mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-10-09 16:34:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 17

bpo-30688: Support \N{name} escapes in re patterns. (GH-5588)

Browse source 
Co-authored-by: Jonathan Eunice <jonathan.eunice@gmail.com>
This commit is contained in:
Serhiy Storchaka 2018-02-10 00:08:17 +02:00 • committed by GitHub
parent 2411292ba8
commit a445feb729
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 77 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

37
Lib/sre_parse.py
View file

@ -13,6 +13,7 @@
# XXX: show string offset and offending character for all errors
from sre_constants import *
import unicodedata
SPECIAL_CHARS = ".\\[{()*+?^$|"
REPEAT_CHARS = "*+?{"
@ -264,19 +265,19 @@ class Tokenizer:
result += c
self.__next()
return result
def getuntil(self, terminator):
def getuntil(self, terminator, name):
result = ''
while True:
c = self.next
self.__next()
if c is None:
if not result:
raise self.error("missing group name")
raise self.error("missing " + name)
raise self.error("missing %s, unterminated name" % terminator,
len(result))
if c == terminator:
if not result:
raise self.error("missing group name", 1)
raise self.error("missing " + name, 1)
break
result += c
return result
@ -322,6 +323,17 @@ def _class_escape(source, escape):
c = int(escape[2:], 16)
chr(c) # raise ValueError for invalid code
return LITERAL, c
elif c == "N" and source.istext:
# named unicode escape e.g. \N{EM DASH}
if not source.match('{'):
raise source.error("missing {")
charname = source.getuntil('}', 'character name')
try:
c = ord(unicodedata.lookup(charname))
except KeyError:
raise source.error("undefined character name %r" % charname,
len(charname) + len(r'\N{}'))
return LITERAL, c
elif c in OCTDIGITS:
# octal escape (up to three digits)
escape += source.getwhile(2, OCTDIGITS)
@ -370,6 +382,17 @@ def _escape(source, escape, state):
c = int(escape[2:], 16)
chr(c) # raise ValueError for invalid code
return LITERAL, c
elif c == "N" and source.istext:
# named unicode escape e.g. \N{EM DASH}
if not source.match('{'):
raise source.error("missing {")
charname = source.getuntil('}', 'character name')
try:
c = ord(unicodedata.lookup(charname))
except KeyError:
raise source.error("undefined character name %r" % charname,
len(charname) + len(r'\N{}'))
return LITERAL, c
elif c == "0":
# octal escape
escape += source.getwhile(2, OCTDIGITS)
@ -679,13 +702,13 @@ def _parse(source, state, verbose, nested, first=False):
# python extensions
if sourcematch("<"):
# named group: skip forward to end of name
name = source.getuntil(">")
name = source.getuntil(">", "group name")
if not name.isidentifier():
msg = "bad character in group name %r" % name
raise source.error(msg, len(name) + 1)
elif sourcematch("="):
# named backreference
name = source.getuntil(")")
name = source.getuntil(")", "group name")
if not name.isidentifier():
msg = "bad character in group name %r" % name
raise source.error(msg, len(name) + 1)
@ -748,7 +771,7 @@ def _parse(source, state, verbose, nested, first=False):
elif char == "(":
# conditional backreference group
condname = source.getuntil(")")
condname = source.getuntil(")", "group name")
if condname.isidentifier():
condgroup = state.groupdict.get(condname)
if condgroup is None:
@ -977,7 +1000,7 @@ def parse_template(source, pattern):
name = ""
if not s.match("<"):
raise s.error("missing <")
name = s.getuntil(">")
name = s.getuntil(">", "group name")
if name.isidentifier():
try:
index = groupindex[name]