xml-tokenizer 0.0.25 → 0.0.27

package/dist/esm/tokenizer/XmlStream.js

@@ -1,445 +1 @@
-import { AMPERSAND, HASH, LOWERCASE_X, ZERO, NINE, UPPERCASE_A, UPPERCASE_F, LOWERCASE_A, LOWERCASE_F, SEMICOLON, COLON, SINGLE_QUOTE, DOUBLE_QUOTE, LINE_FEED } from './ascii-constants.js';
-import { isXmlChar, isXmlSpaceByte, isAsciiDigit, isXmlNameStart, isXmlName } from './utils.js';
-import { XmlError } from './XmlError.js';
-
-var __defProp = Object.defineProperty;
-var __getOwnPropSymbols = Object.getOwnPropertySymbols;
-var __hasOwnProp = Object.prototype.hasOwnProperty;
-var __propIsEnum = Object.prototype.propertyIsEnumerable;
-var __defNormalProp = (obj, key, value) => key in obj ? __defProp(obj, key, { enumerable: true, configurable: true, writable: true, value }) : obj[key] = value;
-var __spreadValues = (a, b) => {
-  for (var prop in b || (b = {}))
-    if (__hasOwnProp.call(b, prop))
-      __defNormalProp(a, prop, b[prop]);
-  if (__getOwnPropSymbols)
-    for (var prop of __getOwnPropSymbols(b)) {
-      if (__propIsEnum.call(b, prop))
-        __defNormalProp(a, prop, b[prop]);
-    }
-  return a;
-};
-var __publicField = (obj, key, value) => __defNormalProp(obj, typeof key !== "symbol" ? key + "" : key, value);
-class XmlStream {
-  constructor(text, options = {}) {
-    __publicField(this, "_text");
-    __publicField(this, "_pos");
-    __publicField(this, "_end");
-    __publicField(this, "config");
-    const { pos = 0, strictDocument = true, allowDtd = true, rawTextElements = null } = options;
-    this._text = text;
-    this._pos = pos;
-    this._end = this._text.length;
-    this.config = {
-      strictDocument,
-      allowDtd,
-      rawTextElements
-    };
-  }
-  /**
-   * Creates a clone of the current stream.
-   *
-   * @returns A new instance of XmlStream with the same state.
-   */
-  clone() {
-    return new XmlStream(this._text, __spreadValues({ pos: this._pos }, this.config));
-  }
-  /**
-   * Gets the current position in the stream.
-   *
-   * @returns The current position.
-   */
-  getPos() {
-    return this._pos;
-  }
-  /**
-   * Checks if the stream is at the end.
-   *
-   * @returns True if at the end, false otherwise.
-   */
-  atEnd() {
-    return this._pos >= this._end;
-  }
-  /**
-   * Gets the current code unit in the stream.
-   *
-   * @returns The current code unit.
-   * @throws XmlError if at the end of the stream.
-   */
-  currCodeUnit() {
-    if (this._pos >= this._end) {
-      throw new XmlError({ type: "UnexpectedEndOfStream" });
-    }
-    return this._text.charCodeAt(this._pos);
-  }
-  /**
-   * Gets the current code unit without checking for the end.
-   *
-   * @returns The current code unit.
-   */
-  currCodeUnitUnchecked() {
-    return this._text.charCodeAt(this._pos);
-  }
-  /**
-   * Gets the next code unit in the stream.
-   *
-   * @returns The next code unit.
-   * @throws XmlError if at the end of the stream.
-   */
-  nextCodeUnit() {
-    if (this._pos + 1 >= this._end) {
-      throw new XmlError({ type: "UnexpectedEndOfStream" });
-    }
-    return this._text.charCodeAt(this._pos + 1);
-  }
-  /**
-   * Consumes a specific code unit (character) from the stream.
-   *
-   * @param codeUnit - The code unit to consume.
-   * @throws XmlError if the current code unit doesn't match or if at the end.
-   */
-  consumeCodeUnit(codeUnit) {
-    const currCodeUnit = this.currCodeUnit();
-    if (currCodeUnit !== codeUnit) {
-      throw new XmlError(
-        { type: "InvalidChar", expected: codeUnit, actual: currCodeUnit },
-        this.genTextPos()
-      );
-    }
-    this._pos += 1;
-  }
-  /**
-   * Tries to consume a specific code unit (character) from the stream.
-   * Unlike `consumeCodeUnit`, it will not throw any errors.
-   *
-   * @param codeUnit - The code unit to consume.
-   * @returns True if the code unit was consumed, false otherwise.
-   */
-  tryConsumeCodeUnit(codeUnit) {
-    if (this.currCodeUnit() === codeUnit) {
-      this._pos += 1;
-      return true;
-    }
-    return false;
-  }
-  /**
-   * Consumes code units that satisfy a predicate function.
-   *
-   * @param predicate - The function to test each code unit.
-   * @returns The consumed string.
-   */
-  consumeCodeUnitsWhile(predicate) {
-    const start = this._pos;
-    this.skipCodeUnitsWhile(predicate);
-    return this.sliceBack(start);
-  }
-  /**
-   * Skips code units that satisfy a predicate function.
-   *
-   * @param predicate - The function to test each code unit.
-   */
-  skipCodeUnitsWhile(predicate) {
-    while (this._pos < this._end && predicate(this.currCodeUnitUnchecked(), this)) {
-      if (!isXmlChar(this.currCodeUnitUnchecked())) {
-        throw new XmlError(
-          {
-            type: "NonXmlChar",
-            char: String.fromCodePoint(this.currCodeUnitUnchecked())
-          },
-          this.genTextPos()
-        );
-      }
-      this._pos += 1;
-    }
-  }
-  /**
-   * Advances the stream position by the specified number of characters.
-   *
-   * @param n - The number of characters to advance.
-   */
-  advance(n) {
-    this._pos += n;
-  }
-  /**
-   * Go to a new position in the stream.
-   *
-   *  @param pos - The new position.
-   */
-  goTo(pos) {
-    this._pos = pos;
-  }
-  /**
-   * Checks if the stream starts with the given text.
-   *
-   * @param text - The text to check.
-   * @returns True if the stream starts with the text, false otherwise.
-   */
-  startsWith(text) {
-    return this._text.startsWith(text, this._pos);
-  }
-  /**
-   * Skips a specific string in the stream.
-   *
-   * @param text - The string to skip.
-   * @throws XmlError if the stream doesn't start with the given string.
-   */
-  skipString(text) {
-    if (!this.startsWith(text)) {
-      throw new XmlError({ type: "InvalidString", expected: text }, this.genTextPos());
-    }
-    this._pos += text.length;
-  }
-  /**
-   * Slices the text from the given position to the current position.
-   *
-   * @param pos - The start position.
-   * @returns The sliced string.
-   */
-  sliceBack(pos) {
-    return this._text.slice(pos, this._pos);
-  }
-  /**
-   * Creates a range from the given start position to the current position.
-   *
-   * @param start - The start position.
-   * @returns The range object.
-   */
-  rangeFrom(start) {
-    return { start, end: this._pos };
-  }
-  /**
-   * Skips whitespace characters in the stream.
-   */
-  skipSpaces() {
-    while (this.startsWithSpace()) {
-      this._pos += 1;
-    }
-  }
-  /**
-   * Checks if the stream starts with a whitespace character.
-   *
-   * @returns True if it starts with a whitespace, false otherwise.
-   */
-  startsWithSpace() {
-    return this._pos < this._end && isXmlSpaceByte(this.currCodeUnitUnchecked());
-  }
-  /**
-   * Consumes whitespace characters in the stream.
-   * Like `skipSpaces`, but checks that the first char is actually a space.
-   *
-   * @throws XmlError if the stream doesn't start with a whitespace or is at the end.
-   */
-  consumeSpaces() {
-    if (this._pos >= this._end) {
-      throw new XmlError({ type: "UnexpectedEndOfStream" }, this.genTextPos());
-    }
-    if (!this.startsWithSpace()) {
-      throw new XmlError(
-        { type: "InvalidChar", expected: "a whitespace", actual: this.currCodeUnitUnchecked() },
-        this.genTextPos()
-      );
-    }
-    this.skipSpaces();
-  }
-  /**
-   * Tries to consume a reference (entity or character reference).
-   * Consumes according to: https://www.w3.org/TR/xml/#NT-Reference
-   *
-   * @returns The consumed reference or null if not a reference.
-   */
-  tryConsumeReference() {
-    const start = this._pos;
-    const subStream = this.clone();
-    const result = subStream.consumeReference();
-    if (result != null) {
-      this._pos += subStream.getPos() - start;
-      return result;
-    }
-    return null;
-  }
-  /**
-   * Consumes a reference (entity or character reference).
-   *
-   * @returns The consumed reference or null if not a reference.
-   */
-  consumeReference() {
-    if (!this.tryConsumeCodeUnit(AMPERSAND)) {
-      return null;
-    }
-    let reference;
-    if (this.tryConsumeCodeUnit(HASH)) {
-      let value;
-      let radix;
-      if (this.tryConsumeCodeUnit(LOWERCASE_X)) {
-        value = this.consumeCodeUnitsWhile(
-          (codeUnit) => codeUnit >= ZERO && codeUnit <= NINE || codeUnit >= UPPERCASE_A && codeUnit <= UPPERCASE_F || codeUnit >= LOWERCASE_A && codeUnit <= LOWERCASE_F
-        );
-        radix = 16;
-      } else {
-        value = this.consumeCodeUnitsWhile((codeUnit) => isAsciiDigit(codeUnit));
-        radix = 10;
-      }
-      const codePoint = parseInt(value, radix);
-      if (isNaN(codePoint) || !isXmlChar(codePoint)) {
-        reference = null;
-      } else {
-        reference = { type: "Char", value: String.fromCodePoint(codePoint) };
-      }
-    } else {
-      const name = this.consumeName();
-      switch (name) {
-        case "quot":
-          reference = { type: "Char", value: '"' };
-          break;
-        case "amp":
-          reference = { type: "Char", value: "&" };
-          break;
-        case "apos":
-          reference = { type: "Char", value: "'" };
-          break;
-        case "lt":
-          reference = { type: "Char", value: "<" };
-          break;
-        case "gt":
-          reference = { type: "Char", value: ">" };
-          break;
-        default:
-          reference = { type: "Entity", value: name };
-      }
-    }
-    if (!this.tryConsumeCodeUnit(SEMICOLON)) {
-      return null;
-    }
-    return reference;
-  }
-  /**
-   * Consumes a XML name.
-   * Consumes according to: https://www.w3.org/TR/xml/#NT-Name
-   *
-   * @returns The consumed name.
-   * @throws XmlError if an invalid name is encountered.
-   */
-  consumeName() {
-    const start = this._pos;
-    this.skipName();
-    const name = this.sliceBack(start);
-    if (name.length === 0) {
-      throw new XmlError({ type: "InvalidName" }, this.genTextPosFrom(start));
-    }
-    return name;
-  }
-  /**
-   * Skips a XML name.
-   * The same as `consumeName`, but does not return the consumed name.
-   * @throws XmlError if an invalid name is encountered.
-   */
-  skipName() {
-    const start = this._pos;
-    while (this._pos < this._end) {
-      const currCodeUnit = this.currCodeUnitUnchecked();
-      if (this._pos === start) {
-        if (!isXmlNameStart(currCodeUnit)) {
-          throw new XmlError({ type: "InvalidName" }, this.genTextPosFrom(start));
-        }
-      } else if (!isXmlName(currCodeUnit)) {
-        break;
-      }
-      this._pos += 1;
-    }
-  }
-  /**
-   * Consumes a qualified XML name and returns it.
-   * Consumes according to: https://www.w3.org/TR/xml-names/#ns-qualnames
-   *
-   * @returns The prefix and local name as a tuple.
-   * @throws XmlError if an invalid qualified XML name is encountered.
-   */
-  consumeQName() {
-    var _a, _b;
-    const start = this._pos;
-    let splitter = null;
-    while (this._pos < this._end) {
-      const currCodeUnit = this.currCodeUnitUnchecked();
-      if (currCodeUnit === COLON) {
-        if (splitter == null) {
-          splitter = this._pos;
-          this._pos += 1;
-        } else {
-          throw new XmlError({ type: "InvalidName" }, this.genTextPosFrom(start));
-        }
-      } else if (isXmlName(currCodeUnit)) {
-        this._pos += 1;
-      } else {
-        break;
-      }
-    }
-    let prefix;
-    let local;
-    if (splitter != null) {
-      prefix = this._text.slice(start, splitter);
-      local = this.sliceBack(splitter + 1);
-    } else {
-      prefix = "";
-      local = this.sliceBack(start);
-    }
-    if (prefix.length > 0 && !isXmlNameStart((_a = prefix[0]) == null ? void 0 : _a.codePointAt(0))) {
-      throw new XmlError({ type: "InvalidName" }, this.genTextPosFrom(start));
-    }
-    if (local.length > 0) {
-      if (!isXmlNameStart((_b = local[0]) == null ? void 0 : _b.codePointAt(0))) {
-        throw new XmlError({ type: "InvalidName" }, this.genTextPosFrom(start));
-      }
-    } else {
-      throw new XmlError({ type: "InvalidName" }, this.genTextPosFrom(start));
-    }
-    return [prefix, local];
-  }
-  /**
-   * Consumes a quote character.
-   *
-   * @returns The consumed quote character.
-   * @throws XmlError if an invalid quote character is encountered.
-   */
-  consumeQuote() {
-    const currCodeUnit = this.currCodeUnit();
-    if (currCodeUnit === SINGLE_QUOTE || currCodeUnit === DOUBLE_QUOTE) {
-      this._pos += 1;
-      return currCodeUnit;
-    }
-    throw new XmlError(
-      { type: "InvalidChar", expected: "a quote", actual: currCodeUnit },
-      this.genTextPos()
-    );
-  }
-  /**
-   * Calculates the current absolute position.
-   * This operation is very expensive. Use only for errors.
-   *
-   * @returns The current text position.
-   */
-  genTextPos() {
-    return this.genTextPosFrom(this._pos);
-  }
-  /**
-   * Calculates an absolute position at the specified position.
-   * This operation is very expensive. Use only for errors.
-   *
-   * @param pos - The position to calculate from.
-   * @returns The calculated text position.
-   */
-  genTextPosFrom(pos) {
-    const clampedPos = Math.min(pos, this._end);
-    let row = 1;
-    let col = 1;
-    for (let i = 0; i < clampedPos; i++) {
-      if (this._text.charCodeAt(i) === LINE_FEED) {
-        row++;
-        col = 1;
-      } else {
-        col++;
-      }
-    }
-    return { row, col };
-  }
-}
-
-export { XmlStream };
+import{AMPERSAND as f,HASH as x,LOWERCASE_X as g,ZERO as U,NINE as w,UPPERCASE_A as y,UPPERCASE_F as S,LOWERCASE_A as E,LOWERCASE_F as v,SEMICOLON as P,COLON as k,SINGLE_QUOTE as N,DOUBLE_QUOTE as T,LINE_FEED as O}from"./ascii-constants.js";import{isXmlChar as d,isXmlSpaceByte as A,isAsciiDigit as b,isXmlNameStart as l,isXmlName as _}from"./utils.js";import{XmlError as o}from"./XmlError.js";var I=Object.defineProperty,m=Object.getOwnPropertySymbols,W=Object.prototype.hasOwnProperty,F=Object.prototype.propertyIsEnumerable,p=(r,t,e)=>t in r?I(r,t,{enumerable:!0,configurable:!0,writable:!0,value:e}):r[t]=e,C=(r,t)=>{for(var e in t||(t={}))W.call(t,e)&&p(r,e,t[e]);if(m)for(var e of m(t))F.call(t,e)&&p(r,e,t[e]);return r},a=(r,t,e)=>p(r,typeof t!="symbol"?t+"":t,e);class u{constructor(t,e={}){a(this,"_text"),a(this,"_pos"),a(this,"_end"),a(this,"config");const{pos:i=0,strictDocument:n=!0,allowDtd:s=!0,rawTextElements:h=null,contextSliceSize:c=30}=e;this._text=t,this._pos=i,this._end=this._text.length,this.config={strictDocument:n,allowDtd:s,rawTextElements:h,contextSliceSize:c}}clone(){return new u(this._text,C({pos:this._pos},this.config))}getPos(){return this._pos}atEnd(){return this._pos>=this._end}currCodeUnit(){if(this._pos>=this._end)throw new o({type:"UnexpectedEndOfStream"});return this._text.charCodeAt(this._pos)}currCodeUnitUnchecked(){return this._text.charCodeAt(this._pos)}nextCodeUnit(){if(this._pos+1>=this._end)throw new o({type:"UnexpectedEndOfStream"});return this._text.charCodeAt(this._pos+1)}consumeCodeUnit(t){const e=this.currCodeUnit();if(e!==t)throw new o({type:"InvalidChar",expected:t,actual:e},this.genTextPos());this._pos+=1}tryConsumeCodeUnit(t){return this.currCodeUnit()===t?(this._pos+=1,!0):!1}consumeCodeUnitsWhile(t){const e=this._pos;return this.skipCodeUnitsWhile(t),this.sliceBack(e)}skipCodeUnitsWhile(t){for(;this._pos<this._end&&t(this.currCodeUnitUnchecked(),this);){if(!d(this.currCodeUnitUnchecked()))throw new o({type:"NonXmlChar",char:String.fromCodePoint(this.currCodeUnitUnchecked())},this.genTextPos());this._pos+=1}}advance(t){this._pos+=t}goTo(t){this._pos=t}goToEnd(){this._pos=this._end}startsWith(t){return this._text.startsWith(t,this._pos)}skipString(t){if(!this.startsWith(t))throw new o({type:"InvalidString",expected:t},this.genTextPos());this._pos+=t.length}sliceBack(t){return this._text.slice(t,this._pos)}rangeFrom(t){return{start:t,end:this._pos}}skipSpaces(){for(;this.startsWithSpace();)this._pos+=1}startsWithSpace(){return this._pos<this._end&&A(this.currCodeUnitUnchecked())}consumeSpaces(){if(this._pos>=this._end)throw new o({type:"UnexpectedEndOfStream"},this.genTextPos());if(!this.startsWithSpace())throw new o({type:"InvalidChar",expected:"a whitespace",actual:this.currCodeUnitUnchecked()},this.genTextPos());this.skipSpaces()}tryConsumeReference(){const t=this._pos,e=this.clone(),i=e.consumeReference();return i!=null?(this._pos+=e.getPos()-t,i):null}consumeReference(){if(!this.tryConsumeCodeUnit(f))return null;let t;if(this.tryConsumeCodeUnit(x)){let e,i;this.tryConsumeCodeUnit(g)?(e=this.consumeCodeUnitsWhile(s=>s>=U&&s<=w||s>=y&&s<=S||s>=E&&s<=v),i=16):(e=this.consumeCodeUnitsWhile(s=>b(s)),i=10);const n=parseInt(e,i);isNaN(n)||!d(n)?t=null:t={type:"Char",value:String.fromCodePoint(n)}}else{const e=this.consumeName();switch(e){case"quot":t={type:"Char",value:'"'};break;case"amp":t={type:"Char",value:"&"};break;case"apos":t={type:"Char",value:"'"};break;case"lt":t={type:"Char",value:"<"};break;case"gt":t={type:"Char",value:">"};break;default:t={type:"Entity",value:e}}}return this.tryConsumeCodeUnit(P)?t:null}consumeName(){const t=this._pos;this.skipName();const e=this.sliceBack(t);if(e.length===0)throw new o({type:"InvalidName"},this.genTextPosFrom(t));return e}skipName(){const t=this._pos;for(;this._pos<this._end;){const e=this.currCodeUnitUnchecked();if(this._pos===t){if(!l(e))throw new o({type:"InvalidName"},this.genTextPosFrom(t))}else if(!_(e))break;this._pos+=1}}consumeQName(){var t,e;const i=this._pos;let n=null;for(;this._pos<this._end;){const c=this.currCodeUnitUnchecked();if(c===k)if(n==null)n=this._pos,this._pos+=1;else throw new o({type:"InvalidName"},this.genTextPosFrom(i));else if(_(c))this._pos+=1;else break}let s,h;if(n!=null?(s=this._text.slice(i,n),h=this.sliceBack(n+1)):(s="",h=this.sliceBack(i)),s.length>0&&!l((t=s[0])==null?void 0:t.codePointAt(0)))throw new o({type:"InvalidName"},this.genTextPosFrom(i));if(h.length>0){if(!l((e=h[0])==null?void 0:e.codePointAt(0)))throw new o({type:"InvalidName"},this.genTextPosFrom(i))}else throw new o({type:"InvalidName"},this.genTextPosFrom(i));return[s,h]}consumeQuote(){const t=this.currCodeUnit();if(t===N||t===T)return this._pos+=1,t;throw new o({type:"InvalidChar",expected:"a quote",actual:t},this.genTextPos())}getTextAround(t,e){const i=Math.floor(e/2),n=Math.max(0,t-i),s=Math.min(this._end,t+i+e%2);return this._text.slice(n,s)}genTextPos(){return this.genTextPosFrom(this._pos)}genTextPosFrom(t){const e=Math.min(t,this._end);let i=1,n=1;for(let s=0;s<e;s++)this._text.charCodeAt(s)===O?(i++,n=1):n++;return C({row:i,col:n},this.config.contextSliceSize?{contextSlice:this.getTextAround(t,this.config.contextSliceSize)}:{})}}export{u as XmlStream};

package/dist/esm/tokenizer/ascii-constants.js

@@ -1,35 +1 @@
-const HORIZONTAL_TAB = 9;
-const LINE_FEED = 10;
-const CARRIAGE_RETURN = 13;
-const SPACE = 32;
-const EXCLAMATION_MARK = 33;
-const DOUBLE_QUOTE = 34;
-const HASH = 35;
-const PERCENT = 37;
-const AMPERSAND = 38;
-const SINGLE_QUOTE = 39;
-const HYPHEN = 45;
-const PERIOD = 46;
-const SLASH = 47;
-const ZERO = 48;
-const NINE = 57;
-const COLON = 58;
-const SEMICOLON = 59;
-const LESS_THAN = 60;
-const EQUALS = 61;
-const GREATER_THAN = 62;
-const QUESTION_MARK = 63;
-const UPPERCASE_A = 65;
-const UPPERCASE_F = 70;
-const UPPERCASE_P = 80;
-const UPPERCASE_S = 83;
-const UPPERCASE_Z = 90;
-const OPEN_SQUARE_BRACKET = 91;
-const CLOSE_SQUARE_BRACKET = 93;
-const UNDERSCORE = 95;
-const LOWERCASE_A = 97;
-const LOWERCASE_F = 102;
-const LOWERCASE_X = 120;
-const LOWERCASE_Z = 122;
-
-export { AMPERSAND, CARRIAGE_RETURN, CLOSE_SQUARE_BRACKET, COLON, DOUBLE_QUOTE, EQUALS, EXCLAMATION_MARK, GREATER_THAN, HASH, HORIZONTAL_TAB, HYPHEN, LESS_THAN, LINE_FEED, LOWERCASE_A, LOWERCASE_F, LOWERCASE_X, LOWERCASE_Z, NINE, OPEN_SQUARE_BRACKET, PERCENT, PERIOD, QUESTION_MARK, SEMICOLON, SINGLE_QUOTE, SLASH, SPACE, UNDERSCORE, UPPERCASE_A, UPPERCASE_F, UPPERCASE_P, UPPERCASE_S, UPPERCASE_Z, ZERO };
+const E=9,A=10,R=13,S=32,_=33,O=34,C=35,N=37,P=38,L=39,U=45,T=46,I=47,H=48,Q=57,D=58,M=59,B=60,K=61,W=62,Z=63,F=65,G=70,o=80,t=83,X=90,c=91,e=93,n=95,p=97,r=102,s=120,x=122;export{P as AMPERSAND,R as CARRIAGE_RETURN,e as CLOSE_SQUARE_BRACKET,D as COLON,O as DOUBLE_QUOTE,K as EQUALS,_ as EXCLAMATION_MARK,W as GREATER_THAN,C as HASH,E as HORIZONTAL_TAB,U as HYPHEN,B as LESS_THAN,A as LINE_FEED,p as LOWERCASE_A,r as LOWERCASE_F,s as LOWERCASE_X,x as LOWERCASE_Z,Q as NINE,c as OPEN_SQUARE_BRACKET,N as PERCENT,T as PERIOD,Z as QUESTION_MARK,M as SEMICOLON,L as SINGLE_QUOTE,I as SLASH,S as SPACE,n as UNDERSCORE,F as UPPERCASE_A,G as UPPERCASE_F,o as UPPERCASE_P,t as UPPERCASE_S,X as UPPERCASE_Z,H as ZERO};