match: add a subclass for dirstate normalizing of the matched patterns
This class is only needed on case insensitive filesystems, and only
for wdir context matches. It allows the user to not match the case of
the items in the filesystem- especially for naming directories, which
dirstate doesn't handle[1]. Making dirstate handle mismatched
directory cases is too expensive[2].
Since dirstate doesn't apply to committed csets, this is only created by
overriding basectx.match() in workingctx, and only on icasefs. The default
arguments have been dropped, because the ctx must be passed to the matcher in
order to function.
For operations that can apply to both wdir and some other context, this ends up
normalizing the filename to the case as it exists in the filesystem, and using
that case for the lookup in the other context. See the diff example in the
test.
Previously, given a directory with an inexact case:
- add worked as expected
- diff, forget and status would silently ignore the request
- files would exit with 1
- commit, revert and remove would fail (even when the commands leading up to
them worked):
$ hg ci -m "AbCDef" capsdir1/capsdir
abort: CapsDir1/CapsDir: no match under directory!
$ hg revert -r '.^' capsdir1/capsdir
capsdir1\capsdir: no such file in rev
64dae27060b7
$ hg remove capsdir1/capsdir
not removing capsdir1\capsdir: no tracked files
[1]
Globs are normalized, so that the -I and -X don't need to be specified with a
case match. Without that, the second last remove (with -X) removes the files,
leaving nothing for the last remove. However, specifying the files as
'glob:**.Txt' does not work. Perhaps this requires 're.IGNORECASE'?
There are only a handful of places that create matchers directly, instead of
being routed through the context.match() method. Some may benefit from changing
over to using ctx.match() as a factory function:
revset.checkstatus()
revset.contains()
revset.filelog()
revset._matchfiles()
localrepository._loadfilter()
ignore.ignore()
fileset.subrepo()
filemerge._picktool()
overrides.addlargefiles()
lfcommands.lfconvert()
kwtemplate.__init__()
eolfile.__init__()
eolfile.checkrev()
acl.buildmatch()
Currently, a toplevel subrepo can be named with an inexact case. However, the
path auditor gets in the way of naming _anything_ in the subrepo if the top
level case doesn't match. That is trickier to handle, because there's the user
provided case, the case in the filesystem, and the case stored in .hgsub. This
can be fixed next cycle.
--- a/tests/test-subrepo-deep-nested-change.t
+++ b/tests/test-subrepo-deep-nested-change.t
@@ -170,8 +170,15 @@
R sub1/sub2/test.txt
$ hg update -Cq
$ touch sub1/sub2/folder/bar
+#if icasefs
+ $ hg addremove Sub1/sub2
+ abort: path 'Sub1\sub2' is inside nested repo 'Sub1'
+ [255]
+ $ hg -q addremove sub1/sub2
+#else
$ hg addremove sub1/sub2
adding sub1/sub2/folder/bar (glob)
+#endif
$ hg status -S
A sub1/sub2/folder/bar
? foo/bar/abc
The narrowmatcher class may need to be tweaked when that is fixed.
[1] http://www.selenic.com/pipermail/mercurial-devel/2015-April/068183.html
[2] http://www.selenic.com/pipermail/mercurial-devel/2015-April/068191.html
# config.py - configuration parsing for Mercurial
#
# Copyright 2009 Matt Mackall <mpm@selenic.com> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from i18n import _
import error, util
import os, errno
class config(object):
def __init__(self, data=None):
self._data = {}
self._source = {}
self._unset = []
if data:
for k in data._data:
self._data[k] = data[k].copy()
self._source = data._source.copy()
def copy(self):
return config(self)
def __contains__(self, section):
return section in self._data
def __getitem__(self, section):
return self._data.get(section, {})
def __iter__(self):
for d in self.sections():
yield d
def update(self, src):
for s, n in src._unset:
if s in self and n in self._data[s]:
del self._data[s][n]
del self._source[(s, n)]
for s in src:
if s not in self:
self._data[s] = util.sortdict()
self._data[s].update(src._data[s])
self._source.update(src._source)
def get(self, section, item, default=None):
return self._data.get(section, {}).get(item, default)
def backup(self, section, item):
"""return a tuple allowing restore to reinstall a previous value
The main reason we need it is because it handles the "no data" case.
"""
try:
value = self._data[section][item]
source = self.source(section, item)
return (section, item, value, source)
except KeyError:
return (section, item)
def source(self, section, item):
return self._source.get((section, item), "")
def sections(self):
return sorted(self._data.keys())
def items(self, section):
return self._data.get(section, {}).items()
def set(self, section, item, value, source=""):
if section not in self:
self._data[section] = util.sortdict()
self._data[section][item] = value
if source:
self._source[(section, item)] = source
def restore(self, data):
"""restore data returned by self.backup"""
if len(data) == 4:
# restore old data
section, item, value, source = data
self._data[section][item] = value
self._source[(section, item)] = source
else:
# no data before, remove everything
section, item = data
if section in self._data:
self._data[section].pop(item, None)
self._source.pop((section, item), None)
def parse(self, src, data, sections=None, remap=None, include=None):
sectionre = util.re.compile(r'\[([^\[]+)\]')
itemre = util.re.compile(r'([^=\s][^=]*?)\s*=\s*(.*\S|)')
contre = util.re.compile(r'\s+(\S|\S.*\S)\s*$')
emptyre = util.re.compile(r'(;|#|\s*$)')
commentre = util.re.compile(r'(;|#)')
unsetre = util.re.compile(r'%unset\s+(\S+)')
includere = util.re.compile(r'%include\s+(\S|\S.*\S)\s*$')
section = ""
item = None
line = 0
cont = False
for l in data.splitlines(True):
line += 1
if line == 1 and l.startswith('\xef\xbb\xbf'):
# Someone set us up the BOM
l = l[3:]
if cont:
if commentre.match(l):
continue
m = contre.match(l)
if m:
if sections and section not in sections:
continue
v = self.get(section, item) + "\n" + m.group(1)
self.set(section, item, v, "%s:%d" % (src, line))
continue
item = None
cont = False
m = includere.match(l)
if m:
inc = util.expandpath(m.group(1))
base = os.path.dirname(src)
inc = os.path.normpath(os.path.join(base, inc))
if include:
try:
include(inc, remap=remap, sections=sections)
except IOError, inst:
if inst.errno != errno.ENOENT:
raise error.ParseError(_("cannot include %s (%s)")
% (inc, inst.strerror),
"%s:%s" % (src, line))
continue
if emptyre.match(l):
continue
m = sectionre.match(l)
if m:
section = m.group(1)
if remap:
section = remap.get(section, section)
if section not in self:
self._data[section] = util.sortdict()
continue
m = itemre.match(l)
if m:
item = m.group(1)
cont = True
if sections and section not in sections:
continue
self.set(section, item, m.group(2), "%s:%d" % (src, line))
continue
m = unsetre.match(l)
if m:
name = m.group(1)
if sections and section not in sections:
continue
if self.get(section, name) is not None:
del self._data[section][name]
self._unset.append((section, name))
continue
raise error.ParseError(l.rstrip(), ("%s:%s" % (src, line)))
def read(self, path, fp=None, sections=None, remap=None):
if not fp:
fp = util.posixfile(path)
self.parse(path, fp.read(), sections, remap, self.read)