@minelang-ts/lexer 0.0.1

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Maysara Elshewehy (https://github.com/maysara-elshewehy)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -0,0 +1,45 @@
+<!-- ╔═══════════════════════════ BEG ════════════════════════════╗ -->
+
+<br>
+<div align="center">
+    <p>
+        <img src="./assets/img/logo.png" alt="logo" style="" height="60" />
+    </p>
+</div>
+
+<div align="center">
+    <img data="version" src="https://img.shields.io/badge/v-0.0.1-black"/>
+    <a href="https://github.com/minelang-ts"><img src="https://img.shields.io/badge/@-minelang--ts-black"/></a>
+    <img src="https://img.shields.io/badge/coverage-99.67%25-brightgreen" alt="Test Coverage" />
+</div>
+<br>
+
+<!-- ╚════════════════════════════════════════════════════════════╝ -->
+
+
+
+<!-- ╔═══════════════════════════ DOC ════════════════════════════╗ -->
+
+- ## Note 📝
+
+    > All repositories related to `minelang-ts`, **like this repository**, are temporary repositories created for the purpose of simulating the final form of the Mine language.
+    >
+    > This means that they will later be ignored or deleted entirely after the real version of Mine is created using Mine itself rather than TypeScript. Until that happens, I will not provide any guarantees for the use of these repositories, since I will not spend much time on them because, as I said, they are temporary.
+
+<!-- ╚════════════════════════════════════════════════════════════╝ -->
+
+
+
+<!-- ╔═══════════════════════════ END ════════════════════════════╗ -->
+
+<br>
+
+<div align="center"><img src="./assets/img/line.png" alt="logo" style="" width="50%" /></div>
+
+<br>
+
+<div align="center">
+    <a href="https://github.com/maysara-elshewehy"><img src="https://img.shields.io/badge/by-Maysara-black"/></a>
+</div>
+
+<!-- ╚════════════════════════════════════════════════════════════╝ -->

package/dist/index.cjs

@@ -0,0 +1,10 @@
+'use strict';Object.defineProperty(exports,'__esModule',{value:true});var B=Object.prototype.toString,x="abcdefghijklmnopqrstuvwxyz0123456789_ABCDEFGHIJKLMNOPQRSTUVWXYZ";function d(o){return !!o&&B.call(o)==="[object RegExp]"}function I(o){return !!o&&typeof o=="object"&&!d(o)&&!Array.isArray(o)}function R(o){return o.replace(/[-/\\^$*+?.()|[\]{}]/g,t=>t==="-"?"\\x2d":"\\"+t)}function S(o){let t=0,e=-1,r=-1;for(;(r=o.indexOf(`
+`,r+1))!==-1;)t++,e=r;return [t,e]}function k(){return this.text}function A(o,t){let e=1,r=1;for(let l=0;l<t;l++)o[l]===`
+`?(e++,r=1):r++;return {line:e,col:r}}function w(o,t){return new RegExp("(?:"+o+")",t?"yu":"y")}function P(o,t){if(o.ignoreCase)throw new Error(`Rule '${t}': /i flag not allowed`);if(o.global)throw new Error(`Rule '${t}': /g flag is implied`);if(o.sticky)throw new Error(`Rule '${t}': /y flag is implied`);if(o.multiline)throw new Error(`Rule '${t}': /m flag is implied`);if(new RegExp("|"+o.source).exec("").length>1)throw new Error(`Rule '${t}': RegExp has capture groups - use (?:\u2026) instead`)}var b=new Map;function L(o,t){let e=(t?"u:":":")+o.source,r=b.get(e);if(r)return r;let l;try{l=new RegExp("^(?:"+o.source+")",t?"u":"");}catch{return {ascii:new Uint8Array(128),high:false}}let i={ascii:new Uint8Array(128),high:false};for(let s=0;s<128;s++){let f=String.fromCharCode(s);l.lastIndex=0,l.test(f+f.repeat(8)+x)&&(i.ascii[s]=1);}return l.lastIndex=0,i.high=l.test("\xE9\xE9\xE9"+x)||l.test("\u4E2D\u4E2D\u4E2D"+x),b.set(e,i),i}function C(o){let t=[];for(let e of Object.getOwnPropertyNames(o)){let r=o[e],l=Array.isArray(r)?r:[r],i=[],s=()=>{i.length&&(t.push({typeName:e,s:{match:i.slice()}}),i=[]);};for(let f of l)I(f)?(s(),t.push({typeName:e,s:f})):i.push(f);s();}return t}function T(o,t){return o.map(({typeName:e,s:r})=>{let l=r.error&&!r.match?[]:Array.isArray(r.match)?r.match:[r.match];for(let a of l)d(a)&&P(a,e);let i=l.filter(a=>!(typeof a=="string"&&a.length===1)),s=null;if(i.length>0){let g=[...i].sort((h,n)=>typeof h=="string"&&typeof n=="string"?n.length-h.length:d(h)?1:d(n)?-1:0).map(h=>typeof h=="string"?R(h):h.source).join("|");if(s=w(g,t),s.lastIndex=0,s.test(""))throw s.lastIndex=0,new Error(`Rule '${e}': pattern matches empty string`);if(s.lastIndex=0,!r.lineBreaks&&!r.error){let h=s.source.includes(`
+`);if(!h){let n=new RegExp(s.source,t?"gu":"g"),p=[`
+`,`a
+b`,`
+foo`,`bar
+`,`foo
+bar`];e:for(let u of p){n.lastIndex=0;let c;for(;(c=n.exec(u))!==null;){if(c[0].includes(`
+`)){h=true;break e}if(c[0].length===0)break}}}if(h)throw s.lastIndex=0,new Error(`Rule '${e}': can match \\n - set lineBreaks: true`)}s.lastIndex=0;}return {rule:{type:e,re:s,lineBreaks:!!(r.lineBreaks||r.error),error:!!r.error,shouldThrow:false,value:r.value??null,typeXform:r.type??null},pats:l}})}function _(o,t){let e=new Array(128).fill(null),r=[],l=[],i=n=>(e[n]||(e[n]={A:[],B:[],C:null}),e[n]);for(let{rule:n,pats:p}of o)if(!n.error)for(let u of p)if(typeof u=="string"){let c=u.charCodeAt(0);u.length===1?c<128?i(c).C=n:r.push({len:1,lit:u,rule:n}):c<128?i(c).A.push({len:u.length,lit:u,rule:n}):r.push({len:u.length,lit:u,rule:n});}else {let{ascii:c,high:v}=L(u,t);for(let m=0;m<128;m++)if(c[m]){let E=i(m);E.B.includes(n)||E.B.push(n);}v&&!l.includes(n)&&l.push(n);}let s=n=>{let p=[];n.A.sort((u,c)=>c.len-u.len);for(let{lit:u,rule:c}of n.A)p.push({re:w(R(u),t),rule:c});for(let u of n.B)p.push({re:u.re,rule:u});return n.C&&p.push({re:null,rule:n.C}),p.length===1?{re0:p[0].re,rule0:p[0].rule,candidates:p}:{re0:void 0,rule0:void 0,candidates:p}},f=new Array(128).fill(null);for(let n=0;n<128;n++)e[n]&&(f[n]=s(e[n]));let a=null;if(r.length||l.length){r.sort((u,c)=>c.len-u.len);let n=[];for(let{lit:u,rule:c}of r)n.push({re:w(R(u),t),rule:c});for(let u of l)n.push({re:u.re,rule:u});let p=n.length===1;a={re0:p?n[0].re:void 0,rule0:p?n[0].rule:void 0,candidates:n};}let g={type:"error",re:null,lineBreaks:true,error:true,shouldThrow:true,value:null,typeXform:null},h=o.find(n=>n.rule.error)?.rule;return {slots:f,highSlot:a,errorRule:h??g}}var y=class{constructor(t){this._buf="";this._pos=0;this._line=1;this._col=1;this._dt=t;}reset(t="",e){return this._buf=t,this._pos=0,this._line=e?.line??1,this._col=e?.col??1,this}save(){return {line:this._line,col:this._col}}next(){let t=this._buf,e=this._pos;if(e===t.length)return;let{slots:r,highSlot:l,errorRule:i}=this._dt,s=t.charCodeAt(e),f=s<128?r[s]:l;if(!f)return this.internalEmit(i,t[e],e);if(f.rule0!==void 0){let a=f.re0,g=f.rule0;return a===null?this.internalEmit(g,t[e],e):(a.lastIndex=e,a.test(t)?this.internalEmit(g,t.slice(e,a.lastIndex),e):this.internalEmit(i,t[e],e))}for(let{re:a,rule:g}of f.candidates){if(a===null)return this.internalEmit(g,t[e],e);if(a.lastIndex=e,a.test(t))return this.internalEmit(g,t.slice(e,a.lastIndex),e)}return this.internalEmit(i,t[e],e)}formatError(t,e="invalid syntax"){let{line:r,col:l}=A(this._buf,t.span.start);return `${e} at line ${r} col ${l}`}internalEmit(t,e,r){let l=0,i=-1;t.lineBreaks&&([l,i]=S(e));let s={type:t.typeXform?t.typeXform(e)??t.type:t.type,text:t.value?t.value(e):e,toString:k,span:{start:r,end:r+e.length}};if(this._pos+=e.length,l>0?(this._line+=l,this._col=e.length-(i+1)+1):this._col+=e.length,t.shouldThrow)throw new Error(this.formatError(s,"invalid syntax"));return s}};function $(o){let t=new Map;for(let e of Object.getOwnPropertyNames(o))for(let r of [].concat(o[e])){if(typeof r!="string")throw new Error(`keywords(): value must be a string (in '${e}')`);t.set(r,e);}return e=>t.get(e)}function j(o){let t=C(o),e=t.some(({s:r})=>(r.match?Array.isArray(r.match)?r.match:[r.match]:[]).some(i=>d(i)&&i.unicode));return new y(_(T(t,e),e))}var X={compile:j,keywords:$};exports.Lexer=y;exports.compile=j;exports.default=X;exports.keywords=$;

package/dist/index.d.cts

@@ -0,0 +1,133 @@
+/** Byte span: start and end positions in the input. */
+interface Span {
+    /** Byte offset from the start of the input. */
+    start: number;
+    /** Byte offset after the match (exclusive). */
+    end: number;
+}
+/** A single token returned by next(). */
+interface Token {
+    /** Token type name as declared in the rule spec. */
+    readonly type: string;
+    /** Matched text, transformed by value() if supplied. */
+    readonly text: string;
+    /** Byte span of the match. */
+    readonly span: Span;
+    toString(): string;
+}
+/** Saved position - pass to reset() to resume from a checkpoint. */
+interface LexerState {
+    readonly line: number;
+    readonly col: number;
+}
+/** Keyword-to-type map for keywords(). */
+type KeywordMap = Record<string, string | string[]>;
+/**
+* Type-transform function.
+* Return a string to override the token type,
+* or undefined to keep the rule's declared type.
+*/
+type TypeTransform = (text: string) => string | undefined;
+/** Full object form of a rule. */
+interface RuleSpec {
+    /** One or more patterns. Strings are exact literals; RegExps are patterns. */
+    match: Pattern | Pattern[];
+    /** Required if the pattern can match a newline. The lexer validates this at compile time. */
+    lineBreaks?: boolean;
+    /** Emit an error token instead of throwing when this rule matches. */
+    error?: boolean;
+    /** Transform matched text before storing in token.value. */
+    value?: (text: string) => string;
+    /** Override the token type. Pass keywords({...}) here. */
+    type?: TypeTransform;
+}
+/** Anything accepted as a rule value in the spec. */
+type RuleValue = Pattern | Pattern[] | RuleSpec | (Pattern | RuleSpec)[];
+/** A string literal or RegExp pattern. */
+type Pattern = string | RegExp;
+/**
+* The spec object passed to compile().
+* Keys are token-type names; values describe what to match.
+*
+* Matching priority:
+*   1. Longer string literals always beat shorter ones ('===' > '=>' > '=').
+*   2. Among rules that share the same first character, RegExp rules run in
+*      declaration order after all string literals.
+*/
+type RulesSpec = Record<string, RuleValue>;
+interface CRule {
+    readonly type: string;
+    readonly re: RegExp | null;
+    readonly lineBreaks: boolean;
+    readonly error: boolean;
+    readonly shouldThrow: boolean;
+    readonly value: ((s: string) => string) | null;
+    readonly typeXform: TypeTransform | null;
+}
+/**
+* One dispatch slot per ASCII charCode.
+*
+* fast: when exactly one candidate exists, re0/rule0 are set.
+*       next() uses them directly, skipping the loop.
+* slow: when 2+ candidates exist (e.g. '===', '=>', '='),
+*       candidates[] is tried in order.
+*/
+interface Slot {
+    readonly re0: RegExp | null | undefined;
+    readonly rule0: CRule | undefined;
+    readonly candidates: readonly {
+        re: RegExp | null;
+        rule: CRule;
+    }[];
+}
+interface DispatchTable {
+    readonly slots: readonly (Slot | null)[];
+    readonly highSlot: Slot | null;
+    readonly errorRule: CRule;
+}
+
+/** A compiled lexer. Create one with compile(). */
+declare class Lexer {
+    private readonly _dt;
+    private _buf;
+    private _pos;
+    private _line;
+    private _col;
+    /** @internal */
+    constructor(dt: DispatchTable);
+    /**
+    * Load new input.
+    * Optionally pass a LexerState from save() to resume from a checkpoint.
+    * Returns `this` so you can chain: lexer.reset(src).next()
+    */
+    reset(input?: string, state?: LexerState): this;
+    /** Snapshot current line/col for later reset(). */
+    save(): LexerState;
+    /** Return the next Token, or undefined at EOF. */
+    next(): Token | undefined;
+    /** Return a human-readable error string with file position. */
+    formatError(token: Token, message?: string): string;
+    private internalEmit;
+}
+
+/**
+* Build a type-transform that remaps matched identifiers to keyword types.
+* Ensures the longest-match principle - 'className' will never be split
+* into 'class' + 'Name'.
+*/
+declare function keywords(map: KeywordMap): TypeTransform;
+/**
+* Compile a rule spec into a Lexer.
+*
+* Rules are matched in declaration order.
+* String literals always beat shorter ones ('===' wins over '=' regardless of order).
+* RegExp rules for the same first character run in declaration order.
+*/
+declare function compile(spec: RulesSpec): Lexer;
+
+declare const _default: {
+    compile: typeof compile;
+    keywords: typeof keywords;
+};
+
+export { type CRule, type DispatchTable, type KeywordMap, Lexer, type LexerState, type Pattern, type RuleSpec, type RuleValue, type RulesSpec, type Slot, type Span, type Token, type TypeTransform, compile, _default as default, keywords };

package/dist/index.d.ts

@@ -0,0 +1,133 @@
+/** Byte span: start and end positions in the input. */
+interface Span {
+    /** Byte offset from the start of the input. */
+    start: number;
+    /** Byte offset after the match (exclusive). */
+    end: number;
+}
+/** A single token returned by next(). */
+interface Token {
+    /** Token type name as declared in the rule spec. */
+    readonly type: string;
+    /** Matched text, transformed by value() if supplied. */
+    readonly text: string;
+    /** Byte span of the match. */
+    readonly span: Span;
+    toString(): string;
+}
+/** Saved position - pass to reset() to resume from a checkpoint. */
+interface LexerState {
+    readonly line: number;
+    readonly col: number;
+}
+/** Keyword-to-type map for keywords(). */
+type KeywordMap = Record<string, string | string[]>;
+/**
+* Type-transform function.
+* Return a string to override the token type,
+* or undefined to keep the rule's declared type.
+*/
+type TypeTransform = (text: string) => string | undefined;
+/** Full object form of a rule. */
+interface RuleSpec {
+    /** One or more patterns. Strings are exact literals; RegExps are patterns. */
+    match: Pattern | Pattern[];
+    /** Required if the pattern can match a newline. The lexer validates this at compile time. */
+    lineBreaks?: boolean;
+    /** Emit an error token instead of throwing when this rule matches. */
+    error?: boolean;
+    /** Transform matched text before storing in token.value. */
+    value?: (text: string) => string;
+    /** Override the token type. Pass keywords({...}) here. */
+    type?: TypeTransform;
+}
+/** Anything accepted as a rule value in the spec. */
+type RuleValue = Pattern | Pattern[] | RuleSpec | (Pattern | RuleSpec)[];
+/** A string literal or RegExp pattern. */
+type Pattern = string | RegExp;
+/**
+* The spec object passed to compile().
+* Keys are token-type names; values describe what to match.
+*
+* Matching priority:
+*   1. Longer string literals always beat shorter ones ('===' > '=>' > '=').
+*   2. Among rules that share the same first character, RegExp rules run in
+*      declaration order after all string literals.
+*/
+type RulesSpec = Record<string, RuleValue>;
+interface CRule {
+    readonly type: string;
+    readonly re: RegExp | null;
+    readonly lineBreaks: boolean;
+    readonly error: boolean;
+    readonly shouldThrow: boolean;
+    readonly value: ((s: string) => string) | null;
+    readonly typeXform: TypeTransform | null;
+}
+/**
+* One dispatch slot per ASCII charCode.
+*
+* fast: when exactly one candidate exists, re0/rule0 are set.
+*       next() uses them directly, skipping the loop.
+* slow: when 2+ candidates exist (e.g. '===', '=>', '='),
+*       candidates[] is tried in order.
+*/
+interface Slot {
+    readonly re0: RegExp | null | undefined;
+    readonly rule0: CRule | undefined;
+    readonly candidates: readonly {
+        re: RegExp | null;
+        rule: CRule;
+    }[];
+}
+interface DispatchTable {
+    readonly slots: readonly (Slot | null)[];
+    readonly highSlot: Slot | null;
+    readonly errorRule: CRule;
+}
+
+/** A compiled lexer. Create one with compile(). */
+declare class Lexer {
+    private readonly _dt;
+    private _buf;
+    private _pos;
+    private _line;
+    private _col;
+    /** @internal */
+    constructor(dt: DispatchTable);
+    /**
+    * Load new input.
+    * Optionally pass a LexerState from save() to resume from a checkpoint.
+    * Returns `this` so you can chain: lexer.reset(src).next()
+    */
+    reset(input?: string, state?: LexerState): this;
+    /** Snapshot current line/col for later reset(). */
+    save(): LexerState;
+    /** Return the next Token, or undefined at EOF. */
+    next(): Token | undefined;
+    /** Return a human-readable error string with file position. */
+    formatError(token: Token, message?: string): string;
+    private internalEmit;
+}
+
+/**
+* Build a type-transform that remaps matched identifiers to keyword types.
+* Ensures the longest-match principle - 'className' will never be split
+* into 'class' + 'Name'.
+*/
+declare function keywords(map: KeywordMap): TypeTransform;
+/**
+* Compile a rule spec into a Lexer.
+*
+* Rules are matched in declaration order.
+* String literals always beat shorter ones ('===' wins over '=' regardless of order).
+* RegExp rules for the same first character run in declaration order.
+*/
+declare function compile(spec: RulesSpec): Lexer;
+
+declare const _default: {
+    compile: typeof compile;
+    keywords: typeof keywords;
+};
+
+export { type CRule, type DispatchTable, type KeywordMap, Lexer, type LexerState, type Pattern, type RuleSpec, type RuleValue, type RulesSpec, type Slot, type Span, type Token, type TypeTransform, compile, _default as default, keywords };

package/dist/index.js

@@ -0,0 +1,10 @@
+var B=Object.prototype.toString,x="abcdefghijklmnopqrstuvwxyz0123456789_ABCDEFGHIJKLMNOPQRSTUVWXYZ";function d(o){return !!o&&B.call(o)==="[object RegExp]"}function I(o){return !!o&&typeof o=="object"&&!d(o)&&!Array.isArray(o)}function R(o){return o.replace(/[-/\\^$*+?.()|[\]{}]/g,t=>t==="-"?"\\x2d":"\\"+t)}function S(o){let t=0,e=-1,r=-1;for(;(r=o.indexOf(`
+`,r+1))!==-1;)t++,e=r;return [t,e]}function k(){return this.text}function A(o,t){let e=1,r=1;for(let l=0;l<t;l++)o[l]===`
+`?(e++,r=1):r++;return {line:e,col:r}}function w(o,t){return new RegExp("(?:"+o+")",t?"yu":"y")}function P(o,t){if(o.ignoreCase)throw new Error(`Rule '${t}': /i flag not allowed`);if(o.global)throw new Error(`Rule '${t}': /g flag is implied`);if(o.sticky)throw new Error(`Rule '${t}': /y flag is implied`);if(o.multiline)throw new Error(`Rule '${t}': /m flag is implied`);if(new RegExp("|"+o.source).exec("").length>1)throw new Error(`Rule '${t}': RegExp has capture groups - use (?:\u2026) instead`)}var b=new Map;function L(o,t){let e=(t?"u:":":")+o.source,r=b.get(e);if(r)return r;let l;try{l=new RegExp("^(?:"+o.source+")",t?"u":"");}catch{return {ascii:new Uint8Array(128),high:false}}let i={ascii:new Uint8Array(128),high:false};for(let s=0;s<128;s++){let f=String.fromCharCode(s);l.lastIndex=0,l.test(f+f.repeat(8)+x)&&(i.ascii[s]=1);}return l.lastIndex=0,i.high=l.test("\xE9\xE9\xE9"+x)||l.test("\u4E2D\u4E2D\u4E2D"+x),b.set(e,i),i}function C(o){let t=[];for(let e of Object.getOwnPropertyNames(o)){let r=o[e],l=Array.isArray(r)?r:[r],i=[],s=()=>{i.length&&(t.push({typeName:e,s:{match:i.slice()}}),i=[]);};for(let f of l)I(f)?(s(),t.push({typeName:e,s:f})):i.push(f);s();}return t}function T(o,t){return o.map(({typeName:e,s:r})=>{let l=r.error&&!r.match?[]:Array.isArray(r.match)?r.match:[r.match];for(let a of l)d(a)&&P(a,e);let i=l.filter(a=>!(typeof a=="string"&&a.length===1)),s=null;if(i.length>0){let g=[...i].sort((h,n)=>typeof h=="string"&&typeof n=="string"?n.length-h.length:d(h)?1:d(n)?-1:0).map(h=>typeof h=="string"?R(h):h.source).join("|");if(s=w(g,t),s.lastIndex=0,s.test(""))throw s.lastIndex=0,new Error(`Rule '${e}': pattern matches empty string`);if(s.lastIndex=0,!r.lineBreaks&&!r.error){let h=s.source.includes(`
+`);if(!h){let n=new RegExp(s.source,t?"gu":"g"),p=[`
+`,`a
+b`,`
+foo`,`bar
+`,`foo
+bar`];e:for(let u of p){n.lastIndex=0;let c;for(;(c=n.exec(u))!==null;){if(c[0].includes(`
+`)){h=true;break e}if(c[0].length===0)break}}}if(h)throw s.lastIndex=0,new Error(`Rule '${e}': can match \\n - set lineBreaks: true`)}s.lastIndex=0;}return {rule:{type:e,re:s,lineBreaks:!!(r.lineBreaks||r.error),error:!!r.error,shouldThrow:false,value:r.value??null,typeXform:r.type??null},pats:l}})}function _(o,t){let e=new Array(128).fill(null),r=[],l=[],i=n=>(e[n]||(e[n]={A:[],B:[],C:null}),e[n]);for(let{rule:n,pats:p}of o)if(!n.error)for(let u of p)if(typeof u=="string"){let c=u.charCodeAt(0);u.length===1?c<128?i(c).C=n:r.push({len:1,lit:u,rule:n}):c<128?i(c).A.push({len:u.length,lit:u,rule:n}):r.push({len:u.length,lit:u,rule:n});}else {let{ascii:c,high:v}=L(u,t);for(let m=0;m<128;m++)if(c[m]){let E=i(m);E.B.includes(n)||E.B.push(n);}v&&!l.includes(n)&&l.push(n);}let s=n=>{let p=[];n.A.sort((u,c)=>c.len-u.len);for(let{lit:u,rule:c}of n.A)p.push({re:w(R(u),t),rule:c});for(let u of n.B)p.push({re:u.re,rule:u});return n.C&&p.push({re:null,rule:n.C}),p.length===1?{re0:p[0].re,rule0:p[0].rule,candidates:p}:{re0:void 0,rule0:void 0,candidates:p}},f=new Array(128).fill(null);for(let n=0;n<128;n++)e[n]&&(f[n]=s(e[n]));let a=null;if(r.length||l.length){r.sort((u,c)=>c.len-u.len);let n=[];for(let{lit:u,rule:c}of r)n.push({re:w(R(u),t),rule:c});for(let u of l)n.push({re:u.re,rule:u});let p=n.length===1;a={re0:p?n[0].re:void 0,rule0:p?n[0].rule:void 0,candidates:n};}let g={type:"error",re:null,lineBreaks:true,error:true,shouldThrow:true,value:null,typeXform:null},h=o.find(n=>n.rule.error)?.rule;return {slots:f,highSlot:a,errorRule:h??g}}var y=class{constructor(t){this._buf="";this._pos=0;this._line=1;this._col=1;this._dt=t;}reset(t="",e){return this._buf=t,this._pos=0,this._line=e?.line??1,this._col=e?.col??1,this}save(){return {line:this._line,col:this._col}}next(){let t=this._buf,e=this._pos;if(e===t.length)return;let{slots:r,highSlot:l,errorRule:i}=this._dt,s=t.charCodeAt(e),f=s<128?r[s]:l;if(!f)return this.internalEmit(i,t[e],e);if(f.rule0!==void 0){let a=f.re0,g=f.rule0;return a===null?this.internalEmit(g,t[e],e):(a.lastIndex=e,a.test(t)?this.internalEmit(g,t.slice(e,a.lastIndex),e):this.internalEmit(i,t[e],e))}for(let{re:a,rule:g}of f.candidates){if(a===null)return this.internalEmit(g,t[e],e);if(a.lastIndex=e,a.test(t))return this.internalEmit(g,t.slice(e,a.lastIndex),e)}return this.internalEmit(i,t[e],e)}formatError(t,e="invalid syntax"){let{line:r,col:l}=A(this._buf,t.span.start);return `${e} at line ${r} col ${l}`}internalEmit(t,e,r){let l=0,i=-1;t.lineBreaks&&([l,i]=S(e));let s={type:t.typeXform?t.typeXform(e)??t.type:t.type,text:t.value?t.value(e):e,toString:k,span:{start:r,end:r+e.length}};if(this._pos+=e.length,l>0?(this._line+=l,this._col=e.length-(i+1)+1):this._col+=e.length,t.shouldThrow)throw new Error(this.formatError(s,"invalid syntax"));return s}};function $(o){let t=new Map;for(let e of Object.getOwnPropertyNames(o))for(let r of [].concat(o[e])){if(typeof r!="string")throw new Error(`keywords(): value must be a string (in '${e}')`);t.set(r,e);}return e=>t.get(e)}function j(o){let t=C(o),e=t.some(({s:r})=>(r.match?Array.isArray(r.match)?r.match:[r.match]:[]).some(i=>d(i)&&i.unicode));return new y(_(T(t,e),e))}var X={compile:j,keywords:$};export{y as Lexer,j as compile,X as default,$ as keywords};

package/package.json

@@ -0,0 +1,54 @@
+{
+  "name": "@minelang-ts/lexer",
+  "version": "0.0.1",
+  "description": "Mine programming language lexer.",
+  "keywords": ["mine", "programming", "language", "lexer"],
+  "license": "MIT",
+  "author": {
+    "email": "maysara.elshewehy@gmail.com",
+    "name": "Maysara Elshewehy",
+    "url": "https://github.com/maysara-elshewehy"
+  },
+  "type": "module",
+  "homepage": "https://github.com/minelang-ts/lexer#readme",
+  "bugs": {
+    "url": "https://github.com/minelang-ts/lexer/issues"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/minelang-ts/lexer.git"
+  },
+  "main": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "files": ["dist"],
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js",
+      "require": "./dist/index.js"
+    }
+  },
+  "engines": {
+    "bun": ">=1.3.3"
+  },
+  "pkg": {
+    "type": "pkg"
+  },
+  "scripts": {},
+  "peerDependencies": {
+    "bun": "^1.3.14"
+  },
+  "dependencies": {},
+  "devDependencies": {
+    "@eslint/js": "^10.0.1",
+    "@stylistic/eslint-plugin": "^5.10.0",
+    "@types/bun": "^1.3.14",
+    "@types/node": "^26.0.1",
+    "bun-plugin-dts": "^0.4.0",
+    "bun-types": "^1.3.14",
+    "ts-node": "^10.9.2",
+    "tsup": "^8.5.1",
+    "typescript": "^6.0.3",
+    "typescript-eslint": "^8.62.1"
+  }
+}