This commit is contained in:
root
2023-03-29 15:20:05 +00:00
parent 5ec489e0e0
commit a0bb8f2d1e
25468 changed files with 3063105 additions and 28 deletions
+21
View File
@@ -0,0 +1,21 @@
MIT License
Copyright (c) 2018 Sven Sauleau <sven@sauleau.com>
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
@@ -0,0 +1,95 @@
function _toConsumableArray(arr) { if (Array.isArray(arr)) { for (var i = 0, arr2 = new Array(arr.length); i < arr.length; i++) { arr2[i] = arr[i]; } return arr2; } else { return Array.from(arr); } }
function _toArray(arr) { return Array.isArray(arr) ? arr : Array.from(arr); }
function con(b) {
if ((b & 0xc0) === 0x80) {
return b & 0x3f;
} else {
throw new Error("invalid UTF-8 encoding");
}
}
function code(min, n) {
if (n < min || 0xd800 <= n && n < 0xe000 || n >= 0x10000) {
throw new Error("invalid UTF-8 encoding");
} else {
return n;
}
}
export function decode(bytes) {
return _decode(bytes).map(function (x) {
return String.fromCharCode(x);
}).join("");
}
function _decode(bytes) {
if (bytes.length === 0) {
return [];
}
/**
* 1 byte
*/
{
var _bytes = _toArray(bytes),
b1 = _bytes[0],
bs = _bytes.slice(1);
if (b1 < 0x80) {
return [code(0x0, b1)].concat(_toConsumableArray(_decode(bs)));
}
if (b1 < 0xc0) {
throw new Error("invalid UTF-8 encoding");
}
}
/**
* 2 bytes
*/
{
var _bytes2 = _toArray(bytes),
_b = _bytes2[0],
b2 = _bytes2[1],
_bs = _bytes2.slice(2);
if (_b < 0xe0) {
return [code(0x80, ((_b & 0x1f) << 6) + con(b2))].concat(_toConsumableArray(_decode(_bs)));
}
}
/**
* 3 bytes
*/
{
var _bytes3 = _toArray(bytes),
_b2 = _bytes3[0],
_b3 = _bytes3[1],
b3 = _bytes3[2],
_bs2 = _bytes3.slice(3);
if (_b2 < 0xf0) {
return [code(0x800, ((_b2 & 0x0f) << 12) + (con(_b3) << 6) + con(b3))].concat(_toConsumableArray(_decode(_bs2)));
}
}
/**
* 4 bytes
*/
{
var _bytes4 = _toArray(bytes),
_b4 = _bytes4[0],
_b5 = _bytes4[1],
_b6 = _bytes4[2],
b4 = _bytes4[3],
_bs3 = _bytes4.slice(4);
if (_b4 < 0xf8) {
return [code(0x10000, (((_b4 & 0x07) << 18) + con(_b5) << 12) + (con(_b6) << 6) + con(b4))].concat(_toConsumableArray(_decode(_bs3)));
}
}
throw new Error("invalid UTF-8 encoding");
}
@@ -0,0 +1,46 @@
function _toConsumableArray(arr) { if (Array.isArray(arr)) { for (var i = 0, arr2 = new Array(arr.length); i < arr.length; i++) { arr2[i] = arr[i]; } return arr2; } else { return Array.from(arr); } }
function _toArray(arr) { return Array.isArray(arr) ? arr : Array.from(arr); }
function con(n) {
return 0x80 | n & 0x3f;
}
export function encode(str) {
var arr = str.split("").map(function (x) {
return x.charCodeAt(0);
});
return _encode(arr);
}
function _encode(arr) {
if (arr.length === 0) {
return [];
}
var _arr = _toArray(arr),
n = _arr[0],
ns = _arr.slice(1);
if (n < 0) {
throw new Error("utf8");
}
if (n < 0x80) {
return [n].concat(_toConsumableArray(_encode(ns)));
}
if (n < 0x800) {
return [0xc0 | n >>> 6, con(n)].concat(_toConsumableArray(_encode(ns)));
}
if (n < 0x10000) {
return [0xe0 | n >>> 12, con(n >>> 6), con(n)].concat(_toConsumableArray(_encode(ns)));
}
if (n < 0x110000) {
return [0xf0 | n >>> 18, con(n >>> 12), con(n >>> 6), con(n)].concat(_toConsumableArray(_encode(ns)));
}
throw new Error("utf8");
}
@@ -0,0 +1,2 @@
export { decode } from "./decoder";
export { encode } from "./encoder";
@@ -0,0 +1,102 @@
"use strict";
Object.defineProperty(exports, "__esModule", {
value: true
});
exports.decode = decode;
function _toConsumableArray(arr) { if (Array.isArray(arr)) { for (var i = 0, arr2 = new Array(arr.length); i < arr.length; i++) { arr2[i] = arr[i]; } return arr2; } else { return Array.from(arr); } }
function _toArray(arr) { return Array.isArray(arr) ? arr : Array.from(arr); }
function con(b) {
if ((b & 0xc0) === 0x80) {
return b & 0x3f;
} else {
throw new Error("invalid UTF-8 encoding");
}
}
function code(min, n) {
if (n < min || 0xd800 <= n && n < 0xe000 || n >= 0x10000) {
throw new Error("invalid UTF-8 encoding");
} else {
return n;
}
}
function decode(bytes) {
return _decode(bytes).map(function (x) {
return String.fromCharCode(x);
}).join("");
}
function _decode(bytes) {
if (bytes.length === 0) {
return [];
}
/**
* 1 byte
*/
{
var _bytes = _toArray(bytes),
b1 = _bytes[0],
bs = _bytes.slice(1);
if (b1 < 0x80) {
return [code(0x0, b1)].concat(_toConsumableArray(_decode(bs)));
}
if (b1 < 0xc0) {
throw new Error("invalid UTF-8 encoding");
}
}
/**
* 2 bytes
*/
{
var _bytes2 = _toArray(bytes),
_b = _bytes2[0],
b2 = _bytes2[1],
_bs = _bytes2.slice(2);
if (_b < 0xe0) {
return [code(0x80, ((_b & 0x1f) << 6) + con(b2))].concat(_toConsumableArray(_decode(_bs)));
}
}
/**
* 3 bytes
*/
{
var _bytes3 = _toArray(bytes),
_b2 = _bytes3[0],
_b3 = _bytes3[1],
b3 = _bytes3[2],
_bs2 = _bytes3.slice(3);
if (_b2 < 0xf0) {
return [code(0x800, ((_b2 & 0x0f) << 12) + (con(_b3) << 6) + con(b3))].concat(_toConsumableArray(_decode(_bs2)));
}
}
/**
* 4 bytes
*/
{
var _bytes4 = _toArray(bytes),
_b4 = _bytes4[0],
_b5 = _bytes4[1],
_b6 = _bytes4[2],
b4 = _bytes4[3],
_bs3 = _bytes4.slice(4);
if (_b4 < 0xf8) {
return [code(0x10000, (((_b4 & 0x07) << 18) + con(_b5) << 12) + (con(_b6) << 6) + con(b4))].concat(_toConsumableArray(_decode(_bs3)));
}
}
throw new Error("invalid UTF-8 encoding");
}
@@ -0,0 +1,53 @@
"use strict";
Object.defineProperty(exports, "__esModule", {
value: true
});
exports.encode = encode;
function _toConsumableArray(arr) { if (Array.isArray(arr)) { for (var i = 0, arr2 = new Array(arr.length); i < arr.length; i++) { arr2[i] = arr[i]; } return arr2; } else { return Array.from(arr); } }
function _toArray(arr) { return Array.isArray(arr) ? arr : Array.from(arr); }
function con(n) {
return 0x80 | n & 0x3f;
}
function encode(str) {
var arr = str.split("").map(function (x) {
return x.charCodeAt(0);
});
return _encode(arr);
}
function _encode(arr) {
if (arr.length === 0) {
return [];
}
var _arr = _toArray(arr),
n = _arr[0],
ns = _arr.slice(1);
if (n < 0) {
throw new Error("utf8");
}
if (n < 0x80) {
return [n].concat(_toConsumableArray(_encode(ns)));
}
if (n < 0x800) {
return [0xc0 | n >>> 6, con(n)].concat(_toConsumableArray(_encode(ns)));
}
if (n < 0x10000) {
return [0xe0 | n >>> 12, con(n >>> 6), con(n)].concat(_toConsumableArray(_encode(ns)));
}
if (n < 0x110000) {
return [0xf0 | n >>> 18, con(n >>> 12), con(n >>> 6), con(n)].concat(_toConsumableArray(_encode(ns)));
}
throw new Error("utf8");
}
@@ -0,0 +1,21 @@
"use strict";
Object.defineProperty(exports, "__esModule", {
value: true
});
Object.defineProperty(exports, "decode", {
enumerable: true,
get: function get() {
return _decoder.decode;
}
});
Object.defineProperty(exports, "encode", {
enumerable: true,
get: function get() {
return _encoder.encode;
}
});
var _decoder = require("./decoder");
var _encoder = require("./encoder");
@@ -0,0 +1,20 @@
{
"name": "@webassemblyjs/utf8",
"version": "1.9.0",
"description": "UTF8 encoder/decoder for WASM",
"main": "lib/index.js",
"module": "esm/index.js",
"scripts": {
"test": "echo \"Error: no test specified\" && exit 1"
},
"repository": {
"type": "git",
"url": "https://github.com/xtuc/webassemblyjs.git"
},
"publishConfig": {
"access": "public"
},
"author": "Sven Sauleau",
"license": "MIT",
"gitHead": "0440b420888c1f7701eb9762ec657775506b87d8"
}
@@ -0,0 +1,86 @@
function con(b) {
if ((b & 0xc0) === 0x80) {
return b & 0x3f;
} else {
throw new Error("invalid UTF-8 encoding");
}
}
function code(min, n) {
if (n < min || (0xd800 <= n && n < 0xe000) || n >= 0x10000) {
throw new Error("invalid UTF-8 encoding");
} else {
return n;
}
}
export function decode(bytes) {
return _decode(bytes)
.map(x => String.fromCharCode(x))
.join("");
}
function _decode(bytes) {
if (bytes.length === 0) {
return [];
}
/**
* 1 byte
*/
{
const [b1, ...bs] = bytes;
if (b1 < 0x80) {
return [code(0x0, b1), ..._decode(bs)];
}
if (b1 < 0xc0) {
throw new Error("invalid UTF-8 encoding");
}
}
/**
* 2 bytes
*/
{
const [b1, b2, ...bs] = bytes;
if (b1 < 0xe0) {
return [code(0x80, ((b1 & 0x1f) << 6) + con(b2)), ..._decode(bs)];
}
}
/**
* 3 bytes
*/
{
const [b1, b2, b3, ...bs] = bytes;
if (b1 < 0xf0) {
return [
code(0x800, ((b1 & 0x0f) << 12) + (con(b2) << 6) + con(b3)),
..._decode(bs)
];
}
}
/**
* 4 bytes
*/
{
const [b1, b2, b3, b4, ...bs] = bytes;
if (b1 < 0xf8) {
return [
code(
0x10000,
((((b1 & 0x07) << 18) + con(b2)) << 12) + (con(b3) << 6) + con(b4)
),
..._decode(bs)
];
}
}
throw new Error("invalid UTF-8 encoding");
}
@@ -0,0 +1,44 @@
function con(n) {
return 0x80 | (n & 0x3f);
}
export function encode(str) {
const arr = str.split("").map(x => x.charCodeAt(0));
return _encode(arr);
}
function _encode(arr) {
if (arr.length === 0) {
return [];
}
const [n, ...ns] = arr;
if (n < 0) {
throw new Error("utf8");
}
if (n < 0x80) {
return [n, ..._encode(ns)];
}
if (n < 0x800) {
return [0xc0 | (n >>> 6), con(n), ..._encode(ns)];
}
if (n < 0x10000) {
return [0xe0 | (n >>> 12), con(n >>> 6), con(n), ..._encode(ns)];
}
if (n < 0x110000) {
return [
0xf0 | (n >>> 18),
con(n >>> 12),
con(n >>> 6),
con(n),
..._encode(ns)
];
}
throw new Error("utf8");
}
@@ -0,0 +1,4 @@
// @flow
export { decode } from "./decoder";
export { encode } from "./encoder";
@@ -0,0 +1,13 @@
const { assert } = require("chai");
const { decode, encode } = require("../lib");
describe("UTF8", () => {
it("should f-1(f(x)) = x", () => {
assert.equal(decode(encode("foo")), "foo");
assert.equal(decode(encode("éé")), "éé");
// TODO(sven): utf8 encoder fails here
// assert.equal(decode(encode("🤣见見")), "🤣见見");
});
});