def parse3(self, text):
"""Parse the text.
We divide the page text to 3 parts:
A: text before the first == level section title
B: text from the first section title to the first stopsection
C: text from the first stopsection to the end.
A and B will be returned as a tuple and poor C will be thrown away.
"""
lines = text.splitlines(1)
comeon = True
where = 0
linenum = 0
tx1 = tx2 = ''
while comeon and linenum < len(lines):
line = lines[linenum]
if sectionpattern.match(line) and not pywikibot.isDisabled(text,where):
tx2 = line
comeon = False
else:
tx1 += line
where += len(line)
linenum += 1
comeon = True
while comeon and linenum < len(lines):
line = lines[linenum]
if stopsectionregex.match(line) and not pywikibot.isDisabled(text,where):
comeon = False
else:
tx2 += line
where += len(line)
linenum += 1
return (tx1, tx2)
def addReferences(self, oldText):
"""
Tries to add a references tag into an existing section where it fits
into. If there is no such section, creates a new section containing
the references tag.
* Returns : The modified pagetext
"""
# Is there an existing section where we can add the references tag?
for section in i18n.translate(self.site, referencesSections):
sectionR = re.compile(r'\r?\n=+ *%s *=+ *\r?\n' % section)
index = 0
while index < len(oldText):
match = sectionR.search(oldText, index)
if match:
if pywikibot.isDisabled(oldText, match.start()):
pywikibot.output(
'Existing %s section is commented out, skipping.'
% section)
index = match.end()
else:
pywikibot.output(
u'Adding references tag to existing %s section...\n'
% section)
newText = (
oldText[:match.end()] + u'\n' +
self.referencesText + u'\n' +
oldText[match.end():]
)
return newText
else:
break
# Create a new section for the references tag
for section in i18n.translate(self.site, placeBeforeSections):
# Find out where to place the new section
sectionR = re.compile(r'\r?\n(?P<ident>=+) *%s *(?P=ident) *\r?\n'
% section)
index = 0
while index < len(oldText):
match = sectionR.search(oldText, index)
if match:
if pywikibot.isDisabled(oldText, match.start()):
pywikibot.output(
'Existing %s section is commented out, won\'t add '
'the references in front of it.' % section)
index = match.end()
else:
pywikibot.output(
u'Adding references section before %s section...\n'
% section)
index = match.start()
ident = match.group('ident')
return self.createReferenceSection(oldText, index,
ident)
else:
break
# This gets complicated: we want to place the new references
# section over the interwiki links and categories, but also
# over all navigation bars, persondata, and other templates
# that are at the bottom of the page. So we need some advanced
# regex magic.
# The strategy is: create a temporary copy of the text. From that,
# keep removing interwiki links, templates etc. from the bottom.
# At the end, look at the length of the temp text. That's the position
# where we'll insert the references section.
catNamespaces = '|'.join(self.site.category_namespaces())
categoryPattern = r'\[\[\s*(%s)\s*:[^\n]*\]\]\s*' % catNamespaces
interwikiPattern = r'\[\[([a-zA-Z\-]+)\s?:([^\[\]\n]*)\]\]\s*'
# won't work with nested templates
# the negative lookahead assures that we'll match the last template
# occurence in the temp text.
### fix me:
### {{commons}} or {{commonscat}} are part of Weblinks section
### * {{template}} is mostly part of a section
### so templatePattern must be fixed
templatePattern = r'\r?\n{{((?!}}).)+?}}\s*'
commentPattern = r'<!--((?!-->).)*?-->\s*'
metadataR = re.compile(r'(\r?\n)?(%s|%s|%s|%s)$'
% (categoryPattern, interwikiPattern,
templatePattern, commentPattern), re.DOTALL)
tmpText = oldText
while True:
match = metadataR.search(tmpText)
if match:
tmpText = tmpText[:match.start()]
else:
break
pywikibot.output(
u'Found no section that can be preceeded by a new references '
u'section.\nPlacing it before interwiki links, categories, and '
u'bottom templates.')
index = len(tmpText)
return self.createReferenceSection(oldText, index)
def addReferences(self, oldText):
"""
Tries to add a references tag into an existing section where it fits
into. If there is no such section, creates a new section containing
the references tag.
* Returns : The modified pagetext
"""
# Is there an existing section where we can add the references tag?
for section in pywikibot.translate(self.site, referencesSections):
sectionR = re.compile(r'\r\n=+ *%s *=+ *\r\n' % section)
index = 0
while index < len(oldText):
match = sectionR.search(oldText, index)
if match:
if pywikibot.isDisabled(oldText, match.start()):
pywikibot.output(
'Existing %s section is commented out, skipping.'
% section)
index = match.end()
else:
pywikibot.output(
u'Adding references tag to existing %s section...\n'
% section)
newText = oldText[:match.end(
)] + u'\n' + self.referencesText + u'\n' + oldText[
match.end():]
return newText
else:
break
# Create a new section for the references tag
for section in pywikibot.translate(self.site, placeBeforeSections):
# Find out where to place the new section
sectionR = re.compile(r'\r\n(?P<ident>=+) *%s *(?P=ident) *\r\n' %
section)
index = 0
while index < len(oldText):
match = sectionR.search(oldText, index)
if match:
if pywikibot.isDisabled(oldText, match.start()):
pywikibot.output(
'Existing %s section is commented out, won\'t add the references in front of it.'
% section)
index = match.end()
else:
pywikibot.output(
u'Adding references section before %s section...\n'
% section)
index = match.start()
ident = match.group('ident')
return self.createReferenceSection(
oldText, index, ident)
else:
break
# This gets complicated: we want to place the new references
# section over the interwiki links and categories, but also
# over all navigation bars, persondata, and other templates
# that are at the bottom of the page. So we need some advanced
# regex magic.
# The strategy is: create a temporary copy of the text. From that,
# keep removing interwiki links, templates etc. from the bottom.
# At the end, look at the length of the temp text. That's the position
# where we'll insert the references section.
catNamespaces = '|'.join(self.site.category_namespaces())
categoryPattern = r'\[\[\s*(%s)\s*:[^\n]*\]\]\s*' % catNamespaces
interwikiPattern = r'\[\[([a-zA-Z\-]+)\s?:([^\[\]\n]*)\]\]\s*'
# won't work with nested templates
# the negative lookahead assures that we'll match the last template
# occurence in the temp text.
### fix me:
### {{commons}} or {{commonscat}} are part of Weblinks section
### * {{template}} is mostly part of a section
### so templatePattern must be fixed
templatePattern = r'\r\n{{((?!}}).)+?}}\s*'
commentPattern = r'<!--((?!-->).)*?-->\s*'
metadataR = re.compile(
r'(\r\n)?(%s|%s|%s|%s)$' % (categoryPattern, interwikiPattern,
templatePattern, commentPattern),
re.DOTALL)
tmpText = oldText
while True:
match = metadataR.search(tmpText)
if match:
tmpText = tmpText[:match.start()]
else:
break
pywikibot.output(
u'Found no section that can be preceeded by a new references section.\nPlacing it before interwiki links, categories, and bottom templates.'
)
index = len(tmpText)
return self.createReferenceSection(oldText, index)