1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
|
#!/usr/bin/python2.6
# coding: utf-8
import os
import json
from StringIO import StringIO
from whoosh.index import open_dir
from whoosh.qparser import QueryParser
import whoosh.searching as searching
import whoosh.fields as fields
import whoosh.analysis as analysis
import whoosh.highlight as highlight
import whoosh.query as query
import flask
import pyPdf
import werkzeug
import subprocess
app = flask.Flask("booksearch")
index_book = open_dir(u"index", u"book")
index_metadata = open_dir(u"index", u"metadata")
@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)
r = werkzeug.Response(open(document['path'], "r"), mimetype="application/pdf",)
r.headers.add('Content-Disposition', 'attachment',
filename=os.path.basename(document['path']))
return r
@app.route("/test")
def test():
input = pyPdf.PdfFileReader(file("test.pdf", 'r'))
page = input.getPage(0)
out = pyPdf.PdfFileWriter()
out.addPage(page)
pdffile = StringIO()
out.write(pdffile)
process = subprocess.Popen(["/usr/bin/convert", "pdf:-", "jpeg:-"], stdin=subprocess.PIPE, stdout=subprocess.PIPE)
outjpg = StringIO()
pdffile.seek(0)
while not process.stdin.closed:
print "."
stdout, stderr = process.communicate(pdffile.read())
if not stdout:
break
outjpg.write(stdout)
outjpg.seek(0)
r = werkzeug.Response(outjpg, mimetype="image/jpeg")
return r
@app.route("/download/page/<int:docnum>/<int:page>", methods=["GET"])
def do_download_page(docnum,page):
document = index.reader().stored_fields(docnum)
inputfile = pyPdf.PdfFileReader(file(document['path'], 'r'))
page = inputfile.getPage(page)
outbuf = StringIO()
outfile = pyPdf.PdfFileWriter()
outfile.addPage(page)
outfile.write(outbuf)
outbuf.seek(0)
r = werkzeug.Response(outbuf, mimetype="application/pdf")
client_filename = os.path.basename(document['path'])[:-3]
client_filename += u".Page-{0}".format(document['pagenumber'])
r.headers.add('Content-Disposition', 'attachment', filename=client_filename)
return r
class MyHtmlFormatter(highlight.HtmlFormatter):
def _format_fragment(self, text, fragment, seen):
text = unicode( flask.Markup.escape(text) )
return highlight.HtmlFormatter._format_fragment(self, text, fragment, seen)
@app.route("/json/excerpt/<int:docnum>/<path:term>", methods=["GET"])
def json_excerpt(docnum, term):
searcher = index.searcher()
def generator(q):
for result in searcher.search(q, limit=1, sortedby="pagenumber"):
terms = [ text for fieldname, text in q.all_terms()
if fieldname == "content" ]
excerpt = highlight.highlight(result.get("content"),
terms,
analysis.FancyAnalyzer(),
highlight.SimpleFragmenter(),
MyHtmlFormatter())
yield json.dumps( { 'pagenumber':result.get("pagenumber"),
'excerpt':excerpt,
'docnum':result.docnum} )
document = searcher.reader().stored_fields(docnum)
q = QueryParser("content").parse(term)
q = query.And([ q, query.Term("path", document['path']) ] )
return werkzeug.Response( generator(q) )
@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)
facets = searching.Facets.from_field(searcher, "path")
results = searcher.search(query, limit=None, sortedby="path")
categories = {}
for key, value in facets.categorize(results).items():
categories[key] = map(lambda v: v[0], value)
return flask.jsonify(categories)
"""
terms = [text for fieldname, text in query.all_terms()
if fieldname == "content"]
matches = []
for result in results:
title = result.get("title")
path = result.get("path")
excerpt = highlight.highlight(result.get("content"),
terms,
analysis.StandardAnalyzer(),
highlight.SimpleFragmenter(),
MyHtmlFormatter())
matches.append( {'path':result.get('path'),
'excerpt':excerpt,
'docnum':result.docnum,
'pagenumber':result.get('pagenumber'),
'title':title })
match_groups = {}
for match in matches:
print match
if not match_groups.has_key(match['path']):
match_groups[match['path']] = { 'matches':[],
'title' : match['title'],
'first_docnum' : match['docnum'],
'filename':os.path.basename(match['path']) }
match_groups[ match['path'] ]['matches'].append(
{ 'excerpt':match['excerpt'],
'docnum':match['docnum'],
'pagenumber':match['pagenumber'] })
objects = match_groups.values()[skip:skip+5]
return flask.render_template('search.html',
match_groups=objects, term=term, skip=skip, resultlen=len(results))
"""
if __name__ == "__main__":
app.debug = True
app.run(host="0.0.0.0")
|
