完成世界书、骰子、apiconfig页面处理

This commit is contained in:
2026-04-30 01:35:10 +08:00
parent a3e3711b2b
commit ba9b925c32
4602 changed files with 785225 additions and 23 deletions

View File

@@ -0,0 +1,209 @@
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 "./generated/decode-data-html.js";
export { xmlDecodeTree } from "./generated/decode-data-xml.js";
export { decodeCodePoint, replaceCodePoint, fromCodePoint, } from "./decode-codepoint.js";
//# sourceMappingURL=decode.d.ts.map

View File

@@ -0,0 +1 @@
{"version":3,"file":"encode.js","sourceRoot":"","sources":["../../src/encode.ts"],"names":[],"mappings":";;AAgBA,gCAEC;AASD,gDAEC;AA7BD,+DAAsD;AACtD,2CAAwD;AAExD,MAAM,YAAY,GAAG,sCAAsC,CAAC;AAE5D;;;;;;;;;;GAUG;AACH,SAAgB,UAAU,CAAC,KAAa;IACpC,OAAO,gBAAgB,CAAC,YAAY,EAAE,KAAK,CAAC,CAAC;AACjD,CAAC;AACD;;;;;;;GAOG;AACH,SAAgB,kBAAkB,CAAC,KAAa;IAC5C,OAAO,gBAAgB,CAAC,uBAAW,EAAE,KAAK,CAAC,CAAC;AAChD,CAAC;AAED,SAAS,gBAAgB,CAAC,MAAc,EAAE,KAAa;IACnD,IAAI,WAAW,GAAG,EAAE,CAAC;IACrB,IAAI,SAAS,GAAG,CAAC,CAAC;IAClB,IAAI,KAAK,CAAC;IAEV,OAAO,CAAC,KAAK,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QAC3C,MAAM,EAAE,KAAK,EAAE,GAAG,KAAK,CAAC;QACxB,WAAW,IAAI,KAAK,CAAC,SAAS,CAAC,SAAS,EAAE,KAAK,CAAC,CAAC;QACjD,MAAM,IAAI,GAAG,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC;QACrC,IAAI,IAAI,GAAG,yBAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;QAE9B,IAAI,OAAO,IAAI,KAAK,QAAQ,EAAE,CAAC;YAC3B,kDAAkD;YAClD,IAAI,KAAK,GAAG,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC;gBAC3B,MAAM,QAAQ,GAAG,KAAK,CAAC,UAAU,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC;gBAC7C,MAAM,KAAK,GACP,OAAO,IAAI,CAAC,CAAC,KAAK,QAAQ;oBACtB,CAAC,CAAC,IAAI,CAAC,CAAC,KAAK,QAAQ;wBACjB,CAAC,CAAC,IAAI,CAAC,CAAC;wBACR,CAAC,CAAC,SAAS;oBACf,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;gBAE/B,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;oBACtB,WAAW,IAAI,KAAK,CAAC;oBACrB,SAAS,GAAG,MAAM,CAAC,SAAS,IAAI,CAAC,CAAC;oBAClC,SAAS;gBACb,CAAC;YACL,CAAC;YAED,IAAI,GAAG,IAAI,CAAC,CAAC,CAAC;QAClB,CAAC;QAED,4EAA4E;QAC5E,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACrB,MAAM,EAAE,GAAG,IAAA,wBAAY,EAAC,KAAK,EAAE,KAAK,CAAC,CAAC;YACtC,WAAW,IAAI,MAAM,EAAE,CAAC,QAAQ,CAAC,EAAE,CAAC,GAAG,CAAC;YACxC,4CAA4C;YAC5C,SAAS,GAAG,MAAM,CAAC,SAAS,IAAI,MAAM,CAAC,EAAE,KAAK,IAAI,CAAC,CAAC;QACxD,CAAC;aAAM,CAAC;YACJ,WAAW,IAAI,IAAI,CAAC;YACpB,SAAS,GAAG,KAAK,GAAG,CAAC,CAAC;QAC1B,CAAC;IACL,CAAC;IAED,OAAO,WAAW,GAAG,KAAK,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC;AACjD,CAAC"}

View File

@@ -0,0 +1 @@
{"version":3,"file":"escape.d.ts","sourceRoot":"","sources":["../../src/escape.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,WAAW,EAAE,MAAiC,CAAC;AAW5D,eAAO,MAAM,YAAY,EAAE,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,KAAK,MAWoB,CAAC;AAE9E;;;;;;GAMG;AACH,wBAAgB,SAAS,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CA0B/C;AAED;;;;;;;;GAQG;AACH,eAAO,MAAM,MAAM,EAAE,OAAO,SAAqB,CAAC;AAqClD;;;;;;GAMG;AACH,eAAO,MAAM,UAAU,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAG1C,CAAC;AAEF;;;;;GAKG;AACH,eAAO,MAAM,eAAe,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAQ3C,CAAC;AAEN;;;;;GAKG;AACH,eAAO,MAAM,UAAU,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAQ1C,CAAC"}

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,3 @@
{
"type": "commonjs"
}

View File

@@ -0,0 +1,19 @@
/**
* Polyfill for `String.fromCodePoint`. It is used to create a string from a Unicode code point.
*/
export declare const fromCodePoint: (...codePoints: number[]) => string;
/**
* Replace the given code point with a replacement character if it is a
* surrogate or is outside the valid range. Otherwise return the code
* point unchanged.
*/
export declare function replaceCodePoint(codePoint: number): number;
/**
* Replace the code point if relevant, then convert it to a string.
*
* @deprecated Use `fromCodePoint(replaceCodePoint(codePoint))` instead.
* @param codePoint The code point to decode.
* @returns The decoded code point.
*/
export declare function decodeCodePoint(codePoint: number): string;
//# sourceMappingURL=decode-codepoint.d.ts.map

209
frontend/node_modules/entities/dist/esm/decode.d.ts generated vendored Normal file
View File

@@ -0,0 +1,209 @@
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 "./generated/decode-data-html.js";
export { xmlDecodeTree } from "./generated/decode-data-xml.js";
export { decodeCodePoint, replaceCodePoint, fromCodePoint, } from "./decode-codepoint.js";
//# sourceMappingURL=decode.d.ts.map

View File

@@ -0,0 +1 @@
{"version":3,"file":"encode.d.ts","sourceRoot":"","sources":["../../src/encode.ts"],"names":[],"mappings":"AAKA;;;;;;;;;;GAUG;AACH,wBAAgB,UAAU,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAEhD;AACD;;;;;;;GAOG;AACH,wBAAgB,kBAAkB,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAExD"}

View File

@@ -0,0 +1 @@
{"version":3,"file":"decode-data-html.js","sourceRoot":"","sources":["../../../src/generated/decode-data-html.ts"],"names":[],"mappings":"AAAA,8CAA8C;AAE9C,MAAM,CAAC,MAAM,cAAc,GAAgB,eAAe,CAAC,IAAI,WAAW;AACtE,kBAAkB;AAClB,eAAe,CAAC,268CAA268C;KACt78C,KAAK,CAAC,EAAE,CAAC;KACT,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,CACnC,CAAC"}

1
frontend/node_modules/entities/dist/esm/index.js.map generated vendored Normal file
View File

@@ -0,0 +1 @@
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAClE,OAAO,EAAE,UAAU,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AAC7D,OAAO,EACH,SAAS,EACT,UAAU,EACV,eAAe,EACf,UAAU,GACb,MAAM,aAAa,CAAC;AAErB,wCAAwC;AACxC,MAAM,CAAN,IAAY,WAKX;AALD,WAAY,WAAW;IACnB,iCAAiC;IACjC,2CAAO,CAAA;IACP,mEAAmE;IACnE,6CAAQ,CAAA;AACZ,CAAC,EALW,WAAW,KAAX,WAAW,QAKtB;AAED,MAAM,CAAN,IAAY,YA2BX;AA3BD,WAAY,YAAY;IACpB;;;OAGG;IACH,+CAAI,CAAA;IACJ;;;;OAIG;IACH,iDAAK,CAAA;IACL;;;OAGG;IACH,yDAAS,CAAA;IACT;;;OAGG;IACH,yDAAS,CAAA;IACT;;;OAGG;IACH,+CAAI,CAAA;AACR,CAAC,EA3BW,YAAY,KAAZ,YAAY,QA2BvB;AAsBD;;;;;GAKG;AACH,MAAM,UAAU,MAAM,CAClB,KAAa,EACb,UAAyC,WAAW,CAAC,GAAG;IAExD,MAAM,KAAK,GAAG,OAAO,OAAO,KAAK,QAAQ,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC;IAEpE,IAAI,KAAK,KAAK,WAAW,CAAC,IAAI,EAAE,CAAC;QAC7B,MAAM,IAAI,GAAG,OAAO,OAAO,KAAK,QAAQ,CAAC,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,SAAS,CAAC;QACpE,OAAO,UAAU,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC;IACnC,CAAC;IAED,OAAO,SAAS,CAAC,KAAK,CAAC,CAAC;AAC5B,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,YAAY,CACxB,KAAa,EACb,UAAyC,WAAW,CAAC,GAAG;;IAExD,MAAM,iBAAiB,GACnB,OAAO,OAAO,KAAK,QAAQ,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC;IAC/D,MAAA,iBAAiB,CAAC,IAAI,oCAAtB,iBAAiB,CAAC,IAAI,GAAK,YAAY,CAAC,MAAM,EAAC;IAE/C,OAAO,MAAM,CAAC,KAAK,EAAE,iBAAiB,CAAC,CAAC;AAC5C,CAAC;AAkBD;;;;;GAKG;AACH,MAAM,UAAU,MAAM,CAClB,KAAa,EACb,UAAyC,WAAW,CAAC,GAAG;IAExD,MAAM,EAAE,IAAI,GAAG,YAAY,CAAC,SAAS,EAAE,KAAK,GAAG,WAAW,CAAC,GAAG,EAAE,GAC5D,OAAO,OAAO,KAAK,QAAQ,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC;IAE/D,QAAQ,IAAI,EAAE,CAAC;QACX,KAAK,YAAY,CAAC,IAAI,CAAC,CAAC,CAAC;YACrB,OAAO,UAAU,CAAC,KAAK,CAAC,CAAC;QAC7B,CAAC;QACD,KAAK,YAAY,CAAC,SAAS,CAAC,CAAC,CAAC;YAC1B,OAAO,eAAe,CAAC,KAAK,CAAC,CAAC;QAClC,CAAC;QACD,KAAK,YAAY,CAAC,IAAI,CAAC,CAAC,CAAC;YACrB,OAAO,UAAU,CAAC,KAAK,CAAC,CAAC;QAC7B,CAAC;QACD,KAAK,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC;YACtB,OAAO,KAAK,KAAK,WAAW,CAAC,IAAI;gBAC7B,CAAC,CAAC,kBAAkB,CAAC,KAAK,CAAC;gBAC3B,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC;QAC3B,CAAC;QACD,0DAA0D;QAC1D,KAAK,YAAY,CAAC,SAAS,CAAC;QAC5B,OAAO,CAAC,CAAC,CAAC;YACN,OAAO,KAAK,KAAK,WAAW,CAAC,IAAI;gBAC7B,CAAC,CAAC,UAAU,CAAC,KAAK,CAAC;gBACnB,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC;QAC3B,CAAC;IACL,CAAC;AACL,CAAC;AAED,OAAO,EACH,SAAS,EACT,MAAM,EACN,UAAU,EACV,eAAe,EACf,UAAU,GACb,MAAM,aAAa,CAAC;AAErB,OAAO,EACH,UAAU,EACV,kBAAkB;AAClB,8BAA8B;AAC9B,UAAU,IAAI,WAAW,EACzB,UAAU,IAAI,WAAW,GAC5B,MAAM,aAAa,CAAC;AAErB,OAAO,EACH,aAAa,EACb,YAAY,EACZ,SAAS,EACT,UAAU,EACV,gBAAgB,EAChB,mBAAmB;AACnB,8BAA8B;AAC9B,UAAU,IAAI,WAAW,EACzB,UAAU,IAAI,WAAW,EACzB,gBAAgB,IAAI,iBAAiB,EACrC,gBAAgB,IAAI,iBAAiB,EACrC,SAAS,IAAI,eAAe,GAC/B,MAAM,aAAa,CAAC"}

3
frontend/node_modules/entities/dist/esm/package.json generated vendored Normal file
View File

@@ -0,0 +1,3 @@
{
"type": "module"
}

320
frontend/node_modules/entities/src/decode.spec.ts generated vendored Normal file
View File

@@ -0,0 +1,320 @@
import { describe, it, expect, vitest } from "vitest";
import * as entities from "./decode.js";
describe("Decode test", () => {
const testcases = [
{ input: "&", output: "&" },
{ input: "&", output: "&" },
{ input: "&", output: "&" },
{ input: "&", output: "&" },
{ input: "&", output: "&" },
{ input: "&", output: "&" },
{ input: "&", output: "&" },
{ input: ":", output: ":" },
{ input: ":", output: ":" },
{ input: ":", output: ":" },
{ input: ":", output: ":" },
{ input: "&#", output: "&#" },
{ input: "&>", output: "&>" },
{ input: "id=770&#anchor", output: "id=770&#anchor" },
];
for (const { input, output } of testcases) {
it(`should XML decode ${input}`, () =>
expect(entities.decodeXML(input)).toBe(output));
it(`should HTML decode ${input}`, () =>
expect(entities.decodeHTML(input)).toBe(output));
}
it("should HTML decode partial legacy entity", () => {
expect(entities.decodeHTMLStrict("&timesbar")).toBe("&timesbar");
expect(entities.decodeHTML("&timesbar")).toBe("×bar");
});
it("should HTML decode legacy entities according to spec", () =>
expect(entities.decodeHTML("?&image_uri=1&=2&image=3")).toBe(
"?&image_uri=1&=2&image=3",
));
it("should back out of legacy entities", () =>
expect(entities.decodeHTML("&ampa")).toBe("&a"));
it("should not parse numeric entities in strict mode", () =>
expect(entities.decodeHTMLStrict("&#55")).toBe("&#55"));
it("should parse &nbsp followed by < (#852)", () =>
expect(entities.decodeHTML("&nbsp<")).toBe("\u00A0<"));
it("should decode trailing legacy entities", () => {
expect(entities.decodeHTML("&timesbar;&timesbar")).toBe("⨱×bar");
});
it("should decode multi-byte entities", () => {
expect(entities.decodeHTML("&NotGreaterFullEqual;")).toBe("≧̸");
});
it("should not decode legacy entities followed by text in attribute mode", () => {
expect(
entities.decodeHTML("&not", entities.DecodingMode.Attribute),
).toBe("¬");
expect(
entities.decodeHTML("&noti", entities.DecodingMode.Attribute),
).toBe("&noti");
expect(
entities.decodeHTML("&not=", entities.DecodingMode.Attribute),
).toBe("&not=");
expect(entities.decodeHTMLAttribute("&notp")).toBe("&notp");
expect(entities.decodeHTMLAttribute("&notP")).toBe("&notP");
expect(entities.decodeHTMLAttribute("&not3")).toBe("&not3");
});
});
describe("EntityDecoder", () => {
it("should decode decimal entities", () => {
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
);
expect(decoder.write("&#5", 1)).toBe(-1);
expect(decoder.write("8;", 0)).toBe(5);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith(":".charCodeAt(0), 5);
});
it("should decode hex entities", () => {
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
);
expect(decoder.write("&#x3a;", 1)).toBe(6);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith(":".charCodeAt(0), 6);
});
it("should decode named entities", () => {
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
);
expect(decoder.write("&amp;", 1)).toBe(5);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith("&".charCodeAt(0), 5);
});
it("should decode legacy entities", () => {
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
);
decoder.startEntity(entities.DecodingMode.Legacy);
expect(decoder.write("&amp", 1)).toBe(-1);
expect(callback).toHaveBeenCalledTimes(0);
expect(decoder.end()).toBe(4);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith("&".charCodeAt(0), 4);
});
it("should decode named entity written character by character", () => {
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
);
for (const c of "amp") {
expect(decoder.write(c, 0)).toBe(-1);
}
expect(decoder.write(";", 0)).toBe(5);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith("&".charCodeAt(0), 5);
});
it("should decode numeric entity written character by character", () => {
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
);
for (const c of "#x3a") {
expect(decoder.write(c, 0)).toBe(-1);
}
expect(decoder.write(";", 0)).toBe(6);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith(":".charCodeAt(0), 6);
});
it("should decode hex entities across several chunks", () => {
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
);
for (const chunk of ["#x", "cf", "ff", "d"]) {
expect(decoder.write(chunk, 0)).toBe(-1);
}
expect(decoder.write(";", 0)).toBe(9);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith(0xc_ff_fd, 9);
});
it("should not fail if nothing is written", () => {
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
);
expect(decoder.end()).toBe(0);
expect(callback).toHaveBeenCalledTimes(0);
});
describe("errors", () => {
it("should produce an error for a named entity without a semicolon", () => {
const errorHandlers = {
missingSemicolonAfterCharacterReference: vitest.fn(),
absenceOfDigitsInNumericCharacterReference: vitest.fn(),
validateNumericCharacterReference: vitest.fn(),
};
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
errorHandlers,
);
decoder.startEntity(entities.DecodingMode.Legacy);
expect(decoder.write("&amp;", 1)).toBe(5);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith("&".charCodeAt(0), 5);
expect(
errorHandlers.missingSemicolonAfterCharacterReference,
).toHaveBeenCalledTimes(0);
decoder.startEntity(entities.DecodingMode.Legacy);
expect(decoder.write("&amp", 1)).toBe(-1);
expect(decoder.end()).toBe(4);
expect(callback).toHaveBeenCalledTimes(2);
expect(callback).toHaveBeenLastCalledWith("&".charCodeAt(0), 4);
expect(
errorHandlers.missingSemicolonAfterCharacterReference,
).toHaveBeenCalledTimes(1);
});
it("should produce an error for a numeric entity without a semicolon", () => {
const errorHandlers = {
missingSemicolonAfterCharacterReference: vitest.fn(),
absenceOfDigitsInNumericCharacterReference: vitest.fn(),
validateNumericCharacterReference: vitest.fn(),
};
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
errorHandlers,
);
decoder.startEntity(entities.DecodingMode.Legacy);
expect(decoder.write("&#x3a", 1)).toBe(-1);
expect(decoder.end()).toBe(5);
expect(callback).toHaveBeenCalledTimes(1);
expect(callback).toHaveBeenCalledWith(0x3a, 5);
expect(
errorHandlers.missingSemicolonAfterCharacterReference,
).toHaveBeenCalledTimes(1);
expect(
errorHandlers.absenceOfDigitsInNumericCharacterReference,
).toHaveBeenCalledTimes(0);
expect(
errorHandlers.validateNumericCharacterReference,
).toHaveBeenCalledTimes(1);
expect(
errorHandlers.validateNumericCharacterReference,
).toHaveBeenCalledWith(0x3a);
});
it("should produce an error for numeric entities without digits", () => {
const errorHandlers = {
missingSemicolonAfterCharacterReference: vitest.fn(),
absenceOfDigitsInNumericCharacterReference: vitest.fn(),
validateNumericCharacterReference: vitest.fn(),
};
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
errorHandlers,
);
decoder.startEntity(entities.DecodingMode.Legacy);
expect(decoder.write("&#", 1)).toBe(-1);
expect(decoder.end()).toBe(0);
expect(callback).toHaveBeenCalledTimes(0);
expect(
errorHandlers.missingSemicolonAfterCharacterReference,
).toHaveBeenCalledTimes(0);
expect(
errorHandlers.absenceOfDigitsInNumericCharacterReference,
).toHaveBeenCalledTimes(1);
expect(
errorHandlers.absenceOfDigitsInNumericCharacterReference,
).toHaveBeenCalledWith(2);
expect(
errorHandlers.validateNumericCharacterReference,
).toHaveBeenCalledTimes(0);
});
it("should produce an error for hex entities without digits", () => {
const errorHandlers = {
missingSemicolonAfterCharacterReference: vitest.fn(),
absenceOfDigitsInNumericCharacterReference: vitest.fn(),
validateNumericCharacterReference: vitest.fn(),
};
const callback = vitest.fn();
const decoder = new entities.EntityDecoder(
entities.htmlDecodeTree,
callback,
errorHandlers,
);
decoder.startEntity(entities.DecodingMode.Legacy);
expect(decoder.write("&#x", 1)).toBe(-1);
expect(decoder.end()).toBe(0);
expect(callback).toHaveBeenCalledTimes(0);
expect(
errorHandlers.missingSemicolonAfterCharacterReference,
).toHaveBeenCalledTimes(0);
expect(
errorHandlers.absenceOfDigitsInNumericCharacterReference,
).toHaveBeenCalledTimes(1);
expect(
errorHandlers.validateNumericCharacterReference,
).toHaveBeenCalledTimes(0);
});
});
});

620
frontend/node_modules/entities/src/decode.ts generated vendored Normal file
View File

@@ -0,0 +1,620 @@
import { htmlDecodeTree } from "./generated/decode-data-html.js";
import { xmlDecodeTree } from "./generated/decode-data-xml.js";
import { replaceCodePoint, fromCodePoint } from "./decode-codepoint.js";
const enum CharCodes {
NUM = 35, // "#"
SEMI = 59, // ";"
EQUALS = 61, // "="
ZERO = 48, // "0"
NINE = 57, // "9"
LOWER_A = 97, // "a"
LOWER_F = 102, // "f"
LOWER_X = 120, // "x"
LOWER_Z = 122, // "z"
UPPER_A = 65, // "A"
UPPER_F = 70, // "F"
UPPER_Z = 90, // "Z"
}
/** Bit that needs to be set to convert an upper case ASCII character to lower case */
const TO_LOWER_BIT = 0b10_0000;
export enum BinTrieFlags {
VALUE_LENGTH = 0b1100_0000_0000_0000,
BRANCH_LENGTH = 0b0011_1111_1000_0000,
JUMP_TABLE = 0b0000_0000_0111_1111,
}
function isNumber(code: number): boolean {
return code >= CharCodes.ZERO && code <= CharCodes.NINE;
}
function isHexadecimalCharacter(code: number): boolean {
return (
(code >= CharCodes.UPPER_A && code <= CharCodes.UPPER_F) ||
(code >= CharCodes.LOWER_A && code <= CharCodes.LOWER_F)
);
}
function isAsciiAlphaNumeric(code: number): boolean {
return (
(code >= CharCodes.UPPER_A && code <= CharCodes.UPPER_Z) ||
(code >= CharCodes.LOWER_A && code <= CharCodes.LOWER_Z) ||
isNumber(code)
);
}
/**
* Checks if the given character is a valid end character for an entity in an attribute.
*
* Attribute values that aren't terminated properly aren't parsed, and shouldn't lead to a parser error.
* See the example in https://html.spec.whatwg.org/multipage/parsing.html#named-character-reference-state
*/
function isEntityInAttributeInvalidEnd(code: number): boolean {
return code === CharCodes.EQUALS || isAsciiAlphaNumeric(code);
}
const enum EntityDecoderState {
EntityStart,
NumericStart,
NumericDecimal,
NumericHex,
NamedEntity,
}
export 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 class EntityDecoder {
constructor(
/** The tree used to decode entities. */
private readonly 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.
*/
private readonly emitCodePoint: (cp: number, consumed: number) => void,
/** An object that is used to produce errors. */
private readonly errors?: EntityErrorProducer | undefined,
) {}
/** The current state of the decoder. */
private state = EntityDecoderState.EntityStart;
/** Characters that were consumed while parsing an entity. */
private consumed = 1;
/**
* The result of the entity.
*
* Either the result index of a numeric entity, or the codepoint of a
* numeric entity.
*/
private result = 0;
/** The current index in the decode tree. */
private treeIndex = 0;
/** The number of characters that were consumed in excess. */
private excess = 1;
/** The mode in which the decoder is operating. */
private decodeMode = DecodingMode.Strict;
/** Resets the instance to make it reusable. */
startEntity(decodeMode: DecodingMode): void {
this.decodeMode = decodeMode;
this.state = EntityDecoderState.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: string, offset: number): number {
switch (this.state) {
case EntityDecoderState.EntityStart: {
if (input.charCodeAt(offset) === CharCodes.NUM) {
this.state = EntityDecoderState.NumericStart;
this.consumed += 1;
return this.stateNumericStart(input, offset + 1);
}
this.state = EntityDecoderState.NamedEntity;
return this.stateNamedEntity(input, offset);
}
case EntityDecoderState.NumericStart: {
return this.stateNumericStart(input, offset);
}
case EntityDecoderState.NumericDecimal: {
return this.stateNumericDecimal(input, offset);
}
case EntityDecoderState.NumericHex: {
return this.stateNumericHex(input, offset);
}
case EntityDecoderState.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.
*/
private stateNumericStart(input: string, offset: number): number {
if (offset >= input.length) {
return -1;
}
if ((input.charCodeAt(offset) | TO_LOWER_BIT) === CharCodes.LOWER_X) {
this.state = EntityDecoderState.NumericHex;
this.consumed += 1;
return this.stateNumericHex(input, offset + 1);
}
this.state = EntityDecoderState.NumericDecimal;
return this.stateNumericDecimal(input, offset);
}
private addToNumericResult(
input: string,
start: number,
end: number,
base: number,
): void {
if (start !== end) {
const digitCount = end - start;
this.result =
this.result * Math.pow(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.
*/
private stateNumericHex(input: string, offset: number): number {
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.
*/
private stateNumericDecimal(input: string, offset: number): number {
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.
*/
private emitNumericEntity(lastCp: number, expectedLength: number): number {
// Ensure we consumed at least one digit.
if (this.consumed <= expectedLength) {
this.errors?.absenceOfDigitsInNumericCharacterReference(
this.consumed,
);
return 0;
}
// Figure out if this is a legit end of the entity
if (lastCp === CharCodes.SEMI) {
this.consumed += 1;
} else if (this.decodeMode === DecodingMode.Strict) {
return 0;
}
this.emitCodePoint(replaceCodePoint(this.result), this.consumed);
if (this.errors) {
if (lastCp !== CharCodes.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.
*/
private stateNamedEntity(input: string, offset: number): number {
const { decodeTree } = this;
let current = decodeTree[this.treeIndex];
// The mask is the number of bytes of the value, including the current byte.
let valueLength = (current & BinTrieFlags.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 === DecodingMode.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 & BinTrieFlags.VALUE_LENGTH) >> 14;
// If the branch is a value, store it and continue
if (valueLength !== 0) {
// If the entity is terminated by a semicolon, we are done.
if (char === CharCodes.SEMI) {
return this.emitNamedEntityData(
this.treeIndex,
valueLength,
this.consumed + this.excess,
);
}
// If we encounter a non-terminated (legacy) entity while parsing strictly, then ignore it.
if (this.decodeMode !== DecodingMode.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.
*/
private emitNotTerminatedNamedEntity(): number {
const { result, decodeTree } = this;
const valueLength =
(decodeTree[result] & BinTrieFlags.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.
*/
private emitNamedEntityData(
result: number,
valueLength: number,
consumed: number,
): number {
const { decodeTree } = this;
this.emitCodePoint(
valueLength === 1
? decodeTree[result] & ~BinTrieFlags.VALUE_LENGTH
: decodeTree[result + 1],
consumed,
);
if (valueLength === 3) {
// For multi-byte values, we need to emit the second byte.
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(): number {
switch (this.state) {
case EntityDecoderState.NamedEntity: {
// Emit a named entity if we have one.
return this.result !== 0 &&
(this.decodeMode !== DecodingMode.Attribute ||
this.result === this.treeIndex)
? this.emitNotTerminatedNamedEntity()
: 0;
}
// Otherwise, emit a numeric entity if we have one.
case EntityDecoderState.NumericDecimal: {
return this.emitNumericEntity(0, 2);
}
case EntityDecoderState.NumericHex: {
return this.emitNumericEntity(0, 3);
}
case EntityDecoderState.NumericStart: {
this.errors?.absenceOfDigitsInNumericCharacterReference(
this.consumed,
);
return 0;
}
case EntityDecoderState.EntityStart: {
// Return 0 if we have no entity.
return 0;
}
}
}
}
/**
* Creates a function that decodes entities in a string.
*
* @param decodeTree The decode tree.
* @returns A function that decodes entities in a string.
*/
function getDecoder(decodeTree: Uint16Array) {
let returnValue = "";
const decoder = new EntityDecoder(
decodeTree,
(data) => (returnValue += fromCodePoint(data)),
);
return function decodeWithTrie(
input: string,
decodeMode: DecodingMode,
): string {
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;
// If `length` is 0, skip the current `&` and continue.
offset = length === 0 ? lastIndex + 1 : lastIndex;
}
const result = returnValue + input.slice(lastIndex);
// Make sure we don't keep a reference to the final string.
returnValue = "";
return result;
};
}
/**
* 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 function determineBranch(
decodeTree: Uint16Array,
current: number,
nodeIndex: number,
char: number,
): number {
const branchCount = (current & BinTrieFlags.BRANCH_LENGTH) >> 7;
const jumpOffset = current & BinTrieFlags.JUMP_TABLE;
// Case 1: Single branch encoded in jump offset
if (branchCount === 0) {
return jumpOffset !== 0 && char === jumpOffset ? nodeIndex : -1;
}
// Case 2: Multiple branches encoded in jump table
if (jumpOffset) {
const value = char - jumpOffset;
return value < 0 || value >= branchCount
? -1
: decodeTree[nodeIndex + value] - 1;
}
// Case 3: Multiple branches encoded in dictionary
// Binary search for the character.
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);
/**
* Decodes an HTML string.
*
* @param htmlString The string to decode.
* @param mode The decoding mode.
* @returns The decoded string.
*/
export function decodeHTML(
htmlString: string,
mode: DecodingMode = DecodingMode.Legacy,
): string {
return htmlDecoder(htmlString, mode);
}
/**
* Decodes an HTML string in an attribute.
*
* @param htmlAttribute The string to decode.
* @returns The decoded string.
*/
export function decodeHTMLAttribute(htmlAttribute: string): string {
return htmlDecoder(htmlAttribute, DecodingMode.Attribute);
}
/**
* Decodes an HTML string, requiring all entities to be terminated by a semicolon.
*
* @param htmlString The string to decode.
* @returns The decoded string.
*/
export function decodeHTMLStrict(htmlString: string): string {
return htmlDecoder(htmlString, DecodingMode.Strict);
}
/**
* Decodes an XML string, requiring all entities to be terminated by a semicolon.
*
* @param xmlString The string to decode.
* @returns The decoded string.
*/
export function decodeXML(xmlString: string): string {
return xmlDecoder(xmlString, DecodingMode.Strict);
}
// Re-export for use by eg. htmlparser2
export { htmlDecodeTree } from "./generated/decode-data-html.js";
export { xmlDecodeTree } from "./generated/decode-data-xml.js";
export {
decodeCodePoint,
replaceCodePoint,
fromCodePoint,
} from "./decode-codepoint.js";

14
frontend/node_modules/entities/src/escape.spec.ts generated vendored Normal file
View File

@@ -0,0 +1,14 @@
import { describe, it, expect } from "vitest";
import * as entities from "./index.js";
describe("escape HTML", () => {
it("should escape HTML attribute values", () =>
expect(entities.escapeAttribute('<a " attr > & value \u00A0!')).toBe(
"<a &quot; attr > &amp; value &nbsp;!",
));
it("should escape HTML text", () =>
expect(entities.escapeText('<a " text > & value \u00A0!')).toBe(
'&lt;a " text &gt; &amp; value &nbsp;!',
));
});

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

188
frontend/node_modules/entities/src/index.ts generated vendored Normal file
View File

@@ -0,0 +1,188 @@
import { decodeXML, decodeHTML, DecodingMode } from "./decode.js";
import { encodeHTML, encodeNonAsciiHTML } from "./encode.js";
import {
encodeXML,
escapeUTF8,
escapeAttribute,
escapeText,
} from "./escape.js";
/** The level of entities to support. */
export enum EntityLevel {
/** Support only XML entities. */
XML = 0,
/** Support HTML entities, which are a superset of XML entities. */
HTML = 1,
}
export enum EncodingMode {
/**
* The output is UTF-8 encoded. Only characters that need escaping within
* XML will be escaped.
*/
UTF8,
/**
* The output consists only of ASCII characters. Characters that need
* escaping within HTML, and characters that aren't ASCII characters will
* be escaped.
*/
ASCII,
/**
* Encode all characters that have an equivalent entity, as well as all
* characters that are not ASCII characters.
*/
Extensive,
/**
* Encode all characters that have to be escaped in HTML attributes,
* following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
*/
Attribute,
/**
* Encode all characters that have to be escaped in HTML text,
* following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
*/
Text,
}
export interface DecodingOptions {
/**
* The level of entities to support.
* @default {@link 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 {@link DecodingMode.Legacy}
*/
mode?: DecodingMode | undefined;
}
/**
* Decodes a string with entities.
*
* @param input String to decode.
* @param options Decoding options.
*/
export function decode(
input: string,
options: DecodingOptions | EntityLevel = EntityLevel.XML,
): string {
const level = typeof options === "number" ? options : options.level;
if (level === EntityLevel.HTML) {
const mode = typeof options === "object" ? options.mode : undefined;
return decodeHTML(input, mode);
}
return decodeXML(input);
}
/**
* Decodes a string with entities. Does not allow missing trailing semicolons for entities.
*
* @param input String to decode.
* @param options Decoding options.
* @deprecated Use `decode` with the `mode` set to `Strict`.
*/
export function decodeStrict(
input: string,
options: DecodingOptions | EntityLevel = EntityLevel.XML,
): string {
const normalizedOptions =
typeof options === "number" ? { level: options } : options;
normalizedOptions.mode ??= DecodingMode.Strict;
return decode(input, normalizedOptions);
}
/**
* Options for `encode`.
*/
export interface EncodingOptions {
/**
* The level of entities to support.
* @default {@link EntityLevel.XML}
*/
level?: EntityLevel;
/**
* Output format.
* @default {@link EncodingMode.Extensive}
*/
mode?: EncodingMode;
}
/**
* Encodes a string with entities.
*
* @param input String to encode.
* @param options Encoding options.
*/
export function encode(
input: string,
options: EncodingOptions | EntityLevel = EntityLevel.XML,
): string {
const { mode = EncodingMode.Extensive, level = EntityLevel.XML } =
typeof options === "number" ? { level: options } : options;
switch (mode) {
case EncodingMode.UTF8: {
return escapeUTF8(input);
}
case EncodingMode.Attribute: {
return escapeAttribute(input);
}
case EncodingMode.Text: {
return escapeText(input);
}
case EncodingMode.ASCII: {
return level === EntityLevel.HTML
? encodeNonAsciiHTML(input)
: encodeXML(input);
}
// eslint-disable-next-line unicorn/no-useless-switch-case
case EncodingMode.Extensive:
default: {
return level === EntityLevel.HTML
? encodeHTML(input)
: encodeXML(input);
}
}
}
export {
encodeXML,
escape,
escapeUTF8,
escapeAttribute,
escapeText,
} from "./escape.js";
export {
encodeHTML,
encodeNonAsciiHTML,
// Legacy aliases (deprecated)
encodeHTML as encodeHTML4,
encodeHTML as encodeHTML5,
} from "./encode.js";
export {
EntityDecoder,
DecodingMode,
decodeXML,
decodeHTML,
decodeHTMLStrict,
decodeHTMLAttribute,
// Legacy aliases (deprecated)
decodeHTML as decodeHTML4,
decodeHTML as decodeHTML5,
decodeHTMLStrict as decodeHTML4Strict,
decodeHTMLStrict as decodeHTML5Strict,
decodeXML as decodeXMLStrict,
} from "./decode.js";