/
str_calc.go
319 lines (281 loc) · 7.05 KB
/
str_calc.go
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
package utils
import (
"fmt"
"sort"
"strconv"
"github.com/glaslos/ssdeep"
"github.com/mfonda/simhash"
"github.com/yaklang/yaklang/common/go-funk"
"github.com/yaklang/yaklang/common/log"
"github.com/yaklang/yaklang/common/utils/mixer"
"gopkg.in/fatih/set.v0"
)
// CalcSimHash 计算并返回一段文本的 SimHash 值
// Example:
// ```
// str.CalcSimHash("hello")
// ```
func SimHash(raw []byte) uint64 {
return simhash.Simhash(simhash.NewWordFeatureSet(raw))
}
// CalcSSDeep 计算并返回一段文本的模糊哈希值
// Example:
// ```
// str.CalcSSDeep("hello")
// ```
func SSDeepHash(raw []byte) string {
hash, err := ssdeep.FuzzyBytes(raw)
if err != nil {
log.Warn(err.Error())
return ""
}
return hash
}
// CalcSimilarity 计算多段文本之间的相似度,根据最长的文本长度选择不同的算法
// 如果最长的文本长度小于等于 2000,使用文本子串匹配算法
// 如果最短的文本长度大于等于 30000,使用模糊哈希算法
// 如果上述算法出现错误,则使用 SimHash 算法
// Example:
// ```
// str.CalcSimilarity("hello", "hello world") // 0.625
// ```
func CalcSimilarity(raw ...[]byte) float64 {
var (
err error
percent float64
)
lens := funk.Map(raw, func(i []byte) int {
return len(i)
}).([]int)
maxLength := funk.MaxInt(lens)
minLength := funk.MinInt(lens)
if maxLength <= 0 {
return 0
}
if maxLength <= 2000 {
percent, err = CalcTextSubStringStability(raw...)
if err != nil {
log.Errorf("calc text substr similarity/stability failed: %s", err)
return 0
}
return percent
}
if minLength >= 30000 {
percent, err = CalcSSDeepStability(raw...)
if err == nil {
return percent
}
}
percent, err = CalcSimHashStability(raw...)
if err == nil {
return percent
}
return 0
}
// CalcTextMaxSubStrStability 使用文本子串匹配算法计算多段文本之间的相似度,返回相似度与错误
// Example:
// ```
// p, err = str.CalcTextMaxSubStrStability("hello", "hello world") // p = 0.625
// ```
func CalcTextSubStringStability(raw ...[]byte) (float64, error) {
var samples []string
for _, i := range raw {
samples = append(samples, string(i))
}
if len(samples) <= 0 {
return 1, Errorf("no enough samples")
}
m, err := mixer.NewMixer(samples, samples)
if err != nil {
return 1, Errorf("create mixer failed: %s", err)
}
var max float64 = 0
var min float64 = 1
for m.Next() == nil {
results := m.Value()
hash1, hash2 := results[0], results[1]
score := similarText(hash1, hash2)
if score <= min {
min = score
}
if score >= max {
max = score
}
}
return min, nil
}
// CalcSSDeepStability 使用模糊哈希算法计算多段文本之间的相似度,返回相似度与错误。传入的文本应该为大文本,即长度大于 30 kb。
// Example:
// ```
// p, err = str.CalcSSDeepStability(str.RandStr(100000), str.RandStr(100000))
// ```
func CalcSSDeepStability(req ...[]byte) (float64, error) {
var hash []string
for _, r := range req {
h := SSDeepHash(r)
if h == "" {
continue
}
hash = append(hash, h)
}
if len(hash) <= 0 {
return 1, Errorf("no enough hash")
}
m, err := mixer.NewMixer(hash, hash)
if err != nil {
return 1, Errorf("create mixer failed: %s", err)
}
var max = 0
var min = 100
for m.Next() == nil {
results := m.Value()
hash1, hash2 := results[0], results[1]
score, err := ssdeep.Distance(hash1, hash2)
if err != nil {
continue
}
if score <= min {
min = score
}
if score >= max {
max = score
}
}
return float64(min) / float64(100), nil
}
// CalcSimHashStability 使用 SimHash 算法计算多段文本之间的相似度,返回相似度与错误。
// Example:
// ```
// p, err = str.CalcSimHashStability("hello", "hello world") // p = 0.96484375
// ```
func CalcSimHashStability(req ...[]byte) (float64, error) {
var hash []string
for _, r := range req {
h := SimHash(r)
hash = append(hash, fmt.Sprint(h))
}
m, err := mixer.NewMixer(hash, hash)
if err != nil {
return 0, err
}
var max uint8 = 0
var min uint8 = 255
for m.Next() == nil {
results := m.Value()
hash1, _ := strconv.ParseUint(results[0], 10, 64)
hash2, _ := strconv.ParseUint(results[1], 10, 64)
res := simhash.Compare(hash1, hash2)
if res <= min {
min = res
}
if res >= max {
max = res
}
}
return (256 - float64(max)) / float64(256), nil
}
// return the len of longest string both in str1 and str2 and the positions in str1 and str2
func SimilarStr(str1 []rune, str2 []rune) (int, int, int) {
var sameLen, tmp, pos1, pos2 = 0, 0, 0, 0
len1, len2 := len(str1), len(str2)
for p := 0; p < len1; p++ {
for q := 0; q < len2; q++ {
tmp = 0
for p+tmp < len1 && q+tmp < len2 && str1[p+tmp] == str2[q+tmp] {
tmp++
}
if tmp > sameLen {
sameLen, pos1, pos2 = tmp, p, q
}
}
}
return sameLen, pos1, pos2
}
// return the total length of longest string both in str1 and str2
func similarChar(str1 []rune, str2 []rune) int {
maxLen, pos1, pos2 := SimilarStr(str1, str2)
total := maxLen
if maxLen != 0 {
if pos1 > 0 && pos2 > 0 {
total += similarChar(str1[:pos1], str2[:pos2])
}
if pos1+maxLen < len(str1) && pos2+maxLen < len(str2) {
total += similarChar(str1[pos1+maxLen:], str2[pos2+maxLen:])
}
}
return total
}
// return a int value in [0, 1], which stands for match level
func similarText(str1 string, str2 string) float64 {
txt1, txt2 := []rune(str1), []rune(str2)
if len(txt1) == 0 || len(txt2) == 0 {
return 0
}
totalLength := float64(similarChar(txt1, txt2))
return totalLength * 2 / float64(len(txt1)+len(txt2))
}
func checkIsSamePage(BaseBody []byte, currentBody []byte, boundary float64) bool {
currentHTML := string(currentBody)
baseHTML := string(BaseBody)
isSamePage := false
// 先计算PageRatio
ratio := similarText(currentHTML, baseHTML)
if ratio > boundary {
isSamePage = true
}
return isSamePage
}
func GetSameSubStringsRunes(text1, text2 []rune) [][]rune {
var ln, pos1, pos2 = 0, 0, 0
var results [][]rune
for {
ln, pos1, pos2 = SimilarStr(text1, text2)
if ln > 0 {
result := text1[pos1 : pos1+ln]
results = append(results, result)
} else {
return results
}
text1 = text1[pos1+ln:]
text2 = text2[pos2+ln:]
}
}
func GetSameSubStrings(raw ...string) []string {
if len(raw) < 2 {
return nil
}
m, err := mixer.NewMixer(raw, raw)
if err != nil {
return nil
}
var results []set.Interface
var visited []string
for {
res := m.Value()
sort.Strings(res)
hash := CalcSha1(res[0], res[1])
if res[0] != res[1] && !StringSliceContain(visited, hash) {
visited = append(visited, hash)
subStrs := GetSameSubStringsRunes([]rune(res[0]), []rune(res[1]))
var tmp = set.New(set.ThreadSafe)
for _, r := range subStrs {
tmp.Add(string(r))
}
results = append(results, tmp)
}
err := m.Next()
if err != nil {
break
}
}
if len(results) > 2 {
return set.StringSlice(set.Intersection(results[0], results[1], results[2:]...))
}
if len(results) == 2 {
return set.StringSlice(set.Intersection(results[0], results[1]))
}
if len(results) == 1 {
return set.StringSlice(results[0])
}
return nil
}