gitea

Development moved to Codeberg

  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
// Copyright 2015, Joe Tsai. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE.md file.

package bzip2

import "github.com/dsnet/compress/internal/errors"

// rleDone is a special "error" to indicate that the RLE stage is done.
var rleDone = errorf(errors.Unknown, "RLE1 stage is completed")

// runLengthEncoding implements the first RLE stage of bzip2. Every sequence
// of 4..255 duplicated bytes is replaced by only the first 4 bytes, and a
// single byte representing the repeat length. Similar to the C bzip2
// implementation, the encoder will always terminate repeat sequences with a
// count (even if it is the end of the buffer), and it will also never produce
// run lengths of 256..259. The decoder can handle the latter case.
//
// For example, if the input was:
//	input:  "AAAAAAABBBBCCCD"
//
// Then the output will be:
//	output: "AAAA\x03BBBB\x00CCCD"
type runLengthEncoding struct {
	buf     []byte
	idx     int
	lastVal byte
	lastCnt int
}

func (rle *runLengthEncoding) Init(buf []byte) {
	*rle = runLengthEncoding{buf: buf}
}

func (rle *runLengthEncoding) Write(buf []byte) (int, error) {
	for i, b := range buf {
		if rle.lastVal != b {
			rle.lastCnt = 0
		}
		rle.lastCnt++
		switch {
		case rle.lastCnt < 4:
			if rle.idx >= len(rle.buf) {
				return i, rleDone
			}
			rle.buf[rle.idx] = b
			rle.idx++
		case rle.lastCnt == 4:
			if rle.idx+1 >= len(rle.buf) {
				return i, rleDone
			}
			rle.buf[rle.idx] = b
			rle.idx++
			rle.buf[rle.idx] = 0
			rle.idx++
		case rle.lastCnt < 256:
			rle.buf[rle.idx-1]++
		default:
			if rle.idx >= len(rle.buf) {
				return i, rleDone
			}
			rle.lastCnt = 1
			rle.buf[rle.idx] = b
			rle.idx++
		}
		rle.lastVal = b
	}
	return len(buf), nil
}

func (rle *runLengthEncoding) Read(buf []byte) (int, error) {
	for i := range buf {
		switch {
		case rle.lastCnt == -4:
			if rle.idx >= len(rle.buf) {
				return i, errorf(errors.Corrupted, "missing terminating run-length repeater")
			}
			rle.lastCnt = int(rle.buf[rle.idx])
			rle.idx++
			if rle.lastCnt > 0 {
				break // Break the switch
			}
			fallthrough // Count was zero, continue the work
		case rle.lastCnt <= 0:
			if rle.idx >= len(rle.buf) {
				return i, rleDone
			}
			b := rle.buf[rle.idx]
			rle.idx++
			if b != rle.lastVal {
				rle.lastCnt = 0
				rle.lastVal = b
			}
		}
		buf[i] = rle.lastVal
		rle.lastCnt--
	}
	return len(buf), nil
}

func (rle *runLengthEncoding) Bytes() []byte { return rle.buf[:rle.idx] }