From 2d9245c4ed1367dd243d0bdcda5509c74803a834 Mon Sep 17 00:00:00 2001 From: Dieter Verfaillie Date: Wed, 4 Jul 2012 07:50:14 +0200 Subject: [PATCH] giscanner: construct list of possible tag names for TAG_RE from _ALL_TAGS... ... instead of having a secondary hard-coded list. This results in the removal of giscanner/annotationpatterns.py to prevent a circular import. https://bugzilla.gnome.org/show_bug.cgi?id=688897 --- Makefile-giscanner.am | 1 - giscanner/annotationparser.py | 224 ++++++++++++++++++++- giscanner/annotationpatterns.py | 252 ------------------------ tests/scanner/annotationparser/test_patterns.py | 4 +- 4 files changed, 221 insertions(+), 260 deletions(-) delete mode 100644 giscanner/annotationpatterns.py diff --git a/Makefile-giscanner.am b/Makefile-giscanner.am index d4d2a62..2bb9b6d 100644 --- a/Makefile-giscanner.am +++ b/Makefile-giscanner.am @@ -30,7 +30,6 @@ pkgpyexec_PYTHON = \ giscanner/__init__.py \ giscanner/annotationmain.py \ giscanner/annotationparser.py \ - giscanner/annotationpatterns.py \ giscanner/ast.py \ giscanner/cachestore.py \ giscanner/codegen.py \ diff --git a/giscanner/annotationparser.py b/giscanner/annotationparser.py index f3bf71e..509579f 100644 --- a/giscanner/annotationparser.py +++ b/giscanner/annotationparser.py @@ -26,11 +26,6 @@ import re from . import message -from .annotationpatterns import (COMMENT_START_RE, COMMENT_END_RE, - COMMENT_ASTERISK_RE, EMPTY_LINE_RE, - SECTION_RE, SYMBOL_RE, PROPERTY_RE, SIGNAL_RE, - PARAMETER_RE, DESCRIPTION_TAG_RE, TAG_RE, - MULTILINE_ANNOTATION_CONTINUATION_RE) from .odict import odict @@ -137,6 +132,225 @@ OPT_TRANSFER_FULL = 'full' OPT_TRANSFER_FLOATING = 'floating' +#The following regular expression programs are built to: +# - match (or substitute) a single comment block line at a time; +# - support MULTILINE mode and should support (but remains untested) +# LOCALE and UNICODE modes. + +# Program matching the start of a comment block. +# +# Results in 0 symbolic groups. +COMMENT_START_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + / # 1 forward slash character + \*{2} # exactly 2 asterisk characters + [^\S\n\r]* # 0 or more whitespace characters + $ # end + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching the end of a comment block. +# +# Results in 0 symbolic groups. +COMMENT_END_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + \*+ # 1 or more asterisk characters + / # 1 forward slash character + $ # end + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching the ' * ' at the beginning of every +# line inside a comment block. +# +# Results in 0 symbolic groups. +COMMENT_ASTERISK_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + \* # 1 asterisk character + [^\S\n\r]? # 0 or 1 whitespace characters. Careful, + # removing more than 1 whitespace + # character would break embedded + # example program indentation + ''', + re.VERBOSE) + +# Program matching an empty line. +# +# Results in 0 symbolic groups. +EMPTY_LINE_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + $ # end + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching SECTION identifiers. +# +# Results in 2 symbolic groups: +# - group 1 = colon +# - group 2 = section_name +SECTION_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + SECTION # SECTION + [^\S\n\r]* # 0 or more whitespace characters + (?P:?) # colon + [^\S\n\r]* # 0 or more whitespace characters + (?P\w\S+)? # section name + [^\S\n\r]* # 0 or more whitespace characters + $ + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching symbol (function, constant, struct and enum) identifiers. +# +# Results in 3 symbolic groups: +# - group 1 = symbol_name +# - group 2 = colon +# - group 3 = annotations +SYMBOL_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + (?P[\w-]*\w) # symbol name + [^\S\n\r]* # 0 or more whitespace characters + (?P:?) # colon + [^\S\n\r]* # 0 or more whitespace characters + (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations + [^\S\n\r]* # 0 or more whitespace characters + $ # end + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching property identifiers. +# +# Results in 4 symbolic groups: +# - group 1 = class_name +# - group 2 = property_name +# - group 3 = colon +# - group 4 = annotations +PROPERTY_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + (?P[\w]+) # class name + [^\S\n\r]* # 0 or more whitespace characters + :{1} # required colon + [^\S\n\r]* # 0 or more whitespace characters + (?P[\w-]*\w) # property name + [^\S\n\r]* # 0 or more whitespace characters + (?P:?) # colon + [^\S\n\r]* # 0 or more whitespace characters + (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations + [^\S\n\r]* # 0 or more whitespace characters + $ # end + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching signal identifiers. +# +# Results in 4 symbolic groups: +# - group 1 = class_name +# - group 2 = signal_name +# - group 3 = colon +# - group 4 = annotations +SIGNAL_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + (?P[\w]+) # class name + [^\S\n\r]* # 0 or more whitespace characters + :{2} # 2 required colons + [^\S\n\r]* # 0 or more whitespace characters + (?P[\w-]*\w) # signal name + [^\S\n\r]* # 0 or more whitespace characters + (?P:?) # colon + [^\S\n\r]* # 0 or more whitespace characters + (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations + [^\S\n\r]* # 0 or more whitespace characters + $ # end + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching parameters. +# +# Results in 4 symbolic groups: +# - group 1 = parameter_name +# - group 2 = annotations +# - group 3 = colon +# - group 4 = description +PARAMETER_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + @ # @ character + (?P[\w-]*\w|\.\.\.) # parameter name + [^\S\n\r]* # 0 or more whitespace characters + :{1} # required colon + [^\S\n\r]* # 0 or more whitespace characters + (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations + (?P:?) # colon + [^\S\n\r]* # 0 or more whitespace characters + (?P.*?) # description + [^\S\n\r]* # 0 or more whitespace characters + $ # end + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching old style "Description:" tag. +# +# Results in 0 symbolic groups. +DESCRIPTION_TAG_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + Description: # 'Description:' literal + ''', + re.VERBOSE | re.MULTILINE) + +# Program matching tags. +# +# Results in 4 symbolic groups: +# - group 1 = tag_name +# - group 2 = annotations +# - group 3 = colon +# - group 4 = description +_all_tags = '|'.join(_ALL_TAGS).replace(' ', '\\ ') +TAG_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + (?P''' + _all_tags + r''') # tag name + [^\S\n\r]* # 0 or more whitespace characters + :{1} # required colon + [^\S\n\r]* # 0 or more whitespace characters + (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations + (?P:?) # colon + [^\S\n\r]* # 0 or more whitespace characters + (?P.*?) # description + [^\S\n\r]* # 0 or more whitespace characters + $ # end + ''', + re.VERBOSE | re.MULTILINE | re.IGNORECASE) + +# Program matching multiline annotation continuations. +# This is used on multiline parameters and tags (but not on the first line) to +# generate warnings about invalid annotations spanning multiple lines. +# +# Results in 3 symbolic groups: +# - group 2 = annotations +# - group 3 = colon +# - group 4 = description +MULTILINE_ANNOTATION_CONTINUATION_RE = re.compile(r''' + ^ # start + [^\S\n\r]* # 0 or more whitespace characters + (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations + (?P:) # colon + [^\S\n\r]* # 0 or more whitespace characters + (?P.*?) # description + [^\S\n\r]* # 0 or more whitespace characters + $ # end + ''', + re.VERBOSE | re.MULTILINE) + + class DocBlock(object): def __init__(self, name): diff --git a/giscanner/annotationpatterns.py b/giscanner/annotationpatterns.py deleted file mode 100644 index 95c11c9..0000000 --- a/giscanner/annotationpatterns.py +++ /dev/null @@ -1,252 +0,0 @@ -# -*- Mode: Python -*- -# GObject-Introspection - a framework for introspecting GObject libraries -# Copyright (C) 2012 Dieter Verfaillie -# -# This program is free software; you can redistribute it and/or -# modify it under the terms of the GNU General Public License -# as published by the Free Software Foundation; either version 2 -# of the License, or (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA -# 02110-1301, USA. -# - - -''' -This module provides regular expression programs that can be used to identify -and extract useful information from different parts of GTK-Doc comment blocks. -These programs are built to: - - match (or substitute) a single comment block line at a time; - - support MULTILINE mode and should support (but remains untested) - LOCALE and UNICODE modes. -''' - - -import re - - -# Program matching the start of a comment block. -# -# Results in 0 symbolic groups. -COMMENT_START_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - / # 1 forward slash character - \*{2} # exactly 2 asterisk characters - [^\S\n\r]* # 0 or more whitespace characters - $ # end - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching the end of a comment block. -# -# Results in 0 symbolic groups. -COMMENT_END_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - \*+ # 1 or more asterisk characters - / # 1 forward slash character - $ # end - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching the "*" at the beginning of every -# line inside a comment block. -# -# Results in 0 symbolic groups. -COMMENT_ASTERISK_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - \* # 1 asterisk character - [^\S\n\r]? # 0 or 1 whitespace characters - # Carefull: removing more would - # break embedded example program - # indentation - ''', - re.VERBOSE) - -# Program matching an empty line. -# -# Results in 0 symbolic groups. -EMPTY_LINE_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or 1 whitespace characters - $ # end - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching SECTION identifiers. -# -# Results in 2 symbolic groups: -# - group 1 = colon -# - group 2 = section_name -SECTION_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - SECTION # SECTION - [^\S\n\r]* # 0 or more whitespace characters - (?P:?) # colon - [^\S\n\r]* # 0 or more whitespace characters - (?P\w\S+)? # section name - [^\S\n\r]* # 0 or more whitespace characters - $ - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching symbol (function, constant, struct and enum) identifiers. -# -# Results in 3 symbolic groups: -# - group 1 = symbol_name -# - group 2 = colon -# - group 3 = annotations -SYMBOL_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - (?P[\w-]*\w) # symbol name - [^\S\n\r]* # 0 or more whitespace characters - (?P:?) # colon - [^\S\n\r]* # 0 or more whitespace characters - (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations - [^\S\n\r]* # 0 or more whitespace characters - $ # end - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching property identifiers. -# -# Results in 4 symbolic groups: -# - group 1 = class_name -# - group 2 = property_name -# - group 3 = colon -# - group 4 = annotations -PROPERTY_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - (?P[\w]+) # class name - [^\S\n\r]* # 0 or more whitespace characters - :{1} # required colon - [^\S\n\r]* # 0 or more whitespace characters - (?P[\w-]*\w) # property name - [^\S\n\r]* # 0 or more whitespace characters - (?P:?) # colon - [^\S\n\r]* # 0 or more whitespace characters - (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations - [^\S\n\r]* # 0 or more whitespace characters - $ # end - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching signal identifiers. -# -# Results in 4 symbolic groups: -# - group 1 = class_name -# - group 2 = signal_name -# - group 3 = colon -# - group 4 = annotations -SIGNAL_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - (?P[\w]+) # class name - [^\S\n\r]* # 0 or more whitespace characters - :{2} # 2 required colons - [^\S\n\r]* # 0 or more whitespace characters - (?P[\w-]*\w) # signal name - [^\S\n\r]* # 0 or more whitespace characters - (?P:?) # colon - [^\S\n\r]* # 0 or more whitespace characters - (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations - [^\S\n\r]* # 0 or more whitespace characters - $ # end - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching parameters. -# -# Results in 4 symbolic groups: -# - group 1 = parameter_name -# - group 2 = annotations -# - group 3 = colon -# - group 4 = description -PARAMETER_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - @ # @ character - (?P[\w-]*\w|\.\.\.) # parameter name - [^\S\n\r]* # 0 or more whitespace characters - :{1} # required colon - [^\S\n\r]* # 0 or more whitespace characters - (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations - (?P:?) # colon - [^\S\n\r]* # 0 or more whitespace characters - (?P.*?) # description - [^\S\n\r]* # 0 or more whitespace characters - $ # end - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching old style "Description:" tag. -# -# Results in 0 symbolic groups. -DESCRIPTION_TAG_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - Description: # 'Description:' literal - ''', - re.VERBOSE | re.MULTILINE) - -# Program matching tags. -# -# Results in 4 symbolic groups: -# - group 1 = tag_name -# - group 2 = annotations -# - group 3 = colon -# - group 4 = description -TAG_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - (?Pvirtual|since|stability| - deprecated|returns| - return\ value|attributes| - rename\ to|type| - unref\ func|ref\ func| - set\ value\ func| - get\ value\ func| - transfer|value) # tag name - [^\S\n\r]* # 0 or more whitespace characters - :{1} # required colon - [^\S\n\r]* # 0 or more whitespace characters - (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations - (?P:?) # colon - [^\S\n\r]* # 0 or more whitespace characters - (?P.*?) # description - [^\S\n\r]* # 0 or more whitespace characters - $ # end - ''', - re.VERBOSE | re.MULTILINE | re.IGNORECASE) - -# Program matching multiline annotation continuations. -# This is used on multiline parameters and tags (but not on the first line) to -# generate warnings about invalid annotations spanning multiple lines. -# -# Results in 3 symbolic groups: -# - group 2 = annotations -# - group 3 = colon -# - group 4 = description -MULTILINE_ANNOTATION_CONTINUATION_RE = re.compile(r''' - ^ # start - [^\S\n\r]* # 0 or more whitespace characters - (?P(?:\(.*?\)[^\S\n\r]*)*) # annotations - (?P:) # colon - [^\S\n\r]* # 0 or more whitespace characters - (?P.*?) # description - [^\S\n\r]* # 0 or more whitespace characters - $ # end - ''', - re.VERBOSE | re.MULTILINE) diff --git a/tests/scanner/annotationparser/test_patterns.py b/tests/scanner/annotationparser/test_patterns.py index 0b5592a..2755cc9 100644 --- a/tests/scanner/annotationparser/test_patterns.py +++ b/tests/scanner/annotationparser/test_patterns.py @@ -31,8 +31,8 @@ against the expected output. ''' -from giscanner.annotationpatterns import (SECTION_RE, SYMBOL_RE, PROPERTY_RE, - SIGNAL_RE, PARAMETER_RE, TAG_RE) +from giscanner.annotationparser import (SECTION_RE, SYMBOL_RE, PROPERTY_RE, + SIGNAL_RE, PARAMETER_RE, TAG_RE) from unittest import (TestCase, main) -- 2.7.4