From 25436fd08fa6d0825a2f7c7b5d51e34873a05187 Mon Sep 17 00:00:00 2001 From: Roozbeh Pournader Date: Wed, 2 Sep 2009 20:03:42 -0700 Subject: [PATCH] Updated Arabic, Persian, and Urdu orthographies - Arabic (ar), Persian (fa), and Urdu (ur) now use generic forms (bug #23004) - Persian (fa) orthography updated to latest standards and orthographies - Persian dialects Dari/Eastern Farsi (prs) and Western Farsi (pes) added --- fc-lang/ar.orth | 81 ++++++++++-------------------------------------- fc-lang/fa.orth | 80 +++++++++++++++++++++++++++++------------------ fc-lang/pes.orth | 26 ++++++++++++++++ fc-lang/prs.orth | 29 +++++++++++++++++ fc-lang/ur.orth | 77 +++++++++++++++++++++++---------------------- 5 files changed, 161 insertions(+), 132 deletions(-) create mode 100644 fc-lang/pes.orth create mode 100644 fc-lang/prs.orth diff --git a/fc-lang/ar.orth b/fc-lang/ar.orth index 5afef09..39fcfa0 100644 --- a/fc-lang/ar.orth +++ b/fc-lang/ar.orth @@ -2,6 +2,7 @@ # fontconfig/fc-lang/ar.orth # # Copyright © 2002 Keith Packard +# Copyright © 2009 Roozbeh Pournader # # Permission to use, copy, modify, distribute, and sell this software and its # documentation for any purpose is hereby granted without fee, provided that @@ -21,68 +22,18 @@ # TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR # PERFORMANCE OF THIS SOFTWARE. # -# Arabic (AR) -# -# General forms. Leave these out for now as most software -# expects presentation forms. -# -#060C # ARABIC COMMA -#061B # ARABIC SEMICOLON -#061F # ARABIC QUESTION MARK -#0621 # ARABIC LETTER HAMZA -#0622 # ARABIC LETTER ALEF WITH MADDA ABOVE -#0623 # ARABIC LETTER ALEF WITH HAMZA ABOVE -#0624 # ARABIC LETTER WAW WITH HAMZA ABOVE -#0625 # ARABIC LETTER ALEF WITH HAMZA BELOW -#0626 # ARABIC LETTER YEH WITH HAMZA ABOVE -#0627 # ARABIC LETTER ALEF -#0628 # ARABIC LETTER BEH -#0629 # ARABIC LETTER TEH MARBUTA -#062A # ARABIC LETTER TEH -#062B # ARABIC LETTER THEH -#062C # ARABIC LETTER JEEM -#062D # ARABIC LETTER HAH -#062E # ARABIC LETTER KHAH -#062F # ARABIC LETTER DAL -#0630 # ARABIC LETTER THAL -#0631 # ARABIC LETTER REH -#0632 # ARABIC LETTER ZAIN -#0633 # ARABIC LETTER SEEN -#0634 # ARABIC LETTER SHEEN -#0635 # ARABIC LETTER SAD -#0636 # ARABIC LETTER DAD -#0637 # ARABIC LETTER TAH -#0638 # ARABIC LETTER ZAH -#0639 # ARABIC LETTER AIN -#063A # ARABIC LETTER GHAIN -#0640 # ARABIC TATWEEL -#0641 # ARABIC LETTER FEH -#0642 # ARABIC LETTER QAF -#0643 # ARABIC LETTER KAF -#0644 # ARABIC LETTER LAM -#0645 # ARABIC LETTER MEEM -#0646 # ARABIC LETTER NOON -#0647 # ARABIC LETTER HEH -#0648 # ARABIC LETTER WAW -#0649 # ARABIC LETTER ALEF MAKSURA -#064A # ARABIC LETTER YEH -#064B # ARABIC FATHATAN -#064C # ARABIC DAMMATAN -#064D # ARABIC KASRATAN -#064E # ARABIC FATHA -#064F # ARABIC DAMMA -#0650 # ARABIC KASRA -#0651 # ARABIC SHADDA -#0652 # ARABIC SUKUN -# -# Data from Roozbeh Pournader -# -# Select fonts based on support for presentation forms; this may -# exclude some OpenType fonts, but the hope is those would be -# located by a clever shaper by Unicode codepoints in any case. -# -# General Forms: -#0621-063a -#0641-064a -# Presentations Forms: -fe80-fefc +# Arabic (ar) +# +# We are assuming that: +# * Most fonts that claim to support an Arabic letter actually do so; +# * Most modern text rendering software use OpenType tables, instead of +# directly using presentation forms. +# * Some good Arabic fonts do not support codepoints for Arabic presentation +# forms. +# Thus, we are switching to general forms of Arabic letters. +# +# General forms: +0621-063a +0641-064a +# Presentations forms: +# fe80-fefc diff --git a/fc-lang/fa.orth b/fc-lang/fa.orth index a988d61..2d9d7fa 100644 --- a/fc-lang/fa.orth +++ b/fc-lang/fa.orth @@ -2,6 +2,7 @@ # fontconfig/fc-lang/fa.orth # # Copyright © 2002 Keith Packard +# Copyright © 2009 Roozbeh Pournader # # Permission to use, copy, modify, distribute, and sell this software and its # documentation for any purpose is hereby granted without fee, provided that @@ -21,33 +22,52 @@ # TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR # PERFORMANCE OF THIS SOFTWARE. # -# Persian (FA) -# -# Data from Roozbeh Pournader -# -# Select fonts based on support for presentation forms; this may -# exclude some OpenType fonts, but the hope is those would be -# located by a clever shaper by Unicode codepoints in any case. -# -# General forms. -#0621-0624 -#0626-063a -#0641-0642 -#0644-0648 -#067e -#0686 -#0698 -#06a9 -#06af -#06cc -# Presentations Forms: -fb56-fb59 -fb7a-fb7d -fb8a-fb8b -fb8e-fb95 -fbfc-fbff -fe80-fe86 -fe89-fed8 -fedd-feee -#fef5-fef8 # These four happen very rarely -fefb-fefc +# Persian (fa) +# +# Sources: +# * ISIRI 6219:2002, "Information Technology — Persian Information +# Interchange and Display Mechanism, using Unicode" +# * "Dastur-e Khat-te Fārsi", Iranian Academy of Persian Language and +# Literature, 4th printing, December 2005, ISBN 964-7531-13-3. Available +# at http://www.persianacademy.ir/fa/das.aspx +# +# We are assuming that: +# * Most fonts that claim to support an Arabic letter actually do so; +# * Most modern text rendering software use OpenType tables, instead of +# directly using presentation forms. +# * Some good Arabic fonts do not support codepoints for Arabic presentation +# forms. +# Thus, we are switching to general forms of Arabic letters. +# +# General forms: +0621-0624 +0626-0628 +0629 # TEH MARBUTA, implicitly considered mandatory in the official orthography +062a-063a +0641-0642 +0644-0648 +064b # FATHATAN, considered mandatory in the official orthography +# 064b-064d # DAMMATAN and KASRATAN, considered mandatory in the official orthography, but very rare +# 064e-0650 # FATHA, DAMMA, and KASRA, not mandataroy in the official orthography +# 0651 # SHADDA, considered mandatory only for legal texts +# 0652 # SUKUN, not mandatory in the official orthography +0654 # HAMZA ABOVE, considered mandatory in the official orthography +# 0656 # SUBSCRIPT ALEF, not mentioned in official orthography, but sometimes used +# 0670 # SUPERSCRIPT ALEF, not explicilty listed in the official orthography, although used in the document; not mandatory +067e +0686 +0698 +06a9 +06af +06cc +# Presentations forms: +#fb56-fb59 +#fb7a-fb7d +#fb8a-fb8b +#fb8e-fb95 +#fbfc-fbff +#fe80-fe86 +#fe89-fed8 +#fedd-feee +##fef5-fef8 # These four happen very rarely +#fefb-fefc diff --git a/fc-lang/pes.orth b/fc-lang/pes.orth new file mode 100644 index 0000000..81b3910 --- /dev/null +++ b/fc-lang/pes.orth @@ -0,0 +1,26 @@ +# +# fontconfig/fc-lang/pes.orth +# +# Copyright © 2009 Roozbeh Pournader +# +# Permission to use, copy, modify, distribute, and sell this software and its +# documentation for any purpose is hereby granted without fee, provided that +# the above copyright notice appear in all copies and that both that +# copyright notice and this permission notice appear in supporting +# documentation, and that the name of Keith Packard not be used in +# advertising or publicity pertaining to distribution of the software without +# specific, written prior permission. Keith Packard makes no +# representations about the suitability of this software for any purpose. It +# is provided "as is" without express or implied warranty. +# +# THE AUTHOR(S) DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, +# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO +# EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY SPECIAL, INDIRECT OR +# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, +# DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER +# TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR +# PERFORMANCE OF THIS SOFTWARE. +# +# Western Farsi (pes) +# +include fa.orth diff --git a/fc-lang/prs.orth b/fc-lang/prs.orth new file mode 100644 index 0000000..98cf654 --- /dev/null +++ b/fc-lang/prs.orth @@ -0,0 +1,29 @@ +# +# fontconfig/fc-lang/prs.orth +# +# Copyright © 2009 Roozbeh Pournader +# +# Permission to use, copy, modify, distribute, and sell this software and its +# documentation for any purpose is hereby granted without fee, provided that +# the above copyright notice appear in all copies and that both that +# copyright notice and this permission notice appear in supporting +# documentation, and that the name of Keith Packard not be used in +# advertising or publicity pertaining to distribution of the software without +# specific, written prior permission. Keith Packard makes no +# representations about the suitability of this software for any purpose. It +# is provided "as is" without express or implied warranty. +# +# THE AUTHOR(S) DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, +# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO +# EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY SPECIAL, INDIRECT OR +# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, +# DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER +# TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR +# PERFORMANCE OF THIS SOFTWARE. +# +# Dari/Eastern Farsi (prs) +# +# We assume that Afghan Persian uses the same orthography as Iranian +# Persian, although the actual orthography is probably less strict than that +# of the Iranian Academy of Persian Language and Literature. +include fa.orth diff --git a/fc-lang/ur.orth b/fc-lang/ur.orth index 767da03..d9b944a 100644 --- a/fc-lang/ur.orth +++ b/fc-lang/ur.orth @@ -2,6 +2,7 @@ # fontconfig/fc-lang/ur.orth # # Copyright © 2002 Keith Packard +# Copyright © 2009 Roozbeh Pournader # # Permission to use, copy, modify, distribute, and sell this software and its # documentation for any purpose is hereby granted without fee, provided that @@ -21,42 +22,44 @@ # TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR # PERFORMANCE OF THIS SOFTWARE. # -# Urdu (UR) +# Urdu (ur) # -# Data from Roozbeh Pournader +# We are assuming that: +# * Most fonts that claim to support an Arabic letter actually do so; +# * Most modern text rendering software use OpenType tables, instead of +# directly using presentation forms. +# * Some good Arabic fonts do not support codepoints for Arabic presentation +# forms. +# Thus, we are switching to general forms of Arabic letters. # -# Select fonts based on support for presentation forms; this may -# exclude some OpenType fonts, but the hope is those would be -# located by a clever shaper by Unicode codepoints in any case. -# -# General forms. -#0621-0624 -#0626-063a -#0641-0642 -#0644-0648 -#0679 -#067e -#0686 -#0688 -#0691 -#0698 -#06a9 -#06af -#06ba -#06be -#06cc -#06d2 -# Presentations Forms: -fb56-fb59 -fb66-fb69 -fb7a-fb7d -fb88-fb8d -fb8e-fb95 -fb9e-fb9f -fbfc-fbff -fbaa-fbaf -fe80-fe86 -fe89-fed8 -fedd-feee -#fef5-fef8 # These four happen very rarely -fefb-fefc +# General forms: +0621-0624 +0626-063a +0641-0642 +0644-0648 +0679 +067e +0686 +0688 +0691 +0698 +06a9 +06af +06ba +06be +06cc +06d2 +# Presentations forms: +#fb56-fb59 +#fb66-fb69 +#fb7a-fb7d +#fb88-fb8d +#fb8e-fb95 +#fb9e-fb9f +#fbfc-fbff +#fbaa-fbaf +#fe80-fe86 +#fe89-fed8 +#fedd-feee +##fef5-fef8 # These four happen very rarely +#fefb-fefc -- 2.39.5