大家都在问encoding-indexes.js，地址：encoding-indexes.js地址https://download.csdn.net/download/he3236220/88955364
- 打印机，需要插usb(或者微信小程序设置wifi)
- 打印机的默认端口是9100（一般是，具体看购买的打印机）
- wifitool.js是用于连接打印机的
- 此文章是用的CPCL指令，可以根据自己的指令格式修改（var command = tsc.jpPrinter.createNew();）
vue
<template>
<view>
<button @click="printSocket">WiFi打印</button>
</view>
</template>
js
<script>
import tsc from "@/static/libs/tsc.js";
import wifiTool from "@/static/libs/WifiTool.js";
export default {
data() {
return {
ip: "192.168.4.245",
port: 9100,
str: "yyy",
};
},
mounted() {
wifiTool.connectWifi("192.168.4.245", 9100);
},
methods: {
test(str, ip, port) {
str = "test";
var Socket = plus.android.importClass("java.net.Socket");
var JavaByte = plus.android.importClass("java.lang.Byte");
var PrintWriter = plus.android.importClass("java.io.PrintWriter");
var BufferedWriter = plus.android.importClass("java.io.BufferedWriter");
var OutputStreamWriter = plus.android.importClass("java.io.OutputStreamWriter");
var BufferedReader = plus.android.importClass("java.io.BufferedReader");
var InputStreamReader = plus.android.importClass("java.io.InputStreamReader");
//测试改良
var StrictMode = plus.android.importClass("android.os.StrictMode");
var Build = plus.android.importClass("android.os.Build");
if (Build.VERSION.SDK_INT > 9) {
var policy = new StrictMode.ThreadPolicy.Builder().permitAll().build();
StrictMode.setThreadPolicy(policy);
}
var socket = new Socket(ip, port);
var outputStreamWriter = new OutputStreamWriter(socket.getOutputStream());
var bufferWriter = new BufferedWriter(outputStreamWriter);
var out = new PrintWriter(bufferWriter, true);
var command = tsc.jpPrinter.createNew();
command.init(0, 200, 200, 210, 1);
command.setCls();
command.setQR(30, 40, 2, 6, "123");
// command.setMag(2, 2);
// command.setText1(55, 30, 180, 60, "地址： 内蒙");
// command.setMag(2, 2);
// command.setText1(55, 6, 180, 120, "重量： 15kg");
command.setPagePrint();
let data = command.getData();
out.println(data);
socket.setSoTimeout(3000);
socket.close();
},
printSocket() {
var command = tsc.jpPrinter.createNew();
command.init(0, 200, 250, 210, 1);
command.setCls();
command.setQR(30, 40, 2, 6, "123");
command.setMag(2, 2);
command.setText1(55, 30, 180, 60, "地址： 内蒙");
command.setMag(2, 2);
command.setText1(55, 6, 180, 120, "重量： 15kg");
command.setPostfeed(32);//打印后走纸
command.setPagePrint();
let data = command.getData();
wifiTool.sendData(data);
},
connectWifi(ip, port) {
if (plus.os.name == "Android") {
// plus.nativeUI.showWaiting("正在打印中。。。");
var Socket = plus.android.importClass("java.net.Socket");
var socket;
var outputStream;
//解决高低版本兼容
var StrictMode = plus.android.importClass("android.os.StrictMode");
var Build = plus.android.importClass("android.os.Build");
if (Build.VERSION.SDK_INT > 9) {
var policy = new StrictMode.ThreadPolicy.Builder().permitAll().build();
StrictMode.setThreadPolicy(policy);
}
try {
socket = new Socket(ip, port);
socket.setKeepAlive(true);
outputStream = socket.getOutputStream();
plus.android.importClass(outputStream);
// var bytes = plus.android.invoke(str, "getBytes", "gbk");
uni.showToast({
title: "wifi连接成功",
});
// plus.nativeUI.closeWaiting();
} catch (e) {
console.log("网络连接超时，请重新连接！");
//TODO handle the exception
// plus.nativeUI.closeWaiting();
}
}
},
},
};
</script>
WifiTool.js
/**
* 初始化参数
*/
//#ifdef APP-PLUS
var Socket = plus.android.importClass("java.net.Socket");
var socket;
var outputStream;
//解决高低版本兼容
var StrictMode = plus.android.importClass("android.os.StrictMode");
var Build = plus.android.importClass("android.os.Build");
//#endif
/**
* 构造对象
*/
var wifiTool = {
connectWifi(ip, port) {
if (Build.VERSION.SDK_INT > 9) {
var policy = new StrictMode.ThreadPolicy.Builder().permitAll().build();
StrictMode.setThreadPolicy(policy);
}
try {
socket = new Socket(ip, port);
socket.setKeepAlive(true);
outputStream = socket.getOutputStream();
plus.android.importClass(outputStream);
// var bytes = plus.android.invoke(str, "getBytes", "gbk");
uni.showToast({
title: 'wifi连接成功',
});
// plus.nativeUI.closeWaiting();
} catch (e) {
console.log("网络连接超时，请重新连接！")
//TODO handle the exception
// plus.nativeUI.closeWaiting();
}
},
sendData(data) {
console.log(outputStream);
outputStream.write(data);
outputStream.flush();
// 关闭socket
// socket.shutdownOutput();
console.log(socket);
}
}
module.exports = wifiTool
tsc.js
/**
* tsc 命令打印工具类
* 2021.04.26 uni-app版本
* @auth boolTrue
*/
var encode = require("./encoding.js");
var jpPrinter = {
createNew: function () {
var jpPrinter = {};
var data = "";
var command = []
var rawCommand = ''
jpPrinter.name = "标签模式";
jpPrinter.init = function (x, y, z, h, q) {
data = "! " + x + " " + y + " " + z + " " + h + " " + q + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.addCommand = function (content) { //将指令转成数组装起
//#ifdef MP-WEIXIN
var code = new encode.TextEncoder(
'gb18030', {
NONSTANDARD_allowLegacyEncoding: true
}).encode(content)
for (var i = 0; i < code.length; ++i) {
command.push(code[i])
}
//#endif
//#ifdef APP-PLUS
let byteCommand = plus.android.invoke(content, 'getBytes', 'gb18030');
for (var i = 0; i < byteCommand.length; ++i) {
command.push(byteCommand[i])
}
//#endif
console.log('command--:', content)
rawCommand += content
}
function intToByte(i) {
// 此处关键 -- android是java平台 byte数值范围是 [-128, 127]
// 因为java平台的byte类型是有符号的 最高位表示符号，所以数值范围固定
// 而图片计算出来的是数值是 0 -255 属于int类型
// 所以把int 转换成byte类型
//#ifdef APP-PLUS
var b = i & 0xFF;
var c = 0;
if (b >= 128) {
c = b % 128;
c = -1 * (128 - c);
} else {
c = b;
}
return c
//#endif
// 而微信小程序不需要，因为小程序api接收的是 无符号8位
//#ifdef MP-WEIXIN
return i
//#endif
}
jpPrinter.setPostfeed = function (length) { //打印之后走纸距离指令
data = "POSTFEED " +length + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setSize = function (pageWidght, pageHeight) { //设置页面大小
data = "SIZE " + pageWidght.toString() + " mm" + "," + pageHeight.toString() + " mm" + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setSpeed = function (printSpeed) { //设置打印机速度
data = "SPEED " + printSpeed.toString() + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setDensity = function (printDensity) { //设置打印机浓度
data = "DENSITY " + printDensity.toString() + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setGap = function (printGap) { //传感器
data = "GAP " + printGap.toString() + " mm\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setCountry = function (country) { //选择国际字符集
/*
001:USA
002:French
003:Latin America
034:Spanish
039:Italian
044:United Kingdom
046:Swedish
047:Norwegian
049:German
*/
data = "COUNTRY " + country + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setCodepage = function (codepage) { //选择国际代码页
/*
8-bit codepage 字符集代表
437:United States
850:Multilingual
852:Slavic
860:Portuguese
863:Canadian/French
865:Nordic
Windows code page
1250:Central Europe
1252:Latin I
1253:Greek
1254:Turkish
以下代码页仅限于 12×24 dot 英数字体
WestEurope:WestEurope
Greek:Greek
Hebrew:Hebrew
EastEurope:EastEurope
Iran:Iran
IranII:IranII
Latvian:Latvian
Arabic:Arabic
Vietnam:Vietnam
Uygur:Uygur
Thai:Thai
1252:Latin I
1257:WPC1257
1251:WPC1251
866:Cyrillic
858:PC858
747:PC747
864:PC864
1001:PC100
*/
data = "CODEPAGE " + codepage + "\r\n";
jpPrinter.addCommand(data)
}
jpPrinter.setCls = function () { //清除打印机缓存
data = "CLS " + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setFeed = function (feed) { //将纸向前推出n
data = "FEED " + feed + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setBackFeed = function (backup) { //将纸向后回拉n
data = "BACKFEED " + backup + "\r\n";
jpPrinter.addCommand(data)
}
jpPrinter.setDirection = function (direction) { //设置打印方向，参考编程手册
data = "DIRECTION " + direction + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setReference = function (x, y) { //设置坐标原点，与打印方向有关
data = "REFERENCE " + x + "," + y + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setFrom = function () { //定位控制指令
data = "FORM \r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setFromfeed = function () { //根据Size进一张标签纸
data = "FORMFEED \r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setHome = function () { //根据Size找到下一张标签纸的位置
data = "HOME \r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setSound = function (level, interval) { //控制蜂鸣器
data = "SOUND " + level + "," + interval + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setLimitfeed = function (limit) { // 检测垂直间距
data = "LIMITFEED " + limit + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setBar = function (x, y, width, height) { //绘制线条
data = "BAR " + x + "," + y + "," + width + "," + height + "\r\n"
jpPrinter.addCommand(data)
};
jpPrinter.setBox = function (x_start, y_start, x_end, y_end, thickness) { //绘制方框
data = "BOX " + x_start + "," + y_start + "," + x_end + "," + y_end + "," + thickness + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setErase = function (x_start, y_start, x_width, y_height) { //清除指定区域的数据
data = "ERASE " + x_start + "," + y_start + "," + x_width + "," + y_height + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setReverse = function (x_start, y_start, x_width, y_height) { //将指定的区域反相打印
data = "REVERSE " + x_start + "," + y_start + "," + x_width + "," + y_height + "\r\n";
jpPrinter.addCommand(data)
};
jpPrinter.setText1 = function (font, s, x, y, str) { //打印文字
data = "TEXT " + font + " " + s + " " + x + " " + y + " " + str + "\r\n"
jpPrinter.addCommand(data)
};
jpPrinter.setText = function (x, y, font, x_, y_, str) { //打印文字
data = "TEXT " + x + "," + y + ",\"" + font + "\"," + 0 + "," + x_ + "," + y_ + "," + "\"" +
str + "\"\r\n"
jpPrinter.addCommand(data)
};
jpPrinter.setMag = function (w,h) { //打印二维码
data = "SETMAG " + w + " " + h + "\r\n"
jpPrinter.addCommand(data)
};
jpPrinter.setQR = function (x, y, m, u, content) { //打印二维码
data = "BARCODE QR " + x + " " + y + " M " + m + " U " + u + "\r\n MA," + content + "\r\nENDQR\r\n"
jpPrinter.addCommand(data)
};
jpPrinter.setPDF = function (type, x, y,xd,yd,c,s, content) { //打印条形
data = "BARCODE " + type + " " + x + " " + y + " XD " + xd + " YD " + yd + " C " + c + " S " + s + "\r\n"+ content+ "\r\nENDPDF\r\n"
jpPrinter.addCommand(data)
};
jpPrinter.setBarCode = function (type, w, r, h, x, y, content) { //打印条形码
data = "BARCODE " + type + " " + w + " " + r + " " + h + " " + x + " " + y + " " + content + "\r\n"
jpPrinter.addCommand(data)
};
// 固定灰度阈值（128以上的都看作白色）
jpPrinter.setBitmap = function (x, y, mode, res) { //添加图片，res为画布参数
var width = parseInt((res.width) / 8 * 8 / 8)
var height = res.height
var imgWidth = res.width
var time = 1;
var temp = res.data.length - width * 32;
var pointList = []
var resultData = []
console.log(width + "--" + height)
data = "BITMAP " + x + "," + y + "," + width + "," + height + "," + mode + ","
jpPrinter.addCommand(data)
//console.log(res.data)
console.log('---以上是原始数据---')
//for循环顺序不要错了，外层遍历高度，内层遍历宽度，因为横向每8个像素点组成一个字节
for (var y = 0; y < height; y++) {
for (var x = 0; x < imgWidth; x++) {
let r = res.data[(y * imgWidth + x) * 4];
let g = res.data[(y * imgWidth + x) * 4 + 1];
let b = res.data[(y * imgWidth + x) * 4 + 2];
let a = res.data[(y * imgWidth + x) * 4 + 3]
//console.log(`当前${y}行${x}列像素,rgba值:(${r},${g},${b},${a})`)
// 像素灰度值
let grayColor = r * 0.299 + g * 0.587 + b * 0.114
//灰度值大于128位
//1不打印, 0打印 （参考：佳博标签打印机编程手册tspl）
if (grayColor > 128) {
pointList.push(1)
} else {
pointList.push(0)
}
}
}
//console.log(pointList)
for (var i = 0; i < pointList.length; i += 8) {
var p = pointList[i] * 128 + pointList[i + 1] * 64 + pointList[i + 2] * 32 + pointList[i +
3] * 16 + pointList[i + 4] * 8 + pointList[i + 5] * 4 + pointList[i + 6] * 2 +
pointList[i + 7]
resultData.push(p)
}
console.log('最终数据：')
//console.log(resultData)
for (var i = 0; i < resultData.length; ++i) {
command.push(intToByte(resultData[i]))
}
}
jpPrinter.setBitmap2 = function (x, y, mode, res) { //添加图片，res为画布参数
var w = res.width
var width = parseInt((res.width + 7) / 8 * 8 / 8)
var height = res.height;
console.log(width + "--" + height)
data = "BITMAP " + x + "," + y + "," + width + "," + height + "," + mode + ","
jpPrinter.addCommand(data)
var r = []
var bits = new Uint8Array(height * width);
for (y = 0; y < height; y++) {
for (x = 0; x < w; x++) {
let r = res.data[(y * w + x) * 4];
let g = res.data[(y * w + x) * 4 + 1];
let b = res.data[(y * w + x) * 4 + 2];
let a = res.data[(y * w + x) * 4 + 3]
var color = ((a & 0xFF) << 24) | ((r & 0xFF) << 16) | ((g & 0xFF) << 8) | ((b & 0xFF) <<
0);
if ((color & 0xFF) > 128) {
bits[parseInt(y * width + x / 8)] |= (0x80 >> (x % 8));
}
}
}
for (var i = 0; i < bits.length; i++) {
//command.push((~bits[i]) & 0xFF);
command.push(intToByte(bits[i]));
//r.push((~bits[i]) & 0xFF);
}
}
// 平均灰度阈值（先计算平均灰度，然后大于平均灰度的都算作白色）
jpPrinter.setBitmap3 = function (x, y, mode, res) { //添加图片，res为画布参数
var width = parseInt((res.width) / 8 * 8 / 8)
var height = res.height
var imgWidth = res.width
var time = 1;
var temp = res.data.length - width * 32;
var pointList = []
var resultData = []
console.log(width + "--" + height)
data = "BITMAP " + x + "," + y + "," + width + "," + height + "," + mode + ","
jpPrinter.addCommand(data)
//console.log(res.data)
console.log('---以上是原始数据---')
let sumRed = 0,
sumGreen = 0,
sumBlue = 0;
let total = height * imgWidth;
let pix = res.data;
for (var i = 0; i < pix.length; i += 4) {
sumRed += pix[i]
sumGreen += pix[i + 1]
sumBlue += pix[i + 2]
}
let avgRed = parseInt(sumRed / total);
let avgGreen = parseInt(sumGreen / total);
let avgBlue = parseInt(sumBlue / total);
let avgGrayColor = avgRed * 0.299 + avgGreen * 0.587 + avgBlue * 0.114
//for循环顺序不要错了，外层遍历高度，内层遍历宽度，因为横向每8个像素点组成一个字节
for (var y = 0; y < height; y++) {
for (var x = 0; x < imgWidth; x++) {
let r = res.data[(y * imgWidth + x) * 4];
let g = res.data[(y * imgWidth + x) * 4 + 1];
let b = res.data[(y * imgWidth + x) * 4 + 2];
let a = res.data[(y * imgWidth + x) * 4 + 3]
// 像素灰度值
let grayColor = r * 0.299 + g * 0.587 + b * 0.114
//灰度值大于128位
//1不打印, 0打印 （参考：佳博标签打印机编程手册tspl）
if (grayColor > avgGrayColor) {
pointList.push(1)
} else {
pointList.push(0)
}
}
}
//console.log(pointList)
for (var i = 0; i < pointList.length; i += 8) {
var p = pointList[i] * 128 + pointList[i + 1] * 64 + pointList[i + 2] * 32 + pointList[i +
3] * 16 + pointList[i + 4] * 8 + pointList[i + 5] * 4 + pointList[i + 6] * 2 +
pointList[i + 7]
resultData.push(p)
}
console.log('最终数据：')
//console.log(resultData)
for (var i = 0; i < resultData.length; ++i) {
command.push(intToByte(resultData[i]))
}
}
jpPrinter.RawCommand = function (data) {
jpPrinter.addCommand(data)
}
jpPrinter.setPagePrint = function () { //打印页面
// data = "PRINT 1,1\r\n"
data = "PRINT \r\n"
jpPrinter.addCommand(data)
};
//获取打印数据
jpPrinter.getData = function () {
return command;
};
jpPrinter.getRawData = function () {
return rawCommand;
};
jpPrinter.clearCommand = function () {
rawCommand = ''
};
return jpPrinter;
}
};
module.exports.jpPrinter = jpPrinter;
encoding.js
// This is free and unencumbered software released into the public domain.
// See LICENSE.md for more information.
/**
* @fileoverview Global |this| required for resolving indexes in node.
* @suppress {globalThis}
*/
(function(global) {
'use strict';
// If we're in node require encoding-indexes and attach it to the global.
if (typeof module !== "undefined" && module.exports &&
!global["encoding-indexes"]) {
global["encoding-indexes"] =
require("./encoding-indexes.js")["encoding-indexes"];
}
//
// Utilities
//
/**
* @param {number} a The number to test.
* @param {number} min The minimum value in the range, inclusive.
* @param {number} max The maximum value in the range, inclusive.
* @return {boolean} True if a >= min and a <= max.
*/
function inRange(a, min, max) {
return min <= a && a <= max;
}
/**
* @param {!Array.<*>} array The array to check.
* @param {*} item The item to look for in the array.
* @return {boolean} True if the item appears in the array.
*/
function includes(array, item) {
return array.indexOf(item) !== -1;
}
var floor = Math.floor;
/**
* @param {*} o
* @return {Object}
*/
function ToDictionary(o) {
if (o === undefined) return {};
if (o === Object(o)) return o;
throw TypeError('Could not convert argument to dictionary');
}
/**
* @param {string} string Input string of UTF-16 code units.
* @return {!Array.<number>} Code points.
*/
function stringToCodePoints(string) {
// https://heycam.github.io/webidl/#dfn-obtain-unicode
// 1. Let S be the DOMString value.
var s = String(string);
// 2. Let n be the length of S.
var n = s.length;
// 3. Initialize i to 0.
var i = 0;
// 4. Initialize U to be an empty sequence of Unicode characters.
var u = [];
// 5. While i < n:
while (i < n) {
// 1. Let c be the code unit in S at index i.
var c = s.charCodeAt(i);
// 2. Depending on the value of c:
// c < 0xD800 or c > 0xDFFF
if (c < 0xD800 || c > 0xDFFF) {
// Append to U the Unicode character with code point c.
u.push(c);
}
// 0xDC00 ≤ c ≤ 0xDFFF
else if (0xDC00 <= c && c <= 0xDFFF) {
// Append to U a U+FFFD REPLACEMENT CHARACTER.
u.push(0xFFFD);
}
// 0xD800 ≤ c ≤ 0xDBFF
else if (0xD800 <= c && c <= 0xDBFF) {
// 1. If i = n−1, then append to U a U+FFFD REPLACEMENT
// CHARACTER.
if (i === n - 1) {
u.push(0xFFFD);
}
// 2. Otherwise, i < n−1:
else {
// 1. Let d be the code unit in S at index i+1.
var d = s.charCodeAt(i + 1);
// 2. If 0xDC00 ≤ d ≤ 0xDFFF, then:
if (0xDC00 <= d && d <= 0xDFFF) {
// 1. Let a be c & 0x3FF.
var a = c & 0x3FF;
// 2. Let b be d & 0x3FF.
var b = d & 0x3FF;
// 3. Append to U the Unicode character with code point
// 2^16+2^10*a+b.
u.push(0x10000 + (a << 10) + b);
// 4. Set i to i+1.
i += 1;
}
// 3. Otherwise, d < 0xDC00 or d > 0xDFFF. Append to U a
// U+FFFD REPLACEMENT CHARACTER.
else {
u.push(0xFFFD);
}
}
}
// 3. Set i to i+1.
i += 1;
}
// 6. Return U.
return u;
}
/**
* @param {!Array.<number>} code_points Array of code points.
* @return {string} string String of UTF-16 code units.
*/
function codePointsToString(code_points) {
var s = '';
for (var i = 0; i < code_points.length; ++i) {
var cp = code_points[i];
if (cp <= 0xFFFF) {
s += String.fromCharCode(cp);
} else {
cp -= 0x10000;
s += String.fromCharCode((cp >> 10) + 0xD800,
(cp & 0x3FF) + 0xDC00);
}
}
return s;
}
//
// Implementation of Encoding specification
// https://encoding.spec.whatwg.org/
//
//
// 4. Terminology
//
/**
* An ASCII byte is a byte in the range 0x00 to 0x7F, inclusive.
* @param {number} a The number to test.
* @return {boolean} True if a is in the range 0x00 to 0x7F, inclusive.
*/
function isASCIIByte(a) {
return 0x00 <= a && a <= 0x7F;
}
/**
* An ASCII code point is a code point in the range U+0000 to
* U+007F, inclusive.
*/
var isASCIICodePoint = isASCIIByte;
/**
* End-of-stream is a special token that signifies no more tokens
* are in the stream.
* @const
*/ var end_of_stream = -1;
/**
* A stream represents an ordered sequence of tokens.
*
* @constructor
* @param {!(Array.<number>|Uint8Array)} tokens Array of tokens that provide
* the stream.
*/
function Stream(tokens) {
/** @type {!Array.<number>} */
this.tokens = [].slice.call(tokens);
// Reversed as push/pop is more efficient than shift/unshift.
this.tokens.reverse();
}
Stream.prototype = {
/**
* @return {boolean} True if end-of-stream has been hit.
*/
endOfStream: function() {
return !this.tokens.length;
},
/**
* When a token is read from a stream, the first token in the
* stream must be returned and subsequently removed, and
* end-of-stream must be returned otherwise.
*
* @return {number} Get the next token from the stream, or
* end_of_stream.
*/
read: function() {
if (!this.tokens.length)
return end_of_stream;
return this.tokens.pop();
},
/**
* When one or more tokens are prepended to a stream, those tokens
* must be inserted, in given order, before the first token in the
* stream.
*
* @param {(number|!Array.<number>)} token The token(s) to prepend to the
* stream.
*/
prepend: function(token) {
if (Array.isArray(token)) {
var tokens = /**@type {!Array.<number>}*/(token);
while (tokens.length)
this.tokens.push(tokens.pop());
} else {
this.tokens.push(token);
}
},
/**
* When one or more tokens are pushed to a stream, those tokens
* must be inserted, in given order, after the last token in the
* stream.
*
* @param {(number|!Array.<number>)} token The tokens(s) to push to the
* stream.
*/
push: function(token) {
if (Array.isArray(token)) {
var tokens = /**@type {!Array.<number>}*/(token);
while (tokens.length)
this.tokens.unshift(tokens.shift());
} else {
this.tokens.unshift(token);
}
}
};
//
// 5. Encodings
//
// 5.1 Encoders and decoders
/** @const */
var finished = -1;
/**
* @param {boolean} fatal If true, decoding errors raise an exception.
* @param {number=} opt_code_point Override the standard fallback code point.
* @return {number} The code point to insert on a decoding error.
*/
function decoderError(fatal, opt_code_point) {
if (fatal)
throw TypeError('Decoder error');
return opt_code_point || 0xFFFD;
}
/**
* @param {number} code_point The code point that could not be encoded.
* @return {number} Always throws, no value is actually returned.
*/
function encoderError(code_point) {
throw TypeError('The code point ' + code_point + ' could not be encoded.');
}
/** @interface */
function Decoder() {}
Decoder.prototype = {
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point, or |finished|.
*/
handler: function(stream, bite) {}
};
/** @interface */
function Encoder() {}
Encoder.prototype = {
/**
* @param {Stream} stream The stream of code points being encoded.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit, or |finished|.
*/
handler: function(stream, code_point) {}
};
// 5.2 Names and labels
// TODO: Define @typedef for Encoding: {name:string,labels:Array.<string>}
// https://github.com/google/closure-compiler/issues/247
/**
* @param {string} label The encoding label.
* @return {?{name:string,labels:Array.<string>}}
*/
function getEncoding(label) {
// 1. Remove any leading and trailing ASCII whitespace from label.
label = String(label).trim().toLowerCase();
// 2. If label is an ASCII case-insensitive match for any of the
// labels listed in the table below, return the corresponding
// encoding, and failure otherwise.
if (Object.prototype.hasOwnProperty.call(label_to_encoding, label)) {
return label_to_encoding[label];
}
return null;
}
/**
* Encodings table: https://encoding.spec.whatwg.org/encodings.json
* @const
* @type {!Array.<{
* heading: string,
* encodings: Array.<{name:string,labels:Array.<string>}>
* }>}
*/
var encodings = [
{
"encodings": [
{
"labels": [
"unicode-1-1-utf-8",
"utf-8",
"utf8"
],
"name": "UTF-8"
}
],
"heading": "The Encoding"
},
{
"encodings": [
{
"labels": [
"866",
"cp866",
"csibm866",
"ibm866"
],
"name": "IBM866"
},
{
"labels": [
"csisolatin2",
"iso-8859-2",
"iso-ir-101",
"iso8859-2",
"iso88592",
"iso_8859-2",
"iso_8859-2:1987",
"l2",
"latin2"
],
"name": "ISO-8859-2"
},
{
"labels": [
"csisolatin3",
"iso-8859-3",
"iso-ir-109",
"iso8859-3",
"iso88593",
"iso_8859-3",
"iso_8859-3:1988",
"l3",
"latin3"
],
"name": "ISO-8859-3"
},
{
"labels": [
"csisolatin4",
"iso-8859-4",
"iso-ir-110",
"iso8859-4",
"iso88594",
"iso_8859-4",
"iso_8859-4:1988",
"l4",
"latin4"
],
"name": "ISO-8859-4"
},
{
"labels": [
"csisolatincyrillic",
"cyrillic",
"iso-8859-5",
"iso-ir-144",
"iso8859-5",
"iso88595",
"iso_8859-5",
"iso_8859-5:1988"
],
"name": "ISO-8859-5"
},
{
"labels": [
"arabic",
"asmo-708",
"csiso88596e",
"csiso88596i",
"csisolatinarabic",
"ecma-114",
"iso-8859-6",
"iso-8859-6-e",
"iso-8859-6-i",
"iso-ir-127",
"iso8859-6",
"iso88596",
"iso_8859-6",
"iso_8859-6:1987"
],
"name": "ISO-8859-6"
},
{
"labels": [
"csisolatingreek",
"ecma-118",
"elot_928",
"greek",
"greek8",
"iso-8859-7",
"iso-ir-126",
"iso8859-7",
"iso88597",
"iso_8859-7",
"iso_8859-7:1987",
"sun_eu_greek"
],
"name": "ISO-8859-7"
},
{
"labels": [
"csiso88598e",
"csisolatinhebrew",
"hebrew",
"iso-8859-8",
"iso-8859-8-e",
"iso-ir-138",
"iso8859-8",
"iso88598",
"iso_8859-8",
"iso_8859-8:1988",
"visual"
],
"name": "ISO-8859-8"
},
{
"labels": [
"csiso88598i",
"iso-8859-8-i",
"logical"
],
"name": "ISO-8859-8-I"
},
{
"labels": [
"csisolatin6",
"iso-8859-10",
"iso-ir-157",
"iso8859-10",
"iso885910",
"l6",
"latin6"
],
"name": "ISO-8859-10"
},
{
"labels": [
"iso-8859-13",
"iso8859-13",
"iso885913"
],
"name": "ISO-8859-13"
},
{
"labels": [
"iso-8859-14",
"iso8859-14",
"iso885914"
],
"name": "ISO-8859-14"
},
{
"labels": [
"csisolatin9",
"iso-8859-15",
"iso8859-15",
"iso885915",
"iso_8859-15",
"l9"
],
"name": "ISO-8859-15"
},
{
"labels": [
"iso-8859-16"
],
"name": "ISO-8859-16"
},
{
"labels": [
"cskoi8r",
"koi",
"koi8",
"koi8-r",
"koi8_r"
],
"name": "KOI8-R"
},
{
"labels": [
"koi8-ru",
"koi8-u"
],
"name": "KOI8-U"
},
{
"labels": [
"csmacintosh",
"mac",
"macintosh",
"x-mac-roman"
],
"name": "macintosh"
},
{
"labels": [
"dos-874",
"iso-8859-11",
"iso8859-11",
"iso885911",
"tis-620",
"windows-874"
],
"name": "windows-874"
},
{
"labels": [
"cp1250",
"windows-1250",
"x-cp1250"
],
"name": "windows-1250"
},
{
"labels": [
"cp1251",
"windows-1251",
"x-cp1251"
],
"name": "windows-1251"
},
{
"labels": [
"ansi_x3.4-1968",
"ascii",
"cp1252",
"cp819",
"csisolatin1",
"ibm819",
"iso-8859-1",
"iso-ir-100",
"iso8859-1",
"iso88591",
"iso_8859-1",
"iso_8859-1:1987",
"l1",
"latin1",
"us-ascii",
"windows-1252",
"x-cp1252"
],
"name": "windows-1252"
},
{
"labels": [
"cp1253",
"windows-1253",
"x-cp1253"
],
"name": "windows-1253"
},
{
"labels": [
"cp1254",
"csisolatin5",
"iso-8859-9",
"iso-ir-148",
"iso8859-9",
"iso88599",
"iso_8859-9",
"iso_8859-9:1989",
"l5",
"latin5",
"windows-1254",
"x-cp1254"
],
"name": "windows-1254"
},
{
"labels": [
"cp1255",
"windows-1255",
"x-cp1255"
],
"name": "windows-1255"
},
{
"labels": [
"cp1256",
"windows-1256",
"x-cp1256"
],
"name": "windows-1256"
},
{
"labels": [
"cp1257",
"windows-1257",
"x-cp1257"
],
"name": "windows-1257"
},
{
"labels": [
"cp1258",
"windows-1258",
"x-cp1258"
],
"name": "windows-1258"
},
{
"labels": [
"x-mac-cyrillic",
"x-mac-ukrainian"
],
"name": "x-mac-cyrillic"
}
],
"heading": "Legacy single-byte encodings"
},
{
"encodings": [
{
"labels": [
"chinese",
"csgb2312",
"csiso58gb231280",
"gb2312",
"gb_2312",
"gb_2312-80",
"gbk",
"iso-ir-58",
"x-gbk"
],
"name": "GBK"
},
{
"labels": [
"gb18030"
],
"name": "gb18030"
}
],
"heading": "Legacy multi-byte Chinese (simplified) encodings"
},
{
"encodings": [
{
"labels": [
"big5",
"big5-hkscs",
"cn-big5",
"csbig5",
"x-x-big5"
],
"name": "Big5"
}
],
"heading": "Legacy multi-byte Chinese (traditional) encodings"
},
{
"encodings": [
{
"labels": [
"cseucpkdfmtjapanese",
"euc-jp",
"x-euc-jp"
],
"name": "EUC-JP"
},
{
"labels": [
"csiso2022jp",
"iso-2022-jp"
],
"name": "ISO-2022-JP"
},
{
"labels": [
"csshiftjis",
"ms932",
"ms_kanji",
"shift-jis",
"shift_jis",
"sjis",
"windows-31j",
"x-sjis"
],
"name": "Shift_JIS"
}
],
"heading": "Legacy multi-byte Japanese encodings"
},
{
"encodings": [
{
"labels": [
"cseuckr",
"csksc56011987",
"euc-kr",
"iso-ir-149",
"korean",
"ks_c_5601-1987",
"ks_c_5601-1989",
"ksc5601",
"ksc_5601",
"windows-949"
],
"name": "EUC-KR"
}
],
"heading": "Legacy multi-byte Korean encodings"
},
{
"encodings": [
{
"labels": [
"csiso2022kr",
"hz-gb-2312",
"iso-2022-cn",
"iso-2022-cn-ext",
"iso-2022-kr"
],
"name": "replacement"
},
{
"labels": [
"utf-16be"
],
"name": "UTF-16BE"
},
{
"labels": [
"utf-16",
"utf-16le"
],
"name": "UTF-16LE"
},
{
"labels": [
"x-user-defined"
],
"name": "x-user-defined"
}
],
"heading": "Legacy miscellaneous encodings"
}
];
// Label to encoding registry.
/** @type {Object.<string,{name:string,labels:Array.<string>}>} */
var label_to_encoding = {};
encodings.forEach(function(category) {
category.encodings.forEach(function(encoding) {
encoding.labels.forEach(function(label) {
label_to_encoding[label] = encoding;
});
});
});
// Registry of of encoder/decoder factories, by encoding name.
/** @type {Object.<string, function({fatal:boolean}): Encoder>} */
var encoders = {};
/** @type {Object.<string, function({fatal:boolean}): Decoder>} */
var decoders = {};
//
// 6. Indexes
//
/**
* @param {number} pointer The |pointer| to search for.
* @param {(!Array.<?number>|undefined)} index The |index| to search within.
* @return {?number} The code point corresponding to |pointer| in |index|,
* or null if |code point| is not in |index|.
*/
function indexCodePointFor(pointer, index) {
if (!index) return null;
return index[pointer] || null;
}
/**
* @param {number} code_point The |code point| to search for.
* @param {!Array.<?number>} index The |index| to search within.
* @return {?number} The first pointer corresponding to |code point| in
* |index|, or null if |code point| is not in |index|.
*/
function indexPointerFor(code_point, index) {
var pointer = index.indexOf(code_point);
return pointer === -1 ? null : pointer;
}
/**
* @param {string} name Name of the index.
* @return {(!Array.<number>|!Array.<Array.<number>>)}
* */
function index(name) {
if (!('encoding-indexes' in global)) {
throw Error("Indexes missing." +
" Did you forget to include encoding-indexes.js first?");
}
return global['encoding-indexes'][name];
}
/**
* @param {number} pointer The |pointer| to search for in the gb18030 index.
* @return {?number} The code point corresponding to |pointer| in |index|,
* or null if |code point| is not in the gb18030 index.
*/
function indexGB18030RangesCodePointFor(pointer) {
// 1. If pointer is greater than 39419 and less than 189000, or
// pointer is greater than 1237575, return null.
if ((pointer > 39419 && pointer < 189000) || (pointer > 1237575))
return null;
// 2. If pointer is 7457, return code point U+E7C7.
if (pointer === 7457) return 0xE7C7;
// 3. Let offset be the last pointer in index gb18030 ranges that
// is equal to or less than pointer and let code point offset be
// its corresponding code point.
var offset = 0;
var code_point_offset = 0;
var idx = index('gb18030-ranges');
var i;
for (i = 0; i < idx.length; ++i) {
/** @type {!Array.<number>} */
var entry = idx[i];
if (entry[0] <= pointer) {
offset = entry[0];
code_point_offset = entry[1];
} else {
break;
}
}
// 4. Return a code point whose value is code point offset +
// pointer − offset.
return code_point_offset + pointer - offset;
}
/**
* @param {number} code_point The |code point| to locate in the gb18030 index.
* @return {number} The first pointer corresponding to |code point| in the
* gb18030 index.
*/
function indexGB18030RangesPointerFor(code_point) {
// 1. If code point is U+E7C7, return pointer 7457.
if (code_point === 0xE7C7) return 7457;
// 2. Let offset be the last code point in index gb18030 ranges
// that is equal to or less than code point and let pointer offset
// be its corresponding pointer.
var offset = 0;
var pointer_offset = 0;
var idx = index('gb18030-ranges');
var i;
for (i = 0; i < idx.length; ++i) {
/** @type {!Array.<number>} */
var entry = idx[i];
if (entry[1] <= code_point) {
offset = entry[1];
pointer_offset = entry[0];
} else {
break;
}
}
// 3. Return a pointer whose value is pointer offset + code point
// − offset.
return pointer_offset + code_point - offset;
}
/**
* @param {number} code_point The |code_point| to search for in the Shift_JIS
* index.
* @return {?number} The code point corresponding to |pointer| in |index|,
* or null if |code point| is not in the Shift_JIS index.
*/
function indexShiftJISPointerFor(code_point) {
// 1. Let index be index jis0208 excluding all entries whose
// pointer is in the range 8272 to 8835, inclusive.
shift_jis_index = shift_jis_index ||
index('jis0208').map(function(code_point, pointer) {
return inRange(pointer, 8272, 8835) ? null : code_point;
});
var index_ = shift_jis_index;
// 2. Return the index pointer for code point in index.
return index_.indexOf(code_point);
}
var shift_jis_index;
/**
* @param {number} code_point The |code_point| to search for in the big5
* index.
* @return {?number} The code point corresponding to |pointer| in |index|,
* or null if |code point| is not in the big5 index.
*/
function indexBig5PointerFor(code_point) {
// 1. Let index be index Big5 excluding all entries whose pointer
big5_index_no_hkscs = big5_index_no_hkscs ||
index('big5').map(function(code_point, pointer) {
return (pointer < (0xA1 - 0x81) * 157) ? null : code_point;
});
var index_ = big5_index_no_hkscs;
// 2. If code point is U+2550, U+255E, U+2561, U+256A, U+5341, or
// U+5345, return the last pointer corresponding to code point in
// index.
if (code_point === 0x2550 || code_point === 0x255E ||
code_point === 0x2561 || code_point === 0x256A ||
code_point === 0x5341 || code_point === 0x5345) {
return index_.lastIndexOf(code_point);
}
// 3. Return the index pointer for code point in index.
return indexPointerFor(code_point, index_);
}
var big5_index_no_hkscs;
//
// 8. API
//
/** @const */ var DEFAULT_ENCODING = 'utf-8';
// 8.1 Interface TextDecoder
/**
* @constructor
* @param {string=} label The label of the encoding;
* defaults to 'utf-8'.
* @param {Object=} options
*/
function TextDecoder(label, options) {
// Web IDL conventions
if (!(this instanceof TextDecoder))
throw TypeError('Called as a function. Did you forget \'new\'?');
label = label !== undefined ? String(label) : DEFAULT_ENCODING;
options = ToDictionary(options);
// A TextDecoder object has an associated encoding, decoder,
// stream, ignore BOM flag (initially unset), BOM seen flag
// (initially unset), error mode (initially replacement), and do
// not flush flag (initially unset).
/** @private */
this._encoding = null;
/** @private @type {?Decoder} */
this._decoder = null;
/** @private @type {boolean} */
this._ignoreBOM = false;
/** @private @type {boolean} */
this._BOMseen = false;
/** @private @type {string} */
this._error_mode = 'replacement';
/** @private @type {boolean} */
this._do_not_flush = false;
// 1. Let encoding be the result of getting an encoding from
// label.
var encoding = getEncoding(label);
// 2. If encoding is failure or replacement, throw a RangeError.
if (encoding === null || encoding.name === 'replacement')
throw RangeError('Unknown encoding: ' + label);
if (!decoders[encoding.name]) {
throw Error('Decoder not present.' +
' Did you forget to include encoding-indexes.js first?');
}
// 3. Let dec be a new TextDecoder object.
var dec = this;
// 4. Set dec's encoding to encoding.
dec._encoding = encoding;
// 5. If options's fatal member is true, set dec's error mode to
// fatal.
if (Boolean(options['fatal']))
dec._error_mode = 'fatal';
// 6. If options's ignoreBOM member is true, set dec's ignore BOM
// flag.
if (Boolean(options['ignoreBOM']))
dec._ignoreBOM = true;
// For pre-ES5 runtimes:
if (!Object.defineProperty) {
this.encoding = dec._encoding.name.toLowerCase();
this.fatal = dec._error_mode === 'fatal';
this.ignoreBOM = dec._ignoreBOM;
}
// 7. Return dec.
return dec;
}
if (Object.defineProperty) {
// The encoding attribute's getter must return encoding's name.
Object.defineProperty(TextDecoder.prototype, 'encoding', {
/** @this {TextDecoder} */
get: function() { return this._encoding.name.toLowerCase(); }
});
// The fatal attribute's getter must return true if error mode
// is fatal, and false otherwise.
Object.defineProperty(TextDecoder.prototype, 'fatal', {
/** @this {TextDecoder} */
get: function() { return this._error_mode === 'fatal'; }
});
// The ignoreBOM attribute's getter must return true if ignore
// BOM flag is set, and false otherwise.
Object.defineProperty(TextDecoder.prototype, 'ignoreBOM', {
/** @this {TextDecoder} */
get: function() { return this._ignoreBOM; }
});
}
/**
* @param {BufferSource=} input The buffer of bytes to decode.
* @param {Object=} options
* @return {string} The decoded string.
*/
TextDecoder.prototype.decode = function decode(input, options) {
var bytes;
if (typeof input === 'object' && input instanceof ArrayBuffer) {
bytes = new Uint8Array(input);
} else if (typeof input === 'object' && 'buffer' in input &&
input.buffer instanceof ArrayBuffer) {
bytes = new Uint8Array(input.buffer,
input.byteOffset,
input.byteLength);
} else {
bytes = new Uint8Array(0);
}
options = ToDictionary(options);
// 1. If the do not flush flag is unset, set decoder to a new
// encoding's decoder, set stream to a new stream, and unset the
// BOM seen flag.
if (!this._do_not_flush) {
this._decoder = decoders[this._encoding.name]({
fatal: this._error_mode === 'fatal'});
this._BOMseen = false;
}
// 2. If options's stream is true, set the do not flush flag, and
// unset the do not flush flag otherwise.
this._do_not_flush = Boolean(options['stream']);
// 3. If input is given, push a copy of input to stream.
// TODO: Align with spec algorithm - maintain stream on instance.
var input_stream = new Stream(bytes);
// 4. Let output be a new stream.
var output = [];
/** @type {?(number|!Array.<number>)} */
var result;
// 5. While true:
while (true) {
// 1. Let token be the result of reading from stream.
var token = input_stream.read();
// 2. If token is end-of-stream and the do not flush flag is
// set, return output, serialized.
// TODO: Align with spec algorithm.
if (token === end_of_stream)
break;
// 3. Otherwise, run these subsubsteps:
// 1. Let result be the result of processing token for decoder,
// stream, output, and error mode.
result = this._decoder.handler(input_stream, token);
// 2. If result is finished, return output, serialized.
if (result === finished)
break;
if (result !== null) {
if (Array.isArray(result))
output.push.apply(output, /**@type {!Array.<number>}*/(result));
else
output.push(result);
}
// 3. Otherwise, if result is error, throw a TypeError.
// (Thrown in handler)
// 4. Otherwise, do nothing.
}
// TODO: Align with spec algorithm.
if (!this._do_not_flush) {
do {
result = this._decoder.handler(input_stream, input_stream.read());
if (result === finished)
break;
if (result === null)
continue;
if (Array.isArray(result))
output.push.apply(output, /**@type {!Array.<number>}*/(result));
else
output.push(result);
} while (!input_stream.endOfStream());
this._decoder = null;
}
// A TextDecoder object also has an associated serialize stream
// algorithm...
/**
* @param {!Array.<number>} stream
* @return {string}
* @this {TextDecoder}
*/
function serializeStream(stream) {
// 1. Let token be the result of reading from stream.
// (Done in-place on array, rather than as a stream)
// 2. If encoding is UTF-8, UTF-16BE, or UTF-16LE, and ignore
// BOM flag and BOM seen flag are unset, run these subsubsteps:
if (includes(['UTF-8', 'UTF-16LE', 'UTF-16BE'], this._encoding.name) &&
!this._ignoreBOM && !this._BOMseen) {
if (stream.length > 0 && stream[0] === 0xFEFF) {
// 1. If token is U+FEFF, set BOM seen flag.
this._BOMseen = true;
stream.shift();
} else if (stream.length > 0) {
// 2. Otherwise, if token is not end-of-stream, set BOM seen
// flag and append token to stream.
this._BOMseen = true;
} else {
// 3. Otherwise, if token is not end-of-stream, append token
// to output.
// (no-op)
}
}
// 4. Otherwise, return output.
return codePointsToString(stream);
}
return serializeStream.call(this, output);
};
// 8.2 Interface TextEncoder
/**
* @constructor
* @param {string=} label The label of the encoding. NONSTANDARD.
* @param {Object=} options NONSTANDARD.
*/
function TextEncoder(label, options) {
// Web IDL conventions
if (!(this instanceof TextEncoder))
throw TypeError('Called as a function. Did you forget \'new\'?');
options = ToDictionary(options);
// A TextEncoder object has an associated encoding and encoder.
/** @private */
this._encoding = null;
/** @private @type {?Encoder} */
this._encoder = null;
// Non-standard
/** @private @type {boolean} */
this._do_not_flush = false;
/** @private @type {string} */
this._fatal = Boolean(options['fatal']) ? 'fatal' : 'replacement';
// 1. Let enc be a new TextEncoder object.
var enc = this;
// 2. Set enc's encoding to UTF-8's encoder.
if (Boolean(options['NONSTANDARD_allowLegacyEncoding'])) {
// NONSTANDARD behavior.
label = label !== undefined ? String(label) : DEFAULT_ENCODING;
var encoding = getEncoding(label);
if (encoding === null || encoding.name === 'replacement')
throw RangeError('Unknown encoding: ' + label);
if (!encoders[encoding.name]) {
throw Error('Encoder not present.' +
' Did you forget to include encoding-indexes.js first?');
}
enc._encoding = encoding;
} else {
// Standard behavior.
enc._encoding = getEncoding('utf-8');
if (label !== undefined && 'console' in global) {
console.warn('TextEncoder constructor called with encoding label, '
+ 'which is ignored.');
}
}
// For pre-ES5 runtimes:
if (!Object.defineProperty)
this.encoding = enc._encoding.name.toLowerCase();
// 3. Return enc.
return enc;
}
if (Object.defineProperty) {
// The encoding attribute's getter must return encoding's name.
Object.defineProperty(TextEncoder.prototype, 'encoding', {
/** @this {TextEncoder} */
get: function() { return this._encoding.name.toLowerCase(); }
});
}
/**
* @param {string=} opt_string The string to encode.
* @param {Object=} options
* @return {!Uint8Array} Encoded bytes, as a Uint8Array.
*/
TextEncoder.prototype.encode = function encode(opt_string, options) {
opt_string = opt_string === undefined ? '' : String(opt_string);
options = ToDictionary(options);
// NOTE: This option is nonstandard. None of the encodings
// permitted for encoding (i.e. UTF-8, UTF-16) are stateful when
// the input is a USVString so streaming is not necessary.
if (!this._do_not_flush)
this._encoder = encoders[this._encoding.name]({
fatal: this._fatal === 'fatal'});
this._do_not_flush = Boolean(options['stream']);
// 1. Convert input to a stream.
var input = new Stream(stringToCodePoints(opt_string));
// 2. Let output be a new stream
var output = [];
/** @type {?(number|!Array.<number>)} */
var result;
// 3. While true, run these substeps:
while (true) {
// 1. Let token be the result of reading from input.
var token = input.read();
if (token === end_of_stream)
break;
// 2. Let result be the result of processing token for encoder,
// input, output.
result = this._encoder.handler(input, token);
if (result === finished)
break;
if (Array.isArray(result))
output.push.apply(output, /**@type {!Array.<number>}*/(result));
else
output.push(result);
}
// TODO: Align with spec algorithm.
if (!this._do_not_flush) {
while (true) {
result = this._encoder.handler(input, input.read());
if (result === finished)
break;
if (Array.isArray(result))
output.push.apply(output, /**@type {!Array.<number>}*/(result));
else
output.push(result);
}
this._encoder = null;
}
// 3. If result is finished, convert output into a byte sequence,
// and then return a Uint8Array object wrapping an ArrayBuffer
// containing output.
return new Uint8Array(output);
};
//
// 9. The encoding
//
// 9.1 utf-8
// 9.1.1 utf-8 decoder
/**
* @constructor
* @implements {Decoder}
* @param {{fatal: boolean}} options
*/
function UTF8Decoder(options) {
var fatal = options.fatal;
// utf-8's decoder's has an associated utf-8 code point, utf-8
// bytes seen, and utf-8 bytes needed (all initially 0), a utf-8
// lower boundary (initially 0x80), and a utf-8 upper boundary
// (initially 0xBF).
var /** @type {number} */ utf8_code_point = 0,
/** @type {number} */ utf8_bytes_seen = 0,
/** @type {number} */ utf8_bytes_needed = 0,
/** @type {number} */ utf8_lower_boundary = 0x80,
/** @type {number} */ utf8_upper_boundary = 0xBF;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream and utf-8 bytes needed is not 0,
// set utf-8 bytes needed to 0 and return error.
if (bite === end_of_stream && utf8_bytes_needed !== 0) {
utf8_bytes_needed = 0;
return decoderError(fatal);
}
// 2. If byte is end-of-stream, return finished.
if (bite === end_of_stream)
return finished;
// 3. If utf-8 bytes needed is 0, based on byte:
if (utf8_bytes_needed === 0) {
// 0x00 to 0x7F
if (inRange(bite, 0x00, 0x7F)) {
// Return a code point whose value is byte.
return bite;
}
// 0xC2 to 0xDF
else if (inRange(bite, 0xC2, 0xDF)) {
// 1. Set utf-8 bytes needed to 1.
utf8_bytes_needed = 1;
// 2. Set UTF-8 code point to byte & 0x1F.
utf8_code_point = bite & 0x1F;
}
// 0xE0 to 0xEF
else if (inRange(bite, 0xE0, 0xEF)) {
// 1. If byte is 0xE0, set utf-8 lower boundary to 0xA0.
if (bite === 0xE0)
utf8_lower_boundary = 0xA0;
// 2. If byte is 0xED, set utf-8 upper boundary to 0x9F.
if (bite === 0xED)
utf8_upper_boundary = 0x9F;
// 3. Set utf-8 bytes needed to 2.
utf8_bytes_needed = 2;
// 4. Set UTF-8 code point to byte & 0xF.
utf8_code_point = bite & 0xF;
}
// 0xF0 to 0xF4
else if (inRange(bite, 0xF0, 0xF4)) {
// 1. If byte is 0xF0, set utf-8 lower boundary to 0x90.
if (bite === 0xF0)
utf8_lower_boundary = 0x90;
// 2. If byte is 0xF4, set utf-8 upper boundary to 0x8F.
if (bite === 0xF4)
utf8_upper_boundary = 0x8F;
// 3. Set utf-8 bytes needed to 3.
utf8_bytes_needed = 3;
// 4. Set UTF-8 code point to byte & 0x7.
utf8_code_point = bite & 0x7;
}
// Otherwise
else {
// Return error.
return decoderError(fatal);
}
// Return continue.
return null;
}
// 4. If byte is not in the range utf-8 lower boundary to utf-8
// upper boundary, inclusive, run these substeps:
if (!inRange(bite, utf8_lower_boundary, utf8_upper_boundary)) {
// 1. Set utf-8 code point, utf-8 bytes needed, and utf-8
// bytes seen to 0, set utf-8 lower boundary to 0x80, and set
// utf-8 upper boundary to 0xBF.
utf8_code_point = utf8_bytes_needed = utf8_bytes_seen = 0;
utf8_lower_boundary = 0x80;
utf8_upper_boundary = 0xBF;
// 2. Prepend byte to stream.
stream.prepend(bite);
// 3. Return error.
return decoderError(fatal);
}
// 5. Set utf-8 lower boundary to 0x80 and utf-8 upper boundary
// to 0xBF.
utf8_lower_boundary = 0x80;
utf8_upper_boundary = 0xBF;
// 6. Set UTF-8 code point to (UTF-8 code point << 6) | (byte &
// 0x3F)
utf8_code_point = (utf8_code_point << 6) | (bite & 0x3F);
// 7. Increase utf-8 bytes seen by one.
utf8_bytes_seen += 1;
// 8. If utf-8 bytes seen is not equal to utf-8 bytes needed,
// continue.
if (utf8_bytes_seen !== utf8_bytes_needed)
return null;
// 9. Let code point be utf-8 code point.
var code_point = utf8_code_point;
// 10. Set utf-8 code point, utf-8 bytes needed, and utf-8 bytes
// seen to 0.
utf8_code_point = utf8_bytes_needed = utf8_bytes_seen = 0;
// 11. Return a code point whose value is code point.
return code_point;
};
}
// 9.1.2 utf-8 encoder
/**
* @constructor
* @implements {Encoder}
* @param {{fatal: boolean}} options
*/
function UTF8Encoder(options) {
var fatal = options.fatal;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is an ASCII code point, return a byte whose
// value is code point.
if (isASCIICodePoint(code_point))
return code_point;
// 3. Set count and offset based on the range code point is in:
var count, offset;
// U+0080 to U+07FF, inclusive:
if (inRange(code_point, 0x0080, 0x07FF)) {
// 1 and 0xC0
count = 1;
offset = 0xC0;
}
// U+0800 to U+FFFF, inclusive:
else if (inRange(code_point, 0x0800, 0xFFFF)) {
// 2 and 0xE0
count = 2;
offset = 0xE0;
}
// U+10000 to U+10FFFF, inclusive:
else if (inRange(code_point, 0x10000, 0x10FFFF)) {
// 3 and 0xF0
count = 3;
offset = 0xF0;
}
// 4. Let bytes be a byte sequence whose first byte is (code
// point >> (6 × count)) + offset.
var bytes = [(code_point >> (6 * count)) + offset];
// 5. Run these substeps while count is greater than 0:
while (count > 0) {
// 1. Set temp to code point >> (6 × (count − 1)).
var temp = code_point >> (6 * (count - 1));
// 2. Append to bytes 0x80 | (temp & 0x3F).
bytes.push(0x80 | (temp & 0x3F));
// 3. Decrease count by one.
count -= 1;
}
// 6. Return bytes bytes, in order.
return bytes;
};
}
/** @param {{fatal: boolean}} options */
encoders['UTF-8'] = function(options) {
return new UTF8Encoder(options);
};
/** @param {{fatal: boolean}} options */
decoders['UTF-8'] = function(options) {
return new UTF8Decoder(options);
};
//
// 10. Legacy single-byte encodings
//
// 10.1 single-byte decoder
/**
* @constructor
* @implements {Decoder}
* @param {!Array.<number>} index The encoding index.
* @param {{fatal: boolean}} options
*/
function SingleByteDecoder(index, options) {
var fatal = options.fatal;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream, return finished.
if (bite === end_of_stream)
return finished;
// 2. If byte is an ASCII byte, return a code point whose value
// is byte.
if (isASCIIByte(bite))
return bite;
// 3. Let code point be the index code point for byte − 0x80 in
// index single-byte.
var code_point = index[bite - 0x80];
// 4. If code point is null, return error.
if (code_point === null)
return decoderError(fatal);
// 5. Return a code point whose value is code point.
return code_point;
};
}
// 10.2 single-byte encoder
/**
* @constructor
* @implements {Encoder}
* @param {!Array.<?number>} index The encoding index.
* @param {{fatal: boolean}} options
*/
function SingleByteEncoder(index, options) {
var fatal = options.fatal;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is an ASCII code point, return a byte whose
// value is code point.
if (isASCIICodePoint(code_point))
return code_point;
// 3. Let pointer be the index pointer for code point in index
// single-byte.
var pointer = indexPointerFor(code_point, index);
// 4. If pointer is null, return error with code point.
if (pointer === null)
encoderError(code_point);
// 5. Return a byte whose value is pointer + 0x80.
return pointer + 0x80;
};
}
(function() {
if (!('encoding-indexes' in global))
return;
encodings.forEach(function(category) {
if (category.heading !== 'Legacy single-byte encodings')
return;
category.encodings.forEach(function(encoding) {
var name = encoding.name;
var idx = index(name.toLowerCase());
/** @param {{fatal: boolean}} options */
decoders[name] = function(options) {
return new SingleByteDecoder(idx, options);
};
/** @param {{fatal: boolean}} options */
encoders[name] = function(options) {
return new SingleByteEncoder(idx, options);
};
});
});
}());
//
// 11. Legacy multi-byte Chinese (simplified) encodings
//
// 11.1 gbk
// 11.1.1 gbk decoder
// gbk's decoder is gb18030's decoder.
/** @param {{fatal: boolean}} options */
decoders['GBK'] = function(options) {
return new GB18030Decoder(options);
};
// 11.1.2 gbk encoder
// gbk's encoder is gb18030's encoder with its gbk flag set.
/** @param {{fatal: boolean}} options */
encoders['GBK'] = function(options) {
return new GB18030Encoder(options, true);
};
// 11.2 gb18030
// 11.2.1 gb18030 decoder
/**
* @constructor
* @implements {Decoder}
* @param {{fatal: boolean}} options
*/
function GB18030Decoder(options) {
var fatal = options.fatal;
// gb18030's decoder has an associated gb18030 first, gb18030
// second, and gb18030 third (all initially 0x00).
var /** @type {number} */ gb18030_first = 0x00,
/** @type {number} */ gb18030_second = 0x00,
/** @type {number} */ gb18030_third = 0x00;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream and gb18030 first, gb18030
// second, and gb18030 third are 0x00, return finished.
if (bite === end_of_stream && gb18030_first === 0x00 &&
gb18030_second === 0x00 && gb18030_third === 0x00) {
return finished;
}
// 2. If byte is end-of-stream, and gb18030 first, gb18030
// second, or gb18030 third is not 0x00, set gb18030 first,
// gb18030 second, and gb18030 third to 0x00, and return error.
if (bite === end_of_stream &&
(gb18030_first !== 0x00 || gb18030_second !== 0x00 ||
gb18030_third !== 0x00)) {
gb18030_first = 0x00;
gb18030_second = 0x00;
gb18030_third = 0x00;
decoderError(fatal);
}
var code_point;
// 3. If gb18030 third is not 0x00, run these substeps:
if (gb18030_third !== 0x00) {
// 1. Let code point be null.
code_point = null;
// 2. If byte is in the range 0x30 to 0x39, inclusive, set
// code point to the index gb18030 ranges code point for
// (((gb18030 first − 0x81) × 10 + gb18030 second − 0x30) ×
// 126 + gb18030 third − 0x81) × 10 + byte − 0x30.
if (inRange(bite, 0x30, 0x39)) {
code_point = indexGB18030RangesCodePointFor(
(((gb18030_first - 0x81) * 10 + gb18030_second - 0x30) * 126 +
gb18030_third - 0x81) * 10 + bite - 0x30);
}
// 3. Let buffer be a byte sequence consisting of gb18030
// second, gb18030 third, and byte, in order.
var buffer = [gb18030_second, gb18030_third, bite];
// 4. Set gb18030 first, gb18030 second, and gb18030 third to
// 0x00.
gb18030_first = 0x00;
gb18030_second = 0x00;
gb18030_third = 0x00;
// 5. If code point is null, prepend buffer to stream and
// return error.
if (code_point === null) {
stream.prepend(buffer);
return decoderError(fatal);
}
// 6. Return a code point whose value is code point.
return code_point;
}
// 4. If gb18030 second is not 0x00, run these substeps:
if (gb18030_second !== 0x00) {
// 1. If byte is in the range 0x81 to 0xFE, inclusive, set
// gb18030 third to byte and return continue.
if (inRange(bite, 0x81, 0xFE)) {
gb18030_third = bite;
return null;
}
// 2. Prepend gb18030 second followed by byte to stream, set
// gb18030 first and gb18030 second to 0x00, and return error.
stream.prepend([gb18030_second, bite]);
gb18030_first = 0x00;
gb18030_second = 0x00;
return decoderError(fatal);
}
// 5. If gb18030 first is not 0x00, run these substeps:
if (gb18030_first !== 0x00) {
// 1. If byte is in the range 0x30 to 0x39, inclusive, set
// gb18030 second to byte and return continue.
if (inRange(bite, 0x30, 0x39)) {
gb18030_second = bite;
return null;
}
// 2. Let lead be gb18030 first, let pointer be null, and set
// gb18030 first to 0x00.
var lead = gb18030_first;
var pointer = null;
gb18030_first = 0x00;
// 3. Let offset be 0x40 if byte is less than 0x7F and 0x41
// otherwise.
var offset = bite < 0x7F ? 0x40 : 0x41;
// 4. If byte is in the range 0x40 to 0x7E, inclusive, or 0x80
// to 0xFE, inclusive, set pointer to (lead − 0x81) × 190 +
// (byte − offset).
if (inRange(bite, 0x40, 0x7E) || inRange(bite, 0x80, 0xFE))
pointer = (lead - 0x81) * 190 + (bite - offset);
// 5. Let code point be null if pointer is null and the index
// code point for pointer in index gb18030 otherwise.
code_point = pointer === null ? null :
indexCodePointFor(pointer, index('gb18030'));
// 6. If code point is null and byte is an ASCII byte, prepend
// byte to stream.
if (code_point === null && isASCIIByte(bite))
stream.prepend(bite);
// 7. If code point is null, return error.
if (code_point === null)
return decoderError(fatal);
// 8. Return a code point whose value is code point.
return code_point;
}
// 6. If byte is an ASCII byte, return a code point whose value
// is byte.
if (isASCIIByte(bite))
return bite;
// 7. If byte is 0x80, return code point U+20AC.
if (bite === 0x80)
return 0x20AC;
// 8. If byte is in the range 0x81 to 0xFE, inclusive, set
// gb18030 first to byte and return continue.
if (inRange(bite, 0x81, 0xFE)) {
gb18030_first = bite;
return null;
}
// 9. Return error.
return decoderError(fatal);
};
}
// 11.2.2 gb18030 encoder
/**
* @constructor
* @implements {Encoder}
* @param {{fatal: boolean}} options
* @param {boolean=} gbk_flag
*/
function GB18030Encoder(options, gbk_flag) {
var fatal = options.fatal;
// gb18030's decoder has an associated gbk flag (initially unset).
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is an ASCII code point, return a byte whose
// value is code point.
if (isASCIICodePoint(code_point))
return code_point;
// 3. If code point is U+E5E5, return error with code point.
if (code_point === 0xE5E5)
return encoderError(code_point);
// 4. If the gbk flag is set and code point is U+20AC, return
// byte 0x80.
if (gbk_flag && code_point === 0x20AC)
return 0x80;
// 5. Let pointer be the index pointer for code point in index
// gb18030.
var pointer = indexPointerFor(code_point, index('gb18030'));
// 6. If pointer is not null, run these substeps:
if (pointer !== null) {
// 1. Let lead be floor(pointer / 190) + 0x81.
var lead = floor(pointer / 190) + 0x81;
// 2. Let trail be pointer % 190.
var trail = pointer % 190;
// 3. Let offset be 0x40 if trail is less than 0x3F and 0x41 otherwise.
var offset = trail < 0x3F ? 0x40 : 0x41;
// 4. Return two bytes whose values are lead and trail + offset.
return [lead, trail + offset];
}
// 7. If gbk flag is set, return error with code point.
if (gbk_flag)
return encoderError(code_point);
// 8. Set pointer to the index gb18030 ranges pointer for code
// point.
pointer = indexGB18030RangesPointerFor(code_point);
// 9. Let byte1 be floor(pointer / 10 / 126 / 10).
var byte1 = floor(pointer / 10 / 126 / 10);
// 10. Set pointer to pointer − byte1 × 10 × 126 × 10.
pointer = pointer - byte1 * 10 * 126 * 10;
// 11. Let byte2 be floor(pointer / 10 / 126).
var byte2 = floor(pointer / 10 / 126);
// 12. Set pointer to pointer − byte2 × 10 × 126.
pointer = pointer - byte2 * 10 * 126;
// 13. Let byte3 be floor(pointer / 10).
var byte3 = floor(pointer / 10);
// 14. Let byte4 be pointer − byte3 × 10.
var byte4 = pointer - byte3 * 10;
// 15. Return four bytes whose values are byte1 + 0x81, byte2 +
// 0x30, byte3 + 0x81, byte4 + 0x30.
return [byte1 + 0x81,
byte2 + 0x30,
byte3 + 0x81,
byte4 + 0x30];
};
}
/** @param {{fatal: boolean}} options */
encoders['gb18030'] = function(options) {
return new GB18030Encoder(options);
};
/** @param {{fatal: boolean}} options */
decoders['gb18030'] = function(options) {
return new GB18030Decoder(options);
};
//
// 12. Legacy multi-byte Chinese (traditional) encodings
//
// 12.1 Big5
// 12.1.1 Big5 decoder
/**
* @constructor
* @implements {Decoder}
* @param {{fatal: boolean}} options
*/
function Big5Decoder(options) {
var fatal = options.fatal;
// Big5's decoder has an associated Big5 lead (initially 0x00).
var /** @type {number} */ Big5_lead = 0x00;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream and Big5 lead is not 0x00, set
// Big5 lead to 0x00 and return error.
if (bite === end_of_stream && Big5_lead !== 0x00) {
Big5_lead = 0x00;
return decoderError(fatal);
}
// 2. If byte is end-of-stream and Big5 lead is 0x00, return
// finished.
if (bite === end_of_stream && Big5_lead === 0x00)
return finished;
// 3. If Big5 lead is not 0x00, let lead be Big5 lead, let
// pointer be null, set Big5 lead to 0x00, and then run these
// substeps:
if (Big5_lead !== 0x00) {
var lead = Big5_lead;
var pointer = null;
Big5_lead = 0x00;
// 1. Let offset be 0x40 if byte is less than 0x7F and 0x62
// otherwise.
var offset = bite < 0x7F ? 0x40 : 0x62;
// 2. If byte is in the range 0x40 to 0x7E, inclusive, or 0xA1
// to 0xFE, inclusive, set pointer to (lead − 0x81) × 157 +
// (byte − offset).
if (inRange(bite, 0x40, 0x7E) || inRange(bite, 0xA1, 0xFE))
pointer = (lead - 0x81) * 157 + (bite - offset);
// 3. If there is a row in the table below whose first column
// is pointer, return the two code points listed in its second
// column
// Pointer | Code points
// --------+--------------
// 1133 | U+00CA U+0304
// 1135 | U+00CA U+030C
// 1164 | U+00EA U+0304
// 1166 | U+00EA U+030C
switch (pointer) {
case 1133: return [0x00CA, 0x0304];
case 1135: return [0x00CA, 0x030C];
case 1164: return [0x00EA, 0x0304];
case 1166: return [0x00EA, 0x030C];
}
// 4. Let code point be null if pointer is null and the index
// code point for pointer in index Big5 otherwise.
var code_point = (pointer === null) ? null :
indexCodePointFor(pointer, index('big5'));
// 5. If code point is null and byte is an ASCII byte, prepend
// byte to stream.
if (code_point === null && isASCIIByte(bite))
stream.prepend(bite);
// 6. If code point is null, return error.
if (code_point === null)
return decoderError(fatal);
// 7. Return a code point whose value is code point.
return code_point;
}
// 4. If byte is an ASCII byte, return a code point whose value
// is byte.
if (isASCIIByte(bite))
return bite;
// 5. If byte is in the range 0x81 to 0xFE, inclusive, set Big5
// lead to byte and return continue.
if (inRange(bite, 0x81, 0xFE)) {
Big5_lead = bite;
return null;
}
// 6. Return error.
return decoderError(fatal);
};
}
// 12.1.2 Big5 encoder
/**
* @constructor
* @implements {Encoder}
* @param {{fatal: boolean}} options
*/
function Big5Encoder(options) {
var fatal = options.fatal;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is an ASCII code point, return a byte whose
// value is code point.
if (isASCIICodePoint(code_point))
return code_point;
// 3. Let pointer be the index Big5 pointer for code point.
var pointer = indexBig5PointerFor(code_point);
// 4. If pointer is null, return error with code point.
if (pointer === null)
return encoderError(code_point);
// 5. Let lead be floor(pointer / 157) + 0x81.
var lead = floor(pointer / 157) + 0x81;
// 6. If lead is less than 0xA1, return error with code point.
if (lead < 0xA1)
return encoderError(code_point);
// 7. Let trail be pointer % 157.
var trail = pointer % 157;
// 8. Let offset be 0x40 if trail is less than 0x3F and 0x62
// otherwise.
var offset = trail < 0x3F ? 0x40 : 0x62;
// Return two bytes whose values are lead and trail + offset.
return [lead, trail + offset];
};
}
/** @param {{fatal: boolean}} options */
encoders['Big5'] = function(options) {
return new Big5Encoder(options);
};
/** @param {{fatal: boolean}} options */
decoders['Big5'] = function(options) {
return new Big5Decoder(options);
};
//
// 13. Legacy multi-byte Japanese encodings
//
// 13.1 euc-jp
// 13.1.1 euc-jp decoder
/**
* @constructor
* @implements {Decoder}
* @param {{fatal: boolean}} options
*/
function EUCJPDecoder(options) {
var fatal = options.fatal;
// euc-jp's decoder has an associated euc-jp jis0212 flag
// (initially unset) and euc-jp lead (initially 0x00).
var /** @type {boolean} */ eucjp_jis0212_flag = false,
/** @type {number} */ eucjp_lead = 0x00;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream and euc-jp lead is not 0x00, set
// euc-jp lead to 0x00, and return error.
if (bite === end_of_stream && eucjp_lead !== 0x00) {
eucjp_lead = 0x00;
return decoderError(fatal);
}
// 2. If byte is end-of-stream and euc-jp lead is 0x00, return
// finished.
if (bite === end_of_stream && eucjp_lead === 0x00)
return finished;
// 3. If euc-jp lead is 0x8E and byte is in the range 0xA1 to
// 0xDF, inclusive, set euc-jp lead to 0x00 and return a code
// point whose value is 0xFF61 − 0xA1 + byte.
if (eucjp_lead === 0x8E && inRange(bite, 0xA1, 0xDF)) {
eucjp_lead = 0x00;
return 0xFF61 - 0xA1 + bite;
}
// 4. If euc-jp lead is 0x8F and byte is in the range 0xA1 to
// 0xFE, inclusive, set the euc-jp jis0212 flag, set euc-jp lead
// to byte, and return continue.
if (eucjp_lead === 0x8F && inRange(bite, 0xA1, 0xFE)) {
eucjp_jis0212_flag = true;
eucjp_lead = bite;
return null;
}
// 5. If euc-jp lead is not 0x00, let lead be euc-jp lead, set
// euc-jp lead to 0x00, and run these substeps:
if (eucjp_lead !== 0x00) {
var lead = eucjp_lead;
eucjp_lead = 0x00;
// 1. Let code point be null.
var code_point = null;
// 2. If lead and byte are both in the range 0xA1 to 0xFE,
// inclusive, set code point to the index code point for (lead
// − 0xA1) × 94 + byte − 0xA1 in index jis0208 if the euc-jp
// jis0212 flag is unset and in index jis0212 otherwise.
if (inRange(lead, 0xA1, 0xFE) && inRange(bite, 0xA1, 0xFE)) {
code_point = indexCodePointFor(
(lead - 0xA1) * 94 + (bite - 0xA1),
index(!eucjp_jis0212_flag ? 'jis0208' : 'jis0212'));
}
// 3. Unset the euc-jp jis0212 flag.
eucjp_jis0212_flag = false;
// 4. If byte is not in the range 0xA1 to 0xFE, inclusive,
// prepend byte to stream.
if (!inRange(bite, 0xA1, 0xFE))
stream.prepend(bite);
// 5. If code point is null, return error.
if (code_point === null)
return decoderError(fatal);
// 6. Return a code point whose value is code point.
return code_point;
}
// 6. If byte is an ASCII byte, return a code point whose value
// is byte.
if (isASCIIByte(bite))
return bite;
// 7. If byte is 0x8E, 0x8F, or in the range 0xA1 to 0xFE,
// inclusive, set euc-jp lead to byte and return continue.
if (bite === 0x8E || bite === 0x8F || inRange(bite, 0xA1, 0xFE)) {
eucjp_lead = bite;
return null;
}
// 8. Return error.
return decoderError(fatal);
};
}
// 13.1.2 euc-jp encoder
/**
* @constructor
* @implements {Encoder}
* @param {{fatal: boolean}} options
*/
function EUCJPEncoder(options) {
var fatal = options.fatal;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is an ASCII code point, return a byte whose
// value is code point.
if (isASCIICodePoint(code_point))
return code_point;
// 3. If code point is U+00A5, return byte 0x5C.
if (code_point === 0x00A5)
return 0x5C;
// 4. If code point is U+203E, return byte 0x7E.
if (code_point === 0x203E)
return 0x7E;
// 5. If code point is in the range U+FF61 to U+FF9F, inclusive,
// return two bytes whose values are 0x8E and code point −
// 0xFF61 + 0xA1.
if (inRange(code_point, 0xFF61, 0xFF9F))
return [0x8E, code_point - 0xFF61 + 0xA1];
// 6. If code point is U+2212, set it to U+FF0D.
if (code_point === 0x2212)
code_point = 0xFF0D;
// 7. Let pointer be the index pointer for code point in index
// jis0208.
var pointer = indexPointerFor(code_point, index('jis0208'));
// 8. If pointer is null, return error with code point.
if (pointer === null)
return encoderError(code_point);
// 9. Let lead be floor(pointer / 94) + 0xA1.
var lead = floor(pointer / 94) + 0xA1;
// 10. Let trail be pointer % 94 + 0xA1.
var trail = pointer % 94 + 0xA1;
// 11. Return two bytes whose values are lead and trail.
return [lead, trail];
};
}
/** @param {{fatal: boolean}} options */
encoders['EUC-JP'] = function(options) {
return new EUCJPEncoder(options);
};
/** @param {{fatal: boolean}} options */
decoders['EUC-JP'] = function(options) {
return new EUCJPDecoder(options);
};
// 13.2 iso-2022-jp
// 13.2.1 iso-2022-jp decoder
/**
* @constructor
* @implements {Decoder}
* @param {{fatal: boolean}} options
*/
function ISO2022JPDecoder(options) {
var fatal = options.fatal;
/** @enum */
var states = {
ASCII: 0,
Roman: 1,
Katakana: 2,
LeadByte: 3,
TrailByte: 4,
EscapeStart: 5,
Escape: 6
};
// iso-2022-jp's decoder has an associated iso-2022-jp decoder
// state (initially ASCII), iso-2022-jp decoder output state
// (initially ASCII), iso-2022-jp lead (initially 0x00), and
// iso-2022-jp output flag (initially unset).
var /** @type {number} */ iso2022jp_decoder_state = states.ASCII,
/** @type {number} */ iso2022jp_decoder_output_state = states.ASCII,
/** @type {number} */ iso2022jp_lead = 0x00,
/** @type {boolean} */ iso2022jp_output_flag = false;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// switching on iso-2022-jp decoder state:
switch (iso2022jp_decoder_state) {
default:
case states.ASCII:
// ASCII
// Based on byte:
// 0x1B
if (bite === 0x1B) {
// Set iso-2022-jp decoder state to escape start and return
// continue.
iso2022jp_decoder_state = states.EscapeStart;
return null;
}
// 0x00 to 0x7F, excluding 0x0E, 0x0F, and 0x1B
if (inRange(bite, 0x00, 0x7F) && bite !== 0x0E
&& bite !== 0x0F && bite !== 0x1B) {
// Unset the iso-2022-jp output flag and return a code point
// whose value is byte.
iso2022jp_output_flag = false;
return bite;
}
// end-of-stream
if (bite === end_of_stream) {
// Return finished.
return finished;
}
// Otherwise
// Unset the iso-2022-jp output flag and return error.
iso2022jp_output_flag = false;
return decoderError(fatal);
case states.Roman:
// Roman
// Based on byte:
// 0x1B
if (bite === 0x1B) {
// Set iso-2022-jp decoder state to escape start and return
// continue.
iso2022jp_decoder_state = states.EscapeStart;
return null;
}
// 0x5C
if (bite === 0x5C) {
// Unset the iso-2022-jp output flag and return code point
// U+00A5.
iso2022jp_output_flag = false;
return 0x00A5;
}
// 0x7E
if (bite === 0x7E) {
// Unset the iso-2022-jp output flag and return code point
// U+203E.
iso2022jp_output_flag = false;
return 0x203E;
}
// 0x00 to 0x7F, excluding 0x0E, 0x0F, 0x1B, 0x5C, and 0x7E
if (inRange(bite, 0x00, 0x7F) && bite !== 0x0E && bite !== 0x0F
&& bite !== 0x1B && bite !== 0x5C && bite !== 0x7E) {
// Unset the iso-2022-jp output flag and return a code point
// whose value is byte.
iso2022jp_output_flag = false;
return bite;
}
// end-of-stream
if (bite === end_of_stream) {
// Return finished.
return finished;
}
// Otherwise
// Unset the iso-2022-jp output flag and return error.
iso2022jp_output_flag = false;
return decoderError(fatal);
case states.Katakana:
// Katakana
// Based on byte:
// 0x1B
if (bite === 0x1B) {
// Set iso-2022-jp decoder state to escape start and return
// continue.
iso2022jp_decoder_state = states.EscapeStart;
return null;
}
// 0x21 to 0x5F
if (inRange(bite, 0x21, 0x5F)) {
// Unset the iso-2022-jp output flag and return a code point
// whose value is 0xFF61 − 0x21 + byte.
iso2022jp_output_flag = false;
return 0xFF61 - 0x21 + bite;
}
// end-of-stream
if (bite === end_of_stream) {
// Return finished.
return finished;
}
// Otherwise
// Unset the iso-2022-jp output flag and return error.
iso2022jp_output_flag = false;
return decoderError(fatal);
case states.LeadByte:
// Lead byte
// Based on byte:
// 0x1B
if (bite === 0x1B) {
// Set iso-2022-jp decoder state to escape start and return
// continue.
iso2022jp_decoder_state = states.EscapeStart;
return null;
}
// 0x21 to 0x7E
if (inRange(bite, 0x21, 0x7E)) {
// Unset the iso-2022-jp output flag, set iso-2022-jp lead
// to byte, iso-2022-jp decoder state to trail byte, and
// return continue.
iso2022jp_output_flag = false;
iso2022jp_lead = bite;
iso2022jp_decoder_state = states.TrailByte;
return null;
}
// end-of-stream
if (bite === end_of_stream) {
// Return finished.
return finished;
}
// Otherwise
// Unset the iso-2022-jp output flag and return error.
iso2022jp_output_flag = false;
return decoderError(fatal);
case states.TrailByte:
// Trail byte
// Based on byte:
// 0x1B
if (bite === 0x1B) {
// Set iso-2022-jp decoder state to escape start and return
// continue.
iso2022jp_decoder_state = states.EscapeStart;
return decoderError(fatal);
}
// 0x21 to 0x7E
if (inRange(bite, 0x21, 0x7E)) {
// 1. Set the iso-2022-jp decoder state to lead byte.
iso2022jp_decoder_state = states.LeadByte;
// 2. Let pointer be (iso-2022-jp lead − 0x21) × 94 + byte − 0x21.
var pointer = (iso2022jp_lead - 0x21) * 94 + bite - 0x21;
// 3. Let code point be the index code point for pointer in
// index jis0208.
var code_point = indexCodePointFor(pointer, index('jis0208'));
// 4. If code point is null, return error.
if (code_point === null)
return decoderError(fatal);
// 5. Return a code point whose value is code point.
return code_point;
}
// end-of-stream
if (bite === end_of_stream) {
// Set the iso-2022-jp decoder state to lead byte, prepend
// byte to stream, and return error.
iso2022jp_decoder_state = states.LeadByte;
stream.prepend(bite);
return decoderError(fatal);
}
// Otherwise
// Set iso-2022-jp decoder state to lead byte and return
// error.
iso2022jp_decoder_state = states.LeadByte;
return decoderError(fatal);
case states.EscapeStart:
// Escape start
// 1. If byte is either 0x24 or 0x28, set iso-2022-jp lead to
// byte, iso-2022-jp decoder state to escape, and return
// continue.
if (bite === 0x24 || bite === 0x28) {
iso2022jp_lead = bite;
iso2022jp_decoder_state = states.Escape;
return null;
}
// 2. Prepend byte to stream.
stream.prepend(bite);
// 3. Unset the iso-2022-jp output flag, set iso-2022-jp
// decoder state to iso-2022-jp decoder output state, and
// return error.
iso2022jp_output_flag = false;
iso2022jp_decoder_state = iso2022jp_decoder_output_state;
return decoderError(fatal);
case states.Escape:
// Escape
// 1. Let lead be iso-2022-jp lead and set iso-2022-jp lead to
// 0x00.
var lead = iso2022jp_lead;
iso2022jp_lead = 0x00;
// 2. Let state be null.
var state = null;
// 3. If lead is 0x28 and byte is 0x42, set state to ASCII.
if (lead === 0x28 && bite === 0x42)
state = states.ASCII;
// 4. If lead is 0x28 and byte is 0x4A, set state to Roman.
if (lead === 0x28 && bite === 0x4A)
state = states.Roman;
// 5. If lead is 0x28 and byte is 0x49, set state to Katakana.
if (lead === 0x28 && bite === 0x49)
state = states.Katakana;
// 6. If lead is 0x24 and byte is either 0x40 or 0x42, set
// state to lead byte.
if (lead === 0x24 && (bite === 0x40 || bite === 0x42))
state = states.LeadByte;
// 7. If state is non-null, run these substeps:
if (state !== null) {
// 1. Set iso-2022-jp decoder state and iso-2022-jp decoder
// output state to states.
iso2022jp_decoder_state = iso2022jp_decoder_state = state;
// 2. Let output flag be the iso-2022-jp output flag.
var output_flag = iso2022jp_output_flag;
// 3. Set the iso-2022-jp output flag.
iso2022jp_output_flag = true;
// 4. Return continue, if output flag is unset, and error
// otherwise.
return !output_flag ? null : decoderError(fatal);
}
// 8. Prepend lead and byte to stream.
stream.prepend([lead, bite]);
// 9. Unset the iso-2022-jp output flag, set iso-2022-jp
// decoder state to iso-2022-jp decoder output state and
// return error.
iso2022jp_output_flag = false;
iso2022jp_decoder_state = iso2022jp_decoder_output_state;
return decoderError(fatal);
}
};
}
// 13.2.2 iso-2022-jp encoder
/**
* @constructor
* @implements {Encoder}
* @param {{fatal: boolean}} options
*/
function ISO2022JPEncoder(options) {
var fatal = options.fatal;
// iso-2022-jp's encoder has an associated iso-2022-jp encoder
// state which is one of ASCII, Roman, and jis0208 (initially
// ASCII).
/** @enum */
var states = {
ASCII: 0,
Roman: 1,
jis0208: 2
};
var /** @type {number} */ iso2022jp_state = states.ASCII;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream and iso-2022-jp encoder
// state is not ASCII, prepend code point to stream, set
// iso-2022-jp encoder state to ASCII, and return three bytes
// 0x1B 0x28 0x42.
if (code_point === end_of_stream &&
iso2022jp_state !== states.ASCII) {
stream.prepend(code_point);
iso2022jp_state = states.ASCII;
return [0x1B, 0x28, 0x42];
}
// 2. If code point is end-of-stream and iso-2022-jp encoder
// state is ASCII, return finished.
if (code_point === end_of_stream && iso2022jp_state === states.ASCII)
return finished;
// 3. If ISO-2022-JP encoder state is ASCII or Roman, and code
// point is U+000E, U+000F, or U+001B, return error with U+FFFD.
if ((iso2022jp_state === states.ASCII ||
iso2022jp_state === states.Roman) &&
(code_point === 0x000E || code_point === 0x000F ||
code_point === 0x001B)) {
return encoderError(0xFFFD);
}
// 4. If iso-2022-jp encoder state is ASCII and code point is an
// ASCII code point, return a byte whose value is code point.
if (iso2022jp_state === states.ASCII &&
isASCIICodePoint(code_point))
return code_point;
// 5. If iso-2022-jp encoder state is Roman and code point is an
// ASCII code point, excluding U+005C and U+007E, or is U+00A5
// or U+203E, run these substeps:
if (iso2022jp_state === states.Roman &&
((isASCIICodePoint(code_point) &&
code_point !== 0x005C && code_point !== 0x007E) ||
(code_point == 0x00A5 || code_point == 0x203E))) {
// 1. If code point is an ASCII code point, return a byte
// whose value is code point.
if (isASCIICodePoint(code_point))
return code_point;
// 2. If code point is U+00A5, return byte 0x5C.
if (code_point === 0x00A5)
return 0x5C;
// 3. If code point is U+203E, return byte 0x7E.
if (code_point === 0x203E)
return 0x7E;
}
// 6. If code point is an ASCII code point, and iso-2022-jp
// encoder state is not ASCII, prepend code point to stream, set
// iso-2022-jp encoder state to ASCII, and return three bytes
// 0x1B 0x28 0x42.
if (isASCIICodePoint(code_point) &&
iso2022jp_state !== states.ASCII) {
stream.prepend(code_point);
iso2022jp_state = states.ASCII;
return [0x1B, 0x28, 0x42];
}
// 7. If code point is either U+00A5 or U+203E, and iso-2022-jp
// encoder state is not Roman, prepend code point to stream, set
// iso-2022-jp encoder state to Roman, and return three bytes
// 0x1B 0x28 0x4A.
if ((code_point === 0x00A5 || code_point === 0x203E) &&
iso2022jp_state !== states.Roman) {
stream.prepend(code_point);
iso2022jp_state = states.Roman;
return [0x1B, 0x28, 0x4A];
}
// 8. If code point is U+2212, set it to U+FF0D.
if (code_point === 0x2212)
code_point = 0xFF0D;
// 9. Let pointer be the index pointer for code point in index
// jis0208.
var pointer = indexPointerFor(code_point, index('jis0208'));
// 10. If pointer is null, return error with code point.
if (pointer === null)
return encoderError(code_point);
// 11. If iso-2022-jp encoder state is not jis0208, prepend code
// point to stream, set iso-2022-jp encoder state to jis0208,
// and return three bytes 0x1B 0x24 0x42.
if (iso2022jp_state !== states.jis0208) {
stream.prepend(code_point);
iso2022jp_state = states.jis0208;
return [0x1B, 0x24, 0x42];
}
// 12. Let lead be floor(pointer / 94) + 0x21.
var lead = floor(pointer / 94) + 0x21;
// 13. Let trail be pointer % 94 + 0x21.
var trail = pointer % 94 + 0x21;
// 14. Return two bytes whose values are lead and trail.
return [lead, trail];
};
}
/** @param {{fatal: boolean}} options */
encoders['ISO-2022-JP'] = function(options) {
return new ISO2022JPEncoder(options);
};
/** @param {{fatal: boolean}} options */
decoders['ISO-2022-JP'] = function(options) {
return new ISO2022JPDecoder(options);
};
// 13.3 Shift_JIS
// 13.3.1 Shift_JIS decoder
/**
* @constructor
* @implements {Decoder}
* @param {{fatal: boolean}} options
*/
function ShiftJISDecoder(options) {
var fatal = options.fatal;
// Shift_JIS's decoder has an associated Shift_JIS lead (initially
// 0x00).
var /** @type {number} */ Shift_JIS_lead = 0x00;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream and Shift_JIS lead is not 0x00,
// set Shift_JIS lead to 0x00 and return error.
if (bite === end_of_stream && Shift_JIS_lead !== 0x00) {
Shift_JIS_lead = 0x00;
return decoderError(fatal);
}
// 2. If byte is end-of-stream and Shift_JIS lead is 0x00,
// return finished.
if (bite === end_of_stream && Shift_JIS_lead === 0x00)
return finished;
// 3. If Shift_JIS lead is not 0x00, let lead be Shift_JIS lead,
// let pointer be null, set Shift_JIS lead to 0x00, and then run
// these substeps:
if (Shift_JIS_lead !== 0x00) {
var lead = Shift_JIS_lead;
var pointer = null;
Shift_JIS_lead = 0x00;
// 1. Let offset be 0x40, if byte is less than 0x7F, and 0x41
// otherwise.
var offset = (bite < 0x7F) ? 0x40 : 0x41;
// 2. Let lead offset be 0x81, if lead is less than 0xA0, and
// 0xC1 otherwise.
var lead_offset = (lead < 0xA0) ? 0x81 : 0xC1;
// 3. If byte is in the range 0x40 to 0x7E, inclusive, or 0x80
// to 0xFC, inclusive, set pointer to (lead − lead offset) ×
// 188 + byte − offset.
if (inRange(bite, 0x40, 0x7E) || inRange(bite, 0x80, 0xFC))
pointer = (lead - lead_offset) * 188 + bite - offset;
// 4. If pointer is in the range 8836 to 10715, inclusive,
// return a code point whose value is 0xE000 − 8836 + pointer.
if (inRange(pointer, 8836, 10715))
return 0xE000 - 8836 + pointer;
// 5. Let code point be null, if pointer is null, and the
// index code point for pointer in index jis0208 otherwise.
var code_point = (pointer === null) ? null :
indexCodePointFor(pointer, index('jis0208'));
// 6. If code point is null and byte is an ASCII byte, prepend
// byte to stream.
if (code_point === null && isASCIIByte(bite))
stream.prepend(bite);
// 7. If code point is null, return error.
if (code_point === null)
return decoderError(fatal);
// 8. Return a code point whose value is code point.
return code_point;
}
// 4. If byte is an ASCII byte or 0x80, return a code point
// whose value is byte.
if (isASCIIByte(bite) || bite === 0x80)
return bite;
// 5. If byte is in the range 0xA1 to 0xDF, inclusive, return a
// code point whose value is 0xFF61 − 0xA1 + byte.
if (inRange(bite, 0xA1, 0xDF))
return 0xFF61 - 0xA1 + bite;
// 6. If byte is in the range 0x81 to 0x9F, inclusive, or 0xE0
// to 0xFC, inclusive, set Shift_JIS lead to byte and return
// continue.
if (inRange(bite, 0x81, 0x9F) || inRange(bite, 0xE0, 0xFC)) {
Shift_JIS_lead = bite;
return null;
}
// 7. Return error.
return decoderError(fatal);
};
}
// 13.3.2 Shift_JIS encoder
/**
* @constructor
* @implements {Encoder}
* @param {{fatal: boolean}} options
*/
function ShiftJISEncoder(options) {
var fatal = options.fatal;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is an ASCII code point or U+0080, return a
// byte whose value is code point.
if (isASCIICodePoint(code_point) || code_point === 0x0080)
return code_point;
// 3. If code point is U+00A5, return byte 0x5C.
if (code_point === 0x00A5)
return 0x5C;
// 4. If code point is U+203E, return byte 0x7E.
if (code_point === 0x203E)
return 0x7E;
// 5. If code point is in the range U+FF61 to U+FF9F, inclusive,
// return a byte whose value is code point − 0xFF61 + 0xA1.
if (inRange(code_point, 0xFF61, 0xFF9F))
return code_point - 0xFF61 + 0xA1;
// 6. If code point is U+2212, set it to U+FF0D.
if (code_point === 0x2212)
code_point = 0xFF0D;
// 7. Let pointer be the index Shift_JIS pointer for code point.
var pointer = indexShiftJISPointerFor(code_point);
// 8. If pointer is null, return error with code point.
if (pointer === null)
return encoderError(code_point);
// 9. Let lead be floor(pointer / 188).
var lead = floor(pointer / 188);
// 10. Let lead offset be 0x81, if lead is less than 0x1F, and
// 0xC1 otherwise.
var lead_offset = (lead < 0x1F) ? 0x81 : 0xC1;
// 11. Let trail be pointer % 188.
var trail = pointer % 188;
// 12. Let offset be 0x40, if trail is less than 0x3F, and 0x41
// otherwise.
var offset = (trail < 0x3F) ? 0x40 : 0x41;
// 13. Return two bytes whose values are lead + lead offset and
// trail + offset.
return [lead + lead_offset, trail + offset];
};
}
/** @param {{fatal: boolean}} options */
encoders['Shift_JIS'] = function(options) {
return new ShiftJISEncoder(options);
};
/** @param {{fatal: boolean}} options */
decoders['Shift_JIS'] = function(options) {
return new ShiftJISDecoder(options);
};
//
// 14. Legacy multi-byte Korean encodings
//
// 14.1 euc-kr
// 14.1.1 euc-kr decoder
/**
* @constructor
* @implements {Decoder}
* @param {{fatal: boolean}} options
*/
function EUCKRDecoder(options) {
var fatal = options.fatal;
// euc-kr's decoder has an associated euc-kr lead (initially 0x00).
var /** @type {number} */ euckr_lead = 0x00;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream and euc-kr lead is not 0x00, set
// euc-kr lead to 0x00 and return error.
if (bite === end_of_stream && euckr_lead !== 0) {
euckr_lead = 0x00;
return decoderError(fatal);
}
// 2. If byte is end-of-stream and euc-kr lead is 0x00, return
// finished.
if (bite === end_of_stream && euckr_lead === 0)
return finished;
// 3. If euc-kr lead is not 0x00, let lead be euc-kr lead, let
// pointer be null, set euc-kr lead to 0x00, and then run these
// substeps:
if (euckr_lead !== 0x00) {
var lead = euckr_lead;
var pointer = null;
euckr_lead = 0x00;
// 1. If byte is in the range 0x41 to 0xFE, inclusive, set
// pointer to (lead − 0x81) × 190 + (byte − 0x41).
if (inRange(bite, 0x41, 0xFE))
pointer = (lead - 0x81) * 190 + (bite - 0x41);
// 2. Let code point be null, if pointer is null, and the
// index code point for pointer in index euc-kr otherwise.
var code_point = (pointer === null)
? null : indexCodePointFor(pointer, index('euc-kr'));
// 3. If code point is null and byte is an ASCII byte, prepend
// byte to stream.
if (pointer === null && isASCIIByte(bite))
stream.prepend(bite);
// 4. If code point is null, return error.
if (code_point === null)
return decoderError(fatal);
// 5. Return a code point whose value is code point.
return code_point;
}
// 4. If byte is an ASCII byte, return a code point whose value
// is byte.
if (isASCIIByte(bite))
return bite;
// 5. If byte is in the range 0x81 to 0xFE, inclusive, set
// euc-kr lead to byte and return continue.
if (inRange(bite, 0x81, 0xFE)) {
euckr_lead = bite;
return null;
}
// 6. Return error.
return decoderError(fatal);
};
}
// 14.1.2 euc-kr encoder
/**
* @constructor
* @implements {Encoder}
* @param {{fatal: boolean}} options
*/
function EUCKREncoder(options) {
var fatal = options.fatal;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is an ASCII code point, return a byte whose
// value is code point.
if (isASCIICodePoint(code_point))
return code_point;
// 3. Let pointer be the index pointer for code point in index
// euc-kr.
var pointer = indexPointerFor(code_point, index('euc-kr'));
// 4. If pointer is null, return error with code point.
if (pointer === null)
return encoderError(code_point);
// 5. Let lead be floor(pointer / 190) + 0x81.
var lead = floor(pointer / 190) + 0x81;
// 6. Let trail be pointer % 190 + 0x41.
var trail = (pointer % 190) + 0x41;
// 7. Return two bytes whose values are lead and trail.
return [lead, trail];
};
}
/** @param {{fatal: boolean}} options */
encoders['EUC-KR'] = function(options) {
return new EUCKREncoder(options);
};
/** @param {{fatal: boolean}} options */
decoders['EUC-KR'] = function(options) {
return new EUCKRDecoder(options);
};
//
// 15. Legacy miscellaneous encodings
//
// 15.1 replacement
// Not needed - API throws RangeError
// 15.2 Common infrastructure for utf-16be and utf-16le
/**
* @param {number} code_unit
* @param {boolean} utf16be
* @return {!Array.<number>} bytes
*/
function convertCodeUnitToBytes(code_unit, utf16be) {
// 1. Let byte1 be code unit >> 8.
var byte1 = code_unit >> 8;
// 2. Let byte2 be code unit & 0x00FF.
var byte2 = code_unit & 0x00FF;
// 3. Then return the bytes in order:
// utf-16be flag is set: byte1, then byte2.
if (utf16be)
return [byte1, byte2];
// utf-16be flag is unset: byte2, then byte1.
return [byte2, byte1];
}
// 15.2.1 shared utf-16 decoder
/**
* @constructor
* @implements {Decoder}
* @param {boolean} utf16_be True if big-endian, false if little-endian.
* @param {{fatal: boolean}} options
*/
function UTF16Decoder(utf16_be, options) {
var fatal = options.fatal;
var /** @type {?number} */ utf16_lead_byte = null,
/** @type {?number} */ utf16_lead_surrogate = null;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream and either utf-16 lead byte or
// utf-16 lead surrogate is not null, set utf-16 lead byte and
// utf-16 lead surrogate to null, and return error.
if (bite === end_of_stream && (utf16_lead_byte !== null ||
utf16_lead_surrogate !== null)) {
return decoderError(fatal);
}
// 2. If byte is end-of-stream and utf-16 lead byte and utf-16
// lead surrogate are null, return finished.
if (bite === end_of_stream && utf16_lead_byte === null &&
utf16_lead_surrogate === null) {
return finished;
}
// 3. If utf-16 lead byte is null, set utf-16 lead byte to byte
// and return continue.
if (utf16_lead_byte === null) {
utf16_lead_byte = bite;
return null;
}
// 4. Let code unit be the result of:
var code_unit;
if (utf16_be) {
// utf-16be decoder flag is set
// (utf-16 lead byte << 8) + byte.
code_unit = (utf16_lead_byte << 8) + bite;
} else {
// utf-16be decoder flag is unset
// (byte << 8) + utf-16 lead byte.
code_unit = (bite << 8) + utf16_lead_byte;
}
// Then set utf-16 lead byte to null.
utf16_lead_byte = null;
// 5. If utf-16 lead surrogate is not null, let lead surrogate
// be utf-16 lead surrogate, set utf-16 lead surrogate to null,
// and then run these substeps:
if (utf16_lead_surrogate !== null) {
var lead_surrogate = utf16_lead_surrogate;
utf16_lead_surrogate = null;
// 1. If code unit is in the range U+DC00 to U+DFFF,
// inclusive, return a code point whose value is 0x10000 +
// ((lead surrogate − 0xD800) << 10) + (code unit − 0xDC00).
if (inRange(code_unit, 0xDC00, 0xDFFF)) {
return 0x10000 + (lead_surrogate - 0xD800) * 0x400 +
(code_unit - 0xDC00);
}
// 2. Prepend the sequence resulting of converting code unit
// to bytes using utf-16be decoder flag to stream and return
// error.
stream.prepend(convertCodeUnitToBytes(code_unit, utf16_be));
return decoderError(fatal);
}
// 6. If code unit is in the range U+D800 to U+DBFF, inclusive,
// set utf-16 lead surrogate to code unit and return continue.
if (inRange(code_unit, 0xD800, 0xDBFF)) {
utf16_lead_surrogate = code_unit;
return null;
}
// 7. If code unit is in the range U+DC00 to U+DFFF, inclusive,
// return error.
if (inRange(code_unit, 0xDC00, 0xDFFF))
return decoderError(fatal);
// 8. Return code point code unit.
return code_unit;
};
}
// 15.2.2 shared utf-16 encoder
/**
* @constructor
* @implements {Encoder}
* @param {boolean} utf16_be True if big-endian, false if little-endian.
* @param {{fatal: boolean}} options
*/
function UTF16Encoder(utf16_be, options) {
var fatal = options.fatal;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1. If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is in the range U+0000 to U+FFFF, inclusive,
// return the sequence resulting of converting code point to
// bytes using utf-16be encoder flag.
if (inRange(code_point, 0x0000, 0xFFFF))
return convertCodeUnitToBytes(code_point, utf16_be);
// 3. Let lead be ((code point − 0x10000) >> 10) + 0xD800,
// converted to bytes using utf-16be encoder flag.
var lead = convertCodeUnitToBytes(
((code_point - 0x10000) >> 10) + 0xD800, utf16_be);
// 4. Let trail be ((code point − 0x10000) & 0x3FF) + 0xDC00,
// converted to bytes using utf-16be encoder flag.
var trail = convertCodeUnitToBytes(
((code_point - 0x10000) & 0x3FF) + 0xDC00, utf16_be);
// 5. Return a byte sequence of lead followed by trail.
return lead.concat(trail);
};
}
// 15.3 utf-16be
// 15.3.1 utf-16be decoder
/** @param {{fatal: boolean}} options */
encoders['UTF-16BE'] = function(options) {
return new UTF16Encoder(true, options);
};
// 15.3.2 utf-16be encoder
/** @param {{fatal: boolean}} options */
decoders['UTF-16BE'] = function(options) {
return new UTF16Decoder(true, options);
};
// 15.4 utf-16le
// 15.4.1 utf-16le decoder
/** @param {{fatal: boolean}} options */
encoders['UTF-16LE'] = function(options) {
return new UTF16Encoder(false, options);
};
// 15.4.2 utf-16le encoder
/** @param {{fatal: boolean}} options */
decoders['UTF-16LE'] = function(options) {
return new UTF16Decoder(false, options);
};
// 15.5 x-user-defined
// 15.5.1 x-user-defined decoder
/**
* @constructor
* @implements {Decoder}
* @param {{fatal: boolean}} options
*/
function XUserDefinedDecoder(options) {
var fatal = options.fatal;
/**
* @param {Stream} stream The stream of bytes being decoded.
* @param {number} bite The next byte read from the stream.
* @return {?(number|!Array.<number>)} The next code point(s)
* decoded, or null if not enough data exists in the input
* stream to decode a complete code point.
*/
this.handler = function(stream, bite) {
// 1. If byte is end-of-stream, return finished.
if (bite === end_of_stream)
return finished;
// 2. If byte is an ASCII byte, return a code point whose value
// is byte.
if (isASCIIByte(bite))
return bite;
// 3. Return a code point whose value is 0xF780 + byte − 0x80.
return 0xF780 + bite - 0x80;
};
}
// 15.5.2 x-user-defined encoder
/**
* @constructor
* @implements {Encoder}
* @param {{fatal: boolean}} options
*/
function XUserDefinedEncoder(options) {
var fatal = options.fatal;
/**
* @param {Stream} stream Input stream.
* @param {number} code_point Next code point read from the stream.
* @return {(number|!Array.<number>)} Byte(s) to emit.
*/
this.handler = function(stream, code_point) {
// 1.If code point is end-of-stream, return finished.
if (code_point === end_of_stream)
return finished;
// 2. If code point is an ASCII code point, return a byte whose
// value is code point.
if (isASCIICodePoint(code_point))
return code_point;
// 3. If code point is in the range U+F780 to U+F7FF, inclusive,
// return a byte whose value is code point − 0xF780 + 0x80.
if (inRange(code_point, 0xF780, 0xF7FF))
return code_point - 0xF780 + 0x80;
// 4. Return error with code point.
return encoderError(code_point);
};
}
/** @param {{fatal: boolean}} options */
encoders['x-user-defined'] = function(options) {
return new XUserDefinedEncoder(options);
};
/** @param {{fatal: boolean}} options */
decoders['x-user-defined'] = function(options) {
return new XUserDefinedDecoder(options);
};
if (!global['TextEncoder'])
global['TextEncoder'] = TextEncoder;
if (!global['TextDecoder'])
global['TextDecoder'] = TextDecoder;
if (typeof module !== "undefined" && module.exports) {
module.exports = {
TextEncoder: global['TextEncoder'],
TextDecoder: global['TextDecoder'],
EncodingIndexes: global["encoding-indexes"]
};
}
// For strict environments where `this` inside the global scope
// is `undefined`, take a pure object instead
}(this || {}));
1820
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
