summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/tex/generic/hyph-utf8/patterns/hyph-tr.tex
diff options
context:
space:
mode:
Diffstat (limited to 'Master/texmf-dist/tex/generic/hyph-utf8/patterns/hyph-tr.tex')
-rw-r--r--Master/texmf-dist/tex/generic/hyph-utf8/patterns/hyph-tr.tex460
1 files changed, 75 insertions, 385 deletions
diff --git a/Master/texmf-dist/tex/generic/hyph-utf8/patterns/hyph-tr.tex b/Master/texmf-dist/tex/generic/hyph-utf8/patterns/hyph-tr.tex
index 7c445c2ee3b..43e54119513 100644
--- a/Master/texmf-dist/tex/generic/hyph-utf8/patterns/hyph-tr.tex
+++ b/Master/texmf-dist/tex/generic/hyph-utf8/patterns/hyph-tr.tex
@@ -1,164 +1,48 @@
-% This file is part of hyph-utf8 package and resulted from
-% semi-manual conversions of hyphenation patterns into UTF-8 in June 2008.
+% hyph-tr.tex
%
-% Source: tkhyph.tex (1992-08-27)
-% Author: P. A. MacKay
+% File auto-generated from generate_patterns_tr.rb that is part of hyph-utf8
%
-% The above mentioned file should become obsolete,
-% and the author of the original file should preferaby modify this file instead.
+% Licence:
+% - Free enough for Debian & TeX Live or any other distributor
+% - If you are reading this and have some suggestion about what to put here, please advise
+% - I (Mojca) would prefer to say 'public domain', but don't know what it means for the original authors
%
-% Modificatios were needed in order to support native UTF-8 engines,
-% but functionality (hopefully) didn't change in any way, at least not intentionally.
-% This file is no longer stand-alone; at least for 8-bit engines
-% you probably want to use loadhyph-foo.tex (which will load this file) instead.
+% Credits:
+% - algorithm developed by P. A. MacKay for the Ottoman Texts Project in 1987
+% - rules adapted for modern Turkish by H. Turgut Uyar <uyar at itu.edu.tr>
+% - initiative to improve Turkish patterns by S. Ekin Kocabas <kocabas at stanford.edu>
+% - script written by Mojca Miklavec <mojca.miklavec.lists at gmail.com> in June 2008
%
-% Modifications were done by Jonathan Kew, Mojca Miklavec & Arthur Reutenauer
-% with help & support from:
-% - Karl Berry, who gave us free hands and all resources
-% - Taco Hoekwater, with useful macros
-% - Hans Hagen, who did the unicodifisation of patterns already long before
-% and helped with testing, suggestions and bug reports
-% - Norbert Preining, who tested & integrated patterns into TeX Live
+% Modifications:
+% - adapted for the use on modern UTF-8 TeX engines
+% - UTF-8 patterns are used
+% - only letters for Modern Turkish + âîû (the first one often needed, the other two don't hurt)
+% - if needed, support for Ottoman Turkish might be provided separately under 'ota' (not 'tr')
%
-% However, the "copyright/copyleft" owner of patterns remains the original author.
-%
-% The copyright statement of this file is thus:
-%
-% Do with this file whatever needs to be done in future for the sake of
-% "a better world" as long as you respect the copyright of original file.
-% If you're the original author of patterns or taking over a new revolution,
-% plese remove all of the TUG comments & credits that we added here -
-% you are the Queen / the King, we are only the servants.
-%
-% If you want to change this file, rather than uploading directly to CTAN,
-% we would be grateful if you could send it to us (http://tug.org/tex-hyphen)
-% or ask for credentials for SVN repository and commit it yourself;
-% we will then upload the whole "package" to CTAN.
-%
-% Before a new "pattern-revolution" starts,
-% please try to follow some guidelines if possible:
-%
-% - \lccode is *forbidden*, and I really mean it
-% - all the patterns should be in UTF-8
-% - the only "allowed" TeX commands in this file are: \patterns, \hyphenation,
-% and if you really cannot do without, also \input and \message
-% - in particular, please no \catcode or \lccode changes,
-% they belong to loadhyph-foo.tex,
-% and no \lefthyphenmin and \righthyphenmin,
-% they have no influence here and belong elsewhere
-% - \begingroup and/or \endinput is not needed
-% - feel free to do whatever you want inside comments
-%
-% We know that TeX is extremely powerful, but give a stupid parser
-% at least a chance to read your patterns.
-%
-% For more unformation see
-%
-% http://tug.org/tex-hyphen
-%
-%------------------------------------------------------------------------------
-%
-% A mechanically generated Turkish Hyphenation table for TeX,
-% using the University of Washington diacritical coding
-% developed by P. A. MacKay for the Ottoman Texts Project.
-%
-% see:
-% - http://www.ctan.org/tex-archive/language/turkish/hyphen/turk_hyf.c
-% - http://www.tug.org/TUGboat/Articles/tb09-1/tb20mackay.pdf
-%
-% ---
-% 1996: conversion into Modern Turkish, DC/EC encoding, Yannis Haralambous
-% tkhyph.tex
-%
-% 2008: notes by Mojca Miklavec
-%
-% Original patterns need special fonts to be able to use them,
-% and use several tricks that only enable same hacks to work properly.
-%
-% I did not dive into details of conversion, but modern Turkish only uses:
-% - 4 "special" vowels: ıiöü
-% - 3 additional consonants: çğş
-% while the converted patterns also use:
-% - acircumflex: â
-% - ocircumflex: ô
-% - ntilde: ñ
-% One could argue that these are used just because they can,
-% but on the other hand there is no zdotaccent (ż).
-%
-% The conversion misencoded dotlessi into ^^11 (should be ^^19).
-%
-% 2008: patterns converted into Unicode.
-% Several characters could be added or removed, but I (Mojca) could not play the judge
-% and did not do any changes, even though I originally intended to fix turk_hyf.c.
-%
-% -------
-% Original encoding:
-%
-% a
-% a= â
-% e
-% i ı
-% i= î
-% i: i
-% o
-% o= ô
-% o: ö
-% u
-% u: ü
-%
-% -------
-%
-% character / UTF-8 letter / EC code / Unicode / Unicode name
-%
-% @ -- arabic hamza
-% # -- ayn
-% b
-% c
-% c: ç E7 U+00E7 LATIN SMALL LETTER C WITH CEDILLA
-% d
-% d! ḍ -- U+1E0D LATIN SMALL LETTER D WITH DOT BELOW
-% d= ḏ -- U+1E0F LATIN SMALL LETTER D WITH LINE BELOW
-% f
-% g
-% g= ğ A7 U+011F LATIN SMALL LETTER G WITH BREVE
-% g: ġ -- U+0121 LATIN SMALL LETTER G WITH DOT ABOVE
-% h
-% h! ḥ -- U+1E25 LATIN SMALL LETTER H WITH DOT BELOW
-% h= ẖ -- U+1E96 LATIN SMALL LETTER H WITH LINE BELOW
-% j
-% k
-% k! ḳ -- U+1E33 LATIN SMALL LETTER K WITH DOT BELOW
-% l
-% m
-% n
-% n= ñ F1 U+00F1 LATIN SMALL LETTER N WITH TILDE
-% p
-% r
-% s
-% s! ṣ -- U+1E63 LATIN SMALL LETTER S WITH DOT BELOW
-% s= -- s with line below - not even in unicode
-% s: ş B3 U+015F LATIN SMALL LETTER S WITH CEDILLA
-% t
-% t! ṭ -- U+1E6D LATIN SMALL LETTER T WITH DOT BELOW
-% t= ṯ -- U+1E6F LATIN SMALL LETTER T WITH LINE BELOW
-% v
-% y
-% z
-% z! ẓ -- U+1E93 LATIN SMALL LETTER Z WITH DOT BELOW
-% z= ẕ -- U+1E95 LATIN SMALL LETTER Z WITH LINE BELOW
-% z: ż BB U+017C LATIN SMALL LETTER Z WITH DOT ABOVE
+% Notes:
+% - you need to use loadhyph-tr.tex, please do not try to put \catcode-s & \lccode-s here
%
\patterns{
+% prohibit hyphen before vowels, allow after
2a1
+2â1
2e1
2ı1
+2i1
+2î1
2o1
+2ö1
2u1
+2ü1
+2û1
+% allow hyphen either side of consonants
1b1
1c1
+1ç1
1d1
1f1
1g1
+1ğ1
1h1
1j1
1k1
@@ -168,163 +52,15 @@
1p1
1r1
1s1
+1ş1
1t1
1v1
1y1
1z1
-2bâ.
-2bî.
-2bi.
-2bô.
-2bö.
-2bü.
-2câ.
-2cî.
-2ci.
-2cô.
-2cö.
-2cü.
-2ça.
-2çâ.
-2çe.
-2çı.
-2çî.
-2çi.
-2ço.
-2çô.
-2çö.
-2çu.
-2çü.
-2dâ.
-2dî.
-2di.
-2dô.
-2dö.
-2dü.
-2fâ.
-2fî.
-2fi.
-2fô.
-2fö.
-2fü.
-2gâ.
-2gî.
-2gi.
-2gô.
-2gö.
-2gü.
-2ğa.
-2ğâ.
-2ğe.
-2ğı.
-2ğî.
-2ği.
-2ğo.
-2ğô.
-2ğö.
-2ğu.
-2ğü.
-2hâ.
-2hî.
-2hi.
-2hô.
-2hö.
-2hü.
-2jâ.
-2jî.
-2ji.
-2jô.
-2jö.
-2jü.
-2kâ.
-2kî.
-2ki.
-2kô.
-2kö.
-2kü.
-2lâ.
-2lî.
-2li.
-2lô.
-2lö.
-2lü.
-2mâ.
-2mî.
-2mi.
-2mô.
-2mö.
-2mü.
-2nâ.
-2nî.
-2ni.
-2nô.
-2nö.
-2nü.
-2ña.
-2ñâ.
-2ñe.
-2ñı.
-2ñî.
-2ñi.
-2ño.
-2ñô.
-2ñö.
-2ñu.
-2ñü.
-2pâ.
-2pî.
-2pi.
-2pô.
-2pö.
-2pü.
-2râ.
-2rî.
-2ri.
-2rô.
-2rö.
-2rü.
-2sâ.
-2sî.
-2si.
-2sô.
-2sö.
-2sü.
-2şa.
-2şâ.
-2şe.
-2şı.
-2şî.
-2şi.
-2şo.
-2şô.
-2şö.
-2şu.
-2şü.
-2tâ.
-2tî.
-2ti.
-2tô.
-2tö.
-2tü.
-2vâ.
-2vî.
-2vi.
-2vô.
-2vö.
-2vü.
-2yâ.
-2yî.
-2yi.
-2yô.
-2yö.
-2yü.
-2zâ.
-2zî.
-2zi.
-2zô.
-2zö.
-2zü.
+% prevent e-cek at end of word
2e2cek.
+% prohibit hyphen before pair of consonants
+% many pairs generated here are impossible anyway
2bb
2bc
2bç
@@ -338,7 +74,6 @@
2bl
2bm
2bn
-2bñ
2bp
2br
2bs
@@ -360,7 +95,6 @@
2cl
2cm
2cn
-2cñ
2cp
2cr
2cs
@@ -382,7 +116,6 @@
2çl
2çm
2çn
-2çñ
2çp
2çr
2çs
@@ -404,7 +137,6 @@
2dl
2dm
2dn
-2dñ
2dp
2dr
2ds
@@ -426,7 +158,6 @@
2fl
2fm
2fn
-2fñ
2fp
2fr
2fs
@@ -448,7 +179,6 @@
2gl
2gm
2gn
-2gñ
2gp
2gr
2gs
@@ -470,7 +200,6 @@
2ğl
2ğm
2ğn
-2ğñ
2ğp
2ğr
2ğs
@@ -492,7 +221,6 @@
2hl
2hm
2hn
-2hñ
2hp
2hr
2hs
@@ -514,7 +242,6 @@
2jl
2jm
2jn
-2jñ
2jp
2jr
2js
@@ -536,7 +263,6 @@
2kl
2km
2kn
-2kñ
2kp
2kr
2ks
@@ -558,7 +284,6 @@
2ll
2lm
2ln
-2lñ
2lp
2lr
2ls
@@ -580,7 +305,6 @@
2ml
2mm
2mn
-2mñ
2mp
2mr
2ms
@@ -602,7 +326,6 @@
2nl
2nm
2nn
-2nñ
2np
2nr
2ns
@@ -611,28 +334,6 @@
2nv
2ny
2nz
-2ñb
-2ñc
-2ñç
-2ñd
-2ñf
-2ñg
-2ñğ
-2ñh
-2ñj
-2ñk
-2ñl
-2ñm
-2ñn
-2ññ
-2ñp
-2ñr
-2ñs
-2ñş
-2ñt
-2ñv
-2ñy
-2ñz
2pb
2pc
2pç
@@ -646,7 +347,6 @@
2pl
2pm
2pn
-2pñ
2pp
2pr
2ps
@@ -668,7 +368,6 @@
2rl
2rm
2rn
-2rñ
2rp
2rr
2rs
@@ -690,7 +389,6 @@
2sl
2sm
2sn
-2sñ
2sp
2sr
2ss
@@ -712,7 +410,6 @@
2şl
2şm
2şn
-2şñ
2şp
2şr
2şs
@@ -734,7 +431,6 @@
2tl
2tm
2tn
-2tñ
2tp
2tr
2ts
@@ -756,7 +452,6 @@
2vl
2vm
2vn
-2vñ
2vp
2vr
2vs
@@ -778,7 +473,6 @@
2yl
2ym
2yn
-2yñ
2yp
2yr
2ys
@@ -800,7 +494,6 @@
2zl
2zm
2zn
-2zñ
2zp
2zr
2zs
@@ -809,133 +502,130 @@
2zv
2zy
2zz
+% allow hyphen between vowels, but not after second vowel of pair
+% several phonetically impossible pairs here
a3a2
a3â2
a3e2
a3ı2
-a3î2
a3i2
+a3î2
a3o2
-a3ô2
a3ö2
a3u2
a3ü2
+a3û2
â3a2
â3â2
â3e2
â3ı2
-â3î2
â3i2
+â3î2
â3o2
-â3ô2
â3ö2
â3u2
â3ü2
+â3û2
e3a2
e3â2
e3e2
e3ı2
-e3î2
e3i2
+e3î2
e3o2
-e3ô2
e3ö2
e3u2
e3ü2
+e3û2
ı3a2
ı3â2
ı3e2
ı3ı2
-ı3î2
ı3i2
+ı3î2
ı3o2
-ı3ô2
ı3ö2
ı3u2
ı3ü2
-î3a2
-î3â2
-î3e2
-î3ı2
-î3î2
-î3i2
-î3o2
-î3ô2
-î3ö2
-î3u2
-î3ü2
+ı3û2
i3a2
i3â2
i3e2
i3ı2
-i3î2
i3i2
+i3î2
i3o2
-i3ô2
i3ö2
i3u2
i3ü2
+i3û2
+î3a2
+î3â2
+î3e2
+î3ı2
+î3i2
+î3î2
+î3o2
+î3ö2
+î3u2
+î3ü2
+î3û2
o3a2
o3â2
o3e2
o3ı2
-o3î2
o3i2
+o3î2
o3o2
-o3ô2
o3ö2
o3u2
o3ü2
-ô3a2
-ô3â2
-ô3e2
-ô3ı2
-ô3î2
-ô3i2
-ô3o2
-ô3ô2
-ô3ö2
-ô3u2
-ô3ü2
+o3û2
ö3a2
ö3â2
ö3e2
ö3ı2
-ö3î2
ö3i2
+ö3î2
ö3o2
-ö3ô2
ö3ö2
ö3u2
ö3ü2
+ö3û2
u3a2
u3â2
u3e2
u3ı2
-u3î2
u3i2
+u3î2
u3o2
-u3ô2
u3ö2
u3u2
u3ü2
+u3û2
ü3a2
ü3â2
ü3e2
ü3ı2
-ü3î2
ü3i2
+ü3î2
ü3o2
-ü3ô2
ü3ö2
ü3u2
ü3ü2
-.â2
-.î2
-.i2
-.ô2
-.ö2
-.ü2
+ü3û2
+û3a2
+û3â2
+û3e2
+û3ı2
+û3i2
+û3î2
+û3o2
+û3ö2
+û3u2
+û3ü2
+û3û2
+% a couple of consonant-clusters
tu4r4k
m1t4rak
}