File: indexwritertester.cpp

package info (click to toggle)
strigi 0.7.2-1
  • links: PTS, VCS
  • area: main
  • in suites: squeeze
  • size: 6,808 kB
  • ctags: 7,071
  • sloc: cpp: 44,468; ansic: 9,764; perl: 515; java: 367; python: 345; xml: 316; yacc: 176; sh: 153; makefile: 38
file content (187 lines) | stat: -rw-r--r-- 6,475 bytes parent folder | download
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
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
/* This file is part of Strigi Desktop Search
 *
 * Copyright (C) 2007 Flavio Castelli <flavio.castelli@gmail.com>
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Library General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Library General Public License for more details.
 *
 * You should have received a copy of the GNU Library General Public License
 * along with this library; see the file COPYING.LIB.  If not, write to
 * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
 * Boston, MA 02110-1301, USA.
 */
#include "indexwritertester.h"

#include "analysisresult.h"
#include "indexwriter.h"
#include "indexreader.h"
#include "fieldtypes.h"
#include "query.h"
#include "queryparser.h"

#include <sstream>

using namespace std;
using namespace strigiunittest;
using namespace Strigi;

void
IndexWriterTest::setUp() {
    IndexTest::setUp();
    m_streamAnalyzer = new StreamAnalyzer( m_analyzerConfiguration );
}

void
IndexWriterTest::tearDown() {
    delete m_streamAnalyzer;
    IndexTest::tearDown();
}

void
IndexWriterTest::testAddText() {
    // make sure the index is empty
    CPPUNIT_ASSERT_EQUAL( 0, m_reader->countDocuments() );

    // test adding very simple text
    string path( "/tmp/dummy.txt" );
    {
        Strigi::AnalysisResult result( path, 1, *m_writer, *m_streamAnalyzer );
        std::string text( "Some dummy text for testing." );
        m_writer->addText( &result, text.c_str(), (int32_t)text.length() );
    }
    m_writer->commit();
    // at this point the new document is most likely not yet visible
    // for query() calls, the reader is not forcibly refreshed
    // it *is* refreshed for calls to countDocuments(), so we call that
    CPPUNIT_ASSERT_EQUAL( 1, m_reader->countDocuments() );

    std::vector<IndexedDocument> results = m_reader->query(
        QueryParser::buildQuery("dummy"), 0, 100 );
    CPPUNIT_ASSERT_EQUAL_MESSAGE( "got invalid number of results", 1,
        (int)results.size() );
    CPPUNIT_ASSERT_EQUAL_MESSAGE( "got invalid path result", path,
        results[0].uri );

    m_writer->deleteAllEntries();

    // FIXME: test adding unicode text

}

void
IndexWriterTest::testDeleteAllEntries() {
    // make sure the index is empty
    CPPUNIT_ASSERT_EQUAL( 0, m_reader->countDocuments() );

    // add some random data
    string path( "/tmp/dummy.txt" );
    {
        Strigi::AnalysisResult result( path, 1, *m_writer, *m_streamAnalyzer );
        m_writer->addValue( &result, m_fieldRegister.pathField, path );
        string filename( "dummy.txt" );
        m_writer->addValue( &result, m_fieldRegister.filenameField, filename );
    }
    m_writer->commit();
    m_writer->deleteAllEntries();
    CPPUNIT_ASSERT_EQUAL( 0, m_reader->countDocuments() );

    // now make sure nothing is left
    std::map<std::string, time_t> children;
    m_reader->getChildren( std::string(), children );
    CPPUNIT_ASSERT_MESSAGE( "Still files left after calling deleteAllEntries.",
        children.empty() );

    std::vector<IndexedDocument> results = m_reader->query(
        QueryParser::buildQuery(
            FieldRegister::pathFieldName + "=\"" + path + "\"" ), 0, 100 );
    CPPUNIT_ASSERT_MESSAGE( "Query results not empty after deleteAllEntries",
       results.empty() );

    results = m_reader->query( QueryParser::buildQuery(
        FieldRegister::filenameFieldName + "=\"dummy.txt\"" ), 0, 100 );
    CPPUNIT_ASSERT_MESSAGE( "Query results not empty after deleteAllEntries",
        results.empty() );
}

void
IndexWriterTest::testDeleteEntries() {
    // make sure the index is empty
    CPPUNIT_ASSERT_EQUAL( 0, m_reader->countDocuments() );

    // add some random data
    string path1( "/tmp/dummy1.txt" );
    string path2( "/tmp/dummy2.txt" );
    string filename1( "dummy1.txt" );
    string filename2( "dummy2.txt" );
    {
        AnalysisResult anaRes1( path1, 1, *m_writer, *m_streamAnalyzer );
        AnalysisResult anaRes2( path2, 1, *m_writer, *m_streamAnalyzer );

        m_writer->addValue(&anaRes1, m_fieldRegister.pathField, anaRes1.path());
        m_writer->addValue(&anaRes1, m_fieldRegister.filenameField, filename1);

        m_writer->addValue(&anaRes2, m_fieldRegister.pathField, anaRes2.path());
        m_writer->addValue(&anaRes2, m_fieldRegister.filenameField, filename2 );
    }
    m_writer->commit();

    // now delete the first one
    std::vector<std::string> entries;
    entries.push_back( path1 );
    m_writer->deleteEntries( entries );
    m_writer->commit();

    // now make sure only the second one it left
    std::map<std::string, time_t> children;
    m_reader->getChildren( std::string(), children );
    CPPUNIT_ASSERT_EQUAL( 1, ( int )children.size() );
    CPPUNIT_ASSERT_EQUAL( path2, children.begin()->first );
}
void
IndexWriterTest::testDeleteNestedEntries() {
    // make sure the index is empty
    CPPUNIT_ASSERT_EQUAL( 0, m_reader->countDocuments() );

    // add some random data
    string path1( "/tmp/dummydir" );
    string path2( "/tmp/dummydir/dummydir2" );
    string path3( "/tmp/dummydir/dummydir2/d.txt" );
    {
        AnalysisResult anaRes1(path1, 1, *m_writer, *m_streamAnalyzer);
        {
            AnalysisResult anaRes2(path2, 1, *m_writer, *m_streamAnalyzer,
                path1);
            {
                AnalysisResult anaRes3(path3, 1, *m_writer, *m_streamAnalyzer,
                    path2);
            }
        }
    }
    m_writer->commit();
    // check that three documents are in the index
    CPPUNIT_ASSERT_EQUAL(3, m_reader->countDocuments());

    m_writer->commit();
    // check that three documents are in the index, even after committing twice
    CPPUNIT_ASSERT_EQUAL(3, m_reader->countDocuments());

    // check that three documents are in the index
    CPPUNIT_ASSERT_EQUAL(3, m_reader->countDocuments());

    // now delete the first one
    std::vector<std::string> entries;
    entries.push_back(path1);
    m_writer->deleteEntries(entries);
    m_writer->commit();
    m_reader->countDocuments();

    // now make sure none are left 
    CPPUNIT_ASSERT_EQUAL( 0, m_reader->countDocuments() );
}