annotate src/lib/unichar.h @ 9603:5efba9f9f0a7 HEAD

Added a global utf8_replacement_char variable.
author Timo Sirainen <tss@iki.fi>
date Fri, 20 Aug 2010 20:37:31 +0100
parents cc7aa7a4dd6d
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
6410
e4eb71ae8e96 Changed .h ifdef/defines to use <NAME>_H format.
Timo Sirainen <tss@iki.fi>
parents: 6129
diff changeset
1 #ifndef UNICHAR_H
e4eb71ae8e96 Changed .h ifdef/defines to use <NAME>_H format.
Timo Sirainen <tss@iki.fi>
parents: 6129
diff changeset
2 #define UNICHAR_H
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
3
7185
6f014a866f38 Replace invalid UTF8 input with a replacement character.
Timo Sirainen <tss@iki.fi>
parents: 7042
diff changeset
4 /* Character used to replace invalid input. */
6f014a866f38 Replace invalid UTF8 input with a replacement character.
Timo Sirainen <tss@iki.fi>
parents: 7042
diff changeset
5 #define UNICODE_REPLACEMENT_CHAR 0xfffd
6f014a866f38 Replace invalid UTF8 input with a replacement character.
Timo Sirainen <tss@iki.fi>
parents: 7042
diff changeset
6
8378
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
7 /* Characters >= base require surrogates */
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
8 #define UTF16_SURROGATE_BASE 0x10000
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
9
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
10 #define UTF16_SURROGATE_SHIFT 10
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
11 #define UTF16_SURROGATE_MASK 0x03ff
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
12 #define UTF16_SURROGATE_HIGH_FIRST 0xd800
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
13 #define UTF16_SURROGATE_HIGH_LAST 0xdbff
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
14 #define UTF16_SURROGATE_HIGH_MAX 0xdfff
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
15 #define UTF16_SURROGATE_LOW_FIRST 0xdc00
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
16 #define UTF16_SURROGATE_LOW_LAST 0xdfff
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
17
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
18 #define UTF16_SURROGATE_HIGH(chr) \
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
19 (UTF16_SURROGATE_HIGH_FIRST + \
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
20 (((chr) - UTF16_SURROGATE_BASE) >> UTF16_SURROGATE_SHIFT))
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
21 #define UTF16_SURROGATE_LOW(chr) \
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
22 (UTF16_SURROGATE_LOW_FIRST + \
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
23 (((chr) - UTF16_SURROGATE_BASE) & UTF16_SURROGATE_MASK))
fcce76948c8a Added some UTF16_ macros for helping UTF-16 conversions.
Timo Sirainen <tss@iki.fi>
parents: 7912
diff changeset
24
9603
5efba9f9f0a7 Added a global utf8_replacement_char variable.
Timo Sirainen <tss@iki.fi>
parents: 9602
diff changeset
25 #define UTF8_REPLACEMENT_CHAR_LEN 3
5efba9f9f0a7 Added a global utf8_replacement_char variable.
Timo Sirainen <tss@iki.fi>
parents: 9602
diff changeset
26
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
27 typedef uint32_t unichar_t;
7042
dcbf6afdf931 Define unichars array type and use it for uni_utf8_to_ucs4() output.
Timo Sirainen <tss@iki.fi>
parents: 6952
diff changeset
28 ARRAY_DEFINE_TYPE(unichars, unichar_t);
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
29
9603
5efba9f9f0a7 Added a global utf8_replacement_char variable.
Timo Sirainen <tss@iki.fi>
parents: 9602
diff changeset
30 extern const unsigned char utf8_replacement_char[UTF8_REPLACEMENT_CHAR_LEN];
5683
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
31 extern const uint8_t *const uni_utf8_non1_bytes;
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
32
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
33 /* Returns number of characters in a NUL-terminated unicode string */
7912
81806d402514 Added more consts, ATTR_CONSTs and ATTR_PUREs.
Timo Sirainen <tss@iki.fi>
parents: 7185
diff changeset
34 unsigned int uni_strlen(const unichar_t *str) ATTR_PURE;
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
35 /* Translates UTF-8 input to UCS-4 output. Returns 0 if ok, -1 if input was
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
36 invalid */
7042
dcbf6afdf931 Define unichars array type and use it for uni_utf8_to_ucs4() output.
Timo Sirainen <tss@iki.fi>
parents: 6952
diff changeset
37 int uni_utf8_to_ucs4(const char *input, ARRAY_TYPE(unichars) *output);
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
38 /* Translates UCS-4 input to UTF-8 output. */
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
39 void uni_ucs4_to_utf8(const unichar_t *input, size_t len, buffer_t *output);
5683
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
40 void uni_ucs4_to_utf8_c(unichar_t chr, buffer_t *output);
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
41
5683
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
42 /* Returns 1 if *chr_r is set, 0 for incomplete trailing character,
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
43 -1 for invalid input. */
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
44 int uni_utf8_get_char(const char *input, unichar_t *chr_r);
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
45 int uni_utf8_get_char_n(const void *input, size_t max_len, unichar_t *chr_r);
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
46 /* Returns UTF-8 string length with maximum input size. */
7912
81806d402514 Added more consts, ATTR_CONSTs and ATTR_PUREs.
Timo Sirainen <tss@iki.fi>
parents: 7185
diff changeset
47 unsigned int uni_utf8_strlen_n(const void *input, size_t size) ATTR_PURE;
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
48
9602
cc7aa7a4dd6d UTF-8 string validity was still checked incorrectly.
Timo Sirainen <tss@iki.fi>
parents: 9476
diff changeset
49 /* Returns the number of bytes belonging to this UTF-8 character. The given
cc7aa7a4dd6d UTF-8 string validity was still checked incorrectly.
Timo Sirainen <tss@iki.fi>
parents: 9476
diff changeset
50 parameter is the first byte of the UTF-8 sequence. Invalid input is
cc7aa7a4dd6d UTF-8 string validity was still checked incorrectly.
Timo Sirainen <tss@iki.fi>
parents: 9476
diff changeset
51 returned with length 1. */
7912
81806d402514 Added more consts, ATTR_CONSTs and ATTR_PUREs.
Timo Sirainen <tss@iki.fi>
parents: 7185
diff changeset
52 static inline unsigned int ATTR_CONST
81806d402514 Added more consts, ATTR_CONSTs and ATTR_PUREs.
Timo Sirainen <tss@iki.fi>
parents: 7185
diff changeset
53 uni_utf8_char_bytes(char chr)
5683
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
54 {
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
55 /* 0x00 .. 0x7f are ASCII. 0x80 .. 0xC1 are invalid. */
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
56 if ((uint8_t)chr < (192 + 2))
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
57 return 1;
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
58 return uni_utf8_non1_bytes[(uint8_t)chr - (192 + 2)];
8101787cdd1c Rewrote some code and cleaned up the API
Timo Sirainen <tss@iki.fi>
parents: 4899
diff changeset
59 }
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
60
6129
04b9eb27283c Added uni_ucs4_to_titlecase() and uni_utf8_to_decomposed_titlecase(). They
Timo Sirainen <tss@iki.fi>
parents: 5683
diff changeset
61 /* Return given character in titlecase. */
7912
81806d402514 Added more consts, ATTR_CONSTs and ATTR_PUREs.
Timo Sirainen <tss@iki.fi>
parents: 7185
diff changeset
62 unichar_t uni_ucs4_to_titlecase(unichar_t chr) ATTR_CONST;
6129
04b9eb27283c Added uni_ucs4_to_titlecase() and uni_utf8_to_decomposed_titlecase(). They
Timo Sirainen <tss@iki.fi>
parents: 5683
diff changeset
63
04b9eb27283c Added uni_ucs4_to_titlecase() and uni_utf8_to_decomposed_titlecase(). They
Timo Sirainen <tss@iki.fi>
parents: 5683
diff changeset
64 /* Convert UTF-8 input to titlecase and decompose the titlecase characters to
04b9eb27283c Added uni_ucs4_to_titlecase() and uni_utf8_to_decomposed_titlecase(). They
Timo Sirainen <tss@iki.fi>
parents: 5683
diff changeset
65 output buffer. Returns 0 if ok, -1 if input was invalid. This generates
7185
6f014a866f38 Replace invalid UTF8 input with a replacement character.
Timo Sirainen <tss@iki.fi>
parents: 7042
diff changeset
66 output that's compatible with i;unicode-casemap comparator. Invalid input
6f014a866f38 Replace invalid UTF8 input with a replacement character.
Timo Sirainen <tss@iki.fi>
parents: 7042
diff changeset
67 is replaced with unicode replacement character (0xfffd). */
6129
04b9eb27283c Added uni_ucs4_to_titlecase() and uni_utf8_to_decomposed_titlecase(). They
Timo Sirainen <tss@iki.fi>
parents: 5683
diff changeset
68 int uni_utf8_to_decomposed_titlecase(const void *input, size_t max_len,
04b9eb27283c Added uni_ucs4_to_titlecase() and uni_utf8_to_decomposed_titlecase(). They
Timo Sirainen <tss@iki.fi>
parents: 5683
diff changeset
69 buffer_t *output);
04b9eb27283c Added uni_ucs4_to_titlecase() and uni_utf8_to_decomposed_titlecase(). They
Timo Sirainen <tss@iki.fi>
parents: 5683
diff changeset
70
7185
6f014a866f38 Replace invalid UTF8 input with a replacement character.
Timo Sirainen <tss@iki.fi>
parents: 7042
diff changeset
71 /* If input contains only valid UTF-8 characters, return TRUE without updating
6f014a866f38 Replace invalid UTF8 input with a replacement character.
Timo Sirainen <tss@iki.fi>
parents: 7042
diff changeset
72 buf. If input contains invalid UTF-8 characters, replace them with unicode
6f014a866f38 Replace invalid UTF8 input with a replacement character.
Timo Sirainen <tss@iki.fi>
parents: 7042
diff changeset
73 replacement character (0xfffd), write the output to buf and return FALSE. */
6952
08e4d7efcd6a uni_utf8_get_valid_data() API changed.
Timo Sirainen <tss@iki.fi>
parents: 6951
diff changeset
74 bool uni_utf8_get_valid_data(const unsigned char *input, size_t size,
08e4d7efcd6a uni_utf8_get_valid_data() API changed.
Timo Sirainen <tss@iki.fi>
parents: 6951
diff changeset
75 buffer_t *buf);
9476
bf2fb1679cb4 Added uni_utf8_str_is_valid().
Timo Sirainen <tss@iki.fi>
parents: 8378
diff changeset
76 /* Returns TRUE if string is valid UTF-8 input. */
bf2fb1679cb4 Added uni_utf8_str_is_valid().
Timo Sirainen <tss@iki.fi>
parents: 8378
diff changeset
77 bool uni_utf8_str_is_valid(const char *str);
6951
1f70c72e4312 Moved uni_utf8_get_valid_data() to lib/
Timo Sirainen <tss@iki.fi>
parents: 6410
diff changeset
78
4899
c98008a7e9b7 Added unichar_t UCS-4 type and some ucs4/utf8 functions.
Timo Sirainen <tss@iki.fi>
parents:
diff changeset
79 #endif