Hi,

On Thu, Dec 23, 2004 at 07:43:40PM +0100, Agustin Martin wrote:
> On Thu, Dec 23, 2004 at 01:54:54PM +0100, Guillem Jover wrote:

> > Ok here it goes the initial UTF-8 patch. This patch also:
> > 
> >  * Change language descriptions (so they are not improperly displayed
> >    on UTF-8 encodings).
> >  * Add some missing OtherChars.
> >  * Change default charsets (to ISO-8859-15).
> >  * Remove redundant and invalid AdditionalChars.
> > 
> > The only problem is that it does not behave properly with the ���
> > character, it does not consider it part of a word, and I'm not sure
> > if I need to add an Otherchars field in the UTF-8 entry and with what
> > encoding. Agust�n what do you think?

> Otherchars refers only to emacs. I do not have a catalan dict available, but
> I suppose it is defined as a stringchar in the base encoding. I will try to
> take a look after Christmas.

I've fixed all stuff Agust�n pointed out.
Here's the revised pseudo-changelog. Patch attached.

 * Add initial UTF-8 support.
 * Remove obsolete Pspell-Ispell.
 * Added Aspell-Locales.
 * Change language descriptions.
 * Add some missing OtherChars.
 * Remove redundant and invalid AdditionalChars.

regards,
guillem
diff -Naur ispellcat-0.4.orig/catalan-i.aff ispellcat-0.4/catalan-i.aff
--- ispellcat-0.4.orig/catalan-i.aff    2004-02-11 14:48:47.000000000 +0100
+++ ispellcat-0.4/catalan-i.aff 2005-01-20 18:37:56.000000000 +0100
@@ -88,6 +88,35 @@
 altstringchar  \"u             �
 altstringchar  \"U             �
 
+# utf8 encoding.
+
+altstringtype "utf8" "tex" ".txt"
+
+altstringchar    @aacute;      �
+altstringchar    @Aacute;      �
+altstringchar    @agrave;      �
+altstringchar    @Agrave;      �
+altstringchar    @eacute;      �
+altstringchar    @Eacute;      �
+altstringchar    @egrave;      �
+altstringchar    @Egrave;      �
+altstringchar    @iacute;      �
+altstringchar    @Iacute;      �
+altstringchar    @iuml;                �
+altstringchar    @Iuml;                �
+altstringchar    @oacute;      �
+altstringchar    @Oacute;      �
+altstringchar    @ograve;      �
+altstringchar    @Ograve;      �
+altstringchar    @uacute;      �
+altstringchar    @Uacute;      �
+altstringchar    @uuml;                �
+altstringchar    @Uuml;                �
+altstringchar    @ccedilla;    �
+altstringchar    @Ccedilla;    �
+altstringchar    @ntilde;      �
+altstringchar    @Ntilde;      �
+altstringchar    @middledot;   �
 
 # Relaci� de flags emprats
 
diff -Naur ispellcat-0.4.orig/debian/aspell-ca.info-aspell 
ispellcat-0.4/debian/aspell-ca.info-aspell
--- ispellcat-0.4.orig/debian/aspell-ca.info-aspell     2005-01-20 
18:15:00.000000000 +0100
+++ ispellcat-0.4/debian/aspell-ca.info-aspell  2005-01-20 18:11:19.000000000 
+0100
@@ -1,12 +1,12 @@
-Language: catal�8 (Catalan 8 bits)
+Language: catala8 (Catalan 8 bits)
 Hash-Name: catala
 Emacsen-Name: catala8
 Casechars: [A-Z����������������a-z����������������]
 Not-Casechars: [^A-Z����������������a-z����������������]
 Otherchars: [---'.�]
-Many-Otherchars:
-Additionalchars: ������������������I���������
+Many-Otherchars: yes
 Additionalchars: ��������������������������������
 Ispell-Args: -B -d catala
 Extended-Character-Mode: ~list
 Coding-System: iso-8859-1
+Aspell-Locales: ca
diff -Naur ispellcat-0.4.orig/debian/icatalan.info-ispell 
ispellcat-0.4/debian/icatalan.info-ispell
--- ispellcat-0.4.orig/debian/icatalan.info-ispell      2005-01-20 
18:15:00.000000000 +0100
+++ ispellcat-0.4/debian/icatalan.info-ispell   2005-01-20 18:14:17.000000000 
+0100
@@ -1,11 +1,11 @@
-Language: catal� TeX (Catalan Tex)
+Language: catala TeX (Catalan Tex)
 Hash-Name: catala
 Emacsen-Name: catala-tex
 Debconf-Display: no
 Casechars: [A-Z����������������a-z����������������]
 Not-Casechars: [^A-Z����������������a-z����������������]
 Otherchars: [---'.�]
-Many-Otherchars:
+Many-Otherchars: yes
 Ispell-Args:-B -d catala
 Additionalchars: ��������������������������������
 Extended-Character-Mode: ~tex
@@ -17,9 +17,18 @@
 Casechars: [A-Z����������������a-z����������������]
 Not-Casechars: [^A-Z����������������a-z����������������]
 Otherchars: [---'.�]
-Many-Otherchars:
+Many-Otherchars: yes
 Additionalchars: ��������������������������������
 Ispell-Args: -B -d catala
 Extended-Character-Mode: ~list
 Coding-System: iso-8859-1
-Pspell-Ispell: ca iso8859-1
+
+Language: catala-utf8 (Catalan utf-8)
+Hash-Name: catala
+Emacsen-Name: catala-utf8
+Debconf-Display: no
+Emacs-Display: no
+Jed-Display: no
+Ispell-Args: -B -d catala
+Extended-Character-Mode: ~utf8
+Coding-System: utf-8
diff -Naur ispellcat-0.4.orig/debian/rules ispellcat-0.4/debian/rules
--- ispellcat-0.4.orig/debian/rules     2005-01-20 18:15:00.000000000 +0100
+++ ispellcat-0.4/debian/rules  2005-01-20 19:01:53.000000000 +0100
@@ -16,8 +16,10 @@
 
        chmod +x debian/strip_mwl
 
+       # Substitute UTF-8 encoded chars
+       sed -f debian/utf-8.sed catalan-i.aff > catalan-i.debian.aff
 #      This generates the icatalan hash file.
-       buildhash catalan-i.dic catalan-i.aff catala.debian.hash
+       buildhash catalan-i.dic catalan-i.debian.aff catala.debian.hash
 #      This generates the wcatalan wordlist.
        debian/strip_mwl | ispell -d $(CURDIR)/catala.debian -e | \
                tr -s ' ' '\n' | uniq > catala.words.debian
@@ -37,6 +39,7 @@
        dh_testdir
        dh_testroot
        rm -f build-stamp 
+       rm -f catalan-i.debian.aff
        rm -f catala.debian.hash catalan-i.dic.stat catalan-i.dic.cnt
        rm -f catala.words.debian
        rm -f ca.rws ca.dat
@@ -51,7 +54,7 @@
        dh_installdirs
 
        # icatalan stuff
-       install -m 644 catalan-i.aff $(IDICT_DIR)/usr/lib/ispell/catala.aff
+       install -m 644 catalan-i.debian.aff 
$(IDICT_DIR)/usr/lib/ispell/catala.aff
        install -m 644 catala.debian.hash 
$(IDICT_DIR)/usr/lib/ispell/catala.hash
        # wcatalan stuff
        install -m 644 catala.words.debian $(WORDS_DIR)/usr/share/dict/catala
diff -Naur ispellcat-0.4.orig/debian/utf-8.sed ispellcat-0.4/debian/utf-8.sed
--- ispellcat-0.4.orig/debian/utf-8.sed 1970-01-01 01:00:00.000000000 +0100
+++ ispellcat-0.4/debian/utf-8.sed      2005-01-20 18:49:51.000000000 +0100
@@ -0,0 +1,26 @@
+s/@aacute;/á/g
+s/@Aacute;/Á/g
+s/@agrave;/à/g
+s/@Agrave;/À/g
+s/@eacute;/é/g
+s/@Eacute;/É/g
+s/@egrave;/è/g
+s/@Egrave;/È/g
+s/@iacute;/í/g
+s/@Iacute;/Í/g
+s/@iuml;/ï/g
+s/@Iuml;/Ü/g
+s/@oacute;/ó/g
+s/@Oacute;/Ó/g
+s/@ograve;/ò/g
+s/@Ograve;/Ò/g
+s/@uacute;/ú/g
+s/@Uacute;/Ú/g
+s/@uuml;/ü/g
+s/@Uuml;/Ü/g
+s/@ccedilla;/ç/g
+s/@Ccedilla;/Ç/g
+s/@ntilde;/ñ/g
+s/@Ntilde;/Ñ/g
+s/@middledot;/·/g
+
diff -Naur ispellcat-0.4.orig/debian/wcatalan.info-wordlist 
ispellcat-0.4/debian/wcatalan.info-wordlist
--- ispellcat-0.4.orig/debian/wcatalan.info-wordlist    2005-01-20 
18:15:00.000000000 +0100
+++ ispellcat-0.4/debian/wcatalan.info-wordlist 2005-01-20 18:01:55.000000000 
+0100
@@ -1,10 +1,10 @@
-Language: catal�8 (Catalan 8 bits)
+Language: catala8 (Catalan 8 bits)
 Hash-Name: catala
 Emacsen-Name: catala8
 Casechars: [A-Z����I���������a-z��������������]
 Not-Casechars: [^A-Z����I���������a-z��������������]
-Otherchars: [---'.]
-Many-Otherchars:
+Otherchars: [---'.�]
+Many-Otherchars: yes
 Additionalchars: ������������������I���������
 Ispell-Args: -B -d catala
 Extended-Character-Mode: ~list

Reply via email to