-
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
// Copyright 2015 go-swagger maintainers
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package swag
import (
"unicode"
)
var nameReplaceTable = map[rune]string{
'@': "At ",
'&': "And ",
'|': "Pipe ",
'$': "Dollar ",
'!': "Bang ",
'-': "",
'_': "",
}
type (
splitter struct {
postSplitInitialismCheck bool
initialisms []string
}
splitterOption func(*splitter) *splitter
)
// split calls the splitter; splitter provides more control and post options
func split(str string) []string {
lexems := newSplitter().split(str)
result := make([]string, 0, len(lexems))
for _, lexem := range lexems {
result = append(result, lexem.GetOriginal())
}
return result
}
func (s *splitter) split(str string) []nameLexem {
return s.toNameLexems(str)
}
func newSplitter(options ...splitterOption) *splitter {
splitter := &splitter{
postSplitInitialismCheck: false,
initialisms: initialisms,
}
for _, option := range options {
splitter = option(splitter)
}
return splitter
}
// withPostSplitInitialismCheck allows to catch initialisms after main split process
func withPostSplitInitialismCheck(s *splitter) *splitter {
s.postSplitInitialismCheck = true
return s
}
type (
initialismMatch struct {
start, end int
body []rune
complete bool
}
initialismMatches []*initialismMatch
)
func (s *splitter) toNameLexems(name string) []nameLexem {
nameRunes := []rune(name)
matches := s.gatherInitialismMatches(nameRunes)
return s.mapMatchesToNameLexems(nameRunes, matches)
}
func (s *splitter) gatherInitialismMatches(nameRunes []rune) initialismMatches {
matches := make(initialismMatches, 0)
for currentRunePosition, currentRune := range nameRunes {
newMatches := make(initialismMatches, 0, len(matches))
// check current initialism matches
for _, match := range matches {
if keepCompleteMatch := match.complete; keepCompleteMatch {
newMatches = append(newMatches, match)
continue
}
// drop failed match
currentMatchRune := match.body[currentRunePosition-match.start]
if !s.initialismRuneEqual(currentMatchRune, currentRune) {
continue
}
// try to complete ongoing match
if currentRunePosition-match.start == len(match.body)-1 {
// we are close; the next step is to check the symbol ahead
// if it is a small letter, then it is not the end of match
// but beginning of the next word
if currentRunePosition < len(nameRunes)-1 {
nextRune := nameRunes[currentRunePosition+1]
if newWord := unicode.IsLower(nextRune); newWord {
// oh ok, it was the start of a new word
continue
}
}
match.complete = true
match.end = currentRunePosition
}
newMatches = append(newMatches, match)
}
// check for new initialism matches
for _, initialism := range s.initialisms {
initialismRunes := []rune(initialism)
if s.initialismRuneEqual(initialismRunes[0], currentRune) {
newMatches = append(newMatches, &initialismMatch{
start: currentRunePosition,
body: initialismRunes,
complete: false,
})
}
}
matches = newMatches
}
return matches
}
func (s *splitter) mapMatchesToNameLexems(nameRunes []rune, matches initialismMatches) []nameLexem {
nameLexems := make([]nameLexem, 0)
var lastAcceptedMatch *initialismMatch
for _, match := range matches {
if !match.complete {
continue
}
if firstMatch := lastAcceptedMatch == nil; firstMatch {
nameLexems = append(nameLexems, s.breakCasualString(nameRunes[:match.start])...)
nameLexems = append(nameLexems, s.breakInitialism(string(match.body)))
lastAcceptedMatch = match
continue
}
if overlappedMatch := match.start <= lastAcceptedMatch.end; overlappedMatch {
continue
}
middle := nameRunes[lastAcceptedMatch.end+1 : match.start]
nameLexems = append(nameLexems, s.breakCasualString(middle)...)
nameLexems = append(nameLexems, s.breakInitialism(string(match.body)))
lastAcceptedMatch = match
}
// we have not found any accepted matches
if lastAcceptedMatch == nil {
return s.breakCasualString(nameRunes)
}
if lastAcceptedMatch.end+1 != len(nameRunes) {
rest := nameRunes[lastAcceptedMatch.end+1:]
nameLexems = append(nameLexems, s.breakCasualString(rest)...)
}
return nameLexems
}
func (s *splitter) initialismRuneEqual(a, b rune) bool {
return a == b
}
func (s *splitter) breakInitialism(original string) nameLexem {
return newInitialismNameLexem(original, original)
}
func (s *splitter) breakCasualString(str []rune) []nameLexem {
segments := make([]nameLexem, 0)
currentSegment := ""
addCasualNameLexem := func(original string) {
segments = append(segments, newCasualNameLexem(original))
}
addInitialismNameLexem := func(original, match string) {
segments = append(segments, newInitialismNameLexem(original, match))
}
addNameLexem := func(original string) {
if s.postSplitInitialismCheck {
for _, initialism := range s.initialisms {
if upper(initialism) == upper(original) {
addInitialismNameLexem(original, initialism)
return
}
}
}
addCasualNameLexem(original)
}
for _, rn := range string(str) {
if replace, found := nameReplaceTable[rn]; found {
if currentSegment != "" {
addNameLexem(currentSegment)
currentSegment = ""
}
if replace != "" {
addNameLexem(replace)
}
continue
}
if !unicode.In(rn, unicode.L, unicode.M, unicode.N, unicode.Pc) {
if currentSegment != "" {
addNameLexem(currentSegment)
currentSegment = ""
}
continue
}
if unicode.IsUpper(rn) {
if currentSegment != "" {
addNameLexem(currentSegment)
}
currentSegment = ""
}
currentSegment += string(rn)
}
if currentSegment != "" {
addNameLexem(currentSegment)
}
return segments
}