From 966a17b12c9deab35ef0a804d9fa1faea9c8042d Mon Sep 17 00:00:00 2001
From: yvesf <yvesf-git@xapek.org>
Date: Sat, 20 Nov 2010 01:58:53 +0100
Subject: page based index; download page; download file

---
 web.py | 46 ++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 38 insertions(+), 8 deletions(-)

(limited to 'web.py')

diff --git a/web.py b/web.py
index 429c516..b747010 100644
--- a/web.py
+++ b/web.py
@@ -7,16 +7,45 @@ import whoosh.analysis as analysis
 from whoosh import highlight
 import flask
 from flask import Flask
-
+import pyPdf
+from StringIO import StringIO
+import werkzeug
 app = Flask("booksearch")
 
 index = open_dir(u"index", mapped=False)
 searcher = index.searcher()
 
+@app.route("/")
+def do_index():
+    return flask.redirect(flask.url_for("do_search",term=""))
+
+@app.route("/download/file/<int:docnum>")
+def do_download_file(docnum):
+   document = index.reader().stored_fields(docnum)
+   filepath = document['path']
+   return werkzeug.Response(open(filepath, "r"), mimetype="application/pdf")
+
+@app.route("/download/page/<int:docnum>", methods=["GET"])
+def do_download_page(docnum):
+   document = index.reader().stored_fields(docnum)
+   filepath = document['path']
+   pagenumber = document['pagenumber']
+   inputfile = pyPdf.PdfFileReader(file(filepath, 'r'))
+   page = inputfile.getPage(pagenumber)
+   outbuf = StringIO()
+   outfile = pyPdf.PdfFileWriter()
+   outfile.addPage(page)
+   outfile.write(outbuf)
+   outbuf.seek(0)
+   return werkzeug.Response(outbuf, mimetype="application/pdf")
 
 @app.route("/search/skip=<int:skip>/<path:term>",methods=["GET"])
 @app.route("/search/<path:term>",methods=["GET"])
+@app.route("/search/", methods=["GET"])
 def do_search(skip=0,term=None):
+    if skip == 0 and not term:
+        return flask.render_template('search.html', objects=[], term="", skip=0)
+
     query = QueryParser("content").parse(term)
     results = searcher.search(query, limit=skip+5)
 
@@ -26,14 +55,15 @@ def do_search(skip=0,term=None):
     for result in results[skip:skip+5]:
         title = result.get("title")
         path = result.get("path")
-#        high = highlight.highlight(result.get("content"), 
-#            terms, 
-#            analysis.StandardAnalyzer(),
-#            highlight.SimpleFragmenter(),
-#            highlight.HtmlFormatter())
-        objects.append({ 'title' : title, 'path' : path, 'excerpt' : 'TODO' })
-    return flask.render_template('search.html', objects=objects, term=term, skip=skip)
+        print path
+        high = highlight.highlight(result.get("content"), 
+            terms, 
+            analysis.StandardAnalyzer(),
+            highlight.SimpleFragmenter(),
+            highlight.HtmlFormatter())
+        objects.append({ 'title' : title, 'path' : path, 'excerpt' : high, 'docnum':result.docnum })
 
+    return flask.render_template('search.html', objects=objects, term=term, skip=skip)
 
 if __name__ == "__main__":
     app.debug = True
-- 
cgit v1.2.1