dvipdfm-x: Support for new Adobe-Japan1-UCS2 CMap

git-svn-id: svn://tug.org/texlive/trunk/Build/source@68889 c570f23f-e606-0410-a88d-b1316a301751

texk/dvipdfm-x/ChangeLog

@@ -1,3 +1,12 @@
+2023-11-18  Yukimasa Morimi  <h20y6m@yahoo.co.jp>
+
+	* cidtype2.c, unicode.c: Support for new Adobe-Japan1-UCS2 CMap.
+	Ignore variation selectors, when mapping from CID to Unicode.
+	Converts CJK Unified Ideographs with variant selectors to
+	CJK Compatibility Ideographs, if possible.
+	https://github.com/texjporg/tex-jp-build/issues/155
+	* configure.ac: version 20231118.
+
 2023-08-11  TANAKA Takuji  <ttk@t-lab.opal.ne.jp>
 
 	* dpxfile.c: Avoid compiler warning on MinGW.

texk/dvipdfm-x/cidtype2.c

@@ -463,18 +463,78 @@ cid_to_code (CMap *cmap, CID cid, int unicode_cmap)
   else if (outbytesleft == 28) {
     if (unicode_cmap) {
       /* We assume the output encoding is UTF-16. */
-      int32_t              uc;
+      int32_t              uc, uvs;
       const unsigned char *endptr;
 
       p      = outbuf;
       endptr = p + 4;
       uc = UC_UTF16BE_decode_char(&p, endptr);
-      if (p != endptr)
-        WARN("CID=%u mapped to non-single Unicode characters...", cid);
-      return p == endptr ? uc : -1;
+      if (p == endptr)
+        return uc; /* single Unicode characters */
+      /* Check following Variation Selectors */
+      uvs = UC_UTF16BE_decode_char(&p, endptr);
+      if (p == endptr && uvs >= 0xfe00 && uvs <= 0xfe0f) {
+          /* Combine CJK compatibility ideograph */
+          int32_t cci = UC_Combine_CJK_compatibility_ideograph(uc, uvs);
+          if (cci > 0)
+            return cci;
+          /* Ignore Standardized Variation Sequence */
+          WARN("Ignored Variation Selector: CID=%u mapped to U+%04X U+%04X", cid, uc, uvs);
+          return uc;
+      }
+      WARN("CID=%u mapped to non-single Unicode characters...", cid);
+      return -1;
     } else {
       return (outbuf[0] << 24)|(outbuf[1] << 16)|(outbuf[2] << 8)|outbuf[3];
     }
+  } else if (outbytesleft == 26) { /* 6 bytes sequence */
+    if (unicode_cmap) {
+      /* We assume the output encoding is UTF-16. */
+      int32_t              uc, uvs;
+      const unsigned char *endptr;
+
+      p      = outbuf;
+      endptr = p + 6;
+      uc = UC_UTF16BE_decode_char(&p, endptr);
+      uvs = UC_UTF16BE_decode_char(&p, endptr);
+      if (p == endptr) {
+        if (uvs >= 0xfe00 && uvs <= 0xfe0f) {
+          /* Combine CJK compatibility ideograph */
+          int32_t cci = UC_Combine_CJK_compatibility_ideograph(uc, uvs);
+          if (cci > 0)
+            return cci;
+          /* Ignore Standardized Variation Sequence */
+          WARN("Ignored Variation Selector: CID=%u mapped to U+%04X U+%04X", cid, uc, uvs);
+          return uc;
+        } else if (uvs >= 0xe0100 && uvs <= 0xe01ef) {
+          /* Ignore Ideographic Variation Sequence */
+          WARN("Ignored Variation Selector: CID=%u mapped to U+%04X U+%04X", cid, uc, uvs);
+          return uc;
+        }
+      }
+      WARN("CID=%u mapped to non-single Unicode characters...", cid);
+      return -1;
+    }
+  } else if (outbytesleft == 24) {  /* 8 bytes sequence */
+    if (unicode_cmap) {
+      /* We assume the output encoding is UTF-16. */
+      int32_t              uc, uvs;
+      const unsigned char *endptr;
+
+      p      = outbuf;
+      endptr = p + 8;
+      uc = UC_UTF16BE_decode_char(&p, endptr);
+      uvs = UC_UTF16BE_decode_char(&p, endptr);
+      if (p == endptr) {
+        if (uvs >= 0xe0100 && uvs <= 0xe01ef) {
+          /* Ignore Ideographic Variation Sequence */
+          WARN("Ignored Variation Selector: CID=%u mapped to U+%04X U+%04X", cid, uc, uvs);
+          return uc;
+        }
+      }
+      WARN("CID=%u mapped to non-single Unicode characters...", cid);
+      return -1;
+      }
   }
 
   return -1;

texk/dvipdfm-x/configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for dvipdfm-x (TeX Live) 20230429.
+# Generated by GNU Autoconf 2.71 for dvipdfm-x (TeX Live) 20231118.
 #
 # Report bugs to <dvipdfmx@tug.org>.
 #
@@ -629,8 +629,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='dvipdfm-x (TeX Live)'
 PACKAGE_TARNAME='dvipdfm-x--tex-live-'
-PACKAGE_VERSION='20230429'
-PACKAGE_STRING='dvipdfm-x (TeX Live) 20230429'
+PACKAGE_VERSION='20231118'
+PACKAGE_STRING='dvipdfm-x (TeX Live) 20231118'
 PACKAGE_BUGREPORT='dvipdfmx@tug.org'
 PACKAGE_URL=''
 
@@ -1396,7 +1396,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures dvipdfm-x (TeX Live) 20230429 to adapt to many kinds of systems.
+\`configure' configures dvipdfm-x (TeX Live) 20231118 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1468,7 +1468,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of dvipdfm-x (TeX Live) 20230429:";;
+     short | recursive ) echo "Configuration of dvipdfm-x (TeX Live) 20231118:";;
    esac
   cat <<\_ACEOF
 
@@ -1598,7 +1598,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-dvipdfm-x (TeX Live) configure 20230429
+dvipdfm-x (TeX Live) configure 20231118
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -2354,7 +2354,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by dvipdfm-x (TeX Live) $as_me 20230429, which was
+It was created by dvipdfm-x (TeX Live) $as_me 20231118, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -8795,7 +8795,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='dvipdfm-x--tex-live-'
- VERSION='20230429'
+ VERSION='20231118'
 
 
 printf "%s\n" "#define PACKAGE \"$PACKAGE\"" >>confdefs.h
@@ -15801,7 +15801,7 @@ Usage: $0 [OPTIONS]
 Report bugs to <bug-libtool@gnu.org>."
 
 lt_cl_version="\
-dvipdfm-x (TeX Live) config.lt 20230429
+dvipdfm-x (TeX Live) config.lt 20231118
 configured by $0, generated by GNU Autoconf 2.71.
 
 Copyright (C) 2011 Free Software Foundation, Inc.
@@ -17723,7 +17723,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by dvipdfm-x (TeX Live) $as_me 20230429, which was
+This file was extended by dvipdfm-x (TeX Live) $as_me 20231118, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -17795,7 +17795,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-dvipdfm-x (TeX Live) config.status 20230429
+dvipdfm-x (TeX Live) config.status 20231118
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 

texk/dvipdfm-x/configure.ac

@@ -8,7 +8,7 @@ dnl   This file is free software; the copyright holder
 dnl   gives unlimited permission to copy and/or distribute it,
 dnl   with or without modifications, as long as this notice is preserved.
 dnl
-AC_INIT([dvipdfm-x (TeX Live)], [20230429], [dvipdfmx@tug.org])
+AC_INIT([dvipdfm-x (TeX Live)], [20231118], [dvipdfmx@tug.org])
 AC_PREREQ([2.65])
 AC_CONFIG_SRCDIR([agl.c])
 AC_CONFIG_AUX_DIR([../../build-aux])