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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
|
diff --git a/absl/strings/ascii.cc b/absl/strings/ascii.cc
index abea3e4..16d0bcc 100644
--- a/absl/strings/ascii.cc
+++ b/absl/strings/ascii.cc
@@ -51,108 +51,6 @@ namespace ascii_internal {
// elif i % 16 == 15:
// print
-// clang-format off
-// Array of bitfields holding character information. Each bit value corresponds
-// to a particular character feature. For readability, and because the value
-// of these bits is tightly coupled to this implementation, the individual bits
-// are not named. Note that bitfields for all characters above ASCII 127 are
-// zero-initialized.
-const unsigned char kPropertyBits[256] = {
- 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x00
- 0x40, 0x68, 0x48, 0x48, 0x48, 0x48, 0x40, 0x40,
- 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x10
- 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
- 0x28, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, // 0x20
- 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
- 0x84, 0x84, 0x84, 0x84, 0x84, 0x84, 0x84, 0x84, // 0x30
- 0x84, 0x84, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
- 0x10, 0x85, 0x85, 0x85, 0x85, 0x85, 0x85, 0x05, // 0x40
- 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05,
- 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, // 0x50
- 0x05, 0x05, 0x05, 0x10, 0x10, 0x10, 0x10, 0x10,
- 0x10, 0x85, 0x85, 0x85, 0x85, 0x85, 0x85, 0x05, // 0x60
- 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05,
- 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, // 0x70
- 0x05, 0x05, 0x05, 0x10, 0x10, 0x10, 0x10, 0x40,
-};
-
-// Array of characters for the ascii_tolower() function. For values 'A'
-// through 'Z', return the lower-case character; otherwise, return the
-// identity of the passed character.
-const char kToLower[256] = {
- '\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',
- '\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
- '\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',
- '\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
- '\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',
- '\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
- '\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',
- '\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
- '\x40', 'a', 'b', 'c', 'd', 'e', 'f', 'g',
- 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',
- 'p', 'q', 'r', 's', 't', 'u', 'v', 'w',
- 'x', 'y', 'z', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
- '\x60', '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67',
- '\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f',
- '\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77',
- '\x78', '\x79', '\x7a', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f',
- '\x80', '\x81', '\x82', '\x83', '\x84', '\x85', '\x86', '\x87',
- '\x88', '\x89', '\x8a', '\x8b', '\x8c', '\x8d', '\x8e', '\x8f',
- '\x90', '\x91', '\x92', '\x93', '\x94', '\x95', '\x96', '\x97',
- '\x98', '\x99', '\x9a', '\x9b', '\x9c', '\x9d', '\x9e', '\x9f',
- '\xa0', '\xa1', '\xa2', '\xa3', '\xa4', '\xa5', '\xa6', '\xa7',
- '\xa8', '\xa9', '\xaa', '\xab', '\xac', '\xad', '\xae', '\xaf',
- '\xb0', '\xb1', '\xb2', '\xb3', '\xb4', '\xb5', '\xb6', '\xb7',
- '\xb8', '\xb9', '\xba', '\xbb', '\xbc', '\xbd', '\xbe', '\xbf',
- '\xc0', '\xc1', '\xc2', '\xc3', '\xc4', '\xc5', '\xc6', '\xc7',
- '\xc8', '\xc9', '\xca', '\xcb', '\xcc', '\xcd', '\xce', '\xcf',
- '\xd0', '\xd1', '\xd2', '\xd3', '\xd4', '\xd5', '\xd6', '\xd7',
- '\xd8', '\xd9', '\xda', '\xdb', '\xdc', '\xdd', '\xde', '\xdf',
- '\xe0', '\xe1', '\xe2', '\xe3', '\xe4', '\xe5', '\xe6', '\xe7',
- '\xe8', '\xe9', '\xea', '\xeb', '\xec', '\xed', '\xee', '\xef',
- '\xf0', '\xf1', '\xf2', '\xf3', '\xf4', '\xf5', '\xf6', '\xf7',
- '\xf8', '\xf9', '\xfa', '\xfb', '\xfc', '\xfd', '\xfe', '\xff',
-};
-
-// Array of characters for the ascii_toupper() function. For values 'a'
-// through 'z', return the upper-case character; otherwise, return the
-// identity of the passed character.
-const char kToUpper[256] = {
- '\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',
- '\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
- '\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',
- '\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
- '\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',
- '\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
- '\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',
- '\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
- '\x40', '\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47',
- '\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f',
- '\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57',
- '\x58', '\x59', '\x5a', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
- '\x60', 'A', 'B', 'C', 'D', 'E', 'F', 'G',
- 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O',
- 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W',
- 'X', 'Y', 'Z', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f',
- '\x80', '\x81', '\x82', '\x83', '\x84', '\x85', '\x86', '\x87',
- '\x88', '\x89', '\x8a', '\x8b', '\x8c', '\x8d', '\x8e', '\x8f',
- '\x90', '\x91', '\x92', '\x93', '\x94', '\x95', '\x96', '\x97',
- '\x98', '\x99', '\x9a', '\x9b', '\x9c', '\x9d', '\x9e', '\x9f',
- '\xa0', '\xa1', '\xa2', '\xa3', '\xa4', '\xa5', '\xa6', '\xa7',
- '\xa8', '\xa9', '\xaa', '\xab', '\xac', '\xad', '\xae', '\xaf',
- '\xb0', '\xb1', '\xb2', '\xb3', '\xb4', '\xb5', '\xb6', '\xb7',
- '\xb8', '\xb9', '\xba', '\xbb', '\xbc', '\xbd', '\xbe', '\xbf',
- '\xc0', '\xc1', '\xc2', '\xc3', '\xc4', '\xc5', '\xc6', '\xc7',
- '\xc8', '\xc9', '\xca', '\xcb', '\xcc', '\xcd', '\xce', '\xcf',
- '\xd0', '\xd1', '\xd2', '\xd3', '\xd4', '\xd5', '\xd6', '\xd7',
- '\xd8', '\xd9', '\xda', '\xdb', '\xdc', '\xdd', '\xde', '\xdf',
- '\xe0', '\xe1', '\xe2', '\xe3', '\xe4', '\xe5', '\xe6', '\xe7',
- '\xe8', '\xe9', '\xea', '\xeb', '\xec', '\xed', '\xee', '\xef',
- '\xf0', '\xf1', '\xf2', '\xf3', '\xf4', '\xf5', '\xf6', '\xf7',
- '\xf8', '\xf9', '\xfa', '\xfb', '\xfc', '\xfd', '\xfe', '\xff',
-};
-// clang-format on
-
} // namespace ascii_internal
void AsciiStrToLower(std::string* s) {
diff --git a/absl/strings/ascii.h b/absl/strings/ascii.h
index 792aabe..989e464 100644
--- a/absl/strings/ascii.h
+++ b/absl/strings/ascii.h
@@ -62,14 +62,105 @@ namespace absl {
ABSL_NAMESPACE_BEGIN
namespace ascii_internal {
-// Declaration for an array of bitfields holding character information.
-extern const unsigned char kPropertyBits[256];
-
-// Declaration for the array of characters to upper-case characters.
-extern const char kToUpper[256];
-
-// Declaration for the array of characters to lower-case characters.
-extern const char kToLower[256];
+// Array of bitfields holding character information. Each bit value corresponds
+// to a particular character feature. For readability, and because the value
+// of these bits is tightly coupled to this implementation, the individual bits
+// are not named. Note that bitfields for all characters above ASCII 127 are
+// zero-initialized.
+const unsigned char kPropertyBits[256] = {
+ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x00
+ 0x40, 0x68, 0x48, 0x48, 0x48, 0x48, 0x40, 0x40,
+ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, // 0x10
+ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
+ 0x28, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, // 0x20
+ 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+ 0x84, 0x84, 0x84, 0x84, 0x84, 0x84, 0x84, 0x84, // 0x30
+ 0x84, 0x84, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x85, 0x85, 0x85, 0x85, 0x85, 0x85, 0x05, // 0x40
+ 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05,
+ 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, // 0x50
+ 0x05, 0x05, 0x05, 0x10, 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x85, 0x85, 0x85, 0x85, 0x85, 0x85, 0x05, // 0x60
+ 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05,
+ 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, // 0x70
+ 0x05, 0x05, 0x05, 0x10, 0x10, 0x10, 0x10, 0x40,
+};
+
+// Array of characters for the ascii_tolower() function. For values 'A'
+// through 'Z', return the lower-case character; otherwise, return the
+// identity of the passed character.
+const char kToLower[256] = {
+ '\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',
+ '\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
+ '\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',
+ '\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
+ '\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',
+ '\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
+ '\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',
+ '\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
+ '\x40', 'a', 'b', 'c', 'd', 'e', 'f', 'g',
+ 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',
+ 'p', 'q', 'r', 's', 't', 'u', 'v', 'w',
+ 'x', 'y', 'z', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
+ '\x60', '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67',
+ '\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f',
+ '\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77',
+ '\x78', '\x79', '\x7a', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f',
+ '\x80', '\x81', '\x82', '\x83', '\x84', '\x85', '\x86', '\x87',
+ '\x88', '\x89', '\x8a', '\x8b', '\x8c', '\x8d', '\x8e', '\x8f',
+ '\x90', '\x91', '\x92', '\x93', '\x94', '\x95', '\x96', '\x97',
+ '\x98', '\x99', '\x9a', '\x9b', '\x9c', '\x9d', '\x9e', '\x9f',
+ '\xa0', '\xa1', '\xa2', '\xa3', '\xa4', '\xa5', '\xa6', '\xa7',
+ '\xa8', '\xa9', '\xaa', '\xab', '\xac', '\xad', '\xae', '\xaf',
+ '\xb0', '\xb1', '\xb2', '\xb3', '\xb4', '\xb5', '\xb6', '\xb7',
+ '\xb8', '\xb9', '\xba', '\xbb', '\xbc', '\xbd', '\xbe', '\xbf',
+ '\xc0', '\xc1', '\xc2', '\xc3', '\xc4', '\xc5', '\xc6', '\xc7',
+ '\xc8', '\xc9', '\xca', '\xcb', '\xcc', '\xcd', '\xce', '\xcf',
+ '\xd0', '\xd1', '\xd2', '\xd3', '\xd4', '\xd5', '\xd6', '\xd7',
+ '\xd8', '\xd9', '\xda', '\xdb', '\xdc', '\xdd', '\xde', '\xdf',
+ '\xe0', '\xe1', '\xe2', '\xe3', '\xe4', '\xe5', '\xe6', '\xe7',
+ '\xe8', '\xe9', '\xea', '\xeb', '\xec', '\xed', '\xee', '\xef',
+ '\xf0', '\xf1', '\xf2', '\xf3', '\xf4', '\xf5', '\xf6', '\xf7',
+ '\xf8', '\xf9', '\xfa', '\xfb', '\xfc', '\xfd', '\xfe', '\xff',
+};
+
+// Array of characters for the ascii_toupper() function. For values 'a'
+// through 'z', return the upper-case character; otherwise, return the
+// identity of the passed character.
+const char kToUpper[256] = {
+ '\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',
+ '\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
+ '\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',
+ '\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
+ '\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',
+ '\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
+ '\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',
+ '\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
+ '\x40', '\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47',
+ '\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f',
+ '\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57',
+ '\x58', '\x59', '\x5a', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
+ '\x60', 'A', 'B', 'C', 'D', 'E', 'F', 'G',
+ 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O',
+ 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W',
+ 'X', 'Y', 'Z', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f',
+ '\x80', '\x81', '\x82', '\x83', '\x84', '\x85', '\x86', '\x87',
+ '\x88', '\x89', '\x8a', '\x8b', '\x8c', '\x8d', '\x8e', '\x8f',
+ '\x90', '\x91', '\x92', '\x93', '\x94', '\x95', '\x96', '\x97',
+ '\x98', '\x99', '\x9a', '\x9b', '\x9c', '\x9d', '\x9e', '\x9f',
+ '\xa0', '\xa1', '\xa2', '\xa3', '\xa4', '\xa5', '\xa6', '\xa7',
+ '\xa8', '\xa9', '\xaa', '\xab', '\xac', '\xad', '\xae', '\xaf',
+ '\xb0', '\xb1', '\xb2', '\xb3', '\xb4', '\xb5', '\xb6', '\xb7',
+ '\xb8', '\xb9', '\xba', '\xbb', '\xbc', '\xbd', '\xbe', '\xbf',
+ '\xc0', '\xc1', '\xc2', '\xc3', '\xc4', '\xc5', '\xc6', '\xc7',
+ '\xc8', '\xc9', '\xca', '\xcb', '\xcc', '\xcd', '\xce', '\xcf',
+ '\xd0', '\xd1', '\xd2', '\xd3', '\xd4', '\xd5', '\xd6', '\xd7',
+ '\xd8', '\xd9', '\xda', '\xdb', '\xdc', '\xdd', '\xde', '\xdf',
+ '\xe0', '\xe1', '\xe2', '\xe3', '\xe4', '\xe5', '\xe6', '\xe7',
+ '\xe8', '\xe9', '\xea', '\xeb', '\xec', '\xed', '\xee', '\xef',
+ '\xf0', '\xf1', '\xf2', '\xf3', '\xf4', '\xf5', '\xf6', '\xf7',
+ '\xf8', '\xf9', '\xfa', '\xfb', '\xfc', '\xfd', '\xfe', '\xff',
+};
} // namespace ascii_internal
|
