File: default.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 (243 lines) | stat: -rw-r--r-- 6,904 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
#
# 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/
#
# This file was originally based on portions of the blame.py script by
# Curt Hagenlocher.
#
# -----------------------------------------------------------------------

import string

import common


class _TokenStream:
  token_term = string.whitespace + ';'

  # the algorithm is about the same speed for any CHUNK_SIZE chosen.
  # grab a good-sized chunk, but not too large to overwhelm memory.
  # note: we use a multiple of a standard block size
  CHUNK_SIZE  = 192 * 512  # about 100k

#  CHUNK_SIZE  = 5	# for debugging, make the function grind...

  def __init__(self, file):
    self.rcsfile = file
    self.idx = 0
    self.buf = self.rcsfile.read(self.CHUNK_SIZE)
    if self.buf == '':
      raise RuntimeError, 'EOF'

  def get(self):
    "Get the next token from the RCS file."

    # Note: we can afford to loop within Python, examining individual
    # characters. For the whitespace and tokens, the number of iterations
    # is typically quite small. Thus, a simple iterative loop will beat
    # out more complex solutions.

    buf = self.buf
    idx = self.idx

    while 1:
      if idx == len(buf):
        buf = self.rcsfile.read(self.CHUNK_SIZE)
        if buf == '':
          # signal EOF by returning None as the token
          del self.buf	# so we fail if get() is called again
          return None
        idx = 0

      if buf[idx] not in string.whitespace:
        break

      idx = idx + 1

    if buf[idx] == ';':
      self.buf = buf
      self.idx = idx + 1
      return ';'

    if buf[idx] != '@':
      end = idx + 1
      token = ''
      while 1:
        # find token characters in the current buffer
        while end < len(buf) and buf[end] not in self.token_term:
          end = end + 1
        token = token + buf[idx:end]

        if end < len(buf):
          # we stopped before the end, so we have a full token
          idx = end
          break

        # we stopped at the end of the buffer, so we may have a partial token
        buf = self.rcsfile.read(self.CHUNK_SIZE)
        idx = end = 0

      self.buf = buf
      self.idx = idx
      return token

    # a "string" which starts with the "@" character. we'll skip it when we
    # search for content.
    idx = idx + 1

    chunks = [ ]

    while 1:
      if idx == len(buf):
        idx = 0
        buf = self.rcsfile.read(self.CHUNK_SIZE)
        if buf == '':
          raise RuntimeError, 'EOF'
      i = string.find(buf, '@', idx)
      if i == -1:
        chunks.append(buf[idx:])
        idx = len(buf)
        continue
      if i == len(buf) - 1:
        chunks.append(buf[idx:i])
        idx = 0
        buf = '@' + self.rcsfile.read(self.CHUNK_SIZE)
        if buf == '@':
          raise RuntimeError, 'EOF'
        continue
      if buf[i + 1] == '@':
        chunks.append(buf[idx:i+1])
        idx = i + 2
        continue

      chunks.append(buf[idx:i])

      self.buf = buf
      self.idx = i + 1

      return string.join(chunks, '')

#  _get = get
#  def get(self):
    token = self._get()
    print 'T:', `token`
    return token

  def match(self, match):
    "Try to match the next token from the input buffer."

    token = self.get()
    if token != match:
      raise RuntimeError, ('Unexpected parsing error in RCS file.\n' +
                           'Expected token: %s, but saw: %s' % (match, token))

  def unget(self, token):
    "Put this token back, for the next get() to return."

    # Override the class' .get method with a function which clears the
    # overridden method then returns the pushed token. Since this function
    # will not be looked up via the class mechanism, it should be a "normal"
    # function, meaning it won't have "self" automatically inserted.
    # Therefore, we need to pass both self and the token thru via defaults.

    # note: we don't put this into the input buffer because it may have been
    # @-unescaped already.

    def give_it_back(self=self, token=token):
      del self.get
      return token

    self.get = give_it_back

  def mget(self, count):
    "Return multiple tokens. 'next' is at the end."
    result = [ ]
    for i in range(count):
      result.append(self.get())
    result.reverse()
    return result


class Parser(common._Parser):
  stream_class = _TokenStream

  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 common.RCSExpected(semi, ';')
      elif token == "branch":
        semi, branch = self.ts.mget(2)
        self.sink.set_principal_branch(branch)
        if semi != ';':
          raise common.RCSExpected(semi, ';')
      elif token == "symbols":
        while 1:
          tag = self.ts.get()
          if tag == ';':
            break
          (tag_name, tag_rev) = string.split(tag, ':')
          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 common.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"