From: Ralph Corderoy Date: Tue, 16 May 2017 10:44:18 +0000 (+0100) Subject: Merge commit '3d0e5b6a4383a5228732edd6cb1532375b771262' X-Git-Url: https://diplodocus.org/git/nmh/commitdiff_plain/1d620f3af45733d0b7bcb30670287f89e8555d13?hp=684716b86dc07a97abbde4a8e2fa3a21b2b9c2d5 Merge commit '3d0e5b6a4383a5228732edd6cb1532375b771262' --- diff --git a/sbr/check_charset.c b/sbr/check_charset.c index b10cde34..e67b4e3d 100644 --- a/sbr/check_charset.c +++ b/sbr/check_charset.c @@ -1,6 +1,86 @@ -/* norm_charmap.c -- map locale's encoding to MIME charset. +/* check_charset.c -- routines for character sets * - * The Single Unix Specification function nl_langinfo(CODESET) + * This code is Copyright (c) 2002, by the authors of nmh. See the + * COPYRIGHT file in the root directory of the nmh distribution for + * complete copyright information. + */ + +#include + +#include +#include + +static char *norm_charmap(char *name); + +/* + * Get the current character set + */ +char * +get_charset(void) +{ + return norm_charmap(nl_langinfo (CODESET)); +} + + +/* + * Check if we can display a given character set natively. + * We are passed the length of the initial part of the + * string to check, since we want to allow the name of the + * character set to be a substring of a larger string. + */ + +int +check_charset (char *str, int len) +{ + static char *mm_charset = NULL; + static char *alt_charset = NULL; + static int mm_len; + static int alt_len; + + /* Cache the name of our default character set */ + if (!mm_charset) { + if (!(mm_charset = get_charset ())) + mm_charset = "US-ASCII"; + mm_len = strlen (mm_charset); + + /* US-ASCII is a subset of the ISO-8859-X and UTF-8 character sets */ + if (!strncasecmp("ISO-8859-", mm_charset, 9) || + !strcasecmp("UTF-8", mm_charset)) { + alt_charset = "US-ASCII"; + alt_len = strlen (alt_charset); + } + } + + /* Check if character set is OK */ + if ((len == mm_len) && !strncasecmp(str, mm_charset, mm_len)) + return 1; + if (alt_charset && (len == alt_len) && !strncasecmp(str, alt_charset, alt_len)) + return 1; + + return 0; +} + + +/* + * Return the name of the character set we are + * using for 8bit text. + */ +char * +write_charset_8bit (void) +{ + static char *mm_charset = NULL; + + /* + * Cache the name of the character set to + * use for 8bit text. + */ + if (!mm_charset && !(mm_charset = get_charset ())) + mm_charset = "x-unknown"; + + return mm_charset; +} + +/* The Single Unix Specification function nl_langinfo(CODESET) * returns the name of the encoding used by the currently selected * locale: * @@ -25,13 +105,11 @@ * http://www.cl.cam.ac.uk/~mgk25/ucs/norm_charmap.c */ -#include - #define digit(x) ((x) >= '0' && (x) <= '9') static char buf[16]; -char * +static char * norm_charmap(char *name) { char *p;