New encoding C99.

Author: bhaible

ChangeLog

@@ -1,3 +1,10 @@
+2002-05-26  Bruno Haible  <bruno@clisp.org>
+
+	* lib/c99.h: New file.
+	* lib/converters.h: Include it.
+	* lib/encodings.def (C99): New encoding.
+	* README, man/iconv_open.3: Document C99 encoding.
+
 2002-05-26  Bruno Haible  <bruno@clisp.org>
 
 	* lib/java.h (java_mbtowc): Accept 12-byte sequences for non-BMP

NOTES

@@ -298,6 +298,9 @@ A: libiconv, as an internationalization library, supports those character
      * UTF-7
        We implement this because it is essential functionality for mail
        applications.
+     * C99
+       We implement it because it's used for C and C++ programs and because
+       it's a nice encoding for debugging.
      * JAVA
        We implement it because it's used for Java programs and because it's
        a nice encoding for debugging.

README

@@ -42,7 +42,7 @@ It provides support for the encodings:
         UTF-16, UTF-16BE, UTF-16LE
         UTF-32, UTF-32BE, UTF-32LE
         UTF-7
-        JAVA
+        C99, JAVA
     Full Unicode, in terms of `uint16_t' or `uint32_t'
         (with machine dependent endianness and alignment)
         UCS-2-INTERNAL, UCS-4-INTERNAL

lib/c99.h

@@ -0,0 +1,125 @@
+/*
+ * Copyright (C) 1999-2002 Free Software Foundation, Inc.
+ * This file is part of the GNU LIBICONV Library.
+ *
+ * The GNU LIBICONV Library is free software; you can redistribute it
+ * and/or modify it under the terms of the GNU Library General Public
+ * License as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * The GNU LIBICONV Library is distributed in the hope that it will be
+ * useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Library General Public License for more details.
+ *
+ * You should have received a copy of the GNU Library General Public
+ * License along with the GNU LIBICONV Library; see the file COPYING.LIB.
+ * If not, write to the Free Software Foundation, Inc., 59 Temple Place -
+ * Suite 330, Boston, MA 02111-1307, USA.
+ */
+
+/*
+ * C99
+ * This is ASCII with \uXXXX and \UXXXXXXXX escape sequences, denoting Unicode
+ * characters. See ISO/IEC 9899:1999, section 6.4.3.
+ * The treatment of control characters in the range U+0080..U+009F is not
+ * specified; we pass them through unmodified.
+ */
+
+static int
+c99_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, int n)
+{
+  unsigned char c;
+  ucs4_t wc;
+  int i;
+
+  c = s[0];
+  if (c < 0xa0) {
+    if (c != '\\') {
+      *pwc = c;
+      return 1;
+    }
+    if (n < 2)
+      return RET_TOOFEW(0);
+    c = s[1];
+    if (c == 'u') {
+      wc = 0;
+      for (i = 2; i < 6; i++) {
+        if (n <= i)
+          return RET_TOOFEW(0);
+        c = s[i];
+        if (c >= '0' && c <= '9')
+          c -= '0';
+        else if (c >= 'A' && c <= 'Z')
+          c -= 'A'-10;
+        else if (c >= 'a' && c <= 'z')
+          c -= 'a'-10;
+        else
+          goto simply_backslash;
+        wc |= (ucs4_t) c << (4 * (5-i));
+      }
+      if ((wc >= 0x00a0 && !(wc >= 0xd800 && wc < 0xe000))
+          || wc == 0x0024 || wc == 0x0040 || wc == 0x0060) {
+        *pwc = wc;
+        return 6;
+      }
+    } else if (c == 'U') {
+      wc = 0;
+      for (i = 2; i < 10; i++) {
+        if (n <= i)
+          return RET_TOOFEW(0);
+        c = s[i];
+        if (c >= '0' && c <= '9')
+          c -= '0';
+        else if (c >= 'A' && c <= 'Z')
+          c -= 'A'-10;
+        else if (c >= 'a' && c <= 'z')
+          c -= 'a'-10;
+        else
+          goto simply_backslash;
+        wc |= (ucs4_t) c << (4 * (9-i));
+      }
+      if ((wc >= 0x00a0 && !(wc >= 0xd800 && wc < 0xe000))
+          || wc == 0x0024 || wc == 0x0040 || wc == 0x0060) {
+        *pwc = wc;
+        return 10;
+      }
+    } else
+      goto simply_backslash;
+  }
+  return RET_ILSEQ;
+simply_backslash:
+  *pwc = '\\';
+  return 1;
+}
+
+static int
+c99_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, int n)
+{
+  if (wc < 0xa0) {
+    *r = wc;
+    return 1;
+  } else {
+    int result;
+    unsigned char u;
+    if (wc < 0x10000) {
+      result = 6;
+      u = 'u';
+    } else {
+      result = 10;
+      u = 'U';
+    }
+    if (n >= result) {
+      int count;
+      r[0] = '\\';
+      r[1] = u;
+      r += 2;
+      for (count = result-3; count >= 0; count--) {
+        unsigned int i = (wc >> (4*count)) & 0x0f;
+        *r++ = (i < 10 ? '0'+i : 'a'-10+i);
+      }
+      return result;
+    } else
+      return RET_TOOSMALL;
+  }
+}

lib/converters.h

@@ -125,6 +125,7 @@ struct conv_struct {
 #include "ucs2swapped.h"
 #include "ucs4internal.h"
 #include "ucs4swapped.h"
+#include "c99.h"
 #include "java.h"
 
 /* 8-bit encodings */

lib/encodings.def

@@ -155,6 +155,11 @@ DEFENCODING(( "UCS-4-SWAPPED",          /* libiconv */
             ucs4swapped,
             { ucs4swapped_mbtowc, NULL }, { ucs4swapped_wctomb, NULL })
 
+DEFENCODING(( "C99",
+            ),
+            c99,
+            { c99_mbtowc, NULL },         { c99_wctomb, NULL })
+
 DEFENCODING(( "JAVA",
             ),
             java,

man/iconv_open.3

@@ -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_OPEN 3  "May 12, 2002" "GNU" "Linux Programmer's Manual"
+.TH ICONV_OPEN 3  "May 26, 2002" "GNU" "Linux Programmer's Manual"
 .SH NAME
 iconv_open \- allocate descriptor for character set conversion
 .SH SYNOPSIS
@@ -114,7 +114,7 @@ UTF-32, UTF-32BE, UTF-32LE
 UTF-7
 .nf
 .fi
-JAVA
+C99, JAVA
 .TP
 Full Unicode, in terms of \fBuint16_t\fP or \fBuint32_t\fP
 (with machine dependent endianness and alignment)