1. 1
2. 2
3. 3
4. 4
5. 5
6. 6
7. 7
8. 8
9. 9
10. 10
11. 11
12. 12
13. 13
14. 14
15. 15
16. 16
17. 17
18. 18
19. 19
20. 20
21. 21
22. 22
23. 23
24. 24
25. 25
26. 26
27. 27
28. 28
29. 29
30. 30
31. 31
32. 32
33. 33
34. 34
35. 35
36. 36
37. 37
38. 38
39. 39
40. 40
41. 41
42. 42
43. 43
44. 44
45. 45
46. 46
47. 47
48. 48
49. 49
50. 50
51. 51
52. 52
53. 53
54. 54
55. 55
56. 56
57. 57
58. 58
59. 59
60. 60
61. 61
62. 62
63. 63
64. 64
65. 65
66. 66
67. 67
68. 68
69. 69
70. 70
71. 71
72. 72
73. 73
74. 74
75. 75
76. 76
77. 77
78. 78
79. 79
80. 80
81. 81
82. 82
83. 83
84. 84
85. 85
86. 86
87. 87
88. 88
89. 89
90. 90
91. 91
92. 92
93. 93
94. 94
95. 95
96. 96
97. 97
98. 98
99. 99
100. 100
101. 101
102. 102
103. 103
104. 104
105. 105
106. 106
107. 107
108. 108
109. 109
110. 110
111. 111
112. 112
113. 113
114. 114
115. 115
116. 116
117. 117
118. 118
119. 119
120. 120
121. 121
122. 122
123. 123
124. 124
125. 125
126. 126
127. 127
128. 128
129. 129

// Copyright 2022 The Gitea Authors. All rights reserved.
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.

package foreachref

import (
	"bufio"
	"bytes"
	"fmt"
	"io"
	"strings"
)

// Parser parses 'git for-each-ref' output according to a given output Format.
type Parser struct {
	//  tokenizes 'git for-each-ref' output into "reference paragraphs".
	scanner *bufio.Scanner

	// format represents the '--format' string that describes the expected
	// 'git for-each-ref' output structure.
	format Format

	// err holds the last encountered error during parsing.
	err error
}

// NewParser creates a 'git for-each-ref' output parser that will parse all
// references in the provided Reader. The references in the output are assumed
// to follow the specified Format.
func NewParser(r io.Reader, format Format) *Parser {
	scanner := bufio.NewScanner(r)

	// in addition to the reference delimiter we specified in the --format,
	// `git for-each-ref` will always add a newline after every reference.
	refDelim := make([]byte, 0, len(format.refDelim)+1)
	refDelim = append(refDelim, format.refDelim...)
	refDelim = append(refDelim, '\n')

	// Split input into delimiter-separated "reference blocks".
	scanner.Split(
		func(data []byte, atEOF bool) (advance int, token []byte, err error) {
			// Scan until delimiter, marking end of reference.
			delimIdx := bytes.Index(data, refDelim)
			if delimIdx >= 0 {
				token := data[:delimIdx]
				advance := delimIdx + len(refDelim)
				return advance, token, nil
			}
			// If we're at EOF, we have a final, non-terminated reference. Return it.
			if atEOF {
				return len(data), data, nil
			}
			// Not yet a full field. Request more data.
			return 0, nil, nil
		})

	return &Parser{
		scanner: scanner,
		format:  format,
		err:     nil,
	}
}

// Next returns the next reference as a collection of key-value pairs. nil
// denotes EOF but is also returned on errors. The Err method should always be
// consulted after Next returning nil.
//
// It could, for example return something like:
//
//	{ "objecttype": "tag", "refname:short": "v1.16.4", "object": "f460b7543ed500e49c133c2cd85c8c55ee9dbe27" }
func (p *Parser) Next() map[string]string {
	if !p.scanner.Scan() {
		return nil
	}
	fields, err := p.parseRef(p.scanner.Text())
	if err != nil {
		p.err = err
		return nil
	}
	return fields
}

// Err returns the latest encountered parsing error.
func (p *Parser) Err() error {
	return p.err
}

// parseRef parses out all key-value pairs from a single reference block, such as
//
//	"objecttype tag\0refname:short v1.16.4\0object f460b7543ed500e49c133c2cd85c8c55ee9dbe27"
func (p *Parser) parseRef(refBlock string) (map[string]string, error) {
	if refBlock == "" {
		// must be at EOF
		return nil, nil
	}

	fieldValues := make(map[string]string)

	fields := strings.Split(refBlock, p.format.fieldDelimStr)
	if len(fields) != len(p.format.fieldNames) {
		return nil, fmt.Errorf("unexpected number of reference fields: wanted %d, was %d",
			len(fields), len(p.format.fieldNames))
	}
	for i, field := range fields {
		field = strings.TrimSpace(field)

		var fieldKey string
		var fieldVal string
		firstSpace := strings.Index(field, " ")
		if firstSpace > 0 {
			fieldKey = field[:firstSpace]
			fieldVal = field[firstSpace+1:]
		} else {
			// could be the case if the requested field had no value
			fieldKey = field
		}

		// enforce the format order of fields
		if p.format.fieldNames[i] != fieldKey {
			return nil, fmt.Errorf("unexpected field name at position %d: wanted: '%s', was: '%s'",
				i, p.format.fieldNames[i], fieldKey)
		}

		fieldValues[fieldKey] = fieldVal
	}

	return fieldValues, nil
}