bryce/language-data
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

first commit

Browse Source
This commit is contained in:
Santhosh Thottingal
2017-08-01 13:49:03 +05:30
commit 9ed4cff140
11 changed files with 7908 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
.eslintrc.json Normal file
View File

@@ -0,0 +1,18 @@
{
"extends": "wikimedia",
"env": {
"es6": true,
"browser": true,
"jquery": true,
"qunit": true,
"node": true,
"mocha": true
},
"globals": {
"require": false
},
"rules": {
"dot-notation": 0,
"wrap-iife": 0
}
}

342
GPL-LICENSE Normal file
View File

@@ -0,0 +1,342 @@
== GNU GENERAL PUBLIC LICENSE ==
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
=== Preamble ===
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. This
General Public License applies to most of the Free Software
Foundation's software and to any other program whose authors commit to
using it. (Some other Free Software Foundation software is covered by
the GNU Library General Public License instead.) You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
this service if you wish), that you receive source code or can get it
if you want it, that you can change the software or use pieces of it
in new free programs; and that you know you can do these things.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must show them these terms so they know their
rights.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
Finally, any free program is threatened constantly by software
patents. We wish to avoid the danger that redistributors of a free
program will individually obtain patent licenses, in effect making the
program proprietary. To prevent this, we have made it clear that any
patent must be licensed for everyone's free use or not licensed at all.
The precise terms and conditions for copying, distribution and
modification follow.
== TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION ==
'''0.''' This License applies to any program or other work which contains
a notice placed by the copyright holder saying it may be distributed
under the terms of this General Public License. The "Program", below,
refers to any such program or work, and a "work based on the Program"
means either the Program or any derivative work under copyright law:
that is to say, a work containing the Program or a portion of it,
either verbatim or with modifications and/or translated into another
language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running the Program is not restricted, and the output from the Program
is covered only if its contents constitute a work based on the
Program (independent of having been made by running the Program).
Whether that is true depends on what the Program does.
'''1.''' You may copy and distribute verbatim copies of the Program's
source code as you receive it, in any medium, provided that you
conspicuously and appropriately publish on each copy an appropriate
copyright notice and disclaimer of warranty; keep intact all the
notices that refer to this License and to the absence of any warranty;
and give any other recipients of the Program a copy of this License
along with the Program.
You may charge a fee for the physical act of transferring a copy, and
you may at your option offer warranty protection in exchange for a fee.
'''2.''' You may modify your copy or copies of the Program or any portion
of it, thus forming a work based on the Program, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
'''a)''' You must cause the modified files to carry prominent notices
stating that you changed the files and the date of any change.
'''b)''' You must cause any work that you distribute or publish, that in
whole or in part contains or is derived from the Program or any
part thereof, to be licensed as a whole at no charge to all third
parties under the terms of this License.
'''c)''' If the modified program normally reads commands interactively
when run, you must cause it, when started running for such
interactive use in the most ordinary way, to print or display an
announcement including an appropriate copyright notice and a
notice that there is no warranty (or else, saying that you provide
a warranty) and that users may redistribute the program under
these conditions, and telling the user how to view a copy of this
License. (Exception: if the Program itself is interactive but
does not normally print such an announcement, your work based on
the Program is not required to print an announcement.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Program,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Program, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Program.
In addition, mere aggregation of another work not based on the Program
with the Program (or with a work based on the Program) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
'''3.''' You may copy and distribute the Program (or a work based on it,
under Section 2) in object code or executable form under the terms of
Sections 1 and 2 above provided that you also do one of the following:
'''a)''' Accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of Sections
1 and 2 above on a medium customarily used for software interchange; or,
'''b)''' Accompany it with a written offer, valid for at least three
years, to give any third party, for a charge no more than your
cost of physically performing source distribution, a complete
machine-readable copy of the corresponding source code, to be
distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,
'''c)''' Accompany it with the information you received as to the offer
to distribute corresponding source code. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form with such
an offer, in accord with Subsection b above.)
The source code for a work means the preferred form of the work for
making modifications to it. For an executable work, complete source
code means all the source code for all modules it contains, plus any
associated interface definition files, plus the scripts used to
control compilation and installation of the executable. However, as a
special exception, the source code distributed need not include
anything that is normally distributed (in either source or binary
form) with the major components (compiler, kernel, and so on) of the
operating system on which the executable runs, unless that component
itself accompanies the executable.
If distribution of executable or object code is made by offering
access to copy from a designated place, then offering equivalent
access to copy the source code from the same place counts as
distribution of the source code, even though third parties are not
compelled to copy the source along with the object code.
'''4.''' You may not copy, modify, sublicense, or distribute the Program
except as expressly provided under this License. Any attempt
otherwise to copy, modify, sublicense or distribute the Program is
void, and will automatically terminate your rights under this License.
However, parties who have received copies, or rights, from you under
this License will not have their licenses terminated so long as such
parties remain in full compliance.
'''5.''' You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Program or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Program (or any work based on the
Program), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Program or works based on it.
'''6.''' Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the
original licensor to copy, distribute or modify the Program subject to
these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties to
this License.
'''7.''' If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Program at all. For example, if a patent
license would not permit royalty-free redistribution of the Program by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Program.
If any portion of this section is held invalid or unenforceable under
any particular circumstance, the balance of the section is intended to
apply and the section as a whole is intended to apply in other
circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system, which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
'''8.''' If the distribution and/or use of the Program is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Program under this License
may add an explicit geographical distribution limitation excluding
those countries, so that distribution is permitted only in or among
countries not thus excluded. In such case, this License incorporates
the limitation as if written in the body of this License.
'''9.''' The Free Software Foundation may publish revised and/or new versions
of the General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the Program
specifies a version number of this License which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
this License, you may choose any version ever published by the Free Software
Foundation.
'''10.''' If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
=== NO WARRANTY ===
'''11.''' BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
REPAIR OR CORRECTION.
'''12.''' IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES.
'''END OF TERMS AND CONDITIONS'''
== How to Apply These Terms to Your New Programs ==
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
Also add information on how to contact you by electronic and paper mail.
If the program is interactive, make it output a short notice like this
when it starts in an interactive mode:
Gnomovision version 69, Copyright (C) year name of author
Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, the commands you use may
be called something other than `show w' and `show c'; they could even be
mouse-clicks or menu items--whatever suits your program.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the program
`Gnomovision' (which makes passes at compilers) written by James Hacker.
<signature of Ty Coon>, 1 April 1989
Ty Coon, President of Vice
This General Public License does not permit incorporating your program into
proprietary programs. If your program is a subroutine library, you may
consider it more useful to permit linking proprietary applications with the
library. If this is what you want to do, use the GNU Library General
Public License instead of this License.

22
MIT-LICENSE Normal file
View File

@@ -0,0 +1,22 @@
Copyright (c) 2012 Alolita Sharma, Amir Aharoni, Arun Ganesh, Brandon Harris,
Niklas Laxström, Pau Giner, Santhosh Thottingal, Siebrand Mazeland and other
contributors. See CREDITS for a list.
Permission is hereby granted, free of charge, to any person obtaining
a copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to
the following conditions:
The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

10
README.md Normal file
View File

@@ -0,0 +1,10 @@
CLDR based language data and utilities
======================================
The language data with following details are populated from the current version of [CLDR supplemental data](http://unicode.org/repos/cldr/trunk/common/supplemental/supplementalData.xml)
1. The script in which a language is written.
2. The script code
3. The language code
4. The regions in which the language is spoken
5. The autonym - language name written in its own script
6. The directionality of the text

631
data/langdb.yaml Normal file
View File

@@ -0,0 +1,631 @@
languages:
aa: [Latn, [AF], Qafár af]
ab: [Cyrl, [EU], Аҧсшәа]
abs: [Latn, [AS], Bahasa Ambon]
ace: [Latn, [AS, PA], Acèh]
acf: [Latn, [AM], kwéyòl]
ady: [Cyrl, [EU, ME], Адыгабзэ]
ady-cyrl: [ady]
ady-latn: [Latn, [EU, ME], Adygabze]
aeb: [aeb-arab]
aeb-arab: [Arab, [AF], تونسي]
aeb-latn: [Latn, [AF], Tûnsî]
af: [Latn, [AF], Afrikaans]
ahr: [Deva, [AS], अहिराणी]
ak: [Latn, [AF], Akan]
akz: [Latn, [AM], Albaamo innaaɬiilka]
aln: [Latn, [EU], Gegë]
am: [Ethi, [AF], አማርኛ]
an: [Latn, [EU], aragonés]
ang: [Latn, [EU], Ænglisc]
anp: [Deva, [AS], अङ्गिका]
ar: [Arab, [ME], العربية]
arc: [Syrc, [ME], ܐܪܡܝܐ]
arn: [Latn, [AM], mapudungun]
aro: [Latn, [AM], Araona]
arq: [Arab, [AF], جازايرية]
ary: [Latn, [ME], Maġribi]
arz: [Arab, [ME], مصرى]
as: [Beng, [AS], অসমীয়া]
ase: [Sgnw, [AM], American sign language]
ast: [Latn, [EU], asturianu]
atj: [Latn, [AM], atikamekw]
av: [Cyrl, [EU], авар]
avk: [Latn, [WW], Kotava]
ay: [Latn, [AM], Aymar aru]
# The Latin script is the default in the North Azerbaijani Wikipedia,
# which uses the macro code 'az'. Its own standard code is 'azj'.
# The Arabic script is the default in the South Azerbaijani Wikipedia,
# which correctly uses the code 'azb'.
# CLDR uses az-latn and az-arab.
az: [az-latn]
az-arab: [Arab, [AS, ME], تۆرکجه]
az-latn: [Latn, [EU, ME], azərbaycanca]
az-cyrl: [Cyrl, [EU, ME], азәрбајҹанҹа]
azb: [az-arab]
azj: [az-latn]
ba: [Cyrl, [EU], башҡортса]
ban: [Bali, [AS], ᬩᬲᬩᬮᬶ]
bar: [Latn, [EU], Boarisch]
bat-smg: [sgs]
bbc-latn: [Latn, [AS], Batak Toba]
# FIXME - autonym in the Batak script is unknown
bbc-batk: [Batk, [AS], Batak Toba]
bbc: [Latn, [AS], Batak Toba]
bcc: [Arab, [AS, ME], جهلسری بلوچی]
bcl: [Latn, [AS], Bikol Central]
be-tarask: [Cyrl, [EU], беларуская (тарашкевіца)]
be-x-old: [be-tarask]
be: [Cyrl, [EU], беларуская]
bew: [Latn, [AS], Bahasa Betawi]
bfa: [Latn, [AF], Bari]
bft: [Arab, [AS], بلتی]
bfq: [Taml, [AS], படகா]
bg: [Cyrl, [EU], български]
bgn: [Arab, [AS, ME], روچ کپتین بلوچی]
# FIXME - currently says Bhojpuri, but it's a macrolanguage.
bh: [bho]
bho: [Deva, [AS], भोजपुरी]
bi: [Latn, [PA], Bislama]
bjn: [Latn, [AS], Bahasa Banjar]
bm: [Latn, [AF], bamanankan]
bn: [Beng, [AS], বাংলা]
bo: [Tibt, [AS], བོད་ཡིག]
bpy: [Beng, [AS], বিষ্ণুপ্রিয়া মণিপুরী]
bqi: [Arab, [AS, ME], بختیاری]
br: [Latn, [EU], brezhoneg]
brh: [Latn, [ME, AS], Bráhuí]
brx: [Deva, [AS], बड़ो]
bs: [Latn, [EU], bosanski]
bto: [Latn, [AS], Iriga Bicolano]
bug: [Bugi, [AS], ᨅᨔ ᨕᨘᨁᨗ]
bxr: [Cyrl, [AS], буряад]
ca: [Latn, [EU], català]
cbk-zam: [Latn, [AS], Chavacano de Zamboanga]
cdo: [Latn, [AS], Mìng-dĕ̤ng-ngṳ̄]
ce: [Cyrl, [EU], нохчийн]
ceb: [Latn, [AS], Cebuano]
ch: [Latn, [PA], Chamoru]
# FIXME chm is actually a macro language that includes
# mhr and mrj, but CLDR Territory-Language information
# uses chm instead of mhr, so for practical reasons
# it should redirect there.
# A better fix would be this:
# https://phabricator.wikimedia.org/T136164
chm: [mhr]
cho: [Latn, [AM], Choctaw]
chr: [Cher, [AM], ᏣᎳᎩ]
chy: [Latn, [AM], Tsetsêhestâhese]
ciw: [Latn, [AM], Ojibwemowin]
cjy: [cjy-hant]
cjy-hans: [Hans, [AS], 晋语（简化字)]
cjy-hant: [Hant, [AS], 晉語]
ckb: [Arab, [ME], کوردیی ناوەندی]
cnh: [Latn, [AS], Lai holh]
co: [Latn, [EU], corsu]
cps: [Latn, [AS], Capiceño]
cr: [Cans, [AM], ᓀᐦᐃᔭᐍᐏᐣ]
cr-cans: [cr]
cr-latn: [Latn, [AM], Nēhiyawēwin]
crh: [Latn, [EU], qırımtatarca]
crh-cyrl: [Cyrl, [EU], къырымтатарджа]
crh-latn: [crh]
cs: [Latn, [EU], čeština]
csb: [Latn, [EU], kaszëbsczi]
# FIXME: which script to prefer?..
cu: [Cyrl, [EU], словѣньскъ / ⰔⰎⰑⰂⰡⰐⰠⰔⰍⰟ]
cv: [Cyrl, [EU], Чӑвашла]
cy: [Latn, [EU], Cymraeg]
da: [Latn, [EU], dansk]
de-at: [Latn, [EU], Österreichisches Deutsch]
de-ch: [Latn, [EU], Schweizer Hochdeutsch]
de-formal: [Latn, [EU], Deutsch (Sie-Form)]
de: [Latn, [EU], Deutsch]
din: [Latn, [AF], Thuɔŋjäŋ]
diq: [Latn, [EU, AS], Zazaki]
dsb: [Latn, [EU], dolnoserbski]
dtp: [Latn, [AS], Dusun Bundu-liwan]
dty: [Deva, [AS], डोटेली]
dv: [Thaa, [AS], ދިވެހިބަސް]
dz: [Tibt, [AS], ཇོང་ཁ]
ee: [Latn, [AF], eʋegbe]
egl: [Latn, [EU], Emiliàn]
el: [Grek, [EU], Ελληνικά]
eml: [Latn, [EU], emiliàn e rumagnòl]
en-ca: [Latn, [AM], Canadian English]
en-gb: [Latn, [EU, AS, PA], British English]
en: [Latn, [EU, AM, AF, ME, AS, PA, WW], English]
eo: [Latn, [WW], Esperanto]
es-419: [Latn, [AM], español de America Latina]
# world?
es-formal: [Latn, [EU, AM, AF, WW], español (formal)]
# world?
es: [Latn, [EU, AM, AF, WW], español]
esu: [Latn, [AM], "Yup'ik"]
et: [Latn, [EU], eesti]
eu: [Latn, [EU], euskara]
ext: [Latn, [EU], estremeñu]
fa: [Arab, [AS, ME], فارسی]
fax: [Latn, [EU], Fala]
ff: [Latn, [AF], Fulfulde]
fi: [Latn, [EU], suomi]
fil: [tl]
fit: [Latn, [EU], meänkieli]
fiu-vro: [vro]
fj: [Latn, [PA], Na Vosa Vakaviti]
fo: [Latn, [EU], føroyskt]
fr: [Latn, [EU, AM, WW], français]
frc: [Latn, [AM], français cadien]
frp: [Latn, [EU], arpetan]
frr: [Latn, [EU], Nordfriisk]
fur: [Latn, [EU], furlan]
fy: [Latn, [EU], Frysk]
ga: [Latn, [EU], Gaeilge]
gag: [Latn, [EU], Gagauz]
gah: [Latn, [AS], Alekano]
gan-hans: [Hans, [AS], 赣语（简体）]
gan-hant: [gan]
gan: [Hant, [AS], 贛語]
gbz: [Latn, [AS], Dari-e Mazdeyasnā]
gcf: [Latn, [AM], Guadeloupean Creole French]
gd: [Latn, [EU], Gàidhlig]
gl: [Latn, [EU], galego]
glk: [Arab, [AS, ME], گیلکی]
gn: [Latn, [AM], "Avañe'ẽ"]
gom: [gom-deva]
gom-deva: [Deva, [AS], गोवा कोंकणी]
gom-latn: [Latn, [AS], Gova Konknni]
got: [Goth, [EU], 𐌲𐌿𐍄𐌹𐍃𐌺]
grc: [Grek, [EU], Ἀρχαία ἑλληνικὴ]
gsw: [Latn, [EU], Alemannisch]
gu: [Gujr, [AS], ગુજરાતી]
guc: [Latn, [AM], Wayúu]
gur: [Latn, [AF], Gurenɛ]
gv: [Latn, [EU], Gaelg]
# CLDR uses ha-latn and ha-arab. Latin is more common and is used in Wikipedia.
ha-arab: [Arab, [AF], هَوُسَ]
ha-latn: [Latn, [AF], Hausa]
ha: [ha-latn]
hak: [Latn, [AS], Hak-kâ-fa]
haw: [Latn, [AM, PA], Hawai`i]
he: [Hebr, [ME], עברית]
hi: [Deva, [AS], हिन्दी]
hif: [Latn, [PA, AS], Fiji Hindi]
hif-deva: [Deva, [AS], फ़ीजी हिन्दी]
hif-latn: [hif]
hil: [Latn, [AS], Ilonggo]
hne: [Deva, [AS], छत्तीसगढ़ी]
ho: [Latn, [PA], Hiri Motu]
hr: [Latn, [EU], hrvatski]
hrx: [Latn, [AM], Hunsrik]
hsb: [Latn, [EU], hornjoserbsce]
hsn: [Hans, [AS], 湘语]
ht: [Latn, [AM], Kreyòl ayisyen]
hu-formal: [Latn, [EU], Magyar (magázó)]
hu: [Latn, [EU], magyar]
hy: [Armn, [EU, ME], Հայերեն]
hz: [Latn, [AF], Otsiherero]
ia: [Latn, [WW], interlingua]
id: [Latn, [AS], Bahasa Indonesia]
ie: [Latn, [WW], Interlingue]
ig: [Latn, [AF], Igbo]
ii: [Yiii, [AS], ꆇꉙ]
ik: [Latn, [AM], Iñupiak]
ike-cans: [Cans, [AM], ᐃᓄᒃᑎᑐᑦ]
ike-latn: [Latn, [AM], inuktitut]
ilo: [Latn, [AS], Ilokano]
inh: [Cyrl, [EU], ГӀалгӀай]
io: [Latn, [WW], Ido]
is: [Latn, [EU], íslenska]
it: [Latn, [EU], italiano]
# For variants ike-* is used
iu: [Cans, [AM], ᐃᓄᒃᑎᑐᑦ]
ja: [Jpan, [AS], 日本語]
jam: [Latn, [AM], Patois]
jbo: [Latn, [WW], lojban]
jdt: [jdt-cyrl]
jdt-cyrl: [Cyrl, [EU, AS], жугьури]
jut: [Latn, [EU], jysk]
jv: [Latn, [AS, PA], Basa Jawa]
# For support in webfonts.
jv-java: [Java, [AS, PA], ꦧꦱꦗꦮ]
ka: [Geor, [EU], ქართული]
kaa: [Latn, [AS], Qaraqalpaqsha]
# Can also be Tfng, but the Wikipedia is mostly Latn
kab: [Latn, [AF, EU], Taqbaylit]
kac: [Latn, [AS], Jinghpaw]
kbd-cyrl: [kbd]
kbd-latn: [Latn, [EU], Qabardjajəbza]
kbd: [Cyrl, [EU, ME], Адыгэбзэ]
kbp: [Latn, [AF], Kabɩyɛ]
kea: [Latn, [AF], Kabuverdianu]
kg: [Latn, [AF], Kongo]
kgp: [Latn, [AM], Kaingáng]
khw: [Arab, [ME, AS], کھوار]
ki: [Latn, [AF], Gĩkũyũ]
kiu: [Latn, [EU, ME], Kırmancki]
kj: [Latn, [AF], Kwanyama]
kjh: [Cyrl, [AS], хакас]
kk: [kk-cyrl]
kk-arab: [Arab, [EU, AS], قازاقشا (تٶتە)]
kk-cn: [kk-arab]
kk-cyrl: [Cyrl, [EU, AS], қазақша]
kk-kz: [kk-cyrl]
kk-latn: [Latn, [EU, AS, ME], qazaqşa]
kk-tr: [kk-latn]
kl: [Latn, [AM, EU], kalaallisut]
km: [Khmr, [AS], ភាសាខ្មែរ]
kn: [Knda, [AS], ಕನ್ನಡ]
knn: [Deva, [AS], महाराष्ट्रीय कोंकणी]
# Here Hang may be even more appropriate, because kp has more resistance to Han
ko-kp: [Kore, [AS], 한국어 (조선)]
# Kore is an alias for Hangul+Han. Maybe Hang is more appropriate?
ko: [Kore, [AS], 한국어]
koi: [Cyrl, [EU], Перем Коми]
kr: [Latn, [AF], Kanuri]
krc: [Cyrl, [EU], къарачай-малкъар]
kri: [Latn, [AF], Krio]
krj: [Latn, [ME, EU], Kinaray-a]
krl: [Latn, [EU], Karjala]
ks-arab: [Arab, [AS], کٲشُر]
ks-deva: [Deva, [AS], कॉशुर]
ks: [Arab, [AS], کٲشُر]
ksf: [Latn, [AF], Bafia]
ksh: [Latn, [EU], Ripoarisch]
# CLDR uses ku-latn and ku-arab. Latin is more common and is used in Wikipedia.
ku: [ku-latn]
ku-arab: [Arab, [EU, ME], كوردي]
ku-latn: [Latn, [EU, ME], Kurdî]
kv: [Cyrl, [EU], коми]
kw: [Latn, [EU], kernowek]
ky: [Cyrl, [AS], Кыргызча]
la: [Latn, [EU], Latina]
lad: [lad-latn]
lad-latn: [Latn, [ME, EU, AM], Ladino]
lad-hebr: [Hebr, [ME, EU, AM], לאדינו]
lb: [Latn, [EU], Lëtzebuergesch]
lbe: [Cyrl, [EU], лакку]
lez: [Cyrl, [EU], лезги]
lfn: [Latn, [WW], Lingua Franca Nova]
lg: [Latn, [AF], Luganda]
li: [Latn, [EU], Limburgs]
lij: [Latn, [EU], Ligure]
liv: [Latn, [EU], Līvõ kēļ]
lki: [Arab, [AS, ME], لەکی‎]
lkt: [Latn, [AM], Lakȟótiyapi]
lld: [Latn, [EU], Ladin]
lmo: [Latn, [EU], lumbaart]
ln: [Latn, [AF], lingála]
lo: [Laoo, [AS], ລາວ]
loz: [Latn, [AF], Silozi]
lt: [Latn, [EU], lietuvių]
lrc: [Arab, [AS, ME], لۊری شومالی]
ltg: [Latn, [EU], latgaļu]
lud: [Latn, [EU], lüüdi]
lus: [Latn, [AS], Mizo ţawng]
lut: [Latn, [AM], dxʷləšucid]
luz: [Arab, [ME], لئری دوٙمینی]
lv: [Latn, [EU], latviešu]
lzh: [Hant, [AS], 文言]
# Also Geor, but the incubator is in Latn
lzz: [Latn, [EU, ME], Lazuri]
mai: [Deva, [AS], मैथिली]
map-bms: [Latn, [AS], Basa Banyumasan]
mdf: [Cyrl, [EU], мокшень]
mfe: [Latn, [AM], Morisyen]
mg: [Latn, [AF], Malagasy]
mh: [Latn, [PA], Ebon]
mhr: [Cyrl, [EU], олык марий]
mi: [Latn, [PA], Māori]
mic: [Latn, [AM], "Mi'kmaq"]
min: [Latn, [AS], Baso Minangkabau]
miq: [Latn, [AM], Mískitu]
mk: [Cyrl, [EU], македонски]
ml: [Mlym, [AS, ME], മലയാളം]
# Hmm, can also have Mong some day in some way
mn: [Cyrl, [AS], монгол]
mnc: [Mong, [AS], ᠮᠠᠨᠵᡠ ᡤᡳᠰᡠᠨ]
mni: [Beng, [AS], মেইতেই লোন্]
mnw: [Mymr, [AS], ဘာသာ မန်]
mo: [Cyrl, [EU], молдовеняскэ]
mr: [Deva, [AS, ME], मराठी]
mrj: [Cyrl, [EU], кырык мары]
ms: [Latn, [AS], Bahasa Melayu]
mt: [Latn, [EU], Malti]
mui: [Latn, [AS], Musi]
mus: [Latn, [AM], Mvskoke]
mwl: [Latn, [EU], Mirandés]
mwv: [Latn, [AS], Behase Mentawei]
mww: [mww-latn]
mww-latn: [Latn, [AS], Hmoob Dawb]
my: [Mymr, [AS], မြန်မာဘာသာ]
myv: [Cyrl, [EU], эрзянь]
mzn: [Arab, [ME, AS], مازِرونی]
na: [Latn, [PA], Dorerin Naoero]
nah: [Latn, [AM], Nāhuatl]
nan: [Latn, [AS], Bân-lâm-gú]
nap: [Latn, [EU], Napulitano]
nb: [Latn, [EU], norsk (bokmål)]
nds-nl: [Latn, [EU], Nedersaksisch]
nds: [Latn, [EU], Plattdüütsch]
ne: [Deva, [AS], नेपाली]
new: [Deva, [AS], नेपाल भाषा]
ng: [Latn, [AF], Oshiwambo]
niu: [Latn, [PA], ko e vagahau Niuē]
njo: [Latn, [AS], Ao]
nl-informal: [Latn, [EU, AM], Nederlands (informeel)]
nl: [Latn, [EU, AM], Nederlands]
nn: [Latn, [EU], norsk (nynorsk)]
# There's also nb for Bokmål and nn for Nynorsk
"no": [Latn, [EU], norsk]
nov: [Latn, [WW], Novial]
nqo: [Nkoo, [AF], ߒߞߏ]
nrm: [Latn, [EU], Nouormand]
nso: [Latn, [AF], Sesotho sa Leboa]
nv: [Latn, [AM], Diné bizaad]
ny: [Latn, [AF], Chi-Chewa]
oc: [Latn, [EU], occitan]
olo: [Latn, [AS, EU], Livvin-Karjalan]
om: [Latn, [AF], Oromoo]
or: [Orya, [AS], ଓଡ଼ିଆ]
os: [Cyrl, [EU], Ирон]
# Bug: 60815
ota: [Arab, [AS, EU], لسان عثمانى]
pa: [pa-guru]
pa-guru: [Guru, [AS], ਪੰਜਾਬੀ]
pag: [Latn, [AS], Pangasinan]
pam: [Latn, [AS], Kapampangan]
pap: [Latn, [AM], Papiamentu]
pbb: [Latn, [AM], Nasa Yuwe]
pcd: [Latn, [EU], Picard]
pdc: [Latn, [EU, AM], Deitsch]
pdt: [Latn, [EU, AM], Plautdietsch]
pfl: [Latn, [EU], Pälzisch]
pi: [Deva, [AS], पालि]
pih: [Latn, [PA], Norfuk / Pitkern]
pis: [Latn, [PA], Pijin]
pko: [Latn, [AF], Pökoot]
pl: [Latn, [EU], polski]
pms: [Latn, [EU], Piemontèis]
pnb: [Arab, [AS, ME], پنجابی]
pnt: [Grek, [EU], Ποντιακά]
ppl: [Latn, [AM], Nawat]
prg: [Latn, [EU], Prūsiskan]
prs: [Arab, [AS, ME], دری]
ps: [Arab, [AS, ME], پښتو]
pt-br: [Latn, [AM], português do Brasil]
pt: [Latn, [EU, AM, AS, PA, AF, WW], português]
qu: [Latn, [AM], Runa Simi]
qug: [Latn, [AM], Runa shimi]
rap: [Latn, [AM], arero rapa nui]
rcf: [Latn, [AF], Kreol Réyoné]
rgn: [Latn, [EU], Rumagnôl]
rif: [Latn, [AF], Tarifit]
rki: [Mymr, [AS], ရခိုင်]
rm: [Latn, [EU], rumantsch]
# Also known as Fíntika Rómma
rmf: [Latn, [EU], kaalengo tšimb]
rmy: [Latn, [EU], Romani]
rn: [Latn, [AF], Kirundi]
ro: [Latn, [EU], română]
roa-rup: [rup]
roa-tara: [Latn, [EU], tarandíne]
rtm: [Latn, [PA], Faeag Rotuma]
# world?
ru: [Cyrl, [EU, AS, ME], русский]
rue: [Cyrl, [EU], русиньскый]
rup: [Latn, [EU], armãneashti]
ruq: [Cyrl, [EU], Влахесте]
ruq-cyrl: [ruq]
# FIXME: broken autonym
ruq-grek: [Grek, [EU], Megleno-Romanian (Greek script)]
ruq-latn: [Latn, [EU], Vlăheşte]
rut: [Cyrl, [EU], мыхаӀбишды]
rw: [Latn, [AF], Kinyarwanda]
# Bug: 60815
rwr: [Deva, [AS], मारवाड़ी]
ryu: [Kana, [AS], ʔucināguci]
sa: [Deva, [AS], संस्कृतम्]
sah: [Cyrl, [EU, AS], саха тыла]
# Currently Latn, potentially Olck
sat: [Latn, [AS], Santali]
saz: [Saur, [AS], ꢱꣃꢬꢵꢯ꣄ꢡ꣄ꢬꢵ]
sc: [Latn, [EU], sardu]
scn: [Latn, [EU], sicilianu]
sco: [Latn, [EU], Scots]
sd: [Arab, [AS], سنڌي]
sdc: [Latn, [EU], Sassaresu]
sdh: [Arab, [ME], کوردی خوارگ]
se: [Latn, [EU], sámegiella]
ses: [Latn, [AF], Koyraboro Senni]
sei: [Latn, [AM], Cmique Itom]
sg: [Latn, [AF], Sängö]
sgs: [Latn, [EU], žemaitėška]
sh: [Latn, [EU], srpskohrvatski]
shi-latn: [Latn, [AF], Tašlḥiyt]
shi-tfng: [Tfng, [AF], ⵜⴰⵛⵍⵃⵉⵜ]
shi: [shi-latn]
shn: [Mymr, [AS], လိၵ်ႈတႆး]
si: [Sinh, [AS], සිංහල]
simple: [Latn, [WW], Simple English]
sk: [Latn, [EU], slovenčina]
sl: [Latn, [EU], slovenščina]
sli: [Latn, [EU], Schläsch]
slr: [Latn, [AS], Salırça]
sly: [Latn, [AS], Bahasa Selayar]
syc: [Syrc, [ME], ܣܘܪܝܝܐ]
sm: [Latn, [PA], Gagana Samoa]
sma: [Latn, [EU], åarjelsaemien]
smj: [Latn, [EU], julevsámegiella]
smn: [Latn, [EU], anarâškielâ]
sms: [Latn, [EU], sää´mǩiõll]
sn: [Latn, [AF], chiShona]
so: [Latn, [AF], Soomaaliga]
son: [Latn, [AF], soŋay]
sq: [Latn, [EU], shqip]
sr: [sr-cyrl]
sr-ec: [sr-cyrl]
sr-cyrl: [Cyrl, [EU], српски]
sr-el: [sr-latn]
sr-latn: [Latn, [EU], srpski]
srn: [Latn, [AM, EU], Sranantongo]
ss: [Latn, [AF], SiSwati]
st: [Latn, [AF], Sesotho]
stq: [Latn, [EU], Seeltersk]
su: [Latn, [AS], Basa Sunda]
sv: [Latn, [EU], svenska]
sw: [Latn, [AF], Kiswahili]
swb: [Latn, [AF], Shikomoro]
sxu: [Latn, [EU], Säggssch]
szl: [Latn, [EU], ślůnski]
ta: [Taml, [AS], தமிழ்]
tcy: [Knda, [AS], ತುಳು]
te: [Telu, [AS], తెలుగు]
tet: [Latn, [AS, PA], tetun]
tg-cyrl: [Cyrl, [AS], тоҷикӣ]
tg-latn: [Latn, [AS], tojikī]
tg: [Cyrl, [AS], тоҷикӣ]
th: [Thai, [AS], ไทย]
ti: [Ethi, [AF], ትግርኛ]
tk: [Latn, [AS], Türkmençe]
tkr: [Cyrl, [AS], ЦӀаьхна миз]
tl: [Latn, [AS], Tagalog]
# A very complicated case. Names.php is Cyrl. In TWN they argue about Cyrl, Latn, and Arab. I can't find reliable external sources. --Amir
tly: [Cyrl, [EU, AS, ME], толышә зывон]
tn: [Latn, [AF], Setswana]
to: [Latn, [PA], lea faka-Tonga]
tokipona: [Latn, [WW], Toki Pona]
tpi: [Latn, [PA, AS], Tok Pisin]
tr: [Latn, [EU, ME], Türkçe]
trp: [Latn, [AS], Kokborok (Tripuri)]
tru: [Latn, [AS], Ṫuroyo]
ts: [Latn, [AF], Xitsonga]
tsd: [Grek, [EU], Τσακωνικά]
tt: [Cyrl, [EU], татарча]
tt-cyrl: [tt]
tt-latn: [Latn, [EU], tatarça]
ttt: [Cyrl, [AS], Tati]
tum: [Latn, [AF], chiTumbuka]
tw: [Latn, [AF], Twi]
twd: [Latn, [EU], Tweants]
ty: [Latn, [PA], reo tahiti]
tyv: [Cyrl, [AS], тыва дыл]
tzl: [Latn, [WW], Talossan]
tzm: [Tfng, [AF], ⵜⴰⵎⴰⵣⵉⵖⵜ]
udm: [Cyrl, [EU], удмурт]
# CLDR uses ug-arab, ug-latn and ug-cyrl.
# Arabic seems to have the largest number of users and is the main script in the Wikipedia.
ug: [ug-arab]
ug-arab: [Arab, [AS], ئۇيغۇرچە]
ug-latn: [Latn, [AS], uyghurche]
ug-cyrl: [Cyrl, [AS], уйғурчә]
uk: [Cyrl, [EU], українська]
ur: [Arab, [AS, ME], اردو]
uz: [Latn, [AS], oʻzbekcha]
ve: [Latn, [AF], Tshivenda]
vec: [Latn, [EU], vèneto]
vep: [Latn, [EU], vepsän kel’]
vi: [Latn, [AS], Tiếng Việt]
vls: [Latn, [EU], West-Vlams]
vmf: [Latn, [EU], Mainfränkisch]
vo: [Latn, [WW], Volapük]
vot: [Latn, [EU], Vaďďa]
vro: [Latn, [EU], Võro]
wa: [Latn, [EU], walon]
war: [Latn, [AS], Winaray]
wls: [Latn, [PA], "Faka'uvea"]
wo: [Latn, [AF], Wolof]
wuu: [Hans, [AS], 吴语]
xal: [Cyrl, [EU], хальмг]
xh: [Latn, [AF], isiXhosa]
xmf: [Geor, [EU], მარგალური]
ydd: [Hebr, [AS, EU], Eastern Yiddish]
yi: [Hebr, [ME, EU, AM], ייִדיש]
yo: [Latn, [AF], Yorùbá]
yrk: [Cyrl, [AS], Ненэцяʼ вада]
yrl: [Latn, [AM], "ñe'engatú"]
yua: [Latn, [AM], "Maaya T'aan"]
yue: [Hant, [AS], 粵語]
za: [Latn, [AS], Vahcuengh]
zea: [Latn, [EU], Zeêuws]
zgh: [Tfng, [AF], ⵜⴰⵎⴰⵣⵉⵖⵜ]
# world? (may apply to many varieties of Chinese)
zh: [Hans, [AS], 中文]
zh-classical: [Hant, [AS], 文言]
zh-cn: [Hans, [AS], 中文（中国大陆）]
zh-hans: [Hans, [AS], 中文（简体）]
zh-hant: [Hant, [AS], 中文（繁體）]
zh-hk: [Hant, [AS], 中文（香港）]
zh-min-nan: [nan]
zh-mo: [Hant, [AS], 中文（澳門）]
zh-my: [Hans, [AS], 中文（马来西亚）]
zh-sg: [Hans, [AS], 中文（新加坡）]
zh-tw: [Hant, [AS], 中文（台灣）]
zh-yue: [yue]
zu: [Latn, [AF], isiZulu]
# All the supported scripts, grouped logically.
#
# The codes are taken from http://unicode.org/iso15924/iso15924-codes.html .
#
# The classification is roughly based on http://www.unicode.org/charts/
# with some practical corrections.
#
# The order of the groups affects display. Pau Giner suggested the order;
# the rationale of the order is to distance the largest groups from
# one another to improve discoverability.
#
# The group name "Other" is reserved.
scriptgroups:
# It's hard to find a better place for Goth except the Latin group.
Latin: [Latn, Goth]
# Greek is probably different enough from Latin and Cyrillic, but user testing
# may prove otherwise.
Greek: [Grek]
WestCaucasian: [Armn, Geor]
Arabic: [Arab]
# Maybe MiddleEastern can be unified with Arabic.
# Maybe Thaana can be moved here from SouthAsian.
# Maybe it can be unified with African.
MiddleEastern: [Hebr, Syrc]
African: [Ethi, Nkoo, Tfng]
# India, Nepal, Bangladesh, Sri-Lanka, Bhutan, Maldives.
#
# Thaana (Thaa, the script of Maldives) is here, even though it's RTL,
# because it's closer geographically to India. Maybe it should be moved
# to MiddleEastern or to Arabic, if that would be easier to users.
#
# Tibetan (Tibt) is here, even though it's classified as "Central Asian" by
# Unicode, because linguistically and geographically it's closely related to
# the Brahmic family.
SouthAsian: [Beng, Deva, Gujr, Guru, Knda, Mlym, Orya, Saur, Sinh, Taml, Telu, Tibt, Thaa]
Cyrillic: [Cyrl]
CJK: [Hans, Hant, Kana, Kore, Jpan, Yiii]
SouthEastAsian: [Bali, Batk, Bugi, Java, Khmr, Laoo, Mymr, Thai]
Mongolian: [Mong]
SignWriting: [Sgnw]
NativeAmerican: [Cher, Cans]
# Undetermined script
Special: [Zyyy]
rtlscripts:
[Arab, Hebr, Syrc, Nkoo, Thaa]
# The numbers are also used in HTML id attributes
regiongroups:
# Worldwide, international
WW: 1
# Special languages. To be shown near Worldwide when relevant.
SP: 1
# America
AM: 2
# Europe
EU: 3
# Middle East
ME: 3
# Africa
AF: 3
# Asia
AS: 4
# Pacific
PA: 4

1046
data/spyc.php Normal file
View File

File diff suppressed because it is too large Load Diff

118
data/ulsdata2json.php Normal file
View File

@@ -0,0 +1,118 @@
<?php
/**
* Script to create the language data in JSON format for ULS.
*
* Copyright (C) 2012 Alolita Sharma, Amir Aharoni, Arun Ganesh, Brandon Harris,
* Niklas Laxström, Pau Giner, Santhosh Thottingal, Siebrand Mazeland and other
* contributors. See CREDITS for a list.
*
* UniversalLanguageSelector is dual licensed GPLv2 or later and MIT. You don't
* have to do anything special to choose one license or the other and you don't
* have to notify anyone which license you are using. You are free to use
* UniversalLanguageSelector in commercial projects as long as the copyright
* header is left intact. See files GPL-LICENSE and MIT-LICENSE for details.
*
* @file
* @ingroup Extensions
* @licence GNU General Public Licence 2.0 or later
* @licence MIT License
*/
include __DIR__ . '/spyc.php';
print "Reading langdb.yaml...\n";
$yamlLangdb = file_get_contents( 'langdb.yaml' );
$parsedLangdb = spyc_load( $yamlLangdb );
$supplementalDataFilename = 'supplementalData.xml';
$supplementalDataUrl =
"http://unicode.org/repos/cldr/trunk/common/supplemental/$supplementalDataFilename";
$curl = curl_init( $supplementalDataUrl );
$supplementalDataFile = fopen( $supplementalDataFilename, 'w' );
curl_setopt( $curl, CURLOPT_FILE, $supplementalDataFile );
curl_setopt( $curl, CURLOPT_HEADER, 0 );
print "Trying to download $supplementalDataUrl...\n";
$curlSuccess = curl_exec( $curl );
curl_close( $curl );
fclose( $supplementalDataFile );
if ( !$curlSuccess ) {
die( "Failed to download CLDR data from $supplementalDataUrl.\n" );
}
print "Downloaded $supplementalDataFilename, trying to parse...\n";
$supplementalData = simplexml_load_file( $supplementalDataFilename );
if ( !( $supplementalData instanceof SimpleXMLElement ) ) {
die( "Attempt to load CLDR data from $supplementalDataFilename failed.\n" );
}
print "CLDR supplemental data parsed successfully, reading territories info...\n";
$parsedLangdb['territories'] = array();
foreach ( $supplementalData->territoryInfo->territory as $territoryRecord ) {
$territoryAtributes = $territoryRecord->attributes();
$territoryCodeAttr = $territoryAtributes['type'];
$territoryCode = (string) $territoryCodeAttr[0];
$parsedLangdb['territories'][$territoryCode] = array();
foreach ( $territoryRecord->languagePopulation as $languageRecord ) {
$languageAttributes = $languageRecord->attributes();
$languageCodeAttr = $languageAttributes['type'];
// Lower case is a convention for language codes in ULS.
// '_' is used in CLDR for compound codes and it's replaced with '-' here.
$normalisedCode = strtr( strtolower( (string) $languageCodeAttr[0] ), '_', '-' );
$parsedLangdb['territories'][$territoryCode][] = $normalisedCode;
// In case of codes with variants, also add the base because ULS might consider
// them as separate languages, e.g. zh, zh-hant and zh-hans.
if ( strpos( $normalisedCode, '-' ) !== false ) {
$parts = explode( '-', $normalisedCode );
$parsedLangdb['territories'][$territoryCode][] = $parts[0];
}
}
}
foreach ( $parsedLangdb['territories'] as $territoryCode => $languages ) {
foreach ( $languages as $index => $language ) {
if ( !isset( $parsedLangdb['languages'][$language] ) ) {
echo "Unknown language $language for territory $territoryCode\n";
unset( $parsedLangdb['territories'][$territoryCode][$index] );
continue;
}
$data = $parsedLangdb['languages'][$language];
if ( count( $data ) === 1 ) {
echo "Redirect for language $language to {$data[0]} territory $territoryCode\n";
$parsedLangdb['territories'][$territoryCode][$index] = $data[0];
continue;
}
}
// Clean-up to save space
if ( count( $parsedLangdb['territories'][$territoryCode] ) === 0 ) {
unset( $parsedLangdb['territories'][$territoryCode] );
continue;
}
// Remove duplicates we might have created
$parsedLangdb['territories'][$territoryCode] =
array_unique( $parsedLangdb['territories'][$territoryCode] );
// We need to renumber or json conversion thinks these are objects
$parsedLangdb['territories'][$territoryCode] =
array_values( $parsedLangdb['territories'][$territoryCode] );
}
print "Writing JSON langdb...\n";
$jsonVerbose = json_encode( $parsedLangdb, JSON_PRETTY_PRINT | JSON_UNESCAPED_UNICODE );
// For making diff review easier.
file_put_contents( '../language-data.json', $jsonVerbose );
print "Done.\n";

261
index.js Normal file
View File

@@ -0,0 +1,261 @@
var languageData = require( './language-data.json' );
/**
* Utility functions for querying language data.
*/
/**
* Is this language a redirect to another language?
* @param {string} language Language code
* @return {string} Target language code if it's a redirect or false if it's not
*/
function isRedirect( language ) {
return ( languageData.languages[ language ] !== undefined && languageData.languages[ language ].length === 1 ) ? languageData.languages[ language ][ 0 ] : false;
}
/**
* Returns the script of the language.
* @param {string} language Language code
* @return {string}
*/
function getScript( language ) {
var target = isRedirect( language );
if ( target ) {
return getScript( target );
}
if ( !languageData.languages[ language ] ) {
// Undetermined
return 'Zyyy';
}
return languageData.languages[ language ][ 0 ];
}
/**
* Returns the regions in which a language is spoken.
* @param {string} language Language code
* @return {string[]} 'UNKNOWN'
*/
function getRegions( language ) {
var target = isRedirect( language );
if ( target ) {
return getRegions( target );
}
return ( languageData.languages[ language ] && languageData.languages[ language ][ 1 ] ) || 'UNKNOWN';
}
/**
* Returns the autonym of the language.
* @param {string} language Language code
* @return {string}
*/
function getAutonym( language ) {
var target = isRedirect( language );
if ( target ) {
return getAutonym( target );
}
return ( languageData.languages[ language ] && languageData.languages[ language ][ 2 ] ) || language;
}
/**
* Returns all language codes and corresponding autonyms
* @return {array}
*/
function getAutonyms() {
var language,
autonymsByCode = {};
for ( language in languageData.languages ) {
if ( isRedirect( language ) ) {
continue;
}
autonymsByCode[ language ] = getAutonym( language );
}
return autonymsByCode;
}
/**
* Returns all languages written in the given scripts.
* @param {string[]} scripts
* @return {string[]} languages codes
*/
function getLanguagesInScripts( scripts ) {
var language, i,
languagesInScripts = [];
for ( language in languageData.languages ) {
if ( isRedirect( language ) ) {
continue;
}
for ( i = 0; i < scripts.length; i++ ) {
if ( scripts[ i ] === getScript( language ) ) {
languagesInScripts.push( language );
break;
}
}
}
return languagesInScripts;
}
/**
* Returns all languages written in script.
* @param {string} script
* @return {string[]} array of strings (languages codes)
*/
function getLanguagesInScript( script ) {
return getLanguagesInScripts( [ script ] );
}
/**
* Returns the script group of a script or 'Other' if it doesn't
* belong to any group.
* @param {string} script Script code
* @return {string} script group name
*/
function getGroupOfScript( script ) {
var scriptGroup;
for ( scriptGroup in languageData.scriptgroups ) {
if ( languageData.scriptgroups[ scriptGroup ].includes( script ) ) {
return scriptGroup;
}
}
return 'Other';
}
/**
* Returns the script group of a language.
* @param {string} language Language code
* @return {string} script group name
*/
function getScriptGroupOfLanguage( language ) {
return getGroupOfScript( getScript( language ) );
}
/**
* Get the given list of languages grouped by script.
* @param {string[]} languages Array of language codes
* @return {Object} Array of languages indexed by script codes
*/
function getLanguagesByScriptGroup( languages ) {
var languagesByScriptGroup = {},
language, resolvedRedirect, langScriptGroup;
for ( language in languages ) {
resolvedRedirect = isRedirect( language ) || language;
langScriptGroup = getScriptGroupOfLanguage( resolvedRedirect );
if ( !languagesByScriptGroup[ langScriptGroup ] ) {
languagesByScriptGroup[ langScriptGroup ] = [];
}
languagesByScriptGroup[ langScriptGroup ].push( language );
}
return languagesByScriptGroup;
}
/**
* Returns an associative array of languages in several regions,
* grouped by script group.
* @param {string[]} regions array of region codes
* @return {Object}
*/
function getLanguagesByScriptGroupInRegions( regions ) {
var language, i, scriptGroup,
languagesByScriptGroupInRegions = {};
for ( language in languageData.languages ) {
if ( isRedirect( language ) ) {
continue;
}
for ( i = 0; i < regions.length; i++ ) {
if ( getRegions( language ).includes( regions[ i ] ) ) {
scriptGroup = getScriptGroupOfLanguage( language );
if ( languagesByScriptGroupInRegions[ scriptGroup ] === undefined ) {
languagesByScriptGroupInRegions[ scriptGroup ] = [];
}
languagesByScriptGroupInRegions[ scriptGroup ].push( language );
break;
}
}
}
return languagesByScriptGroupInRegions;
}
/**
* Returns an associative array of languages in a region,
* grouped by script group.
* @param {string} region Region code
* @return {Object}
*/
function getLanguagesByScriptGroupInRegion( region ) {
return getLanguagesByScriptGroupInRegions( [ region ] );
}
/**
* A callback for sorting languages by autonym.
* Can be used as an argument to a sort function.
* @param {string} a Language code
* @param {string} b Language code
* @return {number}
*/
function sortByAutonym( a, b ) {
var autonymA = getAutonym( a ) || a,
autonymB = getAutonym( b ) || b;
return ( autonymA.toLowerCase() < autonymB.toLowerCase() ) ? -1 : 1;
}
/**
* Check if a language is right-to-left.
* @param {string} language Language code
* @return {boolean}
*/
function isRtl( language ) {
return languageData.rtlscripts.includes( getScript( language ) );
}
/**
* Return the direction of the language
* @param {string} language Language code
* @return {string}
*/
function getDir( language ) {
return isRtl( language ) ? 'rtl' : 'ltr';
}
/**
* Returns the languages spoken in a territory.
* @param {string} territory Territory code
* @return {string[]} list of language codes
*/
function getLanguagesInTerritory( territory ) {
return languageData.territories[ territory ];
}
/**
* Adds a language in run time and sets its options as provided.
* If the target option is provided, the language is defined as a redirect.
* Other possible options are script, regions and autonym.
*
* @param {string} code New language code.
* @param {Object} options Language properties.
*/
function addLanguage( code, options ) {
if ( options.target ) {
languageData.languages[ code ] = [ options.target ];
} else {
languageData.languages[ code ] = [ options.script, options.regions, options.autonym ];
}
}
module.exports = {
addLanguage,
getAutonym,
getAutonyms,
getDir,
getGroupOfScript,
getLanguagesByScriptGroup,
getLanguagesByScriptGroupInRegion,
getLanguagesByScriptGroupInRegions,
getLanguagesInScript,
getLanguagesInScripts,
getLanguagesInTerritory,
getRegions,
getScript,
getScriptGroupOfLanguage,
isRedirect,
isRtl,
sortByAutonym
};

5282
language-data.json Normal file
View File

File diff suppressed because it is too large Load Diff

41
package.json Normal file
View File

@@ -0,0 +1,41 @@
{
"name": "language-data",
"version": "0.1.0",
"description": "Language data and utilities",
"homepage": "https://github.com/wikimedia/language-data.uls",
"keywords": [
"cldr",
"internationalization",
"localization",
"l10n"
],
"author": {
"name": "Santhosh Thottingal",
"email": "santhosh.thottingal@gmail.com"
},
"contributors": [
"Amir Aharoni",
"Niklas Laxström",
"Santhosh Thottingal"
],
"devDependencies": {
"assert": "1.4.1",
"eslint": "2.9.0",
"eslint-config-wikimedia": "0.3.0",
"mocha": "^2.5.3"
},
"repository": {
"type": "git",
"url": "git://github.com/wikimedia/language-data.git"
},
"bugs": {
"url" : "http://github.com/wikimedia/language-data/issues"
},
"engine": {
"node": ">=0.10.x"
},
"license": "(MIT OR GPL-2.0+)",
"scripts": {
"test": "mocha"
}
}

137
test/index.js Normal file
View File

@@ -0,0 +1,137 @@
var languageData = require( '../index' ),
assert = require( 'assert' );
describe( 'languagedata', function () {
var orphanScripts, badRedirects, doubleRedirects, languagesWithoutAutonym;
/*
* Runs over all script codes mentioned in langdb and checks whether
* they belong to the 'Other' group.
*/
orphanScripts = function () {
var language, script,
result = [];
for ( language in languageData.languages ) {
script = languageData.getScript( language );
if ( languageData.getGroupOfScript( script ) === 'Other' ) {
result.push( script );
}
}
return result;
};
/*
* Runs over all languages and checks that all redirects have a valid target.
*/
badRedirects = function () {
var language, target,
result = [];
for ( language in languageData.languages ) {
target = languageData.isRedirect( language );
if ( target && !languageData.languages[ target ] ) {
result.push( language );
}
}
return result;
};
/*
* Runs over all languages and checks that all redirects point to a language.
* There's no reason to have double redirects.
*/
doubleRedirects = function () {
var language, target,
result = [];
for ( language in languageData.languages ) {
target = languageData.isRedirect( language );
if ( target && languageData.isRedirect( target ) ) {
result.push( language );
}
}
return result;
};
/*
* Runs over all script codes mentioned in langdb and checks whether
* they have something that looks like an autonym.
*/
languagesWithoutAutonym = function () {
var language,
result = [];
for ( language in languageData.languages ) {
if ( typeof languageData.getAutonym( language ) !== 'string' ) {
result.push( language );
}
}
return result;
};
it( 'autonyms', function () {
var autonyms;
// Add a language in run time.
// This is done early to make sure that it doesn't break other functions.
languageData.addLanguage( 'qqq', {
script: 'Latn',
regions: [ 'SP' ],
autonym: 'Language documentation'
} );
assert.ok( languageData.getAutonym( 'qqq' ), 'Language documentation', 'Language qqq was added with the correct autonym' );
autonyms = languageData.getAutonyms();
assert.strictEqual( autonyms[ 'zu' ], 'isiZulu', 'Correct autonym is returned for Zulu using getAutonyms().' );
assert.strictEqual( autonyms[ 'pa' ], undefined, 'Language "pa" is not listed in autonyms, because it is a redirect' );
assert.strictEqual( autonyms[ 'pa-guru' ], 'ਪੰਜਾਬੀ', 'Language "pa-guru" has the correct autonym' );
assert.deepEqual( languagesWithoutAutonym(), [], 'All languages have autonyms.' );
assert.strictEqual( languageData.getAutonym( 'pa' ), 'ਪੰਜਾਬੀ', 'Correct autonym of the Punjabi language was selected using code pa.' );
assert.strictEqual( languageData.getAutonym( 'pa-guru' ), 'ਪੰਜਾਬੀ', 'Correct autonym of the Punjabi language was selected using code pa-guru.' );
// autonyms: gn: avañe'ẽ, de: deutsch, hu: magyar, fi: suomi
assert.deepEqual( [ 'de', 'fi', 'gn', 'hu' ].sort( languageData.sortByAutonym ), [
'gn', 'de', 'hu', 'fi'
], 'Languages are correctly sorted by autonym' );
} );
it( 'regions and groups', function () {
var languagesToGroup, groupedLanguages;
// This test assumes that we don't want any scripts to be in the 'Other'
// group. Actually, this may become wrong some day.
assert.deepEqual( orphanScripts(), [], 'All scripts belong to script groups.' );
languagesToGroup = {
en: 'English',
'fiu-vro': 'Võro', // Alias before target
ru: 'русский',
sr: 'српски', // Alias before target
'sr-cyrl': 'српски', // Target before alias
'sr-latn': 'srpski', // Target before alias
'sr-el': 'srpski', // Alias after target
vro: 'Võro' // Target after alias
};
groupedLanguages = {
Latin: [ 'en', 'fiu-vro', 'sr-latn', 'sr-el', 'vro' ],
Cyrillic: [ 'ru', 'sr', 'sr-cyrl' ]
};
assert.deepEqual( languageData.getLanguagesByScriptGroup( languagesToGroup ), groupedLanguages, 'A custom list of languages is grouped correctly using getLanguagesByScriptGroup.' );
assert.deepEqual( languageData.getRegions( 'lzz' ), [
'EU', 'ME'
], 'Correct regions of the Laz language were selected' );
assert.strictEqual( languageData.getRegions( 'no-such-language' ), 'UNKNOWN', 'The region of an invalid language is "UNKNOWN"' );
assert.ok( languageData.getLanguagesInTerritory( 'RU' ).includes( 'sah' ), 'Sakha language is spoken in Russia' );
} );
it( 'scripts', function () {
// This test assumes that we don't want any scripts to be in the 'Other'
// group. Actually, this may become wrong some day.
assert.deepEqual( orphanScripts(), [], 'All scripts belong to script groups.' );
assert.deepEqual( languageData.getLanguagesInScript( 'Guru' ), [ 'pa-guru' ], '"pa-guru" is written in script Guru, and "pa" is skipped as a redirect' );
assert.deepEqual( languageData.getLanguagesInScripts( [ 'Geor', 'Armn' ] ), [ 'hy', 'ka', 'xmf' ], 'languages in scripts Geor and Armn are selected correctly' );
assert.deepEqual( languageData.getLanguagesInScript( 'Knda' ), [
'kn', 'tcy'
], 'languages in script Knda are selected correctly' );
assert.strictEqual( languageData.getGroupOfScript( 'Beng' ), 'SouthAsian', 'Bengali script belongs to the SouthAsian group.' );
assert.strictEqual( languageData.getScriptGroupOfLanguage( 'iu' ), 'NativeAmerican', 'The script of the Inupiaq language belongs to the NativeAmerican group.' );
} );
it( 'redirects', function () {
assert.strictEqual( languageData.isRedirect( 'sr-ec' ), 'sr-cyrl', '"sr-ec" is a redirect to "sr-cyrl"' );
assert.deepEqual( badRedirects(), [], 'All redirects have valid targets.' );
assert.deepEqual( doubleRedirects(), [], 'There are no double redirects.' );
assert.strictEqual( languageData.getScript( 'no-such-language' ), 'Zyyy', 'A script for an unknown language is Zyyy - undetermined' );
assert.strictEqual( languageData.getScript( 'ii' ), 'Yiii', 'Correct script of the Yi language was selected' );
} );
it( 'directionality', function () {
assert.strictEqual( languageData.isRtl( 'te' ), false, 'Telugu language is not RTL' );
assert.strictEqual( languageData.isRtl( 'dv' ), true, 'Divehi language is RTL' );
assert.strictEqual( languageData.getDir( 'mzn' ), 'rtl', 'Mazandarani language is RTL' );
assert.strictEqual( languageData.getDir( 'uk' ), 'ltr', 'Ukrainian language is LTR' );
} );
} );