diff options
Diffstat (limited to 'src/mm-charsets.c')
| -rw-r--r-- | src/mm-charsets.c | 178 |
1 files changed, 176 insertions, 2 deletions
diff --git a/src/mm-charsets.c b/src/mm-charsets.c index 708dd3e1..0956e4e1 100644 --- a/src/mm-charsets.c +++ b/src/mm-charsets.c @@ -36,8 +36,8 @@ static CharsetEntry charset_map[] = { { "IRA", "ASCII", "ASCII", "ASCII//TRANSLIT", MM_MODEM_CHARSET_IRA }, { "GSM", NULL, NULL, NULL, MM_MODEM_CHARSET_GSM }, { "8859-1", NULL, "ISO8859-1", "ISO8859-1//TRANSLIT", MM_MODEM_CHARSET_8859_1 }, - { "PCCP437", NULL, NULL, NULL, MM_MODEM_CHARSET_PCCP437 }, - { "PCDN", NULL, NULL, NULL, MM_MODEM_CHARSET_PCDN }, + { "PCCP437", "CP437", "CP437", "CP437//TRANSLIT", MM_MODEM_CHARSET_PCCP437 }, + { "PCDN", "CP850", "CP850", "CP850//TRANSLIT", MM_MODEM_CHARSET_PCDN }, { "HEX", NULL, NULL, NULL, MM_MODEM_CHARSET_HEX }, { NULL, NULL, NULL, NULL, MM_MODEM_CHARSET_UNKNOWN } }; @@ -456,6 +456,180 @@ mm_charset_utf8_to_unpacked_gsm (const char *utf8, guint32 *out_len) return g_byte_array_free (gsm, FALSE); } +static gboolean +gsm_is_subset (gunichar c, const char *utf8, gsize ulen, guint *out_clen) +{ + guint8 gsm; + + *out_clen = 1; + if (utf8_to_gsm_def_char (utf8, ulen, &gsm)) + return TRUE; + if (utf8_to_gsm_ext_char (utf8, ulen, &gsm)) { + *out_clen = 2; + return TRUE; + } + return FALSE; +} + +static gboolean +ira_is_subset (gunichar c, const char *utf8, gsize ulen, guint *out_clen) +{ + *out_clen = 1; + return (ulen == 1); +} + +static gboolean +ucs2_is_subset (gunichar c, const char *utf8, gsize ulen, guint *out_clen) +{ + *out_clen = 2; + return (c <= 0xFFFF); +} + +static gboolean +iso88591_is_subset (gunichar c, const char *utf8, gsize ulen, guint *out_clen) +{ + *out_clen = 1; + return (c <= 0xFF); +} + +static gboolean +pccp437_is_subset (gunichar c, const char *utf8, gsize ulen, guint *out_clen) +{ + static const gunichar t[] = { + 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7, 0x00ea, + 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x00ec, 0x00c4, 0x00c5, 0x00c9, 0x00e6, + 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9, 0x00ff, 0x00d6, 0x00dc, + 0x00a2, 0x00a3, 0x00a5, 0x20a7, 0x0192, 0x00e1, 0x00ed, 0x00f3, 0x00fa, + 0x00f1, 0x00d1, 0x00aa, 0x00ba, 0x00bf, 0x2310, 0x00ac, 0x00bd, 0x00bc, + 0x00a1, 0x00ab, 0x00bb, 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, + 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, + 0x2510, 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, + 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, 0x2568, + 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, + 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, 0x03b1, 0x00df, 0x0393, + 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4, 0x03a6, 0x0398, 0x03a9, 0x03b4, + 0x221e, 0x03c6, 0x03b5, 0x2229, 0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, + 0x2321, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, + 0x25a0, 0x00a0 + }; + int i; + + *out_clen = 1; + + if (c <= 0x7F) + return TRUE; + for (i = 0; i < sizeof (t) / sizeof (t[0]); i++) { + if (c == t[i]) + return TRUE; + } + return FALSE; +} + +static gboolean +pcdn_is_subset (gunichar c, const char *utf8, gsize ulen, guint *out_clen) +{ + static const gunichar t[] = { + 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7, 0x00ea, + 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x00ec, 0x00c4, 0x00c5, 0x00c9, 0x00e6, + 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9, 0x00ff, 0x00d6, 0x00dc, + 0x00f8, 0x00a3, 0x00d8, 0x00d7, 0x0192, 0x00e1, 0x00ed, 0x00f3, 0x00fa, + 0x00f1, 0x00d1, 0x00aa, 0x00ba, 0x00bf, 0x00ae, 0x00ac, 0x00bd, 0x00bc, + 0x00a1, 0x00ab, 0x00bb, 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x00c1, + 0x00c2, 0x00c0, 0x00a9, 0x2563, 0x2551, 0x2557, 0x255d, 0x00a2, 0x00a5, + 0x2510, 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x00e3, 0x00c3, + 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x00a4, 0x00f0, + 0x00d0, 0x00ca, 0x00cb, 0x00c8, 0x0131, 0x00cd, 0x00ce, 0x00cf, 0x2518, + 0x250c, 0x2588, 0x2584, 0x00a6, 0x00cc, 0x2580, 0x00d3, 0x00df, 0x00d4, + 0x00d2, 0x00f5, 0x00d5, 0x00b5, 0x00fe, 0x00de, 0x00da, 0x00db, 0x00d9, + 0x00fd, 0x00dd, 0x00af, 0x00b4, 0x00ad, 0x00b1, 0x2017, 0x00be, 0x00b6, + 0x00a7, 0x00f7, 0x00b8, 0x00b0, 0x00a8, 0x00b7, 0x00b9, 0x00b3, 0x00b2, + 0x25a0, 0x00a0 + }; + int i; + + *out_clen = 1; + + if (c <= 0x7F) + return TRUE; + for (i = 0; i < sizeof (t) / sizeof (t[0]); i++) { + if (c == t[i]) + return TRUE; + } + return FALSE; +} + +typedef struct { + MMModemCharset cs; + gboolean (*func) (gunichar c, const char *utf8, gsize ulen, guint *out_clen); + guint charsize; +} SubsetEntry; + +SubsetEntry subset_table[] = { + { MM_MODEM_CHARSET_GSM, gsm_is_subset }, + { MM_MODEM_CHARSET_IRA, ira_is_subset }, + { MM_MODEM_CHARSET_UCS2, ucs2_is_subset }, + { MM_MODEM_CHARSET_8859_1, iso88591_is_subset }, + { MM_MODEM_CHARSET_PCCP437, pccp437_is_subset }, + { MM_MODEM_CHARSET_PCDN, pcdn_is_subset }, + { MM_MODEM_CHARSET_UNKNOWN, NULL }, +}; + +/** + * mm_charset_get_encoded_len: + * + * @utf8: UTF-8 valid string + * @charset: the #MMModemCharset to check the length of @utf8 in + * @out_unsupported: on return, number of characters of @utf8 that are not fully + * representable in @charset + * + * Returns: the size in bytes of the string if converted from UTF-8 into @charset. + **/ +guint +mm_charset_get_encoded_len (const char *utf8, + MMModemCharset charset, + guint *out_unsupported) +{ + const char *p = utf8, *next; + guint len = 0, unsupported = 0; + SubsetEntry *e; + + g_return_val_if_fail (charset != MM_MODEM_CHARSET_UNKNOWN, 0); + g_return_val_if_fail (utf8 != NULL, 0); + + if (charset == MM_MODEM_CHARSET_UTF8) + return strlen (utf8); + + /* Find the charset in our subset table */ + for (e = &subset_table[0]; + e->cs != charset && e->cs != MM_MODEM_CHARSET_UNKNOWN; + e++); + g_return_val_if_fail (e->cs != MM_MODEM_CHARSET_UNKNOWN, 0); + + while (*p) { + gunichar c; + const char *end; + guint clen = 0; + + c = g_utf8_get_char_validated (p, -1); + g_return_val_if_fail (c != (gunichar) -1, 0); + end = next = g_utf8_find_next_char (p, NULL); + if (end == NULL) { + /* Find the end... */ + end = p; + while (*end++); + } + + if (!e->func (c, p, (end - p), &clen)) + unsupported++; + len += clen; + p = next; + } + + if (out_unsupported) + *out_unsupported = unsupported; + return len; +} + guint8 * gsm_unpack (const guint8 *gsm, guint32 num_septets, |