Package org.apache.tika.sax

Examples of org.apache.tika.sax.EndDocumentShieldingContentHandler

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
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
      
        // As we don't know which of the metadata or the content
        //  we'll hit first, catch the endDocument call initially
        EndDocumentShieldingContentHandler handler =
          new EndDocumentShieldingContentHandler(baseHandler);
      
        // Process the file in turn
        ZipInputStream zip = new ZipInputStream(stream);
        ZipEntry entry = zip.getNextEntry();
        while (entry != null) {
            if (entry.getName().equals("mimetype")) {
                String type = IOUtils.toString(zip, "UTF-8");
                metadata.set(Metadata.CONTENT_TYPE, type);
            } else if (entry.getName().equals("meta.xml")) {
                meta.parse(zip, new DefaultHandler(), metadata, context);
            } else if (entry.getName().endsWith("content.xml")) {
                content.parse(zip, handler, metadata, context);
            }
            entry = zip.getNextEntry();
        }
       
        // Only now call the end document
        if(handler.getEndDocumentWasCalled()) {
           handler.reallyEndDocument();
        }
    }
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
                extractor = new POIXMLTextExtractorDecorator(context, poiExtractor);
            }
           
            // We need to get the content first, but not end
            //  the document just yet
            EndDocumentShieldingContentHandler handler =
               new EndDocumentShieldingContentHandler(baseHandler);
            extractor.getXHTML(handler, metadata, context);

            // Now we can get the metadata
            extractor.getMetadataExtractor().extract(metadata);
           
            // Then finish up
            handler.reallyEndDocument();
        } catch (IllegalArgumentException e) {
            if (e.getMessage().startsWith("No supported documents found")) {
                throw new TikaException(
                        "TIKA-418: RuntimeException while getting content"
                        + " for thmx and xps file types", e);
View Full Code Here
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
        // Prepare to handle the content
        XHTMLContentHandler xhtml = new XHTMLContentHandler(baseHandler, metadata);

        // As we don't know which of the metadata or the content
        //  we'll hit first, catch the endDocument call initially
        EndDocumentShieldingContentHandler handler =
          new EndDocumentShieldingContentHandler(xhtml);
       
        // If we can, process the metadata first, then the
        //  rest of the file afterwards
        // Only possible to guarantee that when opened from a file not a stream
        ZipEntry entry = null;
        if (zipFile != null) {
            entry = zipFile.getEntry(META_NAME);
            handleZipEntry(entry, zipFile.getInputStream(entry), metadata, context, handler);

            Enumeration<? extends ZipEntry> entries = zipFile.entries();
            while (entries.hasMoreElements()) {
                entry = entries.nextElement();
                if (! META_NAME.equals(entry.getName())) {
                    handleZipEntry(entry, zipFile.getInputStream(entry), metadata, context, handler);
                }
            }
            zipFile.close();
        } else {
            do {
                entry = zipStream.getNextEntry();
                handleZipEntry(entry, zipStream, metadata, context, handler);
            } while (entry != null);
            zipStream.close();
        }
       
        // Only now call the end document
        if(handler.getEndDocumentWasCalled()) {
           handler.reallyEndDocument();
        }
    }
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
                extractor = new POIXMLTextExtractorDecorator(context, poiExtractor);
            }
           
            // We need to get the content first, but not end
            //  the document just yet
            EndDocumentShieldingContentHandler handler =
               new EndDocumentShieldingContentHandler(baseHandler);
            extractor.getXHTML(handler, metadata, context);

            // Now we can get the metadata
            extractor.getMetadataExtractor().extract(metadata);
           
            // Then finish up
            handler.reallyEndDocument();
        } catch (IllegalArgumentException e) {
            if (e.getMessage().startsWith("No supported documents found")) {
                throw new TikaException(
                        "TIKA-418: RuntimeException while getting content"
                        + " for thmx and xps file types", e);
View Full Code Here
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
        XHTMLContentHandler xhtml = new XHTMLContentHandler(baseHandler, metadata);

        // As we don't know which of the metadata or the content
        //  we'll hit first, catch the endDocument call initially
        EndDocumentShieldingContentHandler handler =
          new EndDocumentShieldingContentHandler(xhtml);

        // Process the file in turn
        ZipInputStream zip = new ZipInputStream(stream);
        ZipEntry entry = zip.getNextEntry();
        while (entry != null) {
            if (entry.getName().equals("mimetype")) {
                String type = IOUtils.toString(zip, "UTF-8");
                metadata.set(Metadata.CONTENT_TYPE, type);
            } else if (entry.getName().equals("meta.xml")) {
                meta.parse(zip, new DefaultHandler(), metadata, context);
            } else if (entry.getName().endsWith("content.xml")) {
                if (content instanceof OpenDocumentContentParser) {
                    ((OpenDocumentContentParser) content).parseInternal(zip, handler, metadata, context);
                } else {
                    // Foreign content parser was set:
                    content.parse(zip, handler, metadata, context);
                }
            } else if (entry.getName().endsWith("styles.xml")) {
                if (content instanceof OpenDocumentContentParser) {
                    ((OpenDocumentContentParser) content).parseInternal(zip, handler, metadata, context);
                } else {
                    // Foreign content parser was set:
                    content.parse(zip, handler, metadata, context);
                }
            }
            entry = zip.getNextEntry();
        }
       
        // Only now call the end document
        if(handler.getEndDocumentWasCalled()) {
           handler.reallyEndDocument();
        }
    }
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
                extractor = new POIXMLTextExtractorDecorator(context, poiExtractor);
            }
           
            // We need to get the content first, but not end
            //  the document just yet
            EndDocumentShieldingContentHandler handler =
               new EndDocumentShieldingContentHandler(baseHandler);
            extractor.getXHTML(handler, metadata, context);

            // Now we can get the metadata
            extractor.getMetadataExtractor().extract(metadata);
           
            // Then finish up
            handler.reallyEndDocument();
        } catch (IllegalArgumentException e) {
            if (e.getMessage().startsWith("No supported documents found")) {
                throw new TikaException(
                        "TIKA-418: RuntimeException while getting content"
                        + " for thmx and xps file types", e);
View Full Code Here
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
        // Prepare to handle the content
        XHTMLContentHandler xhtml = new XHTMLContentHandler(baseHandler, metadata);

        // As we don't know which of the metadata or the content
        //  we'll hit first, catch the endDocument call initially
        EndDocumentShieldingContentHandler handler =
          new EndDocumentShieldingContentHandler(xhtml);
       
        // If we can, process the metadata first, then the
        //  rest of the file afterwards
        // Only possible to guarantee that when opened from a file not a stream
        ZipEntry entry = null;
        if (zipFile != null) {
            entry = zipFile.getEntry(META_NAME);
            handleZipEntry(entry, zipFile.getInputStream(entry), metadata, context, handler);

            Enumeration<? extends ZipEntry> entries = zipFile.entries();
            while (entries.hasMoreElements()) {
                entry = entries.nextElement();
                if (! META_NAME.equals(entry.getName())) {
                    handleZipEntry(entry, zipFile.getInputStream(entry), metadata, context, handler);
                }
            }
            zipFile.close();
        } else {
            do {
                entry = zipStream.getNextEntry();
                handleZipEntry(entry, zipStream, metadata, context, handler);
            } while (entry != null);
            zipStream.close();
        }
       
        // Only now call the end document
        if(handler.getEndDocumentWasCalled()) {
           handler.reallyEndDocument();
        }
    }
View Full Code Here
TOP

Related Classes of org.apache.tika.sax.EndDocumentShieldingContentHandler

  • org.apache.tika.parser.microsoft.ooxml.OOXMLExtractorFactory
  • org.apache.tika.parser.odf.OpenDocumentParser
    • 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.