babel/old/babel-test: scripts/import

annotate scripts/import_cldr.py @ 534:e8da49740876

catch exception if environment contains an invalid locale setting (fixes #200)

author	fschwarz
date	Fri, 11 Mar 2011 16:20:57 +0000
parents	bc5a9d30330a
children	423bb50cb8af

rev	line source
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	1 #!/usr/bin/env python
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	2 # -- coding: utf-8 --
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	3 #
529 bc5a9d30330a Bump the copyright. jruigrok parents: 528 diff changeset	4 # Copyright (C) 2007-2011 Edgewall Software
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	5 # All rights reserved.
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	6 #
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	7 # This software is licensed as described in the file COPYING, which
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	8 # you should have received as part of this distribution. The terms
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	9 # are also available at http://babel.edgewall.org/wiki/License.
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	10 #
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	11 # This software consists of voluntary contributions made by many
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	12 # individuals. For the exact contribution history, see the revision
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	13 # history and logs, available at http://babel.edgewall.org/log/.
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	14
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	15 from optparse import OptionParser
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	16 import os
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	17 import pickle
375 369300a7ebd3 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	18 import re
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	19 import sys
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	20 try:
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	21 from xml.etree.ElementTree import parse
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	22 except ImportError:
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	23 from elementtree.ElementTree import parse
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	24
65 7478d663561f Add Babel soruce path to CLDR import script automatically for asmodai ;-). cmlenz parents: 34 diff changeset	25 # Make sure we're using Babel source, and not some previously installed version
7478d663561f Add Babel soruce path to CLDR import script automatically for asmodai ;-). cmlenz parents: 34 diff changeset	26 sys.path.insert(0, os.path.join(os.path.dirname(sys.argv[0]), '..'))
7478d663561f Add Babel soruce path to CLDR import script automatically for asmodai ;-). cmlenz parents: 34 diff changeset	27
9 3be73c6f01f1 Add basic support for number format patterns. jonas parents: 8 diff changeset	28 from babel import dates, numbers
390 ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	29 from babel.plural import PluralRule
375 369300a7ebd3 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	30 from babel.localedata import Alias
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	31
15 76985c08a339 Minor date formatting improvements. cmlenz parents: 13 diff changeset	32 weekdays = {'mon': 0, 'tue': 1, 'wed': 2, 'thu': 3, 'fri': 4, 'sat': 5,
76985c08a339 Minor date formatting improvements. cmlenz parents: 13 diff changeset	33 'sun': 6}
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	34
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	35 try:
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	36 any
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	37 except NameError:
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	38 def any(iterable):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	39 return filter(None, list(iterable))
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	40
375 369300a7ebd3 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	41
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	42 def _text(elem):
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	43 buf = [elem.text or '']
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	44 for child in elem:
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	45 buf.append(_text(child))
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	46 buf.append(elem.tail or '')
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	47 return u''.join(filter(None, buf)).strip()
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	48
375 369300a7ebd3 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	49
369300a7ebd3 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 NAME_RE = re.compile(r"^\w+$")
369300a7ebd3 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 TYPE_ATTR_RE = re.compile(r"^\w+\[@type='(.*?)'\]$")
369300a7ebd3 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
369300a7ebd3 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 NAME_MAP = {
369300a7ebd3 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 'dateFormats': 'date_formats',
369300a7ebd3 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 'dateTimeFormats': 'datetime_formats',
369300a7ebd3 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 'eraAbbr': 'abbreviated',
369300a7ebd3 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 'eraNames': 'wide',
369300a7ebd3 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 'eraNarrow': 'narrow',
369300a7ebd3 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 'timeFormats': 'time_formats'
369300a7ebd3 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 }
369300a7ebd3 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
369300a7ebd3 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 def _translate_alias(ctxt, path):
369300a7ebd3 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 parts = path.split('/')
369300a7ebd3 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 keys = ctxt[:]
369300a7ebd3 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 for part in parts:
369300a7ebd3 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 if part == '..':
369300a7ebd3 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 keys.pop()
369300a7ebd3 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 else:
369300a7ebd3 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 match = TYPE_ATTR_RE.match(part)
369300a7ebd3 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 if match:
369300a7ebd3 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 keys.append(match.group(1))
369300a7ebd3 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 else:
369300a7ebd3 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 assert NAME_RE.match(part)
369300a7ebd3 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 keys.append(NAME_MAP.get(part, part))
369300a7ebd3 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 return keys
369300a7ebd3 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
369300a7ebd3 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
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	78 def main():
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	79 parser = OptionParser(usage='%prog path/to/cldr')
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	80 options, args = parser.parse_args()
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	81 if len(args) != 1:
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	82 parser.error('incorrect number of arguments')
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	83
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	84 srcdir = args[0]
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	85 destdir = os.path.join(os.path.dirname(os.path.abspath(sys.argv[0])),
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	86 '..', 'babel')
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	87
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	88 sup = parse(os.path.join(srcdir, 'supplemental', 'supplementalData.xml'))
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	89
345 64d340f76701 Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	90 # Import global data from the supplemental files
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	91 global_data = {}
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	92
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	93 territory_zones = global_data.setdefault('territory_zones', {})
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	94 zone_aliases = global_data.setdefault('zone_aliases', {})
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	95 zone_territories = global_data.setdefault('zone_territories', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	96 for elem in sup.findall('.//timezoneData/zoneFormatting/zoneItem'):
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	97 tzid = elem.attrib['type']
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	98 territory_zones.setdefault(elem.attrib['territory'], []).append(tzid)
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	99 zone_territories[tzid] = elem.attrib['territory']
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	100 if 'aliases' in elem.attrib:
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	101 for alias in elem.attrib['aliases'].split():
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	102 zone_aliases[alias] = tzid
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	103
345 64d340f76701 Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	104 # Import Metazone mapping
64d340f76701 Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	105 meta_zones = global_data.setdefault('meta_zones', {})
64d340f76701 Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	106 tzsup = parse(os.path.join(srcdir, 'supplemental', 'metazoneInfo.xml'))
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	107 for elem in tzsup.findall('.//timezone'):
345 64d340f76701 Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	108 for child in elem.findall('usesMetazone'):
64d340f76701 Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	109 if 'to' not in child.attrib: # FIXME: support old mappings
64d340f76701 Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	110 meta_zones[elem.attrib['type']] = child.attrib['mzone']
64d340f76701 Update to CLDR 1.5.1, which split out the metazone mappings into a separate supplemental file. cmlenz parents: 233 diff changeset	111
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	112 outfile = open(os.path.join(destdir, 'global.dat'), 'wb')
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	113 try:
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	114 pickle.dump(global_data, outfile, 2)
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	115 finally:
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	116 outfile.close()
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	117
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	118 # build a territory containment mapping for inheritance
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	119 regions = {}
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	120 for elem in sup.findall('.//territoryContainment/group'):
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	121 regions[elem.attrib['type']] = elem.attrib['contains'].split()
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	122
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	123 # Resolve territory containment
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	124 territory_containment = {}
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	125 region_items = regions.items()
9132c9218745 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.sort()
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	127 for group, territory_list in region_items:
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	128 for territory in territory_list:
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	129 containers = territory_containment.setdefault(territory, set([]))
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	130 if group in territory_containment:
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	131 containers \|= territory_containment[group]
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	132 containers.add(group)
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	133
390 ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	134 # prepare the per-locale plural rules definitions
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	135 plural_rules = {}
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	136 prsup = parse(os.path.join(srcdir, 'supplemental', 'plurals.xml'))
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	137 for elem in prsup.findall('.//plurals/pluralRules'):
390 ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	138 rules = []
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	139 for rule in elem.findall('pluralRule'):
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	140 rules.append((rule.attrib['count'], unicode(rule.text)))
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	141 pr = PluralRule(rules)
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	142 for locale in elem.attrib['locales'].split():
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	143 plural_rules[locale] = pr
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	144
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	145 filenames = os.listdir(os.path.join(srcdir, 'main'))
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	146 filenames.remove('root.xml')
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	147 filenames.sort(lambda a,b: len(a)-len(b))
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	148 filenames.insert(0, 'root.xml')
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	149
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	150 for filename in filenames:
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	151 stem, ext = os.path.splitext(filename)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	152 if ext != '.xml':
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	153 continue
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	154
385 cd8761c6f1a6 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	155 print>>sys.stderr, 'Processing input file %r' % filename
26 710090104678 * 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	156 tree = parse(os.path.join(srcdir, 'main', filename))
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	157 data = {}
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	158
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	159 language = None
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	160 elem = tree.find('.//identity/language')
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	161 if elem is not None:
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	162 language = elem.attrib['type']
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	163 print>>sys.stderr, ' Language: %r' % language
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	164
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	165 territory = None
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	166 elem = tree.find('.//identity/territory')
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	167 if elem is not None:
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	168 territory = elem.attrib['type']
13 b6c0de43fa40 Extended and documented `LazyProxy`. cmlenz parents: 9 diff changeset	169 else:
b6c0de43fa40 Extended and documented `LazyProxy`. cmlenz parents: 9 diff changeset	170 territory = '001' # world
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	171 print>>sys.stderr, ' Territory: %r' % territory
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	172 regions = territory_containment.get(territory, [])
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	173 print>>sys.stderr, ' Regions: %r' % regions
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	174
390 ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	175 # plural rules
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	176 locale_id = '_'.join(filter(None, [
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	177 language,
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	178 territory != '001' and territory or None
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	179 ]))
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	180 if locale_id in plural_rules:
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	181 data['plural_form'] = plural_rules[locale_id]
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	182
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	183 # <localeDisplayNames>
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	184
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	185 territories = data.setdefault('territories', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	186 for elem in tree.findall('.//territories/territory'):
375 369300a7ebd3 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	187 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and elem.attrib['type'] in territories:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	189 continue
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	190 territories[elem.attrib['type']] = _text(elem)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	191
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	192 languages = data.setdefault('languages', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	193 for elem in tree.findall('.//languages/language'):
375 369300a7ebd3 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	194 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and elem.attrib['type'] in languages:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	196 continue
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	197 languages[elem.attrib['type']] = _text(elem)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	198
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	199 variants = data.setdefault('variants', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	200 for elem in tree.findall('.//variants/variant'):
375 369300a7ebd3 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	201 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and elem.attrib['type'] in variants:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	203 continue
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	204 variants[elem.attrib['type']] = _text(elem)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	205
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	206 scripts = data.setdefault('scripts', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	207 for elem in tree.findall('.//scripts/script'):
375 369300a7ebd3 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	208 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and elem.attrib['type'] in scripts:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	210 continue
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	211 scripts[elem.attrib['type']] = _text(elem)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	212
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	213 # <dates>
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	214
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	215 week_data = data.setdefault('week_data', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	216 supelem = sup.find('.//weekData')
8 9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	217
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	218 for elem in supelem.findall('minDays'):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	219 territories = elem.attrib['territories'].split()
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	220 if territory in territories or any([r in territories for r in regions]):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	221 week_data['min_days'] = int(elem.attrib['count'])
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	222
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	223 for elem in supelem.findall('firstDay'):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	224 territories = elem.attrib['territories'].split()
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	225 if territory in territories or any([r in territories for r in regions]):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	226 week_data['first_day'] = weekdays[elem.attrib['day']]
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	227
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	228 for elem in supelem.findall('weekendStart'):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	229 territories = elem.attrib['territories'].split()
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	230 if territory in territories or any([r in territories for r in regions]):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	231 week_data['weekend_start'] = weekdays[elem.attrib['day']]
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	232
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	233 for elem in supelem.findall('weekendEnd'):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	234 territories = elem.attrib['territories'].split()
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	235 if territory in territories or any([r in territories for r in regions]):
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	236 week_data['weekend_end'] = weekdays[elem.attrib['day']]
9132c9218745 Pull in some supplemental data from the CLDR, for things like the first day of the week. cmlenz parents: 1 diff changeset	237
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	238 zone_formats = data.setdefault('zone_formats', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	239 for elem in tree.findall('.//timeZoneNames/gmtFormat'):
375 369300a7ebd3 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	240 if 'draft' not in elem.attrib and 'alt' not in elem.attrib:
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	241 zone_formats['gmt'] = unicode(elem.text).replace('{0}', '%s')
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	242 break
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	243 for elem in tree.findall('.//timeZoneNames/regionFormat'):
375 369300a7ebd3 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	244 if 'draft' not in elem.attrib and 'alt' not in elem.attrib:
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	245 zone_formats['region'] = unicode(elem.text).replace('{0}', '%s')
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	246 break
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	247 for elem in tree.findall('.//timeZoneNames/fallbackFormat'):
375 369300a7ebd3 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	248 if 'draft' not in elem.attrib and 'alt' not in elem.attrib:
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	249 zone_formats['fallback'] = unicode(elem.text) \
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	250 .replace('{0}', '%(0)s').replace('{1}', '%(1)s')
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	251 break
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	252
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	253 time_zones = data.setdefault('time_zones', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	254 for elem in tree.findall('.//timeZoneNames/zone'):
28 11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	255 info = {}
11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	256 city = elem.findtext('exemplarCity')
11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	257 if city:
11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	258 info['city'] = unicode(city)
11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	259 for child in elem.findall('long/*'):
11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	260 info.setdefault('long', {})[child.tag] = unicode(child.text)
11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	261 for child in elem.findall('short/*'):
11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	262 info.setdefault('short', {})[child.tag] = unicode(child.text)
11278622ede9 Import basic timezone info from CLDR (see #3). Still missing a couple other pieces in the puzzle. cmlenz parents: 26 diff changeset	263 time_zones[elem.attrib['type']] = info
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	264
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	265 meta_zones = data.setdefault('meta_zones', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	266 for elem in tree.findall('.//timeZoneNames/metazone'):
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	267 info = {}
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	268 city = elem.findtext('exemplarCity')
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	269 if city:
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	270 info['city'] = unicode(city)
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	271 for child in elem.findall('long/*'):
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	272 info.setdefault('long', {})[child.tag] = unicode(child.text)
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	273 for child in elem.findall('short/*'):
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	274 info.setdefault('short', {})[child.tag] = unicode(child.text)
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	275 info['common'] = elem.findtext('commonlyUsed') == 'true'
bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	276 meta_zones[elem.attrib['type']] = info
34 3666f3d3df15 Extended time-zone support. cmlenz parents: 33 diff changeset	277
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	278 for calendar in tree.findall('.//calendars/calendar'):
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	279 if calendar.attrib['type'] != 'gregorian':
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	280 # TODO: support other calendar types
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	281 continue
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	282
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	283 months = data.setdefault('months', {})
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	284 for ctxt in calendar.findall('months/monthContext'):
375 369300a7ebd3 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	285 ctxt_type = ctxt.attrib['type']
369300a7ebd3 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 ctxts = months.setdefault(ctxt_type, {})
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	287 for width in ctxt.findall('monthWidth'):
375 369300a7ebd3 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	288 width_type = width.attrib['type']
369300a7ebd3 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 widths = ctxts.setdefault(width_type, {})
369300a7ebd3 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 for elem in width.getiterator():
369300a7ebd3 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 if elem.tag == 'month':
369300a7ebd3 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 ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and int(elem.attrib['type']) in widths:
369300a7ebd3 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 continue
369300a7ebd3 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 widths[int(elem.attrib.get('type'))] = unicode(elem.text)
369300a7ebd3 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 elif elem.tag == 'alias':
369300a7ebd3 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 ctxts[width_type] = Alias(
369300a7ebd3 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 _translate_alias(['months', ctxt_type, width_type],
369300a7ebd3 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 elem.attrib['path'])
369300a7ebd3 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 )
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	301
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	302 days = data.setdefault('days', {})
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	303 for ctxt in calendar.findall('days/dayContext'):
375 369300a7ebd3 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	304 ctxt_type = ctxt.attrib['type']
369300a7ebd3 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 ctxts = days.setdefault(ctxt_type, {})
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	306 for width in ctxt.findall('dayWidth'):
375 369300a7ebd3 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	307 width_type = width.attrib['type']
369300a7ebd3 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 widths = ctxts.setdefault(width_type, {})
369300a7ebd3 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 for elem in width.getiterator():
369300a7ebd3 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 if elem.tag == 'day':
369300a7ebd3 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 dtype = weekdays[elem.attrib['type']]
369300a7ebd3 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 if ('draft' in elem.attrib or 'alt' not in elem.attrib) \
369300a7ebd3 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 and dtype in widths:
369300a7ebd3 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 continue
369300a7ebd3 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 widths[dtype] = unicode(elem.text)
369300a7ebd3 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 elif elem.tag == 'alias':
369300a7ebd3 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 ctxts[width_type] = Alias(
369300a7ebd3 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 _translate_alias(['days', ctxt_type, width_type],
369300a7ebd3 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 elem.attrib['path'])
369300a7ebd3 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 )
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	321
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	322 quarters = data.setdefault('quarters', {})
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	323 for ctxt in calendar.findall('quarters/quarterContext'):
375 369300a7ebd3 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	324 ctxt_type = ctxt.attrib['type']
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	325 ctxts = quarters.setdefault(ctxt.attrib['type'], {})
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	326 for width in ctxt.findall('quarterWidth'):
375 369300a7ebd3 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	327 width_type = width.attrib['type']
369300a7ebd3 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 widths = ctxts.setdefault(width_type, {})
369300a7ebd3 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 for elem in width.getiterator():
369300a7ebd3 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 if elem.tag == 'quarter':
369300a7ebd3 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 ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and int(elem.attrib['type']) in widths:
369300a7ebd3 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 continue
369300a7ebd3 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 widths[int(elem.attrib['type'])] = unicode(elem.text)
369300a7ebd3 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 elif elem.tag == 'alias':
369300a7ebd3 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 ctxts[width_type] = Alias(
369300a7ebd3 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 _translate_alias(['quarters', ctxt_type, width_type],
369300a7ebd3 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 elem.attrib['path'])
369300a7ebd3 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 )
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	340
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	341 eras = data.setdefault('eras', {})
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	342 for width in calendar.findall('eras/*'):
375 369300a7ebd3 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	343 width_type = NAME_MAP[width.tag]
369300a7ebd3 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 widths = eras.setdefault(width_type, {})
369300a7ebd3 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 for elem in width.getiterator():
369300a7ebd3 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 if elem.tag == 'era':
369300a7ebd3 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 ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and int(elem.attrib['type']) in widths:
369300a7ebd3 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 continue
369300a7ebd3 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 widths[int(elem.attrib.get('type'))] = unicode(elem.text)
369300a7ebd3 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 elif elem.tag == 'alias':
369300a7ebd3 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 eras[width_type] = Alias(
369300a7ebd3 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 _translate_alias(['eras', width_type],
369300a7ebd3 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 elem.attrib['path'])
369300a7ebd3 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 )
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	356
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	357 # AM/PM
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	358 periods = data.setdefault('periods', {})
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	359 for elem in calendar.findall('am'):
375 369300a7ebd3 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	360 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and elem.tag in periods:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	362 continue
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	363 periods[elem.tag] = unicode(elem.text)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	364 for elem in calendar.findall('pm'):
375 369300a7ebd3 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	365 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and elem.tag in periods:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	367 continue
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	368 periods[elem.tag] = unicode(elem.text)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	369
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	370 date_formats = data.setdefault('date_formats', {})
375 369300a7ebd3 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	371 for format in calendar.findall('dateFormats'):
369300a7ebd3 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 elem in format.getiterator():
369300a7ebd3 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 if elem.tag == 'dateFormatLength':
369300a7ebd3 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 'draft' in elem.attrib and \
369300a7ebd3 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 elem.attrib.get('type') in date_formats:
369300a7ebd3 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 continue
369300a7ebd3 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 try:
369300a7ebd3 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 date_formats[elem.attrib.get('type')] = \
369300a7ebd3 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 dates.parse_pattern(unicode(elem.findtext('dateFormat/pattern')))
369300a7ebd3 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 except ValueError, e:
369300a7ebd3 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 print>>sys.stderr, 'ERROR: %s' % e
369300a7ebd3 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 elif elem.tag == 'alias':
369300a7ebd3 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 date_formats = Alias(_translate_alias(
369300a7ebd3 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'], elem.attrib['path'])
369300a7ebd3 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 )
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	386
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	387 time_formats = data.setdefault('time_formats', {})
375 369300a7ebd3 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	388 for format in calendar.findall('timeFormats'):
369300a7ebd3 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 elem in format.getiterator():
369300a7ebd3 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 if elem.tag == 'timeFormatLength':
369300a7ebd3 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 ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and elem.attrib.get('type') in time_formats:
369300a7ebd3 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 continue
369300a7ebd3 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 try:
369300a7ebd3 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 time_formats[elem.attrib.get('type')] = \
369300a7ebd3 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 dates.parse_pattern(unicode(elem.findtext('timeFormat/pattern')))
369300a7ebd3 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 except ValueError, e:
369300a7ebd3 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 print>>sys.stderr, 'ERROR: %s' % e
369300a7ebd3 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 elif elem.tag == 'alias':
369300a7ebd3 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 time_formats = Alias(_translate_alias(
369300a7ebd3 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'], elem.attrib['path'])
369300a7ebd3 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 )
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	403
33 0740b6d31799 * Import datetime patterns from CLDR. cmlenz parents: 28 diff changeset	404 datetime_formats = data.setdefault('datetime_formats', {})
375 369300a7ebd3 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	405 for format in calendar.findall('dateTimeFormats'):
369300a7ebd3 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 elem in format.getiterator():
369300a7ebd3 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 if elem.tag == 'dateTimeFormatLength':
369300a7ebd3 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 ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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 and elem.attrib.get('type') in datetime_formats:
369300a7ebd3 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 continue
369300a7ebd3 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 try:
369300a7ebd3 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 datetime_formats[elem.attrib.get('type')] = \
369300a7ebd3 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 unicode(elem.findtext('dateTimeFormat/pattern'))
369300a7ebd3 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 except ValueError, e:
369300a7ebd3 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 print>>sys.stderr, 'ERROR: %s' % e
369300a7ebd3 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 elif elem.tag == 'alias':
369300a7ebd3 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 datetime_formats = Alias(_translate_alias(
369300a7ebd3 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'], elem.attrib['path'])
369300a7ebd3 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 )
33 0740b6d31799 * Import datetime patterns from CLDR. cmlenz parents: 28 diff changeset	420
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	421 # <numbers>
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	422
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	423 number_symbols = data.setdefault('number_symbols', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	424 for elem in tree.findall('.//numbers/symbols/*'):
436 fd01923aaf1e Fix the import script to skip alt or draft items in the numbers/symbols jruigrok parents: 415 diff changeset	425 if ('draft' in elem.attrib or 'alt' in elem.attrib):
fd01923aaf1e Fix the import script to skip alt or draft items in the numbers/symbols jruigrok parents: 415 diff changeset	426 continue
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	427 number_symbols[elem.tag] = unicode(elem.text)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	428
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	429 decimal_formats = data.setdefault('decimal_formats', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	430 for elem in tree.findall('.//decimalFormats/decimalFormatLength'):
375 369300a7ebd3 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 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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	432 and elem.attrib.get('type') in decimal_formats:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	433 continue
26 710090104678 * 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 pattern = unicode(elem.findtext('decimalFormat/pattern'))
710090104678 * 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	435 decimal_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	436
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	437 scientific_formats = data.setdefault('scientific_formats', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	438 for elem in tree.findall('.//scientificFormats/scientificFormatLength'):
375 369300a7ebd3 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 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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	440 and elem.attrib.get('type') in scientific_formats:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	441 continue
125 b75ae5def3b1 Add currency formatting. cmlenz parents: 65 diff changeset	442 pattern = unicode(elem.findtext('scientificFormat/pattern'))
b75ae5def3b1 Add currency formatting. cmlenz parents: 65 diff changeset	443 scientific_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	444
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	445 currency_formats = data.setdefault('currency_formats', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	446 for elem in tree.findall('.//currencyFormats/currencyFormatLength'):
375 369300a7ebd3 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 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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	448 and elem.attrib.get('type') in currency_formats:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	449 continue
125 b75ae5def3b1 Add currency formatting. cmlenz parents: 65 diff changeset	450 pattern = unicode(elem.findtext('currencyFormat/pattern'))
b75ae5def3b1 Add currency formatting. cmlenz parents: 65 diff changeset	451 currency_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	452
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	453 percent_formats = data.setdefault('percent_formats', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	454 for elem in tree.findall('.//percentFormats/percentFormatLength'):
375 369300a7ebd3 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 if ('draft' in elem.attrib or 'alt' in elem.attrib) \
369300a7ebd3 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	456 and elem.attrib.get('type') in percent_formats:
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	457 continue
26 710090104678 * 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 pattern = unicode(elem.findtext('percentFormat/pattern'))
710090104678 * 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	459 percent_formats[elem.attrib.get('type')] = numbers.parse_pattern(pattern)
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	460
26 710090104678 * 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_names = data.setdefault('currency_names', {})
710090104678 * 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	462 currency_symbols = data.setdefault('currency_symbols', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	463 for elem in tree.findall('.//currencies/currency'):
385 cd8761c6f1a6 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 code = elem.attrib['type']
cd8761c6f1a6 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 # TODO: support plural rules for currency name selection
cd8761c6f1a6 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 for name in elem.findall('displayName'):
cd8761c6f1a6 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 if ('draft' in name.attrib or 'count' in name.attrib) \
cd8761c6f1a6 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 and code in currency_names:
cd8761c6f1a6 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 continue
cd8761c6f1a6 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 currency_names[code] = unicode(name.text)
cd8761c6f1a6 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 # TODO: support choice patterns for currency symbol selection
cd8761c6f1a6 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 symbol = elem.find('symbol')
cd8761c6f1a6 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 if symbol is not None and 'draft' not in symbol.attrib \
cd8761c6f1a6 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 and 'choice' not in symbol.attrib:
cd8761c6f1a6 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	475 currency_symbols[code] = unicode(symbol.text)
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	476
390 ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	477 # <units>
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	478
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	479 unit_patterns = data.setdefault('unit_patterns', {})
467 0228ac359f84 Fix the ElementTree find()/findall() syntax to be compatible with Python 2.7. jruigrok parents: 436 diff changeset	480 for elem in tree.findall('.//units/unit'):
390 ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	481 unit_type = elem.attrib['type']
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	482 unit_pattern = unit_patterns.setdefault(unit_type, {})
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	483 for pattern in elem.findall('unitPattern'):
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	484 unit_patterns[unit_type][pattern.attrib['count']] = \
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	485 unicode(pattern.text)
ecf110e7f604 Preliminary support for timedelta formatting (see #126), and import/expose the locale plural rules from the CLDR. cmlenz parents: 385 diff changeset	486
233 bc22f5aef216 Upgraded to CLDR 1.5 and improved timezone formatting. cmlenz parents: 125 diff changeset	487 outfile = open(os.path.join(destdir, 'localedata', stem + '.dat'), 'wb')
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	488 try:
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	489 pickle.dump(data, outfile, 2)
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	490 finally:
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	491 outfile.close()
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	492
375 369300a7ebd3 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	493
1 f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	494 if __name__ == '__main__':
f71ca60f2a4a Import of initial code base. cmlenz parents: diff changeset	495 main()

Mercurial > babel > old > babel-test

annotate scripts/import_cldr.py @ 534:e8da49740876