new lualatex package lua-check-hyphen (20jun12)

git-svn-id: svn://tug.org/texlive/trunk@27227 c570f23f-e606-0410-a88d-b1316a301751

10 files changed, 332 insertions, 0 deletions

diff --git a/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/README.md b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/README.md
new file mode 100644
index 00000000000..20d8244dc83
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/README.md
@@ -0,0 +1,26 @@
+# lua-check-hyphen
+
+## Usage
+
+    \usepackage{lua-check-hyphen}
+    ...
+    \LuaCheckHyphen{mark,whitelist={filea.txt,fileb.txt}}
+
+## What it does
+
+It lists all hyphenated words in the log file as well as in the file with the extension `.uhy`
+
+## How to use
+
+A typical workflow is:
+
+* run final document
+* put the correctly hyphenated words into a text file (format: each word separated with space or on a single line, only whitespace matters as a separator)
+* add that file to the whitelist (as given above)
+* optionally use the option `mark` to make the unknown hyphenated words visible in the PDF file
+
+
+Copyright 2012 Patrick Gundlach (patrick@gundla.ch)  
+Package version: 0.1
+Public repository: https://github.com/pgundlach/lua-check-hyphen  
+Licensed under the MIT license.
diff --git a/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/luacheckhyphenmanual.pdf b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/luacheckhyphenmanual.pdf
new file mode 100644
index 00000000000..aa837960627
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/luacheckhyphenmanual.pdf
diff --git a/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/luacheckhyphenmanual.tex b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/luacheckhyphenmanual.tex
new file mode 100644
index 00000000000..deab3895410
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/luacheckhyphenmanual.tex
@@ -0,0 +1,93 @@
+\documentclass{ltxdockit}
+\usepackage{dtklogos}
+\newcommand\pkgversion{0.1}
+
+\titlepage{%
+  title={The lua-check-hyphen package},
+  subtitle={Checking your hyphenated words},
+  url={https://github.com/pgundlach/lua-check-hyphen},
+  author={Patrick Gundlach},
+  email={patrick@gundla.ch},
+  revision={\pkgversion},
+  date={\today}}
+
+\hypersetup{%
+  pdftitle={The lua-check-hyphen package},
+  pdfsubject={Checking your hyphenated words},
+  pdfauthor={Patrick Gundlach},
+  pdfkeywords={tex, latex, hyphenation}}
+
+
+
+
+\begin{document}
+\printtitlepage
+\tableofcontents
+
+\section{Introduction}
+
+\TeX\ is pretty good at hyphenating words. But a computer algorithm is not perfect, sometimes we wish to manually check all used hyphenations in a document. This package helps you on this task.
+
+\section{Usage}
+
+This package only works with \LuaTeX. To activate it a
+
+\begin{verbatim}
+	\usepackage{lua-check-hyphen}
+\end{verbatim}
+is enough.
+
+When you process your document with \LuaLaTeX, a file with the suffix \verb|.uhy| is created with that contains every hyphenated word. You can check that file for hyphenation errors.
+
+\section{Advanced usage}
+\label{sec:advanced_usage}
+
+With longer documents it becomes tedious checking for the same hyphenated words over and over. Therefore this package allows you to create a whitelist of \emph{accepted hyphenation}. This whitelist is a simple textfile where the words are separated by whitespace and the allowed hyphenation is marked with a dash (-). You can use the output file \texttt{.uhy} as an input for the whitelist file. You load the file in your document with
+
+\begin{verbatim}
+	\LuaCheckHyphen{whitelist=myfile.txt}
+\end{verbatim}
+
+and a sample file looks like this:
+
+\begin{verbatim}
+seren-ity
+morn-ings
+posses-sion
+\end{verbatim}
+
+or
+
+\begin{verbatim}
+seren-ity morn-ings posses-sion
+\end{verbatim}
+
+The format is not important, the entries must be separated by whitespace.
+
+Words in this whitelist won't be reported. \sty{lua-check-hyphen} assumes that these are valid break points.
+
+You can have more than one whitelist file by giving the filenames separated by comma:
+
+\begin{verbatim}
+	\LuaCheckHyphen{whitelist={file1.txt,file2.txt,file3.txt}}
+\end{verbatim}
+
+\section{Visual marker}
+
+You might want to use the PDF viewer to check for incorrectly hyphenated words. To enable visual feedback, just pass the \texttt{mark} option to the \cmd{usepackage} or to the \cmd{LuaCheckHyphen} command:
+
+\begin{verbatim}
+\usepackage{lua-check-hyphen}
+% or:
+\LuaCheckHyphen{mark}
+\end{verbatim}
+
+This marks all non-whitelisted used hyphenation points in the document with a black square (not to be confused with overfull boxes): 
+
+\includegraphics{sample-crop}
+
+\section{Final document}
+
+When you pass the Option \opt{final} to the \cmd{documentclass}, the \cmd{usepackage} or the \cmd{LuaCheckHyphen} command, all processing is disabled.
+
+\end{document}
\ No newline at end of file
diff --git a/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/sample.pdf b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/sample.pdf
new file mode 100644
index 00000000000..406be84ddca
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/sample.pdf
diff --git a/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/sample.tex b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/sample.tex
new file mode 100644
index 00000000000..618fbf7f174
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/lua-check-hyphen/doc/sample.tex
@@ -0,0 +1,10 @@
+\documentclass{article}
+\usepackage{fontspec,nopageno}
+\usepackage[mark]{lua-check-hyphen}
+\begin{document}
+\parindent0.9em
+\hsize 1.3in
+A wonderful serenity has taken possession of my entire soul, like these sweet
+mornings of spring which I enjoy with my whole heart.
+
+\end{document}
\ No newline at end of file
diff --git a/Master/texmf-dist/tex/lualatex/lua-check-hyphen/lua-check-hyphen.lua b/Master/texmf-dist/tex/lualatex/lua-check-hyphen/lua-check-hyphen.lua
new file mode 100644
index 00000000000..9730b4d5eac
--- /dev/null
+++ b/Master/texmf-dist/tex/lualatex/lua-check-hyphen/lua-check-hyphen.lua
@@ -0,0 +1,163 @@
+-- Copyright 2012 Patrick Gundlach, patrick@gundla.ch
+-- Public repository: https://github.com/pgundlach/lua-check-hyphen (issues/pull requests,...)
+-- Version: 0.1
+
+
+-- for debugging purpuse:
+-- function w( ... )
+--   texio.write_nl(string.format(...))
+-- end
+
+local explode = function(s,p)
+   local t = { }
+   for s in unicode.utf8.gmatch(s,p) do
+       if s ~= "" then
+           t[#t+1] = s
+       end
+   end
+   return t
+end
+
+luachekchyphen = {}
+
+
+luachekchyphen.hyphenattr = luatexbase.new_attribute("hyphenattr")
+luachekchyphen.hyphenwords = {}
+luachekchyphen.all_hyphenatedwords = {}
+luachekchyphen.word_whitelist = {}
+luachekchyphen.rectangle = node.new("whatsit","pdf_literal")
+luachekchyphen.rectangle.data = string.format("q 0 0 10 10 re f S Q")
+
+luachekchyphen.deligature = function ( glyph_node )
+  local sln = unicode.utf8
+  local head = glyph_node.components
+  local str = ""
+  while head do
+    if head.id == 37 then
+      if head.components then
+        str = str .. luachekchyphen.deligature(head)
+      else
+        str = str .. sln.char(head.char)
+      end
+    end
+    head = head.next
+  end
+  return str
+end
+
+
+luachekchyphen.collect_discs = function(head)
+  local word_start
+  local word
+  -- this is where we store all the breakpoints
+  local thisbreakpoint
+  local word_with_hyphen
+  local c
+  local hyphencounter = #luachekchyphen.hyphenwords + 1
+  local sln = unicode.utf8
+  while head do
+    if head.id == 0 then
+    elseif head.id == 7 then --disc
+      word_start = head
+      word_end   = head
+      while word_start.prev and word_start.prev.id ~= 10 do
+        word_start = word_start.prev
+      end
+      word = ""
+      c = 0
+      while word_start and word_start.id ~= 10 do
+        if word_start == head then -- disc
+          -- there is a breakpoint after letter c
+          node.set_attribute(head,luachekchyphen.hyphenattr,hyphencounter)
+          thisbreakpoint = c
+        elseif word_start.id == 37 then
+          c = c + 1
+          if word_start.components then
+            word = word .. luachekchyphen.deligature(word_start)
+          elseif sln.match(sln.char(word_start.char),"%a") then
+            word = word .. sln.char(word_start.char)
+          end
+        end
+        word_start = word_start.next
+      end
+      if thisbreakpoint then
+        word_with_hyphen = sln.sub(word,1,thisbreakpoint) .. "-" .. sln.sub(word,thisbreakpoint+1,-1)
+        luachekchyphen.hyphenwords[hyphencounter] = word_with_hyphen
+        hyphencounter = #luachekchyphen.hyphenwords + 1
+      end
+    end
+    head = head.next
+  end
+  return true
+end
+
+luachekchyphen.check_discs = function (head,parent)
+  local c
+  local word
+  local tmp
+  while head do
+    if head.id < 2 then
+      luachekchyphen.check_discs(head.list,head)
+    elseif head.id == 7 and head.next and head.next.id == 10 then -- disc
+      c = node.has_attribute(head,luachekchyphen.hyphenattr)
+      word = luachekchyphen.hyphenwords[c]
+      if luachekchyphen.word_whitelist[word] then
+      	  -- word found, but OK (whitelisted)
+      else
+	      luachekchyphen.all_hyphenatedwords[word] = true
+     	  if luachekchyphen.drawmarks then
+     	  	tmp = node.copy(luachekchyphen.rectangle)
+     	  	node.insert_after(parent,head,tmp)
+     	  end
+	  end
+    end
+    head = head.next
+  end
+  return true
+end
+
+luachekchyphen.listhyphenatedwords = function()
+	if luachekchyphen.final == "true" then
+		return
+	end
+    local unknown_hyphenation_filename = tex.jobname .. ".uhy"
+    local unknown_hyphenation_file = io.open(unknown_hyphenation_filename,"w")
+  
+    texio.write_nl("All words with unknown hyphenation below")
+    for k,v in pairs(luachekchyphen.all_hyphenatedwords) do
+  	    texio.write_nl(k)
+    	unknown_hyphenation_file:write(k .. "\n")
+    end
+    unknown_hyphenation_file:close()
+    texio.write_nl("All words with unknown hyphenation above\n")
+end
+
+luachekchyphen.enable = function()
+	if luachekchyphen.final == "true" then
+		return
+	end
+  	local whitelistfile,err
+  	local filecontents
+  	if luachekchyphen.whitelist then
+  		for i,v in ipairs(string.explode(luachekchyphen.whitelist,",")) do
+  			whitelistfile,err = io.open(v)
+  			if not whitelistfile then
+  				texio.write_nl(err)
+	  		else
+  				filecontents = whitelistfile:read("*a")
+  				for _,entry in ipairs(explode(filecontents,"[^%s]+")) do
+  					luachekchyphen.word_whitelist[entry] = true
+	  			end
+  			end
+  		end
+ 	end
+  	if luachekchyphen.mark == "true" then
+  		luachekchyphen.drawmarks = true
+  	end
+    luatexbase.add_to_callback("pre_linebreak_filter", luachekchyphen.collect_discs,"collect_discs")
+    luatexbase.add_to_callback("post_linebreak_filter",luachekchyphen.check_discs,"check_discs")
+end
+
+return luachekchyphen
+
+-- end of file
diff --git a/Master/texmf-dist/tex/lualatex/lua-check-hyphen/lua-check-hyphen.sty b/Master/texmf-dist/tex/lualatex/lua-check-hyphen/lua-check-hyphen.sty
new file mode 100644
index 00000000000..a4253fb0579
--- /dev/null
+++ b/Master/texmf-dist/tex/lualatex/lua-check-hyphen/lua-check-hyphen.sty
@@ -0,0 +1,38 @@
+% see lua file for copyright information (MIT License)
+
+\def\luachekchyphenpkgdate{2012/06/20}
+\def\luachekchyphenversion{0.1}
+
+
+\RequirePackage{ifluatex}
+\RequirePackage{luatexbase-attr}
+\RequirePackage{luatextra}
+\RequirePackage{keyval}
+
+\DeclareOption{final}{\setkeys{luacheckhyphen}{final}}
+\DeclareOption*{\setkeys{luacheckhyphen}{\CurrentOption}}
+
+\ProvidesPackage{lua-check-hyphen}[\luachekchyphenpkgdate\space v\luachekchyphenversion\space Hyphenation checking for LuaTeX (PGU)]
+
+
+
+\def\luachekchyphendothings{\directlua{luachekchyphen.enable() }}
+
+\define@key{luacheckhyphen}{final}[true]{\directlua{luachekchyphen.final  = "\luatexluaescapestring{#1}"}}
+\define@key{luacheckhyphen}{mark}[true]{\directlua{luachekchyphen.mark     = "\luatexluaescapestring{#1}"}}
+\define@key{luacheckhyphen}{whitelist}{\directlua{luachekchyphen.whitelist = "\luatexluaescapestring{#1}"}}
+
+
+\ifluatex
+  \AtBeginDocument{\luachekchyphendothings}
+  \directlua{luachekchyphen = require('lua-check-hyphen')}
+  \def\LuaCheckHyphen#1{\setkeys{luacheckhyphen}{#1}}
+  \AtEndDocument{\directlua{luachekchyphen.listhyphenatedwords()}}
+\else
+  \def\LuaCheckHyphen#1{}
+  \message{Warning: lua-check-hyphen only works with LuaTeX (LaTeX format for now)}
+\fi
+
+\ProcessOptions
+
+
diff --git a/Master/tlpkg/libexec/ctan2tds b/Master/tlpkg/libexec/ctan2tds
index 332d545c0fe..3a16b19e559 100755
--- a/Master/tlpkg/libexec/ctan2tds
+++ b/Master/tlpkg/libexec/ctan2tds
@@ -1294,6 +1294,7 @@ $standardtex='\.(.bx|cfg|sty|clo|ldf|cls|def|fd|cmap|4ht)$';
  'listings-ext','\.sty',	# not .cfg
  'logic',	'milstd\.tex|' . $standardtex,
  'ltxkeys',	'\.sty|\.clo|\.ldf|\.cls|\.def|\.fd$',  # not cfg
+ 'lua-check-hyphen', '\.lua|' . $standardtex,
  'lua-visual-debug', '\.lua|' . $standardtex,
  'lua2dox',	'NULL',		# .def is lua code
  'lualatex-math', '\.sty',	# not phst-doc.cls
diff --git a/Master/tlpkg/tlpsrc/collection-luatex.tlpsrc b/Master/tlpkg/tlpsrc/collection-luatex.tlpsrc
index ddaf405f81d..5713f8fd6bf 100644
--- a/Master/tlpkg/tlpsrc/collection-luatex.tlpsrc
+++ b/Master/tlpkg/tlpsrc/collection-luatex.tlpsrc
@@ -8,6 +8,7 @@ depend collection-basic
 depend checkcites
 depend chickenize
 depend interpreter
+depend lua-check-hyphen
 depend lua-visual-debug
 depend lua2dox
 depend luabibentry
diff --git a/Master/tlpkg/tlpsrc/lua-check-hyphen.tlpsrc b/Master/tlpkg/tlpsrc/lua-check-hyphen.tlpsrc
new file mode 100644
index 00000000000..e69de29bb2d
--- /dev/null
+++ b/Master/tlpkg/tlpsrc/lua-check-hyphen.tlpsrc