Put r on a bunch more regex compile/match/sub

Author: AngledLuffa

wikiextractor/extract.py

@@ -30,7 +30,7 @@
 # ----------------------------------------------------------------------
 
 # match tail after wikilink
-tailRE = re.compile('\w+')
+tailRE = re.compile(r'\w+')
 syntaxhighlight = re.compile('<syntaxhighlight .*?>(.*?)</syntaxhighlight>', re.DOTALL)
 
 ## PARAMS ####################################################################
@@ -168,8 +168,8 @@ def clean(extractor, text, expand_templates=False, html_safe=True):
     text = text.replace('\t', ' ')
     text = spaces.sub(' ', text)
     text = dots.sub('...', text)
-    text = re.sub(u' (,:\.\)\]»)', r'\1', text)
-    text = re.sub(u'(\[\(«) ', r'\1', text)
+    text = re.sub(r' (,:\.\)\]»)', r'\1', text)
+    text = re.sub(r'(\[\(«) ', r'\1', text)
     text = re.sub(r'\n\W+?\n', '\n', text, flags=re.U)  # lines with only punctuations
     text = text.replace(',,', ',').replace(',.', '.')
     if html_safe:
@@ -380,7 +380,7 @@ def dropSpans(spans, text):
 # as well as U+3000 is IDEOGRAPHIC SPACE for bug 19052
 EXT_LINK_URL_CLASS = r'[^][<>"\x00-\x20\x7F\s]'
 ExtLinkBracketedRegex = re.compile(
-    '(?i)\[((' + '|'.join(wgUrlProtocols) + ')' + EXT_LINK_URL_CLASS + r'+)\s*([^\]\x00-\x08\x0a-\x1F]*?)\]',
+    r'(?i)\[((' + '|'.join(wgUrlProtocols) + ')' + EXT_LINK_URL_CLASS + r'+)\s*([^\]\x00-\x08\x0a-\x1F]*?)\]',
     re.S | re.U)
 EXT_IMAGE_REGEX = re.compile(
     r"""(?i)^(http://|https://)([^][<>"\x00-\x20\x7F\s]+)
@@ -734,7 +734,7 @@ def fixup(m):
         except:
             return text  # leave as is
 
-    return re.sub("&#?(\w+);", fixup, text)
+    return re.sub(r"&#?(\w+);", fixup, text)
 
 
 # Match HTML comments
@@ -1024,7 +1024,7 @@ def extract(self, out, html_safe=True):
     maxParameterRecursionLevels = 16
 
     # check for template beginning
-    reOpen = re.compile('(?<!{){{(?!{)', re.DOTALL)
+    reOpen = re.compile(r'(?<!{){{(?!{)', re.DOTALL)
 
     def expandTemplates(self, wikitext):
         """
@@ -1434,11 +1434,11 @@ def findMatchingBraces(text, ldelim=0):
     #   {{{link|{{ucfirst:{{{1}}}}}} interchange}}}
 
     if ldelim:  # 2-3
-        reOpen = re.compile('[{]{%d,}' % ldelim)  # at least ldelim
-        reNext = re.compile('[{]{2,}|}{2,}')  # at least 2 open or close bracces
+        reOpen = re.compile(r'[{]{%d,}' % ldelim)  # at least ldelim
+        reNext = re.compile(r'[{]{2,}|}{2,}')  # at least 2 open or close bracces
     else:
-        reOpen = re.compile('{{2,}|\[{2,}')
-        reNext = re.compile('{{2,}|}{2,}|\[{2,}|]{2,}')  # at least 2
+        reOpen = re.compile(r'{{2,}|\[{2,}')
+        reNext = re.compile(r'{{2,}|}{2,}|\[{2,}|]{2,}')  # at least 2
 
     cur = 0
     while True:
@@ -1582,7 +1582,7 @@ def fullyQualifiedTemplateTitle(templateTitle):
         # Leading colon by itself implies main namespace, so strip this colon
         return ucfirst(templateTitle[1:])
     else:
-        m = re.match('([^:]*)(:.*)', templateTitle)
+        m = re.match(r'([^:]*)(:.*)', templateTitle)
         if m:
             # colon found but not in the first position - check if it
             # designates a known namespace
@@ -1689,7 +1689,7 @@ def sharp_ifeq(lvalue, rvalue, valueIfTrue, valueIfFalse=None, *args):
 
 
 def sharp_iferror(test, then='', Else=None, *args):
-    if re.match('<(?:strong|span|p|div)\s(?:[^\s>]*\s+)*?class="(?:[^"\s>]*\s+)*?error(?:\s[^">]*)?"', test):
+    if re.match(r'<(?:strong|span|p|div)\s(?:[^\s>]*\s+)*?class="(?:[^"\s>]*\s+)*?error(?:\s[^">]*)?"', test):
         return then
     elif Else is None:
         return test.strip()
@@ -1860,7 +1860,7 @@ def define_template(title, page):
     # title = normalizeTitle(title)
 
     # check for redirects
-    m = re.match('#REDIRECT.*?\[\[([^\]]*)]]', page[0], re.IGNORECASE)
+    m = re.match(r'#REDIRECT.*?\[\[([^\]]*)]]', page[0], re.IGNORECASE)
     if m:
         redirects[title] = m.group(1)  # normalizeTitle(m.group(1))
         return