X-Git-Url: http://git.madism.org/?p=apps%2Fmadmutt.git;a=blobdiff_plain;f=charset.c;h=bbaf8ca7a6ccb1bdc7b138774d2908ef610939cd;hp=19c3a2b5440c579ab0898a9f608803d29c0b1a7b;hb=2c56b665394c80195b976537e608b690947fcb14;hpb=6833ce8bdca2d64e14485118f2a4417b7e1cb1b1 diff --git a/charset.c b/charset.c index 19c3a2b..bbaf8ca 100644 --- a/charset.c +++ b/charset.c @@ -1,24 +1,15 @@ /* + * Copyright notice from original mutt: * Copyright (C) 1999-2000 Thomas Roessler * - * 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., 59 Temple Place - Suite 330, - * Boston, MA 02111, USA. + * This file is part of mutt-ng, see http://www.muttng.org/. + * It's licensed under the GNU General Public License, + * please see the file GPL in the top level source directory. */ +#if HAVE_CONFIG_H +# include "config.h" +#endif #include #include @@ -30,14 +21,25 @@ #include #include #include +#ifdef HAVE_LANGINFO_CODESET +# include +#endif + +#include +#include +#include +#include #include "mutt.h" #include "charset.h" #ifndef EILSEQ -# define EILSEQ EINVAL +# define EILSEQ EINVAL #endif +char *Charset; +int Charset_is_utf8 = 0; + /* * The following list has been created manually from the data under: * http://www.isi.edu/in-notes/iana/assignments/character-sets @@ -47,258 +49,184 @@ * a preferred MIME name is given. */ -static struct -{ - char *key; - char *pref; -} -PreferredMIMENames[] = -{ - { "ansi_x3.4-1968", "us-ascii" }, - { "iso-ir-6", "us-ascii" }, - { "iso_646.irv:1991", "us-ascii" }, - { "ascii", "us-ascii" }, - { "iso646-us", "us-ascii" }, - { "us", "us-ascii" }, - { "ibm367", "us-ascii" }, - { "cp367", "us-ascii" }, - { "csASCII", "us-ascii" }, - - { "csISO2022KR", "iso-2022-kr" }, - { "csEUCKR", "euc-kr" }, - { "csISO2022JP", "iso-2022-jp" }, - { "csISO2022JP2", "iso-2022-jp-2" }, - - { "ISO_8859-1:1987", "iso-8859-1" }, - { "iso-ir-100", "iso-8859-1" }, - { "iso_8859-1", "iso-8859-1" }, - { "latin1", "iso-8859-1" }, - { "l1", "iso-8859-1" }, - { "IBM819", "iso-8859-1" }, - { "CP819", "iso-8859-1" }, - { "csISOLatin1", "iso-8859-1" }, - - { "ISO_8859-2:1987", "iso-8859-2" }, - { "iso-ir-101", "iso-8859-2" }, - { "iso_8859-2", "iso-8859-2" }, - { "latin2", "iso-8859-2" }, - { "l2", "iso-8859-2" }, - { "csISOLatin2", "iso-8859-2" }, - - { "ISO_8859-3:1988", "iso-8859-3" }, - { "iso-ir-109", "iso-8859-3" }, - { "ISO_8859-3", "iso-8859-3" }, - { "latin3", "iso-8859-3" }, - { "l3", "iso-8859-3" }, - { "csISOLatin3", "iso-8859-3" }, - - { "ISO_8859-4:1988", "iso-8859-4" }, - { "iso-ir-110", "iso-8859-4" }, - { "ISO_8859-4", "iso-8859-4" }, - { "latin4", "iso-8859-4" }, - { "l4", "iso-8859-4" }, - { "csISOLatin4", "iso-8859-4" }, - - { "ISO_8859-6:1987", "iso-8859-6" }, - { "iso-ir-127", "iso-8859-6" }, - { "iso_8859-6", "iso-8859-6" }, - { "ECMA-114", "iso-8859-6" }, - { "ASMO-708", "iso-8859-6" }, - { "arabic", "iso-8859-6" }, - { "csISOLatinArabic", "iso-8859-6" }, - - { "ISO_8859-7:1987", "iso-8859-7" }, - { "iso-ir-126", "iso-8859-7" }, - { "ISO_8859-7", "iso-8859-7" }, - { "ELOT_928", "iso-8859-7" }, - { "ECMA-118", "iso-8859-7" }, - { "greek", "iso-8859-7" }, - { "greek8", "iso-8859-7" }, - { "csISOLatinGreek", "iso-8859-7" }, - - { "ISO_8859-8:1988", "iso-8859-8" }, - { "iso-ir-138", "iso-8859-8" }, - { "ISO_8859-8", "iso-8859-8" }, - { "hebrew", "iso-8859-8" }, - { "csISOLatinHebrew", "iso-8859-8" }, - - { "ISO_8859-5:1988", "iso-8859-5" }, - { "iso-ir-144", "iso-8859-5" }, - { "ISO_8859-5", "iso-8859-5" }, - { "cyrillic", "iso-8859-5" }, - { "csISOLatinCyrillic", "iso8859-5" }, - - { "ISO_8859-9:1989", "iso-8859-9" }, - { "iso-ir-148", "iso-8859-9" }, - { "ISO_8859-9", "iso-8859-9" }, - { "latin5", "iso-8859-9" }, /* this is not a bug */ - { "l5", "iso-8859-9" }, - { "csISOLatin5", "iso-8859-9" }, - - { "ISO_8859-10:1992", "iso-8859-10" }, - { "iso-ir-157", "iso-8859-10" }, - { "latin6", "iso-8859-10" }, /* this is not a bug */ - { "l6", "iso-8859-10" }, - { "csISOLatin6" "iso-8859-10" }, - - { "csKOI8r", "koi8-r" }, - - { "MS_Kanji", "Shift_JIS" }, /* Note the underscore! */ - { "csShiftJis", "Shift_JIS" }, - - { "Extended_UNIX_Code_Packed_Format_for_Japanese", - "EUC-JP" }, - { "csEUCPkdFmtJapanese", - "EUC-JP" }, - - { "csGB2312", "gb2312" }, - { "csbig5", "big5" }, - - /* - * End of official brain damage. What follows has been taken - * from glibc's localedata files. - */ - - { "iso_8859-13", "iso-8859-13" }, - { "iso-ir-179", "iso-8859-13" }, - { "latin7", "iso-8859-13" }, /* this is not a bug */ - { "l7", "iso-8859-13" }, - - { "iso_8859-14", "iso-8859-14" }, - { "latin8", "iso-8859-14" }, /* this is not a bug */ - { "l8", "iso-8859-14" }, - - { "iso_8859-15", "iso-8859-15" }, - { "latin9", "iso-8859-15" }, /* this is not a bug */ - - /* Suggested by Ionel Mugurel Ciobica */ - { "latin0", "iso-8859-15" }, /* this is not a bug */ - - { "iso_8859-16", "iso-8859-16" }, - { "latin10", "iso-8859-16" }, /* this is not a bug */ - - /* - * David Champion has observed this with - * nl_langinfo under SunOS 5.8. - */ - - { "646", "us-ascii" }, - - /* - * http://www.sun.com/software/white-papers/wp-unicode/ - */ - - { "eucJP", "euc-jp" }, - { "PCK", "Shift_JIS" }, - { "ko_KR-euc", "euc-kr" }, - { "zh_TW-big5", "big5" }, - - /* seems to be common on some systems */ - - { "sjis", "Shift_JIS" }, - - - /* - * If you happen to encounter system-specific brain-damage with - * respect to character set naming, please add it above this - * comment, and submit a patch to . - */ - - /* End of aliases. Please keep this line last. */ - - { NULL, NULL } +static struct { + const char *key; + const char *pref; +} PreferredMIMENames[] = { + {"ansi_x3.4-1968", "us-ascii"}, + {"iso-ir-6", "us-ascii"}, + {"iso_646.irv:1991", "us-ascii"}, + {"ascii", "us-ascii"}, + {"iso646-us", "us-ascii"}, + {"us", "us-ascii"}, + {"ibm367", "us-ascii"}, + {"cp367", "us-ascii"}, + {"csascii", "us-ascii"}, + {"csiso2022kr", "iso-2022-kr"}, + {"cseuckr", "euc-kr"}, + {"csiso2022jp", "iso-2022-jp"}, + {"csiso2022jp2", "iso-2022-jp-2"}, + {"iso_8859-1:1987", "iso-8859-1"}, + {"iso-ir-100", "iso-8859-1"}, + {"iso_8859-1", "iso-8859-1"}, + {"latin1", "iso-8859-1"}, + {"l1", "iso-8859-1"}, + {"ibm819", "iso-8859-1"}, + {"cp819", "iso-8859-1"}, + {"csisolatin1", "iso-8859-1"}, + {"iso_8859-2:1987", "iso-8859-2"}, + {"iso-ir-101", "iso-8859-2"}, + {"iso_8859-2", "iso-8859-2"}, + {"latin2", "iso-8859-2"}, + {"l2", "iso-8859-2"}, + {"csisolatin2", "iso-8859-2"}, + {"iso_8859-3:1988", "iso-8859-3"}, + {"iso-ir-109", "iso-8859-3"}, + {"iso_8859-3", "iso-8859-3"}, + {"latin3", "iso-8859-3"}, + {"l3", "iso-8859-3"}, + {"csisolatin3", "iso-8859-3"}, + {"iso_8859-4:1988", "iso-8859-4"}, + {"iso-ir-110", "iso-8859-4"}, + {"iso_8859-4", "iso-8859-4"}, + {"latin4", "iso-8859-4"}, + {"l4", "iso-8859-4"}, + {"csisolatin4", "iso-8859-4"}, + {"iso_8859-6:1987", "iso-8859-6"}, + {"iso-ir-127", "iso-8859-6"}, + {"iso_8859-6", "iso-8859-6"}, + {"ecma-114", "iso-8859-6"}, + {"asmo-708", "iso-8859-6"}, + {"arabic", "iso-8859-6"}, + {"csisolatinarabic", "iso-8859-6"}, + {"iso_8859-7:1987", "iso-8859-7"}, + {"iso-ir-126", "iso-8859-7"}, + {"iso_8859-7", "iso-8859-7"}, + {"elot_928", "iso-8859-7"}, + {"ecma-118", "iso-8859-7"}, + {"greek", "iso-8859-7"}, + {"greek8", "iso-8859-7"}, + {"csisolatingreek", "iso-8859-7"}, + {"iso_8859-8:1988", "iso-8859-8"}, + {"iso-ir-138", "iso-8859-8"}, + {"iso_8859-8", "iso-8859-8"}, + {"hebrew", "iso-8859-8"}, + {"csisolatinhebrew", "iso-8859-8"}, + {"iso_8859-5:1988", "iso-8859-5"}, + {"iso-ir-144", "iso-8859-5"}, + {"iso_8859-5", "iso-8859-5"}, + {"cyrillic", "iso-8859-5"}, + {"csisolatincyrillic", "iso8859-5"}, + {"iso_8859-9:1989", "iso-8859-9"}, + {"iso-ir-148", "iso-8859-9"}, + {"iso_8859-9", "iso-8859-9"}, + {"latin5", "iso-8859-9"}, + {"l5", "iso-8859-9"}, + {"csisolatin5", "iso-8859-9"}, + {"iso_8859-10:1992", "iso-8859-10"}, + {"iso-ir-157", "iso-8859-10"}, + {"latin6", "iso-8859-10"}, + {"l6", "iso-8859-10"}, + {"csisolatin6", "iso-8859-10"}, + {"cskoi8r", "koi8-r"}, + {"ms_kanji", "shift_jis"}, + {"csshiftjis", "shift_jis"}, + {"extended_unix_code_packed_format_for_japanese", "euc-jp"}, + {"cseucpkdfmtjapanese", "euc-jp"}, + {"csgb2312", "gb2312"}, + {"csbig5", "big5"}, + /* end of official brain damage. + what follows has been taken * from glibc's localedata files. */ + {"iso_8859-13", "iso-8859-13"}, + {"iso-ir-179", "iso-8859-13"}, + {"latin7", "iso-8859-13"}, + {"l7", "iso-8859-13"}, + {"iso_8859-14", "iso-8859-14"}, + {"latin8", "iso-8859-14"}, + {"l8", "iso-8859-14"}, + {"iso_8859-15", "iso-8859-15"}, + {"latin9", "iso-8859-15"}, + {"latin0", "iso-8859-15"}, + {"iso_8859-16", "iso-8859-16"}, + {"latin10", "iso-8859-16"}, + {"646", "us-ascii"}, + {"eucjp", "euc-jp"}, + {"pck", "shift_jis"}, + {"ko_kr-euc", "euc-kr"}, + {"zh_tw-big5", "big5"}, + {"sjis", "shift_jis"}, + {"euc-jp-ms", "eucjp-ms"}, + {NULL, NULL} }; -#ifdef HAVE_LANGINFO_CODESET -# include - - void mutt_set_langinfo_charset (void) { - char buff[LONG_STRING]; - char buff2[LONG_STRING]; - - strfcpy (buff, nl_langinfo (CODESET), sizeof (buff)); - mutt_canonical_charset (buff2, sizeof (buff2), buff); - - /* finally, set $charset */ - if (!(Charset = safe_strdup (buff2))) - Charset = safe_strdup ("iso-8859-1"); -} +#ifdef HAVE_LANGINFO_CODESET + char buff[LONG_STRING]; + char buff2[LONG_STRING]; -#else + m_strcpy(buff, sizeof(buff), nl_langinfo(CODESET)); + mutt_canonical_charset(buff2, sizeof(buff2), buff); -void mutt_set_langinfo_charset (void) -{ - Charset = safe_strdup ("iso-8859-1"); + /* finally, set $charset */ + if (!(Charset = m_strdup(buff2))) +#endif + Charset = m_strdup("iso-8859-1"); } -#endif -void mutt_canonical_charset (char *dest, size_t dlen, const char *name) +void mutt_canonical_charset(char *dest, ssize_t dlen, const char *name) { - size_t i; - char *p; - char scratch[LONG_STRING]; - - /* catch some common iso-8859-something misspellings */ - if (!ascii_strncasecmp (name, "8859", 4) && name[4] != '-') - snprintf (scratch, sizeof (scratch), "iso-8859-%s", name +4); - else if (!ascii_strncasecmp (name, "8859-", 5)) - snprintf (scratch, sizeof (scratch), "iso-8859-%s", name + 5); - else if (!ascii_strncasecmp (name, "iso8859", 7) && name[7] != '-') - snprintf (scratch, sizeof (scratch), "iso_8859-%s", name + 7); - else if (!ascii_strncasecmp (name, "iso8859-", 8)) - snprintf (scratch, sizeof (scratch), "iso_8859-%s", name + 8); - else - strfcpy (scratch, NONULL(name), sizeof (scratch)); - - for (i = 0; PreferredMIMENames[i].key; i++) - if (!ascii_strcasecmp (scratch, PreferredMIMENames[i].key) || - !mutt_strcasecmp (scratch, PreferredMIMENames[i].key)) - { - strfcpy (dest, PreferredMIMENames[i].pref, dlen); - return; + ssize_t i; + char *p; + char scratch[LONG_STRING]; + + m_strcpy(scratch, sizeof(scratch), name); + m_strtolower(scratch); + + /* catch some common iso-8859-something misspellings */ + if (!strncmp(scratch, "8859", 4)) { + snprintf(scratch, sizeof(scratch), "iso-8859-%s", + name + 4 + (name[4] == '-')); + m_strtolower(scratch); + } else + if (!strncmp(scratch, "iso8859", 7)) { + snprintf(scratch, sizeof(scratch), "iso-8859-%s", + name + 7 + (name[7] == '-')); + m_strtolower(scratch); } - strfcpy (dest, scratch, dlen); + for (i = 0; PreferredMIMENames[i].key; i++) { + if (!strcmp(scratch, PreferredMIMENames[i].key)) { + m_strcpy(dest, dlen, PreferredMIMENames[i].pref); + return; + } + } - /* for cosmetics' sake, transform to lowercase. */ - for (p = dest; *p; p++) - *p = ascii_tolower (*p); + m_strcpy(dest, dlen, scratch); } -int mutt_chscmp (const char *s, const char *chs) +static int mutt_chscmp(const char *s, const char *chs) { - char buffer[STRING]; + char buffer[STRING]; - if (!s) return 0; + if (!s) + return 0; - mutt_canonical_charset (buffer, sizeof (buffer), s); - return !ascii_strcasecmp (buffer, chs); -} - - -#ifndef HAVE_ICONV - -iconv_t iconv_open (const char *tocode, const char *fromcode) -{ - return (iconv_t)(-1); + mutt_canonical_charset(buffer, sizeof(buffer), s); + return !strcmp(buffer, chs); } -size_t iconv (iconv_t cd, ICONV_CONST char **inbuf, size_t *inbytesleft, - char **outbuf, size_t *outbytesleft) +int mutt_is_utf8(const char *s) { - return 0; + return mutt_chscmp(s, "utf-8"); } -int iconv_close (iconv_t cd) +int mutt_is_us_ascii(const char *s) { - return 0; + return mutt_chscmp(s, "us-ascii"); } -#endif /* !HAVE_ICONV */ - /* * Like iconv_open, but canonicalises the charsets @@ -312,7 +240,7 @@ iconv_t mutt_iconv_open (const char *tocode, const char *fromcode, int flags) char *tmp; iconv_t cd; - + mutt_canonical_charset (tocode1, sizeof (tocode1), tocode); #ifdef M_ICONV_HOOK_TO @@ -325,12 +253,13 @@ iconv_t mutt_iconv_open (const char *tocode, const char *fromcode, int flags) if ((flags & M_ICONV_HOOK_FROM) && (tmp = mutt_charset_hook (fromcode1))) mutt_canonical_charset (fromcode1, sizeof (fromcode1), tmp); - if ((cd = iconv_open (tocode1, fromcode1)) != (iconv_t) -1) + if ((cd = iconv_open (tocode1, fromcode1)) != (iconv_t) - 1) return cd; - if ((tocode2 = mutt_iconv_hook (tocode1)) && (fromcode2 = mutt_iconv_hook (fromcode1))) + if ((tocode2 = mutt_iconv_hook (tocode1)) + && (fromcode2 = mutt_iconv_hook (fromcode1))) return iconv_open (tocode2, fromcode2); - - return (iconv_t) -1; + + return (iconv_t) - 1; } @@ -340,57 +269,59 @@ iconv_t mutt_iconv_open (const char *tocode, const char *fromcode, int flags) * if you're supplying an outrepl, the target charset should be. */ -size_t mutt_iconv (iconv_t cd, ICONV_CONST char **inbuf, size_t *inbytesleft, - char **outbuf, size_t *outbytesleft, - ICONV_CONST char **inrepls, const char *outrepl) +ssize_t mutt_iconv(iconv_t cd, const char **inbuf, ssize_t *inbytesleft, + char **outbuf, ssize_t *outbytesleft, + const char **inrepls, const char *outrepl) { - size_t ret = 0, ret1; - ICONV_CONST char *ib = *inbuf; - size_t ibl = *inbytesleft; + ssize_t ret = 0, ret1; + const char *ib = *inbuf; + ssize_t ibl = *inbytesleft; char *ob = *outbuf; - size_t obl = *outbytesleft; + ssize_t obl = *outbytesleft; - for (;;) - { - ret1 = iconv (cd, &ib, &ibl, &ob, &obl); - if (ret1 != (size_t)-1) + for (;;) { + ret1 = my_iconv(cd, &ib, &ibl, &ob, &obl); + if (ret1 != -1) ret += ret1; - if (ibl && obl && errno == EILSEQ) - { - if (inrepls) - { - /* Try replacing the input */ - ICONV_CONST char **t; - for (t = inrepls; *t; t++) - { - ICONV_CONST char *ib1 = *t; - size_t ibl1 = strlen (*t); - char *ob1 = ob; - size_t obl1 = obl; - iconv (cd, &ib1, &ibl1, &ob1, &obl1); - if (!ibl1) - { - ++ib, --ibl; - ob = ob1, obl = obl1; - ++ret; - break; - } - } - if (*t) - continue; + if (ibl && obl && errno == EILSEQ) { + if (inrepls) { + /* Try replacing the input */ + const char **t; + + for (t = inrepls; *t; t++) { + const char *ib1 = *t; + ssize_t ibl1 = m_strlen(*t); + char *ob1 = ob; + ssize_t obl1 = obl; + + my_iconv(cd, &ib1, &ibl1, &ob1, &obl1); + if (!ibl1) { + ++ib, --ibl; + ob = ob1, obl = obl1; + ++ret; + break; + } + } + if (*t) + continue; } - if (outrepl) - { - /* Try replacing the output */ - int n = strlen (outrepl); - if (n <= obl) - { - memcpy (ob, outrepl, n); - ++ib, --ibl; - ob += n, obl -= n; - ++ret; - continue; - } + /* Replace the output */ + if (!outrepl) + outrepl = "?"; + my_iconv(cd, 0, 0, &ob, &obl); + if (obl) { + ssize_t n = m_strlen(outrepl); + + if (n > obl) { + outrepl = "?"; + n = 1; + } + memcpy (ob, outrepl, n); + ++ib, --ibl; + ob += n, obl -= n; + ++ret; + my_iconv(cd, 0, 0, 0, 0); /* for good measure */ + continue; } } *inbuf = ib, *inbytesleft = ibl; @@ -405,23 +336,23 @@ size_t mutt_iconv (iconv_t cd, ICONV_CONST char **inbuf, size_t *inbytesleft, * Used in rfc2047.c and rfc2231.c */ -int mutt_convert_string (char **ps, const char *from, const char *to, int flags) +int mutt_convert_string (char **ps, const char *from, const char *to, + int flags) { iconv_t cd; - ICONV_CONST char *repls[] = { "\357\277\275", "?", 0 }; + const char *repls[] = { "\357\277\275", "?", 0 }; char *s = *ps; if (!s || !*s) return 0; - if (to && from && (cd = mutt_iconv_open (to, from, flags)) != (iconv_t)-1) - { + if (to && from && (cd = mutt_iconv_open (to, from, flags)) != (iconv_t) - 1) { int len; - ICONV_CONST char *ib; + const char *ib; char *buf, *ob; - size_t ibl, obl; - ICONV_CONST char **inrepls = 0; - char *outrepl = 0; + ssize_t ibl, obl; + const char **inrepls = NULL; + const char *outrepl = NULL; if (mutt_is_utf8 (to)) outrepl = "\357\277\275"; @@ -429,21 +360,19 @@ int mutt_convert_string (char **ps, const char *from, const char *to, int flags) inrepls = repls; else outrepl = "?"; - - len = strlen (s); + + len = m_strlen(s); ib = s, ibl = len + 1; obl = MB_LEN_MAX * ibl; - ob = buf = safe_malloc (obl + 1); - + ob = buf = xmalloc(obl + 1); + mutt_iconv (cd, &ib, &ibl, &ob, &obl, inrepls, outrepl); iconv_close (cd); *ob = '\0'; - FREE (ps); + p_delete(ps); *ps = buf; - - mutt_str_adjust (ps); return 0; } else @@ -456,8 +385,7 @@ int mutt_convert_string (char **ps, const char *from, const char *to, int flags) * Used in sendlib.c for converting from mutt's Charset */ -struct fgetconv_s -{ +struct fgetconv_s { FILE *file; iconv_t cd; char bufi[512]; @@ -465,82 +393,80 @@ struct fgetconv_s char *p; char *ob; char *ib; - size_t ibl; - ICONV_CONST char **inrepls; + ssize_t ibl; + const char **inrepls; }; -struct fgetconv_not -{ +struct fgetconv_not { FILE *file; iconv_t cd; }; -FGETCONV *fgetconv_open (FILE *file, const char *from, const char *to, int flags) +FGETCONV *fgetconv_open (FILE * file, const char *from, const char *to, + int flags) { struct fgetconv_s *fc; - iconv_t cd = (iconv_t)-1; - static ICONV_CONST char *repls[] = { "\357\277\275", "?", 0 }; + iconv_t cd = (iconv_t) - 1; + static const char *repls[] = { "\357\277\275", "?", 0 }; if (from && to) cd = mutt_iconv_open (to, from, flags); - if (cd != (iconv_t)-1) - { - fc = safe_malloc (sizeof (struct fgetconv_s)); + if (cd != (iconv_t) - 1) { + fc = p_new(struct fgetconv_s, 1); fc->p = fc->ob = fc->bufo; fc->ib = fc->bufi; fc->ibl = 0; fc->inrepls = mutt_is_utf8 (to) ? repls : repls + 1; } else - fc = safe_malloc (sizeof (struct fgetconv_not)); + fc = p_new(struct fgetconv_s, 1); fc->file = file; fc->cd = cd; - return (FGETCONV *)fc; + return (FGETCONV *) fc; } -char *fgetconvs (char *buf, size_t l, FGETCONV *_fc) +char *fgetconvs (char *buf, ssize_t l, FGETCONV * _fc) { int c; - size_t r; - - for (r = 0; r + 1 < l;) - { + ssize_t r; + + for (r = 0; r + 1 < l;) { if ((c = fgetconv (_fc)) == EOF) break; buf[r++] = (char) c; - if (c == '\n') + if (c == '\n') break; } buf[r] = '\0'; - - if (r) + + if (r) return buf; - else + else return NULL; } -int fgetconv (FGETCONV *_fc) +int fgetconv (FGETCONV * _fc) { - struct fgetconv_s *fc = (struct fgetconv_s *)_fc; + struct fgetconv_s *fc = (struct fgetconv_s *) _fc; if (!fc) return EOF; - if (fc->cd == (iconv_t)-1) + if (fc->cd == (iconv_t) - 1) return fgetc (fc->file); if (!fc->p) return EOF; if (fc->p < fc->ob) - return (unsigned char)*(fc->p)++; + return (unsigned char) *(fc->p)++; /* Try to convert some more */ fc->p = fc->ob = fc->bufo; - if (fc->ibl) - { - size_t obl = sizeof (fc->bufo); - iconv (fc->cd, (ICONV_CONST char **)&fc->ib, &fc->ibl, &fc->ob, &obl); + if (fc->ibl) { + ssize_t obl = ssizeof(fc->bufo); + + my_iconv(fc->cd, (const char **) &fc->ib, &fc->ibl, &fc->ob, &obl); if (fc->p < fc->ob) - return (unsigned char)*(fc->p)++; + return (unsigned char) *(fc->p)++; } /* If we trusted iconv a bit more, we would at this point @@ -548,24 +474,24 @@ int fgetconv (FGETCONV *_fc) /* Try to read some more */ if (fc->ibl == sizeof (fc->bufi) || - (fc->ibl && fc->ib + fc->ibl < fc->bufi + sizeof (fc->bufi))) - { + (fc->ibl && fc->ib + fc->ibl < fc->bufi + sizeof (fc->bufi))) { fc->p = 0; return EOF; } if (fc->ibl) memcpy (fc->bufi, fc->ib, fc->ibl); fc->ib = fc->bufi; - fc->ibl += fread (fc->ib + fc->ibl, 1, sizeof (fc->bufi) - fc->ibl, fc->file); + fc->ibl += + fread (fc->ib + fc->ibl, 1, sizeof (fc->bufi) - fc->ibl, fc->file); /* Try harder this time to convert some */ - if (fc->ibl) - { - size_t obl = sizeof (fc->bufo); - mutt_iconv (fc->cd, (ICONV_CONST char **)&fc->ib, &fc->ibl, &fc->ob, &obl, - fc->inrepls, 0); + if (fc->ibl) { + ssize_t obl = ssizeof(fc->bufo); + + mutt_iconv (fc->cd, (const char **) &fc->ib, &fc->ibl, &fc->ob, + &obl, fc->inrepls, 0); if (fc->p < fc->ob) - return (unsigned char)*(fc->p)++; + return (unsigned char) *(fc->p)++; } /* Either the file has finished or one of the buffers is too small */ @@ -573,11 +499,107 @@ int fgetconv (FGETCONV *_fc) return EOF; } -void fgetconv_close (FGETCONV **_fc) +void fgetconv_close (FGETCONV ** _fc) { struct fgetconv_s *fc = (struct fgetconv_s *) *_fc; - if (fc->cd != (iconv_t)-1) + if (fc->cd != (iconv_t) - 1) iconv_close (fc->cd); - FREE (_fc); + p_delete(_fc); +} + +const char *mutt_get_first_charset (const char *charset) +{ + static char fcharset[SHORT_STRING]; + const char *c, *c1; + + c = charset; + if (!m_strlen(c)) + return "us-ascii"; + if (!(c1 = strchr (c, ':'))) + return ((char*) charset); + m_strcpy(fcharset, c1 - c + 1, c); + return fcharset; +} + +static ssize_t convert_string (const char *f, ssize_t flen, + const char *from, const char *to, + char **t, ssize_t * tlen) +{ + iconv_t cd; + char *buf, *ob; + ssize_t obl; + ssize_t n; + int e; + + cd = mutt_iconv_open (to, from, 0); + if (cd == (iconv_t) (-1)) + return -1; + obl = 4 * flen + 1; + ob = buf = xmalloc(obl); + n = my_iconv(cd, &f, &flen, &ob, &obl); + if (n < 0 || my_iconv(cd, 0, 0, &ob, &obl) < 0) { + e = errno; + p_delete(&buf); + iconv_close (cd); + errno = e; + return -1; + } + *ob = '\0'; + + *tlen = ob - buf; + + p_realloc(&buf, ob - buf + 1); + *t = buf; + iconv_close (cd); + + return n; +} + +int mutt_convert_nonmime_string (char **ps) +{ + const char *c, *c1; + + for (c = AssumedCharset; c; c = c1 ? c1 + 1 : 0) { + char *u = *ps; + char *s = NULL; + char *fromcode; + ssize_t m, n; + ssize_t ulen = m_strlen(*ps); + ssize_t slen; + + if (!u || !*u) + return 0; + + c1 = strchr (c, ':'); + n = c1 ? c1 - c : m_strlen(c); + if (!n) + continue; + fromcode = p_dupstr(c, n); + m = convert_string (u, ulen, fromcode, Charset, &s, &slen); + p_delete(&fromcode); + if (m != -1) { + p_delete(ps); + *ps = s; + return 0; + } + } + 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 : '?'; }