Tilmann Scheller
0511091e8a
Since the project is now hosted at the JS Foundation we can move to unified copyright notices for the project. Starting with this commit all future contributions to the project should only carry the following copyright notice (except for third-party code which requires copyright information to be preserved): "Copyright JS Foundation and other contributors, http://js.foundation" (without the quotes) This avoids cluttering the codebase with contributor-specific copyright notices which have a higher maintenance overhead and tend to get outdated quickly. Also dropping the year from the copyright notices helps to avoid yearly code changes just to update the copyright notices. Note that each contributor still retains full copyright ownership of his/her contributions and the respective authorship is tracked very accurately via Git. JerryScript-DCO-1.0-Signed-off-by: Tilmann Scheller t.scheller@samsung.com
211 lines
7.8 KiB
C
211 lines
7.8 KiB
C
/* Copyright JS Foundation and other contributors, http://js.foundation
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*
|
|
*
|
|
* Unicode characters and ranges generated by tools/print-unicode-ranges.sh
|
|
* from UnicodeData-3.0.0.txt.
|
|
* See also:
|
|
* http://www.unicode.org/Public/3.0-Update/UnicodeData-3.0.0.txt
|
|
* http://www.unicode.org/Public/3.0-Update/UnicodeData-3.0.0.html
|
|
*/
|
|
|
|
#ifndef LIT_UNICODE_RANGES_INC_H_
|
|
#define LIT_UNICODE_RANGES_INC_H_
|
|
|
|
/**
|
|
* Character interval starting points for the unicode letters.
|
|
*
|
|
* The characters covered by these intervalse are from
|
|
* the following Unicode categories: Lu, Ll, Lt, Lm, Lo, Nl
|
|
*/
|
|
static const uint16_t unicode_letter_interv_sps[] JERRY_CONST_DATA =
|
|
{
|
|
/*
|
|
* these are handled separetely
|
|
* 0x0041, len 25
|
|
* 0x0061, len 25
|
|
*/
|
|
0x00C0, 0x00D8, 0XF8, 0X1F8, 0x0222, 0x0250, 0x02B0, 0x02BB,
|
|
0x02D0, 0x02E0, 0x0388, 0x038E, 0x03A3, 0x03D0, 0x03DA, 0x0400, 0x048C, 0x04C7,
|
|
0x04CB, 0x04D0, 0x04F8, 0x0531, 0x0561, 0x05D0, 0x05F0, 0x0621, 0x0640, 0x0671,
|
|
0x06E5, 0x06FA, 0x0712, 0x0780, 0x0905, 0x0958, 0x0985, 0x098F, 0x0993, 0x09AA,
|
|
0x09B6, 0x09DC, 0x09DF, 0x09F0, 0x0A05, 0x0A0F, 0x0A13, 0x0A2A, 0x0A32, 0x0A35,
|
|
0x0A38, 0x0A59, 0x0A72, 0x0A85, 0x0A8F, 0x0A93, 0x0AAA, 0x0AB2, 0x0AB5, 0x0B05,
|
|
0x0B0F, 0x0B13, 0x0B2A, 0x0B32, 0x0B36, 0x0B5C, 0x0B5F, 0x0B85, 0x0B8E, 0x0B92,
|
|
0x0B99, 0x0B9E, 0x0BA3, 0x0BA8, 0x0BAE, 0x0BB7, 0x0C05, 0x0C0E, 0x0C12, 0x0C2A,
|
|
0x0C35, 0x0C60, 0x0C85, 0x0C8E, 0x0C92, 0x0CAA, 0x0CB5, 0x0CE0, 0x0D05, 0x0D0E,
|
|
0x0D12, 0x0D2A, 0x0D60, 0x0D85, 0x0D9A, 0x0DB3, 0x0DC0, 0x0E01, 0x0E32, 0x0E40,
|
|
0x0E81, 0x0E87, 0x0E94, 0x0E99, 0x0EA1, 0x0EAA, 0x0EAD, 0x0EB2, 0x0EC0, 0x0EDC,
|
|
0x0F40, 0x0F49, 0x0F88, 0x1000, 0x1023, 0x1029, 0x1050, 0x10A0, 0x10D0, 0x1100,
|
|
0x115F, 0x11A8, 0x1200, 0x1208, 0x124A, 0x1250, 0x125A, 0x1260, 0x128A, 0x1290,
|
|
0x12B2, 0x12B8, 0x12C2, 0x12C8, 0x12D0, 0x12D8, 0x12F0, 0x1312, 0x1318, 0x1320,
|
|
0x1348, 0x13A0, 0X1401, 0X1501, 0X1601, 0x166F, 0x1681, 0x16A0, 0x1780, 0x1820,
|
|
0x1880, 0x1E00, 0x1EA0, 0x1F00, 0x1F18, 0x1F20, 0x1F48, 0x1F50, 0x1F5F, 0x1F80,
|
|
0x1FB6, 0x1FC2, 0x1FC6, 0x1FD0, 0x1FD6, 0x1FE0, 0x1FF2, 0x1FF6, 0x210A, 0x2119,
|
|
0x212A, 0x212F, 0x2133, 0x2160, 0x3005, 0x3021, 0x3031, 0x3038, 0x3041, 0x309D,
|
|
0x30A1, 0x30FC, 0x3105, 0x3131, 0x31A0, 0XA000, 0XA100, 0XA200, 0XA300, 0XA400,
|
|
0XF900, 0XFA00, 0xFB00, 0xFB13, 0xFB1F, 0xFB2A, 0xFB38, 0xFB40, 0xFB43, 0xFB46,
|
|
0XFBD3, 0XFCD3, 0xFD50, 0xFD92, 0xFDF0, 0xFE70, 0xFE76, 0xFF21, 0xFF41, 0xFF66,
|
|
0xFFC2, 0xFFCA, 0xFFD2, 0xFFDA
|
|
};
|
|
|
|
/**
|
|
* Character lengths for the unicode letters.
|
|
*
|
|
* The characters covered by these intervalse are from
|
|
* the following Unicode categories: Lu, Ll, Lt, Lm, Lo, Nl
|
|
*/
|
|
static const uint8_t unicode_letter_interv_lens[] JERRY_CONST_DATA =
|
|
{
|
|
22, 30, 255, 39, 17, 93, 8, 6,
|
|
1, 4, 2, 19, 43, 7, 25, 129, 56, 1,
|
|
1, 37, 1, 37, 38, 26, 2, 25, 10, 98,
|
|
1, 2, 26, 37, 52, 9, 7, 1, 21, 6,
|
|
3, 1, 2, 1, 5, 1, 21, 6, 1, 1,
|
|
1, 3, 2, 6, 2, 21, 6, 1, 4, 7,
|
|
1, 21, 6, 1, 3, 1, 2, 5, 2, 3,
|
|
1, 1, 1, 2, 7, 2, 7, 2, 22, 9,
|
|
4, 1, 7, 2, 22, 9, 4, 1, 7, 2,
|
|
22, 15, 1, 17, 23, 8, 6, 47, 1, 6,
|
|
1, 1, 3, 6, 2, 1, 3, 1, 4, 1,
|
|
7, 33, 3, 33, 4, 1, 5, 37, 38, 89,
|
|
67, 81, 6, 62, 3, 6, 3, 38, 3, 30,
|
|
3, 6, 3, 6, 6, 22, 30, 3, 6, 38,
|
|
18, 84, 255, 255, 107, 7, 25, 74, 51, 87,
|
|
40, 155, 89, 21, 5, 37, 5, 7, 30, 52,
|
|
6, 2, 6, 3, 5, 12, 2, 6, 9, 4,
|
|
3, 2, 6, 35, 2, 8, 4, 2, 83, 1,
|
|
89, 2, 39, 93, 23, 255, 255, 255, 255, 140,
|
|
255, 45, 6, 4, 9, 12, 4, 1, 1, 107,
|
|
255, 106, 63, 53, 11, 2, 134, 25, 25, 88,
|
|
5, 5, 5, 2
|
|
};
|
|
|
|
/**
|
|
* Those unicode letter characters that are not inside any of
|
|
* the intervals specified in unicode_letter_intervals array.
|
|
*
|
|
* The characters are from the following Unicode categories:
|
|
* Lu, Ll, Lt, Lm, Lo, Nl
|
|
*/
|
|
static const uint16_t unicode_letter_chars[] JERRY_CONST_DATA =
|
|
{
|
|
0x00AA, 0x00B5, 0x00BA, 0x02EE, 0x037A, 0x0386, 0x038C, 0x0559, 0x06D5, 0x0710,
|
|
0x093D, 0x0950, 0x09B2, 0x0A5E, 0x0A8D, 0x0ABD, 0x0AD0, 0x0AE0, 0x0B3D, 0x0B9C,
|
|
0x0CDE, 0x0DBD, 0x0E84, 0x0E8A, 0x0E8D, 0x0EA5, 0x0EA7, 0x0EBD, 0x0EC6, 0x0F00,
|
|
0x1248, 0x1258, 0x1288, 0x12B0, 0x12C0, 0x1310, 0x1F59, 0x1F5B, 0x1F5D, 0x1FBE,
|
|
0x207F, 0x2102, 0x2107, 0x2115, 0x2124, 0x2126, 0x2128, 0x3400, 0x4DB5, 0x4E00,
|
|
0x9FA5, 0xAC00, 0xD7A3, 0xFB1D, 0xFB3E, 0xFE74
|
|
};
|
|
|
|
/**
|
|
* Character interval starting points for non-letter character
|
|
* that can be used as a non-first character of an identifier.
|
|
*
|
|
* The characters covered by these intervalse are from
|
|
* the following Unicode categories: Nd, Mn, Mc, Pc
|
|
*/
|
|
static const uint16_t unicode_non_letter_ident_part_interv_sps[] JERRY_CONST_DATA =
|
|
{
|
|
/*
|
|
* decimal digits: handled separately
|
|
* 0x0030, len: 9
|
|
*/
|
|
0x0300, 0x0360, 0x0483, 0x0591, 0x05A3, 0x05BB, 0x05C1, 0x064B, 0x0660,
|
|
0x06D6, 0x06DF, 0x06E7, 0x06EA, 0x06F0, 0x0730, 0x07A6, 0x0901, 0x093E, 0x0951,
|
|
0x0962, 0x0966, 0x0981, 0x09BE, 0x09C7, 0x09CB, 0x09E2, 0x09E6, 0x0A3E, 0x0A47,
|
|
0x0A4B, 0x0A66, 0x0A81, 0x0ABE, 0x0AC7, 0x0ACB, 0x0AE6, 0x0B01, 0x0B3E, 0x0B47,
|
|
0x0B4B, 0x0B56, 0x0B66, 0x0B82, 0x0BBE, 0x0BC6, 0x0BCA, 0x0BE7, 0x0C01, 0x0C3E,
|
|
0x0C46, 0x0C4A, 0x0C55, 0x0C66, 0x0C82, 0x0CBE, 0x0CC6, 0x0CCA, 0x0CD5, 0x0CE6,
|
|
0x0D02, 0x0D3E, 0x0D46, 0x0D4A, 0x0D66, 0x0D82, 0x0DCF, 0x0DD8, 0x0DF2, 0x0E34,
|
|
0x0E47, 0x0E50, 0x0EB4, 0x0EBB, 0x0EC8, 0x0ED0, 0x0F18, 0x0F20, 0x0F3E, 0x0F71,
|
|
0x0F86, 0x0F90, 0x0F99, 0x102C, 0x1036, 0x1040, 0x1056, 0x1369, 0x17B4, 0x17E0,
|
|
0x1810, 0x203F, 0x20D0, 0x302A, 0x3099, 0xFE20, 0xFE33, 0xFE4D, 0xFF10
|
|
};
|
|
|
|
/**
|
|
* Character interval lengths for non-letter character
|
|
* that can be used as a non-first character of an identifier.
|
|
*
|
|
* The characters covered by these intervalse are from
|
|
* the following Unicode categories: Nd, Mn, Mc, Pc
|
|
*/
|
|
static const uint8_t unicode_non_letter_ident_part_interv_lens[] =
|
|
{
|
|
78, 2, 3, 16, 22, 2, 1, 10, 9,
|
|
6, 5, 1, 3, 9, 26, 10, 2, 15, 3,
|
|
1, 9, 2, 6, 1, 2, 1, 9, 4, 1,
|
|
2, 11, 2, 7, 2, 2, 9, 2, 5, 1,
|
|
2, 1, 9, 1, 4, 2, 3, 8, 2, 6,
|
|
2, 3, 1, 9, 1, 6, 2, 3, 1, 9,
|
|
1, 5, 2, 3, 9, 1, 5, 7, 1, 6,
|
|
7, 9, 5, 1, 5, 9, 1, 9, 1, 19,
|
|
1, 7, 35, 6, 3, 9, 3, 8, 31, 9,
|
|
9, 1, 12, 5, 1, 3, 1, 2, 9
|
|
};
|
|
|
|
/**
|
|
* Those non-letter characters that can be used as a non-first
|
|
* character of an identifier and not included in any of the intervals
|
|
* specified in unicode_non_letter_ident_part_intervals array.
|
|
*
|
|
* The characters are from the following Unicode categories:
|
|
* Nd, Mn, Mc, Pc
|
|
*/
|
|
static const uint16_t unicode_non_letter_ident_part_chars[] =
|
|
{
|
|
0x005F, 0x05BF, 0x05C4, 0x0670, 0x0711, 0x093C, 0x09BC, 0x09D7, 0x0A02, 0x0A3C,
|
|
0x0ABC, 0x0B3C, 0x0BD7, 0x0D57, 0x0DCA, 0x0DD6, 0x0E31, 0x0EB1, 0x0F35, 0x0F37,
|
|
0x0F39, 0x0FC6, 0x18A9, 0x20E1, 0x30FB, 0xFB1E, 0xFF3F, 0xFF65
|
|
};
|
|
|
|
|
|
/**
|
|
* Unicode separator character interval strting points from Unicode category: Zs
|
|
*/
|
|
static const uint16_t unicode_separator_char_interv_sps[] =
|
|
{
|
|
0x2000
|
|
};
|
|
|
|
/**
|
|
* Unicode separator character interval lengths from Unicode category: Zs
|
|
*/
|
|
static const uint8_t unicode_separator_char_interv_lens[] =
|
|
{
|
|
11
|
|
};
|
|
|
|
/**
|
|
* Unicode separator characters that are not in the
|
|
* unicode_separator_char_intervals array.
|
|
*
|
|
* Unicode category: Zs
|
|
*/
|
|
static const uint16_t unicode_separator_chars[] =
|
|
{
|
|
/*
|
|
* these two chars are handled separatly @see lit_char_is_space_separator
|
|
* 0x0020, space
|
|
* 0x00A0, non-braking space
|
|
*/
|
|
0x1680, \
|
|
0x180E, /* manually added */ \
|
|
0x202F, /* manually added */ \
|
|
0x205F, \
|
|
0x3000
|
|
};
|
|
|
|
#endif
|