diff options
Diffstat (limited to 'utf8.c')
| -rw-r--r-- | utf8.c | 59 |
1 files changed, 57 insertions, 2 deletions
@@ -507,11 +507,66 @@ char *reencode_string(const char *in, const char *out_encoding, const char *in_e if (!in_encoding) return NULL; + conv = iconv_open(out_encoding, in_encoding); - if (conv == (iconv_t) -1) - return NULL; + if (conv == (iconv_t) -1) { + /* + * Some platforms do not have the variously spelled variants of + * UTF-8, so let's fall back to trying the most official + * spelling. We do so only as a fallback in case the platform + * does understand the user's spelling, but not our official + * one. + */ + if (is_encoding_utf8(in_encoding)) + in_encoding = "UTF-8"; + if (is_encoding_utf8(out_encoding)) + out_encoding = "UTF-8"; + conv = iconv_open(out_encoding, in_encoding); + if (conv == (iconv_t) -1) + return NULL; + } + out = reencode_string_iconv(in, strlen(in), conv); iconv_close(conv); return out; } #endif + +/* + * Returns first character length in bytes for multi-byte `text` according to + * `encoding`. + * + * - The `text` pointer is updated to point at the next character. + * - When `remainder_p` is not NULL, on entry `*remainder_p` is how much bytes + * we can consume from text, and on exit `*remainder_p` is reduced by returned + * character length. Otherwise `text` is treated as limited by NUL. + */ +int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding) +{ + int chrlen; + const char *p = *text; + size_t r = (remainder_p ? *remainder_p : SIZE_MAX); + + if (r < 1) + return 0; + + if (is_encoding_utf8(encoding)) { + pick_one_utf8_char(&p, &r); + + chrlen = p ? (p - *text) + : 1 /* not valid UTF-8 -> raw byte sequence */; + } + else { + /* + * TODO use iconv to decode one char and obtain its chrlen + * for now, let's treat encodings != UTF-8 as one-byte + */ + chrlen = 1; + } + + *text += chrlen; + if (remainder_p) + *remainder_p -= chrlen; + + return chrlen; +} |