Mercurial > hg > Members > tobaru > cbc > CbC_llvm

annotate include/llvm/Support/UnicodeCharRanges.h @ 95:afa8332a0e37

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
LLVM 3.8
author Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
date Tue, 13 Oct 2015 17:48:58 +0900
parents 54457678186b
children 7d135dc70f03
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
1 //===--- UnicodeCharRanges.h - Types and functions for character ranges ---===//
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
2 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
3 // The LLVM Compiler Infrastructure
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
4 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
5 // This file is distributed under the University of Illinois Open Source
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
6 // License. See LICENSE.TXT for details.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
7 //
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
8 //===----------------------------------------------------------------------===//
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
9 #ifndef LLVM_SUPPORT_UNICODECHARRANGES_H
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
10 #define LLVM_SUPPORT_UNICODECHARRANGES_H
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
11
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
12 #include "llvm/ADT/ArrayRef.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
13 #include "llvm/ADT/SmallPtrSet.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
14 #include "llvm/Support/Compiler.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
15 #include "llvm/Support/Debug.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
16 #include "llvm/Support/Mutex.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
17 #include "llvm/Support/MutexGuard.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
18 #include "llvm/Support/raw_ostream.h"
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
19 #include <algorithm>
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
20
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
21 namespace llvm {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
22 namespace sys {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
23
77
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
24 #define DEBUG_TYPE "unicode"
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
25
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
26 /// \brief Represents a closed range of Unicode code points [Lower, Upper].
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
27 struct UnicodeCharRange {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
28 uint32_t Lower;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
29 uint32_t Upper;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
30 };
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
31
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
32 inline bool operator<(uint32_t Value, UnicodeCharRange Range) {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
33 return Value < Range.Lower;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
34 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
35 inline bool operator<(UnicodeCharRange Range, uint32_t Value) {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
36 return Range.Upper < Value;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
37 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
38
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
39 /// \brief Holds a reference to an ordered array of UnicodeCharRange and allows
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
40 /// to quickly check if a code point is contained in the set represented by this
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
41 /// array.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
42 class UnicodeCharSet {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
43 public:
77
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
44 typedef ArrayRef<UnicodeCharRange> CharRanges;
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
45
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
46 /// \brief Constructs a UnicodeCharSet instance from an array of
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
47 /// UnicodeCharRanges.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
48 ///
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
49 /// Array pointed by \p Ranges should have the lifetime at least as long as
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
50 /// the UnicodeCharSet instance, and should not change. Array is validated by
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
51 /// the constructor, so it makes sense to create as few UnicodeCharSet
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
52 /// instances per each array of ranges, as possible.
95
afa8332a0e37 LLVM 3.8
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
53 #ifdef NDEBUG
afa8332a0e37 LLVM 3.8
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
54 LLVM_CONSTEXPR UnicodeCharSet(CharRanges Ranges) : Ranges(Ranges) {}
afa8332a0e37 LLVM 3.8
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
55 #else
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
56 UnicodeCharSet(CharRanges Ranges) : Ranges(Ranges) {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
57 assert(rangesAreValid());
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
58 }
95
afa8332a0e37 LLVM 3.8
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 77
diff changeset
59 #endif
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
60
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
61 /// \brief Returns true if the character set contains the Unicode code point
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
62 /// \p C.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
63 bool contains(uint32_t C) const {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
64 return std::binary_search(Ranges.begin(), Ranges.end(), C);
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
65 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
66
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
67 private:
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
68 /// \brief Returns true if each of the ranges is a proper closed range
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
69 /// [min, max], and if the ranges themselves are ordered and non-overlapping.
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
70 bool rangesAreValid() const {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
71 uint32_t Prev = 0;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
72 for (CharRanges::const_iterator I = Ranges.begin(), E = Ranges.end();
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
73 I != E; ++I) {
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
74 if (I != Ranges.begin() && Prev >= I->Lower) {
77
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
75 DEBUG(dbgs() << "Upper bound 0x");
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
76 DEBUG(dbgs().write_hex(Prev));
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
77 DEBUG(dbgs() << " should be less than succeeding lower bound 0x");
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
78 DEBUG(dbgs().write_hex(I->Lower) << "\n");
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
79 return false;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
80 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
81 if (I->Upper < I->Lower) {
77
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
82 DEBUG(dbgs() << "Upper bound 0x");
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
83 DEBUG(dbgs().write_hex(I->Lower));
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
84 DEBUG(dbgs() << " should not be less than lower bound 0x");
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
85 DEBUG(dbgs().write_hex(I->Upper) << "\n");
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
86 return false;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
87 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
88 Prev = I->Upper;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
89 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
90
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
91 return true;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
92 }
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
93
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
94 const CharRanges Ranges;
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
95 };
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
96
77
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
97 #undef DEBUG_TYPE // "unicode"
54457678186b LLVM 3.6
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents: 0
diff changeset
98
0
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
99 } // namespace sys
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
100 } // namespace llvm
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
101
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
102
95c75e76d11b LLVM 3.4
Kaito Tokumori <e105711@ie.u-ryukyu.ac.jp>
parents:
diff changeset
103 #endif // LLVM_SUPPORT_UNICODECHARRANGES_H