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
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
|
# Copyright (C) 2004 - 2006 Aaron Bentley, Canonical Ltd
# <aaron.bentley@utoronto.ca>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
import re
class PatchSyntax(Exception):
def __init__(self, msg):
Exception.__init__(self, msg)
class MalformedPatchHeader(PatchSyntax):
def __init__(self, desc, line):
self.desc = desc
self.line = line
msg = "Malformed patch header. %s\n%r" % (self.desc, self.line)
PatchSyntax.__init__(self, msg)
class MalformedHunkHeader(PatchSyntax):
def __init__(self, desc, line):
self.desc = desc
self.line = line
msg = "Malformed hunk header. %s\n%r" % (self.desc, self.line)
PatchSyntax.__init__(self, msg)
class MalformedLine(PatchSyntax):
def __init__(self, desc, line):
self.desc = desc
self.line = line
msg = "Malformed line. %s\n%s" % (self.desc, self.line)
PatchSyntax.__init__(self, msg)
class PatchConflict(Exception):
def __init__(self, line_no, orig_line, patch_line):
orig = orig_line.rstrip('\n')
patch = str(patch_line).rstrip('\n')
msg = 'Text contents mismatch at line %d. Original has "%s",'\
' but patch says it should be "%s"' % (line_no, orig, patch)
Exception.__init__(self, msg)
def get_patch_names(iter_lines):
try:
line = iter_lines.next()
if not line.startswith("--- "):
raise MalformedPatchHeader("No orig name", line)
else:
orig_name = line[4:].rstrip("\n")
except StopIteration:
raise MalformedPatchHeader("No orig line", "")
try:
line = iter_lines.next()
if not line.startswith("+++ "):
raise PatchSyntax("No mod name")
else:
mod_name = line[4:].rstrip("\n")
except StopIteration:
raise MalformedPatchHeader("No mod line", "")
return (orig_name, mod_name)
def parse_range(textrange):
"""Parse a patch range, handling the "1" special-case
:param textrange: The text to parse
:type textrange: str
:return: the position and range, as a tuple
:rtype: (int, int)
"""
tmp = textrange.split(',')
if len(tmp) == 1:
pos = tmp[0]
range = "1"
else:
(pos, range) = tmp
pos = int(pos)
range = int(range)
return (pos, range)
def hunk_from_header(line):
matches = re.match(r'\@\@ ([^@]*) \@\@( (.*))?\n', line)
if matches is None:
raise MalformedHunkHeader("Does not match format.", line)
try:
(orig, mod) = matches.group(1).split(" ")
except (ValueError, IndexError), e:
raise MalformedHunkHeader(str(e), line)
if not orig.startswith('-') or not mod.startswith('+'):
raise MalformedHunkHeader("Positions don't start with + or -.", line)
try:
(orig_pos, orig_range) = parse_range(orig[1:])
(mod_pos, mod_range) = parse_range(mod[1:])
except (ValueError, IndexError), e:
raise MalformedHunkHeader(str(e), line)
if mod_range < 0 or orig_range < 0:
raise MalformedHunkHeader("Hunk range is negative", line)
tail = matches.group(3)
return Hunk(orig_pos, orig_range, mod_pos, mod_range, tail)
class HunkLine:
def __init__(self, contents):
self.contents = contents
def get_str(self, leadchar):
if self.contents == "\n" and leadchar == " " and False:
return "\n"
if not self.contents.endswith('\n'):
terminator = '\n' + NO_NL
else:
terminator = ''
return leadchar + self.contents + terminator
class ContextLine(HunkLine):
def __init__(self, contents):
HunkLine.__init__(self, contents)
def __str__(self):
return self.get_str(" ")
class InsertLine(HunkLine):
def __init__(self, contents):
HunkLine.__init__(self, contents)
def __str__(self):
return self.get_str("+")
class RemoveLine(HunkLine):
def __init__(self, contents):
HunkLine.__init__(self, contents)
def __str__(self):
return self.get_str("-")
NO_NL = '\\ No newline at end of file\n'
__pychecker__="no-returnvalues"
def parse_line(line):
if line.startswith("\n"):
return ContextLine(line)
elif line.startswith(" "):
return ContextLine(line[1:])
elif line.startswith("+"):
return InsertLine(line[1:])
elif line.startswith("-"):
return RemoveLine(line[1:])
elif line == NO_NL:
return NO_NL
else:
raise MalformedLine("Unknown line type", line)
__pychecker__=""
class Hunk:
def __init__(self, orig_pos, orig_range, mod_pos, mod_range, tail=None):
self.orig_pos = orig_pos
self.orig_range = orig_range
self.mod_pos = mod_pos
self.mod_range = mod_range
self.tail = tail
self.lines = []
def get_header(self):
if self.tail is None:
tail_str = ''
else:
tail_str = ' ' + self.tail
return "@@ -%s +%s @@%s\n" % (self.range_str(self.orig_pos,
self.orig_range),
self.range_str(self.mod_pos,
self.mod_range),
tail_str)
def range_str(self, pos, range):
"""Return a file range, special-casing for 1-line files.
:param pos: The position in the file
:type pos: int
:range: The range in the file
:type range: int
:return: a string in the format 1,4 except when range == pos == 1
"""
if range == 1:
return "%i" % pos
else:
return "%i,%i" % (pos, range)
def __str__(self):
lines = [self.get_header()]
for line in self.lines:
lines.append(str(line))
return "".join(lines)
def shift_to_mod(self, pos):
if pos < self.orig_pos-1:
return 0
elif pos > self.orig_pos+self.orig_range:
return self.mod_range - self.orig_range
else:
return self.shift_to_mod_lines(pos)
def shift_to_mod_lines(self, pos):
assert (pos >= self.orig_pos-1 and pos <= self.orig_pos+self.orig_range)
position = self.orig_pos-1
shift = 0
for line in self.lines:
if isinstance(line, InsertLine):
shift += 1
elif isinstance(line, RemoveLine):
if position == pos:
return None
shift -= 1
position += 1
elif isinstance(line, ContextLine):
position += 1
if position > pos:
break
return shift
def iter_hunks(iter_lines):
hunk = None
for line in iter_lines:
if line == "\n":
if hunk is not None:
yield hunk
hunk = None
continue
if hunk is not None:
yield hunk
hunk = hunk_from_header(line)
orig_size = 0
mod_size = 0
while orig_size < hunk.orig_range or mod_size < hunk.mod_range:
hunk_line = parse_line(iter_lines.next())
hunk.lines.append(hunk_line)
if isinstance(hunk_line, (RemoveLine, ContextLine)):
orig_size += 1
if isinstance(hunk_line, (InsertLine, ContextLine)):
mod_size += 1
if hunk is not None:
yield hunk
class Patch:
def __init__(self, oldname, newname):
self.oldname = oldname
self.newname = newname
self.hunks = []
def __str__(self):
ret = self.get_header()
ret += "".join([str(h) for h in self.hunks])
return ret
def get_header(self):
return "--- %s\n+++ %s\n" % (self.oldname, self.newname)
def stats_str(self):
"""Return a string of patch statistics"""
removes = 0
inserts = 0
for hunk in self.hunks:
for line in hunk.lines:
if isinstance(line, InsertLine):
inserts+=1;
elif isinstance(line, RemoveLine):
removes+=1;
return "%i inserts, %i removes in %i hunks" % \
(inserts, removes, len(self.hunks))
def pos_in_mod(self, position):
newpos = position
for hunk in self.hunks:
shift = hunk.shift_to_mod(position)
if shift is None:
return None
newpos += shift
return newpos
def iter_inserted(self):
"""Iteraties through inserted lines
:return: Pair of line number, line
:rtype: iterator of (int, InsertLine)
"""
for hunk in self.hunks:
pos = hunk.mod_pos - 1;
for line in hunk.lines:
if isinstance(line, InsertLine):
yield (pos, line)
pos += 1
if isinstance(line, ContextLine):
pos += 1
def parse_patch(iter_lines):
(orig_name, mod_name) = get_patch_names(iter_lines)
patch = Patch(orig_name, mod_name)
for hunk in iter_hunks(iter_lines):
patch.hunks.append(hunk)
return patch
def iter_file_patch(iter_lines):
saved_lines = []
orig_range = 0
for line in iter_lines:
if line.startswith('=== ') or line.startswith('*** '):
continue
if line.startswith('#'):
continue
elif orig_range > 0:
if line.startswith('-') or line.startswith(' '):
orig_range -= 1
elif line.startswith('--- '):
if len(saved_lines) > 0:
yield saved_lines
saved_lines = []
elif line.startswith('@@'):
hunk = hunk_from_header(line)
orig_range = hunk.orig_range
saved_lines.append(line)
if len(saved_lines) > 0:
yield saved_lines
def iter_lines_handle_nl(iter_lines):
"""
Iterates through lines, ensuring that lines that originally had no
terminating \n are produced without one. This transformation may be
applied at any point up until hunk line parsing, and is safe to apply
repeatedly.
"""
last_line = None
for line in iter_lines:
if line == NO_NL:
assert last_line.endswith('\n')
last_line = last_line[:-1]
line = None
if last_line is not None:
yield last_line
last_line = line
if last_line is not None:
yield last_line
def parse_patches(iter_lines):
iter_lines = iter_lines_handle_nl(iter_lines)
return [parse_patch(f.__iter__()) for f in iter_file_patch(iter_lines)]
def difference_index(atext, btext):
"""Find the indext of the first character that differs between two texts
:param atext: The first text
:type atext: str
:param btext: The second text
:type str: str
:return: The index, or None if there are no differences within the range
:rtype: int or NoneType
"""
length = len(atext)
if len(btext) < length:
length = len(btext)
for i in range(length):
if atext[i] != btext[i]:
return i;
return None
def iter_patched(orig_lines, patch_lines):
"""Iterate through a series of lines with a patch applied.
This handles a single file, and does exact, not fuzzy patching.
"""
if orig_lines is not None:
orig_lines = orig_lines.__iter__()
seen_patch = []
patch_lines = iter_lines_handle_nl(patch_lines.__iter__())
get_patch_names(patch_lines)
line_no = 1
for hunk in iter_hunks(patch_lines):
while line_no < hunk.orig_pos:
orig_line = orig_lines.next()
yield orig_line
line_no += 1
for hunk_line in hunk.lines:
seen_patch.append(str(hunk_line))
if isinstance(hunk_line, InsertLine):
yield hunk_line.contents
elif isinstance(hunk_line, (ContextLine, RemoveLine)):
orig_line = orig_lines.next()
if orig_line != hunk_line.contents:
raise PatchConflict(line_no, orig_line, "".join(seen_patch))
if isinstance(hunk_line, ContextLine):
yield orig_line
else:
assert isinstance(hunk_line, RemoveLine)
line_no += 1
if orig_lines is not None:
for line in orig_lines:
yield line
|