entities - npm Package Compare versions

Comparing version 2.2.0 to 3.0.0

lib/decode_codepoint.js

 "use strict";
-var __importDefault = (this && this.__importDefault) || function (mod) {
-    return (mod && mod.__esModule) ? mod : { "default": mod };
-};
+// Adapted from https://github.com/mathiasbynens/he/blob/36afe179392226cf1b6ccdb16ebbb7a5a844d93a/src/he.js#L106-L134
 Object.defineProperty(exports, "__esModule", { value: true });
-var decode_json_1 = __importDefault(require("./maps/decode.json"));
-// Adapted from https://github.com/mathiasbynens/he/blob/master/src/he.js#L94-L119
+var decodeMap = new Map([
+    [0, 65533],
+    [128, 8364],
+    [130, 8218],
+    [131, 402],
+    [132, 8222],
+    [133, 8230],
+    [134, 8224],
+    [135, 8225],
+    [136, 710],
+    [137, 8240],
+    [138, 352],
+    [139, 8249],
+    [140, 338],
+    [142, 381],
+    [145, 8216],
+    [146, 8217],
+    [147, 8220],
+    [148, 8221],
+    [149, 8226],
+    [150, 8211],
+    [151, 8212],
+    [152, 732],
+    [153, 8482],
+    [154, 353],
+    [155, 8250],
+    [156, 339],
+    [158, 382],
+    [159, 376],
+]);
 var fromCodePoint = 
-// eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
+// eslint-disable-next-line @typescript-eslint/no-unnecessary-condition, node/no-unsupported-features/es-builtins
 String.fromCodePoint ||
@@ -22,10 +48,8 @@ function (codePoint) {
 function decodeCodePoint(codePoint) {
+    var _a;
     if ((codePoint >= 0xd800 && codePoint <= 0xdfff) || codePoint > 0x10ffff) {
         return "\uFFFD";
     }
-    if (codePoint in decode_json_1.default) {
-        codePoint = decode_json_1.default[codePoint];
-    }
-    return fromCodePoint(codePoint);
+    return fromCodePoint((_a = decodeMap.get(codePoint)) !== null && _a !== void 0 ? _a : codePoint);
 }
 exports.default = decodeCodePoint;

lib/decode.d.ts

@@ -1,5 +0,27 @@
-export declare const decodeXML: (str: string) => string;
-export declare const decodeHTMLStrict: (str: string) => string;
-export declare type MapType = Record<string, string>;
-export declare const decodeHTML: (str: string) => string;
+import htmlDecodeTree from "./generated/decode-data-html";
+import xmlDecodeTree from "./generated/decode-data-xml";
+export { htmlDecodeTree, xmlDecodeTree };
+export declare enum CharCodes {
+    NUM,
+    SEMI,
+    ZERO,
+    NINE,
+    LOWER_A,
+    UPPER_A,
+    LOWER_F,
+    UPPER_F,
+    LOWER_X,
+    UPPER_X
+}
+export declare enum BinTrieFlags {
+    HAS_VALUE = 32768,
+    BRANCH_LENGTH = 32512,
+    MULTI_BYTE = 128,
+    JUMP_TABLE = 127
+}
+export declare const JUMP_OFFSET_BASE: number;
+export declare function determineBranch(decodeTree: Uint16Array, current: number, nodeIdx: number, char: number): number;
+export declare function decodeHTML(str: string): string;
+export declare function decodeHTMLStrict(str: string): string;
+export declare function decodeXML(str: string): string;
 //# sourceMappingURL=decode.d.ts.map

lib/decode.js

@@ -6,49 +6,155 @@ "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.decodeHTML = exports.decodeHTMLStrict = exports.decodeXML = void 0;
-var entities_json_1 = __importDefault(require("./maps/entities.json"));
-var legacy_json_1 = __importDefault(require("./maps/legacy.json"));
-var xml_json_1 = __importDefault(require("./maps/xml.json"));
+exports.decodeXML = exports.decodeHTMLStrict = exports.decodeHTML = exports.determineBranch = exports.JUMP_OFFSET_BASE = exports.BinTrieFlags = exports.CharCodes = exports.xmlDecodeTree = exports.htmlDecodeTree = void 0;
+var decode_data_html_1 = __importDefault(require("./generated/decode-data-html"));
+exports.htmlDecodeTree = decode_data_html_1.default;
+var decode_data_xml_1 = __importDefault(require("./generated/decode-data-xml"));
+exports.xmlDecodeTree = decode_data_xml_1.default;
 var decode_codepoint_1 = __importDefault(require("./decode_codepoint"));
-var strictEntityRe = /&(?:[a-zA-Z0-9]+|#[xX][\da-fA-F]+|#\d+);/g;
-exports.decodeXML = getStrictDecoder(xml_json_1.default);
-exports.decodeHTMLStrict = getStrictDecoder(entities_json_1.default);
-function getStrictDecoder(map) {
-    var replace = getReplacer(map);
-    return function (str) { return String(str).replace(strictEntityRe, replace); };
+var CharCodes;
+(function (CharCodes) {
+    CharCodes[CharCodes["NUM"] = "#".charCodeAt(0)] = "NUM";
+    CharCodes[CharCodes["SEMI"] = ";".charCodeAt(0)] = "SEMI";
+    CharCodes[CharCodes["ZERO"] = "0".charCodeAt(0)] = "ZERO";
+    CharCodes[CharCodes["NINE"] = "9".charCodeAt(0)] = "NINE";
+    CharCodes[CharCodes["LOWER_A"] = "a".charCodeAt(0)] = "LOWER_A";
+    CharCodes[CharCodes["UPPER_A"] = "A".charCodeAt(0)] = "UPPER_A";
+    CharCodes[CharCodes["LOWER_F"] = "f".charCodeAt(0)] = "LOWER_F";
+    CharCodes[CharCodes["UPPER_F"] = "F".charCodeAt(0)] = "UPPER_F";
+    CharCodes[CharCodes["LOWER_X"] = "x".charCodeAt(0)] = "LOWER_X";
+    CharCodes[CharCodes["UPPER_X"] = "X".charCodeAt(0)] = "UPPER_X";
+})(CharCodes = exports.CharCodes || (exports.CharCodes = {}));
+var BinTrieFlags;
+(function (BinTrieFlags) {
+    BinTrieFlags[BinTrieFlags["HAS_VALUE"] = 32768] = "HAS_VALUE";
+    BinTrieFlags[BinTrieFlags["BRANCH_LENGTH"] = 32512] = "BRANCH_LENGTH";
+    BinTrieFlags[BinTrieFlags["MULTI_BYTE"] = 128] = "MULTI_BYTE";
+    BinTrieFlags[BinTrieFlags["JUMP_TABLE"] = 127] = "JUMP_TABLE";
+})(BinTrieFlags = exports.BinTrieFlags || (exports.BinTrieFlags = {}));
+exports.JUMP_OFFSET_BASE = CharCodes.ZERO - 1;
+function getDecoder(decodeTree) {
+    return function decodeHTMLBinary(str, strict) {
+        var ret = "";
+        var lastIdx = 0;
+        var strIdx = 0;
+        while ((strIdx = str.indexOf("&", strIdx)) >= 0) {
+            ret += str.slice(lastIdx, strIdx);
+            lastIdx = strIdx;
+            // Skip the "&"
+            strIdx += 1;
+            // If we have a numeric entity, handle this separately.
+            if (str.charCodeAt(strIdx) === CharCodes.NUM) {
+                // Skip the leading "&#". For hex entities, also skip the leading "x".
+                var start = strIdx + 1;
+                var base = 10;
+                var cp = str.charCodeAt(start);
+                if (cp === CharCodes.LOWER_X || cp === CharCodes.UPPER_X) {
+                    base = 16;
+                    strIdx += 1;
+                    start += 1;
+                }
+                while (((cp = str.charCodeAt(++strIdx)) >= CharCodes.ZERO &&
+                    cp <= CharCodes.NINE) ||
+                    (base === 16 &&
+                        ((cp >= CharCodes.LOWER_A && cp <= CharCodes.LOWER_F) ||
+                            (cp >= CharCodes.UPPER_A &&
+                                cp <= CharCodes.UPPER_F))))
+                    ;
+                if (start !== strIdx) {
+                    var entity = str.substring(start, strIdx);
+                    var parsed = parseInt(entity, base);
+                    if (str.charCodeAt(strIdx) === CharCodes.SEMI) {
+                        strIdx += 1;
+                    }
+                    else if (strict) {
+                        continue;
+                    }
+                    ret += decode_codepoint_1.default(parsed);
+                    lastIdx = strIdx;
+                }
+                continue;
+            }
+            var result = null;
+            var excess = 1;
+            var treeIdx = 0;
+            var current = decodeTree[treeIdx];
+            for (; strIdx < str.length; strIdx++, excess++) {
+                treeIdx = determineBranch(decodeTree, current, treeIdx + 1, str.charCodeAt(strIdx));
+                if (treeIdx < 0)
+                    break;
+                current = decodeTree[treeIdx];
+                // If the branch is a value, store it and continue
+                if (current & BinTrieFlags.HAS_VALUE) {
+                    // If we have a legacy entity while parsing strictly, just skip the number of bytes
+                    if (strict && str.charCodeAt(strIdx) !== CharCodes.SEMI) {
+                        // No need to consider multi-byte values, as the legacy entity is always a single byte
+                        treeIdx += 1;
+                    }
+                    else {
+                        // If this is a surrogate pair, combine the higher bits from the node with the next byte
+                        result =
+                            current & BinTrieFlags.MULTI_BYTE
+                                ? String.fromCharCode(decodeTree[++treeIdx], decodeTree[++treeIdx])
+                                : String.fromCharCode(decodeTree[++treeIdx]);
+                        excess = 0;
+                    }
+                }
+            }
+            if (result != null) {
+                ret += result;
+                lastIdx = strIdx - excess + 1;
+            }
+        }
+        return ret + str.slice(lastIdx);
+    };
 }
-var sorter = function (a, b) { return (a < b ? 1 : -1); };
-exports.decodeHTML = (function () {
-    var legacy = Object.keys(legacy_json_1.default).sort(sorter);
-    var keys = Object.keys(entities_json_1.default).sort(sorter);
-    for (var i = 0, j = 0; i < keys.length; i++) {
-        if (legacy[j] === keys[i]) {
-            keys[i] += ";?";
-            j++;
+function determineBranch(decodeTree, current, nodeIdx, char) {
+    if (current <= 128) {
+        return char === current ? nodeIdx : -1;
+    }
+    var branchCount = (current & BinTrieFlags.BRANCH_LENGTH) >> 8;
+    if (branchCount === 0) {
+        return -1;
+    }
+    if (branchCount === 1) {
+        return char === decodeTree[nodeIdx] ? nodeIdx + 1 : -1;
+    }
+    var jumpOffset = current & BinTrieFlags.JUMP_TABLE;
+    if (jumpOffset) {
+        var value = char - exports.JUMP_OFFSET_BASE - jumpOffset;
+        return value < 0 || value > branchCount
+            ? -1
+            : decodeTree[nodeIdx + value] - 1;
+    }
+    // Binary search for the character.
+    var lo = nodeIdx;
+    var hi = lo + branchCount - 1;
+    while (lo <= hi) {
+        var mid = (lo + hi) >>> 1;
+        var midVal = decodeTree[mid];
+        if (midVal < char) {
+            lo = mid + 1;
         }
+        else if (midVal > char) {
+            hi = mid - 1;
+        }
         else {
-            keys[i] += ";";
+            return decodeTree[mid + branchCount];
         }
     }
-    var re = new RegExp("&(?:" + keys.join("|") + "|#[xX][\\da-fA-F]+;?|#\\d+;?)", "g");
-    var replace = getReplacer(entities_json_1.default);
-    function replacer(str) {
-        if (str.substr(-1) !== ";")
-            str += ";";
-        return replace(str);
-    }
-    // TODO consider creating a merged map
-    return function (str) { return String(str).replace(re, replacer); };
-})();
-function getReplacer(map) {
-    return function replace(str) {
-        if (str.charAt(1) === "#") {
-            var secondChar = str.charAt(2);
-            if (secondChar === "X" || secondChar === "x") {
-                return decode_codepoint_1.default(parseInt(str.substr(3), 16));
-            }
-            return decode_codepoint_1.default(parseInt(str.substr(2), 10));
-        }
-        // eslint-disable-next-line @typescript-eslint/prefer-nullish-coalescing
-        return map[str.slice(1, -1)] || str;
-    };
+    return -1;
 }
+exports.determineBranch = determineBranch;
+var htmlDecoder = getDecoder(decode_data_html_1.default);
+var xmlDecoder = getDecoder(decode_data_xml_1.default);
+function decodeHTML(str) {
+    return htmlDecoder(str, false);
+}
+exports.decodeHTML = decodeHTML;
+function decodeHTMLStrict(str) {
+    return htmlDecoder(str, true);
+}
+exports.decodeHTMLStrict = decodeHTMLStrict;
+function decodeXML(str) {
+    return xmlDecoder(str, true);
+}
+exports.decodeXML = decodeXML;

lib/encode.d.ts

@@ -8,3 +8,3 @@ /**
  */
-export declare const encodeXML: (data: string) => string;
+export declare function encodeXML(str: string): string;
 /**
@@ -20,3 +20,3 @@ * Encodes all entities and non-ASCII characters in the input.
  */
-export declare const encodeHTML: (data: string) => string;
+export declare function encodeHTML(data: string): string;
 /**
@@ -29,3 +29,3 @@ * Encodes all non-ASCII characters, as well as characters not valid in HTML
  */
-export declare const encodeNonAsciiHTML: (data: string) => string;
+export declare function encodeNonAsciiHTML(data: string): string;
 /**
@@ -40,6 +40,5 @@ * Encodes all non-ASCII characters, as well as characters not valid in XML
  */
-export declare function escape(data: string): string;
+export declare const escape: typeof encodeXML;
 /**
- * Encodes all characters not valid in XML documents using numeric hexadecimal
- * reference (eg. `ü`).
+ * Encodes all characters not valid in XML documents using XML entities.
  *
@@ -46,0 +45,0 @@ * Note that the output will be character-set dependent.

lib/encode.js

@@ -8,4 +8,11 @@ "use strict";
 var xml_json_1 = __importDefault(require("./maps/xml.json"));
-var inverseXML = getInverseObj(xml_json_1.default);
-var xmlReplacer = getInverseReplacer(inverseXML);
+var encode_trie_1 = require("./encode-trie");
+var entities_json_1 = __importDefault(require("./maps/entities.json"));
+var htmlReplacer = getCharRegExp(entities_json_1.default, true);
+var xmlReplacer = getCharRegExp(xml_json_1.default, true);
+var xmlInvalidChars = getCharRegExp(xml_json_1.default, false);
+var xmlCodeMap = new Map(Object.keys(xml_json_1.default).map(function (k) { return [
+    xml_json_1.default[k].charCodeAt(0),
+    "&" + k + ";",
+]; }));
 /**
@@ -18,6 +25,23 @@ * Encodes all non-ASCII characters, as well as characters not valid in XML
  */
-exports.encodeXML = getASCIIEncoder(inverseXML);
-var entities_json_1 = __importDefault(require("./maps/entities.json"));
-var inverseHTML = getInverseObj(entities_json_1.default);
-var htmlReplacer = getInverseReplacer(inverseHTML);
+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) {
+            ret += str.substring(lastIdx, i) + next;
+            lastIdx = i + 1;
+        }
+        else {
+            ret += str.substring(lastIdx, i) + "&#x" + encode_trie_1.getCodePoint(str, i).toString(16) + ";";
+            // Increase by 1 if we have a surrogate pair
+            lastIdx = xmlReplacer.lastIndex += Number((char & 0xd800) === 0xd800);
+        }
+    }
+    return ret + str.substr(lastIdx);
+}
+exports.encodeXML = encodeXML;
 /**
@@ -33,3 +57,6 @@ * Encodes all entities and non-ASCII characters in the input.
  */
-exports.encodeHTML = getInverse(inverseHTML, htmlReplacer);
+function encodeHTML(data) {
+    return encode_trie_1.encodeHTMLTrieRe(htmlReplacer, data);
+}
+exports.encodeHTML = encodeHTML;
 /**
@@ -42,32 +69,20 @@ * Encodes all non-ASCII characters, as well as characters not valid in HTML
  */
-exports.encodeNonAsciiHTML = getASCIIEncoder(inverseHTML);
-function getInverseObj(obj) {
-    return Object.keys(obj)
-        .sort()
-        .reduce(function (inverse, name) {
-        inverse[obj[name]] = "&" + name + ";";
-        return inverse;
-    }, {});
+function encodeNonAsciiHTML(data) {
+    return encode_trie_1.encodeHTMLTrieRe(xmlReplacer, data);
 }
-function getInverseReplacer(inverse) {
-    var single = [];
-    var multiple = [];
-    for (var _i = 0, _a = Object.keys(inverse); _i < _a.length; _i++) {
-        var k = _a[_i];
-        if (k.length === 1) {
-            // Add value to single array
-            single.push("\\" + k);
-        }
-        else {
-            // Add value to multiple array
-            multiple.push(k);
-        }
-    }
+exports.encodeNonAsciiHTML = encodeNonAsciiHTML;
+function getCharRegExp(map, nonAscii) {
+    // Collect the start characters of all entities
+    var chars = Object.keys(map)
+        .map(function (k) { return "\\" + map[k].charAt(0); })
+        .filter(function (v) { return !nonAscii || v.charCodeAt(1) < 128; })
+        .sort(function (a, b) { return a.charCodeAt(1) - b.charCodeAt(1); })
+        // Remove duplicates
+        .filter(function (v, i, a) { return v !== a[i + 1]; });
     // Add ranges to single characters.
-    single.sort();
-    for (var start = 0; start < single.length - 1; start++) {
+    for (var start = 0; start < chars.length - 1; start++) {
         // Find the end of a run of characters
         var end = start;
-        while (end < single.length - 1 &&
-            single[end].charCodeAt(1) + 1 === single[end + 1].charCodeAt(1)) {
+        while (end < chars.length - 1 &&
+            chars[end].charCodeAt(1) + 1 === chars[end + 1].charCodeAt(1)) {
             end += 1;
@@ -79,34 +94,6 @@ }
             continue;
-        single.splice(start, count, single[start] + "-" + single[end]);
+        chars.splice(start, count, chars[start] + "-" + chars[end]);
     }
-    multiple.unshift("[" + single.join("") + "]");
-    return new RegExp(multiple.join("|"), "g");
+    return new RegExp("[" + chars.join("") + (nonAscii ? "\\x80-\\uFFFF" : "") + "]", "g");
 }
-// /[^\0-\x7F]/gu
-var reNonASCII = /(?:[\x80-\uD7FF\uE000-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]|[\uD800-\uDBFF](?![\uDC00-\uDFFF])|(?:[^\uD800-\uDBFF]|^)[\uDC00-\uDFFF])/g;
-var getCodePoint = 
-// eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
-String.prototype.codePointAt != null
-    ? // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
-        function (str) { return str.codePointAt(0); }
-    : // http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
-        function (c) {
-            return (c.charCodeAt(0) - 0xd800) * 0x400 +
-                c.charCodeAt(1) -
-                0xdc00 +
-                0x10000;
-        };
-function singleCharReplacer(c) {
-    return "&#x" + (c.length > 1 ? getCodePoint(c) : c.charCodeAt(0))
-        .toString(16)
-        .toUpperCase() + ";";
-}
-function getInverse(inverse, re) {
-    return function (data) {
-        return data
-            .replace(re, function (name) { return inverse[name]; })
-            .replace(reNonASCII, singleCharReplacer);
-    };
-}
-var reEscapeChars = new RegExp(xmlReplacer.source + "|" + reNonASCII.source, "g");
 /**
@@ -121,9 +108,5 @@ * Encodes all non-ASCII characters, as well as characters not valid in XML
  */
-function escape(data) {
-    return data.replace(reEscapeChars, singleCharReplacer);
-}
-exports.escape = escape;
+exports.escape = encodeXML;
 /**
- * Encodes all characters not valid in XML documents using numeric hexadecimal
- * reference (eg. `&#xfc;`).
+ * Encodes all characters not valid in XML documents using XML entities.
  *
@@ -135,9 +118,16 @@ * Note that the output will be character-set dependent.
 function escapeUTF8(data) {
-    return data.replace(xmlReplacer, singleCharReplacer);
+    var match;
+    var lastIdx = 0;
+    var result = "";
+    while ((match = xmlInvalidChars.exec(data))) {
+        if (lastIdx !== match.index) {
+            result += data.substring(lastIdx, match.index);
+        }
+        // We know that this chararcter will be in `inverseXML`
+        result += xmlCodeMap.get(match[0].charCodeAt(0));
+        // Every match will be of length 1
+        lastIdx = match.index + 1;
+    }
+    return result + data.substring(lastIdx);
 }
 exports.escapeUTF8 = escapeUTF8;
-function getASCIIEncoder(obj) {
-    return function (data) {
-        return data.replace(reEscapeChars, function (c) { return obj[c] || singleCharReplacer(c); });
-    };
-}

lib/index.d.ts

@@ -0,1 +1,52 @@
+/** The level of entities to support. */
+export declare enum EntityLevel {
+    /** Support only XML entities. */
+    XML = 0,
+    /** Support HTML entities, which are a superset of XML entities. */
+    HTML = 1
+}
+/** Determines whether some entities are allowed to be written without a trailing `;`. */
+export declare enum DecodingMode {
+    /** Support legacy HTML entities. */
+    Legacy = 0,
+    /** Do not support legacy HTML entities. */
+    Strict = 1
+}
+export declare enum EncodingMode {
+    /**
+     * The output is UTF-8 encoded. Only characters that need escaping within
+     * HTML will be escaped.
+     */
+    UTF8 = 0,
+    /**
+     * The output consists only of ASCII characters. Characters that need
+     * escaping within HTML, and characters that aren't ASCII characters will
+     * be escaped.
+     */
+    ASCII = 1,
+    /**
+     * Encode all characters that have an equivalent entity, as well as all
+     * characters that are not ASCII characters.
+     */
+    Extensive = 2
+}
+interface DecodingOptions {
+    /**
+     * The level of entities to support.
+     * @default EntityLevel.XML
+     */
+    level?: EntityLevel;
+    /**
+     * Decoding mode. If `Legacy`, will support legacy entities not terminated
+     * with a semicolon (`;`).
+     *
+     * Always `Strict` for XML. For HTML, set this to `true` if you are parsing
+     * an attribute value.
+     *
+     * The deprecated `decodeStrict` function defaults this to `Strict`.
+     *
+     * @default DecodingMode.Legacy
+     */
+    mode?: DecodingMode;
+}
 /**
@@ -5,6 +56,5 @@ * Decodes a string with entities.
  * @param data String to decode.
- * @param level Optional level to decode at. 0 = XML, 1 = HTML. Default is 0.
- * @deprecated Use `decodeXML` or `decodeHTML` directly.
+ * @param options Decoding options.
  */
-export declare function decode(data: string, level?: number): string;
+export declare function decode(data: string, options?: DecodingOptions | EntityLevel): string;
 /**
@@ -14,16 +64,30 @@ * Decodes a string with entities. Does not allow missing trailing semicolons for entities.
  * @param data String to decode.
- * @param level Optional level to decode at. 0 = XML, 1 = HTML. Default is 0.
- * @deprecated Use `decodeHTMLStrict` or `decodeXML` directly.
+ * @param options Decoding options.
+ * @deprecated Use `decode` with the `mode` set to `Strict`.
  */
-export declare function decodeStrict(data: string, level?: number): string;
+export declare function decodeStrict(data: string, options?: DecodingOptions | EntityLevel): string;
 /**
+ * Options for `encode`.
+ */
+export interface EncodingOptions {
+    /**
+     * The level of entities to support.
+     * @default EntityLevel.XML
+     */
+    level?: EntityLevel;
+    /**
+     * Output format.
+     * @default EncodingMode.Extensive
+     */
+    mode?: EncodingMode;
+}
+/**
  * Encodes a string with entities.
  *
  * @param data String to encode.
- * @param level Optional level to encode at. 0 = XML, 1 = HTML. Default is 0.
- * @deprecated Use `encodeHTML`, `encodeXML` or `encodeNonAsciiHTML` directly.
+ * @param options Encoding options.
  */
-export declare function encode(data: string, level?: number): string;
+export declare function encode(data: string, options?: EncodingOptions | EntityLevel): string;
 export { encodeXML, encodeHTML, encodeNonAsciiHTML, escape, escapeUTF8, encodeHTML as encodeHTML4, encodeHTML as encodeHTML5, } from "./encode";
 export { decodeXML, decodeHTML, decodeHTMLStrict, decodeHTML as decodeHTML4, decodeHTML as decodeHTML5, decodeHTMLStrict as decodeHTML4Strict, decodeHTMLStrict as decodeHTML5Strict, decodeXML as decodeXMLStrict, } from "./decode";
 //# 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.escapeUTF8 = exports.escape = exports.encodeNonAsciiHTML = exports.encodeHTML = exports.encodeXML = exports.encode = exports.decodeStrict = exports.decode = void 0;
+exports.decodeXMLStrict = exports.decodeHTML5Strict = exports.decodeHTML4Strict = exports.decodeHTML5 = exports.decodeHTML4 = exports.decodeHTMLStrict = exports.decodeHTML = exports.decodeXML = exports.encodeHTML5 = exports.encodeHTML4 = exports.escapeUTF8 = exports.escape = exports.encodeNonAsciiHTML = exports.encodeHTML = exports.encodeXML = exports.encode = exports.decodeStrict = exports.decode = exports.EncodingMode = exports.DecodingMode = exports.EntityLevel = void 0;
 var decode_1 = require("./decode");
 var encode_1 = require("./encode");
+/** The level of entities to support. */
+var EntityLevel;
+(function (EntityLevel) {
+    /** Support only XML entities. */
+    EntityLevel[EntityLevel["XML"] = 0] = "XML";
+    /** Support HTML entities, which are a superset of XML entities. */
+    EntityLevel[EntityLevel["HTML"] = 1] = "HTML";
+})(EntityLevel = exports.EntityLevel || (exports.EntityLevel = {}));
+/** Determines whether some entities are allowed to be written without a trailing `;`. */
+var DecodingMode;
+(function (DecodingMode) {
+    /** Support legacy HTML entities. */
+    DecodingMode[DecodingMode["Legacy"] = 0] = "Legacy";
+    /** Do not support legacy HTML entities. */
+    DecodingMode[DecodingMode["Strict"] = 1] = "Strict";
+})(DecodingMode = exports.DecodingMode || (exports.DecodingMode = {}));
+var EncodingMode;
+(function (EncodingMode) {
+    /**
+     * The output is UTF-8 encoded. Only characters that need escaping within
+     * HTML will be escaped.
+     */
+    EncodingMode[EncodingMode["UTF8"] = 0] = "UTF8";
+    /**
+     * The output consists only of ASCII characters. Characters that need
+     * escaping within HTML, and characters that aren't ASCII characters will
+     * be escaped.
+     */
+    EncodingMode[EncodingMode["ASCII"] = 1] = "ASCII";
+    /**
+     * Encode all characters that have an equivalent entity, as well as all
+     * characters that are not ASCII characters.
+     */
+    EncodingMode[EncodingMode["Extensive"] = 2] = "Extensive";
+})(EncodingMode = exports.EncodingMode || (exports.EncodingMode = {}));
 /**
@@ -10,7 +45,14 @@ * Decodes a string with entities.
  * @param data String to decode.
- * @param level Optional level to decode at. 0 = XML, 1 = HTML. Default is 0.
- * @deprecated Use `decodeXML` or `decodeHTML` directly.
+ * @param options Decoding options.
  */
-function decode(data, level) {
-    return (!level || level <= 0 ? decode_1.decodeXML : decode_1.decodeHTML)(data);
+function decode(data, options) {
+    if (options === void 0) { options = EntityLevel.XML; }
+    var opts = typeof options === "number" ? { level: options } : options;
+    if (opts.level === EntityLevel.HTML) {
+        if (opts.mode === DecodingMode.Strict) {
+            return decode_1.decodeHTMLStrict(data);
+        }
+        return decode_1.decodeHTML(data);
+    }
+    return decode_1.decodeXML(data);
 }
@@ -22,7 +64,15 @@ exports.decode = decode;
  * @param data String to decode.
- * @param level Optional level to decode at. 0 = XML, 1 = HTML. Default is 0.
- * @deprecated Use `decodeHTMLStrict` or `decodeXML` directly.
+ * @param options Decoding options.
+ * @deprecated Use `decode` with the `mode` set to `Strict`.
  */
-function decodeStrict(data, level) {
-    return (!level || level <= 0 ? decode_1.decodeXML : decode_1.decodeHTMLStrict)(data);
+function decodeStrict(data, options) {
+    if (options === void 0) { options = EntityLevel.XML; }
+    var opts = typeof options === "number" ? { level: options } : options;
+    if (opts.level === EntityLevel.HTML) {
+        if (opts.mode === DecodingMode.Legacy) {
+            return decode_1.decodeHTML(data);
+        }
+        return decode_1.decodeHTMLStrict(data);
+    }
+    return decode_1.decodeXML(data);
 }
@@ -34,7 +84,18 @@ exports.decodeStrict = decodeStrict;
  * @param data String to encode.
- * @param level Optional level to encode at. 0 = XML, 1 = HTML. Default is 0.
- * @deprecated Use `encodeHTML`, `encodeXML` or `encodeNonAsciiHTML` directly.
+ * @param options Encoding options.
  */
-function encode(data, level) {
-    return (!level || level <= 0 ? encode_1.encodeXML : encode_1.encodeHTML)(data);
+function encode(data, options) {
+    if (options === void 0) { options = EntityLevel.XML; }
+    var opts = typeof options === "number" ? { level: options } : options;
+    // Mode `UTF8` just escapes XML entities
+    if (opts.mode === EncodingMode.UTF8)
+        return encode_1.escapeUTF8(data);
+    if (opts.level === EntityLevel.HTML) {
+        if (opts.mode === EncodingMode.ASCII) {
+            return encode_1.encodeNonAsciiHTML(data);
+        }
+        return encode_1.encodeHTML(data);
+    }
+    // ASCII and Extensive are equivalent
+    return encode_1.encodeXML(data);
 }
@@ -41,0 +102,0 @@ exports.encode = encode;

package.json

 {
     "name": "entities",
-    "version": "2.2.0",
+    "version": "3.0.0",
     "description": "Encode & decode XML and HTML entities with ease",
@@ -24,19 +24,21 @@ "author": "Felix Boehm <[e-mail]>",
     ],
+    "engines": {
+        "node": ">=0.12"
+    },
     "devDependencies": {
-        "@types/jest": "^26.0.0",
-        "@types/node": "^14.11.8",
-        "@typescript-eslint/eslint-plugin": "^4.4.1",
-        "@typescript-eslint/parser": "^4.4.1",
-        "coveralls": "*",
-        "eslint": "^7.11.0",
-        "eslint-config-prettier": "^7.0.0",
+        "@types/jest": "^26.0.24",
+        "@types/node": "^16.4.13",
+        "@typescript-eslint/eslint-plugin": "^4.29.0",
+        "@typescript-eslint/parser": "^4.29.0",
+        "eslint": "^7.32.0",
+        "eslint-config-prettier": "^8.1.0",
         "eslint-plugin-node": "^11.1.0",
-        "jest": "^26.5.3",
+        "jest": "^27.0.3",
         "prettier": "^2.0.5",
-        "ts-jest": "^26.1.0",
+        "ts-jest": "^27.0.4",
         "typescript": "^4.0.2"
     },
     "scripts": {
-        "test": "jest --coverage && npm run lint",
-        "coverage": "cat coverage/lcov.info | coveralls",
+        "test": "npm run test:jest && npm run lint",
+        "test:jest": "jest",
         "lint": "npm run lint:es && npm run lint:prettier",
@@ -59,3 +61,4 @@ "lint:es": "eslint .",
         "preset": "ts-jest",
-        "testEnvironment": "node"
+        "testEnvironment": "node",
+        "coverageProvider": "v8"
     },
@@ -62,0 +65,0 @@ "prettier": {

readme.md

@@ -31,11 +31,28 @@ # entities [![NPM version](http://img.shields.io/npm/v/entities.svg)](https://npmjs.org/package/entities) [![Downloads](https://img.shields.io/npm/dm/entities.svg)](https://npmjs.org/package/entities) [![Build Status](http://img.shields.io/travis/fb55/entities.svg)](http://travis-ci.org/fb55/entities) [![Coverage](http://img.shields.io/coveralls/fb55/entities.svg)](https://coveralls.io/r/fb55/entities)
 
-| Library        | `decode` performance | `encode` performance | Bundle size                                                                |
-| -------------- | -------------------- | -------------------- | -------------------------------------------------------------------------- |
-| entities       | 10.809s              | 17.683s              | ![npm bundle size](https://img.shields.io/bundlephobia/min/entities)       |
-| html-entities  | 14.029s              | 22.670s              | ![npm bundle size](https://img.shields.io/bundlephobia/min/html-entities)  |
-| he             | 16.163s              | 44.010s              | ![npm bundle size](https://img.shields.io/bundlephobia/min/he)             |
-| parse-entities | 28.507s              | N/A                  | ![npm bundle size](https://img.shields.io/bundlephobia/min/parse-entities) |
+| Library        | `decode` perf | `encode` perf | `escape` perf | Bundle size                                                                |
+| -------------- | ------------- | ------------- | ------------- | -------------------------------------------------------------------------- |
+| entities       | 1.418s        | 6.786s        | 2.196s        | ![npm bundle size](https://img.shields.io/bundlephobia/min/entities)       |
+| html-entities  | 2.530s        | 6.829s        | 2.415s        | ![npm bundle size](https://img.shields.io/bundlephobia/min/html-entities)  |
+| he             | 5.800s        | 24.237s       | 3.624s        | ![npm bundle size](https://img.shields.io/bundlephobia/min/he)             |
+| parse-entities | 9.660s        | N/A           | N/A           | ![npm bundle size](https://img.shields.io/bundlephobia/min/parse-entities) |
 
 ---
 
+## Acknowledgements
+
+This libary wouldn't be possible without the work of these individuals. Thanks
+to
+
+-   [@mathiasbynens](https://github.com/mathiasbynens) for his explanations
+    about character encodings, and his library `he`, which was one of the
+    inspirations for `entities`
+-   [@inikulin](https://github.com/inikulin) for his work on optimized tries for
+    decoding HTML entities for the `parse5` project
+-   [@mdevils](https://github.com/mdevils) for taking on the challenge of
+    producing a quick entity library with his `html-entities` library.
+    `entities` would be quite a bit slower if there wasn't any competition.
+    Right now `entities` is on top, but we'll see how long that lasts!
+
+---
+
 License: BSD-2-Clause
@@ -42,0 +59,0 @@

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

172163

increased by198.52%

Dev dependency count

11

decreased by-8.33%

Number of package files

27

increased by42.11%

Lines of code

1166

increased by136.99%

Number of lines in readme file

75

increased by29.31%

Worsened metrics

Number of medium supply chain risk alerts

1

increased byInfinity%

No dependency changes