|
0
|
1 /* */ package de.mpiwg.dwinter.lucencetools.documents;
|
|
|
2 /* */
|
|
|
3 /* */ import de.mpiwg.dwinter.fulltextIndexer.OCRutils.OCRDocument;
|
|
|
4 import de.mpiwg.dwinter.fulltextIndexer.OCRutils.OCRDocument.OCRLine;
|
|
|
5 /* */ import java.io.File;
|
|
|
6 /* */ import java.io.FileNotFoundException;
|
|
|
7 /* */ import java.io.PrintStream;
|
|
|
8 /* */ import java.io.UnsupportedEncodingException;
|
|
|
9 /* */ import org.apache.lucene.document.DateTools;
|
|
|
10 /* */ import org.apache.lucene.document.DateTools.Resolution;
|
|
|
11 /* */ import org.apache.lucene.document.Document;
|
|
|
12 /* */ import org.apache.lucene.document.Field;
|
|
|
13 /* */ import org.apache.lucene.document.Field.Index;
|
|
|
14 import org.apache.lucene.document.Field.Store;
|
|
|
15 /* */
|
|
|
16 /* */ public class OcropusLineDocument
|
|
|
17 /* */ {
|
|
|
18 /* */ public static Document Document(File f, String cleanPath,String language, OCRDocument.OCRLine ocrline, String pageDimension, String textId)
|
|
|
19 /* */ throws FileNotFoundException, UnsupportedEncodingException
|
|
|
20 /* */ {
|
|
|
21 /* 65 */ return Document(f, cleanPath,language, ocrline, pageDimension, null, textId);
|
|
|
22 /* */ }
|
|
|
23 /* */
|
|
|
24 /* */ public static Document Document(File f, String cleanPath,String language, OCRDocument.OCRLine ocrline, String pageDimension, String dcMetaData, String textId)
|
|
|
25 /* */ throws FileNotFoundException, UnsupportedEncodingException
|
|
|
26 /* */ {
|
|
|
27 /* 72 */ Document doc = new Document();
|
|
|
28 /* */
|
|
|
29 /* 76 */ doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
|
|
|
30 doc.add(new Field("cleanedPath", cleanPath, Field.Store.YES, Field.Index.NOT_ANALYZED));
|
|
|
31 /* 77 */ doc.add(new Field("pageDimension", pageDimension, Field.Store.YES, Field.Index.NOT_ANALYZED));
|
|
|
32 /* 78 */ if (dcMetaData == null)
|
|
|
33 /* 79 */ dcMetaData = "";
|
|
|
34 /* 80 */ System.out.println("++++++++++++++++++DCMD:" + dcMetaData);
|
|
|
35 /* 81 */ doc.add(new Field("dcMetaData", dcMetaData, Field.Store.YES, Field.Index.ANALYZED));
|
|
|
36 /* */
|
|
|
37 /* 90 */ doc.add(
|
|
|
38 /* 92 */ new Field("modified",
|
|
|
39 /* 91 */ DateTools.timeToString(f.lastModified(), DateTools.Resolution.MINUTE),
|
|
|
40 /* 92 */ Field.Store.YES, Field.Index.NOT_ANALYZED));
|
|
|
41 /* */
|
|
|
42 /* 94 */ doc.add(new Field("textId", textId, Field.Store.YES, Field.Index.NOT_ANALYZED));
|
|
|
43 /* */
|
|
|
44 /* 106 */ doc.add(new Field("contents", ocrline.content, Field.Store.NO, Field.Index.ANALYZED));
|
|
|
45 /* 107 */ doc.add(new Field("contentsNormalized", ocrline.content, Field.Store.NO, Field.Index.ANALYZED));
|
|
|
46 /* */
|
|
|
47 /* 111 */ doc.add(new Field("language", language, Field.Store.YES, Field.Index.NOT_ANALYZED));
|
|
|
48 /* */
|
|
|
49 /* 114 */ doc.add(new Field("bbox", ocrline.bbox, Field.Store.YES, Field.Index.NOT_ANALYZED));
|
|
|
50 /* */
|
|
|
51 /* 116 */ doc.add(new Field("lineNumber", ocrline.lineNumber, Field.Store.YES, Field.Index.NOT_ANALYZED));
|
|
|
52 /* 117 */ return doc;
|
|
|
53 /* */ }
|
|
|
54 /* */ }
|
|
|
55
|
|
|
56 /* Location: /private/tmp/fulltextIndexer.jar
|
|
|
57 * Qualified Name: de.mpiwg.dwinter.lucencetools.documents.OcropusLineDocument
|
|
|
58 * JD-Core Version: 0.5.4
|
|
|
59 */ |
