Package org.apache.tika.sax

Examples of org.apache.tika.sax.XHTMLContentHandler.element()

84
85
86
87
88
89
90
91
92
93
94
            } else {
                xhtml.element("p", tag.getAlbum());
            }
            xhtml.element("p", tag.getYear());
            xhtml.element("p", tag.getComment());
            xhtml.element("p", tag.getGenre());
        }
        if (audioAndTags.audio != null) {
            metadata.set("samplerate", String.valueOf(audioAndTags.audio.getSampleRate()));
            metadata.set("channels", String.valueOf(audioAndTags.audio.getChannels()));
            metadata.set("version", audioAndTags.audio.getVersion());
View Full Code Here
151
152
153
154
155
156
157
158
159
160
161
                    }

                    xhtml.characters(curLine);

                    // For plain text email, each line is a real break position.
                    xhtml.element("br", "");
                }
            }
        }

        if (parseState == ParseStates.IN_HEADER) {
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
                xhtml.startElement("div", "class", "package-entry");
                Metadata entrydata = new Metadata();
                String name = entry.getName();
                if (name != null && name.length() > 0) {
                    entrydata.set(Metadata.RESOURCE_NAME_KEY, name);
                    xhtml.element("h1", name);
                }
                try {
                    // Use the delegate parser to parse this entry
                    super.parse(
                            new CloseShieldInputStream(archive),
View Full Code Here
140
141
142
143
144
145
146
147
148
149
150
                    }

                    xhtml.characters(curLine);

                    // For plain text email, each line is a real break position.
                    xhtml.element("br", "");
                }
            }
        }

        if (parseState == ParseStates.IN_HEADER) {
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
                WordExtractor extractor = new WordExtractor(filesystem);

                addTextIfAny(xhtml, "header", extractor.getHeaderText());

                for (String paragraph : extractor.getParagraphText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getFootnoteText()) {
                    xhtml.element("p", paragraph);
                }
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
                for (String paragraph : extractor.getParagraphText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getFootnoteText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getCommentsText()) {
                    xhtml.element("p", paragraph);
                }
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
                for (String paragraph : extractor.getFootnoteText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getCommentsText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getEndnoteText()) {
                    xhtml.element("p", paragraph);
                }
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
                for (String paragraph : extractor.getCommentsText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getEndnoteText()) {
                    xhtml.element("p", paragraph);
                }

                addTextIfAny(xhtml, "footer", extractor.getFooterText());
            } else if ("PowerPoint Document".equals(name)) {
                setType(metadata, "application/vnd.ms-powerpoint");
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
                addTextIfAny(xhtml, "footer", extractor.getFooterText());
            } else if ("PowerPoint Document".equals(name)) {
                setType(metadata, "application/vnd.ms-powerpoint");
                PowerPointExtractor extractor =
                    new PowerPointExtractor(filesystem);
                xhtml.element("p", extractor.getText(true, true));
            } else if ("Workbook".equals(name)) {
                setType(metadata, "application/vnd.ms-excel");
                new ExcelExtractor().parse(filesystem, xhtml);
            } else if ("VisioDocument".equals(name)) {
                setType(metadata, "application/vnd.visio");
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
            } else if ("VisioDocument".equals(name)) {
                setType(metadata, "application/vnd.visio");
                VisioTextExtractor extractor =
                    new VisioTextExtractor(filesystem);
                for (String text : extractor.getAllText()) {
                    xhtml.element("p", text);
                }
            } else if (!outlookExtracted && name.startsWith("__substg1.0_")) {
                // TODO: Cleaner mechanism for detecting Outlook
                outlookExtracted = true;
                setType(metadata, "application/vnd.ms-outlook");
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.