parser-lr 0.0.0 → 0.2.1

package/dist/lib/lexer/lexer.js

@@ -0,0 +1,270 @@
+import { assertLexerState, compileLexerRules, findLongestMatch, hasLongerPossibleMatch, isPrefixOfPotentialMatch, rulesForState, } from './lexer-compile.js';
+import { LexerError } from './lexer-error.js';
+import { LexerInputError } from './lexer-input-error.js';
+import { eofToken, token } from './token.js';
+/**
+ * Stream-based lexer driven by a grammar's `tokens`, `skip`, and `states` sections.
+ *
+ * Push source chunks with {@link push}, signal end-of-input with {@link finish},
+ * then read tokens via {@link next} or iteration. The final token is always `$eof`.
+ */
+export class Lexer {
+    compiled;
+    queue = [];
+    buffer = '';
+    offset = 0;
+    finished = false;
+    eofEmitted = false;
+    currentState;
+    /**
+     * Creates a lexer from a parsed grammar.
+     *
+     * @param grammar - Grammar supplying token and skip rule definitions.
+     */
+    constructor(grammar) {
+        this.compiled = compileLexerRules(grammar);
+        this.currentState = this.compiled.initialState;
+    }
+    /**
+     * Returns the active lexer state name.
+     */
+    get state() {
+        return this.currentState;
+    }
+    /**
+     * Enters a declared lexer state.
+     *
+     * @param stateName - Lexer state to activate.
+     */
+    enterState(stateName) {
+        assertLexerState(this.compiled, stateName);
+        this.currentState = stateName;
+    }
+    /**
+     * Appends the next chunk of source text to the scan buffer.
+     *
+     * @param chunk - Source text fragment.
+     */
+    push(chunk) {
+        if (this.finished) {
+            throw new LexerInputError();
+        }
+        this.buffer += chunk;
+        this.drain(false);
+    }
+    /**
+     * Signals that no further source chunks will arrive.
+     */
+    finish() {
+        this.finished = true;
+        this.drain(true);
+    }
+    /**
+     * Returns the next token, or null when waiting for more input.
+     *
+     * @returns The next token, null while blocked, or `$eof` after input ends.
+     */
+    next() {
+        if (this.eofEmitted) {
+            return null;
+        }
+        if (this.queue.length > 0) {
+            return this.queue.shift() ?? null;
+        }
+        if (!this.finished) {
+            return null;
+        }
+        if (this.buffer.length > 0) {
+            throw new LexerError(`Unexpected character ${JSON.stringify(this.buffer[0])} at offset ${this.offset}`, this.offset);
+        }
+        this.eofEmitted = true;
+        return eofToken(this.offset);
+    }
+    /**
+     * Lexes an entire source string, including a trailing `$eof` token.
+     *
+     * @param source - Input text to tokenize.
+     * @returns Matched tokens in source order.
+     */
+    lex(source) {
+        this.reset();
+        this.push(source);
+        this.finish();
+        const tokens = [];
+        let nextToken = this.next();
+        while (nextToken !== null) {
+            tokens.push(nextToken);
+            nextToken = this.next();
+        }
+        return tokens;
+    }
+    /**
+     * Iterates all tokens until `$eof` after {@link finish} has been called.
+     */
+    [Symbol.iterator]() {
+        return {
+            next: () => {
+                const value = this.next();
+                if (value === null) {
+                    return {
+                        done: true,
+                        value: undefined,
+                    };
+                }
+                return {
+                    done: false,
+                    value,
+                };
+            },
+        };
+    }
+    /**
+     * Scans the buffer and enqueues any tokens ready to emit.
+     *
+     * @param inputFinished - Whether the full input stream has ended.
+     * @param allowChunkBoundary - Whether to commit tokens at a chunk boundary.
+     */
+    drain(inputFinished) {
+        // Scan until the buffer needs more input or input ends with an error.
+        while (true) {
+            const match = this.matchAtBufferStart(inputFinished);
+            if (match === 'need-more') {
+                return;
+            }
+            if (match === null) {
+                if (inputFinished && this.buffer.length > 0) {
+                    throw new LexerError(`Unexpected character ${JSON.stringify(this.buffer[0])} at offset ${this.offset}`, this.offset);
+                }
+                return;
+            }
+            this.buffer = this.buffer.slice(match.text.length);
+            this.offset += match.text.length;
+            if (!match.skip) {
+                this.queue.push(token(match.name, match.text, match.offset));
+            }
+        }
+    }
+    /**
+     * Finds the winning rule match at the start of the scan buffer.
+     *
+     * @param inputFinished - Whether the full input stream has ended.
+     * @param allowChunkBoundary - Whether to commit tokens at a chunk boundary.
+     */
+    matchAtBufferStart(inputFinished) {
+        if (this.buffer.length === 0) {
+            return null;
+        }
+        const activeRules = rulesForState(this.compiled, this.currentState);
+        const bestMatch = findLongestMatch(this.buffer, activeRules);
+        if (bestMatch === null) {
+            if (!inputFinished && isPrefixOfPotentialMatch(this.buffer, activeRules)) {
+                return 'need-more';
+            }
+            return null;
+        }
+        if (bestMatch.text.length === this.buffer.length && !inputFinished) {
+            if (hasLongerPossibleMatch(this.buffer, bestMatch.text, activeRules, false)) {
+                return 'need-more';
+            }
+        }
+        return {
+            name: bestMatch.name,
+            text: bestMatch.text,
+            offset: this.offset,
+            skip: bestMatch.skip,
+        };
+    }
+    /**
+     * Resets stream state for a fresh lex run.
+     */
+    reset() {
+        this.queue.length = 0;
+        this.buffer = '';
+        this.offset = 0;
+        this.finished = false;
+        this.eofEmitted = false;
+    }
+}
+/**
+ * Lexes synchronous source chunks into a token stream ending with `$eof`.
+ *
+ * @param grammar - Grammar supplying lexer rules.
+ * @param chunks - Source text fragments in order.
+ * @returns Token iterator including `$eof`.
+ */
+export function lexChunks(grammar, chunks) {
+    const lexer = new Lexer(grammar);
+    return lexChunksFromLexer(lexer, chunks);
+}
+/**
+ * Lexes asynchronous source chunks into a token stream ending with `$eof`.
+ *
+ * @param grammar - Grammar supplying lexer rules.
+ * @param chunks - Source text fragments in order.
+ * @returns Async token iterator including `$eof`.
+ */
+export async function* lexChunksAsync(grammar, chunks) {
+    const lexer = new Lexer(grammar);
+    for await (const chunk of chunks) {
+        lexer.push(chunk);
+        let nextToken = lexer.next();
+        while (nextToken !== null) {
+            yield nextToken;
+            nextToken = lexer.next();
+        }
+    }
+    lexer.finish();
+    let nextToken = lexer.next();
+    while (nextToken !== null) {
+        yield nextToken;
+        nextToken = lexer.next();
+    }
+}
+/**
+ * Drains tokens from a lexer fed by synchronous chunks.
+ *
+ * @param lexer - Configured lexer instance.
+ * @param chunks - Source text fragments in order.
+ * @returns Token iterator including `$eof`.
+ */
+function* lexChunksFromLexer(lexer, chunks) {
+    for (const chunk of chunks) {
+        lexer.push(chunk);
+        let nextToken = lexer.next();
+        while (nextToken !== null) {
+            yield nextToken;
+            nextToken = lexer.next();
+        }
+    }
+    lexer.finish();
+    let nextToken = lexer.next();
+    while (nextToken !== null) {
+        yield nextToken;
+        nextToken = lexer.next();
+    }
+}
+/**
+ * Collects all tokens from a synchronous chunk stream.
+ *
+ * @param grammar - Grammar supplying lexer rules.
+ * @param chunks - Source text fragments in order.
+ * @returns Matched tokens including `$eof`.
+ */
+export function lexChunkStream(grammar, chunks) {
+    return [...lexChunks(grammar, chunks)];
+}
+/**
+ * Collects all tokens from an asynchronous chunk stream.
+ *
+ * @param grammar - Grammar supplying lexer rules.
+ * @param chunks - Source text fragments in order.
+ * @returns Matched tokens including `$eof`.
+ */
+export async function lexChunkStreamAsync(grammar, chunks) {
+    const tokens = [];
+    for await (const value of lexChunksAsync(grammar, chunks)) {
+        tokens.push(value);
+    }
+    return tokens;
+}
+//# sourceMappingURL=lexer.js.map

package/dist/lib/lexer/lexer.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"lexer.js","sourceRoot":"","sources":["../../../src/lib/lexer/lexer.ts"],"names":[],"mappings":"AAEA,OAAO,EACH,gBAAgB,EAChB,iBAAiB,EACjB,gBAAgB,EAChB,sBAAsB,EACtB,wBAAwB,EACxB,aAAa,GAChB,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAC;AACzD,OAAO,EAAE,QAAQ,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAG7C;;;;;GAKG;AACH,MAAM,OAAO,KAAK;IAEG,QAAQ,CAAqB;IAC7B,KAAK,GAAY,EAAE,CAAC;IAC7B,MAAM,GAAG,EAAE,CAAC;IACZ,MAAM,GAAG,CAAC,CAAC;IACX,QAAQ,GAAG,KAAK,CAAC;IACjB,UAAU,GAAG,KAAK,CAAC;IACnB,YAAY,CAAS;IAE7B;;;;OAIG;IACH,YAAmB,OAAgB;QAE/B,IAAI,CAAC,QAAQ,GAAG,iBAAiB,CAAC,OAAO,CAAC,CAAC;QAC3C,IAAI,CAAC,YAAY,GAAG,IAAI,CAAC,QAAQ,CAAC,YAAY,CAAC;IACnD,CAAC;IAED;;OAEG;IACH,IAAW,KAAK;QAEZ,OAAO,IAAI,CAAC,YAAY,CAAC;IAC7B,CAAC;IAED;;;;OAIG;IACI,UAAU,CAAC,SAAiB;QAE/B,gBAAgB,CAAC,IAAI,CAAC,QAAQ,EAAE,SAAS,CAAC,CAAC;QAC3C,IAAI,CAAC,YAAY,GAAG,SAAS,CAAC;IAClC,CAAC;IAED;;;;OAIG;IACI,IAAI,CAAC,KAAa;QAErB,IAAI,IAAI,CAAC,QAAQ,EACjB,CAAC;YACG,MAAM,IAAI,eAAe,EAAE,CAAC;QAChC,CAAC;QAED,IAAI,CAAC,MAAM,IAAI,KAAK,CAAC;QACrB,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;IACtB,CAAC;IAED;;OAEG;IACI,MAAM;QAET,IAAI,CAAC,QAAQ,GAAG,IAAI,CAAC;QACrB,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IACrB,CAAC;IAED;;;;OAIG;IACI,IAAI;QAEP,IAAI,IAAI,CAAC,UAAU,EACnB,CAAC;YACG,OAAO,IAAI,CAAC;QAChB,CAAC;QAED,IAAI,IAAI,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,EACzB,CAAC;YACG,OAAO,IAAI,CAAC,KAAK,CAAC,KAAK,EAAE,IAAI,IAAI,CAAC;QACtC,CAAC;QAED,IAAI,CAAC,IAAI,CAAC,QAAQ,EAClB,CAAC;YACG,OAAO,IAAI,CAAC;QAChB,CAAC;QAED,IAAI,IAAI,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,EAC1B,CAAC;YACG,MAAM,IAAI,UAAU,CAChB,wBAAwB,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,cAAc,IAAI,CAAC,MAAM,EAAE,EACjF,IAAI,CAAC,MAAM,CACd,CAAC;QACN,CAAC;QAED,IAAI,CAAC,UAAU,GAAG,IAAI,CAAC;QACvB,OAAO,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IACjC,CAAC;IAED;;;;;OAKG;IACI,GAAG,CAAC,MAAc;QAErB,IAAI,CAAC,KAAK,EAAE,CAAC;QACb,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QAClB,IAAI,CAAC,MAAM,EAAE,CAAC;QAEd,MAAM,MAAM,GAAY,EAAE,CAAC;QAC3B,IAAI,SAAS,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QAE5B,OAAO,SAAS,KAAK,IAAI,EACzB,CAAC;YACG,MAAM,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;YACvB,SAAS,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QAC5B,CAAC;QAED,OAAO,MAAM,CAAC;IAClB,CAAC;IAED;;OAEG;IACI,CAAC,MAAM,CAAC,QAAQ,CAAC;QAEpB,OAAO;YACH,IAAI,EAAE,GAA0B,EAAE;gBAE9B,MAAM,KAAK,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;gBAE1B,IAAI,KAAK,KAAK,IAAI,EAClB,CAAC;oBACG,OAAO;wBACH,IAAI,EAAE,IAAI;wBACV,KAAK,EAAE,SAAS;qBACnB,CAAC;gBACN,CAAC;gBAED,OAAO;oBACH,IAAI,EAAE,KAAK;oBACX,KAAK;iBACR,CAAC;YACN,CAAC;SACJ,CAAC;IACN,CAAC;IAED;;;;;OAKG;IACK,KAAK,CAAC,aAAsB;QAEhC,sEAAsE;QACtE,OAAO,IAAI,EACX,CAAC;YACG,MAAM,KAAK,GAAG,IAAI,CAAC,kBAAkB,CAAC,aAAa,CAAC,CAAC;YAErD,IAAI,KAAK,KAAK,WAAW,EACzB,CAAC;gBACG,OAAO;YACX,CAAC;YAED,IAAI,KAAK,KAAK,IAAI,EAClB,CAAC;gBACG,IAAI,aAAa,IAAI,IAAI,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,EAC3C,CAAC;oBACG,MAAM,IAAI,UAAU,CAChB,wBAAwB,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,cAAc,IAAI,CAAC,MAAM,EAAE,EACjF,IAAI,CAAC,MAAM,CACd,CAAC;gBACN,CAAC;gBAED,OAAO;YACX,CAAC;YAED,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;YACnD,IAAI,CAAC,MAAM,IAAI,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC;YAEjC,IAAI,CAAC,KAAK,CAAC,IAAI,EACf,CAAC;gBACG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC;YACjE,CAAC;QACL,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACK,kBAAkB,CAAC,aAAsB;QAK7C,IAAI,IAAI,CAAC,MAAM,CAAC,MAAM,KAAK,CAAC,EAC5B,CAAC;YACG,OAAO,IAAI,CAAC;QAChB,CAAC;QAED,MAAM,WAAW,GAAG,aAAa,CAAC,IAAI,CAAC,QAAQ,EAAE,IAAI,CAAC,YAAY,CAAC,CAAC;QACpE,MAAM,SAAS,GAAG,gBAAgB,CAAC,IAAI,CAAC,MAAM,EAAE,WAAW,CAAC,CAAC;QAE7D,IAAI,SAAS,KAAK,IAAI,EACtB,CAAC;YACG,IAAI,CAAC,aAAa,IAAI,wBAAwB,CAAC,IAAI,CAAC,MAAM,EAAE,WAAW,CAAC,EACxE,CAAC;gBACG,OAAO,WAAW,CAAC;YACvB,CAAC;YAED,OAAO,IAAI,CAAC;QAChB,CAAC;QAED,IAAI,SAAS,CAAC,IAAI,CAAC,MAAM,KAAK,IAAI,CAAC,MAAM,CAAC,MAAM,IAAI,CAAC,aAAa,EAClE,CAAC;YACG,IAAI,sBAAsB,CAAC,IAAI,CAAC,MAAM,EAAE,SAAS,CAAC,IAAI,EAAE,WAAW,EAAE,KAAK,CAAC,EAC3E,CAAC;gBACG,OAAO,WAAW,CAAC;YACvB,CAAC;QACL,CAAC;QAED,OAAO;YACH,IAAI,EAAE,SAAS,CAAC,IAAI;YACpB,IAAI,EAAE,SAAS,CAAC,IAAI;YACpB,MAAM,EAAE,IAAI,CAAC,MAAM;YACnB,IAAI,EAAE,SAAS,CAAC,IAAI;SACvB,CAAC;IACN,CAAC;IAED;;OAEG;IACK,KAAK;QAET,IAAI,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC;QACtB,IAAI,CAAC,MAAM,GAAG,EAAE,CAAC;QACjB,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC;QAChB,IAAI,CAAC,QAAQ,GAAG,KAAK,CAAC;QACtB,IAAI,CAAC,UAAU,GAAG,KAAK,CAAC;IAC5B,CAAC;CACJ;AAED;;;;;;GAMG;AACH,MAAM,UAAU,SAAS,CACrB,OAAgB,EAChB,MAAwB;IAGxB,MAAM,KAAK,GAAG,IAAI,KAAK,CAAC,OAAO,CAAC,CAAC;IAEjC,OAAO,kBAAkB,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;AAC7C,CAAC;AAED;;;;;;GAMG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,cAAc,CACjC,OAAgB,EAChB,MAA6B;IAG7B,MAAM,KAAK,GAAG,IAAI,KAAK,CAAC,OAAO,CAAC,CAAC;IAEjC,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,MAAM,EAChC,CAAC;QACG,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAElB,IAAI,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;QAE7B,OAAO,SAAS,KAAK,IAAI,EACzB,CAAC;YACG,MAAM,SAAS,CAAC;YAChB,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;QAC7B,CAAC;IACL,CAAC;IAED,KAAK,CAAC,MAAM,EAAE,CAAC;IAEf,IAAI,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;IAE7B,OAAO,SAAS,KAAK,IAAI,EACzB,CAAC;QACG,MAAM,SAAS,CAAC;QAChB,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;IAC7B,CAAC;AACL,CAAC;AAED;;;;;;GAMG;AACH,QAAQ,CAAC,CAAC,kBAAkB,CACxB,KAAY,EACZ,MAAwB;IAGxB,KAAK,MAAM,KAAK,IAAI,MAAM,EAC1B,CAAC;QACG,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAElB,IAAI,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;QAE7B,OAAO,SAAS,KAAK,IAAI,EACzB,CAAC;YACG,MAAM,SAAS,CAAC;YAChB,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;QAC7B,CAAC;IACL,CAAC;IAED,KAAK,CAAC,MAAM,EAAE,CAAC;IAEf,IAAI,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;IAE7B,OAAO,SAAS,KAAK,IAAI,EACzB,CAAC;QACG,MAAM,SAAS,CAAC;QAChB,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;IAC7B,CAAC;AACL,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,cAAc,CAC1B,OAAgB,EAChB,MAAwB;IAGxB,OAAO,CAAC,GAAG,SAAS,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,CAAC;AAC3C,CAAC;AAED;;;;;;GAMG;AACH,MAAM,CAAC,KAAK,UAAU,mBAAmB,CACrC,OAAgB,EAChB,MAA6B;IAG7B,MAAM,MAAM,GAAY,EAAE,CAAC;IAE3B,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,cAAc,CAAC,OAAO,EAAE,MAAM,CAAC,EACzD,CAAC;QACG,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IACvB,CAAC;IAED,OAAO,MAAM,CAAC;AAClB,CAAC"}

package/dist/lib/lexer/token.d.ts

@@ -0,0 +1,34 @@
+import type { SourceLocation } from '../ast/ast-node.js';
+/** Token name emitted once at end of input. */
+export declare const EOF_TOKEN_NAME = "$eof";
+/**
+ * Lexeme emitted by the lexer for one token rule match.
+ */
+export interface Token {
+    readonly name: string;
+    readonly text: string;
+    readonly location: SourceLocation;
+}
+/**
+ * Builds a token value from a rule name, matched text, and source offset.
+ *
+ * @param name - Token rule name from the grammar `tokens` section.
+ * @param text - Matched lexeme text.
+ * @param offset - Start offset of the lexeme in the source.
+ * @returns A token record with a source span.
+ */
+export declare function token(name: string, text: string, offset: number): Token;
+/**
+ * Builds the end-of-input token at a source offset.
+ *
+ * @param offset - Source offset where input ended.
+ * @returns An empty `$eof` token.
+ */
+export declare function eofToken(offset: number): Token;
+/**
+ * Returns whether a token is the end-of-input marker.
+ *
+ * @param value - Token to test.
+ */
+export declare function isEofToken(value: Token): boolean;
+//# sourceMappingURL=token.d.ts.map

package/dist/lib/lexer/token.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"token.d.ts","sourceRoot":"","sources":["../../../src/lib/lexer/token.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,oBAAoB,CAAC;AAEzD,+CAA+C;AAC/C,eAAO,MAAM,cAAc,SAAS,CAAC;AAErC;;GAEG;AACH,MAAM,WAAW,KAAK;IAElB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,QAAQ,EAAE,cAAc,CAAC;CACrC;AAED;;;;;;;GAOG;AACH,wBAAgB,KAAK,CACjB,IAAI,EAAE,MAAM,EACZ,IAAI,EAAE,MAAM,EACZ,MAAM,EAAE,MAAM,GACf,KAAK,CAUP;AAED;;;;;GAKG;AACH,wBAAgB,QAAQ,CAAC,MAAM,EAAE,MAAM,GAAG,KAAK,CAG9C;AAED;;;;GAIG;AACH,wBAAgB,UAAU,CAAC,KAAK,EAAE,KAAK,GAAG,OAAO,CAGhD"}

package/dist/lib/lexer/token.js

@@ -0,0 +1,38 @@
+/** Token name emitted once at end of input. */
+export const EOF_TOKEN_NAME = '$eof';
+/**
+ * Builds a token value from a rule name, matched text, and source offset.
+ *
+ * @param name - Token rule name from the grammar `tokens` section.
+ * @param text - Matched lexeme text.
+ * @param offset - Start offset of the lexeme in the source.
+ * @returns A token record with a source span.
+ */
+export function token(name, text, offset) {
+    return {
+        name,
+        text,
+        location: {
+            offset,
+            length: text.length,
+        },
+    };
+}
+/**
+ * Builds the end-of-input token at a source offset.
+ *
+ * @param offset - Source offset where input ended.
+ * @returns An empty `$eof` token.
+ */
+export function eofToken(offset) {
+    return token(EOF_TOKEN_NAME, '', offset);
+}
+/**
+ * Returns whether a token is the end-of-input marker.
+ *
+ * @param value - Token to test.
+ */
+export function isEofToken(value) {
+    return value.name === EOF_TOKEN_NAME;
+}
+//# sourceMappingURL=token.js.map

package/dist/lib/lexer/token.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"token.js","sourceRoot":"","sources":["../../../src/lib/lexer/token.ts"],"names":[],"mappings":"AAEA,+CAA+C;AAC/C,MAAM,CAAC,MAAM,cAAc,GAAG,MAAM,CAAC;AAYrC;;;;;;;GAOG;AACH,MAAM,UAAU,KAAK,CACjB,IAAY,EACZ,IAAY,EACZ,MAAc;IAGd,OAAO;QACH,IAAI;QACJ,IAAI;QACJ,QAAQ,EAAE;YACN,MAAM;YACN,MAAM,EAAE,IAAI,CAAC,MAAM;SACtB;KACJ,CAAC;AACN,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,QAAQ,CAAC,MAAc;IAEnC,OAAO,KAAK,CAAC,cAAc,EAAE,EAAE,EAAE,MAAM,CAAC,CAAC;AAC7C,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,UAAU,CAAC,KAAY;IAEnC,OAAO,KAAK,CAAC,IAAI,KAAK,cAAc,CAAC;AACzC,CAAC"}

package/dist/lib/parse-context-error.d.ts

@@ -0,0 +1,13 @@
+import { ParserLrError } from './errors/parser-lr-error.js';
+/**
+ * Thrown when a parse context cannot be constructed from supplied sources.
+ */
+export declare class ParseContextError extends ParserLrError {
+    /**
+     * Creates a parse context configuration error.
+     *
+     * @param message - Human-readable failure description.
+     */
+    constructor(message: string);
+}
+//# sourceMappingURL=parse-context-error.d.ts.map

package/dist/lib/parse-context-error.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"parse-context-error.d.ts","sourceRoot":"","sources":["../../src/lib/parse-context-error.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAC;AAE5D;;GAEG;AACH,qBAAa,iBAAkB,SAAQ,aAAa;IAEhD;;;;OAIG;gBACgB,OAAO,EAAE,MAAM;CAIrC"}

package/dist/lib/parse-context-error.js

@@ -0,0 +1,15 @@
+import { ParserLrError } from './errors/parser-lr-error.js';
+/**
+ * Thrown when a parse context cannot be constructed from supplied sources.
+ */
+export class ParseContextError extends ParserLrError {
+    /**
+     * Creates a parse context configuration error.
+     *
+     * @param message - Human-readable failure description.
+     */
+    constructor(message) {
+        super(message);
+    }
+}
+//# sourceMappingURL=parse-context-error.js.map

package/dist/lib/parse-context-error.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"parse-context-error.js","sourceRoot":"","sources":["../../src/lib/parse-context-error.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAC;AAE5D;;GAEG;AACH,MAAM,OAAO,iBAAkB,SAAQ,aAAa;IAEhD;;;;OAIG;IACH,YAAmB,OAAe;QAE9B,KAAK,CAAC,OAAO,CAAC,CAAC;IACnB,CAAC;CACJ"}

package/dist/lib/parse-context.d.ts

@@ -0,0 +1,106 @@
+import type { AstNode } from './ast/ast-node.js';
+import type { Lexer } from './lexer/lexer.js';
+import type { Token } from './lexer/token.js';
+import type { LrAlgorithm } from './parse-table/lr-algorithm.js';
+import { ParseTable } from './parse-table/parse-table.js';
+import { ParserLr } from './parser-lr.js';
+/**
+ * Parser and parse table loaded from a grammar or serialized table.
+ */
+export declare class ParseContext {
+    readonly parser: ParserLr;
+    readonly table: ParseTable;
+    /**
+     * Creates a parse context from a parser and its table.
+     *
+     * @param parser - Shift-reduce parser instance.
+     * @param table - Parse table backing the parser.
+     */
+    constructor(parser: ParserLr, table: ParseTable);
+    /**
+     * Builds a parse context from grammar file text.
+     *
+     * @param source - Full `.grammar` file contents.
+     * @param algorithm - LR algorithm used to build the table.
+     * @returns Parser and parse table ready for lexing or parsing.
+     */
+    static fromGrammar(source: string, algorithm?: LrAlgorithm): ParseContext;
+    /**
+     * Builds a parse context from serialized parse table JSON.
+     *
+     * @param json - Serialized parse table JSON.
+     * @returns Parser and parse table ready for lexing or parsing.
+     */
+    static fromTableJson(json: string): ParseContext;
+    /**
+     * Builds a parse context from a grammar or table source string.
+     *
+     * @param options - Grammar source, table JSON, and optional algorithm.
+     * @returns Parser and parse table ready for lexing or parsing.
+     */
+    static fromSources(options: ParseContextSources): ParseContext;
+    /**
+     * Creates a stream lexer for this context's grammar.
+     *
+     * @returns A fresh stream lexer instance.
+     */
+    createLexer(): Lexer;
+    /**
+     * Lexes source text using this context's parser.
+     *
+     * @param source - Input text to tokenize.
+     * @returns Matched tokens in source order, ending with `$eof`.
+     */
+    lex(source: string): readonly Token[];
+    /**
+     * Lexes synchronous source chunks into a token stream ending with `$eof`.
+     *
+     * @param chunks - Source text fragments in order.
+     * @returns Token iterator including `$eof`.
+     */
+    lexChunks(chunks: Iterable<string>): IterableIterator<Token>;
+    /**
+     * Lexes asynchronous source chunks into a token stream ending with `$eof`.
+     *
+     * @param chunks - Source text fragments in order.
+     * @returns Async token iterator including `$eof`.
+     */
+    lexChunksAsync(chunks: AsyncIterable<string>): AsyncIterableIterator<Token>;
+    /**
+     * Collects all tokens from a synchronous chunk stream.
+     *
+     * @param chunks - Source text fragments in order.
+     * @returns Matched tokens including `$eof`.
+     */
+    lexChunkStream(chunks: Iterable<string>): readonly Token[];
+    /**
+     * Collects all tokens from an asynchronous chunk stream.
+     *
+     * @param chunks - Source text fragments in order.
+     * @returns Matched tokens including `$eof`.
+     */
+    lexChunkStreamAsync(chunks: AsyncIterable<string>): Promise<readonly Token[]>;
+    /**
+     * Parses a token stream into a concrete syntax tree.
+     *
+     * @param tokens - Token stream ending with `$eof`.
+     * @returns Parse tree rooted at the grammar start symbol, or null on syntax error.
+     */
+    parse(tokens: readonly Token[]): AstNode | null;
+    /**
+     * Lexes and parses source text into a concrete syntax tree.
+     *
+     * @param source - Input text to parse.
+     * @returns Parse tree rooted at the grammar start symbol, or null on syntax error.
+     */
+    parseSource(source: string): AstNode | null;
+}
+/**
+ * In-memory sources for constructing a {@link ParseContext}.
+ */
+export interface ParseContextSources {
+    readonly grammarSource?: string;
+    readonly tableJson?: string;
+    readonly algorithm?: string;
+}
+//# sourceMappingURL=parse-context.d.ts.map

package/dist/lib/parse-context.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"parse-context.d.ts","sourceRoot":"","sources":["../../src/lib/parse-context.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,mBAAmB,CAAC;AAGjD,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,+BAA+B,CAAC;AAEjE,OAAO,EAAE,UAAU,EAAE,MAAM,8BAA8B,CAAC;AAC1D,OAAO,EAAE,QAAQ,EAAE,MAAM,gBAAgB,CAAC;AAE1C;;GAEG;AACH,qBAAa,YAAY;aASD,MAAM,EAAE,QAAQ;aAChB,KAAK,EAAE,UAAU;IARrC;;;;;OAKG;gBAEiB,MAAM,EAAE,QAAQ,EAChB,KAAK,EAAE,UAAU;IAKrC;;;;;;OAMG;WACW,WAAW,CACrB,MAAM,EAAE,MAAM,EACd,SAAS,GAAE,WAAmB,GAC/B,YAAY;IASf;;;;;OAKG;WACW,aAAa,CAAC,IAAI,EAAE,MAAM,GAAG,YAAY;IAOvD;;;;;OAKG;WACW,WAAW,CAAC,OAAO,EAAE,mBAAmB,GAAG,YAAY;IAmBrE;;;;OAIG;IACI,WAAW,IAAI,KAAK;IAK3B;;;;;OAKG;IACI,GAAG,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,KAAK,EAAE;IAK5C;;;;;OAKG;IACI,SAAS,CAAC,MAAM,EAAE,QAAQ,CAAC,MAAM,CAAC,GAAG,gBAAgB,CAAC,KAAK,CAAC;IAKnE;;;;;OAKG;IACI,cAAc,CAAC,MAAM,EAAE,aAAa,CAAC,MAAM,CAAC,GAAG,qBAAqB,CAAC,KAAK,CAAC;IAKlF;;;;;OAKG;IACI,cAAc,CAAC,MAAM,EAAE,QAAQ,CAAC,MAAM,CAAC,GAAG,SAAS,KAAK,EAAE;IAKjE;;;;;OAKG;IACU,mBAAmB,CAAC,MAAM,EAAE,aAAa,CAAC,MAAM,CAAC,GAAG,OAAO,CAAC,SAAS,KAAK,EAAE,CAAC;IAK1F;;;;;OAKG;IACI,KAAK,CAAC,MAAM,EAAE,SAAS,KAAK,EAAE,GAAG,OAAO,GAAG,IAAI;IAKtD;;;;;OAKG;IACI,WAAW,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,GAAG,IAAI;CAIrD;AAED;;GAEG;AACH,MAAM,WAAW,mBAAmB;IAEhC,QAAQ,CAAC,aAAa,CAAC,EAAE,MAAM,CAAC;IAChC,QAAQ,CAAC,SAAS,CAAC,EAAE,MAAM,CAAC;IAC5B,QAAQ,CAAC,SAAS,CAAC,EAAE,MAAM,CAAC;CAC/B"}

package/dist/lib/parse-context.js

@@ -0,0 +1,133 @@
+import { ParseContextError } from './parse-context-error.js';
+import { readGrammar } from './grammar/read-grammar.js';
+import { parseLrAlgorithm } from './parse-table/lr-algorithm.js';
+import { ParseTable } from './parse-table/parse-table.js';
+import { ParserLr } from './parser-lr.js';
+/**
+ * Parser and parse table loaded from a grammar or serialized table.
+ */
+export class ParseContext {
+    parser;
+    table;
+    /**
+     * Creates a parse context from a parser and its table.
+     *
+     * @param parser - Shift-reduce parser instance.
+     * @param table - Parse table backing the parser.
+     */
+    constructor(parser, table) {
+        this.parser = parser;
+        this.table = table;
+    }
+    /**
+     * Builds a parse context from grammar file text.
+     *
+     * @param source - Full `.grammar` file contents.
+     * @param algorithm - LR algorithm used to build the table.
+     * @returns Parser and parse table ready for lexing or parsing.
+     */
+    static fromGrammar(source, algorithm = 'lr1') {
+        const grammar = readGrammar(source);
+        const table = ParseTable.fromGrammar(grammar, algorithm);
+        const parser = new ParserLr(grammar, table);
+        return new ParseContext(parser, table);
+    }
+    /**
+     * Builds a parse context from serialized parse table JSON.
+     *
+     * @param json - Serialized parse table JSON.
+     * @returns Parser and parse table ready for lexing or parsing.
+     */
+    static fromTableJson(json) {
+        const table = ParseTable.fromJsonString(json);
+        return new ParseContext(ParserLr.fromParseTable(table), table);
+    }
+    /**
+     * Builds a parse context from a grammar or table source string.
+     *
+     * @param options - Grammar source, table JSON, and optional algorithm.
+     * @returns Parser and parse table ready for lexing or parsing.
+     */
+    static fromSources(options) {
+        // Prefer grammar source over a saved table when both are supplied.
+        if (options.grammarSource !== undefined) {
+            return ParseContext.fromGrammar(options.grammarSource, parseLrAlgorithm(options.algorithm));
+        }
+        if (options.tableJson !== undefined) {
+            return ParseContext.fromTableJson(options.tableJson);
+        }
+        throw new ParseContextError('required: grammar source or table JSON');
+    }
+    /**
+     * Creates a stream lexer for this context's grammar.
+     *
+     * @returns A fresh stream lexer instance.
+     */
+    createLexer() {
+        return this.parser.createLexer();
+    }
+    /**
+     * Lexes source text using this context's parser.
+     *
+     * @param source - Input text to tokenize.
+     * @returns Matched tokens in source order, ending with `$eof`.
+     */
+    lex(source) {
+        return this.parser.lex(source);
+    }
+    /**
+     * Lexes synchronous source chunks into a token stream ending with `$eof`.
+     *
+     * @param chunks - Source text fragments in order.
+     * @returns Token iterator including `$eof`.
+     */
+    lexChunks(chunks) {
+        return this.parser.lexChunks(chunks);
+    }
+    /**
+     * Lexes asynchronous source chunks into a token stream ending with `$eof`.
+     *
+     * @param chunks - Source text fragments in order.
+     * @returns Async token iterator including `$eof`.
+     */
+    lexChunksAsync(chunks) {
+        return this.parser.lexChunksAsync(chunks);
+    }
+    /**
+     * Collects all tokens from a synchronous chunk stream.
+     *
+     * @param chunks - Source text fragments in order.
+     * @returns Matched tokens including `$eof`.
+     */
+    lexChunkStream(chunks) {
+        return this.parser.lexChunkStream(chunks);
+    }
+    /**
+     * Collects all tokens from an asynchronous chunk stream.
+     *
+     * @param chunks - Source text fragments in order.
+     * @returns Matched tokens including `$eof`.
+     */
+    async lexChunkStreamAsync(chunks) {
+        return this.parser.lexChunkStreamAsync(chunks);
+    }
+    /**
+     * Parses a token stream into a concrete syntax tree.
+     *
+     * @param tokens - Token stream ending with `$eof`.
+     * @returns Parse tree rooted at the grammar start symbol, or null on syntax error.
+     */
+    parse(tokens) {
+        return this.parser.parse(tokens);
+    }
+    /**
+     * Lexes and parses source text into a concrete syntax tree.
+     *
+     * @param source - Input text to parse.
+     * @returns Parse tree rooted at the grammar start symbol, or null on syntax error.
+     */
+    parseSource(source) {
+        return this.parser.parseSource(source);
+    }
+}
+//# sourceMappingURL=parse-context.js.map

package/dist/lib/parse-context.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"parse-context.js","sourceRoot":"","sources":["../../src/lib/parse-context.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAC;AAC7D,OAAO,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAC;AAIxD,OAAO,EAAE,gBAAgB,EAAE,MAAM,+BAA+B,CAAC;AACjE,OAAO,EAAE,UAAU,EAAE,MAAM,8BAA8B,CAAC;AAC1D,OAAO,EAAE,QAAQ,EAAE,MAAM,gBAAgB,CAAC;AAE1C;;GAEG;AACH,MAAM,OAAO,YAAY;IASD;IACA;IARpB;;;;;OAKG;IACH,YACoB,MAAgB,EAChB,KAAiB;QADjB,WAAM,GAAN,MAAM,CAAU;QAChB,UAAK,GAAL,KAAK,CAAY;IAGrC,CAAC;IAED;;;;;;OAMG;IACI,MAAM,CAAC,WAAW,CACrB,MAAc,EACd,YAAyB,KAAK;QAG9B,MAAM,OAAO,GAAG,WAAW,CAAC,MAAM,CAAC,CAAC;QACpC,MAAM,KAAK,GAAG,UAAU,CAAC,WAAW,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC;QACzD,MAAM,MAAM,GAAG,IAAI,QAAQ,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC;QAE5C,OAAO,IAAI,YAAY,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;IAC3C,CAAC;IAED;;;;;OAKG;IACI,MAAM,CAAC,aAAa,CAAC,IAAY;QAEpC,MAAM,KAAK,GAAG,UAAU,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC;QAE9C,OAAO,IAAI,YAAY,CAAC,QAAQ,CAAC,cAAc,CAAC,KAAK,CAAC,EAAE,KAAK,CAAC,CAAC;IACnE,CAAC;IAED;;;;;OAKG;IACI,MAAM,CAAC,WAAW,CAAC,OAA4B;QAElD,mEAAmE;QACnE,IAAI,OAAO,CAAC,aAAa,KAAK,SAAS,EACvC,CAAC;YACG,OAAO,YAAY,CAAC,WAAW,CAC3B,OAAO,CAAC,aAAa,EACrB,gBAAgB,CAAC,OAAO,CAAC,SAAS,CAAC,CACtC,CAAC;QACN,CAAC;QAED,IAAI,OAAO,CAAC,SAAS,KAAK,SAAS,EACnC,CAAC;YACG,OAAO,YAAY,CAAC,aAAa,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;QACzD,CAAC;QAED,MAAM,IAAI,iBAAiB,CAAC,wCAAwC,CAAC,CAAC;IAC1E,CAAC;IAED;;;;OAIG;IACI,WAAW;QAEd,OAAO,IAAI,CAAC,MAAM,CAAC,WAAW,EAAE,CAAC;IACrC,CAAC;IAED;;;;;OAKG;IACI,GAAG,CAAC,MAAc;QAErB,OAAO,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC;IACnC,CAAC;IAED;;;;;OAKG;IACI,SAAS,CAAC,MAAwB;QAErC,OAAO,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC;IACzC,CAAC;IAED;;;;;OAKG;IACI,cAAc,CAAC,MAA6B;QAE/C,OAAO,IAAI,CAAC,MAAM,CAAC,cAAc,CAAC,MAAM,CAAC,CAAC;IAC9C,CAAC;IAED;;;;;OAKG;IACI,cAAc,CAAC,MAAwB;QAE1C,OAAO,IAAI,CAAC,MAAM,CAAC,cAAc,CAAC,MAAM,CAAC,CAAC;IAC9C,CAAC;IAED;;;;;OAKG;IACI,KAAK,CAAC,mBAAmB,CAAC,MAA6B;QAE1D,OAAO,IAAI,CAAC,MAAM,CAAC,mBAAmB,CAAC,MAAM,CAAC,CAAC;IACnD,CAAC;IAED;;;;;OAKG;IACI,KAAK,CAAC,MAAwB;QAEjC,OAAO,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;IACrC,CAAC;IAED;;;;;OAKG;IACI,WAAW,CAAC,MAAc;QAE7B,OAAO,IAAI,CAAC,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,CAAC;IAC3C,CAAC;CACJ"}

package/dist/lib/parse-output-error.d.ts

@@ -0,0 +1,13 @@
+import { ParserLrError } from './errors/parser-lr-error.js';
+/**
+ * Thrown when parse output cannot be formatted for a requested interchange format.
+ */
+export declare class ParseOutputError extends ParserLrError {
+    /**
+     * Creates a parse output formatting error.
+     *
+     * @param format - Requested output format name.
+     */
+    constructor(format: string);
+}
+//# sourceMappingURL=parse-output-error.d.ts.map

package/dist/lib/parse-output-error.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"parse-output-error.d.ts","sourceRoot":"","sources":["../../src/lib/parse-output-error.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAC;AAE5D;;GAEG;AACH,qBAAa,gBAAiB,SAAQ,aAAa;IAE/C;;;;OAIG;gBACgB,MAAM,EAAE,MAAM;CAIpC"}