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
|
//
// FilterPdf.cs: Very simplistic PDF filter
//
// Author:
// Christopher Orr <dashboard@protactin.co.uk>
//
// Copyright 2004 by Christopher Orr
//
using System;
using System.IO;
using System.Diagnostics;
using Beagle.Util;
using Beagle.Daemon;
namespace Beagle.Filters {
public class FilterPdf : Beagle.Daemon.Filter {
public FilterPdf ()
{
AddSupportedFlavor (FilterFlavor.NewFromMimeType ("application/pdf"));
SnippetMode = true;
}
// FIXME: we should have a reasonable failure mode if pdftotext is
// not installed.
protected override void DoPullProperties ()
{
// create new external process
SafeProcess pc = new SafeProcess ();
pc.Arguments = new string [] { "pdfinfo", FileInfo.FullName };
pc.RedirectStandardOutput = true;
pc.RedirectStandardError = true;
try {
pc.Start ();
} catch (SafeProcessException e) {
Log.Warn (e.Message);
Error ();
return;
}
// add pdfinfo's output to pool
StreamReader pout = new StreamReader (pc.StandardOutput);
string str = null;
string[] tokens = null;
string strMetaTag = null;
bool bKeyword = false;
while ((str = pout.ReadLine ()) != null) {
bKeyword = false;
strMetaTag = null;
tokens = str.Split (':');
if (tokens.Length > 1) {
switch (tokens[0]) {
case "Title":
strMetaTag = "dc:title";
break;
case "Author":
strMetaTag = "dc:author";
break;
case "Pages":
strMetaTag = "fixme:page-count";
bKeyword = true;
break;
case "Creator":
strMetaTag = "dc:creator";
break;
case "Producer":
strMetaTag = "dc:appname";
break;
}
if (strMetaTag != null) {
if (bKeyword)
AddProperty (Beagle.Property.NewUnsearched (strMetaTag,
tokens[1].Trim()));
else
AddProperty (Beagle.Property.New (strMetaTag,
tokens[1].Trim()));
}
}
}
pout.Close ();
// Log any errors or warnings from stderr
pout = new StreamReader (pc.StandardError);
while ((str = pout.ReadLine ()) != null)
Log.Warn ("pdfinfo [{0}]: {1}", Uri, str);
pout.Close ();
pc.Close ();
}
protected override void DoPull ()
{
// create new external process
SafeProcess pc = new SafeProcess ();
pc.Arguments = new string [] { "pdftotext", "-q", "-nopgbrk", "-enc", "UTF-8", FileInfo.FullName, "-" };
pc.RedirectStandardOutput = true;
pc.RedirectStandardError = true;
try {
pc.Start ();
} catch (SafeProcessException e) {
Log.Warn (e.Message);
Error ();
return;
}
// add pdftotext's output to pool
StreamReader pout = new StreamReader (pc.StandardOutput);
// FIXME: I don't think this is really required
// Line by line parsing, however, we have to make
// sure, that "pdftotext" doesn't output any "New-lines".
string str;
while ((str = pout.ReadLine()) != null) {
AppendText (str);
AppendStructuralBreak ();
if (! AllowMoreWords ())
break;
}
pout.Close ();
pout = new StreamReader (pc.StandardError);
while ((str = pout.ReadLine ()) != null)
Log.Warn ("pdftotext [{0}]: {1}", Uri, str);
pout.Close ();
pc.Close ();
Finished ();
}
}
}
|
