This is an archive of the discontinued Mercurial Phabricator instance.

Differential D6184

changelog: extract a _string_unescape() to mirror _string_escape()
ClosedPublic

Authored by martinvonz on Apr 2 2019, 3:30 PM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHGcaa067ee21dc: changelog: extract a _string_unescape() to mirror _string_escape()
Summary

We use our own _string_escape() to encode the "extras" field. Then we
use codecs.escape_decode() to escape it. But there's also a little
workaround for dealing with escaped text that looks like octal numbers
since the fix for
https://bz.mercurial-scm.org/show_bug.cgi?id=3156. This patch extracts
the call to codecs.escape_decode() along with the fix for octal
numbers and puts it in a _string_unescape(). It also updates the test
to check for the octal-number case from the aforementioned bug.

As you may have suspected, I want to be able to reuse this new
function later.

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.

Revision Contents
Changeset List

PathPackages
Mmercurial/changelog.py (21 lines)

Diff 14731

mercurial/changelog.py

) )
_defaultextra = {'branch': 'default'} _defaultextra = {'branch': 'default'}
def _string_escape(text): def _string_escape(text):
""" """
>>> from .pycompat import bytechr as chr >>> from .pycompat import bytechr as chr
>>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)} >>> d = {b'nl': chr(10), b'bs': chr(92), b'cr': chr(13), b'nul': chr(0)}
>>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)sab%(cr)scd%(bs)s%(nl)s" % d >>> s = b"ab%(nl)scd%(bs)s%(bs)sn%(nul)s12ab%(cr)scd%(bs)s%(nl)s" % d
>>> s >>> s
'ab\\ncd\\\\\\\\n\\x00ab\\rcd\\\\\\n' 'ab\\ncd\\\\\\\\n\\x0012ab\\rcd\\\\\\n'
>>> res = _string_escape(s) >>> res = _string_escape(s)
>>> s == stringutil.unescapestr(res) >>> s == _string_unescape(res)
True True
""" """
# subset of the string_escape codec # subset of the string_escape codec
text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r') text = text.replace('\\', '\\\\').replace('\n', '\\n').replace('\r', '\\r')
return text.replace('\0', '\\0') return text.replace('\0', '\\0')
def _string_unescape(text):
if '\\0' in text:
# fix up \0 without getting into trouble with \\0
text = text.replace('\\\\', '\\\\\n')
text = text.replace('\\0', '\0')
text = text.replace('\n', '')
return stringutil.unescapestr(text)
def decodeextra(text): def decodeextra(text):
""" """
>>> from .pycompat import bytechr as chr >>> from .pycompat import bytechr as chr
>>> sorted(decodeextra(encodeextra({b'foo': b'bar', b'baz': chr(0) + b'2'}) >>> sorted(decodeextra(encodeextra({b'foo': b'bar', b'baz': chr(0) + b'2'})
... ).items()) ... ).items())
[('baz', '\\x002'), ('branch', 'default'), ('foo', 'bar')] [('baz', '\\x002'), ('branch', 'default'), ('foo', 'bar')]
>>> sorted(decodeextra(encodeextra({b'foo': b'bar', >>> sorted(decodeextra(encodeextra({b'foo': b'bar',
... b'baz': chr(92) + chr(0) + b'2'}) ... b'baz': chr(92) + chr(0) + b'2'})
... ).items()) ... ).items())
[('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')] [('baz', '\\\\\\x002'), ('branch', 'default'), ('foo', 'bar')]
""" """
extra = _defaultextra.copy() extra = _defaultextra.copy()
for l in text.split('\0'): for l in text.split('\0'):
if l: if l:
if '\\0' in l: k, v = _string_unescape(l).split(':', 1)
# fix up \0 without getting into trouble with \\0
l = l.replace('\\\\', '\\\\\n')
l = l.replace('\\0', '\0')
l = l.replace('\n', '')
k, v = stringutil.unescapestr(l).split(':', 1)
extra[k] = v extra[k] = v
return extra return extra
def encodeextra(d): def encodeextra(d):
# keys must be sorted to produce a deterministic changelog entry # keys must be sorted to produce a deterministic changelog entry
items = [ items = [
_string_escape('%s:%s' % (k, pycompat.bytestr(d[k]))) _string_escape('%s:%s' % (k, pycompat.bytestr(d[k])))
for k in sorted(d) for k in sorted(d)