summaryrefslogtreecommitdiffstats
path: root/tools/grit/grit/node/message.py
blob: 3c5ac645f1137a4b75a5d49a99808601fbb081f3 (plain)
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
#!/usr/bin/python2.4
# Copyright (c) 2011 The Chromium Authors. All rights reserved.
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.

'''Handling of the <message> element.
'''

import re
import types

from grit.node import base

import grit.format.rc_header
import grit.format.rc

from grit import clique
from grit import exception
from grit import tclib
from grit import util

BINARY, UTF8, UTF16 = range(3)

# Finds whitespace at the start and end of a string which can be multiline.
_WHITESPACE = re.compile('(?P<start>\s*)(?P<body>.+?)(?P<end>\s*)\Z',
                         re.DOTALL | re.MULTILINE)


class MessageNode(base.ContentNode):
  '''A <message> element.'''

  # For splitting a list of things that can be separated by commas or
  # whitespace
  _SPLIT_RE = re.compile('\s*,\s*|\s+')

  def __init__(self):
    super(type(self), self).__init__()
    # Valid after EndParsing, this is the MessageClique that contains the
    # source message and any translations of it that have been loaded.
    self.clique = None

    # We don't send leading and trailing whitespace into the translation
    # console, but rather tack it onto the source message and any
    # translations when formatting them into RC files or what have you.
    self.ws_at_start = ''  # Any whitespace characters at the start of the text
    self.ws_at_end = ''  # --"-- at the end of the text

    # A list of "shortcut groups" this message is in.  We check to make sure
    # that shortcut keys (e.g. &J) within each shortcut group are unique.
    self.shortcut_groups_ = []

  def _IsValidChild(self, child):
    return isinstance(child, (PhNode))

  def _IsValidAttribute(self, name, value):
    if name not in ['name', 'offset', 'translateable', 'desc', 'meaning',
                    'internal_comment', 'shortcut_groups', 'custom_type',
                    'validation_expr', 'use_name_for_id']:
      return False
    if name == 'translateable' and value not in ['true', 'false']:
      return False
    return True

  def MandatoryAttributes(self):
    return ['name|offset']

  def DefaultAttributes(self):
    return {
      'translateable' : 'true',
      'desc' : '',
      'meaning' : '',
      'internal_comment' : '',
      'shortcut_groups' : '',
      'custom_type' : '',
      'validation_expr' : '',
      'use_name_for_id' : 'false',
    }

  def GetTextualIds(self):
    '''
    Returns the concatenation of the parent's node first_id and
    this node's offset if it has one, otherwise just call the
    superclass' implementation
    '''
    if 'offset' in self.attrs:
      # we search for the first grouping node in the parents' list
      # to take care of the case where the first parent is an <if> node
      grouping_parent = self.parent
      import grit.node.empty
      while grouping_parent and not isinstance(grouping_parent,
                                               grit.node.empty.GroupingNode):
        grouping_parent = grouping_parent.parent

      assert 'first_id' in grouping_parent.attrs
      return [grouping_parent.attrs['first_id'] + '_' + self.attrs['offset']]
    else:
      return super(type(self), self).GetTextualIds()

  def IsTranslateable(self):
    return self.attrs['translateable'] == 'true'

  def ItemFormatter(self, t):
    # Only generate an output if the if condition is satisfied.
    if not self.SatisfiesOutputCondition():
      return super(type(self), self).ItemFormatter(t)

    if t == 'rc_header':
      return grit.format.rc_header.Item()
    elif t in ('rc_all', 'rc_translateable', 'rc_nontranslateable'):
      return grit.format.rc.Message()
    elif t == 'js_map_format':
        return grit.format.js_map_format.Message()
    else:
      return super(type(self), self).ItemFormatter(t)

  def EndParsing(self):
    super(type(self), self).EndParsing()

    # Make the text (including placeholder references) and list of placeholders,
    # then strip and store leading and trailing whitespace and create the
    # tclib.Message() and a clique to contain it.

    text = ''
    placeholders = []
    for item in self.mixed_content:
      if isinstance(item, types.StringTypes):
        text += item
      else:
        presentation = item.attrs['name'].upper()
        text += presentation
        ex = ' '
        if len(item.children):
          ex = item.children[0].GetCdata()
        original = item.GetCdata()
        placeholders.append(tclib.Placeholder(presentation, original, ex))

    m = _WHITESPACE.match(text)
    if m:
      self.ws_at_start = m.group('start')
      self.ws_at_end = m.group('end')
      text = m.group('body')

    self.shortcut_groups_ = self._SPLIT_RE.split(self.attrs['shortcut_groups'])
    self.shortcut_groups_ = [i for i in self.shortcut_groups_ if i != '']

    description_or_id = self.attrs['desc']
    if description_or_id == '' and 'name' in self.attrs:
      description_or_id = 'ID: %s' % self.attrs['name']

    assigned_id = None
    if (self.attrs['use_name_for_id'] == 'true' and
        self.SatisfiesOutputCondition()):
      assigned_id = self.attrs['name']
    message = tclib.Message(text=text, placeholders=placeholders,
                            description=description_or_id,
                            meaning=self.attrs['meaning'],
                            assigned_id=assigned_id)
    self.clique = self.UberClique().MakeClique(message, self.IsTranslateable())
    for group in self.shortcut_groups_:
      self.clique.AddToShortcutGroup(group)
    if self.attrs['custom_type'] != '':
      self.clique.SetCustomType(util.NewClassInstance(self.attrs['custom_type'],
                                                      clique.CustomType))
    elif self.attrs['validation_expr'] != '':
      self.clique.SetCustomType(
        clique.OneOffCustomType(self.attrs['validation_expr']))

  def GetCliques(self):
    if self.clique:
      return [self.clique]
    else:
      return []

  def Translate(self, lang):
    '''Returns a translated version of this message.
    '''
    assert self.clique
    msg = self.clique.MessageForLanguage(lang,
                                         self.PseudoIsAllowed(),
                                         self.ShouldFallbackToEnglish()
                                         ).GetRealContent()
    return msg.replace('[GRITLANGCODE]', lang)

  def NameOrOffset(self):
    if 'name' in self.attrs:
      return self.attrs['name']
    else:
      return self.attrs['offset']

  def GetDataPackPair(self, lang, encoding):
    '''Returns a (id, string) pair that represents the string id and the string
    in utf8.  This is used to generate the data pack data file.
    '''
    from grit.format import rc_header
    id_map = rc_header.Item.tids_
    id = id_map[self.GetTextualIds()[0]]

    message = self.ws_at_start + self.Translate(lang) + self.ws_at_end
    if "\\n" in message:
      # Windows automatically translates \n to a new line, but GTK+ doesn't.
      # Manually do the conversion here rather than at run time.
      message = message.replace("\\n", "\n")
    # |message| is a python unicode string, so convert to a byte stream that
    # has the correct encoding requested for the datapacks. We skip the first
    # 2 bytes of text resources because it is the BOM.
    if encoding == UTF8:
      return id, message.encode('utf8')
    if encoding == UTF16:
      return id, message.encode('utf16')[2:]
    # Default is BINARY
    return id, message

  # static method
  def Construct(parent, message, name, desc='', meaning='', translateable=True):
    '''Constructs a new message node that is a child of 'parent', with the
    name, desc, meaning and translateable attributes set using the same-named
    parameters and the text of the message and any placeholders taken from
    'message', which must be a tclib.Message() object.'''
    # Convert type to appropriate string
    if translateable:
      translateable = 'true'
    else:
      translateable = 'false'

    node = MessageNode()
    node.StartParsing('message', parent)
    node.HandleAttribute('name', name)
    node.HandleAttribute('desc', desc)
    node.HandleAttribute('meaning', meaning)
    node.HandleAttribute('translateable', translateable)

    items = message.GetContent()
    for ix in range(len(items)):
      if isinstance(items[ix], types.StringTypes):
        text = items[ix]

        # Ensure whitespace at front and back of message is correctly handled.
        if ix == 0:
          text = "'''" + text
        if ix == len(items) - 1:
          text = text + "'''"

        node.AppendContent(text)
      else:
        phnode = PhNode()
        phnode.StartParsing('ph', node)
        phnode.HandleAttribute('name', items[ix].GetPresentation())
        phnode.AppendContent(items[ix].GetOriginal())

        if len(items[ix].GetExample()) and items[ix].GetExample() != ' ':
          exnode = ExNode()
          exnode.StartParsing('ex', phnode)
          exnode.AppendContent(items[ix].GetExample())
          exnode.EndParsing()
          phnode.AddChild(exnode)

        phnode.EndParsing()
        node.AddChild(phnode)

    node.EndParsing()
    return node
  Construct = staticmethod(Construct)

class PhNode(base.ContentNode):
  '''A <ph> element.'''

  def _IsValidChild(self, child):
    return isinstance(child, ExNode)

  def MandatoryAttributes(self):
    return ['name']

  def EndParsing(self):
    super(type(self), self).EndParsing()
    # We only allow a single example for each placeholder
    if len(self.children) > 1:
      raise exception.TooManyExamples()


class ExNode(base.ContentNode):
  '''An <ex> element.'''
  pass