rclchm, rclepub: define config variables chmcatenate and epubcatenate to specify that the files should be indexed as a whole instead of as individual chapters

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