File: gunzip.go

package info (click to toggle)
golang-github-klauspost-compress 1.7.6-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 17,540 kB
  • sloc: asm: 741; cpp: 59; sh: 26; makefile: 8
file content (344 lines) | stat: -rw-r--r-- 9,708 bytes parent folder | download | duplicates (3)
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
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

// Package gzip implements reading and writing of gzip format compressed files,
// as specified in RFC 1952.
package gzip

import (
	"bufio"
	"encoding/binary"
	"errors"
	"hash/crc32"
	"io"
	"time"

	"github.com/klauspost/compress/flate"
)

const (
	gzipID1     = 0x1f
	gzipID2     = 0x8b
	gzipDeflate = 8
	flagText    = 1 << 0
	flagHdrCrc  = 1 << 1
	flagExtra   = 1 << 2
	flagName    = 1 << 3
	flagComment = 1 << 4
)

var (
	// ErrChecksum is returned when reading GZIP data that has an invalid checksum.
	ErrChecksum = errors.New("gzip: invalid checksum")
	// ErrHeader is returned when reading GZIP data that has an invalid header.
	ErrHeader = errors.New("gzip: invalid header")
)

var le = binary.LittleEndian

// noEOF converts io.EOF to io.ErrUnexpectedEOF.
func noEOF(err error) error {
	if err == io.EOF {
		return io.ErrUnexpectedEOF
	}
	return err
}

// The gzip file stores a header giving metadata about the compressed file.
// That header is exposed as the fields of the Writer and Reader structs.
//
// Strings must be UTF-8 encoded and may only contain Unicode code points
// U+0001 through U+00FF, due to limitations of the GZIP file format.
type Header struct {
	Comment string    // comment
	Extra   []byte    // "extra data"
	ModTime time.Time // modification time
	Name    string    // file name
	OS      byte      // operating system type
}

// A Reader is an io.Reader that can be read to retrieve
// uncompressed data from a gzip-format compressed file.
//
// In general, a gzip file can be a concatenation of gzip files,
// each with its own header. Reads from the Reader
// return the concatenation of the uncompressed data of each.
// Only the first header is recorded in the Reader fields.
//
// Gzip files store a length and checksum of the uncompressed data.
// The Reader will return a ErrChecksum when Read
// reaches the end of the uncompressed data if it does not
// have the expected length or checksum. Clients should treat data
// returned by Read as tentative until they receive the io.EOF
// marking the end of the data.
type Reader struct {
	Header       // valid after NewReader or Reader.Reset
	r            flate.Reader
	decompressor io.ReadCloser
	digest       uint32 // CRC-32, IEEE polynomial (section 8)
	size         uint32 // Uncompressed size (section 2.3.1)
	buf          [512]byte
	err          error
	multistream  bool
}

// NewReader creates a new Reader reading the given reader.
// If r does not also implement io.ByteReader,
// the decompressor may read more data than necessary from r.
//
// It is the caller's responsibility to call Close on the Reader when done.
//
// The Reader.Header fields will be valid in the Reader returned.
func NewReader(r io.Reader) (*Reader, error) {
	z := new(Reader)
	if err := z.Reset(r); err != nil {
		return nil, err
	}
	return z, nil
}

// Reset discards the Reader z's state and makes it equivalent to the
// result of its original state from NewReader, but reading from r instead.
// This permits reusing a Reader rather than allocating a new one.
func (z *Reader) Reset(r io.Reader) error {
	*z = Reader{
		decompressor: z.decompressor,
		multistream:  true,
	}
	if rr, ok := r.(flate.Reader); ok {
		z.r = rr
	} else {
		z.r = bufio.NewReader(r)
	}
	z.Header, z.err = z.readHeader()
	return z.err
}

// Multistream controls whether the reader supports multistream files.
//
// If enabled (the default), the Reader expects the input to be a sequence
// of individually gzipped data streams, each with its own header and
// trailer, ending at EOF. The effect is that the concatenation of a sequence
// of gzipped files is treated as equivalent to the gzip of the concatenation
// of the sequence. This is standard behavior for gzip readers.
//
// Calling Multistream(false) disables this behavior; disabling the behavior
// can be useful when reading file formats that distinguish individual gzip
// data streams or mix gzip data streams with other data streams.
// In this mode, when the Reader reaches the end of the data stream,
// Read returns io.EOF. If the underlying reader implements io.ByteReader,
// it will be left positioned just after the gzip stream.
// To start the next stream, call z.Reset(r) followed by z.Multistream(false).
// If there is no next stream, z.Reset(r) will return io.EOF.
func (z *Reader) Multistream(ok bool) {
	z.multistream = ok
}

// readString reads a NUL-terminated string from z.r.
// It treats the bytes read as being encoded as ISO 8859-1 (Latin-1) and
// will output a string encoded using UTF-8.
// This method always updates z.digest with the data read.
func (z *Reader) readString() (string, error) {
	var err error
	needConv := false
	for i := 0; ; i++ {
		if i >= len(z.buf) {
			return "", ErrHeader
		}
		z.buf[i], err = z.r.ReadByte()
		if err != nil {
			return "", err
		}
		if z.buf[i] > 0x7f {
			needConv = true
		}
		if z.buf[i] == 0 {
			// Digest covers the NUL terminator.
			z.digest = crc32.Update(z.digest, crc32.IEEETable, z.buf[:i+1])

			// Strings are ISO 8859-1, Latin-1 (RFC 1952, section 2.3.1).
			if needConv {
				s := make([]rune, 0, i)
				for _, v := range z.buf[:i] {
					s = append(s, rune(v))
				}
				return string(s), nil
			}
			return string(z.buf[:i]), nil
		}
	}
}

// readHeader reads the GZIP header according to section 2.3.1.
// This method does not set z.err.
func (z *Reader) readHeader() (hdr Header, err error) {
	if _, err = io.ReadFull(z.r, z.buf[:10]); err != nil {
		// RFC 1952, section 2.2, says the following:
		//	A gzip file consists of a series of "members" (compressed data sets).
		//
		// Other than this, the specification does not clarify whether a
		// "series" is defined as "one or more" or "zero or more". To err on the
		// side of caution, Go interprets this to mean "zero or more".
		// Thus, it is okay to return io.EOF here.
		return hdr, err
	}
	if z.buf[0] != gzipID1 || z.buf[1] != gzipID2 || z.buf[2] != gzipDeflate {
		return hdr, ErrHeader
	}
	flg := z.buf[3]
	hdr.ModTime = time.Unix(int64(le.Uint32(z.buf[4:8])), 0)
	// z.buf[8] is XFL and is currently ignored.
	hdr.OS = z.buf[9]
	z.digest = crc32.ChecksumIEEE(z.buf[:10])

	if flg&flagExtra != 0 {
		if _, err = io.ReadFull(z.r, z.buf[:2]); err != nil {
			return hdr, noEOF(err)
		}
		z.digest = crc32.Update(z.digest, crc32.IEEETable, z.buf[:2])
		data := make([]byte, le.Uint16(z.buf[:2]))
		if _, err = io.ReadFull(z.r, data); err != nil {
			return hdr, noEOF(err)
		}
		z.digest = crc32.Update(z.digest, crc32.IEEETable, data)
		hdr.Extra = data
	}

	var s string
	if flg&flagName != 0 {
		if s, err = z.readString(); err != nil {
			return hdr, err
		}
		hdr.Name = s
	}

	if flg&flagComment != 0 {
		if s, err = z.readString(); err != nil {
			return hdr, err
		}
		hdr.Comment = s
	}

	if flg&flagHdrCrc != 0 {
		if _, err = io.ReadFull(z.r, z.buf[:2]); err != nil {
			return hdr, noEOF(err)
		}
		digest := le.Uint16(z.buf[:2])
		if digest != uint16(z.digest) {
			return hdr, ErrHeader
		}
	}

	z.digest = 0
	if z.decompressor == nil {
		z.decompressor = flate.NewReader(z.r)
	} else {
		z.decompressor.(flate.Resetter).Reset(z.r, nil)
	}
	return hdr, nil
}

// Read implements io.Reader, reading uncompressed bytes from its underlying Reader.
func (z *Reader) Read(p []byte) (n int, err error) {
	if z.err != nil {
		return 0, z.err
	}

	n, z.err = z.decompressor.Read(p)
	z.digest = crc32.Update(z.digest, crc32.IEEETable, p[:n])
	z.size += uint32(n)
	if z.err != io.EOF {
		// In the normal case we return here.
		return n, z.err
	}

	// Finished file; check checksum and size.
	if _, err := io.ReadFull(z.r, z.buf[:8]); err != nil {
		z.err = noEOF(err)
		return n, z.err
	}
	digest := le.Uint32(z.buf[:4])
	size := le.Uint32(z.buf[4:8])
	if digest != z.digest || size != z.size {
		z.err = ErrChecksum
		return n, z.err
	}
	z.digest, z.size = 0, 0

	// File is ok; check if there is another.
	if !z.multistream {
		return n, io.EOF
	}
	z.err = nil // Remove io.EOF

	if _, z.err = z.readHeader(); z.err != nil {
		return n, z.err
	}

	// Read from next file, if necessary.
	if n > 0 {
		return n, nil
	}
	return z.Read(p)
}

// Support the io.WriteTo interface for io.Copy and friends.
func (z *Reader) WriteTo(w io.Writer) (int64, error) {
	total := int64(0)
	crcWriter := crc32.NewIEEE()
	for {
		if z.err != nil {
			if z.err == io.EOF {
				return total, nil
			}
			return total, z.err
		}

		// We write both to output and digest.
		mw := io.MultiWriter(w, crcWriter)
		n, err := z.decompressor.(io.WriterTo).WriteTo(mw)
		total += n
		z.size += uint32(n)
		if err != nil {
			z.err = err
			return total, z.err
		}

		// Finished file; check checksum + size.
		if _, err := io.ReadFull(z.r, z.buf[0:8]); err != nil {
			if err == io.EOF {
				err = io.ErrUnexpectedEOF
			}
			z.err = err
			return total, err
		}
		z.digest = crcWriter.Sum32()
		digest := le.Uint32(z.buf[:4])
		size := le.Uint32(z.buf[4:8])
		if digest != z.digest || size != z.size {
			z.err = ErrChecksum
			return total, z.err
		}
		z.digest, z.size = 0, 0

		// File is ok; check if there is another.
		if !z.multistream {
			return total, nil
		}
		crcWriter.Reset()
		z.err = nil // Remove io.EOF

		if _, z.err = z.readHeader(); z.err != nil {
			if z.err == io.EOF {
				return total, nil
			}
			return total, z.err
		}
	}
}

// Close closes the Reader. It does not close the underlying io.Reader.
// In order for the GZIP checksum to be verified, the reader must be
// fully consumed until the io.EOF.
func (z *Reader) Close() error { return z.decompressor.Close() }