01: // indexRWIEntry.java
02: // (C) 2007 by Michael Peter Christen; mc@anomic.de, Frankfurt a. M., Germany
03: // first published 07.11.2007 on http://www.anomic.de
04: //
05: // This is a part of YaCy, a peer-to-peer based web search engine
06: //
07: // $LastChangedDate: 2006-04-02 22:40:07 +0200 (So, 02 Apr 2006) $
08: // $LastChangedRevision: 1986 $
09: // $LastChangedBy: orbiter $
10: //
11: // LICENSE
12: //
13: // This program is free software; you can redistribute it and/or modify
14: // it under the terms of the GNU General Public License as published by
15: // the Free Software Foundation; either version 2 of the License, or
16: // (at your option) any later version.
17: //
18: // This program is distributed in the hope that it will be useful,
19: // but WITHOUT ANY WARRANTY; without even the implied warranty of
20: // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21: // GNU General Public License for more details.
22: //
23: // You should have received a copy of the GNU General Public License
24: // along with this program; if not, write to the Free Software
25: // Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
26:
27: package de.anomic.index;
28:
29: import de.anomic.kelondro.kelondroBitfield;
30: import de.anomic.kelondro.kelondroRow.Entry;
31:
32: public interface indexRWIEntry {
33:
34: // appearance flags, used in RWI entry
35: // some names are derived from the Dublin Core Metadata tag set
36: // the flags 0..23 are identical to the category flags in plasmaCondenser
37: public static final int flag_app_dc_description = 24; // word appears in anchor description text (the reference to an url), or any alternative text field of a link
38: public static final int flag_app_dc_title = 25; // word appears in title or headline or any description part
39: public static final int flag_app_dc_creator = 26; // word appears in author
40: public static final int flag_app_dc_subject = 27; // word appears in header tags or other descriptive part
41: public static final int flag_app_dc_identifier = 28; // word appears in url or document identifier
42: public static final int flag_app_emphasized = 29; // word is emphasized in text (i.e. bold, italics, special size)
43:
44: public String toPropertyForm();
45:
46: public Entry toKelondroEntry();
47:
48: public String urlHash();
49:
50: public int quality();
51:
52: public int virtualAge();
53:
54: public long lastModified();
55:
56: public long freshUntil();
57:
58: public int hitcount();
59:
60: public int posintext();
61:
62: public int posinphrase();
63:
64: public int posofphrase();
65:
66: public int wordsintext();
67:
68: public int phrasesintext();
69:
70: public String getLanguage();
71:
72: public char getType();
73:
74: public int wordsintitle();
75:
76: public int llocal();
77:
78: public int lother();
79:
80: public int urllength();
81:
82: public int urlcomps();
83:
84: public kelondroBitfield flags();
85:
86: public double termFrequency();
87:
88: public String toString();
89:
90: public void join(indexRWIEntry oe);
91:
92: public int worddistance();
93:
94: public boolean isNewer(indexRWIEntry other);
95:
96: public boolean isOlder(indexRWIEntry other);
97:
98: }
|