source: proto/charsetcompiler/inputs/Parabix2_mplex @ 3711

Last change on this file since 3711 was 1072, checked in by cameron, 9 years ago

Revise muliplex stream definition

File size: 1.1 KB
Line 
1lex.RefStart = [&]
2lex.Semicolon = [;]
3lex.LAngle = [<]
4lex.RAngle = [>]
5lex.LBracket = [[]
6lex.RBracket = []]
7lex.Exclam = [!]
8lex.QMark = [?]
9lex.Hyphen =  [-]
10lex.Equals = [=]
11lex.SQuote = [']
12lex.DQuote = ["]
13lex.Slash = [/]
14lex.Hash = [#]
15lex.x = [x]
16lex.Colon = [:]
17lex.ASCII_name_start = [_:A-Za-z]
18lex.ASCII_name_char = [-_.0-:A-Za-z]
19lex.NameScan = [-_.0-:A-Za-z\x80-\xFF]
20x00_x1F = [\x00-\x1F]
21lex.CR = [\x0D]
22lex.LF = [\x0A]
23lex.HT = [\x09]
24lex.SP = [ ]
25lex.WS = [\x0D\x0A\x09 ]
26lex.Digit = [0-9]
27lex.Hex = [0-9A-Fa-f]
28
29#   Multiplexed scope stream encodings
30#   - Allow 13 scope streams to be computed using 4 shifts only.
31#
32#   0000 - nonscope stream (bytes not in any scope definition)
33#   0001 - LAngle
34#   0010 - Hyphen
35#   0011 - RefStart
36#   0100 - RBracket
37#   0101 - QMark
38#   0110 - u8prefix2 [\xC0-\xDF]
39#   0111 - unused, future
40#
41#   10xx  - u8prefix3 [\xE0-\xEF]
42#   1000  - xE0
43#   1001  - xED
44#   1011  - xEF
45#   11xx  - u8prefix4 [\xF0-\xFF]
46#   1100  - xF0
47#   1101  - xF4
48#   1111 - unused, future
49
50mplex.s0 = [\xE0-\xFF]
51mplex.s1 = []?\xC0-\xDF\xF0-\xFF]
52mplex.s2 = [-&\xC0-\xDF\xEF]
53mplex.s3 = [<&?\xED\xEF\xF4]
54
Note: See TracBrowser for help on using the repository browser.