Merge branch 'RECOLL_1_23_MAINT'

src/filters/rclchm

@@ -7,11 +7,6 @@ from __future__ import print_function
 # Note: this is not converted to python3, libchm does not have a
 # python3 wrapper at this point (2015-11)
 
-# 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
@@ -20,9 +15,9 @@ import re
 import posixpath
 import urlparse
 import urllib
-if rclchm_catenate:
-    import subprocess
+import subprocess
 
+import rclconfig
 import rclexecm
 
 try:
@@ -196,7 +191,10 @@ class rclCHM:
         self.contents = []
         self.chm = chm.CHMFile()
         self.em = em
-        if rclchm_catenate:
+        cf = rclconfig.RclConfig()
+        self.catenate = cf.getConfParam("chmcatenate")
+        self.catenate = int(self.catenate) if self.catenate else False
+        if self.catenate:
             self.em.setmimetype("text/plain")
         else:
             self.em.setmimetype(rclchm_html_mtype)
@@ -314,7 +312,8 @@ class rclCHM:
         return self.extractone(params["ipath:"])
         
     def getnext(self, params):
-        if rclchm_catenate:
+        if self.catenate:
+            self.em.setmimetype("text/plain")
             alltxt = self.dumpall()
             if alltxt:
                 return (True, alltxt, "", rclexecm.RclExecM.eofnext)

src/filters/rclepub

@@ -1,5 +1,5 @@
 #!/usr/bin/env python2
-"""Extract Html content from an EPUB file (.chm)"""
+"""Extract Html content from an EPUB file (.epub)"""
 from __future__ import print_function
 
 rclepub_html_mtype = "text/html"
@@ -7,8 +7,10 @@ rclepub_html_mtype = "text/html"
 import sys
 import os
 import re
+import subprocess
 
 import rclexecm
+import rclconfig
 
 try:
     import epub
@@ -25,6 +27,9 @@ class rclEPUB:
         self.currentindex = 0
         self.em = em
         self.em.setmimetype(rclepub_html_mtype)
+        cf = rclconfig.RclConfig()
+        self.catenate = cf.getConfParam("epubcatenate")
+        self.catenate = int(self.catenate) if self.catenate else False
 
     def _selfdoc(self):
         meta = self.book.opf.metadata
@@ -72,6 +77,25 @@ class rclEPUB:
             self.em.rclog("extractone: failed: [%s]" % err)
             return (False, "", id, iseof)
 
+    def dumpall(self):
+        self.em.setmimetype('text/plain')
+        alltxt=""
+
+        for idx in range(len(self.contents)):
+            ret,doc,path,iseof = self.extractone(self.contents[idx])
+            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 EPUB file, create a contents array"""
         self.currentindex = -1
@@ -91,6 +115,12 @@ class rclEPUB:
         return self.extractone(params["ipath:"])
 
     def getnext(self, params):
+        if self.catenate:
+            alltxt = self.dumpall()
+            if alltxt:
+                return (True, alltxt, "", rclexecm.RclExecM.eofnext)
+            else:
+                return (False, "", "", rclexecm.RclExecM.eofnow)
 
         if self.currentindex == -1:
             self.currentindex = 0