Use presentation forms for arabic matching, fix comment labeling persian

    general forms

3 files changed, 69 insertions, 53 deletions

diff --git a/fc-lang/ar.orth b/fc-lang/ar.orth
index cd1e428..ae6b1c8 100644
--- a/fc-lang/ar.orth
+++ b/fc-lang/ar.orth
@@ -1,5 +1,5 @@
 #
-# $XFree86$
+# $XFree86: xc/lib/fontconfig/fc-lang/ar.orth,v 1.2 2002/07/06 23:59:15 keithp Exp $
 #
 # Copyright © 2002 Keith Packard, member of The XFree86 Project, Inc.
 #
@@ -22,51 +22,67 @@
 # PERFORMANCE OF THIS SOFTWARE.
 #
 # Arabic (AR)
-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
+#
+# 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 <roozbeh@sharif.edu>
+#
+# 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
diff --git a/fc-lang/fa.orth b/fc-lang/fa.orth
index abdadac..eb590f2 100644
--- a/fc-lang/fa.orth
+++ b/fc-lang/fa.orth
@@ -1,5 +1,5 @@
 #
-# $XFree86$
+# $XFree86: xc/lib/fontconfig/fc-lang/fa.orth,v 1.1 2002/07/09 02:28:26 keithp Exp $
 #
 # Copyright © 2002 Keith Packard, member of The XFree86 Project, Inc.
 #
@@ -29,7 +29,7 @@
 # exclude some OpenType fonts, but the hope is those would be
 # located by a clever shaper by Unicode codepoints in any case.
 #
-# Non presentation forms.
+# General forms.
 #0621-0624
 #0626-063a
 #0641-0642
diff --git a/fc-lang/fclang.h b/fc-lang/fclang.h
index 3f82739..3dc8af5 100644
--- a/fc-lang/fclang.h
+++ b/fc-lang/fclang.h
@@ -34,8 +34,8 @@ static const FcCharLeaf	leaves[520] = {
     0xc0000000, 0xf0fc33c0, 0x03000000, 0x00000000,
     } },
     { { /* 2 */
-    0x88001000, 0x07fffffe, 0x0007ffff, 0x00000000,
     0x00000000, 0x00000000, 0x00000000, 0x00000000,
+    0xffffffff, 0xffffffff, 0xffffffff, 0x1fffffff,
     } },
     { { /* 3 */
     0x00000000, 0x00000000, 0x07fffffe, 0x07fffffe,
@@ -2122,7 +2122,7 @@ static const FcCharLeaf *leaves_ar[1] = {
 };
 
 static const FcChar16 numbers_ar[1] = {
-    0x0006,
+    0x00fe,
 };
 
 static const FcCharLeaf *leaves_az[4] = {