Merge branch 'name-fixing' into development

api.py

@@ -1,4 +1,4 @@
-import re
+import regex
 
 import bottle
 from bottle import request, response
@@ -21,7 +21,7 @@ def api():
         # reform s|search into ^s$|^search$
         # if we don't, 's' matches 'caps' (s)
         r = '|'.join(['^{0}$'.format(r) for r in r.split('|')])
-        if re.search(r, function):
+        if regex.search(r, function):
             dataset = dict()
             dataset['get_link'] = get_link
             data = func(dataset)

lib/nntplib.py

@@ -63,7 +63,7 @@
 # - support HDR
 
 # Imports
-import re
+import regex
 import socket
 import collections
 import datetime
@@ -700,7 +700,7 @@ def list(self, group_pattern=None, *, file=None):
         return resp, self._grouplist(lines)
 
     def _getdescriptions(self, group_pattern, return_all):
-        line_pat = re.compile('^(?P<group>[^ \t]+)[ \t]+(.*)$')
+        line_pat = regex.compile('^(?P<group>[^ \t]+)[ \t]+(.*)$')
         # Try the more std (acc. to RFC2980) LIST NEWSGROUPS first
         resp, lines = self._longcmdstring('LIST NEWSGROUPS ' + group_pattern)
         if not resp.startswith('215'):
@@ -875,7 +875,7 @@ def xhdr(self, hdr, str, *, file=None):
         - resp: server response if successful
         - list: list of (nr, value) strings
         """
-        pat = re.compile('^([0-9]+) ?(.*)\n?')
+        pat = regex.compile('^([0-9]+) ?(.*)\n?')
         resp, lines = self._longcmdstring('XHDR {0} {1}'.format(hdr, str), file)
         def remove_number(line):
             m = pat.match(line)
@@ -951,7 +951,7 @@ def xgtitle(self, group, *, file=None):
         warnings.warn("The XGTITLE extension is not actively used, "
                       "use descriptions() instead",
                       DeprecationWarning, 2)
-        line_pat = re.compile('^([^ \t]+)[ \t]+(.*)$')
+        line_pat = regex.compile('^([^ \t]+)[ \t]+(.*)$')
         resp, raw_lines = self._longcmdstring('XGTITLE ' + group, file)
         lines = []
         for raw_line in raw_lines:
@@ -1253,4 +1253,4 @@ def cut(s, lim):
               )
 
     s.quit()
-
+

lib/rar.py

@@ -211,8 +211,6 @@ def _getContents(self):
             if head_type == 0x73:
                 #TODO: Try to factor this out to reduce time spent in syscalls.
                 self.fp.seek(offset + 2) # Seek to just after HEAD_CRC
-                #FIXME: Check header CRC on all blocks.
-                assert self._check_crc(self.fp.read(11), head_crc)
 
             # TODO: Rework handling of file headers.
             elif head_type == 0x74:

pynab/binaries.py

@@ -1,4 +1,4 @@
-import re
+import regex
 import time
 import datetime
 import pytz
@@ -104,28 +104,28 @@ def process():
     # where(), but it's slow as hell because it's processed by the JS engine
     relevant_groups = db.parts.distinct('group_name')
     for part in db.parts.find({'group_name': {'$in': relevant_groups}}, exhaust=True):
-        for regex in db.regexes.find({'group_name': {'$in': [part['group_name'], '*']}}).sort('ordinal', 1):
+        for reg in db.regexes.find({'group_name': {'$in': [part['group_name'], '*']}}).sort('ordinal', 1):
             # convert php-style regex to python
-            # ie. /(\w+)/i -> (\w+), re.I
+            # ie. /(\w+)/i -> (\w+), regex.I
             # no need to handle s, as it doesn't exist in python
 
             # why not store it as python to begin with? some regex
             # shouldn't be case-insensitive, and this notation allows for that
-            r = regex['regex']
+            r = reg['regex']
             flags = r[r.rfind('/') + 1:]
             r = r[r.find('/') + 1:r.rfind('/')]
-            regex_flags = re.I if 'i' in flags else 0
+            regex_flags = regex.I if 'i' in flags else 0
 
             try:
-                result = re.search(r, part['subject'], regex_flags)
+                result = regex.search(r, part['subject'], regex_flags)
             except:
-                log.error('Broken regex detected. _id: {:d}, removing...'.format(regex['_id']))
-                db.regexes.remove({'_id': regex['_id']})
+                log.error('Broken regex detected. _id: {:d}, removing...'.format(reg['_id']))
+                db.regexes.remove({'_id': reg['_id']})
                 continue
 
             match = result.groupdict() if result else None
             if match:
-                log.debug('Matched part {} to {}.'.format(part['subject'], regex['regex']))
+                log.debug('Matched part {} to {}.'.format(part['subject'], reg['regex']))
                 # remove whitespace in dict values
                 match = {k: v.strip() for k, v in match.items()}
 
@@ -146,7 +146,7 @@ def process():
                 # segment numbers have been stripped by this point, so don't worry
                 # about accidentally hitting those instead
                 if not match.get('parts'):
-                    result = re.search('(\d{1,3}\/\d{1,3})', part['subject'])
+                    result = regex.search('(\d{1,3}\/\d{1,3})', part['subject'])
                     if result:
                         match['parts'] = result.group(1)
 
@@ -175,8 +175,8 @@ def process():
                             'posted_by': part['posted_by'],
                             'group_name': part['group_name'],
                             'xref': part['xref'],
-                            'regex_id': regex['_id'],
-                            'category_id': regex['category_id'],
+                            'regex_id': reg['_id'],
+                            'category_id': reg['category_id'],
                             'req_id': match.get('reqid'),
                             'total_parts': int(total),
                             'parts': {current: part}
@@ -210,7 +210,7 @@ def parse_xref(xref):
     groups = []
     raw_groups = xref.split(' ')
     for raw_group in raw_groups:
-        result = re.search('^([a-z0-9\.\-_]+):(\d+)?$', raw_group, re.I)
+        result = regex.search('^([a-z0-9\.\-_]+):(\d+)?$', raw_group, regex.I)
         if result:
             groups.append(result.group(1))
     return groups