source: main/trunk/greenstone2/common-src/indexers/mgpp/text/TextEl.h@ 25147

Last change on this file since 25147 was 25147, checked in by kjdon, 12 years ago

merged 64_bit_Greenstone branch into trunk, rev 25139

  • Property svn:executable set to *
  • Property svn:keywords set to Author Date Id Revision
File size: 2.2 KB
Line 
1/**************************************************************************
2 *
3 * TextEl.h -- Data structures for parsed documents
4 * Copyright (C) 1999 Rodger McNab
5 *
6 * This program is free software; you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation; either version 2 of the License, or
9 * (at your option) any later version.
10 *
11 * This program is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU General Public License for more details.
15 *
16 * You should have received a copy of the GNU General Public License
17 * along with this program; if not, write to the Free Software
18 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
19 *
20 **************************************************************************/
21
22#ifndef TEXTEL_H
23#define TEXTEL_H
24
25#include "UCArray.h"
26#include "FileBuf.h"
27#include "sysfuncs.h"
28
29enum TextElType {OpenTagE, CloseTagE, TextE};
30
31class TextEl {
32protected:
33 bool ReadTextTag (FileBuf &buf, TextEl &el);
34 bool ReadTextTag (u_char ** buffer, TextEl &el);
35public:
36 TextElType elType;
37 UCArray tagName;
38 UCArray text; // complete text, including tag
39
40 TextEl () { Clear (); }
41 void Clear ();
42};
43
44
45typedef vector<TextEl> TextElArray;
46
47
48// compatMode parses documents similar to "old mg" -- ie with
49// C-b between documents and C-c between paragraphs
50
51// returns true if a text element could be read
52bool ReadTextEl (FileBuf &buf, TextEl &el,
53 bool compatMode, bool &compatInPara);
54bool ReadTextEl (u_char **buffer, TextEl &el,
55 bool compatMode, bool &compatInPara);
56
57// looks for an opening docTag and reads all text elements up
58// to a corresponding closing docTag. note that this does not
59// hierarchically parse the document so you can't nest documents.
60// returns true if a document could be found
61bool ReadDoc (FileBuf &buf, const UCArray &docTag,
62 TextElArray &doc, mg_u_long &docLen,
63 bool compatMode=false);
64
65bool ReadDoc(u_char **buffer, const UCArray &docTag,
66 TextElArray &doc, mg_u_long &docLen,
67 bool compatMode=false);
68
69#endif
Note: See TracBrowser for help on using the repository browser.