X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Funicodeio.c;h=7665144edd3949c10625026a6d8698d5107511f8;hb=4cf71a8c15b38ca98e8b6aef03fe64dfbba51492;hp=8e0b2d8f1f1dc20c11953556e03d8ee4be6fe9b7;hpb=95ad3586497abbbd306a6b2177f5a528a81ed2be;p=gnulib.git diff --git a/lib/unicodeio.c b/lib/unicodeio.c index 8e0b2d8f1..7665144ed 100644 --- a/lib/unicodeio.c +++ b/lib/unicodeio.c @@ -1,121 +1,216 @@ /* Unicode character output to streams with locale dependent encoding. - Copyright (C) 2000 Free Software Foundation, Inc. + Copyright (C) 2000-2003, 2006, 2008-2011 Free Software Foundation, Inc. - This program 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, or (at your option) - any later version. + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 3 of the License, or + (at your option) any later version. This program 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. + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. - You should have received a copy of the GNU Library General Public - License along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, - USA. */ + You should have received a copy of the GNU General Public License + along with this program. If not, see . */ /* Written by Bruno Haible . */ -#ifdef HAVE_CONFIG_H -# include -#endif +#include -#if HAVE_STDDEF_H -# include -#endif +/* Specification. */ +#include "unicodeio.h" #include +#include +#include #if HAVE_ICONV # include -/* Name of UCS-4 encoding with machine dependent endianness and alignment. */ -# ifdef _LIBICONV_VERSION -# define UCS4_NAME "UCS-4-INTERNAL" -# else -# define UCS4_NAME "INTERNAL" -# endif #endif #include -#if ENABLE_NLS -# include -# define _(Text) gettext (Text) -#else -# define _(Text) Text -#endif - -#include "unicodeio.h" - -/* Use md5.h for its nice detection of unsigned 32-bit type. */ -#include "md5.h" -#undef uint32_t -#define uint32_t md5_uint32 - -/* Outputs the Unicode character CODE to the output stream STREAM. +#include "gettext.h" +#define _(msgid) gettext (msgid) +#define N_(msgid) msgid + +#include "localcharset.h" +#include "unistr.h" +#include "ignore-value.h" + +/* When we pass a Unicode character to iconv(), we must pass it in a + suitable encoding. The standardized Unicode encodings are + UTF-8, UCS-2, UCS-4, UTF-16, UTF-16BE, UTF-16LE, UTF-7. + UCS-2 supports only characters up to \U0000FFFF. + UTF-16 and variants support only characters up to \U0010FFFF. + UTF-7 is way too complex and not supported by glibc-2.1. + UCS-4 specification leaves doubts about endianness and byte order + mark. glibc currently interprets it as big endian without byte order + mark, but this is not backed by an RFC. + So we use UTF-8. It supports characters up to \U7FFFFFFF and is + unambiguously defined. */ + +/* Luckily, the encoding's name is platform independent. */ +#define UTF8_NAME "UTF-8" + +/* Converts the Unicode character CODE to its multibyte representation + in the current locale and calls the SUCCESS callback on the resulting + byte sequence. If an error occurs, invokes the FAILURE callback instead, + passing it CODE and an English error string. + Returns whatever the callback returned. Assumes that the locale doesn't change between two calls. */ -void -print_unicode_char (FILE *stream, unsigned int code) +long +unicode_to_mb (unsigned int code, + long (*success) (const char *buf, size_t buflen, + void *callback_arg), + long (*failure) (unsigned int code, const char *msg, + void *callback_arg), + void *callback_arg) { -#if HAVE_ICONV static int initialized; - static iconv_t ucs4_to_local; + static int is_utf8; +#if HAVE_ICONV + static iconv_t utf8_to_local; +#endif - uint32_t in; - char outbuf[25]; - const char *inptr; - size_t inbytesleft; - char *outptr; - size_t outbytesleft; - size_t res; + char inbuf[6]; + int count; if (!initialized) { - extern const char *locale_charset (void); const char *charset = locale_charset (); - ucs4_to_local = (charset != NULL - ? iconv_open (charset, UCS4_NAME) - : (iconv_t)(-1)); - if (ucs4_to_local == (iconv_t)(-1)) - { - /* For an unknown encoding, assume ASCII. */ - ucs4_to_local = iconv_open ("ASCII", UCS4_NAME); - if (ucs4_to_local == (iconv_t)(-1)) - error (1, 0, _("cannot output U+%04X: iconv function not usable"), - code); - } + is_utf8 = !strcmp (charset, UTF8_NAME); +#if HAVE_ICONV + if (!is_utf8) + { + utf8_to_local = iconv_open (charset, UTF8_NAME); + if (utf8_to_local == (iconv_t)(-1)) + /* For an unknown encoding, assume ASCII. */ + utf8_to_local = iconv_open ("ASCII", UTF8_NAME); + } +#endif initialized = 1; } - in = code; - inptr = (char *) ∈ - inbytesleft = sizeof (in); - outptr = outbuf; - outbytesleft = sizeof (outbuf); + /* Test whether the utf8_to_local converter is available at all. */ + if (!is_utf8) + { +#if HAVE_ICONV + if (utf8_to_local == (iconv_t)(-1)) + return failure (code, N_("iconv function not usable"), callback_arg); +#else + return failure (code, N_("iconv function not available"), callback_arg); +#endif + } + + /* Convert the character to UTF-8. */ + count = u8_uctomb ((unsigned char *) inbuf, code, sizeof (inbuf)); + if (count < 0) + return failure (code, N_("character out of range"), callback_arg); - /* Convert the character. */ - res = iconv (ucs4_to_local, &inptr, &inbytesleft, &outptr, &outbytesleft); - if (inbytesleft > 0 || res == (size_t)(-1)) - error (1, res == (size_t)(-1) ? errno : 0, - _("cannot convert U+%04X to local character set"), code); +#if HAVE_ICONV + if (!is_utf8) + { + char outbuf[25]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + inptr = inbuf; + inbytesleft = count; + outptr = outbuf; + outbytesleft = sizeof (outbuf); + + /* Convert the character from UTF-8 to the locale's charset. */ + res = iconv (utf8_to_local, + (ICONV_CONST char **)&inptr, &inbytesleft, + &outptr, &outbytesleft); + if (inbytesleft > 0 || res == (size_t)(-1) + /* Irix iconv() inserts a NUL byte if it cannot convert. */ +# if !defined _LIBICONV_VERSION && (defined sgi || defined __sgi) + || (res > 0 && code != 0 && outptr - outbuf == 1 && *outbuf == '\0') +# endif + ) + return failure (code, NULL, callback_arg); + + /* Avoid glibc-2.1 bug and Solaris 7 bug. */ +# if defined _LIBICONV_VERSION \ + || !(((__GLIBC__ - 0 == 2 && __GLIBC_MINOR__ - 0 <= 1) \ + && !defined __UCLIBC__) \ + || defined __sun) + + /* Get back to the initial shift state. */ + res = iconv (utf8_to_local, NULL, NULL, &outptr, &outbytesleft); + if (res == (size_t)(-1)) + return failure (code, NULL, callback_arg); +# endif - /* Avoid glibc-2.1 bug. */ -# if defined _LIBICONV_VERSION || !(__GLIBC__ - 0 == 2 && __GLIBC_MINOR__ - 0 <= 1) + return success (outbuf, outptr - outbuf, callback_arg); + } +#endif - /* Get back to the initial shift state. */ - res = iconv (ucs4_to_local, NULL, NULL, &outptr, &outbytesleft); - if (res == (size_t)(-1)) - error (1, errno, _("cannot convert U+%04X to local character set"), code); + /* At this point, is_utf8 is true, so no conversion is needed. */ + return success (inbuf, count, callback_arg); +} -# endif +/* Simple success callback that outputs the converted string. + The STREAM is passed as callback_arg. */ +long +fwrite_success_callback (const char *buf, size_t buflen, void *callback_arg) +{ + FILE *stream = (FILE *) callback_arg; + + /* The return value of fwrite can be ignored here, because under normal + conditions (STREAM is an open stream and not wide-character oriented) + when fwrite() returns a value != buflen it also sets STREAM's error + indicator. */ + ignore_value (fwrite (buf, 1, buflen, stream)); + return 0; +} - fwrite (outbuf, 1, outptr - outbuf, stream); +/* Simple failure callback that displays an error and exits. */ +static long +exit_failure_callback (unsigned int code, const char *msg, + void *callback_arg _GL_UNUSED) +{ + if (msg == NULL) + error (1, 0, _("cannot convert U+%04X to local character set"), code); + else + error (1, 0, _("cannot convert U+%04X to local character set: %s"), code, + gettext (msg)); + return -1; +} -#else - error (1, 0, _("cannot output U+%04X: iconv function not available"), code); -#endif +/* Simple failure callback that displays a fallback representation in plain + ASCII, using the same notation as ISO C99 strings. */ +static long +fallback_failure_callback (unsigned int code, + const char *msg _GL_UNUSED, + void *callback_arg) +{ + FILE *stream = (FILE *) callback_arg; + + if (code < 0x10000) + fprintf (stream, "\\u%04X", code); + else + fprintf (stream, "\\U%08X", code); + return -1; +} + +/* Outputs the Unicode character CODE to the output stream STREAM. + Upon failure, exit if exit_on_error is true, otherwise output a fallback + notation. */ +void +print_unicode_char (FILE *stream, unsigned int code, int exit_on_error) +{ + unicode_to_mb (code, fwrite_success_callback, + exit_on_error + ? exit_failure_callback + : fallback_failure_callback, + stream); }