entities - npm Package Compare versions

Comparing version 4.2.0 to 4.3.0

lib/decode_codepoint.d.ts

@@ -0,3 +1,4 @@
+export declare const fromCodePoint: (...codePoints: number[]) => string;
 export declare function replaceCodePoint(codePoint: number): number;
 export default function decodeCodePoint(codePoint: number): string;
 //# sourceMappingURL=decode_codepoint.d.ts.map

lib/decode_codepoint.js

@@ -5,3 +5,3 @@ "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.replaceCodePoint = void 0;
+exports.replaceCodePoint = exports.fromCodePoint = void 0;
 var decodeMap = new Map([
@@ -37,3 +37,3 @@ [0, 65533],
 ]);
-var fromCodePoint = 
+exports.fromCodePoint = 
 // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition, node/no-unsupported-features/es-builtins
@@ -59,5 +59,5 @@ (_a = String.fromCodePoint) !== null && _a !== void 0 ? _a : function (codePoint) {
 function decodeCodePoint(codePoint) {
-    return fromCodePoint(replaceCodePoint(codePoint));
+    return (0, exports.fromCodePoint)(replaceCodePoint(codePoint));
 }
 exports.default = decodeCodePoint;
 //# sourceMappingURL=decode_codepoint.js.map

lib/decode.d.ts

 import htmlDecodeTree from "./generated/decode-data-html.js";
 import xmlDecodeTree from "./generated/decode-data-xml.js";
-import { default as decodeCodePoint, replaceCodePoint } from "./decode_codepoint.js";
-export { htmlDecodeTree, xmlDecodeTree, decodeCodePoint, replaceCodePoint };
+import decodeCodePoint from "./decode_codepoint.js";
+export { htmlDecodeTree, xmlDecodeTree, decodeCodePoint };
+export { replaceCodePoint, fromCodePoint } from "./decode_codepoint.js";
 export declare enum BinTrieFlags {
@@ -6,0 +7,0 @@ VALUE_LENGTH = 49152,

lib/decode.js

 "use strict";
-var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
-    if (k2 === undefined) k2 = k;
-    var desc = Object.getOwnPropertyDescriptor(m, k);
-    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-      desc = { enumerable: true, get: function() { return m[k]; } };
-    }
-    Object.defineProperty(o, k2, desc);
-}) : (function(o, m, k, k2) {
-    if (k2 === undefined) k2 = k;
-    o[k2] = m[k];
-}));
-var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
-    Object.defineProperty(o, "default", { enumerable: true, value: v });
-}) : function(o, v) {
-    o["default"] = v;
-});
-var __importStar = (this && this.__importStar) || function (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
-};
 var __importDefault = (this && this.__importDefault) || function (mod) {
@@ -29,3 +6,3 @@ return (mod && mod.__esModule) ? mod : { "default": mod };
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.decodeXML = exports.decodeHTMLStrict = exports.decodeHTML = exports.determineBranch = exports.BinTrieFlags = exports.replaceCodePoint = exports.decodeCodePoint = exports.xmlDecodeTree = exports.htmlDecodeTree = void 0;
+exports.decodeXML = exports.decodeHTMLStrict = exports.decodeHTML = exports.determineBranch = exports.BinTrieFlags = exports.fromCodePoint = exports.replaceCodePoint = exports.decodeCodePoint = exports.xmlDecodeTree = exports.htmlDecodeTree = void 0;
 var decode_data_html_js_1 = __importDefault(require("./generated/decode-data-html.js"));
@@ -35,5 +12,19 @@ exports.htmlDecodeTree = decode_data_html_js_1.default;
 exports.xmlDecodeTree = decode_data_xml_js_1.default;
-var decode_codepoint_js_1 = __importStar(require("./decode_codepoint.js"));
-Object.defineProperty(exports, "decodeCodePoint", { enumerable: true, get: function () { return decode_codepoint_js_1.default; } });
-Object.defineProperty(exports, "replaceCodePoint", { enumerable: true, get: function () { return decode_codepoint_js_1.replaceCodePoint; } });
+var decode_codepoint_js_1 = __importDefault(require("./decode_codepoint.js"));
+exports.decodeCodePoint = decode_codepoint_js_1.default;
+var decode_codepoint_js_2 = require("./decode_codepoint.js");
+Object.defineProperty(exports, "replaceCodePoint", { enumerable: true, get: function () { return decode_codepoint_js_2.replaceCodePoint; } });
+Object.defineProperty(exports, "fromCodePoint", { enumerable: true, get: function () { return decode_codepoint_js_2.fromCodePoint; } });
+var CharCodes;
+(function (CharCodes) {
+    CharCodes[CharCodes["NUM"] = 35] = "NUM";
+    CharCodes[CharCodes["SEMI"] = 59] = "SEMI";
+    CharCodes[CharCodes["ZERO"] = 48] = "ZERO";
+    CharCodes[CharCodes["NINE"] = 57] = "NINE";
+    CharCodes[CharCodes["LOWER_A"] = 97] = "LOWER_A";
+    CharCodes[CharCodes["LOWER_F"] = 102] = "LOWER_F";
+    CharCodes[CharCodes["LOWER_X"] = 120] = "LOWER_X";
+    /** Bit that needs to be set to convert an upper case ASCII character to lower case */
+    CharCodes[CharCodes["To_LOWER_BIT"] = 32] = "To_LOWER_BIT";
+})(CharCodes || (CharCodes = {}));
 var BinTrieFlags;
@@ -56,3 +47,3 @@ (function (BinTrieFlags) {
             // If we have a numeric entity, handle this separately.
-            if (str.charCodeAt(strIdx) === 35 /* NUM */) {
+            if (str.charCodeAt(strIdx) === CharCodes.NUM) {
                 // Skip the leading "&#". For hex entities, also skip the leading "x".
@@ -62,3 +53,3 @@ var start = strIdx + 1;
                 var cp = str.charCodeAt(start);
-                if ((cp | 32 /* To_LOWER_BIT */) === 120 /* LOWER_X */) {
+                if ((cp | CharCodes.To_LOWER_BIT) === CharCodes.LOWER_X) {
                     base = 16;
@@ -70,10 +61,10 @@ strIdx += 1;
                     cp = str.charCodeAt(++strIdx);
-                while ((cp >= 48 /* ZERO */ && cp <= 57 /* NINE */) ||
+                while ((cp >= CharCodes.ZERO && cp <= CharCodes.NINE) ||
                     (base === 16 &&
-                        (cp | 32 /* To_LOWER_BIT */) >= 97 /* LOWER_A */ &&
-                        (cp | 32 /* To_LOWER_BIT */) <= 102 /* LOWER_F */));
+                        (cp | CharCodes.To_LOWER_BIT) >= CharCodes.LOWER_A &&
+                        (cp | CharCodes.To_LOWER_BIT) <= CharCodes.LOWER_F));
                 if (start !== strIdx) {
                     var entity = str.substring(start, strIdx);
                     var parsed = parseInt(entity, base);
-                    if (str.charCodeAt(strIdx) === 59 /* SEMI */) {
+                    if (str.charCodeAt(strIdx) === CharCodes.SEMI) {
                         strIdx += 1;
@@ -102,3 +93,3 @@ }
                     // If we have a legacy entity while parsing strictly, just skip the number of bytes
-                    if (!strict || str.charCodeAt(strIdx) === 59 /* SEMI */) {
+                    if (!strict || str.charCodeAt(strIdx) === CharCodes.SEMI) {
                         resultIdx = treeIdx;
@@ -105,0 +96,0 @@ excess = 0;

lib/encode.d.ts

 /**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using XML entities.
- *
- * If a character has no equivalent entity, a
- * numeric hexadecimal reference (eg. `ü`) will be used.
- */
-export declare function encodeXML(str: string): string;
-/**
  * Encodes all entities and non-ASCII characters in the input.
@@ -28,34 +20,2 @@ *
 export declare function encodeNonAsciiHTML(data: string): string;
-/**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using numeric hexadecimal reference (eg. `ü`).
- *
- * Have a look at `escapeUTF8` if you want a more concise output at the expense
- * of reduced transportability.
- *
- * @param data String to escape.
- */
-export declare const escape: typeof encodeXML;
-/**
- * Encodes all characters not valid in XML documents using XML entities.
- *
- * Note that the output will be character-set dependent.
- *
- * @param data String to escape.
- */
-export declare const escapeUTF8: (data: string) => string;
-/**
- * Encodes all characters that have to be escaped in HTML attributes,
- * following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
- *
- * @param data String to escape.
- */
-export declare const escapeAttribute: (data: string) => string;
-/**
- * Encodes all characters that have to be escaped in HTML text,
- * following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
- *
- * @param data String to escape.
- */
-export declare const escapeText: (data: string) => string;
 //# sourceMappingURL=encode.d.ts.map

lib/encode.js

 "use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.escapeText = exports.escapeAttribute = exports.escapeUTF8 = exports.escape = exports.encodeNonAsciiHTML = exports.encodeHTML = exports.encodeXML = void 0;
-var encode_trie_js_1 = require("./encode-trie.js");
+exports.encodeNonAsciiHTML = exports.encodeHTML = void 0;
+var encode_html_js_1 = __importDefault(require("./generated/encode-html.js"));
+var escape_js_1 = require("./escape.js");
 var htmlReplacer = /[\t\n!-,./:-@[-`\f{-}$\x80-\uFFFF]/g;
-var xmlReplacer = /["&'<>$\x80-\uFFFF]/g;
-var xmlCodeMap = new Map([
-    [34, "&quot;"],
-    [38, "&amp;"],
-    [39, "&apos;"],
-    [60, "&lt;"],
-    [62, "&gt;"],
-]);
 /**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using XML entities.
- *
- * If a character has no equivalent entity, a
- * numeric hexadecimal reference (eg. `&#xfc;`) will be used.
- */
-function encodeXML(str) {
-    var ret = "";
-    var lastIdx = 0;
-    var match;
-    while ((match = xmlReplacer.exec(str)) !== null) {
-        var i = match.index;
-        var char = str.charCodeAt(i);
-        var next = xmlCodeMap.get(char);
-        if (next !== undefined) {
-            ret += str.substring(lastIdx, i) + next;
-            lastIdx = i + 1;
-        }
-        else {
-            ret += "".concat(str.substring(lastIdx, i), "&#x").concat((0, encode_trie_js_1.getCodePoint)(str, i).toString(16), ";");
-            // Increase by 1 if we have a surrogate pair
-            lastIdx = xmlReplacer.lastIndex += Number((char & 65408) === 0xd800);
-        }
-    }
-    return ret + str.substr(lastIdx);
-}
-exports.encodeXML = encodeXML;
-/**
  * Encodes all entities and non-ASCII characters in the input.
@@ -53,3 +21,3 @@ *
 function encodeHTML(data) {
-    return (0, encode_trie_js_1.encodeHTMLTrieRe)(htmlReplacer, data);
+    return encodeHTMLTrieRe(htmlReplacer, data);
 }
@@ -65,63 +33,45 @@ exports.encodeHTML = encodeHTML;
 function encodeNonAsciiHTML(data) {
-    return (0, encode_trie_js_1.encodeHTMLTrieRe)(xmlReplacer, data);
+    return encodeHTMLTrieRe(escape_js_1.xmlReplacer, data);
 }
 exports.encodeNonAsciiHTML = encodeNonAsciiHTML;
-/**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using numeric hexadecimal reference (eg. `&#xfc;`).
- *
- * Have a look at `escapeUTF8` if you want a more concise output at the expense
- * of reduced transportability.
- *
- * @param data String to escape.
- */
-exports.escape = encodeXML;
-function getEscaper(regex, map) {
-    return function escape(data) {
-        var match;
-        var lastIdx = 0;
-        var result = "";
-        while ((match = regex.exec(data))) {
-            if (lastIdx !== match.index) {
-                result += data.substring(lastIdx, match.index);
+function encodeHTMLTrieRe(regExp, str) {
+    var ret = "";
+    var lastIdx = 0;
+    var match;
+    while ((match = regExp.exec(str)) !== null) {
+        var i = match.index;
+        ret += str.substring(lastIdx, i);
+        var char = str.charCodeAt(i);
+        var next = encode_html_js_1.default.get(char);
+        if (typeof next === "object") {
+            // We are in a branch. Try to match the next char.
+            if (i + 1 < str.length) {
+                var nextChar = str.charCodeAt(i + 1);
+                var value = typeof next.n === "number"
+                    ? next.n === nextChar
+                        ? next.o
+                        : undefined
+                    : next.n.get(nextChar);
+                if (value !== undefined) {
+                    ret += value;
+                    lastIdx = regExp.lastIndex += 1;
+                    continue;
+                }
             }
-            // We know that this chararcter will be in the map.
-            result += map.get(match[0].charCodeAt(0));
-            // Every match will be of length 1
-            lastIdx = match.index + 1;
+            next = next.v;
         }
-        return result + data.substring(lastIdx);
-    };
+        // We might have a tree node without a value; skip and use a numeric entitiy.
+        if (next !== undefined) {
+            ret += next;
+            lastIdx = i + 1;
+        }
+        else {
+            var cp = (0, escape_js_1.getCodePoint)(str, i);
+            ret += "&#x".concat(cp.toString(16), ";");
+            // Increase by 1 if we have a surrogate pair
+            lastIdx = regExp.lastIndex += Number(cp !== char);
+        }
+    }
+    return ret + str.substr(lastIdx);
 }
-/**
- * Encodes all characters not valid in XML documents using XML entities.
- *
- * Note that the output will be character-set dependent.
- *
- * @param data String to escape.
- */
-exports.escapeUTF8 = getEscaper(/[&<>'"]/g, xmlCodeMap);
-/**
- * Encodes all characters that have to be escaped in HTML attributes,
- * following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
- *
- * @param data String to escape.
- */
-exports.escapeAttribute = getEscaper(/["&\u00A0]/g, new Map([
-    [34, "&quot;"],
-    [38, "&amp;"],
-    [160, "&nbsp;"],
-]));
-/**
- * Encodes all characters that have to be escaped in HTML text,
- * following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
- *
- * @param data String to escape.
- */
-exports.escapeText = getEscaper(/[&<>\u00A0]/g, new Map([
-    [38, "&amp;"],
-    [60, "&lt;"],
-    [62, "&gt;"],
-    [160, "&nbsp;"],
-]));
 //# sourceMappingURL=encode.js.map

lib/esm/decode_codepoint.d.ts

@@ -0,3 +1,4 @@
+export declare const fromCodePoint: (...codePoints: number[]) => string;
 export declare function replaceCodePoint(codePoint: number): number;
 export default function decodeCodePoint(codePoint: number): string;
 //# sourceMappingURL=decode_codepoint.d.ts.map

lib/esm/decode_codepoint.js

@@ -33,3 +33,3 @@ // Adapted from https://github.com/mathiasbynens/he/blob/36afe179392226cf1b6ccdb16ebbb7a5a844d93a/src/he.js#L106-L134
 ]);
-const fromCodePoint = 
+export const fromCodePoint = 
 // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition, node/no-unsupported-features/es-builtins
@@ -36,0 +36,0 @@ (_a = String.fromCodePoint) !== null && _a !== void 0 ? _a : function (codePoint) {

lib/esm/decode.d.ts

 import htmlDecodeTree from "./generated/decode-data-html.js";
 import xmlDecodeTree from "./generated/decode-data-xml.js";
-import { default as decodeCodePoint, replaceCodePoint } from "./decode_codepoint.js";
-export { htmlDecodeTree, xmlDecodeTree, decodeCodePoint, replaceCodePoint };
+import decodeCodePoint from "./decode_codepoint.js";
+export { htmlDecodeTree, xmlDecodeTree, decodeCodePoint };
+export { replaceCodePoint, fromCodePoint } from "./decode_codepoint.js";
 export declare enum BinTrieFlags {
@@ -6,0 +7,0 @@ VALUE_LENGTH = 49152,

lib/esm/decode.js

 import htmlDecodeTree from "./generated/decode-data-html.js";
 import xmlDecodeTree from "./generated/decode-data-xml.js";
-import { default as decodeCodePoint, replaceCodePoint, } from "./decode_codepoint.js";
+import decodeCodePoint from "./decode_codepoint.js";
 // Re-export for use by eg. htmlparser2
-export { htmlDecodeTree, xmlDecodeTree, decodeCodePoint, replaceCodePoint };
+export { htmlDecodeTree, xmlDecodeTree, decodeCodePoint };
+export { replaceCodePoint, fromCodePoint } from "./decode_codepoint.js";
+var CharCodes;
+(function (CharCodes) {
+    CharCodes[CharCodes["NUM"] = 35] = "NUM";
+    CharCodes[CharCodes["SEMI"] = 59] = "SEMI";
+    CharCodes[CharCodes["ZERO"] = 48] = "ZERO";
+    CharCodes[CharCodes["NINE"] = 57] = "NINE";
+    CharCodes[CharCodes["LOWER_A"] = 97] = "LOWER_A";
+    CharCodes[CharCodes["LOWER_F"] = 102] = "LOWER_F";
+    CharCodes[CharCodes["LOWER_X"] = 120] = "LOWER_X";
+    /** Bit that needs to be set to convert an upper case ASCII character to lower case */
+    CharCodes[CharCodes["To_LOWER_BIT"] = 32] = "To_LOWER_BIT";
+})(CharCodes || (CharCodes = {}));
 export var BinTrieFlags;
@@ -23,3 +36,3 @@ (function (BinTrieFlags) {
             // If we have a numeric entity, handle this separately.
-            if (str.charCodeAt(strIdx) === 35 /* NUM */) {
+            if (str.charCodeAt(strIdx) === CharCodes.NUM) {
                 // Skip the leading "&#". For hex entities, also skip the leading "x".
@@ -29,3 +42,3 @@ let start = strIdx + 1;
                 let cp = str.charCodeAt(start);
-                if ((cp | 32 /* To_LOWER_BIT */) === 120 /* LOWER_X */) {
+                if ((cp | CharCodes.To_LOWER_BIT) === CharCodes.LOWER_X) {
                     base = 16;
@@ -37,10 +50,10 @@ strIdx += 1;
                     cp = str.charCodeAt(++strIdx);
-                while ((cp >= 48 /* ZERO */ && cp <= 57 /* NINE */) ||
+                while ((cp >= CharCodes.ZERO && cp <= CharCodes.NINE) ||
                     (base === 16 &&
-                        (cp | 32 /* To_LOWER_BIT */) >= 97 /* LOWER_A */ &&
-                        (cp | 32 /* To_LOWER_BIT */) <= 102 /* LOWER_F */));
+                        (cp | CharCodes.To_LOWER_BIT) >= CharCodes.LOWER_A &&
+                        (cp | CharCodes.To_LOWER_BIT) <= CharCodes.LOWER_F));
                 if (start !== strIdx) {
                     const entity = str.substring(start, strIdx);
                     const parsed = parseInt(entity, base);
-                    if (str.charCodeAt(strIdx) === 59 /* SEMI */) {
+                    if (str.charCodeAt(strIdx) === CharCodes.SEMI) {
                         strIdx += 1;
@@ -69,3 +82,3 @@ }
                     // If we have a legacy entity while parsing strictly, just skip the number of bytes
-                    if (!strict || str.charCodeAt(strIdx) === 59 /* SEMI */) {
+                    if (!strict || str.charCodeAt(strIdx) === CharCodes.SEMI) {
                         resultIdx = treeIdx;
@@ -72,0 +85,0 @@ excess = 0;

lib/esm/encode.d.ts

 /**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using XML entities.
- *
- * If a character has no equivalent entity, a
- * numeric hexadecimal reference (eg. `ü`) will be used.
- */
-export declare function encodeXML(str: string): string;
-/**
  * Encodes all entities and non-ASCII characters in the input.
@@ -28,34 +20,2 @@ *
 export declare function encodeNonAsciiHTML(data: string): string;
-/**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using numeric hexadecimal reference (eg. `ü`).
- *
- * Have a look at `escapeUTF8` if you want a more concise output at the expense
- * of reduced transportability.
- *
- * @param data String to escape.
- */
-export declare const escape: typeof encodeXML;
-/**
- * Encodes all characters not valid in XML documents using XML entities.
- *
- * Note that the output will be character-set dependent.
- *
- * @param data String to escape.
- */
-export declare const escapeUTF8: (data: string) => string;
-/**
- * Encodes all characters that have to be escaped in HTML attributes,
- * following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
- *
- * @param data String to escape.
- */
-export declare const escapeAttribute: (data: string) => string;
-/**
- * Encodes all characters that have to be escaped in HTML text,
- * following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
- *
- * @param data String to escape.
- */
-export declare const escapeText: (data: string) => string;
 //# sourceMappingURL=encode.d.ts.map

lib/esm/encode.js

@@ -1,39 +0,5 @@
-import { encodeHTMLTrieRe, getCodePoint } from "./encode-trie.js";
+import htmlTrie from "./generated/encode-html.js";
+import { xmlReplacer, getCodePoint } from "./escape.js";
 const htmlReplacer = /[\t\n!-,./:-@[-`\f{-}$\x80-\uFFFF]/g;
-const xmlReplacer = /["&'<>$\x80-\uFFFF]/g;
-const xmlCodeMap = new Map([
-    [34, "&quot;"],
-    [38, "&amp;"],
-    [39, "&apos;"],
-    [60, "&lt;"],
-    [62, "&gt;"],
-]);
 /**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using XML entities.
- *
- * If a character has no equivalent entity, a
- * numeric hexadecimal reference (eg. `&#xfc;`) will be used.
- */
-export function encodeXML(str) {
-    let ret = "";
-    let lastIdx = 0;
-    let match;
-    while ((match = xmlReplacer.exec(str)) !== null) {
-        const i = match.index;
-        const char = str.charCodeAt(i);
-        const next = xmlCodeMap.get(char);
-        if (next !== undefined) {
-            ret += str.substring(lastIdx, i) + next;
-            lastIdx = i + 1;
-        }
-        else {
-            ret += `${str.substring(lastIdx, i)}&#x${getCodePoint(str, i).toString(16)};`;
-            // Increase by 1 if we have a surrogate pair
-            lastIdx = xmlReplacer.lastIndex += Number((char & 65408) === 0xd800);
-        }
-    }
-    return ret + str.substr(lastIdx);
-}
-/**
  * Encodes all entities and non-ASCII characters in the input.
@@ -61,60 +27,42 @@ *
 }
-/**
- * Encodes all non-ASCII characters, as well as characters not valid in XML
- * documents using numeric hexadecimal reference (eg. `&#xfc;`).
- *
- * Have a look at `escapeUTF8` if you want a more concise output at the expense
- * of reduced transportability.
- *
- * @param data String to escape.
- */
-export const escape = encodeXML;
-function getEscaper(regex, map) {
-    return function escape(data) {
-        let match;
-        let lastIdx = 0;
-        let result = "";
-        while ((match = regex.exec(data))) {
-            if (lastIdx !== match.index) {
-                result += data.substring(lastIdx, match.index);
+function encodeHTMLTrieRe(regExp, str) {
+    let ret = "";
+    let lastIdx = 0;
+    let match;
+    while ((match = regExp.exec(str)) !== null) {
+        const i = match.index;
+        ret += str.substring(lastIdx, i);
+        const char = str.charCodeAt(i);
+        let next = htmlTrie.get(char);
+        if (typeof next === "object") {
+            // We are in a branch. Try to match the next char.
+            if (i + 1 < str.length) {
+                const nextChar = str.charCodeAt(i + 1);
+                const value = typeof next.n === "number"
+                    ? next.n === nextChar
+                        ? next.o
+                        : undefined
+                    : next.n.get(nextChar);
+                if (value !== undefined) {
+                    ret += value;
+                    lastIdx = regExp.lastIndex += 1;
+                    continue;
+                }
             }
-            // We know that this chararcter will be in the map.
-            result += map.get(match[0].charCodeAt(0));
-            // Every match will be of length 1
-            lastIdx = match.index + 1;
+            next = next.v;
         }
-        return result + data.substring(lastIdx);
-    };
+        // We might have a tree node without a value; skip and use a numeric entitiy.
+        if (next !== undefined) {
+            ret += next;
+            lastIdx = i + 1;
+        }
+        else {
+            const cp = getCodePoint(str, i);
+            ret += `&#x${cp.toString(16)};`;
+            // Increase by 1 if we have a surrogate pair
+            lastIdx = regExp.lastIndex += Number(cp !== char);
+        }
+    }
+    return ret + str.substr(lastIdx);
 }
-/**
- * Encodes all characters not valid in XML documents using XML entities.
- *
- * Note that the output will be character-set dependent.
- *
- * @param data String to escape.
- */
-export const escapeUTF8 = getEscaper(/[&<>'"]/g, xmlCodeMap);
-/**
- * Encodes all characters that have to be escaped in HTML attributes,
- * following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
- *
- * @param data String to escape.
- */
-export const escapeAttribute = getEscaper(/["&\u00A0]/g, new Map([
-    [34, "&quot;"],
-    [38, "&amp;"],
-    [160, "&nbsp;"],
-]));
-/**
- * Encodes all characters that have to be escaped in HTML text,
- * following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
- *
- * @param data String to escape.
- */
-export const escapeText = getEscaper(/[&<>\u00A0]/g, new Map([
-    [38, "&amp;"],
-    [60, "&lt;"],
-    [62, "&gt;"],
-    [160, "&nbsp;"],
-]));
 //# sourceMappingURL=encode.js.map

lib/esm/index.d.ts

@@ -99,4 +99,5 @@ /** The level of entities to support. */
 export declare function encode(data: string, options?: EncodingOptions | EntityLevel): string;
-export { encodeXML, encodeHTML, encodeNonAsciiHTML, escape, escapeUTF8, escapeAttribute, escapeText, encodeHTML as encodeHTML4, encodeHTML as encodeHTML5, } from "./encode.js";
+export { encodeXML, escape, escapeUTF8, escapeAttribute, escapeText, } from "./escape.js";
+export { encodeHTML, encodeNonAsciiHTML, encodeHTML as encodeHTML4, encodeHTML as encodeHTML5, } from "./encode.js";
 export { decodeXML, decodeHTML, decodeHTMLStrict, decodeHTML as decodeHTML4, decodeHTML as decodeHTML5, decodeHTMLStrict as decodeHTML4Strict, decodeHTMLStrict as decodeHTML5Strict, decodeXML as decodeXMLStrict, } from "./decode.js";
 //# sourceMappingURL=index.d.ts.map

lib/esm/index.js

 import { decodeXML, decodeHTML, decodeHTMLStrict } from "./decode.js";
-import { encodeXML, escapeUTF8, encodeHTML, encodeNonAsciiHTML, escapeAttribute, escapeText, } from "./encode.js";
+import { encodeHTML, encodeNonAsciiHTML } from "./encode.js";
+import { encodeXML, escapeUTF8, escapeAttribute, escapeText, } from "./escape.js";
 /** The level of entities to support. */
@@ -105,3 +106,4 @@ export var EntityLevel;
 }
-export { encodeXML, encodeHTML, encodeNonAsciiHTML, escape, escapeUTF8, escapeAttribute, escapeText, 
+export { encodeXML, escape, escapeUTF8, escapeAttribute, escapeText, } from "./escape.js";
+export { encodeHTML, encodeNonAsciiHTML, 
 // Legacy aliases (deprecated)
@@ -108,0 +110,0 @@ encodeHTML as encodeHTML4, encodeHTML as encodeHTML5, } from "./encode.js";

lib/index.d.ts

@@ -99,4 +99,5 @@ /** The level of entities to support. */
 export declare function encode(data: string, options?: EncodingOptions | EntityLevel): string;
-export { encodeXML, encodeHTML, encodeNonAsciiHTML, escape, escapeUTF8, escapeAttribute, escapeText, encodeHTML as encodeHTML4, encodeHTML as encodeHTML5, } from "./encode.js";
+export { encodeXML, escape, escapeUTF8, escapeAttribute, escapeText, } from "./escape.js";
+export { encodeHTML, encodeNonAsciiHTML, encodeHTML as encodeHTML4, encodeHTML as encodeHTML5, } from "./encode.js";
 export { decodeXML, decodeHTML, decodeHTMLStrict, decodeHTML as decodeHTML4, decodeHTML as decodeHTML5, decodeHTMLStrict as decodeHTML4Strict, decodeHTMLStrict as decodeHTML5Strict, decodeXML as decodeXMLStrict, } from "./decode.js";
 //# sourceMappingURL=index.d.ts.map

lib/index.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.decodeXMLStrict = exports.decodeHTML5Strict = exports.decodeHTML4Strict = exports.decodeHTML5 = exports.decodeHTML4 = exports.decodeHTMLStrict = exports.decodeHTML = exports.decodeXML = exports.encodeHTML5 = exports.encodeHTML4 = exports.escapeText = exports.escapeAttribute = exports.escapeUTF8 = exports.escape = exports.encodeNonAsciiHTML = exports.encodeHTML = exports.encodeXML = exports.encode = exports.decodeStrict = exports.decode = exports.EncodingMode = exports.DecodingMode = exports.EntityLevel = void 0;
+exports.decodeXMLStrict = exports.decodeHTML5Strict = exports.decodeHTML4Strict = exports.decodeHTML5 = exports.decodeHTML4 = exports.decodeHTMLStrict = exports.decodeHTML = exports.decodeXML = exports.encodeHTML5 = exports.encodeHTML4 = exports.encodeNonAsciiHTML = exports.encodeHTML = exports.escapeText = exports.escapeAttribute = exports.escapeUTF8 = exports.escape = exports.encodeXML = exports.encode = exports.decodeStrict = exports.decode = exports.EncodingMode = exports.DecodingMode = exports.EntityLevel = void 0;
 var decode_js_1 = require("./decode.js");
 var encode_js_1 = require("./encode.js");
+var escape_js_1 = require("./escape.js");
 /** The level of entities to support. */
@@ -99,7 +100,7 @@ var EntityLevel;
     if (opts.mode === EncodingMode.UTF8)
-        return (0, encode_js_1.escapeUTF8)(data);
+        return (0, escape_js_1.escapeUTF8)(data);
     if (opts.mode === EncodingMode.Attribute)
-        return (0, encode_js_1.escapeAttribute)(data);
+        return (0, escape_js_1.escapeAttribute)(data);
     if (opts.mode === EncodingMode.Text)
-        return (0, encode_js_1.escapeText)(data);
+        return (0, escape_js_1.escapeText)(data);
     if (opts.level === EntityLevel.HTML) {
@@ -112,13 +113,14 @@ if (opts.mode === EncodingMode.ASCII) {
     // ASCII and Extensive are equivalent
-    return (0, encode_js_1.encodeXML)(data);
+    return (0, escape_js_1.encodeXML)(data);
 }
 exports.encode = encode;
+var escape_js_2 = require("./escape.js");
+Object.defineProperty(exports, "encodeXML", { enumerable: true, get: function () { return escape_js_2.encodeXML; } });
+Object.defineProperty(exports, "escape", { enumerable: true, get: function () { return escape_js_2.escape; } });
+Object.defineProperty(exports, "escapeUTF8", { enumerable: true, get: function () { return escape_js_2.escapeUTF8; } });
+Object.defineProperty(exports, "escapeAttribute", { enumerable: true, get: function () { return escape_js_2.escapeAttribute; } });
+Object.defineProperty(exports, "escapeText", { enumerable: true, get: function () { return escape_js_2.escapeText; } });
 var encode_js_2 = require("./encode.js");
-Object.defineProperty(exports, "encodeXML", { enumerable: true, get: function () { return encode_js_2.encodeXML; } });
 Object.defineProperty(exports, "encodeHTML", { enumerable: true, get: function () { return encode_js_2.encodeHTML; } });
 Object.defineProperty(exports, "encodeNonAsciiHTML", { enumerable: true, get: function () { return encode_js_2.encodeNonAsciiHTML; } });
-Object.defineProperty(exports, "escape", { enumerable: true, get: function () { return encode_js_2.escape; } });
-Object.defineProperty(exports, "escapeUTF8", { enumerable: true, get: function () { return encode_js_2.escapeUTF8; } });
-Object.defineProperty(exports, "escapeAttribute", { enumerable: true, get: function () { return encode_js_2.escapeAttribute; } });
-Object.defineProperty(exports, "escapeText", { enumerable: true, get: function () { return encode_js_2.escapeText; } });
 // Legacy aliases (deprecated)
@@ -125,0 +127,0 @@ Object.defineProperty(exports, "encodeHTML4", { enumerable: true, get: function () { return encode_js_2.encodeHTML; } });

package.json

 {
     "name": "entities",
-    "version": "4.2.0",
+    "version": "4.3.0",
     "description": "Encode & decode XML and HTML entities with ease & speed",
@@ -30,2 +30,6 @@ "author": "Felix Boehm <[e-mail]>",
             "import": "./lib/esm/decode.js"
+        },
+        "./lib/escape.js": {
+            "require": "./lib/escape.js",
+            "import": "./lib/esm/escape.js"
         }
@@ -50,3 +54,3 @@ },
         "ts-jest": "^27.1.4",
-        "typedoc": "^0.22.13",
+        "typedoc": "^0.22.14",
         "typescript": "^4.6.3"
@@ -65,4 +69,4 @@ },
         "build": "npm run build:cjs && npm run build:esm",
-        "build:cjs": "tsc",
-        "build:esm": "tsc --module esnext --target es2019 --outDir lib/esm && echo '{\"type\":\"module\"}' > lib/esm/package.json",
+        "build:cjs": "tsc --sourceRoot https://raw.githubusercontent.com/fb55/entities/$(git rev-parse HEAD)/src/",
+        "build:esm": "npm run build:cjs -- --module esnext --target es2019 --outDir lib/esm && echo '{\"type\":\"module\"}' > lib/esm/package.json",
         "build:docs": "typedoc --hideGenerator src/index.ts",
@@ -69,0 +73,0 @@ "build:trie": "ts-node scripts/write-decode-map.ts",

No alert changes

Improved metrics

Total package byte prevSize

730095

increased by0.55%

Lines of code

2157

increased by0.33%

No dependency changes