copying Markus Kuhn's ucs 2002-03-11 into trunk

svn path=/trunk/; revision=3976

2 files changed, 263 insertions, 0 deletions

diff --git a/ucs/langinfo.c b/ucs/langinfo.c
new file mode 100644
index 00000000..3d7d64d7
--- /dev/null
+++ b/ucs/langinfo.c
@@ -0,0 +1,119 @@
+/*
+ * This is a quick-and-dirty emulator of the nl_langinfo(CODESET)
+ * function defined in the Single Unix Specification for those systems
+ * (FreeBSD, etc.) that don't have one yet. It behaves as if it had
+ * been called after setlocale(LC_CTYPE, ""), that is it looks at
+ * the locale environment variables.
+ *
+ * http://www.opengroup.org/onlinepubs/7908799/xsh/langinfo.h.html
+ *
+ * Please extend it as needed and suggest improvements to the author.
+ * This emulator will hopefully become redundant soon as
+ * nl_langinfo(CODESET) becomes more widely implemented.
+ *
+ * Since the proposed Li18nux encoding name registry is still not mature,
+ * the output follows the MIME registry where possible:
+ *
+ *   http://www.iana.org/assignments/character-sets
+ *
+ * A possible autoconf test for the availability of nl_langinfo(CODESET)
+ * can be found in
+ *
+ *   http://www.cl.cam.ac.uk/~mgk25/unicode.html#activate
+ *
+ * Markus.Kuhn@cl.cam.ac.uk -- 2002-03-11
+ * Permission to use, copy, modify, and distribute this software
+ * for any purpose and without fee is hereby granted. The author
+ * disclaims all warranties with regard to this software.
+ *
+ * Latest version:
+ *
+ *   http://www.cl.cam.ac.uk/~mgk25/ucs/langinfo.c
+ */
+
+#include <stdlib.h>
+#include <string.h>
+#include "langinfo.h"
+
+#define C_CODESET "US-ASCII"     /* Return this as the encoding of the
+				  * C/POSIX locale. Could as well one day
+				  * become "UTF-8". */
+
+#define digit(x) ((x) >= '0' && (x) <= '9')
+
+static char buf[16];
+
+char *nl_langinfo(nl_item item)
+{
+  char *l, *p;
+  
+  if (item != CODESET)
+    return NULL;
+  
+  if (((l = getenv("LC_ALL"))   && *l) ||
+      ((l = getenv("LC_CTYPE")) && *l) ||
+      ((l = getenv("LANG"))     && *l)) {
+    /* check standardized locales */
+    if (!strcmp(l, "C") || !strcmp(l, "POSIX"))
+      return C_CODESET;
+    /* check for encoding name fragment */
+    if (strstr(l, "UTF") || strstr(l, "utf"))
+      return "UTF-8";
+    if ((p = strstr(l, "8859-"))) {
+      memcpy(buf, "ISO-8859-\0\0", 12);
+      p += 5;
+      if (digit(*p)) {
+	buf[9] = *p++;
+	if (digit(*p)) buf[10] = *p++;
+	return buf;
+      }
+    }
+    if (strstr(l, "KOI8-R")) return "KOI8-R";
+    if (strstr(l, "KOI8-U")) return "KOI8-U";
+    if (strstr(l, "620")) return "TIS-620";
+    if (strstr(l, "2312")) return "GB2312";
+    if (strstr(l, "HKSCS")) return "Big5HKSCS";   /* no MIME charset */
+    if (strstr(l, "Big5") || strstr(l, "BIG5")) return "Big5";
+    if (strstr(l, "GBK")) return "GBK";           /* no MIME charset */
+    if (strstr(l, "18030")) return "GB18030";     /* no MIME charset */
+    if (strstr(l, "Shift_JIS") || strstr(l, "SJIS")) return "Shift_JIS";
+    /* check for conclusive modifier */
+    if (strstr(l, "euro")) return "ISO-8859-15";
+    /* check for language (and perhaps country) codes */
+    if (strstr(l, "zh_TW")) return "Big5";
+    if (strstr(l, "zh_HK")) return "Big5HKSCS";   /* no MIME charset */
+    if (strstr(l, "zh")) return "GB2312";
+    if (strstr(l, "ja")) return "EUC-JP";
+    if (strstr(l, "ko")) return "EUC-KR";
+    if (strstr(l, "ru")) return "KOI8-R";
+    if (strstr(l, "uk")) return "KOI8-U";
+    if (strstr(l, "pl") || strstr(l, "hr") ||
+	strstr(l, "hu") || strstr(l, "cs") ||
+	strstr(l, "sk") || strstr(l, "sl")) return "ISO-8859-2";
+    if (strstr(l, "eo") || strstr(l, "mt")) return "ISO-8859-3";
+    if (strstr(l, "el")) return "ISO-8859-7";
+    if (strstr(l, "he")) return "ISO-8859-8";
+    if (strstr(l, "tr")) return "ISO-8859-9";
+    if (strstr(l, "th")) return "TIS-620";      /* or ISO-8859-11 */
+    if (strstr(l, "lt")) return "ISO-8859-13";
+    if (strstr(l, "cy")) return "ISO-8859-14";
+    if (strstr(l, "ro")) return "ISO-8859-2";   /* or ISO-8859-16 */
+    if (strstr(l, "am") || strstr(l, "vi")) return "UTF-8";
+    /* Send me further rules if you like, but don't forget that we are
+     * *only* interested in locale naming conventions on platforms
+     * that do not already provide an nl_langinfo(CODESET) implementation. */
+    return "ISO-8859-1"; /* should perhaps be "UTF-8" instead */
+  }
+  return C_CODESET;
+}
+
+/* For a demo, compile with "gcc -W -Wall -o langinfo -D TEST langinfo.c" */
+
+#ifdef TEST
+#include <stdio.h>
+int main()
+{
+  printf("%s\n", nl_langinfo(CODESET));
+  return 0;
+}
+#endif
diff --git a/ucs/norm_charmap.c b/ucs/norm_charmap.c
new file mode 100644
index 00000000..30204871
--- /dev/null
+++ b/ucs/norm_charmap.c
@@ -0,0 +1,144 @@
+/*
+ * The Single Unix Specification function nl_langinfo(CODESET)
+ * returns the name of the encoding used by the currently selected
+ * locale:
+ *
+ *   http://www.opengroup.org/onlinepubs/7908799/xsh/langinfo.h.html
+ *
+ * Unfortunately the encoding names are not yet standardized.
+ * This function knows about the encoding names used on many
+ * different systems and converts them where possible into
+ * the corresponding MIME charset name registered in
+ *
+ *   http://www.iana.org/assignments/character-sets
+ *
+ * Please extend it as needed and suggest improvements to the author.
+ *
+ * Markus.Kuhn@cl.cam.ac.uk -- 2002-03-11
+ * Permission to use, copy, modify, and distribute this software
+ * for any purpose and without fee is hereby granted. The author
+ * disclaims all warranties with regard to this software.
+ *
+ * Latest version:
+ *
+ *   http://www.cl.cam.ac.uk/~mgk25/ucs/norm_charmap.c
+ */
+
+#include <string.h>
+
+#ifdef TEST
+#include <stdio.h>
+#include <locale.h>
+#include <langinfo.h>
+#endif
+
+#define digit(x) ((x) >= '0' && (x) <= '9')
+
+static char buf[16];
+
+char *norm_charmap(char *name)
+{
+  char *p;
+  
+  if (!name)
+    return name;
+  
+  /* Many need no remapping, but they are listed here so you
+   * can see what output to expect, and modify for your needs
+   * as necessary. */
+  if (!strcmp(name, "UTF-8"))
+    return "UTF-8";
+  if (!strcmp(name, "EUC-JP"))
+    return "EUC-JP";
+  if (!strcmp(name, "EUC-KR"))
+    return "EUC-KR";
+  if (!strcmp(name, "EUC-TW"))
+    return "EUC-TW";
+  if (!strcmp(name, "KOI8-R"))
+    return "KOI8-R";
+  if (!strcmp(name, "KOI8-U"))
+    return "KOI8-U";
+  if (!strcmp(name, "GBK"))
+    return "GBK";
+  if (!strcmp(name, "GB2312"))
+    return "GB2312";
+  if (!strcmp(name, "GB18030"))
+    return "GB18030";
+  if (!strcmp(name, "VSCII"))
+    return "VSCII";
+  
+  /* ASCII comes in many names */
+  if (!strcmp(name, "ASCII") ||
+      !strcmp(name, "US-ASCII") ||
+      !strcmp(name, "ANSI_X3.4-1968") ||
+      !strcmp(name, "646") ||
+      !strcmp(name, "ISO646") ||
+      !strcmp(name, "ISO_646.IRV"))
+    return "US-ASCII";
+
+  /* ISO 8859 will be converted to "ISO-8859-x" */
+  if ((p = strstr(name, "8859-"))) {
+    memcpy(buf, "ISO-8859-\0\0", 12);
+    p += 5;
+    if (digit(*p)) {
+      buf[9] = *p++;
+      if (digit(*p)) buf[10] = *p++;
+      return buf;
+    }
+  }
+
+  /* Windows code pages will be converted to "WINDOWS-12xx" */
+  if ((p = strstr(name, "CP12"))) {
+    memcpy(buf, "WINDOWS-12\0\0", 13);
+    p += 4;
+    if (digit(*p)) {
+      buf[10] = *p++;
+      if (digit(*p)) buf[11] = *p++;
+      return buf;
+    }
+  }
+
+  /* TIS-620 comes in at least the following two forms */
+  if (!strcmp(name, "TIS-620") ||
+      !strcmp(name, "TIS620.2533"))
+    return "ISO-8859-11";
+
+  /* For some, uppercase/lowercase might differ */
+  if (!strcmp(name, "Big5") || !strcmp(name, "BIG5"))
+    return "Big5";
+  if (!strcmp(name, "Big5HKSCS") || !strcmp(name, "BIG5HKSCS"))
+    return "Big5HKSCS";
+
+  /* I don't know of any implementation of nl_langinfo(CODESET) out
+   * there that returns anything else (and I'm not even certain all of
+   * the above occur in the wild), but just in case, as a fallback,
+   * return the unmodified name. */
+#ifdef TEST
+  printf("**** Unknown encoding name '%s'!\n", name);
+#endif
+  return name;
+}
+
+/* For a demo, compile with
+ *
+ *   gcc -W -Wall -o norm_charmap -D TEST norm_charmap.c
+ *
+ * and then test it on all available locales with
+ *
+ *   for i in `locale -a` ; do printf "$i: " ; LC_ALL=$i ./norm_charmap ; done
+ */
+
+#ifdef TEST
+int main(int argc, char **argv)
+{
+  char *s;
+  if (argc > 1)
+    s = argv[1];
+  else {
+    setlocale(LC_CTYPE, "");
+    s = nl_langinfo(CODESET);
+  }
+  printf("%s -> %s\n", s, norm_charmap(s));
+  return 0;
+}
+#endif