File: snippet.h

package info (click to toggle)
chromium-browser 57.0.2987.98-1~deb8u1
  • links: PTS, VCS
  • area: main
  • in suites: jessie
  • size: 2,637,852 kB
  • ctags: 2,544,394
  • sloc: cpp: 12,815,961; ansic: 3,676,222; python: 1,147,112; asm: 526,608; java: 523,212; xml: 286,794; perl: 92,654; sh: 86,408; objc: 73,271; makefile: 27,698; cs: 18,487; yacc: 13,031; tcl: 12,957; pascal: 4,875; ml: 4,716; lex: 3,904; sql: 3,862; ruby: 1,982; lisp: 1,508; php: 1,368; exp: 404; awk: 325; csh: 117; jsp: 39; sed: 37
file content (76 lines) | stat: -rw-r--r-- 2,663 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
// Copyright 2014 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

// This module computes snippets of queries based on hits in the documents
// for display in history search results.

#ifndef COMPONENTS_QUERY_PARSER_SNIPPET_H__
#define COMPONENTS_QUERY_PARSER_SNIPPET_H__

#include <stddef.h>

#include <vector>

#include "base/strings/string16.h"

namespace query_parser {

class Snippet {
 public:
  // Each MatchPosition is the [begin, end) positions of a match within a
  // string.
  typedef std::pair<size_t, size_t> MatchPosition;
  typedef std::vector<MatchPosition> MatchPositions;

  // Parses an offsets string as returned from a sqlite full text index. An
  // offsets string encodes information about why a row matched a text query.
  // The information is encoded in the string as a set of matches, where each
  // match consists of the column, term-number, location, and length of the
  // match. Each element of the match is separated by a space, as is each match
  // from other matches.
  //
  // This method adds the start and end of each match whose column is
  // column_num to match_positions. The pairs are ordered based on first,
  // with no overlapping elements.
  //
  // NOTE: the positions returned are in terms of UTF8 encoding. To convert the
  // offsets to UTF-16, use ConvertMatchPositionsToWide
  static void ExtractMatchPositions(const std::string& offsets_str,
                                    const std::string& column_num,
                                    MatchPositions* match_positions);

  // Converts match positions as returned from ExtractMatchPositions to be in
  // terms of a UTF-16 2-byte code unit.
  static void ConvertMatchPositionsToWide(
      const std::string& utf8_string,
      Snippet::MatchPositions* match_positions);

  Snippet();
  Snippet(const Snippet& other);
  ~Snippet();

  // Given |matches|, the match positions within |document|, compute the snippet
  // for the document.
  // Note that |document| is UTF-8 and the offsets in |matches| are byte
  // offsets.
  void ComputeSnippet(const MatchPositions& matches,
                      const std::string& document);

  const base::string16& text() const { return text_; }
  const MatchPositions& matches() const { return matches_; }

  // Efficiently swaps the contents of this snippet with the other.
  void Swap(Snippet* other);

 private:
  // The text of the snippet.
  base::string16 text_;

  // The matches within text_.
  MatchPositions matches_;
};

}  // namespace query_parser

#endif  // COMPONENTS_QUERY_PARSER_SNIPPET_H__