This is an archive of the discontinued Mercurial Phabricator instance.

Differential D2147

py3: use email parser that operates on bytes
ClosedPublic

Authored by indygreg on Feb 11 2018, 5:57 PM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHG04984f2e50ae: py3: use email parser that operates on bytes
Summary

email.parser.Parser() operates on str in both Python 2 and 3.
Python 3.2 introduced the email.parser.BytesParser(), which works
like Parser except it accepts bytes.

We implement the pycompat helper as a function so we lazily
import the "email" module.

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Event Timeline

indygreg created this revision.Feb 11 2018, 5:57 PM
Closed by commit rHG04984f2e50ae: py3: use email parser that operates on bytes (authored by indygreg). · Explain WhyFeb 11 2018, 8:40 PM
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mmercurial/patch.py (5 lines)
Mmercurial/pycompat.py (8 lines)

Diff 5447

mercurial/patch.py

# patch.py - patch file parsing routines # patch.py - patch file parsing routines
# #
# Copyright 2006 Brendan Cully <brendan@kublai.com> # Copyright 2006 Brendan Cully <brendan@kublai.com>
# Copyright 2007 Chris Mason <chris.mason@oracle.com> # Copyright 2007 Chris Mason <chris.mason@oracle.com>
# #
# This software may be used and distributed according to the terms of the # This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version. # GNU General Public License version 2 or any later version.
from __future__ import absolute_import, print_function from __future__ import absolute_import, print_function
import collections import collections
import copy import copy
import difflib import difflib
import email import email
import email.parser as emailparser
import errno import errno
import hashlib import hashlib
import os import os
import posixpath import posixpath
import re import re
import shutil import shutil
import tempfile import tempfile
import zlib import zlib
g.flatten(m) g.flatten(m)
fp.seek(0) fp.seek(0)
return fp return fp
for line in stream: for line in stream:
cur.append(line) cur.append(line)
c = chunk(cur) c = chunk(cur)
m = emailparser.Parser().parse(c) m = pycompat.emailparser().parse(c)
if not m.is_multipart(): if not m.is_multipart():
yield msgfp(m) yield msgfp(m)
else: else:
ok_types = ('text/plain', 'text/x-diff', 'text/x-patch') ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
for part in m.walk(): for part in m.walk():
ct = part.get_content_type() ct = part.get_content_type()
if ct not in ok_types: if ct not in ok_types:
continue continue
br'---[ \t].*?^\+\+\+[ \t]|' br'---[ \t].*?^\+\+\+[ \t]|'
br'\*\*\*[ \t].*?^---[ \t])', br'\*\*\*[ \t].*?^---[ \t])',
re.MULTILINE | re.DOTALL) re.MULTILINE | re.DOTALL)
data = {} data = {}
fd, tmpname = tempfile.mkstemp(prefix='hg-patch-') fd, tmpname = tempfile.mkstemp(prefix='hg-patch-')
tmpfp = os.fdopen(fd, pycompat.sysstr('w')) tmpfp = os.fdopen(fd, pycompat.sysstr('w'))
try: try:
msg = emailparser.Parser().parse(fileobj) msg = pycompat.emailparser().parse(fileobj)
subject = msg['Subject'] and mail.headdecode(msg['Subject']) subject = msg['Subject'] and mail.headdecode(msg['Subject'])
data['user'] = msg['From'] and mail.headdecode(msg['From']) data['user'] = msg['From'] and mail.headdecode(msg['From'])
if not subject and not data['user']: if not subject and not data['user']:
# Not an email, restore parsed headers if any # Not an email, restore parsed headers if any
subject = '\n'.join(': '.join(h) for h in msg.items()) + '\n' subject = '\n'.join(': '.join(h) for h in msg.items()) + '\n'
# should try to parse msg['Date'] # should try to parse msg['Date']

mercurial/pycompat.py

""" """
Takes bytes argument, convert it to str i.e. unicodes, pass that into Takes bytes argument, convert it to str i.e. unicodes, pass that into
shlex.split(), convert the returned value to bytes and return that for shlex.split(), convert the returned value to bytes and return that for
Python 3 compatibility as shelx.split() don't accept bytes on Python 3. Python 3 compatibility as shelx.split() don't accept bytes on Python 3.
""" """
ret = shlex.split(s.decode('latin-1')) ret = shlex.split(s.decode('latin-1'))
return [a.encode('latin-1') for a in ret] return [a.encode('latin-1') for a in ret]
def emailparser(*args, **kwargs):
import email.parser
return email.parser.BytesParser(*args, **kwargs)
else: else:
import cStringIO import cStringIO
bytechr = chr bytechr = chr
bytestr = str bytestr = str
iterbytestr = iter iterbytestr = iter
maybebytestr = identity maybebytestr = identity
sysbytes = identity sysbytes = identity
getcwd = os.getcwd getcwd = os.getcwd
sysexecutable = sys.executable sysexecutable = sys.executable
shlexsplit = shlex.split shlexsplit = shlex.split
stringio = cStringIO.StringIO stringio = cStringIO.StringIO
maplist = map maplist = map
ziplist = zip ziplist = zip
rawinput = raw_input rawinput = raw_input
def emailparser(*args, **kwargs):
import email.parser
return email.parser.Parser(*args, **kwargs)
isjython = sysplatform.startswith('java') isjython = sysplatform.startswith('java')
isdarwin = sysplatform == 'darwin' isdarwin = sysplatform == 'darwin'
isposix = osname == 'posix' isposix = osname == 'posix'
iswindows = osname == 'nt' iswindows = osname == 'nt'
def getoptb(args, shortlist, namelist): def getoptb(args, shortlist, namelist):
return _getoptbwrapper(getopt.getopt, args, shortlist, namelist) return _getoptbwrapper(getopt.getopt, args, shortlist, namelist)
def gnugetoptb(args, shortlist, namelist): def gnugetoptb(args, shortlist, namelist):
return _getoptbwrapper(getopt.gnu_getopt, args, shortlist, namelist) return _getoptbwrapper(getopt.gnu_getopt, args, shortlist, namelist)