Package org.apache.tika.parser

Examples of org.apache.tika.parser.Parser

82
83
84
85
86
87
88
89
90
91
92
      else
      {
         // tika-config may contain really big amount of mimetypes, but used only few,
         // so to avoid load in memory many copies of DocumentReader, we will register it
         // only if someone need it
         Parser tikaParser = conf.getParser(mimeType);
         if (tikaParser != null)
         {
            synchronized (this)
            {
               // Check if the reader has been registered since the thread is blocked
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
        Assert.assertFalse(parser.isActive());
    }
   
    @Test
    public void testTerminating() throws Exception {
        Parser parser = new DelayParser(false);
        InputStream is = Mockito.mock(InputStream.class);
        Metadata md = new Metadata();
       
        BaseContentExtractor contentExtractor = Mockito.mock(BaseContentExtractor.class);
        BaseLinkExtractor linkExtractor = Mockito.mock(BaseLinkExtractor.class);
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
    //<start id="tika"/>
    InputStream input = new FileInputStream(
            new File("src/test/resources/pdfBox-sample.pdf"));//<co id="tika.is"/>
    ContentHandler textHandler = new BodyContentHandler();//<co id="tika.handler"/>
    Metadata metadata = new Metadata();//<co id="tika.metadata"/>
    Parser parser = new AutoDetectParser();//<co id="tika.parser"/>
    ParseContext context = new ParseContext();
    parser.parse(input, textHandler, metadata, context);//<co id="tika.parse"/>
    System.out.println("Title: " + metadata.get(Metadata.TITLE));//<co id="tika.title"/>
    System.out.println("Body: " + textHandler.toString());//<co id="tika.body"/>
    /*
<calloutlist>
    <callout arearefs="tika.is"><para>Create the <classname>InputStream</classname> to read in the content</para></callout>
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
    InputStream input = new ByteArrayInputStream(html.getBytes(Charset.forName("UTF-8")));
    ContentHandler text = new BodyContentHandler();//<co id="html.text.co"/>
    LinkContentHandler links = new LinkContentHandler();//<co id="html.link.co"/>
    ContentHandler handler = new TeeContentHandler(links, text);//<co id="html.merge"/>
    Metadata metadata = new Metadata();//<co id="html.store"/>
    Parser parser = new HtmlParser();//<co id="html.parser"/>
    ParseContext context = new ParseContext();
    parser.parse(input, handler, metadata, context);//<co id="html.parse"/>
    System.out.println("Title: " + metadata.get(Metadata.TITLE));
    System.out.println("Body: " + text.toString());
    System.out.println("Links: " + links.getLinks());
    /*
    <calloutlist>
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
    public void testExcel() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testEXCEL.xlsx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testEXCEL.xlsx");
        ContentHandler handler = new BodyContentHandler();

        try {
            parser.parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Simple Excel document", metadata.get(Metadata.TITLE));
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
    public void testExcelFormats() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testEXCEL-formats.xlsx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testEXCEL-formats.xlsx");
        ContentHandler handler = new BodyContentHandler();

        try {
            parser.parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
    public void testPowerPoint() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testPPT.pptx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testPPT.pptx");
        ContentHandler handler = new BodyContentHandler();

        try {
            parser.parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Powerpoint Slide", metadata.get(Metadata.TITLE));
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
    public void testWord() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testWORD.docx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testWORD.docx");
        ContentHandler handler = new BodyContentHandler();

        try {
            parser.parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Word Document", metadata.get(Metadata.TITLE));
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
        File file = getTestFile("testPPT.ppt");
        String s1 = ParseUtils.getStringContent(file, tc);
        String s2 = ParseUtils.getStringContent(
                file, tc, "application/vnd.ms-powerpoint");
        assertEquals(s1, s2);
        Parser parser = tc.getParser("application/vnd.ms-powerpoint");
        Metadata metadata = new Metadata();
        InputStream stream = new FileInputStream(file);
        try {
            parser.parse(stream, new DefaultHandler(), metadata);
        } finally {
            stream.close();
        }
        assertEquals("Sample Powerpoint Slide", metadata.get(Metadata.TITLE));
    }
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
    public void testWORDxtraction() throws Exception {
        File file = getTestFile("testWORD.doc");
        String s1 = ParseUtils.getStringContent(file, tc);
        String s2 = ParseUtils.getStringContent(file, tc, "application/msword");
        assertEquals(s1, s2);
        Parser parser = tc.getParser("application/msword");
        Metadata metadata = new Metadata();
        InputStream stream = new FileInputStream(file);
        try {
            parser.parse(stream, new DefaultHandler(), metadata);
        } finally {
            stream.close();
        }
        assertEquals("Sample Word Document", metadata.get(Metadata.TITLE));
    }
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.Parser

  • bixo.parser.TikaCallableTest
  • com.baasbox.controllers.File
  • com.cloudera.cdk.morphline.solrcell.SolrCellBuilder$SolrCell
  • com.digitalpebble.behemoth.tika.TikaProcessor
  • com.findwise.hydra.stage.tika.SimpleFetchingTikaStageTest
  • com.ikanow.infinit.e.harvest.extraction.document.file.FileHarvester
  • com.ikanow.infinit.e.harvest.extraction.text.legacy.TextExtractorTika
  • com.nidhinova.tika.server.TikaService
  • com.tamingtext.tika.TikaTest
  • ipcress.Extraction
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.