ai/world
1
0
Fork 0
Code Issues 2 Releases Activity

fix

Browse Source
This commit is contained in:
syui
2025-05-12 05:38:44 +09:00
parent dced21c3f8
commit 6d78bfa46e
8120 changed files with 1161564 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
book/node_modules/encoding-sniffer/dist/esm/index.d.ts generated vendored Normal file
View File

@ -0,0 +1,33 @@
/// <reference types="node" resolution-mode="require"/>
/// <reference types="node" resolution-mode="require"/>
import { Transform, type TransformCallback } from "node:stream";
import type { SnifferOptions } from "./sniffer.js";
/**
* Sniff the encoding of a buffer, then decode it.
*
* @param buffer Buffer to be decoded
* @param options Options for the sniffer
* @returns The decoded buffer
*/
export declare function decodeBuffer(buffer: Buffer, options?: SnifferOptions): string;
/**
* Decodes a stream of buffers into a stream of strings.
*
* Reads the first 1024 bytes and passes them to the sniffer. Once an encoding
* has been determined, it passes all data to iconv-lite's stream and outputs
* the results.
*/
export declare class DecodeStream extends Transform {
private readonly sniffer;
private readonly buffers;
/** The iconv decode stream. If it is set, we have read more than `options.maxBytes` bytes. */
private iconv;
private readonly maxBytes;
private readBytes;
constructor(options?: SnifferOptions);
_transform(chunk: Uint8Array, _encoding: string, callback: TransformCallback): void;
private getIconvStream;
_flush(callback: TransformCallback): void;
}
export { type SnifferOptions, getEncoding } from "./sniffer.js";
//# sourceMappingURL=index.d.ts.map

1
book/node_modules/encoding-sniffer/dist/esm/index.d.ts.map generated vendored Normal file
View File

@ -0,0 +1 @@
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":";;AAAA,OAAO,EAAE,SAAS,EAAE,KAAK,iBAAiB,EAAE,MAAM,aAAa,CAAC;AAEhE,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,cAAc,CAAC;AAGnD;;;;;;GAMG;AACH,wBAAgB,YAAY,CACxB,MAAM,EAAE,MAAM,EACd,OAAO,GAAE,cAAmB,GAC7B,MAAM,CAER;AAED;;;;;;GAMG;AACH,qBAAa,YAAa,SAAQ,SAAS;IACvC,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAU;IAClC,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAoB;IAC5C,8FAA8F;IAC9F,OAAO,CAAC,KAAK,CAAuC;IACpD,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAC;IAC1B,OAAO,CAAC,SAAS,CAAK;gBAEV,OAAO,CAAC,EAAE,cAAc;IAM3B,UAAU,CACf,KAAK,EAAE,UAAU,EACjB,SAAS,EAAE,MAAM,EACjB,QAAQ,EAAE,iBAAiB,GAC5B,IAAI;IAeP,OAAO,CAAC,cAAc;IAmBb,MAAM,CAAC,QAAQ,EAAE,iBAAiB,GAAG,IAAI;CAGrD;AAED,OAAO,EAAE,KAAK,cAAc,EAAE,WAAW,EAAE,MAAM,cAAc,CAAC"}

85
book/node_modules/encoding-sniffer/dist/esm/index.js generated vendored Normal file
View File

@ -0,0 +1,85 @@
var __extends = (this && this.__extends) || (function () {
var extendStatics = function (d, b) {
extendStatics = Object.setPrototypeOf ||
({ __proto__: [] } instanceof Array && function (d, b) { d.__proto__ = b; }) ||
function (d, b) { for (var p in b) if (Object.prototype.hasOwnProperty.call(b, p)) d[p] = b[p]; };
return extendStatics(d, b);
};
return function (d, b) {
if (typeof b !== "function" && b !== null)
throw new TypeError("Class extends value " + String(b) + " is not a constructor or null");
extendStatics(d, b);
function __() { this.constructor = d; }
d.prototype = b === null ? Object.create(b) : (__.prototype = b.prototype, new __());
};
})();
import { Transform } from "node:stream";
import iconv from "iconv-lite";
import { Sniffer, getEncoding } from "./sniffer.js";
/**
* Sniff the encoding of a buffer, then decode it.
*
* @param buffer Buffer to be decoded
* @param options Options for the sniffer
* @returns The decoded buffer
*/
export function decodeBuffer(buffer, options) {
if (options === void 0) { options = {}; }
return iconv.decode(buffer, getEncoding(buffer, options));
}
/**
* Decodes a stream of buffers into a stream of strings.
*
* Reads the first 1024 bytes and passes them to the sniffer. Once an encoding
* has been determined, it passes all data to iconv-lite's stream and outputs
* the results.
*/
var DecodeStream = /** @class */ (function (_super) {
__extends(DecodeStream, _super);
function DecodeStream(options) {
var _a;
var _this = _super.call(this, { decodeStrings: false, encoding: "utf-8" }) || this;
_this.buffers = [];
/** The iconv decode stream. If it is set, we have read more than `options.maxBytes` bytes. */
_this.iconv = null;
_this.readBytes = 0;
_this.sniffer = new Sniffer(options);
_this.maxBytes = (_a = options === null || options === void 0 ? void 0 : options.maxBytes) !== null && _a !== void 0 ? _a : 1024;
return _this;
}
DecodeStream.prototype._transform = function (chunk, _encoding, callback) {
if (this.readBytes < this.maxBytes) {
this.sniffer.write(chunk);
this.readBytes += chunk.length;
if (this.readBytes < this.maxBytes) {
this.buffers.push(chunk);
callback();
return;
}
}
this.getIconvStream().write(chunk, callback);
};
DecodeStream.prototype.getIconvStream = function () {
var _this = this;
if (this.iconv) {
return this.iconv;
}
var stream = iconv.decodeStream(this.sniffer.encoding);
stream.on("data", function (chunk) { return _this.push(chunk, "utf-8"); });
stream.on("end", function () { return _this.push(null); });
this.iconv = stream;
for (var _i = 0, _a = this.buffers; _i < _a.length; _i++) {
var buffer = _a[_i];
stream.write(buffer);
}
this.buffers.length = 0;
return stream;
};
DecodeStream.prototype._flush = function (callback) {
this.getIconvStream().end(callback);
};
return DecodeStream;
}(Transform));
export { DecodeStream };
export { getEncoding } from "./sniffer.js";
//# sourceMappingURL=index.js.map

1
book/node_modules/encoding-sniffer/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,EAA0B,MAAM,aAAa,CAAC;AAChE,OAAO,KAAK,MAAM,YAAY,CAAC;AAE/B,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,MAAM,cAAc,CAAC;AAEpD;;;;;;GAMG;AACH,MAAM,UAAU,YAAY,CACxB,MAAc,EACd,OAA4B;IAA5B,wBAAA,EAAA,YAA4B;IAE5B,OAAO,KAAK,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC;AAC9D,CAAC;AAED;;;;;;GAMG;AACH;IAAkC,gCAAS;IAQvC,sBAAY,OAAwB;;QAChC,YAAA,MAAK,YAAC,EAAE,aAAa,EAAE,KAAK,EAAE,QAAQ,EAAE,OAAO,EAAE,CAAC,SAAC;QAPtC,aAAO,GAAiB,EAAE,CAAC;QAC5C,8FAA8F;QACtF,WAAK,GAAkC,IAAI,CAAC;QAE5C,eAAS,GAAG,CAAC,CAAC;QAIlB,KAAI,CAAC,OAAO,GAAG,IAAI,OAAO,CAAC,OAAO,CAAC,CAAC;QACpC,KAAI,CAAC,QAAQ,GAAG,MAAA,OAAO,aAAP,OAAO,uBAAP,OAAO,CAAE,QAAQ,mCAAI,IAAI,CAAC;;IAC9C,CAAC;IAEQ,iCAAU,GAAnB,UACI,KAAiB,EACjB,SAAiB,EACjB,QAA2B;QAE3B,IAAI,IAAI,CAAC,SAAS,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAC;YACjC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;YAC1B,IAAI,CAAC,SAAS,IAAI,KAAK,CAAC,MAAM,CAAC;YAE/B,IAAI,IAAI,CAAC,SAAS,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAC;gBACjC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;gBACzB,QAAQ,EAAE,CAAC;gBACX,OAAO;YACX,CAAC;QACL,CAAC;QAED,IAAI,CAAC,cAAc,EAAE,CAAC,KAAK,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC;IACjD,CAAC;IAEO,qCAAc,GAAtB;QAAA,iBAiBC;QAhBG,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,IAAI,CAAC,KAAK,CAAC;QACtB,CAAC;QAED,IAAM,MAAM,GAAG,KAAK,CAAC,YAAY,CAAC,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;QACzD,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,UAAC,KAAa,IAAK,OAAA,KAAI,CAAC,IAAI,CAAC,KAAK,EAAE,OAAO,CAAC,EAAzB,CAAyB,CAAC,CAAC;QAChE,MAAM,CAAC,EAAE,CAAC,KAAK,EAAE,cAAM,OAAA,KAAI,CAAC,IAAI,CAAC,IAAI,CAAC,EAAf,CAAe,CAAC,CAAC;QAExC,IAAI,CAAC,KAAK,GAAG,MAAM,CAAC;QAEpB,KAAqB,UAAY,EAAZ,KAAA,IAAI,CAAC,OAAO,EAAZ,cAAY,EAAZ,IAAY,EAAE,CAAC;YAA/B,IAAM,MAAM,SAAA;YACb,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;QACzB,CAAC;QACD,IAAI,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC;QAExB,OAAO,MAAM,CAAC;IAClB,CAAC;IAEQ,6BAAM,GAAf,UAAgB,QAA2B;QACvC,IAAI,CAAC,cAAc,EAAE,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;IACxC,CAAC;IACL,mBAAC;AAAD,CAAC,AAvDD,CAAkC,SAAS,GAuD1C;;AAED,OAAO,EAAuB,WAAW,EAAE,MAAM,cAAc,CAAC"}

3
book/node_modules/encoding-sniffer/dist/esm/package.json generated vendored Normal file
View File

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

148
book/node_modules/encoding-sniffer/dist/esm/sniffer.d.ts generated vendored Normal file
View File

@ -0,0 +1,148 @@
export declare enum ResultType {
BOM = 0,
PASSED = 1,
XML_PREFIX = 2,
META_TAG = 3,
XML_ENCODING = 4,
DEFAULT = 5
}
export declare const STRINGS: {
UTF8_BOM: Uint8Array;
UTF16LE_BOM: Uint8Array;
UTF16BE_BOM: Uint8Array;
UTF16LE_XML_PREFIX: Uint8Array;
UTF16BE_XML_PREFIX: Uint8Array;
XML_DECLARATION: Uint8Array;
ENCODING: Uint8Array;
META: Uint8Array;
HTTP_EQUIV: Uint8Array;
CONTENT: Uint8Array;
CONTENT_TYPE: Uint8Array;
CHARSET: Uint8Array;
COMMENT_START: Uint8Array;
COMMENT_END: Uint8Array;
};
export interface SnifferOptions {
/**
* The maximum number of bytes to sniff.
*
* @default 1024
*/
maxBytes?: number;
/**
* The encoding specified by the user.
*/
userEncoding?: string;
/**
* The encoding specified by the transport layer.
*/
transportLayerEncodingLabel?: string;
/**
* The default encoding to use.
*
* @default "windows-1252"
*/
defaultEncoding?: string;
}
export declare class Sniffer {
/** The maximum number of bytes to sniff. */
private readonly maxBytes;
/** The offset of the previous buffers. */
private offset;
private state;
private sectionIndex;
private attribType;
/**
* Indicates if the `http-equiv` is `content-type`.
*
* Initially `null`, a boolean when a value is found.
*/
private gotPragma;
private needsPragma;
private inMetaTag;
encoding: string;
resultType: ResultType;
private setResult;
constructor({ maxBytes, userEncoding, transportLayerEncodingLabel, defaultEncoding, }?: SnifferOptions);
private stateBegin;
private stateBeginLT;
private stateUTF16BE_XML_PREFIX;
private stateUTF16LE_XML_PREFIX;
private stateBOM16LE;
private stateBOM16BE;
private stateBOM8;
private stateBeforeTag;
/**
* We have seen a `<`, and now have to figure out what to do.
*
* Options:
* - `<meta`
* - Any other tag
* - A closing tag
* - `<!--`
* - An XML declaration
*
*/
private stateBeforeTagName;
private stateBeforeCloseTagName;
private stateCommentStart;
private stateCommentEnd;
/**
* Any section starting with `<!`, `<?`, `</`, without being a closing tag or comment.
*/
private stateWeirdTag;
/**
* Advances the section, ignoring upper/lower case.
*
* Make sure the section has left-over characters before calling.
*
* @returns `false` if we did not match the section.
*/
private advanceSectionIC;
/**
* Advances the section.
*
* Make sure the section has left-over characters before calling.
*
* @returns `false` if we did not match the section.
*/
private advanceSection;
private stateTagNameMeta;
private stateTagNameOther;
private stateBeforeAttribute;
private handleMetaAttrib;
private stateMetaAttribHttpEquiv;
private stateMetaAttribC;
private stateMetaAttribCharset;
private stateMetaAttribContent;
private stateMetaAttribAfterName;
private stateAnyAttribName;
private stateAfterAttributeName;
private quoteCharacter;
private readonly attributeValue;
private stateBeforeAttributeValue;
private stateMetaAttribHttpEquivValue;
private handleMetaContentValue;
private handleAttributeValue;
private stateAttributeValueUnquoted;
private findMetaContentEncoding;
private stateMetaContentValueUnquotedBeforeEncoding;
private stateMetaContentValueUnquotedBeforeValue;
private stateMetaContentValueUnquotedValueQuoted;
private stateMetaContentValueUnquotedValueUnquoted;
private stateMetaContentValueQuotedValueUnquoted;
private stateMetaContentValueQuotedValueQuoted;
private stateMetaContentValueQuotedBeforeEncoding;
private stateMetaContentValueQuotedAfterEncoding;
private stateMetaContentValueQuotedBeforeValue;
private stateAttributeValueQuoted;
private stateXMLDeclaration;
private stateXMLDeclarationBeforeEncoding;
private stateXMLDeclarationAfterEncoding;
private stateXMLDeclarationBeforeValue;
private stateXMLDeclarationValue;
write(buffer: Uint8Array): void;
}
/** Get the encoding for the passed buffer. */
export declare function getEncoding(buffer: Uint8Array, options?: SnifferOptions): string;
//# sourceMappingURL=sniffer.d.ts.map

1
book/node_modules/encoding-sniffer/dist/esm/sniffer.d.ts.map generated vendored Normal file
View File

@ -0,0 +1 @@
{"version":3,"file":"sniffer.d.ts","sourceRoot":"","sources":["../../src/sniffer.ts"],"names":[],"mappings":"AAuEA,oBAAY,UAAU;IAElB,GAAG,IAAI;IAEP,MAAM,IAAI;IAEV,UAAU,IAAI;IAEd,QAAQ,IAAI;IAEZ,YAAY,IAAI;IAEhB,OAAO,IAAI;CACd;AAgDD,eAAO,MAAM,OAAO;;;;;;;;;;;;;;;CAenB,CAAC;AAaF,MAAM,WAAW,cAAc;IAC3B;;;;OAIG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB;;OAEG;IACH,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB;;OAEG;IACH,2BAA2B,CAAC,EAAE,MAAM,CAAC;IACrC;;;;OAIG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;CAC5B;AAED,qBAAa,OAAO;IAChB,4CAA4C;IAC5C,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAS;IAClC,0CAA0C;IAC1C,OAAO,CAAC,MAAM,CAAK;IAEnB,OAAO,CAAC,KAAK,CAAe;IAC5B,OAAO,CAAC,YAAY,CAAK;IACzB,OAAO,CAAC,UAAU,CAAmB;IACrC;;;;OAIG;IACH,OAAO,CAAC,SAAS,CAAwB;IACzC,OAAO,CAAC,WAAW,CAAuB;IAE1C,OAAO,CAAC,SAAS,CAAS;IAEnB,QAAQ,SAAkB;IAC1B,UAAU,aAAsB;IAEvC,OAAO,CAAC,SAAS;gBAsBL,EACR,QAAe,EACf,YAAY,EACZ,2BAA2B,EAC3B,eAAe,GAClB,GAAE,cAAmB;IAetB,OAAO,CAAC,UAAU;IAmClB,OAAO,CAAC,YAAY;IAapB,OAAO,CAAC,uBAAuB;IAa/B,OAAO,CAAC,uBAAuB;IAa/B,OAAO,CAAC,YAAY;IASpB,OAAO,CAAC,YAAY;IASpB,OAAO,CAAC,SAAS;IASjB,OAAO,CAAC,cAAc;IAOtB;;;;;;;;;;OAUG;IACH,OAAO,CAAC,kBAAkB;IAiC1B,OAAO,CAAC,uBAAuB;IAO/B,OAAO,CAAC,iBAAiB;IAazB,OAAO,CAAC,eAAe;IAcvB;;OAEG;IACH,OAAO,CAAC,aAAa;IAMrB;;;;;;OAMG;IACH,OAAO,CAAC,gBAAgB;IAIxB;;;;;;OAMG;IACH,OAAO,CAAC,cAAc;IAUtB,OAAO,CAAC,gBAAgB;IAkBxB,OAAO,CAAC,iBAAiB;IAQzB,OAAO,CAAC,oBAAoB;IAsB5B,OAAO,CAAC,gBAAgB;IAgBxB,OAAO,CAAC,wBAAwB;IAIhC,OAAO,CAAC,gBAAgB;IAcxB,OAAO,CAAC,sBAAsB;IAI9B,OAAO,CAAC,sBAAsB;IAI9B,OAAO,CAAC,wBAAwB;IAUhC,OAAO,CAAC,kBAAkB;IAW1B,OAAO,CAAC,uBAAuB;IAW/B,OAAO,CAAC,cAAc,CAAK;IAC3B,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAgB;IAE/C,OAAO,CAAC,yBAAyB;IA8BjC,OAAO,CAAC,6BAA6B;IA+BrC,OAAO,CAAC,sBAAsB;IAe9B,OAAO,CAAC,oBAAoB;IAS5B,OAAO,CAAC,2BAA2B;IAYnC,OAAO,CAAC,uBAAuB;IAY/B,OAAO,CAAC,2CAA2C;IAYnD,OAAO,CAAC,wCAAwC;IAahD,OAAO,CAAC,wCAAwC;IAYhD,OAAO,CAAC,0CAA0C;IAUlD,OAAO,CAAC,wCAAwC;IAWhD,OAAO,CAAC,sCAAsC;IAgB9C,OAAO,CAAC,yCAAyC;IAQjD,OAAO,CAAC,wCAAwC;IAUhD,OAAO,CAAC,sCAAsC;IAW9C,OAAO,CAAC,yBAAyB;IAUjC,OAAO,CAAC,mBAAmB;IAW3B,OAAO,CAAC,iCAAiC;IAazC,OAAO,CAAC,gCAAgC;IASxC,OAAO,CAAC,8BAA8B;IAUtC,OAAO,CAAC,wBAAwB;IAgBzB,KAAK,CAAC,MAAM,EAAE,UAAU,GAAG,IAAI;CAoOzC;AAED,8CAA8C;AAC9C,wBAAgB,WAAW,CACvB,MAAM,EAAE,UAAU,EAClB,OAAO,CAAC,EAAE,cAAc,GACzB,MAAM,CAIR"}

988
book/node_modules/encoding-sniffer/dist/esm/sniffer.js generated vendored Normal file
View File

@ -0,0 +1,988 @@
import { labelToName } from "whatwg-encoding";
// https://html.spec.whatwg.org/multipage/syntax.html#prescan-a-byte-stream-to-determine-its-encoding
var State;
(function (State) {
// Before anything starts; can be any of BOM, UTF-16 XML declarations or meta tags
State[State["Begin"] = 0] = "Begin";
// Inside of a BOM
State[State["BOM16BE"] = 1] = "BOM16BE";
State[State["BOM16LE"] = 2] = "BOM16LE";
State[State["BOM8"] = 3] = "BOM8";
// XML prefix
State[State["UTF16LE_XML_PREFIX"] = 4] = "UTF16LE_XML_PREFIX";
State[State["BeginLT"] = 5] = "BeginLT";
State[State["UTF16BE_XML_PREFIX"] = 6] = "UTF16BE_XML_PREFIX";
// Waiting for opening `<`
State[State["BeforeTag"] = 7] = "BeforeTag";
// After the opening `<`
State[State["BeforeTagName"] = 8] = "BeforeTagName";
// After `</`
State[State["BeforeCloseTagName"] = 9] = "BeforeCloseTagName";
// Beginning of a comment
State[State["CommentStart"] = 10] = "CommentStart";
// End of a comment
State[State["CommentEnd"] = 11] = "CommentEnd";
// A tag name that could be `meta`
State[State["TagNameMeta"] = 12] = "TagNameMeta";
// A tag name that is not `meta`
State[State["TagNameOther"] = 13] = "TagNameOther";
// XML declaration
State[State["XMLDeclaration"] = 14] = "XMLDeclaration";
State[State["XMLDeclarationBeforeEncoding"] = 15] = "XMLDeclarationBeforeEncoding";
State[State["XMLDeclarationAfterEncoding"] = 16] = "XMLDeclarationAfterEncoding";
State[State["XMLDeclarationBeforeValue"] = 17] = "XMLDeclarationBeforeValue";
State[State["XMLDeclarationValue"] = 18] = "XMLDeclarationValue";
// Anything that looks like a tag, but doesn't fit in the above categories
State[State["WeirdTag"] = 19] = "WeirdTag";
State[State["BeforeAttribute"] = 20] = "BeforeAttribute";
/*
* Attributes in meta tag — we compare them to our set here, and back out
* We care about four attributes: http-equiv, content-type, content, charset
*/
State[State["MetaAttribHttpEquiv"] = 21] = "MetaAttribHttpEquiv";
// The value has to be `content-type`
State[State["MetaAttribHttpEquivValue"] = 22] = "MetaAttribHttpEquivValue";
State[State["MetaAttribC"] = 23] = "MetaAttribC";
State[State["MetaAttribContent"] = 24] = "MetaAttribContent";
State[State["MetaAttribCharset"] = 25] = "MetaAttribCharset";
// Waiting for whitespace
State[State["MetaAttribAfterName"] = 26] = "MetaAttribAfterName";
State[State["MetaContentValueQuotedBeforeEncoding"] = 27] = "MetaContentValueQuotedBeforeEncoding";
State[State["MetaContentValueQuotedAfterEncoding"] = 28] = "MetaContentValueQuotedAfterEncoding";
State[State["MetaContentValueQuotedBeforeValue"] = 29] = "MetaContentValueQuotedBeforeValue";
State[State["MetaContentValueQuotedValueQuoted"] = 30] = "MetaContentValueQuotedValueQuoted";
State[State["MetaContentValueQuotedValueUnquoted"] = 31] = "MetaContentValueQuotedValueUnquoted";
State[State["MetaContentValueUnquotedBeforeEncoding"] = 32] = "MetaContentValueUnquotedBeforeEncoding";
State[State["MetaContentValueUnquotedBeforeValue"] = 33] = "MetaContentValueUnquotedBeforeValue";
State[State["MetaContentValueUnquotedValueQuoted"] = 34] = "MetaContentValueUnquotedValueQuoted";
State[State["MetaContentValueUnquotedValueUnquoted"] = 35] = "MetaContentValueUnquotedValueUnquoted";
State[State["AnyAttribName"] = 36] = "AnyAttribName";
// After the name of an attribute, before the equals sign
State[State["AfterAttributeName"] = 37] = "AfterAttributeName";
// After `=`
State[State["BeforeAttributeValue"] = 38] = "BeforeAttributeValue";
State[State["AttributeValueQuoted"] = 39] = "AttributeValueQuoted";
State[State["AttributeValueUnquoted"] = 40] = "AttributeValueUnquoted";
})(State || (State = {}));
export var ResultType;
(function (ResultType) {
// Byte order mark
ResultType[ResultType["BOM"] = 0] = "BOM";
// User- or transport layer-defined
ResultType[ResultType["PASSED"] = 1] = "PASSED";
// XML prefixes
ResultType[ResultType["XML_PREFIX"] = 2] = "XML_PREFIX";
// Meta tag
ResultType[ResultType["META_TAG"] = 3] = "META_TAG";
// XML encoding
ResultType[ResultType["XML_ENCODING"] = 4] = "XML_ENCODING";
// Default
ResultType[ResultType["DEFAULT"] = 5] = "DEFAULT";
})(ResultType || (ResultType = {}));
var AttribType;
(function (AttribType) {
AttribType[AttribType["None"] = 0] = "None";
AttribType[AttribType["HttpEquiv"] = 1] = "HttpEquiv";
AttribType[AttribType["Content"] = 2] = "Content";
AttribType[AttribType["Charset"] = 3] = "Charset";
})(AttribType || (AttribType = {}));
var Chars;
(function (Chars) {
Chars[Chars["NIL"] = 0] = "NIL";
Chars[Chars["TAB"] = 9] = "TAB";
Chars[Chars["LF"] = 10] = "LF";
Chars[Chars["CR"] = 13] = "CR";
Chars[Chars["SPACE"] = 32] = "SPACE";
Chars[Chars["EXCLAMATION"] = 33] = "EXCLAMATION";
Chars[Chars["DQUOTE"] = 34] = "DQUOTE";
Chars[Chars["SQUOTE"] = 39] = "SQUOTE";
Chars[Chars["DASH"] = 45] = "DASH";
Chars[Chars["SLASH"] = 47] = "SLASH";
Chars[Chars["SEMICOLON"] = 59] = "SEMICOLON";
Chars[Chars["LT"] = 60] = "LT";
Chars[Chars["EQUALS"] = 61] = "EQUALS";
Chars[Chars["GT"] = 62] = "GT";
Chars[Chars["QUESTION"] = 63] = "QUESTION";
Chars[Chars["UpperA"] = 65] = "UpperA";
Chars[Chars["UpperZ"] = 90] = "UpperZ";
Chars[Chars["LowerA"] = 97] = "LowerA";
Chars[Chars["LowerZ"] = 122] = "LowerZ";
})(Chars || (Chars = {}));
var SPACE_CHARACTERS = new Set([Chars.SPACE, Chars.LF, Chars.CR, Chars.TAB]);
var END_OF_UNQUOTED_ATTRIBUTE_VALUE = new Set([
Chars.SPACE,
Chars.LF,
Chars.CR,
Chars.TAB,
Chars.GT,
]);
function toUint8Array(str) {
var arr = new Uint8Array(str.length);
for (var i = 0; i < str.length; i++) {
arr[i] = str.charCodeAt(i);
}
return arr;
}
export var STRINGS = {
UTF8_BOM: new Uint8Array([0xef, 0xbb, 0xbf]),
UTF16LE_BOM: new Uint8Array([0xff, 0xfe]),
UTF16BE_BOM: new Uint8Array([0xfe, 0xff]),
UTF16LE_XML_PREFIX: new Uint8Array([0x3c, 0x0, 0x3f, 0x0, 0x78, 0x0]),
UTF16BE_XML_PREFIX: new Uint8Array([0x0, 0x3c, 0x0, 0x3f, 0x0, 0x78]),
XML_DECLARATION: toUint8Array("<?xml"),
ENCODING: toUint8Array("encoding"),
META: toUint8Array("meta"),
HTTP_EQUIV: toUint8Array("http-equiv"),
CONTENT: toUint8Array("content"),
CONTENT_TYPE: toUint8Array("content-type"),
CHARSET: toUint8Array("charset"),
COMMENT_START: toUint8Array("<!--"),
COMMENT_END: toUint8Array("-->"),
};
function isAsciiAlpha(c) {
return ((c >= Chars.UpperA && c <= Chars.UpperZ) ||
(c >= Chars.LowerA && c <= Chars.LowerZ));
}
function isQuote(c) {
return c === Chars.DQUOTE || c === Chars.SQUOTE;
}
var Sniffer = /** @class */ (function () {
function Sniffer(_a) {
var _b = _a === void 0 ? {} : _a, _c = _b.maxBytes, maxBytes = _c === void 0 ? 1024 : _c, userEncoding = _b.userEncoding, transportLayerEncodingLabel = _b.transportLayerEncodingLabel, defaultEncoding = _b.defaultEncoding;
/** The offset of the previous buffers. */
this.offset = 0;
this.state = State.Begin;
this.sectionIndex = 0;
this.attribType = AttribType.None;
/**
* Indicates if the `http-equiv` is `content-type`.
*
* Initially `null`, a boolean when a value is found.
*/
this.gotPragma = null;
this.needsPragma = null;
this.inMetaTag = false;
this.encoding = "windows-1252";
this.resultType = ResultType.DEFAULT;
this.quoteCharacter = 0;
this.attributeValue = [];
this.maxBytes = maxBytes;
if (userEncoding) {
this.setResult(userEncoding, ResultType.PASSED);
}
if (transportLayerEncodingLabel) {
this.setResult(transportLayerEncodingLabel, ResultType.PASSED);
}
if (defaultEncoding) {
this.setResult(defaultEncoding, ResultType.DEFAULT);
}
}
Sniffer.prototype.setResult = function (label, type) {
if (this.resultType === ResultType.DEFAULT || this.resultType > type) {
var encoding = labelToName(label);
if (encoding) {
this.encoding =
// Check if we are in a meta tag and the encoding is `x-user-defined`
type === ResultType.META_TAG &&
encoding === "x-user-defined"
? "windows-1252"
: // Check if we are in a meta tag or xml declaration, and the encoding is UTF-16
(type === ResultType.META_TAG ||
type === ResultType.XML_ENCODING) &&
(encoding === "UTF-16LE" || encoding === "UTF-16BE")
? "UTF-8"
: encoding;
this.resultType = type;
}
}
};
Sniffer.prototype.stateBegin = function (c) {
switch (c) {
case STRINGS.UTF16BE_BOM[0]: {
this.state = State.BOM16BE;
break;
}
case STRINGS.UTF16LE_BOM[0]: {
this.state = State.BOM16LE;
break;
}
case STRINGS.UTF8_BOM[0]: {
this.sectionIndex = 1;
this.state = State.BOM8;
break;
}
case Chars.NIL: {
this.state = State.UTF16BE_XML_PREFIX;
this.sectionIndex = 1;
break;
}
case Chars.LT: {
this.state = State.BeginLT;
break;
}
default: {
this.state = State.BeforeTag;
}
}
};
Sniffer.prototype.stateBeginLT = function (c) {
if (c === Chars.NIL) {
this.state = State.UTF16LE_XML_PREFIX;
this.sectionIndex = 2;
}
else if (c === Chars.QUESTION) {
this.state = State.XMLDeclaration;
this.sectionIndex = 2;
}
else {
this.state = State.BeforeTagName;
this.stateBeforeTagName(c);
}
};
Sniffer.prototype.stateUTF16BE_XML_PREFIX = function (c) {
// Advance position in the section
if (this.advanceSection(STRINGS.UTF16BE_XML_PREFIX, c)) {
if (this.sectionIndex === STRINGS.UTF16BE_XML_PREFIX.length) {
// We have the whole prefix
this.setResult("utf-16be", ResultType.XML_PREFIX);
}
}
else {
this.state = State.BeforeTag;
this.stateBeforeTag(c);
}
};
Sniffer.prototype.stateUTF16LE_XML_PREFIX = function (c) {
// Advance position in the section
if (this.advanceSection(STRINGS.UTF16LE_XML_PREFIX, c)) {
if (this.sectionIndex === STRINGS.UTF16LE_XML_PREFIX.length) {
// We have the whole prefix
this.setResult("utf-16le", ResultType.XML_PREFIX);
}
}
else {
this.state = State.BeforeTag;
this.stateBeforeTag(c);
}
};
Sniffer.prototype.stateBOM16LE = function (c) {
if (c === STRINGS.UTF16LE_BOM[1]) {
this.setResult("utf-16le", ResultType.BOM);
}
else {
this.state = State.BeforeTag;
this.stateBeforeTag(c);
}
};
Sniffer.prototype.stateBOM16BE = function (c) {
if (c === STRINGS.UTF16BE_BOM[1]) {
this.setResult("utf-16be", ResultType.BOM);
}
else {
this.state = State.BeforeTag;
this.stateBeforeTag(c);
}
};
Sniffer.prototype.stateBOM8 = function (c) {
if (this.advanceSection(STRINGS.UTF8_BOM, c) &&
this.sectionIndex === STRINGS.UTF8_BOM.length) {
this.setResult("utf-8", ResultType.BOM);
}
};
Sniffer.prototype.stateBeforeTag = function (c) {
if (c === Chars.LT) {
this.state = State.BeforeTagName;
this.inMetaTag = false;
}
};
/**
* We have seen a `<`, and now have to figure out what to do.
*
* Options:
* - `<meta`
* - Any other tag
* - A closing tag
* - `<!--`
* - An XML declaration
*
*/
Sniffer.prototype.stateBeforeTagName = function (c) {
if (isAsciiAlpha(c)) {
if ((c | 0x20) === STRINGS.META[0]) {
this.sectionIndex = 1;
this.state = State.TagNameMeta;
}
else {
this.state = State.TagNameOther;
}
}
else
switch (c) {
case Chars.SLASH: {
this.state = State.BeforeCloseTagName;
break;
}
case Chars.EXCLAMATION: {
this.state = State.CommentStart;
this.sectionIndex = 2;
break;
}
case Chars.QUESTION: {
this.state = State.WeirdTag;
break;
}
default: {
this.state = State.BeforeTag;
this.stateBeforeTag(c);
}
}
};
Sniffer.prototype.stateBeforeCloseTagName = function (c) {
this.state = isAsciiAlpha(c)
? // Switch to `TagNameOther`; the HTML spec allows attributes here as well.
State.TagNameOther
: State.WeirdTag;
};
Sniffer.prototype.stateCommentStart = function (c) {
if (this.advanceSection(STRINGS.COMMENT_START, c)) {
if (this.sectionIndex === STRINGS.COMMENT_START.length) {
this.state = State.CommentEnd;
// The -- of the comment start can be part of the end.
this.sectionIndex = 2;
}
}
else {
this.state = State.WeirdTag;
this.stateWeirdTag(c);
}
};
Sniffer.prototype.stateCommentEnd = function (c) {
if (this.advanceSection(STRINGS.COMMENT_END, c)) {
if (this.sectionIndex === STRINGS.COMMENT_END.length) {
this.state = State.BeforeTag;
}
}
else if (c === Chars.DASH) {
/*
* If we are here, we know we expected a `>` above.
* Set this to 2, to support many dashes before the closing `>`.
*/
this.sectionIndex = 2;
}
};
/**
* Any section starting with `<!`, `<?`, `</`, without being a closing tag or comment.
*/
Sniffer.prototype.stateWeirdTag = function (c) {
if (c === Chars.GT) {
this.state = State.BeforeTag;
}
};
/**
* Advances the section, ignoring upper/lower case.
*
* Make sure the section has left-over characters before calling.
*
* @returns `false` if we did not match the section.
*/
Sniffer.prototype.advanceSectionIC = function (section, c) {
return this.advanceSection(section, c | 0x20);
};
/**
* Advances the section.
*
* Make sure the section has left-over characters before calling.
*
* @returns `false` if we did not match the section.
*/
Sniffer.prototype.advanceSection = function (section, c) {
if (section[this.sectionIndex] === c) {
this.sectionIndex++;
return true;
}
this.sectionIndex = 0;
return false;
};
Sniffer.prototype.stateTagNameMeta = function (c) {
if (this.sectionIndex < STRINGS.META.length) {
if (this.advanceSectionIC(STRINGS.META, c)) {
return;
}
}
else if (SPACE_CHARACTERS.has(c)) {
this.inMetaTag = true;
this.gotPragma = null;
this.needsPragma = null;
this.state = State.BeforeAttribute;
return;
}
this.state = State.TagNameOther;
// Reconsume in case there is a `>`.
this.stateTagNameOther(c);
};
Sniffer.prototype.stateTagNameOther = function (c) {
if (SPACE_CHARACTERS.has(c)) {
this.state = State.BeforeAttribute;
}
else if (c === Chars.GT) {
this.state = State.BeforeTag;
}
};
Sniffer.prototype.stateBeforeAttribute = function (c) {
if (SPACE_CHARACTERS.has(c))
return;
if (this.inMetaTag) {
var lower = c | 0x20;
if (lower === STRINGS.HTTP_EQUIV[0]) {
this.sectionIndex = 1;
this.state = State.MetaAttribHttpEquiv;
return;
}
else if (lower === STRINGS.CHARSET[0]) {
this.sectionIndex = 1;
this.state = State.MetaAttribC;
return;
}
}
this.state =
c === Chars.SLASH || c === Chars.GT
? State.BeforeTag
: State.AnyAttribName;
};
Sniffer.prototype.handleMetaAttrib = function (c, section, type) {
if (this.advanceSectionIC(section, c)) {
if (this.sectionIndex === section.length) {
this.attribType = type;
this.state = State.MetaAttribAfterName;
}
}
else {
this.state = State.AnyAttribName;
this.stateAnyAttribName(c);
}
};
Sniffer.prototype.stateMetaAttribHttpEquiv = function (c) {
this.handleMetaAttrib(c, STRINGS.HTTP_EQUIV, AttribType.HttpEquiv);
};
Sniffer.prototype.stateMetaAttribC = function (c) {
var lower = c | 0x20;
if (lower === STRINGS.CHARSET[1]) {
this.sectionIndex = 2;
this.state = State.MetaAttribCharset;
}
else if (lower === STRINGS.CONTENT[1]) {
this.sectionIndex = 2;
this.state = State.MetaAttribContent;
}
else {
this.state = State.AnyAttribName;
this.stateAnyAttribName(c);
}
};
Sniffer.prototype.stateMetaAttribCharset = function (c) {
this.handleMetaAttrib(c, STRINGS.CHARSET, AttribType.Charset);
};
Sniffer.prototype.stateMetaAttribContent = function (c) {
this.handleMetaAttrib(c, STRINGS.CONTENT, AttribType.Content);
};
Sniffer.prototype.stateMetaAttribAfterName = function (c) {
if (SPACE_CHARACTERS.has(c) || c === Chars.EQUALS) {
this.state = State.AfterAttributeName;
this.stateAfterAttributeName(c);
}
else {
this.state = State.AnyAttribName;
this.stateAnyAttribName(c);
}
};
Sniffer.prototype.stateAnyAttribName = function (c) {
if (SPACE_CHARACTERS.has(c)) {
this.attribType = AttribType.None;
this.state = State.AfterAttributeName;
}
else if (c === Chars.SLASH || c === Chars.GT) {
this.state = State.BeforeTag;
}
else if (c === Chars.EQUALS) {
this.state = State.BeforeAttributeValue;
}
};
Sniffer.prototype.stateAfterAttributeName = function (c) {
if (SPACE_CHARACTERS.has(c))
return;
if (c === Chars.EQUALS) {
this.state = State.BeforeAttributeValue;
}
else {
this.state = State.BeforeAttribute;
this.stateBeforeAttribute(c);
}
};
Sniffer.prototype.stateBeforeAttributeValue = function (c) {
if (SPACE_CHARACTERS.has(c))
return;
this.attributeValue.length = 0;
this.sectionIndex = 0;
if (isQuote(c)) {
this.quoteCharacter = c;
this.state =
this.attribType === AttribType.Content
? State.MetaContentValueQuotedBeforeEncoding
: this.attribType === AttribType.HttpEquiv
? State.MetaAttribHttpEquivValue
: State.AttributeValueQuoted;
}
else if (this.attribType === AttribType.Content) {
this.state = State.MetaContentValueUnquotedBeforeEncoding;
this.stateMetaContentValueUnquotedBeforeEncoding(c);
}
else if (this.attribType === AttribType.HttpEquiv) {
// We use `quoteCharacter = 0` to signify that the value is unquoted.
this.quoteCharacter = 0;
this.sectionIndex = 0;
this.state = State.MetaAttribHttpEquivValue;
this.stateMetaAttribHttpEquivValue(c);
}
else {
this.state = State.AttributeValueUnquoted;
this.stateAttributeValueUnquoted(c);
}
};
// The value has to be `content-type`
Sniffer.prototype.stateMetaAttribHttpEquivValue = function (c) {
if (this.sectionIndex === STRINGS.CONTENT_TYPE.length) {
if (this.quoteCharacter === 0
? END_OF_UNQUOTED_ATTRIBUTE_VALUE.has(c)
: c === this.quoteCharacter) {
if (this.needsPragma !== null) {
this.setResult(this.needsPragma, ResultType.META_TAG);
}
else if (this.gotPragma === null) {
this.gotPragma = true;
}
this.state = State.BeforeAttribute;
return;
}
}
else if (this.advanceSectionIC(STRINGS.CONTENT_TYPE, c)) {
return;
}
this.gotPragma = false;
if (this.quoteCharacter === 0) {
this.state = State.AttributeValueUnquoted;
this.stateAttributeValueUnquoted(c);
}
else {
this.state = State.AttributeValueQuoted;
this.stateAttributeValueQuoted(c);
}
};
Sniffer.prototype.handleMetaContentValue = function () {
if (this.attributeValue.length === 0)
return;
var encoding = String.fromCharCode.apply(String, this.attributeValue);
if (this.gotPragma) {
this.setResult(encoding, ResultType.META_TAG);
}
else if (this.needsPragma === null) {
// Don't override a previous result.
this.needsPragma = encoding;
}
this.attributeValue.length = 0;
};
Sniffer.prototype.handleAttributeValue = function () {
if (this.attribType === AttribType.Charset) {
this.setResult(String.fromCharCode.apply(String, this.attributeValue), ResultType.META_TAG);
}
};
Sniffer.prototype.stateAttributeValueUnquoted = function (c) {
if (SPACE_CHARACTERS.has(c)) {
this.handleAttributeValue();
this.state = State.BeforeAttribute;
}
else if (c === Chars.SLASH || c === Chars.GT) {
this.handleAttributeValue();
this.state = State.BeforeTag;
}
else if (this.attribType === AttribType.Charset) {
this.attributeValue.push(c | 0x20);
}
};
Sniffer.prototype.findMetaContentEncoding = function (c) {
if (this.advanceSectionIC(STRINGS.CHARSET, c)) {
if (this.sectionIndex === STRINGS.CHARSET.length) {
return true;
}
}
else {
// If we encountered another `c`, assume we started over.
this.sectionIndex = Number(c === STRINGS.CHARSET[0]);
}
return false;
};
Sniffer.prototype.stateMetaContentValueUnquotedBeforeEncoding = function (c) {
if (END_OF_UNQUOTED_ATTRIBUTE_VALUE.has(c)) {
this.stateAttributeValueUnquoted(c);
}
else if (this.sectionIndex === STRINGS.CHARSET.length) {
if (c === Chars.EQUALS) {
this.state = State.MetaContentValueUnquotedBeforeValue;
}
}
else {
this.findMetaContentEncoding(c);
}
};
Sniffer.prototype.stateMetaContentValueUnquotedBeforeValue = function (c) {
if (isQuote(c)) {
this.quoteCharacter = c;
this.state = State.MetaContentValueUnquotedValueQuoted;
}
else if (END_OF_UNQUOTED_ATTRIBUTE_VALUE.has(c)) {
// Can't have spaces here, as it would no longer be part of the attribute value.
this.stateAttributeValueUnquoted(c);
}
else {
this.state = State.MetaContentValueUnquotedValueUnquoted;
this.stateMetaContentValueUnquotedValueUnquoted(c);
}
};
Sniffer.prototype.stateMetaContentValueUnquotedValueQuoted = function (c) {
if (END_OF_UNQUOTED_ATTRIBUTE_VALUE.has(c)) {
// Quotes weren't matched, so we're done.
this.stateAttributeValueUnquoted(c);
}
else if (c === this.quoteCharacter) {
this.handleMetaContentValue();
this.state = State.AttributeValueUnquoted;
}
else {
this.attributeValue.push(c | 0x20);
}
};
Sniffer.prototype.stateMetaContentValueUnquotedValueUnquoted = function (c) {
if (END_OF_UNQUOTED_ATTRIBUTE_VALUE.has(c) || c === Chars.SEMICOLON) {
this.handleMetaContentValue();
this.state = State.AttributeValueUnquoted;
this.stateAttributeValueUnquoted(c);
}
else {
this.attributeValue.push(c | 0x20);
}
};
Sniffer.prototype.stateMetaContentValueQuotedValueUnquoted = function (c) {
if (isQuote(c) || SPACE_CHARACTERS.has(c) || c === Chars.SEMICOLON) {
this.handleMetaContentValue();
// We are done with the value, but might not be at the end of the attribute
this.state = State.AttributeValueQuoted;
this.stateAttributeValueQuoted(c);
}
else {
this.attributeValue.push(c | 0x20);
}
};
Sniffer.prototype.stateMetaContentValueQuotedValueQuoted = function (c) {
if (isQuote(c)) {
// We have reached the end of our value.
if (c !== this.quoteCharacter) {
// Only handle the value if inner quotes were matched.
this.handleMetaContentValue();
}
this.state = State.AttributeValueQuoted;
this.stateAttributeValueQuoted(c);
}
else {
this.attributeValue.push(c | 0x20);
}
};
Sniffer.prototype.stateMetaContentValueQuotedBeforeEncoding = function (c) {
if (c === this.quoteCharacter) {
this.stateAttributeValueQuoted(c);
}
else if (this.findMetaContentEncoding(c)) {
this.state = State.MetaContentValueQuotedAfterEncoding;
}
};
Sniffer.prototype.stateMetaContentValueQuotedAfterEncoding = function (c) {
if (c === Chars.EQUALS) {
this.state = State.MetaContentValueQuotedBeforeValue;
}
else if (!SPACE_CHARACTERS.has(c)) {
// Look for the next encoding
this.state = State.MetaContentValueQuotedBeforeEncoding;
this.stateMetaContentValueQuotedBeforeEncoding(c);
}
};
Sniffer.prototype.stateMetaContentValueQuotedBeforeValue = function (c) {
if (c === this.quoteCharacter) {
this.stateAttributeValueQuoted(c);
}
else if (isQuote(c)) {
this.state = State.MetaContentValueQuotedValueQuoted;
}
else if (!SPACE_CHARACTERS.has(c)) {
this.state = State.MetaContentValueQuotedValueUnquoted;
this.stateMetaContentValueQuotedValueUnquoted(c);
}
};
Sniffer.prototype.stateAttributeValueQuoted = function (c) {
if (c === this.quoteCharacter) {
this.handleAttributeValue();
this.state = State.BeforeAttribute;
}
else if (this.attribType === AttribType.Charset) {
this.attributeValue.push(c | 0x20);
}
};
// Read STRINGS.XML_DECLARATION
Sniffer.prototype.stateXMLDeclaration = function (c) {
if (this.advanceSection(STRINGS.XML_DECLARATION, c)) {
if (this.sectionIndex === STRINGS.XML_DECLARATION.length) {
this.sectionIndex = 0;
this.state = State.XMLDeclarationBeforeEncoding;
}
}
else {
this.state = State.WeirdTag;
}
};
Sniffer.prototype.stateXMLDeclarationBeforeEncoding = function (c) {
if (this.advanceSection(STRINGS.ENCODING, c)) {
if (this.sectionIndex === STRINGS.ENCODING.length) {
this.state = State.XMLDeclarationAfterEncoding;
}
}
else if (c === Chars.GT) {
this.state = State.BeforeTag;
}
else {
// If we encountered another `c`, assume we started over.
this.sectionIndex = Number(c === STRINGS.ENCODING[0]);
}
};
Sniffer.prototype.stateXMLDeclarationAfterEncoding = function (c) {
if (c === Chars.EQUALS) {
this.state = State.XMLDeclarationBeforeValue;
}
else if (c > Chars.SPACE) {
this.state = State.WeirdTag;
this.stateWeirdTag(c);
}
};
Sniffer.prototype.stateXMLDeclarationBeforeValue = function (c) {
if (isQuote(c)) {
this.attributeValue.length = 0;
this.state = State.XMLDeclarationValue;
}
else if (c > Chars.SPACE) {
this.state = State.WeirdTag;
this.stateWeirdTag(c);
}
};
Sniffer.prototype.stateXMLDeclarationValue = function (c) {
if (isQuote(c)) {
this.setResult(String.fromCharCode.apply(String, this.attributeValue), ResultType.XML_ENCODING);
this.state = State.WeirdTag;
}
else if (c === Chars.GT) {
this.state = State.BeforeTag;
}
else if (c <= Chars.SPACE) {
this.state = State.WeirdTag;
}
else {
this.attributeValue.push(c | 0x20);
}
};
Sniffer.prototype.write = function (buffer) {
var index = 0;
for (; index < buffer.length && this.offset + index < this.maxBytes; index++) {
var c = buffer[index];
switch (this.state) {
case State.Begin: {
this.stateBegin(c);
break;
}
case State.BOM16BE: {
this.stateBOM16BE(c);
break;
}
case State.BOM16LE: {
this.stateBOM16LE(c);
break;
}
case State.BOM8: {
this.stateBOM8(c);
break;
}
case State.UTF16LE_XML_PREFIX: {
this.stateUTF16LE_XML_PREFIX(c);
break;
}
case State.BeginLT: {
this.stateBeginLT(c);
break;
}
case State.UTF16BE_XML_PREFIX: {
this.stateUTF16BE_XML_PREFIX(c);
break;
}
case State.BeforeTag: {
// Optimization: Skip all characters until we find a `<`
var idx = buffer.indexOf(Chars.LT, index);
if (idx < 0) {
// We are done with this buffer. Stay in the state and try on the next one.
index = buffer.length;
}
else {
index = idx;
this.stateBeforeTag(Chars.LT);
}
break;
}
case State.BeforeTagName: {
this.stateBeforeTagName(c);
break;
}
case State.BeforeCloseTagName: {
this.stateBeforeCloseTagName(c);
break;
}
case State.CommentStart: {
this.stateCommentStart(c);
break;
}
case State.CommentEnd: {
this.stateCommentEnd(c);
break;
}
case State.TagNameMeta: {
this.stateTagNameMeta(c);
break;
}
case State.TagNameOther: {
this.stateTagNameOther(c);
break;
}
case State.XMLDeclaration: {
this.stateXMLDeclaration(c);
break;
}
case State.XMLDeclarationBeforeEncoding: {
this.stateXMLDeclarationBeforeEncoding(c);
break;
}
case State.XMLDeclarationAfterEncoding: {
this.stateXMLDeclarationAfterEncoding(c);
break;
}
case State.XMLDeclarationBeforeValue: {
this.stateXMLDeclarationBeforeValue(c);
break;
}
case State.XMLDeclarationValue: {
this.stateXMLDeclarationValue(c);
break;
}
case State.WeirdTag: {
this.stateWeirdTag(c);
break;
}
case State.BeforeAttribute: {
this.stateBeforeAttribute(c);
break;
}
case State.MetaAttribHttpEquiv: {
this.stateMetaAttribHttpEquiv(c);
break;
}
case State.MetaAttribHttpEquivValue: {
this.stateMetaAttribHttpEquivValue(c);
break;
}
case State.MetaAttribC: {
this.stateMetaAttribC(c);
break;
}
case State.MetaAttribContent: {
this.stateMetaAttribContent(c);
break;
}
case State.MetaAttribCharset: {
this.stateMetaAttribCharset(c);
break;
}
case State.MetaAttribAfterName: {
this.stateMetaAttribAfterName(c);
break;
}
case State.MetaContentValueQuotedBeforeEncoding: {
this.stateMetaContentValueQuotedBeforeEncoding(c);
break;
}
case State.MetaContentValueQuotedAfterEncoding: {
this.stateMetaContentValueQuotedAfterEncoding(c);
break;
}
case State.MetaContentValueQuotedBeforeValue: {
this.stateMetaContentValueQuotedBeforeValue(c);
break;
}
case State.MetaContentValueQuotedValueQuoted: {
this.stateMetaContentValueQuotedValueQuoted(c);
break;
}
case State.MetaContentValueQuotedValueUnquoted: {
this.stateMetaContentValueQuotedValueUnquoted(c);
break;
}
case State.MetaContentValueUnquotedBeforeEncoding: {
this.stateMetaContentValueUnquotedBeforeEncoding(c);
break;
}
case State.MetaContentValueUnquotedBeforeValue: {
this.stateMetaContentValueUnquotedBeforeValue(c);
break;
}
case State.MetaContentValueUnquotedValueQuoted: {
this.stateMetaContentValueUnquotedValueQuoted(c);
break;
}
case State.MetaContentValueUnquotedValueUnquoted: {
this.stateMetaContentValueUnquotedValueUnquoted(c);
break;
}
case State.AnyAttribName: {
this.stateAnyAttribName(c);
break;
}
case State.AfterAttributeName: {
this.stateAfterAttributeName(c);
break;
}
case State.BeforeAttributeValue: {
this.stateBeforeAttributeValue(c);
break;
}
case State.AttributeValueQuoted: {
this.stateAttributeValueQuoted(c);
break;
}
default: {
// (State.AttributeValueUnquoted)
this.stateAttributeValueUnquoted(c);
}
}
}
this.offset += index;
};
return Sniffer;
}());
export { Sniffer };
/** Get the encoding for the passed buffer. */
export function getEncoding(buffer, options) {
var sniffer = new Sniffer(options);
sniffer.write(buffer);
return sniffer.encoding;
}
//# sourceMappingURL=sniffer.js.map

1
book/node_modules/encoding-sniffer/dist/esm/sniffer.js.map generated vendored Normal file
View File

File diff suppressed because one or more lines are too long