fuwn.net
🏰 Self-documenting Identifier Name Analyser for Go
feat: Initial commit
+2325
+1
.gitignore
+1
.gitignore
···
1
+
bin/
+202
LICENSE-APACHE
+202
LICENSE-APACHE
···
1
+
2
+
Apache License
3
+
Version 2.0, January 2004
4
+
http://www.apache.org/licenses/
5
+
6
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+
1. Definitions.
9
+
10
+
"License" shall mean the terms and conditions for use, reproduction,
11
+
and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+
"Licensor" shall mean the copyright owner or entity authorized by
14
+
the copyright owner that is granting the License.
15
+
16
+
"Legal Entity" shall mean the union of the acting entity and all
17
+
other entities that control, are controlled by, or are under common
18
+
control with that entity. For the purposes of this definition,
19
+
"control" means (i) the power, direct or indirect, to cause the
20
+
direction or management of such entity, whether by contract or
21
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+
outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+
"You" (or "Your") shall mean an individual or Legal Entity
25
+
exercising permissions granted by this License.
26
+
27
+
"Source" form shall mean the preferred form for making modifications,
28
+
including but not limited to software source code, documentation
29
+
source, and configuration files.
30
+
31
+
"Object" form shall mean any form resulting from mechanical
32
+
transformation or translation of a Source form, including but
33
+
not limited to compiled object code, generated documentation,
34
+
and conversions to other media types.
35
+
36
+
"Work" shall mean the work of authorship, whether in Source or
37
+
Object form, made available under the License, as indicated by a
38
+
copyright notice that is included in or attached to the work
39
+
(an example is provided in the Appendix below).
40
+
41
+
"Derivative Works" shall mean any work, whether in Source or Object
42
+
form, that is based on (or derived from) the Work and for which the
43
+
editorial revisions, annotations, elaborations, or other modifications
44
+
represent, as a whole, an original work of authorship. For the purposes
45
+
of this License, Derivative Works shall not include works that remain
46
+
separable from, or merely link (or bind by name) to the interfaces of,
47
+
the Work and Derivative Works thereof.
48
+
49
+
"Contribution" shall mean any work of authorship, including
50
+
the original version of the Work and any modifications or additions
51
+
to that Work or Derivative Works thereof, that is intentionally
52
+
submitted to Licensor for inclusion in the Work by the copyright owner
53
+
or by an individual or Legal Entity authorized to submit on behalf of
54
+
the copyright owner. For the purposes of this definition, "submitted"
55
+
means any form of electronic, verbal, or written communication sent
56
+
to the Licensor or its representatives, including but not limited to
57
+
communication on electronic mailing lists, source code control systems,
58
+
and issue tracking systems that are managed by, or on behalf of, the
59
+
Licensor for the purpose of discussing and improving the Work, but
60
+
excluding communication that is conspicuously marked or otherwise
61
+
designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+
"Contributor" shall mean Licensor and any individual or Legal Entity
64
+
on behalf of whom a Contribution has been received by Licensor and
65
+
subsequently incorporated within the Work.
66
+
67
+
2. Grant of Copyright License. Subject to the terms and conditions of
68
+
this License, each Contributor hereby grants to You a perpetual,
69
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+
copyright license to reproduce, prepare Derivative Works of,
71
+
publicly display, publicly perform, sublicense, and distribute the
72
+
Work and such Derivative Works in Source or Object form.
73
+
74
+
3. Grant of Patent License. Subject to the terms and conditions of
75
+
this License, each Contributor hereby grants to You a perpetual,
76
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+
(except as stated in this section) patent license to make, have made,
78
+
use, offer to sell, sell, import, and otherwise transfer the Work,
79
+
where such license applies only to those patent claims licensable
80
+
by such Contributor that are necessarily infringed by their
81
+
Contribution(s) alone or by combination of their Contribution(s)
82
+
with the Work to which such Contribution(s) was submitted. If You
83
+
institute patent litigation against any entity (including a
84
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+
or a Contribution incorporated within the Work constitutes direct
86
+
or contributory patent infringement, then any patent licenses
87
+
granted to You under this License for that Work shall terminate
88
+
as of the date such litigation is filed.
89
+
90
+
4. Redistribution. You may reproduce and distribute copies of the
91
+
Work or Derivative Works thereof in any medium, with or without
92
+
modifications, and in Source or Object form, provided that You
93
+
meet the following conditions:
94
+
95
+
(a) You must give any other recipients of the Work or
96
+
Derivative Works a copy of this License; and
97
+
98
+
(b) You must cause any modified files to carry prominent notices
99
+
stating that You changed the files; and
100
+
101
+
(c) You must retain, in the Source form of any Derivative Works
102
+
that You distribute, all copyright, patent, trademark, and
103
+
attribution notices from the Source form of the Work,
104
+
excluding those notices that do not pertain to any part of
105
+
the Derivative Works; and
106
+
107
+
(d) If the Work includes a "NOTICE" text file as part of its
108
+
distribution, then any Derivative Works that You distribute must
109
+
include a readable copy of the attribution notices contained
110
+
within such NOTICE file, excluding those notices that do not
111
+
pertain to any part of the Derivative Works, in at least one
112
+
of the following places: within a NOTICE text file distributed
113
+
as part of the Derivative Works; within the Source form or
114
+
documentation, if provided along with the Derivative Works; or,
115
+
within a display generated by the Derivative Works, if and
116
+
wherever such third-party notices normally appear. The contents
117
+
of the NOTICE file are for informational purposes only and
118
+
do not modify the License. You may add Your own attribution
119
+
notices within Derivative Works that You distribute, alongside
120
+
or as an addendum to the NOTICE text from the Work, provided
121
+
that such additional attribution notices cannot be construed
122
+
as modifying the License.
123
+
124
+
You may add Your own copyright statement to Your modifications and
125
+
may provide additional or different license terms and conditions
126
+
for use, reproduction, or distribution of Your modifications, or
127
+
for any such Derivative Works as a whole, provided Your use,
128
+
reproduction, and distribution of the Work otherwise complies with
129
+
the conditions stated in this License.
130
+
131
+
5. Submission of Contributions. Unless You explicitly state otherwise,
132
+
any Contribution intentionally submitted for inclusion in the Work
133
+
by You to the Licensor shall be under the terms and conditions of
134
+
this License, without any additional terms or conditions.
135
+
Notwithstanding the above, nothing herein shall supersede or modify
136
+
the terms of any separate license agreement you may have executed
137
+
with Licensor regarding such Contributions.
138
+
139
+
6. Trademarks. This License does not grant permission to use the trade
140
+
names, trademarks, service marks, or product names of the Licensor,
141
+
except as required for reasonable and customary use in describing the
142
+
origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+
7. Disclaimer of Warranty. Unless required by applicable law or
145
+
agreed to in writing, Licensor provides the Work (and each
146
+
Contributor provides its Contributions) on an "AS IS" BASIS,
147
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+
implied, including, without limitation, any warranties or conditions
149
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+
PARTICULAR PURPOSE. You are solely responsible for determining the
151
+
appropriateness of using or redistributing the Work and assume any
152
+
risks associated with Your exercise of permissions under this License.
153
+
154
+
8. Limitation of Liability. In no event and under no legal theory,
155
+
whether in tort (including negligence), contract, or otherwise,
156
+
unless required by applicable law (such as deliberate and grossly
157
+
negligent acts) or agreed to in writing, shall any Contributor be
158
+
liable to You for damages, including any direct, indirect, special,
159
+
incidental, or consequential damages of any character arising as a
160
+
result of this License or out of the use or inability to use the
161
+
Work (including but not limited to damages for loss of goodwill,
162
+
work stoppage, computer failure or malfunction, or any and all
163
+
other commercial damages or losses), even if such Contributor
164
+
has been advised of the possibility of such damages.
165
+
166
+
9. Accepting Warranty or Additional Liability. While redistributing
167
+
the Work or Derivative Works thereof, You may choose to offer,
168
+
and charge a fee for, acceptance of support, warranty, indemnity,
169
+
or other liability obligations and/or rights consistent with this
170
+
License. However, in accepting such obligations, You may act only
171
+
on Your own behalf and on Your sole responsibility, not on behalf
172
+
of any other Contributor, and only if You agree to indemnify,
173
+
defend, and hold each Contributor harmless for any liability
174
+
incurred by, or claims asserted against, such Contributor by reason
175
+
of your accepting any such warranty or additional liability.
176
+
177
+
END OF TERMS AND CONDITIONS
178
+
179
+
APPENDIX: How to apply the Apache License to your work.
180
+
181
+
To apply the Apache License to your work, attach the following
182
+
boilerplate notice, with the fields enclosed by brackets "[]"
183
+
replaced with your own identifying information. (Don't include
184
+
the brackets!) The text should be enclosed in the appropriate
185
+
comment syntax for the file format. We also recommend that a
186
+
file or class name and description of purpose be included on the
187
+
same "printed page" as the copyright notice for easier
188
+
identification within third-party archives.
189
+
190
+
Copyright [yyyy] [name of copyright owner]
191
+
192
+
Licensed under the Apache License, Version 2.0 (the "License");
193
+
you may not use this file except in compliance with the License.
194
+
You may obtain a copy of the License at
195
+
196
+
http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+
Unless required by applicable law or agreed to in writing, software
199
+
distributed under the License is distributed on an "AS IS" BASIS,
200
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+
See the License for the specific language governing permissions and
202
+
limitations under the License.
+5
LICENSE-MIT
+5
LICENSE-MIT
···
1
+
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
2
+
3
+
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
4
+
5
+
THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+164
README.md
+164
README.md
···
1
+
# 🏰 Kivia
2
+
3
+
> Self-documenting Name Analyser for Go
4
+
5
+
Name things so your code explains itself.
6
+
7
+
Kivia is a fast, local-only analyser that flags identifiers whose terms are absent from dictionary sources or resemble abbreviations of dictionary words. It is built for teams that want explicit, readable naming conventions without external AI calls.
8
+
9
+
## Philosophy
10
+
11
+
Identifier names should be fully self-documenting.
12
+
13
+
Kivia enforces a strict readability standard:
14
+
15
+
- Prefer full words over shorthand
16
+
- Avoid ambiguous abbreviations
17
+
- Keep the naming intent clear from the identifier itself
18
+
19
+
Examples:
20
+
21
+
- `userNum` → invalid (`num` is an abbreviation)
22
+
- `ctx` → invalid (`ctx` is an abbreviation)
23
+
- `userCount` → valid
24
+
- `requestContext` → valid
25
+
26
+
## Rules
27
+
28
+
1. **Dictionary words pass**: If a token is present in the loaded dictionary sources, it passes.
29
+
2. **Abbreviations are violations**: If a token expands to a dictionary word (for example, `ctx` -> `context`), it is flagged.
30
+
3. **Unknown terms are violations**: If a token is not in the dictionary and does not map to a known expansion, it is flagged.
31
+
4. **Minimum length is explicit**: `--min-eval-length` determines whether short identifiers are evaluated.
32
+
33
+
Kivia also applies dictionary-backed spelling-variant matching for common British/American pairs (for example `normalise`/`normalize`, `colour`/`color`, `centre`/`center`).
34
+
35
+
## How It Works
36
+
37
+
Kivia parses Go source using the standard library's AST, extracts identifiers, tokenises names (camel, snake, or kebab), and evaluates each token against a local NLP dictionary pipeline.
38
+
39
+
- No network requests
40
+
- No LLM/API dependency
41
+
- Deterministic local analysis
42
+
43
+
## Installation
44
+
45
+
```bash
46
+
go install github.com/Fuwn/kivia@latest
47
+
```
48
+
49
+
Or build locally:
50
+
51
+
```bash
52
+
go build -o ./bin/kivia .
53
+
```
54
+
55
+
## Usage
56
+
57
+
```bash
58
+
# Analyse a package tree
59
+
kivia --path ./...
60
+
61
+
# Ignore single-letter names during evaluation
62
+
kivia --path ./... --min-eval-length 2
63
+
64
+
# Ignore specific violations
65
+
kivia --path ./... --ignore name=ctx --ignore file=testdata
66
+
67
+
# JSON output without context payload
68
+
kivia --path ./... --format json --omit-context
69
+
```
70
+
71
+
### Flags
72
+
73
+
| Flag | Description |
74
+
|------|-------------|
75
+
| `--path` | Path to analyse (`directory`, `file`, or `./...`). |
76
+
| `--omit-context` | Hide usage context in output. |
77
+
| `--min-eval-length` | Minimum identifier length in runes to evaluate (must be `>= 1`). |
78
+
| `--format` | Output format: `text` or `json`. |
79
+
| `--fail-on-violation` | Exit with code `1` when violations are found. |
80
+
| `--ignore` | Ignore violations by matcher. Repeatable. Prefixes: `name=`, `kind=`, `file=`, `reason=`, `func=`. |
81
+
82
+
## Ignore Matchers
83
+
84
+
`--ignore` supports targeted filtering:
85
+
86
+
- `name=<substring>`
87
+
- `kind=<substring>`
88
+
- `file=<substring>`
89
+
- `reason=<substring>`
90
+
- `func=<substring>`
91
+
92
+
Without a prefix, the matcher is applied as a substring across all violation fields.
93
+
94
+
Example:
95
+
96
+
```bash
97
+
kivia --path ./... \
98
+
--ignore name=ctx \
99
+
--ignore reason=abbreviation \
100
+
--ignore file=_test.go
101
+
```
102
+
103
+
## Output
104
+
105
+
### Text (default)
106
+
107
+
```text
108
+
internal/example/sample.go:12:9 parameter "ctx": Contains abbreviation: ctx.
109
+
context: type=context.Context, function=Handle
110
+
```
111
+
112
+
### JSON
113
+
114
+
```json
115
+
{
116
+
"violations": [
117
+
{
118
+
"identifier": {
119
+
"name": "ctx",
120
+
"kind": "parameter",
121
+
"file": "internal/example/sample.go",
122
+
"line": 12,
123
+
"column": 9,
124
+
"context": {
125
+
"enclosingFunction": "Handle",
126
+
"type": "context.Context"
127
+
}
128
+
},
129
+
"reason": "Contains abbreviation: ctx."
130
+
}
131
+
]
132
+
}
133
+
```
134
+
135
+
## Identifier Scope (Go)
136
+
137
+
Kivia currently extracts and evaluates:
138
+
139
+
- Types
140
+
- Functions and methods
141
+
- Receivers
142
+
- Parameters
143
+
- Named results
144
+
- Variables (`var`/`const` and `:=`)
145
+
- Range keys and values
146
+
- Struct fields
147
+
- Interface methods
148
+
149
+
## Dictionary and NLP Source
150
+
151
+
Kivia loads dictionary data only from configured/system dictionary files.
152
+
153
+
1. `KIVIA_DICTIONARY_PATH` (optional): one path or multiple paths separated by your OS path separator (`:` on macOS/Linux, `;` on Windows). Commas are also accepted.
154
+
2. If `KIVIA_DICTIONARY_PATH` is not set, Kivia uses a default set of dictionary files (for example, `/usr/share/dict/words`, `/usr/share/dict/web2`, and Hunspell dictionaries when present).
155
+
3. If no usable words are found, the analysis fails with an error.
156
+
157
+
## License
158
+
159
+
Licensed under either of [Apache License, Version 2.0](LICENSE-APACHE) or
160
+
[MIT license](LICENSE-MIT) at your option.
161
+
162
+
Unless you explicitly state otherwise, any contribution intentionally submitted
163
+
for inclusion in this crate by you, as defined in the Apache-2.0 license, shall
164
+
be dual licensed as above, without any additional terms or conditions.
+5
go.mod
+5
go.mod
+2
go.sum
+2
go.sum
+208
internal/analyze/analyze.go
+208
internal/analyze/analyze.go
···
1
+
package analyze
2
+
3
+
import (
4
+
"github.com/Fuwn/kivia/internal/collect"
5
+
"strings"
6
+
"unicode"
7
+
"unicode/utf8"
8
+
)
9
+
10
+
type Options struct {
11
+
MinEvaluationLength int
12
+
}
13
+
14
+
type Result struct {
15
+
Violations []Violation `json:"violations"`
16
+
}
17
+
18
+
type Violation struct {
19
+
Identifier collect.Identifier `json:"identifier"`
20
+
Reason string `json:"reason"`
21
+
}
22
+
23
+
func Run(identifiers []collect.Identifier, options Options) (Result, error) {
24
+
minimumEvaluationLength := options.MinEvaluationLength
25
+
26
+
if minimumEvaluationLength <= 0 {
27
+
minimumEvaluationLength = 1
28
+
}
29
+
30
+
resources, err := getResources()
31
+
32
+
if err != nil {
33
+
return Result{}, err
34
+
}
35
+
36
+
violations := make([]Violation, 0)
37
+
38
+
for _, identifier := range identifiers {
39
+
if utf8.RuneCountInString(strings.TrimSpace(identifier.Name)) < minimumEvaluationLength {
40
+
continue
41
+
}
42
+
43
+
evaluation := evaluateIdentifier(identifier, resources, minimumEvaluationLength)
44
+
45
+
if !evaluation.isViolation {
46
+
continue
47
+
}
48
+
49
+
violation := Violation{
50
+
Identifier: identifier,
51
+
Reason: evaluation.reason,
52
+
}
53
+
violations = append(violations, violation)
54
+
}
55
+
56
+
return Result{Violations: violations}, nil
57
+
}
58
+
59
+
type evaluationResult struct {
60
+
isViolation bool
61
+
reason string
62
+
}
63
+
64
+
func evaluateIdentifier(identifier collect.Identifier, resources resources, minimumTokenLength int) evaluationResult {
65
+
name := strings.TrimSpace(identifier.Name)
66
+
67
+
if name == "" {
68
+
return evaluationResult{}
69
+
}
70
+
71
+
tokens := tokenize(name)
72
+
73
+
if len(tokens) == 0 {
74
+
return evaluationResult{}
75
+
}
76
+
77
+
for _, token := range tokens {
78
+
if utf8.RuneCountInString(token) < minimumTokenLength {
79
+
continue
80
+
}
81
+
82
+
if !isAlphabeticToken(token) {
83
+
continue
84
+
}
85
+
86
+
if resources.dictionary.IsWord(token) {
87
+
continue
88
+
}
89
+
90
+
if isUpperCaseToken(name, token) {
91
+
continue
92
+
}
93
+
94
+
if isDisallowedAbbreviation(token, resources) {
95
+
return evaluationResult{isViolation: true, reason: "Contains abbreviation: " + token + "."}
96
+
}
97
+
98
+
return evaluationResult{isViolation: true, reason: "Term not found in dictionary: " + token + "."}
99
+
}
100
+
101
+
return evaluationResult{}
102
+
}
103
+
104
+
func isUpperCaseToken(identifierName string, token string) bool {
105
+
tokenLength := utf8.RuneCountInString(token)
106
+
107
+
if tokenLength < 2 || tokenLength > 8 {
108
+
return false
109
+
}
110
+
111
+
return strings.Contains(identifierName, strings.ToUpper(token))
112
+
}
113
+
114
+
func tokenize(name string) []string {
115
+
name = strings.TrimSpace(name)
116
+
117
+
if name == "" {
118
+
return nil
119
+
}
120
+
121
+
parts := strings.FieldsFunc(name, func(r rune) bool {
122
+
return r == '_' || r == '-' || r == ' '
123
+
})
124
+
125
+
if len(parts) == 0 {
126
+
return nil
127
+
}
128
+
129
+
result := make([]string, 0, len(parts)*2)
130
+
131
+
for _, part := range parts {
132
+
if part == "" {
133
+
continue
134
+
}
135
+
136
+
result = append(result, splitCamel(part)...)
137
+
}
138
+
139
+
return result
140
+
}
141
+
142
+
func splitCamel(input string) []string {
143
+
if input == "" {
144
+
return nil
145
+
}
146
+
147
+
runes := []rune(input)
148
+
149
+
if len(runes) == 0 {
150
+
return nil
151
+
}
152
+
153
+
tokens := make([]string, 0, 2)
154
+
start := 0
155
+
156
+
for index := 1; index < len(runes); index++ {
157
+
current := runes[index]
158
+
previous := runes[index-1]
159
+
next := rune(0)
160
+
161
+
if index+1 < len(runes) {
162
+
next = runes[index+1]
163
+
}
164
+
165
+
isBoundary := false
166
+
167
+
if unicode.IsLower(previous) && unicode.IsUpper(current) {
168
+
isBoundary = true
169
+
}
170
+
171
+
if unicode.IsDigit(previous) != unicode.IsDigit(current) {
172
+
isBoundary = true
173
+
}
174
+
175
+
if unicode.IsUpper(previous) && unicode.IsUpper(current) && next != 0 && unicode.IsLower(next) {
176
+
isBoundary = true
177
+
}
178
+
179
+
if isBoundary {
180
+
tokens = append(tokens, strings.ToLower(string(runes[start:index])))
181
+
start = index
182
+
}
183
+
}
184
+
185
+
tokens = append(tokens, strings.ToLower(string(runes[start:])))
186
+
187
+
return tokens
188
+
}
189
+
190
+
func isDisallowedAbbreviation(token string, resources resources) bool {
191
+
_, hasExpansion := resources.dictionary.AbbreviationExpansion(token)
192
+
193
+
return hasExpansion
194
+
}
195
+
196
+
func isAlphabeticToken(token string) bool {
197
+
if token == "" {
198
+
return false
199
+
}
200
+
201
+
for _, character := range token {
202
+
if !unicode.IsLetter(character) {
203
+
return false
204
+
}
205
+
}
206
+
207
+
return true
208
+
}
+174
internal/analyze/analyze_test.go
+174
internal/analyze/analyze_test.go
···
1
+
package analyze_test
2
+
3
+
import (
4
+
"github.com/Fuwn/kivia/internal/analyze"
5
+
"github.com/Fuwn/kivia/internal/collect"
6
+
"os"
7
+
"path/filepath"
8
+
"testing"
9
+
)
10
+
11
+
func dictionaryPathForTests(testingContext *testing.T) string {
12
+
testingContext.Helper()
13
+
14
+
return filepath.Join("..", "..", "testdata", "dictionary", "words.txt")
15
+
}
16
+
17
+
func TestAnalyzeFlagsAbbreviations(testingContext *testing.T) {
18
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryPathForTests(testingContext))
19
+
20
+
root := filepath.Join("..", "..", "testdata", "samplepkg")
21
+
identifiers, err := collect.FromPath(root)
22
+
23
+
if err != nil {
24
+
testingContext.Fatalf("collect.FromPath returned an error: %v", err)
25
+
}
26
+
27
+
result, err := analyze.Run(identifiers, analyze.Options{})
28
+
29
+
if err != nil {
30
+
testingContext.Fatalf("analyze.Run returned an error: %v", err)
31
+
}
32
+
33
+
if len(result.Violations) == 0 {
34
+
testingContext.Fatalf("Expected at least one violation, got none.")
35
+
}
36
+
37
+
mustContainViolation(testingContext, result, "ctx")
38
+
mustContainViolation(testingContext, result, "userNum")
39
+
mustContainViolation(testingContext, result, "usr")
40
+
}
41
+
42
+
func TestAnalyzeFlagsTechnicalTermsNotInDictionary(testingContext *testing.T) {
43
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryPathForTests(testingContext))
44
+
45
+
identifiers := []collect.Identifier{
46
+
{Name: "userID", Kind: "variable"},
47
+
{Name: "httpClient", Kind: "variable"},
48
+
}
49
+
result, err := analyze.Run(identifiers, analyze.Options{})
50
+
51
+
if err != nil {
52
+
testingContext.Fatalf("analyze.Run returned an error: %v", err)
53
+
}
54
+
55
+
if len(result.Violations) == 0 {
56
+
testingContext.Fatalf("Expected violations, got none.")
57
+
}
58
+
59
+
mustContainViolation(testingContext, result, "userID")
60
+
mustContainViolation(testingContext, result, "httpClient")
61
+
}
62
+
63
+
func TestAnalyzeDoesNotFlagNormalDictionaryWords(testingContext *testing.T) {
64
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryPathForTests(testingContext))
65
+
66
+
identifiers := []collect.Identifier{
67
+
{Name: "options", Kind: "variable"},
68
+
{Name: "parsedResource", Kind: "variable"},
69
+
{Name: "hasResources", Kind: "variable"},
70
+
{Name: "allowlist", Kind: "variable"},
71
+
}
72
+
result, err := analyze.Run(identifiers, analyze.Options{})
73
+
74
+
if err != nil {
75
+
testingContext.Fatalf("analyze.Run returned an error: %v", err)
76
+
}
77
+
78
+
if len(result.Violations) != 0 {
79
+
testingContext.Fatalf("Expected no violations, got %d.", len(result.Violations))
80
+
}
81
+
}
82
+
83
+
func TestAnalyzeMinEvaluationLengthSkipsSingleLetterIdentifiers(testingContext *testing.T) {
84
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryPathForTests(testingContext))
85
+
86
+
identifiers := []collect.Identifier{
87
+
{Name: "t", Kind: "parameter"},
88
+
{Name: "v", Kind: "receiver"},
89
+
{Name: "ctx", Kind: "parameter"},
90
+
}
91
+
result, err := analyze.Run(identifiers, analyze.Options{
92
+
MinEvaluationLength: 2,
93
+
})
94
+
95
+
if err != nil {
96
+
testingContext.Fatalf("analyze.Run returned an error: %v", err)
97
+
}
98
+
99
+
if len(result.Violations) != 1 {
100
+
testingContext.Fatalf("Expected one violation, got %d.", len(result.Violations))
101
+
}
102
+
103
+
if result.Violations[0].Identifier.Name != "ctx" {
104
+
testingContext.Fatalf("Expected only ctx to be evaluated, got %q.", result.Violations[0].Identifier.Name)
105
+
}
106
+
}
107
+
108
+
func TestAnalyzeFlagsExpressionAbbreviation(testingContext *testing.T) {
109
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryPathForTests(testingContext))
110
+
111
+
identifiers := []collect.Identifier{
112
+
{Name: "expr", Kind: "variable"},
113
+
}
114
+
result, err := analyze.Run(identifiers, analyze.Options{
115
+
MinEvaluationLength: 1,
116
+
})
117
+
118
+
if err != nil {
119
+
testingContext.Fatalf("analyze.Run returned an error: %v", err)
120
+
}
121
+
122
+
if len(result.Violations) != 1 {
123
+
testingContext.Fatalf("Expected one violation, got %d.", len(result.Violations))
124
+
}
125
+
126
+
if result.Violations[0].Identifier.Name != "expr" {
127
+
testingContext.Fatalf("Expected expr to be flagged, got %q.", result.Violations[0].Identifier.Name)
128
+
}
129
+
}
130
+
131
+
func TestAnalyzeAllowsUpperCaseTokens(testingContext *testing.T) {
132
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryPathForTests(testingContext))
133
+
134
+
identifiers := []collect.Identifier{
135
+
{Name: "JSON", Kind: "variable"},
136
+
}
137
+
result, err := analyze.Run(identifiers, analyze.Options{})
138
+
139
+
if err != nil {
140
+
testingContext.Fatalf("analyze.Run returned an error: %v", err)
141
+
}
142
+
143
+
if len(result.Violations) != 0 {
144
+
testingContext.Fatalf("Expected no violations, got %d.", len(result.Violations))
145
+
}
146
+
}
147
+
148
+
func TestAnalyzeFailsWhenDictionaryIsUnavailable(testingContext *testing.T) {
149
+
emptyDictionaryPath := filepath.Join(testingContext.TempDir(), "empty.txt")
150
+
151
+
if err := os.WriteFile(emptyDictionaryPath, []byte("\n"), 0o644); err != nil {
152
+
testingContext.Fatalf("os.WriteFile returned an error: %v", err)
153
+
}
154
+
155
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", emptyDictionaryPath)
156
+
157
+
_, err := analyze.Run([]collect.Identifier{{Name: "ctx", Kind: "parameter"}}, analyze.Options{})
158
+
159
+
if err == nil {
160
+
testingContext.Fatalf("Expected analyze.Run to fail when dictionary data is unavailable.")
161
+
}
162
+
}
163
+
164
+
func mustContainViolation(testingContext *testing.T, result analyze.Result, name string) {
165
+
testingContext.Helper()
166
+
167
+
for _, violation := range result.Violations {
168
+
if violation.Identifier.Name == name {
169
+
return
170
+
}
171
+
}
172
+
173
+
testingContext.Fatalf("Expected a violation for %q.", name)
174
+
}
+26
internal/analyze/resources.go
+26
internal/analyze/resources.go
···
1
+
package analyze
2
+
3
+
import (
4
+
"fmt"
5
+
"github.com/Fuwn/kivia/internal/nlp"
6
+
)
7
+
8
+
type resources struct {
9
+
dictionary *nlp.Dictionary
10
+
}
11
+
12
+
func getResources() (resources, error) {
13
+
return loadResources()
14
+
}
15
+
16
+
func loadResources() (resources, error) {
17
+
dictionary, err := nlp.NewDictionary()
18
+
19
+
if err != nil {
20
+
return resources{}, fmt.Errorf("Failed to load dictionary: %w", err)
21
+
}
22
+
23
+
return resources{
24
+
dictionary: dictionary,
25
+
}, nil
26
+
}
+331
internal/collect/collect.go
+331
internal/collect/collect.go
···
1
+
package collect
2
+
3
+
import (
4
+
"bytes"
5
+
"fmt"
6
+
"go/ast"
7
+
"go/parser"
8
+
"go/printer"
9
+
"go/token"
10
+
"io/fs"
11
+
"os"
12
+
"path/filepath"
13
+
"sort"
14
+
"strings"
15
+
)
16
+
17
+
type Context struct {
18
+
EnclosingFunction string `json:"enclosingFunction,omitempty"`
19
+
Type string `json:"type,omitempty"`
20
+
ValueExpression string `json:"valueExpression,omitempty"`
21
+
ParentType string `json:"parentType,omitempty"`
22
+
}
23
+
24
+
type Identifier struct {
25
+
Name string `json:"name"`
26
+
Kind string `json:"kind"`
27
+
File string `json:"file"`
28
+
Line int `json:"line"`
29
+
Column int `json:"column"`
30
+
Context Context `json:"context"`
31
+
}
32
+
33
+
func FromPath(path string) ([]Identifier, error) {
34
+
files, err := discoverFiles(path)
35
+
36
+
if err != nil {
37
+
return nil, err
38
+
}
39
+
40
+
fileSet := token.NewFileSet()
41
+
identifiers := make([]Identifier, 0, 128)
42
+
43
+
for _, filePath := range files {
44
+
fileNode, parseErr := parser.ParseFile(fileSet, filePath, nil, parser.SkipObjectResolution)
45
+
46
+
if parseErr != nil {
47
+
return nil, fmt.Errorf("Failed to parse %s: %w", filePath, parseErr)
48
+
}
49
+
50
+
collector := visitor{
51
+
fileSet: fileSet,
52
+
file: filePath,
53
+
}
54
+
55
+
ast.Walk(&collector, fileNode)
56
+
57
+
identifiers = append(identifiers, collector.identifiers...)
58
+
}
59
+
60
+
return identifiers, nil
61
+
}
62
+
63
+
type visitor struct {
64
+
fileSet *token.FileSet
65
+
file string
66
+
identifiers []Identifier
67
+
functionStack []string
68
+
typeStack []string
69
+
}
70
+
71
+
func (identifierVisitor *visitor) Visit(node ast.Node) ast.Visitor {
72
+
switch typedNode := node.(type) {
73
+
case *ast.FuncDecl:
74
+
identifierVisitor.addIdentifier(typedNode.Name, "function", Context{})
75
+
76
+
identifierVisitor.functionStack = append(identifierVisitor.functionStack, typedNode.Name.Name)
77
+
78
+
identifierVisitor.captureFieldList(typedNode.Recv, "receiver")
79
+
identifierVisitor.captureFieldList(typedNode.Type.Params, "parameter")
80
+
identifierVisitor.captureFieldList(typedNode.Type.Results, "result")
81
+
82
+
return leaveScope(identifierVisitor, func() {
83
+
identifierVisitor.functionStack = identifierVisitor.functionStack[:len(identifierVisitor.functionStack)-1]
84
+
})
85
+
case *ast.TypeSpec:
86
+
identifierVisitor.addIdentifier(typedNode.Name, "type", Context{})
87
+
88
+
identifierVisitor.typeStack = append(identifierVisitor.typeStack, typedNode.Name.Name)
89
+
90
+
identifierVisitor.captureTypeMembers(typedNode.Name.Name, typedNode.Type)
91
+
92
+
return leaveScope(identifierVisitor, func() { identifierVisitor.typeStack = identifierVisitor.typeStack[:len(identifierVisitor.typeStack)-1] })
93
+
case *ast.ValueSpec:
94
+
declaredType := renderExpression(identifierVisitor.fileSet, typedNode.Type)
95
+
rightHandValue := renderExpressionList(identifierVisitor.fileSet, typedNode.Values)
96
+
97
+
for _, name := range typedNode.Names {
98
+
identifierVisitor.addIdentifier(name, "variable", Context{Type: declaredType, ValueExpression: rightHandValue})
99
+
}
100
+
case *ast.AssignStmt:
101
+
if typedNode.Tok != token.DEFINE {
102
+
break
103
+
}
104
+
105
+
rightHandValue := renderExpressionList(identifierVisitor.fileSet, typedNode.Rhs)
106
+
107
+
for index, left := range typedNode.Lhs {
108
+
identifierNode, ok := left.(*ast.Ident)
109
+
110
+
if !ok {
111
+
continue
112
+
}
113
+
114
+
assignmentContext := Context{ValueExpression: rightHandValue}
115
+
116
+
if index < len(typedNode.Rhs) {
117
+
assignmentContext.Type = inferTypeFromExpression(typedNode.Rhs[index])
118
+
}
119
+
120
+
identifierVisitor.addIdentifier(identifierNode, "variable", assignmentContext)
121
+
}
122
+
case *ast.RangeStmt:
123
+
if typedNode.Tok != token.DEFINE {
124
+
break
125
+
}
126
+
127
+
if keyIdentifier, ok := typedNode.Key.(*ast.Ident); ok {
128
+
identifierVisitor.addIdentifier(keyIdentifier, "rangeKey", Context{ValueExpression: renderExpression(identifierVisitor.fileSet, typedNode.X)})
129
+
}
130
+
131
+
if valueIdentifier, ok := typedNode.Value.(*ast.Ident); ok {
132
+
identifierVisitor.addIdentifier(valueIdentifier, "rangeValue", Context{ValueExpression: renderExpression(identifierVisitor.fileSet, typedNode.X)})
133
+
}
134
+
}
135
+
136
+
return identifierVisitor
137
+
}
138
+
139
+
type scopeExit struct {
140
+
parent *visitor
141
+
onLeave func()
142
+
}
143
+
144
+
func leaveScope(parent *visitor, onLeave func()) ast.Visitor {
145
+
return &scopeExit{parent: parent, onLeave: onLeave}
146
+
}
147
+
148
+
func (scopeExitVisitor *scopeExit) Visit(node ast.Node) ast.Visitor {
149
+
if node == nil {
150
+
scopeExitVisitor.onLeave()
151
+
152
+
return nil
153
+
}
154
+
155
+
return scopeExitVisitor.parent
156
+
}
157
+
158
+
func (identifierVisitor *visitor) captureFieldList(fields *ast.FieldList, kind string) {
159
+
if fields == nil {
160
+
return
161
+
}
162
+
163
+
for _, field := range fields.List {
164
+
declaredType := renderExpression(identifierVisitor.fileSet, field.Type)
165
+
166
+
for _, name := range field.Names {
167
+
identifierVisitor.addIdentifier(name, kind, Context{Type: declaredType})
168
+
}
169
+
}
170
+
}
171
+
172
+
func (identifierVisitor *visitor) captureTypeMembers(typeName string, typeExpression ast.Expr) {
173
+
switch typedType := typeExpression.(type) {
174
+
case *ast.StructType:
175
+
if typedType.Fields == nil {
176
+
return
177
+
}
178
+
179
+
for _, field := range typedType.Fields.List {
180
+
memberType := renderExpression(identifierVisitor.fileSet, field.Type)
181
+
182
+
for _, fieldName := range field.Names {
183
+
identifierVisitor.addIdentifier(fieldName, "field", Context{Type: memberType, ParentType: typeName})
184
+
}
185
+
}
186
+
case *ast.InterfaceType:
187
+
if typedType.Methods == nil {
188
+
return
189
+
}
190
+
191
+
for _, method := range typedType.Methods.List {
192
+
memberType := renderExpression(identifierVisitor.fileSet, method.Type)
193
+
194
+
for _, methodName := range method.Names {
195
+
identifierVisitor.addIdentifier(methodName, "interfaceMethod", Context{Type: memberType, ParentType: typeName})
196
+
}
197
+
}
198
+
}
199
+
}
200
+
201
+
func (identifierVisitor *visitor) addIdentifier(identifier *ast.Ident, kind string, context Context) {
202
+
if identifier == nil || identifier.Name == "_" {
203
+
return
204
+
}
205
+
206
+
position := identifierVisitor.fileSet.Position(identifier.NamePos)
207
+
context.EnclosingFunction = currentFunction(identifierVisitor.functionStack)
208
+
identifierVisitor.identifiers = append(identifierVisitor.identifiers, Identifier{
209
+
Name: identifier.Name,
210
+
Kind: kind,
211
+
File: identifierVisitor.file,
212
+
Line: position.Line,
213
+
Column: position.Column,
214
+
Context: context,
215
+
})
216
+
}
217
+
218
+
func currentFunction(stack []string) string {
219
+
if len(stack) == 0 {
220
+
return ""
221
+
}
222
+
223
+
return stack[len(stack)-1]
224
+
}
225
+
226
+
func discoverFiles(path string) ([]string, error) {
227
+
searchRoot := path
228
+
recursive := false
229
+
230
+
if strings.HasSuffix(path, "/...") {
231
+
searchRoot = strings.TrimSuffix(path, "/...")
232
+
recursive = true
233
+
}
234
+
235
+
if searchRoot == "" {
236
+
searchRoot = "."
237
+
}
238
+
239
+
pathFileDetails, err := os.Stat(searchRoot)
240
+
241
+
if err != nil {
242
+
return nil, err
243
+
}
244
+
245
+
if !pathFileDetails.IsDir() {
246
+
if strings.HasSuffix(searchRoot, ".go") {
247
+
return []string{searchRoot}, nil
248
+
}
249
+
250
+
return nil, fmt.Errorf("Path %q is not a Go file.", searchRoot)
251
+
}
252
+
253
+
files := make([]string, 0, 64)
254
+
walkErr := filepath.WalkDir(searchRoot, func(candidate string, entry fs.DirEntry, walkError error) error {
255
+
if walkError != nil {
256
+
return walkError
257
+
}
258
+
259
+
if entry.IsDir() {
260
+
name := entry.Name()
261
+
262
+
if name == ".git" || name == "vendor" || name == "node_modules" {
263
+
return filepath.SkipDir
264
+
}
265
+
266
+
if !recursive && candidate != searchRoot {
267
+
return filepath.SkipDir
268
+
}
269
+
270
+
return nil
271
+
}
272
+
273
+
if strings.HasSuffix(candidate, ".go") {
274
+
files = append(files, candidate)
275
+
}
276
+
277
+
return nil
278
+
})
279
+
280
+
if walkErr != nil {
281
+
return nil, walkErr
282
+
}
283
+
284
+
sort.Strings(files)
285
+
286
+
return files, nil
287
+
}
288
+
289
+
func renderExpression(fileSet *token.FileSet, expression ast.Expr) string {
290
+
if expression == nil {
291
+
return ""
292
+
}
293
+
294
+
var buffer bytes.Buffer
295
+
296
+
if err := printer.Fprint(&buffer, fileSet, expression); err != nil {
297
+
return ""
298
+
}
299
+
300
+
return buffer.String()
301
+
}
302
+
303
+
func renderExpressionList(fileSet *token.FileSet, expressions []ast.Expr) string {
304
+
if len(expressions) == 0 {
305
+
return ""
306
+
}
307
+
308
+
parts := make([]string, 0, len(expressions))
309
+
310
+
for _, expression := range expressions {
311
+
parts = append(parts, renderExpression(fileSet, expression))
312
+
}
313
+
314
+
return strings.Join(parts, ", ")
315
+
}
316
+
317
+
func inferTypeFromExpression(expression ast.Expr) string {
318
+
switch typedExpression := expression.(type) {
319
+
case *ast.CallExpr:
320
+
switch functionExpression := typedExpression.Fun.(type) {
321
+
case *ast.Ident:
322
+
return functionExpression.Name
323
+
case *ast.SelectorExpr:
324
+
return functionExpression.Sel.Name
325
+
}
326
+
327
+
return ""
328
+
default:
329
+
return ""
330
+
}
331
+
}
+614
internal/nlp/dictionary.go
+614
internal/nlp/dictionary.go
···
1
+
package nlp
2
+
3
+
import (
4
+
"bufio"
5
+
"errors"
6
+
"fmt"
7
+
"github.com/sajari/fuzzy"
8
+
"os"
9
+
"path"
10
+
"path/filepath"
11
+
"regexp"
12
+
"sort"
13
+
"strconv"
14
+
"strings"
15
+
"unicode/utf8"
16
+
)
17
+
18
+
var wordPattern = regexp.MustCompile(`[A-Za-z]+`)
19
+
20
+
type Dictionary struct {
21
+
model *fuzzy.Model
22
+
words map[string]struct{}
23
+
wordsByFirstCharacter map[rune][]string
24
+
}
25
+
26
+
func NewDictionary() (*Dictionary, error) {
27
+
words, err := loadWords()
28
+
29
+
if err != nil {
30
+
return nil, err
31
+
}
32
+
33
+
wordSet := makeWordSet(words)
34
+
wordsByFirstCharacter := makeWordsByFirstCharacter(words)
35
+
model, loadErr := loadCachedModel()
36
+
37
+
if loadErr == nil {
38
+
return &Dictionary{model: model, words: wordSet, wordsByFirstCharacter: wordsByFirstCharacter}, nil
39
+
}
40
+
41
+
model = fuzzy.NewModel()
42
+
43
+
model.SetThreshold(1)
44
+
model.SetDepth(1)
45
+
model.SetUseAutocomplete(false)
46
+
model.Train(words)
47
+
48
+
_ = saveCachedModel(model)
49
+
50
+
return &Dictionary{model: model, words: wordSet, wordsByFirstCharacter: wordsByFirstCharacter}, nil
51
+
}
52
+
53
+
func (dictionary *Dictionary) IsWord(token string) bool {
54
+
token = normalizeToken(token)
55
+
56
+
if token == "" || dictionary == nil {
57
+
return false
58
+
}
59
+
60
+
return dictionary.isLexiconWord(token)
61
+
}
62
+
63
+
func (dictionary *Dictionary) Suggest(token string) string {
64
+
token = normalizeToken(token)
65
+
66
+
if token == "" || dictionary == nil || dictionary.model == nil {
67
+
return ""
68
+
}
69
+
70
+
if dictionary.isLexiconWord(token) {
71
+
return ""
72
+
}
73
+
74
+
suggestions := dictionary.model.SpellCheckSuggestions(token, 1)
75
+
76
+
if len(suggestions) == 0 {
77
+
return ""
78
+
}
79
+
80
+
if suggestions[0] == token {
81
+
return ""
82
+
}
83
+
84
+
return suggestions[0]
85
+
}
86
+
87
+
func (dictionary *Dictionary) isLexiconWord(token string) bool {
88
+
if dictionary == nil {
89
+
return false
90
+
}
91
+
92
+
if _, ok := dictionary.words[token]; ok {
93
+
return true
94
+
}
95
+
96
+
candidates := make([]string, 0, 16)
97
+
candidates = append(candidates, inflectionCandidates(token)...)
98
+
candidates = append(candidates, spellingVariantCandidates(token)...)
99
+
100
+
for _, candidate := range inflectionCandidates(token) {
101
+
candidates = append(candidates, spellingVariantCandidates(candidate)...)
102
+
}
103
+
104
+
uniqueCandidates := make(map[string]struct{}, len(candidates))
105
+
106
+
for _, candidate := range candidates {
107
+
if candidate == "" || candidate == token {
108
+
continue
109
+
}
110
+
111
+
if _, seen := uniqueCandidates[candidate]; seen {
112
+
continue
113
+
}
114
+
115
+
uniqueCandidates[candidate] = struct{}{}
116
+
117
+
if _, ok := dictionary.words[candidate]; ok {
118
+
return true
119
+
}
120
+
}
121
+
122
+
return false
123
+
}
124
+
125
+
func (dictionary *Dictionary) AbbreviationExpansion(token string) (string, bool) {
126
+
token = normalizeToken(token)
127
+
128
+
if token == "" || dictionary == nil {
129
+
return "", false
130
+
}
131
+
132
+
tokenLength := utf8.RuneCountInString(token)
133
+
134
+
if tokenLength <= 1 || tokenLength > 4 {
135
+
return "", false
136
+
}
137
+
138
+
firstCharacter, _ := utf8.DecodeRuneInString(token)
139
+
candidates := dictionary.wordsByFirstCharacter[firstCharacter]
140
+
141
+
if len(candidates) == 0 {
142
+
return "", false
143
+
}
144
+
145
+
bestCandidate := ""
146
+
bestScore := 1 << 30
147
+
148
+
for _, candidate := range candidates {
149
+
if !isLikelyAbbreviationForToken(token, candidate) {
150
+
continue
151
+
}
152
+
153
+
score := abbreviationScore(token, candidate)
154
+
155
+
if score < bestScore {
156
+
bestScore = score
157
+
bestCandidate = candidate
158
+
}
159
+
}
160
+
161
+
if bestCandidate == "" {
162
+
return "", false
163
+
}
164
+
165
+
return bestCandidate, true
166
+
}
167
+
168
+
func isLikelyAbbreviationForToken(token string, candidate string) bool {
169
+
if candidate == "" || token == "" || token == candidate {
170
+
return false
171
+
}
172
+
173
+
tokenLength := utf8.RuneCountInString(token)
174
+
candidateLength := utf8.RuneCountInString(candidate)
175
+
176
+
if candidateLength <= tokenLength {
177
+
return false
178
+
}
179
+
180
+
if !isSubsequence(token, candidate) {
181
+
return false
182
+
}
183
+
184
+
if strings.HasPrefix(candidate, token) && tokenLength <= 4 {
185
+
return true
186
+
}
187
+
188
+
tokenConsonants := consonantSkeleton(token)
189
+
candidateConsonants := consonantSkeleton(candidate)
190
+
191
+
if tokenConsonants == "" || candidateConsonants == "" {
192
+
return false
193
+
}
194
+
195
+
if isSubsequence(tokenConsonants, candidateConsonants) && tokenLength <= 5 {
196
+
return true
197
+
}
198
+
199
+
return false
200
+
}
201
+
202
+
func abbreviationScore(token string, candidate string) int {
203
+
tokenLength := utf8.RuneCountInString(token)
204
+
candidateLength := utf8.RuneCountInString(candidate)
205
+
lengthGap := max(candidateLength-tokenLength, 0)
206
+
score := lengthGap * 10
207
+
208
+
if strings.HasPrefix(candidate, token) {
209
+
score -= 3
210
+
}
211
+
212
+
return score
213
+
}
214
+
215
+
func isSubsequence(shorter string, longer string) bool {
216
+
shorterRunes := []rune(shorter)
217
+
longerRunes := []rune(longer)
218
+
shorterIndex := 0
219
+
220
+
for _, character := range longerRunes {
221
+
if shorterIndex >= len(shorterRunes) {
222
+
break
223
+
}
224
+
225
+
if shorterRunes[shorterIndex] == character {
226
+
shorterIndex++
227
+
}
228
+
}
229
+
230
+
return shorterIndex == len(shorterRunes)
231
+
}
232
+
233
+
func consonantSkeleton(word string) string {
234
+
var builder strings.Builder
235
+
236
+
for _, character := range word {
237
+
switch character {
238
+
case 'a', 'e', 'i', 'o', 'u':
239
+
continue
240
+
default:
241
+
builder.WriteRune(character)
242
+
}
243
+
}
244
+
245
+
return builder.String()
246
+
}
247
+
248
+
func inflectionCandidates(token string) []string {
249
+
candidates := make([]string, 0, 8)
250
+
251
+
if strings.HasSuffix(token, "ies") && len(token) > 3 {
252
+
candidates = append(candidates, token[:len(token)-3]+"y")
253
+
}
254
+
255
+
if strings.HasSuffix(token, "es") && len(token) > 2 {
256
+
candidates = append(candidates, token[:len(token)-2])
257
+
}
258
+
259
+
if strings.HasSuffix(token, "s") && len(token) > 1 {
260
+
candidates = append(candidates, token[:len(token)-1])
261
+
}
262
+
263
+
if strings.HasSuffix(token, "ed") && len(token) > 2 {
264
+
candidateWithoutSuffix := token[:len(token)-2]
265
+
candidates = append(candidates, candidateWithoutSuffix)
266
+
candidates = append(candidates, candidateWithoutSuffix+"e")
267
+
268
+
if len(candidateWithoutSuffix) >= 2 {
269
+
lastCharacter := candidateWithoutSuffix[len(candidateWithoutSuffix)-1]
270
+
secondToLastCharacter := candidateWithoutSuffix[len(candidateWithoutSuffix)-2]
271
+
272
+
if lastCharacter == secondToLastCharacter {
273
+
candidates = append(candidates, candidateWithoutSuffix[:len(candidateWithoutSuffix)-1])
274
+
}
275
+
}
276
+
}
277
+
278
+
if strings.HasSuffix(token, "ing") && len(token) > 3 {
279
+
candidateWithoutSuffix := token[:len(token)-3]
280
+
candidates = append(candidates, candidateWithoutSuffix)
281
+
candidates = append(candidates, candidateWithoutSuffix+"e")
282
+
}
283
+
284
+
if strings.HasSuffix(token, "er") && len(token) > 2 {
285
+
candidateWithoutSuffix := token[:len(token)-2]
286
+
candidates = append(candidates, candidateWithoutSuffix)
287
+
candidates = append(candidates, candidateWithoutSuffix+"e")
288
+
289
+
if len(candidateWithoutSuffix) >= 2 {
290
+
lastCharacter := candidateWithoutSuffix[len(candidateWithoutSuffix)-1]
291
+
secondToLastCharacter := candidateWithoutSuffix[len(candidateWithoutSuffix)-2]
292
+
293
+
if lastCharacter == secondToLastCharacter {
294
+
candidates = append(candidates, candidateWithoutSuffix[:len(candidateWithoutSuffix)-1])
295
+
}
296
+
}
297
+
}
298
+
299
+
if strings.HasSuffix(token, "ize") && len(token) > 3 {
300
+
candidates = append(candidates, token[:len(token)-3])
301
+
}
302
+
303
+
if strings.HasSuffix(token, "ized") && len(token) > 4 {
304
+
candidates = append(candidates, token[:len(token)-4])
305
+
}
306
+
307
+
if strings.HasSuffix(token, "izing") && len(token) > 5 {
308
+
candidates = append(candidates, token[:len(token)-5])
309
+
}
310
+
311
+
if strings.HasSuffix(token, "izer") && len(token) > 4 {
312
+
candidates = append(candidates, token[:len(token)-4])
313
+
}
314
+
315
+
if strings.HasSuffix(token, "ization") && len(token) > 7 {
316
+
candidates = append(candidates, token[:len(token)-7])
317
+
}
318
+
319
+
return candidates
320
+
}
321
+
322
+
func spellingVariantCandidates(token string) []string {
323
+
candidates := make([]string, 0, 8)
324
+
325
+
appendSuffixVariant(&candidates, token, "isation", "ization")
326
+
appendSuffixVariant(&candidates, token, "ization", "isation")
327
+
appendSuffixVariant(&candidates, token, "ising", "izing")
328
+
appendSuffixVariant(&candidates, token, "izing", "ising")
329
+
appendSuffixVariant(&candidates, token, "ised", "ized")
330
+
appendSuffixVariant(&candidates, token, "ized", "ised")
331
+
appendSuffixVariant(&candidates, token, "iser", "izer")
332
+
appendSuffixVariant(&candidates, token, "izer", "iser")
333
+
appendSuffixVariant(&candidates, token, "ise", "ize")
334
+
appendSuffixVariant(&candidates, token, "ize", "ise")
335
+
appendSuffixVariant(&candidates, token, "our", "or")
336
+
appendSuffixVariant(&candidates, token, "or", "our")
337
+
appendSuffixVariant(&candidates, token, "tre", "ter")
338
+
appendSuffixVariant(&candidates, token, "ter", "tre")
339
+
340
+
return candidates
341
+
}
342
+
343
+
func appendSuffixVariant(candidates *[]string, token string, fromSuffix string, toSuffix string) {
344
+
if !strings.HasSuffix(token, fromSuffix) || len(token) <= len(fromSuffix) {
345
+
return
346
+
}
347
+
348
+
root := token[:len(token)-len(fromSuffix)]
349
+
*candidates = append(*candidates, root+toSuffix)
350
+
}
351
+
352
+
func makeWordSet(words []string) map[string]struct{} {
353
+
set := make(map[string]struct{}, len(words))
354
+
355
+
for _, word := range words {
356
+
set[word] = struct{}{}
357
+
}
358
+
359
+
return set
360
+
}
361
+
362
+
func makeWordsByFirstCharacter(words []string) map[rune][]string {
363
+
grouped := make(map[rune][]string)
364
+
365
+
for _, word := range words {
366
+
firstCharacter, size := utf8.DecodeRuneInString(word)
367
+
368
+
if firstCharacter == utf8.RuneError && size == 0 {
369
+
continue
370
+
}
371
+
372
+
grouped[firstCharacter] = append(grouped[firstCharacter], word)
373
+
}
374
+
375
+
for firstCharacter := range grouped {
376
+
sort.Strings(grouped[firstCharacter])
377
+
}
378
+
379
+
return grouped
380
+
}
381
+
382
+
func loadWords() ([]string, error) {
383
+
configuredDictionaryPaths := parseDictionaryPaths(os.Getenv("KIVIA_DICTIONARY_PATH"))
384
+
385
+
if len(configuredDictionaryPaths) > 0 {
386
+
words, err := loadWordsFromPaths(configuredDictionaryPaths, true)
387
+
388
+
if err != nil {
389
+
return nil, err
390
+
}
391
+
392
+
if len(words) == 0 {
393
+
return nil, errors.New("configured dictionary sources contain no usable words")
394
+
}
395
+
396
+
return words, nil
397
+
}
398
+
399
+
words, err := loadWordsFromPaths(defaultDictionaryPaths, false)
400
+
401
+
if err != nil {
402
+
return nil, err
403
+
}
404
+
405
+
if len(words) == 0 {
406
+
return nil, errors.New("no usable dictionary words found; set KIVIA_DICTIONARY_PATH")
407
+
}
408
+
409
+
return words, nil
410
+
}
411
+
412
+
func readWordsFromFile(filePath string) ([]string, error) {
413
+
file, err := os.Open(filePath)
414
+
415
+
if err != nil {
416
+
return nil, err
417
+
}
418
+
419
+
defer file.Close()
420
+
421
+
words := make([]string, 0, 1024)
422
+
scanner := bufio.NewScanner(file)
423
+
isSpellDictionaryFile := strings.EqualFold(path.Ext(filePath), ".dic")
424
+
lineNumber := 0
425
+
426
+
for scanner.Scan() {
427
+
lineNumber++
428
+
429
+
line := normalizeDictionaryLine(scanner.Text(), lineNumber, isSpellDictionaryFile)
430
+
431
+
if line == "" {
432
+
continue
433
+
}
434
+
435
+
words = append(words, line)
436
+
}
437
+
438
+
if err := scanner.Err(); err != nil {
439
+
return nil, err
440
+
}
441
+
442
+
return normalizeWords(words), nil
443
+
}
444
+
445
+
func parseDictionaryPaths(value string) []string {
446
+
trimmedValue := strings.TrimSpace(value)
447
+
448
+
if trimmedValue == "" {
449
+
return nil
450
+
}
451
+
452
+
expandedValue := strings.ReplaceAll(trimmedValue, ",", string(os.PathListSeparator))
453
+
parts := strings.Split(expandedValue, string(os.PathListSeparator))
454
+
paths := make([]string, 0, len(parts))
455
+
456
+
for _, entry := range parts {
457
+
candidate := strings.TrimSpace(entry)
458
+
459
+
if candidate == "" {
460
+
continue
461
+
}
462
+
463
+
paths = append(paths, candidate)
464
+
}
465
+
466
+
return paths
467
+
}
468
+
469
+
func loadWordsFromPaths(paths []string, strict bool) ([]string, error) {
470
+
combinedWords := make([]string, 0, 4096)
471
+
472
+
for _, dictionaryPath := range paths {
473
+
words, err := readWordsFromFile(dictionaryPath)
474
+
475
+
if err != nil {
476
+
if strict {
477
+
return nil, fmt.Errorf("failed to read dictionary %q: %w", dictionaryPath, err)
478
+
}
479
+
480
+
continue
481
+
}
482
+
483
+
combinedWords = append(combinedWords, words...)
484
+
}
485
+
486
+
return normalizeWords(combinedWords), nil
487
+
}
488
+
489
+
func normalizeDictionaryLine(line string, lineNumber int, isSpellDictionaryFile bool) string {
490
+
trimmedLine := strings.TrimSpace(line)
491
+
492
+
if trimmedLine == "" || strings.HasPrefix(trimmedLine, "#") {
493
+
return ""
494
+
}
495
+
496
+
if isSpellDictionaryFile && lineNumber == 1 {
497
+
if _, err := strconv.Atoi(trimmedLine); err == nil {
498
+
return ""
499
+
}
500
+
}
501
+
502
+
if slashIndex := strings.Index(trimmedLine, "/"); slashIndex >= 0 {
503
+
trimmedLine = trimmedLine[:slashIndex]
504
+
}
505
+
506
+
return trimmedLine
507
+
}
508
+
509
+
func normalizeWords(words []string) []string {
510
+
unique := make(map[string]struct{}, len(words))
511
+
512
+
for _, word := range words {
513
+
normalized := normalizeToken(word)
514
+
515
+
if normalized == "" {
516
+
continue
517
+
}
518
+
519
+
if len(normalized) <= 1 {
520
+
continue
521
+
}
522
+
523
+
unique[normalized] = struct{}{}
524
+
}
525
+
526
+
output := make([]string, 0, len(unique))
527
+
528
+
for word := range unique {
529
+
output = append(output, word)
530
+
}
531
+
532
+
sort.Strings(output)
533
+
534
+
return output
535
+
}
536
+
537
+
func normalizeToken(token string) string {
538
+
token = strings.ToLower(strings.TrimSpace(token))
539
+
540
+
if token == "" {
541
+
return ""
542
+
}
543
+
544
+
match := wordPattern.FindString(token)
545
+
546
+
if match == "" {
547
+
return ""
548
+
}
549
+
550
+
return match
551
+
}
552
+
553
+
func cachePath() (string, error) {
554
+
base, err := os.UserCacheDir()
555
+
556
+
if err != nil {
557
+
return "", err
558
+
}
559
+
560
+
return filepath.Join(base, "kivia", "fuzzy_model_v1.json"), nil
561
+
}
562
+
563
+
func loadCachedModel() (*fuzzy.Model, error) {
564
+
path, err := cachePath()
565
+
566
+
if err != nil {
567
+
return nil, err
568
+
}
569
+
570
+
model, err := fuzzy.Load(path)
571
+
572
+
if err != nil {
573
+
return nil, err
574
+
}
575
+
576
+
return model, nil
577
+
}
578
+
579
+
func saveCachedModel(model *fuzzy.Model) error {
580
+
if model == nil {
581
+
return errors.New("Model cannot be nil.")
582
+
}
583
+
584
+
path, err := cachePath()
585
+
586
+
if err != nil {
587
+
return err
588
+
}
589
+
590
+
if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
591
+
return err
592
+
}
593
+
594
+
return model.Save(path)
595
+
}
596
+
597
+
var defaultDictionaryPaths = []string{
598
+
"/usr/share/dict/words",
599
+
"/usr/dict/words",
600
+
"/usr/share/dict/web2",
601
+
"/usr/share/dict/web2a",
602
+
"/usr/share/dict/propernames",
603
+
"/usr/share/dict/connectives",
604
+
"/usr/share/hunspell/en_US.dic",
605
+
"/usr/share/hunspell/en_GB.dic",
606
+
"/usr/share/hunspell/en_CA.dic",
607
+
"/usr/share/hunspell/en_AU.dic",
608
+
"/usr/share/myspell/en_US.dic",
609
+
"/usr/share/myspell/en_GB.dic",
610
+
"/opt/homebrew/share/hunspell/en_US.dic",
611
+
"/opt/homebrew/share/hunspell/en_GB.dic",
612
+
"/usr/local/share/hunspell/en_US.dic",
613
+
"/usr/local/share/hunspell/en_GB.dic",
614
+
}
+165
internal/nlp/dictionary_test.go
+165
internal/nlp/dictionary_test.go
···
1
+
package nlp_test
2
+
3
+
import (
4
+
"github.com/Fuwn/kivia/internal/nlp"
5
+
"os"
6
+
"path/filepath"
7
+
"strings"
8
+
"testing"
9
+
)
10
+
11
+
func TestDictionaryRecognizesLexiconWords(testingContext *testing.T) {
12
+
dictionaryFile := filepath.Join("..", "..", "testdata", "dictionary", "words.txt")
13
+
14
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryFile)
15
+
16
+
dictionary, err := nlp.NewDictionary()
17
+
18
+
if err != nil {
19
+
testingContext.Fatalf("NewDictionary returned an error: %v", err)
20
+
}
21
+
22
+
if !dictionary.IsWord("options") {
23
+
testingContext.Fatalf("Expected options to be recognized.")
24
+
}
25
+
26
+
if !dictionary.IsWord("has") {
27
+
testingContext.Fatalf("Expected has to be recognized.")
28
+
}
29
+
30
+
if !dictionary.IsWord("resources") {
31
+
testingContext.Fatalf("Expected resources to be recognized through plural inflection.")
32
+
}
33
+
}
34
+
35
+
func TestDictionaryFindsAbbreviationExpansions(testingContext *testing.T) {
36
+
dictionaryFile := filepath.Join("..", "..", "testdata", "dictionary", "words.txt")
37
+
38
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryFile)
39
+
40
+
dictionary, err := nlp.NewDictionary()
41
+
42
+
if err != nil {
43
+
testingContext.Fatalf("NewDictionary returned an error: %v", err)
44
+
}
45
+
46
+
cases := map[string]string{
47
+
"expr": "expression",
48
+
"ctx": "context",
49
+
"err": "error",
50
+
}
51
+
52
+
for token, expectedExpansion := range cases {
53
+
expansion, ok := dictionary.AbbreviationExpansion(token)
54
+
55
+
if !ok {
56
+
testingContext.Fatalf("Expected an abbreviation expansion for %q.", token)
57
+
}
58
+
59
+
if expansion != expectedExpansion {
60
+
testingContext.Fatalf("Expected %q to expand to %q, got %q.", token, expectedExpansion, expansion)
61
+
}
62
+
}
63
+
}
64
+
65
+
func TestDictionaryLoadsFromMultipleDictionaryFiles(testingContext *testing.T) {
66
+
tempDirectory := testingContext.TempDir()
67
+
firstDictionaryPath := filepath.Join(tempDirectory, "first.txt")
68
+
secondDictionaryPath := filepath.Join(tempDirectory, "second.txt")
69
+
combinedPathList := strings.Join([]string{firstDictionaryPath, secondDictionaryPath}, string(os.PathListSeparator))
70
+
71
+
if err := os.WriteFile(firstDictionaryPath, []byte("alpha\n"), 0o644); err != nil {
72
+
testingContext.Fatalf("os.WriteFile returned an error: %v", err)
73
+
}
74
+
75
+
if err := os.WriteFile(secondDictionaryPath, []byte("beta\n"), 0o644); err != nil {
76
+
testingContext.Fatalf("os.WriteFile returned an error: %v", err)
77
+
}
78
+
79
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", combinedPathList)
80
+
81
+
dictionary, err := nlp.NewDictionary()
82
+
83
+
if err != nil {
84
+
testingContext.Fatalf("NewDictionary returned an error: %v", err)
85
+
}
86
+
87
+
if !dictionary.IsWord("alpha") {
88
+
testingContext.Fatalf("Expected alpha to be recognized.")
89
+
}
90
+
91
+
if !dictionary.IsWord("beta") {
92
+
testingContext.Fatalf("Expected beta to be recognized.")
93
+
}
94
+
}
95
+
96
+
func TestDictionaryFailsWhenConfiguredPathHasNoWords(testingContext *testing.T) {
97
+
tempDirectory := testingContext.TempDir()
98
+
emptyDictionaryPath := filepath.Join(tempDirectory, "empty.txt")
99
+
100
+
if err := os.WriteFile(emptyDictionaryPath, []byte("\n"), 0o644); err != nil {
101
+
testingContext.Fatalf("os.WriteFile returned an error: %v", err)
102
+
}
103
+
104
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", emptyDictionaryPath)
105
+
106
+
_, err := nlp.NewDictionary()
107
+
108
+
if err == nil {
109
+
testingContext.Fatalf("Expected NewDictionary to fail when configured dictionary has no usable words.")
110
+
}
111
+
}
112
+
113
+
func TestDictionaryRecognizesDerivedForms(testingContext *testing.T) {
114
+
tempDirectory := testingContext.TempDir()
115
+
dictionaryPath := filepath.Join(tempDirectory, "base_words.txt")
116
+
117
+
if err := os.WriteFile(dictionaryPath, []byte("trim\ntoken\n"), 0o644); err != nil {
118
+
testingContext.Fatalf("os.WriteFile returned an error: %v", err)
119
+
}
120
+
121
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryPath)
122
+
123
+
dictionary, err := nlp.NewDictionary()
124
+
125
+
if err != nil {
126
+
testingContext.Fatalf("NewDictionary returned an error: %v", err)
127
+
}
128
+
129
+
if !dictionary.IsWord("trimmed") {
130
+
testingContext.Fatalf("Expected trimmed to be recognized from trim.")
131
+
}
132
+
133
+
if !dictionary.IsWord("tokenize") {
134
+
testingContext.Fatalf("Expected tokenize to be recognized from token.")
135
+
}
136
+
}
137
+
138
+
func TestDictionaryRecognizesBritishAndAmericanVariants(testingContext *testing.T) {
139
+
tempDirectory := testingContext.TempDir()
140
+
dictionaryPath := filepath.Join(tempDirectory, "british_words.txt")
141
+
142
+
if err := os.WriteFile(dictionaryPath, []byte("normalise\ncolour\ncentre\n"), 0o644); err != nil {
143
+
testingContext.Fatalf("os.WriteFile returned an error: %v", err)
144
+
}
145
+
146
+
testingContext.Setenv("KIVIA_DICTIONARY_PATH", dictionaryPath)
147
+
148
+
dictionary, err := nlp.NewDictionary()
149
+
150
+
if err != nil {
151
+
testingContext.Fatalf("NewDictionary returned an error: %v", err)
152
+
}
153
+
154
+
if !dictionary.IsWord("normalize") {
155
+
testingContext.Fatalf("Expected normalize to be recognized from normalise.")
156
+
}
157
+
158
+
if !dictionary.IsWord("color") {
159
+
testingContext.Fatalf("Expected color to be recognized from colour.")
160
+
}
161
+
162
+
if !dictionary.IsWord("center") {
163
+
testingContext.Fatalf("Expected center to be recognized from centre.")
164
+
}
165
+
}
+80
internal/report/report.go
+80
internal/report/report.go
···
1
+
package report
2
+
3
+
import (
4
+
"encoding/json"
5
+
"fmt"
6
+
"github.com/Fuwn/kivia/internal/analyze"
7
+
"github.com/Fuwn/kivia/internal/collect"
8
+
"io"
9
+
"strings"
10
+
)
11
+
12
+
func Render(writer io.Writer, result analyze.Result, format string, includeContext bool) error {
13
+
switch strings.ToLower(format) {
14
+
case "json":
15
+
return renderJSON(writer, result, includeContext)
16
+
case "text", "":
17
+
return renderText(writer, result, includeContext)
18
+
default:
19
+
return fmt.Errorf("Unsupported output format %q. Use \"text\" or \"json\".", format)
20
+
}
21
+
}
22
+
23
+
func renderText(writer io.Writer, result analyze.Result, includeContext bool) error {
24
+
if len(result.Violations) == 0 {
25
+
_, err := fmt.Fprintln(writer, "No naming violations found.")
26
+
27
+
return err
28
+
}
29
+
30
+
for _, violation := range result.Violations {
31
+
if _, err := fmt.Fprintf(writer, "%s:%d:%d %s %q: %s\n",
32
+
violation.Identifier.File,
33
+
violation.Identifier.Line,
34
+
violation.Identifier.Column,
35
+
violation.Identifier.Kind,
36
+
violation.Identifier.Name,
37
+
violation.Reason,
38
+
); err != nil {
39
+
return err
40
+
}
41
+
42
+
if includeContext {
43
+
contextParts := make([]string, 0, 3)
44
+
45
+
if violation.Identifier.Context.Type != "" {
46
+
contextParts = append(contextParts, "type="+violation.Identifier.Context.Type)
47
+
}
48
+
49
+
if violation.Identifier.Context.ValueExpression != "" {
50
+
contextParts = append(contextParts, "value="+violation.Identifier.Context.ValueExpression)
51
+
}
52
+
53
+
if violation.Identifier.Context.EnclosingFunction != "" {
54
+
contextParts = append(contextParts, "function="+violation.Identifier.Context.EnclosingFunction)
55
+
}
56
+
57
+
if len(contextParts) > 0 {
58
+
if _, err := fmt.Fprintf(writer, " context: %s\n", strings.Join(contextParts, ", ")); err != nil {
59
+
return err
60
+
}
61
+
}
62
+
}
63
+
}
64
+
65
+
return nil
66
+
}
67
+
68
+
func renderJSON(writer io.Writer, result analyze.Result, includeContext bool) error {
69
+
if !includeContext {
70
+
for index := range result.Violations {
71
+
result.Violations[index].Identifier.Context = collect.Context{}
72
+
}
73
+
}
74
+
75
+
encoder := json.NewEncoder(writer)
76
+
77
+
encoder.SetIndent("", " ")
78
+
79
+
return encoder.Encode(result)
80
+
}
+20
justfile
+20
justfile
···
1
+
set shell := ["bash", "-eu", "-o", "pipefail", "-c"]
2
+
3
+
build:
4
+
mkdir -p bin
5
+
go build -o ./bin/kivia .
6
+
7
+
format:
8
+
iku -w . || go fmt ./...
9
+
10
+
test:
11
+
go test ./...
12
+
13
+
run *args:
14
+
go run . {{args}}
15
+
16
+
self:
17
+
go run . --path ./... --ignore file=testdata
18
+
19
+
install:
20
+
go install .
+196
main.go
+196
main.go
···
1
+
package main
2
+
3
+
import (
4
+
"errors"
5
+
"flag"
6
+
"fmt"
7
+
"github.com/Fuwn/kivia/internal/analyze"
8
+
"github.com/Fuwn/kivia/internal/collect"
9
+
"github.com/Fuwn/kivia/internal/report"
10
+
"os"
11
+
"slices"
12
+
"strings"
13
+
)
14
+
15
+
type options struct {
16
+
Path string
17
+
OmitContext bool
18
+
MinimumEvaluationLength int
19
+
Format string
20
+
FailOnViolation bool
21
+
Ignore []string
22
+
}
23
+
24
+
func parseOptions(arguments []string) (options, error) {
25
+
flagSet := flag.NewFlagSet("kivia", flag.ContinueOnError)
26
+
27
+
flagSet.SetOutput(os.Stderr)
28
+
29
+
var parsed options
30
+
var ignoreValues stringSliceFlag
31
+
32
+
flagSet.StringVar(&parsed.Path, "path", "./...", "Path to analyze (directory, file, or ./...).")
33
+
flagSet.BoolVar(&parsed.OmitContext, "omit-context", false, "Hide usage context in output.")
34
+
flagSet.IntVar(&parsed.MinimumEvaluationLength, "min-eval-length", 1, "Minimum identifier length in runes to evaluate.")
35
+
flagSet.StringVar(&parsed.Format, "format", "text", "Output format: text or JSON.")
36
+
flagSet.BoolVar(&parsed.FailOnViolation, "fail-on-violation", false, "Exit with code 1 when violations are found.")
37
+
flagSet.Var(&ignoreValues, "ignore", "Ignore violations by matcher. Repeat this flag as needed. Prefixes: name=, kind=, file=, reason=, func=.")
38
+
39
+
if err := flagSet.Parse(arguments); err != nil {
40
+
return options{}, err
41
+
}
42
+
43
+
if parsed.MinimumEvaluationLength < 1 {
44
+
return options{}, errors.New("The --min-eval-length value must be at least 1.")
45
+
}
46
+
47
+
parsed.Ignore = slices.Clone(ignoreValues)
48
+
49
+
return parsed, nil
50
+
}
51
+
52
+
func run(parsed options) error {
53
+
identifiers, err := collect.FromPath(parsed.Path)
54
+
55
+
if err != nil {
56
+
return err
57
+
}
58
+
59
+
result, err := analyze.Run(identifiers, analyze.Options{
60
+
MinEvaluationLength: parsed.MinimumEvaluationLength,
61
+
})
62
+
63
+
if err != nil {
64
+
return err
65
+
}
66
+
67
+
result = applyIgnoreFilters(result, parsed.Ignore)
68
+
69
+
if err := report.Render(os.Stdout, result, parsed.Format, !parsed.OmitContext); err != nil {
70
+
return err
71
+
}
72
+
73
+
if parsed.FailOnViolation && len(result.Violations) > 0 {
74
+
return exitCodeError(1)
75
+
}
76
+
77
+
return nil
78
+
}
79
+
80
+
func main() {
81
+
parsed, err := parseOptions(os.Args[1:])
82
+
83
+
if err != nil {
84
+
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
85
+
os.Exit(2)
86
+
}
87
+
88
+
if err := run(parsed); err != nil {
89
+
var codeError exitCodeError
90
+
91
+
if errors.As(err, &codeError) {
92
+
os.Exit(int(codeError))
93
+
}
94
+
95
+
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
96
+
os.Exit(1)
97
+
}
98
+
}
99
+
100
+
type exitCodeError int
101
+
102
+
func (errorCode exitCodeError) Error() string {
103
+
return fmt.Sprintf("Process exited with code %d.", int(errorCode))
104
+
}
105
+
106
+
type stringSliceFlag []string
107
+
108
+
func (values *stringSliceFlag) String() string {
109
+
if values == nil {
110
+
return ""
111
+
}
112
+
113
+
return strings.Join(*values, ",")
114
+
}
115
+
116
+
func (values *stringSliceFlag) Set(value string) error {
117
+
trimmed := strings.TrimSpace(value)
118
+
119
+
if trimmed == "" {
120
+
return errors.New("Ignore matcher cannot be empty.")
121
+
}
122
+
123
+
*values = append(*values, trimmed)
124
+
125
+
return nil
126
+
}
127
+
128
+
func applyIgnoreFilters(result analyze.Result, ignoreMatchers []string) analyze.Result {
129
+
if len(ignoreMatchers) == 0 || len(result.Violations) == 0 {
130
+
return result
131
+
}
132
+
133
+
filteredViolations := make([]analyze.Violation, 0, len(result.Violations))
134
+
135
+
for _, violation := range result.Violations {
136
+
if shouldIgnoreViolation(violation, ignoreMatchers) {
137
+
continue
138
+
}
139
+
140
+
filteredViolations = append(filteredViolations, violation)
141
+
}
142
+
143
+
result.Violations = filteredViolations
144
+
145
+
return result
146
+
}
147
+
148
+
func shouldIgnoreViolation(violation analyze.Violation, ignoreMatchers []string) bool {
149
+
for _, matcher := range ignoreMatchers {
150
+
if matchesViolation(matcher, violation) {
151
+
return true
152
+
}
153
+
}
154
+
155
+
return false
156
+
}
157
+
158
+
func matchesViolation(matcher string, violation analyze.Violation) bool {
159
+
normalizedMatcher := strings.ToLower(strings.TrimSpace(matcher))
160
+
161
+
if normalizedMatcher == "" {
162
+
return false
163
+
}
164
+
165
+
identifier := violation.Identifier
166
+
167
+
if strings.HasPrefix(normalizedMatcher, "name=") {
168
+
return strings.Contains(strings.ToLower(identifier.Name), strings.TrimPrefix(normalizedMatcher, "name="))
169
+
}
170
+
171
+
if strings.HasPrefix(normalizedMatcher, "kind=") {
172
+
return strings.Contains(strings.ToLower(identifier.Kind), strings.TrimPrefix(normalizedMatcher, "kind="))
173
+
}
174
+
175
+
if strings.HasPrefix(normalizedMatcher, "file=") {
176
+
return strings.Contains(strings.ToLower(identifier.File), strings.TrimPrefix(normalizedMatcher, "file="))
177
+
}
178
+
179
+
if strings.HasPrefix(normalizedMatcher, "reason=") {
180
+
return strings.Contains(strings.ToLower(violation.Reason), strings.TrimPrefix(normalizedMatcher, "reason="))
181
+
}
182
+
183
+
if strings.HasPrefix(normalizedMatcher, "func=") {
184
+
return strings.Contains(strings.ToLower(identifier.Context.EnclosingFunction), strings.TrimPrefix(normalizedMatcher, "func="))
185
+
}
186
+
187
+
composite := strings.ToLower(strings.Join([]string{
188
+
identifier.Name,
189
+
identifier.Kind,
190
+
identifier.File,
191
+
violation.Reason,
192
+
identifier.Context.EnclosingFunction,
193
+
}, " "))
194
+
195
+
return strings.Contains(composite, normalizedMatcher)
196
+
}
+103
main_test.go
+103
main_test.go
···
1
+
package main
2
+
3
+
import (
4
+
"github.com/Fuwn/kivia/internal/analyze"
5
+
"github.com/Fuwn/kivia/internal/collect"
6
+
"testing"
7
+
)
8
+
9
+
func TestParseOptionsDefaults(testingContext *testing.T) {
10
+
options, err := parseOptions([]string{"--path", "./testdata"})
11
+
12
+
if err != nil {
13
+
testingContext.Fatalf("parseOptions returned an error: %v", err)
14
+
}
15
+
16
+
if options.MinimumEvaluationLength != 1 {
17
+
testingContext.Fatalf("Expected min-eval-length to default to 1, got %d.", options.MinimumEvaluationLength)
18
+
}
19
+
}
20
+
21
+
func TestParseOptionsRejectsStrictFlag(testingContext *testing.T) {
22
+
_, err := parseOptions([]string{"--path", "./testdata", "--strict"})
23
+
24
+
if err == nil {
25
+
testingContext.Fatalf("Expected parseOptions to fail when --strict is provided.")
26
+
}
27
+
}
28
+
29
+
func TestParseOptionsReadsMultipleIgnoreFlags(testingContext *testing.T) {
30
+
options, err := parseOptions([]string{
31
+
"--path", "./testdata",
32
+
"--ignore", "name=ctx",
33
+
"--ignore", "file=_test.go",
34
+
"--ignore", "reason=too short",
35
+
})
36
+
37
+
if err != nil {
38
+
testingContext.Fatalf("parseOptions returned an error: %v", err)
39
+
}
40
+
41
+
if len(options.Ignore) != 3 {
42
+
testingContext.Fatalf("Expected three ignore values, got %d.", len(options.Ignore))
43
+
}
44
+
}
45
+
46
+
func TestParseOptionsRejectsInvalidMinimumEvaluationLength(testingContext *testing.T) {
47
+
_, err := parseOptions([]string{"--path", "./testdata", "--min-eval-length", "0"})
48
+
49
+
if err == nil {
50
+
testingContext.Fatalf("Expected parseOptions to fail for min-eval-length=0.")
51
+
}
52
+
}
53
+
54
+
func TestApplyIgnoreFilters(testingContext *testing.T) {
55
+
input := analyzeResultFixture()
56
+
filtered := applyIgnoreFilters(input, []string{
57
+
"name=ctx",
58
+
"reason=too short",
59
+
"file=_test.go",
60
+
})
61
+
62
+
if len(filtered.Violations) != 1 {
63
+
testingContext.Fatalf("Expected one remaining violation, got %d.", len(filtered.Violations))
64
+
}
65
+
66
+
if filtered.Violations[0].Identifier.Name != "userNum" {
67
+
testingContext.Fatalf("Unexpected remaining violation: %q.", filtered.Violations[0].Identifier.Name)
68
+
}
69
+
}
70
+
71
+
func analyzeResultFixture() analyze.Result {
72
+
return analyze.Result{
73
+
Violations: []analyze.Violation{
74
+
{
75
+
Identifier: collect.Identifier{
76
+
Name: "ctx",
77
+
Kind: "parameter",
78
+
File: "sample.go",
79
+
Context: collect.Context{
80
+
EnclosingFunction: "Handle",
81
+
},
82
+
},
83
+
Reason: "Contains abbreviation: ctx.",
84
+
},
85
+
{
86
+
Identifier: collect.Identifier{
87
+
Name: "t",
88
+
Kind: "parameter",
89
+
File: "main_test.go",
90
+
},
91
+
Reason: "Name is too short to be self-documenting.",
92
+
},
93
+
{
94
+
Identifier: collect.Identifier{
95
+
Name: "userNum",
96
+
Kind: "parameter",
97
+
File: "sample.go",
98
+
},
99
+
Reason: "Contains abbreviation: num.",
100
+
},
101
+
},
102
+
}
103
+
}
+9
testdata/dictionary/words.txt
+9
testdata/dictionary/words.txt
+20
testdata/samplepkg/sample.go
+20
testdata/samplepkg/sample.go
···
1
+
package samplepkg
2
+
3
+
import "context"
4
+
5
+
type UserCfg struct {
6
+
userNum int
7
+
}
8
+
9
+
func Handle(ctx context.Context, userNum int) int {
10
+
resultVal := userNum + 1
11
+
12
+
for idx, usr := range []string{"a", "b"} {
13
+
_ = idx
14
+
_ = usr
15
+
}
16
+
17
+
_ = ctx
18
+
19
+
return resultVal
20
+
}