Package it.unimi.dsi.lang

Examples of it.unimi.dsi.lang.MutableString

149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
     * @return An alignment iterator restricted to the sequence [start end] interval.
     */
    public final CloseableIterator<Alignment> query(String sequence, int start, int end, boolean contained) {
        LOG.debug(String.format("query %s %d %d %b%n", sequence, start, end, contained));

        final MutableString id = new MutableString(sequence);
        int referenceIndex = targetIdentifiers.getIndex(id);
        if (referenceIndex == -1) {
            // try again removing a chr prefix:
            referenceIndex = targetIdentifiers.getIndex(id.replace("chr", ""));
        }
        try {
            if (referenceIndex == -1) {
                // the reference could not be found in the Goby alignment, probably a wrong reference choice. Not sure how
                // to inform the end user, but we send no results here:
View Full Code Here
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
    }


    public String getValueString(double position, WindowFunction windowFunction) {
        //  //LOG.info("getValueString");
        MutableString buffer = new MutableString();

        buffer.append(entry.toString());
        buffer.replace("\n", "<br>");

        if (this.isPaired()) {
            buffer.append("----------------------" + "<br>");
            buffer.append("Mate start = " + getMate().positionString() + "<br>");
            buffer.append("Mate is mapped = " + (getMate().isMapped() ? "yes" : "no") + "<br>");
            //buf.append("Pair is proper = " + (getProperPairFlag() ? "yes" : "no") + "<br>");
            if (getChr().equals(getMate().getChr())) {
                buffer.append("Insert size = " + getInferredInsertSize() + "<br>");
            }
            if (getPairOrientation().length() > 0) {
                buffer.append("Pair orientation = " + getPairOrientation() + "<br>");
            }
            if (isFirstOfPair()) {
                buffer.append("First of pair <br>");
            }
            if (isSecondOfPair()) {
                buffer.append("Second of pair <br>");
            }
        }
        return buffer.toString();
    }
View Full Code Here
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
177
178
179
180
    BulletParser bulletParser = new BulletParser(
        TRECParsingFactory.INSTANCE);

    bulletParser.setCallback(new DefaultCallback() {
      TRECTopic topic = null;
      MutableString curText = new MutableString();
      Element curElement;

      @Override
      public boolean characters(char[] text, int offset, int length,
          boolean flowBroken) {
        curText.append(text, offset, length);
        return true;
      }

      @Override
      public boolean startElement(Element element,
          Map<Attribute, MutableString> attrMapUnused) {

        // --- New tag
        if (topic != null)
          process();

        // ---
        if (element == TRECParsingFactory.ELEMENT_TOP) {
          topic = new TRECTopic();
        }
        curElement = element;
        return true;
      }

      void removePrefix(String prefix, MutableString text) {
        if (text.startsWith(prefix))
          text.delete(0, prefix.length());

      }

      private void process() {
        curText.trim();
        curText.replace('\n', ' ');
        curText.squeezeSpaces(false);

        if (curElement == TRECParsingFactory.ELEMENT_TITLE) {
          removePrefix("Topic: ", curText);
          if (quoteCommas) {
            StringBuilder builder = new StringBuilder();
            boolean first = true;
            for (String part : curText.toString()
                .split("\\s*,\\s*")) {
              if (first)
                first = false;
              else
                builder.append(' ');

              if (part.indexOf(' ') >= 0) {
                builder.append('"');
                builder.append(part);
                builder.append('"');
              } else
                builder.append(part);
            }

            topic.title = builder.toString();
          } else
            topic.title = curText.toString();
        } else if (curElement == TRECParsingFactory.ELEMENT_NUM) {
          removePrefix("Number: ", curText);
          // Normalise the number
          topic.id = new Integer(curText.toString()).toString();
        } else if (curElement == TRECParsingFactory.ELEMENT_DESC) {
          removePrefix("Description: ", curText);
          topic.description = curText.toString();
        } else if (curElement == TRECParsingFactory.ELEMENT_NARR) {
          // TREC
          removePrefix("Narrative: ", curText);
          topic.narrative = curText.toString();
        } else if (curElement == TRECParsingFactory.ELEMENT_SMRY) {
          removePrefix("Summary: ", curText);
          topic.summary = curText.toString();
        } else if (curElement == TRECParsingFactory.ELEMENT_CON) {
          // TREC 1
          removePrefix("Concepts: ", curText);
          topic.concepts = curText.toString();
        } else if (curElement == TRECParsingFactory.ELEMENT_DEF) {
          // TREC 1
          removePrefix("Definition(s): ", curText);
          removePrefix("Definition: ", curText);
          topic.definitions = curText.toString();
        }
        curElement = null;
        curText.delete(0, curText.length());
      }

      @Override
      public boolean endElement(Element element) {
        if (topic != null)
View Full Code Here
32
33
34
35
36
37
38
39
40
41
42
43
        // FIXME: uses the same default reader as MG4J, but should be
        // adapted!
        FastBufferedReader reader = new FastBufferedReader();
        SimpleQuery.Term term = (SimpleQuery.Term) c;
        reader.setReader(new StringReader(term.getTerm()));
        MutableString word = new MutableString();
        MutableString nonWord = new MutableString();
        try {
          while (reader.next(word, nonWord)) {
            if (word.length() > 0)
              terms.add(new Term(term.getOperator(), word
                  .toString()));
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
   * @param text
   * @param terms
   */
  static private void addTerm(String text, Map<String, MutableInt> terms,
      TermProcessor processor, IndexConfiguration index) {
    MutableString word = new MutableString(text);
    // TODO: Annalina - when the query transformer is implemented, remove
    // the following and just keep the "update" line
    if (processor.processTerm(word)) {
      if (index.getTermId(word) != -1) {
        update(terms, word.toString());
        return;
      }
    }

    String[] array = text.split("-");
View Full Code Here
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
        public boolean startElement(Element element, Map<Attribute, MutableString> attributes) {
            if (charset[0] != null)
                return true;

            if (element == Element.META) {
                final MutableString httpEquiv = attributes.get(Attribute.HTTP_EQUIV);
                final MutableString content = attributes.get(Attribute.CONTENT);
                if (content != null && httpEquiv != null && httpEquiv.toLowerCase().equals("content-type")) {
                    charset[0] = retrieveCharsetFromContentType(content.toString());
//                    return charset[0] == null;
                    return true;
                }

                final MutableString metaCharset = attributes.get(Attribute.CHARSET);
                if  (metaCharset != null) {
                    charset[0] = getCharset(metaCharset.toUpperCase().toString());
                    return true;
//                    return charset[0] == null;
                }
            }
View Full Code Here
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
        BulletParser bulletParser = new BulletParser(
                TRECParsingFactory.INSTANCE);

        bulletParser.setCallback(new DefaultCallback() {
            TRECTopic topic = null;
            MutableString curText = new MutableString();
            Element curElement;

            @Override
            public boolean characters(char[] text, int offset, int length,
                                      boolean flowBroken) {
                curText.append(text, offset, length);
                return true;
            }

            @Override
            public boolean startElement(Element element,
                                        Map<Attribute, MutableString> attrMapUnused) {

                // --- New tag
                if (topic != null)
                    process();

                // ---
                if (element == ELEMENT_TOP) {
                    topic = new TRECTopic();
                }
                curElement = element;
                return true;
            }

            void removePrefix(String prefix, MutableString text) {
                if (text.startsWith(prefix))
                    text.delete(0, prefix.length());

            }

            private void process() {
                curText.trim();
                curText.replace('\n', ' ');
                curText.squeezeSpaces(false);

                if (curElement == ELEMENT_TITLE) {
                    removePrefix("Topic: ", curText);
                    if (quoteCommas) {
                        StringBuilder builder = new StringBuilder();
                        boolean first = true;
                        for (String part : curText.toString()
                                .split("\\s*,\\s*")) {
                            if (first)
                                first = false;
                            else
                                builder.append(' ');

                            if (part.indexOf(' ') >= 0) {
                                builder.append('"');
                                builder.append(part);
                                builder.append('"');
                            } else
                                builder.append(part);
                        }

                        topic.title = builder.toString();
                    } else
                        topic.title = curText.toString();
                } else if (curElement == ELEMENT_NUM) {
                    removePrefix("Number: ", curText);
                    // Normalise the number
                    topic.id = new Integer(curText.toString()).toString();
                } else if (curElement == ELEMENT_DESC) {
                    removePrefix("Description: ", curText);
                    topic.description = curText.toString();
                } else if (curElement == ELEMENT_NARR) {
                    // TREC
                    removePrefix("Narrative: ", curText);
                    topic.narrative = curText.toString();
                } else if (curElement == ELEMENT_SMRY) {
                    removePrefix("Summary: ", curText);
                    topic.summary = curText.toString();
                } else if (curElement == ELEMENT_CON) {
                    // TREC 1
                    removePrefix("Concepts: ", curText);
                    topic.concepts = curText.toString();
                } else if (curElement == ELEMENT_DEF) {
                    // TREC 1
                    removePrefix("Definition(s): ", curText);
                    removePrefix("Definition: ", curText);
                    topic.definitions = curText.toString();
                }
                curElement = null;
                curText.delete(0, curText.length());
            }

            @Override
            public boolean endElement(Element element) {
                if (topic != null)
View Full Code Here
293
294
295
296
297
298
299
300
301
302
303
304
              .document(results.get(i).document);
          Reader reader = (Reader) document.content(fieldIndex);
          WordReader wordReader = document.wordReader(fieldIndex);
          wordReader.setReader(reader);

          MutableString word = new MutableString();
          MutableString nonWord = new MutableString();
          final LongRBTreeSet set = new LongRBTreeSet();

          while (wordReader.next(word, nonWord)) {
            if (processor.processTerm(word)) {
              long termId = index.getTermId(word);
View Full Code Here
211
212
213
214
215
216
217
218
219
220
221
222
    private Result method1(Collection<MG4JRelevanceFeedback.MG4JDocument> feedback, ObjectArrayList<DocumentScoreInfo<Reference2ObjectMap<Index, SelectedInterval[]>>> results, int[] contents, long[] queryTerms) throws IOException {
        // Collect all words from documents and estimate P(w|R) and P(w|N)

        // Compute P(w q1 .. qn)
        MutableString separator = new MutableString();
        MutableString token = new MutableString();

        // Probability of P(w q1 ... qn) - Eq. 9 (model iid) and 12 (conditional)
        Long2DoubleLinkedOpenHashMap p_w_q = new Long2DoubleLinkedOpenHashMap();
        p_w_q.defaultReturnValue(0.);
View Full Code Here
328
329
330
331
332
333
334
335
336
337
338
339
     * @param document The document ID to read
     * @return A multiset containing the frequencies of the contained terms
     * @throws IOException
     */
    private Multiset<Long> readDocument(int[] contents, long document) throws IOException {
        MutableString separator = new MutableString();
        MutableString token = new MutableString();

        final Document doc = collection.document(document);
        long unknown = index.getUnknownTermId();

        Multiset<Long> words = HashMultiset.create();
View Full Code Here
TOP

Related Classes of it.unimi.dsi.lang.MutableString

  • edu.uci.ics.crawler4j.crawler.LinkExtractor
  • it.unimi.dsi.mg4j.document.AbstractDocumentCollection
  • it.unimi.dsi.mg4j.document.AbstractDocumentFactory
  • it.unimi.dsi.mg4j.document.DocumentCollectionTest
  • it.unimi.dsi.mg4j.document.JavamailDocumentCollection
  • it.unimi.dsi.mg4j.document.JdbcDocumentCollection
  • it.unimi.dsi.mg4j.document.MapVirtualDocumentCollection
  • it.unimi.dsi.mg4j.document.SimpleCompressedDocumentCollection
  • it.unimi.dsi.mg4j.document.SimpleCompressedDocumentCollectionBuilder
  • it.unimi.dsi.mg4j.document.ZipDocumentCollection$ZipFactory
    • 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.