summaryrefslogtreecommitdiff
path: root/include/ruby/encoding.h
blob: 2c247c99e9ea4a054367cfc54d77ae11870100e3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
/**********************************************************************

  encoding.h -

  $Author: matz $
  $Date: 2007-05-24 11:49:41 +0900 (Thu, 24 May 2007) $
  created at: Thu May 24 11:49:41 JST 2007

  Copyright (C) 2007 Yukihiro Matsumoto

**********************************************************************/

#ifndef RUBY_ENCODING_H
#define RUBY_ENCODING_H 1

#ifdef HAVE_STDARG_PROTOTYPES
# include <stdarg.h>
#else
# include <varargs.h>
#endif
#include "ruby/oniguruma.h"

#define ENCODING_INLINE_MAX 1023
#define ENCODING_SHIFT (FL_USHIFT+10)
#define ENCODING_MASK (ENCODING_INLINE_MAX<<ENCODING_SHIFT)
#define ENCODING_SET(obj,i) do {\
    RBASIC(obj)->flags &= ~ENCODING_MASK;\
    RBASIC(obj)->flags |= i << ENCODING_SHIFT;\
} while (0)
#define ENCODING_GET(obj) ((RBASIC(obj)->flags & ENCODING_MASK)>>ENCODING_SHIFT)

#define ENC_CODERANGE_MASK	(FL_USER8|FL_USER9)
#define ENC_CODERANGE_UNKNOWN	0
#define ENC_CODERANGE_7BIT	FL_USER8
#define ENC_CODERANGE_VALID	FL_USER9
#define ENC_CODERANGE_BROKEN	(FL_USER8|FL_USER9)
#define ENC_CODERANGE(obj) (RBASIC(obj)->flags & ENC_CODERANGE_MASK)
#define ENC_CODERANGE_ASCIIONLY(obj) (ENC_CODERANGE(obj) == ENC_CODERANGE_7BIT)
#define ENC_CODERANGE_SET(obj,cr) (RBASIC(obj)->flags = \
				   (RBASIC(obj)->flags & ~ENC_CODERANGE_MASK) | (cr))
#define ENC_CODERANGE_CLEAR(obj) ENC_CODERANGE_SET(obj,0)


typedef OnigEncodingType rb_encoding;

int rb_enc_replicate(const char *, rb_encoding *);
int rb_define_dummy_encoding(const char *);
int rb_enc_dummy_p(rb_encoding *);
int rb_enc_to_index(rb_encoding*);
int rb_enc_get_index(VALUE obj);
int rb_enc_find_index(const char *name);
int rb_to_encoding_index(VALUE);
rb_encoding* rb_to_encoding(VALUE);
rb_encoding* rb_enc_get(VALUE);
rb_encoding* rb_enc_compatible(VALUE,VALUE);
rb_encoding* rb_enc_check(VALUE,VALUE);
void rb_enc_associate_index(VALUE, int);
void rb_enc_associate(VALUE, rb_encoding*);
void rb_enc_copy(VALUE dst, VALUE src);

VALUE rb_enc_str_new(const char*, long, rb_encoding*);
VALUE rb_enc_reg_new(const char*, long, rb_encoding*, int);
PRINTF_ARGS(VALUE rb_enc_sprintf(rb_encoding *, const char*, ...), 2, 3);
VALUE rb_enc_vsprintf(rb_encoding *, const char*, va_list);
long rb_enc_strlen(const char*, const char*, rb_encoding*);
char* rb_enc_nth(const char*, const char*, int, rb_encoding*);
VALUE rb_obj_encoding(VALUE);

/* index -> rb_encoding */
rb_encoding* rb_enc_from_index(int idx);

/* name -> rb_encoding */
rb_encoding * rb_enc_find(const char *name);

/* encoding -> name */
#define rb_enc_name(enc) (enc)->name

/* encoding -> minlen/maxlen */
#define rb_enc_mbminlen(enc) (enc)->min_enc_len
#define rb_enc_mbmaxlen(enc) (enc)->max_enc_len

/* -> mbclen (no error notification: 0 < ret <= e-p, no exception) */
int rb_enc_mbclen(const char *p, const char *e, rb_encoding *enc);

/* -> chlen, invalid or needmore */
int rb_enc_precise_mbclen(const char *p, const char *e, rb_encoding *enc);
#define MBCLEN_CHARFOUND(ret)     ONIGENC_MBCLEN_CHARFOUND(ret)
#define MBCLEN_INVALID(ret)       ONIGENC_MBCLEN_INVALID(ret)
#define MBCLEN_NEEDMORE(ret)      ONIGENC_MBCLEN_NEEDMORE(ret)

/* -> 0x00..0x7f, -1 */
int rb_enc_ascget(const char *p, const char *e, int *len, rb_encoding *enc);

/* -> code or raise exception */
int rb_enc_codepoint(const char *p, const char *e, rb_encoding *enc);
#define rb_enc_mbc_to_codepoint(p, e, enc) ONIGENC_MBC_TO_CODE(enc,(UChar*)(p),(UChar*)(e))

/* -> codelen>0 or raise exception */
int rb_enc_codelen(int code, rb_encoding *enc);

/* code,ptr,encoding -> write buf */
#define rb_enc_mbcput(c,buf,enc) ONIGENC_CODE_TO_MBC(enc,c,(UChar*)(buf))

/* ptr, ptr, encoding -> prev_char */
#define rb_enc_prev_char(s,p,enc) (char *)onigenc_get_prev_char_head(enc,(UChar*)(s),(UChar*)(p))
/* ptr, ptr, encoding -> next_char */
#define rb_enc_left_char_head(s,p,enc) (char *)onigenc_get_left_adjust_char_head(enc,(UChar*)(s),(UChar*)(p))
#define rb_enc_right_char_head(s,p,enc) (char *)onigenc_get_right_adjust_char_head(enc,(UChar*)(s),(UChar*)(p))

#define rb_enc_isctype(c,t,enc) ONIGENC_IS_CODE_CTYPE(enc,c,t)
#define rb_enc_isascii(c,enc) ONIGENC_IS_CODE_ASCII(c)
#define rb_enc_isalpha(c,enc) ONIGENC_IS_CODE_ALPHA(enc,c)
#define rb_enc_islower(c,enc) ONIGENC_IS_CODE_LOWER(enc,c)
#define rb_enc_isupper(c,enc) ONIGENC_IS_CODE_UPPER(enc,c)
#define rb_enc_isalnum(c,enc) ONIGENC_IS_CODE_ALNUM(enc,c)
#define rb_enc_isprint(c,enc) ONIGENC_IS_CODE_PRINT(enc,c)
#define rb_enc_isspace(c,enc) ONIGENC_IS_CODE_SPACE(enc,c)
#define rb_enc_isdigit(c,enc) ONIGENC_IS_CODE_DIGIT(enc,c)

#define rb_enc_asciicompat(enc) (rb_enc_mbminlen(enc)==1)

int rb_enc_casefold(char *to, const char *p, const char *e, rb_encoding *enc);
int rb_enc_toupper(int c, rb_encoding *enc);
int rb_enc_tolower(int c, rb_encoding *enc);
ID rb_intern3(const char*, long, rb_encoding*);
ID rb_interned_id_p(const char *, long, rb_encoding *);
int rb_enc_symname_p(const char*, rb_encoding*);
int rb_enc_str_coderange(VALUE);
int rb_enc_str_asciionly_p(VALUE);
#define rb_enc_str_asciicompat_p(str) rb_enc_asciicompat(rb_enc_get(str))
VALUE rb_enc_from_encoding(rb_encoding *enc);
rb_encoding *rb_ascii8bit_encoding(void);
rb_encoding *rb_utf8_encoding(void);
rb_encoding *rb_locale_encoding(void);
rb_encoding *rb_default_external_encoding(void);
VALUE rb_enc_default_external(void);
void rb_enc_set_default_external(VALUE encoding);
VALUE rb_locale_charmap(VALUE klass);

#endif /* RUBY_ENCODING_H */