Remove languages not supported

When the ocr languages list was originally introduced (commit b527776),
the container was running in a ubuntu 18.04 [1]. Later it changed to
alpine linux. Unfortunately it has less languages than in ubuntu.

This commit removes those languages. Fixes #355

[1]: b527776e28 (diff-ec032b25a6c2af24eaf4128c85090c5ce0dcbab64e64eace10be9f4e4683a71bR1)

share/ocr-languages.json

@@ -1,162 +1,63 @@
 {
-    "Arabic script": "Arabic",
-    "Armenian script": "Armenian",
-    "Bengali script": "Bengali",
-    "Canadian Aboriginal script": "Canadian_Aboriginal",
-    "Cherokee script": "Cherokee",
-    "Cyrillic script": "Cyrillic",
-    "Devanagari script": "Devanagari",
-    "Ethiopic script": "Ethiopic",
-    "Fraktur script": "Fraktur",
-    "Georgian script": "Georgian",
-    "Greek script": "Greek",
-    "Gujarati script": "Gujarati",
-    "Gurmukhi script": "Gurmukhi",
-    "Han - Simplified script": "HanS",
-    "Han - Simplified (vertical) script": "HanS_vert",
-    "Han - Traditional script": "HanT",
-    "Han - Traditional (vertical) script": "HanT_vert",
-    "Hangul script": "Hangul",
-    "Hangul (vertical) script": "Hangul_vert",
-    "Hebrew script": "Hebrew",
-    "Japanese script": "Japanese",
-    "Japanese (vertical) script": "Japanese_vert",
-    "Kannada script": "Kannada",
-    "Khmer script": "Khmer",
-    "Lao script": "Lao",
-    "Latin script": "Latin",
-    "Malayalam script": "Malayalam",
-    "Myanmar script": "Myanmar",
-    "Oriya (Odia) script": "Oriya",
-    "Sinhala script": "Sinhala",
-    "Syriac script": "Syriac",
-    "Tamil script": "Tamil",
-    "Telugu script": "Telugu",
-    "Thaana script": "Thaana",
-    "Thai script": "Thai",
-    "Tibetan script": "Tibetan",
-    "Vietnamese script": "Vietnamese",
-    "Amharic": "amh",
     "Afrikaans": "arf",
     "Arabic": "ara",
     "Assamese": "asm",
     "Azerbaijani": "aze",
-    "Azerbaijani (Cyrillic)": "aze_cyrl",
     "Belarusian": "bel",
     "Bengali": "ben",
-    "Tibetan Standard": "bod",
-    "Bosnian": "bos",
-    "Breton": "bre",
     "Bulgarian": "bul",
     "Catalan": "cat",
-    "Cebuano": "ceb",
     "Czech": "ces",
     "Chinese - Simplified": "chi_sim",
-    "Chinese - Simplified (vertical)": "chi_sim_vert",
     "Chinese - Traditional": "chi_tra",
-    "Chinese - Traditional (vertical)": "chi_tra_vert",
     "Cherokee": "chr",
-    "Corsican": "cos",
-    "Welsh": "cym",
     "Danish": "dan",
     "German": "deu",
-    "Divehi": "div",
-    "Dzongkha": "dzo",
     "Greek": "ell",
     "English": "eng",
     "English, Middle (1100-1500)": "enm",
     "Esperanto": "epo",
     "Estonian": "est",
     "Basque": "eus",
-    "Faroese": "fao",
-    "Persian": "fas",
-    "Filipino": "fil",
     "Finnish": "fin",
     "French": "fra",
     "Frankish": "frk",
     "French, Middle (ca.1400-1600)": "frm",
-    "Frisian (Western)": "fry",
-    "Gaelic (Scots)": "gla",
-    "Irish": "gle",
     "Galician": "glg",
-    "Gujarati": "guj",
-    "Hatian": "hat",
     "Hebrew": "heb",
     "Hindi": "hin",
     "Croatian": "hrv",
     "Hungarian": "hun",
-    "Armenian": "hye",
-    "Inuktitut": "iku",
     "Indonesian": "ind",
     "Icelandic": "isl",
     "Italian": "ita",
     "Italian - Old": "ita_old",
-    "Javanese": "jav",
     "Japanese": "jpn",
-    "Japanese (vertical)": "jpn_vert",
     "Kannada": "kan",
     "Georgian": "kat",
-    "Old Georgian": "kat_old",
-    "Kazakh": "kaz",
-    "Khmer": "khm",
-    "Kyrgyz": "kir",
     "Korean": "kor",
-    "Korean (vertical)": "kor_vert",
-    "Kurdish (Arabic)": "kur_ara",
-    "Lao": "lao",
-    "Latin": "lat",
     "Latvian": "lav",
     "Lithuanian": "lit",
-    "Luxembourgish": "ltz",
     "Malayalam": "mal",
-    "Marathi": "mar",
     "Macedonian": "mkd",
     "Maltese": "mlt",
-    "Mongolian": "mon",
-    "Maori": "mri",
     "Malay": "msa",
-    "Burmese": "mya",
-    "Nepali": "nep",
     "Dutch": "nld",
     "Norwegian": "nor",
-    "Occitan (post 1500)": "oci",
-    "Oriya": "ori",
-    "script and orientation": "osd",
-    "Punjabi": "pan",
     "Polish": "pol",
     "Portuguese": "por",
-    "Pashto": "pus",
-    "Quechua": "que",
     "Romanian": "ron",
     "Russian": "rus",
-    "Sanskrit": "san",
-    "Sinhala": "sin",
     "Slovakian": "slk",
-    "Slovenian": "slv",
-    "Sindhi": "snd",
     "Spanish": "spa",
     "Spanish": "spa_old",
     "Albanian": "sqi",
     "Serbian": "srp",
-    "Serbian (Latin)": "srp_latn",
-    "Sundanese": "sun",
     "Swahili": "swa",
     "Swedish": "swe",
-    "Syriac": "syr",
     "Tamil": "tam",
-    "Tatar": "tat",
     "Telugu": "tel",
-    "Tajik": "tgk",
     "Thai": "tha",
-    "Tigrinya": "tir",
-    "Tonga": "ton",
     "Turkish": "tur",
-    "Uyghur": "uig",
-    "Ukrainian": "ukr",
-    "Urdu": "urd",
-    "Uzbek": "uzb",
-    "Uzbek (Cyrillic)": "uzb_cyrl",
-    "Vietnamese": "vie",
-    "Yiddish": "yid",
-    "yor": "Yoruba"
+    "Ukrainian": "ukr"
 }