babel/mirror: scripts/import

annotate scripts/import_cldr.py @ 395:a0457635279d trunk

The `format_timedelta` function now returns, for example, ?1 day? instead of ?0 days? if the granularity is `day` and the delta is less than a day but greater than zero.

author	cmlenz
date	Tue, 15 Jul 2008 16:02:17 +0000
parents	c5bc0f6822a9
children	36038b8ddc49

rev	line source
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	1 #!/usr/bin/env python
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	2 # -- coding: utf-8 --
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	3 #
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	4 # Copyright (C) 2007 Edgewall Software
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	5 # All rights reserved.
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	6 #
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	7 # This software is licensed as described in the file COPYING, which
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	8 # you should have received as part of this distribution. The terms
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	9 # are also available at http://babel.edgewall.org/wiki/License.
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	10 #
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	11 # This software consists of voluntary contributions made by many
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	12 # individuals. For the exact contribution history, see the revision
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	13 # history and logs, available at http://babel.edgewall.org/log/.
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	14
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	15 import copy
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	16 from optparse import OptionParser
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	17 import os
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	18 import pickle
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	19 import re
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	20 import sys
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	21 try:
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	22 from xml.etree.ElementTree import parse
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	23 except ImportError:
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	24 from elementtree.ElementTree import parse
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	25
65 75fe8369ed3b Add Babel soruce path to CLDR import script automatically for asmodai ;-). cmlenz parents: 34 diff changeset	26 # Make sure we're using Babel source, and not some previously installed version
75fe8369ed3b Add Babel soruce path to CLDR import script automatically for asmodai ;-). cmlenz parents: 34 diff changeset	27 sys.path.insert(0, os.path.join(os.path.dirname(sys.argv[0]), '..'))
75fe8369ed3b Add Babel soruce path to CLDR import script automatically for asmodai ;-). cmlenz parents: 34 diff changeset	28
9 9ed6cf5975a1 Add basic support for number format patterns. jonas parents: 8 diff changeset	29 from babel import dates, numbers
390 c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	30 from babel.plural import PluralRule
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	31 from babel.localedata import Alias
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	32
15 244a74232f5e Minor date formatting improvements. cmlenz parents: 13 diff changeset	33 weekdays = {'mon': 0, 'tue': 1, 'wed': 2, 'thu': 3, 'fri': 4, 'sat': 5,
244a74232f5e Minor date formatting improvements. cmlenz parents: 13 diff changeset	34 'sun': 6}
8 29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	35
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	36 try:
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	37 any
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	38 except NameError:
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	39 def any(iterable):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	40 return filter(None, list(iterable))
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	41
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	42
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	43 def _text(elem):
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	44 buf = [elem.text or '']
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	45 for child in elem:
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	46 buf.append(_text(child))
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	47 buf.append(elem.tail or '')
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	48 return u''.join(filter(None, buf)).strip()
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	49
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	50
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	51 NAME_RE = re.compile(r"^\w+$")
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	52 TYPE_ATTR_RE = re.compile(r"^\w+\[@type='(.*?)'\]$")
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	53
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	54 NAME_MAP = {
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	55 'dateFormats': 'date_formats',
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	56 'dateTimeFormats': 'datetime_formats',
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	57 'eraAbbr': 'abbreviated',
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	58 'eraNames': 'wide',
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	59 'eraNarrow': 'narrow',
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	60 'timeFormats': 'time_formats'
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	61 }
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	62
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	63 def _translate_alias(ctxt, path):
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	64 parts = path.split('/')
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	65 keys = ctxt[:]
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	66 for part in parts:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	67 if part == '..':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	68 keys.pop()
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	69 else:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	70 match = TYPE_ATTR_RE.match(part)
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	71 if match:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	72 keys.append(match.group(1))
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	73 else:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	74 assert NAME_RE.match(part)
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	75 keys.append(NAME_MAP.get(part, part))
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	76 return keys
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	77
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	78
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	79 def main():
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	80 parser = OptionParser(usage='%prog path/to/cldr')
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	81 options, args = parser.parse_args()
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	82 if len(args) != 1:
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	83 parser.error('incorrect number of arguments')
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	84
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	85 srcdir = args[0]
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	86 destdir = os.path.join(os.path.dirname(os.path.abspath(sys.argv[0])),
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	87 '..', 'babel')
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	88
8 29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	89 sup = parse(os.path.join(srcdir, 'supplemental', 'supplementalData.xml'))
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	90
345 e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	91 # Import global data from the supplemental files
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	92 global_data = {}
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	93
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	94 territory_zones = global_data.setdefault('territory_zones', {})
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	95 zone_aliases = global_data.setdefault('zone_aliases', {})
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	96 zone_territories = global_data.setdefault('zone_territories', {})
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	97 for elem in sup.findall('//timezoneData/zoneFormatting/zoneItem'):
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	98 tzid = elem.attrib['type']
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	99 territory_zones.setdefault(elem.attrib['territory'], []).append(tzid)
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	100 zone_territories[tzid] = elem.attrib['territory']
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	101 if 'aliases' in elem.attrib:
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	102 for alias in elem.attrib['aliases'].split():
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	103 zone_aliases[alias] = tzid
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	104
345 e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	105 # Import Metazone mapping
e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	106 meta_zones = global_data.setdefault('meta_zones', {})
e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	107 tzsup = parse(os.path.join(srcdir, 'supplemental', 'metazoneInfo.xml'))
e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	108 for elem in tzsup.findall('//timezone'):
e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	109 for child in elem.findall('usesMetazone'):
e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	110 if 'to' not in child.attrib: # FIXME: support old mappings
e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	111 meta_zones[elem.attrib['type']] = child.attrib['mzone']
e818b03b370f Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	112
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	113 outfile = open(os.path.join(destdir, 'global.dat'), 'wb')
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	114 try:
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	115 pickle.dump(global_data, outfile, 2)
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	116 finally:
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	117 outfile.close()
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	118
8 29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	119 # build a territory containment mapping for inheritance
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	120 regions = {}
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	121 for elem in sup.findall('//territoryContainment/group'):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	122 regions[elem.attrib['type']] = elem.attrib['contains'].split()
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	123
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	124 # Resolve territory containment
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	125 territory_containment = {}
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	126 region_items = regions.items()
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	127 region_items.sort()
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	128 for group, territory_list in region_items:
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	129 for territory in territory_list:
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	130 containers = territory_containment.setdefault(territory, set([]))
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	131 if group in territory_containment:
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	132 containers \|= territory_containment[group]
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	133 containers.add(group)
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	134
390 c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	135 # prepare the per-locale plural rules definitions
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	136 plural_rules = {}
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	137 prsup = parse(os.path.join(srcdir, 'supplemental', 'plurals.xml'))
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	138 for elem in prsup.findall('//plurals/pluralRules'):
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	139 rules = []
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	140 for rule in elem.findall('pluralRule'):
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	141 rules.append((rule.attrib['count'], unicode(rule.text)))
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	142 pr = PluralRule(rules)
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	143 for locale in elem.attrib['locales'].split():
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	144 plural_rules[locale] = pr
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	145
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	146 filenames = os.listdir(os.path.join(srcdir, 'main'))
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	147 filenames.remove('root.xml')
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	148 filenames.sort(lambda a,b: len(a)-len(b))
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	149 filenames.insert(0, 'root.xml')
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	150
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	151 for filename in filenames:
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	152 stem, ext = os.path.splitext(filename)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	153 if ext != '.xml':
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	154 continue
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	155
385 38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	156 print>>sys.stderr, 'Processing input file %r' % filename
26 6041782ea677 * Reduce size of locale data pickles by only storing the data provided by each locale itself, and merging inherited data at runtime. cmlenz parents: 22 diff changeset	157 tree = parse(os.path.join(srcdir, 'main', filename))
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	158 data = {}
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	159
8 29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	160 language = None
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	161 elem = tree.find('//identity/language')
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	162 if elem is not None:
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	163 language = elem.attrib['type']
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	164 print>>sys.stderr, ' Language: %r' % language
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	165
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	166 territory = None
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	167 elem = tree.find('//identity/territory')
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	168 if elem is not None:
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	169 territory = elem.attrib['type']
13 368650dc3423 Extended and documented `LazyProxy`. cmlenz parents: 9 diff changeset	170 else:
368650dc3423 Extended and documented `LazyProxy`. cmlenz parents: 9 diff changeset	171 territory = '001' # world
8 29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	172 print>>sys.stderr, ' Territory: %r' % territory
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	173 regions = territory_containment.get(territory, [])
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	174 print>>sys.stderr, ' Regions: %r' % regions
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	175
390 c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	176 # plural rules
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	177 locale_id = '_'.join(filter(None, [
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	178 language,
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	179 territory != '001' and territory or None
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	180 ]))
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	181 if locale_id in plural_rules:
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	182 data['plural_form'] = plural_rules[locale_id]
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	183
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	184 # <localeDisplayNames>
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	185
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	186 territories = data.setdefault('territories', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	187 for elem in tree.findall('//territories/territory'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	188 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	189 and elem.attrib['type'] in territories:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	190 continue
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	191 territories[elem.attrib['type']] = _text(elem)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	192
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	193 languages = data.setdefault('languages', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	194 for elem in tree.findall('//languages/language'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	195 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	196 and elem.attrib['type'] in languages:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	197 continue
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	198 languages[elem.attrib['type']] = _text(elem)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	199
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	200 variants = data.setdefault('variants', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	201 for elem in tree.findall('//variants/variant'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	202 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	203 and elem.attrib['type'] in variants:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	204 continue
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	205 variants[elem.attrib['type']] = _text(elem)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	206
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	207 scripts = data.setdefault('scripts', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	208 for elem in tree.findall('//scripts/script'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	209 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	210 and elem.attrib['type'] in scripts:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	211 continue
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	212 scripts[elem.attrib['type']] = _text(elem)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	213
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	214 # <dates>
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	215
8 29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	216 week_data = data.setdefault('week_data', {})
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	217 supelem = sup.find('//weekData')
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	218
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	219 for elem in supelem.findall('minDays'):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	220 territories = elem.attrib['territories'].split()
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	221 if territory in territories or any([r in territories for r in regions]):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	222 week_data['min_days'] = int(elem.attrib['count'])
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	223
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	224 for elem in supelem.findall('firstDay'):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	225 territories = elem.attrib['territories'].split()
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	226 if territory in territories or any([r in territories for r in regions]):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	227 week_data['first_day'] = weekdays[elem.attrib['day']]
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	228
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	229 for elem in supelem.findall('weekendStart'):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	230 territories = elem.attrib['territories'].split()
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	231 if territory in territories or any([r in territories for r in regions]):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	232 week_data['weekend_start'] = weekdays[elem.attrib['day']]
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	233
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	234 for elem in supelem.findall('weekendEnd'):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	235 territories = elem.attrib['territories'].split()
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	236 if territory in territories or any([r in territories for r in regions]):
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	237 week_data['weekend_end'] = weekdays[elem.attrib['day']]
29f6f9a90f14 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	238
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	239 zone_formats = data.setdefault('zone_formats', {})
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	240 for elem in tree.findall('//timeZoneNames/gmtFormat'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	241 if 'draft' not in elem.attrib and 'alt' not in elem.attrib:
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	242 zone_formats['gmt'] = unicode(elem.text).replace('{0}', '%s')
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	243 break
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	244 for elem in tree.findall('//timeZoneNames/regionFormat'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	245 if 'draft' not in elem.attrib and 'alt' not in elem.attrib:
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	246 zone_formats['region'] = unicode(elem.text).replace('{0}', '%s')
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	247 break
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	248 for elem in tree.findall('//timeZoneNames/fallbackFormat'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	249 if 'draft' not in elem.attrib and 'alt' not in elem.attrib:
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	250 zone_formats['fallback'] = unicode(elem.text) \
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	251 .replace('{0}', '%(0)s').replace('{1}', '%(1)s')
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	252 break
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	253
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	254 time_zones = data.setdefault('time_zones', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	255 for elem in tree.findall('//timeZoneNames/zone'):
28 b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	256 info = {}
b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	257 city = elem.findtext('exemplarCity')
b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	258 if city:
b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	259 info['city'] = unicode(city)
b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	260 for child in elem.findall('long/*'):
b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	261 info.setdefault('long', {})[child.tag] = unicode(child.text)
b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	262 for child in elem.findall('short/*'):
b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	263 info.setdefault('short', {})[child.tag] = unicode(child.text)
b00b06e5ace8 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	264 time_zones[elem.attrib['type']] = info
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	265
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	266 meta_zones = data.setdefault('meta_zones', {})
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	267 for elem in tree.findall('//timeZoneNames/metazone'):
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	268 info = {}
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	269 city = elem.findtext('exemplarCity')
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	270 if city:
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	271 info['city'] = unicode(city)
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	272 for child in elem.findall('long/*'):
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	273 info.setdefault('long', {})[child.tag] = unicode(child.text)
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	274 for child in elem.findall('short/*'):
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	275 info.setdefault('short', {})[child.tag] = unicode(child.text)
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	276 info['common'] = elem.findtext('commonlyUsed') == 'true'
da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	277 meta_zones[elem.attrib['type']] = info
34 464fbcefedde Extended time-zone support. cmlenz parents: 33 diff changeset	278
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	279 for calendar in tree.findall('//calendars/calendar'):
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	280 if calendar.attrib['type'] != 'gregorian':
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	281 # TODO: support other calendar types
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	282 continue
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	283
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	284 months = data.setdefault('months', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	285 for ctxt in calendar.findall('months/monthContext'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	286 ctxt_type = ctxt.attrib['type']
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	287 ctxts = months.setdefault(ctxt_type, {})
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	288 for width in ctxt.findall('monthWidth'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	289 width_type = width.attrib['type']
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	290 widths = ctxts.setdefault(width_type, {})
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	291 for elem in width.getiterator():
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	292 if elem.tag == 'month':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	293 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	294 and int(elem.attrib['type']) in widths:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	295 continue
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	296 widths[int(elem.attrib.get('type'))] = unicode(elem.text)
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	297 elif elem.tag == 'alias':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	298 ctxts[width_type] = Alias(
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	299 _translate_alias(['months', ctxt_type, width_type],
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	300 elem.attrib['path'])
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	301 )
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	302
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	303 days = data.setdefault('days', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	304 for ctxt in calendar.findall('days/dayContext'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	305 ctxt_type = ctxt.attrib['type']
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	306 ctxts = days.setdefault(ctxt_type, {})
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	307 for width in ctxt.findall('dayWidth'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	308 width_type = width.attrib['type']
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	309 widths = ctxts.setdefault(width_type, {})
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	310 for elem in width.getiterator():
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	311 if elem.tag == 'day':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	312 dtype = weekdays[elem.attrib['type']]
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	313 if ('draft' in elem.attrib or 'alt' not in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	314 and dtype in widths:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	315 continue
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	316 widths[dtype] = unicode(elem.text)
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	317 elif elem.tag == 'alias':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	318 ctxts[width_type] = Alias(
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	319 _translate_alias(['days', ctxt_type, width_type],
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	320 elem.attrib['path'])
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	321 )
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	322
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	323 quarters = data.setdefault('quarters', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	324 for ctxt in calendar.findall('quarters/quarterContext'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	325 ctxt_type = ctxt.attrib['type']
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	326 ctxts = quarters.setdefault(ctxt.attrib['type'], {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	327 for width in ctxt.findall('quarterWidth'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	328 width_type = width.attrib['type']
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	329 widths = ctxts.setdefault(width_type, {})
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	330 for elem in width.getiterator():
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	331 if elem.tag == 'quarter':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	332 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	333 and int(elem.attrib['type']) in widths:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	334 continue
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	335 widths[int(elem.attrib['type'])] = unicode(elem.text)
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	336 elif elem.tag == 'alias':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	337 ctxts[width_type] = Alias(
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	338 _translate_alias(['quarters', ctxt_type, width_type],
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	339 elem.attrib['path'])
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	340 )
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	341
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	342 eras = data.setdefault('eras', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	343 for width in calendar.findall('eras/*'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	344 width_type = NAME_MAP[width.tag]
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	345 widths = eras.setdefault(width_type, {})
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	346 for elem in width.getiterator():
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	347 if elem.tag == 'era':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	348 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	349 and int(elem.attrib['type']) in widths:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	350 continue
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	351 widths[int(elem.attrib.get('type'))] = unicode(elem.text)
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	352 elif elem.tag == 'alias':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	353 eras[width_type] = Alias(
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	354 _translate_alias(['eras', width_type],
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	355 elem.attrib['path'])
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	356 )
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	357
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	358 # AM/PM
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	359 periods = data.setdefault('periods', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	360 for elem in calendar.findall('am'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	361 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	362 and elem.tag in periods:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	363 continue
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	364 periods[elem.tag] = unicode(elem.text)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	365 for elem in calendar.findall('pm'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	366 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	367 and elem.tag in periods:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	368 continue
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	369 periods[elem.tag] = unicode(elem.text)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	370
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	371 date_formats = data.setdefault('date_formats', {})
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	372 for format in calendar.findall('dateFormats'):
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	373 for elem in format.getiterator():
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	374 if elem.tag == 'dateFormatLength':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	375 if 'draft' in elem.attrib and \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	376 elem.attrib.get('type') in date_formats:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	377 continue
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	378 try:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	379 date_formats[elem.attrib.get('type')] = \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	380 dates.parse_pattern(unicode(elem.findtext('dateFormat/pattern')))
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	381 except ValueError, e:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	382 print>>sys.stderr, 'ERROR: %s' % e
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	383 elif elem.tag == 'alias':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	384 date_formats = Alias(_translate_alias(
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	385 ['date_formats'], elem.attrib['path'])
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	386 )
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	387
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	388 time_formats = data.setdefault('time_formats', {})
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	389 for format in calendar.findall('timeFormats'):
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	390 for elem in format.getiterator():
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	391 if elem.tag == 'timeFormatLength':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	392 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	393 and elem.attrib.get('type') in time_formats:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	394 continue
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	395 try:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	396 time_formats[elem.attrib.get('type')] = \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	397 dates.parse_pattern(unicode(elem.findtext('timeFormat/pattern')))
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	398 except ValueError, e:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	399 print>>sys.stderr, 'ERROR: %s' % e
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	400 elif elem.tag == 'alias':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	401 time_formats = Alias(_translate_alias(
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	402 ['time_formats'], elem.attrib['path'])
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	403 )
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	404
33 75a64f5a176e * Import datetime patterns from CLDR. cmlenz parents: 28 diff changeset	405 datetime_formats = data.setdefault('datetime_formats', {})
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	406 for format in calendar.findall('dateTimeFormats'):
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	407 for elem in format.getiterator():
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	408 if elem.tag == 'dateTimeFormatLength':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	409 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	410 and elem.attrib.get('type') in datetime_formats:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	411 continue
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	412 try:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	413 datetime_formats[elem.attrib.get('type')] = \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	414 unicode(elem.findtext('dateTimeFormat/pattern'))
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	415 except ValueError, e:
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	416 print>>sys.stderr, 'ERROR: %s' % e
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	417 elif elem.tag == 'alias':
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	418 datetime_formats = Alias(_translate_alias(
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	419 ['datetime_formats'], elem.attrib['path'])
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	420 )
33 75a64f5a176e * Import datetime patterns from CLDR. cmlenz parents: 28 diff changeset	421
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	422 # <numbers>
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	423
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	424 number_symbols = data.setdefault('number_symbols', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	425 for elem in tree.findall('//numbers/symbols/*'):
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	426 number_symbols[elem.tag] = unicode(elem.text)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	427
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	428 decimal_formats = data.setdefault('decimal_formats', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	429 for elem in tree.findall('//decimalFormats/decimalFormatLength'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	430 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	431 and elem.attrib.get('type') in decimal_formats:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	432 continue
26 6041782ea677 * Reduce size of locale data pickles by only storing the data provided by each locale itself, and merging inherited data at runtime. cmlenz parents: 22 diff changeset	433 pattern = unicode(elem.findtext('decimalFormat/pattern'))
6041782ea677 * Reduce size of locale data pickles by only storing the data provided by each locale itself, and merging inherited data at runtime. cmlenz parents: 22 diff changeset	434 decimal_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	435
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	436 scientific_formats = data.setdefault('scientific_formats', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	437 for elem in tree.findall('//scientificFormats/scientificFormatLength'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	438 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	439 and elem.attrib.get('type') in scientific_formats:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	440 continue
125 061ea0e0ac8c Add currency formatting. cmlenz parents: 65 diff changeset	441 pattern = unicode(elem.findtext('scientificFormat/pattern'))
061ea0e0ac8c Add currency formatting. cmlenz parents: 65 diff changeset	442 scientific_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	443
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	444 currency_formats = data.setdefault('currency_formats', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	445 for elem in tree.findall('//currencyFormats/currencyFormatLength'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	446 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	447 and elem.attrib.get('type') in currency_formats:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	448 continue
125 061ea0e0ac8c Add currency formatting. cmlenz parents: 65 diff changeset	449 pattern = unicode(elem.findtext('currencyFormat/pattern'))
061ea0e0ac8c Add currency formatting. cmlenz parents: 65 diff changeset	450 currency_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	451
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	452 percent_formats = data.setdefault('percent_formats', {})
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	453 for elem in tree.findall('//percentFormats/percentFormatLength'):
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	454 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	455 and elem.attrib.get('type') in percent_formats:
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	456 continue
26 6041782ea677 * Reduce size of locale data pickles by only storing the data provided by each locale itself, and merging inherited data at runtime. cmlenz parents: 22 diff changeset	457 pattern = unicode(elem.findtext('percentFormat/pattern'))
6041782ea677 * Reduce size of locale data pickles by only storing the data provided by each locale itself, and merging inherited data at runtime. cmlenz parents: 22 diff changeset	458 percent_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	459
26 6041782ea677 * Reduce size of locale data pickles by only storing the data provided by each locale itself, and merging inherited data at runtime. cmlenz parents: 22 diff changeset	460 currency_names = data.setdefault('currency_names', {})
6041782ea677 * Reduce size of locale data pickles by only storing the data provided by each locale itself, and merging inherited data at runtime. cmlenz parents: 22 diff changeset	461 currency_symbols = data.setdefault('currency_symbols', {})
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	462 for elem in tree.findall('//currencies/currency'):
385 38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	463 code = elem.attrib['type']
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	464 # TODO: support plural rules for currency name selection
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	465 for name in elem.findall('displayName'):
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	466 if ('draft' in name.attrib or 'count' in name.attrib) \
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	467 and code in currency_names:
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	468 continue
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	469 currency_names[code] = unicode(name.text)
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	470 # TODO: support choice patterns for currency symbol selection
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	471 symbol = elem.find('symbol')
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	472 if symbol is not None and 'draft' not in symbol.attrib \
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	473 and 'choice' not in symbol.attrib:
38db48990998 Improve CLDR import of currency-related data to ignore unsupported features such as symbol choice patterns and pluralized display names. See #93. cmlenz parents: 375 diff changeset	474 currency_symbols[code] = unicode(symbol.text)
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	475
390 c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	476 # <units>
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	477
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	478 unit_patterns = data.setdefault('unit_patterns', {})
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	479 for elem in tree.findall('//units/unit'):
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	480 unit_type = elem.attrib['type']
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	481 unit_pattern = unit_patterns.setdefault(unit_type, {})
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	482 for pattern in elem.findall('unitPattern'):
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	483 unit_patterns[unit_type][pattern.attrib['count']] = \
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	484 unicode(pattern.text)
c5bc0f6822a9 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	485
233 da97a3138239 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	486 outfile = open(os.path.join(destdir, 'localedata', stem + '.dat'), 'wb')
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	487 try:
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	488 pickle.dump(data, outfile, 2)
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	489 finally:
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	490 outfile.close()
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	491
375 4eca63af0a12 Implement support for aliases in the CLDR data. Closes #68. Also, update to CLDR 1.6, and a much improved `dump_data` script. cmlenz parents: 345 diff changeset	492
1 7870274479f5 Import of initial code base. cmlenz parents: diff changeset	493 if __name__ == '__main__':
7870274479f5 Import of initial code base. cmlenz parents: diff changeset	494 main()

Mercurial > babel > mirror

annotate scripts/import_cldr.py @ 395:a0457635279d trunk