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
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
|
const std = @import("std");
/// Do an in-place decode of a string that has been encoded in the same way
/// that `bash`'s `printf %q` encodes a string. This is safe because a string
/// can only get shorter after decoding. This destructively modifies the buffer
/// given to it. If an error is returned the buffer may be in an unusable state.
pub fn printfQDecode(buf: [:0]u8) error{DecodeError}![:0]const u8 {
const data: [:0]u8 = data: {
// Strip off `$''` quoting.
if (std.mem.startsWith(u8, buf, "$'")) {
if (buf.len < 3 or !std.mem.endsWith(u8, buf, "'")) return error.DecodeError;
buf[buf.len - 1] = 0;
break :data buf[2 .. buf.len - 1 :0];
}
// Strip off `''` quoting.
if (std.mem.startsWith(u8, buf, "'")) {
if (buf.len < 2 or !std.mem.endsWith(u8, buf, "'")) return error.DecodeError;
buf[buf.len - 1] = 0;
break :data buf[1 .. buf.len - 1 :0];
}
break :data buf;
};
var src: usize = 0;
var dst: usize = 0;
while (src < data.len) {
switch (data[src]) {
else => {
data[dst] = data[src];
src += 1;
dst += 1;
},
'\\' => {
if (src + 1 >= data.len) return error.DecodeError;
switch (data[src + 1]) {
' ',
'\\',
'"',
'\'',
'$',
=> |c| {
data[dst] = c;
src += 2;
dst += 1;
},
'e' => {
data[dst] = std.ascii.control_code.esc;
src += 2;
dst += 1;
},
'n' => {
data[dst] = std.ascii.control_code.lf;
src += 2;
dst += 1;
},
'r' => {
data[dst] = std.ascii.control_code.cr;
src += 2;
dst += 1;
},
't' => {
data[dst] = std.ascii.control_code.ht;
src += 2;
dst += 1;
},
'v' => {
data[dst] = std.ascii.control_code.vt;
src += 2;
dst += 1;
},
else => return error.DecodeError,
}
},
}
}
data[dst] = 0;
return data[0..dst :0];
}
test "printf_q 1" {
const s: [:0]const u8 = "bobr\\ kurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
const dst = try printfQDecode(&src);
try std.testing.expectEqualStrings("bobr kurwa", dst);
}
test "printf_q 2" {
const s: [:0]const u8 = "bobr\\nkurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
const dst = try printfQDecode(&src);
try std.testing.expectEqualStrings("bobr\nkurwa", dst);
}
test "printf_q 3" {
const s: [:0]const u8 = "bobr\\dkurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, printfQDecode(&src));
}
test "printf_q 4" {
const s: [:0]const u8 = "bobr kurwa\\";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, printfQDecode(&src));
}
test "printf_q 5" {
const s: [:0]const u8 = "$'bobr kurwa'";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
const dst = try printfQDecode(&src);
try std.testing.expectEqualStrings("bobr kurwa", dst);
}
test "printf_q 6" {
const s: [:0]const u8 = "'bobr kurwa'";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
const dst = try printfQDecode(&src);
try std.testing.expectEqualStrings("bobr kurwa", dst);
}
test "printf_q 7" {
const s: [:0]const u8 = "$'bobr kurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, printfQDecode(&src));
}
test "printf_q 8" {
const s: [:0]const u8 = "$'";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, printfQDecode(&src));
}
test "printf_q 9" {
const s: [:0]const u8 = "'bobr kurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, printfQDecode(&src));
}
test "printf_q 10" {
const s: [:0]const u8 = "'";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, printfQDecode(&src));
}
/// Do an in-place decode of a string that has been URL percent encoded.
/// This is safe because a string can only get shorter after decoding. This
/// destructively modifies the buffer given to it. If an error is returned the
/// buffer may be in an unusable state.
pub fn urlPercentDecode(buf: [:0]u8) error{DecodeError}![:0]const u8 {
var src: usize = 0;
var dst: usize = 0;
while (src < buf.len) {
switch (buf[src]) {
else => {
buf[dst] = buf[src];
src += 1;
dst += 1;
},
'%' => {
if (src + 2 >= buf.len) return error.DecodeError;
switch (buf[src + 1]) {
'0'...'9', 'a'...'f', 'A'...'F' => {
switch (buf[src + 2]) {
'0'...'9', 'a'...'f', 'A'...'F' => {
buf[dst] = std.math.shl(u8, hex(buf[src + 1]), 4) | hex(buf[src + 2]);
src += 3;
dst += 1;
},
else => return error.DecodeError,
}
},
else => return error.DecodeError,
}
},
}
}
buf[dst] = 0;
return buf[0..dst :0];
}
inline fn hex(c: u8) u4 {
switch (c) {
'0'...'9' => return @truncate(c - '0'),
'a'...'f' => return @truncate(c - 'a' + 10),
'A'...'F' => return @truncate(c - 'A' + 10),
else => unreachable,
}
}
test "singles percent" {
for (0..255) |c| {
var buf_: [4]u8 = undefined;
const buf = try std.fmt.bufPrintZ(&buf_, "%{x:0>2}", .{c});
const decoded = try urlPercentDecode(buf);
try std.testing.expectEqual(1, decoded.len);
try std.testing.expectEqual(c, decoded[0]);
}
for (0..255) |c| {
var buf_: [4]u8 = undefined;
const buf = try std.fmt.bufPrintZ(&buf_, "%{X:0>2}", .{c});
const decoded = try urlPercentDecode(buf);
try std.testing.expectEqual(1, decoded.len);
try std.testing.expectEqual(c, decoded[0]);
}
}
test "percent 1" {
const s: [:0]const u8 = "bobr%20kurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
const dst = try urlPercentDecode(&src);
try std.testing.expectEqualStrings("bobr kurwa", dst);
}
test "percent 2" {
const s: [:0]const u8 = "bobr%2kurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, urlPercentDecode(&src));
}
test "percent 3" {
const s: [:0]const u8 = "bobr%kurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, urlPercentDecode(&src));
}
test "percent 4" {
const s: [:0]const u8 = "bobr%%kurwa";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, urlPercentDecode(&src));
}
test "percent 5" {
const s: [:0]const u8 = "bobr%20kurwa%20";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
const dst = try urlPercentDecode(&src);
try std.testing.expectEqualStrings("bobr kurwa ", dst);
}
test "percent 6" {
const s: [:0]const u8 = "bobr%20kurwa%2";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, urlPercentDecode(&src));
}
test "percent 7" {
const s: [:0]const u8 = "bobr%20kurwa%";
var src: [s.len:0]u8 = undefined;
@memcpy(&src, s);
try std.testing.expectError(error.DecodeError, urlPercentDecode(&src));
}
|
