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
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
|
// Copyright (c) 2009 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.
// File utilities that use the ICU library go in this file. Functions using ICU
// are separated from the other functions to prevent ICU being pulled in by the
// linker if there is a false dependency.
//
// (The VS2005 linker finds such a false dependency and adds ~300K of ICU to
// chrome.exe if this code lives in file_util.cc, even though none of this code
// is called.)
#include "base/file_util.h"
#include "base/singleton.h"
#include "base/string_util.h"
#include "unicode/uniset.h"
namespace {
class IllegalCharacters {
public:
bool contains(UChar32 ucs4) {
return !!set->contains(ucs4);
}
bool containsNone(const string16 &s) {
return !!set->containsNone(icu::UnicodeString(s.c_str(), s.size()));
}
private:
friend class Singleton<IllegalCharacters>;
friend struct DefaultSingletonTraits<IllegalCharacters>;
IllegalCharacters();
~IllegalCharacters() { }
scoped_ptr<icu::UnicodeSet> set;
DISALLOW_COPY_AND_ASSIGN(IllegalCharacters);
};
IllegalCharacters::IllegalCharacters() {
UErrorCode status = U_ZERO_ERROR;
// Control characters, formatting characters, non-characters, and
// some printable ASCII characters regarded as dangerous ('"*/:<>?\\').
// See http://blogs.msdn.com/michkap/archive/2006/11/03/941420.aspx
// and http://msdn2.microsoft.com/en-us/library/Aa365247.aspx
// TODO(jungshik): Revisit the set. ZWJ and ZWNJ are excluded because they
// are legitimate in Arabic and some S/SE Asian scripts. However, when used
// elsewhere, they can be confusing/problematic.
// Also, consider wrapping the set with our Singleton class to create and
// freeze it only once. Note that there's a trade-off between memory and
// speed.
#if defined(WCHAR_T_IS_UTF16)
set.reset(new icu::UnicodeSet(icu::UnicodeString(
L"[[\"*/:<>?\\\\|][:Cc:][:Cf:] - [\u200c\u200d]]"), status));
#else
set.reset(new icu::UnicodeSet(UNICODE_STRING_SIMPLE(
"[[\"*/:<>?\\\\|][:Cc:][:Cf:] - [\\u200c\\u200d]]").unescape(),
status));
#endif
DCHECK(U_SUCCESS(status));
// Add non-characters. If this becomes a performance bottleneck by
// any chance, do not add these to |set| and change IsFilenameLegal()
// to check |ucs4 & 0xFFFEu == 0xFFFEu|, in addiition to calling
// containsNone().
set->add(0xFDD0, 0xFDEF);
for (int i = 0; i <= 0x10; ++i) {
int plane_base = 0x10000 * i;
set->add(plane_base + 0xFFFE, plane_base + 0xFFFF);
}
set->freeze();
}
} // namespace
namespace file_util {
bool IsFilenameLegal(const string16& file_name) {
return Singleton<IllegalCharacters>()->containsNone(file_name);
}
void ReplaceIllegalCharacters(std::wstring* file_name, int replace_char) {
DCHECK(file_name);
DCHECK(!(Singleton<IllegalCharacters>()->contains(replace_char)) &&
replace_char < 0x10000);
// Remove leading and trailing whitespace.
TrimWhitespace(*file_name, TRIM_ALL, file_name);
if (IsFilenameLegal(WideToUTF16(*file_name)))
return;
std::wstring::size_type i = 0;
std::wstring::size_type length = file_name->size();
const wchar_t* wstr = file_name->data();
#if defined(WCHAR_T_IS_UTF16)
// Using |span| method of UnicodeSet might speed things up a bit, but
// it's not likely to matter here.
std::wstring temp;
temp.reserve(length);
while (i < length) {
UChar32 ucs4;
std::wstring::size_type prev = i;
U16_NEXT(wstr, i, length, ucs4);
if (Singleton<IllegalCharacters>()->contains(ucs4)) {
temp.push_back(replace_char);
} else if (ucs4 < 0x10000) {
temp.push_back(ucs4);
} else {
temp.push_back(wstr[prev]);
temp.push_back(wstr[prev + 1]);
}
}
file_name->swap(temp);
#elif defined(WCHAR_T_IS_UTF32)
while (i < length) {
if (Singleton<IllegalCharacters>()->contains(wstr[i])) {
(*file_name)[i] = replace_char;
}
++i;
}
#else
#error wchar_t* should be either UTF-16 or UTF-32
#endif
}
} // namespace
|
