Package org.apache.tika.exception

Examples of org.apache.tika.exception.TikaException

216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
                    EncryptionInfo info = new EncryptionInfo(filesystem);
                    Decryptor d = new Decryptor(info);

                    try {
                        if (!d.verifyPassword(Decryptor.DEFAULT_PASSWORD)) {
                            throw new TikaException("Unable to process: document is encrypted");
                        }

                        OOXMLParser parser = new OOXMLParser();

                        parser.parse(d.getDataStream(filesystem), new EmbeddedContentHandler(
                                        new BodyContentHandler(xhtml)),
                                        metadata, context);
                    } catch (GeneralSecurityException ex) {
                        throw new TikaException("Unable to process encrypted document", ex);
                    }
            }
        }

        xhtml.endDocument();
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
                parse(new DocumentSummaryInformation(properties));
            }
        } catch (FileNotFoundException e) {
            // entry does not exist, just skip it
        } catch (NoPropertySetStreamException e) {
            throw new TikaException("Not a HPSF document", e);
        } catch (UnexpectedPropertySetTypeException e) {
            throw new TikaException("Unexpected HPSF document", e);
        } catch (MarkUnsupportedException e) {
            throw new TikaException("Invalid DocumentInputStream", e);
        }
    }
View Full Code Here
39
40
41
42
43
44
45
46
        super(context);
       
        try {
            this.msg = new MAPIMessage(filesystem);
        } catch (IOException e) {
            throw new TikaException("Failed to parse Outlook message", e);
        }
    }
View Full Code Here
139
140
141
142
143
144
145
146
               xhtml.endElement("div");
              
           }
        } catch(ChunkNotFoundException e) {
           throw new TikaException("POI MAPIMessage broken - didn't return null on missing chunk", e);
        }
    }
View Full Code Here
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
            }
        }

        String encoding = metadata.get(Metadata.CONTENT_ENCODING);
        if (encoding == null) {
            throw new TikaException(
                    "Text encoding could not be detected and no encoding"
                    + " hint is available in document metadata");
        }

        // TIKA-341: Only stomp on content-type after we're done trying to
        // use it to guess at the charset.
        metadata.set(Metadata.CONTENT_TYPE, "text/plain");

        try {
            Reader reader =
                new BufferedReader(new InputStreamReader(stream, encoding));

            // TIKA-240: Drop the BOM when extracting plain text
            reader.mark(1);
            int bom = reader.read();
            if (bom != '\ufeff') { // zero-width no-break space
                reader.reset();
            }

            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();
        } catch (UnsupportedEncodingException e) {
            throw new TikaException(
                    "Unsupported text encoding: " + encoding, e);
        }
    }
View Full Code Here
55
56
57
58
59
60
61
62
        try {
            com.drew.metadata.Metadata tiffMetadata =
                TiffMetadataReader.readMetadata(stream);
            parse(tiffMetadata);
        } catch (TiffProcessingException e) {
            throw new TikaException("Can't read TIFF metadata", e);
        }
    }
View Full Code Here
66
67
68
69
70
71
72
73
       try {
          com.drew.metadata.Metadata jpegMetadata =
             JpegMetadataReader.readMetadata(stream);
          parse(jpegMetadata);
       } catch (JpegProcessingException e) {
          throw new TikaException("Can't read JPEG metadata", e);
       }
    }
View Full Code Here
86
87
88
89
90
91
92
93
                handleCommonImageTags(metadata, tag, directory);
             }
             handleGeoImageTags(metadata);
          }
       } catch (MetadataException e) {
          throw new TikaException("Can't read TIFF/JPEG metadata", e);
       }
    }
View Full Code Here
335
336
337
338
339
340
341
342
            parser.parse(
                    new CloseShieldInputStream(stream),
                    new OfflineContentHandler(
                            new NSNormalizerContentHandler(dh)));
        } catch (ParserConfigurationException e) {
            throw new TikaException("XML parser configuration error", e);
        }
    }
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
                //  specific namespace into the general Tika one
                setIfPresent(metadata, "CommentExtensions CommentExtension", Metadata.COMMENTS);
                setIfPresent(metadata, "markerSequence com", Metadata.COMMENTS);
                setIfPresent(metadata, "Data BitsPerSample", Metadata.BITS_PER_SAMPLE);
            } catch (IIOException e) {
                throw new TikaException(type + " parse error", e);
            }
        }

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
View Full Code Here
TOP

Related Classes of org.apache.tika.exception.TikaException

  • de.innosystec.unrar.tika.RARParser
  • org.apache.jackrabbit.core.query.lucene.JackrabbitParser
  • org.apache.jackrabbit.core.query.pdf.PDF2XHTML
  • org.apache.nutch.parse.tika.TikaConfig
  • org.apache.tika.config.TikaConfig
  • org.apache.tika.detect.AutoDetectReader
  • org.apache.tika.embedder.ExternalEmbedder
  • org.apache.tika.extractor.ParserContainerExtractor
  • org.apache.tika.fork.ForkClient
  • org.apache.tika.fork.ForkParser
    • 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.