filters cleanup continued: remove unused rclps, translate rclabw to python

This commit is contained in:
Jean-Francois Dockes 2018-06-04 10:53:31 +02:00
parent 9bb65fd970
commit 2a45f7fef6
5 changed files with 68 additions and 227 deletions

View File

@ -622,7 +622,7 @@ filterdir = $(pkgdatadir)/filters
filter_DATA = \
desktop/hotrecoll.py \
filters/rcl7z \
filters/rclabw \
filters/rclabw.py \
filters/rclaptosidman \
filters/rclaudio \
filters/rclbibtex.sh \
@ -654,7 +654,6 @@ filters/rclpdf.py \
filters/rclokulnote \
filters/rclopxml.py \
filters/rclppt.py \
filters/rclps \
filters/rclpurple \
filters/rclpython \
filters/rclrar \

View File

@ -1,91 +1,28 @@
#!/bin/sh
# @(#$Id: rclabw,v 1.3 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 an abiword file
#================================================================
#!/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.
######################################
# set variables
LANG=C ; export LANG
LC_ALL=C ; export LC_ALL
progname="rclabw"
filetype=abiword
from __future__ import print_function
import sys
import rclexecm
import rclxslt
#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 - "$infile" <<EOF
<?xml version="1.0"?>
stylesheet_all = '''<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:ab="http://www.abisource.com/awml.dtd"
@ -173,7 +110,46 @@ xsltproc --nonet --novalid - "$infile" <<EOF
</xsl:template>
</xsl:stylesheet>
EOF
'''
# exit normally
exit 0
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)
rclexecm.main(proto, extract)

View File

@ -1,135 +0,0 @@
#!/bin/sh
# @(#$Id: rclps,v 1.10 2007-06-08 13:51:09 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 postscript file by executing pstotext or ps2ascii.
#
# The default is to use pstotext which can deal with accents, but in a
# partially broken way (it always outputs iso8859-1, when it should use utf.
#
# OTOH, ps2ascii is much faster, comes with ghostscript, and sometimes work
# better (ie: on some openoffice output files).
#
#================================================================
# set variables
LANG=C ; export LANG
LC_ALL=C ; export LC_ALL
progname="rclps"
decoder=pstotext
#decoder=ps2ascii
filetype=postscript
#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 $decoder iconv awk
# output the result
# The strange 'BEGIN' setup is to prevent 'file' from thinking this file
# is an awk program
$decoder "$infile" |
awk 'BEGIN'\
' {
printf("<html><head><title></title>\n")
printf("<meta http-equiv=\"Content-Type\" content=\"text/html;charset=UTF-8\">\n")
printf("</head>\n<body><p>");
doescape = 1
cont = ""
}
{
$0 = cont $0
cont = ""
if ($0 == "\f") {
print "</p>\n<hr>\n\f<p>"
next
} else if ($0 ~ /­$/) {
# Note : soft-hyphen is iso8859 0xad
# Break at last whitespace
match($0, "[ \t][^ \t]+$")
line = substr($0, 0, RSTART)
cont = substr($0, RSTART, RLENGTH)
$0 = line
gsub("­", "", cont)
}
if(doescape > 0) {
gsub(/&/, "\\&amp;", $0)
gsub(/</, "\\&lt;", $0)
gsub(/>/, "\\&gt;", $0)
}
print $0 "<br>"
}
END {
print "</p></body></html>"
}' | iconv -f iso-8859-1 -t UTF-8 -c -s

View File

@ -75,7 +75,7 @@ application/vnd.ms-office = execm rcldoc.py
application/ogg = execm rclaudio
application/pdf = execm rclpdf.py
application/postscript = exec pstotext;charset=iso-8859-1;mimetype=text/plain
application/postscript = exec pstotext;charset=cp1252;mimetype=text/plain
application/sql = internal text/plain
application/vnd.ms-excel = execm rclxls.py
application/vnd.ms-powerpoint = execm rclppt.py
@ -110,7 +110,7 @@ application/vnd.sun.xml.writer = execm rclsoff.py
application/vnd.sun.xml.writer.global = execm rclsoff.py
application/vnd.sun.xml.writer.template = execm rclsoff.py
application/vnd.wordperfect = exec wpd2html;mimetype=text/html
application/x-abiword = exec rclabw
application/x-abiword = execm rclabw.py
application/x-awk = internal text/plain
application/x-chm = execm rclchm
application/x-dia-diagram = execm rcldia;mimetype=text/plain

View File

@ -80,6 +80,7 @@ application/vnd.sun.xml.writer.global = execm python rclsoff.py
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
application/vnd.openxmlformats-officedocument.wordprocessingml.document = \
execm python rclopxml.py