Package net.yacy.kelondro.io

Examples of net.yacy.kelondro.io.CharBuffer

78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
    public boolean isIdentityTransformer() {
        return bluelist.isEmpty();
    }

    private static char[] genBlueLetters(int length) {
            final CharBuffer bb = new CharBuffer(" <FONT COLOR=#0000FF>".toCharArray());
            length = length / 2;
            if (length > 10) length = 7;
            while (length-- > 0) {
                bb.append((int)'X');
            }
            bb.append("</FONT> ");
            final char[] result = bb.getChars();
            try {
        bb.close();
      } catch (IOException e) {
          Log.logException(e);
      }
            return result;
    }
View Full Code Here
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
124
125
126
127
128
129
130
131
132
133
134
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
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
   
    private Document[] parse(final MultiProtocolURI location, final String mimeType,
            final String charset, final File dest)
            throws Parser.Failure, InterruptedException {
       
        CharBuffer writer = null;
        try {         
            String docDescription = null;
            String docKeywordStr  = null;
            String docShortTitle  = null;
            String docLongTitle   = null;
            String docAuthor      = null;
            String docLanguage    = null;
           
            // opening the file as zip file
            final ZipFile zipFile = new ZipFile(dest);
            final Enumeration<? extends ZipEntry> zipEnum = zipFile.entries();
            final SAXParserFactory saxParserFactory = SAXParserFactory.newInstance();
           
            // looping through all containing files
            while (zipEnum.hasMoreElements()) {
               
                // getting the next zip file entry
                final ZipEntry zipEntry= zipEnum.nextElement();
                final String entryName = zipEntry.getName();
               
                // content.xml contains the document content in xml format
                if (entryName.equals("content.xml")) {
                   
                    // create a writer for output
                    writer = new CharBuffer();
                   
                    // extract data
                    final InputStream zipFileEntryStream = zipFile.getInputStream(zipEntry);
                    final SAXParser saxParser = saxParserFactory.newSAXParser();
                    saxParser.parse(zipFileEntryStream, new ODContentHandler(writer));
               
                    // close readers and writers
                    zipFileEntryStream.close();
                    writer.close();
                   
                } else if (entryName.equals("meta.xml")) {
                    //  meta.xml contains metadata about the document
                    final InputStream zipFileEntryStream = zipFile.getInputStream(zipEntry);
                    final SAXParser saxParser = saxParserFactory.newSAXParser();
                    final ODMetaHandler metaData = new ODMetaHandler();
                    saxParser.parse(zipFileEntryStream, metaData);
                    docDescription = metaData.getDescription();
                    docKeywordStr  = metaData.getKeyword();
                    docShortTitle  = metaData.getTitle();
                    docLongTitle   = metaData.getSubject();
                    docAuthor      = metaData.getCreator();
                    docLanguage    = metaData.getLanguage();
                }
            }
           
            // make the languages set
            final Set<String> languages = new HashSet<String>(1);
            if (docLanguage != null) languages.add(docLanguage);
           
            // if there is no title availabe we generate one
            if (docLongTitle == null) {
                if (docShortTitle != null) {
                    docLongTitle = docShortTitle;
                }
            }           
        
            // split the keywords
            String[] docKeywords = null;
            if (docKeywordStr != null) docKeywords = docKeywordStr.split(" |,");
           
            // create the parser document
            Document[] docs = null;
            final byte[] contentBytes = UTF8.getBytes(writer.toString());
            docs = new Document[]{new Document(
                    location,
                    mimeType,
                    "UTF-8",
                    this,
                    languages,
                    docKeywords,
                    docLongTitle,
                    docAuthor,
                    "",
                    null,
                    docDescription,
                    0.0f, 0.0f,
                    contentBytes,
                    null,
                    null,
                    null,
                    false)};
            return docs;
        } catch (final Exception e) {           
            if (e instanceof InterruptedException) throw (InterruptedException) e;
            if (e instanceof Parser.Failure) throw (Parser.Failure) e;
           
            // close the writer
            if (writer != null) try { writer.close(); } catch (final Exception ex) {/* ignore this */}
           
            throw new Parser.Failure("Unexpected error while parsing odt file. " + e.getMessage(),location);
        }
    }
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
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
        }

        if (docTitle == null || docTitle.length() == 0) {
            docTitle = MultiProtocolURI.unescape(location.getFileName());
        }
        CharBuffer writer = null;
        try {
            // create a writer for output
            PDFTextStripper stripper = null;
            writer = new CharBuffer();
            stripper = new PDFTextStripper();
            stripper.writeText(pdfDoc, writer); // may throw a NPE
            pdfDoc.close();
            writer.close();
        } catch (final IOException e) {
            // close the writer
            if (writer != null) try { writer.close(); } catch (final Exception ex) {}
            try {pdfDoc.close();} catch (final IOException ee) {}
            //throw new Parser.Failure(e.getMessage(), location);
        } catch (final NullPointerException e) {
            // this exception appeared after the insertion of the jempbox-1.5.0.jar library
            Log.logException(e);
            // close the writer
            if (writer != null) try { writer.close(); } catch (final Exception ex) {}
            try {pdfDoc.close();} catch (final IOException ee) {}
            //throw new Parser.Failure(e.getMessage(), location);
        } finally {
            try {pdfDoc.close();} catch (final IOException e) {}
        }
        pdfDoc = null;

        String[] docKeywords = null;
        if (docKeywordStr != null) {
            docKeywords = docKeywordStr.split(" |,");
        }
        if (docTitle == null) {
            docTitle = docSubject;
        }

        byte[] contentBytes;
        contentBytes = UTF8.getBytes(writer.toString());

        // clear resources in pdfbox. they say that is resolved but it's not. see:
        // https://issues.apache.org/jira/browse/PDFBOX-313
        // https://issues.apache.org/jira/browse/PDFBOX-351
        // https://issues.apache.org/jira/browse/PDFBOX-441
View Full Code Here
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
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
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
        SUPPORTED_MIME_TYPES.add("application/vnd.openxmlformats-officedocument.spreadsheetml.template");
    }
   
    private Document[] parse(final MultiProtocolURI location, final String mimeType, final String charset, final File dest) throws Parser.Failure, InterruptedException {
       
        CharBuffer writer = null;
        try {         
            String docDescription = null;
            String docKeywordStr  = null;
            String docShortTitle  = null;
            String docLongTitle   = null;
            String docAuthor      = null;
            String docLanguage    = null;
           
            // opening the file as zip file
            final ZipFile zipFile= new ZipFile(dest);
            final Enumeration<? extends ZipEntry> zipEnum = zipFile.entries();
            final SAXParserFactory saxParserFactory = SAXParserFactory.newInstance();
           
            // looping through all containing files
            while (zipEnum.hasMoreElements()) {
               
                // get next zip file entry
                final ZipEntry zipEntry= zipEnum.nextElement();
                final String entryName = zipEntry.getName();
               
                // content.xml contains the document content in xml format
                if (entryName.equals("word/document.xml")
                  || entryName.startsWith("ppt/slides/slide")
                  || entryName.startsWith("xl/worksheets/sheet")) {
                   
                    // create a writer for output
                    writer = new CharBuffer();
                   
                    // extract data
                    final InputStream zipFileEntryStream = zipFile.getInputStream(zipEntry);
                    final SAXParser saxParser = saxParserFactory.newSAXParser();
                    saxParser.parse(zipFileEntryStream, new ODContentHandler(writer));
               
                    // close readers and writers
                    zipFileEntryStream.close();
                    writer.close();
                   
                } else if (entryName.equals("docProps/core.xml")) {
                    //  meta.xml contains metadata about the document
                    final InputStream zipFileEntryStream = zipFile.getInputStream(zipEntry);
                    final SAXParser saxParser = saxParserFactory.newSAXParser();
                    final ODMetaHandler metaData = new ODMetaHandler();
                    saxParser.parse(zipFileEntryStream, metaData);
                    docDescription = metaData.getDescription();
                    docKeywordStr  = metaData.getKeyword();
                    docShortTitle  = metaData.getTitle();
                    docLongTitle   = metaData.getSubject();
                    docAuthor      = metaData.getCreator();
                    docLanguage    = metaData.getLanguage();
                }
            }
           
            // make the languages set
            final Set<String> languages = new HashSet<String>(1);
            if (docLanguage != null && docLanguage.length() == 0)
          languages.add(docLanguage);
           
            // if there is no title availabe we generate one
            if ((docLongTitle == null || docLongTitle.length() == 0) && (docShortTitle != null)) {
                    docLongTitle = docShortTitle;
            }           
        
            // split the keywords
            String[] docKeywords = null;
            if (docKeywordStr != null) docKeywords = docKeywordStr.split(" |,");
           
            // create the parser document
            Document[] docs = null;
            final byte[] contentBytes = UTF8.getBytes(writer.toString());
            docs = new Document[]{new Document(
                    location,
                    mimeType,
                    "UTF-8",
                    this,
                    languages,
                    docKeywords,
                    docLongTitle,
                    docAuthor,
                    "",
                    null,
                    docDescription,
                    0.0f, 0.0f,
                    contentBytes,
                    null,
                    null,
                    null,
                    false)};
            return docs;
        } catch (final Exception e) {           
            if (e instanceof InterruptedException) throw (InterruptedException) e;
            if (e instanceof Parser.Failure) throw (Parser.Failure) e;
           
            // close the writer
            if (writer != null) try {
                writer.close();
            } catch (final Exception ex) {/* ignore this */}

            Log.logException(e);
            throw new Parser.Failure("Unexpected error while parsing odt file. " + e.getMessage(),location);
        }
View Full Code Here
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
      if(args.length < 1 || args[0].contains("help")) {
    System.out.println(HELP);

      } else if(args[0].equals("--sign") && args.length==3) {
    CryptoLib cl = new CryptoLib();
    CharBuffer privKeyBuffer = new CharBuffer(new File(args[1]));
    byte[] privKeyByteBuffer = Base64Order.standardCoder.decode(privKeyBuffer.toString());
    PrivateKey privKey = cl.getPrivateKeyFromBytes(privKeyByteBuffer);

    FileInputStream dataStream = new FileInputStream(args[2]);

    byte[] signBuffer = cl.getSignature(privKey, dataStream);
    FileWriter signFile = new FileWriter(args[2] + ".sig");
    signFile.write(Base64Order.standardCoder.encode(signBuffer));
    signFile.close();
      } else if(args[0].equals("--verify") && args.length==3) {
    CryptoLib cl = new CryptoLib();
    CharBuffer pubKeyBuffer = new CharBuffer(new File(args[1]));
    byte[] pubKeyByteBuffer = Base64Order.standardCoder.decode(pubKeyBuffer.toString().trim());
    PublicKey pubKey = cl.getPublicKeyFromBytes(pubKeyByteBuffer);

    FileInputStream dataStream = new FileInputStream(args[2]);

    CharBuffer signBuffer = new CharBuffer(new File(args[2] + ".sig"));
    byte[] signByteBuffer = Base64Order.standardCoder.decode(signBuffer.toString().trim());
    if(cl.verifySignature(pubKey, dataStream, signByteBuffer)) {
        System.out.println("Signature OK!");
    } else {
        System.out.println("Signature FALSE!!!!!!!!!!!");
        System.exit(1);
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
            final boolean passbyIfBinarySuspect
    ) {
        this.outStream     = outStream;
        this.scraper       = scraper;
        this.transformer   = transformer;
        this.buffer        = new CharBuffer(1024);
        this.filterTag     = null;
        this.filterOpts    = null;
        this.filterCont    = null;
        this.inSingleQuote = false;
        this.inDoubleQuote = false;
View Full Code Here
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
            this.out = new OutputStreamWriter(this.outStream,(charSet == null)?Charset.defaultCharset():charSet);
        }
    }

    public static char[] genTag0raw(final String tagname, final boolean opening, final char[] tagopts) {
            final CharBuffer bb = new CharBuffer(tagname.length() + tagopts.length + 3);
            bb.append((int)'<');
            if (!opening) {
                bb.append((int)'/');
            }
            bb.append(tagname);
            if (tagopts.length > 0) {
//              if (tagopts[0] == (byte) 32)
                bb.append(tagopts);
//              else bb.append((byte) 32).append(tagopts);
            }
            bb.append((int)'>');
            final char[] result = bb.getChars();
            try {
                bb.close();
            } catch (final IOException e) {
                Log.logException(e);
            }
            return result;
    }
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
            }
            return result;
    }

    public static char[] genTag1raw(final String tagname, final char[] tagopts, final char[] text) {
            final CharBuffer bb = new CharBuffer(2 * tagname.length() + tagopts.length + text.length + 5);
            bb.append((int)'<').append(tagname);
            if (tagopts.length > 0) {
//              if (tagopts[0] == (byte) 32)
                bb.append(tagopts);
//              else bb.append((byte) 32).append(tagopts);
            }
            bb.append((int)'>');
            bb.append(text);
            bb.append((int)'<').append((int)'/').append(tagname).append((int)'>');
            final char[] result = bb.getChars();
            try {
                bb.close();
            } catch (final IOException e) {
                Log.logException(e);
            }
            return result;
    }
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
            return result;
    }

    public static char[] genTag0(final String tagname, final Properties tagopts, final char quotechar) {
            final char[] tagoptsx = (tagopts.isEmpty()) ? null : genOpts(tagopts, quotechar);
            final CharBuffer bb = new CharBuffer(tagname.length() + ((tagoptsx == null) ? 0 : (tagoptsx.length + 1)) + tagname.length() + 2);
            bb.append((int)'<').append(tagname);
            if (tagoptsx != null) {
                bb.append(32);
                bb.append(tagoptsx);
            }
            bb.append((int)'>');
            final char[] result = bb.getChars();
            try {
                bb.close();
            } catch (final IOException e) {
                Log.logException(e);
            }
            return result;
    }
View Full Code Here
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
            return result;
    }

    public static char[] genTag1(final String tagname, final Properties tagopts, final char[] text, final char quotechar) {
            final char[] gt0 = genTag0(tagname, tagopts, quotechar);
            final CharBuffer cb = new CharBuffer(gt0, gt0.length + text.length + tagname.length() + 3);
            cb.append(text).append((int)'<').append((int)'/').append(tagname).append((int)'>');
            final char[] result = cb.getChars();
            try {
                cb.close();
            } catch (final IOException e) {
                Log.logException(e);
            }
            return result;
    }
View Full Code Here
TOP

Related Classes of net.yacy.kelondro.io.CharBuffer

  • de.anomic.tools.CryptoLib
  • de.anomic.yacy.yacyRelease
  • net.yacy.document.parser.html.ContentScraper
  • net.yacy.document.parser.html.ContentTransformer
  • net.yacy.document.parser.html.TransformerWriter
  • net.yacy.document.parser.odtParser
  • net.yacy.document.parser.ooxmlParser
  • net.yacy.document.parser.pdfParser
  • net.yacy.kelondro.data.meta.URIMetadataRow
  • net.yacy.peers.operation.yacyRelease
    • 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.