From dac88861a9635504af3813f57c443040b7416163 Mon Sep 17 00:00:00 2001
From: yvesf <yvesf-git@xapek.org>
Date: Fri, 19 Nov 2010 23:31:30 +0100
Subject: threading

---
 quick.py | 51 ---------------------------------------------------
 1 file changed, 51 deletions(-)
 delete mode 100644 quick.py

(limited to 'quick.py')

diff --git a/quick.py b/quick.py
deleted file mode 100644
index 631460d..0000000
--- a/quick.py
+++ /dev/null
@@ -1,51 +0,0 @@
-#!/usr/bin/python2.6
-# coding: utf-8
-import os
-import sys
-import pyPdf
-from whoosh.index import create_in
-import whoosh.fields as fields
-import time
-
-schema = fields.Schema(
-    title=fields.TEXT(stored=True),
-    path=fields.ID(stored=True),
-    content=fields.TEXT(stored=True),
-    createtime=fields.NUMERIC() )
-
-index = create_in("index", schema, "books")
-writer = index.writer()
-
-
-# extract
-directory = u"/media/share/books/isbn"
-
-try:
-    for path, directories, files in os.walk(directory):
-        for filename in files:
-            if filename.endswith(".pdf"):
-                filepath = os.path.join(path, filename)
-                print u"Process {0}".format(filepath)
-                inputfile = pyPdf.PdfFileReader(file(filepath, 'r'))
-                title = inputfile.getDocumentInfo().title
-                content = u""
-                i=1
-                numpages = inputfile.getNumPages()
-                for page in inputfile.pages:
-                    sys.stdout.write("\rPage {0}/{1}".format(i, numpages))
-                    sys.stdout.flush()
-                    content += page.extractText()
-                    i+=1
-                print u""
-                writer.add_document(title=title, path=filepath, content=content, createtime=time.time())
-except KeyboardInterrupt:
-    writer.commit()
-
-from whoosh.qparser import QueryParser
-
-searcher = index.searcher()
-
-query = QueryParser("content").parse("world")
-
-results = searcher.search(query)
-print results
-- 
cgit v1.2.1