Upgrade to libiconv-1.0.

Author: bhaible

ChangeLog

@@ -0,0 +1,98 @@
+2000-01-04  Bruno Haible  <haible@clisp.cons.org>
+
+        * Version 1.0 released.
+        * include/libiconv.h.in (_LIBICONV_VERSION): Bump version number.
+        * src/Makefile.in (LIBICONV_VERSION_INFO): Define to 0:1:0.
+          (libiconv.la): Use LIBICONV_VERSION_INFO.
+
+2000-01-03  Bruno Haible  <haible@clisp.cons.org>
+
+        * tests/Makefile.in: New file.
+          tests/check-stateless, tests/table-from.c, tests/table-to.c,
+          tests/*.TXT, tests/genutf8.c: New files, checks for stateless
+          encodings.
+          tests/check-stateful, tests/iconv.c, tests/*-snippet*: New files,
+          checks for stateful encodings.
+        * Makefile.in (all, check, mostlyclean, clean, distclean,
+           maintainer-clean): Descend into tests directory.
+        * configure.in: Add tests/Makefile to AC_OUTPUT duties.
+
+        * src/gentranslit.c: New file.
+        * Makefile.devel (src/translit.h): New rule.
+        * src/translit.def, src/translit.h: New files.
+        * src/iconv.c: Include it.
+          (iconv): Transliterate using translit.h table.
+
+        * src/genflags.c: New file.
+        * Makefile.devel (src/flags.h): New rule.
+        * src/flags.h: New file.
+        * src/iconv.c: Include it.
+          (encoding): Add field 'oflags'.
+          (all_encodings): Initialize the field 'oflags'.
+          (iconv_open): Copy field 'oflags'.
+          (iconv): Transliterate quotation marks U+2018, U+2019, U+201A.
+        * src/Makefile.in (iconv.lo): Update dependencies.
+
+        * src/converters.h: New file, extracted from src/iconv.c.
+        * src/iconv.c: Include it.
+        * src/Makefile.in (iconv.lo): Update dependencies.
+
+        * tools/cjk_variants.c: New file.
+        * tools/Makefile (ALL): Add cjk_variants.h.
+          (cjk_variants.h, cjk_variants): New rules.
+        * src/cjk_variants.h: New file.
+        * src/iconv.c: Include it.
+          (iconv): Use cjk_variants for transliteration.
+
+        * man/iconv.3: Fix description of return value.
+        * euc_kr.h (euc_kr_wctomb): Remove Hangul transliteration.
+        * iso2022_kr.h (iso2022kr_wctomb): Likewise.
+        * src/iconv.c (iconv): Do Hangul transliteration here and increment
+          result once for every transliterated character.
+        * src/johab_hangul.h (johab_hangul_decompose): Change result array
+          from 'unsigned char*' to 'wchar_t*'.
+
+        * src/cp1258.h (cp1258_mbtowc): Return RET_ILSEQ instead of storing
+          0xfffd.
+
+        * src/georgian_ps.h (georgian_ps_wctomb): Accept 0x00e6.
+
+        * src/euc_jp.h (euc_jp_wctomb): Don't treat U+005C and U+007E like
+          Katakana.
+
+        * src/euc_tw.h (euc_tw_mbtowc): Fix typo.
+
+        * src/cp950.h (cp950_mbtowc, cp950_wctomb): Exclude the range
+          0xC6A1..0xC7FE.
+
+        * tools/cjk_tab_to_h.c (read_table_ksc5601): Some Hangul range was
+          not being excluded. Fix that.
+        * src/ksc5601.h: Regenerated.
+        * src/johab.h (johab_mbtowc): Don't accept 0xDA{A1..D3} - this is
+          valid in KSC5601/KSX1001 but not in JOHAB.
+
+        * src/iconv.c (conv_struct): Add fields iindex, oindex.
+          (iconv_open): Fill in iindex, oindex.
+
+        * src/encodings.def (UCS-2-BE): Add aliases "UNICODE-1-1" and
+          "csUnicode11", from IANA charset list.
+          (MacRoman): Add aliases "MAC" and "csMacintosh" for "MACINTOSH",
+          from IANA charset list.
+          (JIS_X0208): Add aliases "X0208", "ISO-IR-87", "csISO87JISX0208",
+          from IANA charset list.
+          (GB_2312-80): New encoding, from IANA charset list.
+
+        * README, man/iconv_open.3: Add MacIceland and MacUkraine.
+
+        * Makefile.devel: Add rules for src/aliases.h and src/aliases.gperf.
+          (all): Depend on src/aliases.h.
+        * src/Makefile.in: Remove rules for $(srcdir)/aliases.h and
+          $(srcdir)/aliases.gperf.
+          (clean): Clean up.
+
+        * src/Makefile.in (libiconv_plug_linux.so): Remove unneeded "-ldl".
+
+1999-12-31  Bruno Haible  <haible@clisp.cons.org>
+
+        * Version 0.3 released.
+

Makefile.devel

@@ -3,14 +3,20 @@
 
 SHELL = /bin/sh
 MAKE = make
+GPERF = gperf
+CC = gcc
+CFLAGS = -O
+CP = cp
+RM = rm -f
 
 
-all : configures src/config.h.msvc include/libiconv.h.msvc
+all : configures src/config.h.msvc include/libiconv.h.msvc src/aliases.h src/flags.h src/translit.h
 
 
 # Before making a new release:
-# - check that the encoding lists in README and iconv_open.3 are up to date,
-# - increment the version number in libiconv.h.in.
+# - check that the encoding lists in README and man/iconv_open.3 are up to date,
+# - increment the version number in include/libiconv.h.in and README,
+# - update the version info in src/Makefile.in,
 # - do "make -f Makefile.devel".
 
 
@@ -43,4 +49,29 @@ include/libiconv.h.msvc : include/libiconv.h.in
 	sed -e 's/@INCLUDE_ICONV_H@//g' -e 's/@HAVE_ICONV_H@/0/' -e 's/@ICONV_CONST@/const/g' < $< > $@
 
 
+# We use "-7" to make a smaller table, but use "unsigned char" array indices
+# to avoid gcc warning.
+src/aliases.h : src/aliases.gperf
+	$(GPERF) -t -L ANSI-C -H aliases_hash -N aliases_lookup -7 -C -k '1,3-7,9-11,$$' src/aliases.gperf | sed -e 's/\[str/\[(unsigned char) str/' > tmp.h
+	$(CP) tmp.h src/aliases.h
+	$(RM) tmp.h
+
+src/aliases.gperf : src/encodings.def src/genaliases.c
+	$(CC) $(CFLAGS) src/genaliases.c -o genaliases
+	./genaliases > src/aliases.gperf
+	$(RM) genaliases
+
+
+src/flags.h : src/converters.h src/genflags.c
+	$(CC) $(CFLAGS) src/genflags.c -o genflags
+	./genflags > src/flags.h
+	$(RM) genflags
+
+
+src/translit.h : src/translit.def src/gentranslit.c
+	$(CC) $(CFLAGS) src/gentranslit.c -o gentranslit
+	./gentranslit < src/translit.def > src/translit.h
+	$(RM) gentranslit
+
+
 force :

Makefile.in

@@ -29,6 +29,7 @@ SHELL = /bin/sh
 all : force
 	cd src; $(MAKE) -r all
 	cd man; $(MAKE) -r all
+	if test -d tests; then cd tests; $(MAKE) -r all; fi
 
 # Installs the library and include files only. Typically called with only
 # $(libdir) and $(includedir) - don't use $(prefix) and $(exec_prefix) here.
@@ -60,24 +61,29 @@ uninstall : force
 check : force
 	cd src; $(MAKE) -r check
 	cd man; $(MAKE) -r check
+	if test -d tests; then cd tests; $(MAKE) -r check; fi
 
 mostlyclean : force
 	cd src; $(MAKE) -r mostlyclean
 	cd man; $(MAKE) -r mostlyclean
+	if test -d tests; then cd tests; $(MAKE) -r mostlyclean; fi
 
 clean : force
 	cd src; $(MAKE) -r clean
 	cd man; $(MAKE) -r clean
+	if test -d tests; then cd tests; $(MAKE) -r clean; fi
 
 distclean : force
 	cd src; if test -f Makefile; then $(MAKE) -r distclean; fi
 	cd man; if test -f Makefile; then $(MAKE) -r distclean; fi
+	if test -d tests; then cd tests; if test -f Makefile; then $(MAKE) -r distclean; fi; fi
 	$(RM) config.status config.log config.cache Makefile libtool
 	$(RM) include/libiconv.h
 
 maintainer-clean : force
 	cd src; if test -f Makefile; then $(MAKE) -r maintainer-clean; fi
 	cd man; if test -f Makefile; then $(MAKE) -r maintainer-clean; fi
+	if test -d tests; then cd tests; if test -f Makefile; then $(MAKE) -r maintainer-clean; fi; fi
 	$(RM) config.status config.log config.cache Makefile libtool
 	$(RM) include/libiconv.h
 

NEWS

@@ -1,3 +1,17 @@
+New in 1.0:
+* Added transliteration facilities.
+* Added a test suite.
+* Fixed the iconv(3) manual page and function: the return value was not
+  described correctly.
+* Fixed a bug in the CP1258 decoder: invalid bytes now yield EILSEQ instead of
+  U+FFFD.
+* Fixed a bug in the Georgian-PS encoder: accept U+00E6.
+* Fixed a bug in the EUC-JP encoder: reject 0x8E5C and 0x8E7E.
+* Fixed a bug in the KSC5601 and JOHAB converters: they recognized some Hangul
+  characters at some invalid code positions.
+* Fixed a bug in the EUC-TW decoder; it was severely broken.
+* Fixed a bug in the CP950 converter: it recognized a dubious BIG5 range.
+
 New in 0.3:
 * Reduced the size of the tables needed for the JOHAB converter.
 * Portability to Win32.

NOTES

@@ -295,10 +295,14 @@ A: 1. Explain the "why" in this file, above.
    the new character set name, with the proper dimensions, but that shouldn't
    be too hard. This yields the CCS. The CES you have to write by hand.
    4. Store the resulting C code file in the src directory. Add a #include
-   directive to iconv.c, and add an entry to the encodings.def file.
+   directive to converters.h, and add an entry to the encodings.def file.
    5. Compile the package, and test your new encoding using a program like
    iconv(1) or clisp(1).
-   6. Update the README and man3/iconv_open.3, to mention the new encoding.
+   6. Augment the testsuite: Add a line to tests/Makefile.in. For a stateless
+   encoding, create the complete table as a TXT file. For a stateful encoding,
+   provide a text snippet encoded using your new encoding and its UTF-8
+   equivalent.
+   7. Update the README and man3/iconv_open.3, to mention the new encoding.
    Add a note in the NEWS file.
 
 Q: What about bidirectional text? Should it be tagged or reversed when
@@ -311,7 +315,6 @@ A: After reading RFC 1556: I don't think so. Support for ISO-8859-8-I and
    the same as ISO-8859-8-I. I'm confused.
 
 Other character sets not implemented:
-"macintosh" = "mac" = "csMacintosh"
 "MNEMONIC" = "csMnemonic"
 "MNEM" = "csMnem"
 "ISO-10646-UCS-Basic" = "csUnicodeASCII"
@@ -324,7 +327,22 @@ Other aliases not implemented (and not implemented in glibc-2.1 either):
   From MSIE4:
     ISO-8859-1: alias ISO8859-1
     ISO-8859-2: alias ISO8859-2
-    GB2312: aliases CHINESE CSISO58GB231280 GB_2312-80 ISO-IR-58
     KSC_5601: alias KS_C_5601
     UTF-8: aliases UNICODE-1-1-UTF-8 UNICODE-2-0-UTF-8
 
+
+Q: How can I integrate libiconv into my package?
+A: Just copy the entire libiconv package into a subdirectory of your package.
+   At configuration time, call libiconv's configure script with the
+   appropriate --srcdir option and maybe --enable-static or --disable-shared.
+   Then "cd libiconv && make && make install-lib libdir=... includedir=...".
+   'install-lib' is a special (not GNU standardized) target which installs
+   only the include file - in $(includedir) - and the library - in $(libdir) -
+   and does not use other directory variables. After "installing" libiconv
+   in your package's build directory, building of your package can proceed.
+
+Q: Why is the testsuite so big?
+A: Because some of the tests are very comprehensive.
+   If you don't feel like using the testsuite, you can simply remove the
+   tests/ directory.
+

README

@@ -1,3 +1,5 @@
+              LIBICONV - character set conversion library
+
 This library provides an iconv() implementation, for use on systems which
 don't have one, or whose implementation cannot convert from/to Unicode.
 
@@ -6,7 +8,8 @@ It provides support for the encodings:
     European languages
         ASCII, ISO-8859-{1,2,3,4,5,7,9,10,13,14,15}, KOI8-R, KOI8-U, KOI8-RU,
         CP{1250,1251,1252,1253,1254,1257}, CP{850,866},
-        Mac{Roman,CentralEurope,Croatian,Romania,Cyrillic,Greek,Turkish},
+        Mac{Roman,CentralEurope,Iceland,Croatian,Romania},
+        Mac{Cyrillic,Ukraine,Greek,Turkish},
         Macintosh
     Semitic languages
         ISO-8859-{6,8}, CP{1255,1256}, Mac{Hebrew,Arabic}
@@ -35,7 +38,9 @@ It provides support for the encodings:
         UCS-2-INTERNAL, UCS-4-INTERNAL
 
 It can convert from any of these encodings to any other, through Unicode
-conversion.
+conversion. It has also some limited support for transliteration, i.e.
+when a character cannot be represented in the target character set, it can
+be approximated through one or several similarly looking characters.
 
 libiconv is for you if your application needs to support multiple character
 encodings, but that support lacks from your system.
@@ -71,4 +76,12 @@ This library can be built and installed in two variants:
     A program's source need not be modified, the program need not even be
     recompiled. Just set the LD_PRELOAD environment variable, that's it!
 
+
+Distribution:
+    ftp://ftp.ilog.fr/pub/Users/haible/gnu/libiconv-1.0.tar.gz
+
+Homepage:
+    http://clisp.cons.org/~haible/packages-libiconv.html
+
+
 Bruno Haible <haible@clisp.cons.org>

TODO

@@ -1717,7 +1717,11 @@ else
 fi
 
 
-test -d include || mkdir include
+if test -d "${srcdir}/tests"; then
+  TESTS_MAKEFILE=tests/Makefile
+else
+  TESTS_MAKEFILE=""
+fi
 trap '' 1 2 15
 cat > confcache <<\EOF
 # This file is a shell script that caches the results of configure
@@ -1818,7 +1822,7 @@ done
 
 ac_given_srcdir=$srcdir
 
-trap 'rm -fr `echo "Makefile src/Makefile man/Makefile include/libiconv.h src/config.h" | sed "s/:[^ ]*//g"` conftest*; exit 1' 1 2 15
+trap 'rm -fr `echo "Makefile src/Makefile man/Makefile ${TESTS_MAKEFILE} include/libiconv.h src/config.h" | sed "s/:[^ ]*//g"` conftest*; exit 1' 1 2 15
 EOF
 cat >> $CONFIG_STATUS <<EOF
 
@@ -1912,7 +1916,7 @@ EOF
 
 cat >> $CONFIG_STATUS <<EOF
 
-CONFIG_FILES=\${CONFIG_FILES-"Makefile src/Makefile man/Makefile include/libiconv.h"}
+CONFIG_FILES=\${CONFIG_FILES-"Makefile src/Makefile man/Makefile ${TESTS_MAKEFILE} include/libiconv.h"}
 EOF
 cat >> $CONFIG_STATUS <<\EOF
 for ac_file in .. $CONFIG_FILES; do if test "x$ac_file" != x..; then

configure

@@ -1,4 +1,4 @@
-dnl Copyright (C) 1999 Free Software Foundation, Inc.
+dnl Copyright (C) 1999-2000 Free Software Foundation, Inc.
 dnl This file is part of the GNU ICONV Library.
 dnl
 dnl The GNU ICONV Library is free software; you can redistribute it and/or
@@ -87,5 +87,9 @@ else
 fi
 AC_SUBST(PLUGLIB)
 
-test -d include || mkdir include
-AC_OUTPUT(Makefile src/Makefile man/Makefile include/libiconv.h)
+if test -d "${srcdir}/tests"; then
+  TESTS_MAKEFILE=tests/Makefile
+else
+  TESTS_MAKEFILE=""
+fi
+AC_OUTPUT(Makefile src/Makefile man/Makefile ${TESTS_MAKEFILE} include/libiconv.h)

configure.in

@@ -1,4 +1,4 @@
-/* Copyright (C) 1999 Free Software Foundation, Inc.
+/* Copyright (C) 1999-2000 Free Software Foundation, Inc.
    This file is part of the GNU ICONV Library.
 
    The GNU ICONV Library is free software; you can redistribute it and/or
@@ -26,7 +26,7 @@
 #ifndef _LIBICONV_H
 #define _LIBICONV_H
 
-#define _LIBICONV_VERSION 0x0003    /* version number: (major<<8) + minor */
+#define _LIBICONV_VERSION 0x0100    /* version number: (major<<8) + minor */
 
 /* Include all possible include files which could define iconv_t. */
 /* The next line should include the system's <iconv.h> file. But if it

include/libiconv.h.in

@@ -1,4 +1,4 @@
-/* Copyright (C) 1999 Free Software Foundation, Inc.
+/* Copyright (C) 1999-2000 Free Software Foundation, Inc.
    This file is part of the GNU ICONV Library.
 
    The GNU ICONV Library is free software; you can redistribute it and/or
@@ -26,7 +26,7 @@
 #ifndef _LIBICONV_H
 #define _LIBICONV_H
 
-#define _LIBICONV_VERSION 0x0003    /* version number: (major<<8) + minor */
+#define _LIBICONV_VERSION 0x0100    /* version number: (major<<8) + minor */
 
 /* Include all possible include files which could define iconv_t. */
 /* The next line should include the system's <iconv.h> file. But if it

include/libiconv.h.msvc

@@ -9,7 +9,7 @@
 .\"   GNU glibc-2 source code and manual
 .\"   OpenGroup's Single Unix specification http://www.UNIX-systems.org/online.html
 .\"
-.TH ICONV 3  "November 27, 1999" "GNU" "Linux Programmer's Manual"
+.TH ICONV 3  "January 2, 2000" "GNU" "Linux Programmer's Manual"
 .SH NAME
 iconv \- perform character set conversion
 .SH SYNOPSIS
@@ -66,8 +66,9 @@ A third state is when \fIinbuf\fP is NULL or \fI*inbuf\fP is NULL, and
 \fIoutbuf\fP is NULL or \fI*outbuf\fP is NULL. In this case, the \fBiconv\fP
 function sets \fIcd\fP's conversion state to the initial state.
 .SH "RETURN VALUE"
-The \fBiconv\fP function returns the number of characters converted during
-this call. In case of error, it sets \fBerrno\fP and returns (iconv_t)(-1).
+The \fBiconv\fP function returns the number of characters converted in a
+non-reversible way during this call; reversible conversions are not counted.
+In case of error, it sets \fBerrno\fP and returns (iconv_t)(-1).
 .SH ERRORS
 The following errors can occur, among others:
 .TP