bpo-31677: email: Remove re.IGNORECASE flag (pythonGH-3868)

methane · web-flow · commit bf477a99e0c8 · 2017-10-04T12:47:38.000+09:00
While there is not real bug in this case, using re.IGNORECASE without re.ASCII
leads unexpected behavior.
Instead of adding re.ASCII, this commit removes re.IGNORECASE flag because
it's easier and simpler.

This commit removes dead copy of the pattern in email.util module too.
While the pattern is same, it is compiled separately because it had different flags.
diff --git a/Lib/email/header.py b/Lib/email/header.py
@@ -36,11 +36,11 @@
   =\?                   # literal =?
   (?P<charset>[^?]*?)   # non-greedy up to the next ? is the charset
   \?                    # literal ?
-  (?P<encoding>[qb])    # either a "q" or a "b", case insensitive
+  (?P<encoding>[qQbB])  # either a "q" or a "b", case insensitive
   \?                    # literal ?
   (?P<encoded>.*?)      # non-greedy up to the next ?= is the encoded string
   \?=                   # literal ?=
-  ''', re.VERBOSE | re.IGNORECASE | re.MULTILINE)
+  ''', re.VERBOSE | re.MULTILINE)
 
 # Field name regexp, including trailing colon, but not separating whitespace,
 # according to RFC 2822.  Character range is from tilde to exclamation mark.
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
@@ -114,18 +114,6 @@ def getaddresses(fieldvalues):
     return a.addresslist
 
 
-
-ecre = re.compile(r'''
-  =\?                   # literal =?
-  (?P<charset>[^?]*?)   # non-greedy up to the next ? is the charset
-  \?                    # literal ?
-  (?P<encoding>[qb])    # either a "q" or a "b", case insensitive
-  \?                    # literal ?
-  (?P<atom>.*?)         # non-greedy up to the next ?= is the atom
-  \?=                   # literal ?=
-  ''', re.VERBOSE | re.IGNORECASE)
-
-
 def _format_timetuple_and_zone(timetuple, zone):
     return '%s, %02d %s %04d %02d:%02d:%02d %s' % (
         ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'][timetuple[6]],
