lbug 0.16.1

An in-process property graph database management system built for query speed and scalability
Documentation 
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

// Copyright 2008 The RE2 Authors.  All Rights Reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

#ifndef RE2_UNICODE_GROUPS_H_
#define RE2_UNICODE_GROUPS_H_

// Unicode character groups.

// The codes get split into ranges of 16-bit codes
// and ranges of 32-bit codes.  It would be simpler
// to use only 32-bit ranges, but these tables are large
// enough to warrant extra care.
//
// Using just 32-bit ranges gives 27 kB of data.
// Adding 16-bit ranges gives 18 kB of data.
// Adding an extra table of 16-bit singletons would reduce
// to 16.5 kB of data but make the data harder to use;
// we don't bother.

#include <stdint.h>

#include "utf.h"
#include "util.h"

namespace lbug {
namespace regex {

struct URange16 {
    uint16_t lo;
    uint16_t hi;
};

struct URange32 {
    Rune lo;
    Rune hi;
};

struct UGroup {
    const char* name;
    int sign; // +1 for [abc], -1 for [^abc]
    const URange16* r16;
    int nr16;
    const URange32* r32;
    int nr32;
};

// Named by property or script name (e.g., "Nd", "N", "Han").
// Negated groups are not included.
extern const UGroup unicode_groups[];
extern const int num_unicode_groups;

// Named by POSIX name (e.g., "[:alpha:]", "[:^lower:]").
// Negated groups are included.
extern const UGroup posix_groups[];
extern const int num_posix_groups;

// Named by Perl name (e.g., "\\d", "\\D").
// Negated groups are included.
extern const UGroup perl_groups[];
extern const int num_perl_groups;

} // namespace regex
} // namespace lbug
#endif // RE2_UNICODE_GROUPS_H_