|
1 """automatically manage newlines in repository files |
|
2 |
|
3 This extension allows you to manage the type of line endings (CRLF or |
|
4 LF) that are used in the repository and in the local working |
|
5 directory. That way you can get CRLF line endings on Windows and LF on |
|
6 Unix/Mac, thereby letting everybody use their OS native line endings. |
|
7 |
|
8 The extension reads its configuration from a versioned ``.hgeol`` |
|
9 configuration file every time you run an ``hg`` command. The |
|
10 ``.hgeol`` file use the same syntax as all other Mercurial |
|
11 configuration files. It uses two sections, ``[patterns]`` and |
|
12 ``[repository]``. |
|
13 |
|
14 The ``[patterns]`` section specifies the line endings used in the |
|
15 working directory. The format is specified by a file pattern. The |
|
16 first match is used, so put more specific patterns first. The |
|
17 available line endings are ``LF``, ``CRLF``, and ``BIN``. |
|
18 |
|
19 Files with the declared format of ``CRLF`` or ``LF`` are always |
|
20 checked out in that format and files declared to be binary (``BIN``) |
|
21 are left unchanged. Additionally, ``native`` is an alias for the |
|
22 platform's default line ending: ``LF`` on Unix (including Mac OS X) |
|
23 and ``CRLF`` on Windows. Note that ``BIN`` (do nothing to line |
|
24 endings) is Mercurial's default behaviour; it is only needed if you |
|
25 need to override a later, more general pattern. |
|
26 |
|
27 The optional ``[repository]`` section specifies the line endings to |
|
28 use for files stored in the repository. It has a single setting, |
|
29 ``native``, which determines the storage line endings for files |
|
30 declared as ``native`` in the ``[patterns]`` section. It can be set to |
|
31 ``LF`` or ``CRLF``. The default is ``LF``. For example, this means |
|
32 that on Windows, files configured as ``native`` (``CRLF`` by default) |
|
33 will be converted to ``LF`` when stored in the repository. Files |
|
34 declared as ``LF``, ``CRLF``, or ``BIN`` in the ``[patterns]`` section |
|
35 are always stored as-is in the repository. |
|
36 |
|
37 Example versioned ``.hgeol`` file:: |
|
38 |
|
39 [patterns] |
|
40 **.py = native |
|
41 **.vcproj = CRLF |
|
42 **.txt = native |
|
43 Makefile = LF |
|
44 **.jpg = BIN |
|
45 |
|
46 [repository] |
|
47 native = LF |
|
48 |
|
49 The extension uses an optional ``[eol]`` section in your hgrc file |
|
50 (not the ``.hgeol`` file) for settings that control the overall |
|
51 behavior. There are two settings: |
|
52 |
|
53 - ``eol.native`` (default ``os.linesep``) can be set to ``LF`` or |
|
54 ``CRLF`` override the default interpretation of ``native`` for |
|
55 checkout. This can be used with :hg:`archive` on Unix, say, to |
|
56 generate an archive where files have line endings for Windows. |
|
57 |
|
58 - ``eol.only-consistent`` (default True) can be set to False to make |
|
59 the extension convert files with inconsistent EOLs. Inconsistent |
|
60 means that there is both ``CRLF`` and ``LF`` present in the file. |
|
61 Such files are normally not touched under the assumption that they |
|
62 have mixed EOLs on purpose. |
|
63 |
|
64 See :hg:`help patterns` for more information about the glob patterns |
|
65 used. |
|
66 """ |
|
67 |
|
68 from mercurial.i18n import _ |
|
69 from mercurial import util, config, extensions, commands, match, cmdutil |
|
70 import re, os |
|
71 |
|
72 # Matches a lone LF, i.e., one that is not part of CRLF. |
|
73 singlelf = re.compile('(^|[^\r])\n') |
|
74 # Matches a single EOL which can either be a CRLF where repeated CR |
|
75 # are removed or a LF. We do not care about old Machintosh files, so a |
|
76 # stray CR is an error. |
|
77 eolre = re.compile('\r*\n') |
|
78 |
|
79 |
|
80 def inconsistenteol(data): |
|
81 return '\r\n' in data and singlelf.search(data) |
|
82 |
|
83 def tolf(s, params, ui, **kwargs): |
|
84 """Filter to convert to LF EOLs.""" |
|
85 if util.binary(s): |
|
86 return s |
|
87 if ui.configbool('eol', 'only-consistent', True) and inconsistenteol(s): |
|
88 return s |
|
89 return eolre.sub('\n', s) |
|
90 |
|
91 def tocrlf(s, params, ui, **kwargs): |
|
92 """Filter to convert to CRLF EOLs.""" |
|
93 if util.binary(s): |
|
94 return s |
|
95 if ui.configbool('eol', 'only-consistent', True) and inconsistenteol(s): |
|
96 return s |
|
97 return eolre.sub('\r\n', s) |
|
98 |
|
99 def isbinary(s, params): |
|
100 """Filter to do nothing with the file.""" |
|
101 return s |
|
102 |
|
103 filters = { |
|
104 'to-lf': tolf, |
|
105 'to-crlf': tocrlf, |
|
106 'is-binary': isbinary, |
|
107 } |
|
108 |
|
109 |
|
110 def hook(ui, repo, node, hooktype, **kwargs): |
|
111 """verify that files have expected EOLs""" |
|
112 files = set() |
|
113 for rev in xrange(repo[node].rev(), len(repo)): |
|
114 files.update(repo[rev].files()) |
|
115 tip = repo['tip'] |
|
116 for f in files: |
|
117 if f not in tip: |
|
118 continue |
|
119 for pattern, target in ui.configitems('encode'): |
|
120 if match.match(repo.root, '', [pattern])(f): |
|
121 data = tip[f].data() |
|
122 if target == "to-lf" and "\r\n" in data: |
|
123 raise util.Abort(_("%s should not have CRLF line endings") |
|
124 % f) |
|
125 elif target == "to-crlf" and singlelf.search(data): |
|
126 raise util.Abort(_("%s should not have LF line endings") |
|
127 % f) |
|
128 |
|
129 |
|
130 def preupdate(ui, repo, hooktype, parent1, parent2): |
|
131 #print "preupdate for %s: %s -> %s" % (repo.root, parent1, parent2) |
|
132 repo.readhgeol(parent1) |
|
133 return False |
|
134 |
|
135 def uisetup(ui): |
|
136 ui.setconfig('hooks', 'preupdate.eol', preupdate) |
|
137 |
|
138 def extsetup(ui): |
|
139 try: |
|
140 extensions.find('win32text') |
|
141 raise util.Abort(_("the eol extension is incompatible with the " |
|
142 "win32text extension")) |
|
143 except KeyError: |
|
144 pass |
|
145 |
|
146 |
|
147 def reposetup(ui, repo): |
|
148 #print "reposetup for", repo.root |
|
149 |
|
150 if not repo.local(): |
|
151 return |
|
152 for name, fn in filters.iteritems(): |
|
153 repo.adddatafilter(name, fn) |
|
154 |
|
155 ui.setconfig('patch', 'eol', 'auto') |
|
156 |
|
157 class eolrepo(repo.__class__): |
|
158 |
|
159 _decode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'} |
|
160 _encode = {'LF': 'to-lf', 'CRLF': 'to-crlf', 'BIN': 'is-binary'} |
|
161 |
|
162 def readhgeol(self, node=None, data=None): |
|
163 if data is None: |
|
164 try: |
|
165 if node is None: |
|
166 data = self.wfile('.hgeol').read() |
|
167 else: |
|
168 data = self[node]['.hgeol'].data() |
|
169 except (IOError, LookupError): |
|
170 return None |
|
171 |
|
172 if self.ui.config('eol', 'native', os.linesep) in ('LF', '\n'): |
|
173 self._decode['NATIVE'] = 'to-lf' |
|
174 else: |
|
175 self._decode['NATIVE'] = 'to-crlf' |
|
176 |
|
177 eol = config.config() |
|
178 eol.parse('.hgeol', data) |
|
179 |
|
180 if eol.get('repository', 'native') == 'CRLF': |
|
181 self._encode['NATIVE'] = 'to-crlf' |
|
182 else: |
|
183 self._encode['NATIVE'] = 'to-lf' |
|
184 |
|
185 for pattern, style in eol.items('patterns'): |
|
186 key = style.upper() |
|
187 try: |
|
188 self.ui.setconfig('decode', pattern, self._decode[key]) |
|
189 self.ui.setconfig('encode', pattern, self._encode[key]) |
|
190 except KeyError: |
|
191 self.ui.warn(_("ignoring unknown EOL style '%s' from %s\n") |
|
192 % (style, eol.source('patterns', pattern))) |
|
193 |
|
194 include = [] |
|
195 exclude = [] |
|
196 for pattern, style in eol.items('patterns'): |
|
197 key = style.upper() |
|
198 if key == 'BIN': |
|
199 exclude.append(pattern) |
|
200 else: |
|
201 include.append(pattern) |
|
202 |
|
203 # This will match the files for which we need to care |
|
204 # about inconsistent newlines. |
|
205 return match.match(self.root, '', [], include, exclude) |
|
206 |
|
207 def _hgcleardirstate(self): |
|
208 self._eolfile = self.readhgeol() or self.readhgeol('tip') |
|
209 |
|
210 if not self._eolfile: |
|
211 self._eolfile = util.never |
|
212 return |
|
213 |
|
214 try: |
|
215 cachemtime = os.path.getmtime(self.join("eol.cache")) |
|
216 except OSError: |
|
217 cachemtime = 0 |
|
218 |
|
219 try: |
|
220 eolmtime = os.path.getmtime(self.wjoin(".hgeol")) |
|
221 except OSError: |
|
222 eolmtime = 0 |
|
223 |
|
224 if eolmtime > cachemtime: |
|
225 ui.debug("eol: detected change in .hgeol\n") |
|
226 # TODO: we could introduce a method for this in dirstate. |
|
227 wlock = None |
|
228 try: |
|
229 wlock = self.wlock() |
|
230 for f, e in self.dirstate._map.iteritems(): |
|
231 self.dirstate._map[f] = (e[0], e[1], -1, 0) |
|
232 self.dirstate._dirty = True |
|
233 # Touch the cache to update mtime. TODO: are we sure this |
|
234 # always enought to update the mtime, or should we write a |
|
235 # bit to the file? |
|
236 self.opener("eol.cache", "w").close() |
|
237 finally: |
|
238 if wlock is not None: |
|
239 wlock.release() |
|
240 |
|
241 def commitctx(self, ctx, error=False): |
|
242 for f in sorted(ctx.added() + ctx.modified()): |
|
243 if not self._eolfile(f): |
|
244 continue |
|
245 data = ctx[f].data() |
|
246 if util.binary(data): |
|
247 # We should not abort here, since the user should |
|
248 # be able to say "** = native" to automatically |
|
249 # have all non-binary files taken care of. |
|
250 continue |
|
251 if inconsistenteol(data): |
|
252 raise util.Abort(_("inconsistent newline style " |
|
253 "in %s\n" % f)) |
|
254 return super(eolrepo, self).commitctx(ctx, error) |
|
255 repo.__class__ = eolrepo |
|
256 repo._hgcleardirstate() |