Package org.apache.tika.detect

Examples of org.apache.tika.detect.AutoDetectReader

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
  @Override
  public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
      throws IOException, SAXException, TikaException {

    AutoDetectReader reader = new AutoDetectReader(new CloseShieldInputStream(stream), metadata, context.get(ServiceLoader.class, LOADER));

    try {
      Charset charset = reader.getCharset();
      String mediaType = metadata.get(Metadata.CONTENT_TYPE);
      String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
      if (mediaType != null && name != null) {
        MediaType type = MediaType.parse(mediaType);
        metadata.set(Metadata.CONTENT_TYPE, type.toString());
        metadata.set(Metadata.CONTENT_ENCODING, charset.name());

        StringBuilder out = new StringBuilder();
        String line;
        int nbLines =  0;
        while ((line = reader.readLine()) != null) {
            out.append(line);
            String author = parserAuthor(line);
            if (author != null) {
              metadata.add(TikaCoreProperties.CREATOR, author);
            }
            nbLines ++;
        }
        metadata.set("LoC", String.valueOf(nbLines));

        Renderer renderer = getRenderer(type.toString());
        String codeAsHtml = renderer.highlight(name, out.toString(), charset.name(), false);
        char[] charArray = codeAsHtml.toCharArray();
        handler.startDocument();
        handler.characters(charArray, 0, charArray.length);
        handler.endDocument();
      }
    } finally {
      reader.close();
    }

  }
View Full Code Here
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
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        // Automatically detect the character encoding
        AutoDetectReader reader = new AutoDetectReader(
                new CloseShieldInputStream(stream), metadata,
                context.get(ServiceLoader.class, LOADER));
        try {
            Charset charset = reader.getCharset();
            String previous = metadata.get(Metadata.CONTENT_TYPE);
            if (previous == null || previous.startsWith("text/html")) {
                MediaType type = new MediaType(MediaType.TEXT_HTML, charset);
                metadata.set(Metadata.CONTENT_TYPE, type.toString());
            }
            // deprecated, see TIKA-431
            metadata.set(Metadata.CONTENT_ENCODING, charset.name());

            // Get the HTML mapper from the parse context
            HtmlMapper mapper =
                    context.get(HtmlMapper.class, new HtmlParserMapper());

            // Parse the HTML document
            org.ccil.cowan.tagsoup.Parser parser =
                    new org.ccil.cowan.tagsoup.Parser();

            // TIKA-528: Reuse share schema to avoid heavy instantiation
            parser.setProperty(
                    org.ccil.cowan.tagsoup.Parser.schemaProperty, HTML_SCHEMA);
            // TIKA-599: Shared schema is thread-safe only if bogons are ignored
            parser.setFeature(
                    org.ccil.cowan.tagsoup.Parser.ignoreBogonsFeature, true);

            parser.setContentHandler(new XHTMLDowngradeHandler(
                    new HtmlHandler(mapper, handler, metadata)));

            parser.parse(reader.asInputSource());
        } finally {
            reader.close();
        }
    }
View Full Code Here
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
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        // Automatically detect the character encoding
        AutoDetectReader reader = new AutoDetectReader(
                new CloseShieldInputStream(stream), metadata, LOADER);
        try {
            Charset charset = reader.getCharset();
            MediaType type = new MediaType(MediaType.TEXT_PLAIN, charset);
            metadata.set(Metadata.CONTENT_TYPE, type.toString());
            // deprecated, see TIKA-431
            metadata.set(Metadata.CONTENT_ENCODING, charset.name());

            XHTMLContentHandler xhtml =
                    new XHTMLContentHandler(handler, metadata);
            xhtml.startDocument();

            xhtml.startElement("p");
            char[] buffer = new char[4096];
            int n = reader.read(buffer);
            while (n != -1) {
                xhtml.characters(buffer, 0, n);
                n = reader.read(buffer);
            }
            xhtml.endElement("p");

            xhtml.endDocument();
        } finally {
            reader.close();
        }
    }
View Full Code Here
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
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        // Automatically detect the character encoding
        AutoDetectReader reader = new AutoDetectReader(
                new CloseShieldInputStream(stream), metadata, LOADER);
        try {
            Charset charset = reader.getCharset();
            String previous = metadata.get(Metadata.CONTENT_TYPE);
            if (previous == null || previous.startsWith("text/html")) {
                MediaType type = new MediaType(MediaType.TEXT_HTML, charset);
                metadata.set(Metadata.CONTENT_TYPE, type.toString());
            }
            // deprecated, see TIKA-431
            metadata.set(Metadata.CONTENT_ENCODING, charset.name());

            // Get the HTML mapper from the parse context
            HtmlMapper mapper =
                    context.get(HtmlMapper.class, new HtmlParserMapper());

            // Parse the HTML document
            org.ccil.cowan.tagsoup.Parser parser =
                    new org.ccil.cowan.tagsoup.Parser();

            // TIKA-528: Reuse share schema to avoid heavy instantiation
            parser.setProperty(
                    org.ccil.cowan.tagsoup.Parser.schemaProperty, HTML_SCHEMA);
            // TIKA-599: Shared schema is thread-safe only if bogons are ignored
            parser.setFeature(
                    org.ccil.cowan.tagsoup.Parser.ignoreBogonsFeature, true);

            parser.setContentHandler(new XHTMLDowngradeHandler(
                    new HtmlHandler(mapper, handler, metadata)));

            parser.parse(reader.asInputSource());
        } finally {
            reader.close();
        }
    }
View Full Code Here
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
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        // Automatically detect the character encoding
        AutoDetectReader reader = new AutoDetectReader(
                new CloseShieldInputStream(stream), metadata,
                context.get(ServiceLoader.class, LOADER));
        try {
            Charset charset = reader.getCharset();
            MediaType type = new MediaType(MediaType.TEXT_PLAIN, charset);
            metadata.set(Metadata.CONTENT_TYPE, type.toString());
            // deprecated, see TIKA-431
            metadata.set(Metadata.CONTENT_ENCODING, charset.name());

            XHTMLContentHandler xhtml =
                    new XHTMLContentHandler(handler, metadata);
            xhtml.startDocument();

            xhtml.startElement("p");
            char[] buffer = new char[4096];
            int n = reader.read(buffer);
            while (n != -1) {
                xhtml.characters(buffer, 0, n);
                n = reader.read(buffer);
            }
            xhtml.endElement("p");

            xhtml.endDocument();
        } finally {
            reader.close();
        }
    }
View Full Code Here
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
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        // Automatically detect the character encoding
        AutoDetectReader reader = new AutoDetectReader(
                new CloseShieldInputStream(stream), metadata,
                context.get(ServiceLoader.class, LOADER));
        try {
            Charset charset = reader.getCharset();
            String previous = metadata.get(Metadata.CONTENT_TYPE);
            if (previous == null || previous.startsWith("text/html")) {
                MediaType type = new MediaType(MediaType.TEXT_HTML, charset);
                metadata.set(Metadata.CONTENT_TYPE, type.toString());
            }
            // deprecated, see TIKA-431
            metadata.set(Metadata.CONTENT_ENCODING, charset.name());

            // Get the HTML mapper from the parse context
            HtmlMapper mapper =
                    context.get(HtmlMapper.class, new HtmlParserMapper());

            // Parse the HTML document
            org.ccil.cowan.tagsoup.Parser parser =
                    new org.ccil.cowan.tagsoup.Parser();

            // Use schema from context or default
            Schema schema = context.get(Schema.class, HTML_SCHEMA);

            // TIKA-528: Reuse share schema to avoid heavy instantiation
            parser.setProperty(
                    org.ccil.cowan.tagsoup.Parser.schemaProperty, schema);
            // TIKA-599: Shared schema is thread-safe only if bogons are ignored
            parser.setFeature(
                    org.ccil.cowan.tagsoup.Parser.ignoreBogonsFeature, true);

            parser.setContentHandler(new XHTMLDowngradeHandler(
                    new HtmlHandler(mapper, handler, metadata)));

            parser.parse(reader.asInputSource());
        } finally {
            reader.close();
        }
    }
View Full Code Here
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
  @Override
  public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
      throws IOException, SAXException, TikaException {

    AutoDetectReader reader = new AutoDetectReader(new CloseShieldInputStream(stream), metadata, context.get(ServiceLoader.class, LOADER));

    try {
      Charset charset = reader.getCharset();
      String mediaType = metadata.get(Metadata.CONTENT_TYPE);
      String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
      if (mediaType != null && name != null) {
        MediaType type = MediaType.parse(mediaType);
        metadata.set(Metadata.CONTENT_TYPE, type.toString());
        metadata.set(Metadata.CONTENT_ENCODING, charset.name());

        StringBuilder out = new StringBuilder();
        String line;
        int nbLines =  0;
        while ((line = reader.readLine()) != null) {
            out.append(line + System.getProperty("line.separator"));
            String author = parserAuthor(line);
            if (author != null) {
              metadata.add(TikaCoreProperties.CREATOR, author);
            }
            nbLines ++;
        }
        metadata.set("LoC", String.valueOf(nbLines));
        Renderer renderer = getRenderer(type.toString());
       
        String codeAsHtml = renderer.highlight(name, out.toString(), charset.name(), false);
       
        Schema schema = context.get(Schema.class, HTML_SCHEMA);

        org.ccil.cowan.tagsoup.Parser parser = new org.ccil.cowan.tagsoup.Parser();
        parser.setProperty(org.ccil.cowan.tagsoup.Parser.schemaProperty, schema);
        parser.setContentHandler(handler);
        parser.parse(new InputSource(new StringReader(codeAsHtml)));
      }
    } finally {
      reader.close();
    }

  }
View Full Code Here
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
        // Only outputting the MIME type as metadata
        metadata.set(Metadata.CONTENT_TYPE, ENVI_MIME_TYPE);

        // The following code was taken from the TXTParser
        // Automatically detect the character encoding
        AutoDetectReader reader = new AutoDetectReader(
                new CloseShieldInputStream(stream), metadata);

        try {
            Charset charset = reader.getCharset();
            MediaType type = new MediaType(MediaType.TEXT_PLAIN, charset);
            // deprecated, see TIKA-431
            metadata.set(Metadata.CONTENT_ENCODING, charset.name());

            XHTMLContentHandler xhtml = new XHTMLContentHandler(handler,
                    metadata);

            xhtml.startDocument();

            // text contents of the xhtml
            String line;
            while ((line = reader.readLine()) != null) {
                xhtml.startElement("p");
                xhtml.characters(line);
                xhtml.endElement("p");
            }
           
            xhtml.endDocument();
        } finally {
            reader.close();
        }
    }
View Full Code Here
TOP

Related Classes of org.apache.tika.detect.AutoDetectReader

  • org.apache.tika.metadata.Metadata
  • org.apache.tika.mime.MediaType
  • org.apache.tika.parser.code.SourceCodeParser
  • org.apache.tika.parser.envi.EnviHeaderParser
  • org.apache.tika.parser.html.HtmlParser
  • org.apache.tika.parser.txt.TXTParser
  • org.xml.sax.InputSource
  • java.io.InputStreamReader
  • org.apache.tika.exception.TikaException
  • java.nio.charset.Charset
    • 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.