├── README.md
├── all-lang-code.txt
├── strings.xml
├── translated
    ├── values-af
    │   └── strings.xml
    ├── values-ak
    │   └── strings.xml
    └── values-sq
    │   └── strings.xml
└── translator.py


/README.md:
--------------------------------------------------------------------------------
 1 | # android-localization-helper
 2 | A python script that helps you create strings.xml for all languages in different hierarchical folder(using Google Translation API)
 3 | 
 4 | # usage
 5 | 
 6 | Syntax
 7 | 
 8 | ```
 9 | python3.7 translator.py <source_lang_code> <string_file_name>
10 | ```
11 | 
12 | Eg,
13 | ```
14 | python3.7 translator.py en strings.xml
15 | ```
16 | 
17 | Output will be created in transalted/ folder with various langugaes folders.
18 | 
19 | Paste them in your res/ folder of Android Project.
20 | 
21 | # credits
22 | 
23 | Combined effort from below repositories + Some Add Ons 
24 | 
25 | https://github.com/Ra-Na/GTranslate-strings-xml
26 | 
27 | https://github.com/Swisyn/android-strings.xml-translator
28 | 
29 | 
30 | # other useful commands
31 | 
32 | Extract only strings from strings.xml
33 | cut -d ">" -f2 strings.xml | cut -d "<" -f1
34 | 
35 | Extract non translatable strings from strings.xml
36 | cat strings.xml|grep -v "translatable" | cut -d ">" -f2  | cut -d "<" -f1
37 | 
38 | 
39 | 


--------------------------------------------------------------------------------
/all-lang-code.txt:
--------------------------------------------------------------------------------
1 | "af", "ak", "sq", "am", "ar", "hy", "az", "eu", "be", "bem", "bn", "bh", "xx-bork", "bs", "br", "bg", "km", "ca", "chr", "ny", "zh-CN", "zh-TW", "co", "hr", "cs", "da", "nl", "xx-elmer", "en", "eo", "et", "ee", "fo", "tl", "fi", "fr", "fy", "gaa", "gl", "ka", "de", "el", "gn", "gu", "xx-hacker", "ht", "ha", "haw", "iw", "hi", "hu", "is", "ig", "id", "ia", "ga", "it", "ja", "jw", "kn", "kk", "rw", "rn", "xx-klingon", "kg", "ko", "kri", "ku", "ckb", "ky", "lo", "la", "lv", "ln", "lt", "loz", "lg", "ach", "mk", "mg", "ms", "ml", "mt", "mi", "mr", "mfe", "mo", "mn", "sr-ME", "ne", "pcm", "nso", "no", "nn", "oc", "or", "om", "ps", "fa", "xx-pirate", "pl", "pt-BR", "pt-PT", "pa", "qu", "ro", "rm", "nyn", "ru", "gd", "sr", "sh", "st", "tn", "crs", "sn", "sd", "si", "sk", "sl", "so", "es", "es-419", "su", "sw", "sv", "tg", "ta", "tt", "te", "th", "ti", "to", "lua", "tum", "tr", "tk", "tw", "ug", "uk", "ur", "uz", "vi", "cy", "wo", "xh", "yi", "yo", "zu"
2 | 


--------------------------------------------------------------------------------
/strings.xml:
--------------------------------------------------------------------------------
 1 | <resources>
 2 |     <string name="hellow">Hello cruel world! </string>
 3 |     <string name="mailtodeveloper">Mail to developer</string>
 4 |     <string name="userisgoat">Tap on checkboxes to select items.</string>
 5 |     <string name="btn_search">Search</string> 
 6 |     <string name="radio_design_ideas">Search in Design Ideas</string> 
 7 |     <string-array name="search_title"> 
 8 | 		<item>What can I search for?</item> 
 9 | 		<item>Do I have to have an account to search and view information?</item> 
10 | 		<item>How do I search for products shown in a design?</item> 
11 | 	</string-array>
12 | </resources>
13 | 


--------------------------------------------------------------------------------
/translated/values-af/strings.xml:
--------------------------------------------------------------------------------
 1 | <resources>
 2 |     <string name="hellow">Hallo wrede wêreld!</string>
 3 |     <string name="mailtodeveloper">Pos na ontwikkelaar</string>
 4 |     <string name="userisgoat">Tik op blokkies om items te kies.</string>
 5 |     <string name="btn_search">Soek</string> 
 6 |     <string name="radio_design_ideas">Soek in Ontwerp Idees</string> 
 7 |     <string-array name="search_title"> 
 8 | 		<item>Waarvoor kan ek soek?</item> 
 9 | 		<item>Moet ek 'n rekening hê om inligting te soek en te sien?</item> 
10 | 		<item>Hoe soek ek produkte wat in 'n ontwerp vertoon word?</item> 
11 | 	</string-array>
12 | </resources>


--------------------------------------------------------------------------------
/translated/values-ak/strings.xml:
--------------------------------------------------------------------------------
 1 | <resources>
 2 |     <string name="hellow">Hello cruel world! </string>
 3 |     <string name="mailtodeveloper">Mail to developer</string>
 4 |     <string name="userisgoat">Tap on checkboxes to select items.</string>
 5 |     <string name="btn_search">Search</string> 
 6 |     <string name="radio_design_ideas">Search in Design Ideas</string> 
 7 |     <string-array name="search_title"> 
 8 | 		<item>What can I search for?</item> 
 9 | 		<item>Do I have to have an account to search and view information?</item> 
10 | 		<item>How do I search for products shown in a design?</item> 
11 | 	</string-array>
12 | </resources>


--------------------------------------------------------------------------------
/translated/values-sq/strings.xml:
--------------------------------------------------------------------------------
 1 | <resources>
 2 |     <string name="hellow">Përshëndetni botën mizore!</string>
 3 |     <string name="mailtodeveloper">Mail për zhvilluesin</string>
 4 |     <string name="userisgoat">Prekni në kutitë e zgjedhjes për të zgjedhur artikujt.</string>
 5 |     <string name="btn_search">kërkim</string> 
 6 |     <string name="radio_design_ideas">Kërko në Ide të Dizajnit</string> 
 7 |     <string-array name="search_title"> 
 8 | 		<item>Çfarë mund të kërkoj?</item> 
 9 | 		<item>A duhet të kem një llogari për të kërkuar dhe parë informacionin?</item> 
10 | 		<item>Si mund të kërkoj për produktet e paraqitura në një dizajn?</item> 
11 | 	</string-array>
12 | </resources>


--------------------------------------------------------------------------------
/translator.py:
--------------------------------------------------------------------------------
  1 | #!/usr/bin/env python
  2 | 
  3 | ### LANGUAGE CODES FOR REFERENCE
  4 | 
  5 | #   af          Afrikaans
  6 | #   ak          Akan
  7 | #   sq          Albanian
  8 | #   am          Amharic
  9 | #   ar          Arabic
 10 | #   hy          Armenian
 11 | #   az          Azerbaijani
 12 | #   eu          Basque
 13 | #   be          Belarusian
 14 | #   bem         Bemba
 15 | #   bn          Bengali
 16 | #   bh          Bihari
 17 | #   xx-bork     Bork, bork, bork!
 18 | #   bs          Bosnian
 19 | #   br          Breton
 20 | #   bg          Bulgarian
 21 | #   km          Cambodian
 22 | #   ca          Catalan
 23 | #   chr         Cherokee
 24 | #   ny          Chichewa
 25 | #   zh-CN       Chinese (Simplified)
 26 | #   zh-TW       Chinese (Traditional)
 27 | #   co          Corsican
 28 | #   hr          Croatian
 29 | #   cs          Czech
 30 | #   da          Danish
 31 | #   nl          Dutch
 32 | #   xx-elmer    Elmer Fudd
 33 | #   en          English
 34 | #   eo          Esperanto
 35 | #   et          Estonian
 36 | #   ee          Ewe
 37 | #   fo          Faroese
 38 | #   tl          Filipino
 39 | #   fi          Finnish
 40 | #   fr          French
 41 | #   fy          Frisian
 42 | #   gaa         Ga
 43 | #   gl          Galician
 44 | #   ka          Georgian
 45 | #   de          German
 46 | #   el          Greek
 47 | #   gn          Guarani
 48 | #   gu          Gujarati
 49 | #   xx-hacker   Hacker
 50 | #   ht          Haitian Creole
 51 | #   ha          Hausa
 52 | #   haw         Hawaiian
 53 | #   iw          Hebrew
 54 | #   hi          Hindi
 55 | #   hu          Hungarian
 56 | #   is          Icelandic
 57 | #   ig          Igbo
 58 | #   id          Indonesian
 59 | #   ia          Interlingua
 60 | #   ga          Irish
 61 | #   it          Italian
 62 | #   ja          Japanese
 63 | #   jw          Javanese
 64 | #   kn          Kannada
 65 | #   kk          Kazakh
 66 | #   rw          Kinyarwanda
 67 | #   rn          Kirundi
 68 | #   xx-klingon  Klingon
 69 | #   kg          Kongo
 70 | #   ko          Korean
 71 | #   kri         Krio (Sierra Leone)
 72 | #   ku          Kurdish
 73 | #   ckb         Kurdish (Soranî)
 74 | #   ky          Kyrgyz
 75 | #   lo          Laothian
 76 | #   la          Latin
 77 | #   lv          Latvian
 78 | #   ln          Lingala
 79 | #   lt          Lithuanian
 80 | #   loz         Lozi
 81 | #   lg          Luganda
 82 | #   ach         Luo
 83 | #   mk          Macedonian
 84 | #   mg          Malagasy
 85 | #   ms          Malay
 86 | #   ml          Malayalam
 87 | #   mt          Maltese
 88 | #   mi          Maori
 89 | #   mr          Marathi
 90 | #   mfe         Mauritian Creole
 91 | #   mo          Moldavian
 92 | #   mn          Mongolian
 93 | #   sr-ME       Montenegrin
 94 | #   ne          Nepali
 95 | #   pcm         Nigerian Pidgin
 96 | #   nso         Northern Sotho
 97 | #   no          Norwegian
 98 | #   nn          Norwegian (Nynorsk)
 99 | #   oc          Occitan
100 | #   or          Oriya
101 | #   om          Oromo
102 | #   ps          Pashto
103 | #   fa          Persian
104 | #   xx-pirate   Pirate
105 | #   pl          Polish
106 | #   pt-BR       Portuguese (Brazil)
107 | #   pt-PT       Portuguese (Portugal)
108 | #   pa          Punjabi
109 | #   qu          Quechua
110 | #   ro          Romanian
111 | #   rm          Romansh
112 | #   nyn         Runyakitara
113 | #   ru          Russian
114 | #   gd          Scots Gaelic
115 | #   sr          Serbian
116 | #   sh          Serbo-Croatian
117 | #   st          Sesotho
118 | #   tn          Setswana
119 | #   crs         Seychellois Creole
120 | #   sn          Shona
121 | #   sd          Sindhi
122 | #   si          Sinhalese
123 | #   sk          Slovak
124 | #   sl          Slovenian
125 | #   so          Somali
126 | #   es          Spanish
127 | #   es-419      Spanish (Latin American)
128 | #   su          Sundanese
129 | #   sw          Swahili
130 | #   sv          Swedish
131 | #   tg          Tajik
132 | #   ta          Tamil
133 | #   tt          Tatar
134 | #   te          Telugu
135 | #   th          Thai
136 | #   ti          Tigrinya
137 | #   to          Tonga
138 | #   lua         Tshiluba
139 | #   tum         Tumbuka
140 | #   tr          Turkish
141 | #   tk          Turkmen
142 | #   tw          Twi
143 | #   ug          Uighur
144 | #   uk          Ukrainian
145 | #   ur          Urdu
146 | #   uz          Uzbek
147 | #   vi          Vietnamese
148 | #   cy          Welsh
149 | #   wo          Wolof
150 | #   xh          Xhosa
151 | #   yi          Yiddish
152 | #   yo          Yoruba
153 | #   zu          Zulu
154 | 
155 | #
156 | #   SUBROUTINES
157 | #
158 | 
159 | # This subroutine extracts the string including html tags
160 | # and may replace "root[i].text".  
161 | # It cannot digest arbitrary encodings, so use it only if necessary.
162 | def findall_content(xml_string, tag):
163 |     pattern = r"<(?:\w+:)?%(tag)s(?:[^>]*)>(.*)</(?:\w+:)?%(tag)s" % {"tag": tag}
164 |     return re.findall(pattern, xml_string, re.DOTALL)
165 | 
166 | 
167 | def create_directory_if_not_exists(directory_name):
168 |     if not os.path.exists(directory_name):
169 |         os.makedirs(directory_name)
170 | 
171 | 
172 | def create_directories(dir_language):
173 |     create_directory_if_not_exists("translated")
174 | 
175 |     file_directory = "translated/" + "values-" + dir_language
176 | 
177 |     create_directory_if_not_exists(file_directory)
178 |     return file_directory
179 | 
180 | default_output_languages = ['af', 'ak', 'sq', 'am', 'ar', 'hy', 'az', 'eu', 'be', 'bem', 'bn', 'bh', 'xx-bork', 'bs', 'br', 'bg', 'km', 'ca', 'chr', 'ny', 'zh-CN', 'zh-TW', 'co', 'hr', 'cs', 'da', 'nl', 'xx-elmer', 'en', 'eo', 'et', 'ee', 'fo', 'tl', 'fi', 'fr', 'fy', 'gaa', 'gl', 'ka', 'de', 'el', 'gn', 'gu', 'xx-hacker', 'ht', 'ha', 'haw', 'iw', 'hi', 'hu', 'is', 'ig', 'id', 'ia', 'ga', 'it', 'ja', 'jw', 'kn', 'kk', 'rw', 'rn', 'xx-klingon', 'kg', 'ko', 'kri', 'ku', 'ckb', 'ky', 'lo', 'la', 'lv', 'ln', 'lt', 'loz', 'lg', 'ach', 'mk', 'mg', 'ms', 'ml', 'mt', 'mi', 'mr', 'mfe', 'mo', 'mn', 'sr-ME', 'ne', 'pcm', 'nso', 'no', 'nn', 'oc', 'or', 'om', 'ps', 'fa', 'xx-pirate', 'pl', 'pt-BR', 'pt-PT', 'pa', 'qu', 'ro', 'rm', 'nyn', 'ru', 'gd', 'sr', 'sh', 'st', 'tn', 'crs', 'sn', 'sd', 'si', 'sk', 'sl', 'so', 'es', 'es-419', 'su', 'sw', 'sv', 'tg', 'ta', 'tt', 'te', 'th', 'ti', 'to', 'lua', 'tum', 'tr', 'tk', 'tw', 'ug', 'uk', 'ur', 'uz', 'vi', 'cy', 'wo', 'xh', 'yi', 'yo', 'zu']
181 | # This subroutine calls Google translate and extracts the translation from
182 | # the html request
183 | def translate(to_translate, to_language="auto", language="auto"):
184 |  # send request
185 |  r = requests.get("https://translate.google.com/m?hl=%s&sl=%s&q=%s"% (to_language, language, to_translate.replace(" ", "+")))
186 | 
187 |  # set markers that enclose the charset identifier
188 |  beforecharset='charset='
189 |  aftercharset='" http-equiv'
190 |  # extract charset 
191 |  parsed1=r.text[r.text.find(beforecharset)+len(beforecharset):]
192 |  parsed2=parsed1[:parsed1.find(aftercharset)]
193 |  # Display warning when encoding mismatch 
194 |  if(parsed2!=r.encoding):
195 |      print('\x1b[1;31;40m' + 'Warning: Potential Charset conflict' )
196 |      print(" Encoding as extracted by SELF    : "+parsed2)
197 |      print(" Encoding as detected by REQUESTS : "+r.encoding+ '\x1b[0m')
198 | 
199 |  # Work around an AGE OLD Python bug in case of windows-874 encoding
200 |  # https://bugs.python.org/issue854511
201 |  if(r.encoding=='windows-874' and os.name=='posix'):
202 |      print('\x1b[1;31;40m' + "Alert: Working around age old Python bug (https://bugs.python.org/issue854511)\nOn Linux, charset windows-874 must be labeled as charset cp874"+'\x1b[0m')
203 |      r.encoding='cp874'
204 | 
205 |  # convert html tags  
206 |  text=html.unescape(r.text)    
207 |  # set markers that enclose the wanted translation
208 |  before_trans = 'class="t0">'
209 |  after_trans='</div><form'
210 |  # extract translation and return it
211 |  parsed1=r.text[r.text.find(before_trans)+len(before_trans):]
212 |  parsed2=parsed1[:parsed1.find(after_trans)]
213 |  return html.unescape(parsed2)
214 | 
215 | #
216 | # MAIN PROGRAM
217 | #
218 | 
219 | # import libraries
220 | import html
221 | import requests
222 | import os
223 | import xml.etree.ElementTree as ET
224 | import sys
225 | from io import BytesIO
226 | import re
227 | 
228 | # read argument vector
229 | INPUTLANGUAGE=sys.argv[1]
230 | INFILE=sys.argv[2]
231 | 
232 | languages_to_translate = default_output_languages
233 | 
234 | if INFILE is None:
235 |     INFILE = "strings.xml"
236 | 
237 | # create outfile name by appending the language code to the infile name
238 | name, ext=os.path.splitext(INFILE)
239 | 
240 | for language_name in languages_to_translate:
241 |     language_to_translate = language_name.strip()
242 | 
243 |     translated_file_directory = create_directories(language_to_translate)
244 |     print(" -> " + language_to_translate + " =========================")
245 | 
246 |     # read xml structure
247 |     tree = ET.parse(INFILE)
248 |     root = tree.getroot()
249 | 
250 |     # cycle through elements 
251 |     for i in range(len(root)):
252 |     #	for each translatable string call the translation subroutine
253 |     #   and replace the string by its translation,
254 |     #   descend into each string array  
255 |         isTranslatable=root[i].get('translatable')
256 |         print((str(i)+" ========================="))
257 |         if(isTranslatable=='false'):
258 |             print("Not translatable")
259 |         if(root[i].tag=='string') & (isTranslatable!='false'):
260 |     # Here you might want to replace root[i].text by the findall_content function
261 |     # if you need to extract html tags
262 |             # ~ totranslate="".join(findall_content(str(ET.tostring(root[i])),"string"))
263 |             totranslate=root[i].text
264 |             if(totranslate!=None):
265 |                 print(totranslate+"-->", end='')
266 |                 root[i].text=translate(totranslate,language_to_translate,INPUTLANGUAGE)
267 |                 print(root[i].text)
268 |         if(root[i].tag=='string-array'):
269 |             print("Entering string array...")
270 |             for j in range(len(root[i])):
271 |     #	for each translatable string call the translation subroutine
272 |     #   and replace the string by its translation,
273 |                 isTranslatable=root[i][j].get('translatable')
274 |                 print((str(i)+" " + str(j) + " ========================="))
275 |                 if(isTranslatable=='false'):
276 |                     print("Not translatable")
277 |                 if(root[i][j].tag=='item') & (isTranslatable!='false'):
278 |     # Here you might want to replace root[i].text by the findall_content function
279 |     # if you need to extract html tags
280 |                     # ~ totranslate="".join(findall_content(str(ET.tostring(root[i][j])),"item"))
281 |                     totranslate=root[i][j].text
282 |                     if(totranslate!=None):
283 |                         print(totranslate+"-->", end='')
284 |                         root[i][j].text=translate(totranslate,language_to_translate,INPUTLANGUAGE)
285 |                         print(root[i][j].text)
286 | 
287 |     # write new xml file
288 |     translated_file = translated_file_directory + "/strings.xml"
289 |     tree.write(translated_file, encoding='utf-8')
290 | 


--------------------------------------------------------------------------------