summaryrefslogtreecommitdiff
path: root/utf8.h
blob: c69cd86bfb97895cb14744730a1f092046b4bd15 (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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
/*    utf8.h
 *
 *    Copyright (c) 1998-2002, Larry Wall
 *
 *    You may distribute under the terms of either the GNU General Public
 *    License or the Artistic License, as specified in the README file.
 *
 */

/* Use UTF-8 as the default script encoding?
 * Turning this on will break scripts having non-UTF8 binary
 * data (such as Latin-1) in string literals. */
#ifdef USE_UTF8_SCRIPTS
#    define USE_UTF8_IN_NAMES (!IN_BYTES)
#else
#    define USE_UTF8_IN_NAMES (PL_hints & HINT_UTF8)
#endif

#ifdef EBCDIC
/* The equivalent of these macros but implementing UTF-EBCDIC
   are in the following header file:
 */

#include "utfebcdic.h"
#else
START_EXTERN_C

#ifdef DOINIT
EXTCONST unsigned char PL_utf8skip[] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* ascii */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* bogus */
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* scripts */
3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,	 /* cjk etc. */
7,13, /* Perl extended (not UTF-8).  Up to 72bit allowed (64-bit + reserved). */
};
#else
EXTCONST unsigned char PL_utf8skip[];
#endif

END_EXTERN_C
#define UTF8SKIP(s) PL_utf8skip[*(U8*)s]

/* Native character to iso-8859-1 */
#define NATIVE_TO_ASCII(ch)      (ch)
#define ASCII_TO_NATIVE(ch)      (ch)
/* Transform after encoding */
#define NATIVE_TO_UTF(ch)        (ch)
#define UTF_TO_NATIVE(ch)        (ch)
/* Transforms in wide UV chars */
#define UNI_TO_NATIVE(ch)        (ch)
#define NATIVE_TO_UNI(ch)        (ch)
/* Transforms in invariant space */
#define NATIVE_TO_NEED(enc,ch)   (ch)
#define ASCII_TO_NEED(enc,ch)    (ch)

/* As there are no translations avoid the function wrapper */
#define Perl_utf8n_to_uvchr Perl_utf8n_to_uvuni
#define Perl_uvchr_to_utf8  Perl_uvuni_to_utf8

/*

 The following table is from Unicode 3.1.

 Code Points		1st Byte  2nd Byte  3rd Byte  4th Byte

   U+0000..U+007F	00..7F   
   U+0080..U+07FF	C2..DF    80..BF   
   U+0800..U+0FFF	E0        A0..BF    80..BF  
   U+1000..U+FFFF	E1..EF    80..BF    80..BF  
  U+10000..U+3FFFF	F0        90..BF    80..BF    80..BF
  U+40000..U+FFFFF	F1..F3    80..BF    80..BF    80..BF
 U+100000..U+10FFFF	F4        80..8F    80..BF    80..BF

 */

#define UNI_IS_INVARIANT(c)		(((UV)c) <  0x80)
#define UTF8_IS_INVARIANT(c)		UNI_IS_INVARIANT(NATIVE_TO_UTF(c))
#define NATIVE_IS_INVARIANT(c)		UNI_IS_INVARIANT(NATIVE_TO_ASCII(c))
#define UTF8_IS_START(c)		(((U8)c) >= 0xc0 && (((U8)c) <= 0xfd))
#define UTF8_IS_CONTINUATION(c)		(((U8)c) >= 0x80 && (((U8)c) <= 0xbf))
#define UTF8_IS_CONTINUED(c) 		(((U8)c) &  0x80)
#define UTF8_IS_DOWNGRADEABLE_START(c)	(((U8)c & 0xfc) == 0xc0)

#define UTF_START_MARK(len) ((len >  7) ? 0xFF : (0xFE << (7-len)))
#define UTF_START_MASK(len) ((len >= 7) ? 0x00 : (0x1F >> (len-2)))

#define UTF_CONTINUATION_MARK		0x80
#define UTF_ACCUMULATION_SHIFT		6
#define UTF_CONTINUATION_MASK		((U8)0x3f)
#define UTF8_ACCUMULATE(old, new)	(((old) << UTF_ACCUMULATION_SHIFT) | (((U8)new) & UTF_CONTINUATION_MASK))

#define UTF8_EIGHT_BIT_HI(c)	((((U8)(c))>>UTF_ACCUMULATION_SHIFT)|UTF_START_MARK(2))
#define UTF8_EIGHT_BIT_LO(c)	(((((U8)(c)))&UTF_CONTINUATION_MASK)|UTF_CONTINUATION_MARK)

#ifdef HAS_QUAD
#define UNISKIP(uv) ( (uv) < 0x80           ? 1 : \
		      (uv) < 0x800          ? 2 : \
		      (uv) < 0x10000        ? 3 : \
		      (uv) < 0x200000       ? 4 : \
		      (uv) < 0x4000000      ? 5 : \
		      (uv) < 0x80000000     ? 6 : \
                      (uv) < UTF8_QUAD_MAX ? 7 : 13 )
#else
/* No, I'm not even going to *TRY* putting #ifdef inside a #define */
#define UNISKIP(uv) ( (uv) < 0x80           ? 1 : \
		      (uv) < 0x800          ? 2 : \
		      (uv) < 0x10000        ? 3 : \
		      (uv) < 0x200000       ? 4 : \
		      (uv) < 0x4000000      ? 5 : \
		      (uv) < 0x80000000     ? 6 : 7 )
#endif

/*
 * Note: we try to be careful never to call the isXXX_utf8() functions
 * unless we're pretty sure we've seen the beginning of a UTF-8 character
 * (that is, the two high bits are set).  Otherwise we risk loading in the
 * heavy-duty SWASHINIT and SWASHGET routines unnecessarily.
 */
#define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || (*((U8*)p) < 0xc0))) \
				? isIDFIRST(*(p)) \
				: isIDFIRST_utf8((U8*)p))
#define isALNUM_lazy_if(p,c)   ((IN_BYTES || (!c || (*((U8*)p) < 0xc0))) \
				? isALNUM(*(p)) \
				: isALNUM_utf8((U8*)p))


#endif /* EBCDIC vs ASCII */

/* Rest of these are attributes of Unicode and perl's internals rather than the encoding */

#define isIDFIRST_lazy(p)	isIDFIRST_lazy_if(p,1)
#define isALNUM_lazy(p)		isALNUM_lazy_if(p,1)

/* how wide can a single UTF8 encoded character become */
#define UTF8_MAXLEN 13
/* how wide a character can become when upper/lowercased */
#define UTF8_MAXLEN_UCLC (UTF8_MAXLEN*2)
/* how wide a character can become when casefolded */
#define UTF8_MAXLEN_FOLD (UTF8_MAXLEN*3)

#define IN_BYTES (PL_curcop->op_private & HINT_BYTES)
#define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES)

#define UTF8_ALLOW_EMPTY		0x0001
#define UTF8_ALLOW_CONTINUATION		0x0002
#define UTF8_ALLOW_NON_CONTINUATION	0x0004
#define UTF8_ALLOW_FE_FF		0x0008
#define UTF8_ALLOW_SHORT		0x0010
#define UTF8_ALLOW_SURROGATE		0x0020
#define UTF8_ALLOW_BOM			0x0040
#define UTF8_ALLOW_FFFF			0x0080
#define UTF8_ALLOW_LONG			0x0100
#define UTF8_ALLOW_ANYUV		(UTF8_ALLOW_EMPTY|UTF8_ALLOW_FE_FF|\
					 UTF8_ALLOW_SURROGATE|UTF8_ALLOW_BOM|\
					 UTF8_ALLOW_FFFF|UTF8_ALLOW_LONG)
#define UTF8_ALLOW_ANY			0x00ff
#define UTF8_CHECK_ONLY			0x0200

#define UNICODE_SURROGATE_FIRST		0xd800
#define UNICODE_SURROGATE_LAST		0xdfff
#define UNICODE_REPLACEMENT		0xfffd
#define UNICODE_BYTER_ORDER_MARK	0xfffe
#define UNICODE_ILLEGAL			0xffff

/* Though our UTF-8 encoding can go beyond this,
 * let's be conservative. */
#define PERL_UNICODE_MAX	0x10FFFF

#define UNICODE_ALLOW_SURROGATE 0x0001	/* Allow UTF-16 surrogates (EVIL) */
#define UNICODE_ALLOW_FDD0	0x0002	/* Allow the U+FDD0...U+FDEF */
#define UNICODE_ALLOW_FFFE	0x0004	/* Allow 0xFFFE, 0x1FFFE, ... */
#define UNICODE_ALLOW_FFFF	0x0008	/* Allow 0xFFFE, 0x1FFFE, ... */
#define UNICODE_ALLOW_SUPER	0x0010	/* Allow past 10xFFFF */
#define UNICODE_ALLOW_ANY	0xFFFF

#define UNICODE_IS_SURROGATE(c)		((c) >= UNICODE_SURROGATE_FIRST && \
					 (c) <= UNICODE_SURROGATE_LAST)
#define UNICODE_IS_REPLACEMENT(c)	((c) == UNICODE_REPLACEMENT)
#define UNICODE_IS_BYTE_ORDER_MARK(c)	((c) == UNICODE_BYTER_ORDER_MARK)
#define UNICODE_IS_ILLEGAL(c)		((c) == UNICODE_ILLEGAL)

#ifdef HAS_QUAD
#    define UTF8_QUAD_MAX	UINT64_C(0x1000000000)
#endif

#define UTF8_IS_ASCII(c) UTF8_IS_INVARIANT(c)

#define UNICODE_LATIN_SMALL_LETTER_SHARP_S	0x00DF
#define UNICODE_GREEK_CAPITAL_LETTER_SIGMA	0x03A3
#define UNICODE_GREEK_SMALL_LETTER_FINAL_SIGMA	0x03C2
#define UNICODE_GREEK_SMALL_LETTER_SIGMA	0x03C3

#define UNI_DISPLAY_ISPRINT	0x0001
#define UNI_DISPLAY_BACKSLASH	0x0002
#define UNI_DISPLAY_QQ		(UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH)
#define UNI_DISPLAY_REGEX	(UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH)

#define ANYOF_UNICODE_FOLD_SHARP_S(node, input, end)	\
	(ANYOF_BITMAP_TEST(node, UNICODE_LATIN_SMALL_LETTER_SHARP_S) && \
	 (ANYOF_FLAGS(node) & ANYOF_UNICODE) && \
	 (ANYOF_FLAGS(node) & ANYOF_FOLD) && \
	 ((end) > (input) + 1) && \
	 toLOWER((input)[0]) == 's' && \
	 toLOWER((input)[1]) == 's')