summaryrefslogtreecommitdiff
path: root/luaextra-lpeg.lua
diff options
context:
space:
mode:
authorKhaled Hosny <khaledhosny@eglug.org>2010-03-22 17:49:04 +0200
committerKhaled Hosny <khaledhosny@eglug.org>2010-03-22 17:49:04 +0200
commit22fa4cc9381179fdd43ca8a251cb49dd2703079d (patch)
treea222ca028b0f3bec9f4057424623323602174c29 /luaextra-lpeg.lua
parent87f7676bed961c8de29cc7fd2bebb41fe106f678 (diff)
downloadlualibs-22fa4cc9381179fdd43ca8a251cb49dd2703079d.tar.gz
Sync with ConTeXt
Diffstat (limited to 'luaextra-lpeg.lua')
-rw-r--r--luaextra-lpeg.lua120
1 files changed, 49 insertions, 71 deletions
diff --git a/luaextra-lpeg.lua b/luaextra-lpeg.lua
index 9e761e4..2e366a9 100644
--- a/luaextra-lpeg.lua
+++ b/luaextra-lpeg.lua
@@ -6,55 +6,58 @@ if not modules then modules = { } end modules ['l-lpeg'] = {
license = "see context related readme files"
}
-lpeg = require("lpeg")
+local lpeg = require("lpeg")
-local P, R, S, Ct, C, Cs, Cc = lpeg.P, lpeg.R, lpeg.S, lpeg.Ct, lpeg.C, lpeg.Cs, lpeg.Cc
-local match = lpeg.match
-
---~ l-lpeg.lua :
+lpeg.patterns = lpeg.patterns or { } -- so that we can share
+local patterns = lpeg.patterns
---~ lpeg.digit = lpeg.R('09')^1
---~ lpeg.sign = lpeg.S('+-')^1
---~ lpeg.cardinal = lpeg.P(lpeg.sign^0 * lpeg.digit^1)
---~ lpeg.integer = lpeg.P(lpeg.sign^0 * lpeg.digit^1)
---~ lpeg.float = lpeg.P(lpeg.sign^0 * lpeg.digit^0 * lpeg.P('.') * lpeg.digit^1)
---~ lpeg.number = lpeg.float + lpeg.integer
---~ lpeg.oct = lpeg.P("0") * lpeg.R('07')^1
---~ lpeg.hex = lpeg.P("0x") * (lpeg.R('09') + lpeg.R('AF'))^1
---~ lpeg.uppercase = lpeg.P("AZ")
---~ lpeg.lowercase = lpeg.P("az")
-
---~ lpeg.eol = lpeg.S('\r\n\f')^1 -- includes formfeed
---~ lpeg.space = lpeg.S(' ')^1
---~ lpeg.nonspace = lpeg.P(1-lpeg.space)^1
---~ lpeg.whitespace = lpeg.S(' \r\n\f\t')^1
---~ lpeg.nonwhitespace = lpeg.P(1-lpeg.whitespace)^1
+local P, R, S, Ct, C, Cs, Cc, V = lpeg.P, lpeg.R, lpeg.S, lpeg.Ct, lpeg.C, lpeg.Cs, lpeg.Cc, lpeg.V
+local match = lpeg.match
-local hash = { }
+local digit, sign = R('09'), S('+-')
+local cr, lf, crlf = P("\r"), P("\n"), P("\r\n")
+local utf8byte = R("\128\191")
+
+patterns.utf8byte = utf8byte
+patterns.utf8one = R("\000\127")
+patterns.utf8two = R("\194\223") * utf8byte
+patterns.utf8three = R("\224\239") * utf8byte * utf8byte
+patterns.utf8four = R("\240\244") * utf8byte * utf8byte * utf8byte
+
+patterns.digit = digit
+patterns.sign = sign
+patterns.cardinal = sign^0 * digit^1
+patterns.integer = sign^0 * digit^1
+patterns.float = sign^0 * digit^0 * P('.') * digit^1
+patterns.number = patterns.float + patterns.integer
+patterns.oct = P("0") * R("07")^1
+patterns.octal = patterns.oct
+patterns.HEX = P("0x") * R("09","AF")^1
+patterns.hex = P("0x") * R("09","af")^1
+patterns.hexadecimal = P("0x") * R("09","AF","af")^1
+patterns.lowercase = R("az")
+patterns.uppercase = R("AZ")
+patterns.letter = patterns.lowercase + patterns.uppercase
+patterns.space = S(" ")
+patterns.eol = S("\n\r")
+patterns.spacer = S(" \t\f\v") -- + string.char(0xc2, 0xa0) if we want utf (cf mail roberto)
+patterns.newline = crlf + cr + lf
+patterns.nonspace = 1 - patterns.space
+patterns.nonspacer = 1 - patterns.spacer
+patterns.whitespace = patterns.eol + patterns.spacer
+patterns.nonwhitespace = 1 - patterns.whitespace
+patterns.utf8 = patterns.utf8one + patterns.utf8two + patterns.utf8three + patterns.utf8four
+patterns.utfbom = P('\000\000\254\255') + P('\255\254\000\000') + P('\255\254') + P('\254\255') + P('\239\187\191')
function lpeg.anywhere(pattern) --slightly adapted from website
- return P { P(pattern) + 1 * lpeg.V(1) }
-end
-
-function lpeg.startswith(pattern) --slightly adapted
- return P(pattern)
+ return P { P(pattern) + 1 * V(1) } -- why so complex?
end
function lpeg.splitter(pattern, action)
return (((1-P(pattern))^1)/action+1)^0
end
--- variant:
-
---~ local parser = lpeg.Ct(lpeg.splitat(newline))
-
-local crlf = P("\r\n")
-local cr = P("\r")
-local lf = P("\n")
-local space = S(" \t\f\v") -- + string.char(0xc2, 0xa0) if we want utf (cf mail roberto)
-local newline = crlf + cr + lf
-local spacing = space^0 * newline
-
+local spacing = patterns.spacer^0 * patterns.newline -- sort of strip
local empty = spacing * Cc("")
local nonempty = Cs((1-spacing)^1) * spacing^-1
local content = (empty + nonempty)^1
@@ -65,7 +68,7 @@ function string:splitlines()
return match(capture,self)
end
-lpeg.linebyline = content -- better make a sublibrary
+patterns.textline = content
--~ local p = lpeg.splitat("->",false) print(match(p,"oeps->what->more")) -- oeps what more
--~ local p = lpeg.splitat("->",true) print(match(p,"oeps->what->more")) -- oeps what->more
@@ -121,45 +124,20 @@ end
--~ local p = pp
--~ for l=1,#list do
--~ if p then
---~ p = p + lpeg.P(list[l])
+--~ p = p + P(list[l])
--~ else
---~ p = lpeg.P(list[l])
+--~ p = P(list[l])
--~ end
--~ end
--~ return p
--~ end
--~ from roberto's site:
---~
---~ -- decode a two-byte UTF-8 sequence
---~ local function f2 (s)
---~ local c1, c2 = string.byte(s, 1, 2)
---~ return c1 * 64 + c2 - 12416
---~ end
---~
---~ -- decode a three-byte UTF-8 sequence
---~ local function f3 (s)
---~ local c1, c2, c3 = string.byte(s, 1, 3)
---~ return (c1 * 64 + c2) * 64 + c3 - 925824
---~ end
---~
---~ -- decode a four-byte UTF-8 sequence
---~ local function f4 (s)
---~ local c1, c2, c3, c4 = string.byte(s, 1, 4)
---~ return ((c1 * 64 + c2) * 64 + c3) * 64 + c4 - 63447168
---~ end
---~
---~ local cont = lpeg.R("\128\191") -- continuation byte
---~
---~ local utf8 = lpeg.R("\0\127") / string.byte
---~ + lpeg.R("\194\223") * cont / f2
---~ + lpeg.R("\224\239") * cont * cont / f3
---~ + lpeg.R("\240\244") * cont * cont * cont / f4
---~
---~ local decode_pattern = lpeg.Ct(utf8^0) * -1
-
-local cont = R("\128\191") -- continuation byte
+local f1 = string.byte
-lpeg.utf8 = R("\0\127") + R("\194\223") * cont + R("\224\239") * cont * cont + R("\240\244") * cont * cont * cont
+local function f2(s) local c1, c2 = f1(s,1,2) return c1 * 64 + c2 - 12416 end
+local function f3(s) local c1, c2, c3 = f1(s,1,3) return (c1 * 64 + c2) * 64 + c3 - 925824 end
+local function f4(s) local c1, c2, c3, c4 = f1(s,1,4) return ((c1 * 64 + c2) * 64 + c3) * 64 + c4 - 63447168 end
+patterns.utf8byte = patterns.utf8one/f1 + patterns.utf8two/f2 + patterns.utf8three/f3 + patterns.utf8four/f4