Changed a bunch of regexes to use r strings; also miscellaneous smaller fixes.

 - Legacy-Id: 16376

Author: levkowetz

ietf/doc/templatetags/ietf_filters.py

@@ -4,8 +4,6 @@
 import datetime
 import re
 
-import types
-
 from email.utils import parseaddr
 
 from django import template
@@ -47,8 +45,8 @@ def parse_email_list(value):
 
     Splitting a string of email addresses should return a list:
 
-    >>> unicode(parse_email_list('joe@example.org, fred@example.com'))
-    u'<a href="mailto:joe@example.org">joe@example.org</a>, <a href="mailto:fred@example.com">fred@example.com</a>'
+    >>> parse_email_list('joe@example.org, fred@example.com')
+    '<a href="mailto:joe@example.org">joe@example.org</a>, <a href="mailto:fred@example.com">fred@example.com</a>'
 
     Parsing a non-string should return the input value, rather than fail:
 
@@ -88,7 +86,7 @@ def strip_email(value):
 @register.filter(name='fix_angle_quotes')
 def fix_angle_quotes(value):
     if "<" in value:
-        value = re.sub("<([\w\-\.]+@[\w\-\.]+)>", "&lt;\1&gt;", value)
+        value = re.sub(r"<([\w\-\.]+@[\w\-\.]+)>", "&lt;\1&gt;", value)
     return value
 
 # there's an "ahref -> a href" in GEN_UTIL
@@ -213,13 +211,13 @@ def urlize_ietf_docs(string, autoescape=None):
     """
     if autoescape and not isinstance(string, SafeData):
         string = escape(string)
-    string = re.sub("(?<!>)(RFC ?)0{0,3}(\d+)", "<a href=\"/doc/rfc\\2/\">\\1\\2</a>", string)
-    string = re.sub("(?<!>)(BCP ?)0{0,3}(\d+)", "<a href=\"/doc/bcp\\2/\">\\1\\2</a>", string)
-    string = re.sub("(?<!>)(STD ?)0{0,3}(\d+)", "<a href=\"/doc/std\\2/\">\\1\\2</a>", string)
-    string = re.sub("(?<!>)(FYI ?)0{0,3}(\d+)", "<a href=\"/doc/fyi\\2/\">\\1\\2</a>", string)
-    string = re.sub("(?<!>)(draft-[-0-9a-zA-Z._+]+)", "<a href=\"/doc/\\1/\">\\1</a>", string)
-    string = re.sub("(?<!>)(conflict-review-[-0-9a-zA-Z._+]+)", "<a href=\"/doc/\\1/\">\\1</a>", string)
-    string = re.sub("(?<!>)(status-change-[-0-9a-zA-Z._+]+)", "<a href=\"/doc/\\1/\">\\1</a>", string)
+    string = re.sub(r"(?<!>)(RFC ?)0{0,3}(\d+)", "<a href=\"/doc/rfc\\2/\">\\1\\2</a>", string)
+    string = re.sub(r"(?<!>)(BCP ?)0{0,3}(\d+)", "<a href=\"/doc/bcp\\2/\">\\1\\2</a>", string)
+    string = re.sub(r"(?<!>)(STD ?)0{0,3}(\d+)", "<a href=\"/doc/std\\2/\">\\1\\2</a>", string)
+    string = re.sub(r"(?<!>)(FYI ?)0{0,3}(\d+)", "<a href=\"/doc/fyi\\2/\">\\1\\2</a>", string)
+    string = re.sub(r"(?<!>)(draft-[-0-9a-zA-Z._+]+)", "<a href=\"/doc/\\1/\">\\1</a>", string)
+    string = re.sub(r"(?<!>)(conflict-review-[-0-9a-zA-Z._+]+)", "<a href=\"/doc/\\1/\">\\1</a>", string)
+    string = re.sub(r"(?<!>)(status-change-[-0-9a-zA-Z._+]+)", "<a href=\"/doc/\\1/\">\\1</a>", string)
     return mark_safe(string)
 urlize_ietf_docs = stringfilter(urlize_ietf_docs)
 
@@ -461,8 +459,8 @@ def capfirst_allcaps(text):
     """Like capfirst, except it doesn't lowercase words in ALL CAPS."""
     result = text
     i = False
-    for token in re.split("(\W+)", striptags(text)):
-        if not re.match("^[A-Z]+$", token):
+    for token in re.split(r"(\W+)", striptags(text)):
+        if not re.match(r"^[A-Z]+$", token):
             if not i:
                 result = result.replace(token, token.capitalize())
                 i = True
@@ -474,8 +472,8 @@ def capfirst_allcaps(text):
 def lower_allcaps(text):
     """Like lower, except it doesn't lowercase words in ALL CAPS."""
     result = text
-    for token in re.split("(\W+)", striptags(text)):
-        if not re.match("^[A-Z]+$", token):
+    for token in re.split(r"(\W+)", striptags(text)):
+        if not re.match(r"^[A-Z]+$", token):
             result = result.replace(token, token.lower())
     return result
 
@@ -515,7 +513,7 @@ def zaptmp(s):
 
 @register.filter()
 def rfcbis(s):
-    m = re.search('^.*-rfc(\d+)-?bis(-.*)?$', s)
+    m = re.search(r'^.*-rfc(\d+)-?bis(-.*)?$', s)
     return None if m is None else 'rfc' + m.group(1) 
 
 @register.filter

ietf/doc/utils.py

@@ -829,7 +829,7 @@ def add_markup(path, doc, lines):
                 line = re.sub(r'Errata exist', r'<a class="text-warning" href="%s">Errata exist</a>'%(errata_url, ), line)
             if is_hst or not rfcnum:
                 # make current draft rev bold
-                line = re.sub(r'>(%s)<'%rev, '><b>\g<1></b><', line)
+                line = re.sub(r'>(%s)<'%rev, r'><b>\g<1></b><', line)
             line = re.sub(r'IPR declarations', r'<a class="text-warning" href="%s">IPR declarations</a>'%(ipr_url, ), line)
             line = line.replace(r'[txt]', r'[<a href="%s">txt</a>]' % doc.href())
             lines[i] = line

ietf/doc/views_doc.py

@@ -623,7 +623,7 @@ def document_main(request, name, rev=None):
 def document_html(request, name, rev=None):
     if name.startswith('rfc0'):
         name = "rfc" + name[3:].lstrip('0')
-    if name.startswith('review-') and re.search('-\d\d\d\d-\d\d$', name):
+    if name.startswith('review-') and re.search(r'-\d\d\d\d-\d\d$', name):
         name = "%s-%s" % (name, rev)
     if rev and not name.startswith('charter-') and re.search('[0-9]{1,2}-[0-9]{2}', rev):
         name = "%s-%s" % (name, rev[:-3])
@@ -658,7 +658,7 @@ def document_html(request, name, rev=None):
     return render(request, "doc/document_html.html", {"doc":doc, "top":top, "navbar_mode":"navbar-static-top",  })
 
 def check_doc_email_aliases():
-    pattern = re.compile('^expand-(.*?)(\..*?)?@.*? +(.*)$')
+    pattern = re.compile(r'^expand-(.*?)(\..*?)?@.*? +(.*)$')
     good_count = 0
     tot_count = 0
     with open(settings.DRAFT_VIRTUAL_PATH,"r") as virtual_file:
@@ -673,9 +673,9 @@ def check_doc_email_aliases():
 
 def get_doc_email_aliases(name):
     if name:
-        pattern = re.compile('^expand-(%s)(\..*?)?@.*? +(.*)$'%name)
+        pattern = re.compile(r'^expand-(%s)(\..*?)?@.*? +(.*)$'%name)
     else:
-        pattern = re.compile('^expand-(.*?)(\..*?)?@.*? +(.*)$')
+        pattern = re.compile(r'^expand-(.*?)(\..*?)?@.*? +(.*)$')
     aliases = []
     with open(settings.DRAFT_VIRTUAL_PATH,"r") as virtual_file:
         for line in virtual_file.readlines():

ietf/person/name.py

@@ -67,7 +67,7 @@ def initials(name):
         given += " "+middle
     # Don't use non-word characters as initials.
     # Example: The Bulgarian transcribed name "'Rnest Balkanska" should not have an initial of "'".
-    given = re.sub('[^ .\w]', '', given)
+    given = re.sub(r'[^ .\w]', '', given)
     initials = " ".join([ n[0].upper()+'.' for n in given.split() ])
     return initials
 

ietf/redirects/views.py

@@ -30,7 +30,7 @@ def redirect(request, path="", script=""):
                 continue
         if fc[0] in rparam:
             remove_args.append(fc[0])
-            num = re.match('(\d+)', rparam[fc[0]])
+            num = re.match(r'(\d+)', rparam[fc[0]])
             if (num and int(num.group(1))) or (num is None):
                 cmd = flag
             break
@@ -64,8 +64,8 @@ def redirect(request, path="", script=""):
         # contains non-ASCII characters. The old scripts didn't support 
         # non-ASCII characters anyway, so there's no need to handle 
         # them fully correctly in these redirects.
-        url += str(rest % rparam)
-        url += "/"
+        (rest % rparam).encode('ascii')
+        url += (rest % rparam) + "/"
     except:
         # rest had something in it that request didn't have, so just
         # redirect to the root of the tool.

ietf/sync/rfceditor.py

@@ -56,7 +56,7 @@ def parse_queue(response):
                 events.expandNode(node)
                 node.normalize()
                 draft_name = get_child_text(node, "draft").strip()
-                draft_name = re.sub("(-\d\d)?(.txt){1,2}$", "", draft_name)
+                draft_name = re.sub(r"(-\d\d)?(.txt){1,2}$", "", draft_name)
                 date_received = get_child_text(node, "date-received")
 
                 state = ""
@@ -306,7 +306,7 @@ def extract_doc_list(parentNode, tagName):
                     abstract = get_child_text(abstract, "p")
 
                 draft = get_child_text(node, "draft")
-                if draft and re.search("-\d\d$", draft):
+                if draft and re.search(r"-\d\d$", draft):
                     draft = draft[0:-3]
 
                 if len(node.getElementsByTagName("errata-url")) > 0:

ietf/utils/draft.py

@@ -191,7 +191,7 @@ def _parse_draftname(self):
                     name, __ = base.split(".", 1)
                 else:
                     name = base
-                revmatch = re.search("\d\d$", name)
+                revmatch = re.search(r"\d\d$", name)
                 if revmatch:
                     filename = name[:-3]
                     revision = name[-2:]
@@ -243,36 +243,36 @@ def begpage(pages, page, newpage, line=None):
         for line in self.rawlines:
             linecount += 1
             line = line.rstrip()
-            if re.search("\[?page [0-9ivx]+\]?[ \t\f]*$", line, re.I):
+            if re.search(r"\[?page [0-9ivx]+\]?[ \t\f]*$", line, re.I):
                 pages, page, newpage = endpage(pages, page, newpage, line)
                 continue
-            if re.search("\f", line, re.I):
+            if re.search(r"\f", line, re.I):
                 pages, page, newpage = begpage(pages, page, newpage)
                 continue
-            if re.search("^ *Internet.Draft.+  .+[12][0-9][0-9][0-9] *$", line, re.I):
+            if re.search(r"^ *Internet.Draft.+  .+[12][0-9][0-9][0-9] *$", line, re.I):
                 pages, page, newpage = begpage(pages, page, newpage, line)
                 continue
     #        if re.search("^ *Internet.Draft  +", line, re.I):
     #            newpage = True
     #            continue
-            if re.search("^ *Draft.+[12][0-9][0-9][0-9] *$", line, re.I):
+            if re.search(r"^ *Draft.+[12][0-9][0-9][0-9] *$", line, re.I):
                 pages, page, newpage = begpage(pages, page, newpage, line)
                 continue
-            if re.search("^RFC[ -]?[0-9]+.*(  +)[12][0-9][0-9][0-9]$", line, re.I):
+            if re.search(r"^RFC[ -]?[0-9]+.*(  +)[12][0-9][0-9][0-9]$", line, re.I):
                 pages, page, newpage = begpage(pages, page, newpage, line)
                 continue
-            if re.search("^draft-[-a-z0-9_.]+.*[0-9][0-9][0-9][0-9]$", line, re.I):
+            if re.search(r"^draft-[-a-z0-9_.]+.*[0-9][0-9][0-9][0-9]$", line, re.I):
                 pages, page, newpage = endpage(pages, page, newpage, line)
                 continue
-            if linecount > 15 and re.search(".{58,}(Jan|Feb|Mar|March|Apr|April|May|Jun|June|Jul|July|Aug|Sep|Oct|Nov|Dec) (19[89][0-9]|20[0-9][0-9]) *$", line, re.I):
+            if linecount > 15 and re.search(r".{58,}(Jan|Feb|Mar|March|Apr|April|May|Jun|June|Jul|July|Aug|Sep|Oct|Nov|Dec) (19[89][0-9]|20[0-9][0-9]) *$", line, re.I):
                 pages, page, newpage = begpage(pages, page, newpage, line)
                 continue
-            if newpage and re.search("^ *draft-[-a-z0-9_.]+ *$", line, re.I):
+            if newpage and re.search(r"^ *draft-[-a-z0-9_.]+ *$", line, re.I):
                 pages, page, newpage = begpage(pages, page, newpage, line)
                 continue
-            if re.search("^[^ \t]+", line):
+            if re.search(r"^[^ \t]+", line):
                 sentence = True
-            if re.search("[^ \t]", line):
+            if re.search(r"[^ \t]", line):
                 if newpage:
                     # 36 is a somewhat arbitrary count for a 'short' line
                     shortthis = len(line.strip()) < 36 # 36 is a somewhat arbitrary count for a 'short' line
@@ -300,7 +300,7 @@ def begpage(pages, page, newpage, line=None):
     # ----------------------------------------------------------------------
     def get_pagecount(self):
         if self._pagecount == None:
-            label_pages = len(re.findall("\[page [0-9ixldv]+\]", self.text, re.I))
+            label_pages = len(re.findall(r"\[page [0-9ixldv]+\]", self.text, re.I))
             count_pages = len(self.pages)
             if label_pages > count_pages/2:
                 self._pagecount = label_pages
@@ -343,7 +343,7 @@ def get_formal_languages(self):
     def get_status(self):
         if self._status == None:
             for line in self.lines[:10]:
-                status_match = re.search("^\s*Intended [Ss]tatus:\s*(.*?)   ", line)
+                status_match = re.search(r"^\s*Intended [Ss]tatus:\s*(.*?)   ", line)
                 if status_match:
                     self._status = status_match.group(1)
                     break
@@ -416,8 +416,8 @@ def get_creation_date(self):
     def get_abstract(self):
         if self._abstract:
             return self._abstract
-        abstract_re = re.compile('^(\s*)abstract', re.I)
-        header_re = re.compile("^(\s*)([0-9]+\.? |Appendix|Status of|Table of|Full Copyright|Copyright|Intellectual Property|Acknowled|Author|Index|Disclaimer).*", re.I)
+        abstract_re = re.compile(r'^(\s*)abstract', re.I)
+        header_re = re.compile(r"^(\s*)([0-9]+\.? |Appendix|Status of|Table of|Full Copyright|Copyright|Intellectual Property|Acknowled|Author|Index|Disclaimer).*", re.I)
         begin = False
         abstract = []
         abstract_indent = 0
@@ -446,7 +446,7 @@ def get_abstract(self):
 
 
     def _check_abstract_indent(self, abstract, indent):
-        indentation_re = re.compile('^(\s)*')
+        indentation_re = re.compile(r'^(\s)*')
         indent_lines = []
         for line in abstract.split('\n'):
             if line:
@@ -807,7 +807,7 @@ def dotexp(s):
                                             _debug( "Cut:   '%s'" % form[beg:end])
                                             author_match = re.search(authpat, columns[col].strip()).group(1)
                                             _debug( "AuthMatch: '%s'" % (author_match,))
-                                            if re.search('\(.*\)$', author_match.strip()):
+                                            if re.search(r'\(.*\)$', author_match.strip()):
                                                 author_match = author_match.rsplit('(',1)[0].strip()
                                             if author_match in companies_seen:
                                                 companies[i] = authors[i]
@@ -887,7 +887,7 @@ def dotexp(s):
     #                 for a in authors:
     #                     if a and a not in companies_seen:
     #                         _debug("Search for: %s"%(r"(^|\W)"+re.sub("\.? ", ".* ", a)+"(\W|$)"))
-                    authmatch = [ a for a in authors[i+1:] if a and not a.lower() in companies_seen and (re.search((r"(?i)(^|\W)"+re.sub("[. ]+", ".*", a)+"(\W|$)"), line.strip()) or acronym_match(a, line.strip()) )]
+                    authmatch = [ a for a in authors[i+1:] if a and not a.lower() in companies_seen and (re.search((r"(?i)(^|\W)"+re.sub(r"[. ]+", ".*", a)+r"(\W|$)"), line.strip()) or acronym_match(a, line.strip()) )]
 
                     if authmatch:
                         _debug("     ? Other author or company ?  : %s" % authmatch)
@@ -915,9 +915,9 @@ def columnify(l):
                             column = l.replace('\t', 8 * ' ')[max(0, beg - 1):end].strip()
                         except:
                             column = l
-                        column = re.sub(" *(?:\(at\)| <at> | at ) *", "@", column)
-                        column = re.sub(" *(?:\(dot\)| <dot> | dot ) *", ".", column)
-                        column = re.sub("&cisco.com", "@cisco.com", column)
+                        column = re.sub(r" *(?:\(at\)| <at> | at ) *", "@", column)
+                        column = re.sub(r" *(?:\(dot\)| <dot> | dot ) *", ".", column)
+                        column = re.sub(r"&cisco.com", "@cisco.com", column)
                         column = column.replace("\xa0", " ")
                         return column
 
@@ -1003,13 +1003,13 @@ def columnify(l):
     def get_title(self):
         if self._title:
             return self._title
-        match = re.search('(?:\n\s*\n\s*)((.+\n){0,2}(.+\n*))(\s+<?draft-\S+\s*\n)\s*\n', self.pages[0])
+        match = re.search(r'(?:\n\s*\n\s*)((.+\n){0,2}(.+\n*))(\s+<?draft-\S+\s*\n)\s*\n', self.pages[0])
         if not match:
-            match = re.search('(?:\n\s*\n\s*)<?draft-\S+\s*\n*((.+\n){1,3})\s*\n', self.pages[0])
+            match = re.search(r'(?:\n\s*\n\s*)<?draft-\S+\s*\n*((.+\n){1,3})\s*\n', self.pages[0])
         if not match:
-            match = re.search('(?:\n\s*\n\s*)((.+\n){0,2}(.+\n*))(\s*\n){2}', self.pages[0])
+            match = re.search(r'(?:\n\s*\n\s*)((.+\n){0,2}(.+\n*))(\s*\n){2}', self.pages[0])
         if not match:
-            match = re.search('(?i)(.+\n|.+\n.+\n)(\s*status of this memo\s*\n)', self.pages[0])
+            match = re.search(r'(?i)(.+\n|.+\n.+\n)(\s*status of this memo\s*\n)', self.pages[0])
         if match:
             title = match.group(1)
             title = title.strip()
@@ -1147,10 +1147,10 @@ def old_get_refs( self ):
                             para += " "
                         para += line
                     refs += [ para ]
-                    rfc_match = re.search("(?i)rfc ?\d+", para)
+                    rfc_match = re.search(r"(?i)rfc ?\d+", para)
                     if rfc_match:
                         rfcrefs += [ rfc_match.group(0).replace(" ","").lower() ]
-                    draft_match = re.search("draft-[a-z0-9-]+", para)
+                    draft_match = re.search(r"draft-[a-z0-9-]+", para)
                     if draft_match:
                         draft = draft_match.group(0).lower()
                         if not draft in draftrefs:
@@ -1185,7 +1185,7 @@ def getmeta(fn):
             if not os.path.exists(filename):
                 fn = filename
                 while not "-00." in fn:
-                    revmatch = re.search("-(\d\d)\.", fn)
+                    revmatch = re.search(r"-(\d\d)\.", fn)
                     if revmatch:
                         rev = revmatch.group(1)
                         prev = "%02d" % (int(rev)-1)
@@ -1312,7 +1312,7 @@ def _main(outfile=sys.stdout):
     # Option processing
     # ----------------------------------------------------------------------
     options = ""
-    for line in re.findall("\n +(if|elif) +opt in \[(.+)\]:\s+#(.+)\n", open(sys.argv[0]).read()):
+    for line in re.findall(r"\n +(if|elif) +opt in \[(.+)\]:\s+#(.+)\n", open(sys.argv[0]).read()):
         if not options:
             options += "OPTIONS\n"
         options += "        %-16s %s\n" % (line[1].replace('"', ''), line[2])

ietf/utils/draft_search.py

@@ -1,8 +1,8 @@
-# Copyright The IETF Trust 2007, All Rights Reserved
+# Copyright The IETF Trust 2007-2019, All Rights Reserved
 import re
 
 def normalize_draftname(string):
     string = string.strip()
-    string = re.sub("\.txt$","",string)
-    string = re.sub("-\d\d$","",string)
+    string = re.sub(r"\.txt$","",string)
+    string = re.sub(r"-\d\d$","",string)
     return string

ietf/utils/markup_txt.py

@@ -74,11 +74,11 @@ def markup(content, width=None):
     # expand tabs + escape 
     content = escape(content.expandtabs())
 
-    content = re.sub("\n(.+\[Page \d+\])\n\f\n(.+)\n", """\n<span class="m_ftr">\g<1></span>\n<span class="m_hdr">\g<2></span>\n""", content)
-    content = re.sub("\n(.+\[Page \d+\])\n\s*$", """\n<span class="m_ftr">\g<1></span>\n""", content)
+    content = re.sub(r"\n(.+\[Page \d+\])\n\f\n(.+)\n", r"""\n<span class="m_ftr">\g<1></span>\n<span class="m_hdr">\g<2></span>\n""", content)
+    content = re.sub(r"\n(.+\[Page \d+\])\n\s*$", r"""\n<span class="m_ftr">\g<1></span>\n""", content)
     # remove remaining FFs (to be valid XHTML)
     content = content.replace("\f","\n")
 
-    content = re.sub("\n\n([0-9]+\\.|[A-Z]\\.[0-9]|Appendix|Status of|Abstract|Table of|Full Copyright|Copyright|Intellectual Property|Acknowled|Author|Index)(.*)(?=\n\n)", """\n\n<span class="m_h">\g<1>\g<2></span>""", content)
+    content = re.sub(r"\n\n([0-9]+\\.|[A-Z]\\.[0-9]|Appendix|Status of|Abstract|Table of|Full Copyright|Copyright|Intellectual Property|Acknowled|Author|Index)(.*)(?=\n\n)", r"""\n\n<span class="m_h">\g<1>\g<2></span>""", content)
 
     return "<pre>" + content + "</pre>\n"

ietf/utils/pdf.py

@@ -1,3 +1,4 @@
+# Copyright The IETF Trust 2015-2019, All Rights Reserved
 import re
 
 def pdf_pages(filename):
@@ -7,7 +8,7 @@ def pdf_pages(filename):
     except IOError:
         return 0
     for line in infile:
-        m = re.match('\] /Count ([0-9]+)',line)
+        m = re.match(r'\] /Count ([0-9]+)',line)
         if m:
             return int(m.group(1))
     return 0