False, pretty_print, with_tail, False) * if (<_Element>content)._c_node.type == tree.XML_ELEMENT_NODE: * if not self._element_stack: # <<<<<<<<<<<<<< @@ -145394,7 +145400,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ */ } - /* "src/lxml/serializer.pxi":1174 + /* "src/lxml/serializer.pxi":1175 * self._c_encoding, NULL, c_method, * False, False, pretty_print, with_tail, False) * if (<_Element>content)._c_node.type == tree.XML_ELEMENT_NODE: # <<<<<<<<<<<<<< @@ -145403,7 +145409,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ */ } - /* "src/lxml/serializer.pxi":1168 + /* "src/lxml/serializer.pxi":1169 * tree.xmlOutputBufferWriteEscape(self._c_out, _xcstr(content), NULL) * * elif iselement(content): # <<<<<<<<<<<<<< @@ -145413,7 +145419,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ goto __pyx_L5; } - /* "src/lxml/serializer.pxi":1178 + /* "src/lxml/serializer.pxi":1179 * self._status = WRITER_FINISHED * else: * raise TypeError("got invalid input value of type %s, expected string or Element" % type(content)) # <<<<<<<<<<<<<< @@ -145421,30 +145427,30 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ * if not self._buffered: */ /*else*/ { - __pyx_t_11 = __Pyx_PyString_Format(__pyx_kp_s_got_invalid_input_value_of_type, ((PyObject *)Py_TYPE(__pyx_v_content))); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1178, __pyx_L1_error) + __pyx_t_11 = __Pyx_PyString_Format(__pyx_kp_s_got_invalid_input_value_of_type, ((PyObject *)Py_TYPE(__pyx_v_content))); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1179, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); - __pyx_t_8 = PyTuple_New(1); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1178, __pyx_L1_error) + __pyx_t_8 = PyTuple_New(1); if (unlikely(!__pyx_t_8)) __PYX_ERR(7, 1179, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_GIVEREF(__pyx_t_11); PyTuple_SET_ITEM(__pyx_t_8, 0, __pyx_t_11); __pyx_t_11 = 0; - __pyx_t_11 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_t_8, NULL); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1178, __pyx_L1_error) + __pyx_t_11 = __Pyx_PyObject_Call(__pyx_builtin_TypeError, __pyx_t_8, NULL); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1179, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_Raise(__pyx_t_11, 0, 0, 0); __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; - __PYX_ERR(7, 1178, __pyx_L1_error) + __PYX_ERR(7, 1179, __pyx_L1_error) } __pyx_L5:; - /* "src/lxml/serializer.pxi":1179 + /* "src/lxml/serializer.pxi":1180 * else: * raise TypeError("got invalid input value of type %s, expected string or Element" % type(content)) * self._handle_error(self._c_out.error) # <<<<<<<<<<<<<< * if not self._buffered: * tree.xmlOutputBufferFlush(self._c_out) */ - __pyx_t_11 = __pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(__pyx_v_self, __pyx_v_self->_c_out->error); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1179, __pyx_L1_error) + __pyx_t_11 = __pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(__pyx_v_self, __pyx_v_self->_c_out->error); if (unlikely(!__pyx_t_11)) __PYX_ERR(7, 1180, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_11); __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0; @@ -145458,7 +145464,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ } __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - /* "src/lxml/serializer.pxi":1180 + /* "src/lxml/serializer.pxi":1181 * raise TypeError("got invalid input value of type %s, expected string or Element" % type(content)) * self._handle_error(self._c_out.error) * if not self._buffered: # <<<<<<<<<<<<<< @@ -145468,7 +145474,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ __pyx_t_7 = ((!(__pyx_v_self->_buffered != 0)) != 0); if (__pyx_t_7) { - /* "src/lxml/serializer.pxi":1181 + /* "src/lxml/serializer.pxi":1182 * self._handle_error(self._c_out.error) * if not self._buffered: * tree.xmlOutputBufferFlush(self._c_out) # <<<<<<<<<<<<<< @@ -145477,7 +145483,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ */ xmlOutputBufferFlush(__pyx_v_self->_c_out); - /* "src/lxml/serializer.pxi":1180 + /* "src/lxml/serializer.pxi":1181 * raise TypeError("got invalid input value of type %s, expected string or Element" % type(content)) * self._handle_error(self._c_out.error) * if not self._buffered: # <<<<<<<<<<<<<< @@ -145517,7 +145523,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_10write(struct _ return __pyx_r; } -/* "src/lxml/serializer.pxi":1183 +/* "src/lxml/serializer.pxi":1184 * tree.xmlOutputBufferFlush(self._c_out) * * def flush(self): # <<<<<<<<<<<<<< @@ -145545,7 +145551,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_12flush(struct _ __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("flush", 0); - /* "src/lxml/serializer.pxi":1188 + /* "src/lxml/serializer.pxi":1189 * Write any pending content of the current output buffer to the stream. * """ * assert self._c_out is not NULL # <<<<<<<<<<<<<< @@ -145556,12 +145562,12 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_12flush(struct _ if (unlikely(!Py_OptimizeFlag)) { if (unlikely(!((__pyx_v_self->_c_out != NULL) != 0))) { PyErr_SetNone(PyExc_AssertionError); - __PYX_ERR(7, 1188, __pyx_L1_error) + __PYX_ERR(7, 1189, __pyx_L1_error) } } #endif - /* "src/lxml/serializer.pxi":1189 + /* "src/lxml/serializer.pxi":1190 * """ * assert self._c_out is not NULL * tree.xmlOutputBufferFlush(self._c_out) # <<<<<<<<<<<<<< @@ -145570,7 +145576,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_12flush(struct _ */ xmlOutputBufferFlush(__pyx_v_self->_c_out); - /* "src/lxml/serializer.pxi":1183 + /* "src/lxml/serializer.pxi":1184 * tree.xmlOutputBufferFlush(self._c_out) * * def flush(self): # <<<<<<<<<<<<<< @@ -145590,7 +145596,7 @@ static PyObject *__pyx_pf_4lxml_5etree_22_IncrementalFileWriter_12flush(struct _ return __pyx_r; } -/* "src/lxml/serializer.pxi":1191 +/* "src/lxml/serializer.pxi":1192 * tree.xmlOutputBufferFlush(self._c_out) * * cdef _close(self, bint raise_on_error): # <<<<<<<<<<<<<< @@ -145608,7 +145614,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p int __pyx_t_4; __Pyx_RefNannySetupContext("_close", 0); - /* "src/lxml/serializer.pxi":1192 + /* "src/lxml/serializer.pxi":1193 * * cdef _close(self, bint raise_on_error): * if raise_on_error: # <<<<<<<<<<<<<< @@ -145618,7 +145624,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p __pyx_t_1 = (__pyx_v_raise_on_error != 0); if (__pyx_t_1) { - /* "src/lxml/serializer.pxi":1193 + /* "src/lxml/serializer.pxi":1194 * cdef _close(self, bint raise_on_error): * if raise_on_error: * if self._status < WRITER_IN_ELEMENT: # <<<<<<<<<<<<<< @@ -145628,23 +145634,23 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p __pyx_t_1 = ((__pyx_v_self->_status < __pyx_e_4lxml_5etree_WRITER_IN_ELEMENT) != 0); if (__pyx_t_1) { - /* "src/lxml/serializer.pxi":1194 + /* "src/lxml/serializer.pxi":1195 * if raise_on_error: * if self._status < WRITER_IN_ELEMENT: * raise LxmlSyntaxError("no content written") # <<<<<<<<<<<<<< * if self._element_stack: * raise LxmlSyntaxError("pending open tags on close") */ - __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_LxmlSyntaxError); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1194, __pyx_L1_error) + __pyx_t_2 = __Pyx_GetModuleGlobalName(__pyx_n_s_LxmlSyntaxError); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1195, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); - __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_tuple__78, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(7, 1194, __pyx_L1_error) + __pyx_t_3 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_tuple__78, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(7, 1195, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; - __PYX_ERR(7, 1194, __pyx_L1_error) + __PYX_ERR(7, 1195, __pyx_L1_error) - /* "src/lxml/serializer.pxi":1193 + /* "src/lxml/serializer.pxi":1194 * cdef _close(self, bint raise_on_error): * if raise_on_error: * if self._status < WRITER_IN_ELEMENT: # <<<<<<<<<<<<<< @@ -145653,7 +145659,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ } - /* "src/lxml/serializer.pxi":1195 + /* "src/lxml/serializer.pxi":1196 * if self._status < WRITER_IN_ELEMENT: * raise LxmlSyntaxError("no content written") * if self._element_stack: # <<<<<<<<<<<<<< @@ -145663,23 +145669,23 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p __pyx_t_1 = (__pyx_v_self->_element_stack != Py_None) && (PyList_GET_SIZE(__pyx_v_self->_element_stack) != 0); if (__pyx_t_1) { - /* "src/lxml/serializer.pxi":1196 + /* "src/lxml/serializer.pxi":1197 * raise LxmlSyntaxError("no content written") * if self._element_stack: * raise LxmlSyntaxError("pending open tags on close") # <<<<<<<<<<<<<< * error_result = self._c_out.error * if error_result == xmlerror.XML_ERR_OK: */ - __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_LxmlSyntaxError); if (unlikely(!__pyx_t_3)) __PYX_ERR(7, 1196, __pyx_L1_error) + __pyx_t_3 = __Pyx_GetModuleGlobalName(__pyx_n_s_LxmlSyntaxError); if (unlikely(!__pyx_t_3)) __PYX_ERR(7, 1197, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); - __pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_tuple__79, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1196, __pyx_L1_error) + __pyx_t_2 = __Pyx_PyObject_Call(__pyx_t_3, __pyx_tuple__79, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1197, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_Raise(__pyx_t_2, 0, 0, 0); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - __PYX_ERR(7, 1196, __pyx_L1_error) + __PYX_ERR(7, 1197, __pyx_L1_error) - /* "src/lxml/serializer.pxi":1195 + /* "src/lxml/serializer.pxi":1196 * if self._status < WRITER_IN_ELEMENT: * raise LxmlSyntaxError("no content written") * if self._element_stack: # <<<<<<<<<<<<<< @@ -145688,7 +145694,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ } - /* "src/lxml/serializer.pxi":1192 + /* "src/lxml/serializer.pxi":1193 * * cdef _close(self, bint raise_on_error): * if raise_on_error: # <<<<<<<<<<<<<< @@ -145697,7 +145703,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ } - /* "src/lxml/serializer.pxi":1197 + /* "src/lxml/serializer.pxi":1198 * if self._element_stack: * raise LxmlSyntaxError("pending open tags on close") * error_result = self._c_out.error # <<<<<<<<<<<<<< @@ -145707,7 +145713,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p __pyx_t_4 = __pyx_v_self->_c_out->error; __pyx_v_error_result = __pyx_t_4; - /* "src/lxml/serializer.pxi":1198 + /* "src/lxml/serializer.pxi":1199 * raise LxmlSyntaxError("pending open tags on close") * error_result = self._c_out.error * if error_result == xmlerror.XML_ERR_OK: # <<<<<<<<<<<<<< @@ -145717,7 +145723,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p __pyx_t_1 = ((__pyx_v_error_result == XML_ERR_OK) != 0); if (__pyx_t_1) { - /* "src/lxml/serializer.pxi":1199 + /* "src/lxml/serializer.pxi":1200 * error_result = self._c_out.error * if error_result == xmlerror.XML_ERR_OK: * error_result = tree.xmlOutputBufferClose(self._c_out) # <<<<<<<<<<<<<< @@ -145726,7 +145732,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ __pyx_v_error_result = xmlOutputBufferClose(__pyx_v_self->_c_out); - /* "src/lxml/serializer.pxi":1200 + /* "src/lxml/serializer.pxi":1201 * if error_result == xmlerror.XML_ERR_OK: * error_result = tree.xmlOutputBufferClose(self._c_out) * if error_result > 0: # <<<<<<<<<<<<<< @@ -145736,7 +145742,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p __pyx_t_1 = ((__pyx_v_error_result > 0) != 0); if (__pyx_t_1) { - /* "src/lxml/serializer.pxi":1201 + /* "src/lxml/serializer.pxi":1202 * error_result = tree.xmlOutputBufferClose(self._c_out) * if error_result > 0: * error_result = xmlerror.XML_ERR_OK # <<<<<<<<<<<<<< @@ -145745,7 +145751,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ __pyx_v_error_result = XML_ERR_OK; - /* "src/lxml/serializer.pxi":1200 + /* "src/lxml/serializer.pxi":1201 * if error_result == xmlerror.XML_ERR_OK: * error_result = tree.xmlOutputBufferClose(self._c_out) * if error_result > 0: # <<<<<<<<<<<<<< @@ -145754,7 +145760,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ } - /* "src/lxml/serializer.pxi":1198 + /* "src/lxml/serializer.pxi":1199 * raise LxmlSyntaxError("pending open tags on close") * error_result = self._c_out.error * if error_result == xmlerror.XML_ERR_OK: # <<<<<<<<<<<<<< @@ -145764,7 +145770,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p goto __pyx_L6; } - /* "src/lxml/serializer.pxi":1203 + /* "src/lxml/serializer.pxi":1204 * error_result = xmlerror.XML_ERR_OK * else: * tree.xmlOutputBufferClose(self._c_out) # <<<<<<<<<<<<<< @@ -145776,7 +145782,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p } __pyx_L6:; - /* "src/lxml/serializer.pxi":1204 + /* "src/lxml/serializer.pxi":1205 * else: * tree.xmlOutputBufferClose(self._c_out) * self._status = WRITER_FINISHED # <<<<<<<<<<<<<< @@ -145785,7 +145791,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ __pyx_v_self->_status = __pyx_e_4lxml_5etree_WRITER_FINISHED; - /* "src/lxml/serializer.pxi":1205 + /* "src/lxml/serializer.pxi":1206 * tree.xmlOutputBufferClose(self._c_out) * self._status = WRITER_FINISHED * self._c_out = NULL # <<<<<<<<<<<<<< @@ -145794,7 +145800,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ __pyx_v_self->_c_out = NULL; - /* "src/lxml/serializer.pxi":1206 + /* "src/lxml/serializer.pxi":1207 * self._status = WRITER_FINISHED * self._c_out = NULL * del self._element_stack[:] # <<<<<<<<<<<<<< @@ -145803,11 +145809,11 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ if (unlikely(__pyx_v_self->_element_stack == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); - __PYX_ERR(7, 1206, __pyx_L1_error) + __PYX_ERR(7, 1207, __pyx_L1_error) } - if (__Pyx_PyObject_DelSlice(__pyx_v_self->_element_stack, 0, 0, NULL, NULL, NULL, 0, 0, 1) < 0) __PYX_ERR(7, 1206, __pyx_L1_error) + if (__Pyx_PyObject_DelSlice(__pyx_v_self->_element_stack, 0, 0, NULL, NULL, NULL, 0, 0, 1) < 0) __PYX_ERR(7, 1207, __pyx_L1_error) - /* "src/lxml/serializer.pxi":1207 + /* "src/lxml/serializer.pxi":1208 * self._c_out = NULL * del self._element_stack[:] * if raise_on_error: # <<<<<<<<<<<<<< @@ -145817,18 +145823,18 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p __pyx_t_1 = (__pyx_v_raise_on_error != 0); if (__pyx_t_1) { - /* "src/lxml/serializer.pxi":1208 + /* "src/lxml/serializer.pxi":1209 * del self._element_stack[:] * if raise_on_error: * self._handle_error(error_result) # <<<<<<<<<<<<<< * * cdef _handle_error(self, int error_result): */ - __pyx_t_2 = __pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(__pyx_v_self, __pyx_v_error_result); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1208, __pyx_L1_error) + __pyx_t_2 = __pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(__pyx_v_self, __pyx_v_error_result); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1209, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "src/lxml/serializer.pxi":1207 + /* "src/lxml/serializer.pxi":1208 * self._c_out = NULL * del self._element_stack[:] * if raise_on_error: # <<<<<<<<<<<<<< @@ -145837,7 +145843,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p */ } - /* "src/lxml/serializer.pxi":1191 + /* "src/lxml/serializer.pxi":1192 * tree.xmlOutputBufferFlush(self._c_out) * * cdef _close(self, bint raise_on_error): # <<<<<<<<<<<<<< @@ -145859,7 +145865,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__close(struct __p return __pyx_r; } -/* "src/lxml/serializer.pxi":1210 +/* "src/lxml/serializer.pxi":1211 * self._handle_error(error_result) * * cdef _handle_error(self, int error_result): # <<<<<<<<<<<<<< @@ -145876,7 +145882,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(str PyObject *__pyx_t_4 = NULL; __Pyx_RefNannySetupContext("_handle_error", 0); - /* "src/lxml/serializer.pxi":1211 + /* "src/lxml/serializer.pxi":1212 * * cdef _handle_error(self, int error_result): * if error_result != xmlerror.XML_ERR_OK: # <<<<<<<<<<<<<< @@ -145886,7 +145892,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(str __pyx_t_1 = ((__pyx_v_error_result != XML_ERR_OK) != 0); if (__pyx_t_1) { - /* "src/lxml/serializer.pxi":1212 + /* "src/lxml/serializer.pxi":1213 * cdef _handle_error(self, int error_result): * if error_result != xmlerror.XML_ERR_OK: * if self._target is not None: # <<<<<<<<<<<<<< @@ -145897,16 +145903,16 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(str __pyx_t_2 = (__pyx_t_1 != 0); if (__pyx_t_2) { - /* "src/lxml/serializer.pxi":1213 + /* "src/lxml/serializer.pxi":1214 * if error_result != xmlerror.XML_ERR_OK: * if self._target is not None: * self._target._exc_context._raise_if_stored() # <<<<<<<<<<<<<< * _raiseSerialisationError(error_result) * */ - __pyx_t_3 = ((struct __pyx_vtabstruct_4lxml_5etree__ExceptionContext *)__pyx_v_self->_target->_exc_context->__pyx_vtab)->_raise_if_stored(__pyx_v_self->_target->_exc_context); if (unlikely(__pyx_t_3 == -1)) __PYX_ERR(7, 1213, __pyx_L1_error) + __pyx_t_3 = ((struct __pyx_vtabstruct_4lxml_5etree__ExceptionContext *)__pyx_v_self->_target->_exc_context->__pyx_vtab)->_raise_if_stored(__pyx_v_self->_target->_exc_context); if (unlikely(__pyx_t_3 == -1)) __PYX_ERR(7, 1214, __pyx_L1_error) - /* "src/lxml/serializer.pxi":1212 + /* "src/lxml/serializer.pxi":1213 * cdef _handle_error(self, int error_result): * if error_result != xmlerror.XML_ERR_OK: * if self._target is not None: # <<<<<<<<<<<<<< @@ -145915,18 +145921,18 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(str */ } - /* "src/lxml/serializer.pxi":1214 + /* "src/lxml/serializer.pxi":1215 * if self._target is not None: * self._target._exc_context._raise_if_stored() * _raiseSerialisationError(error_result) # <<<<<<<<<<<<<< * * @cython.final */ - __pyx_t_4 = __pyx_f_4lxml_5etree__raiseSerialisationError(__pyx_v_error_result); if (unlikely(!__pyx_t_4)) __PYX_ERR(7, 1214, __pyx_L1_error) + __pyx_t_4 = __pyx_f_4lxml_5etree__raiseSerialisationError(__pyx_v_error_result); if (unlikely(!__pyx_t_4)) __PYX_ERR(7, 1215, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; - /* "src/lxml/serializer.pxi":1211 + /* "src/lxml/serializer.pxi":1212 * * cdef _handle_error(self, int error_result): * if error_result != xmlerror.XML_ERR_OK: # <<<<<<<<<<<<<< @@ -145935,7 +145941,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(str */ } - /* "src/lxml/serializer.pxi":1210 + /* "src/lxml/serializer.pxi":1211 * self._handle_error(error_result) * * cdef _handle_error(self, int error_result): # <<<<<<<<<<<<<< @@ -145956,7 +145962,7 @@ static PyObject *__pyx_f_4lxml_5etree_22_IncrementalFileWriter__handle_error(str return __pyx_r; } -/* "src/lxml/serializer.pxi":1223 +/* "src/lxml/serializer.pxi":1224 * cdef _IncrementalFileWriter _writer * * def __cinit__(self, _IncrementalFileWriter writer not None, element_config): # <<<<<<<<<<<<<< @@ -145992,11 +145998,11 @@ static int __pyx_pw_4lxml_5etree_18_FileWriterElement_1__cinit__(PyObject *__pyx case 1: if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_element_config)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("__cinit__", 1, 2, 2, 1); __PYX_ERR(7, 1223, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__cinit__", 1, 2, 2, 1); __PYX_ERR(7, 1224, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__cinit__") < 0)) __PYX_ERR(7, 1223, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__cinit__") < 0)) __PYX_ERR(7, 1224, __pyx_L3_error) } } else if (PyTuple_GET_SIZE(__pyx_args) != 2) { goto __pyx_L5_argtuple_error; @@ -146009,13 +146015,13 @@ static int __pyx_pw_4lxml_5etree_18_FileWriterElement_1__cinit__(PyObject *__pyx } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("__cinit__", 1, 2, 2, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(7, 1223, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__cinit__", 1, 2, 2, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(7, 1224, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("lxml.etree._FileWriterElement.__cinit__", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return -1; __pyx_L4_argument_unpacking_done:; - if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_writer), __pyx_ptype_4lxml_5etree__IncrementalFileWriter, 0, "writer", 0))) __PYX_ERR(7, 1223, __pyx_L1_error) + if (unlikely(!__Pyx_ArgTypeTest(((PyObject *)__pyx_v_writer), __pyx_ptype_4lxml_5etree__IncrementalFileWriter, 0, "writer", 0))) __PYX_ERR(7, 1224, __pyx_L1_error) __pyx_r = __pyx_pf_4lxml_5etree_18_FileWriterElement___cinit__(((struct __pyx_obj_4lxml_5etree__FileWriterElement *)__pyx_v_self), __pyx_v_writer, __pyx_v_element_config); /* function exit code */ @@ -146032,7 +146038,7 @@ static int __pyx_pf_4lxml_5etree_18_FileWriterElement___cinit__(struct __pyx_obj __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__cinit__", 0); - /* "src/lxml/serializer.pxi":1224 + /* "src/lxml/serializer.pxi":1225 * * def __cinit__(self, _IncrementalFileWriter writer not None, element_config): * self._writer = writer # <<<<<<<<<<<<<< @@ -146045,7 +146051,7 @@ static int __pyx_pf_4lxml_5etree_18_FileWriterElement___cinit__(struct __pyx_obj __Pyx_DECREF(((PyObject *)__pyx_v_self->_writer)); __pyx_v_self->_writer = __pyx_v_writer; - /* "src/lxml/serializer.pxi":1225 + /* "src/lxml/serializer.pxi":1226 * def __cinit__(self, _IncrementalFileWriter writer not None, element_config): * self._writer = writer * self._element = element_config # <<<<<<<<<<<<<< @@ -146058,7 +146064,7 @@ static int __pyx_pf_4lxml_5etree_18_FileWriterElement___cinit__(struct __pyx_obj __Pyx_DECREF(__pyx_v_self->_element); __pyx_v_self->_element = __pyx_v_element_config; - /* "src/lxml/serializer.pxi":1223 + /* "src/lxml/serializer.pxi":1224 * cdef _IncrementalFileWriter _writer * * def __cinit__(self, _IncrementalFileWriter writer not None, element_config): # <<<<<<<<<<<<<< @@ -146072,7 +146078,7 @@ static int __pyx_pf_4lxml_5etree_18_FileWriterElement___cinit__(struct __pyx_obj return __pyx_r; } -/* "src/lxml/serializer.pxi":1227 +/* "src/lxml/serializer.pxi":1228 * self._element = element_config * * def __enter__(self): # <<<<<<<<<<<<<< @@ -146101,7 +146107,7 @@ static PyObject *__pyx_pf_4lxml_5etree_18_FileWriterElement_2__enter__(struct __ PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("__enter__", 0); - /* "src/lxml/serializer.pxi":1228 + /* "src/lxml/serializer.pxi":1229 * * def __enter__(self): * self._writer._write_start_element(self._element) # <<<<<<<<<<<<<< @@ -146110,12 +146116,12 @@ static PyObject *__pyx_pf_4lxml_5etree_18_FileWriterElement_2__enter__(struct __ */ __pyx_t_1 = __pyx_v_self->_element; __Pyx_INCREF(__pyx_t_1); - __pyx_t_2 = __pyx_f_4lxml_5etree_22_IncrementalFileWriter__write_start_element(__pyx_v_self->_writer, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1228, __pyx_L1_error) + __pyx_t_2 = __pyx_f_4lxml_5etree_22_IncrementalFileWriter__write_start_element(__pyx_v_self->_writer, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1229, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "src/lxml/serializer.pxi":1227 + /* "src/lxml/serializer.pxi":1228 * self._element = element_config * * def __enter__(self): # <<<<<<<<<<<<<< @@ -146137,7 +146143,7 @@ static PyObject *__pyx_pf_4lxml_5etree_18_FileWriterElement_2__enter__(struct __ return __pyx_r; } -/* "src/lxml/serializer.pxi":1230 +/* "src/lxml/serializer.pxi":1231 * self._writer._write_start_element(self._element) * * def __exit__(self, exc_type, exc_val, exc_tb): # <<<<<<<<<<<<<< @@ -146175,16 +146181,16 @@ static PyObject *__pyx_pw_4lxml_5etree_18_FileWriterElement_5__exit__(PyObject * case 1: if (likely((values[1] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_exc_val)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("__exit__", 1, 3, 3, 1); __PYX_ERR(7, 1230, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__exit__", 1, 3, 3, 1); __PYX_ERR(7, 1231, __pyx_L3_error) } case 2: if (likely((values[2] = PyDict_GetItem(__pyx_kwds, __pyx_n_s_exc_tb)) != 0)) kw_args--; else { - __Pyx_RaiseArgtupleInvalid("__exit__", 1, 3, 3, 2); __PYX_ERR(7, 1230, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__exit__", 1, 3, 3, 2); __PYX_ERR(7, 1231, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { - if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__exit__") < 0)) __PYX_ERR(7, 1230, __pyx_L3_error) + if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_pyargnames, 0, values, pos_args, "__exit__") < 0)) __PYX_ERR(7, 1231, __pyx_L3_error) } } else if (PyTuple_GET_SIZE(__pyx_args) != 3) { goto __pyx_L5_argtuple_error; @@ -146199,7 +146205,7 @@ static PyObject *__pyx_pw_4lxml_5etree_18_FileWriterElement_5__exit__(PyObject * } goto __pyx_L4_argument_unpacking_done; __pyx_L5_argtuple_error:; - __Pyx_RaiseArgtupleInvalid("__exit__", 1, 3, 3, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(7, 1230, __pyx_L3_error) + __Pyx_RaiseArgtupleInvalid("__exit__", 1, 3, 3, PyTuple_GET_SIZE(__pyx_args)); __PYX_ERR(7, 1231, __pyx_L3_error) __pyx_L3_error:; __Pyx_AddTraceback("lxml.etree._FileWriterElement.__exit__", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); @@ -146219,19 +146225,19 @@ static PyObject *__pyx_pf_4lxml_5etree_18_FileWriterElement_4__exit__(struct __p PyObject *__pyx_t_2 = NULL; __Pyx_RefNannySetupContext("__exit__", 0); - /* "src/lxml/serializer.pxi":1231 + /* "src/lxml/serializer.pxi":1232 * * def __exit__(self, exc_type, exc_val, exc_tb): * self._writer._write_end_element(self._element) # <<<<<<<<<<<<<< */ __pyx_t_1 = __pyx_v_self->_element; __Pyx_INCREF(__pyx_t_1); - __pyx_t_2 = __pyx_f_4lxml_5etree_22_IncrementalFileWriter__write_end_element(__pyx_v_self->_writer, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1231, __pyx_L1_error) + __pyx_t_2 = __pyx_f_4lxml_5etree_22_IncrementalFileWriter__write_end_element(__pyx_v_self->_writer, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(7, 1232, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; - /* "src/lxml/serializer.pxi":1230 + /* "src/lxml/serializer.pxi":1231 * self._writer._write_start_element(self._element) * * def __exit__(self, exc_type, exc_val, exc_tb): # <<<<<<<<<<<<<< @@ -216633,7 +216639,6 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {&__pyx_kp_b_http_www_w3_org_1999_XSL_Transfo, __pyx_k_http_www_w3_org_1999_XSL_Transfo, sizeof(__pyx_k_http_www_w3_org_1999_XSL_Transfo), 0, 0, 0, 0}, {&__pyx_kp_u_http_www_w3_org_1999_XSL_Transfo, __pyx_k_http_www_w3_org_1999_XSL_Transfo, sizeof(__pyx_k_http_www_w3_org_1999_XSL_Transfo), 0, 1, 0, 0}, {&__pyx_kp_b_http_www_w3_org_1999_xhtml, __pyx_k_http_www_w3_org_1999_xhtml, sizeof(__pyx_k_http_www_w3_org_1999_xhtml), 0, 0, 0, 0}, - {&__pyx_kp_s_http_www_w3_org_1999_xhtml, __pyx_k_http_www_w3_org_1999_xhtml, sizeof(__pyx_k_http_www_w3_org_1999_xhtml), 0, 0, 1, 0}, {&__pyx_kp_b_http_www_w3_org_2001_XMLSchema, __pyx_k_http_www_w3_org_2001_XMLSchema, sizeof(__pyx_k_http_www_w3_org_2001_XMLSchema), 0, 0, 0, 0}, {&__pyx_kp_u_http_www_w3_org_2001_XMLSchema, __pyx_k_http_www_w3_org_2001_XMLSchema, sizeof(__pyx_k_http_www_w3_org_2001_XMLSchema), 0, 1, 0, 0}, {&__pyx_kp_b_http_www_w3_org_2001_XMLSchema_i, __pyx_k_http_www_w3_org_2001_XMLSchema_i, sizeof(__pyx_k_http_www_w3_org_2001_XMLSchema_i), 0, 0, 0, 0}, @@ -216915,7 +216920,7 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {&__pyx_kp_s_s_s_object_name_r_type_r_occur, __pyx_k_s_s_object_name_r_type_r_occur, sizeof(__pyx_k_s_s_object_name_r_type_r_occur), 0, 0, 1, 0}, {&__pyx_kp_u_s_w_s_s, __pyx_k_s_w_s_s, sizeof(__pyx_k_s_w_s_s), 0, 1, 0, 0}, {&__pyx_n_s_schema, __pyx_k_schema, sizeof(__pyx_k_schema), 0, 0, 1, 1}, - {&__pyx_n_s_script, __pyx_k_script, sizeof(__pyx_k_script), 0, 0, 1, 1}, + {&__pyx_n_b_script, __pyx_k_script, sizeof(__pyx_k_script), 0, 0, 0, 1}, {&__pyx_n_s_search, __pyx_k_search, sizeof(__pyx_k_search), 0, 0, 1, 1}, {&__pyx_n_s_self, __pyx_k_self, sizeof(__pyx_k_self), 0, 0, 1, 1}, {&__pyx_n_s_self_node, __pyx_k_self_node, sizeof(__pyx_k_self_node), 0, 0, 1, 1}, @@ -216960,6 +216965,7 @@ static __Pyx_StringTabEntry __pyx_string_tab[] = { {&__pyx_n_s_strip_tags, __pyx_k_strip_tags, sizeof(__pyx_k_strip_tags), 0, 0, 1, 1}, {&__pyx_n_s_strparam, __pyx_k_strparam, sizeof(__pyx_k_strparam), 0, 0, 1, 1}, {&__pyx_n_s_strval, __pyx_k_strval, sizeof(__pyx_k_strval), 0, 0, 1, 1}, + {&__pyx_n_b_style, __pyx_k_style, sizeof(__pyx_k_style), 0, 0, 0, 1}, {&__pyx_n_s_style, __pyx_k_style, sizeof(__pyx_k_style), 0, 0, 1, 1}, {&__pyx_n_s_sub, __pyx_k_sub, sizeof(__pyx_k_sub), 0, 0, 1, 1}, {&__pyx_n_s_super, __pyx_k_super, sizeof(__pyx_k_super), 0, 0, 1, 1}, @@ -217719,36 +217725,36 @@ static int __Pyx_InitCachedConstants(void) { __Pyx_GOTREF(__pyx_tuple__76); __Pyx_GIVEREF(__pyx_tuple__76); - /* "src/lxml/serializer.pxi":1170 + /* "src/lxml/serializer.pxi":1171 * elif iselement(content): * if self._status > WRITER_IN_ELEMENT: * raise LxmlSyntaxError("cannot append trailing element to complete XML document") # <<<<<<<<<<<<<< * _writeNodeToBuffer(self._c_out, (<_Element>content)._c_node, * self._c_encoding, NULL, c_method, */ - __pyx_tuple__77 = PyTuple_Pack(1, __pyx_kp_s_cannot_append_trailing_element_t); if (unlikely(!__pyx_tuple__77)) __PYX_ERR(7, 1170, __pyx_L1_error) + __pyx_tuple__77 = PyTuple_Pack(1, __pyx_kp_s_cannot_append_trailing_element_t); if (unlikely(!__pyx_tuple__77)) __PYX_ERR(7, 1171, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__77); __Pyx_GIVEREF(__pyx_tuple__77); - /* "src/lxml/serializer.pxi":1194 + /* "src/lxml/serializer.pxi":1195 * if raise_on_error: * if self._status < WRITER_IN_ELEMENT: * raise LxmlSyntaxError("no content written") # <<<<<<<<<<<<<< * if self._element_stack: * raise LxmlSyntaxError("pending open tags on close") */ - __pyx_tuple__78 = PyTuple_Pack(1, __pyx_kp_s_no_content_written); if (unlikely(!__pyx_tuple__78)) __PYX_ERR(7, 1194, __pyx_L1_error) + __pyx_tuple__78 = PyTuple_Pack(1, __pyx_kp_s_no_content_written); if (unlikely(!__pyx_tuple__78)) __PYX_ERR(7, 1195, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__78); __Pyx_GIVEREF(__pyx_tuple__78); - /* "src/lxml/serializer.pxi":1196 + /* "src/lxml/serializer.pxi":1197 * raise LxmlSyntaxError("no content written") * if self._element_stack: * raise LxmlSyntaxError("pending open tags on close") # <<<<<<<<<<<<<< * error_result = self._c_out.error * if error_result == xmlerror.XML_ERR_OK: */ - __pyx_tuple__79 = PyTuple_Pack(1, __pyx_kp_s_pending_open_tags_on_close); if (unlikely(!__pyx_tuple__79)) __PYX_ERR(7, 1196, __pyx_L1_error) + __pyx_tuple__79 = PyTuple_Pack(1, __pyx_kp_s_pending_open_tags_on_close); if (unlikely(!__pyx_tuple__79)) __PYX_ERR(7, 1197, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__79); __Pyx_GIVEREF(__pyx_tuple__79); @@ -220446,40 +220452,40 @@ static int __Pyx_InitCachedConstants(void) { __Pyx_GIVEREF(__pyx_tuple__501); __pyx_codeobj__502 = (PyObject*)__Pyx_PyCode_New(1, 3, 10, 0, CO_VARARGS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__501, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_home_stefan_source_Python_lxml_10, __pyx_n_s_write, 1143, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__502)) __PYX_ERR(7, 1143, __pyx_L1_error) - /* "src/lxml/serializer.pxi":1183 + /* "src/lxml/serializer.pxi":1184 * tree.xmlOutputBufferFlush(self._c_out) * * def flush(self): # <<<<<<<<<<<<<< * """flush(self) * */ - __pyx_tuple__503 = PyTuple_Pack(1, __pyx_n_s_self); if (unlikely(!__pyx_tuple__503)) __PYX_ERR(7, 1183, __pyx_L1_error) + __pyx_tuple__503 = PyTuple_Pack(1, __pyx_n_s_self); if (unlikely(!__pyx_tuple__503)) __PYX_ERR(7, 1184, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__503); __Pyx_GIVEREF(__pyx_tuple__503); - __pyx_codeobj__504 = (PyObject*)__Pyx_PyCode_New(1, 0, 1, 0, 0, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__503, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_home_stefan_source_Python_lxml_10, __pyx_n_s_flush, 1183, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__504)) __PYX_ERR(7, 1183, __pyx_L1_error) + __pyx_codeobj__504 = (PyObject*)__Pyx_PyCode_New(1, 0, 1, 0, 0, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__503, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_home_stefan_source_Python_lxml_10, __pyx_n_s_flush, 1184, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__504)) __PYX_ERR(7, 1184, __pyx_L1_error) - /* "src/lxml/serializer.pxi":1227 + /* "src/lxml/serializer.pxi":1228 * self._element = element_config * * def __enter__(self): # <<<<<<<<<<<<<< * self._writer._write_start_element(self._element) * */ - __pyx_tuple__505 = PyTuple_Pack(1, __pyx_n_s_self); if (unlikely(!__pyx_tuple__505)) __PYX_ERR(7, 1227, __pyx_L1_error) + __pyx_tuple__505 = PyTuple_Pack(1, __pyx_n_s_self); if (unlikely(!__pyx_tuple__505)) __PYX_ERR(7, 1228, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__505); __Pyx_GIVEREF(__pyx_tuple__505); - __pyx_codeobj__506 = (PyObject*)__Pyx_PyCode_New(1, 0, 1, 0, 0, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__505, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_home_stefan_source_Python_lxml_10, __pyx_n_s_enter, 1227, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__506)) __PYX_ERR(7, 1227, __pyx_L1_error) + __pyx_codeobj__506 = (PyObject*)__Pyx_PyCode_New(1, 0, 1, 0, 0, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__505, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_home_stefan_source_Python_lxml_10, __pyx_n_s_enter, 1228, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__506)) __PYX_ERR(7, 1228, __pyx_L1_error) - /* "src/lxml/serializer.pxi":1230 + /* "src/lxml/serializer.pxi":1231 * self._writer._write_start_element(self._element) * * def __exit__(self, exc_type, exc_val, exc_tb): # <<<<<<<<<<<<<< * self._writer._write_end_element(self._element) */ - __pyx_tuple__507 = PyTuple_Pack(4, __pyx_n_s_self, __pyx_n_s_exc_type, __pyx_n_s_exc_val, __pyx_n_s_exc_tb); if (unlikely(!__pyx_tuple__507)) __PYX_ERR(7, 1230, __pyx_L1_error) + __pyx_tuple__507 = PyTuple_Pack(4, __pyx_n_s_self, __pyx_n_s_exc_type, __pyx_n_s_exc_val, __pyx_n_s_exc_tb); if (unlikely(!__pyx_tuple__507)) __PYX_ERR(7, 1231, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__507); __Pyx_GIVEREF(__pyx_tuple__507); - __pyx_codeobj__508 = (PyObject*)__Pyx_PyCode_New(4, 0, 4, 0, 0, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__507, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_home_stefan_source_Python_lxml_10, __pyx_n_s_exit, 1230, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__508)) __PYX_ERR(7, 1230, __pyx_L1_error) + __pyx_codeobj__508 = (PyObject*)__Pyx_PyCode_New(4, 0, 4, 0, 0, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__507, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_home_stefan_source_Python_lxml_10, __pyx_n_s_exit, 1231, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__508)) __PYX_ERR(7, 1231, __pyx_L1_error) /* "src/lxml/iterparse.pxi":147 * return self._parser.version @@ -222321,7 +222327,7 @@ PyMODINIT_FUNC PyInit_etree(void) __pyx_type_4lxml_5etree__IncrementalFileWriter.tp_print = 0; if (__Pyx_SetVtable(__pyx_type_4lxml_5etree__IncrementalFileWriter.tp_dict, __pyx_vtabptr_4lxml_5etree__IncrementalFileWriter) < 0) __PYX_ERR(7, 944, __pyx_L1_error) __pyx_ptype_4lxml_5etree__IncrementalFileWriter = &__pyx_type_4lxml_5etree__IncrementalFileWriter; - if (PyType_Ready(&__pyx_type_4lxml_5etree__FileWriterElement) < 0) __PYX_ERR(7, 1219, __pyx_L1_error) + if (PyType_Ready(&__pyx_type_4lxml_5etree__FileWriterElement) < 0) __PYX_ERR(7, 1220, __pyx_L1_error) __pyx_type_4lxml_5etree__FileWriterElement.tp_print = 0; __pyx_ptype_4lxml_5etree__FileWriterElement = &__pyx_type_4lxml_5etree__FileWriterElement; __pyx_vtabptr_4lxml_5etree_iterparse = &__pyx_vtable_4lxml_5etree_iterparse; @@ -227901,41 +227907,41 @@ PyMODINIT_FUNC PyInit_etree(void) __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; PyType_Modified(__pyx_ptype_4lxml_5etree__IncrementalFileWriter); - /* "src/lxml/serializer.pxi":1183 + /* "src/lxml/serializer.pxi":1184 * tree.xmlOutputBufferFlush(self._c_out) * * def flush(self): # <<<<<<<<<<<<<< * """flush(self) * */ - __pyx_t_6 = __Pyx_CyFunction_NewEx(&__pyx_mdef_4lxml_5etree_22_IncrementalFileWriter_13flush, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_IncrementalFileWriter_flush, NULL, __pyx_n_s_lxml_etree, __pyx_d, ((PyObject *)__pyx_codeobj__504)); if (unlikely(!__pyx_t_6)) __PYX_ERR(7, 1183, __pyx_L1_error) + __pyx_t_6 = __Pyx_CyFunction_NewEx(&__pyx_mdef_4lxml_5etree_22_IncrementalFileWriter_13flush, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_IncrementalFileWriter_flush, NULL, __pyx_n_s_lxml_etree, __pyx_d, ((PyObject *)__pyx_codeobj__504)); if (unlikely(!__pyx_t_6)) __PYX_ERR(7, 1184, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); - if (PyDict_SetItem((PyObject *)__pyx_ptype_4lxml_5etree__IncrementalFileWriter->tp_dict, __pyx_n_s_flush, __pyx_t_6) < 0) __PYX_ERR(7, 1183, __pyx_L1_error) + if (PyDict_SetItem((PyObject *)__pyx_ptype_4lxml_5etree__IncrementalFileWriter->tp_dict, __pyx_n_s_flush, __pyx_t_6) < 0) __PYX_ERR(7, 1184, __pyx_L1_error) __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; PyType_Modified(__pyx_ptype_4lxml_5etree__IncrementalFileWriter); - /* "src/lxml/serializer.pxi":1227 + /* "src/lxml/serializer.pxi":1228 * self._element = element_config * * def __enter__(self): # <<<<<<<<<<<<<< * self._writer._write_start_element(self._element) * */ - __pyx_t_6 = __Pyx_CyFunction_NewEx(&__pyx_mdef_4lxml_5etree_18_FileWriterElement_3__enter__, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_FileWriterElement___enter, NULL, __pyx_n_s_lxml_etree, __pyx_d, ((PyObject *)__pyx_codeobj__506)); if (unlikely(!__pyx_t_6)) __PYX_ERR(7, 1227, __pyx_L1_error) + __pyx_t_6 = __Pyx_CyFunction_NewEx(&__pyx_mdef_4lxml_5etree_18_FileWriterElement_3__enter__, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_FileWriterElement___enter, NULL, __pyx_n_s_lxml_etree, __pyx_d, ((PyObject *)__pyx_codeobj__506)); if (unlikely(!__pyx_t_6)) __PYX_ERR(7, 1228, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); - if (PyDict_SetItem((PyObject *)__pyx_ptype_4lxml_5etree__FileWriterElement->tp_dict, __pyx_n_s_enter, __pyx_t_6) < 0) __PYX_ERR(7, 1227, __pyx_L1_error) + if (PyDict_SetItem((PyObject *)__pyx_ptype_4lxml_5etree__FileWriterElement->tp_dict, __pyx_n_s_enter, __pyx_t_6) < 0) __PYX_ERR(7, 1228, __pyx_L1_error) __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; PyType_Modified(__pyx_ptype_4lxml_5etree__FileWriterElement); - /* "src/lxml/serializer.pxi":1230 + /* "src/lxml/serializer.pxi":1231 * self._writer._write_start_element(self._element) * * def __exit__(self, exc_type, exc_val, exc_tb): # <<<<<<<<<<<<<< * self._writer._write_end_element(self._element) */ - __pyx_t_6 = __Pyx_CyFunction_NewEx(&__pyx_mdef_4lxml_5etree_18_FileWriterElement_5__exit__, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_FileWriterElement___exit, NULL, __pyx_n_s_lxml_etree, __pyx_d, ((PyObject *)__pyx_codeobj__508)); if (unlikely(!__pyx_t_6)) __PYX_ERR(7, 1230, __pyx_L1_error) + __pyx_t_6 = __Pyx_CyFunction_NewEx(&__pyx_mdef_4lxml_5etree_18_FileWriterElement_5__exit__, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_FileWriterElement___exit, NULL, __pyx_n_s_lxml_etree, __pyx_d, ((PyObject *)__pyx_codeobj__508)); if (unlikely(!__pyx_t_6)) __PYX_ERR(7, 1231, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); - if (PyDict_SetItem((PyObject *)__pyx_ptype_4lxml_5etree__FileWriterElement->tp_dict, __pyx_n_s_exit, __pyx_t_6) < 0) __PYX_ERR(7, 1230, __pyx_L1_error) + if (PyDict_SetItem((PyObject *)__pyx_ptype_4lxml_5etree__FileWriterElement->tp_dict, __pyx_n_s_exit, __pyx_t_6) < 0) __PYX_ERR(7, 1231, __pyx_L1_error) __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; PyType_Modified(__pyx_ptype_4lxml_5etree__FileWriterElement); diff --git a/src/lxml/serializer.pxi b/src/lxml/serializer.pxi index d16b08a1..8cee18d8 100644 --- a/src/lxml/serializer.pxi +++ b/src/lxml/serializer.pxi @@ -1159,9 +1159,10 @@ cdef class _IncrementalFileWriter: content = _utf8(content) ns, name, _, _ = self._element_stack[-1] - if c_method == OUTPUT_METHOD_HTML and \ - ns in (None, 'http://www.w3.org/1999/xhtml') and name in ('script', 'style'): - tree.xmlOutputBufferWrite(self._c_out, len(content), content) + if (c_method == OUTPUT_METHOD_HTML and + ns in (None, b'http://www.w3.org/1999/xhtml') and + name in (b'script', b'style')): + tree.xmlOutputBufferWrite(self._c_out, len(content), _cstr(content)) else: tree.xmlOutputBufferWriteEscape(self._c_out, _xcstr(content), NULL) diff --git a/src/lxml/tests/common_imports.py b/src/lxml/tests/common_imports.py index 85b1157d..3a73a29e 100644 --- a/src/lxml/tests/common_imports.py +++ b/src/lxml/tests/common_imports.py @@ -117,12 +117,15 @@ def _get_caller_relative_path(filename, frame_depth=2): from io import StringIO +unichr_escape = re.compile(r'\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}') + if sys.version_info[0] >= 3: # Python 3 from builtins import str as unicode + from codecs import unicode_escape_decode _chr = chr def _str(s, encoding="UTF-8"): - return s + return unichr_escape.sub(lambda x: unicode_escape_decode(x.group(0))[0], s) def _bytes(s, encoding="UTF-8"): return s.encode(encoding) from io import BytesIO as _BytesIO @@ -144,8 +147,6 @@ if sys.version_info[0] >= 3: doctests, {}, os.path.basename(filename), filename, 0)) else: # Python 2 - unichr_escape = re.compile(r'\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}') - from __builtin__ import unicode _chr = unichr def _str(s, encoding="UTF-8"): @@ -174,12 +175,16 @@ else: try: skipIf = unittest.skipIf except AttributeError: - def skipIf(condition, why, - _skip=lambda test_method: None, - _keep=lambda test_method: test_method): + def skipIf(condition, why): + def _skip(thing): + import types + if isinstance(thing, (type, types.ClassType)): + return type(thing.__name__, (object,), {}) + else: + return None if condition: return _skip - return _keep + return lambda thing: thing class HelperTestCase(unittest.TestCase): diff --git a/src/lxml/tests/test_incremental_xmlfile.py b/src/lxml/tests/test_incremental_xmlfile.py index 7a7e0730..867db4a8 100644 --- a/src/lxml/tests/test_incremental_xmlfile.py +++ b/src/lxml/tests/test_incremental_xmlfile.py @@ -2,11 +2,9 @@ """ Tests for the incremental XML serialisation API. - -Tests require Python 2.5 or later. """ -from __future__ import with_statement +from __future__ import with_statement, absolute_import import unittest import tempfile, os, sys @@ -15,7 +13,7 @@ this_dir = os.path.dirname(__file__) if this_dir not in sys.path: sys.path.insert(0, this_dir) # needed for Py3 -from common_imports import etree, BytesIO, HelperTestCase, skipIf, _str +from .common_imports import etree, BytesIO, HelperTestCase, skipIf, _str class _XmlFileTestCaseBase(HelperTestCase): @@ -286,6 +284,7 @@ class TempXmlFileTestCase(_XmlFileTestCaseBase): self._file = tempfile.TemporaryFile() +@skipIf(sys.platform.startswith("win"), "Can't reopen temporary files on Windows") class TempPathXmlFileTestCase(_XmlFileTestCaseBase): def setUp(self): self._tmpfile = tempfile.NamedTemporaryFile() diff --git a/tools/manylinux/build-wheels.sh b/tools/manylinux/build-wheels.sh index 5c92d7af..308c38a9 100755 --- a/tools/manylinux/build-wheels.sh +++ b/tools/manylinux/build-wheels.sh @@ -65,7 +65,8 @@ repair_wheels() { } show_wheels() { - ls -l $WHEELHOUSE + filename=${SDIST##*/} + ls -l $WHEELHOUSE/${filename%%.tar.gz} } prepare_system diff --git a/version.txt b/version.txt index 0b2eb36f..c1e43e6d 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -3.7.2 +3.7.3