1/* Copyright JS Foundation and other contributors, http://js.foundation
2 *
3 * Licensed under the Apache License, Version 2.0 (the "License");
4 * you may not use this file except in compliance with the License.
5 * You may obtain a copy of the License at
6 *
7 * http://www.apache.org/licenses/LICENSE-2.0
8 *
9 * Unless required by applicable law or agreed to in writing, software
10 * distributed under the License is distributed on an "AS IS" BASIS
11 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 * See the License for the specific language governing permissions and
13 * limitations under the License.
14 */
15
16#ifndef LIT_STRINGS_H
17#define LIT_STRINGS_H
18
19#include "jrt.h"
20#include "lit-globals.h"
21
22/**
23 * Null character (used in few cases as utf-8 string end marker)
24 */
25#define LIT_BYTE_NULL (0)
26
27/**
28 * For the formal definition of Unicode transformation formats (UTF) see Section 3.9, Unicode Encoding Forms in The
29 * Unicode Standard (http://www.unicode.org/versions/Unicode3.0.0/ch03.pdf#G7404).
30 */
31#define LIT_UNICODE_CODE_POINT_NULL (0x0)
32#define LIT_UNICODE_CODE_POINT_MAX (0x10FFFF)
33
34#define LIT_UTF16_CODE_UNIT_MAX (0xFFFF)
35#define LIT_UTF16_FIRST_SURROGATE_CODE_POINT (0x10000)
36#define LIT_UTF16_LOW_SURROGATE_MARKER (0xDC00)
37#define LIT_UTF16_HIGH_SURROGATE_MARKER (0xD800)
38#define LIT_UTF16_HIGH_SURROGATE_MIN (0xD800)
39#define LIT_UTF16_HIGH_SURROGATE_MAX (0xDBFF)
40#define LIT_UTF16_LOW_SURROGATE_MIN (0xDC00)
41#define LIT_UTF16_LOW_SURROGATE_MAX (0xDFFF)
42#define LIT_UTF16_BITS_IN_SURROGATE (10)
43#define LIT_UTF16_LAST_10_BITS_MASK (0x3FF)
44
45#define LIT_UTF8_1_BYTE_MARKER (0x00)
46#define LIT_UTF8_2_BYTE_MARKER (0xC0)
47#define LIT_UTF8_3_BYTE_MARKER (0xE0)
48#define LIT_UTF8_4_BYTE_MARKER (0xF0)
49#define LIT_UTF8_EXTRA_BYTE_MARKER (0x80)
50
51#define LIT_UTF8_1_BYTE_MASK (0x80)
52#define LIT_UTF8_2_BYTE_MASK (0xE0)
53#define LIT_UTF8_3_BYTE_MASK (0xF0)
54#define LIT_UTF8_4_BYTE_MASK (0xF8)
55#define LIT_UTF8_EXTRA_BYTE_MASK (0xC0)
56
57#define LIT_UTF8_LAST_7_BITS_MASK (0x7F)
58#define LIT_UTF8_LAST_6_BITS_MASK (0x3F)
59#define LIT_UTF8_LAST_5_BITS_MASK (0x1F)
60#define LIT_UTF8_LAST_4_BITS_MASK (0x0F)
61#define LIT_UTF8_LAST_3_BITS_MASK (0x07)
62#define LIT_UTF8_LAST_2_BITS_MASK (0x03)
63#define LIT_UTF8_LAST_1_BIT_MASK (0x01)
64
65#define LIT_UTF8_BITS_IN_EXTRA_BYTES (6)
66
67#define LIT_UTF8_1_BYTE_CODE_POINT_MAX (0x7F)
68#define LIT_UTF8_2_BYTE_CODE_POINT_MIN (0x80)
69#define LIT_UTF8_2_BYTE_CODE_POINT_MAX (0x7FF)
70#define LIT_UTF8_3_BYTE_CODE_POINT_MIN (0x800)
71#define LIT_UTF8_3_BYTE_CODE_POINT_MAX (LIT_UTF16_CODE_UNIT_MAX)
72#define LIT_UTF8_4_BYTE_CODE_POINT_MIN (0x10000)
73#define LIT_UTF8_4_BYTE_CODE_POINT_MAX (LIT_UNICODE_CODE_POINT_MAX)
74
75/**
76 * Differnce between byte count needed to represent code point greater than 0xFFFF
77 * in common UTF-8 (4 bytes required) and CESU-8 (6 bytes required)
78 */
79#define LIT_UTF8_CESU8_SURROGATE_SIZE_DIF (2 * LIT_UTF8_MAX_BYTES_IN_CODE_UNIT - LIT_UTF8_MAX_BYTES_IN_CODE_POINT)
80
81/**
82 * Byte values >= LIT_UTF8_FIRST_BYTE_MAX are not allowed in internal strings
83 */
84#define LIT_UTF8_FIRST_BYTE_MAX (0xF8)
85
86/* validation */
87bool lit_is_valid_utf8_string (const lit_utf8_byte_t *utf8_buf_p, lit_utf8_size_t buf_size);
88bool lit_is_valid_cesu8_string (const lit_utf8_byte_t *cesu8_buf_p, lit_utf8_size_t buf_size);
89
90/* checks */
91bool lit_is_code_point_utf16_low_surrogate (lit_code_point_t code_point);
92bool lit_is_code_point_utf16_high_surrogate (lit_code_point_t code_point);
93
94/* size */
95lit_utf8_size_t lit_zt_utf8_string_size (const lit_utf8_byte_t *utf8_str_p);
96lit_utf8_size_t lit_get_utf8_size_of_cesu8_string (const lit_utf8_byte_t *cesu8_buf_p, lit_utf8_size_t cesu8_buf_size);
97
98/* length */
99lit_utf8_size_t lit_utf8_string_length (const lit_utf8_byte_t *utf8_buf_p, lit_utf8_size_t utf8_buf_size);
100lit_utf8_size_t lit_get_utf8_length_of_cesu8_string (const lit_utf8_byte_t *cesu8_buf_p,
101 lit_utf8_size_t cesu8_buf_size);
102
103/* hash */
104lit_string_hash_t lit_utf8_string_calc_hash (const lit_utf8_byte_t *utf8_buf_p, lit_utf8_size_t utf8_buf_size);
105lit_string_hash_t lit_utf8_string_hash_combine (lit_string_hash_t hash_basis, const lit_utf8_byte_t *utf8_buf_p,
106 lit_utf8_size_t utf8_buf_size);
107
108/* code unit access */
109ecma_char_t lit_utf8_string_code_unit_at (const lit_utf8_byte_t *utf8_buf_p, lit_utf8_size_t utf8_buf_size,
110 lit_utf8_size_t code_unit_offset);
111lit_utf8_size_t lit_get_unicode_char_size_by_utf8_first_byte (const lit_utf8_byte_t first_byte);
112
113/* conversion */
114lit_utf8_size_t lit_code_unit_to_utf8 (ecma_char_t code_unit, lit_utf8_byte_t *buf_p);
115lit_utf8_size_t lit_code_point_to_utf8 (lit_code_point_t code_point, lit_utf8_byte_t *buf);
116lit_utf8_size_t lit_code_point_to_cesu8 (lit_code_point_t code_point, lit_utf8_byte_t *buf);
117lit_utf8_size_t lit_convert_cesu8_string_to_utf8_string (const lit_utf8_byte_t *cesu8_string,
118 lit_utf8_size_t cesu8_size,
119 lit_utf8_byte_t *utf8_string,
120 lit_utf8_size_t utf8_size);
121lit_code_point_t lit_convert_surrogate_pair_to_code_point (ecma_char_t high_surrogate, ecma_char_t low_surrogate);
122
123bool lit_compare_utf8_strings_relational (const lit_utf8_byte_t *string1_p, lit_utf8_size_t string1_size,
124 const lit_utf8_byte_t *string2_p, lit_utf8_size_t string2_size);
125
126uint8_t lit_utf16_encode_code_point (lit_code_point_t cp, ecma_char_t *cu_p);
127
128/* read code point from buffer */
129lit_utf8_size_t lit_read_code_point_from_utf8 (const lit_utf8_byte_t *buf_p, lit_utf8_size_t buf_size,
130 lit_code_point_t *code_point);
131
132lit_utf8_size_t lit_read_code_unit_from_utf8 (const lit_utf8_byte_t *buf_p,
133 ecma_char_t *code_point);
134
135lit_utf8_size_t lit_read_prev_code_unit_from_utf8 (const lit_utf8_byte_t *buf_p,
136 ecma_char_t *code_point);
137
138ecma_char_t lit_cesu8_read_next (const lit_utf8_byte_t **buf_p);
139ecma_char_t lit_cesu8_read_prev (const lit_utf8_byte_t **buf_p);
140ecma_char_t lit_cesu8_peek_next (const lit_utf8_byte_t *buf_p);
141ecma_char_t lit_cesu8_peek_prev (const lit_utf8_byte_t *buf_p);
142void lit_utf8_incr (const lit_utf8_byte_t **buf_p);
143void lit_utf8_decr (const lit_utf8_byte_t **buf_p);
144
145#endif /* !LIT_STRINGS_H */
146