@studiocms/wysiwyg 0.1.0-experimental.1 → 0.1.0-experimental.3

package/dist/runtime/decoder/util.d.ts

@@ -1,208 +0,0 @@
-export declare enum BinTrieFlags {
-    VALUE_LENGTH = 49152,
-    BRANCH_LENGTH = 16256,
-    JUMP_TABLE = 127
-}
-export declare enum DecodingMode {
-    /** Entities in text nodes that can end with any character. */
-    Legacy = 0,
-    /** Only allow entities terminated with a semicolon. */
-    Strict = 1,
-    /** Entities in attributes have limitations on ending characters. */
-    Attribute = 2
-}
-/**
- * Producers for character reference errors as defined in the HTML spec.
- */
-export interface EntityErrorProducer {
-    missingSemicolonAfterCharacterReference(): void;
-    absenceOfDigitsInNumericCharacterReference(consumedCharacters: number): void;
-    validateNumericCharacterReference(code: number): void;
-}
-/**
- * Token decoder with support of writing partial entities.
- */
-export declare class EntityDecoder {
-    /** The tree used to decode entities. */
-    private readonly decodeTree;
-    /**
-     * The function that is called when a codepoint is decoded.
-     *
-     * For multi-byte named entities, this will be called multiple times,
-     * with the second codepoint, and the same `consumed` value.
-     *
-     * @param codepoint The decoded codepoint.
-     * @param consumed The number of bytes consumed by the decoder.
-     */
-    private readonly emitCodePoint;
-    /** An object that is used to produce errors. */
-    private readonly errors?;
-    constructor(
-    /** The tree used to decode entities. */
-    decodeTree: Uint16Array, 
-    /**
-     * The function that is called when a codepoint is decoded.
-     *
-     * For multi-byte named entities, this will be called multiple times,
-     * with the second codepoint, and the same `consumed` value.
-     *
-     * @param codepoint The decoded codepoint.
-     * @param consumed The number of bytes consumed by the decoder.
-     */
-    emitCodePoint: (cp: number, consumed: number) => void, 
-    /** An object that is used to produce errors. */
-    errors?: EntityErrorProducer | undefined);
-    /** The current state of the decoder. */
-    private state;
-    /** Characters that were consumed while parsing an entity. */
-    private consumed;
-    /**
-     * The result of the entity.
-     *
-     * Either the result index of a numeric entity, or the codepoint of a
-     * numeric entity.
-     */
-    private result;
-    /** The current index in the decode tree. */
-    private treeIndex;
-    /** The number of characters that were consumed in excess. */
-    private excess;
-    /** The mode in which the decoder is operating. */
-    private decodeMode;
-    /** Resets the instance to make it reusable. */
-    startEntity(decodeMode: DecodingMode): void;
-    /**
-     * Write an entity to the decoder. This can be called multiple times with partial entities.
-     * If the entity is incomplete, the decoder will return -1.
-     *
-     * Mirrors the implementation of `getDecoder`, but with the ability to stop decoding if the
-     * entity is incomplete, and resume when the next string is written.
-     *
-     * @param input The string containing the entity (or a continuation of the entity).
-     * @param offset The offset at which the entity begins. Should be 0 if this is not the first call.
-     * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-     */
-    write(input: string, offset: number): number;
-    /**
-     * Switches between the numeric decimal and hexadecimal states.
-     *
-     * Equivalent to the `Numeric character reference state` in the HTML spec.
-     *
-     * @param input The string containing the entity (or a continuation of the entity).
-     * @param offset The current offset.
-     * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-     */
-    private stateNumericStart;
-    private addToNumericResult;
-    /**
-     * Parses a hexadecimal numeric entity.
-     *
-     * Equivalent to the `Hexademical character reference state` in the HTML spec.
-     *
-     * @param input The string containing the entity (or a continuation of the entity).
-     * @param offset The current offset.
-     * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-     */
-    private stateNumericHex;
-    /**
-     * Parses a decimal numeric entity.
-     *
-     * Equivalent to the `Decimal character reference state` in the HTML spec.
-     *
-     * @param input The string containing the entity (or a continuation of the entity).
-     * @param offset The current offset.
-     * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-     */
-    private stateNumericDecimal;
-    /**
-     * Validate and emit a numeric entity.
-     *
-     * Implements the logic from the `Hexademical character reference start
-     * state` and `Numeric character reference end state` in the HTML spec.
-     *
-     * @param lastCp The last code point of the entity. Used to see if the
-     *               entity was terminated with a semicolon.
-     * @param expectedLength The minimum number of characters that should be
-     *                       consumed. Used to validate that at least one digit
-     *                       was consumed.
-     * @returns The number of characters that were consumed.
-     */
-    private emitNumericEntity;
-    /**
-     * Parses a named entity.
-     *
-     * Equivalent to the `Named character reference state` in the HTML spec.
-     *
-     * @param input The string containing the entity (or a continuation of the entity).
-     * @param offset The current offset.
-     * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-     */
-    private stateNamedEntity;
-    /**
-     * Emit a named entity that was not terminated with a semicolon.
-     *
-     * @returns The number of characters consumed.
-     */
-    private emitNotTerminatedNamedEntity;
-    /**
-     * Emit a named entity.
-     *
-     * @param result The index of the entity in the decode tree.
-     * @param valueLength The number of bytes in the entity.
-     * @param consumed The number of characters consumed.
-     *
-     * @returns The number of characters consumed.
-     */
-    private emitNamedEntityData;
-    /**
-     * Signal to the parser that the end of the input was reached.
-     *
-     * Remaining data will be emitted and relevant errors will be produced.
-     *
-     * @returns The number of characters consumed.
-     */
-    end(): number;
-}
-/**
- * Determines the branch of the current node that is taken given the current
- * character. This function is used to traverse the trie.
- *
- * @param decodeTree The trie.
- * @param current The current node.
- * @param nodeIdx The index right after the current node and its value.
- * @param char The current character.
- * @returns The index of the next node, or -1 if no branch is taken.
- */
-export declare function determineBranch(decodeTree: Uint16Array, current: number, nodeIndex: number, char: number): number;
-/**
- * Decodes an HTML string.
- *
- * @param htmlString The string to decode.
- * @param mode The decoding mode.
- * @returns The decoded string.
- */
-export declare function decodeHTML(htmlString: string, mode?: DecodingMode): string;
-/**
- * Decodes an HTML string in an attribute.
- *
- * @param htmlAttribute The string to decode.
- * @returns The decoded string.
- */
-export declare function decodeHTMLAttribute(htmlAttribute: string): string;
-/**
- * Decodes an HTML string, requiring all entities to be terminated by a semicolon.
- *
- * @param htmlString The string to decode.
- * @returns The decoded string.
- */
-export declare function decodeHTMLStrict(htmlString: string): string;
-/**
- * Decodes an XML string, requiring all entities to be terminated by a semicolon.
- *
- * @param xmlString The string to decode.
- * @returns The decoded string.
- */
-export declare function decodeXML(xmlString: string): string;
-export { htmlDecodeTree } from './decode-data-html.js';
-export { xmlDecodeTree } from './decode-data-xml.js';
-export { decodeCodePoint, replaceCodePoint, fromCodePoint, } from './decode-codepoint.js';

package/dist/runtime/decoder/util.js

@@ -1,415 +0,0 @@
-import { fromCodePoint, replaceCodePoint } from "./decode-codepoint.js";
-import { htmlDecodeTree } from "./decode-data-html.js";
-import { xmlDecodeTree } from "./decode-data-xml.js";
-var CharCodes = /* @__PURE__ */ ((CharCodes2) => {
-  CharCodes2[CharCodes2["NUM"] = 35] = "NUM";
-  CharCodes2[CharCodes2["SEMI"] = 59] = "SEMI";
-  CharCodes2[CharCodes2["EQUALS"] = 61] = "EQUALS";
-  CharCodes2[CharCodes2["ZERO"] = 48] = "ZERO";
-  CharCodes2[CharCodes2["NINE"] = 57] = "NINE";
-  CharCodes2[CharCodes2["LOWER_A"] = 97] = "LOWER_A";
-  CharCodes2[CharCodes2["LOWER_F"] = 102] = "LOWER_F";
-  CharCodes2[CharCodes2["LOWER_X"] = 120] = "LOWER_X";
-  CharCodes2[CharCodes2["LOWER_Z"] = 122] = "LOWER_Z";
-  CharCodes2[CharCodes2["UPPER_A"] = 65] = "UPPER_A";
-  CharCodes2[CharCodes2["UPPER_F"] = 70] = "UPPER_F";
-  CharCodes2[CharCodes2["UPPER_Z"] = 90] = "UPPER_Z";
-  return CharCodes2;
-})(CharCodes || {});
-const TO_LOWER_BIT = 32;
-var BinTrieFlags = /* @__PURE__ */ ((BinTrieFlags2) => {
-  BinTrieFlags2[BinTrieFlags2["VALUE_LENGTH"] = 49152] = "VALUE_LENGTH";
-  BinTrieFlags2[BinTrieFlags2["BRANCH_LENGTH"] = 16256] = "BRANCH_LENGTH";
-  BinTrieFlags2[BinTrieFlags2["JUMP_TABLE"] = 127] = "JUMP_TABLE";
-  return BinTrieFlags2;
-})(BinTrieFlags || {});
-function isNumber(code) {
-  return code >= 48 /* ZERO */ && code <= 57 /* NINE */;
-}
-function isHexadecimalCharacter(code) {
-  return code >= 65 /* UPPER_A */ && code <= 70 /* UPPER_F */ || code >= 97 /* LOWER_A */ && code <= 102 /* LOWER_F */;
-}
-function isAsciiAlphaNumeric(code) {
-  return code >= 65 /* UPPER_A */ && code <= 90 /* UPPER_Z */ || code >= 97 /* LOWER_A */ && code <= 122 /* LOWER_Z */ || isNumber(code);
-}
-function isEntityInAttributeInvalidEnd(code) {
-  return code === 61 /* EQUALS */ || isAsciiAlphaNumeric(code);
-}
-var EntityDecoderState = /* @__PURE__ */ ((EntityDecoderState2) => {
-  EntityDecoderState2[EntityDecoderState2["EntityStart"] = 0] = "EntityStart";
-  EntityDecoderState2[EntityDecoderState2["NumericStart"] = 1] = "NumericStart";
-  EntityDecoderState2[EntityDecoderState2["NumericDecimal"] = 2] = "NumericDecimal";
-  EntityDecoderState2[EntityDecoderState2["NumericHex"] = 3] = "NumericHex";
-  EntityDecoderState2[EntityDecoderState2["NamedEntity"] = 4] = "NamedEntity";
-  return EntityDecoderState2;
-})(EntityDecoderState || {});
-var DecodingMode = /* @__PURE__ */ ((DecodingMode2) => {
-  DecodingMode2[DecodingMode2["Legacy"] = 0] = "Legacy";
-  DecodingMode2[DecodingMode2["Strict"] = 1] = "Strict";
-  DecodingMode2[DecodingMode2["Attribute"] = 2] = "Attribute";
-  return DecodingMode2;
-})(DecodingMode || {});
-class EntityDecoder {
-  constructor(decodeTree, emitCodePoint, errors) {
-    this.decodeTree = decodeTree;
-    this.emitCodePoint = emitCodePoint;
-    this.errors = errors;
-  }
-  /** The current state of the decoder. */
-  state = 0 /* EntityStart */;
-  /** Characters that were consumed while parsing an entity. */
-  consumed = 1;
-  /**
-   * The result of the entity.
-   *
-   * Either the result index of a numeric entity, or the codepoint of a
-   * numeric entity.
-   */
-  result = 0;
-  /** The current index in the decode tree. */
-  treeIndex = 0;
-  /** The number of characters that were consumed in excess. */
-  excess = 1;
-  /** The mode in which the decoder is operating. */
-  decodeMode = 1 /* Strict */;
-  /** Resets the instance to make it reusable. */
-  startEntity(decodeMode) {
-    this.decodeMode = decodeMode;
-    this.state = 0 /* EntityStart */;
-    this.result = 0;
-    this.treeIndex = 0;
-    this.excess = 1;
-    this.consumed = 1;
-  }
-  /**
-   * Write an entity to the decoder. This can be called multiple times with partial entities.
-   * If the entity is incomplete, the decoder will return -1.
-   *
-   * Mirrors the implementation of `getDecoder`, but with the ability to stop decoding if the
-   * entity is incomplete, and resume when the next string is written.
-   *
-   * @param input The string containing the entity (or a continuation of the entity).
-   * @param offset The offset at which the entity begins. Should be 0 if this is not the first call.
-   * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-   */
-  write(input, offset) {
-    switch (this.state) {
-      case 0 /* EntityStart */: {
-        if (input.charCodeAt(offset) === 35 /* NUM */) {
-          this.state = 1 /* NumericStart */;
-          this.consumed += 1;
-          return this.stateNumericStart(input, offset + 1);
-        }
-        this.state = 4 /* NamedEntity */;
-        return this.stateNamedEntity(input, offset);
-      }
-      case 1 /* NumericStart */: {
-        return this.stateNumericStart(input, offset);
-      }
-      case 2 /* NumericDecimal */: {
-        return this.stateNumericDecimal(input, offset);
-      }
-      case 3 /* NumericHex */: {
-        return this.stateNumericHex(input, offset);
-      }
-      case 4 /* NamedEntity */: {
-        return this.stateNamedEntity(input, offset);
-      }
-    }
-  }
-  /**
-   * Switches between the numeric decimal and hexadecimal states.
-   *
-   * Equivalent to the `Numeric character reference state` in the HTML spec.
-   *
-   * @param input The string containing the entity (or a continuation of the entity).
-   * @param offset The current offset.
-   * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-   */
-  stateNumericStart(input, offset) {
-    if (offset >= input.length) {
-      return -1;
-    }
-    if ((input.charCodeAt(offset) | TO_LOWER_BIT) === 120 /* LOWER_X */) {
-      this.state = 3 /* NumericHex */;
-      this.consumed += 1;
-      return this.stateNumericHex(input, offset + 1);
-    }
-    this.state = 2 /* NumericDecimal */;
-    return this.stateNumericDecimal(input, offset);
-  }
-  addToNumericResult(input, start, end, base) {
-    if (start !== end) {
-      const digitCount = end - start;
-      this.result = this.result * base ** digitCount + Number.parseInt(input.substr(start, digitCount), base);
-      this.consumed += digitCount;
-    }
-  }
-  /**
-   * Parses a hexadecimal numeric entity.
-   *
-   * Equivalent to the `Hexademical character reference state` in the HTML spec.
-   *
-   * @param input The string containing the entity (or a continuation of the entity).
-   * @param offset The current offset.
-   * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-   */
-  stateNumericHex(input, offset) {
-    const startIndex = offset;
-    while (offset < input.length) {
-      const char = input.charCodeAt(offset);
-      if (isNumber(char) || isHexadecimalCharacter(char)) {
-        offset += 1;
-      } else {
-        this.addToNumericResult(input, startIndex, offset, 16);
-        return this.emitNumericEntity(char, 3);
-      }
-    }
-    this.addToNumericResult(input, startIndex, offset, 16);
-    return -1;
-  }
-  /**
-   * Parses a decimal numeric entity.
-   *
-   * Equivalent to the `Decimal character reference state` in the HTML spec.
-   *
-   * @param input The string containing the entity (or a continuation of the entity).
-   * @param offset The current offset.
-   * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-   */
-  stateNumericDecimal(input, offset) {
-    const startIndex = offset;
-    while (offset < input.length) {
-      const char = input.charCodeAt(offset);
-      if (isNumber(char)) {
-        offset += 1;
-      } else {
-        this.addToNumericResult(input, startIndex, offset, 10);
-        return this.emitNumericEntity(char, 2);
-      }
-    }
-    this.addToNumericResult(input, startIndex, offset, 10);
-    return -1;
-  }
-  /**
-   * Validate and emit a numeric entity.
-   *
-   * Implements the logic from the `Hexademical character reference start
-   * state` and `Numeric character reference end state` in the HTML spec.
-   *
-   * @param lastCp The last code point of the entity. Used to see if the
-   *               entity was terminated with a semicolon.
-   * @param expectedLength The minimum number of characters that should be
-   *                       consumed. Used to validate that at least one digit
-   *                       was consumed.
-   * @returns The number of characters that were consumed.
-   */
-  emitNumericEntity(lastCp, expectedLength) {
-    if (this.consumed <= expectedLength) {
-      this.errors?.absenceOfDigitsInNumericCharacterReference(this.consumed);
-      return 0;
-    }
-    if (lastCp === 59 /* SEMI */) {
-      this.consumed += 1;
-    } else if (this.decodeMode === 1 /* Strict */) {
-      return 0;
-    }
-    this.emitCodePoint(replaceCodePoint(this.result), this.consumed);
-    if (this.errors) {
-      if (lastCp !== 59 /* SEMI */) {
-        this.errors.missingSemicolonAfterCharacterReference();
-      }
-      this.errors.validateNumericCharacterReference(this.result);
-    }
-    return this.consumed;
-  }
-  /**
-   * Parses a named entity.
-   *
-   * Equivalent to the `Named character reference state` in the HTML spec.
-   *
-   * @param input The string containing the entity (or a continuation of the entity).
-   * @param offset The current offset.
-   * @returns The number of characters that were consumed, or -1 if the entity is incomplete.
-   */
-  stateNamedEntity(input, offset) {
-    const { decodeTree } = this;
-    let current = decodeTree[this.treeIndex];
-    let valueLength = (current & 49152 /* VALUE_LENGTH */) >> 14;
-    for (; offset < input.length; offset++, this.excess++) {
-      const char = input.charCodeAt(offset);
-      this.treeIndex = determineBranch(
-        decodeTree,
-        current,
-        this.treeIndex + Math.max(1, valueLength),
-        char
-      );
-      if (this.treeIndex < 0) {
-        return this.result === 0 || // If we are parsing an attribute
-        this.decodeMode === 2 /* Attribute */ && // We shouldn't have consumed any characters after the entity,
-        (valueLength === 0 || // And there should be no invalid characters.
-        isEntityInAttributeInvalidEnd(char)) ? 0 : this.emitNotTerminatedNamedEntity();
-      }
-      current = decodeTree[this.treeIndex];
-      valueLength = (current & 49152 /* VALUE_LENGTH */) >> 14;
-      if (valueLength !== 0) {
-        if (char === 59 /* SEMI */) {
-          return this.emitNamedEntityData(this.treeIndex, valueLength, this.consumed + this.excess);
-        }
-        if (this.decodeMode !== 1 /* Strict */) {
-          this.result = this.treeIndex;
-          this.consumed += this.excess;
-          this.excess = 0;
-        }
-      }
-    }
-    return -1;
-  }
-  /**
-   * Emit a named entity that was not terminated with a semicolon.
-   *
-   * @returns The number of characters consumed.
-   */
-  emitNotTerminatedNamedEntity() {
-    const { result, decodeTree } = this;
-    const valueLength = (decodeTree[result] & 49152 /* VALUE_LENGTH */) >> 14;
-    this.emitNamedEntityData(result, valueLength, this.consumed);
-    this.errors?.missingSemicolonAfterCharacterReference();
-    return this.consumed;
-  }
-  /**
-   * Emit a named entity.
-   *
-   * @param result The index of the entity in the decode tree.
-   * @param valueLength The number of bytes in the entity.
-   * @param consumed The number of characters consumed.
-   *
-   * @returns The number of characters consumed.
-   */
-  emitNamedEntityData(result, valueLength, consumed) {
-    const { decodeTree } = this;
-    this.emitCodePoint(
-      valueLength === 1 ? decodeTree[result] & ~49152 /* VALUE_LENGTH */ : decodeTree[result + 1],
-      consumed
-    );
-    if (valueLength === 3) {
-      this.emitCodePoint(decodeTree[result + 2], consumed);
-    }
-    return consumed;
-  }
-  /**
-   * Signal to the parser that the end of the input was reached.
-   *
-   * Remaining data will be emitted and relevant errors will be produced.
-   *
-   * @returns The number of characters consumed.
-   */
-  end() {
-    switch (this.state) {
-      case 4 /* NamedEntity */: {
-        return this.result !== 0 && (this.decodeMode !== 2 /* Attribute */ || this.result === this.treeIndex) ? this.emitNotTerminatedNamedEntity() : 0;
-      }
-      // Otherwise, emit a numeric entity if we have one.
-      case 2 /* NumericDecimal */: {
-        return this.emitNumericEntity(0, 2);
-      }
-      case 3 /* NumericHex */: {
-        return this.emitNumericEntity(0, 3);
-      }
-      case 1 /* NumericStart */: {
-        this.errors?.absenceOfDigitsInNumericCharacterReference(this.consumed);
-        return 0;
-      }
-      case 0 /* EntityStart */: {
-        return 0;
-      }
-    }
-  }
-}
-function getDecoder(decodeTree) {
-  let returnValue = "";
-  const decoder = new EntityDecoder(decodeTree, (data) => returnValue += fromCodePoint(data));
-  return function decodeWithTrie(input, decodeMode) {
-    let lastIndex = 0;
-    let offset = 0;
-    while ((offset = input.indexOf("&", offset)) >= 0) {
-      returnValue += input.slice(lastIndex, offset);
-      decoder.startEntity(decodeMode);
-      const length = decoder.write(
-        input,
-        // Skip the "&"
-        offset + 1
-      );
-      if (length < 0) {
-        lastIndex = offset + decoder.end();
-        break;
-      }
-      lastIndex = offset + length;
-      offset = length === 0 ? lastIndex + 1 : lastIndex;
-    }
-    const result = returnValue + input.slice(lastIndex);
-    returnValue = "";
-    return result;
-  };
-}
-function determineBranch(decodeTree, current, nodeIndex, char) {
-  const branchCount = (current & 16256 /* BRANCH_LENGTH */) >> 7;
-  const jumpOffset = current & 127 /* JUMP_TABLE */;
-  if (branchCount === 0) {
-    return jumpOffset !== 0 && char === jumpOffset ? nodeIndex : -1;
-  }
-  if (jumpOffset) {
-    const value = char - jumpOffset;
-    return value < 0 || value >= branchCount ? -1 : decodeTree[nodeIndex + value] - 1;
-  }
-  let lo = nodeIndex;
-  let hi = lo + branchCount - 1;
-  while (lo <= hi) {
-    const mid = lo + hi >>> 1;
-    const midValue = decodeTree[mid];
-    if (midValue < char) {
-      lo = mid + 1;
-    } else if (midValue > char) {
-      hi = mid - 1;
-    } else {
-      return decodeTree[mid + branchCount];
-    }
-  }
-  return -1;
-}
-const htmlDecoder = /* @__PURE__ */ getDecoder(htmlDecodeTree);
-const xmlDecoder = /* @__PURE__ */ getDecoder(xmlDecodeTree);
-function decodeHTML(htmlString, mode = 0 /* Legacy */) {
-  return htmlDecoder(htmlString, mode);
-}
-function decodeHTMLAttribute(htmlAttribute) {
-  return htmlDecoder(htmlAttribute, 2 /* Attribute */);
-}
-function decodeHTMLStrict(htmlString) {
-  return htmlDecoder(htmlString, 1 /* Strict */);
-}
-function decodeXML(xmlString) {
-  return xmlDecoder(xmlString, 1 /* Strict */);
-}
-import { htmlDecodeTree as htmlDecodeTree2 } from "./decode-data-html.js";
-import { xmlDecodeTree as xmlDecodeTree2 } from "./decode-data-xml.js";
-import {
-  decodeCodePoint,
-  replaceCodePoint as replaceCodePoint2,
-  fromCodePoint as fromCodePoint2
-} from "./decode-codepoint.js";
-export {
-  BinTrieFlags,
-  DecodingMode,
-  EntityDecoder,
-  decodeCodePoint,
-  decodeHTML,
-  decodeHTMLAttribute,
-  decodeHTMLStrict,
-  decodeXML,
-  determineBranch,
-  fromCodePoint2 as fromCodePoint,
-  htmlDecodeTree2 as htmlDecodeTree,
-  replaceCodePoint2 as replaceCodePoint,
-  xmlDecodeTree2 as xmlDecodeTree
-};