X-Git-Url: http://git.madism.org/?p=apps%2Fmadmutt.git;a=blobdiff_plain;f=charset.c;h=9a80d319366dacc7f3a3795063a9449366096760;hp=544b3573fa04cebdb0de5fb5b37ec8f5a42bc9c3;hb=fdb93a08e305b8755260144807e4d45106a9cb9f;hpb=2c3617ad2d8a2ad98b573cc34483d1cb7cd451f5 diff --git a/charset.c b/charset.c index 544b357..9a80d31 100644 --- a/charset.c +++ b/charset.c @@ -1,3 +1,21 @@ +/* + * 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 2 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 + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, + * MA 02110-1301, USA. + * + * Copyright © 2006 Pierre Habouzit + */ /* * Copyright notice from original mutt: * Copyright (C) 1999-2000 Thomas Roessler @@ -39,44 +57,57 @@ char *Charset; int Charset_is_utf8 = 0; +wchar_t CharsetReplacement = '?'; -void mutt_set_langinfo_charset(void) +void charset_initialize(void) { #ifdef HAVE_LANGINFO_CODESET char buff[LONG_STRING]; char buff2[LONG_STRING]; m_strcpy(buff, sizeof(buff), nl_langinfo(CODESET)); - mutt_canonical_charset(buff2, sizeof(buff2), buff); + charset_canonicalize(buff2, sizeof(buff2), buff); /* finally, set $charset */ - if (!(Charset = m_strdup(buff2))) + if (!m_strisempty(buff2)) { + m_strreplace(&Charset, buff2); + } else +#endif + { + m_strreplace(&Charset, "iso-8859-1"); + } + + Charset_is_utf8 = !strcmp(Charset, "utf-8"); + CharsetReplacement = Charset_is_utf8 ? 0xfffd : '?'; + +#ifdef HAVE_BIND_TEXTDOMAIN_CODESET + bind_textdomain_codeset(PACKAGE, Charset); #endif - Charset = m_strdup("iso-8859-1"); } #include "charset.gperf" - -void mutt_canonical_charset(char *dest, ssize_t dlen, const char *name) +void charset_canonicalize(char *dest, ssize_t dlen, const char *name) { const struct cset_pair *cp; char scratch[LONG_STRING]; - int i; + const char *p; + int i = 0; // canonize name: only keep a-z0-9 and dots, put into lowercase - for (i = 0; i < ssizeof(scratch); i++) { - if (isalnum(*name) || *name == '.') { - scratch[i++] = tolower((unsigned char)*name); - } - - if (!*name || *name == ':') { - scratch[i] = '\0'; - break; + for (p = name; *p && *p != ':' && i < ssizeof(scratch) - 1; p++) { + if (isalnum(*p) || *p== '.') { + scratch[i++] = tolower((unsigned char)*p); } } - - cp = mutt_canonical_charset_aux(scratch, strlen(scratch)); - m_strcpy(dest, dlen, cp ? cp->pref : name); + scratch[i] = '\0'; + + cp = charset_canonicalize_aux(scratch, strlen(scratch)); + if (cp) { + m_strcpy(dest, dlen, cp->pref); + } else { + m_strcpy(dest, dlen, name); + m_strtolower(dest); + } } static int mutt_chscmp(const char *s, const char *chs) @@ -86,16 +117,16 @@ static int mutt_chscmp(const char *s, const char *chs) if (!s) return 0; - mutt_canonical_charset(buffer, sizeof(buffer), s); + charset_canonicalize(buffer, sizeof(buffer), s); return !strcmp(buffer, chs); } -int mutt_is_utf8(const char *s) +int charset_is_utf8(const char *s) { return mutt_chscmp(s, "utf-8"); } -int mutt_is_us_ascii(const char *s) +int charset_is_us_ascii(const char *s) { return mutt_chscmp(s, "us-ascii"); } @@ -114,17 +145,17 @@ iconv_t mutt_iconv_open (const char *tocode, const char *fromcode, int flags) iconv_t cd; - mutt_canonical_charset (tocode1, sizeof (tocode1), tocode); + charset_canonicalize (tocode1, sizeof (tocode1), tocode); #ifdef M_ICONV_HOOK_TO /* Not used. */ if ((flags & M_ICONV_HOOK_TO) && (tmp = mutt_charset_hook (tocode1))) - mutt_canonical_charset (tocode1, sizeof (tocode1), tmp); + charset_canonicalize (tocode1, sizeof (tocode1), tmp); #endif - mutt_canonical_charset (fromcode1, sizeof (fromcode1), fromcode); + charset_canonicalize (fromcode1, sizeof (fromcode1), fromcode); if ((flags & M_ICONV_HOOK_FROM) && (tmp = mutt_charset_hook (fromcode1))) - mutt_canonical_charset (fromcode1, sizeof (fromcode1), tmp); + charset_canonicalize (fromcode1, sizeof (fromcode1), tmp); if ((cd = iconv_open (tocode1, fromcode1)) != (iconv_t) - 1) return cd; @@ -227,9 +258,9 @@ int mutt_convert_string (char **ps, const char *from, const char *to, const char **inrepls = NULL; const char *outrepl = NULL; - if (mutt_is_utf8 (to)) + if (charset_is_utf8 (to)) outrepl = "\357\277\275"; - else if (mutt_is_utf8 (from)) + else if (charset_is_utf8 (from)) inrepls = repls; else outrepl = "?"; @@ -290,7 +321,7 @@ FGETCONV *fgetconv_open (FILE * file, const char *from, const char *to, fc->p = fc->ob = fc->bufo; fc->ib = fc->bufi; fc->ibl = 0; - fc->inrepls = mutt_is_utf8 (to) ? repls : repls + 1; + fc->inrepls = charset_is_utf8 (to) ? repls : repls + 1; } else fc = p_new(struct fgetconv_s, 1); @@ -459,20 +490,3 @@ int mutt_convert_nonmime_string (char **ps) } return -1; } - -void mutt_set_charset (char *charset) -{ - char buffer[STRING]; - - mutt_canonical_charset (buffer, sizeof (buffer), charset); - Charset_is_utf8 = !strcmp(buffer, "utf-8"); - -#ifdef HAVE_BIND_TEXTDOMAIN_CODESET - bind_textdomain_codeset (PACKAGE, buffer); -#endif -} - -wchar_t replacement_char(void) -{ - return Charset_is_utf8 ? 0xfffd : '?'; -}