This is an archive of the discontinued Mercurial Phabricator instance.

Differential D3306

patch: make extract() a context manager (API)
ClosedPublic

Authored by indygreg on Apr 13 2018, 2:26 AM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHG5537d8f5e989: patch: make extract() a context manager (API)
Summary

Previously, this function was creating a temporary file and relying
on callers to unlink it. Yuck.

We convert the function to a context manager and tie the lifetime of
the temporary file to that of the context manager. This changed
indentation not only from the context manager, but also from the
elination of try blocks. It was just easier to split the heart of
extract() into its own function.

The single consumer of this function has been refactored to use it as
a context manager. Code for cleaning up the file in tryimportone()
has also been removed.

.. api::

``patch.extract()`` is now a context manager. Callers no longer have
to worry about deleting the temporary file it creates, as the file is
tied to the lifetime of the context manager.

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.Apr 13 2018, 2:26 AM
Closed by commit rHG5537d8f5e989: patch: make extract() a context manager (API) (authored by indygreg). · Explain WhyApr 13 2018, 8:44 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mmercurial/cmdutil.py (248 lines)
Mmercurial/commands.py (9 lines)
Mmercurial/patch.py (161 lines)

Diff 8111

mercurial/cmdutil.py

p2 = patchdata.get('p2') p2 = patchdata.get('p2')
nocommit = opts.get('no_commit') nocommit = opts.get('no_commit')
importbranch = opts.get('import_branch') importbranch = opts.get('import_branch')
update = not opts.get('bypass') update = not opts.get('bypass')
strip = opts["strip"] strip = opts["strip"]
prefix = opts["prefix"] prefix = opts["prefix"]
sim = float(opts.get('similarity') or 0) sim = float(opts.get('similarity') or 0)
if not tmpname: if not tmpname:
return (None, None, False) return None, None, False
rejects = False rejects = False
try:
cmdline_message = logmessage(ui, opts) cmdline_message = logmessage(ui, opts)
if cmdline_message: if cmdline_message:
# pickup the cmdline msg # pickup the cmdline msg
message = cmdline_message message = cmdline_message
elif message: elif message:
# pickup the patch msg # pickup the patch msg
message = message.strip() message = message.strip()
else: else:
# launch the editor # launch the editor
message = None message = None
ui.debug('message:\n%s\n' % (message or '')) ui.debug('message:\n%s\n' % (message or ''))
if len(parents) == 1: if len(parents) == 1:
parents.append(repo[nullid]) parents.append(repo[nullid])
if opts.get('exact'): if opts.get('exact'):
if not nodeid or not p1: if not nodeid or not p1:
raise error.Abort(_('not a Mercurial patch')) raise error.Abort(_('not a Mercurial patch'))
p1 = repo[p1] p1 = repo[p1]
p2 = repo[p2 or nullid] p2 = repo[p2 or nullid]
elif p2: elif p2:
try: try:
p1 = repo[p1] p1 = repo[p1]
p2 = repo[p2] p2 = repo[p2]
# Without any options, consider p2 only if the # Without any options, consider p2 only if the
# patch is being applied on top of the recorded # patch is being applied on top of the recorded
# first parent. # first parent.
if p1 != parents[0]: if p1 != parents[0]:
p1 = parents[0] p1 = parents[0]
p2 = repo[nullid] p2 = repo[nullid]
except error.RepoError: except error.RepoError:
p1, p2 = parents p1, p2 = parents
if p2.node() == nullid: if p2.node() == nullid:
ui.warn(_("warning: import the patch as a normal revision\n" ui.warn(_("warning: import the patch as a normal revision\n"
"(use --exact to import the patch as a merge)\n")) "(use --exact to import the patch as a merge)\n"))
else: else:
p1, p2 = parents p1, p2 = parents
n = None n = None
if update: if update:
if p1 != parents[0]: if p1 != parents[0]:
updatefunc(repo, p1.node()) updatefunc(repo, p1.node())
if p2 != parents[1]: if p2 != parents[1]:
repo.setparents(p1.node(), p2.node()) repo.setparents(p1.node(), p2.node())
if opts.get('exact') or importbranch: if opts.get('exact') or importbranch:
repo.dirstate.setbranch(branch or 'default') repo.dirstate.setbranch(branch or 'default')
partial = opts.get('partial', False) partial = opts.get('partial', False)
files = set() files = set()
try: try:
patch.patch(ui, repo, tmpname, strip=strip, prefix=prefix, patch.patch(ui, repo, tmpname, strip=strip, prefix=prefix,
files=files, eolmode=None, similarity=sim / 100.0) files=files, eolmode=None, similarity=sim / 100.0)
except error.PatchError as e: except error.PatchError as e:
if not partial: if not partial:
raise error.Abort(pycompat.bytestr(e)) raise error.Abort(pycompat.bytestr(e))
if partial: if partial:
rejects = True rejects = True
files = list(files) files = list(files)
if nocommit: if nocommit:
if message: if message:
msgs.append(message) msgs.append(message)
else: else:
if opts.get('exact') or p2: if opts.get('exact') or p2:
# If you got here, you either use --force and know what # If you got here, you either use --force and know what
# you are doing or used --exact or a merge patch while # you are doing or used --exact or a merge patch while
# being updated to its first parent. # being updated to its first parent.
m = None m = None
else: else:
m = scmutil.matchfiles(repo, files or []) m = scmutil.matchfiles(repo, files or [])
editform = mergeeditform(repo[None], 'import.normal') editform = mergeeditform(repo[None], 'import.normal')
if opts.get('exact'): if opts.get('exact'):
editor = None editor = None
else: else:
editor = getcommiteditor(editform=editform, editor = getcommiteditor(editform=editform,
**pycompat.strkwargs(opts)) **pycompat.strkwargs(opts))
extra = {} extra = {}
for idfunc in extrapreimport: for idfunc in extrapreimport:
extrapreimportmap[idfunc](repo, patchdata, extra, opts) extrapreimportmap[idfunc](repo, patchdata, extra, opts)
overrides = {} overrides = {}
if partial: if partial:
overrides[('ui', 'allowemptycommit')] = True overrides[('ui', 'allowemptycommit')] = True
with repo.ui.configoverride(overrides, 'import'): with repo.ui.configoverride(overrides, 'import'):
n = repo.commit(message, user, n = repo.commit(message, user,
date, match=m, date, match=m,
editor=editor, extra=extra) editor=editor, extra=extra)
for idfunc in extrapostimport: for idfunc in extrapostimport:
extrapostimportmap[idfunc](repo[n]) extrapostimportmap[idfunc](repo[n])
else: else:
if opts.get('exact') or importbranch: if opts.get('exact') or importbranch:
branch = branch or 'default' branch = branch or 'default'
else: else:
branch = p1.branch() branch = p1.branch()
store = patch.filestore() store = patch.filestore()
try: try:
files = set() files = set()
try: try:
patch.patchrepo(ui, repo, p1, store, tmpname, strip, prefix, patch.patchrepo(ui, repo, p1, store, tmpname, strip, prefix,
files, eolmode=None) files, eolmode=None)
except error.PatchError as e: except error.PatchError as e:
raise error.Abort(stringutil.forcebytestr(e)) raise error.Abort(stringutil.forcebytestr(e))
if opts.get('exact'): if opts.get('exact'):
editor = None editor = None
else: else:
editor = getcommiteditor(editform='import.bypass') editor = getcommiteditor(editform='import.bypass')
memctx = context.memctx(repo, (p1.node(), p2.node()), memctx = context.memctx(repo, (p1.node(), p2.node()),
message, message,
files=files, files=files,
filectxfn=store, filectxfn=store,
user=user, user=user,
date=date, date=date,
branch=branch, branch=branch,
editor=editor) editor=editor)
n = memctx.commit() n = memctx.commit()
finally: finally:
store.close() store.close()
if opts.get('exact') and nocommit: if opts.get('exact') and nocommit:
# --exact with --no-commit is still useful in that it does merge # --exact with --no-commit is still useful in that it does merge
# and branch bits # and branch bits
ui.warn(_("warning: can't check exact import with --no-commit\n")) ui.warn(_("warning: can't check exact import with --no-commit\n"))
elif opts.get('exact') and hex(n) != nodeid: elif opts.get('exact') and hex(n) != nodeid:
raise error.Abort(_('patch is damaged or loses information')) raise error.Abort(_('patch is damaged or loses information'))
msg = _('applied to working directory') msg = _('applied to working directory')
if n: if n:
# i18n: refers to a short changeset id # i18n: refers to a short changeset id
msg = _('created %s') % short(n) msg = _('created %s') % short(n)
return (msg, n, rejects) return msg, n, rejects
finally:
os.unlink(tmpname)
# facility to let extensions include additional data in an exported patch # facility to let extensions include additional data in an exported patch
# list of identifiers to be executed in order # list of identifiers to be executed in order
extraexport = [] extraexport = []
# mapping from identifier to actual export function # mapping from identifier to actual export function
# function as to return a string to be added to the header or None # function as to return a string to be added to the header or None
# it is given two arguments (sequencenumber, changectx) # it is given two arguments (sequencenumber, changectx)
extraexportmap = {} extraexportmap = {}

mercurial/commands.py

patchurl = 'stdin' # for error message patchurl = 'stdin' # for error message
else: else:
patchurl = os.path.join(base, patchurl) patchurl = os.path.join(base, patchurl)
ui.status(_('applying %s\n') % patchurl) ui.status(_('applying %s\n') % patchurl)
patchfile = hg.openpath(ui, patchurl) patchfile = hg.openpath(ui, patchurl)
haspatch = False haspatch = False
for hunk in patch.split(patchfile): for hunk in patch.split(patchfile):
patchdata = patch.extract(ui, hunk) with patch.extract(ui, hunk) as patchdata:
msg, node, rej = cmdutil.tryimportone(ui, repo, patchdata, msg, node, rej = cmdutil.tryimportone(ui, repo, patchdata,
parents, opts, parents, opts,
msgs, hg.clean) msgs, hg.clean)
if msg: if msg:
haspatch = True haspatch = True
ui.note(msg + '\n') ui.note(msg + '\n')
if update or exact: if update or exact:
parents = repo[None].parents() parents = repo[None].parents()
else: else:
parents = [repo[node]] parents = [repo[node]]
if rej: if rej:

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 contextlib
import copy import copy
import difflib import difflib
import email import email
import errno import errno
import hashlib import hashlib
import os import os
import posixpath import posixpath
import re import re
## Some facility for extensible patch parsing: ## Some facility for extensible patch parsing:
# list of pairs ("header to match", "data key") # list of pairs ("header to match", "data key")
patchheadermap = [('Date', 'date'), patchheadermap = [('Date', 'date'),
('Branch', 'branch'), ('Branch', 'branch'),
('Node ID', 'nodeid'), ('Node ID', 'nodeid'),
] ]
@contextlib.contextmanager
def extract(ui, fileobj): def extract(ui, fileobj):
'''extract patch from data read from fileobj. '''extract patch from data read from fileobj.
patch can be a normal patch or contained in an email message. patch can be a normal patch or contained in an email message.
return a dictionary. Standard keys are: return a dictionary. Standard keys are:
- filename, - filename,
- message, - message,
- user, - user,
- date, - date,
- branch, - branch,
- node, - node,
- p1, - p1,
- p2. - p2.
Any item can be missing from the dictionary. If filename is missing, Any item can be missing from the dictionary. If filename is missing,
fileobj did not contain a patch. Caller must unlink filename when done.''' fileobj did not contain a patch. Caller must unlink filename when done.'''
fd, tmpname = tempfile.mkstemp(prefix='hg-patch-')
tmpfp = os.fdopen(fd, r'wb')
try:
yield _extract(ui, fileobj, tmpname, tmpfp)
finally:
tmpfp.close()
os.unlink(tmpname)
def _extract(ui, fileobj, tmpname, tmpfp):
# attempt to detect the start of a patch # attempt to detect the start of a patch
# (this heuristic is borrowed from quilt) # (this heuristic is borrowed from quilt)
diffre = re.compile(br'^(?:Index:[ \t]|diff[ \t]-|RCS file: |' diffre = re.compile(br'^(?:Index:[ \t]|diff[ \t]-|RCS file: |'
br'retrieving revision [0-9]+(\.[0-9]+)*$|' br'retrieving revision [0-9]+(\.[0-9]+)*$|'
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-')
tmpfp = os.fdopen(fd, r'wb')
try:
msg = pycompat.emailparser().parse(fileobj) msg = pycompat.emailparser().parse(fileobj)
subject = msg[r'Subject'] and mail.headdecode(msg[r'Subject']) subject = msg[r'Subject'] and mail.headdecode(msg[r'Subject'])
data['user'] = msg[r'From'] and mail.headdecode(msg[r'From']) data['user'] = msg[r'From'] and mail.headdecode(msg[r'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(map(encoding.strtolocal, h)) subject = '\n'.join(': '.join(map(encoding.strtolocal, h))
for h in msg.items()) + '\n' for h in msg.items()) + '\n'
# should try to parse msg['Date'] # should try to parse msg['Date']
parents = [] parents = []
if subject: if subject:
if subject.startswith('[PATCH'): if subject.startswith('[PATCH'):
pend = subject.find(']') pend = subject.find(']')
if pend >= 0: if pend >= 0:
subject = subject[pend + 1:].lstrip() subject = subject[pend + 1:].lstrip()
subject = re.sub(br'\n[ \t]+', ' ', subject) subject = re.sub(br'\n[ \t]+', ' ', subject)
ui.debug('Subject: %s\n' % subject) ui.debug('Subject: %s\n' % subject)
if data['user']: if data['user']:
ui.debug('From: %s\n' % data['user']) ui.debug('From: %s\n' % data['user'])
diffs_seen = 0 diffs_seen = 0
ok_types = ('text/plain', 'text/x-diff', 'text/x-patch') ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
message = '' message = ''
for part in msg.walk(): for part in msg.walk():
content_type = pycompat.bytestr(part.get_content_type()) content_type = pycompat.bytestr(part.get_content_type())
ui.debug('Content-Type: %s\n' % content_type) ui.debug('Content-Type: %s\n' % content_type)
if content_type not in ok_types: if content_type not in ok_types:
continue continue
payload = part.get_payload(decode=True) payload = part.get_payload(decode=True)
m = diffre.search(payload) m = diffre.search(payload)
if m: if m:
hgpatch = False hgpatch = False
hgpatchheader = False hgpatchheader = False
ignoretext = False ignoretext = False
ui.debug('found patch at byte %d\n' % m.start(0)) ui.debug('found patch at byte %d\n' % m.start(0))
diffs_seen += 1 diffs_seen += 1
cfp = stringio() cfp = stringio()
for line in payload[:m.start(0)].splitlines(): for line in payload[:m.start(0)].splitlines():
if line.startswith('# HG changeset patch') and not hgpatch: if line.startswith('# HG changeset patch') and not hgpatch:
ui.debug('patch generated by hg export\n') ui.debug('patch generated by hg export\n')
hgpatch = True hgpatch = True
hgpatchheader = True hgpatchheader = True
# drop earlier commit message content # drop earlier commit message content
cfp.seek(0) cfp.seek(0)
cfp.truncate() cfp.truncate()
subject = None subject = None
elif hgpatchheader: elif hgpatchheader:
if line.startswith('# User '): if line.startswith('# User '):
data['user'] = line[7:] data['user'] = line[7:]
ui.debug('From: %s\n' % data['user']) ui.debug('From: %s\n' % data['user'])
elif line.startswith("# Parent "): elif line.startswith("# Parent "):
parents.append(line[9:].lstrip()) parents.append(line[9:].lstrip())
elif line.startswith("# "): elif line.startswith("# "):
for header, key in patchheadermap: for header, key in patchheadermap:
prefix = '# %s ' % header prefix = '# %s ' % header
if line.startswith(prefix): if line.startswith(prefix):
data[key] = line[len(prefix):] data[key] = line[len(prefix):]
else: else:
hgpatchheader = False hgpatchheader = False
elif line == '---': elif line == '---':
ignoretext = True ignoretext = True
if not hgpatchheader and not ignoretext: if not hgpatchheader and not ignoretext:
cfp.write(line) cfp.write(line)
cfp.write('\n') cfp.write('\n')
message = cfp.getvalue() message = cfp.getvalue()
if tmpfp: if tmpfp:
tmpfp.write(payload) tmpfp.write(payload)
if not payload.endswith('\n'): if not payload.endswith('\n'):
tmpfp.write('\n') tmpfp.write('\n')
elif not diffs_seen and message and content_type == 'text/plain': elif not diffs_seen and message and content_type == 'text/plain':
message += '\n' + payload message += '\n' + payload
except: # re-raises
tmpfp.close()
os.unlink(tmpname)
raise
if subject and not message.startswith(subject): if subject and not message.startswith(subject):
message = '%s\n%s' % (subject, message) message = '%s\n%s' % (subject, message)
data['message'] = message data['message'] = message
tmpfp.close() tmpfp.close()
if parents: if parents:
data['p1'] = parents.pop(0) data['p1'] = parents.pop(0)
if parents: if parents:
data['p2'] = parents.pop(0) data['p2'] = parents.pop(0)
if diffs_seen: if diffs_seen:
data['filename'] = tmpname data['filename'] = tmpname
else:
os.unlink(tmpname)
return data return data
class patchmeta(object): class patchmeta(object):
"""Patched file metadata """Patched file metadata
'op' is the performed operation within ADD, DELETE, RENAME, MODIFY 'op' is the performed operation within ADD, DELETE, RENAME, MODIFY
or COPY. 'path' is patched file path. 'oldpath' is set to the or COPY. 'path' is patched file path. 'oldpath' is set to the
origin file when 'op' is either COPY or RENAME, None otherwise. If origin file when 'op' is either COPY or RENAME, None otherwise. If