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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
|
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Parse URLs (actually URIs, but that seems overly pedantic).
// RFC 3986
package http
import (
"os"
"strconv"
"strings"
)
// URLError reports an error and the operation and URL that caused it.
type URLError struct {
Op string
URL string
Error os.Error
}
func (e *URLError) String() string { return e.Op + " " + e.URL + ": " + e.Error.String() }
func ishex(c byte) bool {
switch {
case '0' <= c && c <= '9':
return true
case 'a' <= c && c <= 'f':
return true
case 'A' <= c && c <= 'F':
return true
}
return false
}
func unhex(c byte) byte {
switch {
case '0' <= c && c <= '9':
return c - '0'
case 'a' <= c && c <= 'f':
return c - 'a' + 10
case 'A' <= c && c <= 'F':
return c - 'A' + 10
}
return 0
}
type URLEscapeError string
func (e URLEscapeError) String() string {
return "invalid URL escape " + strconv.Quote(string(e))
}
// Return true if the specified character should be escaped when
// appearing in a URL string, according to RFC 2396.
func shouldEscape(c byte) bool {
if c <= ' ' || c >= 0x7F {
return true
}
switch c {
case '<', '>', '#', '%', '"', // RFC 2396 delims
'{', '}', '|', '\\', '^', '[', ']', '`', // RFC2396 unwise
'?', '&', '=', '+': // RFC 2396 reserved in path
return true
}
return false
}
// CanonicalPath applies the algorithm specified in RFC 2396 to
// simplify the path, removing unnecessary . and .. elements.
func CanonicalPath(path string) string {
buf := []byte(path)
a := buf[0:0]
// state helps to find /.. ^.. ^. and /. patterns.
// state == 1 - prev char is '/' or beginning of the string.
// state > 1 - prev state > 0 and prev char was '.'
// state == 0 - otherwise
state := 1
cnt := 0
for _, v := range buf {
switch v {
case '/':
s := state
state = 1
switch s {
case 2:
a = a[0 : len(a)-1]
continue
case 3:
if cnt > 0 {
i := len(a) - 4
for ; i >= 0 && a[i] != '/'; i-- {
}
a = a[0 : i+1]
cnt--
continue
}
default:
if len(a) > 0 {
cnt++
}
}
case '.':
if state > 0 {
state++
}
default:
state = 0
}
l := len(a)
a = a[0 : l+1]
a[l] = v
}
switch {
case state == 2:
a = a[0 : len(a)-1]
case state == 3 && cnt > 0:
i := len(a) - 4
for ; i >= 0 && a[i] != '/'; i-- {
}
a = a[0 : i+1]
}
return string(a)
}
// URLUnescape unescapes a URL-encoded string,
// converting %AB into the byte 0xAB and '+' into ' ' (space).
// It returns an error if any % is not followed
// by two hexadecimal digits.
func URLUnescape(s string) (string, os.Error) { return urlUnescape(s, true) }
// urlUnescape is like URLUnescape but can be told not to
// convert + into space. URLUnescape implements what is
// called "URL encoding" but that only applies to query strings.
// Elsewhere in the URL, + does not mean space.
func urlUnescape(s string, doPlus bool) (string, os.Error) {
// Count %, check that they're well-formed.
n := 0
hasPlus := false
for i := 0; i < len(s); {
switch s[i] {
case '%':
n++
if i+2 >= len(s) || !ishex(s[i+1]) || !ishex(s[i+2]) {
s = s[i:]
if len(s) > 3 {
s = s[0:3]
}
return "", URLEscapeError(s)
}
i += 3
case '+':
hasPlus = doPlus
i++
default:
i++
}
}
if n == 0 && !hasPlus {
return s, nil
}
t := make([]byte, len(s)-2*n)
j := 0
for i := 0; i < len(s); {
switch s[i] {
case '%':
t[j] = unhex(s[i+1])<<4 | unhex(s[i+2])
j++
i += 3
case '+':
if doPlus {
t[j] = ' '
} else {
t[j] = '+'
}
j++
i++
default:
t[j] = s[i]
j++
i++
}
}
return string(t), nil
}
// URLEscape converts a string into URL-encoded form.
func URLEscape(s string) string { return urlEscape(s, true) }
func urlEscape(s string, doPlus bool) string {
spaceCount, hexCount := 0, 0
for i := 0; i < len(s); i++ {
c := s[i]
if shouldEscape(c) {
if c == ' ' && doPlus {
spaceCount++
} else {
hexCount++
}
}
}
if spaceCount == 0 && hexCount == 0 {
return s
}
t := make([]byte, len(s)+2*hexCount)
j := 0
for i := 0; i < len(s); i++ {
switch c := s[i]; {
case c == ' ' && doPlus:
t[j] = '+'
j++
case shouldEscape(c):
t[j] = '%'
t[j+1] = "0123456789abcdef"[c>>4]
t[j+2] = "0123456789abcdef"[c&15]
j += 3
default:
t[j] = s[i]
j++
}
}
return string(t)
}
// A URL represents a parsed URL (technically, a URI reference).
// The general form represented is:
// scheme://[userinfo@]host/path[?query][#fragment]
// The Raw, RawPath, and RawQuery fields are in "wire format" (special
// characters must be hex-escaped if not meant to have special meaning).
// All other fields are logical values; '+' or '%' represent themselves.
//
// Note, the reason for using wire format for the query is that it needs
// to be split into key/value pairs before decoding.
type URL struct {
Raw string // the original string
Scheme string // scheme
Authority string // [userinfo@]host
Userinfo string // userinfo
Host string // host
RawPath string // /path[?query][#fragment]
Path string // /path
RawQuery string // query
Fragment string // fragment
}
// Maybe rawurl is of the form scheme:path.
// (Scheme must be [a-zA-Z][a-zA-Z0-9+-.]*)
// If so, return scheme, path; else return "", rawurl.
func getscheme(rawurl string) (scheme, path string, err os.Error) {
for i := 0; i < len(rawurl); i++ {
c := rawurl[i]
switch {
case 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z':
// do nothing
case '0' <= c && c <= '9' || c == '+' || c == '-' || c == '.':
if i == 0 {
return "", rawurl, nil
}
case c == ':':
if i == 0 {
return "", "", os.ErrorString("missing protocol scheme")
}
return rawurl[0:i], rawurl[i+1:], nil
default:
// we have encountered an invalid character,
// so there is no valid scheme
return "", rawurl, nil
}
}
return "", rawurl, nil
}
// Maybe s is of the form t c u.
// If so, return t, c u (or t, u if cutc == true).
// If not, return s, "".
func split(s string, c byte, cutc bool) (string, string) {
for i := 0; i < len(s); i++ {
if s[i] == c {
if cutc {
return s[0:i], s[i+1:]
}
return s[0:i], s[i:]
}
}
return s, ""
}
// ParseURL parses rawurl into a URL structure.
// The string rawurl is assumed not to have a #fragment suffix.
// (Web browsers strip #fragment before sending the URL to a web server.)
func ParseURL(rawurl string) (url *URL, err os.Error) {
if rawurl == "" {
err = os.ErrorString("empty url")
goto Error
}
url = new(URL)
url.Raw = rawurl
// split off possible leading "http:", "mailto:", etc.
var path string
if url.Scheme, path, err = getscheme(rawurl); err != nil {
goto Error
}
// RFC 2396: a relative URI (no scheme) has a ?query,
// but absolute URIs only have query if path begins with /
var query string
if url.Scheme == "" || len(path) > 0 && path[0] == '/' {
path, query = split(path, '?', false)
if len(query) > 1 {
url.RawQuery = query[1:]
}
}
// Maybe path is //authority/path
if len(path) > 2 && path[0:2] == "//" {
url.Authority, path = split(path[2:], '/', false)
}
url.RawPath = path + query
// If there's no @, split's default is wrong. Check explicitly.
if strings.Index(url.Authority, "@") < 0 {
url.Host = url.Authority
} else {
url.Userinfo, url.Host = split(url.Authority, '@', true)
}
if url.Path, err = urlUnescape(path, false); err != nil {
goto Error
}
// Remove escapes from the Authority and Userinfo fields, and verify
// that Scheme and Host contain no escapes (that would be illegal).
if url.Authority, err = urlUnescape(url.Authority, false); err != nil {
goto Error
}
if url.Userinfo, err = urlUnescape(url.Userinfo, false); err != nil {
goto Error
}
if strings.Index(url.Scheme, "%") >= 0 {
err = os.ErrorString("hexadecimal escape in scheme")
goto Error
}
if strings.Index(url.Host, "%") >= 0 {
err = os.ErrorString("hexadecimal escape in host")
goto Error
}
return url, nil
Error:
return nil, &URLError{"parse", rawurl, err}
}
// ParseURLReference is like ParseURL but allows a trailing #fragment.
func ParseURLReference(rawurlref string) (url *URL, err os.Error) {
// Cut off #frag.
rawurl, frag := split(rawurlref, '#', false)
if url, err = ParseURL(rawurl); err != nil {
return nil, err
}
url.Raw += frag
url.RawPath += frag
if len(frag) > 1 {
frag = frag[1:]
if url.Fragment, err = urlUnescape(frag, false); err != nil {
return nil, &URLError{"parse", rawurl, err}
}
}
return url, nil
}
// String reassembles url into a valid URL string.
//
// There are redundant fields stored in the URL structure:
// the String method consults Scheme, Path, Host, Userinfo,
// RawQuery, and Fragment, but not Raw, RawPath or Authority.
func (url *URL) String() string {
result := ""
if url.Scheme != "" {
result += url.Scheme + ":"
}
if url.Host != "" || url.Userinfo != "" {
result += "//"
if url.Userinfo != "" {
result += urlEscape(url.Userinfo, false) + "@"
}
result += url.Host
}
result += urlEscape(url.Path, false)
if url.RawQuery != "" {
result += "?" + url.RawQuery
}
if url.Fragment != "" {
result += "#" + urlEscape(url.Fragment, false)
}
return result
}
|