diff options
Diffstat (limited to 'tex/generic/context/luatex-fonts-merged.lua')
| -rw-r--r-- | tex/generic/context/luatex-fonts-merged.lua | 1369 |
1 files changed, 716 insertions, 653 deletions
diff --git a/tex/generic/context/luatex-fonts-merged.lua b/tex/generic/context/luatex-fonts-merged.lua index c90043534..0cfbf2a0c 100644 --- a/tex/generic/context/luatex-fonts-merged.lua +++ b/tex/generic/context/luatex-fonts-merged.lua @@ -1,6 +1,6 @@ -- merged file : luatex-fonts-merged.lua -- parent file : luatex-fonts.lua --- merge date : 06/09/11 12:49:16 +-- merge date : 06/11/11 16:45:35 do -- begin closure to overcome local limits and interference @@ -127,650 +127,6 @@ end -- closure do -- begin closure to overcome local limits and interference -if not modules then modules = { } end modules ['l-lpeg'] = { - version = 1.001, - comment = "companion to luat-lib.mkiv", - author = "Hans Hagen, PRAGMA-ADE, Hasselt NL", - copyright = "PRAGMA ADE / ConTeXt Development Team", - license = "see context related readme files" -} - -local lpeg = require("lpeg") - -local type = type - --- Beware, we predefine a bunch of patterns here and one reason for doing so --- is that we get consistent behaviour in some of the visualizers. - -lpeg.patterns = lpeg.patterns or { } -- so that we can share -local patterns = lpeg.patterns - -local P, R, S, V, match = lpeg.P, lpeg.R, lpeg.S, lpeg.V, lpeg.match -local Ct, C, Cs, Cc = lpeg.Ct, lpeg.C, lpeg.Cs, lpeg.Cc -local lpegtype = lpeg.type - -local utfcharacters = string.utfcharacters -local utfgmatch = unicode and unicode.utf8.gmatch - -local anything = P(1) -local endofstring = P(-1) -local alwaysmatched = P(true) - -patterns.anything = anything -patterns.endofstring = endofstring -patterns.beginofstring = alwaysmatched -patterns.alwaysmatched = alwaysmatched - -local digit, sign = R('09'), S('+-') -local cr, lf, crlf = P("\r"), P("\n"), P("\r\n") -local newline = crlf + cr + lf -local escaped = P("\\") * anything -local squote = P("'") -local dquote = P('"') -local space = P(" ") - -local utfbom_32_be = P('\000\000\254\255') -local utfbom_32_le = P('\255\254\000\000') -local utfbom_16_be = P('\255\254') -local utfbom_16_le = P('\254\255') -local utfbom_8 = P('\239\187\191') -local utfbom = utfbom_32_be + utfbom_32_le - + utfbom_16_be + utfbom_16_le - + utfbom_8 -local utftype = utfbom_32_be / "utf-32-be" + utfbom_32_le / "utf-32-le" - + utfbom_16_be / "utf-16-be" + utfbom_16_le / "utf-16-le" - + utfbom_8 / "utf-8" + alwaysmatched / "unknown" - -local utf8next = R("\128\191") - -patterns.utf8one = R("\000\127") -patterns.utf8two = R("\194\223") * utf8next -patterns.utf8three = R("\224\239") * utf8next * utf8next -patterns.utf8four = R("\240\244") * utf8next * utf8next * utf8next -patterns.utfbom = utfbom -patterns.utftype = utftype - -local utf8char = patterns.utf8one + patterns.utf8two + patterns.utf8three + patterns.utf8four -local validutf8char = utf8char^0 * endofstring * Cc(true) + Cc(false) - -patterns.utf8 = utf8char -patterns.utf8char = utf8char -patterns.validutf8 = validutf8char -patterns.validutf8char = validutf8char - -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.cfloat = sign^0 * digit^0 * P(',') * digit^1 -patterns.number = patterns.float + patterns.integer -patterns.cnumber = patterns.cfloat + 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 = space -patterns.tab = P("\t") -patterns.spaceortab = patterns.space + patterns.tab -patterns.eol = S("\n\r") -patterns.spacer = S(" \t\f\v") -- + string.char(0xc2, 0xa0) if we want utf (cf mail roberto) -patterns.newline = newline -patterns.emptyline = newline^1 -patterns.nonspacer = 1 - patterns.spacer -patterns.whitespace = patterns.eol + patterns.spacer -patterns.nonwhitespace = 1 - patterns.whitespace -patterns.equal = P("=") -patterns.comma = P(",") -patterns.commaspacer = P(",") * patterns.spacer^0 -patterns.period = P(".") -patterns.colon = P(":") -patterns.semicolon = P(";") -patterns.underscore = P("_") -patterns.escaped = escaped -patterns.squote = squote -patterns.dquote = dquote -patterns.nosquote = (escaped + (1-squote))^0 -patterns.nodquote = (escaped + (1-dquote))^0 -patterns.unsingle = (squote/"") * patterns.nosquote * (squote/"") -patterns.undouble = (dquote/"") * patterns.nodquote * (dquote/"") -patterns.unquoted = patterns.undouble + patterns.unsingle -- more often undouble -patterns.unspacer = ((patterns.spacer^1)/"")^0 - -patterns.somecontent = (anything - newline - space)^1 -- (utf8char - newline - space)^1 -patterns.beginline = #(1-newline) - -local unquoted = Cs(patterns.unquoted * endofstring) -- not C - -function string.unquoted(str) - return match(unquoted,str) or str -end - ---~ print(string.unquoted("test")) ---~ print(string.unquoted([["t\"est"]])) ---~ print(string.unquoted([["t\"est"x]])) ---~ print(string.unquoted("\'test\'")) - -function lpeg.anywhere(pattern) --slightly adapted from website - 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 - -local splitters_s, splitters_m = { }, { } - -local function splitat(separator,single) - local splitter = (single and splitters_s[separator]) or splitters_m[separator] - if not splitter then - separator = P(separator) - local other = C((1 - separator)^0) - if single then - local any = anything - splitter = other * (separator * C(any^0) + "") -- ? - splitters_s[separator] = splitter - else - splitter = other * (separator * other)^0 - splitters_m[separator] = splitter - end - end - return splitter -end - -lpeg.splitat = splitat - ---~ local p = splitat("->",false) print(match(p,"oeps->what->more")) -- oeps what more ---~ local p = splitat("->",true) print(match(p,"oeps->what->more")) -- oeps what->more ---~ local p = splitat("->",false) print(match(p,"oeps")) -- oeps ---~ local p = splitat("->",true) print(match(p,"oeps")) -- oeps - -local cache = { } - -function lpeg.split(separator,str) - local c = cache[separator] - if not c then - c = Ct(splitat(separator)) - cache[separator] = c - end - return match(c,str) -end - -function string.split(str,separator) - local c = cache[separator] - if not c then - c = Ct(splitat(separator)) - cache[separator] = c - end - return match(c,str) -end - -local spacing = patterns.spacer^0 * newline -- sort of strip -local empty = spacing * Cc("") -local nonempty = Cs((1-spacing)^1) * spacing^-1 -local content = (empty + nonempty)^1 - -patterns.textline = content - ---~ local linesplitter = Ct(content^0) ---~ ---~ function string.splitlines(str) ---~ return match(linesplitter,str) ---~ end - -local linesplitter = Ct(splitat(newline)) - -patterns.linesplitter = linesplitter - -function string.splitlines(str) - return match(linesplitter,str) -end - -local utflinesplitter = utfbom^-1 * Ct(splitat(newline)) - -patterns.utflinesplitter = utflinesplitter - -function string.utfsplitlines(str) - return match(utflinesplitter,str) -end - ---~ lpeg.splitters = cache -- no longer public - -local cache = { } - -function lpeg.checkedsplit(separator,str) - local c = cache[separator] - if not c then - separator = P(separator) - local other = C((1 - separator)^1) - c = Ct(separator^0 * other * (separator^1 * other)^0) - cache[separator] = c - end - return match(c,str) -end - -function string.checkedsplit(str,separator) - local c = cache[separator] - if not c then - separator = P(separator) - local other = C((1 - separator)^1) - c = Ct(separator^0 * other * (separator^1 * other)^0) - cache[separator] = c - end - return match(c,str) -end - ---~ from roberto's site: - -local f1 = string.byte - -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 - -local utf8byte = patterns.utf8one/f1 + patterns.utf8two/f2 + patterns.utf8three/f3 + patterns.utf8four/f4 - -patterns.utf8byte = utf8byte - ---~ local str = " a b c d " - ---~ local s = lpeg.stripper(lpeg.R("az")) print("["..lpeg.match(s,str).."]") ---~ local s = lpeg.keeper(lpeg.R("az")) print("["..lpeg.match(s,str).."]") ---~ local s = lpeg.stripper("ab") print("["..lpeg.match(s,str).."]") ---~ local s = lpeg.keeper("ab") print("["..lpeg.match(s,str).."]") - -local cache = { } - -function lpeg.stripper(str) - if type(str) == "string" then - local s = cache[str] - if not s then - s = Cs(((S(str)^1)/"" + 1)^0) - cache[str] = s - end - return s - else - return Cs(((str^1)/"" + 1)^0) - end -end - -local cache = { } - -function lpeg.keeper(str) - if type(str) == "string" then - local s = cache[str] - if not s then - s = Cs((((1-S(str))^1)/"" + 1)^0) - cache[str] = s - end - return s - else - return Cs((((1-str)^1)/"" + 1)^0) - end -end - -function lpeg.frontstripper(str) -- or pattern (yet undocumented) - return (P(str) + P(true)) * Cs(P(1)^0) -end - -function lpeg.endstripper(str) -- or pattern (yet undocumented) - return Cs((1 - P(str) * P(-1))^0) -end - --- Just for fun I looked at the used bytecode and --- p = (p and p + pp) or pp gets one more (testset). - -function lpeg.replacer(one,two) - if type(one) == "table" then - local no = #one - if no > 0 then - local p - for i=1,no do - local o = one[i] - local pp = P(o[1]) / o[2] - if p then - p = p + pp - else - p = pp - end - end - return Cs((p + 1)^0) - end - else - two = two or "" - return Cs((P(one)/two + 1)^0) - end -end - -local splitters_f, splitters_s = { }, { } - -function lpeg.firstofsplit(separator) -- always return value - local splitter = splitters_f[separator] - if not splitter then - separator = P(separator) - splitter = C((1 - separator)^0) - splitters_f[separator] = splitter - end - return splitter -end - -function lpeg.secondofsplit(separator) -- nil if not split - local splitter = splitters_s[separator] - if not splitter then - separator = P(separator) - splitter = (1 - separator)^0 * separator * C(anything^0) - splitters_s[separator] = splitter - end - return splitter -end - -function lpeg.balancer(left,right) - left, right = P(left), P(right) - return P { left * ((1 - left - right) + V(1))^0 * right } -end - ---~ print(1,match(lpeg.firstofsplit(":"),"bc:de")) ---~ print(2,match(lpeg.firstofsplit(":"),":de")) -- empty ---~ print(3,match(lpeg.firstofsplit(":"),"bc")) ---~ print(4,match(lpeg.secondofsplit(":"),"bc:de")) ---~ print(5,match(lpeg.secondofsplit(":"),"bc:")) -- empty ---~ print(6,match(lpeg.secondofsplit(":",""),"bc")) ---~ print(7,match(lpeg.secondofsplit(":"),"bc")) ---~ print(9,match(lpeg.secondofsplit(":","123"),"bc")) - ---~ -- slower: ---~ ---~ function lpeg.counter(pattern) ---~ local n, pattern = 0, (lpeg.P(pattern)/function() n = n + 1 end + lpeg.anything)^0 ---~ return function(str) n = 0 ; lpegmatch(pattern,str) ; return n end ---~ end - -local nany = utf8char/"" - -function lpeg.counter(pattern) - pattern = Cs((P(pattern)/" " + nany)^0) - return function(str) - return #match(pattern,str) - end -end - -if utfgmatch then - - function lpeg.count(str,what) -- replaces string.count - if type(what) == "string" then - local n = 0 - for _ in utfgmatch(str,what) do - n = n + 1 - end - return n - else -- 4 times slower but still faster than / function - return #match(Cs((P(what)/" " + nany)^0),str) - end - end - -else - - local cache = { } - - function lpeg.count(str,what) -- replaces string.count - if type(what) == "string" then - local p = cache[what] - if not p then - p = Cs((P(what)/" " + nany)^0) - cache[p] = p - end - return #match(p,str) - else -- 4 times slower but still faster than / function - return #match(Cs((P(what)/" " + nany)^0),str) - end - end - -end - -local patterns_escapes = { -- also defines in l-string - ["%"] = "%%", - ["."] = "%.", - ["+"] = "%+", ["-"] = "%-", ["*"] = "%*", - ["["] = "%[", ["]"] = "%]", - ["("] = "%)", [")"] = "%)", - -- ["{"] = "%{", ["}"] = "%}" - -- ["^"] = "%^", ["$"] = "%$", -} - -local simple_escapes = { -- also defines in l-string - ["-"] = "%-", - ["."] = "%.", - ["?"] = ".", - ["*"] = ".*", -} - -local p = Cs((S("-.+*%()[]") / patterns_escapes + anything)^0) -local s = Cs((S("-.+*%()[]") / simple_escapes + anything)^0) - -function string.escapedpattern(str,simple) - return match(simple and s or p,str) -end - --- utf extensies - -lpeg.UP = lpeg.P - -if utfcharacters then - - function lpeg.US(str) - local p - for uc in utfcharacters(str) do - if p then - p = p + P(uc) - else - p = P(uc) - end - end - return p - end - - -elseif utfgmatch then - - function lpeg.US(str) - local p - for uc in utfgmatch(str,".") do - if p then - p = p + P(uc) - else - p = P(uc) - end - end - return p - end - -else - - function lpeg.US(str) - local p - local f = function(uc) - if p then - p = p + P(uc) - else - p = P(uc) - end - end - match((utf8char/f)^0,str) - return p - end - -end - -local range = Cs(utf8byte) * (Cs(utf8byte) + Cc(false)) - -local utfchar = unicode and unicode.utf8 and unicode.utf8.char - -function lpeg.UR(str,more) - local first, last - if type(str) == "number" then - first = str - last = more or first - else - first, last = match(range,str) - if not last then - return P(str) - end - end - if first == last then - return P(str) - elseif utfchar and last - first < 8 then -- a somewhat arbitrary criterium - local p - for i=first,last do - if p then - p = p + P(utfchar(i)) - else - p = P(utfchar(i)) - end - end - return p -- nil when invalid range - else - local f = function(b) - return b >= first and b <= last - end - return utf8byte / f -- nil when invalid range - end -end - ---~ lpeg.print(lpeg.R("ab","cd","gh")) ---~ lpeg.print(lpeg.P("a","b","c")) ---~ lpeg.print(lpeg.S("a","b","c")) - ---~ print(lpeg.count("äáàa",lpeg.P("á") + lpeg.P("à"))) ---~ print(lpeg.count("äáàa",lpeg.UP("áà"))) ---~ print(lpeg.count("äáàa",lpeg.US("àá"))) ---~ print(lpeg.count("äáàa",lpeg.UR("aá"))) ---~ print(lpeg.count("äáàa",lpeg.UR("àá"))) ---~ print(lpeg.count("äáàa",lpeg.UR(0x0000,0xFFFF))) - -function lpeg.oneof(list,...) -- lpeg.oneof("elseif","else","if","then") - if type(list) ~= "table" then - list = { list, ... } - end - -- sort(list) -- longest match first - local p = P(list[1]) - for l=2,#list do - p = p + P(list[l]) - end - return p -end - -function lpeg.is_lpeg(p) - return p and lpegtype(p) == "pattern" -end - ---~ Cf(Ct("") * (Cg(C(...) * "=" * Cs(...)))^0, rawset) - -end -- closure - -do -- begin closure to overcome local limits and interference - -if not modules then modules = { } end modules ['l-boolean'] = { - version = 1.001, - comment = "companion to luat-lib.mkiv", - author = "Hans Hagen, PRAGMA-ADE, Hasselt NL", - copyright = "PRAGMA ADE / ConTeXt Development Team", - license = "see context related readme files" -} - -local type, tonumber = type, tonumber - -boolean = boolean or { } -local boolean = boolean - --- function boolean.tonumber(b) --- return b and 1 or 0 -- test and test and return or return --- end - -function boolean.tonumber(b) - if b then return 1 else return 0 end -- test and return or return -end - -function toboolean(str,tolerant) - if tolerant then - local tstr = type(str) - if tstr == "string" then - return str == "true" or str == "yes" or str == "on" or str == "1" or str == "t" - elseif tstr == "number" then - return tonumber(str) ~= 0 - elseif tstr == "nil" then - return false - else - return str - end - elseif str == "true" then - return true - elseif str == "false" then - return false - else - return str - end -end - -string.toboolean = toboolean - -function string.is_boolean(str,default) - if type(str) == "string" then - if str == "true" or str == "yes" or str == "on" or str == "t" then - return true - elseif str == "false" or str == "no" or str == "off" or str == "f" then - return false - end - end - return default -end - -end -- closure - -do -- begin closure to overcome local limits and interference - -if not modules then modules = { } end modules ['l-math'] = { - version = 1.001, - comment = "companion to luat-lib.mkiv", - author = "Hans Hagen, PRAGMA-ADE, Hasselt NL", - copyright = "PRAGMA ADE / ConTeXt Development Team", - license = "see context related readme files" -} - -local floor, sin, cos, tan = math.floor, math.sin, math.cos, math.tan - -if not math.round then - function math.round(x) return floor(x + 0.5) end -end - -if not math.div then - function math.div(n,m) return floor(n/m) end -end - -if not math.mod then - function math.mod(n,m) return n % m end -end - -local pipi = 2*math.pi/360 - -if not math.sind then - function math.sind(d) return sin(d*pipi) end - function math.cosd(d) return cos(d*pipi) end - function math.tand(d) return tan(d*pipi) end -end - -if not math.odd then - function math.odd (n) return n % 2 == 0 end - function math.even(n) return n % 2 ~= 0 end -end - -end -- closure - -do -- begin closure to overcome local limits and interference - if not modules then modules = { } end modules ['l-table'] = { version = 1.001, comment = "companion to luat-lib.mkiv", @@ -1703,6 +1059,713 @@ function table.has_one_entry(t) return t and not next(t,next(t)) end +-- new + +function table.loweredkeys(t) -- maybe utf + local l = { } + for k, v in next, t do + l[lower(k)] = v + end + return l +end + +end -- closure + +do -- begin closure to overcome local limits and interference + +if not modules then modules = { } end modules ['l-lpeg'] = { + version = 1.001, + comment = "companion to luat-lib.mkiv", + author = "Hans Hagen, PRAGMA-ADE, Hasselt NL", + copyright = "PRAGMA ADE / ConTeXt Development Team", + license = "see context related readme files" +} + +local lpeg = require("lpeg") + +local type = type +local byte, char = string.byte, string.char + +-- Beware, we predefine a bunch of patterns here and one reason for doing so +-- is that we get consistent behaviour in some of the visualizers. + +lpeg.patterns = lpeg.patterns or { } -- so that we can share +local patterns = lpeg.patterns + +local P, R, S, V, match = lpeg.P, lpeg.R, lpeg.S, lpeg.V, lpeg.match +local Ct, C, Cs, Cc = lpeg.Ct, lpeg.C, lpeg.Cs, lpeg.Cc +local lpegtype = lpeg.type + +local utfcharacters = string.utfcharacters +local utfgmatch = unicode and unicode.utf8.gmatch + +local anything = P(1) +local endofstring = P(-1) +local alwaysmatched = P(true) + +patterns.anything = anything +patterns.endofstring = endofstring +patterns.beginofstring = alwaysmatched +patterns.alwaysmatched = alwaysmatched + +local digit, sign = R('09'), S('+-') +local cr, lf, crlf = P("\r"), P("\n"), P("\r\n") +local newline = crlf + cr + lf +local escaped = P("\\") * anything +local squote = P("'") +local dquote = P('"') +local space = P(" ") + +local utfbom_32_be = P('\000\000\254\255') +local utfbom_32_le = P('\255\254\000\000') +local utfbom_16_be = P('\255\254') +local utfbom_16_le = P('\254\255') +local utfbom_8 = P('\239\187\191') +local utfbom = utfbom_32_be + utfbom_32_le + + utfbom_16_be + utfbom_16_le + + utfbom_8 +local utftype = utfbom_32_be / "utf-32-be" + utfbom_32_le / "utf-32-le" + + utfbom_16_be / "utf-16-be" + utfbom_16_le / "utf-16-le" + + utfbom_8 / "utf-8" + alwaysmatched / "unknown" + +local utf8next = R("\128\191") + +patterns.utf8one = R("\000\127") +patterns.utf8two = R("\194\223") * utf8next +patterns.utf8three = R("\224\239") * utf8next * utf8next +patterns.utf8four = R("\240\244") * utf8next * utf8next * utf8next +patterns.utfbom = utfbom +patterns.utftype = utftype + +local utf8char = patterns.utf8one + patterns.utf8two + patterns.utf8three + patterns.utf8four +local validutf8char = utf8char^0 * endofstring * Cc(true) + Cc(false) + +patterns.utf8 = utf8char +patterns.utf8char = utf8char +patterns.validutf8 = validutf8char +patterns.validutf8char = validutf8char + +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.cfloat = sign^0 * digit^0 * P(',') * digit^1 +patterns.number = patterns.float + patterns.integer +patterns.cnumber = patterns.cfloat + 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 = space +patterns.tab = P("\t") +patterns.spaceortab = patterns.space + patterns.tab +patterns.eol = S("\n\r") +patterns.spacer = S(" \t\f\v") -- + char(0xc2, 0xa0) if we want utf (cf mail roberto) +patterns.newline = newline +patterns.emptyline = newline^1 +patterns.nonspacer = 1 - patterns.spacer +patterns.whitespace = patterns.eol + patterns.spacer +patterns.nonwhitespace = 1 - patterns.whitespace +patterns.equal = P("=") +patterns.comma = P(",") +patterns.commaspacer = P(",") * patterns.spacer^0 +patterns.period = P(".") +patterns.colon = P(":") +patterns.semicolon = P(";") +patterns.underscore = P("_") +patterns.escaped = escaped +patterns.squote = squote +patterns.dquote = dquote +patterns.nosquote = (escaped + (1-squote))^0 +patterns.nodquote = (escaped + (1-dquote))^0 +patterns.unsingle = (squote/"") * patterns.nosquote * (squote/"") +patterns.undouble = (dquote/"") * patterns.nodquote * (dquote/"") +patterns.unquoted = patterns.undouble + patterns.unsingle -- more often undouble +patterns.unspacer = ((patterns.spacer^1)/"")^0 + +patterns.somecontent = (anything - newline - space)^1 -- (utf8char - newline - space)^1 +patterns.beginline = #(1-newline) + +local unquoted = Cs(patterns.unquoted * endofstring) -- not C + +function string.unquoted(str) + return match(unquoted,str) or str +end + +-- more efficient: + +local unquoted = ( + squote * Cs(1 - P(-2)) * squote + + dquote * Cs(1 - P(-2)) * dquote +) + +function string.unquoted(str) + return match(unquoted,str) or str +end + +patterns.unquoted = unquoted + +--~ print(string.unquoted("test")) +--~ print(string.unquoted([["t\"est"]])) +--~ print(string.unquoted([["t\"est"x]])) +--~ print(string.unquoted("\'test\'")) + +function lpeg.anywhere(pattern) --slightly adapted from website + 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 + +function lpeg.tsplitter(pattern, action) + return Ct((((1-P(pattern))^1)/action+1)^0) +end + +-- probleem: separator can be lpeg and that does not hash too well, but +-- it's quite okay as the key is then not garbage collected + +local splitters_s, splitters_m, splitters_t = { }, { }, { } + +local function splitat(separator,single) + local splitter = (single and splitters_s[separator]) or splitters_m[separator] + if not splitter then + separator = P(separator) + local other = C((1 - separator)^0) + if single then + local any = anything + splitter = other * (separator * C(any^0) + "") -- ? + splitters_s[separator] = splitter + else + splitter = other * (separator * other)^0 + splitters_m[separator] = splitter + end + end + return splitter +end + +local function tsplitat(separator) + local splitter = splitters_t[separator] + if not splitter then + splitter = Ct(splitat(separator)) + splitters_t[separator] = splitter + end + return splitter +end + +lpeg.splitat = splitat +lpeg.tsplitat = tsplitat + +--~ local p = splitat("->",false) print(match(p,"oeps->what->more")) -- oeps what more +--~ local p = splitat("->",true) print(match(p,"oeps->what->more")) -- oeps what->more +--~ local p = splitat("->",false) print(match(p,"oeps")) -- oeps +--~ local p = splitat("->",true) print(match(p,"oeps")) -- oeps + +local cache = { } + +function lpeg.split(separator,str) + local c = cache[separator] + if not c then + c = tsplitat(separator) + cache[separator] = c + end + return match(c,str) +end + +function string.split(str,separator) + local c = cache[separator] + if not c then + c = tsplitat(separator) + cache[separator] = c + end + return match(c,str) +end + +local spacing = patterns.spacer^0 * newline -- sort of strip +local empty = spacing * Cc("") +local nonempty = Cs((1-spacing)^1) * spacing^-1 +local content = (empty + nonempty)^1 + +patterns.textline = content + +--~ local linesplitter = Ct(content^0) +--~ +--~ function string.splitlines(str) +--~ return match(linesplitter,str) +--~ end + +local linesplitter = tsplitat(newline) + +patterns.linesplitter = linesplitter + +function string.splitlines(str) + return match(linesplitter,str) +end + +local utflinesplitter = utfbom^-1 * tsplitat(newline) + +patterns.utflinesplitter = utflinesplitter + +function string.utfsplitlines(str) + return match(utflinesplitter,str) +end + +--~ lpeg.splitters = cache -- no longer public + +local cache = { } + +function lpeg.checkedsplit(separator,str) + local c = cache[separator] + if not c then + separator = P(separator) + local other = C((1 - separator)^1) + c = Ct(separator^0 * other * (separator^1 * other)^0) + cache[separator] = c + end + return match(c,str) +end + +function string.checkedsplit(str,separator) + local c = cache[separator] + if not c then + separator = P(separator) + local other = C((1 - separator)^1) + c = Ct(separator^0 * other * (separator^1 * other)^0) + cache[separator] = c + end + return match(c,str) +end + +--~ from roberto's site: + +local function f2(s) local c1, c2 = byte(s,1,2) return c1 * 64 + c2 - 12416 end +local function f3(s) local c1, c2, c3 = byte(s,1,3) return (c1 * 64 + c2) * 64 + c3 - 925824 end +local function f4(s) local c1, c2, c3, c4 = byte(s,1,4) return ((c1 * 64 + c2) * 64 + c3) * 64 + c4 - 63447168 end + +local utf8byte = patterns.utf8one/byte + patterns.utf8two/f2 + patterns.utf8three/f3 + patterns.utf8four/f4 + +patterns.utf8byte = utf8byte + +--~ local str = " a b c d " + +--~ local s = lpeg.stripper(lpeg.R("az")) print("["..lpeg.match(s,str).."]") +--~ local s = lpeg.keeper(lpeg.R("az")) print("["..lpeg.match(s,str).."]") +--~ local s = lpeg.stripper("ab") print("["..lpeg.match(s,str).."]") +--~ local s = lpeg.keeper("ab") print("["..lpeg.match(s,str).."]") + +local cache = { } + +function lpeg.stripper(str) + if type(str) == "string" then + local s = cache[str] + if not s then + s = Cs(((S(str)^1)/"" + 1)^0) + cache[str] = s + end + return s + else + return Cs(((str^1)/"" + 1)^0) + end +end + +local cache = { } + +function lpeg.keeper(str) + if type(str) == "string" then + local s = cache[str] + if not s then + s = Cs((((1-S(str))^1)/"" + 1)^0) + cache[str] = s + end + return s + else + return Cs((((1-str)^1)/"" + 1)^0) + end +end + +function lpeg.frontstripper(str) -- or pattern (yet undocumented) + return (P(str) + P(true)) * Cs(P(1)^0) +end + +function lpeg.endstripper(str) -- or pattern (yet undocumented) + return Cs((1 - P(str) * P(-1))^0) +end + +-- Just for fun I looked at the used bytecode and +-- p = (p and p + pp) or pp gets one more (testset). + +function lpeg.replacer(one,two) + if type(one) == "table" then + local no = #one + if no > 0 then + local p + for i=1,no do + local o = one[i] + local pp = P(o[1]) / o[2] + if p then + p = p + pp + else + p = pp + end + end + return Cs((p + 1)^0) + end + else + two = two or "" + return Cs((P(one)/two + 1)^0) + end +end + +local splitters_f, splitters_s = { }, { } + +function lpeg.firstofsplit(separator) -- always return value + local splitter = splitters_f[separator] + if not splitter then + separator = P(separator) + splitter = C((1 - separator)^0) + splitters_f[separator] = splitter + end + return splitter +end + +function lpeg.secondofsplit(separator) -- nil if not split + local splitter = splitters_s[separator] + if not splitter then + separator = P(separator) + splitter = (1 - separator)^0 * separator * C(anything^0) + splitters_s[separator] = splitter + end + return splitter +end + +function lpeg.balancer(left,right) + left, right = P(left), P(right) + return P { left * ((1 - left - right) + V(1))^0 * right } +end + +--~ print(1,match(lpeg.firstofsplit(":"),"bc:de")) +--~ print(2,match(lpeg.firstofsplit(":"),":de")) -- empty +--~ print(3,match(lpeg.firstofsplit(":"),"bc")) +--~ print(4,match(lpeg.secondofsplit(":"),"bc:de")) +--~ print(5,match(lpeg.secondofsplit(":"),"bc:")) -- empty +--~ print(6,match(lpeg.secondofsplit(":",""),"bc")) +--~ print(7,match(lpeg.secondofsplit(":"),"bc")) +--~ print(9,match(lpeg.secondofsplit(":","123"),"bc")) + +--~ -- slower: +--~ +--~ function lpeg.counter(pattern) +--~ local n, pattern = 0, (lpeg.P(pattern)/function() n = n + 1 end + lpeg.anything)^0 +--~ return function(str) n = 0 ; lpegmatch(pattern,str) ; return n end +--~ end + +local nany = utf8char/"" + +function lpeg.counter(pattern) + pattern = Cs((P(pattern)/" " + nany)^0) + return function(str) + return #match(pattern,str) + end +end + +if utfgmatch then + + function lpeg.count(str,what) -- replaces string.count + if type(what) == "string" then + local n = 0 + for _ in utfgmatch(str,what) do + n = n + 1 + end + return n + else -- 4 times slower but still faster than / function + return #match(Cs((P(what)/" " + nany)^0),str) + end + end + +else + + local cache = { } + + function lpeg.count(str,what) -- replaces string.count + if type(what) == "string" then + local p = cache[what] + if not p then + p = Cs((P(what)/" " + nany)^0) + cache[p] = p + end + return #match(p,str) + else -- 4 times slower but still faster than / function + return #match(Cs((P(what)/" " + nany)^0),str) + end + end + +end + +local patterns_escapes = { -- also defines in l-string + ["%"] = "%%", + ["."] = "%.", + ["+"] = "%+", ["-"] = "%-", ["*"] = "%*", + ["["] = "%[", ["]"] = "%]", + ["("] = "%)", [")"] = "%)", + -- ["{"] = "%{", ["}"] = "%}" + -- ["^"] = "%^", ["$"] = "%$", +} + +local simple_escapes = { -- also defines in l-string + ["-"] = "%-", + ["."] = "%.", + ["?"] = ".", + ["*"] = ".*", +} + +local p = Cs((S("-.+*%()[]") / patterns_escapes + anything)^0) +local s = Cs((S("-.+*%()[]") / simple_escapes + anything)^0) + +function string.escapedpattern(str,simple) + return match(simple and s or p,str) +end + +-- utf extensies + +lpeg.UP = lpeg.P + +if utfcharacters then + + function lpeg.US(str) + local p + for uc in utfcharacters(str) do + if p then + p = p + P(uc) + else + p = P(uc) + end + end + return p + end + + +elseif utfgmatch then + + function lpeg.US(str) + local p + for uc in utfgmatch(str,".") do + if p then + p = p + P(uc) + else + p = P(uc) + end + end + return p + end + +else + + function lpeg.US(str) + local p + local f = function(uc) + if p then + p = p + P(uc) + else + p = P(uc) + end + end + match((utf8char/f)^0,str) + return p + end + +end + +local range = Cs(utf8byte) * (Cs(utf8byte) + Cc(false)) + +local utfchar = unicode and unicode.utf8 and unicode.utf8.char + +function lpeg.UR(str,more) + local first, last + if type(str) == "number" then + first = str + last = more or first + else + first, last = match(range,str) + if not last then + return P(str) + end + end + if first == last then + return P(str) + elseif utfchar and last - first < 8 then -- a somewhat arbitrary criterium + local p + for i=first,last do + if p then + p = p + P(utfchar(i)) + else + p = P(utfchar(i)) + end + end + return p -- nil when invalid range + else + local f = function(b) + return b >= first and b <= last + end + return utf8byte / f -- nil when invalid range + end +end + +--~ lpeg.print(lpeg.R("ab","cd","gh")) +--~ lpeg.print(lpeg.P("a","b","c")) +--~ lpeg.print(lpeg.S("a","b","c")) + +--~ print(lpeg.count("äáàa",lpeg.P("á") + lpeg.P("à"))) +--~ print(lpeg.count("äáàa",lpeg.UP("áà"))) +--~ print(lpeg.count("äáàa",lpeg.US("àá"))) +--~ print(lpeg.count("äáàa",lpeg.UR("aá"))) +--~ print(lpeg.count("äáàa",lpeg.UR("àá"))) +--~ print(lpeg.count("äáàa",lpeg.UR(0x0000,0xFFFF))) + +function lpeg.oneof(list,...) -- lpeg.oneof("elseif","else","if","then") + if type(list) ~= "table" then + list = { list, ... } + end + -- sort(list) -- longest match first + local p = P(list[1]) + for l=2,#list do + p = p + P(list[l]) + end + return p +end + +function lpeg.is_lpeg(p) + return p and lpegtype(p) == "pattern" +end + +-- For the moment here, but it might move to utilities: + +local sort, fastcopy, sortedpairs = table.sort, table.fastcopy, table.sortedpairs -- dependency! + +function lpeg.append(list,pp) + local p = pp + if #list > 0 then + list = fastcopy(list) + sort(list) + for l=1,#list do + if p then + p = P(list[l]) + p + else + p = P(list[l]) + end + end + else + for k, v in sortedpairs(list) do + if p then + p = P(k)/v + p + else + p = P(k)/v + end + end + end + return p +end + +--~ Cf(Ct("") * (Cg(C(...) * "=" * Cs(...)))^0, rawset) + +end -- closure + +do -- begin closure to overcome local limits and interference + +if not modules then modules = { } end modules ['l-boolean'] = { + version = 1.001, + comment = "companion to luat-lib.mkiv", + author = "Hans Hagen, PRAGMA-ADE, Hasselt NL", + copyright = "PRAGMA ADE / ConTeXt Development Team", + license = "see context related readme files" +} + +local type, tonumber = type, tonumber + +boolean = boolean or { } +local boolean = boolean + +function boolean.tonumber(b) + if b then return 1 else return 0 end -- test and return or return +end + +function toboolean(str,tolerant) + if tolerant then + local tstr = type(str) + if tstr == "string" then + return str == "true" or str == "yes" or str == "on" or str == "1" or str == "t" + elseif tstr == "number" then + return tonumber(str) ~= 0 + elseif tstr == "nil" then + return false + else + return str + end + elseif str == "true" then + return true + elseif str == "false" then + return false + else + return str + end +end + +string.toboolean = toboolean + +function string.is_boolean(str,default) + if type(str) == "string" then + if str == "true" or str == "yes" or str == "on" or str == "t" then + return true + elseif str == "false" or str == "no" or str == "off" or str == "f" then + return false + end + end + return default +end + +end -- closure + +do -- begin closure to overcome local limits and interference + +if not modules then modules = { } end modules ['l-math'] = { + version = 1.001, + comment = "companion to luat-lib.mkiv", + author = "Hans Hagen, PRAGMA-ADE, Hasselt NL", + copyright = "PRAGMA ADE / ConTeXt Development Team", + license = "see context related readme files" +} + +local floor, sin, cos, tan = math.floor, math.sin, math.cos, math.tan + +if not math.round then + function math.round(x) return floor(x + 0.5) end +end + +if not math.div then + function math.div(n,m) return floor(n/m) end +end + +if not math.mod then + function math.mod(n,m) return n % m end +end + +local pipi = 2*math.pi/360 + +if not math.sind then + function math.sind(d) return sin(d*pipi) end + function math.cosd(d) return cos(d*pipi) end + function math.tand(d) return tan(d*pipi) end +end + +if not math.odd then + function math.odd (n) return n % 2 == 0 end + function math.even(n) return n % 2 ~= 0 end +end + end -- closure do -- begin closure to overcome local limits and interference @@ -2958,6 +3021,7 @@ local next, tostring, rawget = next, tostring, rawget local format, match, lower, gsub = string.format, string.match, string.lower, string.gsub local utfbyte = utf.byte local sort, insert, concat, sortedkeys, serialize, fastcopy = table.sort, table.insert, table.concat, table.sortedkeys, table.serialize, table.fastcopy +local derivetable = table.derive local trace_defining = false trackers.register("fonts.defining", function(v) trace_defining = v end) local trace_scaling = false trackers.register("fonts.scaling" , function(v) trace_scaling = v end) @@ -3139,10 +3203,9 @@ function constructors.scale(tfmdata,specification) local mathparameters = tfmdata.mathparameters or { } -- local targetcharacters = { } - local targetdescriptions = table.derive(descriptions) - local targetparameters = table.derive(parameters) - -- local targetmathparameters = table.fastcopy(mathparameters) -- happens elsewhere - local targetproperties = table.derive(properties) + local targetdescriptions = derivetable(descriptions) + local targetparameters = derivetable(parameters) + local targetproperties = derivetable(properties) local targetgoodies = goodies -- we need to loop so no metatable target.characters = targetcharacters target.descriptions = targetdescriptions @@ -4827,7 +4890,7 @@ local getn = table.getn local lpegmatch = lpeg.match local reversed, concat, remove = table.reversed, table.concat, table.remove local ioflush = io.flush -local fastcopy, tohash = table.fastcopy, table.tohash +local fastcopy, tohash, derivetable = table.fastcopy, table.tohash, table.derive local allocate = utilities.storage.allocate local registertracker = trackers.register @@ -6476,9 +6539,9 @@ local function copytotfm(data,cache_id) if data then local metadata = data.metadata local resources = data.resources - local properties = table.derive(data.properties) - local descriptions = table.derive(data.descriptions) - local goodies = table.derive(data.goodies) + local properties = derivetable(data.properties) + local descriptions = derivetable(data.descriptions) + local goodies = derivetable(data.goodies) local characters = { } local parameters = { } local mathparameters = { } |