lexer: new lexer for man/roff format

2 files changed, 36 insertions, 0 deletions

diff --git a/lexers/lexer.lua b/lexers/lexer.lua
index 871bd1d..b42dc26 100644
--- a/lexers/lexer.lua
+++ b/lexers/lexer.lua
@@ -1595,6 +1595,7 @@ function M.get_style(lexer, lang, token_name)
 end
 
 local files = {
+	[".1|.2|.3|.4|.5|.6|.7|.8|.9|.1x|.2x|.3x|.4x|.5x|.6x|.7x|.8x|.9x"] = "man",
 	[".as|.asc"] = "actionscript",
 	[".adb|.ads"] = "ada",
 	[".g|.g4"] = "antlr",
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