Import Upstream version 0.5.0

.travis.yml

+sudo: required
+dist: trusty
+language: cpp
+
+addons:
+  apt:
+    packages:
+      - libxml++2.6-dev
+      - libarchive-dev
+
+script:
+  - autoreconf -fi
+  - ./configure --disable-static --enable-zhfst
+  - make -j3
+  - make -j1 check

AUTHORS

+Authors of HFST ospell
+----------------------
+
+This lists authors relevant for copyright issues. See also THANKS.
+
+2012-2017, Erik Axelson <erik.axelson@helsinki.fi>
+2010-2016, Sam Hardwick <sam.hardwick@gmail.com>
+2015-2017, Tino Didriksen <mail@tinodidriksen.com>
+2010-2016, Sjur Nørstebø Moshagen <sjur.n.moshagen@uit.no>
+2010-2016, Tommi Pirinen <flammie@iki.fi>
+2013, Francis M. Tyers <ftyers@prompsit.com>

COPYING

+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

INSTALL

+Installation Instructions
+*************************
+
+Copyright (C) 1994, 1995, 1996, 1999, 2000, 2001, 2002, 2004, 2005,
+2006 Free Software Foundation, Inc.
+
+This file is free documentation; the Free Software Foundation gives
+unlimited permission to copy, distribute and modify it.
+
+Basic Installation
+==================
+
+Briefly, the shell commands `./configure; make; make install' should
+configure, build, and install this package.  The following
+more-detailed instructions are generic; see the `README' file for
+instructions specific to this package.
+
+   The `configure' shell script attempts to guess correct values for
+various system-dependent variables used during compilation.  It uses
+those values to create a `Makefile' in each directory of the package.
+It may also create one or more `.h' files containing system-dependent
+definitions.  Finally, it creates a shell script `config.status' that
+you can run in the future to recreate the current configuration, and a
+file `config.log' containing compiler output (useful mainly for
+debugging `configure').
+
+   It can also use an optional file (typically called `config.cache'
+and enabled with `--cache-file=config.cache' or simply `-C') that saves
+the results of its tests to speed up reconfiguring.  Caching is
+disabled by default to prevent problems with accidental use of stale
+cache files.
+
+   If you need to do unusual things to compile the package, please try
+to figure out how `configure' could check whether to do them, and mail
+diffs or instructions to the address given in the `README' so they can
+be considered for the next release.  If you are using the cache, and at
+some point `config.cache' contains results you don't want to keep, you
+may remove or edit it.
+
+   The file `configure.ac' (or `configure.in') is used to create
+`configure' by a program called `autoconf'.  You need `configure.ac' if
+you want to change it or regenerate `configure' using a newer version
+of `autoconf'.
+
+The simplest way to compile this package is:
+
+  1. `cd' to the directory containing the package's source code and type
+     `./configure' to configure the package for your system.
+
+     Running `configure' might take a while.  While running, it prints
+     some messages telling which features it is checking for.
+
+  2. Type `make' to compile the package.
+
+  3. Optionally, type `make check' to run any self-tests that come with
+     the package.
+
+  4. Type `make install' to install the programs and any data files and
+     documentation.
+
+  5. You can remove the program binaries and object files from the
+     source code directory by typing `make clean'.  To also remove the
+     files that `configure' created (so you can compile the package for
+     a different kind of computer), type `make distclean'.  There is
+     also a `make maintainer-clean' target, but that is intended mainly
+     for the package's developers.  If you use it, you may have to get
+     all sorts of other programs in order to regenerate files that came
+     with the distribution.
+
+Compilers and Options
+=====================
+
+Some systems require unusual options for compilation or linking that the
+`configure' script does not know about.  Run `./configure --help' for
+details on some of the pertinent environment variables.
+
+   You can give `configure' initial values for configuration parameters
+by setting variables in the command line or in the environment.  Here
+is an example:
+
+     ./configure CC=c99 CFLAGS=-g LIBS=-lposix
+
+   *Note Defining Variables::, for more details.
+
+Compiling For Multiple Architectures
+====================================
+
+You can compile the package for more than one kind of computer at the
+same time, by placing the object files for each architecture in their
+own directory.  To do this, you can use GNU `make'.  `cd' to the
+directory where you want the object files and executables to go and run
+the `configure' script.  `configure' automatically checks for the
+source code in the directory that `configure' is in and in `..'.
+
+   With a non-GNU `make', it is safer to compile the package for one
+architecture at a time in the source code directory.  After you have
+installed the package for one architecture, use `make distclean' before
+reconfiguring for another architecture.
+
+Installation Names
+==================
+
+By default, `make install' installs the package's commands under
+`/usr/local/bin', include files under `/usr/local/include', etc.  You
+can specify an installation prefix other than `/usr/local' by giving
+`configure' the option `--prefix=PREFIX'.
+
+   You can specify separate installation prefixes for
+architecture-specific files and architecture-independent files.  If you
+pass the option `--exec-prefix=PREFIX' to `configure', the package uses
+PREFIX as the prefix for installing programs and libraries.
+Documentation and other data files still use the regular prefix.
+
+   In addition, if you use an unusual directory layout you can give
+options like `--bindir=DIR' to specify different values for particular
+kinds of files.  Run `configure --help' for a list of the directories
+you can set and what kinds of files go in them.
+
+   If the package supports it, you can cause programs to be installed
+with an extra prefix or suffix on their names by giving `configure' the
+option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'.
+
+Optional Features
+=================
+
+Some packages pay attention to `--enable-FEATURE' options to
+`configure', where FEATURE indicates an optional part of the package.
+They may also pay attention to `--with-PACKAGE' options, where PACKAGE
+is something like `gnu-as' or `x' (for the X Window System).  The
+`README' should mention any `--enable-' and `--with-' options that the
+package recognizes.
+
+   For packages that use the X Window System, `configure' can usually
+find the X include and library files automatically, but if it doesn't,
+you can use the `configure' options `--x-includes=DIR' and
+`--x-libraries=DIR' to specify their locations.
+
+Specifying the System Type
+==========================
+
+There may be some features `configure' cannot figure out automatically,
+but needs to determine by the type of machine the package will run on.
+Usually, assuming the package is built to be run on the _same_
+architectures, `configure' can figure that out, but if it prints a
+message saying it cannot guess the machine type, give it the
+`--build=TYPE' option.  TYPE can either be a short name for the system
+type, such as `sun4', or a canonical name which has the form:
+
+     CPU-COMPANY-SYSTEM
+
+where SYSTEM can have one of these forms:
+
+     OS KERNEL-OS
+
+   See the file `config.sub' for the possible values of each field.  If
+`config.sub' isn't included in this package, then this package doesn't
+need to know the machine type.
+
+   If you are _building_ compiler tools for cross-compiling, you should
+use the option `--target=TYPE' to select the type of system they will
+produce code for.
+
+   If you want to _use_ a cross compiler, that generates code for a
+platform different from the build platform, you should specify the
+"host" platform (i.e., that on which the generated programs will
+eventually be run) with `--host=TYPE'.
+
+Sharing Defaults
+================
+
+If you want to set default values for `configure' scripts to share, you
+can create a site shell script called `config.site' that gives default
+values for variables like `CC', `cache_file', and `prefix'.
+`configure' looks for `PREFIX/share/config.site' if it exists, then
+`PREFIX/etc/config.site' if it exists.  Or, you can set the
+`CONFIG_SITE' environment variable to the location of the site script.
+A warning: not all `configure' scripts look for a site script.
+
+Defining Variables
+==================
+
+Variables not defined in a site shell script can be set in the
+environment passed to `configure'.  However, some packages may run
+configure again during the build, and the customized values of these
+variables may be lost.  In order to avoid this problem, you should set
+them in the `configure' command line, using `VAR=value'.  For example:
+
+     ./configure CC=/usr/local2/bin/gcc
+
+causes the specified `gcc' to be used as the C compiler (unless it is
+overridden in the site shell script).
+
+Unfortunately, this technique does not work for `CONFIG_SHELL' due to
+an Autoconf bug.  Until the bug is fixed you can use this workaround:
+
+     CONFIG_SHELL=/bin/bash /bin/bash ./configure CONFIG_SHELL=/bin/bash
+
+`configure' Invocation
+======================
+
+`configure' recognizes the following options to control how it operates.
+
+`--help'
+`-h'
+     Print a summary of the options to `configure', and exit.
+
+`--version'
+`-V'
+     Print the version of Autoconf used to generate the `configure'
+     script, and exit.
+
+`--cache-file=FILE'
+     Enable the cache: use and save the results of the tests in FILE,
+     traditionally `config.cache'.  FILE defaults to `/dev/null' to
+     disable caching.
+
+`--config-cache'
+`-C'
+     Alias for `--cache-file=config.cache'.
+
+`--quiet'
+`--silent'
+`-q'
+     Do not print messages saying which checks are being made.  To
+     suppress all normal output, redirect it to `/dev/null' (any error
+     messages will still be shown).
+
+`--srcdir=DIR'
+     Look for the package's source code in directory DIR.  Usually
+     `configure' can determine that directory automatically.
+
+`configure' also accepts some other, not widely useful, options.  Run
+`configure --help' for more details.
+

Makefile.am

+## Process this file with automake to produce Makefile.in
+
+# Copyright 2010 University of Helsinki
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+# to silence:
+# libtoolize: Consider adding `-I m4' to ACLOCAL_AMFLAGS in Makefile.am.
+ACLOCAL_AMFLAGS=-I m4
+
+# targets
+if EXTRA_DEMOS
+CONFERENCE_DEMOS=hfst-ospell-norvig hfst-ospell-fsmnlp-2012 hfst-ospell-cicling\
+				 hfst-ospell-survey hfst-ospell-lrec2013 hfst-ispell
+endif # EXTRA_DEMOS
+
+if HFST_OSPELL_OFFICE
+MAYBE_HFST_OSPELL_OFFICE=hfst-ospell-office
+endif # HFST_OSPELL_OFFICE
+
+bin_PROGRAMS=hfst-ospell $(MAYBE_HFST_OSPELL_OFFICE) $(CONFERENCE_DEMOS)
+lib_LTLIBRARIES=libhfstospell.la
+man1_MANS=hfst-ospell.1 hfst-ospell-office.1
+
+PKG_LIBS=
+PKG_CXXFLAGS=
+
+if WANT_ARCHIVE
+PKG_LIBS+=$(LIBARCHIVE_LIBS)
+PKG_CXXFLAGS+=$(LIBARCHIVE_CFLAGS)
+endif
+
+if WANT_LIBXMLPP
+PKG_LIBS+=$(LIBXMLPP_LIBS)
+PKG_CXXFLAGS+=$(LIBXMLPP_CFLAGS)
+endif
+
+if WANT_TINYXML2
+PKG_LIBS+=$(TINYXML2_LIBS)
+PKG_CXXFLAGS+=$(TINYXML2_CFLAGS)
+endif
+
+# library parts
+libhfstospell_la_SOURCES=hfst-ol.cc ospell.cc \
+						 ZHfstOspeller.cc ZHfstOspellerXmlMetadata.cc
+libhfstospell_la_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) $(PKG_CXXFLAGS)
+libhfstospell_la_LDFLAGS=-no-undefined -version-info 10:0:0 \
+						 $(PKG_LIBS)
+
+# link sample program against library here
+hfst_ospell_SOURCES=main.cc
+hfst_ospell_LDADD=libhfstospell.la
+hfst_ospell_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) \
+					 $(PKG_CXXFLAGS)
+
+if HFST_OSPELL_OFFICE
+
+hfst_ospell_office_SOURCES=office.cc
+hfst_ospell_office_LDADD=libhfstospell.la
+hfst_ospell_office_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) $(PKG_CXXFLAGS)
+
+endif # HFST_OSPELL_OFFICE
+
+if EXTRA_DEMOS
+
+hfst_ospell_norvig_SOURCES=main-norvig.cc
+hfst_ospell_norvig_LDADD=libhfstospell.la
+hfst_ospell_norvig_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) \
+							$(PKG_CXXFLAGS)
+
+hfst_ospell_cicling_SOURCES=main-cicling.cc
+hfst_ospell_cicling_LDADD=libhfstospell.la
+hfst_ospell_cicling_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) \
+							 $(PKG_CXXFLAGS)
+
+hfst_ospell_lrec2013_SOURCES=main-lrec2013.cc
+hfst_ospell_lrec2013_LDADD=libhfstospell.la
+hfst_ospell_lrec2013_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) \
+							$(PKG_CXXFLAGS)
+
+hfst_ospell_survey_SOURCES=main-survey.cc
+hfst_ospell_survey_LDADD=libhfstospell.la
+hfst_ospell_survey_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) \
+							$(PKG_CXXFLAGS)
+
+hfst_ospell_fsmnlp_2012_SOURCES=main-fsmnlp-2012.cc
+hfst_ospell_fsmnlp_2012_LDADD=libhfstospell.la
+hfst_ospell_fsmnlp_2012_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) \
+								 $(PKG_CXXFLAGS)
+endif # EXTRA_DEMOS
+
+if EXTRA_DEMOS
+
+hfst_ispell_SOURCES=main-ispell.cc
+hfst_ispell_LDADD=libhfstospell.la
+hfst_ispell_CXXFLAGS=$(AM_CXXFLAGS) $(CXXFLAGS) \
+							$(PKG_CXXFLAGS)
+
+endif # EXTRA_DEMOS
+
+# install headers for library in hfst's includedir
+include_HEADERS=hfst-ol.h ospell.h ol-exceptions.h \
+				ZHfstOspeller.h ZHfstOspellerXmlMetadata.h \
+				hfstol-stdafx.h
+
+# pkgconfig
+pkgconfigdir=$(libdir)/pkgconfig
+pkgconfig_DATA=hfstospell.pc
+
+# tests
+TESTS=tests/basic-zhfst.sh tests/basic-edit1.sh \
+	  tests/empty-descriptions.sh tests/empty-titles.sh tests/empty-locale.sh \
+	  tests/trailing-spaces.sh tests/bad-errormodel.sh tests/empty-zhfst.sh \
+	  tests/analyse-spell.sh tests/no-errormodel.sh
+if WANT_ARCHIVE
+XFAIL_TESTS=tests/empty-descriptions.sh tests/empty-titles.sh tests/empty-locale.sh tests/empty-zhfst.sh
+else
+XFAIL_TESTS=tests/empty-descriptions.sh tests/empty-titles.sh tests/empty-locale.sh tests/empty-zhfst.sh \
+	tests/basic-zhfst.sh tests/basic-edit1.sh tests/trailing-spaces.sh tests/bad-errormodel.sh \
+	tests/analyse-spell.sh tests/no-errormodel.sh
+endif
+
+if CAN_DOXYGEN
+doxygen:
+	$(DOXYGEN)
+endif
+
+EXTRA_DIST=hfst-ospell.1 hfst-ospell-office.1 tests/basic-zhfst.sh tests/basic-edit1.sh \
+	  tests/empty-descriptions.sh tests/empty-titles.sh tests/empty-locale.sh \
+	  tests/trailing-spaces.sh tests/bad-errormodel.sh tests/empty-zhfst.sh \
+	  tests/analyse-spell.sh tests/no-errormodel.sh \
+	  tests/empty-descriptions.sh tests/empty-titles.sh tests/empty-locale.sh tests/empty-zhfst.sh \
+	  tests/acceptor.basic.txt tests/analyser.default.txt tests/errmodel.basic.txt tests/errmodel.edit1.txt tests/errmodel.extrachars.txt \
+	  tests/test.strings \
+	  tests/bad_errormodel.zhfst tests/empty_descriptions.zhfst tests/empty_locale.zhfst tests/empty_titles.zhfst tests/no_errormodel.zhfst \
+	  tests/speller_analyser.zhfst tests/speller_basic.zhfst tests/speller_edit1.zhfst tests/trailing_spaces.zhfst \
+	  tests/basic_test.xml tests/empty_descriptions.xml tests/empty_locale.xml tests/empty_titles.xml tests/no_errmodel.xml tests/trailing_spaces.xml

NEWS

+NEWS for hfst-ospell
+====================
+
+This file contains all noteworthy changes in HFST-ospell development between
+releases. For full listing of changes see ChangeLog.
+
+Noteworthy changes in 0.5.0
+---------------------------
+
+* rename hfst_ol namespace to hfst_ospell to avoid conflicts
+* improve distinguishing between lemmas and tags in analysis
+* fix issue #37
+* avoid shadowing multicharacter ascii-beginning symbols
+* use minimal XML parsing to get locale, title, and description for Voikko and other frontends
+
+Noteworthy changes in 0.4.5
+---------------------------
+
+* this is a bugfix release
+
+Noteworthy changes in 0.4.4
+---------------------------
+
+* restructure order of files
+* remove HFST dependency
+* fix issue #26
+* check for failures in archive extraction
+* fix dll issues on windows
+* allow building without XML support
+
+Noteworthy changes in 0.4.3
+---------------------------
+
+* fixes for big endian conversions
+* use max version for tinyxml
+
+Noteworthy changes in 0.4.2
+---------------------------
+
+* small modifications to tests and documentation
+
+Noteworthy changes in 0.4.1
+---------------------------
+
+* set time cutoff to 6.0 seconds for ospell-office
+* minor bug fixes
+
+Noteworthy changes in 0.4.0
+---------------------------
+
+* add option --beam to hfst-ospell for restricting the search to a margin above the optimum
+* add option --time-cutoff to hfst-ospell for restricting the time spent on searching for better corrections
+* add option --enable-hfst-ospell-office to configure (defaults to yes)
+* use libarchive2 if libarchive3 is not available
+* determine and use highest supported C++ standard when compiling
+* support unknown and identity arcs both in the lexicon and error model
+
+Noteworthy changes in 0.3.0
+---------------------------
+
+* New API for analysing and suggesting
+* Moved code from headers to implementation files (API change)
+* Added Doxygen to mark stable API
+* Fixes for bad and malformed metadara handling
+* Limiting number of suggestions now works
+
+Noteworthy changes in 0.2.5
+---------------------------
+
+* optional support for tinyxml2
+* preliminary support for two-tape automata and *analysis* lookup
+* conference demos are no longer built by default
+* libarchive newer than 3 allowed
+
+Noteworthy changes in 0.2.4
+---------------------------
+
+* renamed the package hfstospell (from hfst-ospell), the previous rename caused
+  build issues.
+
+Noteworthy changes in 0.2.3
+---------------------------
+
+* fixed a bug that caused certain types of paths with flag diacritics not to
+  be accepted.
+
+Noteworthy changes in 0.2.2
+---------------------------
+
+* Memory and speed improvements; data structures for automaton changed
+
+* Tests and bug fixes for building
+
+Noteworthy changes in 0.2.1
+---------------------------
+
+* Added support for extracting zipped transducer collections to memory instead
+  of temporary files
+
+* Changed from libxml to libxml++ for XML parsing
+
+Noteworthy changes in 0.2.0
+---------------------------
+
+* Added support for zipped XML based transducer collection format.
+
+* Few new frontends for various experiments
+
+* Lots of metadata everywhere
+
+Noteworthy changes in 0.1.1
+---------------------------
+
+* Added autoconfiscation to avoid bugs like missing Makefile in tarball
+
+Noteworthy changes in 0.1
+-------------------------
+
+* First release
+
+

README

+# Hfst-ospell library and toy commandline tester
+
+This is a minimal hfst optimized lookup format based spell checker library and
+a demonstrational implementation of command line based spell checker. The
+library is licenced under Apache licence version 2, other licences can be
+obtained from University of Helsinki.
+
+[![Build Status](https://travis-ci.org/hfst/hfst-ospell.svg?branch=master)](https://travis-ci.org/hfst/hfst-ospell)
+
+## Dependencies
+
+- libxml++2
+- libarchive
+
+## Debian packages for dependencies
+
+- libxml++2-dev
+- libarchive-dev
+
+## Usage
+
+Usage in external programs:
+
+    #include <ospell.h>
+
+and compile your project with:
+
+    $(pkg-config --cflags hfstospell)
+
+and link with:
+
+    $(pkg-config --libs hfstospell)
+
+## Programming examples
+
+The library lives in a namespace called hfst_ospell. Pass (weighted!) Transducer
+pointers to the Speller constructor, eg.:
+
+    FILE * error_source = fopen(error_filename, "r");
+    FILE * lexicon_file = fopen(lexicon_filename, "r");
+    hfst_ospell::Transducer * error;
+    hfst_ospell::Transducer * lexicon;
+    try {
+        error = new hfst_ospell::Transducer(error_source);
+        lexicon = new hfst_ospell::Transducer(lexicon_file);
+    } catch (hfst_ospell::TransducerParsingException& e) {
+            /* problem with transducer file, usually completely
+            different type of file - there's no magic number
+            in the header to check for this */
+        }
+    hfst_ospell::Speller * speller;
+    try {
+        speller = new hfst_ospell::Speller(error, lexicon);
+    } catch (hfst_ospell::AlphabetTranslationException& e) {
+        /* problem with translating between the two alphabets */
+    }
+
+
+And use the functions:
+
+    // returns true if line is found in lexicon
+    bool hfst_ospell::Speller::check(char * line);
+
+    // CorrectionQueue is a priority queue, sorted by weight
+    hfst_ospell::CorrectionQueue hfst_ospell::Speller::correct(char * line);
+
+
+to communicate with it. See main.cc for a concrete usage example. 
+
+## Command-line tool
+
+Main.cc provides a demo utility with the following help message:
+
+    Usage: hfst-ospell [OPTIONS] ERRORSOURCE LEXICON
+    Run a composition of ERRORSOURCE and LEXICON on standard input and
+    print corrected output
+
+      -h, --help                  Print this help message
+      -V, --version               Print version information
+      -v, --verbose               Be verbose
+      -q, --quiet                 Don't be verbose (default)
+      -s, --silent                Same as quiet
+
+
+    Report bugs to hfst-bugs@ling.helsinki.fi
+
+# Use in real-world applications
+
+The HFST based spellers can be used in real applications with help of
+[voikko](http://voikko.sf.net). Voikko in turn can be used with enchant,
+libreoffice, and firefox.
+

ZHfstOspeller.cc

+/* -*- Mode: C++ -*- */
+// Copyright 2010 University of Helsinki
+//
+//  Licensed under the Apache License, Version 2.0 (the "License");
+//  you may not use this file except in compliance with the License.
+//  You may obtain a copy of the License at
+//
+//      http://www.apache.org/licenses/LICENSE-2.0
+//
+//  Unless required by applicable law or agreed to in writing, software
+//  distributed under the License is distributed on an "AS IS" BASIS,
+//  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+//  See the License for the specific language governing permissions and
+//  limitations under the License.
+
+#if HAVE_CONFIG_H
+#  include <config.h>
+#endif
+
+// C
+#if HAVE_LIBARCHIVE
+#  include <archive.h>
+#  include <archive_entry.h>
+#endif
+// C++
+#if HAVE_LIBXML
+#  include <libxml++/libxml++.h>
+#endif
+#include <string>
+#include <map>
+
+using std::string;
+using std::map;
+
+// local
+#include "ospell.h"
+#include "hfst-ol.h"
+#include "ZHfstOspeller.h"
+
+namespace hfst_ospell
+  {
+
+#if HAVE_LIBARCHIVE
+inline std::string extract_to_mem(archive* ar, archive_entry* entry) {
+    size_t full_length = 0;
+    const struct stat* st = archive_entry_stat(entry);
+    size_t buffsize = st->st_size;
+    if (buffsize == 0) {
+        std::cerr << archive_error_string(ar) << std::endl;
+        throw ZHfstZipReadingError("Reading archive resulted in zero length entry");
+    }
+
+    std::string buff(buffsize, 0);
+    for (;;) {
+        ssize_t curr = archive_read_data(ar, &buff[0] + full_length, buffsize - full_length);
+        if (0 == curr) {
+            break;
+        }
+        else if (ARCHIVE_RETRY == curr) {
+            continue;
+        }
+        else if (ARCHIVE_FAILED == curr) {
+            throw ZHfstZipReadingError("Archive broken (ARCHIVE_FAILED)");
+        }
+        else if (curr < 0) {
+            throw ZHfstZipReadingError("Archive broken...");
+        }
+        else {
+            full_length += curr;
+        }
+    }
+
+    if (full_length == 0) {
+        std::cerr << archive_error_string(ar) << std::endl;
+        throw ZHfstZipReadingError("Reading archive resulted in zero length");
+    }
+
+    return buff;
+}
+
+inline Transducer* transducer_to_mem(archive* ar, archive_entry* entry) {
+    std::string buff = extract_to_mem(ar, entry);
+    Transducer *trans = new Transducer(&buff[0]);
+    return trans;
+}
+
+inline char* extract_to_tmp_dir(archive* ar) {
+    char* rv = strdup("/tmp/zhfstospellXXXXXXXX");
+    int temp_fd = mkstemp(rv);
+    int rr = archive_read_data_into_fd(ar, temp_fd);
+    if ((rr != ARCHIVE_EOF) && (rr != ARCHIVE_OK)) {
+        throw ZHfstZipReadingError("Archive not EOF'd or OK'd");
+    }
+    close(temp_fd);
+    return rv;
+}
+
+inline Transducer* transducer_to_tmp_dir(archive* ar) {
+    char *filename = extract_to_tmp_dir(ar);
+    FILE* f = fopen(filename, "rb");
+    if (f == nullptr) {
+        throw ZHfstTemporaryWritingError("reading acceptor back from temp file");
+    }
+    return new Transducer(f);
+}
+
+#endif // HAVE_LIBARCHIVE
+
+ZHfstOspeller::ZHfstOspeller() :
+    suggestions_maximum_(0),
+    maximum_weight_(-1.0),
+    beam_(-1.0),
+    time_cutoff_(0.0),
+    can_spell_(false),
+    can_correct_(false),
+    can_analyse_(true),
+    current_speller_(0),
+    current_sugger_(0)
+    {
+    }
+
+ZHfstOspeller::~ZHfstOspeller()
+  {
+    if ((current_speller_ != NULL) && (current_sugger_ != NULL))
+      {
+        if (current_speller_ != current_sugger_)
+          {
+            delete current_speller_;
+            delete current_sugger_;
+          }
+        else
+          {
+            delete current_speller_;
+          }
+        current_sugger_ = 0;
+        current_speller_ = 0;
+      }
+    for (auto& acceptor : acceptors_)
+      {
+        delete acceptor.second;
+      }
+    for (auto& errmodel : errmodels_)
+      {
+        delete errmodel.second;
+      }
+    can_spell_ = false;
+    can_correct_ = false;
+  }
+
+void
+ZHfstOspeller::inject_speller(Speller * s)
+  {
+      current_speller_ = s;
+      current_sugger_ = s;
+      can_spell_ = true;
+      can_correct_ = true;
+  }
+
+void
+ZHfstOspeller::set_queue_limit(unsigned long limit)
+  {
+    suggestions_maximum_ = limit;
+  }
+
+void
+ZHfstOspeller::set_weight_limit(Weight limit)
+  {
+    maximum_weight_ = limit;
+  }
+
+void
+ZHfstOspeller::set_beam(Weight beam)
+  {
+      beam_ = beam;
+  }
+
+void
+ZHfstOspeller::set_time_cutoff(float time_cutoff)
+  {
+      time_cutoff_ = time_cutoff;
+  }
+
+bool
+ZHfstOspeller::spell(const string& wordform)
+  {
+    if (can_spell_ && (current_speller_ != 0))
+      {
+        char* wf = strdup(wordform.c_str());
+        bool rv = current_speller_->check(wf);
+        free(wf);
+        return rv;
+      }
+    return false;
+  }
+
+CorrectionQueue
+ZHfstOspeller::suggest(const string& wordform)
+  {
+    CorrectionQueue rv;
+    if ((can_correct_) && (current_sugger_ != 0))
+      {
+        char* wf = strdup(wordform.c_str());
+        rv = current_sugger_->correct(wf,
+                                      suggestions_maximum_,
+                                      maximum_weight_,
+                                      beam_,
+                                      time_cutoff_);
+        free(wf);
+        return rv;
+      }
+    return rv;
+  }
+
+AnalysisQueue
+ZHfstOspeller::analyse(const string& wordform, bool ask_sugger)
+  {
+    AnalysisQueue rv;
+    char* wf = strdup(wordform.c_str());
+    if ((can_analyse_) && (!ask_sugger) && (current_speller_ != 0))
+      {
+          rv = current_speller_->analyse(wf);
+      }
+    else if ((can_analyse_) && (ask_sugger) && (current_sugger_ != 0))
+      {
+          rv = current_sugger_->analyse(wf);
+      }
+    free(wf);
+    return rv;
+  }
+
+AnalysisSymbolsQueue
+ZHfstOspeller::analyseSymbols(const string& wordform, bool ask_sugger)
+  {
+    AnalysisSymbolsQueue rv;
+    char* wf = strdup(wordform.c_str());
+    if ((can_analyse_) && (!ask_sugger) && (current_speller_ != 0))
+      {
+          rv = current_speller_->analyseSymbols(wf);
+      }
+    else if ((can_analyse_) && (ask_sugger) && (current_sugger_ != 0))
+      {
+          rv = current_sugger_->analyseSymbols(wf);
+      }
+    free(wf);
+    return rv;
+  }
+
+AnalysisCorrectionQueue
+ZHfstOspeller::suggest_analyses(const string& wordform)
+  {
+    AnalysisCorrectionQueue rv;
+    // FIXME: should be atomic
+    CorrectionQueue cq = suggest(wordform);
+    while (cq.size() > 0)
+      {
+        AnalysisQueue aq = analyse(cq.top().first, true);
+        while (aq.size() > 0)
+          {
+            StringPair sp(cq.top().first, aq.top().first);
+            StringPairWeightPair spwp(sp, aq.top().second);
+            rv.push(spwp);
+            aq.pop();
+          }
+        cq.pop();
+      }
+    return rv;
+  }
+
+void
+ZHfstOspeller::read_zhfst(const string& filename)
+  {
+#if HAVE_LIBARCHIVE
+    struct archive* ar = archive_read_new();
+    struct archive_entry* entry = 0;
+
+#if USE_LIBARCHIVE_2
+    archive_read_support_compression_all(ar);
+#else
+    archive_read_support_filter_all(ar);
+#endif // USE_LIBARCHIVE_2
+
+    archive_read_support_format_all(ar);
+    int rr = archive_read_open_filename(ar, filename.c_str(), 10240);
+    if (rr != ARCHIVE_OK)
+      {
+        throw ZHfstZipReadingError("Archive not OK");
+      }
+    for (int rr = archive_read_next_header(ar, &entry);
+         rr != ARCHIVE_EOF;
+         rr = archive_read_next_header(ar, &entry))
+      {
+        if (rr != ARCHIVE_OK)
+          {
+            throw ZHfstZipReadingError("Archive not OK");
+          }
+        char* filename = strdup(archive_entry_pathname(entry));
+        if (strncmp(filename, "acceptor.", strlen("acceptor.")) == 0) {
+            Transducer* trans = nullptr;
+
+#if ZHFST_EXTRACT_TO_MEM == 1
+            // Try to memory first...
+            try {
+                trans = transducer_to_mem(ar, entry);
+            }
+            catch (...) {
+                // If that failed, try to /tmp
+                //std::cerr << "Failed to memory - falling back to /tmp" << std::endl;
+                trans = transducer_to_tmp_dir(ar);
+            }
+#else
+            // Try to /tmp first...
+            try {
+                trans = transducer_to_tmp_dir(ar);
+            }
+            catch (...) {
+                // If that failed, try to memory
+                //std::cerr << "Failed to /tmp - falling back to memory" << std::endl;
+                trans = transducer_to_mem(ar, entry);
+            }
+#endif
+            if (trans == nullptr) {
+                throw ZHfstZipReadingError("Failed to extract acceptor");
+            }
+
+            char* p = filename;
+            p += strlen("acceptor.");
+            size_t descr_len = 0;
+            for (const char* q = p; *q != '\0'; q++)
+              {
+                if (*q == '.')
+                  {
+                    break;
+                  }
+                else
+                    {
+                      descr_len++;
+                    }
+              }
+
+            char* descr = hfst_strndup(p, descr_len);
+            acceptors_[descr] = trans;
+            free(descr);
+          }
+        else if (strncmp(filename, "errmodel.", strlen("errmodel.")) == 0) {
+            Transducer* trans = nullptr;
+
+#if ZHFST_EXTRACT_TO_MEM == 1
+            // Try to memory first...
+            try {
+                trans = transducer_to_mem(ar, entry);
+            }
+            catch (...) {
+                // If that failed, try to /tmp
+                //std::cerr << "Failed to memory - falling back to /tmp" << std::endl;
+                trans = transducer_to_tmp_dir(ar);
+            }
+#else
+            // Try to /tmp first...
+            try {
+                trans = transducer_to_tmp_dir(ar);
+            }
+            catch (...) {
+                // If that failed, try to memory
+                //std::cerr << "Failed to /tmp - falling back to memory" << std::endl;
+                trans = transducer_to_mem(ar, entry);
+            }
+#endif
+            if (trans == nullptr) {
+                throw ZHfstZipReadingError("Failed to extract error model");
+            }
+
+            const char* p = filename;
+            p += strlen("errmodel.");
+            size_t descr_len = 0;
+            for (const char* q = p; *q != '\0'; q++)
+              {
+                if (*q == '.')
+                  {
+                    break;
+                  }
+                else
+                  {
+                    descr_len++;
+                  }
+              }
+
+            char* descr = hfst_strndup(p, descr_len);
+            errmodels_[descr] = trans;
+            free(descr);
+          } // if acceptor or errmodel
+        else if (strcmp(filename, "index.xml") == 0) {
+            // Always try to memory first, as index.xml is tiny
+            try {
+                std::string full_data = extract_to_mem(ar, entry);
+                metadata_.read_xml(&full_data[0], full_data.size());
+            }
+            catch (...) {
+                char* temporary = extract_to_tmp_dir(ar);
+                metadata_.read_xml(temporary);
+            }
+          }
+        else
+          {
+            fprintf(stderr, "Unknown file in archive %s\n", filename);
+          }
+        free(filename);
+      } // while r != ARCHIVE_EOF
+    archive_read_close(ar);
+
+#if USE_LIBARCHIVE_2
+    archive_read_finish(ar);
+#else
+    archive_read_free(ar);
+#endif // USE_LIBARCHIVE_2
+
+    if ((errmodels_.find("default") != errmodels_.end()) &&
+        (acceptors_.find("default") != acceptors_.end()))
+      {
+        current_speller_ = new Speller(
+                                       errmodels_["default"],
+                                       acceptors_["default"]
+                                       );
+        current_sugger_ = current_speller_;
+        can_spell_ = true;
+        can_correct_ = true;
+      }
+    else if ((acceptors_.size() > 0) && (errmodels_.size() > 0))
+      {
+        fprintf(stderr, "Could not find default speller, using %s %s\n",
+                acceptors_.begin()->first.c_str(),
+                errmodels_.begin()->first.c_str());
+        current_speller_ = new Speller(
+                                       errmodels_.begin()->second,
+                                       acceptors_.begin()->second
+                                       );
+        current_sugger_ = current_speller_;
+        can_spell_ = true;
+        can_correct_ = true;
+      }
+    else if ((acceptors_.size() > 0) &&
+             (acceptors_.find("default") != acceptors_.end()))
+      {
+        current_speller_ = new Speller(0, acceptors_["default"]);
+        current_sugger_ = current_speller_;
+        can_spell_ = true;
+        can_correct_ = false;
+      }
+    else if (acceptors_.size() > 0)
+      {
+        current_speller_ = new Speller(0, acceptors_.begin()->second);
+        current_sugger_ = current_speller_;
+        can_spell_ = true;
+        can_correct_ = false;
+      }
+    else
+      {
+        throw ZHfstZipReadingError("No automata found in zip");
+      }
+    can_analyse_ = can_spell_ | can_correct_;
+#else
+    throw ZHfstZipReadingError("Zip support was disabled");
+#endif // HAVE_LIBARCHIVE
+  }
+
+
+const ZHfstOspellerXmlMetadata&
+ZHfstOspeller::get_metadata() const
+  {
+    return metadata_;
+  }
+
+string
+ZHfstOspeller::metadata_dump() const
+  {
+    return metadata_.debug_dump();
+
+  }
+} // namespace hfst_ospell

ZHfstOspeller.h

+/* -*- Mode: C++ -*- */
+// Copyright 2010 University of Helsinki
+//
+//  Licensed under the Apache License, Version 2.0 (the "License");
+//  you may not use this file except in compliance with the License.
+//  You may obtain a copy of the License at
+//
+//      http://www.apache.org/licenses/LICENSE-2.0
+//
+//  Unless required by applicable law or agreed to in writing, software
+//  distributed under the License is distributed on an "AS IS" BASIS,
+//  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+//  See the License for the specific language governing permissions and
+//  limitations under the License.
+
+//! @mainpage API to HFST ospell WFST spell-checking
+//!
+//! The hfst-ospell API has several layers for different end-users. A suggested
+//! starting point for new user is the @c ZHfstOspeller object, which reads an
+//! automaton set from zipped hfst file with metadata and provides high level
+//! access to it with generic spell-checking, correction and analysis functions.
+//! Second level of access is the Speller object, which can be used to
+//! construct spell-checker with two automata and traverse it and query
+//! low-level properties. The Speller is constructed with two Transducer objects
+//! which are the low-level access point to the automata with all the gory
+//! details of transition tables and symbol translations, headers and such.
+
+#ifndef HFST_OSPELL_ZHFSTOSPELLER_H_
+#define HFST_OSPELL_ZHFSTOSPELLER_H_
+
+#include "hfstol-stdafx.h"
+
+#if HAVE_CONFIG_H
+#  include <config.h>
+#endif
+
+#include <stdexcept>
+#include <map>
+
+#include "ospell.h"
+#include "hfst-ol.h"
+#include "ZHfstOspellerXmlMetadata.h"
+
+namespace hfst_ospell
+  {
+    //! @brief ZHfstOspeller class holds one speller contained in one
+    //!        zhfst file.
+    //!        Ospeller can perform all basic writer tool functionality that
+    //!        is supporte by the automata in the zhfst archive.
+    class ZHfstOspeller
+      {
+        public:
+            //! @brief create speller with default values for undefined
+            //!        language.
+            OSPELL_API ZHfstOspeller();
+            //! @brief destroy all automata used by the speller.
+            OSPELL_API ~ZHfstOspeller();
+
+            //! @brief assign a speller-suggestor circumventing the ZHFST format
+            OSPELL_API void inject_speller(Speller * s);
+            //! @brief set upper limit to priority queue when performing
+            //         suggestions or analyses.
+            OSPELL_API void set_queue_limit(unsigned long limit);
+            //! @brief set upper limit for weights
+            OSPELL_API void set_weight_limit(Weight limit);
+            //! @brief set search beam
+            OSPELL_API void set_beam(Weight beam);
+            //! @brief set time cutoff for correcting
+            OSPELL_API void set_time_cutoff(float time_cutoff);
+            //! @brief construct speller from named file containing valid
+            //!        zhfst archive.
+            OSPELL_API void read_zhfst(const std::string& filename);
+
+            //! @brief  check if the given word is spelled correctly
+            OSPELL_API bool spell(const std::string& wordform);
+            //! @brief construct an ordered set of corrections for misspelled
+            //!        word form.
+            OSPELL_API CorrectionQueue suggest(const std::string& wordform);
+            //! @brief analyse word form morphologically
+            //! @param wordform   the string to analyse
+            //! @param ask_sugger whether to use the spelling correction model
+            //                    instead of the detection model
+            AnalysisQueue analyse(const std::string& wordform,
+                                  bool ask_sugger = false);
+            //! @brief analyse word form morphologically, unconcatenated output
+            //!        strings (making it easier to find Multichar_symbols of
+            //!        the FST)
+            //! @param wordform   the string to analyse
+            //! @param ask_sugger whether to use the spelling correction model
+            //                    instead of the detection model
+            AnalysisSymbolsQueue analyseSymbols(const std::string& wordform,
+                                                bool ask_sugger = false);
+            //! @brief construct an ordered set of corrections with analyses
+            AnalysisCorrectionQueue suggest_analyses(const std::string&
+                                                     wordform);
+            //! @brief hyphenate word form
+            HyphenationQueue hyphenate(const std::string& wordform);
+
+            //! @brief get access to metadata read from XML.
+            const ZHfstOspellerXmlMetadata& get_metadata() const;
+            //! @brief create string representation of the speller for
+            //!        programmer to debug
+            std::string metadata_dump() const;
+        private:
+            //! @brief file or path where the speller came from
+            std::string filename_;
+            //! @brief upper bound for suggestions generated and given
+            unsigned long suggestions_maximum_;
+            //! @brief upper bound for suggestion weight generated and given
+            Weight maximum_weight_;
+            //! @brief upper bound for search beam around best candidate
+            Weight beam_;
+            //! @brief upper bound for search time in seconds
+            float time_cutoff_;
+            //! @brief whether automatons loaded yet can be used to check
+            //!        spelling
+            bool can_spell_;
+            //! @brief whether automatons loaded yet can be used to correct
+            //!        word forms
+            bool can_correct_;
+            //! @brief whether automatons loaded yet can be used to analyse
+            //!        word forms
+            bool can_analyse_;
+            //! @brief whether automatons loaded yet can be used to hyphenate
+            //!        word forms
+            bool can_hyphenate_;
+            //! @brief dictionaries loaded
+            std::map<std::string, Transducer*> acceptors_;
+            //! @brief error models loaded
+            std::map<std::string, Transducer*> errmodels_;
+            //! @brief pointer to current speller
+            Speller* current_speller_;
+            //! @brief pointer to current correction model
+            Speller* current_sugger_;
+            //! @brief pointer to current morphological analyser
+            Speller* current_analyser_;
+            //! @brief pointer to current hyphenator
+            Transducer* current_hyphenator_;
+            //! @brief the metadata of loaded speller
+            ZHfstOspellerXmlMetadata metadata_;
+      };
+
+    //! @brief Top-level exception for zhfst handling.
+
+    //! Contains a human-readable error message that can be displayed to
+    //! end-user as additional info when either solving exception or exiting.
+    class ZHfstException : public std::runtime_error
+      {
+        public:
+            ZHfstException() : std::runtime_error("unknown") {}
+            //! @brief construct error with human readable message.
+            //!
+            //! the message will be displayed when recovering or dying from
+            //! exception
+            explicit ZHfstException(const std::string& message) : std::runtime_error(message) {}
+      };
+
+    //! @brief Generic error in metadata parsing.
+    //
+    //! Gets raised if metadata is erroneous or missing.
+    class ZHfstMetaDataParsingError : public ZHfstException
+    {
+        public:
+            explicit ZHfstMetaDataParsingError(const std::string& message) : ZHfstException(message) {}
+    };
+
+    //! @brief Exception for XML parser errors.
+    //
+    //! Gets raised if underlying XML parser finds an error in XML data.
+    //! Errors include non-valid XML, missing or erroneous attributes or
+    //! elements, etc.
+    class ZHfstXmlParsingError : public ZHfstException
+    {
+      public:
+          explicit ZHfstXmlParsingError(const std::string& message) : ZHfstException(message) {}
+    };
+
+    //! @brief Generic error while reading zip file.
+    //!
+    //! Happens when libarchive is unable to proceed reading zip file or
+    //! zip file is missing required files.
+    class ZHfstZipReadingError : public ZHfstException
+    {
+      public:
+          explicit ZHfstZipReadingError(const std::string& message) : ZHfstException(message) {}
+    };
+
+    //! @brief Error when writing to temporary location.
+    //
+    //! This exception gets thrown, when e.g., zip extraction is unable to
+    //! find or open temporary file for writing.
+    class ZHfstTemporaryWritingError : public ZHfstException
+    {
+      public:
+          explicit ZHfstTemporaryWritingError(const std::string& message) : ZHfstException(message) {}
+    };
+
+  } // namespace hfst_ospell
+
+
+#endif // HFST_OSPELL_OSPELLER_SET_H_
+// vim: set ft=cpp.doxygen:

ZHfstOspellerXmlMetadata.h

+/* -*- Mode: C++ -*- */
+// Copyright 2010 University of Helsinki
+//
+//  Licensed under the Apache License, Version 2.0 (the "License");
+//  you may not use this file except in compliance with the License.
+//  You may obtain a copy of the License at
+//
+//      http://www.apache.org/licenses/LICENSE-2.0
+//
+//  Unless required by applicable law or agreed to in writing, software
+//  distributed under the License is distributed on an "AS IS" BASIS,
+//  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+//  See the License for the specific language governing permissions and
+//  limitations under the License.
+
+#ifndef HFST_OSPELL_ZHFSTOSPELLERXMLMETADATA_H_
+#define HFST_OSPELL_ZHFSTOSPELLERXMLMETADATA_H_ 1
+
+#include "hfstol-stdafx.h"
+
+#if HAVE_CONFIG_H
+#  include <config.h>
+#endif
+
+#include <map>
+
+using std::map;
+
+#if HAVE_LIBXML
+#  include <libxml++/libxml++.h>
+#elif HAVE_TINYXML2
+#  include <tinyxml2.h>
+#endif
+
+#include "ospell.h"
+#include "hfst-ol.h"
+
+namespace hfst_ospell 
+  {
+    //! @brief data type for associating set of translations to languages.
+    typedef std::map<std::string,std::string> LanguageVersions;
+
+
+    //! @brief ZHfstOspellerInfo represents one info block of an zhfst file.
+    //! @see https://victorio.uit.no/langtech/trunk/plan/proof/doc/lexfile-spec.xml
+    struct ZHfstOspellerInfoMetadata
+      {
+        //! @brief active locale of speller in BCP format
+        std::string locale_;
+        //! @brief transalation of titles to all languages
+        LanguageVersions title_;
+        //! @brief translation of descriptions to all languages
+        LanguageVersions description_;
+        //! @brief version defintition as free form string
+        std::string version_;
+        //! @brief vcs revision as string
+        std::string vcsrev_;
+        //! @brief date for age of speller as string
+        std::string date_;
+        //! @brief producer of the speller
+        std::string producer_;
+        //! @brief email address of the speller
+        std::string email_;
+        //! @brief web address of the speller
+        std::string website_;
+      };
+    //! @brief Represents one acceptor block in XML metadata
+    struct ZHfstOspellerAcceptorMetadata
+      {
+        //! @brief unique id of acceptor
+        std::string id_;
+        //! @brief descr part of acceptor
+        std::string descr_;
+        //! @brief type of dictionary
+        std::string type_;
+        //! @brief type of transducer
+        std::string transtype_;
+        //! @brief titles of dictionary in languages
+        LanguageVersions title_;
+        //! @brief descriptions of dictionary in languages
+        LanguageVersions description_;
+      };
+    //! @brief Represents one errmodel block in XML metadata
+    struct ZHfstOspellerErrModelMetadata
+      {
+        //! @brief id of each error model in set
+        std::string id_;
+        //! @brief descr part of each id
+        std::string descr_;
+        //! @brief title of error models in languages
+        LanguageVersions title_;
+        //! @brief description of error models in languages
+        LanguageVersions description_;
+        //! @brief types of error models
+        std::vector<std::string> type_; 
+        //! @brief models
+        std::vector<std::string> model_;
+      };
+    //! @brief holds one index.xml metadata for whole ospeller
+    class ZHfstOspellerXmlMetadata
+      {
+        public:
+        //! @brief construct metadata for undefined language and other default
+        //!        values
+        ZHfstOspellerXmlMetadata();
+        //! @brief read metadata from XML file by @a filename.
+        void read_xml(const std::string& filename);
+        //! @brief read XML from in memory @a data pointer with given @a length
+        //!
+        //! Depending on the XML library compiled in, the data length may
+        //! be omitted and the buffer may be overflown.
+        void read_xml(const char* data, size_t data_length);
+        //! @brief create a programmer readable dump of XML metadata.
+        //!
+        //! shows linear serialisation of all header data in random order.
+        std::string debug_dump() const;
+
+        public:
+        ZHfstOspellerInfoMetadata info_; //!< The info node data
+        //! @brief data for acceptor nodes
+        std::map<std::string,ZHfstOspellerAcceptorMetadata> acceptor_; 
+        //! @brief data for errmodel nodes
+        std::vector<ZHfstOspellerErrModelMetadata> errmodel_;
+#if HAVE_LIBXML
+        private:
+        void parse_xml(const xmlpp::Document* doc);
+        void verify_hfstspeller(xmlpp::Node* hfstspellerNode);
+        void parse_info(xmlpp::Node* infoNode);
+        void parse_locale(xmlpp::Node* localeNode);
+        void parse_title(xmlpp::Node* titleNode);
+        void parse_description(xmlpp::Node* descriptionNode);
+        void parse_version(xmlpp::Node* versionNode);
+        void parse_date(xmlpp::Node* dateNode);
+        void parse_producer(xmlpp::Node* producerNode);
+        void parse_contact(xmlpp::Node* contactNode);
+        void parse_acceptor(xmlpp::Node* acceptorNode);
+        void parse_title(xmlpp::Node* titleNode, const std::string& accName);
+        void parse_description(xmlpp::Node* descriptionNode,
+                               const std::string& accName);
+        void parse_errmodel(xmlpp::Node* errmodelNode);
+        void parse_title(xmlpp::Node* titleNode, size_t errm_count);
+        void parse_description(xmlpp::Node* descriptionNode, size_t errm_count);
+        void parse_type(xmlpp::Node* typeNode, size_t errm_count);
+        void parse_model(xmlpp::Node* modelNode, size_t errm_count);
+#elif HAVE_TINYXML2
+        private:
+        void parse_xml(const tinyxml2::XMLDocument& doc);
+        void verify_hfstspeller(const tinyxml2::XMLElement& hfstspellerNode);
+        void parse_info(const tinyxml2::XMLElement& infoNode);
+        void parse_locale(const tinyxml2::XMLElement& localeNode);
+        void parse_title(const tinyxml2::XMLElement& titleNode);
+        void parse_description(const tinyxml2::XMLElement& descriptionNode);
+        void parse_version(const tinyxml2::XMLElement& versionNode);
+        void parse_date(const tinyxml2::XMLElement& dateNode);
+        void parse_producer(const tinyxml2::XMLElement& producerNode);
+        void parse_contact(const tinyxml2::XMLElement& contactNode);
+        void parse_acceptor(const tinyxml2::XMLElement& acceptorNode);
+        void parse_title(const tinyxml2::XMLElement& titleNode, const std::string& accName);
+        void parse_description(const tinyxml2::XMLElement& descriptionNode,
+                               const std::string& accName);
+        void parse_errmodel(const tinyxml2::XMLElement& errmodelNode);
+        void parse_title(const tinyxml2::XMLElement& titleNode, size_t errm_count);
+        void parse_description(const tinyxml2::XMLElement& descriptionNode, size_t errm_count);
+        void parse_type(const tinyxml2::XMLElement& typeNode, size_t errm_count);
+        void parse_model(const tinyxml2::XMLElement& modelNode, size_t errm_count);
+
+#endif
+      };
+}
+
+#endif // inclusion GUARD
+// vim: set ft=cpp.doxygen:

authors.xml

+<?xml version="1.0" encoding="utf-8"?>
+<authors>
+    <author uid="mie">
+        Tommi A Pirinen &lt;tommi.pirinen@helsinki.fi&gt;
+   </author>
+</authors>
+

configure.ac

+## Process this file with autoconf to produce configure script
+
+## Copyright (C) 2010 University of Helsinki
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+
+# autoconf requirements
+AC_PREREQ([2.62])
+AC_INIT([hfstospell], [0.5.0], [hfst-bugs@helsinki.fi], [hfstospell], [http://hfst.github.io])
+
+LT_PREREQ([2.2.6])
+
+# init
+AC_CONFIG_AUX_DIR([build-aux])
+AM_INIT_AUTOMAKE([1.11 -Wall -Werror foreign check-news color-tests silent-rules])
+AM_SILENT_RULES([yes])
+AC_REVISION([$Revision$])
+AC_CONFIG_MACRO_DIR([m4])
+AC_CONFIG_SRCDIR([ospell.cc])
+AC_CONFIG_HEADERS([config.h])
+
+# Information on package
+HFSTOSPELL_NAME=hfstospell
+HFSTOSPELL_MAJOR=0
+HFSTOSPELL_MINOR=5
+HFSTOSPELL_EXTENSION=.0
+HFSTOSPELL_VERSION=$HFSTOSPELL_MAJOR.$HFSTOSPELL_MINOR$HFSTOSPELL_EXTENSION
+AC_SUBST(HFSTOSPELL_MAJOR)
+AC_SUBST(HFSTOSPELL_MINOR)
+AC_SUBST(HFSTOSPELL_VERSION)
+AC_SUBST(HFSTOSPELL_NAME)
+
+# Check for pkg-config first - the configuration won't work if it isn't available:
+AC_PATH_PROG([PKGCONFIG], [pkg-config], [no])
+AS_IF([test "x$PKGCONFIG" = xno], [AC_MSG_ERROR([pkg-config is required - please install])])
+AC_PATH_PROG([DOXYGEN], [doxygen], [false])
+AM_CONDITIONAL([CAN_DOXYGEN], [test "x$DOXYGEN" != xfalse])
+
+# Settings
+AC_ARG_ENABLE([extra_demos],
+              [AS_HELP_STRING([--enable-extra-demos],
+                              [build conference demos for science reproduction @<:@default=no@:>@])],
+              [enable_extra_demos=$enableval], [enable_extra_demos=no])
+AM_CONDITIONAL([EXTRA_DEMOS], [test x$enable_extra_demos != xno])
+AC_ARG_ENABLE([hfst_ospell_office],
+              [AS_HELP_STRING([--enable-hfst-ospell-office],
+                              [build hfst-ospell-office @<:@default=yes@:>@])],
+              [enable_hfst_ospell_ofiice=$enableval], [enable_hfst_ospell_office=yes])
+AM_CONDITIONAL([HFST_OSPELL_OFFICE], [test x$enable_hfst_ospell_office != xno])
+AC_ARG_ENABLE([zhfst],
+              [AS_HELP_STRING([--enable-zhfst],
+                              [support zipped complex automaton sets @<:@default=check@:>@])],
+              [enable_zhfst=$enableval], [enable_zhfst=check])
+AC_ARG_WITH([libxmlpp],
+              [AS_HELP_STRING([--with-libxmlpp],
+                              [support xml metadata for zipped automaton sets with libxml++-2.6 @<:@default=yes@:>@])],
+              [with_libxmlpp=$withval], [with_libxmlpp=yes])
+AC_ARG_WITH([tinyxml2],
+              [AS_HELP_STRING([--with-tinyxml2],
+                              [support xml metadata for zipped automaton sets with tinyxml2 @<:@default=no@:>@])],
+              [with_tinyxml2=$withval], [with_tinyxml2=no])
+
+AC_ARG_WITH([extract],
+            [AS_HELP_STRING([--with-extract=TARGET],
+                           [extract zhfst archives to tmpdir or mem @<:@default=mem@:>@])],
+            [with_extract=$withval], [with_extract=mem])
+AS_IF([test "x$with_extract" = xmem], [AC_DEFINE([ZHFST_EXTRACT_TO_MEM], [1],
+                        [Define to extract zhfst archives to char buffer first])],
+          [AS_IF([test "x$with_extract" = xtmpdir],
+                 [AC_DEFINE([ZHFST_EXTRACT_TO_MEM], [0],
+                            [Define to extract zhfst to tmp dir first])],
+          [AC_MSG_ERROR([Use with-extract to mem or tmpdir])])])
+
+# Checks for programs
+m4_ifdef([AM_PROG_AR], [AM_PROG_AR])
+AC_PROG_CC
+AC_PROG_CXX
+AC_LIBTOOL_WIN32_DLL
+LT_INIT
+AC_PROG_INSTALL
+AC_PROG_LN_S
+AC_PROG_MAKE_SET
+
+# Checks for libraries
+AS_IF([test x$enable_zhfst != xno],
+      [PKG_CHECK_MODULES([LIBARCHIVE], [libarchive > 3],
+                  [AC_DEFINE([HAVE_LIBARCHIVE], [1], [Use archives])
+                   enable_zhfst=yes],
+                  [PKG_CHECK_MODULES([LIBARCHIVE], [libarchive > 2],
+                              [AC_DEFINE([HAVE_LIBARCHIVE], [1], [Use archives])
+	                       AC_DEFINE([USE_LIBARCHIVE_2], [1], [Use libarchive2])
+                               enable_zhfst=yes],
+                              [AS_IF([test x$enable_zhfst != xcheck],
+                                     [AC_MSG_ERROR([zhfst support requires either libarchive or libarchive2])
+                                      enable_zhfst=no],
+                                     [enable_zhfst=no])])])])
+
+AM_CONDITIONAL([WANT_ARCHIVE], [test x$enable_zhfst != xno])
+AS_IF([test x$with_libxmlpp != xno],
+      [PKG_CHECK_MODULES([LIBXMLPP], [libxml++-2.6 >= 2.10.0],
+                         [AC_DEFINE([HAVE_LIBXML], [1], [Use libxml++])
+                          enable_xml=libxmlpp],
+                         [AC_MSG_ERROR([libxml++ failed])
+                          enable_xml=no])])
+AM_CONDITIONAL([WANT_LIBXMLPP], [test x$enable_xml = xlibxmlpp])
+AS_IF([test x$with_tinyxml2 != xno -a x$with_libxmlpp = xno],
+      [PKG_CHECK_MODULES([TINYXML2], [tinyxml2 >= 1.0.8 tinyxml2 < 3],
+                         [AC_DEFINE([HAVE_TINYXML2], [1], [Use tinyxml])
+                          enable_xml=tinyxml2],
+                         [AC_MSG_ERROR([tinyxml missing])
+                          enable_xml=no])])
+AM_CONDITIONAL([WANT_TINYXML2], [test x$enable_xml = xtinyxml2])
+
+# Find ICU in the new and old way
+PKG_CHECK_MODULES(ICU, [icu-uc >= 4], [], [
+ AC_PATH_PROG([ICU_CONFIG], [icu-config], [false])
+ AS_IF([test x$ICU_CONFIG != xfalse], [
+  ICU_LIBS=$($ICU_CONFIG --ldflags)
+ ])
+])
+LIBS="$LIBS $ICU_LIBS"
+
+# Checks for header files
+AC_CHECK_HEADERS([getopt.h error.h])
+
+# Checks for types
+AC_TYPE_SIZE_T
+
+# Checks for structures
+
+# Checks for compiler characteristics
+AC_C_BIGENDIAN
+
+# Checks for library functions
+AC_FUNC_MALLOC
+AC_CHECK_FUNCS([strndup error])
+# Checks for system services
+
+# Checks for highest supported C++ standard
+AC_LANG(C++)
+AX_CHECK_COMPILE_FLAG([-std=c++17], [CXXFLAGS="$CXXFLAGS -std=c++17"], [
+ AX_CHECK_COMPILE_FLAG([-std=c++1z], [CXXFLAGS="$CXXFLAGS -std=c++1z"], [
+  AX_CHECK_COMPILE_FLAG([-std=c++14], [CXXFLAGS="$CXXFLAGS -std=c++14"], [
+   AX_CHECK_COMPILE_FLAG([-std=c++1y], [CXXFLAGS="$CXXFLAGS -std=c++1y"], [
+    AX_CHECK_COMPILE_FLAG([-std=c++11], [CXXFLAGS="$CXXFLAGS -std=c++11"], [
+     AC_MSG_ERROR([could not enable C++11 or newer])
+    ])
+   ])
+  ])
+ ])
+])
+
+# config files
+AC_CONFIG_FILES([Makefile hfstospell.pc])
+
+# output
+AC_OUTPUT
+
+cat <<EOF
+-- Building $PACKAGE_STRING
+    * zhfst support: $enable_zhfst
+    * extracting to: $with_extract
+    * xml support: $enable_xml
+    * hfst-ospell-office: $enable_hfst_ospell_office
+    * conference demos: $enable_extra_demos
+EOF
+AS_IF([test x$with_libxmlpp != xno -a x$with_tinyxml2 != xno],
+      [AC_MSG_ERROR([You can only have one xml library (e.g., --with-tinyxml2 --without-libxmlpp)])])

doc/index.html

+<!DOCTYPE html>
+<html>
+    <head>
+        <meta charset="UTF-8">
+        <title>HFST ospell–Free WFST spell-checker and library</title>
+    </head>
+    <body>
+        <h1><img src="doc/html/edit2-small.png"
+            alt="[edit distance 2 automaton]"/>
+            HFST ospell</h1>
+        <p>
+        HFST ospell is a free open source spell-checker using weighted
+        finite-state automata. It is a light-weight library for using
+        combinations of two automata–a language model and an error model–for
+        spell-checking and correction.
+        </p>
+        <p>
+        It has optional support for XML-based metadata using libxml++2 or
+        tinyxml2. Automata compression is supported through libarchive,
+        currently with zip format.
+        </p>
+        <p>
+        The API of the library is stable to support updating the shared library
+        while keeping the automata and the plugins for enchant and LibreOffice
+        in place. The <a href="doc/html/">api documentation</a> is maintained with
+        doxygen.
+        </p>
+        <p>
+        You can download the library and small demo applications from 
+        <a href="http://hfst.sf.net/">HFST’s main sourceforge site</a>.
+        </p>
+    </body>
+</html>
+