summaryrefslogtreecommitdiff
path: root/Master
diff options
context:
space:
mode:
authorKarl Berry <karl@freefriends.org>2012-12-02 23:27:13 +0000
committerKarl Berry <karl@freefriends.org>2012-12-02 23:27:13 +0000
commitdf141e41c79cc6a9b97f9ac0de97b19054849e9b (patch)
tree7986468b5110a67480f1857af4ee509aed857295 /Master
parent8c4fc53986e6136d225c9c93382bca6607071fea (diff)
new lualatex package spelling (1dec12)
git-svn-id: svn://tug.org/texlive/trunk@28425 c570f23f-e606-0410-a88d-b1316a301751
Diffstat (limited to 'Master')
-rw-r--r--Master/texmf-dist/doc/lualatex/spelling/LICENSE416
-rw-r--r--Master/texmf-dist/doc/lualatex/spelling/README68
-rw-r--r--Master/texmf-dist/doc/lualatex/spelling/spelling-doc.bad5
-rw-r--r--Master/texmf-dist/doc/lualatex/spelling/spelling-doc.pdfbin0 -> 89987 bytes
-rw-r--r--Master/texmf-dist/doc/lualatex/spelling/spelling-doc.tex495
-rwxr-xr-xMaster/texmf-dist/scripts/spelling/spelling-recurse.lua110
-rwxr-xr-xMaster/texmf-dist/scripts/spelling/spelling-stage-1.lua122
-rwxr-xr-xMaster/texmf-dist/scripts/spelling/spelling-stage-2.lua551
-rwxr-xr-xMaster/texmf-dist/scripts/spelling/spelling-stage-3.lua305
-rwxr-xr-xMaster/texmf-dist/scripts/spelling/spelling-stage-4.lua223
-rwxr-xr-xMaster/texmf-dist/scripts/spelling/spelling.lua163
-rw-r--r--Master/texmf-dist/tex/lualatex/spelling/spelling.sty140
-rwxr-xr-xMaster/tlpkg/bin/tlpkg-ctan-check4
-rwxr-xr-xMaster/tlpkg/libexec/ctan2tds1
-rw-r--r--Master/tlpkg/tlpsrc/collection-luatex.tlpsrc1
-rw-r--r--Master/tlpkg/tlpsrc/spelling.tlpsrc0
16 files changed, 2603 insertions, 1 deletions
diff --git a/Master/texmf-dist/doc/lualatex/spelling/LICENSE b/Master/texmf-dist/doc/lualatex/spelling/LICENSE
new file mode 100644
index 00000000000..22443139013
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/spelling/LICENSE
@@ -0,0 +1,416 @@
+The LaTeX Project Public License
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+
+LPPL Version 1.3c 2008-05-04
+
+Copyright 1999 2002-2008 LaTeX3 Project
+ Everyone is allowed to distribute verbatim copies of this
+ license document, but modification of it is not allowed.
+
+
+PREAMBLE
+========
+
+The LaTeX Project Public License (LPPL) is the primary license under
+which the LaTeX kernel and the base LaTeX packages are distributed.
+
+You may use this license for any work of which you hold the copyright
+and which you wish to distribute. This license may be particularly
+suitable if your work is TeX-related (such as a LaTeX package), but
+it is written in such a way that you can use it even if your work is
+unrelated to TeX.
+
+The section `WHETHER AND HOW TO DISTRIBUTE WORKS UNDER THIS LICENSE',
+below, gives instructions, examples, and recommendations for authors
+who are considering distributing their works under this license.
+
+This license gives conditions under which a work may be distributed
+and modified, as well as conditions under which modified versions of
+that work may be distributed.
+
+We, the LaTeX3 Project, believe that the conditions below give you
+the freedom to make and distribute modified versions of your work
+that conform with whatever technical specifications you wish while
+maintaining the availability, integrity, and reliability of
+that work. If you do not see how to achieve your goal while
+meeting these conditions, then read the document `cfgguide.tex'
+and `modguide.tex' in the base LaTeX distribution for suggestions.
+
+
+DEFINITIONS
+===========
+
+In this license document the following terms are used:
+
+ `Work'
+ Any work being distributed under this License.
+
+ `Derived Work'
+ Any work that under any applicable law is derived from the Work.
+
+ `Modification'
+ Any procedure that produces a Derived Work under any applicable
+ law -- for example, the production of a file containing an
+ original file associated with the Work or a significant portion of
+ such a file, either verbatim or with modifications and/or
+ translated into another language.
+
+ `Modify'
+ To apply any procedure that produces a Derived Work under any
+ applicable law.
+
+ `Distribution'
+ Making copies of the Work available from one person to another, in
+ whole or in part. Distribution includes (but is not limited to)
+ making any electronic components of the Work accessible by
+ file transfer protocols such as FTP or HTTP or by shared file
+ systems such as Sun's Network File System (NFS).
+
+ `Compiled Work'
+ A version of the Work that has been processed into a form where it
+ is directly usable on a computer system. This processing may
+ include using installation facilities provided by the Work,
+ transformations of the Work, copying of components of the Work, or
+ other activities. Note that modification of any installation
+ facilities provided by the Work constitutes modification of the Work.
+
+ `Current Maintainer'
+ A person or persons nominated as such within the Work. If there is
+ no such explicit nomination then it is the `Copyright Holder' under
+ any applicable law.
+
+ `Base Interpreter'
+ A program or process that is normally needed for running or
+ interpreting a part or the whole of the Work.
+
+ A Base Interpreter may depend on external components but these
+ are not considered part of the Base Interpreter provided that each
+ external component clearly identifies itself whenever it is used
+ interactively. Unless explicitly specified when applying the
+ license to the Work, the only applicable Base Interpreter is a
+ `LaTeX-Format' or in the case of files belonging to the
+ `LaTeX-format' a program implementing the `TeX language'.
+
+
+
+CONDITIONS ON DISTRIBUTION AND MODIFICATION
+===========================================
+
+1. Activities other than distribution and/or modification of the Work
+are not covered by this license; they are outside its scope. In
+particular, the act of running the Work is not restricted and no
+requirements are made concerning any offers of support for the Work.
+
+2. You may distribute a complete, unmodified copy of the Work as you
+received it. Distribution of only part of the Work is considered
+modification of the Work, and no right to distribute such a Derived
+Work may be assumed under the terms of this clause.
+
+3. You may distribute a Compiled Work that has been generated from a
+complete, unmodified copy of the Work as distributed under Clause 2
+above, as long as that Compiled Work is distributed in such a way that
+the recipients may install the Compiled Work on their system exactly
+as it would have been installed if they generated a Compiled Work
+directly from the Work.
+
+4. If you are the Current Maintainer of the Work, you may, without
+restriction, modify the Work, thus creating a Derived Work. You may
+also distribute the Derived Work without restriction, including
+Compiled Works generated from the Derived Work. Derived Works
+distributed in this manner by the Current Maintainer are considered to
+be updated versions of the Work.
+
+5. If you are not the Current Maintainer of the Work, you may modify
+your copy of the Work, thus creating a Derived Work based on the Work,
+and compile this Derived Work, thus creating a Compiled Work based on
+the Derived Work.
+
+6. If you are not the Current Maintainer of the Work, you may
+distribute a Derived Work provided the following conditions are met
+for every component of the Work unless that component clearly states
+in the copyright notice that it is exempt from that condition. Only
+the Current Maintainer is allowed to add such statements of exemption
+to a component of the Work.
+
+ a. If a component of this Derived Work can be a direct replacement
+ for a component of the Work when that component is used with the
+ Base Interpreter, then, wherever this component of the Work
+ identifies itself to the user when used interactively with that
+ Base Interpreter, the replacement component of this Derived Work
+ clearly and unambiguously identifies itself as a modified version
+ of this component to the user when used interactively with that
+ Base Interpreter.
+
+ b. Every component of the Derived Work contains prominent notices
+ detailing the nature of the changes to that component, or a
+ prominent reference to another file that is distributed as part
+ of the Derived Work and that contains a complete and accurate log
+ of the changes.
+
+ c. No information in the Derived Work implies that any persons,
+ including (but not limited to) the authors of the original version
+ of the Work, provide any support, including (but not limited to)
+ the reporting and handling of errors, to recipients of the
+ Derived Work unless those persons have stated explicitly that
+ they do provide such support for the Derived Work.
+
+ d. You distribute at least one of the following with the Derived Work:
+
+ 1. A complete, unmodified copy of the Work;
+ if your distribution of a modified component is made by
+ offering access to copy the modified component from a
+ designated place, then offering equivalent access to copy
+ the Work from the same or some similar place meets this
+ condition, even though third parties are not compelled to
+ copy the Work along with the modified component;
+
+ 2. Information that is sufficient to obtain a complete,
+ unmodified copy of the Work.
+
+7. If you are not the Current Maintainer of the Work, you may
+distribute a Compiled Work generated from a Derived Work, as long as
+the Derived Work is distributed to all recipients of the Compiled
+Work, and as long as the conditions of Clause 6, above, are met with
+regard to the Derived Work.
+
+8. The conditions above are not intended to prohibit, and hence do not
+apply to, the modification, by any method, of any component so that it
+becomes identical to an updated version of that component of the Work as
+it is distributed by the Current Maintainer under Clause 4, above.
+
+9. Distribution of the Work or any Derived Work in an alternative
+format, where the Work or that Derived Work (in whole or in part) is
+then produced by applying some process to that format, does not relax or
+nullify any sections of this license as they pertain to the results of
+applying that process.
+
+10. a. A Derived Work may be distributed under a different license
+ provided that license itself honors the conditions listed in
+ Clause 6 above, in regard to the Work, though it does not have
+ to honor the rest of the conditions in this license.
+
+ b. If a Derived Work is distributed under a different license, that
+ Derived Work must provide sufficient documentation as part of
+ itself to allow each recipient of that Derived Work to honor the
+ restrictions in Clause 6 above, concerning changes from the Work.
+
+11. This license places no restrictions on works that are unrelated to
+the Work, nor does this license place any restrictions on aggregating
+such works with the Work by any means.
+
+12. Nothing in this license is intended to, or may be used to, prevent
+complete compliance by all parties with all applicable laws.
+
+
+NO WARRANTY
+===========
+
+There is no warranty for the Work. Except when otherwise stated in
+writing, the Copyright Holder provides the Work `as is', without
+warranty of any kind, either expressed or implied, including, but not
+limited to, the implied warranties of merchantability and fitness for a
+particular purpose. The entire risk as to the quality and performance
+of the Work is with you. Should the Work prove defective, you assume
+the cost of all necessary servicing, repair, or correction.
+
+In no event unless required by applicable law or agreed to in writing
+will The Copyright Holder, or any author named in the components of the
+Work, or any other party who may distribute and/or modify the Work as
+permitted above, be liable to you for damages, including any general,
+special, incidental or consequential damages arising out of any use of
+the Work or out of inability to use the Work (including, but not limited
+to, loss of data, data being rendered inaccurate, or losses sustained by
+anyone as a result of any failure of the Work to operate with any other
+programs), even if the Copyright Holder or said author or said other
+party has been advised of the possibility of such damages.
+
+
+MAINTENANCE OF THE WORK
+=======================
+
+The Work has the status `author-maintained' if the Copyright Holder
+explicitly and prominently states near the primary copyright notice in
+the Work that the Work can only be maintained by the Copyright Holder
+or simply that it is `author-maintained'.
+
+The Work has the status `maintained' if there is a Current Maintainer
+who has indicated in the Work that they are willing to receive error
+reports for the Work (for example, by supplying a valid e-mail
+address). It is not required for the Current Maintainer to acknowledge
+or act upon these error reports.
+
+The Work changes from status `maintained' to `unmaintained' if there
+is no Current Maintainer, or the person stated to be Current
+Maintainer of the work cannot be reached through the indicated means
+of communication for a period of six months, and there are no other
+significant signs of active maintenance.
+
+You can become the Current Maintainer of the Work by agreement with
+any existing Current Maintainer to take over this role.
+
+If the Work is unmaintained, you can become the Current Maintainer of
+the Work through the following steps:
+
+ 1. Make a reasonable attempt to trace the Current Maintainer (and
+ the Copyright Holder, if the two differ) through the means of
+ an Internet or similar search.
+
+ 2. If this search is successful, then enquire whether the Work
+ is still maintained.
+
+ a. If it is being maintained, then ask the Current Maintainer
+ to update their communication data within one month.
+
+ b. If the search is unsuccessful or no action to resume active
+ maintenance is taken by the Current Maintainer, then announce
+ within the pertinent community your intention to take over
+ maintenance. (If the Work is a LaTeX work, this could be
+ done, for example, by posting to comp.text.tex.)
+
+ 3a. If the Current Maintainer is reachable and agrees to pass
+ maintenance of the Work to you, then this takes effect
+ immediately upon announcement.
+
+ b. If the Current Maintainer is not reachable and the Copyright
+ Holder agrees that maintenance of the Work be passed to you,
+ then this takes effect immediately upon announcement.
+
+ 4. If you make an `intention announcement' as described in 2b. above
+ and after three months your intention is challenged neither by
+ the Current Maintainer nor by the Copyright Holder nor by other
+ people, then you may arrange for the Work to be changed so as
+ to name you as the (new) Current Maintainer.
+
+ 5. If the previously unreachable Current Maintainer becomes
+ reachable once more within three months of a change completed
+ under the terms of 3b) or 4), then that Current Maintainer must
+ become or remain the Current Maintainer upon request provided
+ they then update their communication data within one month.
+
+A change in the Current Maintainer does not, of itself, alter the fact
+that the Work is distributed under the LPPL license.
+
+If you become the Current Maintainer of the Work, you should
+immediately provide, within the Work, a prominent and unambiguous
+statement of your status as Current Maintainer. You should also
+announce your new status to the same pertinent community as
+in 2b) above.
+
+
+WHETHER AND HOW TO DISTRIBUTE WORKS UNDER THIS LICENSE
+======================================================
+
+This section contains important instructions, examples, and
+recommendations for authors who are considering distributing their
+works under this license. These authors are addressed as `you' in
+this section.
+
+Choosing This License or Another License
+----------------------------------------
+
+If for any part of your work you want or need to use *distribution*
+conditions that differ significantly from those in this license, then
+do not refer to this license anywhere in your work but, instead,
+distribute your work under a different license. You may use the text
+of this license as a model for your own license, but your license
+should not refer to the LPPL or otherwise give the impression that
+your work is distributed under the LPPL.
+
+The document `modguide.tex' in the base LaTeX distribution explains
+the motivation behind the conditions of this license. It explains,
+for example, why distributing LaTeX under the GNU General Public
+License (GPL) was considered inappropriate. Even if your work is
+unrelated to LaTeX, the discussion in `modguide.tex' may still be
+relevant, and authors intending to distribute their works under any
+license are encouraged to read it.
+
+A Recommendation on Modification Without Distribution
+-----------------------------------------------------
+
+It is wise never to modify a component of the Work, even for your own
+personal use, without also meeting the above conditions for
+distributing the modified component. While you might intend that such
+modifications will never be distributed, often this will happen by
+accident -- you may forget that you have modified that component; or
+it may not occur to you when allowing others to access the modified
+version that you are thus distributing it and violating the conditions
+of this license in ways that could have legal implications and, worse,
+cause problems for the community. It is therefore usually in your
+best interest to keep your copy of the Work identical with the public
+one. Many works provide ways to control the behavior of that work
+without altering any of its licensed components.
+
+How to Use This License
+-----------------------
+
+To use this license, place in each of the components of your work both
+an explicit copyright notice including your name and the year the work
+was authored and/or last substantially modified. Include also a
+statement that the distribution and/or modification of that
+component is constrained by the conditions in this license.
+
+Here is an example of such a notice and statement:
+
+ %% pig.dtx
+ %% Copyright 2005 M. Y. Name
+ %
+ % This work may be distributed and/or modified under the
+ % conditions of the LaTeX Project Public License, either version 1.3
+ % of this license or (at your option) any later version.
+ % The latest version of this license is in
+ % http://www.latex-project.org/lppl.txt
+ % and version 1.3 or later is part of all distributions of LaTeX
+ % version 2005/12/01 or later.
+ %
+ % This work has the LPPL maintenance status `maintained'.
+ %
+ % The Current Maintainer of this work is M. Y. Name.
+ %
+ % This work consists of the files pig.dtx and pig.ins
+ % and the derived file pig.sty.
+
+Given such a notice and statement in a file, the conditions
+given in this license document would apply, with the `Work' referring
+to the three files `pig.dtx', `pig.ins', and `pig.sty' (the last being
+generated from `pig.dtx' using `pig.ins'), the `Base Interpreter'
+referring to any `LaTeX-Format', and both `Copyright Holder' and
+`Current Maintainer' referring to the person `M. Y. Name'.
+
+If you do not want the Maintenance section of LPPL to apply to your
+Work, change `maintained' above into `author-maintained'.
+However, we recommend that you use `maintained', as the Maintenance
+section was added in order to ensure that your Work remains useful to
+the community even when you can no longer maintain and support it
+yourself.
+
+Derived Works That Are Not Replacements
+---------------------------------------
+
+Several clauses of the LPPL specify means to provide reliability and
+stability for the user community. They therefore concern themselves
+with the case that a Derived Work is intended to be used as a
+(compatible or incompatible) replacement of the original Work. If
+this is not the case (e.g., if a few lines of code are reused for a
+completely different task), then clauses 6b and 6d shall not apply.
+
+
+Important Recommendations
+-------------------------
+
+ Defining What Constitutes the Work
+
+ The LPPL requires that distributions of the Work contain all the
+ files of the Work. It is therefore important that you provide a
+ way for the licensee to determine which files constitute the Work.
+ This could, for example, be achieved by explicitly listing all the
+ files of the Work near the copyright notice of each file or by
+ using a line such as:
+
+ % This work consists of all files listed in manifest.txt.
+
+ in that place. In the absence of an unequivocal list it might be
+ impossible for the licensee to determine what is considered by you
+ to comprise the Work and, in such a case, the licensee would be
+ entitled to make reasonable conjectures as to which files comprise
+ the Work.
+
diff --git a/Master/texmf-dist/doc/lualatex/spelling/README b/Master/texmf-dist/doc/lualatex/spelling/README
new file mode 100644
index 00000000000..c6b8a9347a1
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/spelling/README
@@ -0,0 +1,68 @@
+This material is subject to the LaTeX Project Public License. See
+<http://www.latex-project.org/lppl/> for the details of that license.
+
+
+
+### Package information
+
+Package name: spelling
+Summary description: Aid spell-checking LuaTeX documents.
+Version: v0.1
+Date: 2012-11-30
+License: [LPPL v1.3c](http://www.latex-project.org/lppl/lppl-1-3c.html)
+Maintenance status: maintained
+Current maintainer: Stephan Hennig, <sh2d@arcor.de>
+
+
+
+### Description
+
+This package aids spell-checking of TeX documents compiled with the
+LuaTeX engine. It can give visual feedback in PDF output similar to
+WYSIWYG word processors. The package relies on an external
+spell-checker application to check spelling of a text file and to output
+a list of bad spellings. The package should work with most
+spell-checkers, even dumb, TeX-unaware ones.
+
+
+
+### Development
+
+The development repository is currently hosted at
+[GitHub](https://github.com/sh2d/spelling/). Code documentation is in
+[LuaDoc](http://keplerproject.github.com/luadoc/) format and can be
+generated via
+
+ luadoc -d API *.lua
+
+Bugs and a wish list can be found in the
+[issue tracker](https://github.com/sh2d/spelling/issues/).
+Contributions of any kind are warmly welcome!
+
+
+_Happy TeXing!_
+
+
+
+### File list
+
+ LICENSE
+ README
+ spelling.lua
+ spelling.sty
+ spelling-doc.bad
+ spelling-doc.tex
+ spelling-recurse.lua
+ spelling-stage-1.lua
+ spelling-stage-2.lua
+ spelling-stage-3.lua
+ spelling-stage-4.lua
+
+
+
+<!--
+%%% Local Variables:
+%%% coding: utf-8
+%%% mode: markdown
+%%% End:
+-->
diff --git a/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.bad b/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.bad
new file mode 100644
index 00000000000..4904a447e82
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.bad
@@ -0,0 +1,5 @@
+packgae
+Ther
+spellling
+foo’s
+incorect
diff --git a/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.pdf b/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.pdf
new file mode 100644
index 00000000000..ee8c4492c93
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.pdf
Binary files differ
diff --git a/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.tex b/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.tex
new file mode 100644
index 00000000000..8d0d8a00af5
--- /dev/null
+++ b/Master/texmf-dist/doc/lualatex/spelling/spelling-doc.tex
@@ -0,0 +1,495 @@
+%%% spelling-doc.sty
+%%% Copyright 2012 Stephan Hennig
+%%
+%% This work may be distributed and/or modified under the conditions of
+%% the LaTeX Project Public License, either version 1.3 of this license
+%% or (at your option) any later version. The latest version of this
+%% license is in http://www.latex-project.org/lppl.txt
+%% and version 1.3 or later is part of all distributions of LaTeX
+%% version 2005/12/01 or later.
+%%
+%% See file README for more information.
+%%
+\documentclass[11pt]{article}
+\usepackage{fontspec}
+\defaultfontfeatures{Ligatures=TeX}
+\usepackage{multicol}
+\usepackage{listings}
+\lstset{
+ basicstyle=\ttfamily,
+ columns=spaceflexible,
+}
+% Short-cut for non-language code snippets.
+\lstMakeShortInline\|
+% Short-cut for LaTeX code snippets.
+\lstMakeShortInline[
+language={[LaTeX]TeX},
+basicstyle=\ttfamily,
+]°
+\usepackage{xspace}
+\usepackage{array}
+\usepackage{booktabs}
+\usepackage[latin, UKenglish]{babel}
+\usepackage[rgb, x11names]{xcolor}
+\usepackage{hyperref}
+\hypersetup{
+ pdftitle={spelling},
+ pdfauthor={Stephan Hennig},
+ pdfkeywords={spell-checking, spelling, TeX, LuaTeX}
+}
+\hypersetup{
+ english,% For \autoref.
+ pdfstartview={XYZ null null null},% Zoom factor is determined by viewer.
+ colorlinks,
+ linkcolor=RoyalBlue3,
+ urlcolor=Chocolate4,
+ citecolor=DeepPink2
+}
+\usepackage{spelling}
+\spellingreadbad{\jobname.bad}
+\newcommand*{\pkg}{\textsf{spelling}}
+\newcommand*{\acr}[1]{\mbox{\scshape#1}}
+\newcommand*{\descr}[1]{〈\emph{#1}〉}
+\newcommand*{\cmd}[1]{\mbox{\ttfamily\textbackslash#1}}
+\newcommand*{\macro}[1]{\cmd{#1}\marginpar{\cmd{#1}}}
+\newcommand*{\latinphrase}[1]{\foreignlanguage{latin}{\emph{#1}}}
+\newcommand*{\lpcf}{\latinphrase{cf.}\xspace}
+\newcommand*{\lpeg}{\latinphrase{e.\,g.}\xspace}
+\newcommand*{\lpetc}{\latinphrase{etc.}\xspace}
+\newcommand*{\lpie}{\latinphrase{i.\,e.}\xspace}
+\begin{document}
+\author{Stephan Hennig\thanks{sh2d@arcor.de}}
+\title{\pkg\thanks{This document describes the \pkg\ packgae v0.1.}}
+\maketitle
+
+
+\begin{abstract}
+ This package aids spell-checking of \TeX\ documents compiled with the
+ Lua\TeX\ engine. It can give visual feedback in \acr{pdf} output
+ similar to \acr{wysiwyg} word processors. The package relies on an
+ external spell-checker application to check spelling of a text file
+ and to output a list of bad spellings. The package should work with
+ most spell-checkers, even dumb, \TeX-unaware ones.
+
+ \emph{Warning! This package is in a very early state. Everything may
+ change!}
+\end{abstract}
+
+\begin{multicols}{2}
+\small
+% Set toc entries ragged right. Trick taken from tocloft.pdf.
+\makeatletter
+\renewcommand{\@tocrmarg}{2.55em plus1fil}
+\makeatother
+\tableofcontents
+\end{multicols}
+
+
+\section{Introduction}
+\label{sec:intro}
+
+Ther are three main approaches to spell-checking \TeX\ documents:
+
+\begin{enumerate}
+
+\item checking spelling in the |.tex| source file,
+
+\item converting a |.tex| file to another format, for which a proved
+ spell-checking solution exists,
+
+\item checking spelling after a |.tex| file has been processed by \TeX.
+
+\end{enumerate}
+
+All of these approaches have their strengths and weaknesses. This
+package follows the third approach, providing some unique features:
+
+\begin{itemize}
+
+\item When extracting text from typeset \acr{dvi}, \acr{ps} or \acr{pdf}
+ files, hyphenation has to be switched off during the \TeX\ run to
+ avoid lots of false positives being reported by the spell-checker.
+ That is, one doesn't work on the original document.
+
+ In contrast to that, the \pkg\ package works transparently on the
+ original |.tex| source file. Text is extracted \emph{during}
+ typesetting, after Lua\TeX\ has applied its catcode and macro
+ machinery, but before hyphenation takes place.
+
+\item The \pkg\ package can highlight words with known incorrect
+ spelling in \acr{pdf} output, giving visual feedback similar to
+ \acr{wysiwyg} word processors.%
+ \footnote{Currently, only colouring words is implemented.}
+
+\end{itemize}
+
+
+\section{Usage}
+\label{sec:usage}
+
+The \pkg\ package requires the Lua\TeX\ engine. Currently, only the
+\LaTeX\ format is supported. \emph{The package consists of Lua modules
+ that do the actual work. The \LaTeX\ package is effectively a wrapper
+ around the modules' Lua-API. Implementing support for other formats
+ shouldn't be too difficult. Since the author is a \LaTeX-only user,
+ support has to be contributed by, \lpeg, you. By the way, the \LaTeX\
+ package needs some polishing, too. Contributions are welcome!}
+
+
+\subsection{Work-flow}
+\label{sec:work-flow}
+
+The work-flow of the \pkg\ package is as follows:
+
+\begin{enumerate}
+
+\item After the package is loaded in the preamble of a |.tex| source
+ file via °\usepackage{spelling}°, a list of bad spellings is read from
+ a file named \descr{jobname}|.spb|, if that file exists.
+
+\item During the Lua\TeX\ run, text is extracted from pages and all
+ words are checked against the list of bad spellings. Words with a
+ known incorrect spelling are highlighted in \acr{pdf} output.
+
+\item At the end of the Lua\TeX\ run, in addition to the \acr{pdf} file,
+ a text file is written, named \descr{jobname}|.txt|, by default. The
+ text file should contain most of the text of the original document.
+
+\item The text file is then checked by your favourite spell-checker
+ application, \lpeg, Aspell or Hunspell. The spell-checker should be
+ able to write a list of bad spellings to a file. Otherwise, visual
+ feedback in \acr{pdf} output won't work. The file should preferably
+ be named \descr{jobname}|.spb|, but any other file name works just as
+ well.
+
+\item Now, there are two ways to proceed:
+
+ \begin{enumerate}
+
+ \item Visually minded people may just compile their document a second
+ time. This time, file \descr{jobname}|.spb| is read-in again and
+ the words with incorrect spelling found by the spell-checker should
+ now be highlighted in \acr{pdf} output. Checking the \acr{pdf}
+ file, the necessary corrections to the |.tex| source file can be
+ applied.
+
+ \item If you're not interested in visual feedback or if your
+ spell-checker doesn't provide a non-interactive mode, you can as
+ well apply the necessary corrections directly to the |.tex| source
+ file(s), either interactively, during the spell-checker run, or by
+ looking at the final list of bad spellings in an editor (whatever
+ file it was saved to). That way, the benefit of this package is,
+ that spell-checker input has already been processed by Lua\TeX, but
+ contains no hyphenated words.
+
+ \end{enumerate}
+
+\end{enumerate}
+
+
+\subsection{Word lists}
+\label{sec:wordlists}
+
+As described above, if a file \descr{jobname}|.spb| exists, it is loaded
+by the \pkg\ package. The words found in the file are stored in an
+internal list of bad spellings and are later used for highlighting
+spelling mistakes in \acr{pdf} output. Words from additional files can
+be appended to the internal list of bad spellings with the
+\macro{spellingreadbad} command. Argument is a file name. The format
+of a word list file is one word per line. The same word may occur
+multiple times. The file must be in the \acr{utf-8} encoding.
+
+In addition to file \descr{jobname}|.spb|, a second file
+\descr{jobname}|.spg| is read, if that file exists. The words found in
+that file are stored in an internal list of good spellings. Words in
+the Lua\TeX\ document are only considered spelling mistakes if they
+occur in the list of bad spellings, but not in the list of good
+spellings. That is, words in the list of good spellings are never
+highlighted in \acr{pdf} output. The list of good spellings can be used
+to deal with false positives (words incorrectly reported as bad
+spellings by the spell-checker). Words from additional files can be
+appended to the internal list of good spellings with the
+\macro{spellingreadgood} command. Argument is a file name. File format
+is one word per line. The same word may occur multiple times. The file
+must be in the \acr{utf-8} encoding.
+
+Note, most spell-checkers provide means to deal with unknown words via
+additional dictionaries. It is recommended to configure your
+spell-checker to report as few false positives as possible.
+
+
+\subsection{Highlighting spellling mistakes}
+\label{sec:highlight}
+
+\paragraph{Enabling/disabling} Highlighting spelling mistakes (words
+with known incorrect spelling) in \acr{pdf} output can be toggled on and
+off with command \macro{spellinghighlight}. If the argument is |on|,
+highlighting is enabled. For other arguments, highlighting is disabled.
+Highlighting is enabled, by default.
+
+\paragraph{Colour} The colour used for highlighting bad spellings can be
+determined by command \cmd{spellinghighlightcolor}. Argument is a
+colour statement in the \acr{pdf} language. As an example, the colour
+red in the \acr{rgb} colour space is represented by the statement %
+|1 0 0 rg|. In the \acr{cmyk} colour space, a reddish colour is
+represented by |0 1 1 0 k|. Default colour used for highlighting is %
+|1 0 0 rg|, \lpie, red in the \acr{rgb} colour space. \emph{Warning:
+ There's currently no error checking. Make sure, you're applying a
+ valid PDF colour statement!}
+
+
+\subsection{Text output}
+\label{sec:textoutput}
+
+\paragraph{Text file} After loading the \pkg\ package, at the end of the
+Lua\TeX\ run, a text file is written that contains most of the document
+text. The text file is no close text rendering of the typeset document,
+but serves as input for your favourite spell-checker application. It
+contains the document text in a simple format: paragraphs separated by
+blank lines. A paragraph is anything that, during typesetting, starts
+with a |local_par| whatsit node in the node list representing a typeset
+page of the original document, \lpeg, paragraphs in running text,
+footnotes, marginal notes, (in-lined) °\parbox° commands or cells from
+°p°-like table columns \lpetc
+
+Paragraphs consist of words separated by spaces. A word is the textual
+representation of a chain of consecutive nodes of type |glyph|, |disc|
+or |kern|. Boxes are processed transparently. That is, the \pkg\
+package (highly imperfectly) tries to recognise as a single word what in
+typeset output looks like a single word. As an example, the \LaTeX\
+code
+
+\begin{center}
+ \begin{tabular}{c}
+\begin{lstlisting}[language={[LaTeX]TeX}]
+foo\mbox{'s bar}s
+\end{lstlisting}
+ \end{tabular}
+\end{center}
+which is typeset as
+
+\begin{center}
+ foo\mbox{'s bar}s
+\end{center}
+is considered two words \textit{foo's} and \textit{bars}, instead of the
+four words \textit{foo}, \textit{'s}, \textit{bar} and~\textit{s}.%
+\footnote{This document has been compiled with a custom list of bad
+ spellings, which is why the word \emph{foo's} should be highlighted.}
+
+\paragraph{Enabling/disabling} Text output can be toggled on and off
+with command \macro{spellingoutput}. If the argument is |on|, text
+output is enabled. For other arguments, text output is disabled. Text
+output is enabled, by default.
+
+\paragraph{File name} \hspace{0pt plus 5em} Text output file name can be
+configured via command \macro{spellingoutputname}. Argument is the new
+file name. Default text output file name is \descr{jobname}|.txt|.
+
+\paragraph{Line length} In text output, paragraphs can either be broken
+into lines of a fixed length or paragraph can be put on a single line.
+The behaviour can be controlled via command
+\macro{spellingoutputlinelength}. Argument is a number. If the number
+is smaller than~1, paragraphs are put on a single line. For larger
+arguments, the number specifies the maximum line length. Note, lines
+are broken at spaces only. Words longer than maximum line length are
+put on a single line exceeding maximum line length. Default line length
+is~72.
+
+\paragraph{Line ending convention} The end-of-line (\acr{eol}) character
+in text output can be configured via command \macro{spellingoutputeol}.
+Argument is an arbitrary sequence of characters in the \acr{utf-8}
+encoding.
+
+Well, things are a bit more complicated, because in Lua\TeX, as in the
+original \TeX, some characters are treated special. To keep Lua\TeX\
+from messing with our \acr{eol} characters in the input, we need to set
+their category codes accordingly. As an example, to set \acr{eol}
+character to follow \acr{dos} line ending convention (carriage return
+followed by line feed, \TeX\ notation |^^M^^J|), the following code can
+be used:
+
+\begin{lstlisting}[language={[LaTeX]TeX}]
+\begingroup
+\catcode`\^^J=12% make line feed and carriage return
+\catcode`\^^M=12% of category Other
+\spellingoutputeol{^^M^^J}
+\endgroup
+\end{lstlisting}
+%
+For the \acr{unix} line ending convention (a single line feed), just
+leave out |^^M| in the argument to |\spellingoutputeol|.
+
+Default line ending convention depends on the operating system
+determined by Lua\TeX. If |os.type| is either |windows| or |msdos|,
+\acr{dos} line ending convention is used. Otherwise \acr{unix} line
+ending convention is used.
+
+
+\subsection{Text extraction}
+\label{sec:textextraction}
+
+\paragraph{Enabling/disabling} Text extraction can be enabled and
+disabled in the document via command \macro{spellingextract}. If the
+argument is |on|, text extraction is enabled. For other arguments, text
+extraction is disabled. The command should be used in vertical mode,
+\lpie, outside paragraphs. If text extraction is disabled in the
+document preamble, an empty text file is written at the end of the
+Lua\TeX\ run. Text extraction is enabled, by default.
+
+Note, text extraction and visual feedback are orthogonal features. That
+is, if text extraction is disabled for part of a document, \lpeg, a long
+table, words with a known incorrect spelling are still highlighted in
+that part.
+
+
+\subsection{Code point mapping}
+\label{sec:cp-mapping}
+
+As explained in \autoref{sec:textoutput}, the text file written at the
+end of the Lua\TeX\ run is in the \acr{utf-8} encoding. Unicode
+contains a wealth of code points with a special meaning, such as
+ligatures, alternative letters, symbols \lpetc Unfortunately, not all
+spell-checker applications are smart enough to correctly interpret all
+Unicode code points that may occur in a document. For that reason, a
+code point mapping feature has been implemented that allows for mapping
+certain Unicode code points that may appear in a node list to arbitrary
+strings in text output. A typical example is to map ligatures to the
+characters corresponding to their constituting letters. The default
+mappings applied can be found in \autoref{tab:cp-mapping}.
+
+\begin{table}
+ \centering
+
+ \begin{tabular}{>{\ttfamily}l>{\ttfamily}l>{\ttfamily}l}
+ \normalfont Unicode name & \normalfont code point & \normalfont target characters\\
+ \addlinespace
+ \toprule
+ \addlinespace
+
+ LATIN CAPITAL LIGATURE IJ & 0x0132 & IJ\\
+ LATIN SMALL LIGATURE IJ & 0x0133 & ij\\
+ LATIN CAPITAL LIGATURE OE & 0x0152 & OE\\
+ LATIN SMALL LIGATURE OE & 0x0153 & oe\\
+ LATIN SMALL LETTER LONG S & 0x017f & s\\
+ LATIN CAPITAL LETTER SHARP S & 0x1e9e & SS\\
+ LATIN SMALL LIGATURE FF & 0xfb00 & ff\\
+ LATIN SMALL LIGATURE FI & 0xfb01 & fi\\
+ LATIN SMALL LIGATURE FL & 0xfb02 & fl\\
+ LATIN SMALL LIGATURE FFI & 0xfb03 & ffi\\
+ LATIN SMALL LIGATURE FFL & 0xfb04 & ffl\\
+ LATIN SMALL LIGATURE LONG S T & 0xfb05 & st\\
+ LATIN SMALL LIGATURE ST & 0xfb06 & st\\
+ \end{tabular}
+
+ \caption{Default code point mappings.}
+ \label{tab:cp-mapping}
+
+\end{table}
+
+Additional mappings can be declared by command \macro{spellingmapping}.
+This command takes two arguments, a number that refers to the Unicode
+code point, and a sequence of arbitrary characters that is the mapping
+target. The code point number must be in a format that can be parsed by
+Lua. The characters must be in the \acr{utf-8} encoding.
+
+New mappings only have effect on the following document text. The
+command should therefore be used in the document preamble. As an
+example, the character |A| can be mapped to |Z| and \latinphrase{vice
+ versa} with the following code:
+
+\begin{lstlisting}[language={[LaTeX]TeX}]
+\spellingmapping{65}{Z}% A => Z
+\spellingmapping{90}{A}% Z => A
+\end{lstlisting}
+
+Another command \macro{spellingclearallmappings} can be used to remove
+all existing code point mappings.
+
+
+\subsection{Tables}
+\label{sec:tables}
+
+How do tables fit into the simple text file format that has only
+paragraphs and blank lines as described in \autoref{sec:textoutput}?
+What is a paragraph with regards to tables? A whole table? A row? A
+single cell?
+
+By default, only text from cells in °p°(aragraph)-like columns is put on
+their own paragraph, because the corresponding node list branches
+contain a |local_par| whatsit node (\lpcf \autoref{sec:textoutput}).
+The behaviour can be changed with the \macro{spellingtablepar} command.
+This command takes as argument a number. If the argument is~0, the
+behaviour is described as above. If the argument is~1, a blank line is
+inserted before and after every table row (but at most once between
+table rows). If the argument is~2, a blank line is inserted before and
+after every table cell. By default, no blank lines are inserted.
+
+
+\section{Bugs}
+\label{sec:bugs}
+
+Note, this package is in a very early state. Expect bugs! Package
+development is hosted at
+\href{http://github.com/sh2d/spelling/}{\bfseries GitHub}. The full
+list of known bugs and feature requests can be found in the
+\href{http://github.com/sh2d/spelling/issues/}{\bfseries issue tracker}.
+New bugs should be reported there.
+
+The most user-visible issues are listed below:
+
+\begin{itemize}
+
+\item There's no support for the Plain \TeX\ or Con\TeX\ formats other
+ than the \acr{API} of the package's Lua modules, yet
+ (\href{https://github.com/sh2d/spelling/issues/1}{issue~1}).
+
+\item Macros provided by the \LaTeX\ package have very long names. A
+ \emph{key-value} package option interface would be much more
+ user-friendly
+ (\href{https://github.com/sh2d/spelling/issues/2}{issue~2}).
+
+\item There are a couple of issues with text extraction and highlighting
+ incorrect spellings:
+
+ \begin{itemize}
+
+ \item Text in head and foot lines is neither extracted nor highlighted
+ (\href{https://github.com/sh2d/spelling/issues/7}{issue~7}).
+
+ \item Punctuation characters are currently not stripped from words.
+ If the list of bad spellings contains an entry, say,
+ \emph{incorect}, and the text contains that spelling directly
+ followed by a comma, a quotation mark \lpetc, the incorect spelling
+ is not highlighted
+ (\href{https://github.com/sh2d/spelling/issues/8}{issue~8}).
+
+ \item The first word starting right after an |hlist|, \lpeg, the first
+ word within an |\mbox|, is never highlighted. It is extracted and
+ written to the text file, though
+ (\href{https://github.com/sh2d/spelling/issues/6}{issue~6}).
+
+ \item Bad spellings that are hyphenated at a page break are not
+ highlighted
+ (\href{https://github.com/sh2d/spelling/issues/10}{issue~10}).
+
+ \end{itemize}
+
+
+\end{itemize}
+
+Any contributions are warmly welcome!
+
+\bigskip
+\emph{Happy \TeX ing!}
+
+
+\end{document}
+
+
+
+%%% Local Variables:
+%%% mode: latex
+%%% TeX-PDF-mode: t
+%%% TeX-master: t
+%%% coding: utf-8
+%%% End:
diff --git a/Master/texmf-dist/scripts/spelling/spelling-recurse.lua b/Master/texmf-dist/scripts/spelling/spelling-recurse.lua
new file mode 100755
index 00000000000..273614d0e6c
--- /dev/null
+++ b/Master/texmf-dist/scripts/spelling/spelling-recurse.lua
@@ -0,0 +1,110 @@
+--- spelling-recurse.lua
+--- Copyright 2012 Stephan Hennig
+--
+-- This work may be distributed and/or modified under the conditions of
+-- the LaTeX Project Public License, either version 1.3 of this license
+-- or (at your option) any later version. The latest version of this
+-- license is in http://www.latex-project.org/lppl.txt
+-- and version 1.3 or later is part of all distributions of LaTeX
+-- version 2005/12/01 or later.
+--
+-- See file README for more information.
+--
+
+
+--- Helper module for recursing into a node list.
+-- This module provides means to recurse into a node list, calling
+-- user-provided call-back functions upon certain events.
+--
+-- @author Stephan Hennig
+-- @copyright 2012 Stephan Hennig
+-- @release version 0.1
+--
+-- @trick Prevent LuaDoc from looking past here for module description.
+--[[ Trick LuaDoc into entering 'module' mode without using that command.
+module(...)
+--]]
+
+
+-- Module table.
+local M = {}
+
+
+-- Function short-cuts.
+local traverse = node.traverse
+
+
+-- Short-cuts for constants.
+local HLIST = node.id('hlist')
+local VLIST = node.id('vlist')
+
+
+--- Scan a node list and call call-back functions upon certain events.
+-- This function scans a node list. Upon certain events, user-defined
+-- call-back functions are called. Call-back functions have to be
+-- provided in a table. Call-back functions and corresponding events
+-- are:
+--
+-- <dl>
+--
+-- <dt>`vlist_pre_recurse`</dt> <dd>A vlist is about to be recursed
+-- into. Argument is the vlist node.</dd>
+--
+-- <dt>`vlist_post_recurse`</dt> <dd>Recursing into a vlist has been
+-- finished. Argument is the vlist node.</dd>
+--
+-- <dt>`hlist_pre_recurse`</dt> <dd>An hlist is about to be recursed
+-- into. Argument is the hlist node.</dd>
+--
+-- <dt>`hlist_post_recurse`</dt> <dd>Recursing into a hlist has been
+-- finished. Argument is the hlist node.</dd>
+--
+-- <dt>`visit`</dt> <dd>A node of type other that `vlist` and `hlist`
+-- has been found. Arguments are the head node of the current node
+-- (head node of the current branch) and the current node.</dd>
+--
+-- </dl>
+--
+-- If a call-back entry in the table is `nil`, the corresponding event
+-- is ignored.
+--
+-- @param head Node list.
+-- @param cb Table of call-back functions.
+local function recurse_node_list(head, cb)
+ -- Make call-back functions local identifiers.
+ local cb_vlist_pre_recurse = cb.vlist_pre_recurse
+ local cb_vlist_post_recurse = cb.vlist_post_recurse
+ local cb_hlist_pre_recurse = cb.hlist_pre_recurse
+ local cb_hlist_post_recurse = cb.hlist_post_recurse
+ local cb_visit_node = cb.visit_node
+ -- Iterate over nodes in current branch.
+ for n in traverse(head) do
+ local nid = n.id
+ -- Test for vlist node.
+ if nid == VLIST then
+ -- Announce vlist pre-traversal.
+ if cb_vlist_pre_recurse then cb_vlist_pre_recurse(n) end
+ -- Recurse into 'vlist'.
+ recurse_node_list(n.head, cb)
+ -- Announce vlist post-traversal.
+ if cb_vlist_post_recurse then cb_vlist_post_recurse(n) end
+ -- Test for hlist node.
+ elseif nid == HLIST then
+ -- Announce hlist pre-traversal.
+ if cb_hlist_pre_recurse then cb_hlist_pre_recurse(n) end
+ -- Recurse into 'hlist'.
+ recurse_node_list(n.head, cb)
+ -- Announce hlist post-traversal.
+ if cb_hlist_post_recurse then cb_hlist_post_recurse(n) end
+ -- Other nodes.
+ else
+ -- Visit node.
+ if cb_visit_node then cb_visit_node(head, n) end
+ end
+ end
+end
+M.recurse_node_list = recurse_node_list
+
+
+-- Return module table.
+return M
diff --git a/Master/texmf-dist/scripts/spelling/spelling-stage-1.lua b/Master/texmf-dist/scripts/spelling/spelling-stage-1.lua
new file mode 100755
index 00000000000..a36c6fcf6b4
--- /dev/null
+++ b/Master/texmf-dist/scripts/spelling/spelling-stage-1.lua
@@ -0,0 +1,122 @@
+--- spelling-stage-1.lua
+--- Copyright 2012 Stephan Hennig
+--
+-- This work may be distributed and/or modified under the conditions of
+-- the LaTeX Project Public License, either version 1.3 of this license
+-- or (at your option) any later version. The latest version of this
+-- license is in http://www.latex-project.org/lppl.txt
+-- and version 1.3 or later is part of all distributions of LaTeX
+-- version 2005/12/01 or later.
+--
+-- See file README for more information.
+--
+
+
+--- Read lists of bad and good strings.
+--
+-- @author Stephan Hennig
+-- @copyright 2012 Stephan Hennig
+-- @release version 0.1
+--
+-- @trick Prevent LuaDoc from looking past here for module description.
+--[[ Trick LuaDoc into entering 'module' mode without using that command.
+module(...)
+--]]
+
+
+-- Module table.
+local M = {}
+
+
+-- Function short-cuts.
+
+
+-- Declare local variables to store references to resources that are
+-- provided by external code.
+--
+-- Table of known bad strings.
+local __is_bad
+--
+-- Table of known good strings.
+local __is_good
+
+
+--- Set module resources.
+-- Make various resources, that are provided by external code, available
+-- to this module.
+--
+-- @param res Ressource table.
+local function set_resources(res)
+ __is_bad = res.is_bad
+ __is_good = res.is_good
+end
+M.set_resources = set_resources
+
+
+--- Generic function for reading a list of strings from a file.
+-- All strings read from the given file are mapped to the boolean value
+-- `true`. The format of the file is simple: one string per file.
+--
+-- @param fname Name of file containing strings.
+-- @param t Table that maps strings to the value `true`.
+-- @return Number of total and new strings read.
+local function __read_strings(fname, t)
+ local total_c = 0
+ local new_c = 0
+ local f, msg = io.open(fname, 'r')
+ if f then
+ -- Iterate line-wise through file.
+ for l in f:lines() do
+ -- Map string to boolean value `true`.
+ if not t[l] then
+ t[l] = true
+ new_c = new_c + 1
+ end
+ total_c = total_c + 1
+ end
+ else
+ texio.write_nl('package spelling: Warning! Could not open file: ' .. msg)
+ end
+ return total_c, new_c
+end
+
+
+--- Read a list of bad strings from a file.
+-- All strings read from the given file (words with known incorrect
+-- spelling) are mapped to the boolean value `true` in table `__is_bad`.
+--
+-- @param fname Name of file containing bad strings. If an empty string
+-- is provided, strings are read from file `<jobname>.bad`.
+local function read_bad_strings(fname)
+ -- If file name is empty, set default file name.
+ if fname == '' then
+ fname = tex.jobname .. '.bad'
+ end
+ local total, new = __read_strings(fname, __is_bad)
+ texio.write_nl('package spelling: ' .. total .. ' bad strings ('
+ .. new .. ' new) read from file \'' .. fname .. '\'.')
+end
+M.read_bad_strings = read_bad_strings
+
+
+--- Read a list of good strings from a file.
+-- All strings read from the given file (words with known correct
+-- spelling) are mapped to the boolean value `true` in table
+-- `__is_good`.
+--
+-- @param fname Name of file containing good strings. If an empty
+-- string is provided, strings are read from file `<jobname>.good`.
+local function read_good_strings(fname)
+ -- If file name is empty, set default file name.
+ if fname == '' then
+ fname = tex.jobname .. '.good'
+ end
+ local total, new = __read_strings(fname, __is_good)
+ texio.write_nl('package spelling: ' .. total .. ' good strings ('
+ .. new .. ' new) read from file \'' .. fname .. '\'.')
+end
+M.read_good_strings = read_good_strings
+
+
+-- Return module table.
+return M
diff --git a/Master/texmf-dist/scripts/spelling/spelling-stage-2.lua b/Master/texmf-dist/scripts/spelling/spelling-stage-2.lua
new file mode 100755
index 00000000000..e22b40552b1
--- /dev/null
+++ b/Master/texmf-dist/scripts/spelling/spelling-stage-2.lua
@@ -0,0 +1,551 @@
+--- spelling-stage-2.lua
+--- Copyright 2012 Stephan Hennig
+--
+-- This work may be distributed and/or modified under the conditions of
+-- the LaTeX Project Public License, either version 1.3 of this license
+-- or (at your option) any later version. The latest version of this
+-- license is in http://www.latex-project.org/lppl.txt
+-- and version 1.3 or later is part of all distributions of LaTeX
+-- version 2005/12/01 or later.
+--
+-- See file README for more information.
+--
+
+
+--- Tag node lists with word strings before hyphenation takes place.
+-- This module provides means to tag node lists by inserting
+-- user-defined whatsit nodes before and after first and last node
+-- belonging to a chain representing a string in the node list. The
+-- final tag node contains a reference to a string containing the word
+-- string. Tagging is applied before hyphenation takes place.
+--
+-- @author Stephan Hennig
+-- @copyright 2012 Stephan Hennig
+-- @release version 0.1
+--
+-- @trick Prevent LuaDoc from looking past here for module description.
+--[[ Trick LuaDoc into entering 'module' mode without using that command.
+module(...)
+--]]
+
+
+-- Module table.
+local M = {}
+
+
+-- Import helper module.
+local __recurse = require 'spelling-recurse'
+local __recurse_node_list = __recurse.recurse_node_list
+
+
+-- Function short-cuts.
+local tabconcat = table.concat
+local tabinsert = table.insert
+local tabremove = table.remove
+local utf8char = unicode.utf8.char
+local node_new = node.new
+local node_insert_after = node.insert_after
+local node_insert_before = node.insert_before
+
+
+-- Short-cuts for constants.
+local DISC = node.id('disc')
+local GLYPH = node.id('glyph')
+local KERN = node.id('kern')
+local WHATSIT = node.id('whatsit')
+local LOCAL_PAR = node.subtype('local_par')
+local USER_DEFINED = node.subtype('user_defined')
+local PDF_COLORSTACK = node.subtype('pdf_colorstack')
+
+
+-- Declare local variables to store references to resources that are
+-- provided by external code.
+--
+-- Table of known bad spellings.
+local __is_bad
+--
+-- Table of known good spellings.
+local __is_good
+--
+-- ID of user-defined whatsit nodes.
+local __whatsit_uid
+
+
+--- Set module resources.
+-- Make various resources, that are provided by external code, available
+-- to this module.
+--
+-- @param res Ressource table.
+local function set_resources(res)
+ __is_bad = res.is_bad
+ __is_good = res.is_good
+ __whatsit_uid = res.whatsit_uid
+end
+M.set_resources = set_resources
+
+
+--- Module options.
+-- This table contains all module options. User functions to set
+-- options are provided.
+--
+-- @class table
+-- @name __opts
+-- @field hl_color Colour used for highlighting bad spellings in PDF
+-- output.
+local __opts = {
+ hl_color,
+}
+
+
+--- Set colour used for highlighting.
+-- Set colourused for highlighting bad spellings in PDF output.
+--
+-- @param col New colour. This must be a colour statement in PDF format
+-- given as string. As an example, the string `1 0 0 rg` represents a
+-- red colour in the RGB colour space. A similar colour in the CMYK
+-- colour space would be represented by the string '0 1 1 0 k'.
+local function set_highlight_color(col)
+ __opts.hl_color = col
+end
+M.set_highlight_color = set_highlight_color
+
+
+--- Convert a Unicode code point to a regular UTF-8 encoded string.
+-- This function can be used as an `__index` meta method.
+--
+-- @param t original table
+-- @param cp originl key, a Unicode code point
+-- @return UTF-8 encoded string corresponding to the Unicode code point.
+local function __meta_cp2utf8(t, cp)
+ return utf8char(cp)
+end
+
+
+--- Table of Unicode code point mappings.
+-- This table maps Unicode code point to strings. The mappings are used
+-- during text extraction to translate certain Unicode code points to an
+-- arbitrary string instead of the corresponding UTF-8 encoded
+-- character.<br />
+--
+-- As an example, by adding an appropriate entry to this table, the
+-- single Unicode code point U-fb00 (LATIN SMALL LIGATURE FF) can be
+-- resolved into the multi character string 'ff' instead of being
+-- converted to the single character string 'ff' ('&#xfb00;').<br />
+--
+-- Keys are Unicode code points. Values must be strings in the UTF-8
+-- encoding. If a key is not present in this table, the regular UTF-8
+-- character is returned by means of a meta table.<br />
+--
+-- @class table
+-- @name __codepoint_map
+local __codepoint_map = {
+
+ [0x0132] = 'IJ',-- LATIN CAPITAL LIGATURE IJ
+ [0x0133] = 'ij',-- LATIN SMALL LIGATURE IJ
+ [0x0152] = 'OE',-- LATIN CAPITAL LIGATURE OE
+ [0x0153] = 'oe',-- LATIN SMALL LIGATURE OE
+ [0x017f] = 's',-- LATIN SMALL LETTER LONG S
+
+ [0x1e9e] = 'SS',-- LATIN CAPITAL LETTER SHARP S
+
+ [0xfb00] = 'ff',-- LATIN SMALL LIGATURE FF
+ [0xfb01] = 'fi',-- LATIN SMALL LIGATURE FI
+ [0xfb02] = 'fl',-- LATIN SMALL LIGATURE FL
+ [0xfb03] = 'ffi',-- LATIN SMALL LIGATURE FFI
+ [0xfb04] = 'ffl',-- LATIN SMALL LIGATURE FFL
+ [0xfb05] = 'st',-- LATIN SMALL LIGATURE LONG S T
+ [0xfb06] = 'st',-- LATIN SMALL LIGATURE ST
+
+}
+
+
+--- Meta table for code point mapping table.
+--
+-- @class table
+-- @name __meta_codepoint_map
+-- @field __index Index operator.
+local __meta_codepoint_map = {
+ __index = __meta_cp2utf8,
+}
+
+
+-- Set meta table for code point mapping table.
+setmetatable(__codepoint_map, __meta_codepoint_map)
+
+
+--- Clear all code point mappings.
+-- After calling this function, there are no known code point mappings
+-- and no code point mapping takes place during text extraction.
+local function clear_all_mappings()
+ __codepoint_map = {}
+ setmetatable(__codepoint_map, __meta_codepoint_map)
+end
+M.clear_all_mappings = clear_all_mappings
+
+
+--- Manage Unicode code point mappings.
+-- This function can be used to set-up code point mappings. First
+-- argument must be a number, second argument must be a string in the
+-- UTF-8 encoding or `nil`.<br />
+--
+-- If the second argument is a string, after calling this function, the
+-- Unicode code point given as first argument, when found in a node list
+-- during text extraction, is mapped to the string given as second
+-- argument instead of being converted to a UTF-8 encoded character
+-- corresponding to the code point.<br />
+--
+-- If the second argument is `nil`, a mapping for the given code point,
+-- if existing, is deleted.
+--
+-- @param cp A Unicode code point, e.g., 0xfb00 for the code point LATIN
+-- SMALL LIGATURE FF.
+-- @param newt New target string to map the code point to or `nil`.
+-- @return Old target string the code point was mapped to before
+-- (possibly `nil`). If any arguments are invalid, return value is
+-- `false`. Arguments are invalid if code point is not of type `number`
+-- or not in the range 0 to 0x10ffff or if new target string is neither
+-- of type `string` nor `nil`).
+local function set_mapping(cp, newt)
+ -- Prevent from invalid entries in mapping table.
+ if (type(cp) ~= 'number') or
+ (cp < 0) or
+ (cp > 0x10ffff) or
+ ((type(newt) ~= 'string') and (type(newt) ~= 'nil')) then
+ return false
+ end
+ -- Retrieve old mapping.
+ local oldt = rawget(__codepoint_map, cp)
+ -- Set new mapping.
+ __codepoint_map[cp] = newt
+ -- Return old mapping.
+ return oldt
+end
+M.set_mapping = set_mapping
+
+
+-- First and last nodes known to belong to the current word and their
+-- head nodes. These nodes are logged, so that after recognizing the
+-- end of a word, they can be tagged by inserting new user-defined
+-- whatsit nodes before and after them.
+local __curr_word_start_head
+local __curr_word_start
+local __curr_word_end_head
+local __curr_word_end
+
+
+--- Tag the current word in the node list.
+-- Insert tag nodes (user-defined whatsit nodes) into the node list
+-- before and after the first and last nodes belonging to the current
+-- word. The tag marking the start of a word contains as value an empty
+-- string. The tag marking the end of a word contains as value a
+-- reference to the word string.
+--
+-- @param word Word string.
+local function __tag_word(word)
+ -- Check, if start node of current word is a head node. Inserting
+ -- before head nodes needs special attention. This is not yet
+ -- implemented.
+ if (__curr_word_start ~= __curr_word_start_head) then
+ -- Create new start tag node.
+ local start_tag = node_new(WHATSIT, USER_DEFINED)
+ -- Mark whatsit node with module ID, so that we can recognize it
+ -- later.
+ start_tag.user_id = __whatsit_uid
+ -- Value is an empty string.
+ start_tag.type = 115
+ start_tag.value = ''
+ -- Insert start tag before first node belonging to current word.
+ node_insert_before(__curr_word_start_head, __curr_word_start, start_tag)
+ end
+ -- Create new end tag node.
+ local end_tag = node_new(WHATSIT, USER_DEFINED)
+ -- Mark whatsit node with module ID, so that we can recognize it
+ -- later.
+ end_tag.user_id = __whatsit_uid
+ -- Value of end tag is an index (a number).
+ end_tag.type = 115
+ end_tag.value = word
+ -- Insert end tag after last node belonging to current word.
+ node_insert_after(__curr_word_end_head, __curr_word_end, end_tag)
+end
+
+
+--- Highlight bad spelling by colour.
+-- Insert colour whatsits before and after the first and last nodes
+-- known to belong to the current word.
+local function __highlight_by_color()
+ -- Check, if start node of current word is a head node. Inserting
+ -- before head nodes needs special attention. This is not yet
+ -- implemented.
+ if (__curr_word_start ~= __curr_word_start_head) then
+ -- Create pdf_colorstack whatsit nodes.
+ local push = node_new(WHATSIT, PDF_COLORSTACK)
+ local pop = node_new(WHATSIT, PDF_COLORSTACK)
+ push.stack = 0
+ pop.stack = 0
+ push.cmd = 1
+ pop.cmd = 2
+ push.data = __opts.hl_color
+ node_insert_before(__curr_word_start_head, __curr_word_start, push)
+ node_insert_after(__curr_word_end_head, __curr_word_end, pop)
+ end
+end
+
+
+--- Generic function for highlighting bad spellings.
+local function __highlight_bad_word()
+ __highlight_by_color()
+end
+
+
+-- Tagging status.
+local __is_active_tagging
+
+
+-- Highlighting status.
+local __is_active_highlighting
+
+
+--- Data structure that stores the characters of a word string.
+-- The current word data structure is an ordered list (an array) of the
+-- characters of the word. The characters are collected while scanning
+-- a node list. They are concatenated to a single string only after the
+-- end of a word is detected, before inserting the current word into the
+-- current paragraph data structure.
+--
+-- @class table
+-- @name __curr_word
+local __curr_word
+
+
+--- Act upon detection of end of current word string.
+-- If the current word contains visible characters, store the current
+-- word in the current tag.
+local function __finish_current_word()
+ -- Finish a word?
+ if __curr_word then
+ local word = tabconcat(__curr_word)
+ -- Check, if the current word has already been tagged. This is only
+ -- a quick hack.
+ local start_prev = __curr_word_start.prev
+ local end_next = __curr_word_end.next
+ if start_prev and end_next
+ and (start_prev.id == WHATSIT)
+ and (start_prev.subtype == USER_DEFINED)
+ and (start_prev.user_id == __whatsit_uid)
+ and (start_prev.type == 115)
+ and (start_prev.value == '')
+ and (end_next.id == WHATSIT)
+ and (end_next.subtype == USER_DEFINED)
+ and (end_next.user_id == __whatsit_uid)
+ and (end_next.type == 115)
+ and (end_next.value == word) then
+ __curr_word = nil
+ __curr_word_start_head = nil
+ __curr_word_start = nil
+ __curr_word_end_head = nil
+ __curr_word_end = nil
+ return
+ end
+ -- Tag node list with word string.
+ if __is_active_tagging then
+ __tag_word(word)
+ end
+ -- Test for bad spelling.
+ if __is_active_highlighting and __is_bad[word] and not __is_good[word] then
+ __highlight_bad_word()
+ end
+ __curr_word = nil
+ end
+ __curr_word_start_head = nil
+ __curr_word_start = nil
+ __curr_word_end_head = nil
+ __curr_word_end = nil
+end
+
+
+--- Act upon detection of end of current paragraph.
+-- If the current paragraph contains words, store the current paragraph
+-- in the text document.
+local function __finish_current_paragraph()
+ -- Finish current word.
+ __finish_current_word()
+end
+
+
+--- Paragraph management stack.
+-- Stack of boolean flags, that are used for logging the occurence of a
+-- new paragraph within nested vlists.
+local __is_vlist_paragraph
+
+
+--- Paragraph management.
+-- This function puts a new boolean flag onto a stack that is used to
+-- log the occurence of a new paragraph, while recursing into the coming
+-- vlist. After finishing recursing into the vlist, the flag needs to
+-- be removed from the stack. Depending on the flag, the then current
+-- paragraph can be finished.
+local function __vlist_pre_recurse()
+ tabinsert(__is_vlist_paragraph, false)
+end
+
+
+--- Paragraph management.
+-- Remove flag from stack after recursing into a vlist. If necessary,
+-- finish the current paragraph.
+local function __vlist_post_recurse()
+ local p = tabremove(__is_vlist_paragraph)
+ if p then
+ __finish_current_paragraph()
+ end
+end
+
+
+--- Find paragraphs and strings.
+-- While scanning a node list, this call-back function finds nodes
+-- representing the start of a paragraph (local_par whatsit nodes) and
+-- strings (chains of nodes of type glyph, kern, disc).
+--
+-- @param head Head node of current branch.
+-- @param n The current node.
+local function __visit_node(head, n)
+ local nid = n.id
+ -- Test for word string component node.
+ if nid == GLYPH then
+ -- Save first node belonging to current word and its head for later
+ -- reference.
+ if not __curr_word_start then
+ __curr_word_start_head = head
+ __curr_word_start = n
+ end
+ -- Save latest node belonging to current word and its head for later
+ -- reference.
+ __curr_word_end_head = head
+ __curr_word_end = n
+ -- Provide new empty word, if necessary.
+ if not __curr_word then
+ __curr_word = {}
+ end
+ -- Append character to current word string.
+ tabinsert(__curr_word, __codepoint_map[n.char])
+ -- Test for other word string component nodes.
+ elseif (nid == DISC) or (nid == KERN) then
+ -- We're still within the current word string. Do nothing.
+ -- Test for paragraph start.
+ elseif (nid == WHATSIT) and (n.subtype == LOCAL_PAR) then
+ __finish_current_paragraph()
+ __is_vlist_paragraph[#__is_vlist_paragraph] = true
+ else
+ -- End of current word string detected.
+ __finish_current_word()
+ end
+end
+
+
+--- Table of call-back functions for node list recursion: store the
+--- word strings found in a node list.
+-- The call-back functions in this table identify chains of nodes
+-- representing word strings in a node list and stores the strings in
+-- the text document. Local_par whatsit nodes are word boundaries.
+-- Nodes of type `hlist` are recursed into as if they were non-existent.
+-- As an example, the LaTeX input `a\mbox{a b}b` is recognized as two
+-- strings `aa` and `bb`.
+--
+-- @class table
+-- @name __cb_tag_words
+-- @field vlist_pre_recurse Paragraph management.
+-- @field vlist_post_recurse Paragraph management.
+-- @field visit_node Find nodes representing paragraphs and words.
+local __cb_tag_words = {
+
+ vlist_pre_recurse = __vlist_pre_recurse,
+ vlist_post_recurse = __vlist_post_recurse,
+ visit_node = __visit_node,
+
+}
+
+
+--- Process node list according to this stage.
+-- This function recurses into the given node list, extracts all text
+-- and stores it in the text document.
+--
+-- @param head Node list.
+local function __process_node_list(head)
+ __curr_word_start_head = nil
+ __curr_word_start = nil
+ __curr_word_end_head = nil
+ __curr_word_end = nil
+ __recurse_node_list(head, __cb_tag_words)
+ -- Clean-up left-over word and/or paragraph.
+ __finish_current_paragraph()
+end
+
+
+--- Call-back function that processes the node list.
+--
+-- @param head Node list.
+local function __cb_pre_linebreak_filter_pkg_spelling(head)
+ __process_node_list(head)
+ return head
+end
+
+
+--- Start tagging text.
+-- After calling this function, words are tagged in node lists before
+-- hyphenation takes place.
+local function enable_text_tagging()
+ __is_active_tagging = true
+end
+M.enable_text_tagging = enable_text_tagging
+
+
+--- Stop tagging text.
+-- After calling this function, no more word tagging in node lists takes
+-- place.
+local function disable_text_tagging()
+ __is_active_tagging = false
+end
+M.disable_text_tagging = disable_text_tagging
+
+
+--- Start highlighting bad spellings.
+-- After calling this function, bad spellings are highlighted in PDF
+-- output.
+local function enable_word_highlighting()
+ __is_active_highlighting = true
+end
+M.enable_word_highlighting = enable_word_highlighting
+
+
+--- Stop highlighting bad spellings.
+-- After calling this function, no more bad spellings are highlighted in
+-- PDF output.
+local function disable_word_highlighting()
+ __is_active_highlighting = false
+end
+M.disable_word_highlighting = disable_word_highlighting
+
+
+--- Module initialisation.
+--
+local function __init()
+ -- Create empty paragraph management stack.
+ __is_vlist_paragraph = {}
+ -- Remember tagging status.
+ __is_active_tagging = false
+ -- Remember highlighting status.
+ __is_active_highlighting = false
+ -- Set default highlighting colour.
+ set_highlight_color('1 0 0 rg')
+ -- Register call-back: Before TeX breaks a paragraph into lines, tag
+ -- and highlight strings.
+ luatexbase.add_to_callback('pre_linebreak_filter', __cb_pre_linebreak_filter_pkg_spelling, '__cb_pre_linebreak_filter_pkg_spelling')
+end
+
+
+-- Initialize module.
+__init()
+
+
+-- Return module table.
+return M
diff --git a/Master/texmf-dist/scripts/spelling/spelling-stage-3.lua b/Master/texmf-dist/scripts/spelling/spelling-stage-3.lua
new file mode 100755
index 00000000000..d7467abdf0e
--- /dev/null
+++ b/Master/texmf-dist/scripts/spelling/spelling-stage-3.lua
@@ -0,0 +1,305 @@
+--- spelling-stage-3.lua
+--- Copyright 2012 Stephan Hennig
+--
+-- This work may be distributed and/or modified under the conditions of
+-- the LaTeX Project Public License, either version 1.3 of this license
+-- or (at your option) any later version. The latest version of this
+-- license is in http://www.latex-project.org/lppl.txt
+-- and version 1.3 or later is part of all distributions of LaTeX
+-- version 2005/12/01 or later.
+--
+-- See file README for more information.
+--
+
+
+--- Store the text of a LuaTeX document in a text document data
+--- structure.
+-- This module provides means to extract text from a LuaTeX document and
+-- to store it in a text document data structure.
+--
+-- In the text document, words are stored as UTF-8 encoded strings. A
+-- mapping mechanism is provided by which, during word string
+-- recognition, individual code-points, e.g., of glyph nodes, can be
+-- translated to arbitrary UTF-8 strings, e.g., ligatures to single
+-- letters.
+--
+-- @author Stephan Hennig
+-- @copyright 2012 Stephan Hennig
+-- @release version 0.1
+--
+-- @trick Prevent LuaDoc from looking past here for module description.
+--[[ Trick LuaDoc into entering 'module' mode without using that command.
+module(...)
+--]]
+
+
+-- Module table.
+local M = {}
+
+
+-- Import helper module.
+local __recurse = require 'spelling-recurse'
+local __recurse_node_list = __recurse.recurse_node_list
+
+
+-- Function short-cuts.
+local tabinsert = table.insert
+local tabremove = table.remove
+
+
+-- Short-cuts for constants.
+local WHATSIT = node.id('whatsit')
+local LOCAL_PAR = node.subtype('local_par')
+local USER_DEFINED = node.subtype('user_defined')
+
+
+-- Declare local variables to store references to resources that are
+-- provided by external code.
+--
+-- Text document data structure.
+local __text_document
+--
+-- ID of user-defined whatsit nodes.
+local __whatsit_uid
+
+
+--- Set module resources.
+-- Make various resources, that are provided by external code, available
+-- to this module.
+--
+-- @param res Ressource table.
+local function set_resources(res)
+ __text_document = res.text_document
+ __whatsit_uid = res.whatsit_uid
+end
+M.set_resources = set_resources
+
+
+--- Module options.
+-- This table contains all module options. User functions to set
+-- options are provided.
+--
+-- @class table
+-- @name __opts
+-- @field table_par When processing a table, when should paragraphs be
+-- inserted into the text document?<br />
+--
+-- <ul>
+-- <li> 0 - Don't touch tables in any way.</li>
+-- <li> 1 - Insert paragraphs before and after hlists of type
+-- <i>alignment column or row</i>, i.e., before and after
+-- every table row.</li>
+-- <li> 2 - Insert paragraphs before and after hlists of type
+-- <i>alignment cell</i>, i.e., before and after every table
+-- cell.</li>
+-- </ul>
+local __opts = {
+ table_par,
+}
+
+
+--- Set table behaviour.
+-- Determine when paragraphs are inserted within tables.
+--
+-- @param value New value.
+local function set_table_paragraphs(value)
+ __opts.table_par = value
+end
+M.set_table_paragraphs = set_table_paragraphs
+
+
+--- Data structure that stores the word strings found in a node list.
+--
+-- @class table
+-- @name __curr_paragraph
+local __curr_paragraph
+
+
+--- Act upon detection of end of current word string.
+-- If the current word contains visible characters, store the current
+-- word in the current paragraph.
+--
+-- @param n String tag node.
+local function __finish_current_word(n)
+ -- Provide new empty paragraph, if necessary.
+ if not __curr_paragraph then
+ __curr_paragraph = {}
+ end
+ -- Append current string to current paragraph.
+ tabinsert(__curr_paragraph, n.value)
+end
+
+
+--- Act upon detection of end of current paragraph.
+-- If the current paragraph contains words, store the current paragraph
+-- in the text document.
+local function __finish_current_paragraph()
+ -- Finish a paragraph?
+ if __curr_paragraph then
+ -- Append current paragraph to document structure.
+ tabinsert(__text_document, __curr_paragraph)
+ __curr_paragraph = nil
+ end
+end
+
+
+--- Paragraph management stack.
+-- Stack of boolean flags, that are used for logging the occurence of a
+-- new paragraph within nested vlists.
+local __is_vlist_paragraph
+
+
+--- Paragraph management.
+-- This function puts a new boolean flag onto a stack that is used to
+-- log the occurence of a new paragraph, while recursing into the coming
+-- vlist. After finishing recursing into the vlist, the flag needs to
+-- be removed from the stack. Depending on the flag, the then current
+-- paragraph can be finished.
+local function __vlist_pre_recurse()
+ tabinsert(__is_vlist_paragraph, false)
+end
+
+
+--- Paragraph management.
+-- Remove flag from stack after recursing into a vlist. If necessary,
+-- finish the current paragraph.
+local function __vlist_post_recurse()
+ local p = tabremove(__is_vlist_paragraph)
+ if p then
+ __finish_current_paragraph()
+ end
+end
+
+
+--- Handle tables lines and cells.
+-- Start a new paragraph before and after an hlist of subtype `alignment
+-- column or row` or `alignment cell`, depending on option `table_par`.
+--
+-- @param n hlist node.
+local function __handle_table(n)
+ local subtype = n.subtype
+ local table_par = __opts.table_par
+ if (subtype == 4) and (table_par == 1) then
+ __finish_current_paragraph()
+ elseif (subtype == 5) and (table_par == 2) then
+ __finish_current_paragraph()
+ end
+end
+
+
+--- Find paragraphs and strings.
+-- While scanning a node list, this call-back function finds nodes
+-- representing the start of a paragraph (local_par whatsit nodes) and
+-- string tags (user_defined whatsit nodes).
+--
+-- @param head Head node of current branch.
+-- @param n The current node.
+local function __visit_node(head, n)
+ local nid = n.id
+ -- Test for node containing a word string.
+ if nid == WHATSIT then
+ -- Test for word string tag.
+ if (n.subtype == USER_DEFINED) and (n.user_id == __whatsit_uid) then
+ -- End tag?
+ if n.value ~= '' then
+ __finish_current_word(n)
+ end
+ -- Test for paragraph start.
+ elseif n.subtype == LOCAL_PAR then
+ __finish_current_paragraph()
+ __is_vlist_paragraph[#__is_vlist_paragraph] = true
+ end
+ end
+end
+
+
+--- Table of call-back functions for node list recursion: store the
+--- word strings found in a node list.
+-- The call-back functions in this table identify chains of nodes
+-- representing word strings in a node list and stores the strings in
+-- the text document. A new paragraph is started at local_par whatsit
+-- nodes and after finishing a vlist containing a local_par whatsit
+-- node. Nodes of type `hlist` are recursed into as if they were
+-- non-existent. As an example, the LaTeX input `a\mbox{a b}b` is
+-- recognized as two strings `aa` and `bb`.
+--
+-- @class table
+-- @name __cb_store_words
+-- @field vlist_pre_recurse Paragraph management.
+-- @field vlist_post_recurse Paragraph management.
+-- @field hlist_pre_recurse Table management.
+-- @field hlist_post_recurse Table management.
+-- @field visit_node Find nodes representing paragraphs and words.
+local __cb_store_words = {
+
+ vlist_pre_recurse = __vlist_pre_recurse,
+ vlist_post_recurse = __vlist_post_recurse,
+ hlist_pre_recurse = __handle_table,
+ hlist_post_recurse = __handle_table,
+ visit_node = __visit_node,
+
+}
+
+
+--- Process node list according to this stage.
+-- This function recurses into the given node list, finds strings in
+-- tags and stores them in the text document.
+--
+-- @param head Node list.
+local function __process_node_list(head)
+ __recurse_node_list(head, __cb_store_words)
+ -- Clean-up left-over word and/or paragraph.
+ __finish_current_paragraph()
+end
+
+
+-- Call-back status.
+local __is_active_storage
+
+
+--- Call-back function that processes the node list.
+-- <i>This is a global function!</i>
+--
+-- @param head Node list.
+function cb_AtBeginShipout_pkg_spelling(box)
+ if __is_active_storage then
+ __process_node_list(tex.box[box])
+ end
+end
+
+
+--- Start storing text.
+-- After calling this function, text is stored in the text document.
+local function enable_text_storage()
+ __is_active_storage = true
+end
+M.enable_text_storage = enable_text_storage
+
+
+--- Stop storing text.
+-- After calling this function, no more text is stored in the text
+-- document.
+local function disable_text_storage()
+ __is_active_storage = false
+end
+M.disable_text_storage = disable_text_storage
+
+
+--- Module initialisation.
+--
+local function __init()
+ -- Create empty paragraph management stack.
+ __is_vlist_paragraph = {}
+ -- Remember call-back status.
+ __is_active_storage = false
+ -- Set default table paragraph behaviour.
+ set_table_paragraphs(0)
+end
+
+
+-- Initialize module.
+__init()
+
+
+-- Return module table.
+return M
diff --git a/Master/texmf-dist/scripts/spelling/spelling-stage-4.lua b/Master/texmf-dist/scripts/spelling/spelling-stage-4.lua
new file mode 100755
index 00000000000..3850c94f884
--- /dev/null
+++ b/Master/texmf-dist/scripts/spelling/spelling-stage-4.lua
@@ -0,0 +1,223 @@
+--- spelling-stage-4.lua
+--- Copyright 2012 Stephan Hennig
+--
+-- This work may be distributed and/or modified under the conditions of
+-- the LaTeX Project Public License, either version 1.3 of this license
+-- or (at your option) any later version. The latest version of this
+-- license is in http://www.latex-project.org/lppl.txt
+-- and version 1.3 or later is part of all distributions of LaTeX
+-- version 2005/12/01 or later.
+--
+-- See file README for more information.
+--
+
+
+--- At the end of a LuaTeX run, write the text stored in a text document
+--- data structure to a file.
+-- This module provides means to write the text stored in a text
+-- document data structure to a file at the end of a LuaTeX run.
+--
+-- @author Stephan Hennig
+-- @copyright 2012 Stephan Hennig
+-- @release version 0.1
+--
+-- @trick Prevent LuaDoc from looking past here for module description.
+--[[ Trick LuaDoc into entering 'module' mode without using that command.
+module(...)
+--]]
+
+
+-- Module table.
+local M = {}
+
+
+-- Function short-cuts.
+local tabconcat = table.concat
+local utf8len = unicode.utf8.len
+
+
+-- Declare local variables to store references to resources that are
+-- provided by external code.
+--
+-- Text document data structure.
+local __text_document
+
+
+--- Set module resources.
+-- Make various resources, that are provided by external code, available
+-- to this module.
+--
+-- @param res Ressource table.
+local function set_resources(res)
+ __text_document = res.text_document
+end
+M.set_resources = set_resources
+
+
+--- Module options.
+-- This table contains all module options. User functions to set
+-- options are provided.
+--
+-- @class table
+-- @name __opts
+-- @field output_eol End-of-line character in output.
+-- @field output_file_name Output file name.
+-- @field output_line_length Line length in output.
+local __opts = {
+ output_eol,
+ output_file_name,
+ output_line_lenght,
+}
+
+
+--- Set output EOL character.
+-- Text output will be written with the given end-of-line character.
+--
+-- @param eol New output EOL character.
+local function set_output_eol(eol)
+ __opts.output_eol = eol
+end
+M.set_output_eol = set_output_eol
+
+
+--- Set output file name.
+-- Text output will be written to a file with the given name.
+--
+-- @param name New output file name.
+local function set_output_file_name(name)
+ __opts.output_file_name = name
+end
+M.set_output_file_name = set_output_file_name
+
+
+--- Set output line length.
+-- Set the number of columns in text output. Text output will be
+-- wrapped at spaces so that lines don't contain more than the specified
+-- number of characters per line. There's one exception: if a word is
+-- longer than the specified number of characters, the word is put on
+-- its own line and that line will be overfull.
+--
+-- @param cols New line length in output. If the argument is smaller
+-- than 1, lines aren't wrapped, i.e., all text of a paragraph is put on
+-- a single line.
+local function set_output_line_length(cols)
+ __opts.output_line_length = cols
+end
+M.set_output_line_length = set_output_line_length
+
+
+--- Break a paragraph into lines of a fixed length and write the lines
+--- to a file.
+--
+-- @param f A file handle.
+-- @param par A text paragraph (an array of words).
+local function __write_text_paragraph(f, par)
+ local maxlinelength = __opts.output_line_length
+ local eol = __opts.output_eol
+ -- Index of first word on current line. Initialize current line with
+ -- first word of paragraph.
+ local lstart = 1
+ -- Track current line length.
+ local llen = utf8len(par[1])
+ -- Iterate over remaining words in paragraph.
+ for i = 2,#par do
+ local wlen = utf8len(par[i])
+ -- Does word fit onto current line?
+ if (llen + 1 + wlen <= maxlinelength) or (maxlinelength < 1) then
+ -- Append word to current line.
+ llen = llen + 1 + wlen
+ else
+ -- Write the current line up to the preceeding word to file (words
+ -- separated by spaces and with a trailing newline).
+ f:write(tabconcat(par, ' ', lstart, i-1), eol)
+ -- Initialize new current line.
+ lstart = i
+ llen = wlen
+ end
+ end
+ -- Write last line of paragraph.
+ f:write(tabconcat(par, ' ', lstart), eol)
+end
+
+
+--- Write all text stored in the text document to a file.
+--
+local function __write_text_document()
+ -- Open output file.
+ local fname = __opts.output_file_name or (tex.jobname .. '.txt')
+ local f = assert(io.open(fname, 'wb'))
+ local eol = __opts.output_eol
+ -- Iterate through document paragraphs.
+ for _,par in ipairs(__text_document) do
+ -- Separate paragraphs by a blank line.
+ f:write(eol)
+ -- Write paragraph to file.
+ __write_text_paragraph(f, par)
+ -- Delete paragraph from memory.
+ __text_document[_] = nil
+ end
+ -- Close output file.
+ f:close()
+end
+
+
+--- Callback function that writes all document text into a file.
+local function __cb_stopr_pkg_spelling()
+ __write_text_document()
+end
+
+
+-- Call-back status.
+local __is_active_output
+
+
+--- Enable text document output.
+-- Registers call-back `stop_run` to output the text stored in the text
+-- document at the end of the LuaTeX run.
+local function enable_text_output()
+ if not __is_active_output then
+ -- Register call-back: At the end of the LuaTeX run, output all text
+ -- stored in the text document.
+ luatexbase.add_to_callback('stop_run', __write_text_document, '__cb_stop_run_pkg_spelling')
+ __is_active_output = true
+ end
+end
+M.enable_text_output = enable_text_output
+
+
+--- Disable text document output.
+-- De-registers call-back `stop_run`.
+local function disable_text_output()
+ if __is_active_output then
+ -- De-register call-back.
+ luatexbase.remove_from_callback('stop_run', '__cb_stop_run_pkg_spelling')
+ __is_active_output = false
+ end
+end
+M.disable_text_output = disable_text_output
+
+
+--- Module initialisation.
+--
+local function __init()
+ -- Set default output file name.
+ set_output_file_name(nil)
+ -- Set default output line length.
+ set_output_line_length(72)
+ -- Set default output EOL character.
+ if (os.type == 'windows') or (os.type == 'msdos') then
+ set_output_eol('\r\n')
+ else
+ set_output_eol('\n')
+ end
+ -- Remember call-back status.
+ __is_active_output = false
+end
+
+
+-- Initialize module.
+__init()
+
+
+-- Return module table.
+return M
diff --git a/Master/texmf-dist/scripts/spelling/spelling.lua b/Master/texmf-dist/scripts/spelling/spelling.lua
new file mode 100755
index 00000000000..d16688ce0be
--- /dev/null
+++ b/Master/texmf-dist/scripts/spelling/spelling.lua
@@ -0,0 +1,163 @@
+--- spelling.lua
+--- Copyright 2012 Stephan Hennig
+--
+-- This work may be distributed and/or modified under the conditions of
+-- the LaTeX Project Public License, either version 1.3 of this license
+-- or (at your option) any later version. The latest version of this
+-- license is in http://www.latex-project.org/lppl.txt
+-- and version 1.3 or later is part of all distributions of LaTeX
+-- version 2005/12/01 or later.
+--
+-- See file README for more information.
+--
+
+
+--- Global table of modules.
+-- The work of the spelling package can be separated into four
+-- stages:<br />
+--
+-- <dl>
+--
+-- <dt>Stage 1</dt>
+-- <dd><ul>
+-- <li>Load list(s) of bad strings.</li>
+-- <li>Load list(s) of good strings.</li>
+-- </ul></dd>
+--
+-- <dt>Stage 2 (call-back <code>pre_linebreak_filter</code>)</dt>
+-- <dd><ul>
+-- <li>Tag word strings in node lists before paragraph breaking
+-- takes place.</li>
+-- <li>Check spelling of strings.</li>
+-- <li>Highlight strings with known incorrect spelling in PDF
+-- output.</li>
+-- </ul></dd>
+--
+-- <dt>Stage 3 (<code>\AtBeginShipout</code>)</dt>
+-- <dd><ul>
+-- <li>Store all strings found on built page via tag nodes in text
+-- document data structure.</li>
+-- </ul></dd>
+--
+-- <dt>Stage 4 (call-back <code>stop_run</code>)</dt>
+-- <dd><ul>
+-- <li>Output text stored in text document data structure to a
+-- file.</li>
+-- </ul></dd>
+--
+-- </dl>
+--
+-- The code of the spelling package is organized in modules reflecting
+-- these stages. References to modules are made available in a global
+-- table so that module's public functions are accessible from within
+-- external code. Table indices correspond to the stages as shown
+-- above.<br />
+--
+-- <ul>
+-- <li><code>spelling-stage-1.lua : pkg_spelling_stage[1]</code></li>
+-- <li><code>spelling-stage-2.lua : pkg_spelling_stage[2]</code></li>
+-- <li><code>spelling-stage-3.lua : pkg_spelling_stage[3]</code></li>
+-- <li><code>spelling-stage-4.lua : pkg_spelling_stage[4]</code></li>
+-- </ul>
+--
+-- @class table
+-- @name pkg_spelling_stage
+pkg_spelling_stage = {
+
+ -- string list loading
+ [1] = require 'spelling-stage-1',
+ -- node list tagging
+ -- spell-checking
+ -- bad string highlighting
+ [2] = require 'spelling-stage-2',
+ -- text storage
+ [3] = require 'spelling-stage-3',
+ -- text output
+ [4] = require 'spelling-stage-4',
+
+}
+
+
+--- Table of package-wide resources that are shared among several
+--- modules.
+--
+-- @class table
+-- @name res
+--
+-- @field is_bad Table.<br />
+--
+-- This table maps all strings known as bad spellings to the value
+-- `true`.
+--
+-- @field is_good Table.<br />
+--
+-- This table maps all strings known as good spellings to the value
+-- `true`.
+--
+-- @field text_document Table.<br />
+--
+-- Data structure that stores the text of a document. The text document
+-- data structure stores the text of a document. The data structure is
+-- quite simple. A text document is an ordered list (an array) of
+-- paragraphs. A paragraph is an ordered list (an array) of words. A
+-- word is a single UTF-8 encoded string.<br />
+--
+-- During the LuTeX run, node lists are scanned for strings before
+-- hyphenation takes place. The strings found in a node list are stored
+-- in the current paragraph. After finishing scanning a node list, the
+-- current paragraph is inserted into the text document. At the end of
+-- the LuaTeX run, all paragraphs of the text document are broken into
+-- lines of a fixed length and the lines are written to a file.<br />
+--
+-- Here's the rationale of this approach:
+--
+-- <ul>
+--
+-- <li> It reduces file access <i>during</i> the LuaTeX run by delaying
+-- write operations until the end.
+--
+-- <li> It saves space. In Lua, strings are internalized. Since in a
+-- document, the same words are used over and over again, relatively
+-- few strings are actually stored in memory.
+--
+-- <li> It allows for pre-processing the text document before writing it
+-- to a file.
+--
+-- </ul>
+--
+-- @field whatsit_uid Number.<br />
+--
+-- Unique ID for marking user-defined whatsit nodes created by this
+-- package. The ID is generated at run-time. See this <a
+-- href="https://github.com/mpg/luatexbase/issues/8">GitHub issue</a>.
+--
+local res = {
+
+ is_bad,
+ is_good,
+ text_document,
+ whatsit_uid,
+
+}
+
+
+--- Package initialisation.
+--
+local function __init()
+ -- Create resources.
+ res.is_bad = {}
+ res.is_good = {}
+ res.text_document = {}
+ res.whatsit_uid = 163
+ -- Make resources available to modules.
+ pkg_spelling_stage[1].set_resources(res)
+ pkg_spelling_stage[2].set_resources(res)
+ pkg_spelling_stage[3].set_resources(res)
+ pkg_spelling_stage[4].set_resources(res)
+ -- Enable text storage.
+ pkg_spelling_stage[3].enable_text_storage()
+end
+
+
+-- Initialize package.
+__init()
diff --git a/Master/texmf-dist/tex/lualatex/spelling/spelling.sty b/Master/texmf-dist/tex/lualatex/spelling/spelling.sty
new file mode 100644
index 00000000000..c363e53c129
--- /dev/null
+++ b/Master/texmf-dist/tex/lualatex/spelling/spelling.sty
@@ -0,0 +1,140 @@
+%%% spelling.sty
+%%% Copyright 2012 Stephan Hennig
+%%
+%% This work may be distributed and/or modified under the conditions of
+%% the LaTeX Project Public License, either version 1.3 of this license
+%% or (at your option) any later version. The latest version of this
+%% license is in http://www.latex-project.org/lppl.txt
+%% and version 1.3 or later is part of all distributions of LaTeX
+%% version 2005/12/01 or later.
+%%
+%% See file README for more information.
+%%
+\ProvidesPackage{spelling}
+ [2012/11/30 v0.1 Aid spell-checking (SH)]
+\NeedsTeXFormat{LaTeX2e}[1999/12/01]
+% Test for the LuaTeX engine.
+\RequirePackage{ifluatex}
+\ifluatex
+\else
+\PackageError{spelling}{LuaTeX engine required}{You could try with the
+ `lualatex' command.}
+\fi
+\RequirePackage{ifthen}
+\RequirePackage{luatexbase}
+\directlua name {spelling}{dofile('spelling.lua')}
+% Words are extracted after pages have been built. In lack of a proper
+% Lua call-back, we're hooking into shipout from the LaTeX side.
+\RequirePackage{atbegshi}
+\AtBeginShipout{%
+ \directlua name {spelling-atbeginshipout}{cb_AtBeginShipout_pkg_spelling(\the\AtBeginShipoutBox)}%
+}
+% Provide command for reading-in a list of bad spellings.
+\newcommand*{\spellingreadbad}[1]{%
+ \directlua{
+ pkg_spelling_stage[1].read_bad_strings('\luaescapestring{#1}')
+ }%
+}
+% Provide command for reading-in a list of good spellings.
+\newcommand*{\spellingreadgood}[1]{%
+ \directlua{
+ pkg_spelling_stage[1].read_good_strings('\luaescapestring{#1}')
+ }%
+}
+% Provide command for enabling/disabling visual feedback.
+\newcommand*{\spellinghighlight}[1]{%
+ \ifthenelse{\equal{#1}{on}}{%
+ \directlua{
+ pkg_spelling_stage[2].enable_word_highlighting()
+ }%
+ }{%
+ \directlua{
+ pkg_spelling_stage[2].disable_word_highlighting()
+ }%
+ }%
+}
+% Provide command for setting visual feedback colour.
+\newcommand*{\spellinghighlightcolor}[1]{%
+ \directlua{
+ pkg_spelling_stage[2].set_highlight_color('\luaescapestring{#1}')
+ }%
+}
+% Provide command for enabling/disabling text ouput.
+\newcommand*{\spellingoutput}[1]{%
+ \ifthenelse{\equal{#1}{on}}{%
+ \directlua{
+ pkg_spelling_stage[4].enable_text_output()
+ }%
+ }{%
+ \directlua{
+ pkg_spelling_stage[4].disable_text_output()
+ }%
+ }%
+}
+% Provide command for setting text output file name.
+\newcommand*{\spellingoutputname}[1]{%
+ \directlua{
+ pkg_spelling_stage[4].set_output_file_name('\luaescapestring{#1}')
+ }%
+}
+% Provide command for setting text output file line length.
+\newcommand*{\spellingoutputlinelength}[1]{%
+ \directlua{
+ pkg_spelling_stage[4].set_output_line_length('\luaescapestring{#1}')
+ }%
+}
+% Provide command for setting text output EOL character.
+\newcommand*{\spellingoutputeol}[1]{%
+ \directlua{
+ pkg_spelling_stage[4].set_output_eol('\luaescapestring{#1}')
+ }%
+}
+% Provide command for enabling/disabling text extraction.
+\newcommand*{\spellingextract}[1]{%
+ \ifthenelse{\equal{#1}{on}}{%
+ \directlua{
+ pkg_spelling_stage[2].enable_text_tagging()
+ }%
+ }{%
+ \directlua{
+ pkg_spelling_stage[2].disable_text_tagging()
+ }%
+ }%
+}
+% Provide command to declare code point mappings.
+\newcommand*{\spellingmapping}[2]{%
+ \directlua{
+ local r = pkg_spelling_stage[2].set_mapping(\luaescapestring{#1}, '\luaescapestring{#2}')
+ if r == false then
+ texio.write_nl('package spelling: invalid mapping: \luaescapestring{#1} => \luaescapestring{#2}')
+ end
+ }%
+}
+% Provide command to clear all existing code point mappings.
+\newcommand*{\spellingclearallmappings}{%
+ \directlua{
+ pkg_spelling_stage[2].clear_all_mappings()
+ }%
+}
+% Provide command to specify table paragraph behaviour.
+\newcommand*{\spellingtablepar}[1]{%
+ \directlua{
+ pkg_spelling_stage[3].set_table_paragraphs(\luaescapestring{#1})
+ }%
+}
+% Try to read a list of bad spellings from file `\jobname.spb'.
+\IfFileExists{\jobname.spb}{%
+ \spellingreadbad{\jobname.spb}%
+}{%
+}
+% Try to read a list of good spellings from file `\jobname.spg'.
+\IfFileExists{\jobname.spg}{%
+ \spellingreadgood{\jobname.spg}%
+}{%
+}
+% Enable visual feedback.
+\spellinghighlight{on}
+% Enable text ouput at the end of the LuaTeX run.
+\spellingoutput{on}
+% Enable text extraction.
+\spellingextract{on}
diff --git a/Master/tlpkg/bin/tlpkg-ctan-check b/Master/tlpkg/bin/tlpkg-ctan-check
index 6c7f3e4a194..f900a075e7e 100755
--- a/Master/tlpkg/bin/tlpkg-ctan-check
+++ b/Master/tlpkg/bin/tlpkg-ctan-check
@@ -382,7 +382,7 @@ my @TLP_working = qw(
skak skaknew skb skeycommand skeyval skull
slantsc slideshow smalltableof smartdiagram smartref
snapshot songbook sort-by-letters soton soul sourcecodepro sourcesanspro
- spanglish spanish spanish-mx sparklines spie
+ spanglish spanish spanish-mx sparklines spelling spie
sphack splines splitbib splitindex spot spotcolor spreadtab spverbatim
srbook-mem srcltx sseq
stack stage standalone starfont statistik statex statex2 staves
@@ -534,11 +534,13 @@ my @TLP_no_check = (
"pstools", # binary
"psutils", # binary
"ptex", # binary
+ "roex", # GUST
"seetexk", # binary
"synctex", # binary
"t1utils", # binary
"tetex", # our sources
"tex", # binary
+ "tex-virtual-academy-pl",# GUST
"tex4ht", # binary
"texconfig", # our sources
"texdoc", # binary
diff --git a/Master/tlpkg/libexec/ctan2tds b/Master/tlpkg/libexec/ctan2tds
index 7050c63180d..de50089b2ff 100755
--- a/Master/tlpkg/libexec/ctan2tds
+++ b/Master/tlpkg/libexec/ctan2tds
@@ -2238,6 +2238,7 @@ $standardxmt='\.xmt';
'lualatex-math' => '\.lua$',
'luasseq' => '\.lua$',
'mycv' => 'mycv_split_contents\.pl',
+ 'spelling' => '\.lua$',
);
# scripts that should end up in $bindir too.
diff --git a/Master/tlpkg/tlpsrc/collection-luatex.tlpsrc b/Master/tlpkg/tlpsrc/collection-luatex.tlpsrc
index 8c8c7487278..094eb547821 100644
--- a/Master/tlpkg/tlpsrc/collection-luatex.tlpsrc
+++ b/Master/tlpkg/tlpsrc/collection-luatex.tlpsrc
@@ -26,3 +26,4 @@ depend luatextra
depend luaxml
depend odsfile
depend showhyphens
+depend spelling
diff --git a/Master/tlpkg/tlpsrc/spelling.tlpsrc b/Master/tlpkg/tlpsrc/spelling.tlpsrc
new file mode 100644
index 00000000000..e69de29bb2d
--- /dev/null
+++ b/Master/tlpkg/tlpsrc/spelling.tlpsrc