1 /******************************************************************************
2 * Copyright (C) 2008 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_TextCollection_h_
22 #define _SXSI_TextCollection_h_
24 #include "Tools.h" // Defines ulong and uchar.
26 #include <utility> // Defines std::pair.
28 // Default samplerate for suffix array samples
29 #define TEXTCOLLECTION_DEFAULT_SAMPLERATE 64
35 * General interface for a text collection
37 * Class is virtual, make objects by calling
38 * the static method InitTextCollection().
43 // Type of document identifier
45 // Type for text position (FIXME ulong or long?)
46 typedef ulong TextPosition;
51 * New samplerate can be given, otherwise will use the one specified in the save file!
52 * Note: This is not a static method; call InitTextCollection() first to get the object handle.
54 * Throws an exception if std::fread() fails.
57 static TextCollection* Load(FILE *, unsigned samplerate = 0);
60 * Save data structure into a file
62 * Throws an exception if std::fwrite() fails.
64 virtual void Save(FILE *) const = 0;
69 virtual ~TextCollection() { };
72 * Tests if the string pointed to by DocId is empty
74 virtual bool EmptyText(DocId) const = 0;
79 * Returns the i'th text in the collection.
80 * The numbering starts from 0.
82 virtual uchar* GetText(DocId) const = 0;
84 * Returns substring [i, j] of k'th text
86 * Note: Parameters i and j are text positions inside the k'th text.
88 // virtual uchar* GetText(DocId, TextPosition, TextPosition) const = 0;
90 * Returns backwards (reverse) iterator to the end of i'th text
92 * Note: Do we need this?
93 * Forward iterator would be really in-efficient compared to
96 * TODO Define and implement const_reverse_iterator.
98 //const_reverse_iterator rend(DocId) const;
101 * Existential queries
103 // Is there a text prefixed by given string?
104 virtual bool IsPrefix(uchar const *) const = 0;
105 // Is there a text having given string as a suffix?
106 virtual bool IsSuffix(uchar const *) const = 0;
107 // Is there a text that equals given string?
108 virtual bool IsEqual(uchar const *) const = 0;
109 // Does a text contain given string?
110 virtual bool IsContains(uchar const *) const = 0;
111 // Is there a text that is lexicographically less than given string?
112 virtual bool IsLessThan(uchar const *) const = 0;
115 * Existential queries for given DocId interval.
117 virtual bool IsPrefix(uchar const *, DocId, DocId) const = 0;
118 virtual bool IsSuffix(uchar const *, DocId, DocId) const = 0;
119 virtual bool IsEqual(uchar const *, DocId, DocId) const = 0;
120 virtual bool IsContains(uchar const *, DocId, DocId) const = 0;
121 virtual bool IsLessThan(uchar const *, DocId, DocId) const = 0;
125 * Result is the number of occurrences.
127 virtual ulong Count(uchar const *) const = 0;
129 * More counting queries
130 * Result is the number of documents.
132 virtual unsigned CountPrefix(uchar const *) const = 0;
133 virtual unsigned CountSuffix(uchar const *) const = 0;
134 virtual unsigned CountEqual(uchar const *) const = 0;
135 virtual unsigned CountContains(uchar const *) const = 0;
136 virtual unsigned CountLessThan(uchar const *) const = 0;
139 * Counting queries for given DocId interval
141 virtual unsigned CountPrefix(uchar const *, DocId, DocId) const = 0;
142 virtual unsigned CountSuffix(uchar const *, DocId, DocId) const = 0;
143 virtual unsigned CountEqual(uchar const *, DocId, DocId) const = 0;
144 virtual unsigned CountContains(uchar const *, DocId, DocId) const = 0;
145 virtual unsigned CountLessThan(uchar const *, DocId, DocId) const = 0;
148 * Document reporting queries
150 * Result is a vector of document id's in some undefined order.
152 // Data type for results
153 typedef std::vector<DocId> document_result;
154 virtual document_result Prefix(uchar const *) const = 0;
155 virtual document_result Suffix(uchar const *) const = 0;
156 virtual document_result Equal(uchar const *) const = 0;
157 virtual document_result Contains(uchar const *) const = 0;
158 virtual document_result LessThan(uchar const *) const = 0;
161 * Document reporting queries for given DocId interval.
163 virtual document_result Prefix(uchar const *, DocId, DocId) const = 0;
164 virtual document_result Suffix(uchar const *, DocId, DocId) const = 0;
165 virtual document_result Equal(uchar const *, DocId, DocId) const = 0;
166 virtual document_result Contains(uchar const *, DocId, DocId) const = 0;
167 virtual document_result LessThan(uchar const *, DocId, DocId) const = 0;
170 * Full reporting queries
172 * Result is a vector of pairs <doc id, offset> in some undefined order.
174 // Data type for results
175 typedef std::vector<std::pair<DocId, TextPosition> > full_result;
176 virtual full_result FullContains(uchar const *) const = 0;
177 // Full reporting query for given DocId interval
178 virtual full_result FullContains(uchar const *, DocId, DocId) const = 0;
181 // Protected constructor; use TextCollectionBuilder
182 TextCollection() { };
184 // No copy constructor or assignment
185 TextCollection(TextCollection const&);
186 TextCollection& operator = (TextCollection const&);