python filters: create common main program inside rclexecm.py to help with testing

src/filters/rclaudio

@@ -37,7 +37,6 @@ class AudioTagExtractor:
     def __init__(self, em):
         self.em = em
         self.currentindex = 0
-        self.em.setmimetype("text/html")
 
     def extractone(self, params):
         #self.em.rclog("extractone %s %s" % (params["filename:"], params["mimetype:"]))
@@ -76,6 +75,7 @@ class AudioTagExtractor:
             title = self.em.htmlescape(tags["title"][0].encode("utf-8"))
         except:
             pass
+        self.em.setmimetype("text/html")
         alldata = self.em.htmlescape(tags.pprint().encode("utf-8"))
         alldata = alldata.replace("\n", "<br>")
         docdata = htmltemplate % (album, artist, title, alldata)
@@ -98,5 +98,6 @@ class AudioTagExtractor:
             self.currentindex += 1
             return ret
 
-e = rclexecm.RclExecM()
+proto = rclexecm.RclExecM()
-e.mainloop(AudioTagExtractor(e))
+extract = AudioTagExtractor(proto)
+rclexecm.main(proto, extract)

src/filters/rclchm

@@ -112,6 +112,7 @@ class rclCHM:
         res, doc = self.chm.RetrieveObject(ui)
         #self.em.rclog("extract: RetrieveObject: %d [%s]" % (res, doc))
         if res > 0:
+            self.em.setmimetype("text/html")
             return (True, doc, path, iseof)
         return (False, "", path, iseof)
     
@@ -146,5 +147,6 @@ class rclCHM:
             self.currentindex += 1
             return ret
 
-e = rclexecm.RclExecM()
+proto = rclexecm.RclExecM()
-e.mainloop(rclCHM(e))
+extract = rclCHM(proto)
+rclexecm.main(proto, extract)

src/filters/rclexecm.py

@@ -28,6 +28,9 @@ class RclExecM:
     # Our worker sometimes knows the mime types of the data it sends
     def setmimetype(self, mt):
         self.mimetype = mt
+
+    # Read single parameter from process input: line with param name and size
+    # followed by data.
     def readparam(self):
         s = sys.stdin.readline()
         if s == '':
@@ -95,6 +98,7 @@ class RclExecM:
             
         # If we have an ipath, that's what we look for, else ask for next entry
         ipath = ""
+        self.mimetype = ""
         if params.has_key("ipath:") and len(params["ipath:"]):
             ok, data, ipath, eof = processor.getipath(params)
         else:
@@ -123,3 +127,42 @@ class RclExecM:
             # Got message, act on it
             self.processmessage(processor, params)
 
+
+# Common main routine for all python execm filters: either run the
+# normal protocol engine or a local loop to test without recollindex
+def main(proto, extract):
+    if len(sys.argv) == 1:
+        proto.mainloop(extract)
+    else:
+        # Got a file name parameter: TESTING without an execm parent
+        # Loop on all entries or get specific ipath
+        if not extract.openfile({'filename:':sys.argv[1]}):
+            print "Open error"
+            sys.exit(1)
+        ipath = ""
+        if len(sys.argv) == 3:
+            ipath = sys.argv[2]
+
+        if ipath != "":
+            ok, data, ipath, eof = extract.getipath({'ipath:':ipath})
+            if ok:
+                print "== Found entry for ipath %s (mimetype [%s]):" % \
+                      (ipath, proto.mimetype)
+                print data
+                print
+            else:
+                print "Got error, eof %d"%eof
+            sys.exit(0)
+
+        ecnt = 0   
+        while 1:
+            ok, data, ipath, eof = extract.getnext("")
+            if ok:
+                ecnt = ecnt + 1
+                print "== Entry %d ipath %s (mimetype [%s]:" % \
+                      (ecnt, ipath, proto.mimetype)
+#                print data
+                print
+            else:
+                print "Not ok, eof %d" % eof
+                break

src/filters/rclics

@@ -37,7 +37,6 @@ class IcalExtractor:
         self.file = ""
 	self.contents = []
         self.em = em
-        self.em.setmimetype("text/plain")
 
     def extractone(self, index):
         if index >= len(self.contents):
@@ -48,6 +47,7 @@ class IcalExtractor:
         iseof = rclexecm.RclExecM.noteof
         if self.currentindex >= len(self.contents) -1:
             iseof = rclexecm.RclExecM.eofnext
+        self.em.setmimetype("text/plain")
         return (True, docdata, str(index), iseof)
 
     ###### File type handler api, used by rclexecm ---------->
@@ -152,29 +152,6 @@ class ICalSimpleSplitter:
         return lo
  
 
-##### Main program: either talk to the parent or execute test loop
+proto = rclexecm.RclExecM()
-
+extract = IcalExtractor(proto)
-e = rclexecm.RclExecM()
+rclexecm.main(proto, extract)
-ical = IcalExtractor(e)
-
-if len(sys.argv) == 1:
-    e.mainloop(ical)
-else:
-    # Got a file name parameter: testing without an execm parent
-    # Loop on all entries
-    if not ical.openfile({'filename:':sys.argv[1]}):
-        print "Open error"
-        sys.exit(1)
-
-    ecnt = 0   
-    while 1:
-        ok, data, ipath, eof = ical.getnext("")
-        if ok:
-            ecnt = ecnt + 1
-            print "=========== ENTRY %d =================" % ecnt
-            print data
-            print
-        else:
-            print "Got error, eof %d"%eof
-            break
-    

src/filters/rclinfo

@@ -29,7 +29,6 @@ class InfoExtractor:
         self.file = ""
 	self.contents = []
         self.em = em
-        self.em.setmimetype("text/html")
 
     def extractone(self, index):
         if index >= len(self.contents):
@@ -44,6 +43,7 @@ class InfoExtractor:
         iseof = rclexecm.RclExecM.noteof
         if self.currentindex >= len(self.contents) -1:
             iseof = rclexecm.RclExecM.eofnext
+        self.em.setmimetype("text/html")
         return (True, docdata, str(index), iseof)
 
     ###### File type handler api, used by rclexecm ---------->
@@ -195,41 +195,6 @@ class InfoSimpleSplitter:
  
 
 ##### Main program: either talk to the parent or execute test loop
-
+proto = rclexecm.RclExecM()
-e = rclexecm.RclExecM()
+extract = InfoExtractor(proto)
-info = InfoExtractor(e)
+rclexecm.main(proto, extract)
-
-if len(sys.argv) == 1:
-    e.mainloop(info)
-else:
-    # Got a file name parameter: TESTING without an execm parent
-    # Loop on all entries or get specific ipath
-    if not info.openfile({'filename:':sys.argv[1]}):
-        print "Open error"
-        sys.exit(1)
-    ipath = ""
-    if len(sys.argv) == 3:
-        ipath = sys.argv[2]
-
-    if ipath != "":
-        ok, data, ipath, eof = info.getipath({'ipath:':ipath})
-        if ok:
-            print "=========== ENTRY for IPATH %s =============" % (ipath)
-            print data
-            print
-        else:
-            print "Got error, eof %d"%eof
-        sys.exit(0)
-
-    ecnt = 0   
-    while 1:
-        ok, data, ipath, eof = info.getnext("")
-        if ok:
-            ecnt = ecnt + 1
-            print "=========== ENTRY %d IPATH %s =============" % (ecnt,ipath)
-#            print data
-            print
-        else:
-            print "Got error, eof %d"%eof
-            break
-    

src/filters/rclzip

@@ -48,5 +48,7 @@ class ZipExtractor:
             self.currentindex += 1
             return ret
 
-e = rclexecm.RclExecM()
+# Main program: create protocol handler and extractor and run them
-e.mainloop(ZipExtractor(e))
+proto = rclexecm.RclExecM()
+extract = ZipExtractor(proto)
+rclexecm.main(proto, extract)