Package org.apache.tika.parser.microsoft

Examples of org.apache.tika.parser.microsoft.OfficeParser

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
            String name = tokenizer.nextToken();
            if (name.equals(
                    "org.apache.jackrabbit.extractor.HTMLTextExtractor")) {
                parsers.put(MediaType.text("html"), new HtmlParser());
            } else if (name.equals("org.apache.jackrabbit.extractor.MsExcelTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put(MediaType.application("vnd.ms-excel"), parser);
                parsers.put(MediaType.application("msexcel"), parser);
                parsers.put(MediaType.application("excel"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.MsOutlookTextExtractor")) {
                parsers.put(MediaType.application("vnd.ms-outlook"), new OfficeParser());
            } else if (name.equals("org.apache.jackrabbit.extractor.MsPowerPointExtractor")
                    || name.equals("org.apache.jackrabbit.extractor.MsPowerPointTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put(MediaType.application("vnd.ms-powerpoint"), parser);
                parsers.put(MediaType.application("mspowerpoint"), parser);
                parsers.put(MediaType.application("powerpoint"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.MsWordTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put(MediaType.application("vnd.ms-word"), parser);
                parsers.put(MediaType.application("msword"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.MsTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put(MediaType.application("vnd.ms-word"), parser);
                parsers.put(MediaType.application("msword"), parser);
                parsers.put(MediaType.application("vnd.ms-powerpoint"), parser);
                parsers.put(MediaType.application("mspowerpoint"), parser);
                parsers.put(MediaType.application("vnd.ms-excel"), parser);
                parsers.put(MediaType.application("vnd.openxmlformats-officedocument.wordprocessingml.document"), parser);
                parsers.put(MediaType.application("vnd.openxmlformats-officedocument.presentationml.presentation"), parser);
                parsers.put(MediaType.application("vnd.openxmlformats-officedocument.spreadsheetml.sheet"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.OpenOfficeTextExtractor")) {
                Parser parser = new OpenDocumentParser();
                parsers.put(MediaType.application("vnd.oasis.opendocument.database"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.formula"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.graphics"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.presentation"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.spreadsheet"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.text"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.calc"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.draw"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.impress"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.writer"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put(MediaType.application("pdf"), new PDFParser());
            } else if (name.equals("org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put(MediaType.TEXT_PLAIN, new TXTParser());
            } else if (name.equals("org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                parsers.put(MediaType.image("png"), parser);
                parsers.put(MediaType.image("apng"), parser);
                parsers.put(MediaType.image("mng"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put(MediaType.application("rtf"), parser);
                parsers.put(MediaType.text("rtf"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put(MediaType.APPLICATION_XML, parser);
                parsers.put(MediaType.text("xml"), parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
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
            if (name.equals(
                    "org.apache.jackrabbit.extractor.HTMLTextExtractor")) {
                parsers.put("text/html", new HtmlParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsExcelTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-excel", parser);
                parsers.put("application/msexcel", parser);
                parsers.put("application/excel", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsOutlookTextExtractor")) {
                parsers.put("application/vnd.ms-outlook", new OfficeParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsPowerPointExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-powerpoint", parser);
                parsers.put("application/mspowerpoint", parser);
                parsers.put("application/powerpoint", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsWordTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-word", parser);
                parsers.put("application/msword", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-word", parser);
                parsers.put("application/msword", parser);
                parsers.put("application/vnd.ms-powerpoint", parser);
                parsers.put("application/mspowerpoint", parser);
                parsers.put("application/vnd.ms-excel", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.wordprocessingml.document", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.presentationml.presentation", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.OpenOfficeTextExtractor")) {
                Parser parser = new OpenOfficeParser();
                parsers.put("application/vnd.oasis.opendocument.database", parser);
                parsers.put("application/vnd.oasis.opendocument.formula", parser);
                parsers.put("application/vnd.oasis.opendocument.graphics", parser);
                parsers.put("application/vnd.oasis.opendocument.presentation", parser);
                parsers.put("application/vnd.oasis.opendocument.spreadsheet", parser);
                parsers.put("application/vnd.oasis.opendocument.text", parser);
                parsers.put("application/vnd.sun.xml.calc", parser);
                parsers.put("application/vnd.sun.xml.draw", parser);
                parsers.put("application/vnd.sun.xml.impress", parser);
                parsers.put("application/vnd.sun.xml.writer", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put("application/pdf", new PDFParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put("text/plain", new TXTParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);
                parsers.put("image/mng", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
176
177
178
179
180
181
182
183
184
185
186
    private static void initialize() {
        // No particular parsing context is needed
        ParseContext parseContext = new ParseContext();

        // MS Office Binary File Format
        addConverter( new OfficeParser().getSupportedTypes( parseContext ),
                MSOfficeBinaryConverter.class );

        // Rich Text Format
        addConverter( new RTFParser().getSupportedTypes( parseContext ), RTFConverter.class );
View Full Code Here
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
            if (name.equals(
                    "org.apache.jackrabbit.extractor.HTMLTextExtractor")) {
                parsers.put("text/html", new HtmlParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsExcelTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-excel", parser);
                parsers.put("application/msexcel", parser);
                parsers.put("application/excel", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsOutlookTextExtractor")) {
                parsers.put("application/vnd.ms-outlook", new OfficeParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsPowerPointExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-powerpoint", parser);
                parsers.put("application/mspowerpoint", parser);
                parsers.put("application/powerpoint", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsWordTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-word", parser);
                parsers.put("application/msword", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-word", parser);
                parsers.put("application/msword", parser);
                parsers.put("application/vnd.ms-powerpoint", parser);
                parsers.put("application/mspowerpoint", parser);
                parsers.put("application/vnd.ms-excel", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.wordprocessingml.document", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.presentationml.presentation", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.OpenOfficeTextExtractor")) {
                Parser parser = new OpenDocumentParser();
                parsers.put("application/vnd.oasis.opendocument.database", parser);
                parsers.put("application/vnd.oasis.opendocument.formula", parser);
                parsers.put("application/vnd.oasis.opendocument.graphics", parser);
                parsers.put("application/vnd.oasis.opendocument.presentation", parser);
                parsers.put("application/vnd.oasis.opendocument.spreadsheet", parser);
                parsers.put("application/vnd.oasis.opendocument.text", parser);
                parsers.put("application/vnd.sun.xml.calc", parser);
                parsers.put("application/vnd.sun.xml.draw", parser);
                parsers.put("application/vnd.sun.xml.impress", parser);
                parsers.put("application/vnd.sun.xml.writer", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put("application/pdf", new PDFParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put("text/plain", new TXTParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);
                parsers.put("image/mng", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
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
            if (name.equals(
                    "org.apache.jackrabbit.extractor.HTMLTextExtractor")) {
                parsers.put("text/html", new HtmlParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsExcelTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-excel", parser);
                parsers.put("application/msexcel", parser);
                parsers.put("application/excel", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsOutlookTextExtractor")) {
                parsers.put("application/vnd.ms-outlook", new OfficeParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsPowerPointExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-powerpoint", parser);
                parsers.put("application/mspowerpoint", parser);
                parsers.put("application/powerpoint", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsWordTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-word", parser);
                parsers.put("application/msword", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.MsTextExtractor")) {
                Parser parser = new OfficeParser();
                parsers.put("application/vnd.ms-word", parser);
                parsers.put("application/msword", parser);
                parsers.put("application/vnd.ms-powerpoint", parser);
                parsers.put("application/mspowerpoint", parser);
                parsers.put("application/vnd.ms-excel", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.wordprocessingml.document", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.presentationml.presentation", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.OpenOfficeTextExtractor")) {
                Parser parser = new OpenDocumentParser();
                parsers.put("application/vnd.oasis.opendocument.database", parser);
                parsers.put("application/vnd.oasis.opendocument.formula", parser);
                parsers.put("application/vnd.oasis.opendocument.graphics", parser);
                parsers.put("application/vnd.oasis.opendocument.presentation", parser);
                parsers.put("application/vnd.oasis.opendocument.spreadsheet", parser);
                parsers.put("application/vnd.oasis.opendocument.text", parser);
                parsers.put("application/vnd.sun.xml.calc", parser);
                parsers.put("application/vnd.sun.xml.draw", parser);
                parsers.put("application/vnd.sun.xml.impress", parser);
                parsers.put("application/vnd.sun.xml.writer", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put("application/pdf", new PDFParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put("text/plain", new TXTParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);
                parsers.put("image/mng", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
458
459
460
461
462
463
464
465
466
467
468
469
470
    InputStream input;
    try {
      input = new FileInputStream(new File(f.fileName()));
      ContentHandler textHandler = new BodyContentHandler(-1);
      Metadata metadata = new Metadata();
      OfficeParser parser = new OfficeParser(); 
      ParseContext context = new ParseContext();
      parser.parse(input, textHandler, metadata, context);
      String[] result = textHandler.toString().split(regex);
      for (int i=0; i<result.length && keepRunning; i++) {
        if (interrupt) {
          processInterrupt();
        }
View Full Code Here
176
177
178
179
180
181
182
183
184
185
186
    private static void initialize() {
        // No particular parsing context is needed
        ParseContext parseContext = new ParseContext();

        // MS Office Binary File Format
        addConverter( new OfficeParser().getSupportedTypes( parseContext ),
                MSOfficeBinaryConverter.class );

        // Rich Text Format
        addConverter( new RTFParser().getSupportedTypes( parseContext ), RTFConverter.class );
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
        InputStream input = SolidworksParserTest.class.getResourceAsStream(
                "/test-documents/testsolidworksPart2013SP2.SLDPRT");
        try {
            ContentHandler handler = new BodyContentHandler();
            Metadata metadata = new Metadata();
            new OfficeParser().parse(input, handler, metadata, new ParseContext());

            //Check content type
            assertEquals("application/sldworks",metadata.get(Metadata.CONTENT_TYPE));
            
            //Check properties
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
        InputStream input = SolidworksParserTest.class.getResourceAsStream(
                "/test-documents/testsolidworksPart2014SP0.SLDPRT");
        try {
            ContentHandler handler = new BodyContentHandler();
            Metadata metadata = new Metadata();
            new OfficeParser().parse(input, handler, metadata, new ParseContext());

            //Check content type
            assertEquals("application/sldworks",metadata.get(Metadata.CONTENT_TYPE));
           
            //Check properties
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
        InputStream input = SolidworksParserTest.class.getResourceAsStream(
                "/test-documents/testsolidworksAssembly2013SP2.SLDASM");
        try {
            ContentHandler handler = new BodyContentHandler();
            Metadata metadata = new Metadata();
            new OfficeParser().parse(input, handler, metadata, new ParseContext());

            //Check content type
            assertEquals("application/sldworks",metadata.get(Metadata.CONTENT_TYPE));
           
            //Check properties
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.microsoft.OfficeParser

  • cx.fbn.nevernote.threads.IndexRunner
  • org.apache.jackrabbit.core.query.lucene.JackrabbitParser
  • org.apache.poi.hdgf.extractor.VisioTextExtractor
  • org.apache.poi.hpbf.extractor.PublisherTextExtractor
  • org.apache.poi.hpsf.CustomProperties
  • org.apache.poi.hpsf.DocumentSummaryInformation
  • org.apache.poi.hpsf.PropertySet
  • org.apache.poi.hpsf.SummaryInformation
  • org.apache.poi.hslf.extractor.PowerPointExtractor
  • org.apache.poi.hwpf.extractor.WordExtractor
    • 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.