summaryrefslogtreecommitdiffstats
path: root/modules/git/repo_language_stats_nogogit.go
blob: 4c6f07f0fba57bd861b316b9409a72c8f967fab5 (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
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
// Copyright 2020 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.

// +build !gogit

package git

import (
	"bufio"
	"bytes"
	"io"
	"math"
	"strings"

	"code.gitea.io/gitea/modules/analyze"

	"github.com/go-enry/go-enry/v2"
)

// GetLanguageStats calculates language stats for git repository at specified commit
func (repo *Repository) GetLanguageStats(commitID string) (map[string]int64, error) {
	// We will feed the commit IDs in order into cat-file --batch, followed by blobs as necessary.
	// so let's create a batch stdin and stdout

	batchStdinReader, batchStdinWriter := io.Pipe()
	batchStdoutReader, batchStdoutWriter := io.Pipe()
	defer func() {
		_ = batchStdinReader.Close()
		_ = batchStdinWriter.Close()
		_ = batchStdoutReader.Close()
		_ = batchStdoutWriter.Close()
	}()

	go func() {
		stderr := strings.Builder{}
		err := NewCommand("cat-file", "--batch").RunInDirFullPipeline(repo.Path, batchStdoutWriter, &stderr, batchStdinReader)
		if err != nil {
			_ = batchStdoutWriter.CloseWithError(ConcatenateError(err, (&stderr).String()))
			_ = batchStdinReader.CloseWithError(ConcatenateError(err, (&stderr).String()))
		} else {
			_ = batchStdoutWriter.Close()
			_ = batchStdinReader.Close()
		}
	}()

	// For simplicities sake we'll us a buffered reader
	batchReader := bufio.NewReader(batchStdoutReader)

	writeID := func(id string) error {
		_, err := batchStdinWriter.Write([]byte(id))
		if err != nil {
			return err
		}
		_, err = batchStdinWriter.Write([]byte{'\n'})
		return err
	}

	if err := writeID(commitID); err != nil {
		return nil, err
	}
	shaBytes, typ, size, err := ReadBatchLine(batchReader)
	if typ != "commit" {
		log("Unable to get commit for: %s. Err: %v", commitID, err)
		return nil, ErrNotExist{commitID, ""}
	}

	sha, err := NewIDFromString(string(shaBytes))
	if err != nil {
		log("Unable to get commit for: %s. Err: %v", commitID, err)
		return nil, ErrNotExist{commitID, ""}
	}

	commit, err := CommitFromReader(repo, sha, io.LimitReader(batchReader, size))
	if err != nil {
		log("Unable to get commit for: %s. Err: %v", commitID, err)
		return nil, err
	}

	tree := commit.Tree

	entries, err := tree.ListEntriesRecursive()
	if err != nil {
		return nil, err
	}

	contentBuf := bytes.Buffer{}
	var content []byte
	sizes := make(map[string]int64)
	for _, f := range entries {
		contentBuf.Reset()
		content = contentBuf.Bytes()
		if f.Size() == 0 || enry.IsVendor(f.Name()) || enry.IsDotFile(f.Name()) ||
			enry.IsDocumentation(f.Name()) || enry.IsConfiguration(f.Name()) {
			continue
		}

		// If content can not be read or file is too big just do detection by filename

		if f.Size() <= bigFileSize {
			if err := writeID(f.ID.String()); err != nil {
				return nil, err
			}
			_, _, size, err := ReadBatchLine(batchReader)
			if err != nil {
				log("Error reading blob: %s Err: %v", f.ID.String(), err)
				return nil, err
			}

			sizeToRead := size
			discard := int64(0)
			if size > fileSizeLimit {
				sizeToRead = fileSizeLimit
				discard = size - fileSizeLimit
			}

			_, err = contentBuf.ReadFrom(io.LimitReader(batchReader, sizeToRead))
			if err != nil {
				return nil, err
			}
			content = contentBuf.Bytes()
			err = discardFull(batchReader, discard)
			if err != nil {
				return nil, err
			}
		}
		if enry.IsGenerated(f.Name(), content) {
			continue
		}

		// TODO: Use .gitattributes file for linguist overrides
		// FIXME: Why can't we split this and the IsGenerated tests to avoid reading the blob unless absolutely necessary?
		// - eg. do the all the detection tests using filename first before reading content.
		language := analyze.GetCodeLanguage(f.Name(), content)
		if language == enry.OtherLanguage || language == "" {
			continue
		}

		// group languages, such as Pug -> HTML; SCSS -> CSS
		group := enry.GetLanguageGroup(language)
		if group != "" {
			language = group
		}

		sizes[language] += f.Size()

		continue
	}

	// filter special languages unless they are the only language
	if len(sizes) > 1 {
		for language := range sizes {
			langtype := enry.GetLanguageType(language)
			if langtype != enry.Programming && langtype != enry.Markup {
				delete(sizes, language)
			}
		}
	}

	return sizes, nil
}

func discardFull(rd *bufio.Reader, discard int64) error {
	if discard > math.MaxInt32 {
		n, err := rd.Discard(math.MaxInt32)
		discard -= int64(n)
		if err != nil {
			return err
		}
	}
	for discard > 0 {
		n, err := rd.Discard(int(discard))
		discard -= int64(n)
		if err != nil {
			return err
		}
	}
	return nil
}