aboutsummaryrefslogtreecommitdiffstats
path: root/plumbing/format/packfile/packfile.go
blob: 00014f6a5c57a772dedd2e4f12e127c7e78baf3c (plain) (blame)
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
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
package packfile

import (
	"bytes"
	"io"

	billy "gopkg.in/src-d/go-billy.v4"
	"gopkg.in/src-d/go-git.v4/plumbing"
	"gopkg.in/src-d/go-git.v4/plumbing/cache"
	"gopkg.in/src-d/go-git.v4/plumbing/format/idxfile"
	"gopkg.in/src-d/go-git.v4/plumbing/storer"
)

// Packfile allows retrieving information from inside a packfile.
type Packfile struct {
	idxfile.Index
	billy.File
	s              *Scanner
	deltaBaseCache cache.Object
	offsetToType   map[int64]plumbing.ObjectType
}

// NewPackfile returns a packfile representation for the given packfile file
// and packfile idx.
func NewPackfile(index idxfile.Index, file billy.File) *Packfile {
	s := NewScanner(file)

	return &Packfile{
		index,
		file,
		s,
		cache.NewObjectLRUDefault(),
		make(map[int64]plumbing.ObjectType),
	}
}

// Get retrieves the encoded object in the packfile with the given hash.
func (p *Packfile) Get(h plumbing.Hash) (plumbing.EncodedObject, error) {
	offset, err := p.FindOffset(h)
	if err != nil {
		return nil, err
	}

	return p.GetByOffset(offset)
}

// GetByOffset retrieves the encoded object from the packfile with the given
// offset.
func (p *Packfile) GetByOffset(o int64) (plumbing.EncodedObject, error) {
	hash, err := p.FindHash(o)
	if err == nil {
		if obj, ok := p.deltaBaseCache.Get(hash); ok {
			return obj, nil
		}
	}

	if _, err := p.s.SeekFromStart(o); err != nil {
		return nil, err
	}

	return p.nextObject()
}

func (p *Packfile) nextObjectHeader() (*ObjectHeader, error) {
	h, err := p.s.NextObjectHeader()
	p.s.pendingObject = nil
	return h, err
}

func (p *Packfile) getObjectData(
	h *ObjectHeader,
) (typ plumbing.ObjectType, size int64, err error) {
	switch h.Type {
	case plumbing.CommitObject, plumbing.TreeObject, plumbing.BlobObject, plumbing.TagObject:
		typ = h.Type
		size = h.Length
	case plumbing.REFDeltaObject, plumbing.OFSDeltaObject:
		buf := bufPool.Get().(*bytes.Buffer)
		buf.Reset()
		defer bufPool.Put(buf)

		_, _, err = p.s.NextObject(buf)
		if err != nil {
			return
		}

		delta := buf.Bytes()
		_, delta = decodeLEB128(delta) // skip src size
		sz, _ := decodeLEB128(delta)
		size = int64(sz)

		var offset int64
		if h.Type == plumbing.REFDeltaObject {
			offset, err = p.FindOffset(h.Reference)
			if err != nil {
				return
			}
		} else {
			offset = h.OffsetReference
		}

		if baseType, ok := p.offsetToType[offset]; ok {
			typ = baseType
		} else {
			if _, err = p.s.SeekFromStart(offset); err != nil {
				return
			}

			h, err = p.nextObjectHeader()
			if err != nil {
				return
			}

			typ, _, err = p.getObjectData(h)
			if err != nil {
				return
			}
		}
	default:
		err = ErrInvalidObject.AddDetails("type %q", h.Type)
	}

	return
}

func (p *Packfile) getObjectSize(h *ObjectHeader) (int64, error) {
	switch h.Type {
	case plumbing.CommitObject, plumbing.TreeObject, plumbing.BlobObject, plumbing.TagObject:
		return h.Length, nil
	case plumbing.REFDeltaObject, plumbing.OFSDeltaObject:
		buf := bufPool.Get().(*bytes.Buffer)
		buf.Reset()
		defer bufPool.Put(buf)

		if _, _, err := p.s.NextObject(buf); err != nil {
			return 0, err
		}

		delta := buf.Bytes()
		_, delta = decodeLEB128(delta) // skip src size
		sz, _ := decodeLEB128(delta)
		return int64(sz), nil
	default:
		return 0, ErrInvalidObject.AddDetails("type %q", h.Type)
	}
}

func (p *Packfile) getObjectType(h *ObjectHeader) (typ plumbing.ObjectType, err error) {
	switch h.Type {
	case plumbing.CommitObject, plumbing.TreeObject, plumbing.BlobObject, plumbing.TagObject:
		return h.Type, nil
	case plumbing.REFDeltaObject, plumbing.OFSDeltaObject:
		var offset int64
		if h.Type == plumbing.REFDeltaObject {
			offset, err = p.FindOffset(h.Reference)
			if err != nil {
				return
			}
		} else {
			offset = h.OffsetReference
		}

		if baseType, ok := p.offsetToType[offset]; ok {
			typ = baseType
		} else {
			if _, err = p.s.SeekFromStart(offset); err != nil {
				return
			}

			h, err = p.nextObjectHeader()
			if err != nil {
				return
			}

			typ, err = p.getObjectType(h)
			if err != nil {
				return
			}
		}
	default:
		err = ErrInvalidObject.AddDetails("type %q", h.Type)
	}

	return
}

func (p *Packfile) nextObject() (plumbing.EncodedObject, error) {
	h, err := p.nextObjectHeader()
	if err != nil {
		return nil, err
	}

	hash, err := p.FindHash(h.Offset)
	if err != nil {
		return nil, err
	}

	size, err := p.getObjectSize(h)
	if err != nil {
		return nil, err
	}

	typ, err := p.getObjectType(h)
	if err != nil {
		return nil, err
	}

	p.offsetToType[h.Offset] = typ

	return NewDiskObject(hash, typ, h.Offset, size, p), nil
}

func (p *Packfile) getObjectContent(offset int64) (io.ReadCloser, error) {
	if _, err := p.s.SeekFromStart(offset); err != nil {
		return nil, err
	}

	h, err := p.nextObjectHeader()
	if err != nil {
		return nil, err
	}

	var obj = new(plumbing.MemoryObject)
	obj.SetSize(h.Length)
	obj.SetType(h.Type)

	switch h.Type {
	case plumbing.CommitObject, plumbing.TreeObject, plumbing.BlobObject, plumbing.TagObject:
		err = p.fillRegularObjectContent(obj)
	case plumbing.REFDeltaObject:
		err = p.fillREFDeltaObjectContent(obj, h.Reference)
	case plumbing.OFSDeltaObject:
		err = p.fillOFSDeltaObjectContent(obj, h.OffsetReference)
	default:
		err = ErrInvalidObject.AddDetails("type %q", h.Type)
	}

	if err != nil {
		return nil, err
	}

	return obj.Reader()
}

func (p *Packfile) fillRegularObjectContent(obj plumbing.EncodedObject) error {
	w, err := obj.Writer()
	if err != nil {
		return err
	}

	_, _, err = p.s.NextObject(w)
	return err
}

func (p *Packfile) fillREFDeltaObjectContent(obj plumbing.EncodedObject, ref plumbing.Hash) error {
	buf := bufPool.Get().(*bytes.Buffer)
	buf.Reset()
	_, _, err := p.s.NextObject(buf)
	if err != nil {
		return err
	}

	base, ok := p.cacheGet(ref)
	if !ok {
		base, err = p.Get(ref)
		if err != nil {
			return err
		}
	}

	obj.SetType(base.Type())
	err = ApplyDelta(obj, base, buf.Bytes())
	p.cachePut(obj)
	bufPool.Put(buf)

	return err
}

func (p *Packfile) fillOFSDeltaObjectContent(obj plumbing.EncodedObject, offset int64) error {
	buf := bytes.NewBuffer(nil)
	_, _, err := p.s.NextObject(buf)
	if err != nil {
		return err
	}

	var base plumbing.EncodedObject
	var ok bool
	hash, err := p.FindHash(offset)
	if err == nil {
		base, ok = p.cacheGet(hash)
	}

	if !ok {
		base, err = p.GetByOffset(offset)
		if err != nil {
			return err
		}

		p.cachePut(base)
	}

	obj.SetType(base.Type())
	err = ApplyDelta(obj, base, buf.Bytes())
	p.cachePut(obj)

	return err
}

func (p *Packfile) cacheGet(h plumbing.Hash) (plumbing.EncodedObject, bool) {
	if p.deltaBaseCache == nil {
		return nil, false
	}

	return p.deltaBaseCache.Get(h)
}

func (p *Packfile) cachePut(obj plumbing.EncodedObject) {
	if p.deltaBaseCache == nil {
		return
	}

	p.deltaBaseCache.Put(obj)
}

// GetAll returns an iterator with all encoded objects in the packfile.
// The iterator returned is not thread-safe, it should be used in the same
// thread as the Packfile instance.
func (p *Packfile) GetAll() (storer.EncodedObjectIter, error) {
	entries, err := p.Entries()
	if err != nil {
		return nil, err
	}

	return &objectIter{
		// Easiest way to provide an object decoder is just to pass a Packfile
		// instance. To not mess with the seeks, it's a new instance with a
		// different scanner but the same cache and offset to hash map for
		// reusing as much cache as possible.
		p: &Packfile{
			p.Index,
			p.File,
			NewScanner(p.File),
			p.deltaBaseCache,
			p.offsetToType,
		},
		iter: entries,
	}, nil
}

// ID returns the ID of the packfile, which is the checksum at the end of it.
func (p *Packfile) ID() (plumbing.Hash, error) {
	if _, err := p.File.Seek(-20, io.SeekEnd); err != nil {
		return plumbing.ZeroHash, err
	}

	var hash plumbing.Hash
	if _, err := io.ReadFull(p.File, hash[:]); err != nil {
		return plumbing.ZeroHash, err
	}

	return hash, nil
}

// Close the packfile and its resources.
func (p *Packfile) Close() error {
	return p.File.Close()
}

type objectDecoder interface {
	nextObject() (plumbing.EncodedObject, error)
}

type objectIter struct {
	p    *Packfile
	iter idxfile.EntryIter
}

func (i *objectIter) Next() (plumbing.EncodedObject, error) {
	e, err := i.iter.Next()
	if err != nil {
		return nil, err
	}

	return i.p.GetByOffset(int64(e.Offset))
}

func (i *objectIter) ForEach(f func(plumbing.EncodedObject) error) error {
	for {
		o, err := i.Next()
		if err != nil {
			if err == io.EOF {
				return nil
			}
			return err
		}

		if err := f(o); err != nil {
			return err
		}
	}
}

func (i *objectIter) Close() {
	i.iter.Close()
}