2005-09-15 09:58:31 -04:00
|
|
|
#ifndef EL__INTL_CHARSETS_H
|
|
|
|
#define EL__INTL_CHARSETS_H
|
|
|
|
|
|
|
|
typedef uint32_t unicode_val_T;
|
|
|
|
|
2006-08-19 06:29:37 -04:00
|
|
|
/* U+FFFD REPLACEMENT CHARACTER. Used when no Unicode mapping is
|
|
|
|
* known for a byte in a codepage, or when invalid UTF-8 is received
|
|
|
|
* from a terminal. After generating the character, ELinks then
|
|
|
|
* treats it like any other Unicode character. The user can also type
|
|
|
|
* this character directly, and it can occur in documents. */
|
|
|
|
#define UCS_REPLACEMENT_CHARACTER ((unicode_val_T) 0xFFFD)
|
|
|
|
|
|
|
|
/* A special value that fits in unicode_val_T but is outside the range
|
|
|
|
* of Unicode characters. utf_8_to_unicode and cp_to_unicode return
|
|
|
|
* this if the input is too short. This is also used as a placeholder
|
|
|
|
* for the second cell of a double-cell character. */
|
2006-07-31 15:23:47 -04:00
|
|
|
#define UCS_NO_CHAR ((unicode_val_T) 0xFFFFFFFD)
|
2005-09-15 09:58:31 -04:00
|
|
|
|
|
|
|
/* replacement character. See u2cp(). */
|
|
|
|
#define NBSP_CHAR ((unsigned char) 1)
|
|
|
|
#define NBSP_CHAR_STRING "\001"
|
|
|
|
|
|
|
|
struct conv_table {
|
|
|
|
int t;
|
|
|
|
union {
|
|
|
|
unsigned char *str;
|
|
|
|
struct conv_table *tbl;
|
|
|
|
} u;
|
|
|
|
};
|
|
|
|
|
|
|
|
enum convert_string_mode {
|
|
|
|
CSM_DEFAULT, /* Convert any char. */
|
|
|
|
CSM_QUERY, /* Special handling of '&' and '=' chars. */
|
|
|
|
CSM_FORM, /* Special handling of '&' and '=' chars in forms. */
|
|
|
|
CSM_NONE, /* Convert nothing. */
|
|
|
|
};
|
|
|
|
|
|
|
|
struct conv_table *get_translation_table(int, int);
|
|
|
|
unsigned char *get_entity_string(const unsigned char *str, const int strlen, int encoding);
|
|
|
|
|
|
|
|
/* The convert_string() name is also used by Samba (version 3.0.3), which
|
|
|
|
* provides libnss_wins.so.2, which is called somewhere inside
|
|
|
|
* _nss_wins_gethostbyname_r(). This name clash causes the elinks hostname
|
|
|
|
* lookup thread to crash so we need to rename the symbol. */
|
|
|
|
/* Reported by Derek Poon and filed as bug 453 */
|
|
|
|
#undef convert_string
|
|
|
|
#define convert_string convert_string_elinks
|
|
|
|
|
|
|
|
/* This routine converts a string from one charset to another according to the
|
|
|
|
* passed @convert_table, potentially also decoding SGML (HTML) entities along
|
|
|
|
* the way (according to @mode). It either returns dynamically allocated
|
|
|
|
* converted string of length @length, or if the @callback is non-NULL it calls
|
|
|
|
* it each few bytes instead and always returns NULL (@length is undefined).
|
|
|
|
* Note that it's ok not to care and pass NULL as @length. */
|
|
|
|
unsigned char *convert_string(struct conv_table *convert_table,
|
|
|
|
unsigned char *chars, int charslen, int cp,
|
|
|
|
enum convert_string_mode mode, int *length,
|
|
|
|
void (*callback)(void *data, unsigned char *buf, int buflen),
|
|
|
|
void *callback_data);
|
|
|
|
|
|
|
|
int get_cp_index(unsigned char *);
|
|
|
|
unsigned char *get_cp_name(int);
|
|
|
|
unsigned char *get_cp_mime_name(int);
|
2006-07-18 11:51:03 -04:00
|
|
|
int is_cp_utf8(int);
|
2005-09-15 09:58:31 -04:00
|
|
|
void free_conv_table(void);
|
2006-02-02 18:27:01 -05:00
|
|
|
#ifdef CONFIG_UTF_8
|
2006-01-14 16:44:00 -05:00
|
|
|
inline unsigned char *encode_utf_8(unicode_val_T);
|
2006-05-01 16:58:51 -04:00
|
|
|
inline unsigned char *utf8_prevchar(unsigned char *, int, unsigned char *);
|
2006-01-30 19:09:49 -05:00
|
|
|
inline int utf8charlen(const unsigned char *);
|
2006-03-04 18:10:33 -05:00
|
|
|
int utf8_char2cells(unsigned char *, unsigned char *);
|
|
|
|
int utf8_ptr2cells(unsigned char *, unsigned char *);
|
2006-04-07 16:06:17 -04:00
|
|
|
int utf8_ptr2chars(unsigned char *, unsigned char *);
|
2006-03-04 18:10:33 -05:00
|
|
|
int utf8_cells2bytes(unsigned char *, int, unsigned char *);
|
2006-02-07 19:42:39 -05:00
|
|
|
inline int unicode_to_cell(unicode_val_T);
|
2006-08-05 12:45:53 -04:00
|
|
|
unicode_val_T unicode_fold_label_case(unicode_val_T);
|
2006-01-14 16:44:00 -05:00
|
|
|
inline int strlen_utf8(unsigned char **);
|
|
|
|
inline unicode_val_T utf_8_to_unicode(unsigned char **, unsigned char *);
|
2006-08-13 16:35:50 -04:00
|
|
|
unicode_val_T cp_to_unicode(int, unsigned char **, unsigned char *);
|
2006-02-02 18:27:01 -05:00
|
|
|
#endif /* CONFIG_UTF_8 */
|
2006-01-14 16:44:00 -05:00
|
|
|
|
2006-08-12 09:04:21 -04:00
|
|
|
unicode_val_T cp2u(int, unsigned char);
|
2005-09-15 09:58:31 -04:00
|
|
|
unsigned char *cp2utf_8(int, int);
|
|
|
|
|
|
|
|
unsigned char *u2cp_(unicode_val_T, int, int no_nbsp_hack);
|
|
|
|
#define u2cp(u, to) u2cp_(u, to, 0)
|
|
|
|
#define u2cp_no_nbsp(u, to) u2cp_(u, to, 1)
|
|
|
|
|
|
|
|
void init_charsets_lookup(void);
|
|
|
|
void free_charsets_lookup(void);
|
|
|
|
|
2006-08-24 16:30:41 -04:00
|
|
|
/* UTF-16 encodes each Unicode character U+0000...U+FFFF as a single
|
|
|
|
* 16-bit code unit, and each character U+10000...U+10FFFF as a pair
|
|
|
|
* of two code units: a high surrogate followed by a low surrogate.
|
|
|
|
* The range U+D800...U+DFFF is reserved for these surrogates. */
|
|
|
|
#define is_utf16_surrogate(u) (((u) & 0xFFFFF800) == 0xD800)
|
|
|
|
#define is_utf16_high_surrogate(u) (((u) & 0xFFFFFC00) == 0xD800)
|
|
|
|
#define is_utf16_low_surrogate(u) (((u) & 0xFFFFFC00) == 0xDC00)
|
|
|
|
#define join_utf16_surrogates(high,low) (0x10000 + (((high) - 0xD800L) << 10) + ((low) - 0xDC00))
|
|
|
|
#define needs_utf16_surrogates(u) ((uint32_t) ((u) - 0x10000) < 0x100000)
|
|
|
|
#define get_utf16_high_surrogate(u) (0xD800 + (((u) - 0x10000) >> 10))
|
|
|
|
#define get_utf16_low_surrogate(u) (0xDC00 + ((u) & 0x3FF))
|
|
|
|
|
2005-09-15 09:58:31 -04:00
|
|
|
#endif
|