breakcmd() now uses LPeg patterns. commands with up to two optional and two mandatory arguments are now processed by \MkArbBreak{}

1 files changed, 31 insertions, 66 deletions

diff --git a/arabluatex.lua b/arabluatex.lua
index e83206f..7db1cc8 100644
--- a/arabluatex.lua
+++ b/arabluatex.lua
@@ -27,58 +27,13 @@ require("arabluatex_fullvoc")
 require("arabluatex_novoc")
 require("arabluatex_trans")
 
--- arabluatex now uses lpeg
-local original_gsub = string.gsub
-function string.gsub(s, patt, repl)
-  if lpeg.type(patt) ~= "pattern" then
-    -- If patt isn't an LPEG pattern, revert to the normal gsub
-    return original_gsub(s, patt, repl)
-  else
-    -- Standardise repl to a function which takes the whole match
-    -- as the first argument, and then subsequent matches (if
-    -- there were any).
-    local typ = type(repl)
-    if typ == "table" then
-      local t = repl
-      repl = function(all, ...)
-        if select('#', ...) == 0 then
-          return t[all]
-        else
-          return t[...]
-        end
-      end
-    elseif typ == "string" then
-      local s = repl
-      repl = function(...)
-        local matches = {...}
-        return s:gsub("%%([0-9%%])", function(c)
-          if c == "%" then
-            return "%"
-          else
-            return matches[tonumber(c) + 1]
-          end
-        end)
-      end
-    elseif typ == "function" then
-      local f = repl
-      repl = function(all, ...)
-        if select('#', ...) == 0 then
-          return f(all)
-        else
-          return f(...)
-        end
-      end
-    else
-      error("Expected table / string / function")
-    end
-    return lpeg.Cs{
-      (lpeg.C(patt) / repl + 1) * lpeg.V(1) + true
-    }:match(s)
-  end
+-- lpeg equivalent for string.gsub()
+local function gsub(s, patt, repl)
+  patt = lpeg.P(patt)
+  patt = lpeg.Cs((patt / repl + 1)^0)
+  return lpeg.match(patt, s)
 end
 
-P = lpeg.P
-
 local function protectarb(str)
    str = string.gsub(str, "(\\arb.?)(%[.-%])(%b{})", "\\@arb%2%3")
    str = string.gsub(str, "(\\begin.?)(%b{})(%b[])", "\\@@begin{%2%3}")
@@ -98,7 +53,14 @@ local function unprotectarb(str)
 return str
 end
 
-brkcmds = {}
+-- 'albrkcmds' is what is set by default.  'brkcmds' is what may be
+-- set in the preamble as argument of \MkArbBreak{}
+local albrkcmds = {
+   "Footnote",
+   "Marginpar",
+   "arbmark"
+}
+local brkcmds = {}
 
 function mkarbbreak(str)
    str = str ..","
@@ -112,34 +74,33 @@ function mkarbbreak(str)
    return brkcmds
 end
 
+-- some basic patterns:
+local dblbkslash = lpeg.Cs("\\")
+local bsqbrackets = lpeg.Cs{ "[" * ((1 - lpeg.S"[]") + lpeg.V(1))^0 * "]" }
+local bcbraces = lpeg.Cs{ "{" * ((1 - lpeg.S"{}") + lpeg.V(1))^0 * "}" }
+local spce = lpeg.P(" ")
+local bsqbracketsii = lpeg.Cs(bsqbrackets^-2)
+local bcbracesii = lpeg.Cs(spce^-1 * bcbraces * spce^-1 * bcbraces^-1)
+
 local function breakcmd(str)
+      for i = 1,#albrkcmds do
+         str = gsub(str, dblbkslash * lpeg.Cs(albrkcmds[i]) * spce^-1 * bsqbracketsii * bcbracesii, "}%1%2%3%4\\arb{")
+      end
    -- user commands
    if next(brkcmds) == nil then
       -- nothing to do
    else
       for i = 1,#brkcmds do
-         str = string.gsub(str, "\\"..brkcmds[i].."%s?(%b[])(%b{})",
-           function(opt, body)
-             opt = string.sub(opt, 2, -2)
-             body = string.sub(body, 2, -2)
-        return string.format("}\\"..brkcmds[i].."[%s]{%s}\\arb{", opt, body)
-         end)
-      end
-      for i = 1,#brkcmds do
-         str = string.gsub(str, "\\"..brkcmds[i].."%s?(%b{})",
-           function(body)
-             body = string.sub(body, 2, -2)
-             return string.format("}\\"..brkcmds[i].."{%s}\\arb{", body)
-         end)
+         str = gsub(str, dblbkslash * lpeg.Cs(brkcmds[i]) * spce^-1 * bsqbracketsii * bcbracesii, "}%1%2%3%4\\arb{")
       end
    end
    -- process \item[], then \item[]
-        str = string.gsub(str, "\\(item.?)(%b[])",
+   str = string.gsub(str, "\\(item.?)(%b[])",
           function(tag, body)
           body = string.sub(body, 2, -2)
           return string.format("}\\item[\\arb{%s}] \\arb{", body)
         end)
-        str = string.gsub(str, "(\\item)(%s+)", "%1{}%2")
+   str = string.gsub(str, "(\\item)(%s+)", "%1{}%2")
    -- \edtext
    str = string.gsub(str, "\\(edtext.-)(%b{})(%b{})",
         function(tag, bodylem, bodyvar)
@@ -166,6 +127,7 @@ local function breakcmd(str)
     bodytext = string.sub(bodytext, 2, -2)
     return string.format("}\\%s{%s}{\\arb{%s}}\\arb{", tag, bodycolor, bodytext)
    end)
+--[[
    -- Footnote
    str = string.gsub(str, "\\(Footnote.-)(%b{})",
                 function(tag, body)
@@ -178,18 +140,21 @@ local function breakcmd(str)
                 body = string.sub(body, 2, -2)
                 return string.format("}\\%s{%s}\\arb{", tag, body)
                 end)
+--]]
    -- Abjad
    str = string.gsub(str, "\\(abjad.-)(%b{})",
         function(tag, body)
         body = string.sub(body, 2, -2)
         return string.format("}\\aemph{\\%s{%s}}\\arb{", tag, body)
         end)
+--[[
    -- Arbmark
    str = string.gsub(str, "\\(arbmark.-)(%b{})",
         function(tag, body)
         body = string.sub(body, 2, -2)
         return string.format("}\\%s{%s}\\arb{", tag, body)
         end)
+--]]
    return str
 end