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
|
// Copyright (c) 2020 Cisco and/or its affiliates.
//
// 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 binapigen
import (
"go/token"
"strings"
"unicode"
"unicode/utf8"
)
// commonInitialisms is a set of common initialisms that need to stay in upper case.
var commonInitialisms = map[string]bool{
"ACL": true,
"API": true,
// NOTE: There are only two occurences of the word 'ascii' and
// these already have initialism before and after ASCII part,
// thus disabling initialism for this case.
"ASCII": false,
"CPU": true,
"CSS": true,
"DNS": true,
"DHCP": true,
"EOF": true,
"GUID": true,
"HTML": true,
"HTTP": true,
"HTTPS": true,
"ID": true,
"IP": true,
"ICMP": true,
"JSON": true,
"LHS": true,
"QPS": true,
"PID": true,
"RAM": true,
"RHS": true,
"RPC": true,
"SLA": true,
"SMTP": true,
"SQL": true,
"SSH": true,
"TCP": true,
"TLS": true,
"TTL": true,
"UDP": true,
"UI": true,
"UID": true,
"UUID": true,
"URI": true,
"URL": true,
"UTF8": true,
"VM": true,
"VPN": true,
"XML": true,
"XMPP": true,
"XSRF": true,
"XSS": true,
}
// specialInitialisms is a set of special initialisms that need part to stay in upper case.
var specialInitialisms = map[string]string{
"IPV": "IPv",
}
func usesInitialism(s string) string {
u := strings.ToUpper(s)
if commonInitialisms[u] {
return u
} else if su, ok := specialInitialisms[u]; ok {
return su
}
return ""
}
// camelCaseName returns correct name identifier (camelCase).
func camelCaseName(name string) (should string) {
name = strings.Title(name)
// Fast path for simple cases: "_" and all lowercase.
if name == "_" {
return name
}
allLower := true
for _, r := range name {
if !unicode.IsLower(r) {
allLower = false
break
}
}
if allLower {
return name
}
// Split camelCase at any lower->upper transition, and split on underscores.
// Check each word for common initialisms.
runes := []rune(name)
w, i := 0, 0 // index of start of word, scan
for i+1 <= len(runes) {
eow := false // whether we hit the end of a word
if i+1 == len(runes) {
eow = true
} else if runes[i+1] == '_' {
// underscore; shift the remainder forward over any run of underscores
eow = true
n := 1
for i+n+1 < len(runes) && runes[i+n+1] == '_' {
n++
}
// Leave at most one underscore if the underscore is between two digits
if i+n+1 < len(runes) && unicode.IsDigit(runes[i]) && unicode.IsDigit(runes[i+n+1]) {
n--
}
copy(runes[i+1:], runes[i+n+1:])
runes = runes[:len(runes)-n]
} else if unicode.IsLower(runes[i]) && !unicode.IsLower(runes[i+1]) {
// lower->non-lower
eow = true
}
i++
if !eow {
continue
}
// [w,i) is a word.
word := string(runes[w:i])
if u := usesInitialism(word); u != "" {
// Keep consistent case, which is lowercase only at the start.
if w == 0 && unicode.IsLower(runes[w]) {
u = strings.ToLower(u)
}
// All the common initialisms are ASCII,
// so we can replace the bytes exactly.
copy(runes[w:], []rune(u))
} else if w > 0 && strings.ToLower(word) == word {
// already all lowercase, and not the first word, so uppercase the first character.
runes[w] = unicode.ToUpper(runes[w])
}
w = i
}
return string(runes)
}
// sanitizedName returns the string converted into a valid Go identifier.
func sanitizedName(s string) string {
r, _ := utf8.DecodeRuneInString(s)
if token.Lookup(s).IsKeyword() || !unicode.IsLetter(r) {
return s + "s"
}
return s
}
|
