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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (C) 2007 Edgewall Software
# All rights reserved.
#
# This software is licensed as described in the file COPYING, which
# you should have received as part of this distribution. The terms
# are also available at http://babel.edgewall.org/wiki/License.
#
# This software consists of voluntary contributions made by many
# individuals. For the exact contribution history, see the revision
# history and logs, available at http://babel.edgewall.org/log/.
import copy
from optparse import OptionParser
import os
import pickle
import sys
try:
from xml.etree.ElementTree import parse
except ImportError:
from elementtree.ElementTree import parse
# Make sure we're using Babel source, and not some previously installed version
sys.path.insert(0, os.path.join(os.path.dirname(sys.argv[0]), '..'))
from babel import dates, numbers
weekdays = {'mon': 0, 'tue': 1, 'wed': 2, 'thu': 3, 'fri': 4, 'sat': 5,
'sun': 6}
try:
any
except NameError:
def any(iterable):
return filter(None, list(iterable))
def _text(elem):
buf = [elem.text or '']
for child in elem:
buf.append(_text(child))
buf.append(elem.tail or '')
return u''.join(filter(None, buf)).strip()
def main():
parser = OptionParser(usage='%prog path/to/cldr')
options, args = parser.parse_args()
if len(args) != 1:
parser.error('incorrect number of arguments')
srcdir = args[0]
destdir = os.path.join(os.path.dirname(os.path.abspath(sys.argv[0])),
'..', 'babel')
sup = parse(os.path.join(srcdir, 'supplemental', 'supplementalData.xml'))
# import global data from the supplemental files
global_data = {}
territory_zones = global_data.setdefault('territory_zones', {})
zone_aliases = global_data.setdefault('zone_aliases', {})
zone_territories = global_data.setdefault('zone_territories', {})
for elem in sup.findall('//timezoneData/zoneFormatting/zoneItem'):
tzid = elem.attrib['type']
territory_zones.setdefault(elem.attrib['territory'], []).append(tzid)
zone_territories[tzid] = elem.attrib['territory']
if 'aliases' in elem.attrib:
for alias in elem.attrib['aliases'].split():
zone_aliases[alias] = tzid
outfile = open(os.path.join(destdir, 'global.dat'), 'wb')
try:
pickle.dump(global_data, outfile, 2)
finally:
outfile.close()
# build a territory containment mapping for inheritance
regions = {}
for elem in sup.findall('//territoryContainment/group'):
regions[elem.attrib['type']] = elem.attrib['contains'].split()
# Resolve territory containment
territory_containment = {}
region_items = regions.items()
region_items.sort()
for group, territory_list in region_items:
for territory in territory_list:
containers = territory_containment.setdefault(territory, set([]))
if group in territory_containment:
containers |= territory_containment[group]
containers.add(group)
filenames = os.listdir(os.path.join(srcdir, 'main'))
filenames.remove('root.xml')
filenames.sort(lambda a,b: len(a)-len(b))
filenames.insert(0, 'root.xml')
for filename in filenames:
print>>sys.stderr, 'Processing input file %r' % filename
stem, ext = os.path.splitext(filename)
if ext != '.xml':
continue
tree = parse(os.path.join(srcdir, 'main', filename))
data = {}
language = None
elem = tree.find('//identity/language')
if elem is not None:
language = elem.attrib['type']
print>>sys.stderr, ' Language: %r' % language
territory = None
elem = tree.find('//identity/territory')
if elem is not None:
territory = elem.attrib['type']
else:
territory = '001' # world
print>>sys.stderr, ' Territory: %r' % territory
regions = territory_containment.get(territory, [])
print>>sys.stderr, ' Regions: %r' % regions
# <localeDisplayNames>
territories = data.setdefault('territories', {})
for elem in tree.findall('//territories/territory'):
if 'draft' in elem.attrib and elem.attrib['type'] in territories:
continue
territories[elem.attrib['type']] = _text(elem)
languages = data.setdefault('languages', {})
for elem in tree.findall('//languages/language'):
if 'draft' in elem.attrib and elem.attrib['type'] in languages:
continue
languages[elem.attrib['type']] = _text(elem)
variants = data.setdefault('variants', {})
for elem in tree.findall('//variants/variant'):
if 'draft' in elem.attrib and elem.attrib['type'] in variants:
continue
variants[elem.attrib['type']] = _text(elem)
scripts = data.setdefault('scripts', {})
for elem in tree.findall('//scripts/script'):
if 'draft' in elem.attrib and elem.attrib['type'] in scripts:
continue
scripts[elem.attrib['type']] = _text(elem)
# <dates>
week_data = data.setdefault('week_data', {})
supelem = sup.find('//weekData')
for elem in supelem.findall('minDays'):
territories = elem.attrib['territories'].split()
if territory in territories or any([r in territories for r in regions]):
week_data['min_days'] = int(elem.attrib['count'])
for elem in supelem.findall('firstDay'):
territories = elem.attrib['territories'].split()
if territory in territories or any([r in territories for r in regions]):
week_data['first_day'] = weekdays[elem.attrib['day']]
for elem in supelem.findall('weekendStart'):
territories = elem.attrib['territories'].split()
if territory in territories or any([r in territories for r in regions]):
week_data['weekend_start'] = weekdays[elem.attrib['day']]
for elem in supelem.findall('weekendEnd'):
territories = elem.attrib['territories'].split()
if territory in territories or any([r in territories for r in regions]):
week_data['weekend_end'] = weekdays[elem.attrib['day']]
zone_formats = data.setdefault('zone_formats', {})
for elem in tree.findall('//timeZoneNames/gmtFormat'):
if 'draft' not in elem.attrib:
zone_formats['gmt'] = unicode(elem.text).replace('{0}', '%s')
break
for elem in tree.findall('//timeZoneNames/regionFormat'):
if 'draft' not in elem.attrib:
zone_formats['region'] = unicode(elem.text).replace('{0}', '%s')
break
for elem in tree.findall('//timeZoneNames/fallbackFormat'):
if 'draft' not in elem.attrib:
zone_formats['fallback'] = unicode(elem.text) \
.replace('{0}', '%(0)s').replace('{1}', '%(1)s')
break
time_zones = data.setdefault('time_zones', {})
for elem in tree.findall('//timeZoneNames/zone'):
info = {}
city = elem.findtext('exemplarCity')
if city:
info['city'] = unicode(city)
for child in elem.findall('long/*'):
info.setdefault('long', {})[child.tag] = unicode(child.text)
for child in elem.findall('short/*'):
info.setdefault('short', {})[child.tag] = unicode(child.text)
for child in elem.findall('usesMetazone'):
if 'to' not in child.attrib: # FIXME: support old mappings
info['use_metazone'] = child.attrib['mzone']
time_zones[elem.attrib['type']] = info
meta_zones = data.setdefault('meta_zones', {})
for elem in tree.findall('//timeZoneNames/metazone'):
info = {}
city = elem.findtext('exemplarCity')
if city:
info['city'] = unicode(city)
for child in elem.findall('long/*'):
info.setdefault('long', {})[child.tag] = unicode(child.text)
for child in elem.findall('short/*'):
info.setdefault('short', {})[child.tag] = unicode(child.text)
info['common'] = elem.findtext('commonlyUsed') == 'true'
meta_zones[elem.attrib['type']] = info
for calendar in tree.findall('//calendars/calendar'):
if calendar.attrib['type'] != 'gregorian':
# TODO: support other calendar types
continue
months = data.setdefault('months', {})
for ctxt in calendar.findall('months/monthContext'):
ctxts = months.setdefault(ctxt.attrib['type'], {})
for width in ctxt.findall('monthWidth'):
widths = ctxts.setdefault(width.attrib['type'], {})
for elem in width.findall('month'):
if 'draft' in elem.attrib and int(elem.attrib['type']) in widths:
continue
widths[int(elem.attrib.get('type'))] = unicode(elem.text)
days = data.setdefault('days', {})
for ctxt in calendar.findall('days/dayContext'):
ctxts = days.setdefault(ctxt.attrib['type'], {})
for width in ctxt.findall('dayWidth'):
widths = ctxts.setdefault(width.attrib['type'], {})
for elem in width.findall('day'):
dtype = weekdays[elem.attrib['type']]
if 'draft' in elem.attrib and dtype in widths:
continue
widths[dtype] = unicode(elem.text)
quarters = data.setdefault('quarters', {})
for ctxt in calendar.findall('quarters/quarterContext'):
ctxts = quarters.setdefault(ctxt.attrib['type'], {})
for width in ctxt.findall('quarterWidth'):
widths = ctxts.setdefault(width.attrib['type'], {})
for elem in width.findall('quarter'):
if 'draft' in elem.attrib and int(elem.attrib['type']) in widths:
continue
widths[int(elem.attrib.get('type'))] = unicode(elem.text)
eras = data.setdefault('eras', {})
for width in calendar.findall('eras/*'):
ewidth = {
'eraAbbr': 'abbreviated',
'eraNames': 'wide',
'eraNarrow': 'narrow',
}[width.tag]
widths = eras.setdefault(ewidth, {})
for elem in width.findall('era'):
if 'draft' in elem.attrib and int(elem.attrib['type']) in widths:
continue
widths[int(elem.attrib.get('type'))] = unicode(elem.text)
# AM/PM
periods = data.setdefault('periods', {})
for elem in calendar.findall('am'):
if 'draft' in elem.attrib and elem.tag in periods:
continue
periods[elem.tag] = unicode(elem.text)
for elem in calendar.findall('pm'):
if 'draft' in elem.attrib and elem.tag in periods:
continue
periods[elem.tag] = unicode(elem.text)
date_formats = data.setdefault('date_formats', {})
for elem in calendar.findall('dateFormats/dateFormatLength'):
if 'draft' in elem.attrib and elem.attrib.get('type') in date_formats:
continue
try:
date_formats[elem.attrib.get('type')] = \
dates.parse_pattern(unicode(elem.findtext('dateFormat/pattern')))
except ValueError, e:
print>>sys.stderr, 'ERROR: %s' % e
time_formats = data.setdefault('time_formats', {})
for elem in calendar.findall('timeFormats/timeFormatLength'):
if 'draft' in elem.attrib and elem.attrib.get('type') in time_formats:
continue
try:
time_formats[elem.attrib.get('type')] = \
dates.parse_pattern(unicode(elem.findtext('timeFormat/pattern')))
except ValueError, e:
print>>sys.stderr, 'ERROR: %s' % e
datetime_formats = data.setdefault('datetime_formats', {})
for elem in calendar.findall('dateTimeFormats/dateTimeFormatLength'):
if 'draft' in elem.attrib and elem.attrib.get('type') in datetime_formats:
continue
try:
datetime_formats[elem.attrib.get('type')] = \
unicode(elem.findtext('dateTimeFormat/pattern'))
except ValueError, e:
print>>sys.stderr, 'ERROR: %s' % e
# <numbers>
number_symbols = data.setdefault('number_symbols', {})
for elem in tree.findall('//numbers/symbols/*'):
number_symbols[elem.tag] = unicode(elem.text)
decimal_formats = data.setdefault('decimal_formats', {})
for elem in tree.findall('//decimalFormats/decimalFormatLength'):
if 'draft' in elem.attrib and elem.attrib.get('type') in decimal_formats:
continue
pattern = unicode(elem.findtext('decimalFormat/pattern'))
decimal_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
scientific_formats = data.setdefault('scientific_formats', {})
for elem in tree.findall('//scientificFormats/scientificFormatLength'):
if 'draft' in elem.attrib and elem.attrib.get('type') in scientific_formats:
continue
pattern = unicode(elem.findtext('scientificFormat/pattern'))
scientific_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
currency_formats = data.setdefault('currency_formats', {})
for elem in tree.findall('//currencyFormats/currencyFormatLength'):
if 'draft' in elem.attrib and elem.attrib.get('type') in currency_formats:
continue
pattern = unicode(elem.findtext('currencyFormat/pattern'))
currency_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
percent_formats = data.setdefault('percent_formats', {})
for elem in tree.findall('//percentFormats/percentFormatLength'):
if 'draft' in elem.attrib and elem.attrib.get('type') in percent_formats:
continue
pattern = unicode(elem.findtext('percentFormat/pattern'))
percent_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
currency_names = data.setdefault('currency_names', {})
currency_symbols = data.setdefault('currency_symbols', {})
for elem in tree.findall('//currencies/currency'):
name = elem.findtext('displayName')
if name:
currency_names[elem.attrib['type']] = unicode(name)
symbol = elem.findtext('symbol')
if symbol:
currency_symbols[elem.attrib['type']] = unicode(symbol)
outfile = open(os.path.join(destdir, 'localedata', stem + '.dat'), 'wb')
try:
pickle.dump(data, outfile, 2)
finally:
outfile.close()
if __name__ == '__main__':
main()
|
