Package org.apache.tika.parser.txt

Examples of org.apache.tika.parser.txt.CharsetDetector

33
34
35
36
37
38
39
40
41
42
43
* @version $Id$
*/
public class TikaEncodingDetector implements EncodingDetector {

    public String guessEncoding(InputStream is) throws IOException {
        CharsetDetector charsetDetector = new CharsetDetector();
        charsetDetector.setText( is instanceof BufferedInputStream ? is : new BufferedInputStream(is) );
        charsetDetector.enableInputFilter(true);
        CharsetMatch cm = charsetDetector.detect();
        return cm.getName();
    }
View Full Code Here
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
            }
        }

        // No charset in a meta http-equiv tag, see if it's in the passed content-encoding
        // hint, or the passed content-type hint.
        CharsetDetector detector = new CharsetDetector();
        String incomingCharset = metadata.get(Metadata.CONTENT_ENCODING);
        String incomingType = metadata.get(Metadata.CONTENT_TYPE);
        if (incomingCharset == null && incomingType != null) {
            // TIKA-341: Use charset in content-type
            MediaType mt = MediaType.parse(incomingType);
            if (mt != null) {
                String charset = mt.getParameters().get("charset");
                if ((charset != null) && Charset.isSupported(charset)) {
                    incomingCharset = charset;
                }
            }
        }

        if (incomingCharset != null) {
            detector.setDeclaredEncoding(incomingCharset);
        }

        // TIKA-341 without enabling input filtering (stripping of tags) the
        // short HTML tests don't work well.
        detector.enableInputFilter(true);
        detector.setText(stream);
        for (CharsetMatch match : detector.detectAll()) {
            if (Charset.isSupported(match.getName())) {
                metadata.set(Metadata.CONTENT_ENCODING, match.getName());

                // TIKA-339: Don't set language, as it's typically not a very good
                // guess, and it can create ambiguity if another (better) language
View Full Code Here
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
            }
        }

        // No charset in a meta http-equiv tag, see if it's in the passed content-encoding
        // hint, or the passed content-type hint.
        CharsetDetector detector = new CharsetDetector();
        String incomingCharset = metadata.get(Metadata.CONTENT_ENCODING);
        String incomingType = metadata.get(Metadata.CONTENT_TYPE);
        if (incomingCharset == null && incomingType != null) {
            // TIKA-341: Use charset in content-type
            MediaType mt = MediaType.parse(incomingType);
            if (mt != null) {
                String charset = mt.getParameters().get("charset");
                if ((charset != null) && Charset.isSupported(charset)) {
                    incomingCharset = charset;
                }
            }
        }

        if (incomingCharset != null) {
            detector.setDeclaredEncoding(incomingCharset);
        }

        // TIKA-341 without enabling input filtering (stripping of tags) the
        // short HTML tests don't work well.
        detector.enableInputFilter(true);
        detector.setText(stream);
        for (CharsetMatch match : detector.detectAll()) {
            if (Charset.isSupported(match.getName())) {
                metadata.set(Metadata.CONTENT_ENCODING, match.getName());

                // TIKA-339: Don't set language, as it's typically not a very good
                // guess, and it can create ambiguity if another (better) language
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
* @version $Id: TikaEncodingDetector.java 1231556 2012-01-14 18:47:58Z mostarda $
*/
public class TikaEncodingDetector implements EncodingDetector {

    public String guessEncoding(InputStream is) throws IOException {
        CharsetDetector charsetDetector = new CharsetDetector();
        charsetDetector.setText( is instanceof BufferedInputStream ? is : new BufferedInputStream(is) );
        charsetDetector.enableInputFilter(true);
        CharsetMatch cm = charsetDetector.detect();
        return cm.getName();
    }
View Full Code Here
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
            }
        }

        // No (valid) charset in a meta http-equiv tag, see if it's in the passed content-encoding
        // hint, or the passed content-type hint.
        CharsetDetector detector = new CharsetDetector();
        String incomingCharset = metadata.get(Metadata.CONTENT_ENCODING);
        String incomingType = metadata.get(Metadata.CONTENT_TYPE);
        if (incomingCharset == null && incomingType != null) {
            // TIKA-341: Use charset in content-type
            MediaType mt = MediaType.parse(incomingType);
            if (mt != null) {
                String charset = mt.getParameters().get("charset");
                if ((charset != null) && Charset.isSupported(charset)) {
                    incomingCharset = charset;
                }
            }
        }

        if (incomingCharset != null) {
            detector.setDeclaredEncoding(incomingCharset);
        }

        // TIKA-341 without enabling input filtering (stripping of tags) the
        // short HTML tests don't work well.
        detector.enableInputFilter(true);
        detector.setText(stream);
        for (CharsetMatch match : detector.detectAll()) {
            if (Charset.isSupported(match.getName())) {
                metadata.set(Metadata.CONTENT_ENCODING, match.getName());

                // TIKA-339: Don't set language, as it's typically not a very good
                // guess, and it can create ambiguity if another (better) language
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
              } else {
                 // Nothing in the header, try encoding detection
                 //  on the message body
                 StringChunk text = msg.getMainChunks().textBodyChunk;
                 if(text != null) {
                    CharsetDetector detector = new CharsetDetector();
                    detector.setText( text.getRawValue() );
                    CharsetMatch match = detector.detect();
                    if(match.getConfidence() > 35) {
                       msg.set7BitEncoding( match.getName() );
                    }
                 }
              }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
              } else {
                 // Nothing in the header, try encoding detection
                 //  on the message body
                 StringChunk text = msg.getMainChunks().textBodyChunk;
                 if(text != null) {
                    CharsetDetector detector = new CharsetDetector();
                    detector.setText( text.getRawValue() );
                    CharsetMatch match = detector.detect();
                    if(match.getConfidence() > 35) {
                       msg.set7BitEncoding( match.getName() );
                    }
                 }
              }
View Full Code Here
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
            }
        }

        // No (valid) charset in a meta http-equiv tag, see if it's in the passed content-encoding
        // hint, or the passed content-type hint.
        CharsetDetector detector = new CharsetDetector();
        String incomingCharset = metadata.get(Metadata.CONTENT_ENCODING);
        String incomingType = metadata.get(Metadata.CONTENT_TYPE);
        if (incomingCharset == null && incomingType != null) {
            // TIKA-341: Use charset in content-type
            MediaType mt = MediaType.parse(incomingType);
            if (mt != null) {
                String charset = mt.getParameters().get("charset");
                if ((charset != null) && Charset.isSupported(charset)) {
                    incomingCharset = charset;
                }
            }
        }

        if (incomingCharset != null) {
            detector.setDeclaredEncoding(incomingCharset);
        }

        // TIKA-341 without enabling input filtering (stripping of tags) the
        // short HTML tests don't work well.
        detector.enableInputFilter(true);
        detector.setText(stream);
        for (CharsetMatch match : detector.detectAll()) {
            if (Charset.isSupported(match.getName())) {
                metadata.set(Metadata.CONTENT_ENCODING, match.getName());

                // TIKA-339: Don't set language, as it's typically not a very good
                // guess, and it can create ambiguity if another (better) language
View Full Code Here
85
86
87
88
89
90
91
92
93
94
95
        if (!"text/html".equals(mime_type)) {
          return;
        }
                              
        // try to determine character encoding for content
        CharsetMatch charset = new CharsetDetector().setText(item.getContent().getBytes()).detect();               
       
        // fetch http response as decoded by CharsetDetector
        String decodedHttpResponse;       
        try {
          decodedHttpResponse = charset.getString();
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
        int headerLength = locateEndOfHeader(v.getBytes());
                              
        // try to determine character encoding for rest of response   
        // ( 4 bytes for the header/body seperator 0d 0a 0d 0a
        InputStream responseBytes = new ByteArrayInputStream(v.getBytes(), headerLength + 4, v.getLength() - headerLength - 4);
        CharsetMatch charset = new CharsetDetector().setText(responseBytes).detect();               
       
        // fetch http response as decoded by CharsetDetector
        String decodedHttpResponse;       
        try {
          decodedHttpResponse = charset.getString();
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.txt.CharsetDetector

  • cc.FilterTextHtml$FilterTextHtmlMapper
  • cc.FilterTextHtml2$FilterTextHtmlMapper
  • org.apache.any23.encoding.TikaEncodingDetector
  • org.apache.tika.parser.html.HtmlParser
  • org.apache.tika.parser.microsoft.OutlookExtractor
  • org.sleuthkit.autopsy.thunderbirdparser.MboxParser
  • java.util.ArrayList
  • 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.