Bug 29312 - RFE: feature to indicate which characters are missing to satisfy the language support

Add fc-validate to check the language coverage in a font.

8 files changed, 497 insertions, 4 deletions

diff --git a/Makefile.am b/Makefile.am
index 6aee88a5..84c91acb 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -23,7 +23,7 @@
 
 SUBDIRS=fontconfig fc-case fc-lang fc-glyphname src \
 	fc-cache fc-cat fc-list fc-match fc-pattern fc-query fc-scan \
-	conf.d test
+	fc-validate conf.d test
 if ENABLE_DOCS
 SUBDIRS += doc
 DIST_SUBDIRS = $(SUBDIRS)
diff --git a/configure.ac b/configure.ac
index 803084c0..55110779 100644
--- a/configure.ac
+++ b/configure.ac
@@ -677,6 +677,7 @@ fc-match/Makefile
 fc-pattern/Makefile
 fc-query/Makefile
 fc-scan/Makefile
+fc-validate/Makefile
 doc/Makefile
 doc/version.sgml
 test/Makefile
diff --git a/doc/fclangset.fncs b/doc/fclangset.fncs
index e2a40b85..c08d60c7 100644
--- a/doc/fclangset.fncs
+++ b/doc/fclangset.fncs
@@ -178,6 +178,14 @@ Returns a string set of all languages in <parameter>langset</parameter>.
 Returns a string set of all known languages.
 @@
 
+@RET@		FcChar8 *
+@FUNC@		FcLangNormalize
+@TYPE1@		const FcChar8 *			@ARG1@		lang
+@PURPOSE@	Normalize the language string
+@DESC@
+Returns a string to make <parameter>lang</parameter> suitable on fontconfig.
+@@
+
 @RET@		const FcCharSet *
 @FUNC@		FcLangGetCharSet
 @TYPE1@		const FcChar8 *			@ARG1@		lang
diff --git a/fc-validate/Makefile.am b/fc-validate/Makefile.am
new file mode 100644
index 00000000..b3c95b40
--- /dev/null
+++ b/fc-validate/Makefile.am
@@ -0,0 +1,60 @@
+#
+#  fontconfig/fc-query/Makefile.am
+#
+#  Copyright © 2003 Keith Packard
+#
+#  Permission to use, copy, modify, distribute, and sell this software and its
+#  documentation for any purpose is hereby granted without fee, provided that
+#  the above copyright notice appear in all copies and that both that
+#  copyright notice and this permission notice appear in supporting
+#  documentation, and that the name of the author(s) not be used in
+#  advertising or publicity pertaining to distribution of the software without
+#  specific, written prior permission.  The authors make no
+#  representations about the suitability of this software for any purpose.  It
+#  is provided "as is" without express or implied warranty.
+#
+#  THE AUTHOR(S) DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+#  INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
+#  EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY SPECIAL, INDIRECT OR
+#  CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+#  DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+#  TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+#  PERFORMANCE OF THIS SOFTWARE.
+
+bin_PROGRAMS=fc-validate
+
+DOC2MAN = docbook2man
+
+FC_VALIDATE_SRC=${top_srcdir}/fc-validate
+
+SGML = ${FC_VALIDATE_SRC}/fc-validate.sgml
+
+INCLUDES=-I${top_srcdir} $(FREETYPE_CFLAGS) $(WARN_CFLAGS)
+
+BUILT_MANS=fc-validate.1
+
+if ENABLE_DOCS
+man_MANS=${BUILT_MANS}
+endif
+
+EXTRA_DIST=fc-validate.sgml $(BUILT_MANS)
+
+CLEANFILES =
+
+fc_validate_LDADD = ${top_builddir}/src/libfontconfig.la
+
+if USEDOCBOOK
+
+${man_MANS}: ${SGML}
+	$(AM_V_GEN) $(RM) $@; \
+	$(DOC2MAN) ${SGML}; \
+	$(RM) manpage.*
+
+all-local: $(man_MANS)
+
+CLEANFILES += $(man_MANS)
+else
+all-local:
+endif
+
+-include $(top_srcdir)/git.mk
diff --git a/fc-validate/fc-validate.c b/fc-validate/fc-validate.c
new file mode 100644
index 00000000..6ecff367
--- /dev/null
+++ b/fc-validate/fc-validate.c
@@ -0,0 +1,242 @@
+/*
+ * fontconfig/fc-validate/fc-validate.c
+ *
+ * Copyright © 2003 Keith Packard
+ * Copyright © 2012 Red Hat, Inc.
+ * Red Hat Author(s): Akira TAGOH
+ *
+ * Permission to use, copy, modify, distribute, and sell this software and its
+ * documentation for any purpose is hereby granted without fee, provided that
+ * the above copyright notice appear in all copies and that both that
+ * copyright notice and this permission notice appear in supporting
+ * documentation, and that the name of the author(s) not be used in
+ * advertising or publicity pertaining to distribution of the software without
+ * specific, written prior permission.  The authors make no
+ * representations about the suitability of this software for any purpose.  It
+ * is provided "as is" without express or implied warranty.
+ *
+ * THE AUTHOR(S) DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
+ * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
+ * EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY SPECIAL, INDIRECT OR
+ * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+ * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+ * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+ * PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifdef HAVE_CONFIG_H
+#include <config.h>
+#else
+#ifdef linux
+#define HAVE_GETOPT_LONG 1
+#endif
+#define HAVE_GETOPT 1
+#endif
+
+#include <fontconfig/fontconfig.h>
+#include <fontconfig/fcfreetype.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <locale.h>
+
+#ifndef HAVE_GETOPT
+#define HAVE_GETOPT 0
+#endif
+#ifndef HAVE_GETOPT_LONG
+#define HAVE_GETOPT_LONG 0
+#endif
+
+#if HAVE_GETOPT_LONG
+#undef  _GNU_SOURCE
+#define _GNU_SOURCE
+#include <getopt.h>
+static const struct option longopts[] = {
+    {"index", 1, 0, 'i'},
+    {"lang", 1, 0, 'l'},
+    {"verbose", 0, 0, 'v'},
+    {"version", 0, 0, 'V'},
+    {"help", 0, 0, 'h'},
+    {NULL,0,0,0},
+};
+#else
+#if HAVE_GETOPT
+extern char *optarg;
+extern int optind, opterr, optopt;
+#endif
+#endif
+
+static void
+usage (char *program, int error)
+{
+    FILE *file = error ? stderr : stdout;
+#if HAVE_GETOPT_LONG
+    fprintf (file, "usage: %s [-Vhv] [-i index] [-l LANG] [--index index] [--lang LANG] [--verbose] [--version] [--help] font-file...\n",
+	     program);
+#else
+    fprintf (file, "usage: %s [-Vhv] [-i index] [-l LANG] font-file...\n",
+	     program);
+#endif
+    fprintf (file, "Validate font files and print result\n");
+    fprintf (file, "\n");
+#if HAVE_GETOPT_LONG
+    fprintf (file, "  -i, --index INDEX    display the INDEX face of each font file only\n");
+    fprintf (file, "  -l, --lang=LANG      set LANG instead of current locale\n");
+    fprintf (file, "  -v, --verbose        show more detailed information\n");
+    fprintf (file, "  -V, --version        display font config version and exit\n");
+    fprintf (file, "  -h, --help           display this help and exit\n");
+#else
+    fprintf (file, "  -i INDEX   (index)        display the INDEX face of each font file only\n");
+    fprintf (file, "  -l LANG    (lang)         set LANG instead of current locale\n");
+    fprintf (file, "  -v         (verbose)      show more detailed information\n");
+    fprintf (file, "  -V         (version)      display font config version and exit\n");
+    fprintf (file, "  -h         (help)         display this help and exit\n");
+#endif
+    exit (error);
+}
+
+int
+main (int argc, char **argv)
+{
+    int		index_set = 0;
+    int		set_index = 0;
+    FcChar8     *lang = NULL;
+    const FcCharSet *fcs_lang = NULL;
+    int		err = 0;
+    int		i;
+    FT_Library  ftlib;
+    FcBool      verbose = FcFalse;
+#if HAVE_GETOPT_LONG || HAVE_GETOPT
+    int		c;
+
+    setlocale (LC_ALL, "");
+
+#if HAVE_GETOPT_LONG
+    while ((c = getopt_long (argc, argv, "i:l:mVhv", longopts, NULL)) != -1)
+#else
+    while ((c = getopt (argc, argv, "i:l:mVhv")) != -1)
+#endif
+    {
+	switch (c) {
+	case 'i':
+	    index_set = 1;
+	    set_index = atoi (optarg);
+	    break;
+	case 'l':
+	    lang = (FcChar8 *) FcLangNormalize ((const FcChar8 *) optarg);
+	    break;
+	case 'v':
+	    verbose = FcTrue;
+	    break;
+	case 'V':
+	    fprintf (stderr, "fontconfig version %d.%d.%d\n",
+		     FC_MAJOR, FC_MINOR, FC_REVISION);
+	    exit (0);
+	case 'h':
+	    usage (argv[0], 0);
+	default:
+	    usage (argv[0], 1);
+	}
+    }
+    i = optind;
+#else
+    i = 1;
+    verbose = FcTrue;
+#endif
+
+    if (i == argc)
+	usage (argv[0], 1);
+
+    if (!lang)
+	lang = FcLangNormalize ((const FcChar8 *) setlocale (LC_CTYPE, NULL));
+
+    if (lang)
+	fcs_lang = FcLangGetCharSet (lang);
+
+    if (FT_Init_FreeType (&ftlib))
+    {
+	fprintf (stderr, "Can't initalize FreeType library\n");
+	return 1;
+    }
+
+    for (; i < argc; i++)
+    {
+	int index;
+
+	index = set_index;
+
+	do {
+	    FT_Face face;
+	    FcCharSet *fcs, *fcs_sub;
+
+	    if (FT_New_Face (ftlib, argv[i], index, &face))
+	    {
+		if (!index_set && index > 0)
+		    break;
+		fprintf (stderr, "Unable to open %s\n", argv[i]);
+		err = 1;
+	    }
+	    else
+	    {
+		FcChar32 count;
+
+		fcs = FcFreeTypeCharSet (face, NULL);
+		fcs_sub = FcCharSetSubtract (fcs_lang, fcs);
+
+		count = FcCharSetCount (fcs_sub);
+		if (count > 0)
+		{
+		    FcChar32 ucs4, pos, map[FC_CHARSET_MAP_SIZE];
+
+		    printf ("%s:%d Missing %d glyph(s) to satisfy the coverage for %s language\n",
+			    argv[i], index, count, lang);
+
+		    if (verbose)
+		    {
+			for (ucs4 = FcCharSetFirstPage (fcs_sub, map, &pos);
+			     ucs4 != FC_CHARSET_DONE;
+			     ucs4 = FcCharSetNextPage (fcs_sub, map, &pos))
+			{
+			    int j;
+
+			    for (j = 0; j < FC_CHARSET_MAP_SIZE; j++)
+			    {
+				FcChar32 bits = map[j];
+				FcChar32 base = ucs4 + j * 32;
+				int b = 0;
+
+				while (bits)
+				{
+				    if (bits & 1)
+					printf ("  0x%04x\n", base + b);
+				    bits >>= 1;
+				    b++;
+				}
+			    }
+			}
+		    }
+		}
+		else
+		{
+		    printf ("%s:%d Satisfy the coverage for %s language\n", argv[i], index, lang);
+		}
+
+		FcCharSetDestroy (fcs);
+		FcCharSetDestroy (fcs_sub);
+
+		FT_Done_Face (face);
+	    }
+
+	    index++;
+	} while (index_set == 0);
+    }
+
+    FT_Done_FreeType (ftlib);
+
+    if (lang)
+	FcStrFree (lang);
+
+    FcFini ();
+    return err;
+}
diff --git a/fc-validate/fc-validate.sgml b/fc-validate/fc-validate.sgml
new file mode 100644
index 00000000..c677ef29
--- /dev/null
+++ b/fc-validate/fc-validate.sgml
@@ -0,0 +1,182 @@
+<!doctype refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN" [
+
+<!-- Process this file with docbook-to-man to generate an nroff manual
+     page: `docbook-to-man manpage.sgml > manpage.1'.  You may view
+     the manual page with: `docbook-to-man manpage.sgml | nroff -man |
+     less'.  A typical entry in a Makefile or Makefile.am is:
+
+manpage.1: manpage.sgml
+	docbook-to-man $< > $@
+
+
+	The docbook-to-man binary is found in the docbook-to-man package.
+	Please remember that if you create the nroff version in one of the
+	debian/rules file targets (such as build), you will need to include
+	docbook-to-man in your Build-Depends control field.
+
+  -->
+
+  <!-- Fill in your name for FIRSTNAME and SURNAME. -->
+  <!ENTITY dhfirstname "<firstname>Akira</firstname>">
+  <!ENTITY dhsurname   "<surname>TAGOH</surname>">
+  <!-- Please adjust the date whenever revising the manpage. -->
+  <!ENTITY dhdate      "<date>Sep 10, 2012</date>">
+  <!-- SECTION should be 1-8, maybe w/ subsection other parameters are
+       allowed: see man(7), man(1). -->
+  <!ENTITY dhsection   "<manvolnum>1</manvolnum>">
+  <!ENTITY dhemail     "<email>akira@tagoh.org</email>">
+  <!ENTITY dhusername  "Akira TAGOH">
+  <!ENTITY dhucpackage "<refentrytitle>fc-validate</refentrytitle>">
+  <!ENTITY dhpackage   "fc-validate">
+
+  <!ENTITY gnu         "<acronym>GNU</acronym>">
+  <!ENTITY gpl         "&gnu; <acronym>GPL</acronym>">
+]>
+
+<refentry>
+  <refentryinfo>
+    <address>
+      &dhemail;
+    </address>
+    <author>
+      &dhfirstname;
+      &dhsurname;
+    </author>
+    <copyright>
+      <year>2012</year>
+      <holder>&dhusername;</holder>
+    </copyright>
+    &dhdate;
+  </refentryinfo>
+  <refmeta>
+    &dhucpackage;
+
+    &dhsection;
+  </refmeta>
+  <refnamediv>
+    <refname>&dhpackage;</refname>
+
+    <refpurpose>validate font files</refpurpose>
+  </refnamediv>
+  <refsynopsisdiv>
+    <cmdsynopsis>
+      <command>&dhpackage;</command>
+
+      <arg><option>-Vhv</option></arg>
+      <sbr>
+      <group>
+        <arg><option>-i</option> <option><replaceable>index</replaceable></option></arg>
+        <arg><option>--index</option> <option><replaceable>index</replaceable></option></arg>
+      </group>
+      <group>
+	<arg><option>-l</option> <option><replaceable>lang</replaceable></option></arg>
+	<arg><option>--lang</option> <option><replaceable>lang</replaceable></option></arg>
+      </group>
+      <arg><option>--verbose</option></arg>
+      <arg><option>--version</option></arg>
+      <arg><option>--help</option></arg>
+      <arg choice="req" rep="repeat"><option><replaceable>font-file</replaceable></option></arg>
+
+     </cmdsynopsis>
+  </refsynopsisdiv>
+  <refsect1>
+    <title>DESCRIPTION</title>
+
+    <para><command>&dhpackage;</command> validates
+    <replaceable>font-file</replaceable>(s) if each fonts satisfies
+    the language coverage according to the orthography files in fontconfig.
+    If <option>--index</option> is given, only one face of each file is
+    validated, otherwise all faces are validated.</para>
+
+  </refsect1>
+  <refsect1>
+    <title>OPTIONS</title>
+
+    <para>This program follows the usual &gnu; command line syntax,
+      with long options starting with two dashes (`-').  A summary of
+      options is included below.</para>
+
+    <variablelist>
+      <varlistentry>
+        <term><option>-i</option>
+          <option>--index</option>
+	  <option><replaceable>index</replaceable></option>
+        </term>
+        <listitem>
+          <para>Only query face indexed <replaceable>index</replaceable> of
+	  each file.</para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><option>-l</option>
+	  <option>--lang</option>
+	  <option><replaceable>lang</replaceable></option>
+	</term>
+	<listitem>
+	  <para>Set <replaceable>lang</replaceable> as a language instead of current locale. this is used for <option>-m</option>.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+	<term><option>-v</option>
+	  <option>--verbose</option>
+	</term>
+	<listitem>
+	  <para>Show more detailed information.</para>
+	</listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><option>-V</option>
+          <option>--version</option>
+        </term>
+        <listitem>
+          <para>Show version of the program and exit.</para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><option>-h</option>
+          <option>--help</option>
+        </term>
+        <listitem>
+          <para>Show summary of options.</para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><option><replaceable>font-file</replaceable></option>
+        </term>
+        <listitem>
+          <para>Query <replaceable>font-file</replaceable> for font faces.</para>
+        </listitem>
+      </varlistentry>
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>RETURN CODES</title>
+    <para><command>fc-validate</command> returns error code 0 for successful parsing,
+    or 1 if any errors occured or if at least one font face could not be opened.</para>
+  </refsect1>
+
+  <refsect1>
+    <title>AUTHOR</title>
+
+    <para>This manual page was updated by &dhusername; &dhemail;.</para>
+
+  </refsect1>
+</refentry>
+
+<!-- Keep this comment at the end of the file
+Local variables:
+mode: sgml
+sgml-omittag:t
+sgml-shorttag:t
+sgml-minimize-attributes:nil
+sgml-always-quote-attributes:t
+sgml-indent-step:2
+sgml-indent-data:t
+sgml-parent-document:nil
+sgml-default-dtd-file:nil
+sgml-exposed-tags:nil
+sgml-local-catalogs:nil
+sgml-local-ecat-files:nil
+End:
+-->
diff --git a/fontconfig/fontconfig.h b/fontconfig/fontconfig.h
index 1af63abf..2a609e5e 100644
--- a/fontconfig/fontconfig.h
+++ b/fontconfig/fontconfig.h
@@ -580,6 +580,9 @@ FcInitBringUptoDate (void);
 FcPublic FcStrSet *
 FcGetLangs (void);
 
+FcPublic FcChar8 *
+FcLangNormalize (const FcChar8 *lang);
+
 FcPublic const FcCharSet *
 FcLangGetCharSet (const FcChar8 *lang);
 
diff --git a/src/fcint.h b/src/fcint.h
index 3883bc96..51292679 100644
--- a/src/fcint.h
+++ b/src/fcint.h
@@ -817,9 +817,6 @@ FcPrivate FcLangSet *
 FcFreeTypeLangSet (const FcCharSet  *charset,
 		   const FcChar8    *exclusiveLang);
 
-FcPrivate FcChar8 *
-FcLangNormalize (const FcChar8 *lang);
-
 FcPrivate FcLangResult
 FcLangCompare (const FcChar8 *s1, const FcChar8 *s2);