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_CHAR_HELPERS_H
17#define LIT_CHAR_HELPERS_H
18
19#include "lit-globals.h"
20
21/**
22 * Invalid character code point
23 */
24#define LIT_INVALID_CP 0xFFFFFFFF
25
26/**
27 * Result of lit_char_to_lower_case/lit_char_to_upper_case consist more than of a single code unit
28 */
29#define LIT_MULTIPLE_CU 0xFFFFFFFE
30
31/*
32 * Format control characters (ECMA-262 v5, Table 1)
33 */
34#define LIT_CHAR_ZWNJ ((ecma_char_t) 0x200C) /* zero width non-joiner */
35#define LIT_CHAR_ZWJ ((ecma_char_t) 0x200D) /* zero width joiner */
36#define LIT_CHAR_BOM ((ecma_char_t) 0xFEFF) /* byte order mark */
37
38/*
39 * Whitespace characters (ECMA-262 v5, Table 2)
40 */
41#define LIT_CHAR_TAB ((ecma_char_t) 0x0009) /* tab */
42#define LIT_CHAR_VTAB ((ecma_char_t) 0x000B) /* vertical tab */
43#define LIT_CHAR_FF ((ecma_char_t) 0x000C) /* form feed */
44#define LIT_CHAR_SP ((ecma_char_t) 0x0020) /* space */
45#define LIT_CHAR_NBSP ((ecma_char_t) 0x00A0) /* no-break space */
46#define LIT_CHAR_MVS ((ecma_char_t) 0x180E) /* mongolian vowel separator */
47/* LIT_CHAR_BOM is defined above */
48
49bool lit_char_is_white_space (lit_code_point_t c);
50
51/*
52 * Line terminator characters (ECMA-262 v5, Table 3)
53 */
54#define LIT_CHAR_LF ((ecma_char_t) 0x000A) /* line feed */
55#define LIT_CHAR_CR ((ecma_char_t) 0x000D) /* carriage return */
56#define LIT_CHAR_LS ((ecma_char_t) 0x2028) /* line separator */
57#define LIT_CHAR_PS ((ecma_char_t) 0x2029) /* paragraph separator */
58
59bool lit_char_is_line_terminator (ecma_char_t c);
60
61/*
62 * String Single Character Escape Sequences (ECMA-262 v5, Table 4)
63 */
64#define LIT_CHAR_BS ((ecma_char_t) 0x0008) /* backspace */
65/* LIT_CHAR_TAB is defined above */
66/* LIT_CHAR_LF is defined above */
67/* LIT_CHAR_VTAB is defined above */
68/* LIT_CHAR_FF is defined above */
69/* LIT_CHAR_CR is defined above */
70#define LIT_CHAR_DOUBLE_QUOTE ((ecma_char_t) '"') /* double quote */
71#define LIT_CHAR_SINGLE_QUOTE ((ecma_char_t) '\'') /* single quote */
72#define LIT_CHAR_BACKSLASH ((ecma_char_t) '\\') /* reverse solidus (backslash) */
73
74/*
75 * Comment characters (ECMA-262 v5, 7.4)
76 */
77#define LIT_CHAR_SLASH ((ecma_char_t) '/') /* solidus */
78#define LIT_CHAR_ASTERISK ((ecma_char_t) '*') /* asterisk */
79
80/*
81 * Identifier name characters (ECMA-262 v5, 7.6)
82 */
83#define LIT_CHAR_DOLLAR_SIGN ((ecma_char_t) '$') /* dollar sign */
84#define LIT_CHAR_UNDERSCORE ((ecma_char_t) '_') /* low line (underscore) */
85/* LIT_CHAR_BACKSLASH defined above */
86
87bool lit_code_point_is_identifier_start (lit_code_point_t code_point);
88bool lit_code_point_is_identifier_part (lit_code_point_t code_point);
89
90/*
91 * Punctuator characters (ECMA-262 v5, 7.7)
92 */
93#define LIT_CHAR_LEFT_BRACE ((ecma_char_t) '{') /* left curly bracket */
94#define LIT_CHAR_RIGHT_BRACE ((ecma_char_t) '}') /* right curly bracket */
95#define LIT_CHAR_LEFT_PAREN ((ecma_char_t) '(') /* left parenthesis */
96#define LIT_CHAR_RIGHT_PAREN ((ecma_char_t) ')') /* right parenthesis */
97#define LIT_CHAR_LEFT_SQUARE ((ecma_char_t) '[') /* left square bracket */
98#define LIT_CHAR_RIGHT_SQUARE ((ecma_char_t) ']') /* right square bracket */
99#define LIT_CHAR_DOT ((ecma_char_t) '.') /* dot */
100#define LIT_CHAR_SEMICOLON ((ecma_char_t) ';') /* semicolon */
101#define LIT_CHAR_COMMA ((ecma_char_t) ',') /* comma */
102#define LIT_CHAR_LESS_THAN ((ecma_char_t) '<') /* less-than sign */
103#define LIT_CHAR_GREATER_THAN ((ecma_char_t) '>') /* greater-than sign */
104#define LIT_CHAR_EQUALS ((ecma_char_t) '=') /* equals sign */
105#define LIT_CHAR_PLUS ((ecma_char_t) '+') /* plus sign */
106#define LIT_CHAR_MINUS ((ecma_char_t) '-') /* hyphen-minus */
107/* LIT_CHAR_ASTERISK is defined above */
108#define LIT_CHAR_PERCENT ((ecma_char_t) '%') /* percent sign */
109#define LIT_CHAR_AMPERSAND ((ecma_char_t) '&') /* ampersand */
110#define LIT_CHAR_VLINE ((ecma_char_t) '|') /* vertical line */
111#define LIT_CHAR_CIRCUMFLEX ((ecma_char_t) '^') /* circumflex accent */
112#define LIT_CHAR_EXCLAMATION ((ecma_char_t) '!') /* exclamation mark */
113#define LIT_CHAR_TILDE ((ecma_char_t) '~') /* tilde */
114#define LIT_CHAR_QUESTION ((ecma_char_t) '?') /* question mark */
115#define LIT_CHAR_COLON ((ecma_char_t) ':') /* colon */
116
117/*
118 * Special characters for String.prototype.replace.
119 */
120#define LIT_CHAR_GRAVE_ACCENT ((ecma_char_t) '`') /* grave accent */
121
122/**
123 * Uppercase ASCII letters
124 */
125#define LIT_CHAR_UPPERCASE_A ((ecma_char_t) 'A')
126#define LIT_CHAR_UPPERCASE_B ((ecma_char_t) 'B')
127#define LIT_CHAR_UPPERCASE_C ((ecma_char_t) 'C')
128#define LIT_CHAR_UPPERCASE_D ((ecma_char_t) 'D')
129#define LIT_CHAR_UPPERCASE_E ((ecma_char_t) 'E')
130#define LIT_CHAR_UPPERCASE_F ((ecma_char_t) 'F')
131#define LIT_CHAR_UPPERCASE_G ((ecma_char_t) 'G')
132#define LIT_CHAR_UPPERCASE_H ((ecma_char_t) 'H')
133#define LIT_CHAR_UPPERCASE_I ((ecma_char_t) 'I')
134#define LIT_CHAR_UPPERCASE_J ((ecma_char_t) 'J')
135#define LIT_CHAR_UPPERCASE_K ((ecma_char_t) 'K')
136#define LIT_CHAR_UPPERCASE_L ((ecma_char_t) 'L')
137#define LIT_CHAR_UPPERCASE_M ((ecma_char_t) 'M')
138#define LIT_CHAR_UPPERCASE_N ((ecma_char_t) 'N')
139#define LIT_CHAR_UPPERCASE_O ((ecma_char_t) 'O')
140#define LIT_CHAR_UPPERCASE_P ((ecma_char_t) 'P')
141#define LIT_CHAR_UPPERCASE_Q ((ecma_char_t) 'Q')
142#define LIT_CHAR_UPPERCASE_R ((ecma_char_t) 'R')
143#define LIT_CHAR_UPPERCASE_S ((ecma_char_t) 'S')
144#define LIT_CHAR_UPPERCASE_T ((ecma_char_t) 'T')
145#define LIT_CHAR_UPPERCASE_U ((ecma_char_t) 'U')
146#define LIT_CHAR_UPPERCASE_V ((ecma_char_t) 'V')
147#define LIT_CHAR_UPPERCASE_W ((ecma_char_t) 'W')
148#define LIT_CHAR_UPPERCASE_X ((ecma_char_t) 'X')
149#define LIT_CHAR_UPPERCASE_Y ((ecma_char_t) 'Y')
150#define LIT_CHAR_UPPERCASE_Z ((ecma_char_t) 'Z')
151
152/**
153 * Lowercase ASCII letters
154 */
155#define LIT_CHAR_LOWERCASE_A ((ecma_char_t) 'a')
156#define LIT_CHAR_LOWERCASE_B ((ecma_char_t) 'b')
157#define LIT_CHAR_LOWERCASE_C ((ecma_char_t) 'c')
158#define LIT_CHAR_LOWERCASE_D ((ecma_char_t) 'd')
159#define LIT_CHAR_LOWERCASE_E ((ecma_char_t) 'e')
160#define LIT_CHAR_LOWERCASE_F ((ecma_char_t) 'f')
161#define LIT_CHAR_LOWERCASE_G ((ecma_char_t) 'g')
162#define LIT_CHAR_LOWERCASE_H ((ecma_char_t) 'h')
163#define LIT_CHAR_LOWERCASE_I ((ecma_char_t) 'i')
164#define LIT_CHAR_LOWERCASE_J ((ecma_char_t) 'j')
165#define LIT_CHAR_LOWERCASE_K ((ecma_char_t) 'k')
166#define LIT_CHAR_LOWERCASE_L ((ecma_char_t) 'l')
167#define LIT_CHAR_LOWERCASE_M ((ecma_char_t) 'm')
168#define LIT_CHAR_LOWERCASE_N ((ecma_char_t) 'n')
169#define LIT_CHAR_LOWERCASE_O ((ecma_char_t) 'o')
170#define LIT_CHAR_LOWERCASE_P ((ecma_char_t) 'p')
171#define LIT_CHAR_LOWERCASE_Q ((ecma_char_t) 'q')
172#define LIT_CHAR_LOWERCASE_R ((ecma_char_t) 'r')
173#define LIT_CHAR_LOWERCASE_S ((ecma_char_t) 's')
174#define LIT_CHAR_LOWERCASE_T ((ecma_char_t) 't')
175#define LIT_CHAR_LOWERCASE_U ((ecma_char_t) 'u')
176#define LIT_CHAR_LOWERCASE_V ((ecma_char_t) 'v')
177#define LIT_CHAR_LOWERCASE_W ((ecma_char_t) 'w')
178#define LIT_CHAR_LOWERCASE_X ((ecma_char_t) 'x')
179#define LIT_CHAR_LOWERCASE_Y ((ecma_char_t) 'y')
180#define LIT_CHAR_LOWERCASE_Z ((ecma_char_t) 'z')
181
182/**
183 * ASCII decimal digits
184 */
185#define LIT_CHAR_0 ((ecma_char_t) '0')
186#define LIT_CHAR_1 ((ecma_char_t) '1')
187#define LIT_CHAR_2 ((ecma_char_t) '2')
188#define LIT_CHAR_3 ((ecma_char_t) '3')
189#define LIT_CHAR_4 ((ecma_char_t) '4')
190#define LIT_CHAR_5 ((ecma_char_t) '5')
191#define LIT_CHAR_6 ((ecma_char_t) '6')
192#define LIT_CHAR_7 ((ecma_char_t) '7')
193#define LIT_CHAR_8 ((ecma_char_t) '8')
194#define LIT_CHAR_9 ((ecma_char_t) '9')
195
196/**
197 * ASCII character ranges
198 */
199#define LIT_CHAR_ASCII_UPPERCASE_LETTERS_BEGIN LIT_CHAR_UPPERCASE_A /* uppercase letters range */
200#define LIT_CHAR_ASCII_UPPERCASE_LETTERS_END LIT_CHAR_UPPERCASE_Z
201
202#define LIT_CHAR_ASCII_LOWERCASE_LETTERS_BEGIN LIT_CHAR_LOWERCASE_A /* lowercase letters range */
203#define LIT_CHAR_ASCII_LOWERCASE_LETTERS_END LIT_CHAR_LOWERCASE_Z
204
205#define LIT_CHAR_ASCII_UPPERCASE_LETTERS_HEX_BEGIN LIT_CHAR_UPPERCASE_A /* uppercase letters for
206 * hexadecimal digits range */
207#define LIT_CHAR_ASCII_UPPERCASE_LETTERS_HEX_END LIT_CHAR_UPPERCASE_F
208
209#define LIT_CHAR_ASCII_LOWERCASE_LETTERS_HEX_BEGIN LIT_CHAR_LOWERCASE_A /* lowercase letters for
210 * hexadecimal digits range */
211#define LIT_CHAR_ASCII_LOWERCASE_LETTERS_HEX_END LIT_CHAR_LOWERCASE_F
212
213#define LIT_CHAR_ASCII_OCTAL_DIGITS_BEGIN LIT_CHAR_0 /* octal digits range */
214#define LIT_CHAR_ASCII_OCTAL_DIGITS_END LIT_CHAR_7
215
216#define LIT_CHAR_ASCII_DIGITS_BEGIN LIT_CHAR_0 /* decimal digits range */
217#define LIT_CHAR_ASCII_DIGITS_END LIT_CHAR_9
218
219#define LEXER_TO_ASCII_LOWERCASE(character) ((character) | LIT_CHAR_SP)
220
221bool lit_char_is_octal_digit (ecma_char_t c);
222bool lit_char_is_decimal_digit (ecma_char_t c);
223bool lit_char_is_hex_digit (ecma_char_t c);
224#if ENABLED (JERRY_ESNEXT)
225bool lit_char_is_binary_digit (ecma_char_t c);
226#endif /* ENABLED (JERRY_ESNEXT) */
227void lit_char_unicode_escape (ecma_stringbuilder_t *builder_p, ecma_char_t c);
228uint32_t lit_char_hex_to_int (ecma_char_t c);
229size_t lit_code_point_to_cesu8_bytes (uint8_t *dst_p, lit_code_point_t code_point);
230size_t lit_code_point_get_cesu8_length (lit_code_point_t code_point);
231void lit_four_byte_utf8_char_to_cesu8 (uint8_t *dst_p, const uint8_t *source_p);
232uint32_t lit_char_hex_lookup (const lit_utf8_byte_t *buf_p, const lit_utf8_byte_t *const buf_end_p, uint32_t lookup);
233uint32_t lit_parse_decimal (const lit_utf8_byte_t **buffer_p, const lit_utf8_byte_t *const buffer_end_p);
234bool lit_find_char_in_string (ecma_string_t *str_p, lit_utf8_byte_t c);
235
236/**
237 * Null character
238 */
239#define LIT_CHAR_NULL ((ecma_char_t) '\0')
240
241/*
242 * Part of IsWordChar abstract operation (ECMA-262 v5, 15.10.2.6, step 3)
243 */
244bool lit_char_is_word_char (lit_code_point_t c);
245
246/*
247 * Utility functions for uppercasing / lowercasing
248 */
249
250lit_code_point_t lit_char_to_lower_case (lit_code_point_t cp, ecma_stringbuilder_t *builder_p);
251lit_code_point_t lit_char_to_upper_case (lit_code_point_t cp, ecma_stringbuilder_t *builder_p);
252
253#if ENABLED (JERRY_ESNEXT)
254bool lit_char_fold_to_lower (lit_code_point_t cp);
255bool lit_char_fold_to_upper (lit_code_point_t cp);
256#endif /* ENABLED (JERRY_ESNEXT) */
257
258#endif /* !LIT_CHAR_HELPERS_H */
259