File: common.py

package info (click to toggle)
viewcvs 0.9.2%2Bcvs.1.0.dev.2004.07.28-1.5
  • links: PTS
  • area: main
  • in suites: sarge
  • size: 1,436 kB
  • ctags: 1,355
  • sloc: python: 10,094; cpp: 840; ansic: 763; yacc: 526; sh: 168; makefile: 114
file content (293 lines) | stat: -rw-r--r-- 8,284 bytes parent folder | download | duplicates (3)
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
#
# Copyright (C) 2000-2002 The ViewCVS Group. All Rights Reserved.
#
# By using this file, you agree to the terms and conditions set forth in
# the LICENSE.html file which can be found at the top level of the ViewCVS
# distribution or at http://viewcvs.sourceforge.net/license-1.html.
#
# Contact information:
#   Greg Stein, PO Box 760, Palo Alto, CA, 94302
#   gstein@lyra.org, http://viewcvs.sourceforge.net/
#
# -----------------------------------------------------------------------
#
# This software is being maintained as part of the ViewCVS project.
# Information is available at:
#    http://viewcvs.sourceforge.net/
#
# -----------------------------------------------------------------------

"""common.py: common classes and functions for the RCS parsing tools."""

import time
import string

### compat isn't in vclib right now. need to work up a solution
import compat


class Sink:
  def set_head_revision(self, revision):
    pass
  def set_principal_branch(self, branch_name):
    pass
  def define_tag(self, name, revision):
    pass
  def set_access(self, accessors):
    pass
  def set_expansion(self, mode):
    pass
  def set_locking(self, mode):
    """Used to signal locking mode.

    Called with mode argument 'strict' if strict locking
    Not called when no locking used."""
    pass
  def set_locker(self, revision, locker):
    pass
  def set_comment(self, comment):
    pass
  def set_description(self, description):
    pass
  def define_revision(self, revision, timestamp, author, state,
                      branches, next):
    pass
  def set_revision_info(self, revision, log, text):
    pass
  def admin_completed(self):
    pass
  def tree_completed(self):
    pass
  def parse_completed(self):
    pass


# --------------------------------------------------------------------------
#
# EXCEPTIONS USED BY RCSPARSE
#

class RCSParseError(Exception):
  pass
class RCSIllegalCharacter(RCSParseError):
  pass
### need more work on this one
class RCSExpected(RCSParseError):
  def __init__(self, got, wanted):
    RCSParseError.__init__(self, got, wanted)

class RCSStopParser(Exception):
  pass

# --------------------------------------------------------------------------
#
# STANDARD TOKEN STREAM-BASED PARSER
#

class _Parser:
  stream_class = None	# subclasses need to define this

  def parse_rcs_admin(self):
    while 1:
      # Read initial token at beginning of line
      token = self.ts.get()

      # We're done once we reach the description of the RCS tree
      if token[0] in string.digits:
        self.ts.unget(token)
        return

      if token == "head":
        semi, rev = self.ts.mget(2)
        self.sink.set_head_revision(rev)
        if semi != ';':
          raise RCSExpected(semi, ';')
      elif token == "branch":
        semi, branch = self.ts.mget(2)
        self.sink.set_principal_branch(branch)
        if semi != ';':
          raise RCSExpected(semi, ';')
      elif token == "symbols":
        while 1:
          tag = self.ts.get()
          if tag == ';':
            break
          self.ts.match(':')
          tag_name = tag
          tag_rev = self.ts.get()
          self.sink.define_tag(tag_name, tag_rev)
      elif token == "comment":
        semi, comment = self.ts.mget(2)
        self.sink.set_comment(comment)
        if semi != ';':
          raise RCSExpected(semi, ';')
      elif token == "expand":
        semi, expand_mode = self.ts.mget(2)
        self.sink.set_expansion(expand_mode)
        if semi != ';':
          raise RCSExpected(semi, ';')
      elif token == "locks":
        while 1:
          tag = self.ts.get()
          if tag == ';':
            break
          (locker, rev) = string.split(tag,':')
          self.sink.set_locker(rev, locker)

        tag = self.ts.get()
        if tag == "strict":
          self.sink.set_locking("strict")
          self.ts.match(';')
        else:
          self.ts.unget(tag)
      elif token == "access":
        accessors = []
        while 1:
          tag = self.ts.get()
          if tag == ';':
            if accessors != []:
              self.sink.set_access(accessors)
            break
          accessors = accessors + [ tag ]

      # Chew up "newphrase"
      else:
        pass
        # warn("Unexpected RCS token: $token\n")

    raise RuntimeError, "Unexpected EOF"

  def parse_rcs_tree(self):
    while 1:
      revision = self.ts.get()

      # End of RCS tree description ?
      if revision == 'desc':
        self.ts.unget(revision)
        return

      # Parse date
      semi, date, sym = self.ts.mget(3)
      if sym != 'date':
        raise RCSExpected(sym, 'date')
      if semi != ';':
        raise RCSExpected(semi, ';')

      # Convert date into timestamp
      date_fields = string.split(date, '.') + ['0', '0', '0']
      date_fields = map(string.atoi, date_fields)
      # need to make the date four digits for timegm
      EPOCH = 1970
      if date_fields[0] < EPOCH:
          if date_fields[0] < 70:
              date_fields[0] = date_fields[0] + 2000
          else:
              date_fields[0] = date_fields[0] + 1900
          if date_fields[0] < EPOCH:
              raise ValueError, 'invalid year'

      timestamp = compat.timegm(tuple(date_fields))

      # Parse author
      ### NOTE: authors containing whitespace are violations of the
      ### RCS specification.  We are making an allowance here because
      ### CVSNT is known to produce these sorts of authors.
      self.ts.match('author')
      author = ''
      while 1:
        token = self.ts.get()
        if token == ';':
          break
        author = author + token + ' '
      author = author[:-1]	# toss the trailing space

      # Parse state
      self.ts.match('state')
      state = ''
      while 1:
        token = self.ts.get()
        if token == ';':
          break
        state = state + token + ' '
      state = state[:-1]	# toss the trailing space

      # Parse branches
      self.ts.match('branches')
      branches = [ ]
      while 1:
        token = self.ts.get()
        if token == ';':
          break
        branches.append(token)

      # Parse revision of next delta in chain
      next, sym = self.ts.mget(2)
      if sym != 'next':
        raise RCSExpected(sym, 'next')
      if next == ';':
        next = None
      else:
        self.ts.match(';')

      # there are some files with extra tags in them. for example:
      #    owner	640;
      #    group	15;
      #    permissions	644;
      #    hardlinks	@configure.in@;
      # this is "newphrase" in RCSFILE(5). we just want to skip over these.
      while 1:
        token = self.ts.get()
        if token == 'desc' or token[0] in string.digits:
          self.ts.unget(token)
          break
        # consume everything up to the semicolon
        while self.ts.get() != ';':
          pass

      self.sink.define_revision(revision, timestamp, author, state, branches,
                                next)

  def parse_rcs_description(self):
    self.ts.match('desc')
    self.sink.set_description(self.ts.get())

  def parse_rcs_deltatext(self):
    while 1:
      revision = self.ts.get()
      if revision is None:
        # EOF
        break
      text, sym2, log, sym1 = self.ts.mget(4)
      if sym1 != 'log':
        print `text[:100], sym2[:100], log[:100], sym1[:100]`
        raise RCSExpected(sym1, 'log')
      if sym2 != 'text':
        raise RCSExpected(sym2, 'text')
      ### need to add code to chew up "newphrase"
      self.sink.set_revision_info(revision, log, text)

  def parse(self, file, sink):
    self.ts = self.stream_class(file)
    self.sink = sink

    self.parse_rcs_admin()

    # let sink know when the admin section has been completed
    self.sink.admin_completed()

    self.parse_rcs_tree()

    # many sinks want to know when the tree has been completed so they can
    # do some work to prep for the arrival of the deltatext
    self.sink.tree_completed()

    self.parse_rcs_description()
    self.parse_rcs_deltatext()

    # easiest for us to tell the sink it is done, rather than worry about
    # higher level software doing it.
    self.sink.parse_completed()

    self.ts = self.sink = None

# --------------------------------------------------------------------------