This is an archive of the discontinued Mercurial Phabricator instance.

Differential D10449

parselist: move the function from config to stringutil
ClosedPublic

Authored by marmoute on Apr 15 2021, 8:55 PM.

Details

Reviewers
Alphare
pulkit
Group Reviewers
hg-reviewers
Commits
rHGb0e92313107e: parselist: move the function from config to stringutil
Summary

We move the function in a lower level module to avoid cycle. It moves next to
parsebool who had to migrate for the same reasons.

Diff Detail

Repository
rHG Mercurial
Branch
default
Lint
No Linters Available
Unit
No Unit Test Coverage

Event Timeline

marmoute created this revision.Apr 15 2021, 8:55 PM
baymax updated this revision to Diff 27018.Apr 17 2021, 7:45 PM

✅ refresh by Heptapod after a successful CI run (🐙 💚)

Alphare accepted this revision.Apr 29 2021, 9:17 AM
This revision is now accepted and ready to land.Apr 29 2021, 9:17 AM
baymax updated this revision to Diff 27209.Apr 29 2021, 1:47 PM

✅ refresh by Heptapod after a successful CI run (🐙 💚)

baymax updated this revision to Diff 27237.Apr 30 2021, 8:25 AM

✅ refresh by Heptapod after a successful CI run (🐙 💚)

baymax updated this revision to Diff 27421.May 3 2021, 9:53 AM

✅ refresh by Heptapod after a successful CI run (🐙 💚)

pulkit accepted this revision.May 15 2021, 3:16 PM
marmoute added a commit: rHGb0e92313107e: parselist: move the function from config to stringutil.May 15 2021, 7:22 PM
Closed by commit rHGb0e92313107e: parselist: move the function from config to stringutil (authored by marmoute). · Explain Why
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

Diff 27237

mercurial/config.py

abs = os.path.normpath(os.path.join(dir, rel)) abs = os.path.normpath(os.path.join(dir, rel))
self.read(abs, remap=remap, sections=sections) self.read(abs, remap=remap, sections=sections)
# anything after the include has a higher level # anything after the include has a higher level
self.new_source() self.new_source()
self.parse( self.parse(
path, fp.read(), sections=sections, remap=remap, include=include path, fp.read(), sections=sections, remap=remap, include=include
) )
def parselist(value):
"""parse a configuration value as a list of comma/space separated strings
>>> parselist(b'this,is "a small" ,test')
['this', 'is', 'a small', 'test']
"""
def _parse_plain(parts, s, offset):
whitespace = False
while offset < len(s) and (
s[offset : offset + 1].isspace() or s[offset : offset + 1] == b','
):
whitespace = True
offset += 1
if offset >= len(s):
return None, parts, offset
if whitespace:
parts.append(b'')
if s[offset : offset + 1] == b'"' and not parts[-1]:
return _parse_quote, parts, offset + 1
elif s[offset : offset + 1] == b'"' and parts[-1][-1:] == b'\\':
parts[-1] = parts[-1][:-1] + s[offset : offset + 1]
return _parse_plain, parts, offset + 1
parts[-1] += s[offset : offset + 1]
return _parse_plain, parts, offset + 1
def _parse_quote(parts, s, offset):
if offset < len(s) and s[offset : offset + 1] == b'"': # ""
parts.append(b'')
offset += 1
while offset < len(s) and (
s[offset : offset + 1].isspace()
or s[offset : offset + 1] == b','
):
offset += 1
return _parse_plain, parts, offset
while offset < len(s) and s[offset : offset + 1] != b'"':
if (
s[offset : offset + 1] == b'\\'
and offset + 1 < len(s)
and s[offset + 1 : offset + 2] == b'"'
):
offset += 1
parts[-1] += b'"'
else:
parts[-1] += s[offset : offset + 1]
offset += 1
if offset >= len(s):
real_parts = _configlist(parts[-1])
if not real_parts:
parts[-1] = b'"'
else:
real_parts[0] = b'"' + real_parts[0]
parts = parts[:-1]
parts.extend(real_parts)
return None, parts, offset
offset += 1
while offset < len(s) and s[offset : offset + 1] in [b' ', b',']:
offset += 1
if offset < len(s):
if offset + 1 == len(s) and s[offset : offset + 1] == b'"':
parts[-1] += b'"'
offset += 1
else:
parts.append(b'')
else:
return None, parts, offset
return _parse_plain, parts, offset
def _configlist(s):
s = s.rstrip(b' ,')
if not s:
return []
parser, parts, offset = _parse_plain, [b''], 0
while parser:
parser, parts, offset = parser(parts, s, offset)
return parts
if value is not None and isinstance(value, bytes):
result = _configlist(value.lstrip(b' ,\n'))
else:
result = value
return result or []

mercurial/ui.py

>>> u.configlist(s, b'list1') >>> u.configlist(s, b'list1')
['this', 'is', 'a small', 'test'] ['this', 'is', 'a small', 'test']
>>> u.setconfig(s, b'list2', b'this, is "a small" , test ') >>> u.setconfig(s, b'list2', b'this, is "a small" , test ')
>>> u.configlist(s, b'list2') >>> u.configlist(s, b'list2')
['this', 'is', 'a small', 'test'] ['this', 'is', 'a small', 'test']
""" """
# default is not always a list # default is not always a list
v = self.configwith( v = self.configwith(
config.parselist, section, name, default, b'list', untrusted stringutil.parselist, section, name, default, b'list', untrusted
) )
if isinstance(v, bytes): if isinstance(v, bytes):
return config.parselist(v) return stringutil.parselist(v)
elif v is None: elif v is None:
return [] return []
return v return v
def configdate(self, section, name, default=_unset, untrusted=False): def configdate(self, section, name, default=_unset, untrusted=False):
"""parse a configuration element as a tuple of ints """parse a configuration element as a tuple of ints
>>> u = ui(); s = b'foo' >>> u = ui(); s = b'foo'

mercurial/utils/stringutil.py

def parsebool(s): def parsebool(s):
"""Parse s into a boolean. """Parse s into a boolean.
If s is not a valid boolean, returns None. If s is not a valid boolean, returns None.
""" """
return _booleans.get(s.lower(), None) return _booleans.get(s.lower(), None)
def parselist(value):
"""parse a configuration value as a list of comma/space separated strings
>>> parselist(b'this,is "a small" ,test')
['this', 'is', 'a small', 'test']
"""
def _parse_plain(parts, s, offset):
whitespace = False
while offset < len(s) and (
s[offset : offset + 1].isspace() or s[offset : offset + 1] == b','
):
whitespace = True
offset += 1
if offset >= len(s):
return None, parts, offset
if whitespace:
parts.append(b'')
if s[offset : offset + 1] == b'"' and not parts[-1]:
return _parse_quote, parts, offset + 1
elif s[offset : offset + 1] == b'"' and parts[-1][-1:] == b'\\':
parts[-1] = parts[-1][:-1] + s[offset : offset + 1]
return _parse_plain, parts, offset + 1
parts[-1] += s[offset : offset + 1]
return _parse_plain, parts, offset + 1
def _parse_quote(parts, s, offset):
if offset < len(s) and s[offset : offset + 1] == b'"': # ""
parts.append(b'')
offset += 1
while offset < len(s) and (
s[offset : offset + 1].isspace()
or s[offset : offset + 1] == b','
):
offset += 1
return _parse_plain, parts, offset
while offset < len(s) and s[offset : offset + 1] != b'"':
if (
s[offset : offset + 1] == b'\\'
and offset + 1 < len(s)
and s[offset + 1 : offset + 2] == b'"'
):
offset += 1
parts[-1] += b'"'
else:
parts[-1] += s[offset : offset + 1]
offset += 1
if offset >= len(s):
real_parts = _configlist(parts[-1])
if not real_parts:
parts[-1] = b'"'
else:
real_parts[0] = b'"' + real_parts[0]
parts = parts[:-1]
parts.extend(real_parts)
return None, parts, offset
offset += 1
while offset < len(s) and s[offset : offset + 1] in [b' ', b',']:
offset += 1
if offset < len(s):
if offset + 1 == len(s) and s[offset : offset + 1] == b'"':
parts[-1] += b'"'
offset += 1
else:
parts.append(b'')
else:
return None, parts, offset
return _parse_plain, parts, offset
def _configlist(s):
s = s.rstrip(b' ,')
if not s:
return []
parser, parts, offset = _parse_plain, [b''], 0
while parser:
parser, parts, offset = parser(parts, s, offset)
return parts
if value is not None and isinstance(value, bytes):
result = _configlist(value.lstrip(b' ,\n'))
else:
result = value
return result or []
def evalpythonliteral(s): def evalpythonliteral(s):
"""Evaluate a string containing a Python literal expression""" """Evaluate a string containing a Python literal expression"""
# We could backport our tokenizer hack to rewrite '' to u'' if we want # We could backport our tokenizer hack to rewrite '' to u'' if we want
if pycompat.ispy3: if pycompat.ispy3:
return ast.literal_eval(s.decode('latin1')) return ast.literal_eval(s.decode('latin1'))
return ast.literal_eval(s) return ast.literal_eval(s)

rust/hg-core/src/config/config.rs

) -> Result<bool, ConfigValueParseError> { ) -> Result<bool, ConfigValueParseError> {
Ok(self.get_option(section, item)?.unwrap_or(false)) Ok(self.get_option(section, item)?.unwrap_or(false))
} }
/// Returns the corresponding list-value in the config if found, or `None`. /// Returns the corresponding list-value in the config if found, or `None`.
/// ///
/// This is appropriate for new configuration keys. The value syntax is /// This is appropriate for new configuration keys. The value syntax is
/// **not** the same as most existing list-valued config, which has Python /// **not** the same as most existing list-valued config, which has Python
/// parsing implemented in `parselist()` in `mercurial/config.py`. /// parsing implemented in `parselist()` in
/// Faithfully porting that parsing algorithm to Rust (including behavior /// `mercurial/utils/stringutil.py`. Faithfully porting that parsing
/// that are arguably bugs) turned out to be non-trivial and hasn’t been /// algorithm to Rust (including behavior that are arguably bugs)
/// completed as of this writing. /// turned out to be non-trivial and hasn’t been completed as of this
/// writing.
/// ///
/// Instead, the "simple" syntax is: split on comma, then trim leading and /// Instead, the "simple" syntax is: split on comma, then trim leading and
/// trailing whitespace of each component. Quotes or backslashes are not /// trailing whitespace of each component. Quotes or backslashes are not
/// interpreted in any way. Commas are mandatory between values. Values /// interpreted in any way. Commas are mandatory between values. Values
/// that contain a comma are not supported. /// that contain a comma are not supported.
pub fn get_simple_list( pub fn get_simple_list(
&self, &self,
section: &[u8], section: &[u8],

tests/test-doctest.py

('hgext.convert.filemap', '{}'), ('hgext.convert.filemap', '{}'),
('hgext.convert.p4', '{}'), ('hgext.convert.p4', '{}'),
('hgext.convert.subversion', '{}'), ('hgext.convert.subversion', '{}'),
('hgext.fix', '{}'), ('hgext.fix', '{}'),
('hgext.mq', '{}'), ('hgext.mq', '{}'),
('mercurial.changelog', '{}'), ('mercurial.changelog', '{}'),
('mercurial.cmdutil', '{}'), ('mercurial.cmdutil', '{}'),
('mercurial.color', '{}'), ('mercurial.color', '{}'),
('mercurial.config', '{}'),
('mercurial.dagparser', "{'optionflags': 4}"), ('mercurial.dagparser', "{'optionflags': 4}"),
('mercurial.encoding', '{}'), ('mercurial.encoding', '{}'),
('mercurial.fancyopts', '{}'), ('mercurial.fancyopts', '{}'),
('mercurial.formatter', '{}'), ('mercurial.formatter', '{}'),
('mercurial.hg', '{}'), ('mercurial.hg', '{}'),
('mercurial.hgweb.hgwebdir_mod', '{}'), ('mercurial.hgweb.hgwebdir_mod', '{}'),
('mercurial.match', '{}'), ('mercurial.match', '{}'),
('mercurial.mdiff', '{}'), ('mercurial.mdiff', '{}'),