diff options
Diffstat (limited to 'utf8.c')
| -rw-r--r-- | utf8.c | 62 |
1 files changed, 49 insertions, 13 deletions
@@ -4,6 +4,11 @@ /* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */ +static const char utf16_be_bom[] = {'\xFE', '\xFF'}; +static const char utf16_le_bom[] = {'\xFF', '\xFE'}; +static const char utf32_be_bom[] = {'\0', '\0', '\xFE', '\xFF'}; +static const char utf32_le_bom[] = {'\xFF', '\xFE', '\0', '\0'}; + struct interval { ucs_char_t first; ucs_char_t last; @@ -470,16 +475,17 @@ int utf8_fprintf(FILE *stream, const char *format, ...) #else typedef char * iconv_ibp; #endif -char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outsz_p) +char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, + size_t bom_len, size_t *outsz_p) { size_t outsz, outalloc; char *out, *outpos; iconv_ibp cp; outsz = insz; - outalloc = outsz + 1; /* for terminating NUL */ + outalloc = st_add(outsz, 1 + bom_len); /* for terminating NUL */ out = xmalloc(outalloc); - outpos = out; + outpos = out + bom_len; cp = (iconv_ibp)in; while (1) { @@ -497,7 +503,7 @@ char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outs * converting the rest. */ sofar = outpos - out; - outalloc = sofar + insz * 2 + 32; + outalloc = st_add3(sofar, st_mult(insz, 2), 32); out = xrealloc(out, outalloc); outpos = out + sofar; outsz = outalloc - sofar - 1; @@ -534,16 +540,50 @@ static const char *fallback_encoding(const char *name) return name; } -char *reencode_string_len(const char *in, int insz, +char *reencode_string_len(const char *in, size_t insz, const char *out_encoding, const char *in_encoding, - int *outsz) + size_t *outsz) { iconv_t conv; char *out; + const char *bom_str = NULL; + size_t bom_len = 0; if (!in_encoding) return NULL; + /* UTF-16LE-BOM is the same as UTF-16 for reading */ + if (same_utf_encoding("UTF-16LE-BOM", in_encoding)) + in_encoding = "UTF-16"; + + /* + * For writing, UTF-16 iconv typically creates "UTF-16BE-BOM" + * Some users under Windows want the little endian version + * + * We handle UTF-16 and UTF-32 ourselves only if the platform does not + * provide a BOM (which we require), since we want to match the behavior + * of the system tools and libc as much as possible. + */ + if (same_utf_encoding("UTF-16LE-BOM", out_encoding)) { + bom_str = utf16_le_bom; + bom_len = sizeof(utf16_le_bom); + out_encoding = "UTF-16LE"; + } else if (same_utf_encoding("UTF-16BE-BOM", out_encoding)) { + bom_str = utf16_be_bom; + bom_len = sizeof(utf16_be_bom); + out_encoding = "UTF-16BE"; +#ifdef ICONV_OMITS_BOM + } else if (same_utf_encoding("UTF-16", out_encoding)) { + bom_str = utf16_be_bom; + bom_len = sizeof(utf16_be_bom); + out_encoding = "UTF-16BE"; + } else if (same_utf_encoding("UTF-32", out_encoding)) { + bom_str = utf32_be_bom; + bom_len = sizeof(utf32_be_bom); + out_encoding = "UTF-32BE"; +#endif + } + conv = iconv_open(out_encoding, in_encoding); if (conv == (iconv_t) -1) { in_encoding = fallback_encoding(in_encoding); @@ -553,9 +593,10 @@ char *reencode_string_len(const char *in, int insz, if (conv == (iconv_t) -1) return NULL; } - - out = reencode_string_iconv(in, insz, conv, outsz); + out = reencode_string_iconv(in, insz, conv, bom_len, outsz); iconv_close(conv); + if (out && bom_str && bom_len) + memcpy(out, bom_str, bom_len); return out; } #endif @@ -566,11 +607,6 @@ static int has_bom_prefix(const char *data, size_t len, return data && bom && (len >= bom_len) && !memcmp(data, bom, bom_len); } -static const char utf16_be_bom[] = {0xFE, 0xFF}; -static const char utf16_le_bom[] = {0xFF, 0xFE}; -static const char utf32_be_bom[] = {0x00, 0x00, 0xFE, 0xFF}; -static const char utf32_le_bom[] = {0xFF, 0xFE, 0x00, 0x00}; - int has_prohibited_utf_bom(const char *enc, const char *data, size_t len) { return ( |