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
|
package analyze
import (
"github.com/Fuwn/kivia/internal/collect"
"strings"
"unicode"
"unicode/utf8"
)
type Options struct {
MinEvaluationLength int
}
type Result struct {
Violations []Violation `json:"violations"`
}
type Violation struct {
Identifier collect.Identifier `json:"identifier"`
Reason string `json:"reason"`
}
func Run(identifiers []collect.Identifier, options Options) (Result, error) {
minimumEvaluationLength := options.MinEvaluationLength
if minimumEvaluationLength <= 0 {
minimumEvaluationLength = 1
}
resources, err := getResources()
if err != nil {
return Result{}, err
}
violations := make([]Violation, 0)
for _, identifier := range identifiers {
if utf8.RuneCountInString(strings.TrimSpace(identifier.Name)) < minimumEvaluationLength {
continue
}
evaluation := evaluateIdentifier(identifier, resources, minimumEvaluationLength)
if !evaluation.isViolation {
continue
}
violation := Violation{
Identifier: identifier,
Reason: evaluation.reason,
}
violations = append(violations, violation)
}
return Result{Violations: violations}, nil
}
type evaluationResult struct {
isViolation bool
reason string
}
func evaluateIdentifier(identifier collect.Identifier, resources resources, minimumTokenLength int) evaluationResult {
name := strings.TrimSpace(identifier.Name)
if name == "" {
return evaluationResult{}
}
tokens := tokenize(name)
if len(tokens) == 0 {
return evaluationResult{}
}
for _, token := range tokens {
if utf8.RuneCountInString(token) < minimumTokenLength {
continue
}
if !isAlphabeticToken(token) {
continue
}
if resources.dictionary.IsWord(token) {
continue
}
if isUpperCaseToken(name, token) {
continue
}
if isDisallowedAbbreviation(token, resources) {
return evaluationResult{isViolation: true, reason: "Contains abbreviation: " + token + "."}
}
return evaluationResult{isViolation: true, reason: "Term not found in dictionary: " + token + "."}
}
return evaluationResult{}
}
func isUpperCaseToken(identifierName string, token string) bool {
tokenLength := utf8.RuneCountInString(token)
if tokenLength < 2 || tokenLength > 8 {
return false
}
return strings.Contains(identifierName, strings.ToUpper(token))
}
func tokenize(name string) []string {
name = strings.TrimSpace(name)
if name == "" {
return nil
}
parts := strings.FieldsFunc(name, func(r rune) bool {
return r == '_' || r == '-' || r == ' '
})
if len(parts) == 0 {
return nil
}
result := make([]string, 0, len(parts)*2)
for _, part := range parts {
if part == "" {
continue
}
result = append(result, splitCamel(part)...)
}
return result
}
func splitCamel(input string) []string {
if input == "" {
return nil
}
runes := []rune(input)
if len(runes) == 0 {
return nil
}
tokens := make([]string, 0, 2)
start := 0
for index := 1; index < len(runes); index++ {
current := runes[index]
previous := runes[index-1]
next := rune(0)
if index+1 < len(runes) {
next = runes[index+1]
}
isBoundary := false
if unicode.IsLower(previous) && unicode.IsUpper(current) {
isBoundary = true
}
if unicode.IsDigit(previous) != unicode.IsDigit(current) {
isBoundary = true
}
if unicode.IsUpper(previous) && unicode.IsUpper(current) && next != 0 && unicode.IsLower(next) {
isBoundary = true
}
if isBoundary {
tokens = append(tokens, strings.ToLower(string(runes[start:index])))
start = index
}
}
tokens = append(tokens, strings.ToLower(string(runes[start:])))
return tokens
}
func isDisallowedAbbreviation(token string, resources resources) bool {
_, hasExpansion := resources.dictionary.AbbreviationExpansion(token)
return hasExpansion
}
func isAlphabeticToken(token string) bool {
if token == "" {
return false
}
for _, character := range token {
if !unicode.IsLetter(character) {
return false
}
}
return true
}
|