in flexflate/huffman_bit_writer.go [370:517]
func (w *huffmanBitWriter) writeBlock(tokens []token, eof bool, input []byte) {
if w.err != nil {
return
}
for i := range w.literalFreq {
w.literalFreq[i] = 0
}
for i := range w.offsetFreq {
w.offsetFreq[i] = 0
}
n := len(tokens)
tokens = tokens[0 : n+1]
tokens[n] = endBlockMarker
for _, t := range tokens {
switch t.typ() {
case literalType:
w.literalFreq[t.literal()]++
case matchType:
length := t.length()
offset := t.offset()
w.literalFreq[lengthCodesStart+lengthCode(length)]++
w.offsetFreq[offsetCode(offset)]++
}
}
// get the number of literals
numLiterals := len(w.literalFreq)
for w.literalFreq[numLiterals-1] == 0 {
numLiterals--
}
// get the number of offsets
numOffsets := len(w.offsetFreq)
for numOffsets > 0 && w.offsetFreq[numOffsets-1] == 0 {
numOffsets--
}
if numOffsets == 0 {
// We haven't found a single match. If we want to go with the dynamic encoding,
// we should count at least one offset to be sure that the offset huffman tree could be encoded.
w.offsetFreq[0] = 1
numOffsets = 1
}
w.literalEncoding.generate(w.literalFreq, 15)
w.offsetEncoding.generate(w.offsetFreq, 15)
storedBytes := 0
if input != nil {
storedBytes = len(input)
}
var extraBits int64
var storedSize int64 = math.MaxInt64
if storedBytes <= maxStoreBlockSize && input != nil {
storedSize = int64((storedBytes + 5) * 8)
// We only bother calculating the costs of the extra bits required by
// the length of offset fields (which will be the same for both fixed
// and dynamic encoding), if we need to compare those two encodings
// against stored encoding.
for lengthCode := lengthCodesStart + 8; lengthCode < numLiterals; lengthCode++ {
// First eight length codes have extra size = 0.
extraBits += int64(w.literalFreq[lengthCode]) * int64(lengthExtraBits[lengthCode-lengthCodesStart])
}
for offsetCode := 4; offsetCode < numOffsets; offsetCode++ {
// First four offset codes have extra size = 0.
extraBits += int64(w.offsetFreq[offsetCode]) * int64(offsetExtraBits[offsetCode])
}
}
// Figure out smallest code.
// Fixed Huffman baseline.
var size = int64(3) +
fixedLiteralEncoding.bitLength(w.literalFreq) +
fixedOffsetEncoding.bitLength(w.offsetFreq) +
extraBits
var literalEncoding = fixedLiteralEncoding
var offsetEncoding = fixedOffsetEncoding
// Dynamic Huffman?
var numCodegens int
// Generate codegen and codegenFrequencies, which indicates how to encode
// the literalEncoding and the offsetEncoding.
w.generateCodegen(numLiterals, numOffsets)
w.codegenEncoding.generate(w.codegenFreq, 7)
numCodegens = len(w.codegenFreq)
for numCodegens > 4 && w.codegenFreq[codegenOrder[numCodegens-1]] == 0 {
numCodegens--
}
dynamicHeader := int64(3+5+5+4+(3*numCodegens)) +
w.codegenEncoding.bitLength(w.codegenFreq) +
int64(extraBits) +
int64(w.codegenFreq[16]*2) +
int64(w.codegenFreq[17]*3) +
int64(w.codegenFreq[18]*7)
dynamicSize := dynamicHeader +
w.literalEncoding.bitLength(w.literalFreq) +
w.offsetEncoding.bitLength(w.offsetFreq)
if dynamicSize < size {
size = dynamicSize
literalEncoding = w.literalEncoding
offsetEncoding = w.offsetEncoding
}
// Stored bytes?
if storedSize < size {
w.writeStoredHeader(storedBytes, eof)
w.writeBytes(input[0:storedBytes])
return
}
// Huffman.
if literalEncoding == fixedLiteralEncoding {
w.writeFixedHeader(eof)
} else {
w.writeDynamicHeader(numLiterals, numOffsets, numCodegens, eof)
}
for _, t := range tokens {
switch t.typ() {
case literalType:
w.writeCode(literalEncoding, t.literal())
break
case matchType:
// Write the length
length := t.length()
lengthCode := lengthCode(length)
w.writeCode(literalEncoding, lengthCode+lengthCodesStart)
extraLengthBits := int32(lengthExtraBits[lengthCode])
if extraLengthBits > 0 {
extraLength := int32(length - lengthBase[lengthCode])
w.writeBits(extraLength, extraLengthBits)
}
// Write the offset
offset := t.offset()
offsetCode := offsetCode(offset)
w.writeCode(offsetEncoding, offsetCode)
extraOffsetBits := int32(offsetExtraBits[offsetCode])
if extraOffsetBits > 0 {
extraOffset := int32(offset - offsetBase[offsetCode])
w.writeBits(extraOffset, extraOffsetBits)
}
break
default:
panic("unknown token type: " + string(t))
}
}
}