aadf80aa28
Test a corpus of 585 public domain FLAC files with a duration of less than 1 minute from freesound.org. Out of these files, the following increased code coverage and where thus added to the test suit. * 19875 (sample rate 48 kHz) * 44127 (8 bits-per-sample, sample rate 22254) * 80574 (sample rate 22050) * 191885 (block size 1, verbatim) * 212768 (sample rate 88200) * 220014 (utf-8 continuation byte) * 243749 (sample rate 8000) * 257344 (sample rate 32000) * 256529 (sample rate 192000)
178 lines
5.6 KiB
Go
178 lines
5.6 KiB
Go
package frame
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"log"
|
|
)
|
|
|
|
const (
|
|
t1 = 0x00 // 0000 0000
|
|
tx = 0x80 // 1000 0000
|
|
t2 = 0xC0 // 1100 0000
|
|
t3 = 0xE0 // 1110 0000
|
|
t4 = 0xF0 // 1111 0000
|
|
t5 = 0xF8 // 1111 1000
|
|
t6 = 0xFC // 1111 1100
|
|
t7 = 0xFE // 1111 1110
|
|
t8 = 0xFF // 1111 1111
|
|
|
|
maskx = 0x3F // 0011 1111
|
|
mask2 = 0x1F // 0001 1111
|
|
mask3 = 0x0F // 0000 1111
|
|
mask4 = 0x07 // 0000 0111
|
|
mask5 = 0x03 // 0000 0011
|
|
mask6 = 0x01 // 0000 0001
|
|
|
|
rune1Max = 1<<7 - 1
|
|
rune2Max = 1<<11 - 1
|
|
rune3Max = 1<<16 - 1
|
|
rune4Max = 1<<21 - 1
|
|
rune5Max = 1<<26 - 1
|
|
rune6Max = 1<<31 - 1
|
|
)
|
|
|
|
// decodeUTF8Int decodes a "UTF-8" coded number and returns it.
|
|
//
|
|
// ref: http://permalink.gmane.org/gmane.comp.audio.compression.flac.devel/3033
|
|
//
|
|
// Algorithm description:
|
|
// - read one byte B0 from the stream
|
|
// - if B0 = 0xxxxxxx then the read value is B0 -> end
|
|
// - if B0 = 10xxxxxx, the encoding is invalid
|
|
// - if B0 = 11xxxxxx, set L to the number of leading binary 1s minus 1:
|
|
// B0 = 110xxxxx -> L = 1
|
|
// B0 = 1110xxxx -> L = 2
|
|
// B0 = 11110xxx -> L = 3
|
|
// B0 = 111110xx -> L = 4
|
|
// B0 = 1111110x -> L = 5
|
|
// B0 = 11111110 -> L = 6
|
|
// - assign the bits following the encoding (the x bits in the examples) to
|
|
// a variable R with a magnitude of at least 36 bits
|
|
// - loop from 1 to L
|
|
// - left shift R 6 bits
|
|
// - read B from the stream
|
|
// - if B does not match 10xxxxxx, the encoding is invalid
|
|
// - set R = R or <the lower 6 bits from B>
|
|
// - the read value is R
|
|
func decodeUTF8Int(r io.Reader) (n uint64, err error) {
|
|
c0, err := readByte(r)
|
|
if err != nil {
|
|
return 0, err
|
|
}
|
|
|
|
// 1-byte, 7-bit sequence?
|
|
if c0 < tx {
|
|
// if c0 == 0xxxxxxx
|
|
// total: 7 bits (7)
|
|
return uint64(c0), nil
|
|
}
|
|
|
|
// unexpected continuation byte?
|
|
if c0 < t2 {
|
|
// if c0 == 10xxxxxx
|
|
return 0, errors.New("frame.decodeUTF8Int: unexpected continuation byte")
|
|
}
|
|
|
|
// get number of continuation bytes and store bits from c0.
|
|
var l int
|
|
switch {
|
|
case c0 < t3:
|
|
// if c0 == 110xxxxx
|
|
// total: 11 bits (5 + 6)
|
|
l = 1
|
|
n = uint64(c0 & mask2)
|
|
case c0 < t4:
|
|
// if c0 == 1110xxxx
|
|
// total: 16 bits (4 + 6 + 6)
|
|
l = 2
|
|
n = uint64(c0 & mask3)
|
|
case c0 < t5:
|
|
// if c0 == 11110xxx
|
|
// total: 21 bits (3 + 6 + 6 + 6)
|
|
l = 3
|
|
n = uint64(c0 & mask4)
|
|
// TODO(u): Remove log message when the test cases have been extended.
|
|
log.Printf("frame.decodeUTF8Int: The flac library test cases do not yet include any audio files with %d UTF-8 continuation bytes. If possible please consider contributing this audio sample to improve the reliability of the test cases.", l)
|
|
case c0 < t6:
|
|
// if c0 == 111110xx
|
|
// total: 26 bits (2 + 6 + 6 + 6 + 6)
|
|
l = 4
|
|
n = uint64(c0 & mask5)
|
|
// TODO(u): Remove log message when the test cases have been extended.
|
|
log.Printf("frame.decodeUTF8Int: The flac library test cases do not yet include any audio files with %d UTF-8 continuation bytes. If possible please consider contributing this audio sample to improve the reliability of the test cases.", l)
|
|
case c0 < t7:
|
|
// if c0 == 1111110x
|
|
// total: 31 bits (1 + 6 + 6 + 6 + 6 + 6)
|
|
l = 5
|
|
n = uint64(c0 & mask6)
|
|
// TODO(u): Remove log message when the test cases have been extended.
|
|
log.Printf("frame.decodeUTF8Int: The flac library test cases do not yet include any audio files with %d UTF-8 continuation bytes. If possible please consider contributing this audio sample to improve the reliability of the test cases.", l)
|
|
case c0 < t8:
|
|
// if c0 == 11111110
|
|
// total: 36 bits (0 + 6 + 6 + 6 + 6 + 6 + 6)
|
|
l = 6
|
|
n = 0
|
|
// TODO(u): Remove log message when the test cases have been extended.
|
|
log.Printf("frame.decodeUTF8Int: The flac library test cases do not yet include any audio files with %d UTF-8 continuation bytes. If possible please consider contributing this audio sample to improve the reliability of the test cases.", l)
|
|
}
|
|
|
|
// store bits from continuation bytes.
|
|
for i := 0; i < l; i++ {
|
|
n <<= 6
|
|
c, err := readByte(r)
|
|
if err != nil {
|
|
if err == io.EOF {
|
|
return 0, io.ErrUnexpectedEOF
|
|
}
|
|
return 0, err
|
|
}
|
|
if c < tx || t2 <= c {
|
|
// if c != 10xxxxxx
|
|
return 0, errors.New("frame.decodeUTF8Int: expected continuation byte")
|
|
}
|
|
n |= uint64(c & maskx)
|
|
}
|
|
|
|
// check if number representation is larger than necessary.
|
|
switch l {
|
|
case 1:
|
|
if n <= rune1Max {
|
|
return 0, fmt.Errorf("frame.decodeUTF8Int: larger number representation than necessary; n (%d) stored in %d bytes, could be stored in %d bytes", n, l+1, l)
|
|
}
|
|
case 2:
|
|
if n <= rune2Max {
|
|
return 0, fmt.Errorf("frame.decodeUTF8Int: larger number representation than necessary; n (%d) stored in %d bytes, could be stored in %d bytes", n, l+1, l)
|
|
}
|
|
case 3:
|
|
if n <= rune3Max {
|
|
return 0, fmt.Errorf("frame.decodeUTF8Int: larger number representation than necessary; n (%d) stored in %d bytes, could be stored in %d bytes", n, l+1, l)
|
|
}
|
|
case 4:
|
|
if n <= rune4Max {
|
|
return 0, fmt.Errorf("frame.decodeUTF8Int: larger number representation than necessary; n (%d) stored in %d bytes, could be stored in %d bytes", n, l+1, l)
|
|
}
|
|
case 5:
|
|
if n <= rune5Max {
|
|
return 0, fmt.Errorf("frame.decodeUTF8Int: larger number representation than necessary; n (%d) stored in %d bytes, could be stored in %d bytes", n, l+1, l)
|
|
}
|
|
case 6:
|
|
if n <= rune6Max {
|
|
return 0, fmt.Errorf("frame.decodeUTF8Int: larger number representation than necessary; n (%d) stored in %d bytes, could be stored in %d bytes", n, l+1, l)
|
|
}
|
|
}
|
|
|
|
return n, nil
|
|
}
|
|
|
|
// readByte reads and returns the next byte from the provided io.Reader.
|
|
func readByte(r io.Reader) (c byte, err error) {
|
|
buf := make([]byte, 1)
|
|
_, err = io.ReadFull(r, buf)
|
|
if err != nil {
|
|
return 0, err
|
|
}
|
|
return buf[0], nil
|
|
}
|