/usr/share/pyshared/mercurial/mdiff.py is in mercurial-common 2.0.2-1ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | # mdiff.py - diff and patch routines for mercurial
#
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
#
# 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 bdiff, mpatch, util
import re, struct
def splitnewlines(text):
'''like str.splitlines, but only split on newlines.'''
lines = [l + '\n' for l in text.split('\n')]
if lines:
if lines[-1] == '\n':
lines.pop()
else:
lines[-1] = lines[-1][:-1]
return lines
class diffopts(object):
'''context is the number of context lines
text treats all files as text
showfunc enables diff -p output
git enables the git extended patch format
nodates removes dates from diff headers
ignorews ignores all whitespace changes in the diff
ignorewsamount ignores changes in the amount of whitespace
ignoreblanklines ignores changes whose lines are all blank
upgrade generates git diffs to avoid data loss
'''
defaults = {
'context': 3,
'text': False,
'showfunc': False,
'git': False,
'nodates': False,
'ignorews': False,
'ignorewsamount': False,
'ignoreblanklines': False,
'upgrade': False,
}
__slots__ = defaults.keys()
def __init__(self, **opts):
for k in self.__slots__:
v = opts.get(k)
if v is None:
v = self.defaults[k]
setattr(self, k, v)
try:
self.context = int(self.context)
except ValueError:
raise util.Abort(_('diff context lines count must be '
'an integer, not %r') % self.context)
def copy(self, **kwargs):
opts = dict((k, getattr(self, k)) for k in self.defaults)
opts.update(kwargs)
return diffopts(**opts)
defaultopts = diffopts()
def wsclean(opts, text, blank=True):
if opts.ignorews:
text = re.sub('[ \t\r]+', '', text)
elif opts.ignorewsamount:
text = re.sub('[ \t\r]+', ' ', text)
text = text.replace(' \n', '\n')
if blank and opts.ignoreblanklines:
text = re.sub('\n+', '\n', text).strip('\n')
return text
def diffline(revs, a, b, opts):
parts = ['diff']
if opts.git:
parts.append('--git')
if revs and not opts.git:
parts.append(' '.join(["-r %s" % rev for rev in revs]))
if opts.git:
parts.append('a/%s' % a)
parts.append('b/%s' % b)
else:
parts.append(a)
return ' '.join(parts) + '\n'
def unidiff(a, ad, b, bd, fn1, fn2, r=None, opts=defaultopts):
def datetag(date, addtab=True):
if not opts.git and not opts.nodates:
return '\t%s\n' % date
if addtab and ' ' in fn1:
return '\t\n'
return '\n'
if not a and not b:
return ""
epoch = util.datestr((0, 0))
if not opts.text and (util.binary(a) or util.binary(b)):
if a and b and len(a) == len(b) and a == b:
return ""
l = ['Binary file %s has changed\n' % fn1]
elif not a:
b = splitnewlines(b)
if a is None:
l1 = '--- /dev/null%s' % datetag(epoch, False)
else:
l1 = "--- %s%s" % ("a/" + fn1, datetag(ad))
l2 = "+++ %s%s" % ("b/" + fn2, datetag(bd))
l3 = "@@ -0,0 +1,%d @@\n" % len(b)
l = [l1, l2, l3] + ["+" + e for e in b]
elif not b:
a = splitnewlines(a)
l1 = "--- %s%s" % ("a/" + fn1, datetag(ad))
if b is None:
l2 = '+++ /dev/null%s' % datetag(epoch, False)
else:
l2 = "+++ %s%s" % ("b/" + fn2, datetag(bd))
l3 = "@@ -1,%d +0,0 @@\n" % len(a)
l = [l1, l2, l3] + ["-" + e for e in a]
else:
al = splitnewlines(a)
bl = splitnewlines(b)
l = list(_unidiff(a, b, al, bl, opts=opts))
if not l:
return ""
l.insert(0, "--- a/%s%s" % (fn1, datetag(ad)))
l.insert(1, "+++ b/%s%s" % (fn2, datetag(bd)))
for ln in xrange(len(l)):
if l[ln][-1] != '\n':
l[ln] += "\n\ No newline at end of file\n"
if r:
l.insert(0, diffline(r, fn1, fn2, opts))
return "".join(l)
# creates a headerless unified diff
# t1 and t2 are the text to be diffed
# l1 and l2 are the text broken up into lines
def _unidiff(t1, t2, l1, l2, opts=defaultopts):
def contextend(l, len):
ret = l + opts.context
if ret > len:
ret = len
return ret
def contextstart(l):
ret = l - opts.context
if ret < 0:
return 0
return ret
lastfunc = [0, '']
def yieldhunk(hunk):
(astart, a2, bstart, b2, delta) = hunk
aend = contextend(a2, len(l1))
alen = aend - astart
blen = b2 - bstart + aend - a2
func = ""
if opts.showfunc:
lastpos, func = lastfunc
# walk backwards from the start of the context up to the start of
# the previous hunk context until we find a line starting with an
# alphanumeric char.
for i in xrange(astart - 1, lastpos - 1, -1):
if l1[i][0].isalnum():
func = ' ' + l1[i].rstrip()[:40]
lastfunc[1] = func
break
# by recording this hunk's starting point as the next place to
# start looking for function lines, we avoid reading any line in
# the file more than once.
lastfunc[0] = astart
# zero-length hunk ranges report their start line as one less
if alen:
astart += 1
if blen:
bstart += 1
yield "@@ -%d,%d +%d,%d @@%s\n" % (astart, alen,
bstart, blen, func)
for x in delta:
yield x
for x in xrange(a2, aend):
yield ' ' + l1[x]
# bdiff.blocks gives us the matching sequences in the files. The loop
# below finds the spaces between those matching sequences and translates
# them into diff output.
#
if opts.ignorews or opts.ignorewsamount:
t1 = wsclean(opts, t1, False)
t2 = wsclean(opts, t2, False)
diff = bdiff.blocks(t1, t2)
hunk = None
for i, s1 in enumerate(diff):
# The first match is special.
# we've either found a match starting at line 0 or a match later
# in the file. If it starts later, old and new below will both be
# empty and we'll continue to the next match.
if i > 0:
s = diff[i - 1]
else:
s = [0, 0, 0, 0]
delta = []
a1 = s[1]
a2 = s1[0]
b1 = s[3]
b2 = s1[2]
old = l1[a1:a2]
new = l2[b1:b2]
# bdiff sometimes gives huge matches past eof, this check eats them,
# and deals with the special first match case described above
if not old and not new:
continue
if opts.ignoreblanklines:
if wsclean(opts, "".join(old)) == wsclean(opts, "".join(new)):
continue
astart = contextstart(a1)
bstart = contextstart(b1)
prev = None
if hunk:
# join with the previous hunk if it falls inside the context
if astart < hunk[1] + opts.context + 1:
prev = hunk
astart = hunk[1]
bstart = hunk[3]
else:
for x in yieldhunk(hunk):
yield x
if prev:
# we've joined the previous hunk, record the new ending points.
hunk[1] = a2
hunk[3] = b2
delta = hunk[4]
else:
# create a new hunk
hunk = [astart, a2, bstart, b2, delta]
delta[len(delta):] = [' ' + x for x in l1[astart:a1]]
delta[len(delta):] = ['-' + x for x in old]
delta[len(delta):] = ['+' + x for x in new]
if hunk:
for x in yieldhunk(hunk):
yield x
def patchtext(bin):
pos = 0
t = []
while pos < len(bin):
p1, p2, l = struct.unpack(">lll", bin[pos:pos + 12])
pos += 12
t.append(bin[pos:pos + l])
pos += l
return "".join(t)
def patch(a, bin):
if len(a) == 0:
# skip over trivial delta header
return buffer(bin, 12)
return mpatch.patches(a, [bin])
# similar to difflib.SequenceMatcher.get_matching_blocks
def get_matching_blocks(a, b):
return [(d[0], d[2], d[1] - d[0]) for d in bdiff.blocks(a, b)]
def trivialdiffheader(length):
return struct.pack(">lll", 0, 0, length)
patches = mpatch.patches
patchedsize = mpatch.patchedsize
textdiff = bdiff.bdiff
|