more filter cleanup: factorize code in the vanilla xslt ones, move a few more to python.

This commit is contained in:
Jean-Francois Dockes 2018-06-04 13:30:09 +02:00
parent 2a45f7fef6
commit 211ea8010c
17 changed files with 373 additions and 697 deletions

View File

@ -559,6 +559,7 @@ rclpychm:
rclpychm-install:
(cd python/pychm || exit 1; \
set -x; \
mkdir -p ${librcldir}; \
mv dist/pychm*.egg ${librcldir};\
)
rclpychm-clean:
@ -636,9 +637,10 @@ filters/rclepub \
filters/rclepub1 \
filters/rclexec1.py \
filters/rclexecm.py \
filters/rclfb2 \
filters/rclfb2.py \
filters/rclgaim \
filters/rclgnm \
filters/rclgenxslt.py \
filters/rclgnm.py \
filters/rclics \
filters/rclimg \
filters/rclimg.py \
@ -651,7 +653,7 @@ filters/rcllyx \
filters/rclman \
filters/rclmidi.py \
filters/rclpdf.py \
filters/rclokulnote \
filters/rclokulnote.py \
filters/rclopxml.py \
filters/rclppt.py \
filters/rclpurple \
@ -660,7 +662,6 @@ filters/rclrar \
filters/rclrtf.py \
filters/rclscribus \
filters/rclshowinfo \
filters/rclsiduxman \
filters/rclsoff.py \
filters/rclsoff-flat.py \
filters/rclsvg.py \

View File

@ -1,4 +1,7 @@
#!/usr/bin/python
#!/usr/bin/python2
#
# wnck does not have a python3 binding as far as I can see (or at
# least it's not packaged by, e.g. Debian. So python2 only for now.
#
# This script should be linked to a keyboard shortcut. Under gnome,
# you can do this from the main preferences menu, or directly execute

View File

@ -20,7 +20,7 @@ from __future__ import print_function
import sys
import rclexecm
import rclxslt
import rclgenxslt
stylesheet_all = '''<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
@ -112,44 +112,7 @@ stylesheet_all = '''<?xml version="1.0"?>
</xsl:stylesheet>
'''
class ABWExtractor:
def __init__(self, em):
self.em = em
self.currentindex = 0
def extractone(self, params):
if "filename:" not in params:
self.em.rclog("extractone: no mime or file name")
return (False, "", "", rclexecm.RclExecM.eofnow)
fn = params["filename:"]
try:
data = open(fn, 'rb').read()
docdata = rclxslt.apply_sheet_data(stylesheet_all, data)
except Exception as err:
self.em.rclog("%s: bad data: %s" % (fn, err))
return (False, "", "", rclexecm.RclExecM.eofnow)
return (True, docdata, "", rclexecm.RclExecM.eofnext)
###### File type handler api, used by rclexecm ---------->
def openfile(self, params):
self.currentindex = 0
return True
def getipath(self, params):
return self.extractone(params)
def getnext(self, params):
if self.currentindex >= 1:
return (False, "", "", rclexecm.RclExecM.eofnow)
else:
ret= self.extractone(params)
self.currentindex += 1
return ret
if __name__ == '__main__':
proto = rclexecm.RclExecM()
extract = ABWExtractor(proto)
extract = rclgenxslt.XSLTExtractor(proto, stylesheet_all)
rclexecm.main(proto, extract)

View File

@ -17,11 +17,11 @@
# 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
#
# Extract text from a dvi file by either executing dvitops and rclps
# or using catdvi. dvitops has given better results during tests, and is
# chosen first if available, but the dvitops/rclps combination is much
# slower than catdvi
# set variables
# Extract text from a dvi file by either executing dvitops and
# pstotext or using catdvi. dvitops has given better results during
# tests, and is chosen first if available, but the dvitops/pstotext
# combination is much slower than catdvi set variables. In any case,
# the program is not too good with special characters (e.g. ligatures)
LANG=C ; export LANG
LC_ALL=C ; export LC_ALL
progname="rcldvi"
@ -94,26 +94,25 @@ umask 77
# !! Leave the following line unmodified !
#ENDRECFILTCOMMONCODE
# Find rclps. Note: this only works because we are always executed with a
# full path
rclps=`dirname $0`/rclps
decoderdvips()
{
dvips -f $1 2> /dev/null | pstotext | iconv -f cp1252 -t utf-8 -c -s
}
decodercatdvi()
{
catdvi $1
}
decoder=""
if iscmd dvips -a iscmd pstotext ; then
decoder=dvips
decoder=decoderdvips
elif iscmd catdvi ; then
decoder=catdvi
decoder=decodercatdvi
fi
if test X$decoder = X ; then
senderror HELPERNOTFOUND dvips or catdvi
fi
if test X$decoder = Xdvips ; then
$decoder -f < "$infile" 2> /dev/null | $rclps -
exit $?
fi
# The strange 'BEGIN' setup is to prevent 'file' from thinking this file
# is an awk program
$decoder "$infile" |

View File

@ -1,139 +0,0 @@
#!/bin/sh
# @(#$Id: rclopxml,v 1.3 2008-10-08 08:27:34 dockes Exp $ (C) 2004 J.F.Dockes
#================================================================
# Extract text from an fb2 ebook (xml)
#================================================================
# set variables
LANG=C ; export LANG
LC_ALL=C ; export LC_ALL
progname=rclfb2
filetype=fb2
#RECFILTCOMMONCODE
##############################################################################
# !! Leave the previous line unmodified!! Code imported from the
# recfiltcommon file
# Utility code common to all shell filters. This could be sourced at run
# time, but it's slightly more efficient to include the code in the
# filters at build time (with a sed script).
# Describe error in a way that can be interpreted by our caller
senderror()
{
echo RECFILTERROR $*
# Also alert on stderr just in case
echo ":2:$progname::: $*" 1>&2
exit 1
}
iscmd()
{
cmd=$1
case $cmd in
*/*)
if test -x $cmd -a ! -d $cmd ; then return 0; else return 1; fi ;;
*)
oldifs=$IFS; IFS=":"; set -- $PATH; IFS=$oldifs
for d in $*;do test -x $d/$cmd -a ! -d $d/$cmd && return 0;done
return 1 ;;
esac
}
checkcmds()
{
for cmd in $*;do
if iscmd $cmd
then
a=1
else
senderror HELPERNOTFOUND $cmd
fi
done
}
# show help message
if test $# -ne 1 -o "$1" = "--help"
then
echo "Convert a $filetype file to HTML text for Recoll indexing."
echo "Usage: $progname [infile]"
exit 1
fi
infile="$1"
# check the input file existence (may be '-' for stdin)
if test "X$infile" != X- -a ! -f "$infile"
then
senderror INPUTNOSUCHFILE "$infile"
fi
# protect access to our temp files and directories
umask 77
##############################################################################
# !! Leave the following line unmodified !
#ENDRECFILTCOMMONCODE
checkcmds xsltproc
xsltproc --nonet --novalid - "$infile" <<EOF
<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:fb="http://www.gribuser.ru/xml/fictionbook/2.0"
exclude-result-prefixes="fb"
>
<xsl:output method="html" encoding="UTF-8"/>
<xsl:template match="/fb:FictionBook">
<html>
<xsl:apply-templates select="fb:description"/>
<xsl:apply-templates select="fb:body"/>
</html>
</xsl:template>
<xsl:template match="fb:description">
<head>
<xsl:apply-templates select="fb:title-info"/>
</head><xsl:text>
</xsl:text>
</xsl:template>
<xsl:template match="fb:description/fb:title-info">
<xsl:apply-templates select="fb:book-title"/>
<xsl:apply-templates select="fb:author"/>
</xsl:template>
<xsl:template match="fb:description/fb:title-info/fb:book-title">
<title> <xsl:value-of select="."/> </title>
</xsl:template>
<xsl:template match="fb:description/fb:title-info/fb:author">
<meta>
<xsl:attribute name="name">author</xsl:attribute>
<xsl:attribute name="content">
<xsl:value-of select="fb:first-name"/><xsl:text> </xsl:text>
<xsl:value-of select="fb:middle-name"/><xsl:text> </xsl:text>
<xsl:value-of select="fb:last-name"/>
</xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="fb:body">
<body>
<xsl:apply-templates select="fb:section"/>
</body>
</xsl:template>
<xsl:template match="fb:body/fb:section">
<xsl:for-each select="fb:p">
<p><xsl:value-of select="."/></p>
</xsl:for-each>
</xsl:template>
</xsl:stylesheet>
EOF

87
src/filters/rclfb2.py Executable file
View File

@ -0,0 +1,87 @@
#!/usr/bin/env python3
# Copyright (C) 2014 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.
######################################
from __future__ import print_function
import sys
import rclexecm
import rclxslt
import rclgenxslt
stylesheet_all = '''<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:fb="http://www.gribuser.ru/xml/fictionbook/2.0"
exclude-result-prefixes="fb"
>
<xsl:output method="html" encoding="UTF-8"/>
<xsl:template match="/fb:FictionBook">
<html>
<xsl:apply-templates select="fb:description"/>
<xsl:apply-templates select="fb:body"/>
</html>
</xsl:template>
<xsl:template match="fb:description">
<head>
<xsl:apply-templates select="fb:title-info"/>
</head><xsl:text>
</xsl:text>
</xsl:template>
<xsl:template match="fb:description/fb:title-info">
<xsl:apply-templates select="fb:book-title"/>
<xsl:apply-templates select="fb:author"/>
</xsl:template>
<xsl:template match="fb:description/fb:title-info/fb:book-title">
<title> <xsl:value-of select="."/> </title>
</xsl:template>
<xsl:template match="fb:description/fb:title-info/fb:author">
<meta>
<xsl:attribute name="name">author</xsl:attribute>
<xsl:attribute name="content">
<xsl:value-of select="fb:first-name"/><xsl:text> </xsl:text>
<xsl:value-of select="fb:middle-name"/><xsl:text> </xsl:text>
<xsl:value-of select="fb:last-name"/>
</xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="fb:body">
<body>
<xsl:apply-templates select="fb:section"/>
</body>
</xsl:template>
<xsl:template match="fb:body/fb:section">
<xsl:for-each select="fb:p">
<p><xsl:value-of select="."/></p>
</xsl:for-each>
</xsl:template>
</xsl:stylesheet>
'''
if __name__ == '__main__':
proto = rclexecm.RclExecM()
extract = rclgenxslt.XSLTExtractor(proto, stylesheet_all)
rclexecm.main(proto, extract)

65
src/filters/rclgenxslt.py Executable file
View File

@ -0,0 +1,65 @@
#!/usr/bin/env python3
# Copyright (C) 2018 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.
######################################
from __future__ import print_function
import sys
import rclexecm
import rclxslt
import gzip
class XSLTExtractor:
def __init__(self, em, stylesheet, gzip=False):
self.em = em
self.currentindex = 0
self.stylesheet = stylesheet
self.dogz = gzip
def extractone(self, params):
if "filename:" not in params:
self.em.rclog("extractone: no mime or file name")
return (False, "", "", rclexecm.RclExecM.eofnow)
fn = params["filename:"]
try:
if self.dogz:
data = gzip.open(fn, 'rb').read()
else:
data = open(fn, 'rb').read()
docdata = rclxslt.apply_sheet_data(self.stylesheet, data)
except Exception as err:
self.em.rclog("%s: bad data: %s" % (fn, err))
return (False, "", "", rclexecm.RclExecM.eofnow)
return (True, docdata, "", rclexecm.RclExecM.eofnext)
###### File type handler api, used by rclexecm ---------->
def openfile(self, params):
self.currentindex = 0
return True
def getipath(self, params):
return self.extractone(params)
def getnext(self, params):
if self.currentindex >= 1:
return (False, "", "", rclexecm.RclExecM.eofnow)
else:
ret= self.extractone(params)
self.currentindex += 1
return ret

View File

@ -1,191 +0,0 @@
#!/bin/sh
# @(#$Id: rclsoff,v 1.12 2008-10-08 08:27:34 dockes Exp $ (C) 2004 J.F.Dockes
# Parts taken from Estraier:
#================================================================
# Estraier: a personal full-text search system
# Copyright (C) 2003-2004 Mikio Hirabayashi
#================================================================
#================================================================
# Extract text from a gnumeric spreadsheet
#================================================================
# set variables
LANG=C ; export LANG
LC_ALL=C ; export LC_ALL
progname="rclgnumeric"
filetype=gnumeric
#RECFILTCOMMONCODE
##############################################################################
# !! Leave the previous line unmodified!! Code imported from the
# recfiltcommon file
# Utility code common to all shell filters. This could be sourced at run
# time, but it's slightly more efficient to include the code in the
# filters at build time (with a sed script).
# Describe error in a way that can be interpreted by our caller
senderror()
{
echo RECFILTERROR $*
# Also alert on stderr just in case
echo ":2:$progname::: $*" 1>&2
exit 1
}
iscmd()
{
cmd=$1
case $cmd in
*/*)
if test -x $cmd -a ! -d $cmd ; then return 0; else return 1; fi ;;
*)
oldifs=$IFS; IFS=":"; set -- $PATH; IFS=$oldifs
for d in $*;do test -x $d/$cmd -a ! -d $d/$cmd && return 0;done
return 1 ;;
esac
}
checkcmds()
{
for cmd in $*;do
if iscmd $cmd
then
a=1
else
senderror HELPERNOTFOUND $cmd
fi
done
}
# show help message
if test $# -ne 1 -o "$1" = "--help"
then
echo "Convert a $filetype file to HTML text for Recoll indexing."
echo "Usage: $progname [infile]"
exit 1
fi
infile="$1"
# check the input file existence (may be '-' for stdin)
if test "X$infile" != X- -a ! -f "$infile"
then
senderror INPUTNOSUCHFILE "$infile"
fi
# protect access to our temp files and directories
umask 77
##############################################################################
# !! Leave the following line unmodified !
#ENDRECFILTCOMMONCODE
checkcmds xsltproc gunzip
# We need a temporary file
if test z"$RECOLL_TMPDIR" != z; then
ttdir=$RECOLL_TMPDIR
elif test z"$TMPDIR" != z ; then
ttdir=$TMPDIR
else
ttdir=/tmp
fi
tmpfile=$ttdir/rclgnm.XXXXXX
tmpfile=`mktemp "$tmpfile"`
if [ $? -ne 0 ]; then
senderror "$0: Can't create temp file, exiting..."
fi
cleanup()
{
rm -f $tmpfile
}
trap cleanup EXIT HUP QUIT INT TERM
gunzip < $1 > $tmpfile || senderror "Cant uncompress input"
xsltproc --novalid --nonet - $tmpfile <<EOF
<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0"
xmlns:xlink="http://www.w3.org/1999/xlink"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0"
xmlns:ooo="http://openoffice.org/2004/office"
xmlns:gnm="http://www.gnumeric.org/v10.dtd"
exclude-result-prefixes="office xlink meta ooo dc"
>
<xsl:output method="html" encoding="UTF-8"/>
<xsl:template match="/">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<xsl:apply-templates select="//office:document-meta/office:meta"/>
</head>
<body>
<xsl:apply-templates select="//gnm:Cells"/>
<xsl:apply-templates select="//gnm:Objects"/>
</body>
</html>
</xsl:template>
<xsl:template match="//dc:date">
<meta>
<xsl:attribute name="name">date</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="//dc:description">
<meta>
<xsl:attribute name="name">abstract</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="//meta:keyword">
<meta>
<xsl:attribute name="name">keywords</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="//dc:subject">
<meta>
<xsl:attribute name="name">keywords</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="//dc:title">
<title> <xsl:value-of select="."/> </title>
</xsl:template>
<xsl:template match="//meta:initial-creator">
<meta>
<xsl:attribute name="name">author</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="office:meta/*"/>
<xsl:template match="gnm:Cell">
<p><xsl:value-of select="."/></p>
</xsl:template>
<xsl:template match="gnm:CellComment">
<blockquote><xsl:value-of select="@Text"/></blockquote>
</xsl:template>
</xsl:stylesheet>
EOF

112
src/filters/rclgnm.py Executable file
View File

@ -0,0 +1,112 @@
#!/usr/bin/env python3
# Copyright (C) 2014 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.
######################################
from __future__ import print_function
import sys
import rclexecm
import rclgenxslt
stylesheet_all = '''<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0"
xmlns:xlink="http://www.w3.org/1999/xlink"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0"
xmlns:ooo="http://openoffice.org/2004/office"
xmlns:gnm="http://www.gnumeric.org/v10.dtd"
exclude-result-prefixes="office xlink meta ooo dc"
>
<xsl:output method="html" encoding="UTF-8"/>
<xsl:template match="/">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
<xsl:apply-templates select="//office:document-meta/office:meta"/>
</head>
<body>
<xsl:apply-templates select="//gnm:Cells"/>
<xsl:apply-templates select="//gnm:Objects"/>
</body>
</html>
</xsl:template>
<xsl:template match="//dc:date">
<meta>
<xsl:attribute name="name">date</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="//dc:description">
<meta>
<xsl:attribute name="name">abstract</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="//meta:keyword">
<meta>
<xsl:attribute name="name">keywords</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="//dc:subject">
<meta>
<xsl:attribute name="name">keywords</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="//dc:title">
<title> <xsl:value-of select="."/> </title>
</xsl:template>
<xsl:template match="//meta:initial-creator">
<meta>
<xsl:attribute name="name">author</xsl:attribute>
<xsl:attribute name="content"><xsl:value-of select="."/></xsl:attribute>
</meta>
</xsl:template>
<xsl:template match="office:meta/*"/>
<xsl:template match="gnm:Cell">
<p><xsl:value-of select="."/></p>
</xsl:template>
<xsl:template match="gnm:CellComment">
<blockquote><xsl:value-of select="@Text"/></blockquote>
</xsl:template>
</xsl:stylesheet>
'''
if __name__ == '__main__':
proto = rclexecm.RclExecM()
extract = rclgenxslt.XSLTExtractor(proto, stylesheet_all, gzip=True)
rclexecm.main(proto, extract)

View File

@ -1,130 +0,0 @@
#!/bin/sh
# @(#$Id: rclsoff,v 1.12 2008-10-08 08:27:34 dockes Exp $ (C) 2004 J.F.Dockes
# Parts taken from Estraier:
#================================================================
# Estraier: a personal full-text search system
# Copyright (C) 2003-2004 Mikio Hirabayashi
#================================================================
#================================================================
# Extract text from a gnumeric spreadsheet
#================================================================
# set variables
LANG=C ; export LANG
LC_ALL=C ; export LC_ALL
progname="rclgnumeric"
filetype=gnumeric
#RECFILTCOMMONCODE
##############################################################################
# !! Leave the previous line unmodified!! Code imported from the
# recfiltcommon file
# Utility code common to all shell filters. This could be sourced at run
# time, but it's slightly more efficient to include the code in the
# filters at build time (with a sed script).
# Describe error in a way that can be interpreted by our caller
senderror()
{
echo RECFILTERROR $*
# Also alert on stderr just in case
echo ":2:$progname::: $*" 1>&2
exit 1
}
iscmd()
{
cmd=$1
case $cmd in
*/*)
if test -x $cmd -a ! -d $cmd ; then return 0; else return 1; fi ;;
*)
oldifs=$IFS; IFS=":"; set -- $PATH; IFS=$oldifs
for d in $*;do test -x $d/$cmd -a ! -d $d/$cmd && return 0;done
return 1 ;;
esac
}
checkcmds()
{
for cmd in $*;do
if iscmd $cmd
then
a=1
else
senderror HELPERNOTFOUND $cmd
fi
done
}
# show help message
if test $# -ne 1 -o "$1" = "--help"
then
echo "Convert a $filetype file to HTML text for Recoll indexing."
echo "Usage: $progname [infile]"
exit 1
fi
infile="$1"
# check the input file existence (may be '-' for stdin)
if test "X$infile" != X- -a ! -f "$infile"
then
senderror INPUTNOSUCHFILE "$infile"
fi
# protect access to our temp files and directories
umask 77
##############################################################################
# !! Leave the following line unmodified !
#ENDRECFILTCOMMONCODE
checkcmds xsltproc
xsltproc --novalid --nonet - "$infile" <<EOF
<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<xsl:output method="html" encoding="UTF-8"/>
<xsl:strip-space elements="*" />
<xsl:template match="/">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<title>
Okular notes about: <xsl:value-of select="/documentInfo/@url" />
</title>
</head>
<body>
<xsl:apply-templates />
</body>
</html>
</xsl:template>
<xsl:template match="node()">
<xsl:apply-templates select="@* | node() "/>
</xsl:template>
<xsl:template match="text()">
<p><xsl:value-of select="."/></p>
<xsl:text >
</xsl:text>
</xsl:template>
<xsl:template match="@contents|@author">
<p><xsl:value-of select="." /></p>
<xsl:text >
</xsl:text>
</xsl:template>
<xsl:template match="@*"/>
</xsl:stylesheet>
EOF

70
src/filters/rclokulnote.py Executable file
View File

@ -0,0 +1,70 @@
#!/usr/bin/env python3
# Copyright (C) 2014 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.
######################################
from __future__ import print_function
import sys
import rclexecm
import rclgenxslt
stylesheet_all = '''<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<xsl:output method="html" encoding="UTF-8"/>
<xsl:strip-space elements="*" />
<xsl:template match="/">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<title>
Okular notes about: <xsl:value-of select="/documentInfo/@url" />
</title>
</head>
<body>
<xsl:apply-templates />
</body>
</html>
</xsl:template>
<xsl:template match="node()">
<xsl:apply-templates select="@* | node() "/>
</xsl:template>
<xsl:template match="text()">
<p><xsl:value-of select="."/></p>
<xsl:text >
</xsl:text>
</xsl:template>
<xsl:template match="@contents|@author">
<p><xsl:value-of select="." /></p>
<xsl:text >
</xsl:text>
</xsl:template>
<xsl:template match="@*"/>
</xsl:stylesheet>
'''
if __name__ == '__main__':
proto = rclexecm.RclExecM()
extract = rclgenxslt.XSLTExtractor(proto, stylesheet_all)
rclexecm.main(proto, extract)

View File

@ -1,92 +0,0 @@
#!/bin/sh
# @(#$Id: rclsiduxman,v 1.1 2008-06-09 09:12:05 dockes Exp $ (C) 2004 J.F.Dockes
# Parts taken from Estraier:
#================================================================
# Estraier: a personal full-text search system
# Copyright (C) 2003-2004 Mikio Hirabayashi
#================================================================
#================================================================
# Strip the menu part from sidux manual pages to improve search precision
#================================================================
# set variables
LANG=C ; export LANG
LC_ALL=C ; export LC_ALL
progname="rclsiduxman"
filetype="sidux manual htm"
#RECFILTCOMMONCODE
##############################################################################
# !! Leave the previous line unmodified!! Code imported from the
# recfiltcommon file
# Utility code common to all shell filters. This could be sourced at run
# time, but it's slightly more efficient to include the code in the
# filters at build time (with a sed script).
# Describe error in a way that can be interpreted by our caller
senderror()
{
echo RECFILTERROR $*
# Also alert on stderr just in case
echo ":2:$progname::: $*" 1>&2
exit 1
}
iscmd()
{
cmd=$1
case $cmd in
*/*)
if test -x $cmd -a ! -d $cmd ; then return 0; else return 1; fi ;;
*)
oldifs=$IFS; IFS=":"; set -- $PATH; IFS=$oldifs
for d in $*;do test -x $d/$cmd -a ! -d $d/$cmd && return 0;done
return 1 ;;
esac
}
checkcmds()
{
for cmd in $*;do
if iscmd $cmd
then
a=1
else
senderror HELPERNOTFOUND $cmd
fi
done
}
# show help message
if test $# -ne 1 -o "$1" = "--help"
then
echo "Convert a $filetype file to HTML text for Recoll indexing."
echo "Usage: $progname [infile]"
exit 1
fi
infile="$1"
# check the input file existence (may be '-' for stdin)
if test "X$infile" != X- -a ! -f "$infile"
then
senderror INPUTNOSUCHFILE "$infile"
fi
# protect access to our temp files and directories
umask 77
##############################################################################
# !! Leave the following line unmodified !
#ENDRECFILTCOMMONCODE
checkcmds sed
# Delete everything from <div id="menu"> to <div id="main-page">
# This prints an additional blank line at top which does not matter
sed -n -e '1,/<div id="menu">/{x;p' -e '}' \
-e '/<div id="main-page">/,$p' < "$infile"
# exit normally
exit 0

View File

@ -15,12 +15,11 @@
# Free Software Foundation, Inc.,
# 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
######################################
from __future__ import print_function
import sys
import rclexecm
import rclxslt
import rclgenxslt
stylesheet_all = '''<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
@ -100,43 +99,7 @@ stylesheet_all = '''<?xml version="1.0"?>
</xsl:stylesheet>
'''
class SVGExtractor:
def __init__(self, em):
self.em = em
self.currentindex = 0
def extractone(self, params):
if "filename:" not in params:
self.em.rclog("extractone: no mime or file name")
return (False, "", "", rclexecm.RclExecM.eofnow)
fn = params["filename:"]
try:
data = open(fn, 'rb').read()
docdata = rclxslt.apply_sheet_data(stylesheet_all, data)
except Exception as err:
self.em.rclog("%s: bad data: %s" % (fn, err))
return (False, "", "", rclexecm.RclExecM.eofnow)
return (True, docdata, "", rclexecm.RclExecM.eofnext)
###### File type handler api, used by rclexecm ---------->
def openfile(self, params):
self.currentindex = 0
return True
def getipath(self, params):
return self.extractone(params)
def getnext(self, params):
if self.currentindex >= 1:
return (False, "", "", rclexecm.RclExecM.eofnow)
else:
ret= self.extractone(params)
self.currentindex += 1
return ret
if __name__ == '__main__':
proto = rclexecm.RclExecM()
extract = SVGExtractor(proto)
extract = rclgenxslt.XSLTExtractor(proto, stylesheet_all)
rclexecm.main(proto, extract)

View File

@ -18,7 +18,7 @@
import sys
import rclexecm
import rclxslt
import rclgenxslt
stylesheet_all = '''<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
@ -56,43 +56,7 @@ stylesheet_all = '''<?xml version="1.0"?>
</xsl:stylesheet>
'''
class XMLExtractor:
def __init__(self, em):
self.em = em
self.currentindex = 0
def extractone(self, params):
if "filename:" not in params:
self.em.rclog("extractone: no mime or file name")
return (False, "", "", rclexecm.RclExecM.eofnow)
fn = params["filename:"]
try:
data = open(fn, 'rb').read()
docdata = rclxslt.apply_sheet_data(stylesheet_all, data)
except Exception as err:
self.em.rclog("%s: bad data: " % (fn, err))
return (False, "", "", rclexecm.RclExecM.eofnow)
return (True, docdata, "", rclexecm.RclExecM.eofnext)
###### File type handler api, used by rclexecm ---------->
def openfile(self, params):
self.currentindex = 0
return True
def getipath(self, params):
return self.extractone(params)
def getnext(self, params):
if self.currentindex >= 1:
return (False, "", "", rclexecm.RclExecM.eofnow)
else:
ret= self.extractone(params)
self.currentindex += 1
return ret
if __name__ == '__main__':
proto = rclexecm.RclExecM()
extract = XMLExtractor(proto)
extract = rclgenxslt.XSLTExtractor(proto, stylesheet_all)
rclexecm.main(proto, extract)

View File

@ -32,7 +32,8 @@ if PY2:
print("RECFILTERROR HELPERNOTFOUND python:libxml2/python:libxslt1")
sys.exit(1);
def _apply_sheet_doc(sheet, doc):
styledoc = libxml2.parseMemory(sheet, len(sheet))
styledoc = libxml2.readMemory(sheet, len(sheet), '', '',
options=libxml2.XML_PARSE_NONET)
style = libxslt.parseStylesheetDoc(styledoc)
result = style.applyStylesheet(doc, None)
res = ""
@ -46,10 +47,11 @@ if PY2:
result.freeDoc()
return res
def apply_sheet_data(sheet, data):
doc = libxml2.parseMemory(data, len(data))
doc = libxml2.readMemory(data, len(data), '', '',
options=libxml2.XML_PARSE_NONET)
return _apply_sheet_doc(sheet, doc)
def apply_sheet_file(sheet, fn):
doc = libxml2.parseFile(fn)
doc = libxml2.readFile(fn, '', options=libxml2.XML_PARSE_NONET)
return _apply_sheet_doc(sheet, doc)
else:
try:

View File

@ -118,12 +118,12 @@ application/x-dvi = exec rcldvi
application/x-flac = execm rclaudio
application/x-gnote = execm rclxml.py
application/x-gnuinfo = execm rclinfo
application/x-gnumeric = exec rclgnm
application/x-gnumeric = execm rclgnm.py
application/x-kword = exec rclkwd
application/x-lyx = exec rcllyx
application/x-mimehtml = internal message/rfc822
#application/x-mobipocket-ebook = execm rclmobi
application/x-okular-notes = exec rclokulnote
application/x-okular-notes = execm rclokulnote.py
application/x-perl = internal text/plain
# Returned by xdg-mime for .php. Future-proofing
application/x-php = internal text/plain
@ -168,9 +168,8 @@ text/css = internal text/plain
application/javascript = internal text/plain
text/x-bibtex = exec rclbibtex.sh ; mimetype = text/plain
text/x-csv = internal text/plain
text/x-fictionbook = exec rclfb2
text/x-fictionbook = execm rclfb2.py
text/x-gaim-log = exec rclgaim
text/x-html-sidux-man = exec rclsiduxman
text/x-html-aptosid-man = exec rclaptosidman
text/x-lua = internal
text/x-chm-html = internal text/html
@ -283,7 +282,6 @@ text/x-c++ = source
text/x-csv = txt
text/x-fictionbook = document
text/x-html-aptosid-man = aptosid-book
text/x-html-sidux-man = sidux-book
text/x-ini = txt
text/x-bibtex = txt
text/x-lua = source

View File

@ -81,6 +81,7 @@ application/vnd.sun.xml.writer.template = execm python rclsoff.py
application/vnd.wordperfect = exec wpd/wpd2html;mimetype=text/html
application/x-abiword = execm python rclabw.py
text/x-fictionbook = execm python rclfb2.py
application/vnd.openxmlformats-officedocument.wordprocessingml.document = \
execm python rclopxml.py