Attachment #26482 for bug #42111

Lines 789-795 Link Here

(-)DocumentClass.py (-7 / +9 lines)
789		789
790	def doc_literal(	790	def doc_literal(
791	self, s,	791	self, s,
792	expr = re.compile(r"(\W+\|^)'([%s%s%s\s]+)'([%s]+\|$)" % (letters, digits, literal_punc, phrase_delimiters)).search,):	792	expr = re.compile(r"(\W+\|^)'((?:\w\|[%s%s\s])+)'([%s]+\|$)" % (digits, literal_punc, phrase_delimiters), re.U).search,):
793		793
794	# old expr... failed to cross newlines.	794	# old expr... failed to cross newlines.
795	# expr=re.compile(	795	# expr=re.compile(
Lines 807-813 Link Here
807		807
808	def doc_emphasize(	808	def doc_emphasize(
809	self, s,	809	self, s,
810	expr = re.compile(r'\([%s%s%s\s]+?)\' % (letters, digits, strongem_punc)).search	810	# i18nal variant
		811	expr = re.compile(r'\((?:\w\|[%s\s])+?)\' % (strongem_punc), re.U).search
		812	#expr = re.compile(r'\([%s%s%s\s]+?)\' % (letters, digits, strongem_punc)).search
811	#expr = re.compile(r'\s\([ \n\r%s0-9.:/;,\'\"\?\-\_\/\=\-\>\<]+)\(?!\\|-)' % letters).search # old expr, inconsistent punctuation	813	#expr = re.compile(r'\s\([ \n\r%s0-9.:/;,\'\"\?\-\_\/\=\-\>\<]+)\(?!\\|-)' % letters).search # old expr, inconsistent punctuation
812	):	814	):
813		815
Lines 853-859 Link Here
853		855
854	def doc_underline(self,	856	def doc_underline(self,
855	s,	857	s,
856	expr=re.compile(r'_([%s%s%s\s]+)_([\s%s]\|$)' % (letters, digits, under_punc,phrase_delimiters)).search):	858	expr=re.compile(r'_((?:\w\|[%s\s])+)_([\s%s]\|$)' % (under_punc,phrase_delimiters), re.U).search):
857		859
858	result = expr(s)	860	result = expr(s)
859	if result:	861	if result:
Lines 867-873 Link Here
867		869
868	def doc_strong(self,	870	def doc_strong(self,
869	s,	871	s,
870	expr = re.compile(r'\\([%s%s%s\s]+?)\\' % (letters, digits, strongem_punc)).search	872	expr = re.compile(r'\\((?:\w\|[%s%s\s])+?)\\' % (digits, strongem_punc), re.U).search
871	#expr = re.compile(r'\s\\([ \n\r%s0-9.:/;,\'\"\?\-\_\/\=\-\>\<]+)\\(?!\\|-)' % letters).search, # old expr, inconsistent punc, failed to cross newlines.	873	#expr = re.compile(r'\s\\([ \n\r%s0-9.:/;,\'\"\?\-\_\/\=\-\>\<]+)\\(?!\\|-)' % letters).search, # old expr, inconsistent punc, failed to cross newlines.
872	):	874	):
873		875
Lines 879-885 Link Here
879	return None	881	return None
880		882
881	## Some constants to make the doc_href() regex easier to read.	883	## Some constants to make the doc_href() regex easier to read.
882	_DQUOTEDTEXT = r'("[ %s0-9\n\r%s]+")' % (letters,dbl_quoted_punc) ## double quoted text	884	_DQUOTEDTEXT = r'("[^"]+")'
883	_ABSOLUTE_URL=r'((http\|https\|ftp\|mailto\|file\|about)[:/]+?[%s0-9_\@\.\,\?\!\/\:\;\-\#\~\=\&\%%\+]+)' % letters	885	_ABSOLUTE_URL=r'((http\|https\|ftp\|mailto\|file\|about)[:/]+?[%s0-9_\@\.\,\?\!\/\:\;\-\#\~\=\&\%%\+]+)' % letters
884	_ABS_AND_RELATIVE_URL=r'([%s0-9_\@\.\,\?\!\/\:\;\-\#\~\=\&\%%\+]+)' % letters	886	_ABS_AND_RELATIVE_URL=r'([%s0-9_\@\.\,\?\!\/\:\;\-\#\~\=\&\%%\+]+)' % letters
885		887
Lines 887-898 Link Here
887		889
888		890
889	def doc_href1(self, s,	891	def doc_href1(self, s,
890	expr=re.compile(_DQUOTEDTEXT + "(:)" + _ABS_AND_RELATIVE_URL + _SPACES).search	892	expr=re.compile(_DQUOTEDTEXT + "(:)" + _ABS_AND_RELATIVE_URL + _SPACES, re.U).search
891	):	893	):
892	return self.doc_href(s, expr)	894	return self.doc_href(s, expr)
893		895
894	def doc_href2(self, s,	896	def doc_href2(self, s,
895	expr=re.compile(_DQUOTEDTEXT + r'(\,\s+)' + _ABSOLUTE_URL + _SPACES).search	897	expr=re.compile(_DQUOTEDTEXT + r'(\,\s+)' + _ABSOLUTE_URL + _SPACES, re.U).search
896	):	898	):
897	return self.doc_href(s, expr)	899	return self.doc_href(s, expr)
898		900

Lines 30-41 Link Here

(-)DocumentWithImages.py (-3 / +3 lines)
30		30
31	def doc_img(	31	def doc_img(
32	self, s,	32	self, s,
33	expr1=re.compile('\"([ _a-zA-Z0-9*.:/;,\-\n\~]+)\":img:([a-zA-Z0-9\_\-.:/;,\n\~]+)').search,	33	expr1=re.compile('\"((?:\w\|[ *.:/;,\-\n\~])+)\":img:([a-zA-Z0-9\_\-.:/;,\n\~]+)', re.U).search,
34	expr2=re.compile('\"([ _a-zA-Z0-9*.:/;,\-\n\~]+)\":img:([a-zA-Z0-9\_\-.:/;,\n\~]+):([a-zA-Z0-9_\-.:/;,\n\~]+)').search	34	expr2=re.compile('\"((?:\w\|[ *.:/;,\-\n\~])+)\":img:([a-zA-Z0-9\_\-.:/;,\n\~]+):([a-zA-Z0-9_\-.:/;,\n\~]+)', re.U).search
35	):	35	):
36
37	r = expr2(s)	36	r = expr2(s)
38	if r:	37	if r:
		38
39		39
40	# Warning: the regex are getting confused when the string after :img:	40	# Warning: the regex are getting confused when the string after :img:
41	# is an URL containing ":" (Collector #2276)	41	# is an URL containing ":" (Collector #2276)

Lines 115-120 Link Here

(-)ST.py (+3 lines)
115	Structure => [paragraph,[sub-paragraphs]]	115	Structure => [paragraph,[sub-paragraphs]]
116	"""	116	"""
117		117
		118	if type(paragraphs) == type(''):
		119	paragraphs = unicode(paragraphs, 'utf-8')
		120
118	currentlevel = 0	121	currentlevel = 0
119	currentindent = 0	122	currentindent = 0
120	levels = {0:0}	123	levels = {0:0}

Lines 210-222 Link Here

(-)tests/testStructuredText.py (-6 / +15 lines)
210	'<code>"literal":http://www.zope.org/.</code>')	210	'<code>"literal":http://www.zope.org/.</code>')
211		211
212		212
213	def XXXtestUnicodeContent(self):	213	def testUnicodeContent(self):
214	# This fails because ST uses the default locale to get "letters"	214	self._test(u"h\xe9 y\xe9 xx",
215	# whereas it should use \w+ and re.U if the string is Unicode.	215	u"h\xe9 <strong>y\xe9</strong> xx")
216	#self._test(u"h\xe9 y\xe9 xx",	216	self._test(u"h\xe9 y\xe9 xx",
217	# u"h\xe9 <strong>y\xe9</strong> xx")	217	u"h\xe9 <em>y\xe9</em> xx")
218	pass	218	self._test(u"h\xe9 _y\xe9_ xx",
		219	u"h\xe9 <u>y\xe9</u> xx")
		220	self._test(u"h\xe9 'y\xe9' xx",
		221	u"h\xe9 <code>y\xe9</code> xx")
		222	self._test(u"h\xe9 \"y\xe9\":http://zope.org xx",
		223	u"h\xe9 <a href=\"http://zope.org\">y\xe9</a> xx")
219		224
		225	def testDoNotHang(self):
		226	raw_str = 'UAB "Vita Baltic International" produkcijos asortiment\u0105 papild\u0117 dar trys specifines nedegumo savybes turin\u010dios porolono ru\u0161ys. \nSpalio m\u0117nes\u012f buvo gauti tarptautiniai sertifikatai, liudijantys, kad porolonai CV 3037, CV 3538 ir CV 2533 atitinka degumo standart\u0173 BS 5852:Part 2: 1982 reikalavimus. Tai labai gera \u017einia bald\u0173 gamintojams, gaminantiems baldus ir \u010diu\u017einius,\nkuri\u0173 gaminiams keliami ypatingi importuotoj\u0173 reikalavimai.'
		227	res_txt = raw_str
		228	self._test(raw_str, res_txt)
220		229
221	def test_suite():	230	def test_suite():
222	suite = unittest.TestSuite()	231	suite = unittest.TestSuite()

Return to bug 42111