* Merged XML Unicode extensions

ChangeLog

@@ -1,3 +1,8 @@
+Oct 27, 2006
+
+  * ENHANCEMENT: Started branch XML_UNICODE to provide support for Unicode
+    filenames, tags and elements.  
+
 Aug 28, 2006
 
   * DOCUMENTATION: Moved to sgml.doc, using the same system as the

Makefile.in

@@ -41,7 +41,8 @@ INSTALL=@INSTALL@
 INSTALL_PROGRAM=@INSTALL_PROGRAM@
 INSTALL_DATA=@INSTALL_DATA@
 
-LIBOBJ=		parser.o util.o charmap.o catalog.o model.o xmlns.o utf8.o
+LIBOBJ=		parser.o util.o charmap.o catalog.o model.o xmlns.o utf8.o \
+		xml_unicode.o
 PLOBJ=		$(LIBOBJ) error.o sgml2pl.o quote.o
 SGMLOBJ=	$(LIBOBJ) sgml.o
 DTD2PLOBJ=	$(LIBOBJ) dtd2pl.o prolog.o

Makefile.mak

@@ -13,7 +13,7 @@ PLHOME=..\..
 PKGDLL=sgml2pl
 
 LIBOBJ=		parser.obj util.obj charmap.obj catalog.obj \
-		model.obj xmlns.obj utf8.obj
+		model.obj xmlns.obj utf8.obj xml_unicode.obj
 OBJ=		$(LIBOBJ) sgml2pl.obj error.obj quote.obj
 SGMLOBJ=	$(LIBOBJ) sgml.obj
 DTDFILES=	HTML4.dcl HTML4.dtd HTML4.soc \

TODO

@@ -8,3 +8,19 @@ TODO LIST:
 		<tag name="value>
 	* Allow for (a,b) as attribute-type (name-group)
 	* Handle source-info in included SYSTEM entities
+
+UNICODE:
+
+	* Started full unicode support under the CVS branch XML_UNICODE.
+	* Old version only allows for unicide in CDATA (attribute values
+	  and element content)
+	* New adds throughout: element-names, tags, filenames, etc.
+
+	ISSUES:
+		- Port to Windows
+		- Testing
+			- File-entities
+		- Leak setting filename using istrdup() in sgml2pl
+		- Verify performance.  Optimise.
+		- Own character classification and conversion
+			- Copy from Prolog?

Test/ok/utf8-ru.ok

@@ -0,0 +1,2 @@
+[element('Человек', [язык=мова], ['Borys'])].
+[].

Test/utf8-ru.xml

@@ -0,0 +1,3 @@
+<?xml version="1.0" encoding="utf-8"?>
+
+<Человек язык="мова">Borys</Человек>

Test/wrtest.pl

@@ -50,9 +50,13 @@
 	    ml_file(Ext),
 	    file_base_name(File, Base),
 	    \+ blocked(Base),
-	    format(user_error, '~w ... (ISO Latin-1) ...', [Base]),
-	    fixed_point(File, iso_latin_1),
-	    format(user_error, ' (UTF-8) ...', []),
+	    format(user_error, '~w ... ', [Base]),
+	    (	\+ utf8(Base)
+	    ->  format(user_error, ' (ISO Latin-1) ... ', []),
+		fixed_point(File, iso_latin_1)
+	    ;	true
+	    ),
+	    format(user_error, ' (UTF-8) ... ', []),
 	    fixed_point(File, utf8),
 	    format(user_error, ' done~n', []),
 	    fail
@@ -63,7 +67,7 @@
 ml_file(sgml).
 ml_file(html).
 
-%	blocked(+File)
+%%	blocked(+File)
 %	
 %	List of test-files that are blocked.  These are either negative
 %	tests or tests involving SDATA.
@@ -74,8 +78,19 @@
 blocked('cent-nul.xml').
 blocked('defent.sgml').
 
-fixed_point(File) :-
-	fixed_point(File, iso_latin_1).
+
+%%	utf8(+File)
+%
+%	File requires UTF-8.  These are files that have UTF-8 characters
+%	in element or attribute names.
+
+utf8('utf8-ru.xml').
+
+
+%%	fixed_point(+File, +Encoding)
+%
+%	Perform write/read round-trip and  validate   the  data  has not
+%	changed.
 
 fixed_point(File, Encoding) :-
 	file_name_extension(_, xml, File), !,