morfologik-svn — SVN notification list

[<daw...@us...>]

Revision: 154
          http://morfologik.svn.sourceforge.net/morfologik/?rev=154&view=rev
Author:   dawidweiss
Date:     2009-03-27 08:14:42 +0000 (Fri, 27 Mar 2009)

Log Message:
-----------
Added FSA version that works for me.

Added Paths:
-----------
    fsa/
    fsa/CHANGES
    fsa/INSTALL
    fsa/Makefile
    fsa/README
    fsa/TROUBLESHOOTING
    fsa/Times
    fsa/accent.cc
    fsa/accent.h
    fsa/accent_main.cc
    fsa/build_fsa.cc
    fsa/build_fsa.h
    fsa/builds_fsa.cc
    fsa/buildu_fsa.cc
    fsa/chkmorph.pl
    fsa/common.cc
    fsa/common.h
    fsa/compile_options.h
    fsa/de.acc
    fsa/de.lang
    fsa/de_morph_data.awk
    fsa/de_morph_infix.awk
    fsa/deguess.awk
    fsa/deguess.pl
    fsa/demorph.awk
    fsa/demorph.pl
    fsa/dump.cc
    fsa/filesel.tcl
    fsa/filesel.tcl.in
    fsa/find_irregular.awk
    fsa/find_irregular.pl
    fsa/fr.acc
    fsa/fr.lang
    fsa/fsa.h
    fsa/fsa_accent.1
    fsa/fsa_accent.exe
    fsa/fsa_build.1
    fsa/fsa_build.exe
    fsa/fsa_dump
    fsa/fsa_guess.1
    fsa/fsa_guess.5
    fsa/fsa_guess.exe
    fsa/fsa_hash.1
    fsa/fsa_hash.exe
    fsa/fsa_morph.1
    fsa/fsa_morph.5
    fsa/fsa_morph.exe
    fsa/fsa_prefix.1
    fsa/fsa_prefix.exe
    fsa/fsa_spell.1
    fsa/fsa_spell.exe
    fsa/fsa_ubuild.1
    fsa/fsa_ubuild.exe
    fsa/fsa_version.h
    fsa/fsa_visual.1
    fsa/fsa_visual.exe
    fsa/gendata.pl
    fsa/guess.cc
    fsa/guess.h
    fsa/guess_main.cc
    fsa/hash.cc
    fsa/hash.h
    fsa/hash_main.cc
    fsa/ie1
    fsa/jaccent-skeleton
    fsa/jguess-skeleton
    fsa/jmorph-skeleton
    fsa/jspell-skeleton
    fsa/jspell.el
    fsa/mkindex.cc
    fsa/mmorph23c.awk
    fsa/mmorph23c.pl
    fsa/morph.cc
    fsa/morph.h
    fsa/morph_data.awk
    fsa/morph_data.pl
    fsa/morph_infix.awk
    fsa/morph_infix.pl
    fsa/morph_main.cc
    fsa/morph_prefix.awk
    fsa/morph_prefix.pl
    fsa/nindex.cc
    fsa/nindex.h
    fsa/nnode.cc
    fsa/nnode.h
    fsa/nstr.cc
    fsa/nstr.h
    fsa/one_word_io.cc
    fsa/out
    fsa/pl.acc
    fsa/pl.chcl
    fsa/pl.lang
    fsa/prefix.cc
    fsa/prefix.h
    fsa/prefix_main.cc
    fsa/prep_atg.awk
    fsa/prep_atg.pl
    fsa/prep_ati.awk
    fsa/prep_ati.pl
    fsa/prep_atl.awk
    fsa/prep_atl.pl
    fsa/prep_atp.awk
    fsa/prep_atp.pl
    fsa/putinplace.pl
    fsa/simplify.pl
    fsa/snode.cc
    fsa/sortatt.pl
    fsa/sortondesc.pl
    fsa/spell.cc
    fsa/spell.h
    fsa/spell_main.cc
    fsa/tclmacq-help.txt
    fsa/tclmacq-lang.txt
    fsa/tclmacq.tcl
    fsa/tclmacq.tcl.in
    fsa/text_io.cc
    fsa/unode.cc
    fsa/unode.h
    fsa/visual_main.cc
    fsa/visualize.cc
    fsa/visualize.h

Property Changed:
----------------
    /


Property changes on: 
___________________________________________________________________
Modified: svn:ignore
   - fsa*

   + 


Added: fsa/CHANGES
===================================================================
--- fsa/CHANGES	                        (rev 0)
+++ fsa/CHANGES	2009-03-27 08:14:42 UTC (rev 154)
@@ -0,0 +1,339 @@
+Version 0.5:
+- Word length in programs using automata increased to 120.
+- Option `clean' provided in Makefile.
+- Option `-v' provided in all programs (gives version details).
+- Sorting of arcs on frequency in optimization phase of automaton creation.
+- Merging two nodes that share the same arc.
+- This file added.
+Version 0.6:
+- Option -v corrected.
+- fr.acc file added to distribution.
+- man pages provided.
+- Compilation options shown in -v in all programs.
+- Option -X provided in fsa_build (makes an index a tergo for word category
+  guessing).
+- New program - fsa_guess - added; it predicts word categories based on
+  word endings.
+- New program - fsa_hash - added; it is used for perfect hashing.
+- Option -i added to programs using automata; it specifies input files.
+- Option -l added to programs using automata; it provides information
+  on language specific features, such as which characters form words,
+  and on case conversions.
+- New module - text_io - provided that processes text files (many words
+  in line, punctuation, etc.), and gives grep-like output.
+Version 0.7:
+- In one_word_io, replacements are now separated by a comma and a space
+  (was: space only); this makes it possible to have a two-word
+  replacement for one word - in other words: now run-on words can be
+  corrected.
+- New compile option RUNON_WORDS added; if turned on, fsa_spell checks
+  for run-on words, i.e. it checks whether inserting a space somewhere
+  inside the word results in two correct words.
+- New compile option CHCLASS added; if turned on, a dedicated file
+  specifies equivalent sequences of characters, so that e.g. `rz' and
+  `z' with a dot above (\.z in TeX) may be only one edit distance unit
+  apart from each other.
+- Emacs interface for spelling correction added; it is an adaptation of
+  ispell.el.
+Version 0.8:
+- New program fsa_morph performs morphological analysis (but not generation).
+- Improved INSTALL guidelines.
+- README more up to date, obsolete data removed, better file list.
+- fsa_guess now guesses lexemes as well (with GUESS_LEXEMES).
+- awk scripts for data preparation.
+Version 0.9:
+- Corrected a bug that caused segment violations when using dictionaries
+  of different sizes, and thus preventing users from using personal
+  dictionaries.
+- fsa_guess now recognizes prefixes with GUESS_PREFIX option.
+- New options -g and -p for fsa_guess to simulate compile options.
+- Words and lines can now be of arbitrary length.
+- Binary search in leaf vectors of the register - this does speed up
+  processing considerably.
+- New compile option for creating an index a tergo: GENERALIZE; it gives
+  smallest automata sizes.
+- New compile option STATISTICS prints... wait for it... some statistics
+  in fsa_build.
+Version 0.10:
+- Corrected a bug in fsa_build that showed up when using PRUNE_ARCS options
+  while compiling an index a tergo.
+- Corrected a bug in fsa_guess that prevented the proper use of -g option.
+  Now -g and -p are independent.
+- Introduced a limit on the number of analyses in fsa_guess.
+- Introduced a limit on the depth of search for suffixes.
+- Corrected a bug in fsa_build man page.
+- Changed definitions of node and arc_node classes, so that the automaton
+  requires less memory than before (by a quarter).
+Version 0.11:
+- Corrected a bug in statistics.
+- Option -r added to the function usage() in fsa_spell.
+- Removed random inline in fsa.h.
+- Updated #ifdefs so that all #ifdef NUMBERS are enclosed in #ifdef FLEXIBLE.
+- Updated Makefile so that it contains description of NUMBERS
+- Corrected a bug in fsa_build that appeared while reading long input lines
+- Updated description of -v option for all programs
+- Corrected the effect of GENERALIZE option
+- Introduced -m option in fsa_guess (prediction of mmorph descriptions
+  of words based on inflected forms). mmorph is a morphology program
+  available from ISSCO, Geneva, http://www.issco.unige.ch/
+  or http://issco-www.unige.ch/
+- fsa_build is now faster.
+- Corrected a bug in PRUNE_ARCS option application.
+Version 0.12:
+- Added a new program: fsa_ubuild.
+Version 0.13:
+- Corrected a bug in fsa_ubuild that excluded some words from the automaton;
+  the bug was in the function already_there().
+- Added new program: fsa_visual.
+- Added an entry for version 0.12 in this file.
+Version 0.14:
+- Corrected a bug in Makefile (introduced in 0.12) - there was no rule
+  for making buildu_fsa.o.
+- Changed declarations in fsa.h to simplify their use.
+- Added perl scripts (awk scripts translated with a2p) for portability.
+- Corrected a bug in fsa_hash: -N did not work correctly.
+- fsa_visual uses manhattan edges.
+- Introduced a new compile option STOPBIT that changes the format
+  version, and makes automata smaller (by nearly 20% for large
+  automata).
+- Included more information on data preparation in README, and on
+  compile options in INSTALL.
+- Compiled the package on Solaris using g++ 2.6.0 to improve
+  portability (thanks Sabine).
+Version 0.15:
+- Corrected a bug in list.empty_list - a memory leak that could be a nuisance
+  with fsa_prefix operationg on large data.
+- Corrected perl scripts.
+- Added new script: morph_infix.{awk,pl}. It prepares data for an automaton
+  to be used with fsa_morph for languages that have prefixes and infixes
+  (like German).
+- Added new compile option: MORPH_INFIX, and two new runtime options for
+  fsa_morph: -I and -P. They make it possible to use data prepared with
+  morph_infix.{awk,pl}.
+- Added new compile option: POOR_MORPH that enables -A option in
+  fsa_morph. That option enables morphological analysis giving only
+  categories, and no base form.
+- Added new script: morph_prefix.{awk.pl}. It prepares data for an automaton
+  to be used with fsa_morph for languages that have prefixes (like Polish).
+Version 0.16:
+- Corrected a memory leak bug in fsa_morph. Now fsa_morph works two orders 
+  of magnitude faster.
+- Corrected manual pages (format errors).
+Version 0.17:
+- Added new compile option for fsa_build and fsa_ubuild:
+  DESCENDING. If on, makes resulting automata smaller, but slower.
+- Improved morph_infix.{awk,pl}.
+- New option -F added to fsa_build and fsa_ubuild. It sets the filler
+  character.
+- New scripts added: prep_ati.{awk,pl}. They prepare data with coded infixes
+  and prefixes for guessing lexemes and categories using fsa_guess.
+- New scripts added: prep_atp.{awk,pl}. They prepare data with coded prefixes
+  for guessing lexemes and categories using fsa_guess.
+- fsa_hash now works correctly with the STOPBIT option.
+- corrected another bug in fsa_hash, which probably lingered there
+  from the beginning, and which made fsa_hash unusable for more than
+  256 words.
+Version 0.18:
+- Added new compile option MORE_COMPR that tries to get more compression
+  when using fsa_build or fsa_ubuild compiled with NEXTBIT.
+Version 0.19:
+- Added new compile option TAILS that enables compression of tails
+  (last transitions) of states.
+- Now MORE_COMPR also tries to squeeze some bytes without NEXTBIT.
+- Corrected a bug in Makefile introduced in 0.18 (one comment too
+  many).
+- Enriched documentation on options in INSTALL.
+- Corrected a bug in fsa_visual that showed up with variable size
+  arcs, i.e. NEXTBIT or TAILS.
+- Added a check on whether -O option should be used in fsa_visual and
+  supply it when necessary even when the user doesn't do that.
+- Added LOOSING_RPM compile option to circumvent a bug in g++ or
+  stdlibc++ found in new rpms (I have to use SuSE now, and I got
+  reports of the same bugs appearing on Red Hat, but no problems on
+  Debian). This does not solve all the problems - if they appear,
+  switch optimization off (remove -O2 from compile options).
+- Added a small program fsa_dump. It is not in Makefile, as it is not
+  tested yet. The source is in dump.cc. The program lists the contents
+  of an automaton as transitions.
+- Added scripts: de_morph_data.{awk,pl} and de_morph_infix.{awk,pl}
+  that produce the 3 column format out of data for fsa_build.
+- Added scripts: demorph.{awk,pl} that produce the 3 column format from
+  the output of fsa_morph.
+Version 0.20
+- Moved mark_inner() to nnode.cc, as it can be used without A_TERGO option.
+- Added an info on producing the contents of an automaton.
+- Fixed display of statistics for NEXTBIT and TAILS
+- Corrected placement of conditionals so that compilation without
+  FLEXIBLE is possible. But do use FLEXIBLE!
+- Added a Tcl script - an interface for fsa_guess as a tool for
+  acquisition of descriptions for a morphological dictionary.
+- Added additional information to -v option of all programs.
+- MORE_COMPR is now *much* faster; actually, it became usable.
+- Added a new perl script chkmorph.pl that removes those predictions
+  made by fsa_guess that cannot produce the required flectional form.
+- Added sortatt.pl perl script that sorts words on their
+  categories/features; it is used by the tcl/tk interface, and it is
+  specially useful when comparing output of two descriptions.
+- added gendata.pl - a perl script that generates data for guessing
+  morphological descriptions in mmorph format of unknown words.
+Version 0.21
+- Corrected some bugs in gendata.pl.
+- Added new compile option - WEIGHTED.
+- Corrected a bug in chkmorph.pl.
+- Corrected a bug in fsa_ubuild (thanks to Christen Blom - Dahl)
+- Totally rewritten GENERALIZE. I hope it provides better results.
+- Added new script sortondesc.pl that sorts morphological descriptions
+  of words so that the most probable come first. A description is
+  judged to be more probable when it appears in more words.
+- Corrected a horrible bug in fsa_spell that manifested itself when
+  the edit distance was set to 0. Program gave arbitrary results.
+- Tcl/Tk interface for lexical acquisition is now much more powerful.
+- Added a new script putinplace.pl that should put descriptions chosen
+  with the Tcl/Tk tool in their appropriate places.
+Version 0.22
+- Corrected conditional compilation so that it is now possible to
+  compile without MORE_COMPR.
+- Added guided correction (right mouse button on description) to the
+  dictionary acquisition tool. The interface is improved.
+- Added statistics to the dictionary acquisition interface.
+Version 0.23
+- In the Tcl/Tk tool, corrected output from mmorph matching so that if
+  all values of a feature are generated, nothing comes out, and when
+  no features are generated, the feature name is deleted from the
+  output.
+- In the Tcl/Tk tool, corrected deleting features using the right mouse
+  button menu.
+- Corrected the script chkmorph.pl so that no phony item appears at
+  the end (there is no dangling comma at the end).
+- Added a new option to ignore the filler character in morphology.
+- Corrected building a weighted guessing automaton. It still needs my
+  attention.
+Version 0.24
+- Corrected dropping one hypothesis in sortondesc.pl script.
+- Corrected a bug in fsa_build that make pointer size calculation invalid
+  (thanks to Gertjan van Noord).
+- Corrected a bug in fsa_spell for distances greater than 1 (thanks to
+  Jiri Andel).
+Version 0.25
+- Included perl and tcl scripts in installation in Makefile.
+- Corrected a bug in fsa_hash: null pointers were followed in word->number
+  conversion (thanks to Martin Povolny).
+Version 0.26
+- Included perl and tcl scripts deleted by mistake from 0.25.
+- Corrected Makefile so that it does not delete perl and tcl scripts
+  in make realclean.
+Version 0.27
+- Corrected a bug in Undo operation in Tcl/Tk interface.
+- Moved customization of tclmacq to Makefile.
+- Adapted tclmacq to new version of Tcl/Tk.
+Version 0.28
+- Corrected a bug in tclmacq (Tcl/Tk interface for dictionary
+  acquisition). Sorting was done before (and not after) expansion of
+  alternatives, which resulted in apparently random order.
+- Added some include directives needed in the most recent compilers
+  (thanks to Dawid Weiss).
+- Corrected setting the FILLER character in builds_fsa.cc (thanks to
+  Dawid Weiss).
+- Corrected usage info for dump.cc (thanks to Dawid Weiss).
+Version 0.29
+- Corrected a bug in simplify.pl (it produced duplicates).
+Version 0.30
+- Corrected a bug in fsa_morph. When one entry was a prefix of another
+  entry, the words were the same, but one annotation was shorter then
+  the other one, the longer entry was not printed (thanks to Gertjan
+  van Noord).
+Version 0.31
+- Corrected the use of one variable so that the package compiles with
+  the old set of options (thanks to Michael Daum).
+Version 0.32
+- The package now compiles under g++ 3.1.1.
+Version 0.33
+- jguess is again produced (thanks to Leonoor van der Beek)
+- Corrected fsa_hash so that words not in the dictionary return -1
+  and not a slash (thanks to Vinay Middha).
+- Added a file TROUBLESHOOTING describing the most common problems people have
+  while trying to install and use the package. As a bonus, I included some
+  solutions as well.
+- Added possibility of morphological analysis of words without tags, i.e.
+  stemming or lemmatization (thanks to Gertjan van Noord). Just remove
+  the last annotation separator (+) and anything that follows it from
+  the output of a script preparing morphological data.
+Version 0.34
+- States can have up to 255 (was: 127) outgoing transitions when
+  compiled with STOPBIT (thanks to Gertjan van Noord).
+- Closed memory leaks in handling of lists (thanks to Martin Povolny).
+Version 0.35
+- Corrected a bug introduced in the previous version (deleting the
+  wrong thing).
+Version 0.36
+- Corrected a bug in dynamic growth of strings read from input in
+  programs that use automata, i.e. not fsa_build nor fsa_ubuild
+  (thanks to Gertjan van Noord).
+Version 0.37
+- Replaced recursion with iteration in some programs, e.g. fsa_hash.
+  fsa_hash is now about 3.5 percent faster.
+Version 0.38
+- Introduced a "-a" runtime option to list the contents of the whole
+  dictionary. The updated glibc++ version I have now treats reading an
+  empty line as an error, so there is no way to learn if an empty line
+  was indeed read.
+- Introduced a new compile option DUMP_ALL to supress printing the
+  leading space in fsa_prefix.
+- Corrected some type errors and vestiges of previous versions when
+  using DEBUG compile option (thanks to Nikolay Ketsaris).
+- Corrected dump.cc to print non-ASCII characters.
+Version 0.39
+- fsa_spell now compiles also without CHCLASS (thanks to Nikolay Ketsaris).
+- Added ios::binary in 3 places for the benefit of those who have the
+  misfortune of being forces to use the virus distribution system from
+  M$.
+- Corrected exit code in fsa_prefix when -a is used (thanks to Marcin
+  Mi\xB3kowski)
+- Corrected a bug in fsa_build and fsa_ubuild when -O was
+  used. Certain states were compressed "too much", i.e. comparison of
+  transitions did not work in part_cmp_nodes due to a modification
+  introduced several versions ago.
+- Changed the script ie1 to make it immediately useful for debugging
+  should anything unpredictable happen.
+- Removed the outrageously outdated file ToDo.
+Version 0.40
+- Corrected a bug in the initialization of the H_matrix in fsa_spell
+  (thanks to Guillaume Rousse).
+- Corrected a bug in ie1 (return value for fgrep)
+- Changed the way parameters are passed to most functions in programs
+  that use automata (passing first arc instead of the parent arc).
+  This might have introduced some new errors...
+- Added a parameter to fsa_spell to force the search for replacements
+  (thanks to Guillaume Rousse).
+- Added two new compile options. The first one -- SPARSE -- changes
+  the way the automaton is represented. if the option is used, then
+  most of transitions of the automaton are stored as a sparse
+  matrix. Only annotations (e.g. in morphological dictionaries) are
+  still stored as lists of transitions. The new representation is
+  faster for most tasks, but it takes longer to produce, and it is
+  larger. The option SLOW_SPARSE makes sure that we try to fill in
+  every hole in the sparse matrix, but it results in *VERY* slow
+  construction, and the results are practically the same.
+Version 0.41
+- Corrected a bug in fsa_ubuild that caused the FILLER not to be set (thanks
+  to Marco Baroni)
+Version 0.42
+- Corrected a compile error in mmorph.cc when MORPH_INFIX was undefined.
+- Corrected an error in fsa_prefix that gave infinite loops while
+  listing words with certain prefixes.
+- Corrected a bug that resulted from new glibc++ I/O behaviour (thanks
+  to Gertjan van Noord)
+- Changed the licence so that the package is freer than it used to be.
+Version 0.43
+- Corrected a bug in fsa_morph that never got a chance to manifest
+  itself there because of the way C++ initializes variables, but it
+  was a bug anyway (thanks to Jirka Mikulasek).
+Version 0.44
+- Corrected a bug in fsa_morph that was introduced in version 0.40 and
+  resulted in inability to process infixes (thanks to Marcin Milkowski).
+- Corrected a bug in fsa_guess that was introduced in version 0.40 and
+  resulted in inability to process infixes (thanks to Marcin Milkowski).
+Version 0.45
+- Corrected a bug in counting transitions with the next flag set that
+  resulted in incorrect pointer size in fsa_build/fsa_ubuild (thanks
+  to Marcin Milkowski and Dawid Weiss).

Added: fsa/INSTALL
===================================================================
--- fsa/INSTALL	                        (rev 0)
+++ fsa/INSTALL	2009-03-27 08:14:42 UTC (rev 154)
@@ -0,0 +1,810 @@
+1. COMPILATION
+
+1.1. General
+
+  All programs are written in C++. You need a C++ compiler to compile them.
+  I have used GNU g++ 2.6.0 under SunOS 4.1.4, and later under
+  Solaris. This version was compiled with g++ 2.7.2.1. Previous versions
+  may have problems with templates. I had problems compiling this
+  version with Solaris CC - again, templates were to blame.
+
+  If you work under Unix, and you have a g++ compiler, a simple command:
+
+  make
+
+  should work. If you use a different compiler, append CXX=that_compiler to
+  the command line, e.g.:
+
+  make CXX=CC
+
+  If you use another operating system, and a different compiler, you should
+  have manuals for them. Consult them. Under the infamous so called
+  operating system from Microsoft, you should consider adding
+  ios::binary to the declaration of fstream dict(...) in file common.cc.
+
+  Note that emacs lisp package works with emacs 19.34, and it will
+  almost certainly not work with emacs 20.
+
+1.2. Compile options
+
+  Before you jump to experiment with various options, or jump out
+  of the window on seeing how many options there are, please note
+  that a default set of them is provided in the Makefile, so do not worry.
+
+  Please note that you can see what options were used for compiling
+  a particular program by invoking it with -v option. When you change
+  compile options and recompile the programs, please do "make clean" first
+  - it may save you a lot of troubles.
+
+  There are some compile options that may be worth trying. First,
+  normal optimization for speed (done by the compiler):
+
+  CPPFLAGS=-O
+  or
+  CPPFLAGS=-O2
+
+  Then there are options used for conditional compilation of the source
+  code. They are specified in CFLAGS with -D, i.e. use e.g.
+
+  make CPPFLAGS=-DJOIN_PAIRS
+
+  to compile the programs with JOIN_PAIRS option on. To specify more
+  options, put them into quotes, e.g.:
+
+  make CPPFLAGS='-DA_TERGO -DSORT_ON_FREQ'
+
+  Be careful when specifying MORE_COMPR. The construction time may
+  rise dramatically when you use -O run-time option of fsa_build or
+  fsa_ubuild. That time is spent not on construction itself, but
+  rather on reordering the arcs, and trying to match them.
+
+  In the following descriptions, the following fileds are used:
+  Assumes: those options must be defined.
+  Excludes: those options cannot be defined.
+  Used in: this option is given to programs in the list.
+  Affects: this option changes the output of programs in the list.
+
+1.2.1. Options changing format version number
+
+  In the present version, there are 6 numbered format versions: 0, 1, 2
+  4, 5, and 128 (or -127, or 0x80). For differences between these formats
+  see file fsa.h. The formats correspond to different settings of the
+  following compile options: LARGE_DICTIONARIES, FLEXIBLE, STOPBIT, NEXTBIT,
+  TAILS, SPARSE. In the following table, LARGE_DICTIONARIES appears as L_D.
+
+  	L_D	FLEXIBLE	STOPBIT	NEXTBIT	    TAILS   WEIGHTED	SPARSE
+  0:	-	-		-	-	    -	    -		-
+  1:	-	+		-	-	    -	    -		-
+  2:	-	+		-	+	    -	    -		-
+  4:	-	+		+	-	    -	    -		-
+  5:	-	+		+	+	    -	    -		-
+  6:	-	+		+	-	    +	    -		-
+  7:	-	+		+	+	    +	    -		-
+  8:	-	+		+	+	    -	    +		-
+  9:	-	+		+	-	    -	    -		+
+  10:	-	+		+	+	    -	    -		+
+  11:	-	+		+	-	    +	    -		+
+  12:	-	+		+	+	    +	    -		+
+  128:	+	-		-	-	    -	    -		-
+
+  Note that in order to produce an automaton in format version 8, -W
+  runtime option must be given to fsa_build or fsa_ubuild. Otherwise
+  version 5 will be produced.
+
+
+  FLEXIBLE
+  makes it possible to produce dictionaries (automata) tailored to
+  particular needs. The size of arcs is determined dynamically. This
+  should be on, as the old way gives (usually) bigger
+  dictionaries. This option also makes the automata portable - another
+  reason for using it. I may remove inflexible code from the future
+  versions of this package.
+  Assumes: no options.
+  Excludes: LARGE_DICTIONARIES.
+  Used in: all programs.
+  Affects: fsa_build, fsa_ubuild.
+  When to use: always.
+
+  LARGE_DICTIONARIES
+  This is an old option to be used without FLEXIBLE when the automaton
+  gets too big. Note that FLEXIBLE makes it possible to produce
+  dictionaries of any size while making them as small as possible, so
+  you do not need this LARGE_DICTIONARIES. I am not sure whether it
+  still works.
+  Assumes: no options.
+  Excludes: FLEXIBLE, STOPBIT, NEXTBIT, NUMBERS.
+  Used in: all programs.
+  Affects: fsa_build, fsa_ubuild.
+  When to use: never.
+
+  NEXTBIT
+  introduces a 1b flag that is set when the target of the arc
+  is placed right after the current one in the automaton, and cleared
+  otherwise. Otherwise the bit is not set. In case the flag is set,
+  the go_to field, i.e. the address of the node to which this arc
+  points, is dropped - only the (1 byte) part than contains
+  the flag is kept. This usually produces smaller automata, as there
+  are frequently chains of nodes one following another, and for the
+  arcs of those nodes it is not necessary to store the whole addresses
+  of the next nodes in those chains. However, since the nodes are no
+  longer fixed size, and we have additional 1b flag that takes place
+  in the go_to field, the size of the resulting automaton may actually
+  be higher when the additional 2-3 bytes cross the byte boundary in
+  the go_to field. Also note that in order to increase the
+  compression, the numbering scheme is different from the usual one in
+  that it starts numbering the children from the last arc. This is
+  done in order to have more nodes lying just after the arc that
+  points to them.
+  Assumes: FLEXIBLE.
+  Excludes: LARGE_DICTIONARIES, JOIN_PAIRS.
+  Used in: all programs.
+  Affects: fsa_build, fsa_ubuild, fsa_prefix.
+  When to use: always.
+
+  STOPBIT
+  replaces counters that hold the number of arcs for each node with
+  one bit for each arc that says whether it is the last one in the
+  node. This gives smaller automata, although maybe a fraction of a
+  percent slower. Note that while automata produced with this option
+  are never larger than those produced without it, for some automata,
+  the size does not change. The reason is that 1-bit markers have to
+  find room in the goto bytes, and they may provoke crossing the byte
+  barrier.
+  Assumes: FLEXIBLE.
+  Excludes: LARGE_DICTIONARIES, JOIN_PAIRS.
+  Used in: all programs.
+  Affects: fsa_build, fsa_ubuild, fsa_prefix.
+  When to use: always.
+
+  TAILS
+  introduces a 1b flag that is set for a particular node when the tail
+  of that node (i.e. a number of arcs that are the last arcs of the
+  node) matches the tail of another node somewhere else in the
+  automaton. If the byte is set, then the present arc is followed by
+  the address of the isomorphic tail in another node in the
+  automaton. For example, if we have node A with arcs (a, c, d) (we
+  skip the addresses, and markers of finality for brevity), and a node
+  B with arcs (b, c, d), then in node B, we can have only an arc with
+  b, and a pointer to (c, d) from A. The arc b in B has the flag
+  set. Or we can do that the other way round, i.e. node A may contain
+  only arc a with the flag set, and the node B is written in
+  whole. Note that the flag takes space in the goto field, so it may
+  leed to increase in space. However, it should normally produce
+  smaller automata. It always leeds to bigger construction times.
+  Assumes: FLEXIBLE, STOPBIT.
+  Excludes: LARGE_DICTIONARIES, JOIN_PAIRS.
+  Used in: all programs.
+  Affects: fsa_build, fsa_ubuild, fsa_prefix.
+  When to use: for static dictionaries after testing (for certain
+               sizes the automata can actually be bigger).
+
+  WEIGHTED
+  introduces weights in every arc. The weights are proportional to the
+  number of strings recognized in the part of the automaton reachable
+  via that arc. Weights take only one byte, so if the number of
+  strings is too large to fit into one byte, the weights on all arcs
+  of the parent node are descreased proportinally. This option
+  requires more memory during construction process, and automata are
+  larger (they may even contain multiple copies of isomorphic nodes,
+  but with different weights). However, this option makes it possible
+  to introduce probabilities to fsa_guess.
+  Assumes: FLEXIBLE, STOPBIT, NEXTBIT, A_TERGO.
+  Excludes: LARGE_DICTIONARIES, JOIN_PAIRS.
+  Used in: all_programs.
+  Affects: fsa_build, fsa_ubuild, fsa_guess.
+  When to use: for adding new words to a morphological dictionary, for tagging.
+
+  SPARSE
+  introduces sparse matrix representation. If there is no annotation
+  separator in the strings, the entire automaton is stored using it
+  (except for some dummy data). If there are annotations, they are
+  stored in the traditional format (list of transitions). This option
+  gives fast recognition times, fast word to number
+  conversion (perfect hashing), but larger dictionaries, slow listing
+  of contents, slow number to word conversion, and slow search for
+  candidates in spelling correction, slow guessing, slow construction.
+  Assumes: FLEXIBLE, STOPBIT
+  Excludes: LARGE_DICTIONARIES, JOIN_PAIRS, WEIGHTED
+  Used in: all programs.
+  Affects: fsa_build, fsa_ubuild, fsa_prefix.
+  When to use: When the programs should be optimized for speed rather
+               than for size, number to word conversion speed is not
+	       critical to the system, and spelling correction is
+	       called mostly on correct words. See file `Times' for
+	       results of my experiments.
+
+1.2.2. Options changing format without changing format version number
+
+  NUMBERS
+  makes it possible to build automata that have word numbering
+  information in them, and to use them. That information is used by
+  fsa_hash. To build automata that have the numbering information in
+  them, use -N option of fsa_build. Note that when using -N, its is
+  not arcs, but bytes that are addressable, so we need 2 or usually 3
+  bits more for the goto field. This in turn may be translated into
+  increasing the arc size by one byte. Even when we have room for
+  those additional bits in the current byte frame, note that the
+  numbering information also takes place (as many bytes as it takes to
+  number all words stored in the automaton). You cannot use
+  compression (runtime option -O) with -N.
+  Assumes: FLEXIBLE.
+  Excludes: LARGE_DICTIONARIES.
+  Used in: all programs.
+  Affects: fsa_build, fsa_ubuild, fsa_hash, fsa_prefix.
+  When to use: if you use perfect hashing.
+
+1.2.3. Options changing the size of the automaton without changing the format
+
+  DESCENDING
+  makes the resulting automaton built with -O a bit smaller, but much slower.
+  Assumes: SORT_ON_FREQ.
+  Excludes: No options.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild, fsa_prefix, fsa_hash.
+  When to use: If you want a bit smaller but a bit slower to use automata.
+
+  JOIN_PAIRS
+  makes the resulting automaton smaller if you use fsa_build with "-O"
+  (the option of fsa_build, or fsa_ubuild, not the compiler). It works
+  by sharing one arc by two two-arc nodes, where possible.
+  Assumes: No options.
+  Excludes: STOPBIT, NEXTBIT.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild, fsa_prefix, fsa_hash.
+  When to use: never.
+
+  MORE_COMPR
+  changes the order of arcs to get more compression. Requires more
+  memory. With -O, the execution time is much, much longer.
+  Assumes: NEXTBIT or STOPBIT.
+  Excludes: No options.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild, fsa_prefix, fsa_hash.
+  When to use: for static dictionaries.
+
+  SORT_ON_FREQ
+  makes the the automaton smaller (independently of JOIN_PAIRS). It
+  works by sorting the arcs on frequency. Note that this changes the
+  order of words in the automaton. If DESCENDING not set, can make the
+  resulting automaton built with -O faster.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild, fsa_prefix, fsa_hash.
+  When to use: always except for cases when you build something huge in
+               real time.
+
+1.2.4. Option affecting the way guessing automata (index a tergo) are built.
+
+  A_TERGO
+  enables -X option in fsa_build. This creates an index a tergo (a
+  guessing automaton).
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild, fsa_guess.
+  When to use: if you use fsa_guess.
+
+  GENERALIZE
+  In fsa_build called with -X option, reduces the size of the automaton
+  while loosing the advantage of always annotating correctly words that
+  are already in the dictionary. This options makes the automaton
+  smaller than PRUNE_ARCS.
+  Assumes: A_TERGO.
+  Excludes: PRUNE_ARCS.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild, fsa_guess.
+  When to use: if you use fsa_guess for adding new words to a dictionary.
+
+  PRUNE_ARCS
+  launches additional pruning during guessing automaton (index a
+  tergo) creation. The resulting automaton will be smaller, and
+  predictions narrower (maybe more precise, but those less probable
+  may be missing). Automata produced with this option are larger than
+  with GENERALIZE.
+  Assumes: A_TERGO.
+  Excludes: GENERALIZE.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild, fsa_guess.
+  When to use: if you use fsa_guess for tagging.
+
+1.2.5. Options affecting the way guessing automata are interpreted
+
+  GUESS_LEXEMES
+  makes fsa_guess tries to guess not only categories, but lexemes as
+  well. The data must be prepared differently (see man pages for
+  fsa_build and fsa_guess). Run-time option -g switches off guessing
+  lexemes.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_guess.
+  Affects: fsa_guess.
+  When to use: if you use fsa_guess for more tasks than tagging.
+
+  GUESS_MMORPH
+  makes it possible to use -m option in fsa_guess, i.e. prediction of
+  mmorph descriptions. mmorph is a morphology program developed at
+  ISSCO, Geneva.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_guess.
+  Affects: fsa_guess.
+  When to use: for using fsa_guess in acquisition of new words for a
+	       morphological dictionary.
+
+  GUESS_PREFIX
+  makes fsa_guess use information about prefixes to disambiguate
+  morphological parses. Requires GUESS_LEXEMES. Data must be prepared
+  differently (see man pages for fsa_build and fsa_guess). Reduces the
+  size of the a tergo dictionary compared with that created to be used
+  with GUESS_LEXEMES only. Run-time option -p switches off the use of
+  prefixes in guessing.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_guess.
+  Affects: fsa_guess.
+  When to use: when you use fsa_guess, and the language you are
+	       working on has prefixes or infixes.
+
+1.2.6. Options changing the way morphological automata are interpreted
+
+  MORPH_INFIX
+  makes it possible to use -P and -I options that interpret coded
+  prefixes (-P), and coded prefixes and infixes (-I) in fsa_morph.
+  For more details, see README file, and the man page for fsa_morph(5).
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_morph.
+  Affects: fsa_morph.
+  When to use: when you use fsa_morph, and the language you are
+	       working on has prefixes or infixes.
+
+  POOR_MORPH
+  makes it possible to use -A option, so that the automata can contain
+  only information about categories, and no information about the base
+  form of an inflected form.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_morph.
+  Affects: fsa_morph.
+  When to use: if you use fsa_morph only for tagging.
+
+1.2.7. Various options.
+
+  CASECONV
+  works with fsa_spell. It makes it possible to check capitalized words
+  as if they were all lowercase.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_accent, fsa_morph, fsa_spell.
+  Affects: fsa_accent, fsa_morph, fsa_spell.
+  When to use: when case conversion is needed.
+
+  CHCLASS
+  makes it possible to treat certain two-letter sequences in certain
+  context as if they were single letters. This is useful in
+  spelling. E.g. in Polish, `rz' and `z' with a dot above (\.z in TeX)
+  are pronounced in exactly the same way, so they may be confused. This
+  option makes it possible to treat such replacements as if they were
+  one edit distance unit apart from each other. This option is used in
+  fsa_spell.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_spell.
+  Affects: fsa_spell.
+  When to use: for spelling correction in languages for which edit
+	       distance one is not sufficient.
+
+  DEBUG
+  If you have a few spare months, you can compile the programs with
+  CFLAGS=-DDEBUG. That will give huge amounts of information about program
+  internals during execution time. It may also give compile errors. In
+  debugging the program, I just comment out particular ifdefs.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: all programs.
+  Affects: all programs.
+  When to use: never.
+
+  DUMP_ALL
+  works with fsa_prefix. If you compile the program with this option,
+  no space will be prepended to listed entries. In particular, this
+  can list the contents of the dictionary without the need to remove
+  the leading space. Use -a run-time option to list the contents.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_prefix.
+  Affects: fsa_prefix.
+  When to use: to list the contents of a dictionary.
+
+  LOOSING_RPM
+  makes it possible to use the programs even on linux distributions
+  using rpms. The libstdc++ distributed with RedHat and SuSE has
+  broken I/O. You probably do need to use that option with more stable
+  distributions. This option does not fix the -O2 problem,
+  however. You will still have to use -O only.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: all programs.
+  Affects: all programs.
+  When to use: with corrupted versions og libg++, e.g. Red Hat and SuSE.
+
+  PROGRESS
+  In fsa_build, shows how many lines have been read so far, and what is
+  being done at the moment, i.e. what phase the processing is in.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild.
+  When to use: when you build something huge and you are not sure if
+	       it works.
+
+  RUNON_WORDS
+  makes it possible to check whether inserting a space inside the
+  checked word produces two correct words. This works with fsa_spell.
+  Assumes: no options.
+  Excludes: no options.
+  Used in: fsa_spell.
+  Affects: fsa_spell.
+  When to use: for spellchecking.
+
+  SHOW_FILLERS
+  enables printing of filler characters by fsa_prefix (they are normally
+  not printed).
+  Assumes: no option.
+  Excludes: no option.
+  Used in: fsa_prefix.
+  Affects: fsa_prefix.
+  When to use: for diagnostics.
+
+  SLOW_SPARSE
+  checks for every hole in a sparse matrix whether it can still be filled,
+  which could lead to smaller automata. This slows down construction
+  process for large automata by orders of magnitude.
+  Assumes: FLEXIBLE, STOPBIT, SPARSE.
+  Excludes: WEIGHTED, LARGE_DICTIONARIES.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild.
+  When to use: If you think you waist too many transitions in a sparse
+	       matrix in small automata.
+
+  STATISTICS
+  In fsa_build, shows some statistics on the resulting automaton: the
+  number of states, transitions, etc.
+  Assumes: no option.
+  Excludes: no options.
+  Used in: fsa_build, fsa_ubuild.
+  Affects: fsa_build, fsa_ubuild.
+  When to use: when you are interested in properties of automata.
+
+2. CONSTANTS
+
+  Max_word_len
+  Defined in: common.h
+  Default value: 120.
+  Affects: All programs except fsa_build and fsa_ubuild.
+  Description:
+  Restrictions: Must be positive.
+
+  LIST_INIT_SIZE
+  Defined in: common.h
+  Default value: 16.
+  Affects: All programs except fsa_build and fsa_ubuild.
+  Description: Initial size of a list, e.g. list of replacements, list
+	       of dictionary names etc. The bigger, the faster.
+  Restrictions: Must be positive.
+
+  LIST_STEP_SIZE
+  Defined in: common.h
+  Default value: 8.
+  Affects: All programs except fsa_build and fsa_ubuild.
+  Description: If a list grows beyond LIST_INIT_SIZE, its size is
+	       increased by this value. The bigger, the faster.
+  Restrictions: Must be positive.
+
+  MAX_ARCS_PER_NODE
+  Defined in: fsa.h
+  Default value: 255 or 128, depending on compile options.
+  Affects: All programs.
+  Description: Maximal number of outgoing transitions per state. Do
+	       not change.
+  Restrictions: Depends on the structure of states and transitions. Do
+		not change.
+
+  MAX_NOT_CYCLE
+  Defined in: common.h
+  Default value: 1024.
+  Affects:
+  Description: Maximal length of a string in the automaton. It is used
+	       to detect errors.
+  Restrictions: Must be positive.
+
+  MAX_VANITY_LEVEL
+  Defined in: guess.h
+  Default value: 5.
+  Affects: fsa_guess.
+  Description:
+  Restrictions:
+
+  PAIR_REG_LEN
+  Defined in: nindex.h
+  Default value: 32.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  MAX_SPARSE_WAIT
+  Defined in: nnode.h
+  Default value: 3.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  Max_edit_distance
+  Defined in: spell.h
+  Default value: 3.
+  Affects: fsa_spell.
+  Description:
+  Restrictions:
+
+  WORD_BUFFER_LENGTH
+  Defined in: build_fsa.cc
+  Default_value: 128.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  UNREDUCIBLE
+  Defined in: mkindex.cc
+  Default value: 4.
+  Affects:
+  Description:
+  Restrictions:
+
+  WITH_ANNOT
+  Defined in: mkindex.cc
+  Default value: 2.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions: Do not change.
+
+  NO_ANNOT
+  Defined in: mkindex.cc
+  Default_value: 1.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions: Do not change.
+
+  NODE_TO_BE_REDUCED
+  Defined in: mkindex.cc
+  Default value: -5.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions: Do not change.
+
+  NODE_UNREDUCIBLE
+  Defined in: mkindex.cc
+  Default value: -6.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions: Do not change.
+
+  NODE_IN_TAGS
+  Defined in: mkindex.cc
+  Default value: -7.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions: Do not change.
+
+  NODE_MERGED
+  Defined in: mkindex.cc
+  Default value: -8.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions: Do not change.
+
+  NODE_TO_BE_MERGED
+  Defined in: mkindex.cc
+  Default value: -9.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions: Do not change.
+
+  MIN_PRUNE
+  Defined in: mkindex.cc
+  Default value: 2.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  MAX_DESTS
+  Defined in: mkindex.cc
+  Default value: 32.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  MIN_DESTS_MEMBERS
+  Defined in: mkindex.cc
+  Default value: 0.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  MAX_ANNOTS
+  Defined in: mkindex.cc
+  Default value: 20.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  MAX_DIFF_ANNOTS
+  Defined in: mkindex.cc
+  Default value: 20.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  MIN_KIDS_TO_MERGE
+  Defined in: mkindex.cc
+  Default value: 2.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  MIN_ANNOTS
+  Defined in: mkindex.cc
+  Default value: 3.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  AN_NOM
+  Defined in: mkindex.cc
+  Default value: 1.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  AN_DENOM
+  Defined in: mkindex.cc
+  Default value: 2.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+  INDEX_SIZE_STEP
+  Defined in: nindex.cc and nnode.cc.
+  Default value: 16.
+  Affects: fsa_build and fsa_ubuild.
+  Description:
+  Restrictions:
+
+
+3. INSTALLATION
+
+  Copy all dictionaries you want to be installed into the source dictionary
+  of the package. Dictionaries are provided separately, so make sure you
+  have copied them (at least those you may need). Note that the
+  dictionaries on http://www.pg.gda.pl/~jandac/fsa.html have been
+  prepared long time ago using only those options that were available
+  at that time. If you want to use them, compile the program as you
+  like, try to use the dictionaries, and you will probably get an
+  error message saying what compile options were used for compilation
+  of fsa_build that constructed the dictionaries. Save Makefile,
+  delete some options from it, make clean, make, use fsa_prefix to get
+  the contents, restore Makefile, make clean, make, and build the
+  automata again (they should be much smaller with the default set of
+  options for the current version).
+
+3.1. Admin part
+
+  For Polish users, you may look at pl.chcl file and uncomment some
+  lines, if too many users watch too much tv, and read too little.
+
+  There are a few variables in Makefile that you can change. These are
+  PREFIXDIR - parent dir of BINDIR, MANDIR, DICTDIR (default: /usr/local);
+  BINDIR    - where the programs should be placed (default: $PREFIXDIR/bin);
+  MANDIR    - where the man pages should be placed (default:
+	      $PREFIXDIR/man);
+  DICTDIR   - where dictionaries, accent files, language files, and
+	      character class files should be placed (default:
+	      $PREFIXDIR/lib);
+  LISPDIR   - where jspell.el should be placed. I think the site-lisp
+	      directory is better than lisp directory. Check your emacs
+	      version as it normally forms a part of that name.
+	      The directory specified in Makefile by default will
+	      probably not work for you;
+  TCLMACQDIR- where files supporting execution of the tcl/tk interface
+	      tclmacq should go (help file and language file);
+  TCLMACQBINDIR
+	    - where tcl scripts and perl scripts supporting tclmacq
+	      should go (it should be the same as BINDIR);
+  PREP_FCONF- It should be set to \# for Tcl versions prior to 8.2 (I
+	      think), and to nothing for 8.2 and higher. If man
+	      fconfigure shows -encoding option present, then the
+	      variable should be empty, otherwise it should be set to \#
+  MANSECT   - in which section of the manual the pages should be placed.
+
+  You can specify those variables on the command line, e.g.:
+
+  make installlisp LISPDIR=/utl/share/gnu/emacs/site-lisp
+
+  make install	       - installes everything,
+  make installbin      - installes the binaries without man pages,
+  make installman      - installes the manpages,
+  make installscripts  - installes interface scripts (jspell & jaccent),
+  make installlisp     - installes jspell.el (byte compile it afterward),
+  make installdicts    - installes dictionaries (if any), accent files,
+		         language files, character class files.
+
+  Note that with newer linux emacs distributions, the LISPDIR should
+  point to something like /etc/emacs/site-start.d, and the file names
+  should have a prefix `50'. If you put the jspell.el there, it will
+  be loaded automatically, so that you will not need (require 'jspell)
+  in your .emacs file.
+
+3.2. Admin or user part
+
+  The following commands can be put either in site-start.el file in
+  the site-lisp directory, or in users' .emacs files. The first method
+  makes the packet functions available to all users, and it should be
+  done by the administrator. The second method enables the functions
+  on a per-user basis. Note that emacs functions used to work with
+  emacs19, they will probably (almost certainly) not work with emacs20.
+
+  ;; make functions known to emacs
+  (require 'jspell)
+
+  ;; install menus
+  (define-key-after
+    (lookup-key global-map [menu-bar edit])
+    [jspell] '("Jspell" .jspell-menu-map) 'ispell)
+
+  You may want to specify the default dictionary with e.g.:
+
+  (setq jspell-dictionary "polski")
+
+  You may want to compile additional dictionaries. Read the README
+  file and the man page for fsa_build. Remember to sort the data and
+  exclude duplicates (use sort -u) for fsa_build.
+
+  New perl and tcl/tk scripts: sortatt.pl and tclmacq.tcl require
+  setting some variables located at the top of those files.
+
+3.3. Mostly user part
+
+  The following variables can be changed by the user in their .emacs
+  file:
+
+  jmorph-format		- defines the format of morphotactic annotations
+			  (tags). It is an argument to format function
+			  (resembles C format in printf). It contains 3
+			  %s, corresponding to the inflected word,
+			  lexeme, and tag. The correspondence between
+			  those items and particular %s is given by the
+			  variable jmorph-order. Morphotactic
+			  annotations are added by jmorph-* functions.
+			  Example: (setq jmorph-format "%s_%s+%s").
+
+  jmorph-order		- defines the correspondance between the
+			  inflected word, lexeme, and annotations and %s
+			  in jmorph-format; in other words, it defines
+			  the order in which they appear as %s in
+			  jmorph-format. Example: (setq jmorph-order '(1
+			  2 3)).
+			  
+  jspell-morph-sep	- defines a separator character that separates a
+			  lexeme from annotations in the output from
+			  jmorph script. Example: (setq jspell-morph-sep
+			  "&")
+
+  jaccent-automatically	- accents are restored without asking the user
+			  for permission if there is only one choice.
+			  Example: (setq jaccent-automatically t)
+
+  jmorph-automatically	- morphotactic annotations are added without
+			  asking the user for permission if there is
+			  only one choice. Example: (setq
+			  jmorph-automatically nil).
+

Added: fsa/Makefile
===================================================================
--- fsa/Makefile	                        (rev 0)
+++ fsa/Makefile	2009-03-27 08:14:42 UTC (rev 154)
@@ -0,0 +1,369 @@
+# Makefile for building a final state automaton
+# Copyright (c) Jan Daciuk <ja...@pg...>, 1996, 1997, 1998, 1999
+#
+# The most difficult parts written by Dominique Petitpierre
+
+# These define i/o behaviour of programs
+TEXT_IO = one_word_io.o	# texts as input, grep -like output
+WORD_IO = one_word_io.o	# one word per line input
+
+
+# Installation program
+INSTALL = cp -i
+
+# C++ compiler
+CXX=g++
+
+# Compile options (see the file INSTALL for detail)
+# A_TERGO	- include code to build an index a tergo (recognizing word
+#		  categories)
+# CASECONV	- the first letter in spellchecking may be uppercase - check
+#		  both upper & lower
+# CHCLASS	- checks if a string is replaced with another string that
+#		  sounds similar; in the present form, this checks one-letter
+#		  strings against two-letter strings, and vice versa
+# DEBUG		- produces huge amounts of useless data
+# DESCENDING	- produces a bit smaller, but much slower automata
+# DUMP_ALL	- does not print the leading space in fsa_prefix
+# FLEXIBLE	- arc size should be adapted to automaton size; better
+#		  compression, (slightly) less speed, architecture independence
+# GENERALIZE	- used with A_TERGO to reduce the size of the guessing
+#		  automaton, and to increase recall
+# GUESS_LEXEMES	- tries to guess not only tags, but lexemes as well
+#		  in fsa_guess
+# GUESS_MMORPH	- makes it possible to use -m option in fsa_guess to predict
+#		  morphological descriptions of lexemes corresponding to
+#		  unknown inflected words; the descriptions are in the format
+#		  of mmorph - MULTEXT morphology tool developed at ISSCO.
+# GUESS_PREFIX	- tries to include information about prefixes to disambiguate
+#		  morphological parses in fsa_guess
+# JOIN_PAIRS	- used to prune the automaton (arcs share memory) with -X
+#		  option in fsa_build
+# LARGE_DICTIONARIES
+#		- to build big but a little bit faster automata (do not use it)
+# LOOSING_RPM	- to work around a bug in rpm libstdc++ library
+# MORE_COMPR	- to built smaller automata more slowly
+# MORPH_INFIX	- makes it possible to use -I and -P options in fsa_morph
+#		  for recognition of coded prefixes and infixes
+# NEXTBIT	- changes the format of the automaton, so that when there are
+#		  chains of nodes, one following another, one bit is set
+#		  in the goto field to indicate that fact, and only one byte
+#		  from the goto field is used; it usually gives smaller
+#		  automata
+# NUMBERS	- it is possible to use fsa_hash and build dictionaries for
+#		  perfect hashing
+# POOR_MORPH	- enables -A option in fsa_morph for morphological analysis
+#		  giving only categories, and no base forms.
+# PROGRESS	- shows how many lines were read, what fsa_build does
+# PRUNE_ARCS	- used with A_TERGO to reduce the size of the guessing
+#		  automaton, and to increase precision
+# RUNON_WORDS	- checks whether inserting a space inside the word results
+#		  in two correct words in fsa_spell
+# SHOW_FILLERS	- the filler character should be displayed in fsa_prefix
+# SORT_ON_FREQ	- arcs should be sorted on frequency (better compression)
+# SLOW_SPARSE	- try to fill every hole in sparse matrix representation
+# SPARSE	- use sparse matrix representation
+# STATISTICS	- shows some statistics after having built an automaton
+# STOPBIT	- changes the format of the automaton, so that there are
+#		  no counters, but for each arc there is a bit that says
+#		  whether it is the last one in the node; this gives smaller
+#		  automata
+# TAILS		- changes the format of the automaton, allowing for more
+#		  arc sharing, so more compression at the cost of construction
+#		  time
+# WEIGHTED	- introduces weights on arcs for guessing automata.
+#
+# PRUNE_ARCS works only with A_TERGO
+# GUESS_LEXEMES works only with A_TERGO
+# LARGE_DICTIONARIES and FLEXIBLE cannot be specified together
+# NUMBERS works only with FLEXIBLE
+# STOPBIT works only with FLEXIBLE
+# (use FLEXIBLE)
+#
+# See INSTALL file for info on compile options.
+#
+# Some versions of g++ (or stdlibc++) are broken - if so, don't use -O2!
+# !!! If you change these, please do make clean first before each make
+CPPFLAGS=-O2 --pedantic -Wall \
+  -DFLEXIBLE  \
+  -DNUMBERS \
+  -DA_TERGO \
+  -DGENERALIZE \
+  -DSORT_ON_FREQ \
+  -DSHOW_FILLERS  \
+  -DSTOPBIT \
+  -DNEXTBIT \
+  -DMORE_COMPR \
+  -DCASECONV \
+  -DRUNON_WORDS \
+  -DMORPH_INFIX \
+  -DPOOR_MORPH \
+  -DCHCLASS \
+  -DGUESS_LEXEMES -DGUESS_PREFIX \
+  -DGUESS_MMORPH \
+  -DDUMP_ALL \
+  -DSTATISTICS \
+  -DPROGRESS \
+  -DLOOSING_RPM #-DDMALLOC
+
+
+
+
+# -pg
+
+#  -DTAILS \
+#  -DJOIN_PAIRS \
+#  -DPRUNE_ARCS \
+#  -DPROGRESS \
+#  -DWEIGHTED \
+#  -DSTATISTICS \
+#  -DSPARSE \
+
+# Normally empty
+#LDFLAGS=-L/usr/local/lib -ldmallocxx
+LDFLAGS=
+
+# Install directories
+PREFIXDIR = /usr/local
+
+# this is where fsa_build, fsa_spell, etc. should go
+BINDIR = ${PREFIXDIR}/bin
+# this is where the manuals should be kept
+MANDIR = ${PREFIXDIR}/man
+# this is where the dictionaries should go; also accent and language files
+DICTDIR = ${PREFIXDIR}/lib
+# this is where emacs lisp files go
+LISPDIR = /usr/lib/emacs/site-lisp
+# this is where tcl scripts go (also perl scripts used in tclmacq)
+TCLMACQBINDIR = ${BINDIR}
+# this is where tclmacq support files (help, language) go
+TCLMACQDIR = ${PREFIXDIR}/lib
+# The following should be empty if man fconfigure shows -encoding option,
+# and set to \# otherwise. In other words, if your Tcl version is 8.0,
+# you should set it to \#, and if it is 8.2 or higher -- leave it empty.
+PREP_FCONF = \#
+#PREP_FCONF
+# to which man section man pages for fsa belong
+MANSECT1 = 1
+MANSECT5 = 5
+
+########################################################################
+
+# Objects that make particular programs
+SPELL_OBJECTS = common.o spell.o nstr.o ${TEXT_IO} spell_main.o
+ACCENT_OBJECTS = common.o nstr.o ${TEXT_IO} accent_main.o accent.o
+FSA_B_OBJECTS = build_fsa.o nnode.o nindex.o nstr.o
+FSA_S_OBJECTS = builds_fsa.o snode.o
+FSA_U_OBJECTS = buildu_fsa.o unode.o
+PREFIX_OBJECTS = common.o nstr.o one_word_io.o prefix.o prefix_main.o
+GUESS_OBJECTS = common.o nstr.o ${TEXT_IO} guess.o guess_main.o
+HASH_OBJECTS =  common.o nstr.o ${TEXT_IO} hash.o hash_main.o
+MORPH_OBJECTS = common.o nstr.o ${TEXT_IO} morph.o morph_main.o
+VISUAL_OBJECTS = common.o nstr.o ${TEXT_IO} visualize.o visual_main.o
+ALL_PROGS = fsa_spell fsa_build fsa_accent fsa_prefix fsa_guess fsa_hash \
+ fsa_morph fsa_ubuild fsa_visual
+SKL_SCRIPTS = jspell jaccent jmorph jguess
+TCL_SCRIPTS = tclmacq.tcl filesel.tcl
+ALL_SCRIPTS = ${SKL_SCRIPTS} chkmorph.pl deguess.pl demorph.pl \
+ find_irregular.pl gendata.pl mmorph23c.pl morph_data.pl morph_infix.pl \
+ morph_prefix.pl prep_atg.pl prep_ati.pl prep_atl.pl prep_atp.pl \
+ putinplace.pl simplify.pl sortatt.pl sortondesc.pl tclmacq.tcl filesel.tcl
+# Note that awk scripts are not portable
+AWK_SCRIPTS = de_morph_data.awk de_morph_infix.awk deguess.awk demorph.awk \
+ find_irregular.awk mmorph23c.awk morph_data.awk morph_infix.awk \
+ morph_prefix.awk prep_atg.awk prep_ati.awk prep_atl.awk prep_atp.awk
+TCL_SUPP_FILES = tclmacq-help.txt tclmacq-lang.txt
+
+ALL_OBJ = common.o spell.o nstr.o spell_main.o \
+ accent_main.o accent.o build_fsa.o nnode.o nindex.o prefix.o prefix_main.o \
+ guess.o guess_main.o hash.o hash_main.o morph.o morph_main.o builds_fsa.o \
+ buildu_fsa.o unode.o snode.o visualize.o visual_main.o
+
+
+all: ${ALL_PROGS}
+
+
+fsa_spell: ${SPELL_OBJECTS}
+	${CXX} ${CPPFLAGS} ${SPELL_OBJECTS} ${LDFLAGS} -o fsa_spell
+
+fsa_accent: ${ACCENT_OBJECTS}
+	${CXX} ${CPPFLAGS} ${ACCENT_OBJECTS} ${LDFLAGS} -o fsa_accent
+
+fsa_build: ${FSA_B_OBJECTS} ${FSA_S_OBJECTS}
+	${CXX} ${CPPFLAGS} ${FSA_B_OBJECTS} ${FSA_S_OBJECTS} ${LDFLAGS} -o fsa_build
+
+fsa_ubuild: ${FSA_B_OBJECTS} ${FSA_U_OBJECTS}
+	${CXX} ${CPPFLAGS} ${FSA_B_OBJECTS} ${FSA_U_OBJECTS} ${LDFLAGS} -o fsa_ubuild
+
+
+fsa_prefix: ${PREFIX_OBJECTS}
+	${CXX} ${CPPFLAGS} ${PREFIX_OBJECTS} ${LDFLAGS} -o fsa_prefix
+
+fsa_guess: ${GUESS_OBJECTS}
+	${CXX} ${CPPFLAGS} ${GUESS_OBJECTS} ${LDFLAGS} -o fsa_guess
+
+fsa_hash: ${HASH_OBJECTS}
+	${CXX} ${CPPFLAGS} ${HASH_OBJECTS} ${LDFLAGS} -o fsa_hash
+
+fsa_morph: ${MORPH_OBJECTS}
+	${CXX} ${CPPFLAGS} ${MORPH_OBJECTS} ${LDFLAGS} -o fsa_morph
+
+fsa_visual: ${VISUAL_OBJECTS}
+	${CXX} ${CPPFLAGS} ${VISUAL_OBJECTS} ${LDFLAGS} -o fsa_visual
+
+fsa_dump: dump.cc
+	${CXX} ${CPPFLAGS} dump.cc ${LDFLAGS} -o fsa_dump
+
+common.o: common.cc fsa.h nstr.h common.h
+	${CXX} ${CPPFLAGS} -c common.cc
+
+spell.o: spell.cc fsa.h nstr.h spell.h common.h
+	${CXX} ${CPPFLAGS} -c spell.cc
+
+nstr.o:	nstr.cc nstr.h
+	${CXX} ${CPPFLAGS} -c nstr.cc
+
+build_fsa.o: build_fsa.cc nnode.h nindex.h nstr.h fsa.h fsa_version.h mkindex.cc
+	${CXX} ${CPPFLAGS} -c build_fsa.cc
+
+builds_fsa.o: builds_fsa.cc nnode.h nindex.h nstr.h fsa.h fsa_version.h mkindex.cc compile_options.h
+	${CXX} ${CPPFLAGS} -c builds_fsa.cc
+
+buildu_fsa.o: buildu_fsa.cc nnode.h unode.h nindex.h nstr.h fsa.h fsa_version.h mkindex.cc compile_options.h
+	${CXX} ${CPPFLAGS} -c buildu_fsa.cc
+
+nnode.o: nnode.cc nnode.h nstr.h fsa.h nindex.h
+	${CXX} ${CPPFLAGS} -c nnode.cc
+
+unode.o: unode.cc unode.h nnode.h nstr.h fsa.h nindex.h
+	${CXX} ${CPPFLAGS} -c unode.cc
+
+snode.o: snode.cc nnode.h nstr.h fsa.h nindex.h
+	${CXX} ${CPPFLAGS} -c snode.cc
+
+nindex.o: nindex.cc nindex.h nnode.h
+	${CXX} ${CPPFLAGS} -c nindex.cc
+
+one_word_io.o: one_word_io.cc fsa.h common.h
+	${CXX} ${CPPFLAGS} -c one_word_io.cc
+
+text_io.o: text_io.cc common.h fsa.h
+	${CXX} ${CPPFLAGS} -c text_io.cc
+
+spell_main.o: spell_main.cc common.h spell.h fsa_version.h compile_options.h
+	${CXX} ${CPPFLAGS} -c spell_main.cc
+
+accent_main.o: accent_main.cc comm...
 
[truncated message content]