1 /******************************************************************************
2 * Copyright (C) 2009 by Niko Valimaki <nvalimak@cs.helsinki.fi> *
3 * Text collection interface for an in-memory XQuery/XPath engine *
5 * This program is free software; you can redistribute it and/or modify *
6 * it under the terms of the GNU Lesser General Public License as published *
7 * by the Free Software Foundation; either version 2 of the License, or *
8 * (at your option) any later version. *
10 * This program is distributed in the hope that it will be useful, *
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of *
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
13 * GNU Lesser General Public License for more details. *
15 * You should have received a copy of the GNU Lesser General Public License *
16 * along with this program; if not, write to the *
17 * Free Software Foundation, Inc., *
18 * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. *
19 ******************************************************************************/
21 #ifndef _SXSI_TextCollectionBuilder_h_
22 #define _SXSI_TextCollectionBuilder_h_
24 #include "TextCollection.h"
25 #include "TextStorage.h"
26 #include "Tools.h" // Defines ulong and uchar.
30 #include <utility> // Defines std::pair.
31 #include <cstring> // Defines std::strlen, added by Kim
33 // Un-comment to compare BWT against a BWT generated from class dynFMI:
34 //#define TCB_TEST_BWT
36 // Default samplerate for suffix array samples
37 #define TEXTCOLLECTION_DEFAULT_SAMPLERATE 64
39 // Default input length, used to calculate the buffer size.
40 #define TEXTCOLLECTION_DEFAULT_INPUT_LENGTH (150 * 1024 * 1024)
45 struct TCBuilderRep; // Pimpl
48 * Build an instance of the TextCollection class.
50 class TextCollectionBuilder
53 explicit TextCollectionBuilder(unsigned samplerate = TEXTCOLLECTION_DEFAULT_SAMPLERATE,
54 ulong estimatedInputLength = TEXTCOLLECTION_DEFAULT_INPUT_LENGTH);
55 ~TextCollectionBuilder();
60 * Must be a zero-terminated string from alphabet [1,255].
61 * Can not be called after makeStatic().
62 * The i'th text insertion gets an identifier value i-1.
63 * In other words, document identifiers start from 0.
65 * Second parameter tells if the text will be added to the
66 * index also. If false, text is added only to the TextCollection
67 * and can not be searched for.
69 void InsertText(uchar const *, bool index = true);
73 * Convert to a static collection.
74 * New texts can not be inserted after this operation.
76 * TextStorage type defaults to TYPE_PLAIN_TEXT, another
77 * possible type is TYPE_LZ_INDEX.
79 TextCollection * InitTextCollection(char type = TextStorage::TYPE_PLAIN_TEXT);
82 // Using Pimpl idiom to hide RLCSA implementation.
83 struct TCBuilderRep * p_;
85 // No copy constructor or assignment
86 TextCollectionBuilder(TextCollectionBuilder const&);
87 TextCollectionBuilder& operator = (TextCollectionBuilder const&);