1 | /**********************************************************************
|
---|
2 | *
|
---|
3 | * GS2LuceneIndexer.java
|
---|
4 | *
|
---|
5 | * Copyright 2004 The New Zealand Digital Library Project
|
---|
6 | *
|
---|
7 | * A component of the Greenstone digital library software
|
---|
8 | * from the New Zealand Digital Library Project at the
|
---|
9 | * University of Waikato, New Zealand.
|
---|
10 | *
|
---|
11 | * This program is free software; you can redistribute it and/or modify
|
---|
12 | * it under the terms of the GNU General Public License as published by
|
---|
13 | * the Free Software Foundation; either version 2 of the License, or
|
---|
14 | * (at your option) any later version.
|
---|
15 | *
|
---|
16 | * This program is distributed in the hope that it will be useful,
|
---|
17 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
18 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
19 | * GNU General Public License for more details.
|
---|
20 | *
|
---|
21 | * You should have received a copy of the GNU General Public License
|
---|
22 | * along with this program; if not, write to the Free Software
|
---|
23 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
24 | *
|
---|
25 | *********************************************************************/
|
---|
26 |
|
---|
27 | package org.greenstone.LuceneWrapper;
|
---|
28 |
|
---|
29 |
|
---|
30 | import java.io.*;
|
---|
31 | import java.util.Vector;
|
---|
32 |
|
---|
33 | /**
|
---|
34 | * class for indexing XML generated by lucenebuildproc.pm
|
---|
35 | */
|
---|
36 |
|
---|
37 | public class GS2LuceneIndexer {
|
---|
38 |
|
---|
39 | public static void main (String args[]) throws Exception
|
---|
40 | {
|
---|
41 |
|
---|
42 | int verbosity = 1;
|
---|
43 | boolean create = false;
|
---|
44 |
|
---|
45 | Vector filtered_args = new Vector();
|
---|
46 |
|
---|
47 | int argc = args.length;
|
---|
48 | int i = 0;
|
---|
49 | while (i<argc) {
|
---|
50 | if (args[i].startsWith("-")) {
|
---|
51 |
|
---|
52 | // -create causes build to be incremental
|
---|
53 | if (args[i].equals("-create")) {
|
---|
54 | create = true;
|
---|
55 | }
|
---|
56 |
|
---|
57 | // -verbosity [num]
|
---|
58 | else if (args[i].equals("-verbosity")) {
|
---|
59 | i++;
|
---|
60 | if (i<argc) {
|
---|
61 | verbosity = Integer.parseInt(args[i]);
|
---|
62 | }
|
---|
63 | }
|
---|
64 | else {
|
---|
65 | System.out.println("Unrecognised option: " + args[i]);
|
---|
66 | }
|
---|
67 | }
|
---|
68 | else {
|
---|
69 | filtered_args.add((Object)args[i]);
|
---|
70 | }
|
---|
71 | i++;
|
---|
72 | }
|
---|
73 |
|
---|
74 | if (filtered_args.size() != 3) {
|
---|
75 | System.out.println("Usage: java GS2LuceneIndexer [-create|-verbosity [num]] doc-tag-level building_dir index");
|
---|
76 | return;
|
---|
77 | }
|
---|
78 |
|
---|
79 | String doc_tag_level = (String)filtered_args.get(0);
|
---|
80 | String building_dirname = (String)filtered_args.get(1);
|
---|
81 | String index_dirname = (String)filtered_args.get(2);
|
---|
82 |
|
---|
83 | String import_dirname = building_dirname + File.separator + "text";
|
---|
84 |
|
---|
85 | File import_dir = new File(import_dirname);
|
---|
86 | File building_dir = new File(building_dirname);
|
---|
87 |
|
---|
88 | if (!import_dir.exists()) {
|
---|
89 | System.out.println("Couldn't find import directory: "+import_dirname);
|
---|
90 | return;
|
---|
91 | }
|
---|
92 |
|
---|
93 | File idx_dir = new File(building_dir.getPath()+File.separator+index_dirname+File.separator);
|
---|
94 | idx_dir.mkdir();
|
---|
95 |
|
---|
96 | // Set up indexer
|
---|
97 | IndexXML indexer = new IndexXML(doc_tag_level,idx_dir, create);
|
---|
98 | indexer.init();
|
---|
99 |
|
---|
100 | // Read from stdin the files to process
|
---|
101 | try {
|
---|
102 | InputStreamReader isr = new InputStreamReader(System.in, "UTF-8");
|
---|
103 | BufferedReader brin = new BufferedReader(isr);
|
---|
104 |
|
---|
105 | StringBuffer xml_text = new StringBuffer(1024);
|
---|
106 | String line = null;
|
---|
107 | while ((line = brin.readLine()) != null) {
|
---|
108 | xml_text.append(line);
|
---|
109 | if (line.startsWith("</Doc>")) {
|
---|
110 | indexer.indexFile(xml_text.toString());
|
---|
111 | xml_text = new StringBuffer(1024);
|
---|
112 | }
|
---|
113 | //File xml_file = new File(import_dir + File.separator + line);
|
---|
114 | //indexer.indexFile(xml_file); // ****
|
---|
115 | }
|
---|
116 |
|
---|
117 | brin.close();
|
---|
118 | isr.close();
|
---|
119 |
|
---|
120 | } catch (IOException e) {
|
---|
121 | System.err.println("Error: unable to read from stdin");
|
---|
122 | e.printStackTrace();
|
---|
123 | }
|
---|
124 |
|
---|
125 | indexer.finish();
|
---|
126 | }
|
---|
127 | }
|
---|