Merged in hxcan/recoll (pull request #1): get active indexes from the environment
This commit is contained in:
medoc
parent
5bd071c5a6
commit
311decd6e6
68 changed files with 1474 additions and 624 deletions
|
|
@ -9,15 +9,16 @@ Build-Depends: debhelper (>= 7),
|
|||
libxapian-dev (>= 1.0.15),
|
||||
libx11-dev,
|
||||
libz-dev,
|
||||
python-dev,
|
||||
python-all-dev (>= 2.6.6-3~),
|
||||
quilt
|
||||
Standards-Version: 3.8.3
|
||||
Standards-Version: 3.9.3
|
||||
|
||||
Package: recoll
|
||||
Architecture: any
|
||||
Depends: ${shlibs:Depends}, ${misc:Depends}
|
||||
Recommends: aspell, python, xsltproc
|
||||
Suggests: antiword, catdoc, ghostscript, libimage-exiftool-perl, poppler-utils, unrtf, python-mutagen
|
||||
Recommends: aspell, python, xdg-utils, xsltproc
|
||||
Suggests: antiword, catdoc, ghostscript, libimage-exiftool-perl, poppler-utils,
|
||||
pstotext, python-chm, python-mutagen, unrtf, untex
|
||||
Description: a personal full text search package with a QT GUI
|
||||
The Recoll personal full text search package is based on a very strong
|
||||
backend (Xapian), for which it provides an easy to use and feature-rich
|
||||
|
|
|
|||
|
|
@ -1,113 +1,219 @@
|
|||
This package was debianized by Jean-Francois Dockes <jfd@recoll.org> on
|
||||
Wed, 10 Jan 2007 16:04:13 +0100.
|
||||
Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
|
||||
Upstream-Name: recoll
|
||||
Upstream-Contact: Jean-Francois Dockes <jean-francois.dockes@wanadoo.fr>
|
||||
Source: http://www.lesbonscomptes.com/recoll/
|
||||
|
||||
It was downloaded from http://www.recoll.org
|
||||
Files: *
|
||||
Copyright: 2005-2012, Jean-Francois Dockes <jean-francois.dockes@wanadoo.fr>
|
||||
License: GPL-2+
|
||||
|
||||
Upstream Author: Jean-Francois Dockes <jfd@recoll.org>
|
||||
Files: Binc IMAP project (bincimapmime/*)
|
||||
Copyright: 2002-2005, Andreas Aardal Hanssen <andreas-binc@bincimap.org>
|
||||
License: GPL-2+
|
||||
|
||||
Copyright: (C) 2005,2006, Jean-Francois Dockes <jfd@recoll.org>
|
||||
Files: filters/rcl* files index/csguess.cpp internfile/htmlparse.cpp
|
||||
Copyright: 2000-2004, Mikio Hirabayashi
|
||||
License: GPL-2+
|
||||
|
||||
Files: filters/rclpython
|
||||
Copyright: J\xfcrgen Hermann, Mike Brown, Christopher Arndt
|
||||
<http://chrisarndt.de/en/software/python/colorize.html>
|
||||
License: GPL-2+
|
||||
|
||||
Files: internfile/htmlparse.cpp mh_html.cpp
|
||||
Copyright: 1999-2001, BrightStation PLC
|
||||
Copyright: 2001, Ananova Ltd
|
||||
Copyright: 2002-2004, Olly Betts
|
||||
License: GPL-2+
|
||||
|
||||
Files: unac/*
|
||||
Copyright: 2000-2002, Loic Dachary <loic@senga.org>
|
||||
License: GPL-2+
|
||||
|
||||
Files: common/*
|
||||
Copyright: 2004-2005, J.F.Dockes
|
||||
License: GPL-2+
|
||||
|
||||
Files: debian/*
|
||||
Copyright: 2007-2012, Kartik Mistry <kartik@debian.org>
|
||||
License: GPL-2+
|
||||
|
||||
License: GPL-2+
|
||||
This package is free software; you can redistribute it and/or modify it under
|
||||
the terms of the GNU General Public License as published by the Free Software
|
||||
Foundation; either version 2 of the License, or (at your option) any later
|
||||
version.
|
||||
.
|
||||
This package is distributed in the hope that it will be useful, but WITHOUT
|
||||
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
|
||||
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
|
||||
.
|
||||
You should have received a copy of the GNU General Public License along with
|
||||
this package; if not, write to the Free Software Foundation, Inc., 51 Franklin
|
||||
St, Fifth Floor, Boston, MA 02110-1301 USA
|
||||
.
|
||||
On Debian systems, the complete text of the GNU General Public License can be
|
||||
found in `/usr/share/common-licenses/GPL-2' and
|
||||
`/usr/share/common-licenses/GPL-3'.
|
||||
|
||||
Files: aspell/*
|
||||
Copyright: 2001-2002, by Kevin Atkinson
|
||||
License: LGPL-2+
|
||||
|
||||
Files: images/text-x-python.png
|
||||
Copyright: David Vignoni <http://www.oxygen-icons.org/>
|
||||
License: LGPL-2+
|
||||
|
||||
License: LGPL-2+
|
||||
This package is free software; you can redistribute it and/or modify it under
|
||||
the terms of the GNU Lesser General Public License as published by the Free
|
||||
Software Foundation; either version 2 of the License, or (at your option) any
|
||||
later version.
|
||||
.
|
||||
This package is distributed in the hope that it will be useful, but WITHOUT
|
||||
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
|
||||
FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more
|
||||
details.
|
||||
.
|
||||
You should have received a copy of the GNU Lesser General Public License along
|
||||
with this package; if not, write to the Free Software Foundation, Inc., 51
|
||||
Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
||||
.
|
||||
On Debian systems, the complete text of the GNU Lesser General Public License
|
||||
can be found in `/usr/share/common-licenses/LGPL-2' and
|
||||
`/usr/share/common-licenses/LGPL-2.1' and `/usr/share/common-licenses/LGPL-3'.
|
||||
|
||||
Files: qtgui/q3richtext_p.h
|
||||
Copyright: 1992-2007, Trolltech ASA. All rights reserved
|
||||
License:
|
||||
This file is part of the Qt3Support module of the Qt Toolkit.
|
||||
.
|
||||
This file may be used under the terms of the GNU General Public License
|
||||
version 2.0 as published by the Free Software Foundation and appearing in the
|
||||
file LICENSE.GPL included in the packaging of this file. Please review the
|
||||
following information to ensure GNU General Public Licensing requirements will
|
||||
be met: http://trolltech.com/products/qt/licenses/licensing/opensource/
|
||||
.
|
||||
If you are unsure which license is appropriate for your use, please review the
|
||||
following information:
|
||||
http://trolltech.com/products/qt/licenses/licensing/licensingoverview
|
||||
or contact the sales department at sales@trolltech.com.
|
||||
.
|
||||
In addition, as a special exception, Trolltech gives you certain additional
|
||||
rights. These rights are described in the Trolltech GPL Exception version 1.0,
|
||||
which can be found at http://www.trolltech.com/products/qt/gplexception/ and
|
||||
in the file GPL_EXCEPTION.txt in this package.
|
||||
.
|
||||
In addition, as a special exception, Trolltech, as the sole copyright
|
||||
holder for Qt Designer, grants users of the Qt/Eclipse Integration
|
||||
plug-in the right for the Qt/Eclipse Integration to link to
|
||||
functionality provided by Qt Designer and its related libraries.
|
||||
.
|
||||
Trolltech reserves all rights not expressly granted herein.
|
||||
.
|
||||
Trolltech ASA (c) 2007
|
||||
.
|
||||
This file is provided AS IS with NO WARRANTY OF ANY KIND, INCLUDING THE
|
||||
WARRANTY OF DESIGN, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
|
||||
|
||||
This package is free software; you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation; either version 2 of the License, or
|
||||
(at your option) any later version.
|
||||
|
||||
This package is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with this package; if not, write to the Free Software
|
||||
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
||||
|
||||
On Debian systems, the complete text of the GNU General
|
||||
Public License can be found in `/usr/share/common-licenses/GPL'.
|
||||
|
||||
The Debian packaging is (C) 2007, Jean-Francois Dockes <jfd@recoll.org> and
|
||||
is licensed under the GPL, see above.
|
||||
|
||||
Portions of the software are:
|
||||
|
||||
Copyright (C) 2001-2002 by Kevin Atkinson under the GNU LGPL:
|
||||
/* This file is part of The New Aspell
|
||||
* Copyright (C) 2001-2002 by Kevin Atkinson under the GNU LGPL
|
||||
* license version 2.0 or 2.1. You should have received a copy of the
|
||||
* LGPL license along with this library if you did not you can find it
|
||||
* at http://www.gnu.org/.
|
||||
|
||||
On Debian systems, the complete text of the GNU LGPL
|
||||
can be found in `/usr/share/common-licenses/LGPL-2'.
|
||||
|
||||
|
||||
Copyright 2002-2005 Andreas Aardal Hanssen
|
||||
Copyright (C) 2000-2004 Mikio Hirabayashi
|
||||
Copyright 1999,2000,2001 BrightStation PLC
|
||||
Copyright 2001 Ananova Ltd
|
||||
Copyright 2002 Olly Betts
|
||||
Copyright (C) 2000, 2001, 2002 Loic Dachary <loic@senga.org>
|
||||
- GPL V2 or later, same license text as above
|
||||
|
||||
Copyright (c) 1991-2004 Unicode, Inc.
|
||||
|
||||
COPYRIGHT AND PERMISSION NOTICE
|
||||
|
||||
Copyright © 1991-2006 Unicode, Inc. All rights reserved. Distributed under
|
||||
the Terms of Use in http://www.unicode.org/copyright.html.
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a
|
||||
copy of the Unicode data files and any associated documentation (the "Data
|
||||
Files") or Unicode software and any associated documentation (the
|
||||
"Software") to deal in the Data Files or Software without restriction,
|
||||
including without limitation the rights to use, copy, modify, merge,
|
||||
publish, distribute, and/or sell copies of the Data Files or Software, and
|
||||
to permit persons to whom the Data Files or Software are furnished to do
|
||||
so, provided that (a) the above copyright notice(s) and this permission
|
||||
notice appear with all copies of the Data Files or Software, (b) both the
|
||||
above copyright notice(s) and this permission notice appear in associated
|
||||
documentation, and (c) there is clear notice in each modified Data File or
|
||||
in the Software as well as in the documentation associated with the Data
|
||||
File(s) or Software that the data or software has been modified.
|
||||
|
||||
Files: common/uproplist.h
|
||||
Copyright: 1991-2006, Unicode, Inc.
|
||||
License:
|
||||
All rights reserved. Distributed under the Terms of Use in
|
||||
http://www.unicode.org/copyright.html
|
||||
.
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of the Unicode data files and any associated documentation (the "Data Files")
|
||||
or Unicode software and any associated documentation (the "Software") to deal
|
||||
in the Data Files or Software without restriction, including without
|
||||
limitation the rights to use, copy, modify, merge, publish, distribute, and/or
|
||||
sell copies of the Data Files or Software, and to permit persons to whom the
|
||||
Data Files or Software are furnished to do so, provided that (a) the above
|
||||
copyright notice(s) and this permission notice appear with all copies of the
|
||||
Data Files or Software, (b) both the above copyright notice(s) and this
|
||||
permission notice appear in associated documentation, and (c) there is clear
|
||||
notice in each modified Data File or in the Software as well as in the
|
||||
documentation associated with the Data File(s) or Software that the data or
|
||||
software has been modified.
|
||||
.
|
||||
THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
|
||||
KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF
|
||||
THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS
|
||||
INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR
|
||||
CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF
|
||||
USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
|
||||
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
|
||||
PERFORMANCE OF THE DATA FILES OR SOFTWARE.
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD
|
||||
PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN
|
||||
THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL
|
||||
DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
|
||||
PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
|
||||
ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THE
|
||||
DATA FILES OR SOFTWARE.
|
||||
.
|
||||
Except as contained in this notice, the name of a copyright holder shall not
|
||||
be used in advertising or otherwise to promote the sale, use or other dealings
|
||||
in these Data Files or Software without prior written authorization of the
|
||||
copyright holder.
|
||||
|
||||
Except as contained in this notice, the name of a copyright holder shall
|
||||
not be used in advertising or otherwise to promote the sale, use or other
|
||||
dealings in these Data Files or Software without prior written
|
||||
authorization of the copyright holder.
|
||||
Files: utils/md5.*
|
||||
Copyright: 1991-1992, RSA Data Security, Inc. All rights reserved.
|
||||
License:
|
||||
MD5C.C - RSA Data Security, Inc., MD5 message-digest algorithm
|
||||
.
|
||||
License to copy and use this software is granted provided that it is
|
||||
identified as the "RSA Data Security, Inc. MD5 Message-Digest Algorithm" in
|
||||
all material mentioning or referencing this software or this function.
|
||||
.
|
||||
License is also granted to make and use derivative works provided that such
|
||||
works are identified as "derived from the RSA Data Security, Inc. MD5
|
||||
Message-Digest Algorithm" in all material mentioning or referencing the
|
||||
derived work.
|
||||
.
|
||||
RSA Data Security, Inc. makes no representations concerning either the
|
||||
merchantability of this software or the suitability of this software for any
|
||||
particular purpose. It is provided "as is" without express or implied warranty
|
||||
of any kind.
|
||||
.
|
||||
These notices must be retained in any copies of any part of this documentation
|
||||
and/or software.
|
||||
|
||||
Copyright (C) 1991-2, RSA Data Security, Inc. Created 1991. All
|
||||
/*
|
||||
* MD5C.C - RSA Data Security, Inc., MD5 message-digest algorithm
|
||||
*
|
||||
* Copyright (C) 1991-2, RSA Data Security, Inc. Created 1991. All
|
||||
* rights reserved.
|
||||
*
|
||||
* License to copy and use this software is granted provided that it
|
||||
* is identified as the "RSA Data Security, Inc. MD5 Message-Digest
|
||||
* Algorithm" in all material mentioning or referencing this software
|
||||
* or this function.
|
||||
*
|
||||
* License is also granted to make and use derivative works provided
|
||||
* that such works are identified as "derived from the RSA Data
|
||||
* Security, Inc. MD5 Message-Digest Algorithm" in all material
|
||||
* mentioning or referencing the derived work.
|
||||
*
|
||||
* RSA Data Security, Inc. makes no representations concerning either
|
||||
* the merchantability of this software or the suitability of this
|
||||
* software for any particular purpose. It is provided "as is"
|
||||
* without express or implied warranty of any kind.
|
||||
*
|
||||
* These notices must be retained in any copies of any part of this
|
||||
* documentation and/or software.
|
||||
*/
|
||||
Files: desktop/xdg-utils-1.0.1/*
|
||||
Copyright: 2006, Kevin Krammer <kevin.krammer@gmx.at>,
|
||||
Jeremy White <jwhite@codeweavers.com>
|
||||
License:
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
.
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
.
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
Files: index/csguess.cpp
|
||||
Copyright: 2000-2004, Mikio Hirabayashi
|
||||
License: LGPL-2.1+
|
||||
This file is part of QDBM, Quick Database Manager.
|
||||
.
|
||||
QDBM is free software; you can redistribute it and/or modify it under
|
||||
the terms of the GNU Lesser General Public License as published by the
|
||||
Free Software Foundation; either version 2.1 of the License or any later
|
||||
version.
|
||||
.
|
||||
QDBM is distributed in the hope that it will be useful, but WITHOUT ANY
|
||||
WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
|
||||
License for more details.
|
||||
.
|
||||
You should have received a copy of the GNU Lesser General Public License
|
||||
along with QDBM; if not, write to the Free Software Foundation, Inc.,
|
||||
51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
|
||||
.
|
||||
On Debian systems, the complete text of the GNU Lesser General Public License
|
||||
can be found in `/usr/share/common-licenses/LGPL-2.1' and
|
||||
`/usr/share/common-licenses/LGPL-3'.
|
||||
|
|
|
|||
|
|
@ -1 +0,0 @@
|
|||
README
|
||||
|
|
@ -1,5 +1,8 @@
|
|||
setup.py --root and --user options interfer with debian wanting a dist-packages,
|
||||
not site-packages installation for python modules
|
||||
Description: Fix python module installation
|
||||
setup.py --root and --user options interfer with debian wanting a
|
||||
dist-packages, not site-packages installation for python modules
|
||||
Author: Jean-Francois Dockes <jf@dockes.org>
|
||||
Last-Update: 2012-03-26
|
||||
--- a/recollinstall.in
|
||||
+++ b/recollinstall.in
|
||||
@@ -139,5 +139,4 @@
|
||||
|
|
|
|||
|
|
@ -1,7 +1,5 @@
|
|||
#!/usr/bin/make -f
|
||||
|
||||
include /usr/share/quilt/quilt.make
|
||||
|
||||
# Uncomment this to turn on verbose mode.
|
||||
#export DH_VERBOSE=1
|
||||
|
||||
|
|
@ -28,13 +26,15 @@ config.status: configure
|
|||
--mandir=\$${prefix}/share/man \
|
||||
--prefix=/usr
|
||||
|
||||
build: build-stamp
|
||||
build-stamp: $(QUILT_STAMPFN) config.status
|
||||
build: build-arch build-indep
|
||||
build-arch: build-stamp
|
||||
build-indep: build-stamp
|
||||
build-stamp: config.status
|
||||
dh_testdir
|
||||
$(MAKE)
|
||||
touch $@
|
||||
|
||||
clean: unpatch
|
||||
clean:
|
||||
dh_testdir
|
||||
dh_testroot
|
||||
rm -f build-stamp config.log
|
||||
|
|
@ -46,8 +46,11 @@ install:
|
|||
dh_testroot
|
||||
dh_prep
|
||||
dh_installdirs
|
||||
$(MAKE) prefix=$(CURDIR)/debian/recoll/usr install
|
||||
(cd python/recoll;python setup.py install --install-layout=deb --root=$(CURDIR)/debian/recoll/ )
|
||||
|
||||
$(MAKE) STRIP=ls prefix=$(CURDIR)/debian/tmp/usr install
|
||||
(cd python/recoll; python setup.py install \
|
||||
--install-layout=deb \
|
||||
--prefix=$(CURDIR)/debian/tmp/usr )
|
||||
|
||||
binary-arch: build install
|
||||
dh_testdir
|
||||
|
|
@ -56,6 +59,7 @@ binary-arch: build install
|
|||
dh_installdocs README
|
||||
dh_installmenu
|
||||
dh_installman
|
||||
dh_install --sourcedir=debian/tmp
|
||||
dh_link
|
||||
dh_strip
|
||||
dh_compress
|
||||
|
|
@ -69,4 +73,4 @@ binary-arch: build install
|
|||
binary-indep: build install
|
||||
|
||||
binary: binary-indep binary-arch
|
||||
.PHONY: build clean binary-indep binary-arch binary install
|
||||
.PHONY: build build-arch build-indep clean binary-indep binary-arch binary install
|
||||
|
|
|
|||
1
packaging/debian/debianrclqt4/source/format
Normal file
1
packaging/debian/debianrclqt4/source/format
Normal file
|
|
@ -0,0 +1 @@
|
|||
3.0 (quilt)
|
||||
|
|
@ -1,12 +1,2 @@
|
|||
# Example watch control file for uscan
|
||||
# Rename this file to "watch" and then you can run the "uscan" command
|
||||
# to check for upstream updates and more.
|
||||
# See uscan(1) for format
|
||||
|
||||
# Compulsory line, this is a version 3 file
|
||||
version=3
|
||||
|
||||
# Uncomment to examine a Webpage
|
||||
# <Webpage URL> <string match>
|
||||
http://www.recoll.org/download.html recoll-(.*)\.tar\.gz
|
||||
|
||||
|
|
|
|||
39
src/README
39
src/README
|
|
@ -235,24 +235,37 @@ More documentation can be found in the doc/ directory or at http://www.recoll.or
|
|||
files with different character sets, encodings, and languages into the
|
||||
same index. It has input filters for many document types.
|
||||
|
||||
Stemming depends on the document language. Recoll stores the unstemmed
|
||||
versions of terms and uses auxiliary databases for term expansion. It can
|
||||
switch stemming languages, or add a language, without re-indexing. Storing
|
||||
documents in different languages in the same index is possible, and useful
|
||||
in practice, but does introduce possibilities of confusion. Recoll
|
||||
currently makes no attempt at automatic language recognition.
|
||||
Stemming is the process by which Recoll reduces words to their radicals so
|
||||
that searching does not depend, for example, on a word being singular or
|
||||
plural (floor, floors), or on a verb tense (flooring, floored). Because
|
||||
the mechanisms used for stemming depend on the specific grammatical rules
|
||||
for each language, there is a separate stemmer module for most common
|
||||
languages where stemming makes sense. Storing documents written in
|
||||
different languages in the same index is possible, and commonly done. In
|
||||
this situation, you can specify several stemming languages for the index.
|
||||
Recoll stores the unstemmed versions of terms in the main index and uses
|
||||
auxiliary databases for term expansion (one for each stemming language),
|
||||
which means that you can switch stemming languages between searches, or
|
||||
add a language without needing a full reindex. Recoll currently makes no
|
||||
attempt at automatic language recognition, which means that the stemmer
|
||||
will sometimes be applied to terms from other languages with potentially
|
||||
strange results. In practise, even if this introduces possibilities of
|
||||
confusion, this approach has been proven quite useful, and, awaiting the
|
||||
addition of an automatic language recognition module to Recoll, it is much
|
||||
less cumbersome than separating your documents according to what language
|
||||
they are written in.
|
||||
|
||||
Recoll has many parameters which define exactly what to index, and how to
|
||||
classify and decode the source documents. These are kept in configuration
|
||||
files. A default configuration is copied into a standard location (usually
|
||||
something like /usr/[local/]share/recoll/examples) during installation.
|
||||
The default parameters from this file may be overridden by values that you
|
||||
set inside your personal configuration, found by default in the .recoll
|
||||
sub-directory of your home directory. The default configuration will index
|
||||
your home directory with default parameters and should be sufficient for
|
||||
giving Recoll a try, but you may want to adjust it later, which can be
|
||||
done either by editing the text files or by using configuration menus in
|
||||
the recoll GUI
|
||||
The default values set by the configuration files in this directory may be
|
||||
overridden by values that you set inside your personal configuration,
|
||||
found by default in the .recoll sub-directory of your home directory. The
|
||||
default configuration will index your home directory with default
|
||||
parameters and should be sufficient for giving Recoll a try, but you may
|
||||
want to adjust it later, which can be done either by editing the text
|
||||
files or by using configuration menus in the recoll GUI
|
||||
|
||||
Indexing is started automatically the first time you execute the recoll
|
||||
search graphical user interface, or by executing the recollindex command.
|
||||
|
|
|
|||
|
|
@ -1 +1 @@
|
|||
1.17.1
|
||||
1.17.2
|
||||
|
|
|
|||
|
|
@ -109,7 +109,9 @@
|
|||
#undef _FILE_OFFSET_BITS
|
||||
#undef _LARGE_FILES
|
||||
|
||||
#if _FILE_OFFSET_BITS == 64 || defined(__APPLE__) || defined(__OpenBSD__)
|
||||
/* The __FreeBSD_kernel__ thing is for debian/kfreebsd. */
|
||||
#if _FILE_OFFSET_BITS == 64 || defined(__APPLE__) || defined(__OpenBSD__) ||\
|
||||
defined(__FreeBSD_kernel__)
|
||||
#define OFFTPC "%lld"
|
||||
#else
|
||||
#define OFFTPC "%ld"
|
||||
|
|
|
|||
|
|
@ -107,9 +107,15 @@ RclConfig *recollinit(RclInitFlags flags,
|
|||
// Make sure the locale charset is initialized (so that multiple
|
||||
// threads don't try to do it at once).
|
||||
config->getDefCharset();
|
||||
|
||||
// Init unac locking
|
||||
unac_init_mt();
|
||||
|
||||
// Init Unac translation exceptions
|
||||
string unacex;
|
||||
if (config->getConfParam("unac_except_trans", unacex) && !unacex.empty())
|
||||
unac_set_except_translations(unacex.c_str());
|
||||
|
||||
int flushmb;
|
||||
if (config->getConfParam("idxflushmb", &flushmb) && flushmb > 0) {
|
||||
LOGDEB1(("rclinit: idxflushmb=%d, set XAPIAN_FLUSH_THRESHOLD to 10E6\n",
|
||||
|
|
|
|||
|
|
@ -88,6 +88,7 @@ using namespace std;
|
|||
|
||||
#include "unacpp.h"
|
||||
#include "readfile.h"
|
||||
#include "rclinit.h"
|
||||
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
|
|
@ -98,8 +99,13 @@ int main(int argc, char **argv)
|
|||
}
|
||||
const char *encoding = argv[1];
|
||||
string ifn = argv[2];
|
||||
if (!ifn.compare("stdin"))
|
||||
ifn.clear();
|
||||
const char *ofn = argv[3];
|
||||
|
||||
string reason;
|
||||
(void)recollinit(RCLINIT_NONE, 0, 0, reason, 0);
|
||||
|
||||
string odata;
|
||||
if (!file_to_string(ifn, odata)) {
|
||||
cerr << "file_to_string: " << odata << endl;
|
||||
|
|
@ -111,7 +117,12 @@ int main(int argc, char **argv)
|
|||
exit(1);
|
||||
}
|
||||
|
||||
int fd = open(ofn, O_CREAT|O_EXCL|O_WRONLY, 0666);
|
||||
int fd;
|
||||
if (strcmp(ofn, "stdout")) {
|
||||
fd = open(ofn, O_CREAT|O_EXCL|O_WRONLY, 0666);
|
||||
} else {
|
||||
fd = 1;
|
||||
}
|
||||
if (fd < 0) {
|
||||
cerr << "Open/Create " << ofn << " failed: " << strerror(errno)
|
||||
<< endl;
|
||||
|
|
|
|||
28
src/configure
vendored
28
src/configure
vendored
|
|
@ -1,6 +1,6 @@
|
|||
#! /bin/sh
|
||||
# Guess values for system-dependent variables and create Makefiles.
|
||||
# Generated by GNU Autoconf 2.68 for Recoll 1.17.0.
|
||||
# Generated by GNU Autoconf 2.68 for Recoll 1.17.1.
|
||||
#
|
||||
#
|
||||
# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001,
|
||||
|
|
@ -557,8 +557,8 @@ MAKEFLAGS=
|
|||
# Identity of this package.
|
||||
PACKAGE_NAME='Recoll'
|
||||
PACKAGE_TARNAME='recoll'
|
||||
PACKAGE_VERSION='1.17.0'
|
||||
PACKAGE_STRING='Recoll 1.17.0'
|
||||
PACKAGE_VERSION='1.17.1'
|
||||
PACKAGE_STRING='Recoll 1.17.1'
|
||||
PACKAGE_BUGREPORT=''
|
||||
PACKAGE_URL=''
|
||||
|
||||
|
|
@ -618,6 +618,7 @@ QTGUI
|
|||
QMAKE
|
||||
LIBFAM
|
||||
LIBXAPIANSTATICEXTRA
|
||||
LIBXAPIANDIR
|
||||
LIBXAPIAN
|
||||
LIBICONV
|
||||
INCICONV
|
||||
|
|
@ -1257,7 +1258,7 @@ if test "$ac_init_help" = "long"; then
|
|||
# Omit some internal or obsolete options to make the list less imposing.
|
||||
# This message is too long to be a string in the A/UX 3.1 sh.
|
||||
cat <<_ACEOF
|
||||
\`configure' configures Recoll 1.17.0 to adapt to many kinds of systems.
|
||||
\`configure' configures Recoll 1.17.1 to adapt to many kinds of systems.
|
||||
|
||||
Usage: $0 [OPTION]... [VAR=VALUE]...
|
||||
|
||||
|
|
@ -1322,7 +1323,7 @@ fi
|
|||
|
||||
if test -n "$ac_init_help"; then
|
||||
case $ac_init_help in
|
||||
short | recursive ) echo "Configuration of Recoll 1.17.0:";;
|
||||
short | recursive ) echo "Configuration of Recoll 1.17.1:";;
|
||||
esac
|
||||
cat <<\_ACEOF
|
||||
|
||||
|
|
@ -1449,7 +1450,7 @@ fi
|
|||
test -n "$ac_init_help" && exit $ac_status
|
||||
if $ac_init_version; then
|
||||
cat <<\_ACEOF
|
||||
Recoll configure 1.17.0
|
||||
Recoll configure 1.17.1
|
||||
generated by GNU Autoconf 2.68
|
||||
|
||||
Copyright (C) 2010 Free Software Foundation, Inc.
|
||||
|
|
@ -2002,7 +2003,7 @@ cat >config.log <<_ACEOF
|
|||
This file contains any messages produced by compilers while
|
||||
running configure, to aid debugging if configure makes a mistake.
|
||||
|
||||
It was created by Recoll $as_me 1.17.0, which was
|
||||
It was created by Recoll $as_me 1.17.1, which was
|
||||
generated by GNU Autoconf 2.68. Invocation command line was
|
||||
|
||||
$ $0 $@
|
||||
|
|
@ -4598,10 +4599,16 @@ done
|
|||
LIBXAPIAN=$tmpxaplib
|
||||
# Also recent xapian libs need lz even when they think they don't...
|
||||
LIBXAPIAN="$LIBXAPIAN -lz"
|
||||
LIBXAPIANDIR=`$XAPIAN_CONFIG --libs | awk '{print $1}'`
|
||||
case A"$LIBXAPIANDIR" in
|
||||
A-L*) LIBXAPIANDIR=`echo $LIBXAPIANDIR | sed -e 's/-L//'`;;
|
||||
*) LIBXAPIANDIR="";;
|
||||
esac
|
||||
XAPIANCXXFLAGS=`$XAPIAN_CONFIG --cxxflags`
|
||||
|
||||
#echo XAPIAN_CONFIG: $XAPIAN_CONFIG
|
||||
#echo LIBXAPIAN: $LIBXAPIAN
|
||||
#echo LIBXAPIANDIR: $LIBXAPIANDIR
|
||||
#echo LIBXAPIANSTATICEXTRA: $LIBXAPIANSTATICEXTRA
|
||||
#echo XAPIANCXXFLAGS: $XAPIANCXXFLAGS
|
||||
|
||||
|
|
@ -5644,7 +5651,8 @@ test "X$m_prefix" = "XNONE" && m_prefix=/usr/local
|
|||
m_datadir=${m_prefix}/share
|
||||
QTRECOLL_DATADIR=${m_datadir}/recoll
|
||||
|
||||
RCLVERSION='1.17.0'
|
||||
RCLVERSION='1.17.1'
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
@ -6213,7 +6221,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
|
|||
# report actual input values of CONFIG_FILES etc. instead of their
|
||||
# values after options handling.
|
||||
ac_log="
|
||||
This file was extended by Recoll $as_me 1.17.0, which was
|
||||
This file was extended by Recoll $as_me 1.17.1, which was
|
||||
generated by GNU Autoconf 2.68. Invocation command line was
|
||||
|
||||
CONFIG_FILES = $CONFIG_FILES
|
||||
|
|
@ -6275,7 +6283,7 @@ _ACEOF
|
|||
cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
|
||||
ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
|
||||
ac_cs_version="\\
|
||||
Recoll config.status 1.17.0
|
||||
Recoll config.status 1.17.1
|
||||
configured by $0, generated by GNU Autoconf 2.68,
|
||||
with options \\"\$ac_cs_config\\"
|
||||
|
||||
|
|
|
|||
|
|
@ -321,10 +321,16 @@ done
|
|||
LIBXAPIAN=$tmpxaplib
|
||||
# Also recent xapian libs need lz even when they think they don't...
|
||||
LIBXAPIAN="$LIBXAPIAN -lz"
|
||||
LIBXAPIANDIR=`$XAPIAN_CONFIG --libs | awk '{print $1}'`
|
||||
case A"$LIBXAPIANDIR" in
|
||||
A-L*) LIBXAPIANDIR=`echo $LIBXAPIANDIR | sed -e 's/-L//'`;;
|
||||
*) LIBXAPIANDIR="";;
|
||||
esac
|
||||
XAPIANCXXFLAGS=`$XAPIAN_CONFIG --cxxflags`
|
||||
|
||||
#echo XAPIAN_CONFIG: $XAPIAN_CONFIG
|
||||
#echo LIBXAPIAN: $LIBXAPIAN
|
||||
#echo LIBXAPIANDIR: $LIBXAPIANDIR
|
||||
#echo LIBXAPIANSTATICEXTRA: $LIBXAPIANSTATICEXTRA
|
||||
#echo XAPIANCXXFLAGS: $XAPIANCXXFLAGS
|
||||
|
||||
|
|
@ -504,6 +510,7 @@ AC_SUBST(X_EXTRA_LIBS)
|
|||
AC_SUBST(INCICONV)
|
||||
AC_SUBST(LIBICONV)
|
||||
AC_SUBST(LIBXAPIAN)
|
||||
AC_SUBST(LIBXAPIANDIR)
|
||||
AC_SUBST(LIBXAPIANSTATICEXTRA)
|
||||
AC_SUBST(LIBFAM)
|
||||
AC_SUBST(QMAKE)
|
||||
|
|
|
|||
212
src/doc/user/docbook-xsl.css
Normal file
212
src/doc/user/docbook-xsl.css
Normal file
|
|
@ -0,0 +1,212 @@
|
|||
/*
|
||||
* Copyright (c) 2001, 2003, 2010 The FreeBSD Documentation Project
|
||||
* All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
* 1. Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
||||
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
||||
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
||||
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
||||
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
||||
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||
* SUCH DAMAGE.
|
||||
*
|
||||
* $FreeBSD: doc/share/misc/docbook.css,v 1.15 2010/03/20 04:15:01 hrs Exp $
|
||||
*/
|
||||
|
||||
body address {
|
||||
line-height: 1.3;
|
||||
margin: .6em 0;
|
||||
}
|
||||
|
||||
body blockquote {
|
||||
margin-top: .75em;
|
||||
line-height: 1.5;
|
||||
margin-bottom: .75em;
|
||||
}
|
||||
|
||||
html body {
|
||||
margin: 1em 8% 1em 10%;
|
||||
line-height: 1.2;
|
||||
}
|
||||
|
||||
.legalnotice {
|
||||
font-size: small;
|
||||
font-variant: small-caps;
|
||||
}
|
||||
|
||||
body div {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
dl {
|
||||
margin: .8em 0;
|
||||
line-height: 1.2;
|
||||
}
|
||||
|
||||
body form {
|
||||
margin: .6em 0;
|
||||
}
|
||||
|
||||
h1, h2, h3, h4, h5, h6,
|
||||
div.example p b,
|
||||
.question,
|
||||
div.table p b,
|
||||
div.procedure p b {
|
||||
color: #990000;
|
||||
}
|
||||
|
||||
body h1, body h2, body h3, body h4, body h5, body h6 {
|
||||
line-height: 1.3;
|
||||
margin-left: 0;
|
||||
}
|
||||
|
||||
body h1, body h2 {
|
||||
margin: .8em 0 0 -4%;
|
||||
}
|
||||
|
||||
body h3, body h4 {
|
||||
margin: .8em 0 0 -3%;
|
||||
}
|
||||
|
||||
body h5 {
|
||||
margin: .8em 0 0 -2%;
|
||||
}
|
||||
|
||||
body h6 {
|
||||
margin: .8em 0 0 -1%;
|
||||
}
|
||||
|
||||
body hr {
|
||||
margin: .6em;
|
||||
border-width: 0 0 1px 0;
|
||||
border-style: solid;
|
||||
border-color: #cecece;
|
||||
}
|
||||
|
||||
body img.navheader {
|
||||
margin: 0 0 0 -4%;
|
||||
}
|
||||
|
||||
ol {
|
||||
margin: 0 0 0 5%;
|
||||
line-height: 1.2;
|
||||
}
|
||||
|
||||
body pre {
|
||||
margin: .75em 0;
|
||||
line-height: 1.0;
|
||||
font-family: monospace;
|
||||
}
|
||||
|
||||
body td, body th {
|
||||
line-height: 1.2;
|
||||
}
|
||||
|
||||
ul, body dir, body menu {
|
||||
margin: 0 0 0 5%;
|
||||
line-height: 1.2;
|
||||
}
|
||||
|
||||
html {
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
body p b.application {
|
||||
color: #000000;
|
||||
}
|
||||
body p span.application {
|
||||
font-weight: bold;
|
||||
color: #000000;
|
||||
}
|
||||
|
||||
.filename {
|
||||
color: #007a00;
|
||||
}
|
||||
|
||||
.guimenu, .guimenuitem, .guisubmenu,
|
||||
.guilabel, .interface,
|
||||
.shortcut, .shortcut .keycap {
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
.guibutton {
|
||||
background-color: #cfcfcf;
|
||||
padding: 2px;
|
||||
}
|
||||
|
||||
.accel {
|
||||
background-color: #f0f0f0;
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
.screen {
|
||||
padding: 1ex;
|
||||
}
|
||||
|
||||
.programlisting {
|
||||
padding: 1ex;
|
||||
background-color: #eee;
|
||||
border: 1px solid #ccc;
|
||||
}
|
||||
|
||||
@media screen { /* hide from ie3 */
|
||||
a[href]:hover { background: #ffa }
|
||||
}
|
||||
|
||||
blockquote.note {
|
||||
color: #222;
|
||||
background: #eee;
|
||||
border: 1px solid #ccc;
|
||||
padding: 0.4em 0.4em;
|
||||
width: 85%;
|
||||
}
|
||||
|
||||
blockquote.tip {
|
||||
color: #004f00;
|
||||
background: #d8ecd6;
|
||||
border: 1px solid green;
|
||||
padding: 0.2em 2em;
|
||||
width: 85%;
|
||||
}
|
||||
|
||||
blockquote.important {
|
||||
font-style:italic;
|
||||
border: 1px solid #a00;
|
||||
border-left: 12px solid #c00;
|
||||
padding: 0.1em 1em;
|
||||
}
|
||||
|
||||
blockquote.warning {
|
||||
color: #9f1313;
|
||||
background: #f8e8e8;
|
||||
border: 1px solid #e59595;
|
||||
padding: 0.2em 2em;
|
||||
width: 85%;
|
||||
}
|
||||
|
||||
.example {
|
||||
background: #fefde6;
|
||||
border: 1px solid #f1bb16;
|
||||
margin: 1em 0;
|
||||
padding: 0.2em 2em;
|
||||
width: 90%;
|
||||
}
|
||||
|
||||
.informaltable table.calstable tr td {
|
||||
padding-left: 1em;
|
||||
padding-right: 1em;
|
||||
}
|
||||
|
|
@ -34,6 +34,9 @@
|
|||
<para>This document introduces full text search notions
|
||||
and describes the installation and use of the &RCL;
|
||||
application. It currently describes &RCL; &RCLVERSION;.</para>
|
||||
<!-- <para>[ <ulink url="index.html">Split HTML</ulink> /
|
||||
<ulink url="usermanual-xml.html">Single HTML</ulink> ]</para>
|
||||
-->
|
||||
</abstract>
|
||||
|
||||
|
||||
|
|
@ -45,12 +48,12 @@
|
|||
<sect1 id="rcl.introduction.tryit">
|
||||
<title>Giving it a try</title>
|
||||
|
||||
<para>If you do not like reading manuals (who does?) and would
|
||||
like to give &RCL; a try, just perform <link
|
||||
linkend="rcl.install.binary">installation</link> and start the
|
||||
<command>recoll</command> user interface, which will index your
|
||||
home directory by default, allowing you to search immediately after
|
||||
indexing completes.</para>
|
||||
<para>If you do not like reading manuals (who does?) and would like
|
||||
to give &RCL; a try, just <link
|
||||
linkend="rcl.install.binary">install</link> the application and
|
||||
start the <command>recoll</command> graphical user interface (GUI),
|
||||
which will ask to index your home directory by default, allowing
|
||||
you to search immediately after indexing completes.</para>
|
||||
|
||||
<para>Do not do this if your home directory contains a huge
|
||||
number of documents and you do not want to wait or are very
|
||||
|
|
@ -135,45 +138,65 @@
|
|||
different character sets, encodings, and languages into the same
|
||||
index. It has input filters for many document types.</para>
|
||||
|
||||
<para>Stemming depends on the document language. &RCL; stores
|
||||
the unstemmed versions of terms and uses auxiliary databases for
|
||||
term expansion. It can switch stemming languages, or add a
|
||||
language, without re-indexing. Storing documents in different
|
||||
languages in the same index is possible, and useful in
|
||||
practice, but does introduce possibilities of confusion. &RCL;
|
||||
currently makes no attempt at automatic language recognition.</para>
|
||||
<para>Stemming is the process by which &RCL; reduces words to
|
||||
their radicals so that searching does not depend, for example,
|
||||
on a word being singular or plural (floor, floors), or on a verb
|
||||
tense (flooring, floored). Because the mechanisms used for
|
||||
stemming depend on the specific grammatical rules for each
|
||||
language, there is a separate stemmer module for most common
|
||||
languages where stemming makes sense. Storing documents written
|
||||
in different languages in the same index is possible, and
|
||||
commonly done. In this situation, you can specify several
|
||||
stemming languages for the index. &RCL; stores the unstemmed
|
||||
versions of terms in the main index and uses auxiliary databases
|
||||
for term expansion (one for each stemming language), which means
|
||||
that you can switch stemming languages between searches, or add
|
||||
a language without needing a full reindex. &RCL; currently
|
||||
makes no attempt at automatic language recognition, which means
|
||||
that the stemmer will sometimes be applied to terms from other
|
||||
languages with potentially strange results. In practise, even if
|
||||
this introduces possibilities of confusion, this approach has
|
||||
been proven quite useful, and, awaiting the addition of an
|
||||
automatic language recognition module to &RCL;, it is much less
|
||||
cumbersome than separating your documents according to what
|
||||
language they are written in.</para>
|
||||
|
||||
<para>&RCL; has many parameters which define exactly what to
|
||||
index, and how to classify and decode the source documents. These
|
||||
are kept in <link linkend="rcl.indexing.config">configuration
|
||||
files</link>. A default configuration is copied into a standard
|
||||
location (usually something like
|
||||
<filename>/usr/[local/]share/recoll/examples</filename>) during
|
||||
installation. The default parameters from this file may be
|
||||
overridden by values that you set inside your personal
|
||||
configuration, found by default in the <filename>.recoll</filename>
|
||||
sub-directory of your home directory. The default configuration
|
||||
will index your home directory with default parameters and should
|
||||
be sufficient for giving &RCL; a try, but you may want to adjust it
|
||||
later, which can be done either by editing the text files or by
|
||||
using configuration menus in the <command>recoll</command>
|
||||
GUI</para>
|
||||
index, and how to classify and decode the source
|
||||
documents. These are kept in <link
|
||||
linkend="rcl.indexing.config">configuration files</link>. A
|
||||
default configuration is copied into a standard location
|
||||
(usually something like
|
||||
<filename>/usr/[local/]share/recoll/examples</filename>)
|
||||
during installation. The default values set by the
|
||||
configuration files in this directory may be overridden by
|
||||
values that you set inside your personal configuration, found
|
||||
by default in the <filename>.recoll</filename> sub-directory
|
||||
of your home directory. The default configuration will index
|
||||
your home directory with default parameters and should be
|
||||
sufficient for giving &RCL; a try, but you may want to adjust
|
||||
it later, which can be done either by editing the text files
|
||||
or by using configuration menus in the
|
||||
<command>recoll</command> GUI</para>
|
||||
|
||||
<para><link linkend="rcl.indexing.periodic.exec">Indexing</link>
|
||||
is started automatically the first time you execute the
|
||||
<command>recoll</command> search graphical user interface, or by
|
||||
executing the <command>recollindex</command> command.</para>
|
||||
<para>The <link linkend="rcl.indexing.periodic.exec">indexing
|
||||
process</link> is started automatically the first time you
|
||||
execute the <command>recoll</command> GUI. Indexing can also be
|
||||
performed by executing the <command>recollindex</command>
|
||||
command.</para>
|
||||
|
||||
<para><link linkend="rcl.search">Searches</link> are usually
|
||||
performed inside the <command>recoll</command> graphical user
|
||||
interface (GUI) program, which has many options to help you find
|
||||
what you are looking for. However, there are other ways to perform
|
||||
&RCL; searches: mostly a <link linkend="rcl.search.commandline">
|
||||
command line tool</link>, a
|
||||
performed inside the <command>recoll</command> GUI, which has many
|
||||
options to help you find what you are looking for. However, there
|
||||
are other ways to perform &RCL; searches: mostly a <link
|
||||
linkend="rcl.search.commandline">
|
||||
command line interface</link>, a
|
||||
<link linkend="rcl.program.api.python">
|
||||
<application>Python</application>
|
||||
programming interface</link>, and a <link linkend="rcl.searchkio">
|
||||
<application>KDE</application> KIO slave module</link>.</para>
|
||||
programming interface</link>, a <link linkend="rcl.searchkio">
|
||||
<application>KDE</application> KIO slave module</link>, and
|
||||
a <application>Ubuntu Unity Lens</application> module.
|
||||
</para>
|
||||
|
||||
</sect1>
|
||||
</chapter>
|
||||
|
|
@ -234,25 +257,27 @@
|
|||
<link linkend="rcl.indexing.config">configuration files</link>.</para>
|
||||
|
||||
<para>Most file types, like HTML or word processing files, only hold
|
||||
one document. Some file types, like mail folder files or zip
|
||||
one document. Some file types, like email folders or zip
|
||||
archives, can hold many individually indexed documents, which may
|
||||
in turn be themselves compound ones. Such hierarchies can go quite
|
||||
deep, and &RCL; has no problem processing, for example, an ms-word
|
||||
document which would be an attachment to an email message part of
|
||||
a folder file archived inside a zip file...</para>
|
||||
deep, and &RCL; can process, for example, an
|
||||
<application>ms-word</application>
|
||||
document stored as an attachment to an email message inside an
|
||||
email folder archived in a zip file...</para>
|
||||
|
||||
<para>&RCL; indexing processes plain text, HTML, openoffice
|
||||
and e-mail files, and a few others internally.</para>
|
||||
<para>&RCL; indexing processes plain text, HTML, OpenDocument
|
||||
(Open/LibreOffice), email formats, and a few others internally.</para>
|
||||
|
||||
<para>Other file types (ie: postscript, pdf, ms-word, rtf ...)
|
||||
need external applications for preprocessing. The list is in the
|
||||
<link linkend="rcl.install.external"> installation</link>
|
||||
section. After every indexing operation, &RCL; updates a list of
|
||||
commands that would be needed for indexing existing files
|
||||
types. This list can be displayed from the
|
||||
<command>recoll</command> <guilabel>File</guilabel> menu. It is
|
||||
stored in the <filename>missing</filename> text file
|
||||
inside the configuration directory.</para>
|
||||
types. This list can be displayed by selecting the menu option
|
||||
<guilabel>File</guilabel>-><guilabel>Show Missing Helpers</guilabel>
|
||||
in the <command>recoll</command> GUI. It is stored in the
|
||||
<filename>missing</filename> text file inside the configuration
|
||||
directory.</para>
|
||||
|
||||
<para>Without further configuration, &RCL; will index all
|
||||
appropriate files from your home directory, with a reasonable
|
||||
|
|
@ -336,9 +361,9 @@ recoll
|
|||
indexed).</para>
|
||||
|
||||
<para>Of course, images, sound and video do not increase the
|
||||
index size, which means that it will be quite typical nowadays
|
||||
(2006), that even a big index will be negligible against the
|
||||
total amount of data on the computer.</para>
|
||||
index size, which means that nowadays (2012), typically, even a big
|
||||
index will be negligible against the total amount of data on the
|
||||
computer.</para>
|
||||
|
||||
<para>The index data directory (<filename>xapiandb</filename>)
|
||||
only contains data that can be completely rebuilt by an index run
|
||||
|
|
@ -439,14 +464,20 @@ recoll
|
|||
option.)</para>
|
||||
|
||||
<para>The interface is started from the
|
||||
<guilabel>Preferences</guilabel> menu. It has two main
|
||||
panels. The first panel allows setting global variables, like
|
||||
the list of top directories or the list of skipped paths. The
|
||||
second panel allows setting variables that can be redefined
|
||||
for subdirectories. This second panel has an initially empty list of
|
||||
customisation directories, to which you can add. The variables
|
||||
are then set for the currently selected directory (or at the top
|
||||
level if the empty line is selected).</para>
|
||||
<guilabel>Preferences</guilabel>-><guilabel>Indexing
|
||||
Configuration</guilabel> menu entry. It is divided in three tabs,
|
||||
<guilabel>Global parameters</guilabel>, <guilabel>Local
|
||||
parameters</guilabel>, and <guilabel>Beagle web history</guilabel>,
|
||||
which is explained in the next section.</para>
|
||||
|
||||
<para>The first tab allows setting global variables, like the lists
|
||||
of top directories, skipped paths, or stemming languages.</para>
|
||||
|
||||
<para>The second tab allows setting variables that can be redefined
|
||||
for subdirectories. This second tab has an initially empty list of
|
||||
customisation directories, to which you can add. The variables are
|
||||
then set for the currently selected directory (or at the top level
|
||||
if the empty line is selected).</para>
|
||||
|
||||
<para>The meaning for most entries in the interface is
|
||||
self-evident and documented by a <literal>ToolTip</literal>
|
||||
|
|
@ -521,15 +552,17 @@ recoll
|
|||
if canceled).</para>
|
||||
|
||||
<para>The <command>recollindex</command> indexing process can be
|
||||
interrupted by sending an interrupt (^C, SIGINT) or terminate
|
||||
interrupted by sending an interrupt (Ctrl-C, SIGINT) or terminate
|
||||
(SIGTERM) signal. Some time may elapse before the process exits,
|
||||
because it needs to properly flush and close the index. The
|
||||
indexing thread can be equivalently stopped from the menu.</para>
|
||||
because it needs to properly flush and close the index. This can
|
||||
also be done from the <command>recoll</command> GUI
|
||||
<guilabel>File</guilabel>-><guilabel>Stop Indexing</guilabel>
|
||||
menu entry.</para>
|
||||
|
||||
<para>After such an interruption, the index will be somewhat
|
||||
inconsistent because some operations which are normally performed
|
||||
at the end of the indexing pass will have been skipped (for
|
||||
exemple, the stemming and spelling databases will be inexistant
|
||||
example, the stemming and spelling databases will be inexistant
|
||||
or out of date). You just need to restart indexing at a later
|
||||
time to restore consistency. The indexing will restart at the
|
||||
interruption point (the full file tree will be traversed,
|
||||
|
|
@ -576,7 +609,8 @@ recoll
|
|||
<para>As of version 1.17 the &RCL; GUI has dialogs to manage
|
||||
<filename>crontab</filename> entries for
|
||||
<command>recollindex</command>. You can reach them from the
|
||||
<guimenu>Preferences->Indexing Schedule</guimenu> menu. They only
|
||||
<guilabel>Preferences</guilabel>-><guilabel>Indexing
|
||||
Schedule</guilabel> menu. They only
|
||||
work with the good old <command>cron</command>, and do not give
|
||||
access to all features of <command>cron</command> scheduling.</para>
|
||||
|
||||
|
|
@ -652,12 +686,13 @@ fvwm
|
|||
on the log level.</para>
|
||||
|
||||
<para>When building &RCL;, the real time indexing support can be
|
||||
customised during package
|
||||
<link linkend="rcl.install.building.build">configuration</link>
|
||||
with the <literal>--with[out]-fam</literal> or
|
||||
customised during package <link
|
||||
linkend="rcl.install.building.build">configuration</link> with the
|
||||
<literal>--with[out]-fam</literal> or
|
||||
<literal>--with[out]-inotify</literal> options. The default is
|
||||
currently to include inotify monitoring on systems that support
|
||||
it, and, as of recoll 1.17, gamin support on FreeBSD.</para>
|
||||
currently to include <application>inotify</application> monitoring
|
||||
on systems that support it, and, as of recoll 1.17,
|
||||
<application>gamin</application> support on FreeBSD.</para>
|
||||
|
||||
<para>While it is convenient that data is indexed in real time,
|
||||
repeated indexing can generate a significant load on the
|
||||
|
|
@ -712,7 +747,7 @@ fvwm
|
|||
<para>In most cases, you can enter the terms as you
|
||||
think them, even if they contain embedded punctuation or other
|
||||
non-textual characters. For
|
||||
exemple, &RCL; can handle things like e-mail addresses, or
|
||||
example, &RCL; can handle things like email addresses, or
|
||||
arbitrary cut and paste from another text window, punctation
|
||||
and all.</para>
|
||||
|
||||
|
|
@ -950,7 +985,7 @@ fvwm
|
|||
that you can't actually visualize the folder (there will be an
|
||||
error dialog if you try). &RCL; is unfortunately not yet smart
|
||||
enough to disable the entry in this case. In other cases, the
|
||||
<guilabel>Open</guilabel> option makes sense, for exemple to
|
||||
<guilabel>Open</guilabel> option makes sense, for example to
|
||||
start a <application>chm</application> viewer on the parent
|
||||
document for a help page.</para>
|
||||
|
||||
|
|
@ -1006,7 +1041,7 @@ fvwm
|
|||
create a new preview window. The old one stays open until you
|
||||
close it.</para>
|
||||
|
||||
<para>You can close a preview tab by typing <keycap>^W</keycap>
|
||||
<para>You can close a preview tab by typing <keycap>Ctrl-W</keycap>
|
||||
(<keycap>Ctrl</keycap> + <keycap>W</keycap>) in the
|
||||
window. Closing the last tab for a window will also close the
|
||||
window.</para>
|
||||
|
|
@ -1030,7 +1065,7 @@ fvwm
|
|||
<keycap>F3</keycap> inside the text area to get to the next
|
||||
occurrence.</para>
|
||||
|
||||
<para>If you have a search string entered and you use ^Up/^Down
|
||||
<para>If you have a search string entered and you use Ctrl-Up/Ctrl-Down
|
||||
to browse the results, the search is initiated for each successive
|
||||
document. If the string is found, the cursor will be positioned
|
||||
at the first occurrence of the search string.</para>
|
||||
|
|
@ -1042,8 +1077,8 @@ fvwm
|
|||
the main text but in one of the fields.</para>
|
||||
|
||||
<para>You can print the current preview window contents by typing
|
||||
<keycap>^P</keycap> (<keycap>Ctrl</keycap> + <keycap>P</keycap>) in
|
||||
the window text.</para>
|
||||
<keycap>Ctrl-P</keycap> (<keycap>Ctrl</keycap> +
|
||||
<keycap>P</keycap>) in the window text.</para>
|
||||
|
||||
</sect2>
|
||||
|
||||
|
|
@ -1539,19 +1574,19 @@ fvwm
|
|||
</formalpara>
|
||||
|
||||
<formalpara><title>Closing previews</title>
|
||||
<para>Entering <keycap>^W</keycap> in a tab will
|
||||
<para>Entering <keycap>Ctrl-W</keycap> in a tab will
|
||||
close it (and, for the last tab, close the preview
|
||||
window). Entering <keycap>Esc</keycap> will close the preview
|
||||
window and all its tabs.</para>
|
||||
</formalpara>
|
||||
|
||||
<formalpara><title>Printing previews</title>
|
||||
<para>Entering <keycap>^P</keycap> in a preview window will print
|
||||
<para>Entering <keycap>Ctrl-P</keycap> in a preview window will print
|
||||
the currently displayed text.</para>
|
||||
</formalpara>
|
||||
|
||||
<formalpara><title>Quitting</title>
|
||||
<para>Entering <keycap>^Q</keycap> almost anywhere will
|
||||
<para>Entering <keycap>Ctrl-Q</keycap> almost anywhere will
|
||||
close the application.</para>
|
||||
</formalpara>
|
||||
</sect3>
|
||||
|
|
@ -1588,9 +1623,10 @@ fvwm
|
|||
on startup. The default value is empty, but there is a
|
||||
skeleton style sheet (<filename>recoll.qss</filename>)
|
||||
inside the <filename>/usr/share/recoll/examples</filename>
|
||||
directory. Using a style sheet, you can change most Recoll
|
||||
graphical parameters: colors, fonts, etc. See the sample
|
||||
file for a few simple examples.</para>
|
||||
directory. Using a style sheet, you can change most
|
||||
<command>recoll</command> graphical parameters: colors,
|
||||
fonts, etc. See the sample file for a few simple
|
||||
examples.</para>
|
||||
</listitem>
|
||||
|
||||
<listitem><para><guilabel>Maximum text size highlighted for
|
||||
|
|
@ -1830,7 +1866,7 @@ fvwm
|
|||
<para>No more detail will be given about the header part (only
|
||||
useful with the WebKit build), if there are restrictions to
|
||||
what you can do, they are beyond this author's HTML/CSS/Javascript
|
||||
abilities... There are a few exemples on the
|
||||
abilities... There are a few examples on the
|
||||
<ulink url="http://www.recoll.org/custom.html">page about
|
||||
customising the result list</ulink> on the &RCL; web site.</para>
|
||||
|
||||
|
|
@ -2126,7 +2162,7 @@ text/html [file:///Users/uncrypted-dockes/projets/bateaux/ilur/factEtCie/r
|
|||
<replaceable>potatoes</replaceable> (in any part of the document).</para>
|
||||
|
||||
<para>An element is composed of an optional field specification,
|
||||
and a value, separated by a colon. Exemple:
|
||||
and a value, separated by a colon. Example:
|
||||
<replaceable>Beatles</replaceable>,
|
||||
<replaceable>author:balzac</replaceable>,
|
||||
<replaceable>dc:title:grandet</replaceable> </para>
|
||||
|
|
@ -2163,7 +2199,7 @@ text/html [file:///Users/uncrypted-dockes/projets/bateaux/ilur/factEtCie/r
|
|||
<replaceable>title:prejudice title:pride</replaceable>, and is
|
||||
unlikely to find a result.</para>
|
||||
|
||||
<para>Modifiers can be set on a phrase clause, for exemple to specify
|
||||
<para>Modifiers can be set on a phrase clause, for example to specify
|
||||
a proximity search (unordered). See
|
||||
<link linkend="rcl.search.lang.modifiers">the modifier
|
||||
section</link>.</para>
|
||||
|
|
@ -2209,7 +2245,7 @@ text/html [file:///Users/uncrypted-dockes/projets/bateaux/ilur/factEtCie/r
|
|||
</listitem>
|
||||
|
||||
<listitem><para><literal>size</literal> for filtering the
|
||||
results on file size. Exemple:
|
||||
results on file size. Example:
|
||||
<literal>size<10000</literal>. You can use
|
||||
<literal><</literal>, <literal>></literal> or
|
||||
<literal>=</literal> as operators. You can specify a range like the
|
||||
|
|
@ -2233,7 +2269,7 @@ text/html [file:///Users/uncrypted-dockes/projets/bateaux/ilur/factEtCie/r
|
|||
The days and months parts may be missing. If the
|
||||
<literal>/</literal> is present but an element is missing, the
|
||||
missing element is interpreted as the lowest or highest date in the
|
||||
index. Exemples:</para>
|
||||
index. Examples:</para>
|
||||
<itemizedlist>
|
||||
<listitem><para><literal>2001-03-01/2002-05-01</literal> the
|
||||
basic syntax for an interval of dates.</para>
|
||||
|
|
@ -2555,7 +2591,7 @@ text/html [file:///Users/uncrypted-dockes/projets/bateaux/ilur/factEtCie/r
|
|||
<literal>Subject:</literal> for email) when indexing. This is not
|
||||
essential.</para>
|
||||
|
||||
<para>You should look to one of the simple filters, for exemple
|
||||
<para>You should look to one of the simple filters, for example
|
||||
<literal>rclps</literal> for a starting point.</para>
|
||||
|
||||
<para>Don't forget to make your filter executable before
|
||||
|
|
@ -3087,7 +3123,7 @@ while query.next >= 0 and query.next < nres:
|
|||
<para>You will only have to check or install <link
|
||||
linkend="rcl.install.external">supporting applications</link>
|
||||
for the file types that you want to index beyond those that are
|
||||
natively processed by &RCL; (text, HTML, mail files, and a few
|
||||
natively processed by &RCL; (text, HTML, email files, and a few
|
||||
others).</para>
|
||||
|
||||
<para>You should also maybe have a look at the
|
||||
|
|
@ -3259,13 +3295,13 @@ while query.next >= 0 and query.next < nres:
|
|||
<listitem><para>Konqueror webarchive format with Python (uses the
|
||||
Tarfile module).</para></listitem>
|
||||
|
||||
<listitem><para>mimehtml web archive format (support based on the mail
|
||||
<listitem><para>mimehtml web archive format (support based on the email
|
||||
filter, which introduces some mild weirdness, but still
|
||||
usable).</para></listitem>
|
||||
|
||||
</itemizedlist>
|
||||
|
||||
<para>Text, HTML, mail folders, and Scribus files are
|
||||
<para>Text, HTML, email folders, and Scribus files are
|
||||
processed internally. <application>Lyx</application> is used to
|
||||
index Lyx files. Many filters need <command>iconv</command> and the
|
||||
standard <command>sed</command> and <command>awk</command>.
|
||||
|
|
@ -3557,6 +3593,28 @@ while query.next >= 0 and query.next < nres:
|
|||
List elements with embedded spaces can be quoted using
|
||||
double-quotes.</para>
|
||||
|
||||
<formalpara><title>Encoding issues</title>
|
||||
<para>Most of the configuration parameters are plain ASCII. Two
|
||||
particular sets of values may cause encoding issues:</para>
|
||||
|
||||
<itemizedlist>
|
||||
<listitem><para>File path parameters may contain non-ascii
|
||||
characters and should use the exact same byte values as found in
|
||||
the file system directory. Usually, this means that the
|
||||
configuration file should use the system default locale
|
||||
encoding.</para>
|
||||
</listitem>
|
||||
<listitem><para>The <literal>unac_except_trans</literal> parameter
|
||||
should be encoded in UTF-8. If your system locale is not UTF-8, and
|
||||
you need to also specify non-ascii file paths, this poses a
|
||||
difficulty because common text editors cannot handle multiple
|
||||
encodings in a single file. In this relatively unlikely case, you
|
||||
can edit the configuration file as two separate text files with
|
||||
appropriate encodings, and concatenate them to create the complete
|
||||
configuration.</para>
|
||||
</listitem>
|
||||
</itemizedlist>
|
||||
|
||||
<sect2 id="rcl.install.config.recollconf">
|
||||
<title>Main configuration file</title>
|
||||
|
||||
|
|
@ -3611,7 +3669,7 @@ skippedNames = #* bin CVS Cache cache* caughtspam tmp .thumbnails .svn \
|
|||
<para>The list in the default configuration does not
|
||||
exclude hidden directories (names beginning with a
|
||||
dot), which means that it may index quite a few things
|
||||
that you do not want. On the other hand, mail user
|
||||
that you do not want. On the other hand, email user
|
||||
agents like <application>thunderbird</application>
|
||||
usually store messages in hidden directories, and you
|
||||
probably want this indexed. One possible solution is to
|
||||
|
|
@ -3816,9 +3874,36 @@ skippedPaths = ~/somedir/∗.txt
|
|||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
<varlistentry><term><literal>unac_except_trans</literal></term>
|
||||
<listitem><para>This is a list of characters, encoded in UTF-8,
|
||||
which should be handled specially when converting text to
|
||||
unaccented lowercase. For example, in Swedish, the letter
|
||||
<literal>a with diaeresis </literal> has full alphabet
|
||||
citizenship and should not be turned into an
|
||||
<literal>a</literal>. Each element in the space-separated list
|
||||
has the special character as first element and the translation
|
||||
following. The handling of both the lowercase and upper-case
|
||||
versions of a character should be specified, as appartenance to
|
||||
the list will turn-off both standard accent and case
|
||||
processing. Example for Swedish:</para>
|
||||
<programlisting>
|
||||
unac_except_trans = åå Åå ää Ää öö Öö
|
||||
</programlisting>
|
||||
|
||||
<para>Note that the translation is not limited to a single
|
||||
character, you could very well have something like
|
||||
<literal>üue</literal> in the list.</para>
|
||||
|
||||
<para>This parameter can't be defined for subdirectories, it
|
||||
is global, because there is no way to do otherwise when
|
||||
querying. If you have document sets which would need different
|
||||
values, you will have to index and query them separately.</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
<varlistentry><term><literal>maildefcharset</literal></term>
|
||||
<listitem><para>This can be used to define the default
|
||||
character set specifically for mail messages which don't
|
||||
character set specifically for email messages which don't
|
||||
specify it. This is mainly useful for readpst (libpst) dumps,
|
||||
which are utf-8 but do not say so.</para>
|
||||
</listitem>
|
||||
|
|
@ -4081,9 +4166,9 @@ mondelaypatterns = *.log:20 "this one has spaces*:10"
|
|||
<varlistentry>
|
||||
<term>filter-specific sections</term>
|
||||
<listitem><para>Some filters may need specific
|
||||
configuration for handling fields. Only the mail message filter
|
||||
configuration for handling fields. Only the email message filter
|
||||
currently has such a section (named
|
||||
<literal>[mail]</literal>). It allows indexing arbitrary mail
|
||||
<literal>[mail]</literal>). It allows indexing arbitrary email
|
||||
headers in addition to the ones indexed by default. Other such
|
||||
sections may appear in the future.</para>
|
||||
</listitem>
|
||||
|
|
@ -4093,9 +4178,9 @@ mondelaypatterns = *.log:20 "this one has spaces*:10"
|
|||
|
||||
<para>Here follows a small example of a personal
|
||||
<filename>fields</filename>
|
||||
file. This would extract a specific mail header and
|
||||
file. This would extract a specific email header and
|
||||
use it as a searchable field, with data displayable inside result
|
||||
lists. (Side note: as the mail filter does no decoding on the values,
|
||||
lists. (Side note: as the email filter does no decoding on the values,
|
||||
only plain ascii headers can be indexed, and only the
|
||||
first occurrence will be used for headers that occur several times).
|
||||
|
||||
|
|
|
|||
49
src/doc/user/xmlmake.sh
Normal file
49
src/doc/user/xmlmake.sh
Normal file
|
|
@ -0,0 +1,49 @@
|
|||
#!/bin/sh
|
||||
|
||||
# A script to produce the Recoll manual with an xml toolchain.
|
||||
# Limitations:
|
||||
# - Does not produce the links to the whole/chunked versions at the top
|
||||
# of the document
|
||||
# - The anchor names from the source text are converted to uppercase by
|
||||
# the sgml toolchain. This does not happen with the xml toolchain,
|
||||
# which means that external links like
|
||||
# usermanual.html#RCL.CONFIG.INDEXING won't work because fragments are
|
||||
# case-sensitive. This could be solved by converting all ids inside the
|
||||
# source file to upper-case.
|
||||
|
||||
# Wherever docbook.xsl and chunk.xsl live
|
||||
XSLDIR="/usr/local/share/xsl/docbook/"
|
||||
|
||||
dochunky=1
|
||||
test $# -eq 1 && dochunky=0
|
||||
|
||||
# Remove the SGML header and uncomment the XML one
|
||||
sed -e '\!//FreeBSD//DTD!d' \
|
||||
-e '\!DTD DocBook XML!s/<!--//' \
|
||||
-e '\!/docbookx.dtd!s/-->//' \
|
||||
< usermanual.sgml > usermanual.xml
|
||||
|
||||
# Options common to the single-file and chunked versions
|
||||
commonoptions="--stringparam section.autolabel 1 \
|
||||
--stringparam section.autolabel.max.depth 3 \
|
||||
--stringparam section.label.includes.component.label 1 \
|
||||
--stringparam autotoc.label.in.hyperlink 0 \
|
||||
--stringparam abstract.notitle.enabled 1 \
|
||||
--stringparam html.stylesheet docbook-xsl.css \
|
||||
--stringparam generate.toc \"book toc,title,figure,table,example,equation\" \
|
||||
"
|
||||
|
||||
# Do the chunky thing
|
||||
test $dochunky -ne 0 && eval xsltproc $commonoptions \
|
||||
--stringparam use.id.as.filename 1 \
|
||||
"$XSLDIR/html/chunk.xsl" \
|
||||
usermanual.xml
|
||||
|
||||
# Produce the single file version
|
||||
eval xsltproc $commonoptions \
|
||||
-o usermanual-xml.html \
|
||||
"$XSLDIR/html/docbook.xsl" \
|
||||
usermanual.xml
|
||||
|
||||
tidy -indent usermanual-xml.html > tmpfile
|
||||
mv -f tmpfile usermanual-xml.html
|
||||
|
|
@ -2,11 +2,20 @@
|
|||
"""Extract Html files from a Microsoft Compiled Html Help file (.chm)
|
||||
Needs at least python 2.2 for HTMLParser (chmlib needs 2.2 too)"""
|
||||
|
||||
# Do we return individual chapters as html pages or concatenate everything?
|
||||
rclchm_catenate = 0
|
||||
# Use special html type to allow for mimeconf/mimeview Open magic,
|
||||
# Or go the regular html way with text/html
|
||||
#rclchm_html_mtype = "text/x-chm-html"
|
||||
rclchm_html_mtype = "text/html"
|
||||
|
||||
import sys
|
||||
import os
|
||||
import posixpath
|
||||
import urlparse
|
||||
import urllib
|
||||
if rclchm_catenate:
|
||||
import subprocess
|
||||
|
||||
import rclexecm
|
||||
|
||||
|
|
@ -171,6 +180,10 @@ class rclCHM:
|
|||
self.tp = ChmTopicsParser(em)
|
||||
self.currentindex = 0
|
||||
self.em = em
|
||||
if rclchm_catenate:
|
||||
self.em.setmimetype("text/plain")
|
||||
else:
|
||||
self.em.setmimetype(rclchm_html_mtype)
|
||||
|
||||
def extractone(self, path):
|
||||
"""Extract one path-named internal file from the chm file"""
|
||||
|
|
@ -188,10 +201,27 @@ class rclCHM:
|
|||
res, doc = self.chm.RetrieveObject(ui)
|
||||
#self.em.rclog("extract: RetrieveObject: %d [%s]" % (res, doc))
|
||||
if res > 0:
|
||||
self.em.setmimetype("text/html")
|
||||
self.em.setmimetype(rclchm_html_mtype)
|
||||
return (True, doc, path, iseof)
|
||||
return (False, "", path, iseof)
|
||||
|
||||
def dumpall(self):
|
||||
alltxt=""
|
||||
for pth in self.tp.contents:
|
||||
ret,doc,path,iseof = self.extractone(pth)
|
||||
if not ret:
|
||||
continue
|
||||
# Feed doc to lynx
|
||||
process = subprocess.Popen(["lynx", "-stdin", "-dump", "-nolist",
|
||||
"-display_charset=utf8",
|
||||
"-force_html"],
|
||||
stdin=subprocess.PIPE,
|
||||
stdout=subprocess.PIPE
|
||||
)
|
||||
txt,err = process.communicate(doc)
|
||||
alltxt += txt
|
||||
return alltxt
|
||||
|
||||
def openfile(self, params):
|
||||
"""Open the chm file and build the contents list by extracting and
|
||||
parsing the Topics object"""
|
||||
|
|
@ -239,6 +269,13 @@ class rclCHM:
|
|||
return self.extractone(params["ipath:"])
|
||||
|
||||
def getnext(self, params):
|
||||
if rclchm_catenate:
|
||||
alltxt = self.dumpall()
|
||||
if alltxt:
|
||||
return (True, alltxt, "", rclexecm.RclExecM.eofnext)
|
||||
else:
|
||||
return (False, "", "", rclexecm.RclExecM.eofnow)
|
||||
|
||||
if self.currentindex >= len(self.tp.contents):
|
||||
return (False, "", "", rclexecm.RclExecM.eofnow)
|
||||
else:
|
||||
|
|
|
|||
124
src/filters/rcldia
Executable file
124
src/filters/rcldia
Executable file
|
|
@ -0,0 +1,124 @@
|
|||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
# dia (http://live.gnome.org/Dia) file filter for recoll
|
||||
# stefan.friedel@iwr.uni-heidelberg.de 2012
|
||||
#
|
||||
# add the following to ~/.recoll/mimeconf into the [index] section:
|
||||
# application/x-dia-diagram = execm rcldia;mimetype=text/html;charset=utf-8
|
||||
# and into the [icons] section:
|
||||
# application/x-dia-diagram = drawing
|
||||
# and finally under [categories]:
|
||||
# other = ...\
|
||||
# application/x-dia-diagram
|
||||
#
|
||||
# in ~/.recoll/mimemap:
|
||||
# .dia = application/x-dia-diagram
|
||||
|
||||
# Small fixes from jfd: dia files are sometimes not compressed.
|
||||
# And a note: this file actually has no reason to return HTML as there is
|
||||
# no metadata. We could just as well and more simply return text/plain
|
||||
import rclexecm
|
||||
import re
|
||||
from gzip import GzipFile
|
||||
import xml.parsers.expat
|
||||
|
||||
# some regexps to parse/format the xml data: delete #/spaces at the b/eol and
|
||||
# ignore empty lines
|
||||
rhs = re.compile(r'^[#|\s+](.*)')
|
||||
rhe = re.compile(r'(.*)[#|\s+]$')
|
||||
rempty = re.compile(r'^#?\s*#?$')
|
||||
|
||||
htmltemplate = '''
|
||||
<html><head>
|
||||
<meta http-equiv="Content-Type" content="text/html;charset=UTF-8">
|
||||
</head>
|
||||
<body>
|
||||
{0}
|
||||
</body>
|
||||
</html>
|
||||
'''
|
||||
|
||||
# xml parser for dia xml file
|
||||
class Parser:
|
||||
def __init__(self,rclem):
|
||||
self._parser = xml.parsers.expat.ParserCreate(encoding='UTF-8')
|
||||
self._parser.StartElementHandler = self.startelement
|
||||
self._parser.EndElementHandler = self.endelement
|
||||
self._parser.CharacterDataHandler = self.chardata
|
||||
self.string = []
|
||||
self.handlethis = False
|
||||
self.rclem = rclem
|
||||
|
||||
def startelement(self, name, attrs):
|
||||
if name == 'dia:string':
|
||||
self.handlethis = True
|
||||
else:
|
||||
self.handlethis = False
|
||||
|
||||
def chardata(self,data):
|
||||
if self.handlethis:
|
||||
# check if line is not empty and replace hashes/spaces
|
||||
# tricky: after htmlescape check also for umlauts
|
||||
if not rempty.search(data):
|
||||
self.string.append(self.rclem.htmlescape(
|
||||
rhe.sub(r'\1',rhs.sub(r'\1',data))).encode('ascii', 'xmlcharrefreplace'))
|
||||
|
||||
def endelement(self,name):
|
||||
self.handlethis = False
|
||||
|
||||
def feed(self, fh):
|
||||
self._parser.ParseFile(fh)
|
||||
del self._parser
|
||||
|
||||
class DiaExtractor:
|
||||
def __init__(self, em):
|
||||
self.em = em
|
||||
|
||||
def extractdia(self):
|
||||
docdata = ""
|
||||
ipath = ""
|
||||
try:
|
||||
docdata = self.ExtractDiaText()
|
||||
ok = True
|
||||
except Exception, err:
|
||||
ok = False
|
||||
iseof = rclexecm.RclExecM.eofnext
|
||||
self.em.setmimetype("text/html")
|
||||
return (ok, docdata, ipath, iseof)
|
||||
|
||||
###### File type handler api, used by rclexecm ---------->
|
||||
def openfile(self, params):
|
||||
try:
|
||||
self.dia = GzipFile(params["filename:"], 'r')
|
||||
# Dial files are sometimes not compressed. Quite weirdly,
|
||||
# GzipFile does not complain until we try to read. Have to do it
|
||||
# here to be able to retry an uncompressed open.
|
||||
data = self.dia.readline()
|
||||
self.dia.seek(0)
|
||||
return True
|
||||
except:
|
||||
# File not compressed ?
|
||||
try:
|
||||
self.dia = open(params["filename:"], 'r')
|
||||
except:
|
||||
return False
|
||||
return True
|
||||
|
||||
def getipath(self, params):
|
||||
ok, data, ipath, eof = self.extractdia()
|
||||
return (ok, data, ipath, eof)
|
||||
|
||||
def getnext(self, params):
|
||||
ok, data, ipath, eof = self.extractdia()
|
||||
return (ok, data, ipath, eof)
|
||||
|
||||
###### read data
|
||||
def ExtractDiaText(self):
|
||||
diap = Parser(self.em)
|
||||
diap.feed(self.dia)
|
||||
return htmltemplate.format('\n'.join(diap.string))
|
||||
|
||||
# Main program: create protocol handler and extractor and run them
|
||||
proto = rclexecm.RclExecM()
|
||||
extract = DiaExtractor(proto)
|
||||
rclexecm.main(proto, extract)
|
||||
|
|
@ -24,8 +24,11 @@ class RclExecM:
|
|||
sys.exit(exitvalue)
|
||||
|
||||
def htmlescape(self, txt):
|
||||
txt = txt.replace("<", "<")
|
||||
# This must stay first (it somehow had managed to skip after
|
||||
# the next line, with rather interesting results)
|
||||
txt = txt.replace("&", "&")
|
||||
|
||||
txt = txt.replace("<", "<")
|
||||
txt = txt.replace('"', "&dquot;")
|
||||
return txt
|
||||
|
||||
|
|
|
|||
|
|
@ -28,14 +28,6 @@ subtreelist : $(SUBTREELIST_OBJS)
|
|||
subtreelist.o : subtreelist.cpp
|
||||
$(CXX) $(ALL_CXXFLAGS) -DTEST_SUBTREELIST -c subtreelist.cpp
|
||||
|
||||
CSGUESS_OBJS= trcsguess.o $(BIGLIB)
|
||||
csguess : $(CSGUESS_OBJS)
|
||||
$(CXX) $(ALL_CXXFLAGS) -o csguess $(CSGUESS_OBJS) \
|
||||
$(LIBICONV)
|
||||
trcsguess.o : csguess.cpp
|
||||
$(CXX) $(ALL_CXXFLAGS) -DTEST_CSGUESS -c -o trcsguess.o \
|
||||
csguess.cpp
|
||||
|
||||
MIMETYPE_OBJS= trmimetype.o $(BIGLIB)
|
||||
mimetype : $(MIMETYPE_OBJS)
|
||||
$(CXX) $(ALL_CXXFLAGS) -o mimetype $(MIMETYPE_OBJS) \
|
||||
|
|
|
|||
|
|
@ -1,215 +0,0 @@
|
|||
/* Copyright (C) 2004 J.F.Dockes
|
||||
* This program is free software; you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation; either version 2 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License
|
||||
* along with this program; if not, write to the
|
||||
* Free Software Foundation, Inc.,
|
||||
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
*/
|
||||
|
||||
#ifndef TEST_CSGUESS
|
||||
|
||||
// This code was converted from estraier / qdbm / myconf.c:
|
||||
|
||||
/**************************************************************************
|
||||
* Copyright (C) 2000-2004 Mikio Hirabayashi
|
||||
*
|
||||
* This file is part of QDBM, Quick Database Manager.
|
||||
*
|
||||
* QDBM is free software; you can redistribute it and/or modify it under the
|
||||
* terms of the GNU Lesser General Public License as published by the Free
|
||||
* Software Foundation; either version 2.1 of the License or any later
|
||||
* version. QDBM is distributed in the hope that it will be useful, but
|
||||
* WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
|
||||
* or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
|
||||
* License for more details. You should have received a copy of the GNU
|
||||
* Lesser General Public License along with QDBM; if not, write to the Free
|
||||
* Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
|
||||
* 02111-1307 USA.
|
||||
* *********************************************************/
|
||||
|
||||
#include <errno.h>
|
||||
#include <cstring>
|
||||
#include <iostream>
|
||||
|
||||
#ifndef NO_NAMESPACES
|
||||
using std::string;
|
||||
#endif /* NO_NAMESPACES */
|
||||
|
||||
#include <iconv.h>
|
||||
|
||||
#include "csguess.h"
|
||||
#include "autoconfig.h"
|
||||
#ifdef RCL_ICONV_INBUF_CONST
|
||||
#define ICV_P2_TYPE const char**
|
||||
#else
|
||||
#define ICV_P2_TYPE char**
|
||||
#endif
|
||||
|
||||
// The values from estraier were 32768, 256, 0.001
|
||||
const int ICONVCHECKSIZ = 32768;
|
||||
const int ICONVMISSMAX = 256;
|
||||
const double ICONVALLWRAT = 0.001;
|
||||
|
||||
// Try to transcode and count errors (for charset guessing)
|
||||
static int transcodeErrCnt(const char *ptr, int size,
|
||||
const char *icode, const char *ocode)
|
||||
{
|
||||
iconv_t ic;
|
||||
char obuf[2*ICONVCHECKSIZ], *wp, *rp;
|
||||
size_t isiz, osiz;
|
||||
int miss;
|
||||
isiz = size;
|
||||
if((ic = iconv_open(ocode, icode)) == (iconv_t)-1)
|
||||
return size;
|
||||
miss = 0;
|
||||
rp = (char *)ptr;
|
||||
while(isiz > 0){
|
||||
osiz = 2*ICONVCHECKSIZ;
|
||||
wp = obuf;
|
||||
if(iconv(ic, (ICV_P2_TYPE)&rp, &isiz, &wp, &osiz) == (size_t)-1){
|
||||
if(errno == EILSEQ || errno == EINVAL){
|
||||
rp++;
|
||||
isiz--;
|
||||
miss++;
|
||||
if(miss >= ICONVMISSMAX)
|
||||
break;
|
||||
} else {
|
||||
miss = size;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
if(iconv_close(ic) == -1)
|
||||
return size;
|
||||
return miss;
|
||||
}
|
||||
|
||||
// Try to guess character encoding. This could be optimized quite a
|
||||
// lot by avoiding the multiple passes on the document, to be done
|
||||
// after usefulness is demonstrated...
|
||||
string csguess(const string &in, const string &dflt)
|
||||
{
|
||||
const char *hypo;
|
||||
int i, miss;
|
||||
const char *text = in.c_str();
|
||||
bool cr = false;
|
||||
|
||||
int size = in.length();
|
||||
if (size > ICONVCHECKSIZ)
|
||||
size = ICONVCHECKSIZ;
|
||||
|
||||
// UTF-16 with normal prefix ?
|
||||
if (size >= 2 && (!memcmp(text, "\xfe\xff", 2) ||
|
||||
!memcmp(text, "\xff\xfe", 2)))
|
||||
return "UTF-16";
|
||||
|
||||
// If we find a zero at an appropriate position, guess it's UTF-16
|
||||
// anyway. This is a quite expensive test for other texts as we'll
|
||||
// have to scan the whole thing.
|
||||
for (i = 0; i < size - 1; i += 2) {
|
||||
if (text[i] == 0 && text[i + 1] != 0)
|
||||
return "UTF-16BE";
|
||||
if (text[i + 1] == 0 && text[i] != 0)
|
||||
return "UTF-16LE";
|
||||
}
|
||||
|
||||
// Look for iso-2022 (rfc1468) specific escape sequences. As
|
||||
// iso-2022 begins in ascii, and typically soon escapes, these
|
||||
// succeed fast for a japanese text, but are quite expensive for
|
||||
// any other
|
||||
for (i = 0; i < size - 3; i++) {
|
||||
if (text[i] == 0x1b) {
|
||||
i++;
|
||||
if (text[i] == '(' && strchr("BJHI", text[i + 1]))
|
||||
return "ISO-2022-JP";
|
||||
if (text[i] == '$' && strchr("@B(", text[i + 1]))
|
||||
return "ISO-2022-JP";
|
||||
}
|
||||
}
|
||||
|
||||
// Try conversions from ascii and utf-8. These are unlikely to succeed
|
||||
// by mistake.
|
||||
if (transcodeErrCnt(text, size, "US-ASCII", "UTF-16BE") < 1)
|
||||
return "US-ASCII";
|
||||
|
||||
if (transcodeErrCnt(text, size, "UTF-8", "UTF-16BE") < 1)
|
||||
return "UTF-8";
|
||||
|
||||
hypo = 0;
|
||||
for (i = 0; i < size; i++) {
|
||||
if (text[i] == 0xd) {
|
||||
cr = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (cr) {
|
||||
if ((miss = transcodeErrCnt(text, size, "Shift_JIS", "EUC-JP")) < 1)
|
||||
return "Shift_JIS";
|
||||
if (!hypo && miss / (double)size <= ICONVALLWRAT)
|
||||
hypo = "Shift_JIS";
|
||||
if ((miss = transcodeErrCnt(text, size, "EUC-JP", "UTF-16BE")) < 1)
|
||||
return "EUC-JP";
|
||||
if (!hypo && miss / (double)size <= ICONVALLWRAT)
|
||||
hypo = "EUC-JP";
|
||||
} else {
|
||||
if ((miss = transcodeErrCnt(text, size, "EUC-JP", "UTF-16BE")) < 1)
|
||||
return "EUC-JP";
|
||||
if (!hypo && miss / (double)size <= ICONVALLWRAT)
|
||||
hypo = "EUC-JP";
|
||||
if ((miss = transcodeErrCnt(text, size, "Shift_JIS", "EUC-JP")) < 1)
|
||||
return "Shift_JIS";
|
||||
if (!hypo && miss / (double)size <= ICONVALLWRAT)
|
||||
hypo = "Shift_JIS";
|
||||
}
|
||||
if ((miss = transcodeErrCnt(text, size, "UTF-8", "UTF-16BE")) < 1)
|
||||
return "UTF-8";
|
||||
if (!hypo && miss / (double)size <= ICONVALLWRAT)
|
||||
hypo = "UTF-8";
|
||||
if ((miss = transcodeErrCnt(text, size, "CP932", "UTF-16BE")) < 1)
|
||||
return "CP932";
|
||||
if (!hypo && miss / (double)size <= ICONVALLWRAT)
|
||||
hypo = "CP932";
|
||||
|
||||
return hypo ? hypo : dflt;
|
||||
}
|
||||
|
||||
#else
|
||||
|
||||
#include <errno.h>
|
||||
|
||||
#include <cstdlib>
|
||||
#include <string>
|
||||
#include <iostream>
|
||||
|
||||
using namespace std;
|
||||
|
||||
#include "readfile.h"
|
||||
#include "csguess.h"
|
||||
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
if (argc != 2) {
|
||||
cerr << "Usage: trcsguess <filename> <default>" << endl;
|
||||
exit(1);
|
||||
}
|
||||
const string filename = argv[1];
|
||||
const string dflt = argv[2];
|
||||
string text;
|
||||
if (!file_to_string(filename, text)) {
|
||||
cerr << "Couldnt read file, errno " << errno << endl;
|
||||
exit(1);
|
||||
}
|
||||
cout << csguess(text, dflt) << endl;
|
||||
exit(0);
|
||||
}
|
||||
#endif
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
/* Copyright (C) 2004 J.F.Dockes
|
||||
* This program is free software; you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation; either version 2 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License
|
||||
* along with this program; if not, write to the
|
||||
* Free Software Foundation, Inc.,
|
||||
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
*/
|
||||
#ifndef _CSGUESS_H_INCLUDED_
|
||||
#define _CSGUESS_H_INCLUDED_
|
||||
|
||||
#include <string>
|
||||
|
||||
|
||||
// Try to guess the character set. This might guess unicode encodings, and
|
||||
// some asian charsets, but has no chance, for example, of discriminating
|
||||
// betweeen the different iso8859-xx charsets.
|
||||
extern std::string csguess(const std::string &in, const std::string &dflt);
|
||||
|
||||
#endif /* _CSGUESS_H_INCLUDED_ */
|
||||
|
|
@ -39,7 +39,6 @@
|
|||
#include "readfile.h"
|
||||
#include "indexer.h"
|
||||
#include "fsindexer.h"
|
||||
#include "csguess.h"
|
||||
#include "transcode.h"
|
||||
#include "debuglog.h"
|
||||
#include "internfile.h"
|
||||
|
|
|
|||
|
|
@ -18,7 +18,6 @@
|
|||
#include "cstr.h"
|
||||
#include "mimehandler.h"
|
||||
#include "debuglog.h"
|
||||
#include "csguess.h"
|
||||
#include "readfile.h"
|
||||
#include "transcode.h"
|
||||
#include "mimeparse.h"
|
||||
|
|
|
|||
|
|
@ -29,7 +29,6 @@ using namespace std;
|
|||
|
||||
#include "cstr.h"
|
||||
#include "mh_text.h"
|
||||
#include "csguess.h"
|
||||
#include "debuglog.h"
|
||||
#include "readfile.h"
|
||||
#include "md5.h"
|
||||
|
|
|
|||
|
|
@ -6,15 +6,15 @@ LIBS = librcl.a
|
|||
|
||||
all: $(LIBS)
|
||||
|
||||
OBJS = rclaspell.o beaglequeuecache.o cstr.o rclconfig.o rclinit.o textsplit.o unacpp.o beaglequeue.o csguess.o fsindexer.o indexer.o mimetype.o subtreelist.o htmlparse.o myhtmlparse.o mimehandler.o internfile.o mh_exec.o mh_execm.o mh_html.o mh_mail.o mh_mbox.o mh_text.o txtdcode.o docseq.o docseqdb.o docseqhist.o filtseq.o dynconf.o plaintorich.o recollq.o reslistpager.o sortseq.o wasastringtoquery.o wasatorcl.o rcldb.o rcldoc.o rclquery.o searchdata.o stemdb.o stoplist.o base64.o circache.o closefrom.o conftree.o copyfile.o debuglog.o ecrontab.o execmd.o fstreewalk.o idfile.o fileudi.o md5.o mimeparse.o netcon.o pathut.o pxattr.o rclionice.o readfile.o smallut.o transcode.o wipedir.o x11mon.o mime-getpart.o mime-parsefull.o mime-parseonlyheader.o mime-printbody.o mime-printdoc.o mime-printheader.o mime.o convert.o iodevice.o iofactory.o
|
||||
DEPS = rclaspell.dep.stamp beaglequeuecache.dep.stamp cstr.dep.stamp rclconfig.dep.stamp rclinit.dep.stamp textsplit.dep.stamp unacpp.dep.stamp beaglequeue.dep.stamp csguess.dep.stamp fsindexer.dep.stamp indexer.dep.stamp mimetype.dep.stamp subtreelist.dep.stamp htmlparse.dep.stamp myhtmlparse.dep.stamp mimehandler.dep.stamp internfile.dep.stamp mh_exec.dep.stamp mh_execm.dep.stamp mh_html.dep.stamp mh_mail.dep.stamp mh_mbox.dep.stamp mh_text.dep.stamp txtdcode.dep.stamp docseq.dep.stamp docseqdb.dep.stamp docseqhist.dep.stamp filtseq.dep.stamp dynconf.dep.stamp plaintorich.dep.stamp recollq.dep.stamp reslistpager.dep.stamp sortseq.dep.stamp wasastringtoquery.dep.stamp wasatorcl.dep.stamp rcldb.dep.stamp rcldoc.dep.stamp rclquery.dep.stamp searchdata.dep.stamp stemdb.dep.stamp stoplist.dep.stamp base64.dep.stamp circache.dep.stamp closefrom.dep.stamp conftree.dep.stamp copyfile.dep.stamp debuglog.dep.stamp ecrontab.dep.stamp execmd.dep.stamp fstreewalk.dep.stamp idfile.dep.stamp fileudi.dep.stamp md5.dep.stamp mimeparse.dep.stamp netcon.dep.stamp pathut.dep.stamp pxattr.dep.stamp rclionice.dep.stamp readfile.dep.stamp smallut.dep.stamp transcode.dep.stamp wipedir.dep.stamp x11mon.dep.stamp mime-getpart.dep.stamp mime-parsefull.dep.stamp mime-parseonlyheader.dep.stamp mime-printbody.dep.stamp mime-printdoc.dep.stamp mime-printheader.dep.stamp mime.dep.stamp convert.dep.stamp iodevice.dep.stamp iofactory.dep.stamp
|
||||
OBJS = rclaspell.o beaglequeuecache.o cstr.o rclconfig.o rclinit.o textsplit.o unacpp.o beaglequeue.o fsindexer.o indexer.o mimetype.o subtreelist.o htmlparse.o myhtmlparse.o mimehandler.o internfile.o mh_exec.o mh_execm.o mh_html.o mh_mail.o mh_mbox.o mh_text.o txtdcode.o docseq.o docseqdb.o docseqhist.o filtseq.o dynconf.o plaintorich.o recollq.o reslistpager.o sortseq.o wasastringtoquery.o wasatorcl.o rcldb.o rcldoc.o rclquery.o searchdata.o stemdb.o stoplist.o base64.o circache.o closefrom.o conftree.o copyfile.o debuglog.o ecrontab.o execmd.o fstreewalk.o idfile.o fileudi.o md5.o mimeparse.o netcon.o pathut.o pxattr.o rclionice.o readfile.o smallut.o transcode.o wipedir.o x11mon.o mime-getpart.o mime-parsefull.o mime-parseonlyheader.o mime-printbody.o mime-printdoc.o mime-printheader.o mime.o convert.o iodevice.o iofactory.o
|
||||
DEPS = rclaspell.dep.stamp beaglequeuecache.dep.stamp cstr.dep.stamp rclconfig.dep.stamp rclinit.dep.stamp textsplit.dep.stamp unacpp.dep.stamp beaglequeue.dep.stamp fsindexer.dep.stamp indexer.dep.stamp mimetype.dep.stamp subtreelist.dep.stamp htmlparse.dep.stamp myhtmlparse.dep.stamp mimehandler.dep.stamp internfile.dep.stamp mh_exec.dep.stamp mh_execm.dep.stamp mh_html.dep.stamp mh_mail.dep.stamp mh_mbox.dep.stamp mh_text.dep.stamp txtdcode.dep.stamp docseq.dep.stamp docseqdb.dep.stamp docseqhist.dep.stamp filtseq.dep.stamp dynconf.dep.stamp plaintorich.dep.stamp recollq.dep.stamp reslistpager.dep.stamp sortseq.dep.stamp wasastringtoquery.dep.stamp wasatorcl.dep.stamp rcldb.dep.stamp rcldoc.dep.stamp rclquery.dep.stamp searchdata.dep.stamp stemdb.dep.stamp stoplist.dep.stamp base64.dep.stamp circache.dep.stamp closefrom.dep.stamp conftree.dep.stamp copyfile.dep.stamp debuglog.dep.stamp ecrontab.dep.stamp execmd.dep.stamp fstreewalk.dep.stamp idfile.dep.stamp fileudi.dep.stamp md5.dep.stamp mimeparse.dep.stamp netcon.dep.stamp pathut.dep.stamp pxattr.dep.stamp rclionice.dep.stamp readfile.dep.stamp smallut.dep.stamp transcode.dep.stamp wipedir.dep.stamp x11mon.dep.stamp mime-getpart.dep.stamp mime-parsefull.dep.stamp mime-parseonlyheader.dep.stamp mime-printbody.dep.stamp mime-printdoc.dep.stamp mime-printheader.dep.stamp mime.dep.stamp convert.dep.stamp iodevice.dep.stamp iofactory.dep.stamp
|
||||
|
||||
librcl.a : $(DEPS) $(OBJS) unac.o
|
||||
ar ru librcl.a $(OBJS) unac.o
|
||||
$(RANLIB) librcl.a
|
||||
|
||||
unac.o : $(depth)/unac/unac.c $(depth)/unac/unac.h $(depth)/mk/localdefs
|
||||
$(CC) $(ALL_CXXFLAGS) -c $(depth)/unac/unac.c
|
||||
$(CXX) $(ALL_CXXFLAGS) -c $(depth)/unac/unac.c
|
||||
rclaspell.o : ../aspell/rclaspell.cpp $(depth)/mk/localdefs
|
||||
$(CXX) $(ALL_CXXFLAGS) -c ../aspell/rclaspell.cpp
|
||||
beaglequeuecache.o : ../common/beaglequeuecache.cpp $(depth)/mk/localdefs
|
||||
|
|
@ -31,8 +31,6 @@ unacpp.o : ../common/unacpp.cpp $(depth)/mk/localdefs
|
|||
$(CXX) $(ALL_CXXFLAGS) -c ../common/unacpp.cpp
|
||||
beaglequeue.o : ../index/beaglequeue.cpp $(depth)/mk/localdefs
|
||||
$(CXX) $(ALL_CXXFLAGS) -c ../index/beaglequeue.cpp
|
||||
csguess.o : ../index/csguess.cpp $(depth)/mk/localdefs
|
||||
$(CXX) $(ALL_CXXFLAGS) -c ../index/csguess.cpp
|
||||
fsindexer.o : ../index/fsindexer.cpp $(depth)/mk/localdefs
|
||||
$(CXX) $(ALL_CXXFLAGS) -c ../index/fsindexer.cpp
|
||||
indexer.o : ../index/indexer.cpp $(depth)/mk/localdefs
|
||||
|
|
@ -191,9 +189,6 @@ unacpp.dep.stamp : ../common/unacpp.cpp $(depth)/mk/localdefs
|
|||
beaglequeue.dep.stamp : ../index/beaglequeue.cpp $(depth)/mk/localdefs
|
||||
$(CXX) -M $(ALL_CXXFLAGS) ../index/beaglequeue.cpp > beaglequeue.dep
|
||||
touch beaglequeue.dep.stamp
|
||||
csguess.dep.stamp : ../index/csguess.cpp $(depth)/mk/localdefs
|
||||
$(CXX) -M $(ALL_CXXFLAGS) ../index/csguess.cpp > csguess.dep
|
||||
touch csguess.dep.stamp
|
||||
fsindexer.dep.stamp : ../index/fsindexer.cpp $(depth)/mk/localdefs
|
||||
$(CXX) -M $(ALL_CXXFLAGS) ../index/fsindexer.cpp > fsindexer.dep
|
||||
touch fsindexer.dep.stamp
|
||||
|
|
@ -364,7 +359,6 @@ include rclinit.dep
|
|||
include textsplit.dep
|
||||
include unacpp.dep
|
||||
include beaglequeue.dep
|
||||
include csguess.dep
|
||||
include fsindexer.dep
|
||||
include indexer.dep
|
||||
include mimetype.dep
|
||||
|
|
|
|||
|
|
@ -12,7 +12,6 @@ ${depth}/common/rclinit.cpp \
|
|||
${depth}/common/textsplit.cpp \
|
||||
${depth}/common/unacpp.cpp \
|
||||
${depth}/index/beaglequeue.cpp \
|
||||
${depth}/index/csguess.cpp \
|
||||
${depth}/index/fsindexer.cpp \
|
||||
${depth}/index/indexer.cpp \
|
||||
${depth}/index/mimetype.cpp \
|
||||
|
|
@ -122,7 +121,7 @@ librcl.a : \$(DEPS) \$(OBJS) unac.o
|
|||
\$(RANLIB) librcl.a
|
||||
|
||||
unac.o : \$(depth)/unac/unac.c \$(depth)/unac/unac.h $defs
|
||||
\$(CC) \$(ALL_CXXFLAGS) -c \$(depth)/unac/unac.c
|
||||
\$(CXX) \$(ALL_CXXFLAGS) -c \$(depth)/unac/unac.c
|
||||
EOF
|
||||
|
||||
for c in $SRC_CPP;do
|
||||
|
|
|
|||
|
|
@ -142,6 +142,7 @@ filters/rclabw
|
|||
filters/rclaptosidman
|
||||
filters/rclaudio
|
||||
filters/rclchm
|
||||
filters/rcldia
|
||||
filters/rcldjvu
|
||||
filters/rcldoc
|
||||
filters/rcldvi
|
||||
|
|
@ -185,8 +186,6 @@ index/
|
|||
index/Makefile
|
||||
index/beaglequeue.cpp
|
||||
index/beaglequeue.h
|
||||
index/csguess.cpp
|
||||
index/csguess.h
|
||||
index/fsindexer.cpp
|
||||
index/fsindexer.h
|
||||
index/indexer.cpp
|
||||
|
|
|
|||
|
|
@ -3,14 +3,21 @@ import os
|
|||
import sys
|
||||
|
||||
sysname = os.uname()[0]
|
||||
if sysname == 'Linux':
|
||||
libs = ['rcl', 'xapian']
|
||||
else:
|
||||
libs = ['rcl', 'xapian', 'iconv']
|
||||
|
||||
|
||||
top = os.path.join('..', '..')
|
||||
|
||||
libiconv = "@LIBICONV@"
|
||||
|
||||
if libiconv.find("-liconv") != -1:
|
||||
libs = ['rcl', 'xapian', 'iconv']
|
||||
else:
|
||||
libs = ['rcl', 'xapian']
|
||||
|
||||
libxapiandir="@LIBXAPIANDIR@"
|
||||
if libxapiandir != "":
|
||||
libdirs = [os.path.join(top, 'lib'), libxapiandir, '/usr/local/lib']
|
||||
else:
|
||||
libdirs = [os.path.join(top, 'lib'), '/usr/local/lib']
|
||||
|
||||
# Verify that the Recoll library was compiled with the PIC options
|
||||
localdefs = os.path.join(top, 'mk', 'localdefs')
|
||||
try:
|
||||
|
|
@ -42,7 +49,7 @@ module1 = Extension('recoll',
|
|||
os.path.join(top, 'unac')
|
||||
],
|
||||
libraries = libs,
|
||||
library_dirs = [os.path.join(top, 'lib'), '/usr/local/lib'],
|
||||
library_dirs = libdirs,
|
||||
sources = ['pyrecoll.cpp',
|
||||
])
|
||||
|
||||
|
|
|
|||
|
|
@ -176,7 +176,7 @@
|
|||
</message>
|
||||
<message>
|
||||
<source>Filter sizes</source>
|
||||
<translation>Tamaños de filtros</translation>
|
||||
<translation>Filtro de tamaños</translation>
|
||||
</message>
|
||||
</context>
|
||||
<context>
|
||||
|
|
|
|||
|
|
@ -88,12 +88,6 @@ unix {
|
|||
|
||||
UNAME = $$system(uname -s)
|
||||
contains( UNAME, [lL]inux ) {
|
||||
LIBS -= -liconv
|
||||
LIBS += -ldl -lX11
|
||||
}
|
||||
|
||||
contains( UNAME, GNU/kFreeBSD ) {
|
||||
LIBS -= -liconv
|
||||
LIBS += -ldl -lX11
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -231,9 +231,16 @@ string QtGuiResListPager::iconUrl(RclConfig *config, Rcl::Doc& doc)
|
|||
ConfIndexer::docsToPaths(docs, paths);
|
||||
if (!paths.empty()) {
|
||||
string path;
|
||||
LOGDEB2(("ResList::iconUrl: source path [%s]\n", paths[0].c_str()));
|
||||
if (thumbPathForUrl(cstr_fileu + paths[0], 128, path)) {
|
||||
LOGDEB2(("ResList::iconUrl: icon path [%s]\n", path.c_str()));
|
||||
return cstr_fileu + path;
|
||||
} else {
|
||||
LOGDEB2(("ResList::iconUrl: no icon: path [%s]\n",
|
||||
path.c_str()));
|
||||
}
|
||||
} else {
|
||||
LOGDEB(("ResList::iconUrl: docsToPaths failed\n"));
|
||||
}
|
||||
}
|
||||
return ResListPager::iconUrl(config, doc);
|
||||
|
|
|
|||
|
|
@ -71,6 +71,7 @@ application/vnd.wordperfect = exec wpd2html;mimetype=text/html
|
|||
application/x-abiword = exec rclabw
|
||||
application/x-awk = internal text/plain
|
||||
application/x-chm = execm rclchm
|
||||
application/x-dia-diagram = execm rcldia;mimetype=text/html;charset=utf-8
|
||||
application/x-dvi = exec rcldvi
|
||||
application/x-flac = execm rclaudio
|
||||
application/x-gnuinfo = execm rclinfo
|
||||
|
|
@ -107,6 +108,7 @@ text/x-fictionbook = exec rclfb2
|
|||
text/x-gaim-log = exec rclgaim
|
||||
text/x-html-sidux-man = exec rclsiduxman
|
||||
text/x-html-aptosid-man = exec rclaptosidman
|
||||
text/x-chm-html = internal text/html
|
||||
text/x-ini = internal text/plain
|
||||
text/x-mail = internal
|
||||
text/x-man = exec rclman
|
||||
|
|
@ -153,6 +155,7 @@ application/vnd.sun.xml.writer.global = wordprocessing
|
|||
application/vnd.sun.xml.writer.template = wordprocessing
|
||||
application/vnd.wordperfect = wordprocessing
|
||||
application/x-abiword = wordprocessing
|
||||
application/x-dia-diagram = drawing
|
||||
application/x-dvi = document
|
||||
application/x-flac = sownd
|
||||
application/x-fsdirectory = folder
|
||||
|
|
@ -283,6 +286,7 @@ message = message/rfc822 \
|
|||
other = application/vnd.sun.xml.draw \
|
||||
application/vnd.sun.xml.draw.template \
|
||||
application/vnd.sun.xml.math \
|
||||
application/x-dia-diagram \
|
||||
application/x-fsdirectory \
|
||||
application/x-mimehtml \
|
||||
application/x-rar \
|
||||
|
|
|
|||
|
|
@ -41,6 +41,7 @@
|
|||
|
||||
.djvu = image/vnd.djvu
|
||||
.svg = image/svg+xml
|
||||
.dia = application/x-dia-diagram
|
||||
|
||||
.gz = application/x-gzip
|
||||
.Z = application/x-gzip
|
||||
|
|
|
|||
|
|
@ -52,6 +52,7 @@ application/vnd.sun.xml.writer.template = libreoffice %f
|
|||
application/vnd.wordperfect = libreoffice %f
|
||||
|
||||
application/x-chm = kchmviewer %f
|
||||
application/x-dia-diagram = dia %f
|
||||
application/x-fsdirectory = dolphin %f
|
||||
application/x-gnuinfo = xterm -e "info -f %f"
|
||||
application/x-gnumeric = gnumeric %f
|
||||
|
|
@ -82,6 +83,7 @@ text/x-c+ = emacsclient %f
|
|||
text/x-c++ = emacsclient %f
|
||||
text/x-html-sidux-man = konqueror %f
|
||||
text/x-html-aptosid-man = iceweasel %f
|
||||
text/x-chm-html = openchm %f %i
|
||||
text/x-ini = emacsclient %f
|
||||
text/x-man = xterm -u8 -e "groff -T ascii -man %f | more"
|
||||
text/x-python = idle %f
|
||||
|
|
|
|||
|
|
@ -65,6 +65,17 @@ indexstemminglanguages = english
|
|||
# match your LANG and is not 8859-1, set it here.
|
||||
# defaultcharset = iso-8859-1
|
||||
|
||||
# A list of characters, encoded in UTF-8, which should be handled specially
|
||||
# when converting text to unaccented lowercase. For example, in Swedish,
|
||||
# the letter a with diaeresis has full alphabet citizenship and should not
|
||||
# be turned into an a.
|
||||
# Each element in the space-separated list has the special character as
|
||||
# first element and the translation following. The handling of both the
|
||||
# lowercase and upper-case versions of a character should be specified, as
|
||||
# appartenance to the list will turn-off both standard accent and case
|
||||
# processing. Example for Swedish:
|
||||
# unac_except_trans = åå Åå ää Ää öö Öö
|
||||
|
||||
# Where to store the database (directory). This may be an absolute path,
|
||||
# else it is taken as relative to the configuration directory (-c argument
|
||||
# or $RECOLL_CONFDIR).
|
||||
|
|
|
|||
129
src/unac/unac.c
129
src/unac/unac.c
|
|
@ -17,15 +17,57 @@
|
|||
*/
|
||||
|
||||
#ifdef HAVE_CONFIG_H
|
||||
#ifdef RECOLL_DATADIR
|
||||
#include "autoconfig.h"
|
||||
#else
|
||||
#include "config.h"
|
||||
#endif /* RECOLL */
|
||||
#endif /* HAVE_CONFIG_H */
|
||||
|
||||
#ifdef RECOLL_DATADIR
|
||||
/* Yes, recoll unac is actually c++, lets face modernity, I will not be
|
||||
caught writing another binary search */
|
||||
#include <vector>
|
||||
#include <map>
|
||||
#include <string>
|
||||
#include <algorithm>
|
||||
using std::string;
|
||||
using std::vector;
|
||||
using std::map;
|
||||
#include "smallut.h"
|
||||
|
||||
/*
|
||||
Storage for the exception translations. These are chars which
|
||||
should not be translated according to what UnicodeData says, but
|
||||
instead according to some local rule. There will usually be very
|
||||
few of them, but they must be looked up for every translated char.
|
||||
|
||||
We use a sorted vector for fastest elimination by binary search and
|
||||
a vector<string> to store the translations
|
||||
*/
|
||||
static vector<unsigned short> except_chars;
|
||||
static vector<string> except_trans;
|
||||
static inline size_t is_except_char(unsigned short c)
|
||||
{
|
||||
vector<unsigned short>::iterator it =
|
||||
std::lower_bound(except_chars.begin(), except_chars.end(), c);
|
||||
if (it == except_chars.end() || *it != c) {
|
||||
return (size_t(-1));
|
||||
}
|
||||
return std::distance(except_chars.begin(), it);
|
||||
}
|
||||
#endif /* RECOLL_DATADIR */
|
||||
|
||||
/*
|
||||
* If configure.in has not defined this symbol, assume const. It
|
||||
* does not harm much: a warning will be issued during compilation.
|
||||
*/
|
||||
#ifndef ICONV_CONST
|
||||
#ifdef RCL_ICONV_INBUF_CONST
|
||||
#define ICONV_CONST const
|
||||
#else
|
||||
#define ICONV_CONST
|
||||
#endif
|
||||
#endif /* ICONV_CONST */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
|
@ -12622,12 +12664,12 @@ int unacmaybefold_string_utf16(const char* in, size_t in_length,
|
|||
char* out;
|
||||
int out_size;
|
||||
int out_length;
|
||||
int i;
|
||||
unsigned int i;
|
||||
|
||||
out_size = in_length > 0 ? in_length : 1024;
|
||||
|
||||
out = *outp;
|
||||
out = realloc(out, out_size + 1);
|
||||
out = (char*)realloc(out, out_size + 1);
|
||||
if(out == 0) {
|
||||
if(debug_level >= UNAC_DEBUG_LOW)
|
||||
DEBUG("realloc %d bytes failed\n", out_size+1);
|
||||
|
|
@ -12646,11 +12688,25 @@ int unacmaybefold_string_utf16(const char* in, size_t in_length,
|
|||
/*
|
||||
* Lookup the tables for decomposition information
|
||||
*/
|
||||
#ifdef RECOLL_DATADIR
|
||||
size_t idx;
|
||||
if (except_chars.size() != 0 && (idx=is_except_char(c)) != (size_t)-1) {
|
||||
p = (unsigned short *)(except_trans[idx].c_str() + 2);
|
||||
l = (except_trans[idx].size() - 2) / 2;
|
||||
/* unsigned char *cp = (unsigned char *)p;
|
||||
fprintf(stderr, "l %d cp[0] %x cp[1] %x\n", l, (unsigned int)cp[0],
|
||||
(unsigned int)cp[1]);*/
|
||||
} else {
|
||||
#endif /* RECOLL_DATADIR */
|
||||
if (dofold) {
|
||||
unacfold_char_utf16(c, p, l);
|
||||
} else {
|
||||
unac_char_utf16(c, p, l);
|
||||
}
|
||||
#ifdef RECOLL_DATADIR
|
||||
}
|
||||
#endif /* RECOLL_DATADIR */
|
||||
|
||||
/*
|
||||
* Explain what's done in great detail
|
||||
*/
|
||||
|
|
@ -12678,7 +12734,7 @@ int unacmaybefold_string_utf16(const char* in, size_t in_length,
|
|||
char *saved;
|
||||
out_size += ((l + 1) * 2) + 1024;
|
||||
saved = out;
|
||||
out = realloc(out, out_size);
|
||||
out = (char *)realloc(out, out_size);
|
||||
if(out == 0) {
|
||||
if(debug_level >= UNAC_DEBUG_LOW)
|
||||
DEBUG("realloc %d bytes failed\n", out_size);
|
||||
|
|
@ -12798,7 +12854,7 @@ static int convert(const char* from, const char* to,
|
|||
out_size = in_length > 0 ? in_length : 1024;
|
||||
|
||||
out = *outp;
|
||||
out = realloc(out, out_size + 1);
|
||||
out = (char *)realloc(out, out_size + 1);
|
||||
if(out == 0) {
|
||||
/* *outp still valid, no freeing */
|
||||
if(debug_level >= UNAC_DEBUG_LOW)
|
||||
|
|
@ -12884,7 +12940,7 @@ static int convert(const char* from, const char* to,
|
|||
{
|
||||
char *saved = out_base;
|
||||
/* +1 for null */
|
||||
out_base = realloc(out_base, out_size + 1);
|
||||
out_base = (char *)realloc(out_base, out_size + 1);
|
||||
if (out_base == 0) {
|
||||
/* *outp potentially not valid any more. Free here,
|
||||
* and zero out */
|
||||
|
|
@ -12929,7 +12985,7 @@ int unacmaybefold_string(const char* charset,
|
|||
*/
|
||||
if (in_length <= 0) {
|
||||
if(!*outp) {
|
||||
if ((*outp = malloc(32)) == 0)
|
||||
if ((*outp = (char*)malloc(32)) == 0)
|
||||
return -1;
|
||||
}
|
||||
(*outp)[0] = '\0';
|
||||
|
|
@ -12975,3 +13031,64 @@ const char* unac_version(void)
|
|||
return UNAC_VERSION;
|
||||
}
|
||||
|
||||
#ifdef RECOLL_DATADIR
|
||||
void unac_set_except_translations(const char *spectrans)
|
||||
{
|
||||
except_chars.clear();
|
||||
except_trans.clear();
|
||||
if (!spectrans || !spectrans[0])
|
||||
return;
|
||||
|
||||
// The translation tables out of Unicode are in machine byte order (we
|
||||
// just let the compiler read the values).
|
||||
// For the translation part, we need to choose our encoding in accordance )
|
||||
// (16BE or 16LE depending on processor)
|
||||
// On the contrary, the source char is always to be compared to
|
||||
// the input text, which is encoded in UTF-16BE ... What a mess.
|
||||
static const char *machinecoding = 0;
|
||||
bool littleendian = true;
|
||||
if (machinecoding == 0) {
|
||||
const char* charshort = "\001\002";
|
||||
short *ip = (short *)charshort;
|
||||
if (*ip == 0x0102) {
|
||||
littleendian = false;
|
||||
machinecoding = "UTF-16BE";
|
||||
} else {
|
||||
littleendian = true;
|
||||
machinecoding = "UTF-16LE";
|
||||
}
|
||||
}
|
||||
|
||||
vector<string> vtrans;
|
||||
stringToStrings(spectrans, vtrans);
|
||||
|
||||
for (vector<string>::iterator it = vtrans.begin();
|
||||
it != vtrans.end(); it++) {
|
||||
|
||||
/* Convert the whole thing to utf-16be/le according to endianness */
|
||||
char *out = 0;
|
||||
size_t outsize;
|
||||
if (convert("UTF-8", machinecoding,
|
||||
it->c_str(), it->size(),
|
||||
&out, &outsize) != 0 || outsize < 2)
|
||||
continue;
|
||||
|
||||
/* The source char must be utf-16be as this is what we convert the
|
||||
input text to for internal processing */
|
||||
unsigned short ch;
|
||||
if (littleendian)
|
||||
ch = (out[1] << 8) | (out[0] & 0xff);
|
||||
else
|
||||
ch = (out[0] << 8) | (out[1] & 0xff);
|
||||
|
||||
/* fprintf(stderr, "outsize %d Ch is 0x%hx\n", int(outsize), ch);*/
|
||||
except_chars.push_back(ch);
|
||||
// We keep ch as the first 2 bytes in the translation so that
|
||||
// both vectors sort identically
|
||||
except_trans.push_back(string((const char *)out, outsize));
|
||||
free(out);
|
||||
}
|
||||
std::sort(except_chars.begin(), except_chars.end());
|
||||
std::sort(except_trans.begin(), except_trans.end());
|
||||
}
|
||||
#endif /* RECOLL_DATADIR */
|
||||
|
|
|
|||
|
|
@ -116,6 +116,22 @@ int unacfold_string(const char* charset,
|
|||
/* To be called before starting threads in mt programs */
|
||||
void unac_init_mt();
|
||||
|
||||
#ifdef RECOLL_DATADIR
|
||||
#include <string>
|
||||
/**
|
||||
* Set exceptions for unaccenting, for characters which should not be
|
||||
* handled according to what the Unicode tables say. For example "a
|
||||
* with circle above" should not be stripped to a in swedish, etc.
|
||||
*
|
||||
* @param spectrans defines the translations as a blank separated list of
|
||||
* UTF-8 strings. Inside each string, the first character is the exception
|
||||
* the rest is the translation (which may be empty). You can use double
|
||||
* quotes for translations which should include white space. The double-quote
|
||||
* can't be an exception character, deal with it...
|
||||
*/
|
||||
void unac_set_except_translations(const char *spectrans);
|
||||
#endif /* RECOLL_DATADIR */
|
||||
|
||||
/*
|
||||
* Return unac version number.
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -389,6 +389,52 @@ bool path_isdir(const string& path)
|
|||
return false;
|
||||
}
|
||||
|
||||
// Allowed punctuation in the path part of an URI according to RFC2396
|
||||
// -_.!~*'():@&=+$,
|
||||
/*
|
||||
21 !
|
||||
22 "
|
||||
23 #
|
||||
24 $
|
||||
25 %
|
||||
26 &
|
||||
27 '
|
||||
28 (
|
||||
29 )
|
||||
2A *
|
||||
2B +
|
||||
2C ,
|
||||
2D -
|
||||
2E .
|
||||
2F /
|
||||
30 0
|
||||
...
|
||||
39 9
|
||||
3A :
|
||||
3B ;
|
||||
3C <
|
||||
3D =
|
||||
3E >
|
||||
3F ?
|
||||
40 @
|
||||
41 A
|
||||
...
|
||||
5A Z
|
||||
5B [
|
||||
5C \
|
||||
5D ]
|
||||
5E ^
|
||||
5F _
|
||||
60 `
|
||||
61 a
|
||||
...
|
||||
7A z
|
||||
7B {
|
||||
7C |
|
||||
7D }
|
||||
7E ~
|
||||
7F DEL
|
||||
*/
|
||||
string url_encode(const string& url, string::size_type offs)
|
||||
{
|
||||
string out = url.substr(0, offs);
|
||||
|
|
@ -397,24 +443,23 @@ string url_encode(const string& url, string::size_type offs)
|
|||
int c;
|
||||
const char *h = "0123456789ABCDEF";
|
||||
c = cp[i];
|
||||
if(c <= 0x1f ||
|
||||
if (c <= 0x20 ||
|
||||
c >= 0x7f ||
|
||||
c == '<' ||
|
||||
c == '>' ||
|
||||
c == ' ' ||
|
||||
c == '\t'||
|
||||
c == '"' ||
|
||||
c == '#' ||
|
||||
c == '%' ||
|
||||
c == '{' ||
|
||||
c == '}' ||
|
||||
c == '|' ||
|
||||
c == '\\' ||
|
||||
c == '^' ||
|
||||
c == '~'||
|
||||
c == ';' ||
|
||||
c == '<' ||
|
||||
c == '>' ||
|
||||
c == '?' ||
|
||||
c == '[' ||
|
||||
c == '\\' ||
|
||||
c == ']' ||
|
||||
c == '`') {
|
||||
c == '^' ||
|
||||
c == '`' ||
|
||||
c == '{' ||
|
||||
c == '|' ||
|
||||
c == '}' ) {
|
||||
out += '%';
|
||||
out += h[(c >> 4) & 0xf];
|
||||
out += h[c & 0xf];
|
||||
|
|
@ -445,7 +490,9 @@ string url_gpath(const string& url)
|
|||
return path_canon(url.substr(colon+1));
|
||||
}
|
||||
|
||||
// Convert to file path if url is like file://
|
||||
// Convert to file path if url is like file:
|
||||
// Note: this only works with our internal pseudo-urls which are not
|
||||
// encoded/escaped
|
||||
string fileurltolocalpath(string url)
|
||||
{
|
||||
if (url.find("file://") == 0)
|
||||
|
|
@ -570,7 +617,8 @@ static const string thmbdirnormal = ".thumbnails/normal";
|
|||
static void thumbname(const string& url, string& name)
|
||||
{
|
||||
string digest;
|
||||
MD5String(url, digest);
|
||||
string l_url = url_encode(url);
|
||||
MD5String(l_url, digest);
|
||||
MD5HexPrint(digest, name);
|
||||
name += ".png";
|
||||
}
|
||||
|
|
|
|||
|
|
@ -15,6 +15,7 @@
|
|||
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
||||
*/
|
||||
#include <stdio.h>
|
||||
#include <unistd.h>
|
||||
|
||||
#include "rclionice.h"
|
||||
#include "execmd.h"
|
||||
|
|
|
|||
|
|
@ -15,6 +15,8 @@ daemSkippedPaths = \
|
|||
|
||||
defaultcharset = iso-8859-1
|
||||
|
||||
unac_except_trans = åå Åå ää Ää öö Öö
|
||||
|
||||
[/home/dockes/projets/fulltext/testrecoll/special]
|
||||
defaultcharset = iso-8859-1
|
||||
[/home/dockes/projets/fulltext/testrecoll/txt]
|
||||
|
|
|
|||
14
tests/dia/dia.sh
Executable file
14
tests/dia/dia.sh
Executable file
|
|
@ -0,0 +1,14 @@
|
|||
#!/bin/sh
|
||||
|
||||
topdir=`dirname $0`/..
|
||||
. $topdir/shared.sh
|
||||
|
||||
initvariables $0
|
||||
(
|
||||
recollq DEPARTMENT NumberOfEmployees
|
||||
recollq Within5Min WaterLevel KeptBelow
|
||||
) 2> $mystderr | egrep -v '^Recoll query: ' > $mystdout
|
||||
|
||||
diff -w ${myname}.txt $mystdout > $mydiffs 2>&1
|
||||
|
||||
checkresult
|
||||
4
tests/dia/dia.txt
Normal file
4
tests/dia/dia.txt
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
1 results
|
||||
application/x-dia-diagram [file:///home/dockes/projets/fulltext/testrecoll/dia/ER-demo.dia] [ER-demo.dia] 60803 bytes
|
||||
1 results
|
||||
application/x-dia-diagram [file:///home/dockes/projets/fulltext/testrecoll/dia/Istar.dia] [Istar.dia] 3537 bytes
|
||||
|
|
@ -8,7 +8,9 @@ initvariables $0
|
|||
(
|
||||
recollq 'Bienvenue Dans Univers De Lyx'
|
||||
recollq 'Welcome To Lyx'
|
||||
recollq 'Udvozli Ont A LyX'
|
||||
recollq 'LyX rendkivul jol dokumentalt'
|
||||
# cant use this one because o-diaeresis is in the swedish unacex
|
||||
# recollq 'Udvozli Ont A LyX'
|
||||
) 2> $mystderr | egrep -v '^Recoll query: ' > $mystdout
|
||||
|
||||
diff -w ${myname}.txt $mystdout > $mydiffs 2>&1
|
||||
|
|
|
|||
20
tests/unacex/unacex.sh
Executable file
20
tests/unacex/unacex.sh
Executable file
|
|
@ -0,0 +1,20 @@
|
|||
#!/bin/sh
|
||||
|
||||
topdir=`dirname $0`/..
|
||||
. $topdir/shared.sh
|
||||
|
||||
initvariables $0
|
||||
|
||||
# We need an utf-8 locale for the 1st command to properly read its argument
|
||||
export LANG=fr_FR.UTF-8
|
||||
|
||||
(
|
||||
# Should succeed
|
||||
recollq '"strippes: UNACEXååääöö"'
|
||||
# Should fail
|
||||
recollq '"strippes: UNACEXaaaaoo"'
|
||||
) 2> $mystderr | egrep -v '^Recoll query: ' > $mystdout
|
||||
|
||||
diff -w ${myname}.txt $mystdout > $mydiffs 2>&1
|
||||
|
||||
checkresult
|
||||
3
tests/unacex/unacex.txt
Normal file
3
tests/unacex/unacex.txt
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
1 results
|
||||
text/html [file:///home/dockes/projets/fulltext/testrecoll/unacex/swedishchars.html] [Some chars] 293 bytes
|
||||
0 results
|
||||
129
unac/unac.c
129
unac/unac.c
|
|
@ -17,15 +17,57 @@
|
|||
*/
|
||||
|
||||
#ifdef HAVE_CONFIG_H
|
||||
#ifdef RECOLL_DATADIR
|
||||
#include "autoconfig.h"
|
||||
#else
|
||||
#include "config.h"
|
||||
#endif /* RECOLL */
|
||||
#endif /* HAVE_CONFIG_H */
|
||||
|
||||
#ifdef RECOLL_DATADIR
|
||||
/* Yes, recoll unac is actually c++, lets face modernity, I will not be
|
||||
caught writing another binary search */
|
||||
#include <vector>
|
||||
#include <map>
|
||||
#include <string>
|
||||
#include <algorithm>
|
||||
using std::string;
|
||||
using std::vector;
|
||||
using std::map;
|
||||
#include "smallut.h"
|
||||
|
||||
/*
|
||||
Storage for the exception translations. These are chars which
|
||||
should not be translated according to what UnicodeData says, but
|
||||
instead according to some local rule. There will usually be very
|
||||
few of them, but they must be looked up for every translated char.
|
||||
|
||||
We use a sorted vector for fastest elimination by binary search and
|
||||
a vector<string> to store the translations
|
||||
*/
|
||||
static vector<unsigned short> except_chars;
|
||||
static vector<string> except_trans;
|
||||
static inline size_t is_except_char(unsigned short c)
|
||||
{
|
||||
vector<unsigned short>::iterator it =
|
||||
std::lower_bound(except_chars.begin(), except_chars.end(), c);
|
||||
if (it == except_chars.end() || *it != c) {
|
||||
return (size_t(-1));
|
||||
}
|
||||
return std::distance(except_chars.begin(), it);
|
||||
}
|
||||
#endif /* RECOLL_DATADIR */
|
||||
|
||||
/*
|
||||
* If configure.in has not defined this symbol, assume const. It
|
||||
* does not harm much: a warning will be issued during compilation.
|
||||
*/
|
||||
#ifndef ICONV_CONST
|
||||
#ifdef RCL_ICONV_INBUF_CONST
|
||||
#define ICONV_CONST const
|
||||
#else
|
||||
#define ICONV_CONST
|
||||
#endif
|
||||
#endif /* ICONV_CONST */
|
||||
|
||||
#include <stdlib.h>
|
||||
|
|
@ -12622,12 +12664,12 @@ int unacmaybefold_string_utf16(const char* in, size_t in_length,
|
|||
char* out;
|
||||
int out_size;
|
||||
int out_length;
|
||||
int i;
|
||||
unsigned int i;
|
||||
|
||||
out_size = in_length > 0 ? in_length : 1024;
|
||||
|
||||
out = *outp;
|
||||
out = realloc(out, out_size + 1);
|
||||
out = (char*)realloc(out, out_size + 1);
|
||||
if(out == 0) {
|
||||
if(debug_level >= UNAC_DEBUG_LOW)
|
||||
DEBUG("realloc %d bytes failed\n", out_size+1);
|
||||
|
|
@ -12646,11 +12688,25 @@ int unacmaybefold_string_utf16(const char* in, size_t in_length,
|
|||
/*
|
||||
* Lookup the tables for decomposition information
|
||||
*/
|
||||
#ifdef RECOLL_DATADIR
|
||||
size_t idx;
|
||||
if (except_chars.size() != 0 && (idx=is_except_char(c)) != (size_t)-1) {
|
||||
p = (unsigned short *)(except_trans[idx].c_str() + 2);
|
||||
l = (except_trans[idx].size() - 2) / 2;
|
||||
/* unsigned char *cp = (unsigned char *)p;
|
||||
fprintf(stderr, "l %d cp[0] %x cp[1] %x\n", l, (unsigned int)cp[0],
|
||||
(unsigned int)cp[1]);*/
|
||||
} else {
|
||||
#endif /* RECOLL_DATADIR */
|
||||
if (dofold) {
|
||||
unacfold_char_utf16(c, p, l);
|
||||
} else {
|
||||
unac_char_utf16(c, p, l);
|
||||
}
|
||||
#ifdef RECOLL_DATADIR
|
||||
}
|
||||
#endif /* RECOLL_DATADIR */
|
||||
|
||||
/*
|
||||
* Explain what's done in great detail
|
||||
*/
|
||||
|
|
@ -12678,7 +12734,7 @@ int unacmaybefold_string_utf16(const char* in, size_t in_length,
|
|||
char *saved;
|
||||
out_size += ((l + 1) * 2) + 1024;
|
||||
saved = out;
|
||||
out = realloc(out, out_size);
|
||||
out = (char *)realloc(out, out_size);
|
||||
if(out == 0) {
|
||||
if(debug_level >= UNAC_DEBUG_LOW)
|
||||
DEBUG("realloc %d bytes failed\n", out_size);
|
||||
|
|
@ -12798,7 +12854,7 @@ static int convert(const char* from, const char* to,
|
|||
out_size = in_length > 0 ? in_length : 1024;
|
||||
|
||||
out = *outp;
|
||||
out = realloc(out, out_size + 1);
|
||||
out = (char *)realloc(out, out_size + 1);
|
||||
if(out == 0) {
|
||||
/* *outp still valid, no freeing */
|
||||
if(debug_level >= UNAC_DEBUG_LOW)
|
||||
|
|
@ -12884,7 +12940,7 @@ static int convert(const char* from, const char* to,
|
|||
{
|
||||
char *saved = out_base;
|
||||
/* +1 for null */
|
||||
out_base = realloc(out_base, out_size + 1);
|
||||
out_base = (char *)realloc(out_base, out_size + 1);
|
||||
if (out_base == 0) {
|
||||
/* *outp potentially not valid any more. Free here,
|
||||
* and zero out */
|
||||
|
|
@ -12929,7 +12985,7 @@ int unacmaybefold_string(const char* charset,
|
|||
*/
|
||||
if (in_length <= 0) {
|
||||
if(!*outp) {
|
||||
if ((*outp = malloc(32)) == 0)
|
||||
if ((*outp = (char*)malloc(32)) == 0)
|
||||
return -1;
|
||||
}
|
||||
(*outp)[0] = '\0';
|
||||
|
|
@ -12975,3 +13031,64 @@ const char* unac_version(void)
|
|||
return UNAC_VERSION;
|
||||
}
|
||||
|
||||
#ifdef RECOLL_DATADIR
|
||||
void unac_set_except_translations(const char *spectrans)
|
||||
{
|
||||
except_chars.clear();
|
||||
except_trans.clear();
|
||||
if (!spectrans || !spectrans[0])
|
||||
return;
|
||||
|
||||
// The translation tables out of Unicode are in machine byte order (we
|
||||
// just let the compiler read the values).
|
||||
// For the translation part, we need to choose our encoding in accordance )
|
||||
// (16BE or 16LE depending on processor)
|
||||
// On the contrary, the source char is always to be compared to
|
||||
// the input text, which is encoded in UTF-16BE ... What a mess.
|
||||
static const char *machinecoding = 0;
|
||||
bool littleendian = true;
|
||||
if (machinecoding == 0) {
|
||||
const char* charshort = "\001\002";
|
||||
short *ip = (short *)charshort;
|
||||
if (*ip == 0x0102) {
|
||||
littleendian = false;
|
||||
machinecoding = "UTF-16BE";
|
||||
} else {
|
||||
littleendian = true;
|
||||
machinecoding = "UTF-16LE";
|
||||
}
|
||||
}
|
||||
|
||||
vector<string> vtrans;
|
||||
stringToStrings(spectrans, vtrans);
|
||||
|
||||
for (vector<string>::iterator it = vtrans.begin();
|
||||
it != vtrans.end(); it++) {
|
||||
|
||||
/* Convert the whole thing to utf-16be/le according to endianness */
|
||||
char *out = 0;
|
||||
size_t outsize;
|
||||
if (convert("UTF-8", machinecoding,
|
||||
it->c_str(), it->size(),
|
||||
&out, &outsize) != 0 || outsize < 2)
|
||||
continue;
|
||||
|
||||
/* The source char must be utf-16be as this is what we convert the
|
||||
input text to for internal processing */
|
||||
unsigned short ch;
|
||||
if (littleendian)
|
||||
ch = (out[1] << 8) | (out[0] & 0xff);
|
||||
else
|
||||
ch = (out[0] << 8) | (out[1] & 0xff);
|
||||
|
||||
/* fprintf(stderr, "outsize %d Ch is 0x%hx\n", int(outsize), ch);*/
|
||||
except_chars.push_back(ch);
|
||||
// We keep ch as the first 2 bytes in the translation so that
|
||||
// both vectors sort identically
|
||||
except_trans.push_back(string((const char *)out, outsize));
|
||||
free(out);
|
||||
}
|
||||
std::sort(except_chars.begin(), except_chars.end());
|
||||
std::sort(except_trans.begin(), except_trans.end());
|
||||
}
|
||||
#endif /* RECOLL_DATADIR */
|
||||
|
|
|
|||
16
unac/unac.h
16
unac/unac.h
|
|
@ -116,6 +116,22 @@ int unacfold_string(const char* charset,
|
|||
/* To be called before starting threads in mt programs */
|
||||
void unac_init_mt();
|
||||
|
||||
#ifdef RECOLL_DATADIR
|
||||
#include <string>
|
||||
/**
|
||||
* Set exceptions for unaccenting, for characters which should not be
|
||||
* handled according to what the Unicode tables say. For example "a
|
||||
* with circle above" should not be stripped to a in swedish, etc.
|
||||
*
|
||||
* @param spectrans defines the translations as a blank separated list of
|
||||
* UTF-8 strings. Inside each string, the first character is the exception
|
||||
* the rest is the translation (which may be empty). You can use double
|
||||
* quotes for translations which should include white space. The double-quote
|
||||
* can't be an exception character, deal with it...
|
||||
*/
|
||||
void unac_set_except_translations(const char *spectrans);
|
||||
#endif /* RECOLL_DATADIR */
|
||||
|
||||
/*
|
||||
* Return unac version number.
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@
|
|||
<meta name="Keywords" content=
|
||||
"full text search, desktop search, unix, linux">
|
||||
<meta http-equiv="Content-language" content="en">
|
||||
<meta http-equiv="content-type" content="text/html; charset=iso-8859-1">
|
||||
<meta http-equiv="content-type" content="text/html; charset=utf-8">
|
||||
<meta name="robots" content="All,Index,Follow">
|
||||
|
||||
<link type="text/css" rel="stylesheet" href="styles/style.css">
|
||||
|
|
@ -34,6 +34,8 @@
|
|||
|
||||
<ul>
|
||||
<li><a href="usermanual/index.html">English, HTML</a></li>
|
||||
<li><a href="http://stupidbeauty.com/Blog/2012/03/recoll%E7%94%A8%E6%88%B6%E6%89%8B%E5%86%8A%E7%BF%BB%E8%AD%AF%EF%BC%8Crecoll-user-manual-2/">
|
||||
中文，HTML</a></li>
|
||||
<li><a href="usermanual/recoll_user_manual.pdf">English, PDF</a></li>
|
||||
<li><a href="http://mcz.altervista.org/Pagine/usermanual-italian.html">
|
||||
Italian (rather old)</a></li>
|
||||
|
|
|
|||
|
|
@ -90,8 +90,8 @@
|
|||
compressed versions). Some types are handled internally (no
|
||||
external application needed). Other types need a separate
|
||||
application to be installed to extract the text. Types that
|
||||
only need very common utilities (awk/sed/groff etc.) are
|
||||
listed in the native section.</p>
|
||||
only need very common utilities (awk/sed/groff/Python etc.)
|
||||
are listed in the native section.</p>
|
||||
|
||||
<h4>File types indexed natively</h4>
|
||||
|
||||
|
|
@ -100,22 +100,25 @@
|
|||
|
||||
<li><span class="literal">html</span>.</li>
|
||||
|
||||
<li><span class="literal">maildir</span> and <span class=
|
||||
"literal">mailbox</span> (<span class=
|
||||
"literal">Mozilla</span>, <span class=
|
||||
"literal">Thunderbird</span> and <span class=
|
||||
"literal">Evolution</span> mail ok).</li>
|
||||
<li><span class="literal">maildir</span> and
|
||||
<span class="literal">mailbox</span> (
|
||||
<span class="literal">Mozilla</span>,
|
||||
<span class="literal">Thunderbird</span> and
|
||||
<span class="literal">Evolution</span>mail ok).
|
||||
</li>
|
||||
|
||||
<li><span class="literal">gaim</span> and <span class=
|
||||
"literal">purple</span> log files.</li>
|
||||
<li><span class="literal">gaim</span> and
|
||||
<span class="literal">purple</span> log files.</li>
|
||||
|
||||
<li><span class="literal">Lyx</span> files (needs <span
|
||||
class="literal">Lyx</span> to be installed).</li>
|
||||
<li><span class="literal">Lyx</span> files (needs
|
||||
<span class="literal">Lyx</span> to be installed).</li>
|
||||
|
||||
<li><span class="literal">Scribus</span> files.</li>
|
||||
|
||||
<li><span class="literal">Man pages</span> (need <span
|
||||
class="command">groff</span>).</li>
|
||||
<li><span class="literal">Man pages</span> (needs
|
||||
<span class="command">groff</span>).</li>
|
||||
|
||||
<li><span class="literal">Dia</span> diagrams.</li>
|
||||
</ul>
|
||||
|
||||
<h4>File types indexed with external helpers</h4>
|
||||
|
|
@ -124,8 +127,9 @@
|
|||
command in addition to the applications specifically listed.</p>
|
||||
|
||||
<h5>The XML ones</h5>
|
||||
<p>The following types need <span class=
|
||||
"command">xsltproc</span> from the <b>libxslt</b> package.
|
||||
|
||||
<p>The following types need <span class="command">
|
||||
xsltproc</span> from the <b>libxslt</b> package.
|
||||
Quite a few also need <span class="command">unzip</span>:</p>
|
||||
|
||||
<ul>
|
||||
|
|
@ -148,6 +152,9 @@
|
|||
|
||||
<h5>Other formats</h5>
|
||||
|
||||
<p>The following need miscellaneous helper programs to decode
|
||||
the internal formats.</p>
|
||||
|
||||
<ul>
|
||||
<li><span class="literal">pdf</span> with the <span class=
|
||||
"command">pdftotext</span> command, which can be installed
|
||||
|
|
@ -166,7 +173,8 @@
|
|||
"http://vitus.wagner.pp.ru/software/catdoc/">catdoc</a> utilities.</li>
|
||||
|
||||
<li><span class="literal">CHM (Microsoft help)</span> files
|
||||
with <span class="command">Python, <a href="http://gnochm.sourceforge.net/pychm.html">pychm</a>
|
||||
with <span class="command">Python,
|
||||
<a href="http://gnochm.sourceforge.net/pychm.html">pychm</a>
|
||||
and <a href="http://www.jedrea.com/chmlib/">chmlib</a></span>.</li>
|
||||
|
||||
<li><span class="literal">GNU info</span> files
|
||||
|
|
|
|||
|
|
@ -75,6 +75,11 @@
|
|||
should upgrade.</p>
|
||||
</blockquote>
|
||||
|
||||
<h2>DIA files</h2>
|
||||
<p><a href="rcldia">rcldia</a> is a new filter
|
||||
for <a href="http://projects.gnome.org/dia/">Dia</a> files,
|
||||
contributed by Stefan Friedel.</p>
|
||||
|
||||
<h2>CHM files</h2>
|
||||
<p><a href="rclchm">rclchm</a>. The previous version of the
|
||||
filter mishandled files which had encoded internal URLs (not
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@
|
|||
<meta name="Description" content="Recoll is a personal desktop full text search application for Unix, Linux and Mac OS X, based on the Xapian search engine library.">
|
||||
<meta name="Keywords" content="full text search,fulltext,full text,search,desktop search,unix,linux,open source,free">
|
||||
<meta http-equiv="Content-language" content="en">
|
||||
<meta http-equiv="content-type" content="text/html; charset=iso-8859-1">
|
||||
<meta http-equiv="content-type" content="text/html; charset=utf-8">
|
||||
<meta name="robots" content="All,Index,Follow">
|
||||
<link type="text/css" rel="stylesheet" href="styles/style.css">
|
||||
</head>
|
||||
|
|
@ -69,20 +69,19 @@
|
|||
<h2>News: </h2>
|
||||
<div class="news">
|
||||
<ul>
|
||||
<li>2012-03-27: The Unity Lens can now handle results for embedded
|
||||
documents, using the Recoll GUI as a proxy to extract and
|
||||
display them.</li>
|
||||
<li>2012-04-07: we now have a Chinese user manual: Recoll现在有中文手册咯：
|
||||
<a href="http://stupidbeauty.com/Blog/2012/03/recoll%E7%94%A8%E6%88%B6%E6%89%8B%E5%86%8A%E7%BF%BB%E8%AD%AF%EF%BC%8Crecoll-user-manual-2/">
|
||||
Recoll中文手册，HTML</a></li>
|
||||
|
||||
<li>2012-03-26: Recoll gets a Ubuntu Unity Lens. If you are running
|
||||
<li>2012-03-27: Recoll gets a Ubuntu Unity Lens. If you are running
|
||||
an Ubuntu release where this makes sense, you can install
|
||||
the recoll-lens package from the
|
||||
<a href="https://launchpad.net/~recoll-backports/+archive/recoll-1.15-on">
|
||||
Recoll PPA</a>. <br />
|
||||
<i><b>Please note</b></i>: for now, the Lens will only return
|
||||
results which are normal files, not embedded documents.
|
||||
Ie: no mbox messages, no attachments, no archive
|
||||
members, etc. For now, you'll have to use the full Recoll
|
||||
GUI to find these.</li>
|
||||
Recoll PPA</a>. The Lens uses the Recoll GUI as a proxy to
|
||||
extract and display embedded documents, which native utility
|
||||
can't reach directly. And of course you still need to run
|
||||
the GUI (or the command line recollindex) to get indexing
|
||||
going !</li>
|
||||
|
||||
<li>2012-03-24: Release 1.17 is out, see
|
||||
the <a href="release-1.17.html">Release notes</a>. </li>
|
||||
|
|
|
|||
2
website/pics/00REMAKEALB.sh
Normal file
2
website/pics/00REMAKEALB.sh
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
#!/bin/sh
|
||||
onlylist=1 photalb . .
|
||||
|
|
@ -1,9 +1,30 @@
|
|||
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
|
||||
|
||||
<html>
|
||||
<head>
|
||||
<title>Photos</title>
|
||||
<title>Recoll screenshots</title>
|
||||
|
||||
<meta name="generator" content="HTML Tidy, see www.w3.org">
|
||||
<meta name="Author" content="Jean-Francois Dockes">
|
||||
<meta name="Description" content=
|
||||
"recoll is a simple full-text search system for unix and linux
|
||||
based on the powerful and mature xapian engine">
|
||||
<meta name="Keywords" content=
|
||||
"full text search, desktop search, unix, linux">
|
||||
<meta http-equiv="Content-language" content="en">
|
||||
<meta http-equiv="content-type" content="text/html; charset=utf-8">
|
||||
<meta name="robots" content="All,Index,Follow">
|
||||
|
||||
<link type="text/css" rel="stylesheet" href="../styles/style.css">
|
||||
</head>
|
||||
|
||||
<body>
|
||||
|
||||
<div class="content">
|
||||
|
||||
<h1>Recoll Screenshots</h1>
|
||||
<li><a href="../index.html">Back to Recoll home</a></li>
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<td align="center"><a href="recoll0.html"><img src="recoll0-thumb.png"></a></td>
|
||||
|
|
@ -19,4 +40,5 @@
|
|||
</tr>
|
||||
<tr>
|
||||
<td align="center"><a href="recoll-HTML_search_results.html"><img src="recoll-HTML_search_results-thumb.png"></a></td>
|
||||
</tr></table></body></html>
|
||||
</tr></table>
|
||||
</body></html>
|
||||
|
|
|
|||
27
website/pics/index.html.head
Normal file
27
website/pics/index.html.head
Normal file
|
|
@ -0,0 +1,27 @@
|
|||
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
|
||||
|
||||
<html>
|
||||
<head>
|
||||
<title>Recoll screenshots</title>
|
||||
|
||||
<meta name="generator" content="HTML Tidy, see www.w3.org">
|
||||
<meta name="Author" content="Jean-Francois Dockes">
|
||||
<meta name="Description" content=
|
||||
"recoll is a simple full-text search system for unix and linux
|
||||
based on the powerful and mature xapian engine">
|
||||
<meta name="Keywords" content=
|
||||
"full text search, desktop search, unix, linux">
|
||||
<meta http-equiv="Content-language" content="en">
|
||||
<meta http-equiv="content-type" content="text/html; charset=utf-8">
|
||||
<meta name="robots" content="All,Index,Follow">
|
||||
|
||||
<link type="text/css" rel="stylesheet" href="../styles/style.css">
|
||||
</head>
|
||||
|
||||
<body>
|
||||
|
||||
<div class="content">
|
||||
|
||||
<h1>Recoll Screenshots</h1>
|
||||
<li><a href="../index.html">Back to Recoll home</a></li>
|
||||
|
||||
|
|
@ -4,9 +4,9 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="recoll_chinese.html">Prev</a> <a href="..">Up</a>
|
||||
<p><a href="recoll_chinese.html">Prev</a> <a href=".">Up</a>
|
||||
<a href="recoll0.html">Next</a>
|
||||
<a href="recoll-HTML_search_results.png">Raw Image</a></p>
|
||||
<a href="recoll-HTML_search_results.png">Image</a></p>
|
||||
<p>A customized result list, thanks to Michael Croes. The html code follows,
|
||||
it should be pasted into the
|
||||
<i>Preferences->Query Configuration->Result paragraph format string</i> entry.
|
||||
|
|
|
|||
|
|
@ -4,9 +4,9 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="..">Prev</a> <a href="..">Up</a>
|
||||
<p><a href=".">Prev</a> <a href=".">Up</a>
|
||||
<a href="result-table.html">Next</a>
|
||||
<a href="recoll0.png">Raw Image</a></p>
|
||||
<a href="recoll0.png">Image</a></p>
|
||||
<p>Search results.</p>
|
||||
<p><img height="90%" src="recoll0.png"></p>
|
||||
</body>
|
||||
|
|
|
|||
|
|
@ -4,9 +4,9 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="result-table.html">Prev</a> <a href="..">Up</a>
|
||||
<p><a href="result-table.html">Prev</a> <a href=".">Up</a>
|
||||
<a href="recoll2.html">Next</a>
|
||||
<a href="recoll1.png">Raw Image</a></p>
|
||||
<a href="recoll1.png">Image</a></p>
|
||||
<p>A result list with a preview window open.</p>
|
||||
<p><img height="90%" src="recoll1.png"></p>
|
||||
</body>
|
||||
|
|
|
|||
Binary file not shown.
|
Before Width: | Height: | Size: 45 KiB After Width: | Height: | Size: 25 KiB |
|
|
@ -4,10 +4,10 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="recoll1.html">Prev</a> <a href="..">Up</a>
|
||||
<p><a href="recoll1.html">Prev</a> <a href=".">Up</a>
|
||||
<a href="recoll3.html">Next</a>
|
||||
<a href="recoll2.png">Raw Image</a></p>
|
||||
<p>The advanced search dialog.</p>
|
||||
<a href="recoll2.png">Image</a></p>
|
||||
<p>The two tabs in the advanced search dialog.</p>
|
||||
<p><img height="90%" src="recoll2.png"></p>
|
||||
</body>
|
||||
</html>
|
||||
|
|
|
|||
Binary file not shown.
|
Before Width: | Height: | Size: 46 KiB After Width: | Height: | Size: 46 KiB |
|
|
@ -1 +1 @@
|
|||
The advanced search dialog.
|
||||
The two tabs in the advanced search dialog.
|
||||
|
|
|
|||
|
|
@ -4,9 +4,9 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="recoll2.html">Prev</a> <a href="..">Up</a>
|
||||
<p><a href="recoll2.html">Prev</a> <a href=".">Up</a>
|
||||
<a href="recoll4.html">Next</a>
|
||||
<a href="recoll3.png">Raw Image</a></p>
|
||||
<a href="recoll3.png">Image</a></p>
|
||||
<p>A result list from which the native application (firefox)
|
||||
was started by clicking the Edit link.</p>
|
||||
<p><img height="90%" src="recoll3.png"></p>
|
||||
|
|
|
|||
|
|
@ -4,9 +4,9 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="recoll3.html">Prev</a> <a href="..">Up</a>
|
||||
<p><a href="recoll3.html">Prev</a> <a href=".">Up</a>
|
||||
<a href="recoll5.html">Next</a>
|
||||
<a href="recoll4.png">Raw Image</a></p>
|
||||
<a href="recoll4.png">Image</a></p>
|
||||
<p>The document history window looks a little like a result list
|
||||
I'm afraid...</p>
|
||||
<p><img height="90%" src="recoll4.png"></p>
|
||||
|
|
|
|||
|
|
@ -4,9 +4,9 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="recoll4.html">Prev</a> <a href="..">Up</a>
|
||||
<p><a href="recoll4.html">Prev</a> <a href=".">Up</a>
|
||||
<a href="recoll_chinese.html">Next</a>
|
||||
<a href="recoll5.png">Raw Image</a></p>
|
||||
<a href="recoll5.png">Image</a></p>
|
||||
<p>The term explorer tool in phonetic mode.</p>
|
||||
<p><img height="90%" src="recoll5.png"></p>
|
||||
</body>
|
||||
|
|
|
|||
|
|
@ -4,9 +4,9 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="recoll5.html">Prev</a> <a href="..">Up</a>
|
||||
<p><a href="recoll5.html">Prev</a> <a href=".">Up</a>
|
||||
<a href="recoll-HTML_search_results.html">Next</a>
|
||||
<a href="recoll_chinese.png">Raw Image</a></p>
|
||||
<a href="recoll_chinese.png">Image</a></p>
|
||||
<p>Recoll searching Chinese text. Chinese text search is based on n-grams and
|
||||
relatively rough, but still useful (I am told).</p>
|
||||
<p><img height="90%" src="recoll_chinese.png"></p>
|
||||
|
|
|
|||
|
|
@ -4,9 +4,9 @@
|
|||
<title>Photo</title>
|
||||
</head>
|
||||
<body>
|
||||
<p><a href="recoll0.html">Prev</a> <a href="..">Up</a>
|
||||
<p><a href="recoll0.html">Prev</a> <a href=".">Up</a>
|
||||
<a href="recoll1.html">Next</a>
|
||||
<a href="result-table.png">Raw Image</a></p>
|
||||
<a href="result-table.png">Image</a></p>
|
||||
<p></p>
|
||||
<p><img height="90%" src="result-table.png"></p>
|
||||
</body>
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue