diff --git a/src/filters/rclchm b/src/filters/rclchm
index b78a1cd4..2bb78352 100755
--- a/src/filters/rclchm
+++ b/src/filters/rclchm
@@ -11,6 +11,7 @@ rclchm_html_mtype = "text/html"
import sys
import os
+import re
import posixpath
import urlparse
import urllib
@@ -201,6 +202,8 @@ class rclCHM:
res, doc = self.chm.RetrieveObject(ui)
#self.em.rclog("extract: RetrieveObject: %d [%s]" % (res, doc))
if res > 0:
+ doc = re.sub('''''', doc)
self.em.setmimetype(rclchm_html_mtype)
return (True, doc, path, iseof)
return (False, "", path, iseof)
diff --git a/src/filters/rclepub b/src/filters/rclepub
new file mode 100755
index 00000000..d1b9b39c
--- /dev/null
+++ b/src/filters/rclepub
@@ -0,0 +1,74 @@
+#!/usr/bin/env python
+"""Extract Html content from an EPUB file (.chm)"""
+
+rclepub_html_mtype = "text/html"
+
+import sys
+import os
+import re
+
+import rclexecm
+
+try:
+ import epub
+except:
+ print "RECFILTERROR HELPERNOTFOUND python:epub"
+ sys.exit(1);
+
+class rclEPUB:
+ """RclExecM slave worker for extracting all text from an EPUB
+ file. We first extract the list of internal nodes, and them return them
+ one by one. The ipath is the internal href"""
+
+ def __init__(self, em):
+ self.currentindex = 0
+ self.em = em
+ self.em.setmimetype(rclepub_html_mtype)
+
+ def extractone(self, path):
+ """Extract one path-named internal file from the EPUB file"""
+
+ #self.em.rclog("extractone: [%s]"%(path))
+ iseof = rclexecm.RclExecM.noteof
+ if self.currentindex >= len(self.contents) -1:
+ iseof = rclexecm.RclExecM.eofnext
+
+ try:
+ doc = self.book.read(path)
+ doc = re.sub('''''', doc)
+ return (True, doc, path, iseof)
+ except Exception, err:
+ self.em.rclog("openfile: failed: [%s]" % err)
+ return (False, "", path, iseof)
+
+ def openfile(self, params):
+ """Open the EPUB file"""
+ self.currentindex = 0
+ self.contents = []
+ try:
+ self.book = epub.open(params["filename:"])
+ except Exception, err:
+ self.em.rclog("openfile: failed: [%s]" % err)
+ return False
+ for id, item in self.book.opf.manifest.iteritems():
+# print item.__dict__
+ if item.media_type == u'application/xhtml+xml':
+ self.contents.append(item.href)
+ return True
+
+
+ def getipath(self, params):
+ return self.extractone(params["ipath:"])
+
+ def getnext(self, params):
+ if self.currentindex >= len(self.contents):
+ return (False, "", "", rclexecm.RclExecM.eofnow)
+ else:
+ ret= self.extractone(self.contents[self.currentindex])
+ self.currentindex += 1
+ return ret
+
+proto = rclexecm.RclExecM()
+extract = rclEPUB(proto)
+rclexecm.main(proto, extract)
diff --git a/src/filters/rclinfo b/src/filters/rclinfo
index 1ccc2a72..01ef47d9 100755
--- a/src/filters/rclinfo
+++ b/src/filters/rclinfo
@@ -20,8 +20,10 @@ htmltemplate = '''
%s
+
-
+
+
%s
diff --git a/src/filters/rclshowchm b/src/filters/rclshowchm
new file mode 100755
index 00000000..a1ef8e06
--- /dev/null
+++ b/src/filters/rclshowchm
@@ -0,0 +1,3 @@
+#!/bin/sh
+
+kchmviewer --url $2 $1