diff --git a/src/filters/rclinfo b/src/filters/rclinfo index 203e7e57..8047c842 100755 --- a/src/filters/rclinfo +++ b/src/filters/rclinfo @@ -32,13 +32,17 @@ class InfoExtractor: nodename, docdata = self.contents[index] nodename = self.em.htmlescape(nodename) docdata = self.em.htmlescape(docdata) + print("type(docdata) = %s type(nodename) = %s"% \ + (type(docdata), type(nodename)), file=sys.stderr) # strange whitespace to avoid changing the module tests (same as old) - docdata = b'\n\n \n ' + nodename + \ + docdata = b'\n<html>\n <head>\n <title>' + \ + nodename + \ b'\n' + \ - ' \n' + \ + b' \n' + \ b' \n \n' + \ b' 
\n   ' + \
-                  docdata + b'\n
\n\n' + docdata + \ + b'\n \n\n' iseof = rclexecm.RclExecM.noteof if self.currentindex >= len(self.contents) -1: diff --git a/src/filters/rclkar b/src/filters/rclkar index 00432b15..940f13d0 100755 --- a/src/filters/rclkar +++ b/src/filters/rclkar @@ -1,4 +1,4 @@ -#!/usr/bin/env python +#!/usr/bin/env python2 # Read a .kar midi karaoke file and translate to recoll indexable format # This does not work with Python3 yet because python:midi doesn't diff --git a/src/filters/rclmpdf.py b/src/filters/rclmpdf.py index 0b5ba836..4d7e9634 100755 --- a/src/filters/rclmpdf.py +++ b/src/filters/rclmpdf.py @@ -120,24 +120,24 @@ class PDFExtractor: inheader = False inbody = False didcs = False - output = '' - cont = '' - for line in input.split('\n'): + output = b'' + cont = b'' + for line in input.split(b'\n'): line = cont + line - cont = '' - if re.search('', line): + cont = b'' + if re.search(b'', line): inheader = False - if re.search('', line): + if re.search(b'', line): inbody = False if inheader: if not didcs: - output += '\n' + output += b'\n' didcs = True - m = re.search(r'(.*)(.*)(<\/title>.*)', line) + m = re.search(rb'(.*<title>)(.*)(<\/title>.*)', line) if not m: - m = re.search(r'(.*content=")(.*)(".*/>.*)', line) + m = re.search(rb'(.*content=")(.*)(".*/>.*)', line) if m: line = m.group(1) + self.em.htmlescape(m.group(2)) + \ m.group(3) @@ -145,7 +145,7 @@ class PDFExtractor: # Recoll treats "Subject" as a "title" element # (based on emails). The PDF "Subject" metadata # field is more like an HTML "description" - line = re.sub('name="Subject"', 'name="Description"', line, 1) + line = re.sub(b'name="Subject"', b'name="Description"', line, 1) elif inbody: # Remove end-of-line hyphenation. It's not clear that @@ -158,12 +158,12 @@ class PDFExtractor: #cont = m.group(2).rstrip('-') line = self.em.htmlescape(line) - if re.search('<head>', line): + if re.search(b'<head>', line): inheader = True - if re.search('<pre>', line): + if re.search(b'<pre>', line): inbody = True - output += line + '\n' + output += line + b'\n' return output diff --git a/src/filters/rcltar b/src/filters/rcltar index f597bb79..74aaecbd 100755 --- a/src/filters/rcltar +++ b/src/filters/rcltar @@ -23,15 +23,15 @@ class TarExtractor: self.namen = [] def extractone(self, ipath): - docdata = "" + docdata = b'' try: info = self.tar.getmember(ipath) if info.size > self.em.maxmembersize: # skip - docdata = "" + docdata = b'' self.em.rclog("extractone: entry %s size %d too big" % (ipath, info.size)) - docdata = "" # raise TarError("Member too big") + docdata = b'' # raise TarError("Member too big") else: docdata = self.tar.extractfile(ipath).read() ok = True @@ -45,7 +45,7 @@ class TarExtractor: def openfile(self, params): self.currentindex = -1 try: - self.tar = tarfile.open(name=params["filename:"],mode='r') + self.tar = tarfile.open(name=params["filename:"], mode='r') #self.namen = [ y.name for y in filter(lambda z:z.isfile(),self.tar.getmembers())] self.namen = [ y.name for y in [z for z in self.tar.getmembers() if z.isfile()]] diff --git a/src/filters/rcltext.py b/src/filters/rcltext.py index 847a80b2..f449dfe6 100755 --- a/src/filters/rcltext.py +++ b/src/filters/rcltext.py @@ -21,7 +21,7 @@ class TxtDump: fn = params["filename:"] # No charset, so recoll will have to use its config to guess it - txt = '<html><head><title>
'
+        txt = b'
'
         try:
             f = open(fn, "rb")
             txt += self.em.htmlescape(f.read())
@@ -29,7 +29,7 @@ class TxtDump:
             self.em.rclog("TxtDump: %s : %s" % (fn, err))
             return (False, "", "", rclexecm.RclExecM.eofnow)
             
-        txt += '
'
+        txt += b'
' return (True, txt, "", rclexecm.RclExecM.eofnext) ###### File type handler api, used by rclexecm ----------> diff --git a/src/filters/xlsxmltocsv.py b/src/filters/xlsxmltocsv.py index cfc39304..7fa12e58 100755 --- a/src/filters/xlsxmltocsv.py +++ b/src/filters/xlsxmltocsv.py @@ -1,14 +1,33 @@ #!/usr/bin/env python2 +# Copyright (C) 2015 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. # Transform XML output from xls-dump.py into csv format. -# Note: msodumper is not compatible with python3. +# +# Note: this would be difficult to make compatible with python 3 <= 3.4 +# because of the use of % interpolation on what should be bytes. +# The python2 restriction is not a big issue at this point because +# msodumper is not compatible with python3 anyway +# % interpolation for bytes is planned for python 3.5, at which point +# porting this module will become trivial. from __future__ import print_function import sys import xml.sax -sys.path.append(sys.path[0]+"/msodump.zip") -from msodumper.globals import error dtt = True @@ -62,7 +81,7 @@ if __name__ == '__main__': xml.sax.parse(sys.stdin, handler) print(handler.output) except BaseException as err: - error("xml-parse: %s\n" % (str(sys.exc_info()[:2]),)) + print("xml-parse: %s\n" % (str(sys.exc_info()[:2]),), file=sys.stderr) sys.exit(1) sys.exit(0)