我正在寻找一个JavaScript函数，它可以接受一个字符串并返回一个压缩（更短）的字符串。
我正在开发一个Chrome Web应用程序，将长字符串（HTML）保存到本地数据库中。为了测试，我尝试对存储数据库的文件进行压缩，结果其大小缩小了五倍，因此我认为如果压缩它所存储的内容，可以帮助保持数据库更小。
我在这里找到了一个JavaScript实现的LZSS：http://code.google.com/p/u-lzss/ （“U-LZSS”）。
当我用简短的示例字符串“手动”测试时（解码等于编码），它似乎能够工作，并且在Chrome中速度也相当快。但是当给出大字符串（100 ko）时，它似乎会混淆/混合字符串的后一半部分。
是否可能U-LZSS只适用于短字符串而无法处理较大的字符串？并且是否可能调整一些参数以提高上限？
compressToBase64() 和 decompressFromBase64() 完美地满足了我的需求。 - TripeHoundfunction compress(string, encoding) {
const byteArray = new TextEncoder().encode(string);
const cs = new CompressionStream(encoding);
const writer = cs.writable.getWriter();
writer.write(byteArray);
writer.close();
return new Response(cs.readable).arrayBuffer();
}
function decompress(byteArray, encoding) {
const cs = new DecompressionStream(encoding);
const writer = cs.writable.getWriter();
writer.write(byteArray);
writer.close();
return new Response(cs.readable).arrayBuffer().then(function (arrayBuffer) {
return new TextDecoder().decode(arrayBuffer);
});
}
const test = "http://www.ScriptCompress.com - Simple Packer/Minify/Compress JavaScript Minify, Fixify & Prettify 75 JS Obfuscators In 1 App 25 JS Compressors (Gzip, Bzip, LZMA, etc) PHP, HTML & JS Packers In 1 App PHP Source Code Packers Text Packer HTML Packer or v2 or v3 or LZW Twitter Compress or More Words DNA & Base64 Packer (freq tool) or v2 JS JavaScript Code Golfer Encode Between Quotes Decode Almost Anything Password Protect Scripts HTML Minifier v2 or Encoder or Escaper CSS Minifier or Compressor v2 SVG Image Shrinker HTML To: SVG or SVGZ (Gzipped) HTML To: PNG or v2 2015 JS Packer v2 v3 Embedded File Generator Extreme Packer or version 2 Our Blog DemoScene JS Packer Basic JS Packer or New Version Asciify JavaScript Escape JavaScript Characters UnPacker Packed JS JavaScript Minify/Uglify Text Splitter/Chunker Twitter, Use More Characters Base64 Drag 'n Drop Redirect URL DataURI Get Words Repeated LZMA Archiver ZIP Read/Extract/Make BEAUTIFIER & CODE FIXER WHAK-A-SCRIPT JAVASCRIPT MANGLER 30 STRING ENCODERS CONVERTERS, ENCRYPTION & ENCODERS 43 Byte 1px GIF Generator Steganography PNG Generator WEB APPS VIA DATAURL OLD VERSION OF WHAK PAKr Fun Text Encrypt Our Google";
async function testCompression(text, encoding = 'deflate') {
console.log(encoding + ':');
console.time('compress');
const compressedData = await compress(text, encoding);
console.timeEnd('compress');
console.log('compressed length:', compressedData.byteLength, 'bytes');
console.time('decompress');
const decompressedText = await decompress(compressedData, encoding);
console.timeEnd('decompress');
console.log('decompressed length:', decompressedText.length, 'characters');
console.assert(text === decompressedText);
}
(async function () {
await testCompression(test, 'deflate');
await testCompression(test, 'gzip');
}());
document.getElementById('go').onclick = function () {
const s = document.getElementById('string').value;
testCompression(s, 'gzip');
};<div>
<label>
String to compress:
<input id="string" />
</label>
</div>
<button id="go">Go</button>brotli 呢？ - Mir-Ismaili以下是我从LZW修改的编码函数（en）和解码函数（de），它们的大小分别为276字节和191字节，并且在完全工作的演示中。互联网上没有比我提供的更小、更快的例程。
function en(c){var x='charCodeAt',b,e={},f=c.split(""),d=[],a=f[0],g=256;for(b=1;b<f.length;b++)c=f[b],null!=e[a+c]?a+=c:(d.push(1<a.length?e[a]:a[x](0)),e[a+c]=g,g++,a=c);d.push(1<a.length?e[a]:a[x](0));for(b=0;b<d.length;b++)d[b]=String.fromCharCode(d[b]);return d.join("")}
function de(b){var a,e={},d=b.split(""),c=f=d[0],g=[c],h=o=256;for(b=1;b<d.length;b++)a=d[b].charCodeAt(0),a=h>a?d[b]:e[a]?e[a]:f+c,g.push(a),c=a.charAt(0),e[o]=f+c,o++,f=a;return g.join("")}
var compressed=en("http://www.ScriptCompress.com - Simple Packer/Minify/Compress JavaScript Minify, Fixify & Prettify 75 JS Obfuscators In 1 App 25 JS Compressors (Gzip, Bzip, LZMA, etc) PHP, HTML & JS Packers In 1 App PHP Source Code Packers Text Packer HTML Packer or v2 or v3 or LZW Twitter Compress or More Words DNA & Base64 Packer (freq tool) or v2 JS JavaScript Code Golfer Encode Between Quotes Decode Almost Anything Password Protect Scripts HTML Minifier v2 or Encoder or Escaper CSS Minifier or Compressor v2 SVG Image Shrinker HTML To: SVG or SVGZ (Gzipped) HTML To: PNG or v2 2015 JS Packer v2 v3 Embedded File Generator Extreme Packer or version 2 Our Blog DemoScene JS Packer Basic JS Packer or New Version Asciify JavaScript Escape JavaScript Characters UnPacker Packed JS JavaScript Minify/Uglify Text Splitter/Chunker Twitter, Use More Characters Base64 Drag 'n Drop Redirect URL DataURI Get Words Repeated LZMA Archiver ZIP Read/Extract/Make BEAUTIFIER & CODE FIXER WHAK-A-SCRIPT JAVASCRIPT MANGLER 30 STRING ENCODERS CONVERTERS, ENCRYPTION & ENCODERS 43 Byte 1px GIF Generator Steganography PNG Generator WEB APPS VIA DATAURL OLD VERSION OF WHAK PAKr Fun Text Encrypt Our Google");
var decompressed=de(compressed);
document.writeln('<hr>'+compressed+'<hr><h1>'+compressed.length+' characters versus original '+decompressed.length+' characters.</h1><hr>'+decompressed+'<hr>');`在Object.de处`
`Uncaught ReferenceError: f未定义`
`Uncaught ReferenceError: o未定义` - PartialFlavor_55KP在Piskvor的建议下，我测试了在这个问题的答案中找到的代码：JavaScript实现Gzip（得票最高的答案：LZW实现），并发现：
...虽然不及5，但总比没有好。所以我使用了它。
（我希望我能接受Piskvor的答案，但那只是一个评论。）
let cset = "";
for (let i=35; i<35+85+1; i++) {
if (i !== 92) cset += String.fromCharCode(i);
}
将4个字节（b0，b1，b2和b3，每个字节的值在0到255之间）编码成5个字符的代码如下：
// First convert to 0...4294967295
let x = ((b0*256 + b1)*256 + b2)*256 + b3;
// Then convert to base 85
let result = "";
for (let i=0; i<5; i++) {
let x2 = Math.floor(x / 85);
result += cset[x - x2*85];
x = x2;
}
// There are two Huffman-encoded code streams
// T - single chars (0..127) and sequence lengths (128...255)
// A - high bits of relative addresses of sequence (0..255)
//
// Expansion algorithm is:
// 1) Read a code X from T
// 2) If it's a char (X < 128) then add to output
// 3) otherwise (X>=128) read sequence address ADDR from stream A (high bits)
// and from input (low bits) and copy X-128 bytes from ADDR bytes "ago"
//
let Z = 5831; // expanded size
let i = 0, // source ptr
a = 0, // current bits accumulator
n = 0; // number of available bits in a
// Read a single bit
let b = function(){
if (!n) {
// There are no more bits available in the accumulator, read a new chunk:
// 5 ASCII escape-safe chars will be transformed in 4 8-bit binary bytes
// (like BASE64, just a bit more dense)
a = 0;
let w = 5;
while (w--) {
let y = s.charCodeAt(i+w); // get next char
a = a*85 + (y > 125 ? 92 : y) - 35; // extract base-85 "digit" (note, uses ~ instead of \ that requires quoting)
}
n = 32; // we got 32 bits in a
i += 5; // we consumed 5 characters from source
}
return (a >> --n) & 1; // extract a single bit
};
// Read a code of z bits by concatenating bits coming from b()
let v = function(z){
return (--z ? v(z) : 0)*2+b();
};
// Read an Huffman (sub-)tree: a bit will tell if we need to
// read a two sub-trees or a leaf
let h = function(){
return b() ? [h(), h()] : v(8);
};
// Read A and T Huffman trees
let A = h(), T = h();
// Extract a code given a node:
// if the node is an array (intermediate node) then we need to read a bit
// from the input binary stream to decide which way to go down the tree,
// if it's a number then we just return the value.
// `n.map` is truthy for arrays and falsy for numbers.
let d = function(n){
return n.map ? d(n[b()]) : n;
};
let S=""; // Output
// While we're not done
while(S.length<Z){
// Extract a code from T
x = d(T);
if (x < 128) {
// This is a single character, copy to output
S += String.fromCharCode(x);
} else {
// This is a sequence of x-128 bytes, get address and copy it
// Note: high 8 bits are from the Huffman tree A and 8 low bits
// are instead directly form the bit stream as they're basically
// noise and there's nothing to gain by trying to compress them.
S += S.substr(S.length-(d(A)<<8)-v(8), x-128)
};
}
async function compress(inString) {
const compressedStream = await new Response(inString).body.pipeThrough(new CompressionStream('gzip'))
const bytes = await new Response(compressedStream).arrayBuffer()
return bytes
}
将字节数组解压缩以获取原始字符串
async function decompress(bytes) {
const decompressedStream = await new Response(bytes).body.pipeThrough(new DecompressionStream('gzip'))
const outString = await new Response(decompressed).text()
return outString
}
这个库在其他语言中也有实现。我目前正在研究Python实现，但解压缩似乎存在问题。但如果你只使用JS，这个库看起来非常好。
在实现任何内容之前，请尝试通过文本文件进行实验，因为我认为以下内容不一定适用：
所以我想，如果压缩存储的东西，它将有助于保持数据库更小。
这是因为无损压缩算法对于重复模式（例如空格）非常有效。
u-lzss似乎只能处理 UTF-8 编码的字符串。 - Frédéric Hamidi