validate canons without yatest_common

6 files changed, 1239 insertions, 0 deletions

diff --git a/library/cpp/langs/README.md b/library/cpp/langs/README.md
new file mode 100644
index 0000000000..537ae31e1b
--- /dev/null
+++ b/library/cpp/langs/README.md
@@ -0,0 +1,8 @@
+Здесь описаны константы для [языков](https://a.yandex-team.ru/arc/trunk/arcadia/library/cpp/langs/langs.h) и [письменностей](https://a.yandex-team.ru/arc/trunk/arcadia/library/cpp/langs/scripts.h) (скриптов в терминах Unicode).
+
+В терминах этих констант языков работают [документная](https://a.yandex-team.ru/arc/trunk/arcadia/kernel/recshell/recshell.h) и [запросная](https://a.yandex-team.ru/arc/trunk/arcadia/dict/recognize/queryrec) распознавалки языка.
+
+Имеется [набор функций](https://a.yandex-team.ru/arc/trunk/arcadia/library/cpp/langs/langs.h?rev=r6909333#L142-214) для преобразования констант в двухбуквенный или трехбуквенный код и обратного получения константы по строке с учетом синонимов. Есть [функции](https://a.yandex-team.ru/arc/trunk/arcadia/library/cpp/langs/langs.h?rev=r6909333#L216-217) для определения письменности по языку и по символу).
+
+В списке констант представлены не все языки и письменности, а лишь те, которые представляли интерес для поиска Яндекса и машинного перевода.
+Имеется несколько псевдоязыков типа `LANG_UZB_CYR` или `LANG_KAZ_LAT`.
diff --git a/library/cpp/langs/generated/uniscripts.cpp b/library/cpp/langs/generated/uniscripts.cpp
new file mode 100644
index 0000000000..59cc6a70c2
--- /dev/null
+++ b/library/cpp/langs/generated/uniscripts.cpp
@@ -0,0 +1,458 @@
+// Generated from http://www.unicode.org/Public/UNIDATA/Scripts.txt
+// The best way to alter this file is to modify uniscripts.py
+#include <library/cpp/langs/langs.h>
+#include <util/system/yassert.h>
+
+#include <cstring>
+
+namespace NCharsetInternal {
+    struct TScriptRange {
+        EScript Script;
+        wchar32 Start;
+        wchar32 End;
+    };
+
+    const TScriptRange ScriptRanges[] = {
+        { SCRIPT_ETHIOPIC, 0x1200, 0x1248 },
+        { SCRIPT_ETHIOPIC, 0x124A, 0x124D },
+        { SCRIPT_ETHIOPIC, 0x1250, 0x1256 },
+        { SCRIPT_ETHIOPIC, 0x1258, 0x1258 },
+        { SCRIPT_ETHIOPIC, 0x125A, 0x125D },
+        { SCRIPT_ETHIOPIC, 0x1260, 0x1288 },
+        { SCRIPT_ETHIOPIC, 0x128A, 0x128D },
+        { SCRIPT_ETHIOPIC, 0x1290, 0x12B0 },
+        { SCRIPT_ETHIOPIC, 0x12B2, 0x12B5 },
+        { SCRIPT_ETHIOPIC, 0x12B8, 0x12BE },
+        { SCRIPT_ETHIOPIC, 0x12C0, 0x12C0 },
+        { SCRIPT_ETHIOPIC, 0x12C2, 0x12C5 },
+        { SCRIPT_ETHIOPIC, 0x12C8, 0x12D6 },
+        { SCRIPT_ETHIOPIC, 0x12D8, 0x1310 },
+        { SCRIPT_ETHIOPIC, 0x1312, 0x1315 },
+        { SCRIPT_ETHIOPIC, 0x1318, 0x135A },
+        { SCRIPT_ETHIOPIC, 0x135D, 0x137C },
+        { SCRIPT_ETHIOPIC, 0x1380, 0x1399 },
+        { SCRIPT_ETHIOPIC, 0x2D80, 0x2D96 },
+        { SCRIPT_ETHIOPIC, 0x2DA0, 0x2DA6 },
+        { SCRIPT_ETHIOPIC, 0x2DA8, 0x2DAE },
+        { SCRIPT_ETHIOPIC, 0x2DB0, 0x2DB6 },
+        { SCRIPT_ETHIOPIC, 0x2DB8, 0x2DBE },
+        { SCRIPT_ETHIOPIC, 0x2DC0, 0x2DC6 },
+        { SCRIPT_ETHIOPIC, 0x2DC8, 0x2DCE },
+        { SCRIPT_ETHIOPIC, 0x2DD0, 0x2DD6 },
+        { SCRIPT_ETHIOPIC, 0x2DD8, 0x2DDE },
+        { SCRIPT_ETHIOPIC, 0xAB01, 0xAB06 },
+        { SCRIPT_ETHIOPIC, 0xAB09, 0xAB0E },
+        { SCRIPT_ETHIOPIC, 0xAB11, 0xAB16 },
+        { SCRIPT_ETHIOPIC, 0xAB20, 0xAB26 },
+        { SCRIPT_ETHIOPIC, 0xAB28, 0xAB2E },
+        { SCRIPT_ARABIC, 0x600, 0x604 },
+        { SCRIPT_ARABIC, 0x606, 0x60B },
+        { SCRIPT_ARABIC, 0x60D, 0x61A },
+        { SCRIPT_ARABIC, 0x61E, 0x61E },
+        { SCRIPT_ARABIC, 0x620, 0x63F },
+        { SCRIPT_ARABIC, 0x641, 0x64A },
+        { SCRIPT_ARABIC, 0x656, 0x66F },
+        { SCRIPT_ARABIC, 0x671, 0x6DC },
+        { SCRIPT_ARABIC, 0x6DE, 0x6FF },
+        { SCRIPT_ARABIC, 0x750, 0x77F },
+        { SCRIPT_ARABIC, 0x8A0, 0x8B4 },
+        { SCRIPT_ARABIC, 0x8B6, 0x8BD },
+        { SCRIPT_ARABIC, 0x8D4, 0x8E1 },
+        { SCRIPT_ARABIC, 0x8E3, 0x8FF },
+        { SCRIPT_ARABIC, 0xFB50, 0xFBC1 },
+        { SCRIPT_ARABIC, 0xFBD3, 0xFD3D },
+        { SCRIPT_ARABIC, 0xFD50, 0xFD8F },
+        { SCRIPT_ARABIC, 0xFD92, 0xFDC7 },
+        { SCRIPT_ARABIC, 0xFDF0, 0xFDFD },
+        { SCRIPT_ARABIC, 0xFE70, 0xFE74 },
+        { SCRIPT_ARABIC, 0xFE76, 0xFEFC },
+        { SCRIPT_MONGOLIAN, 0x1800, 0x1801 },
+        { SCRIPT_MONGOLIAN, 0x1804, 0x1804 },
+        { SCRIPT_MONGOLIAN, 0x1806, 0x180E },
+        { SCRIPT_MONGOLIAN, 0x1810, 0x1819 },
+        { SCRIPT_MONGOLIAN, 0x1820, 0x1877 },
+        { SCRIPT_MONGOLIAN, 0x1880, 0x18AA },
+        { SCRIPT_TAMIL, 0xB82, 0xB83 },
+        { SCRIPT_TAMIL, 0xB85, 0xB8A },
+        { SCRIPT_TAMIL, 0xB8E, 0xB90 },
+        { SCRIPT_TAMIL, 0xB92, 0xB95 },
+        { SCRIPT_TAMIL, 0xB99, 0xB9A },
+        { SCRIPT_TAMIL, 0xB9C, 0xB9C },
+        { SCRIPT_TAMIL, 0xB9E, 0xB9F },
+        { SCRIPT_TAMIL, 0xBA3, 0xBA4 },
+        { SCRIPT_TAMIL, 0xBA8, 0xBAA },
+        { SCRIPT_TAMIL, 0xBAE, 0xBB9 },
+        { SCRIPT_TAMIL, 0xBBE, 0xBC2 },
+        { SCRIPT_TAMIL, 0xBC6, 0xBC8 },
+        { SCRIPT_TAMIL, 0xBCA, 0xBCD },
+        { SCRIPT_TAMIL, 0xBD0, 0xBD0 },
+        { SCRIPT_TAMIL, 0xBD7, 0xBD7 },
+        { SCRIPT_TAMIL, 0xBE6, 0xBFA },
+        { SCRIPT_GUJARATI, 0xA81, 0xA83 },
+        { SCRIPT_GUJARATI, 0xA85, 0xA8D },
+        { SCRIPT_GUJARATI, 0xA8F, 0xA91 },
+        { SCRIPT_GUJARATI, 0xA93, 0xAA8 },
+        { SCRIPT_GUJARATI, 0xAAA, 0xAB0 },
+        { SCRIPT_GUJARATI, 0xAB2, 0xAB3 },
+        { SCRIPT_GUJARATI, 0xAB5, 0xAB9 },
+        { SCRIPT_GUJARATI, 0xABC, 0xAC5 },
+        { SCRIPT_GUJARATI, 0xAC7, 0xAC9 },
+        { SCRIPT_GUJARATI, 0xACB, 0xACD },
+        { SCRIPT_GUJARATI, 0xAD0, 0xAD0 },
+        { SCRIPT_GUJARATI, 0xAE0, 0xAE3 },
+        { SCRIPT_GUJARATI, 0xAE6, 0xAF1 },
+        { SCRIPT_GUJARATI, 0xAF9, 0xAF9 },
+        { SCRIPT_MALAYALAM, 0xD01, 0xD03 },
+        { SCRIPT_MALAYALAM, 0xD05, 0xD0C },
+        { SCRIPT_MALAYALAM, 0xD0E, 0xD10 },
+        { SCRIPT_MALAYALAM, 0xD12, 0xD3A },
+        { SCRIPT_MALAYALAM, 0xD3D, 0xD44 },
+        { SCRIPT_MALAYALAM, 0xD46, 0xD48 },
+        { SCRIPT_MALAYALAM, 0xD4A, 0xD4F },
+        { SCRIPT_MALAYALAM, 0xD54, 0xD63 },
+        { SCRIPT_MALAYALAM, 0xD66, 0xD7F },
+        { SCRIPT_ARMENIAN, 0x531, 0x556 },
+        { SCRIPT_ARMENIAN, 0x559, 0x55F },
+        { SCRIPT_ARMENIAN, 0x561, 0x587 },
+        { SCRIPT_ARMENIAN, 0x58A, 0x58A },
+        { SCRIPT_ARMENIAN, 0x58D, 0x58F },
+        { SCRIPT_ARMENIAN, 0xFB13, 0xFB17 },
+        { SCRIPT_HANGUL, 0x1100, 0x11FF },
+        { SCRIPT_HANGUL, 0x302E, 0x302F },
+        { SCRIPT_HANGUL, 0x3131, 0x318E },
+        { SCRIPT_HANGUL, 0x3200, 0x321E },
+        { SCRIPT_HANGUL, 0x3260, 0x327E },
+        { SCRIPT_HANGUL, 0xA960, 0xA97C },
+        { SCRIPT_HANGUL, 0xAC00, 0xD7A3 },
+        { SCRIPT_HANGUL, 0xD7B0, 0xD7C6 },
+        { SCRIPT_HANGUL, 0xD7CB, 0xD7FB },
+        { SCRIPT_HANGUL, 0xFFA0, 0xFFBE },
+        { SCRIPT_HANGUL, 0xFFC2, 0xFFC7 },
+        { SCRIPT_HANGUL, 0xFFCA, 0xFFCF },
+        { SCRIPT_HANGUL, 0xFFD2, 0xFFD7 },
+        { SCRIPT_HANGUL, 0xFFDA, 0xFFDC },
+        { SCRIPT_GURMUKHI, 0xA01, 0xA03 },
+        { SCRIPT_GURMUKHI, 0xA05, 0xA0A },
+        { SCRIPT_GURMUKHI, 0xA0F, 0xA10 },
+        { SCRIPT_GURMUKHI, 0xA13, 0xA28 },
+        { SCRIPT_GURMUKHI, 0xA2A, 0xA30 },
+        { SCRIPT_GURMUKHI, 0xA32, 0xA33 },
+        { SCRIPT_GURMUKHI, 0xA35, 0xA36 },
+        { SCRIPT_GURMUKHI, 0xA38, 0xA39 },
+        { SCRIPT_GURMUKHI, 0xA3C, 0xA3C },
+        { SCRIPT_GURMUKHI, 0xA3E, 0xA42 },
+        { SCRIPT_GURMUKHI, 0xA47, 0xA48 },
+        { SCRIPT_GURMUKHI, 0xA4B, 0xA4D },
+        { SCRIPT_GURMUKHI, 0xA51, 0xA51 },
+        { SCRIPT_GURMUKHI, 0xA59, 0xA5C },
+        { SCRIPT_GURMUKHI, 0xA5E, 0xA5E },
+        { SCRIPT_GURMUKHI, 0xA66, 0xA75 },
+        { SCRIPT_CYRILLIC, 0x400, 0x484 },
+        { SCRIPT_CYRILLIC, 0x487, 0x52F },
+        { SCRIPT_CYRILLIC, 0x1C80, 0x1C88 },
+        { SCRIPT_CYRILLIC, 0x1D2B, 0x1D2B },
+        { SCRIPT_CYRILLIC, 0x1D78, 0x1D78 },
+        { SCRIPT_CYRILLIC, 0x2DE0, 0x2DFF },
+        { SCRIPT_CYRILLIC, 0xA640, 0xA69F },
+        { SCRIPT_CYRILLIC, 0xFE2E, 0xFE2F },
+        { SCRIPT_DEVANAGARI, 0x900, 0x950 },
+        { SCRIPT_DEVANAGARI, 0x953, 0x963 },
+        { SCRIPT_DEVANAGARI, 0x966, 0x97F },
+        { SCRIPT_DEVANAGARI, 0xA8E0, 0xA8FD },
+        { SCRIPT_HEBREW, 0x591, 0x5C7 },
+        { SCRIPT_HEBREW, 0x5D0, 0x5EA },
+        { SCRIPT_HEBREW, 0x5F0, 0x5F4 },
+        { SCRIPT_HEBREW, 0xFB1D, 0xFB36 },
+        { SCRIPT_HEBREW, 0xFB38, 0xFB3C },
+        { SCRIPT_HEBREW, 0xFB3E, 0xFB3E },
+        { SCRIPT_HEBREW, 0xFB40, 0xFB41 },
+        { SCRIPT_HEBREW, 0xFB43, 0xFB44 },
+        { SCRIPT_HEBREW, 0xFB46, 0xFB4F },
+        { SCRIPT_THAI, 0xE01, 0xE3A },
+        { SCRIPT_THAI, 0xE40, 0xE5B },
+        { SCRIPT_SYRIAC, 0x700, 0x70D },
+        { SCRIPT_SYRIAC, 0x70F, 0x74A },
+        { SCRIPT_SYRIAC, 0x74D, 0x74F },
+        { SCRIPT_KANNADA, 0xC80, 0xC83 },
+        { SCRIPT_KANNADA, 0xC85, 0xC8C },
+        { SCRIPT_KANNADA, 0xC8E, 0xC90 },
+        { SCRIPT_KANNADA, 0xC92, 0xCA8 },
+        { SCRIPT_KANNADA, 0xCAA, 0xCB3 },
+        { SCRIPT_KANNADA, 0xCB5, 0xCB9 },
+        { SCRIPT_KANNADA, 0xCBC, 0xCC4 },
+        { SCRIPT_KANNADA, 0xCC6, 0xCC8 },
+        { SCRIPT_KANNADA, 0xCCA, 0xCCD },
+        { SCRIPT_KANNADA, 0xCD5, 0xCD6 },
+        { SCRIPT_KANNADA, 0xCDE, 0xCDE },
+        { SCRIPT_KANNADA, 0xCE0, 0xCE3 },
+        { SCRIPT_KANNADA, 0xCE6, 0xCEF },
+        { SCRIPT_KANNADA, 0xCF1, 0xCF2 },
+        { SCRIPT_LAO, 0xE81, 0xE82 },
+        { SCRIPT_LAO, 0xE84, 0xE84 },
+        { SCRIPT_LAO, 0xE87, 0xE88 },
+        { SCRIPT_LAO, 0xE8A, 0xE8A },
+        { SCRIPT_LAO, 0xE8D, 0xE8D },
+        { SCRIPT_LAO, 0xE94, 0xE97 },
+        { SCRIPT_LAO, 0xE99, 0xE9F },
+        { SCRIPT_LAO, 0xEA1, 0xEA3 },
+        { SCRIPT_LAO, 0xEA5, 0xEA5 },
+        { SCRIPT_LAO, 0xEA7, 0xEA7 },
+        { SCRIPT_LAO, 0xEAA, 0xEAB },
+        { SCRIPT_LAO, 0xEAD, 0xEB9 },
+        { SCRIPT_LAO, 0xEBB, 0xEBD },
+        { SCRIPT_LAO, 0xEC0, 0xEC4 },
+        { SCRIPT_LAO, 0xEC6, 0xEC6 },
+        { SCRIPT_LAO, 0xEC8, 0xECD },
+        { SCRIPT_LAO, 0xED0, 0xED9 },
+        { SCRIPT_LAO, 0xEDC, 0xEDF },
+        { SCRIPT_TELUGU, 0xC00, 0xC03 },
+        { SCRIPT_TELUGU, 0xC05, 0xC0C },
+        { SCRIPT_TELUGU, 0xC0E, 0xC10 },
+        { SCRIPT_TELUGU, 0xC12, 0xC28 },
+        { SCRIPT_TELUGU, 0xC2A, 0xC39 },
+        { SCRIPT_TELUGU, 0xC3D, 0xC44 },
+        { SCRIPT_TELUGU, 0xC46, 0xC48 },
+        { SCRIPT_TELUGU, 0xC4A, 0xC4D },
+        { SCRIPT_TELUGU, 0xC55, 0xC56 },
+        { SCRIPT_TELUGU, 0xC58, 0xC5A },
+        { SCRIPT_TELUGU, 0xC60, 0xC63 },
+        { SCRIPT_TELUGU, 0xC66, 0xC6F },
+        { SCRIPT_TELUGU, 0xC78, 0xC7F },
+        { SCRIPT_KHMER, 0x1780, 0x17DD },
+        { SCRIPT_KHMER, 0x17E0, 0x17E9 },
+        { SCRIPT_KHMER, 0x17F0, 0x17F9 },
+        { SCRIPT_KHMER, 0x19E0, 0x19FF },
+        { SCRIPT_LATIN, 0x41, 0x5A },
+        { SCRIPT_LATIN, 0x61, 0x7A },
+        { SCRIPT_LATIN, 0xAA, 0xAA },
+        { SCRIPT_LATIN, 0xBA, 0xBA },
+        { SCRIPT_LATIN, 0xC0, 0xD6 },
+        { SCRIPT_LATIN, 0xD8, 0xF6 },
+        { SCRIPT_LATIN, 0xF8, 0x2B8 },
+        { SCRIPT_LATIN, 0x2E0, 0x2E4 },
+        { SCRIPT_LATIN, 0x1D00, 0x1D25 },
+        { SCRIPT_LATIN, 0x1D2C, 0x1D5C },
+        { SCRIPT_LATIN, 0x1D62, 0x1D65 },
+        { SCRIPT_LATIN, 0x1D6B, 0x1D77 },
+        { SCRIPT_LATIN, 0x1D79, 0x1DBE },
+        { SCRIPT_LATIN, 0x1E00, 0x1EFF },
+        { SCRIPT_LATIN, 0x2071, 0x2071 },
+        { SCRIPT_LATIN, 0x207F, 0x207F },
+        { SCRIPT_LATIN, 0x2090, 0x209C },
+        { SCRIPT_LATIN, 0x212A, 0x212B },
+        { SCRIPT_LATIN, 0x2132, 0x2132 },
+        { SCRIPT_LATIN, 0x214E, 0x214E },
+        { SCRIPT_LATIN, 0x2160, 0x2188 },
+        { SCRIPT_LATIN, 0x2C60, 0x2C7F },
+        { SCRIPT_LATIN, 0xA722, 0xA787 },
+        { SCRIPT_LATIN, 0xA78B, 0xA7AE },
+        { SCRIPT_LATIN, 0xA7B0, 0xA7B7 },
+        { SCRIPT_LATIN, 0xA7F7, 0xA7FF },
+        { SCRIPT_LATIN, 0xAB30, 0xAB5A },
+        { SCRIPT_LATIN, 0xAB5C, 0xAB64 },
+        { SCRIPT_LATIN, 0xFB00, 0xFB06 },
+        { SCRIPT_LATIN, 0xFF21, 0xFF3A },
+        { SCRIPT_LATIN, 0xFF41, 0xFF5A },
+        { SCRIPT_TIBETAN, 0xF00, 0xF47 },
+        { SCRIPT_TIBETAN, 0xF49, 0xF6C },
+        { SCRIPT_TIBETAN, 0xF71, 0xF97 },
+        { SCRIPT_TIBETAN, 0xF99, 0xFBC },
+        { SCRIPT_TIBETAN, 0xFBE, 0xFCC },
+        { SCRIPT_TIBETAN, 0xFCE, 0xFD4 },
+        { SCRIPT_TIBETAN, 0xFD9, 0xFDA },
+        { SCRIPT_MYANMAR, 0x1000, 0x109F },
+        { SCRIPT_MYANMAR, 0xA9E0, 0xA9FE },
+        { SCRIPT_MYANMAR, 0xAA60, 0xAA7F },
+        { SCRIPT_OTHER, 0x2EA, 0x2EB },
+        { SCRIPT_OTHER, 0x7C0, 0x7FA },
+        { SCRIPT_OTHER, 0x800, 0x82D },
+        { SCRIPT_OTHER, 0x830, 0x83E },
+        { SCRIPT_OTHER, 0x840, 0x85B },
+        { SCRIPT_OTHER, 0x85E, 0x85E },
+        { SCRIPT_OTHER, 0x13A0, 0x13F5 },
+        { SCRIPT_OTHER, 0x13F8, 0x13FD },
+        { SCRIPT_OTHER, 0x1400, 0x169C },
+        { SCRIPT_OTHER, 0x1700, 0x170C },
+        { SCRIPT_OTHER, 0x170E, 0x1714 },
+        { SCRIPT_OTHER, 0x1720, 0x1734 },
+        { SCRIPT_OTHER, 0x1740, 0x1753 },
+        { SCRIPT_OTHER, 0x1760, 0x176C },
+        { SCRIPT_OTHER, 0x176E, 0x1770 },
+        { SCRIPT_OTHER, 0x1772, 0x1773 },
+        { SCRIPT_OTHER, 0x18B0, 0x18F5 },
+        { SCRIPT_OTHER, 0x1900, 0x191E },
+        { SCRIPT_OTHER, 0x1920, 0x192B },
+        { SCRIPT_OTHER, 0x1930, 0x193B },
+        { SCRIPT_OTHER, 0x1940, 0x1940 },
+        { SCRIPT_OTHER, 0x1944, 0x196D },
+        { SCRIPT_OTHER, 0x1970, 0x1974 },
+        { SCRIPT_OTHER, 0x1980, 0x19AB },
+        { SCRIPT_OTHER, 0x19B0, 0x19C9 },
+        { SCRIPT_OTHER, 0x19D0, 0x19DA },
+        { SCRIPT_OTHER, 0x19DE, 0x19DF },
+        { SCRIPT_OTHER, 0x1A00, 0x1A1B },
+        { SCRIPT_OTHER, 0x1A1E, 0x1A5E },
+        { SCRIPT_OTHER, 0x1A60, 0x1A7C },
+        { SCRIPT_OTHER, 0x1A7F, 0x1A89 },
+        { SCRIPT_OTHER, 0x1A90, 0x1A99 },
+        { SCRIPT_OTHER, 0x1AA0, 0x1AAD },
+        { SCRIPT_OTHER, 0x1B00, 0x1B4B },
+        { SCRIPT_OTHER, 0x1B50, 0x1B7C },
+        { SCRIPT_OTHER, 0x1B80, 0x1BF3 },
+        { SCRIPT_OTHER, 0x1BFC, 0x1C37 },
+        { SCRIPT_OTHER, 0x1C3B, 0x1C49 },
+        { SCRIPT_OTHER, 0x1C4D, 0x1C7F },
+        { SCRIPT_OTHER, 0x1CC0, 0x1CC7 },
+        { SCRIPT_OTHER, 0x2800, 0x28FF },
+        { SCRIPT_OTHER, 0x2C00, 0x2C2E },
+        { SCRIPT_OTHER, 0x2C30, 0x2C5E },
+        { SCRIPT_OTHER, 0x2D30, 0x2D67 },
+        { SCRIPT_OTHER, 0x2D6F, 0x2D70 },
+        { SCRIPT_OTHER, 0x2D7F, 0x2D7F },
+        { SCRIPT_OTHER, 0x3105, 0x312D },
+        { SCRIPT_OTHER, 0x31A0, 0x31BA },
+        { SCRIPT_OTHER, 0xA000, 0xA48C },
+        { SCRIPT_OTHER, 0xA490, 0xA4C6 },
+        { SCRIPT_OTHER, 0xA4D0, 0xA62B },
+        { SCRIPT_OTHER, 0xA6A0, 0xA6F7 },
+        { SCRIPT_OTHER, 0xA800, 0xA82B },
+        { SCRIPT_OTHER, 0xA840, 0xA877 },
+        { SCRIPT_OTHER, 0xA880, 0xA8C5 },
+        { SCRIPT_OTHER, 0xA8CE, 0xA8D9 },
+        { SCRIPT_OTHER, 0xA900, 0xA92D },
+        { SCRIPT_OTHER, 0xA92F, 0xA953 },
+        { SCRIPT_OTHER, 0xA95F, 0xA95F },
+        { SCRIPT_OTHER, 0xA980, 0xA9CD },
+        { SCRIPT_OTHER, 0xA9D0, 0xA9D9 },
+        { SCRIPT_OTHER, 0xA9DE, 0xA9DF },
+        { SCRIPT_OTHER, 0xAA00, 0xAA36 },
+        { SCRIPT_OTHER, 0xAA40, 0xAA4D },
+        { SCRIPT_OTHER, 0xAA50, 0xAA59 },
+        { SCRIPT_OTHER, 0xAA5C, 0xAA5F },
+        { SCRIPT_OTHER, 0xAA80, 0xAAC2 },
+        { SCRIPT_OTHER, 0xAADB, 0xAAF6 },
+        { SCRIPT_OTHER, 0xAB70, 0xABED },
+        { SCRIPT_OTHER, 0xABF0, 0xABF9 },
+        { SCRIPT_HAN, 0x2E80, 0x2E99 },
+        { SCRIPT_HAN, 0x2E9B, 0x2EF3 },
+        { SCRIPT_HAN, 0x2F00, 0x2FD5 },
+        { SCRIPT_HAN, 0x3005, 0x3005 },
+        { SCRIPT_HAN, 0x3007, 0x3007 },
+        { SCRIPT_HAN, 0x3021, 0x3029 },
+        { SCRIPT_HAN, 0x3038, 0x303B },
+        { SCRIPT_HAN, 0x3400, 0x4DB5 },
+        { SCRIPT_HAN, 0x4E00, 0x9FD5 },
+        { SCRIPT_HAN, 0xF900, 0xFA6D },
+        { SCRIPT_HAN, 0xFA70, 0xFAD9 },
+        { SCRIPT_THAANA, 0x780, 0x7B1 },
+        { SCRIPT_HIRAGANA, 0x3041, 0x3096 },
+        { SCRIPT_HIRAGANA, 0x309D, 0x309F },
+        { SCRIPT_KATAKANA, 0x30A1, 0x30FA },
+        { SCRIPT_KATAKANA, 0x30FD, 0x30FF },
+        { SCRIPT_KATAKANA, 0x31F0, 0x31FF },
+        { SCRIPT_KATAKANA, 0x32D0, 0x32FE },
+        { SCRIPT_KATAKANA, 0x3300, 0x3357 },
+        { SCRIPT_KATAKANA, 0xFF66, 0xFF6F },
+        { SCRIPT_KATAKANA, 0xFF71, 0xFF9D },
+        { SCRIPT_ORIYA, 0xB01, 0xB03 },
+        { SCRIPT_ORIYA, 0xB05, 0xB0C },
+        { SCRIPT_ORIYA, 0xB0F, 0xB10 },
+        { SCRIPT_ORIYA, 0xB13, 0xB28 },
+        { SCRIPT_ORIYA, 0xB2A, 0xB30 },
+        { SCRIPT_ORIYA, 0xB32, 0xB33 },
+        { SCRIPT_ORIYA, 0xB35, 0xB39 },
+        { SCRIPT_ORIYA, 0xB3C, 0xB44 },
+        { SCRIPT_ORIYA, 0xB47, 0xB48 },
+        { SCRIPT_ORIYA, 0xB4B, 0xB4D },
+        { SCRIPT_ORIYA, 0xB56, 0xB57 },
+        { SCRIPT_ORIYA, 0xB5C, 0xB5D },
+        { SCRIPT_ORIYA, 0xB5F, 0xB63 },
+        { SCRIPT_ORIYA, 0xB66, 0xB77 },
+        { SCRIPT_BENGALI, 0x980, 0x983 },
+        { SCRIPT_BENGALI, 0x985, 0x98C },
+        { SCRIPT_BENGALI, 0x98F, 0x990 },
+        { SCRIPT_BENGALI, 0x993, 0x9A8 },
+        { SCRIPT_BENGALI, 0x9AA, 0x9B0 },
+        { SCRIPT_BENGALI, 0x9B2, 0x9B2 },
+        { SCRIPT_BENGALI, 0x9B6, 0x9B9 },
+        { SCRIPT_BENGALI, 0x9BC, 0x9C4 },
+        { SCRIPT_BENGALI, 0x9C7, 0x9C8 },
+        { SCRIPT_BENGALI, 0x9CB, 0x9CE },
+        { SCRIPT_BENGALI, 0x9D7, 0x9D7 },
+        { SCRIPT_BENGALI, 0x9DC, 0x9DD },
+        { SCRIPT_BENGALI, 0x9DF, 0x9E3 },
+        { SCRIPT_BENGALI, 0x9E6, 0x9FB },
+        { SCRIPT_RUNIC, 0x16A0, 0x16EA },
+        { SCRIPT_RUNIC, 0x16EE, 0x16F8 },
+        { SCRIPT_SINHALA, 0xD82, 0xD83 },
+        { SCRIPT_SINHALA, 0xD85, 0xD96 },
+        { SCRIPT_SINHALA, 0xD9A, 0xDB1 },
+        { SCRIPT_SINHALA, 0xDB3, 0xDBB },
+        { SCRIPT_SINHALA, 0xDBD, 0xDBD },
+        { SCRIPT_SINHALA, 0xDC0, 0xDC6 },
+        { SCRIPT_SINHALA, 0xDCA, 0xDCA },
+        { SCRIPT_SINHALA, 0xDCF, 0xDD4 },
+        { SCRIPT_SINHALA, 0xDD6, 0xDD6 },
+        { SCRIPT_SINHALA, 0xDD8, 0xDDF },
+        { SCRIPT_SINHALA, 0xDE6, 0xDEF },
+        { SCRIPT_SINHALA, 0xDF2, 0xDF4 },
+        { SCRIPT_COPTIC, 0x3E2, 0x3EF },
+        { SCRIPT_COPTIC, 0x2C80, 0x2CF3 },
+        { SCRIPT_COPTIC, 0x2CF9, 0x2CFF },
+        { SCRIPT_GEORGIAN, 0x10A0, 0x10C5 },
+        { SCRIPT_GEORGIAN, 0x10C7, 0x10C7 },
+        { SCRIPT_GEORGIAN, 0x10CD, 0x10CD },
+        { SCRIPT_GEORGIAN, 0x10D0, 0x10FA },
+        { SCRIPT_GEORGIAN, 0x10FC, 0x10FF },
+        { SCRIPT_GEORGIAN, 0x2D00, 0x2D25 },
+        { SCRIPT_GEORGIAN, 0x2D27, 0x2D27 },
+        { SCRIPT_GEORGIAN, 0x2D2D, 0x2D2D },
+        { SCRIPT_GREEK, 0x370, 0x373 },
+        { SCRIPT_GREEK, 0x375, 0x377 },
+        { SCRIPT_GREEK, 0x37A, 0x37D },
+        { SCRIPT_GREEK, 0x37F, 0x37F },
+        { SCRIPT_GREEK, 0x384, 0x384 },
+        { SCRIPT_GREEK, 0x386, 0x386 },
+        { SCRIPT_GREEK, 0x388, 0x38A },
+        { SCRIPT_GREEK, 0x38C, 0x38C },
+        { SCRIPT_GREEK, 0x38E, 0x3A1 },
+        { SCRIPT_GREEK, 0x3A3, 0x3E1 },
+        { SCRIPT_GREEK, 0x3F0, 0x3FF },
+        { SCRIPT_GREEK, 0x1D26, 0x1D2A },
+        { SCRIPT_GREEK, 0x1D5D, 0x1D61 },
+        { SCRIPT_GREEK, 0x1D66, 0x1D6A },
+        { SCRIPT_GREEK, 0x1DBF, 0x1DBF },
+        { SCRIPT_GREEK, 0x1F00, 0x1F15 },
+        { SCRIPT_GREEK, 0x1F18, 0x1F1D },
+        { SCRIPT_GREEK, 0x1F20, 0x1F45 },
+        { SCRIPT_GREEK, 0x1F48, 0x1F4D },
+        { SCRIPT_GREEK, 0x1F50, 0x1F57 },
+        { SCRIPT_GREEK, 0x1F59, 0x1F59 },
+        { SCRIPT_GREEK, 0x1F5B, 0x1F5B },
+        { SCRIPT_GREEK, 0x1F5D, 0x1F5D },
+        { SCRIPT_GREEK, 0x1F5F, 0x1F7D },
+        { SCRIPT_GREEK, 0x1F80, 0x1FB4 },
+        { SCRIPT_GREEK, 0x1FB6, 0x1FC4 },
+        { SCRIPT_GREEK, 0x1FC6, 0x1FD3 },
+        { SCRIPT_GREEK, 0x1FD6, 0x1FDB },
+        { SCRIPT_GREEK, 0x1FDD, 0x1FEF },
+        { SCRIPT_GREEK, 0x1FF2, 0x1FF4 },
+        { SCRIPT_GREEK, 0x1FF6, 0x1FFE },
+        { SCRIPT_GREEK, 0x2126, 0x2126 },
+        { SCRIPT_GREEK, 0xAB65, 0xAB65 },
+    };
+
+    void InitScriptData(ui8 data[], size_t len) {
+        memset (data, 0, len * sizeof(ui8));
+        for (auto range : ScriptRanges) {
+            Y_ASSERT(range.Start <= range.End);
+            Y_ASSERT((unsigned)range.Script < 0x100);
+            size_t end = range.End;
+            if (end >= len)
+                end = len;
+            for (size_t j = range.Start; j <= end; ++j) {
+                data[j] = (ui8)range.Script;
+            }
+        }
+    }
+}
diff --git a/library/cpp/langs/langs.cpp b/library/cpp/langs/langs.cpp
new file mode 100644
index 0000000000..2c508e1602
--- /dev/null
+++ b/library/cpp/langs/langs.cpp
@@ -0,0 +1,330 @@
+#include "langs.h"
+
+#include <library/cpp/digest/lower_case/hash_ops.h>
+
+#include <util/generic/array_size.h>
+#include <util/generic/hash.h>
+#include <util/generic/singleton.h>
+#include <util/generic/strbuf.h>
+#include <util/generic/yexception.h>
+#include <util/system/defaults.h>
+
+#include <array>
+#include <cctype>
+
+/*
+ * define language by ELanguage
+ */
+
+namespace {
+    struct TLanguageNameAndEnum {
+        ELanguage Language;
+        EScript Script;
+        const char* EnglishName;
+        const char* BiblioName;
+        const char* IsoName;
+        const char* Synonyms;
+    };
+
+    const TLanguageNameAndEnum LanguageNameAndEnum[] = {
+        {LANG_UNK, SCRIPT_OTHER, "Unknown", "unk", "mis", nullptr},
+        {LANG_RUS, SCRIPT_CYRILLIC, "Russian", "rus", "ru", "ru-RU"},
+        {LANG_ENG, SCRIPT_LATIN, "English", "eng", "en", "en-US, en-GB, en-CA, en-NZ, en-AU"},
+        {LANG_POL, SCRIPT_LATIN, "Polish", "pol", "pl", nullptr},
+        {LANG_HUN, SCRIPT_LATIN, "Hungarian", "hun", "hu", nullptr},
+        {LANG_UKR, SCRIPT_CYRILLIC, "Ukrainian", "ukr", "uk", "uk-UA"},
+        {LANG_GER, SCRIPT_LATIN, "German", "ger", "de", "deu"},
+        {LANG_FRE, SCRIPT_LATIN, "French", "fre", "fr", "fra, frn, fr-FR, fr-CA"},
+        {LANG_TAT, SCRIPT_CYRILLIC, "Tatar", "tat", "tt", nullptr},
+        {LANG_BEL, SCRIPT_CYRILLIC, "Belarusian", "bel", "be", "blr, Belorussian"},
+        {LANG_KAZ, SCRIPT_CYRILLIC, "Kazakh", "kaz", "kk", "kk-Cyrl"},
+        {LANG_ALB, SCRIPT_LATIN, "Albanian", "alb", "sq", nullptr},
+        {LANG_SPA, SCRIPT_LATIN, "Spanish", "spa", "es", nullptr},
+        {LANG_ITA, SCRIPT_LATIN, "Italian", "ita", "it", nullptr},
+        {LANG_ARM, SCRIPT_ARMENIAN, "Armenian", "arm", "hy", "hye"},
+        {LANG_DAN, SCRIPT_LATIN, "Danish", "dan", "da", nullptr},
+        {LANG_POR, SCRIPT_LATIN, "Portuguese", "por", "pt", nullptr},
+        {LANG_ICE, SCRIPT_LATIN, "Icelandic", "ice", "is", "isl"},
+        {LANG_SLO, SCRIPT_LATIN, "Slovak", "slo", "sk", "slk"},
+        {LANG_SLV, SCRIPT_LATIN, "Slovene", "slv", "sl", "Slovenian"},
+        {LANG_DUT, SCRIPT_LATIN, "Dutch", "dut", "nl", "nld"},
+        {LANG_BUL, SCRIPT_CYRILLIC, "Bulgarian", "bul", "bg", nullptr},
+        {LANG_CAT, SCRIPT_LATIN, "Catalan", "cat", "ca", nullptr},
+        {LANG_HRV, SCRIPT_LATIN, "Croatian", "hrv", "hr", "scr"},
+        {LANG_CZE, SCRIPT_LATIN, "Czech", "cze", "cs", "ces"},
+        {LANG_GRE, SCRIPT_GREEK, "Greek", "gre", "el", "ell"},
+        {LANG_HEB, SCRIPT_HEBREW, "Hebrew", "heb", "he", "iw"}, // 'iw' is old ISO-639 code
+        {LANG_NOR, SCRIPT_LATIN, "Norwegian", "nor", "no", nullptr},
+        {LANG_MAC, SCRIPT_CYRILLIC, "Macedonian", "mac", "mk", nullptr},
+        {LANG_SWE, SCRIPT_LATIN, "Swedish", "swe", "sv", nullptr},
+        {LANG_KOR, SCRIPT_HANGUL, "Korean", "kor", "ko", nullptr},
+        {LANG_LAT, SCRIPT_LATIN, "Latin", "lat", "la", nullptr},
+        {LANG_BASIC_RUS, SCRIPT_CYRILLIC, "Basic Russian", "basic-rus", "bas-ru", nullptr},
+        {LANG_BOS, SCRIPT_LATIN, "Bosnian", "bos", "bs", nullptr},
+        {LANG_MLT, SCRIPT_LATIN, "Maltese", "mlt", "mt", nullptr},
+
+        {LANG_EMPTY, SCRIPT_OTHER, "Empty", "empty", nullptr, nullptr},
+        {LANG_UNK_LAT, SCRIPT_LATIN, "Unknown Latin", "unklat", nullptr, nullptr},
+        {LANG_UNK_CYR, SCRIPT_CYRILLIC, "Unknown Cyrillic", "unkcyr", nullptr, nullptr},
+        {LANG_UNK_ALPHA, SCRIPT_OTHER, "Unknown Alpha", "unkalpha", nullptr, nullptr},
+
+        {LANG_FIN, SCRIPT_LATIN, "Finnish", "fin", "fi", nullptr},
+        {LANG_EST, SCRIPT_LATIN, "Estonian", "est", "et", nullptr},
+        {LANG_LAV, SCRIPT_LATIN, "Latvian", "lav", "lv", nullptr},
+        {LANG_LIT, SCRIPT_LATIN, "Lithuanian", "lit", "lt", nullptr},
+        {LANG_BAK, SCRIPT_CYRILLIC, "Bashkir", "bak", "ba", nullptr},
+        {LANG_TUR, SCRIPT_LATIN, "Turkish", "tur", "tr", nullptr},
+        {LANG_RUM, SCRIPT_LATIN, "Romanian", "rum", "ro", "ron"},
+        {LANG_MON, SCRIPT_CYRILLIC, "Mongolian", "mon", "mn", nullptr},
+        {LANG_UZB, SCRIPT_LATIN, "Uzbek", "uzb", "uz", "uz-Latn"},
+        {LANG_KIR, SCRIPT_CYRILLIC, "Kirghiz", "kir", "ky", "Kyrgyz"},
+        {LANG_TGK, SCRIPT_CYRILLIC, "Tajik", "tgk", "tg", nullptr},
+        {LANG_TUK, SCRIPT_LATIN, "Turkmen", "tuk", "tk", nullptr},
+        {LANG_SRP, SCRIPT_CYRILLIC, "Serbian", "srp", "sr", nullptr},
+        {LANG_AZE, SCRIPT_LATIN, "Azerbaijani", "aze", "az", "Azeri"},
+        {LANG_BASIC_ENG, SCRIPT_LATIN, "Basic English", "basic-eng", "bas-en", nullptr},
+        {LANG_GEO, SCRIPT_GEORGIAN, "Georgian", "geo", "ka", "kat"},
+        {LANG_ARA, SCRIPT_ARABIC, "Arabic", "ara", "ar", nullptr},
+        {LANG_PER, SCRIPT_ARABIC, "Persian", "per", "fa", "fas"},
+        {LANG_CHU, SCRIPT_CYRILLIC, "Church Slavonic", "chu", "cu", nullptr},
+        {LANG_CHI, SCRIPT_HAN, "Chinese", "chi", "zh", "zho"},
+        {LANG_JPN, SCRIPT_HIRAGANA, "Japanese", "jpn", "ja", nullptr},
+        {LANG_IND, SCRIPT_LATIN, "Indonesian", "ind", "id", "in"}, // 'in' is old ISO-639 code
+        {LANG_MAY, SCRIPT_LATIN, "Malay", "may", "ms", "msa"},
+        {LANG_THA, SCRIPT_THAI, "Thai", "tha", "th", nullptr},
+        {LANG_VIE, SCRIPT_LATIN, "Vietnamese", "vie", "vi", nullptr},
+        {LANG_GLE, SCRIPT_LATIN, "Irish", "gle", "ga", nullptr},
+        {LANG_TGL, SCRIPT_LATIN, "Tagalog", "tgl", "tl", "fil"},
+        {LANG_HIN, SCRIPT_DEVANAGARI, "Hindi", "hin", "hi", nullptr},
+        {LANG_AFR, SCRIPT_LATIN, "Afrikaans", "afr", "af", nullptr},
+        {LANG_URD, SCRIPT_ARABIC, "Urdu", "urd", "ur", nullptr},
+        {LANG_MYA, SCRIPT_MYANMAR, "Burmese", "mya", "my", nullptr},
+        {LANG_KHM, SCRIPT_KHMER, "Khmer", "khm", "km", nullptr},
+        {LANG_LAO, SCRIPT_LAO, "Lao", "lao", "lo", "Laotian, Laothian"},
+        {LANG_TAM, SCRIPT_TAMIL, "Tamil", "tam", "ta", nullptr},
+        {LANG_BEN, SCRIPT_BENGALI, "Bengali", "ben", "bn", nullptr},
+        {LANG_GUJ, SCRIPT_GUJARATI, "Gujarati", "guj", "gu", nullptr},
+        {LANG_KAN, SCRIPT_KANNADA, "Kannada", "kan", "kn", nullptr},
+        {LANG_PAN, SCRIPT_GURMUKHI, "Punjabi", "pan", "pa", nullptr},
+        {LANG_SIN, SCRIPT_SINHALA, "Sinhalese", "sin", "si", nullptr},
+        {LANG_SWA, SCRIPT_LATIN, "Swahili", "swa", "sw", nullptr},
+        {LANG_BAQ, SCRIPT_LATIN, "Basque", "baq", "eu", "eus"},
+        {LANG_WEL, SCRIPT_LATIN, "Welsh", "wel", "cy", "cym"},
+        {LANG_GLG, SCRIPT_LATIN, "Galician", "glg", "gl", nullptr},
+        {LANG_HAT, SCRIPT_LATIN, "Haitian Creole", "hat", "ht", "Haitian"},
+        {LANG_MLG, SCRIPT_LATIN, "Malagasy", "mlg", "mg", nullptr},
+        {LANG_CHV, SCRIPT_CYRILLIC, "Chuvash", "chv", "cv", nullptr},
+        {LANG_UDM, SCRIPT_CYRILLIC, "Udmurt", "udm", "udm", nullptr},
+        {LANG_KPV, SCRIPT_CYRILLIC, "Komi-Zyrian", "kpv", "kv", "Komi, kom"},
+        {LANG_MHR, SCRIPT_CYRILLIC, "Meadow Mari", "mhr", "mhr", "EasternMari, Mari, chm"},
+        {LANG_SJN, SCRIPT_LATIN, "Sindarin", "sjn", "sjn", nullptr},
+        {LANG_MRJ, SCRIPT_CYRILLIC, "Hill Mari", "mrj", "mrj", "WesternMari"},
+        {LANG_KOI, SCRIPT_CYRILLIC, "Komi-Permyak", "koi", "koi", nullptr},
+        {LANG_LTZ, SCRIPT_LATIN, "Luxembourgish", "ltz", "lb", "Luxemburgish"},
+        {LANG_GLA, SCRIPT_LATIN, "Scottish Gaelic", "gla", "gd", "Gaelic"},
+        {LANG_CEB, SCRIPT_LATIN, "Cebuano", "ceb", "ceb", "Bisaya, Binisaya, Visayan"},
+        {LANG_PUS, SCRIPT_ARABIC, "Pashto", "pus", "ps", nullptr},
+        {LANG_KMR, SCRIPT_LATIN, "Kurmanji", "kmr", "ku", "Kurdish"},
+        {LANG_AMH, SCRIPT_ETHIOPIC, "Amharic", "amh", "am", nullptr},
+        {LANG_ZUL, SCRIPT_LATIN, "Zulu", "zul", "zu", nullptr},
+        {LANG_IBO, SCRIPT_LATIN, "Igbo", "ibo", "ig", "Ibo"},
+        {LANG_YOR, SCRIPT_LATIN, "Yoruba", "yor", "yo", nullptr},
+        {LANG_COS, SCRIPT_LATIN, "Corsican", "cos", "co", nullptr},
+        {LANG_XHO, SCRIPT_LATIN, "Xhosa", "xho", "xh", nullptr},
+        {LANG_JAV, SCRIPT_LATIN, "Javanese", "jav", "jv", nullptr}, // Also SCRIPT_JAVANESE and SCRIPT_ARABIC
+        {LANG_NEP, SCRIPT_DEVANAGARI, "Nepali", "nep", "ne", nullptr},
+        {LANG_SND, SCRIPT_DEVANAGARI, "Sindhi", "snd", "sd", nullptr}, // Also SCRIPT_ARABIC and SCRIPT_GUJARATI
+        {LANG_SOM, SCRIPT_LATIN, "Somali", "som", "so", nullptr},
+        {LANG_EPO, SCRIPT_LATIN, "Esperanto", "epo", "eo", nullptr},
+        {LANG_TEL, SCRIPT_TELUGU, "Telugu", "tel", "te", nullptr},
+        {LANG_MAR, SCRIPT_DEVANAGARI, "Marathi", "mar", "mr", nullptr},
+        {LANG_HAU, SCRIPT_LATIN, "Hausa", "hau", "ha", nullptr},
+        {LANG_YID, SCRIPT_HEBREW, "Yiddish", "yid", "yi", nullptr},
+        {LANG_MAL, SCRIPT_MALAYALAM, "Malayalam", "mal", "ml", nullptr},
+        {LANG_MAO, SCRIPT_LATIN, "Maori", "mao", "mi", "mri"},
+        {LANG_SUN, SCRIPT_LATIN, "Sundanese", "sun", "su", nullptr},
+        {LANG_PAP, SCRIPT_LATIN, "Papiamento", "pap", "pap", nullptr},
+        {LANG_UZB_CYR, SCRIPT_CYRILLIC, "Cyrillic Uzbek", "uzbcyr", "uz-Cyrl", nullptr}, // https://tools.ietf.org/html/rfc5646
+        {LANG_TRANSCR_IPA, SCRIPT_LATIN, "International Phonetic Alphabet Transcription", "ipa", "tr-ipa", nullptr},
+        {LANG_EMJ, SCRIPT_LATIN, "Emoji", "emj", "emj", nullptr},
+        {LANG_UYG, SCRIPT_ARABIC, "Uyghur", "uig", "ug", nullptr},
+        {LANG_BRE, SCRIPT_LATIN, "Breton", "bre", "br", nullptr},
+        {LANG_SAH, SCRIPT_CYRILLIC, "Yakut", "sah", "sah", nullptr},
+        {LANG_KAZ_LAT, SCRIPT_LATIN, "Latin Kazakh", "kazlat", "kk-Latn", nullptr},
+    };
+
+    static_assert(static_cast<size_t>(LANG_MAX) == Y_ARRAY_SIZE(LanguageNameAndEnum), "Size doesn't match");
+
+    class TLanguagesMap {
+    private:
+        static const char* const EMPTY_NAME;
+
+        using TNamesHash = THashMap<TStringBuf, ELanguage, TCIOps, TCIOps>;
+        TNamesHash Hash;
+
+        using TNamesArray = std::array<const char*, static_cast<size_t>(LANG_MAX)>;
+        TNamesArray BiblioNames;
+        TNamesArray IsoNames;
+        TNamesArray FullNames;
+
+        using TScripts = std::array<EScript, static_cast<size_t>(LANG_MAX)>;
+        TScripts Scripts;
+
+    private:
+        void AddNameToHash(const TStringBuf& name, ELanguage language) {
+            if (Hash.find(name) != Hash.end()) {
+                Y_ASSERT(Hash.find(name)->second == language);
+                return;
+            }
+
+            Hash[name] = language;
+        }
+
+        void AddName(const char* name, ELanguage language, TNamesArray& names) {
+            if (name == nullptr || strlen(name) == 0)
+                return;
+
+            Y_ASSERT(names[language] == EMPTY_NAME);
+            names[language] = name;
+
+            AddNameToHash(name, language);
+        }
+
+        void AddSynonyms(const char* syn, ELanguage language) {
+            static const char* del = " ,;";
+            if (!syn)
+                return;
+            while (*syn) {
+                size_t len = strcspn(syn, del);
+                AddNameToHash(TStringBuf(syn, len), language);
+                syn += len;
+                while (*syn && strchr(del, *syn))
+                    ++syn;
+            }
+        }
+
+    public:
+        TLanguagesMap() {
+            BiblioNames.fill(EMPTY_NAME);
+            IsoNames.fill(EMPTY_NAME);
+            FullNames.fill(EMPTY_NAME);
+            Scripts.fill(SCRIPT_OTHER);
+
+            for (size_t i = 0; i != Y_ARRAY_SIZE(LanguageNameAndEnum); ++i) {
+                const TLanguageNameAndEnum& val = LanguageNameAndEnum[i];
+
+                ELanguage language = val.Language;
+
+                AddName(val.BiblioName, language, BiblioNames);
+                AddName(val.IsoName, language, IsoNames);
+                AddName(val.EnglishName, language, FullNames);
+                AddSynonyms(val.Synonyms, language);
+
+                if (Scripts[language] == SCRIPT_OTHER) {
+                    Scripts[language] = val.Script;
+                }
+            }
+        }
+
+    public:
+        inline ELanguage LanguageByName(const TStringBuf& name, ELanguage def) const {
+            if (!name)
+                return def;
+
+            TNamesHash::const_iterator i = Hash.find(name);
+            if (i == Hash.end()) {
+                // Try to extract the primary language code from constructions like "en-cockney" or "zh_Hant"
+                size_t dash_pos = name.find_first_of("_-");
+                if (dash_pos != TStringBuf::npos)
+                    i = Hash.find(name.substr(0, dash_pos));
+                if (i == Hash.end())
+                    return def;
+            }
+
+            return i->second;
+        }
+
+        inline const char* FullNameByLanguage(ELanguage language) const {
+            if (language < 0 || static_cast<size_t>(language) >= FullNames.size())
+                return nullptr;
+
+            return FullNames[language];
+        }
+        inline const char* BiblioNameByLanguage(ELanguage language) const {
+            if (language < 0 || static_cast<size_t>(language) >= BiblioNames.size())
+                return nullptr;
+
+            return BiblioNames[language];
+        }
+        inline const char* IsoNameByLanguage(ELanguage language) const {
+            if (language < 0 || static_cast<size_t>(language) >= IsoNames.size())
+                return nullptr;
+
+            return IsoNames[language];
+        }
+
+        inline EScript Script(ELanguage language) const {
+            return Scripts[language];
+        }
+    };
+}
+
+const char* const TLanguagesMap::EMPTY_NAME = "";
+
+const char* FullNameByLanguage(ELanguage language) {
+    return Singleton<TLanguagesMap>()->FullNameByLanguage(language);
+}
+const char* NameByLanguage(ELanguage language) {
+    return Singleton<TLanguagesMap>()->BiblioNameByLanguage(language);
+}
+const char* IsoNameByLanguage(ELanguage language) {
+    return Singleton<TLanguagesMap>()->IsoNameByLanguage(language);
+}
+
+ELanguage LanguageByNameStrict(const TStringBuf& name) {
+    return Singleton<TLanguagesMap>()->LanguageByName(name, LANG_MAX);
+}
+
+ELanguage LanguageByNameOrDie(const TStringBuf& name) {
+    ELanguage result = LanguageByNameStrict(name);
+    if (result == LANG_MAX) {
+        ythrow yexception() << "LanguageByNameOrDie: invalid language '" << name << "'";
+    }
+    return result;
+}
+
+ELanguage LanguageByName(const TStringBuf& name) {
+    return Singleton<TLanguagesMap>()->LanguageByName(name, LANG_UNK);
+}
+
+EScript ScriptByLanguage(ELanguage language) {
+    return Singleton<TLanguagesMap>()->Script(language);
+}
+
+namespace {
+    const size_t MAX_GLYPH = 0x10000;
+    class TScriptGlyphIndex {
+    public:
+        TScriptGlyphIndex() {
+            NCharsetInternal::InitScriptData(Data, MAX_GLYPH);
+        }
+
+        EScript GetGlyphScript(wchar32 glyph) const {
+            if (glyph >= MAX_GLYPH)
+                return SCRIPT_UNKNOWN;
+            return (EScript)Data[glyph];
+        }
+
+    private:
+        ui8 Data[MAX_GLYPH];
+    };
+}
+
+EScript ScriptByGlyph(wchar32 glyph) {
+    return HugeSingleton<TScriptGlyphIndex>()->GetGlyphScript(glyph);
+}
+
+template <>
+void Out<ELanguage>(IOutputStream& o, ELanguage lang) {
+    o << NameByLanguage(lang);
+}
diff --git a/library/cpp/langs/langs.h b/library/cpp/langs/langs.h
new file mode 100644
index 0000000000..360ab6a832
--- /dev/null
+++ b/library/cpp/langs/langs.h
@@ -0,0 +1,229 @@
+#pragma once
+
+#include "scripts.h"
+
+#include <util/generic/strbuf.h>
+#include <util/system/defaults.h>
+
+#if defined(_win_)
+// LANG_LAO is #define in WinNT.h
+#undef LANG_LAO
+#endif
+
+// Language names are given according to ISO 639-2/B
+// Some languages are not present in ISO 639-2/B. Then ISO 639-3 is used.
+// http://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
+enum ELanguage {
+    LANG_UNK = 0,           // Unknown
+    LANG_RUS = 1,           // Russian
+    LANG_ENG = 2,           // English
+    LANG_POL = 3,           // Polish
+    LANG_HUN = 4,           // Hungarian
+    LANG_UKR = 5,           // Ukrainian
+    LANG_GER = 6,           // German
+    LANG_FRE = 7,           // French
+    LANG_TAT = 8,           // Tatar
+    LANG_BEL = 9,           // Belarusian
+    LANG_KAZ = 10,          // Kazakh
+    LANG_ALB = 11,          // Albanian
+    LANG_SPA = 12,          // Spanish
+    LANG_ITA = 13,          // Italian
+    LANG_ARM = 14,          // Armenian
+    LANG_DAN = 15,          // Danish
+    LANG_POR = 16,          // Portuguese
+    LANG_ICE = 17,          // Icelandic
+    LANG_SLO = 18,          // Slovak
+    LANG_SLV = 19,          // Slovene
+    LANG_DUT = 20,          // Dutch (Netherlandish language)
+    LANG_BUL = 21,          // Bulgarian
+    LANG_CAT = 22,          // Catalan
+    LANG_HRV = 23,          // Croatian
+    LANG_CZE = 24,          // Czech
+    LANG_GRE = 25,          // Greek
+    LANG_HEB = 26,          // Hebrew
+    LANG_NOR = 27,          // Norwegian
+    LANG_MAC = 28,          // Macedonian
+    LANG_SWE = 29,          // Swedish
+    LANG_KOR = 30,          // Korean
+    LANG_LAT = 31,          // Latin
+    LANG_BASIC_RUS = 32,    // Simplified version of Russian (used at lemmer only)
+    LANG_BOS = 33,          // Bosnian
+    LANG_MLT = 34,          // Maltese
+    LANG_EMPTY = 35,        // Indicate that document is empty
+    LANG_UNK_LAT = 36,      // Any unrecognized latin language
+    LANG_UNK_CYR = 37,      // Any unrecognized cyrillic language
+    LANG_UNK_ALPHA = 38,    // Any unrecognized alphabetic language not fit into previous categories
+    LANG_FIN = 39,          // Finnish
+    LANG_EST = 40,          // Estonian
+    LANG_LAV = 41,          // Latvian
+    LANG_LIT = 42,          // Lithuanian
+    LANG_BAK = 43,          // Bashkir
+    LANG_TUR = 44,          // Turkish
+    LANG_RUM = 45,          // Romanian (also Moldavian)
+    LANG_MON = 46,          // Mongolian
+    LANG_UZB = 47,          // Uzbek
+    LANG_KIR = 48,          // Kirghiz
+    LANG_TGK = 49,          // Tajik
+    LANG_TUK = 50,          // Turkmen
+    LANG_SRP = 51,          // Serbian
+    LANG_AZE = 52,          // Azerbaijani
+    LANG_BASIC_ENG = 53,    // Simplified version of English (used at lemmer only)
+    LANG_GEO = 54,          // Georgian
+    LANG_ARA = 55,          // Arabic
+    LANG_PER = 56,          // Persian
+    LANG_CHU = 57,          // Church Slavonic
+    LANG_CHI = 58,          // Chinese
+    LANG_JPN = 59,          // Japanese
+    LANG_IND = 60,          // Indonesian
+    LANG_MAY = 61,          // Malay
+    LANG_THA = 62,          // Thai
+    LANG_VIE = 63,          // Vietnamese
+    LANG_GLE = 64,          // Irish (Gaelic)
+    LANG_TGL = 65,          // Tagalog (Filipino)
+    LANG_HIN = 66,          // Hindi
+    LANG_AFR = 67,          // Afrikaans
+    LANG_URD = 68,          // Urdu
+    LANG_MYA = 69,          // Burmese
+    LANG_KHM = 70,          // Khmer
+    LANG_LAO = 71,          // Lao
+    LANG_TAM = 72,          // Tamil
+    LANG_BEN = 73,          // Bengali
+    LANG_GUJ = 74,          // Gujarati
+    LANG_KAN = 75,          // Kannada
+    LANG_PAN = 76,          // Punjabi
+    LANG_SIN = 77,          // Sinhalese
+    LANG_SWA = 78,          // Swahili
+    LANG_BAQ = 79,          // Basque
+    LANG_WEL = 80,          // Welsh
+    LANG_GLG = 81,          // Galician
+    LANG_HAT = 82,          // Haitian Creole
+    LANG_MLG = 83,          // Malagasy
+    LANG_CHV = 84,          // Chuvash
+    LANG_UDM = 85,          // Udmurt
+    LANG_KPV = 86,          // Komi-Zyrian
+    LANG_MHR = 87,          // Meadow Mari (Eastern Mari)
+    LANG_SJN = 88,          // Sindarin
+    LANG_MRJ = 89,          // Hill Mari (Western Mari)
+    LANG_KOI = 90,          // Komi-Permyak
+    LANG_LTZ = 91,          // Luxembourgish
+    LANG_GLA = 92,          // Scottish Gaelic
+    LANG_CEB = 93,          // Cebuano
+    LANG_PUS = 94,          // Pashto
+    LANG_KMR = 95,          // Kurmanji
+    LANG_AMH = 96,          // Amharic
+    LANG_ZUL = 97,          // Zulu
+    LANG_IBO = 98,          // Igbo
+    LANG_YOR = 99,          // Yoruba
+    LANG_COS = 100,         // Corsican
+    LANG_XHO = 101,         // Xhosa
+    LANG_JAV = 102,         // Javanese
+    LANG_NEP = 103,         // Nepali
+    LANG_SND = 104,         // Sindhi
+    LANG_SOM = 105,         // Somali
+    LANG_EPO = 106,         // Esperanto
+    LANG_TEL = 107,         // Telugu
+    LANG_MAR = 108,         // Marathi
+    LANG_HAU = 109,         // Hausa
+    LANG_YID = 110,         // Yiddish
+    LANG_MAL = 111,         // Malayalam
+    LANG_MAO = 112,         // Maori
+    LANG_SUN = 113,         // Sundanese
+    LANG_PAP = 114,         // Papiamento
+    LANG_UZB_CYR = 115,     // Cyrillic Uzbek
+    LANG_TRANSCR_IPA = 116, // International Phonetic Alphabet Transcription
+    LANG_EMJ = 117,         // Emoji
+    LANG_UYG = 118,         // Uyghur
+    LANG_BRE = 119,         // Breton
+    LANG_SAH = 120,         // Yakut
+    LANG_KAZ_LAT = 121,     // Latin Kazakh
+    LANG_MAX
+};
+
+/**
+ * Converts string to corresponding enum. Will try to extract the primary language code from
+ * constructions like "en-cockney" or "zh_Hant". In case of failure will return `LANG_UNK`.
+ *
+ * @param name              Language name
+ * @return                  Language enum
+ */
+ELanguage LanguageByName(const TStringBuf& name);
+
+/**
+ * Same as `LanguageByName`, but in case of failure will return `LANG_MAX`.
+ *
+ * @see LanguageByName
+ */
+ELanguage LanguageByNameStrict(const TStringBuf& name);
+
+/**
+ * Converts language enum to corresponding ISO 639-2/B alpha-3 code. For languages missing in ISO
+ * standard convertions are:
+ *   - LANG_UNK:          "unk"
+ *   - LANG_BASIC_RUS:    "basic-rus"
+ *   - LANG_EMPTY:        "empty"
+ *   - LANG_UNK_LAT:      "unklat"
+ *   - LANG_UNK_CYR:      "unkcyr"
+ *   - LANG_UNK_ALPHA:    "unkalpha"
+ *   - LANG_BASIC_ENG:    "basic-eng"
+ *   - LANG_TRANSCR_IPA   "transcr-ipa"
+ * If language is missing in `ELanguage` or if it is a `LANG_MAX` then return value will be
+ * `nullptr`.
+ *
+ * @param language         Language enum
+ * @return                 Language ISO 639-2/B alpha-3 code
+ */
+const char* NameByLanguage(ELanguage language);
+
+/**
+ * Converts language enum to corresponding ISO 639-1 alpha-2 code. For languages missing in ISO
+ * standard convertions are:
+ *   - LANG_UNK:          "mis"
+ *   - LANG_BASIC_RUS:    "bas-ru"
+ *   - LANG_EMPTY:        ""
+ *   - LANG_UNK_LAT:      ""
+ *   - LANG_UNK_CYR:      ""
+ *   - LANG_UNK_ALPHA:    ""
+ *   - LANG_BASIC_ENG:    "bas-en"
+ *   - LANG_TRANSCR_IPA   "tr-ipa"
+ * If language is missing in `ELanguage` or if it is a `LANG_MAX` then return value will be
+ * `nullptr`.
+ *
+ * @param language         Language enum
+ * @return                 Language ISO 639-1 alpha-2 code
+ */
+const char* IsoNameByLanguage(ELanguage language);
+
+/**
+ * Converts language enum to corresponding human-readable language name. E.g. "Russian" for
+ * `LANG_RUS` or "Basic Russian" for `LANG_BASIC_RUS`. If language is missing in `ELanguage` or if
+ * it is a `LANG_MAX` then return value will be `nullptr`.
+ *
+ * @param language         Language enum
+ */
+const char* FullNameByLanguage(ELanguage language);
+
+/**
+ * Same as `LanguageByNameStrict` but in case of failure will throw `yexception`.
+ *
+ * @see LanguageByNameStrict
+ */
+ELanguage LanguageByNameOrDie(const TStringBuf& name);
+
+constexpr bool UnknownLanguage(const ELanguage language) noexcept {
+    return language == LANG_UNK || language == LANG_UNK_LAT || language == LANG_UNK_CYR || language == LANG_UNK_ALPHA || language == LANG_EMPTY;
+}
+
+EScript ScriptByLanguage(ELanguage language);
+EScript ScriptByGlyph(wchar32 glyph);
+
+namespace NCharsetInternal {
+    void InitScriptData(ui8 data[], size_t len);
+}
+
+inline bool LatinScript(ELanguage language) {
+    return ScriptByLanguage(language) == SCRIPT_LATIN;
+}
+
+inline bool CyrillicScript(ELanguage language) {
+    return ScriptByLanguage(language) == SCRIPT_CYRILLIC;
+}
diff --git a/library/cpp/langs/scripts.cpp b/library/cpp/langs/scripts.cpp
new file mode 100644
index 0000000000..41cc91d3ce
--- /dev/null
+++ b/library/cpp/langs/scripts.cpp
@@ -0,0 +1,158 @@
+#include "scripts.h"
+
+#include <library/cpp/digest/lower_case/hash_ops.h>
+
+#include <util/generic/hash.h>
+#include <util/generic/singleton.h>
+#include <util/generic/strbuf.h>
+#include <util/generic/yexception.h>
+#include <util/system/defaults.h>
+
+#include <array>
+
+namespace {
+    struct TScriptNameAndEnum {
+        EScript Script;
+        const char* EnglishName;
+        const char* IsoName;
+    };
+
+    const TScriptNameAndEnum ScriptNameAndEnum[] = {
+        {SCRIPT_UNKNOWN, "Unknown", "Zzzz"},
+        {SCRIPT_LATIN, "Latin", "Latn"},
+        {SCRIPT_CYRILLIC, "Cyrillic", "Cyrl"},
+
+        {SCRIPT_GREEK, "Greek", "Grek"},
+        {SCRIPT_ARABIC, "Arabic", "Arab"},
+        {SCRIPT_HEBREW, "Hebrew", "Hebr"},
+        {SCRIPT_ARMENIAN, "Armenian", "Armn"},
+        {SCRIPT_GEORGIAN, "Georgian", "Geor"},
+
+        {SCRIPT_HAN, "Han", "Hans"}, // We use more common Simpliied variant (as opposed to Traditional 'Hant')
+        {SCRIPT_KATAKANA, "Katakana", "Kana"},
+        {SCRIPT_HIRAGANA, "Hiragana", "Hira"},
+        {SCRIPT_HANGUL, "Hangul", "Hang"},
+
+        {SCRIPT_DEVANAGARI, "Devanagari", "Deva"},
+        {SCRIPT_BENGALI, "Bengali", "Beng"},
+        {SCRIPT_GUJARATI, "Gujarati", "Gujr"},
+        {SCRIPT_GURMUKHI, "Gurmukhi", "Guru"},
+        {SCRIPT_KANNADA, "Kannada", "Knda"},
+        {SCRIPT_MALAYALAM, "Malayalam", "Mlym"},
+        {SCRIPT_ORIYA, "Oriya", "Orya"},
+        {SCRIPT_TAMIL, "Tamil", "Taml"},
+        {SCRIPT_TELUGU, "Telugu", "Telu"},
+        {SCRIPT_THAANA, "Thaana", "Thaa"},
+        {SCRIPT_SINHALA, "Sinhala", "Sinh"},
+
+        {SCRIPT_MYANMAR, "Myanmar", "Mymr"},
+        {SCRIPT_THAI, "Thai", "Thai"},
+        {SCRIPT_LAO, "Lao", "Laoo"},
+        {SCRIPT_KHMER, "Khmer", "Khmr"},
+        {SCRIPT_TIBETAN, "Tibetan", "Tibt"},
+        {SCRIPT_MONGOLIAN, "Mongolian", "Mong"},
+
+        {SCRIPT_ETHIOPIC, "Ethiopic", "Ethi"},
+        {SCRIPT_RUNIC, "Runic", "Runr"},
+        {SCRIPT_COPTIC, "Coptic", "Copt"},
+        {SCRIPT_SYRIAC, "Syriac", "Syrc"},
+
+        {SCRIPT_OTHER, "Other", "Zyyy"},
+    };
+
+    static_assert(static_cast<size_t>(SCRIPT_MAX) == Y_ARRAY_SIZE(ScriptNameAndEnum), "Size doesn't match");
+
+    class TScriptsMap {
+    private:
+        static const char* const EMPTY_NAME;
+
+        using TNamesHash = THashMap<TStringBuf, EScript, TCIOps, TCIOps>;
+        TNamesHash Hash;
+
+        using TNamesArray = std::array<const char*, static_cast<size_t>(SCRIPT_MAX)>;
+        TNamesArray IsoNames;
+        TNamesArray FullNames;
+
+    private:
+        void AddNameToHash(const TStringBuf& name, EScript script) {
+            if (Hash.find(name) != Hash.end()) {
+                Y_ASSERT(Hash.find(name)->second == script);
+                return;
+            }
+
+            Hash[name] = script;
+        }
+
+        void AddName(const char* name, EScript script, TNamesArray& names) {
+            if (name == nullptr || strlen(name) == 0)
+                return;
+
+            Y_ASSERT(names[script] == EMPTY_NAME);
+            names[script] = name;
+
+            AddNameToHash(name, script);
+        }
+
+    public:
+        TScriptsMap() {
+            IsoNames.fill(EMPTY_NAME);
+            FullNames.fill(EMPTY_NAME);
+
+            for (const auto& val : ScriptNameAndEnum) {
+                EScript script = val.Script;
+
+                AddName(val.IsoName, script, IsoNames);
+                AddName(val.EnglishName, script, FullNames);
+            }
+        }
+
+    public:
+        inline EScript ScriptByName(const TStringBuf& name, EScript def) const {
+            if (!name)
+                return def;
+
+            TNamesHash::const_iterator i = Hash.find(name);
+            if (i == Hash.end()) {
+                return def;
+            }
+
+            return i->second;
+        }
+
+        inline const char* FullNameByScript(EScript script) const {
+            if (script < 0 || static_cast<size_t>(script) >= FullNames.size())
+                return nullptr;
+
+            return FullNames[script];
+        }
+
+        inline const char* IsoNameByScript(EScript script) const {
+            if (script < 0 || static_cast<size_t>(script) >= IsoNames.size())
+                return nullptr;
+
+            return IsoNames[script];
+        }
+    };
+}
+
+const char* const TScriptsMap::EMPTY_NAME = "";
+
+const char* FullNameByScript(EScript script) {
+    return Singleton<TScriptsMap>()->FullNameByScript(script);
+}
+
+const char* IsoNameByScript(EScript script) {
+    return Singleton<TScriptsMap>()->IsoNameByScript(script);
+}
+
+EScript ScriptByName(const TStringBuf& name) {
+    return Singleton<TScriptsMap>()->ScriptByName(name, SCRIPT_UNKNOWN);
+}
+
+EScript ScriptByNameOrDie(const TStringBuf& name) {
+    EScript result = ScriptByName(name);
+    if (result == SCRIPT_UNKNOWN) {
+        ythrow yexception() << "ScriptByNameOrDie: invalid script '" << name << "'";
+    }
+    return result;
+}
diff --git a/library/cpp/langs/scripts.h b/library/cpp/langs/scripts.h
new file mode 100644
index 0000000000..4c47a33d2c
--- /dev/null
+++ b/library/cpp/langs/scripts.h
@@ -0,0 +1,56 @@
+#pragma once
+
+#include <util/generic/strbuf.h>
+
+// Writing systems, a.k.a. scripts
+//
+enum EScript {
+    SCRIPT_UNKNOWN = 0,
+    SCRIPT_LATIN,
+    SCRIPT_CYRILLIC,
+
+    SCRIPT_GREEK,
+    SCRIPT_ARABIC,
+    SCRIPT_HEBREW,
+    SCRIPT_ARMENIAN,
+    SCRIPT_GEORGIAN,
+
+    SCRIPT_HAN,
+    SCRIPT_KATAKANA,
+    SCRIPT_HIRAGANA,
+    SCRIPT_HANGUL,
+
+    SCRIPT_DEVANAGARI,
+    SCRIPT_BENGALI,
+    SCRIPT_GUJARATI,
+    SCRIPT_GURMUKHI,
+    SCRIPT_KANNADA,
+    SCRIPT_MALAYALAM,
+    SCRIPT_ORIYA,
+    SCRIPT_TAMIL,
+    SCRIPT_TELUGU,
+    SCRIPT_THAANA,
+    SCRIPT_SINHALA,
+
+    SCRIPT_MYANMAR,
+    SCRIPT_THAI,
+    SCRIPT_LAO,
+    SCRIPT_KHMER,
+    SCRIPT_TIBETAN,
+    SCRIPT_MONGOLIAN,
+
+    SCRIPT_ETHIOPIC,
+    SCRIPT_RUNIC,
+    SCRIPT_COPTIC,
+    SCRIPT_SYRIAC,
+
+    SCRIPT_OTHER,
+    SCRIPT_MAX
+};
+
+// According to ISO 15924 codes. See https://en.wikipedia.org/wiki/ISO_15924
+//
+EScript ScriptByName(const TStringBuf& name);
+EScript ScriptByNameOrDie(const TStringBuf& name);
+const char* IsoNameByScript(EScript script);
+const char* FullNameByScript(EScript script);