blob: 64477e54b78c894b9d2af2de6a3d55766c8e683c [file] [log] [blame]
# ScriptMetadata.txt
# Copyright © 1991-2016 Unicode, Inc.
# CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
# For terms of use, see http://www.unicode.org/copyright.html
#
# This file provides general information about scripts that may be useful to implementations processing text.
# The information is the best currently available, and may change between versions of CLDR.
#
# Format:
# The data is not in XML; instead it uses the semicolon-delimited format from the Unicode Character Database (UCD).
# This is so that parsers of the UCD can more easily be adapted to read the data.
# Additional fields may be added in future versions; parsers may be designed to ignore those fields until they are revised.
#
# Field - Description
#
# 0 - Script Identifier
# 1 - Web Rank:
# The approximate rank of this script from a large sample of the web,
# in terms of the number of characters found in that script.
# Below 32 the ranking is not statistically significant.
# 2 - Sample Character:
# A sample character for use in "Last Resort" style fonts.
# For printing the combining mark for Zinh in a chart, U+25CC can be prepended.
# See http://unicode.org/policies/lastresortfont_eula.html
# 3 - Origin country:
# The approximate area where the script originated, expressed as a BCP47 region code.
# 4 - Density:
# The approximate information density of characters in this script, based on comparison of bilingual texts.
# 5 - ID Usage:
# The usage for IDs (tables 4-7) according to UAX #31.
# For a description of values, see
# http://unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers
# 6 - RTL:
# YES if the script is RTL
# Derived from whether the script contains RTL letters according to the Bidi_Class property
# 7 - LB letters:
# YES if the major languages using the script allow linebreaks between letters (excluding hyphenation).
# Derived from LB property.
# 8 - Shaping Required:
# YES if shaping is required for the major languages using that script for NFC text.
# This includes not only ligation (and Indic conjuncts), Indic vowel splitting/reordering, and
# Arabic-style contextual shaping, but also cases where NSM placement is required, like Thai.
# MIN if NSM placement is sufficient, not the more complex shaping.
# The NSM placement may only be necessary for some major languages using the script.
# 9 - Input Method Engine Required:
# YES if the major languages using the script require IMEs.
# In particular, users (of languages for that script) would be accustomed to using IMEs (such as Japanese)
# and typical commercial products for those languages would need IME support in order to be competitive.
# 10- Cased
# YES if in modern (or most recent) usage case distinctions are customary.
#
# Sometimes a script is included here before it is added in the Unicode Standard.
# Such scripts are marked with a "provisional" comment.
#
# Note: For the most likely language for each script, see
# http://unicode.org/repos/cldr-tmp/trunk/diff/supplemental/likely_subtags.html
#
Zyyy; 1; 0040; ZZ; -1; RECOMMENDED; UNKNOWN; UNKNOWN; UNKNOWN; UNKNOWN; UNKNOWN
Latn; 2; 004C; IT; 1; RECOMMENDED; NO; NO; MIN; NO; YES
Hanb; 3; 5B57; CN; 3; RECOMMENDED; NO; YES; NO; YES; NO
Hani; 3; 5B57; CN; 3; RECOMMENDED; NO; YES; NO; YES; NO
Hans; 3; 5B57; CN; 3; RECOMMENDED; NO; YES; NO; YES; NO
Hant; 3; 5B57; CN; 3; RECOMMENDED; NO; YES; NO; YES; NO
Cyrl; 4; 042F; BG; 1; RECOMMENDED; NO; NO; MIN; NO; YES
Hira; 5; 304B; JP; 2; RECOMMENDED; NO; YES; NO; NO; NO
Jpan; 5; 304B; JP; 2; RECOMMENDED; NO; YES; NO; YES; NO
Kana; 6; 30AB; JP; 2; RECOMMENDED; NO; YES; NO; NO; NO
Thai; 7; 0E17; TH; 1; RECOMMENDED; NO; YES; MIN; NO; NO
Arab; 8; 0628; SA; 1; RECOMMENDED; YES; NO; YES; NO; NO
Hang; 9; AC00; KR; 3; RECOMMENDED; NO; NO; MIN; YES; NO
Jamo; 9; 1112; KR; 3; RECOMMENDED; NO; NO; MIN; YES; NO
Kore; 9; AC00; KR; 3; RECOMMENDED; NO; NO; MIN; YES; NO
Deva; 10; 0905; IN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Grek; 11; 03A9; GR; 1; RECOMMENDED; NO; NO; NO; NO; YES
Hebr; 12; 05D0; IL; 1; RECOMMENDED; YES; NO; NO; NO; NO
Taml; 13; 0B95; IN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Knda; 14; 0C95; IN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Geor; 15; 10D3; GE; 1; RECOMMENDED; NO; NO; NO; NO; NO
Mlym; 16; 0D15; IN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Telu; 17; 0C15; IN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Armn; 18; 0531; AM; 1; RECOMMENDED; NO; NO; NO; NO; YES
Mymr; 19; 1000; MM; 1; RECOMMENDED; NO; YES; YES; NO; NO
Gujr; 20; 0A95; IN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Beng; 21; 0995; BD; 1; RECOMMENDED; NO; NO; YES; NO; NO
Guru; 22; 0A15; IN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Laoo; 23; 0EA5; LA; 1; RECOMMENDED; NO; YES; YES; NO; NO
Zinh; 24; 0308; ZZ; -1; RECOMMENDED; UNKNOWN; UNKNOWN; MIN; UNKNOWN; UNKNOWN
Khmr; 25; 1780; KH; 1; RECOMMENDED; NO; YES; YES; NO; NO
Tibt; 27; 0F40; CN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Sinh; 28; 0D85; LK; 1; RECOMMENDED; NO; NO; YES; NO; NO
Ethi; 29; 12A0; ET; 2; RECOMMENDED; NO; NO; MIN; YES; NO
Thaa; 30; 078C; MV; 1; RECOMMENDED; YES; NO; YES; NO; NO
Orya; 31; 0B15; IN; 1; RECOMMENDED; NO; NO; YES; NO; NO
Zzzz; 32; FDD0; ZZ; -1; UNKNOWN; UNKNOWN; UNKNOWN; UNKNOWN; UNKNOWN; UNKNOWN
Adlm; 33; 1E909; GN; 1; LIMITED_USE; YES; NO; MIN; NO; YES
Aghb; 33; 10537; RU; 1; EXCLUSION; NO; NO; NO; NO; NO
Ahom; 33; 11717; IN; 1; EXCLUSION; NO; YES; YES; NO; NO
Armi; 33; 10840; IR; 1; EXCLUSION; YES; NO; NO; NO; NO
Avst; 33; 10B00; IR; 1; EXCLUSION; YES; NO; YES; NO; NO
Bali; 33; 1B05; ID; 1; LIMITED_USE; NO; NO; YES; NO; NO
Bamu; 33; A6A0; CM; 1; LIMITED_USE; NO; NO; MIN; YES; NO
Bass; 33; 16AE6; LR; 1; EXCLUSION; NO; NO; NO; NO; NO
Batk; 33; 1BC0; ID; 1; LIMITED_USE; NO; NO; YES; NO; NO
Bhks; 33; 11C0E; IN; 1; EXCLUSION; NO; NO; YES; NO; NO
Bopo; 33; 3105; CN; 2; RECOMMENDED; NO; YES; NO; NO; NO
Brah; 33; 11005; IN; 1; EXCLUSION; NO; NO; YES; NO; NO
Brai; 33; 280E; FR; -1; UNKNOWN; UNKNOWN; UNKNOWN; UNKNOWN; UNKNOWN; UNKNOWN
Bugi; 33; 1A00; ID; 1; EXCLUSION; NO; NO; MIN; NO; NO
Buhd; 33; 1743; PH; 1; EXCLUSION; NO; NO; YES; NO; NO
Cakm; 33; 11103; BD; 1; LIMITED_USE; NO; NO; YES; NO; NO
Cans; 33; 14C0; CA; 2; LIMITED_USE; NO; NO; NO; YES; NO
Cari; 33; 102A0; TR; 1; EXCLUSION; NO; NO; NO; NO; NO
Cham; 33; AA00; VN; 1; LIMITED_USE; NO; NO; YES; NO; NO
Cher; 33; 13C4; US; 2; LIMITED_USE; NO; NO; NO; NO; YES
Copt; 33; 03E2; EG; 1; EXCLUSION; NO; NO; MIN; NO; YES
Cprt; 33; 10800; CY; 1; EXCLUSION; YES; NO; NO; NO; NO
Dogr; 33; 1180B; IN; 1; EXCLUSION; NO; NO; YES; NO; NO
Dsrt; 33; 10414; US; 1; EXCLUSION; NO; NO; NO; NO; YES
Dupl; 33; 1BC20; FR; 1; EXCLUSION; NO; NO; NO; YES; NO
Egyp; 33; 13153; EG; 3; EXCLUSION; NO; NO; YES; YES; NO
Elba; 33; 10500; AL; 1; EXCLUSION; NO; NO; NO; NO; NO
Elym; 33; 10FF1; IR; 1; EXCLUSION; YES; NO; NO; NO; NO # provisional data for future Unicode 12.0 script
Glag; 33; 2C00; BG; 1; EXCLUSION; NO; NO; NO; NO; YES
Gong; 33; 11D71; IN; 1; LIMITED_USE; NO; NO; YES; NO; NO
Gonm; 33; 11D10; IN; 1; EXCLUSION; NO; NO; YES; NO; NO
Goth; 33; 10330; UA; 1; EXCLUSION; NO; NO; NO; NO; NO
Gran; 33; 11315; IN; 1; EXCLUSION; NO; NO; NO; NO; NO
Hano; 33; 1723; PH; 1; EXCLUSION; NO; NO; YES; NO; NO
Hatr; 33; 108F4; IQ; 1; EXCLUSION; YES; NO; NO; NO; NO
Hluw; 33; 14400; TR; 1; EXCLUSION; NO; NO; NO; YES; NO
Hmng; 33; 16B1C; LA; 1; EXCLUSION; NO; NO; NO; NO; NO
Hmnp; 33; 1E108; US; 1; LIMITED_USE; NO; NO; NO; NO; NO # provisional data for future Unicode 12.0 script
Hung; 33; 10CA1; HU; 1; EXCLUSION; YES; NO; NO; NO; YES
Ital; 33; 10300; IT; 1; EXCLUSION; NO; NO; NO; NO; NO
Java; 33; A984; ID; 1; LIMITED_USE; NO; NO; YES; NO; NO
Kali; 33; A90A; MM; 1; LIMITED_USE; NO; NO; MIN; NO; NO
Khar; 33; 10A00; PK; 1; EXCLUSION; YES; NO; YES; NO; NO
Khoj; 33; 11208; IN; 1; EXCLUSION; NO; NO; NO; NO; NO
Kthi; 33; 11083; IN; 1; EXCLUSION; NO; NO; MIN; NO; NO
Lana; 33; 1A20; TH; 1; LIMITED_USE; NO; YES; YES; NO; NO
Lepc; 33; 1C00; IN; 1; LIMITED_USE; NO; NO; YES; NO; NO
Limb; 33; 1900; IN; 1; LIMITED_USE; NO; NO; YES; NO; NO
Lina; 33; 10647; GR; 1; EXCLUSION; NO; NO; NO; YES; NO
Linb; 33; 10000; GR; 1; EXCLUSION; NO; NO; NO; YES; NO
Lisu; 33; A4D0; CN; 1; LIMITED_USE; NO; NO; NO; YES; NO
Lyci; 33; 10280; TR; 1; EXCLUSION; NO; NO; NO; NO; NO
Lydi; 33; 10920; TR; 1; EXCLUSION; YES; NO; NO; NO; NO
Mahj; 33; 11152; IN; 1; EXCLUSION; NO; NO; NO; NO; NO
Maka; 33; 11EE5; ID; 1; EXCLUSION; NO; NO; MIN; NO; NO
Mand; 33; 0840; IR; 1; LIMITED_USE; YES; NO; YES; NO; NO
Mani; 33; 10AD8; CN; 1; EXCLUSION; YES; NO; NO; NO; NO
Marc; 33; 11C72; CN; 1; EXCLUSION; NO; NO; YES; NO; NO
Medf; 33; 16E40; NG; 1; EXCLUSION; NO; NO; NO; NO; YES
Mend; 33; 1E802; SL; 1; EXCLUSION; YES; NO; NO; YES; NO
Merc; 33; 109A0; SD; 1; EXCLUSION; YES; NO; NO; NO; NO
Mero; 33; 10980; SD; 1; EXCLUSION; YES; NO; NO; NO; NO
Modi; 33; 1160E; IN; 1; EXCLUSION; NO; NO; NO; NO; NO
Mong; 33; 1826; MN; 1; EXCLUSION; NO; NO; YES; NO; NO
Mroo; 33; 16A4F; BD; 1; EXCLUSION; NO; NO; NO; NO; NO
Mtei; 33; ABC0; IN; 1; LIMITED_USE; NO; NO; YES; NO; NO
Mult; 33; 1128F; PK; 1; EXCLUSION; NO; NO; NO; NO; NO
Nand; 33; 119CE; IN; 1; EXCLUSION; NO; NO; YES; NO; NO # provisional data for future Unicode 12.0 script
Narb; 33; 10A95; SA; 1; EXCLUSION; YES; NO; NO; NO; NO
Nbat; 33; 10896; JO; 1; EXCLUSION; YES; NO; NO; NO; NO
Newa; 33; 11412; NP; 1; LIMITED_USE; NO; NO; YES; NO; NO
Nkoo; 33; 07CA; GN; 1; LIMITED_USE; YES; NO; YES; NO; NO
Nshu; 33; 1B1C4; CN; 2; EXCLUSION; NO; YES; NO; YES; NO
Ogam; 33; 168F; IE; 1; EXCLUSION; NO; NO; NO; NO; NO
Olck; 33; 1C5A; IN; 1; LIMITED_USE; NO; NO; NO; NO; NO
Orkh; 33; 10C00; MN; 1; EXCLUSION; YES; NO; NO; NO; NO
Osge; 33; 104B5; US; 1; LIMITED_USE; NO; NO; NO; NO; YES
Osma; 33; 10480; SO; 1; EXCLUSION; NO; NO; NO; NO; NO
Palm; 33; 10873; SY; 1; EXCLUSION; YES; NO; NO; NO; NO
Pauc; 33; 11AC0; MM; 1; EXCLUSION; NO; NO; NO; NO; NO
Perm; 33; 1036B; RU; 1; EXCLUSION; NO; NO; NO; NO; NO
Phag; 33; A840; CN; 1; EXCLUSION; NO; NO; YES; NO; NO
Phli; 33; 10B60; IR; 1; EXCLUSION; YES; NO; NO; NO; NO
Phlp; 33; 10B8F; CN; 1; EXCLUSION; YES; NO; NO; NO; NO
Phnx; 33; 10900; LB; 1; EXCLUSION; YES; NO; NO; NO; NO
Plrd; 33; 16F00; CN; 1; LIMITED_USE; NO; NO; YES; NO; NO
Prti; 33; 10B40; IR; 1; EXCLUSION; YES; NO; NO; NO; NO
Rjng; 33; A930; ID; 1; EXCLUSION; NO; NO; YES; NO; NO
Rohg; 33; 10D12; MM; 1; LIMITED_USE; YES; NO; YES; NO; NO
Runr; 33; 16A0; SE; 1; EXCLUSION; NO; NO; NO; NO; NO
Samr; 33; 0800; IL; 1; EXCLUSION; YES; NO; MIN; NO; NO
Sarb; 33; 10A60; YE; 1; EXCLUSION; YES; NO; NO; NO; NO
Saur; 33; A882; IN; 1; LIMITED_USE; NO; NO; YES; NO; NO
Sgnw; 33; 1D850; US; 1; EXCLUSION; NO; NO; NO; YES; NO
Shaw; 33; 10450; GB; 1; EXCLUSION; NO; NO; NO; NO; NO
Shrd; 33; 11183; IN; 1; EXCLUSION; NO; NO; YES; NO; NO
Sidd; 33; 1158E; IN; 1; EXCLUSION; NO; NO; NO; NO; NO
Sind; 33; 112BE; IN; 1; EXCLUSION; NO; NO; NO; NO; NO
Sogd; 33; 10F42; UZ; 1; EXCLUSION; YES; NO; YES; NO; NO
Sogo; 33; 10F19; UZ; 1; EXCLUSION; YES; NO; NO; NO; NO
Sora; 33; 110D0; IN; 1; EXCLUSION; NO; NO; NO; NO; NO
Soyo; 33; 11A5C; MN; 1; EXCLUSION; NO; NO; YES; NO; NO
Sund; 33; 1B83; ID; 1; LIMITED_USE; NO; NO; YES; NO; NO
Sylo; 33; A800; BD; 1; LIMITED_USE; NO; NO; YES; NO; NO
Syrc; 33; 0710; SY; 1; LIMITED_USE; YES; NO; YES; NO; NO
Tagb; 33; 1763; PH; 1; EXCLUSION; NO; NO; NO; NO; NO
Takr; 33; 11680; IN; 1; EXCLUSION; NO; NO; YES; NO; NO
Tale; 33; 1950; CN; 1; LIMITED_USE; NO; YES; NO; NO; NO
Talu; 33; 1980; CN; 1; LIMITED_USE; NO; YES; YES; NO; NO
Tang; 33; 18229; CN; 3; EXCLUSION; NO; YES; NO; YES; NO
Tavt; 33; AA80; VN; 1; LIMITED_USE; NO; YES; YES; NO; NO
Tfng; 33; 2D30; MA; 1; LIMITED_USE; NO; NO; NO; NO; NO
Tglg; 33; 1703; PH; 1; EXCLUSION; NO; NO; MIN; NO; NO
Tirh; 33; 11484; IN; 1; EXCLUSION; NO; NO; NO; NO; NO
Ugar; 33; 10380; SY; 1; EXCLUSION; NO; NO; NO; NO; NO
Vaii; 33; A549; LR; 2; LIMITED_USE; NO; NO; NO; YES; NO
Wara; 33; 118B4; IN; 1; EXCLUSION; NO; NO; NO; NO; YES
Wcho; 33; 1E2E1; IN; 1; LIMITED_USE; NO; NO; NO; NO; NO # provisional data for future Unicode 12.0 script
Xpeo; 33; 103A0; IR; 1; EXCLUSION; NO; NO; NO; NO; NO
Xsux; 33; 12000; IQ; 3; EXCLUSION; NO; NO; NO; YES; NO
Yiii; 33; A288; CN; 3; LIMITED_USE; NO; YES; NO; YES; NO
Zanb; 33; 11A0B; MN; 1; EXCLUSION; NO; NO; YES; NO; NO
# EOF