page based index; download page; download file

1 files changed, 7 insertions, 5 deletions

diff --git a/index.py b/index.py
index 3758233..5a982a9 100644
--- a/index.py
+++ b/index.py
@@ -13,6 +13,7 @@ from threading import Thread, Condition
 schema = fields.Schema(
     title=fields.TEXT(stored=True),
     path=fields.ID(stored=True),
+    pagenumber=fields.NUMERIC(stored=True),
     content=fields.TEXT(stored=True),
     createtime=fields.NUMERIC() )
 
@@ -48,10 +49,11 @@ class PDFWorker(Thread):
                 print u"{0} processing {1}".format(self.name, filepath)
                 inputfile = pyPdf.PdfFileReader(file(filepath, 'r'))
                 title = inputfile.getDocumentInfo().title
-                content = u""
+                pagenumber = 0
                 for page in inputfile.pages:
-                    content += page.extractText()
-                documents.put( {"title":title, "path":filepath, "content":content, "createtime":time.time() } )
+                    pagenumber += 1
+                    content = page.extractText()
+                    documents.put( {"title":title, "path":filepath, "pagenumber":pagenumber, "content":content, "createtime":time.time() } )
             except Exception, e:
                 print u"{0} Exception: {1}".format(self.name, str(e))
             finally:
@@ -65,12 +67,12 @@ class IndexWorker(Thread):
                 doc = documents.get(True, 0.5)
             except Empty:
                 continue
-            print u"{0} adding     {1}".format(self.name, doc['path'])
+            print u"{0} adding     {1} page {2}".format(self.name, doc['path'], doc['pagenumber'])
             writer = index.writer()
             writer.add_document(**doc)
             writer.commit()
             documents.task_done()
-            print u"{0} added      {1}".format(self.name, doc['path'])
+            print u"{0} added      {1} page {2}".format(self.name, doc['path'], doc['pagenumber'])
 
 threads = map(lambda i: PDFWorker(), range(1))
 for thread in threads: