Index: localeTools.py |
=================================================================== |
--- a/localeTools.py |
+++ b/localeTools.py |
@@ -5,21 +5,85 @@ |
# http://mozilla.org/MPL/2.0/. |
import re, os, sys, codecs, json, urllib, urllib2 |
from StringIO import StringIO |
from ConfigParser import SafeConfigParser |
from zipfile import ZipFile |
from xml.parsers.expat import ParserCreate, XML_PARAM_ENTITY_PARSING_ALWAYS |
-langMapping = { |
+langMappingGecko = { |
'dsb': 'dsb-DE', |
'hsb': 'hsb-DE', |
} |
+langMappingChrome = { |
+ 'es-419': 'es-AR', |
+ 'es': 'es-ES', |
+ 'sv': 'sv-SE', |
+ 'ml': 'ml-IN', |
+ 'nb': 'no', |
+} |
+ |
+chromeLocales = [ |
+ "am", |
+ "ar", |
+ "bg", |
+ "bn", |
+ "ca", |
+ "cs", |
+ "da", |
+ "de", |
+ "el", |
+ "en-GB", |
+ "en-US", |
+ "es-419", |
+ "es", |
+ "et", |
+ "fa", |
+ "fi", |
+ "fil", |
+ "fr", |
+ "gu", |
+ "he", |
+ "hi", |
+ "hr", |
+ "hu", |
+ "id", |
+ "it", |
+ "ja", |
+ "kn", |
+ "ko", |
+ "lt", |
+ "lv", |
+ "ml", |
+ "mr", |
+ "ms", |
+ "nb", |
+ "nl", |
+ "pl", |
+ "pt-BR", |
+ "pt-PT", |
+ "ro", |
+ "ru", |
+ "sk", |
+ "sl", |
+ "sr", |
+ "sv", |
+ "sw", |
+ "ta", |
+ "te", |
+ "th", |
+ "tr", |
+ "uk", |
+ "vi", |
+ "zh-CN", |
+ "zh-TW", |
+] |
+ |
class OrderedDict(dict): |
def __init__(self): |
self.__order = [] |
def __setitem__(self, key, value): |
self.__order.append(key) |
dict.__setitem__(self, key, value) |
def iteritems(self): |
done = set() |
@@ -29,16 +93,20 @@ class OrderedDict(dict): |
done.add(key) |
def escapeEntity(value): |
return value.replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"') |
def unescapeEntity(value): |
return value.replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"') |
+def mapLocale(type, locale): |
+ mapping = langMappingChrome if type == 'chrome' else langMappingGecko |
+ return mapping.get(locale, locale) |
+ |
def parseDTDString(data, path): |
result = [] |
currentComment = [None] |
parser = ParserCreate() |
parser.UseForeignDTD(True) |
parser.SetParamEntityParsing(XML_PARAM_ENTITY_PARSING_ALWAYS) |
@@ -140,104 +208,168 @@ def toJSON(path): |
result = OrderedDict() |
for name, comment, value in it: |
obj = {'message': value} |
if comment == None: |
obj['description'] = name |
else: |
obj['description'] = '%s: %s' % (name, comment) |
result[name] = obj |
- return json.dumps(result, indent=2) |
+ return json.dumps(result, ensure_ascii=False, indent=2) |
def fromJSON(path, data): |
data = json.loads(data) |
if not data: |
if os.path.exists(path): |
os.remove(path) |
return |
dir = os.path.dirname(path) |
if not os.path.exists(dir): |
os.makedirs(dir) |
file = codecs.open(path, 'wb', encoding='utf-8') |
for key, value in data.iteritems(): |
file.write(generateStringEntry(key, value['message'], path)) |
file.close() |
-def setupTranslations(locales, projectName, key): |
+def preprocessChromeLocale(path, metadata, isMaster): |
+ fileHandle = codecs.open(path, 'rb', encoding='utf-8') |
+ data = json.load(fileHandle) |
+ fileHandle.close() |
+ |
+ # Remove synced keys, these don't need to be translated |
+ if metadata.has_section('locale_sync'): |
+ for file, stringIDs in metadata.items('locale_sync'): |
+ for stringID in re.split(r'\s+', stringIDs): |
+ if file == 'remove': |
+ key = stringID |
+ else: |
+ key = re.sub(r'\..*', '', file) + '_' + re.sub(r'\W', '_', stringID) |
+ if key in data: |
+ del data[key] |
+ |
+ for key, value in data.iteritems(): |
+ if isMaster: |
+ # Make sure the key name is listed in the description |
+ if "description" in value: |
+ value["description"] = "%s: %s" % (key, value["description"]) |
+ else: |
+ value["description"] = key |
+ else: |
+ # Delete description from translations |
+ if "description" in value: |
+ del value["description"] |
+ |
+ return json.dumps(data, ensure_ascii=False, sort_keys=True, indent=2) |
+ |
+def setupTranslations(type, locales, projectName, key): |
+ # Copy locales list, we don't want to change the parameter |
locales = set(locales) |
- firefoxLocales = urllib2.urlopen('http://www.mozilla.org/en-US/firefox/all.html').read() |
- for match in re.finditer(r'&lang=([\w\-]+)"', firefoxLocales): |
- locales.add(langMapping.get(match.group(1), match.group(1))) |
- langPacks = urllib2.urlopen('https://addons.mozilla.org/en-US/firefox/language-tools/').read() |
- for match in re.finditer(r'<tr>.*?</tr>', langPacks, re.S): |
- if match.group(0).find('Install Language Pack') >= 0: |
- match2 = re.search(r'lang="([\w\-]+)"', match.group(0)) |
- if match2: |
- locales.add(langMapping.get(match2.group(1), match2.group(1))) |
+ |
+ # Fill up with locales that we don't have but the browser supports |
+ if type == 'chrome': |
+ for locale in chromeLocales: |
+ locales.add(locale) |
+ else: |
+ firefoxLocales = urllib2.urlopen('http://www.mozilla.org/en-US/firefox/all.html').read() |
+ for match in re.finditer(r'&lang=([\w\-]+)"', firefoxLocales): |
+ locales.add(mapLocale(type, match.group(1))) |
+ langPacks = urllib2.urlopen('https://addons.mozilla.org/en-US/firefox/language-tools/').read() |
+ for match in re.finditer(r'<tr>.*?</tr>', langPacks, re.S): |
+ if match.group(0).find('Install Language Pack') >= 0: |
+ match2 = re.search(r'lang="([\w\-]+)"', match.group(0)) |
+ if match2: |
+ locales.add(mapLocale(type, match2.group(1))) |
+ |
+ # Convert locale codes to the ones that Crowdin will understand |
+ locales = set(map(lambda locale: mapLocale(type, locale), locales)) |
allowed = set() |
allowedLocales = urllib2.urlopen('http://crowdin.net/page/language-codes').read() |
for match in re.finditer(r'<tr>\s*<td>([\w\-]+)</td>', allowedLocales, re.S): |
allowed.add(match.group(1)) |
if not allowed.issuperset(locales): |
print 'Warning, following locales aren\'t allowed by server: ' + ', '.join(locales - allowed) |
locales = list(locales & allowed) |
locales.sort() |
params = urllib.urlencode([('languages[]', locale) for locale in locales]) |
result = urllib2.urlopen('http://api.crowdin.net/api/project/%s/edit-project?key=%s&%s' % (projectName, key, params)).read() |
if result.find('<success') < 0: |
raise Exception('Server indicated that the operation was not successful\n' + result) |
-def updateTranslationMaster(dir, locale, projectName, key): |
+def postFiles(files, url): |
+ boundary = '----------ThIs_Is_tHe_bouNdaRY_$' |
+ body = '' |
+ for file, data in files: |
+ body += '--%s\r\n' % boundary |
+ body += 'Content-Disposition: form-data; name="files[%s]"; filename="%s"\r\n' % (file, file) |
+ body += 'Content-Type: application/octet-stream\r\n' |
+ body += 'Content-Transfer-Encoding: binary\r\n' |
+ body += '\r\n' + data + '\r\n' |
+ body += '--%s--\r\n' % boundary |
+ |
+ body = body.encode('utf-8') |
+ request = urllib2.Request(url, StringIO(body)) |
+ request.add_header('Content-Type', 'multipart/form-data; boundary=%s' % boundary) |
+ request.add_header('Content-Length', len(body)) |
+ result = urllib2.urlopen(request).read() |
+ if result.find('<success') < 0: |
+ raise Exception('Server indicated that the operation was not successful\n' + result) |
+ |
+def updateTranslationMaster(type, metadata, dir, projectName, key): |
result = json.load(urllib2.urlopen('http://api.crowdin.net/api/project/%s/info?key=%s&json=1' % (projectName, key))) |
existing = set(map(lambda f: f['name'], result['files'])) |
add = [] |
update = [] |
for file in os.listdir(dir): |
path = os.path.join(dir, file) |
if os.path.isfile(path): |
- data = toJSON(path) |
+ if type == 'chrome': |
+ data = preprocessChromeLocale(path, metadata, True) |
+ newName = file |
+ else: |
+ data = toJSON(path) |
+ newName = file + '.json' |
+ |
if data: |
- newName = file + '.json' |
if newName in existing: |
update.append((newName, data)) |
existing.remove(newName) |
else: |
add.append((newName, data)) |
- def postFiles(files, url): |
- boundary = '----------ThIs_Is_tHe_bouNdaRY_$' |
- body = '' |
- for file, data in files: |
- body += '--%s\r\n' % boundary |
- body += 'Content-Disposition: form-data; name="files[%s]"; filename="%s"\r\n' % (file, file) |
- body += 'Content-Type: application/octet-stream\r\n' |
- body += '\r\n' + data.encode('utf-8') + '\r\n' |
- body += '--%s--\r\n' % boundary |
- |
- request = urllib2.Request(url, body) |
- request.add_header('Content-Type', 'multipart/form-data; boundary=%s' % boundary) |
- request.add_header('Content-Length', len(body)) |
- result = urllib2.urlopen(request).read() |
- if result.find('<success') < 0: |
- raise Exception('Server indicated that the operation was not successful\n' + result) |
- |
if len(add): |
titles = urllib.urlencode([('titles[%s]' % name, re.sub(r'\.json', '', name)) for name, data in add]) |
postFiles(add, 'http://api.crowdin.net/api/project/%s/add-file?key=%s&type=chrome&%s' % (projectName, key, titles)) |
if len(update): |
postFiles(update, 'http://api.crowdin.net/api/project/%s/update-file?key=%s' % (projectName, key)) |
for file in existing: |
result = urllib2.urlopen('http://api.crowdin.net/api/project/%s/delete-file?key=%s&file=%s' % (projectName, key, file)).read() |
if result.find('<success') < 0: |
raise Exception('Server indicated that the operation was not successful\n' + result) |
+def uploadTranslations(type, metadata, dir, locale, projectName, key): |
+ files = [] |
+ for file in os.listdir(dir): |
+ path = os.path.join(dir, file) |
+ if os.path.isfile(path): |
+ if type == 'chrome': |
+ data = preprocessChromeLocale(path, metadata, False) |
+ newName = file |
+ else: |
+ data = toJSON(path) |
+ newName = file + '.json' |
+ |
+ if data: |
+ files.append((newName, data)) |
+ if len(files): |
+ postFiles(files, 'http://api.crowdin.net/api/project/%s/upload-translation?key=%s&language=%s' % (projectName, key, mapLocale(type, locale))) |
+ |
def getTranslations(localesDir, defaultLocale, projectName, key): |
result = urllib2.urlopen('http://api.crowdin.net/api/project/%s/export?key=%s' % (projectName, key)).read() |
if result.find('<success') < 0: |
raise Exception('Server indicated that the operation was not successful\n' + result) |
result = urllib2.urlopen('http://api.crowdin.net/api/project/%s/download/all.zip?key=%s' % (projectName, key)).read() |
zip = ZipFile(StringIO(result)) |
dirs = {} |
@@ -245,17 +377,17 @@ def getTranslations(localesDir, defaultL |
if not info.filename.endswith('.dtd.json') and not info.filename.endswith('.properties.json'): |
continue |
dir, file = os.path.split(info.filename) |
origFile = re.sub(r'\.json$', '', file) |
if not re.match(r'^[\w\-]+$', dir) or dir == defaultLocale: |
continue |
- for key, value in langMapping.iteritems(): |
+ for key, value in langMappingGecko.iteritems(): |
if value == dir: |
dir = key |
if not dir in dirs: |
dirs[dir] = set() |
dirs[dir].add(origFile) |
data = zip.open(info.filename).read() |