purell.go 11.7 KB
Newer Older
ale's avatar
ale committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
/*
Package purell offers URL normalization as described on the wikipedia page:
http://en.wikipedia.org/wiki/URL_normalization
*/
package purell

import (
	"bytes"
	"fmt"
	"net/url"
	"regexp"
	"sort"
	"strconv"
	"strings"
)

// A set of normalization flags determines how a URL will
// be normalized.
type NormalizationFlags uint

const (
	// Safe normalizations
23
	FlagLowercaseScheme           NormalizationFlags = 1 << iota // HTTP://host -> http://host
ale's avatar
ale committed
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
	FlagLowercaseHost                                            // http://HOST -> http://host
	FlagUppercaseEscapes                                         // http://host/t%ef -> http://host/t%EF
	FlagDecodeUnnecessaryEscapes                                 // http://host/t%41 -> http://host/tA
	FlagEncodeNecessaryEscapes                                   // http://host/!"#$ -> http://host/%21%22#$
	FlagRemoveDefaultPort                                        // http://host:80 -> http://host
	FlagRemoveEmptyQuerySeparator                                // http://host/path? -> http://host/path

	// Usually safe normalizations
	FlagRemoveTrailingSlash // http://host/path/ -> http://host/path
	FlagAddTrailingSlash    // http://host/path -> http://host/path/ (should choose only one of these add/remove trailing slash flags)
	FlagRemoveDotSegments   // http://host/path/./a/b/../c -> http://host/path/a/c

	// Unsafe normalizations
	FlagRemoveDirectoryIndex   // http://host/path/index.html -> http://host/path/
	FlagRemoveFragment         // http://host/path#fragment -> http://host/path
	FlagForceHTTP              // https://host -> http://host
	FlagRemoveDuplicateSlashes // http://host/path//a///b -> http://host/path/a/b
	FlagRemoveWWW              // http://www.host/ -> http://host/
	FlagAddWWW                 // http://host/ -> http://www.host/ (should choose only one of these add/remove WWW flags)
	FlagSortQuery              // http://host/path?c=3&b=2&a=1&b=1 -> http://host/path?a=1&b=1&b=2&c=3

	// Normalizations not in the wikipedia article, required to cover tests cases
	// submitted by jehiah
	FlagDecodeDWORDHost           // http://1113982867 -> http://66.102.7.147
	FlagDecodeOctalHost           // http://0102.0146.07.0223 -> http://66.102.7.147
	FlagDecodeHexHost             // http://0x42660793 -> http://66.102.7.147
	FlagRemoveUnnecessaryHostDots // http://.host../path -> http://host/path
	FlagRemoveEmptyPortSeparator  // http://host:/path -> http://host/path

	// Convenience set of safe normalizations
	FlagsSafe NormalizationFlags = FlagLowercaseHost | FlagLowercaseScheme | FlagUppercaseEscapes | FlagDecodeUnnecessaryEscapes | FlagEncodeNecessaryEscapes | FlagRemoveDefaultPort | FlagRemoveEmptyQuerySeparator

	// For convenience sets, "greedy" uses the "remove trailing slash" and "remove www. prefix" flags,
	// while "non-greedy" uses the "add (or keep) the trailing slash" and "add www. prefix".

	// Convenience set of usually safe normalizations (includes FlagsSafe)
	FlagsUsuallySafeGreedy    NormalizationFlags = FlagsSafe | FlagRemoveTrailingSlash | FlagRemoveDotSegments
	FlagsUsuallySafeNonGreedy NormalizationFlags = FlagsSafe | FlagAddTrailingSlash | FlagRemoveDotSegments

	// Convenience set of unsafe normalizations (includes FlagsUsuallySafe)
	FlagsUnsafeGreedy    NormalizationFlags = FlagsUsuallySafeGreedy | FlagRemoveDirectoryIndex | FlagRemoveFragment | FlagForceHTTP | FlagRemoveDuplicateSlashes | FlagRemoveWWW | FlagSortQuery
	FlagsUnsafeNonGreedy NormalizationFlags = FlagsUsuallySafeNonGreedy | FlagRemoveDirectoryIndex | FlagRemoveFragment | FlagForceHTTP | FlagRemoveDuplicateSlashes | FlagAddWWW | FlagSortQuery

	// Convenience set of all available flags
	FlagsAllGreedy    = FlagsUnsafeGreedy | FlagDecodeDWORDHost | FlagDecodeOctalHost | FlagDecodeHexHost | FlagRemoveUnnecessaryHostDots | FlagRemoveEmptyPortSeparator
	FlagsAllNonGreedy = FlagsUnsafeNonGreedy | FlagDecodeDWORDHost | FlagDecodeOctalHost | FlagDecodeHexHost | FlagRemoveUnnecessaryHostDots | FlagRemoveEmptyPortSeparator
)

const (
	defaultHttpPort  = ":80"
	defaultHttpsPort = ":443"
)

// Regular expressions used by the normalizations
var rxPort = regexp.MustCompile(`(:\d+)/?$`)
var rxDirIndex = regexp.MustCompile(`(^|/)((?:default|index)\.\w{1,4})$`)
var rxDupSlashes = regexp.MustCompile(`/{2,}`)
var rxDWORDHost = regexp.MustCompile(`^(\d+)((?:\.+)?(?:\:\d*)?)$`)
var rxOctalHost = regexp.MustCompile(`^(0\d*)\.(0\d*)\.(0\d*)\.(0\d*)((?:\.+)?(?:\:\d*)?)$`)
var rxHexHost = regexp.MustCompile(`^0x([0-9A-Fa-f]+)((?:\.+)?(?:\:\d*)?)$`)
var rxHostDots = regexp.MustCompile(`^(.+?)(:\d+)?$`)
var rxEmptyPort = regexp.MustCompile(`:+$`)

// Map of flags to implementation function.
// FlagDecodeUnnecessaryEscapes has no action, since it is done automatically
// by parsing the string as an URL. Same for FlagUppercaseEscapes and FlagRemoveEmptyQuerySeparator.

// Since maps have undefined traversing order, make a slice of ordered keys
var flagsOrder = []NormalizationFlags{
	FlagLowercaseScheme,
	FlagLowercaseHost,
	FlagRemoveDefaultPort,
	FlagRemoveDirectoryIndex,
	FlagRemoveDotSegments,
	FlagRemoveFragment,
	FlagForceHTTP, // Must be after remove default port (because https=443/http=80)
	FlagRemoveDuplicateSlashes,
	FlagRemoveWWW,
	FlagAddWWW,
	FlagSortQuery,
	FlagDecodeDWORDHost,
	FlagDecodeOctalHost,
	FlagDecodeHexHost,
	FlagRemoveUnnecessaryHostDots,
	FlagRemoveEmptyPortSeparator,
	FlagRemoveTrailingSlash, // These two (add/remove trailing slash) must be last
	FlagAddTrailingSlash,
}

// ... and then the map, where order is unimportant
var flags = map[NormalizationFlags]func(*url.URL){
	FlagLowercaseScheme:           lowercaseScheme,
	FlagLowercaseHost:             lowercaseHost,
	FlagRemoveDefaultPort:         removeDefaultPort,
	FlagRemoveDirectoryIndex:      removeDirectoryIndex,
	FlagRemoveDotSegments:         removeDotSegments,
	FlagRemoveFragment:            removeFragment,
	FlagForceHTTP:                 forceHTTP,
	FlagRemoveDuplicateSlashes:    removeDuplicateSlashes,
	FlagRemoveWWW:                 removeWWW,
	FlagAddWWW:                    addWWW,
	FlagSortQuery:                 sortQuery,
	FlagDecodeDWORDHost:           decodeDWORDHost,
	FlagDecodeOctalHost:           decodeOctalHost,
	FlagDecodeHexHost:             decodeHexHost,
	FlagRemoveUnnecessaryHostDots: removeUnncessaryHostDots,
	FlagRemoveEmptyPortSeparator:  removeEmptyPortSeparator,
	FlagRemoveTrailingSlash:       removeTrailingSlash,
	FlagAddTrailingSlash:          addTrailingSlash,
}

// MustNormalizeURLString returns the normalized string, and panics if an error occurs.
// It takes an URL string as input, as well as the normalization flags.
func MustNormalizeURLString(u string, f NormalizationFlags) string {
138
	if parsed, e := url.Parse(u); e != nil {
ale's avatar
ale committed
139
		panic(e)
140
141
	} else {
		return NormalizeURL(parsed, f)
ale's avatar
ale committed
142
	}
143
	panic("Unreachable code.")
ale's avatar
ale committed
144
145
146
147
148
}

// NormalizeURLString returns the normalized string, or an error if it can't be parsed into an URL object.
// It takes an URL string as input, as well as the normalization flags.
func NormalizeURLString(u string, f NormalizationFlags) (string, error) {
149
150
151
152
	if parsed, e := url.Parse(u); e != nil {
		return "", e
	} else {
		return NormalizeURL(parsed, f), nil
ale's avatar
ale committed
153
	}
154
	panic("Unreachable code.")
ale's avatar
ale committed
155
156
157
158
159
160
161
162
163
164
}

// NormalizeURL returns the normalized string.
// It takes a parsed URL object as input, as well as the normalization flags.
func NormalizeURL(u *url.URL, f NormalizationFlags) string {
	for _, k := range flagsOrder {
		if f&k == k {
			flags[k](u)
		}
	}
165
	return u.String()
ale's avatar
ale committed
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
}

func lowercaseScheme(u *url.URL) {
	if len(u.Scheme) > 0 {
		u.Scheme = strings.ToLower(u.Scheme)
	}
}

func lowercaseHost(u *url.URL) {
	if len(u.Host) > 0 {
		u.Host = strings.ToLower(u.Host)
	}
}

func removeDefaultPort(u *url.URL) {
	if len(u.Host) > 0 {
		scheme := strings.ToLower(u.Scheme)
		u.Host = rxPort.ReplaceAllStringFunc(u.Host, func(val string) string {
			if (scheme == "http" && val == defaultHttpPort) || (scheme == "https" && val == defaultHttpsPort) {
				return ""
			}
			return val
		})
	}
}

func removeTrailingSlash(u *url.URL) {
193
194
195
196
	if l := len(u.Path); l > 0 && strings.HasSuffix(u.Path, "/") {
		u.Path = u.Path[:l-1]
	} else if l = len(u.Host); l > 0 && strings.HasSuffix(u.Host, "/") {
		u.Host = u.Host[:l-1]
ale's avatar
ale committed
197
198
199
200
	}
}

func addTrailingSlash(u *url.URL) {
201
202
203
204
	if l := len(u.Path); l > 0 && !strings.HasSuffix(u.Path, "/") {
		u.Path += "/"
	} else if l = len(u.Host); l > 0 && !strings.HasSuffix(u.Host, "/") {
		u.Host += "/"
ale's avatar
ale committed
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
	}
}

func removeDotSegments(u *url.URL) {
	if len(u.Path) > 0 {
		var dotFree []string
		var lastIsDot bool

		sections := strings.Split(u.Path, "/")
		for _, s := range sections {
			if s == ".." {
				if len(dotFree) > 0 {
					dotFree = dotFree[:len(dotFree)-1]
				}
			} else if s != "." {
				dotFree = append(dotFree, s)
			}
			lastIsDot = (s == "." || s == "..")
		}
		// Special case if host does not end with / and new path does not begin with /
		u.Path = strings.Join(dotFree, "/")
226
		if !strings.HasSuffix(u.Host, "/") && !strings.HasPrefix(u.Path, "/") {
ale's avatar
ale committed
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
			u.Path = "/" + u.Path
		}
		// Special case if the last segment was a dot, make sure the path ends with a slash
		if lastIsDot && !strings.HasSuffix(u.Path, "/") {
			u.Path += "/"
		}
	}
}

func removeDirectoryIndex(u *url.URL) {
	if len(u.Path) > 0 {
		u.Path = rxDirIndex.ReplaceAllString(u.Path, "$1")
	}
}

func removeFragment(u *url.URL) {
	u.Fragment = ""
}

func forceHTTP(u *url.URL) {
	if strings.ToLower(u.Scheme) == "https" {
		u.Scheme = "http"
	}
}

func removeDuplicateSlashes(u *url.URL) {
	if len(u.Path) > 0 {
		u.Path = rxDupSlashes.ReplaceAllString(u.Path, "/")
	}
}

func removeWWW(u *url.URL) {
	if len(u.Host) > 0 && strings.HasPrefix(strings.ToLower(u.Host), "www.") {
		u.Host = u.Host[4:]
	}
}

func addWWW(u *url.URL) {
	if len(u.Host) > 0 && !strings.HasPrefix(strings.ToLower(u.Host), "www.") {
		u.Host = "www." + u.Host
	}
}

func sortQuery(u *url.URL) {
	q := u.Query()

	if len(q) > 0 {
		arKeys := make([]string, len(q))
		i := 0
276
		for k, _ := range q {
ale's avatar
ale committed
277
278
279
280
281
282
283
284
285
286
287
			arKeys[i] = k
			i++
		}
		sort.Strings(arKeys)
		buf := new(bytes.Buffer)
		for _, k := range arKeys {
			sort.Strings(q[k])
			for _, v := range q[k] {
				if buf.Len() > 0 {
					buf.WriteRune('&')
				}
288
				buf.WriteString(fmt.Sprintf("%s=%s", k, url.QueryEscape(v)))
ale's avatar
ale committed
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
			}
		}

		// Rebuild the raw query string
		u.RawQuery = buf.String()
	}
}

func decodeDWORDHost(u *url.URL) {
	if len(u.Host) > 0 {
		if matches := rxDWORDHost.FindStringSubmatch(u.Host); len(matches) > 2 {
			var parts [4]int64

			dword, _ := strconv.ParseInt(matches[1], 10, 0)
			for i, shift := range []uint{24, 16, 8, 0} {
				parts[i] = dword >> shift & 0xFF
			}
			u.Host = fmt.Sprintf("%d.%d.%d.%d%s", parts[0], parts[1], parts[2], parts[3], matches[2])
		}
	}
}

func decodeOctalHost(u *url.URL) {
	if len(u.Host) > 0 {
		if matches := rxOctalHost.FindStringSubmatch(u.Host); len(matches) > 5 {
			var parts [4]int64

			for i := 1; i <= 4; i++ {
				parts[i-1], _ = strconv.ParseInt(matches[i], 8, 0)
			}
			u.Host = fmt.Sprintf("%d.%d.%d.%d%s", parts[0], parts[1], parts[2], parts[3], matches[5])
		}
	}
}

func decodeHexHost(u *url.URL) {
	if len(u.Host) > 0 {
		if matches := rxHexHost.FindStringSubmatch(u.Host); len(matches) > 2 {
			// Conversion is safe because of regex validation
			parsed, _ := strconv.ParseInt(matches[1], 16, 0)
			// Set host as DWORD (base 10) encoded host
			u.Host = fmt.Sprintf("%d%s", parsed, matches[2])
			// The rest is the same as decoding a DWORD host
			decodeDWORDHost(u)
		}
	}
}

func removeUnncessaryHostDots(u *url.URL) {
	if len(u.Host) > 0 {
		if matches := rxHostDots.FindStringSubmatch(u.Host); len(matches) > 1 {
			// Trim the leading and trailing dots
			u.Host = strings.Trim(matches[1], ".")
			if len(matches) > 2 {
				u.Host += matches[2]
			}
		}
	}
}

func removeEmptyPortSeparator(u *url.URL) {
	if len(u.Host) > 0 {
		u.Host = rxEmptyPort.ReplaceAllString(u.Host, "")
	}
}