scite-context-lexer-bnf.lua /size: 3492 b    last modification: 2021-10-28 13:49
1local info = {
2    version   = 1.001,
3    comment   = "scintilla lpeg lexer for bnf",
4    author    = "Hans Hagen, PRAGMA-ADE, Hasselt NL",
5    copyright = "PRAGMA ADE / ConTeXt Development Team",
6    license   = "see context related readme files",
7}
8
9-- will replace the one in metafun
10
11local lpeg = lpeg
12local P, R, S = lpeg.P, lpeg.R, lpeg.S
13
14local lexers        = require("scite-context-lexer")
15
16local patterns      = lexers.patterns
17local token         = lexers.token
18
19local bnflexer      = lexers.new("bnf","scite-context-lexer-bnf")
20local bnfwhitespace = bnflexer.whitespace
21
22-- from wikipedia:
23--
24-- <syntax>         ::= <rule> | <rule> <syntax>
25-- <rule>           ::= <opt-whitespace> "<" <rule-name> ">" <opt-whitespace> "::=" <opt-whitespace> <expression> <line-end>
26-- <opt-whitespace> ::= " " <opt-whitespace> | ""
27-- <expression>     ::= <list> | <list> <opt-whitespace> "|" <opt-whitespace> <expression>
28-- <line-end>       ::= <opt-whitespace> <EOL> | <line-end> <line-end>
29-- <list>           ::= <term> | <term> <opt-whitespace> <list>
30-- <term>           ::= <literal> | "<" <rule-name> ">"
31-- <literal>        ::= '"' <text1> '"' | "'" <text2> "'"
32-- <text1>          ::= "" | <character1> <text1>
33-- <text2>          ::= "" | <character2> <text2>
34-- <character>      ::= <letter> | <digit> | <symbol>
35-- <letter>         ::= "A" | "B" | "C" | "D" | "E" | "F" | "G" | "H" | "I" | "J" | "K" | "L" | "M" | "N" | "O" | "P" | "Q" | "R" | "S" | "T" | "U" | "V" | "W" | "X" | "Y" | "Z" | "a" | "b" | "c" | "d" | "e" | "f" | "g" | "h" | "i" | "j" | "k" | "l" | "m" | "n" | "o" | "p" | "q" | "r" | "s" | "t" | "u" | "v" | "w" | "x" | "y" | "z"
36-- <digit>          ::= "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
37-- <symbol>         ::= "|" | " " | "-" | "!" | "#" | "$" | "%" | "&" | "(" | ")" | "*" | "+" | "," | "-" | "." | "/" | ":" | ";" | ">" | "=" | "<" | "?" | "@" | "[" | "\" | "]" | "^" | "_" | "`" | "{" | "}" | "~"
38-- <character1>     ::= <character> | "'"
39-- <character2>     ::= <character> | '"'
40-- <rule-name>      ::= <letter> | <rule-name> <rule-char>
41-- <rule-char>      ::= <letter> | <digit> | "-"
42
43local anything  = patterns.anything
44local separator = P("|")
45local left      = P("<")
46local right     = P(">")
47local space     = S(" \t\n\r\f")
48local spaces    = space^1
49local letter    = R("AZ","az")
50local digit     = R("09")
51local symbol    = S([[| -!#$%&()*+,-./:;>=<?@[\]^_`{}~]])
52local text      = (letter + digit + symbol^0)
53local name      = letter * (letter + digit + P("-"))^0
54local becomes   = P("::=")
55local extra     = P("|")
56local single    = P("'")
57local double    = P('"')
58
59local t_spacing = token(bnfwhitespace,space^1)
60local t_term    = token("command",left)
61                * token("text",name)
62                * token("command",right)
63local t_text    = token("quote",single)
64                * token("text",text)
65                * token("quote",single)
66                + token("quote",double)
67                * token("text",text)
68                * token("quote",double)
69local t_becomes = token("operator",becomes)
70local t_extra   = token("extra",extra)
71local t_rest    = token("default",anything)
72
73bnflexer.rules = {
74    { "whitespace", t_spacing },
75    { "term",       t_term    },
76    { "text",       t_text    },
77    { "becomes",    t_becomes },
78    { "extra",      t_extra   },
79    { "rest",       t_rest    },
80}
81
82bnflexer.folding = {
83    ["<"] = { ["grouping"] =  1 },
84    [">"] = { ["grouping"] = -1 },
85}
86
87return bnflexer
88