From a0837f7180949ddf9a96b3267f222e24cf72facd Mon Sep 17 00:00:00 2001 From: "David B. Lamkins" Date: Sat, 31 Oct 2015 19:14:48 +0100 Subject: lexer: new lexer for man/roff format --- lexers/man.lua | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 lexers/man.lua (limited to 'lexers/man.lua') diff --git a/lexers/man.lua b/lexers/man.lua new file mode 100644 index 0000000..a2d6175 --- /dev/null +++ b/lexers/man.lua @@ -0,0 +1,35 @@ +-- man/roff LPeg lexer. + +local l = require('lexer') +local token, word_match = l.token, l.word_match +local P, R, S = lpeg.P, lpeg.R, lpeg.S + +local M = {_NAME = 'man'} + +-- Whitespace. +local ws = token(l.WHITESPACE, l.space^1) + +-- Markup. +local rule1 = token(l.STRING, + P('.') * (P('B') * P('R')^-1 + P('I') * P('PR')^-1) * l.nonnewline^0) +local rule2 = token(l.NUMBER, P('.') * S('ST') * P('H') * l.nonnewline^0) +local rule3 = token(l.KEYWORD, + P('.br') + P('.DS') + P('.RS') + P('.RE') + P('.PD')) +local rule4 = token(l.LABEL, P('.') * (S('ST') * P('H') + P('.TP'))) +local rule5 = token(l.VARIABLE, + P('.B') * P('R')^-1 + P('.I') * S('PR')^-1 + P('.PP')) +local rule6 = token(l.TYPE, P('\\f') * S('BIPR')) +local rule7 = token(l.PREPROCESSOR, l.starts_line('.') * l.alpha^1) + +M._rules = { + {'whitespace', ws}, + {'rule1', rule1}, + {'rule2', rule2}, + {'rule3', rule3}, + {'rule4', rule4}, + {'rule5', rule5}, + {'rule6', rule6}, + {'rule7', rule7}, +} + +return M -- cgit v1.2.3