summaryrefslogtreecommitdiff
path: root/vendor/github.com/google/yamlfmt/content_analyzer.go
blob: 4083e6b8a58d5f4ae4874bd5b3cfdfa45a428a27 (plain)
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
// Copyright 2024 Google LLC
//
// 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 yamlfmt

import (
	"os"
	"regexp"

	"github.com/google/yamlfmt/internal/collections"
)

type ContentAnalyzer interface {
	ExcludePathsByContent(paths []string) ([]string, []string, error)
}

type BasicContentAnalyzer struct {
	RegexPatterns []*regexp.Regexp
}

func NewBasicContentAnalyzer(patterns []string) (BasicContentAnalyzer, error) {
	analyzer := BasicContentAnalyzer{RegexPatterns: []*regexp.Regexp{}}
	compileErrs := collections.Errors{}
	for _, pattern := range patterns {
		re, err := regexp.Compile(pattern)
		if err != nil {
			compileErrs = append(compileErrs, err)
			continue
		}
		analyzer.RegexPatterns = append(analyzer.RegexPatterns, re)
	}
	return analyzer, compileErrs.Combine()
}

func (a BasicContentAnalyzer) ExcludePathsByContent(paths []string) ([]string, []string, error) {
	pathsToFormat := collections.SliceToSet(paths)
	pathsExcluded := []string{}
	pathErrs := collections.Errors{}

	for _, path := range paths {
		content, err := os.ReadFile(path)
		if err != nil {
			pathErrs = append(pathErrs, err)
			continue
		}

		// Search metadata for ignore
		metadata, mdErrs := ReadMetadata(content, path)
		if len(mdErrs) != 0 {
			pathErrs = append(pathErrs, mdErrs...)
		}
		ignoreFound := false
		for md := range metadata {
			if md.Type == MetadataIgnore {
				ignoreFound = true
				break
			}
		}
		if ignoreFound {
			pathsExcluded = append(pathsExcluded, path)
			pathsToFormat.Remove(path)
			continue
		}

		// Check if content matches any regex
		matched := false
		for _, pattern := range a.RegexPatterns {
			if pattern.Match(content) {
				matched = true
			}
		}
		if matched {
			pathsExcluded = append(pathsExcluded, path)
			pathsToFormat.Remove(path)
		}
	}

	return pathsToFormat.ToSlice(), pathsExcluded, pathErrs.Combine()
}