@guojc1/sql-formatter-compact 1.0.0

package/dist/cjs/lexer/TokenizerEngine.d.ts

@@ -0,0 +1,31 @@
+import { Token, TokenType } from './token.js';
+export interface RegExpLike {
+    lastIndex: number;
+    exec(input: string): string[] | null;
+}
+export interface TokenRule {
+    type: TokenType;
+    regex: RegExpLike;
+    text?: (rawText: string) => string;
+    key?: (rawText: string) => string;
+}
+export default class TokenizerEngine {
+    private rules;
+    private dialectName;
+    private input;
+    private index;
+    constructor(rules: TokenRule[], dialectName: string);
+    /**
+     * Takes a SQL string and breaks it into tokens.
+     * Each token is an object with type and value.
+     *
+     * @param {string} input - The SQL string
+     * @returns {Token[]} output token stream
+     */
+    tokenize(input: string): Token[];
+    private createParseError;
+    private dialectInfo;
+    private getWhitespace;
+    private getNextToken;
+    private match;
+}

package/dist/cjs/lexer/TokenizerEngine.js

@@ -0,0 +1,95 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+const lineColFromIndex_js_1 = require("./lineColFromIndex.js");
+const regexUtil_js_1 = require("./regexUtil.js");
+class TokenizerEngine {
+    constructor(rules, dialectName) {
+        this.rules = rules;
+        this.dialectName = dialectName;
+        this.input = ''; // The input SQL string to process
+        this.index = 0; // Current position in string
+    }
+    /**
+     * Takes a SQL string and breaks it into tokens.
+     * Each token is an object with type and value.
+     *
+     * @param {string} input - The SQL string
+     * @returns {Token[]} output token stream
+     */
+    tokenize(input) {
+        this.input = input;
+        this.index = 0;
+        const tokens = [];
+        let token;
+        // Keep processing the string until end is reached
+        while (this.index < this.input.length) {
+            // skip any preceding whitespace
+            const precedingWhitespace = this.getWhitespace();
+            if (this.index < this.input.length) {
+                // Get the next token and the token type
+                token = this.getNextToken();
+                if (!token) {
+                    throw this.createParseError();
+                }
+                tokens.push(Object.assign(Object.assign({}, token), { precedingWhitespace }));
+            }
+        }
+        return tokens;
+    }
+    createParseError() {
+        const text = this.input.slice(this.index, this.index + 10);
+        const { line, col } = (0, lineColFromIndex_js_1.lineColFromIndex)(this.input, this.index);
+        return new Error(`Parse error: Unexpected "${text}" at line ${line} column ${col}.\n${this.dialectInfo()}`);
+    }
+    dialectInfo() {
+        if (this.dialectName === 'sql') {
+            return (`This likely happens because you're using the default "sql" dialect.\n` +
+                `If possible, please select a more specific dialect (like sqlite, postgresql, etc).`);
+        }
+        else {
+            return `SQL dialect used: "${this.dialectName}".`;
+        }
+    }
+    getWhitespace() {
+        regexUtil_js_1.WHITESPACE_REGEX.lastIndex = this.index;
+        const matches = regexUtil_js_1.WHITESPACE_REGEX.exec(this.input);
+        if (matches) {
+            // Advance current position by matched whitespace length
+            this.index += matches[0].length;
+            return matches[0];
+        }
+        return undefined;
+    }
+    getNextToken() {
+        for (const rule of this.rules) {
+            const token = this.match(rule);
+            if (token) {
+                return token;
+            }
+        }
+        return undefined;
+    }
+    // Attempts to match token rule regex at current position in input
+    match(rule) {
+        rule.regex.lastIndex = this.index;
+        const matches = rule.regex.exec(this.input);
+        if (matches) {
+            const matchedText = matches[0];
+            const token = {
+                type: rule.type,
+                raw: matchedText,
+                text: rule.text ? rule.text(matchedText) : matchedText,
+                start: this.index,
+            };
+            if (rule.key) {
+                token.key = rule.key(matchedText);
+            }
+            // Advance current position by matched token length
+            this.index += matchedText.length;
+            return token;
+        }
+        return undefined;
+    }
+}
+exports.default = TokenizerEngine;
+//# sourceMappingURL=TokenizerEngine.js.map

package/dist/cjs/lexer/TokenizerEngine.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"TokenizerEngine.js","sourceRoot":"","sources":["../../../src/lexer/TokenizerEngine.ts"],"names":[],"mappings":";;AACA,+DAAyD;AACzD,iDAAkD;AAkBlD,MAAqB,eAAe;IAIlC,YAAoB,KAAkB,EAAU,WAAmB;QAA/C,UAAK,GAAL,KAAK,CAAa;QAAU,gBAAW,GAAX,WAAW,CAAQ;QAH3D,UAAK,GAAG,EAAE,CAAC,CAAC,kCAAkC;QAC9C,UAAK,GAAG,CAAC,CAAC,CAAC,6BAA6B;IAEsB,CAAC;IAEvE;;;;;;OAMG;IACI,QAAQ,CAAC,KAAa;QAC3B,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC;QACnB,IAAI,CAAC,KAAK,GAAG,CAAC,CAAC;QACf,MAAM,MAAM,GAAY,EAAE,CAAC;QAC3B,IAAI,KAAwB,CAAC;QAE7B,kDAAkD;QAClD,OAAO,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE;YACrC,gCAAgC;YAChC,MAAM,mBAAmB,GAAG,IAAI,CAAC,aAAa,EAAE,CAAC;YAEjD,IAAI,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE;gBAClC,wCAAwC;gBACxC,KAAK,GAAG,IAAI,CAAC,YAAY,EAAE,CAAC;gBAC5B,IAAI,CAAC,KAAK,EAAE;oBACV,MAAM,IAAI,CAAC,gBAAgB,EAAE,CAAC;iBAC/B;gBAED,MAAM,CAAC,IAAI,iCAAM,KAAK,KAAE,mBAAmB,IAAG,CAAC;aAChD;SACF;QACD,OAAO,MAAM,CAAC;IAChB,CAAC;IAEO,gBAAgB;QACtB,MAAM,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,EAAE,IAAI,CAAC,KAAK,GAAG,EAAE,CAAC,CAAC;QAC3D,MAAM,EAAE,IAAI,EAAE,GAAG,EAAE,GAAG,IAAA,sCAAgB,EAAC,IAAI,CAAC,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC;QAC/D,OAAO,IAAI,KAAK,CACd,4BAA4B,IAAI,aAAa,IAAI,WAAW,GAAG,MAAM,IAAI,CAAC,WAAW,EAAE,EAAE,CAC1F,CAAC;IACJ,CAAC;IAEO,WAAW;QACjB,IAAI,IAAI,CAAC,WAAW,KAAK,KAAK,EAAE;YAC9B,OAAO,CACL,uEAAuE;gBACvE,oFAAoF,CACrF,CAAC;SACH;aAAM;YACL,OAAO,sBAAsB,IAAI,CAAC,WAAW,IAAI,CAAC;SACnD;IACH,CAAC;IAEO,aAAa;QACnB,+BAAgB,CAAC,SAAS,GAAG,IAAI,CAAC,KAAK,CAAC;QAExC,MAAM,OAAO,GAAG,+BAAgB,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAClD,IAAI,OAAO,EAAE;YACX,wDAAwD;YACxD,IAAI,CAAC,KAAK,IAAI,OAAO,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;YAChC,OAAO,OAAO,CAAC,CAAC,CAAC,CAAC;SACnB;QACD,OAAO,SAAS,CAAC;IACnB,CAAC;IAEO,YAAY;QAClB,KAAK,MAAM,IAAI,IAAI,IAAI,CAAC,KAAK,EAAE;YAC7B,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;YAC/B,IAAI,KAAK,EAAE;gBACT,OAAO,KAAK,CAAC;aACd;SACF;QACD,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,kEAAkE;IAC1D,KAAK,CAAC,IAAe;QAC3B,IAAI,CAAC,KAAK,CAAC,SAAS,GAAG,IAAI,CAAC,KAAK,CAAC;QAClC,MAAM,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAC5C,IAAI,OAAO,EAAE;YACX,MAAM,WAAW,GAAG,OAAO,CAAC,CAAC,CAAC,CAAC;YAE/B,MAAM,KAAK,GAAU;gBACnB,IAAI,EAAE,IAAI,CAAC,IAAI;gBACf,GAAG,EAAE,WAAW;gBAChB,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,WAAW;gBACtD,KAAK,EAAE,IAAI,CAAC,KAAK;aAClB,CAAC;YAEF,IAAI,IAAI,CAAC,GAAG,EAAE;gBACZ,KAAK,CAAC,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC;aACnC;YAED,mDAAmD;YACnD,IAAI,CAAC,KAAK,IAAI,WAAW,CAAC,MAAM,CAAC;YACjC,OAAO,KAAK,CAAC;SACd;QACD,OAAO,SAAS,CAAC;IACnB,CAAC;CACF;AAtGD,kCAsGC"}

package/dist/cjs/lexer/TokenizerOptions.d.ts

@@ -0,0 +1,56 @@
+import { quotePatterns } from './regexFactory.js';
+import { Token } from './token.js';
+export interface IdentChars {
+    first?: string;
+    rest?: string;
+    dashes?: boolean;
+    allowFirstCharNumber?: boolean;
+}
+export type PlainQuoteType = keyof typeof quotePatterns;
+export interface PrefixedQuoteType {
+    quote: PlainQuoteType;
+    prefixes: string[];
+    requirePrefix?: boolean;
+}
+export interface RegexPattern {
+    regex: string;
+}
+export type QuoteType = PlainQuoteType | PrefixedQuoteType | RegexPattern;
+export type VariableType = RegexPattern | PrefixedQuoteType;
+export interface ParamTypes {
+    positional?: boolean;
+    numbered?: ('?' | ':' | '$')[];
+    named?: (':' | '@' | '$')[];
+    quoted?: (':' | '@' | '$')[];
+    custom?: CustomParameter[];
+}
+export interface CustomParameter {
+    regex: string;
+    key?: (text: string) => string;
+}
+export interface TokenizerOptions {
+    reservedSelect: string[];
+    reservedClauses: string[];
+    supportsXor?: boolean;
+    reservedSetOperations: string[];
+    reservedJoins: string[];
+    reservedKeywordPhrases?: string[];
+    reservedDataTypePhrases?: string[];
+    reservedFunctionNames: string[];
+    reservedDataTypes: string[];
+    reservedKeywords: string[];
+    stringTypes: QuoteType[];
+    identTypes: QuoteType[];
+    variableTypes?: VariableType[];
+    extraParens?: ('[]' | '{}')[];
+    paramTypes?: ParamTypes;
+    lineCommentTypes?: string[];
+    nestedBlockComments?: boolean;
+    identChars?: IdentChars;
+    paramChars?: IdentChars;
+    operators?: string[];
+    propertyAccessOperators?: string[];
+    operatorKeyword?: boolean;
+    underscoresInNumbers?: boolean;
+    postProcess?: (tokens: Token[]) => Token[];
+}

package/dist/cjs/lexer/TokenizerOptions.js

@@ -0,0 +1,3 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+//# sourceMappingURL=TokenizerOptions.js.map

package/dist/cjs/lexer/TokenizerOptions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"TokenizerOptions.js","sourceRoot":"","sources":["../../../src/lexer/TokenizerOptions.ts"],"names":[],"mappings":""}

package/dist/cjs/lexer/disambiguateTokens.d.ts

@@ -0,0 +1,18 @@
+import { Token } from './token.js';
+/**
+ * Ensures that no keyword token (RESERVED_*) is preceded or followed by a dot (.)
+ * or any other property-access operator.
+ *
+ * Ensures that all RESERVED_FUNCTION_NAME tokens are followed by "(".
+ * If they're not, converts the token to IDENTIFIER.
+ *
+ * Converts RESERVED_DATA_TYPE tokens followed by "(" to RESERVED_PARAMETERIZED_DATA_TYPE.
+ *
+ * When IDENTIFIER or RESERVED_DATA_TYPE token is followed by "["
+ * converts it to ARRAY_IDENTIFIER or ARRAY_KEYWORD accordingly.
+ *
+ * This is needed to avoid ambiguity in parser which expects function names
+ * to always be followed by open-paren, and to distinguish between
+ * array accessor `foo[1]` and array literal `[1, 2, 3]`.
+ */
+export declare function disambiguateTokens(tokens: Token[]): Token[];

package/dist/cjs/lexer/disambiguateTokens.js

@@ -0,0 +1,90 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.disambiguateTokens = void 0;
+const token_js_1 = require("./token.js");
+/**
+ * Ensures that no keyword token (RESERVED_*) is preceded or followed by a dot (.)
+ * or any other property-access operator.
+ *
+ * Ensures that all RESERVED_FUNCTION_NAME tokens are followed by "(".
+ * If they're not, converts the token to IDENTIFIER.
+ *
+ * Converts RESERVED_DATA_TYPE tokens followed by "(" to RESERVED_PARAMETERIZED_DATA_TYPE.
+ *
+ * When IDENTIFIER or RESERVED_DATA_TYPE token is followed by "["
+ * converts it to ARRAY_IDENTIFIER or ARRAY_KEYWORD accordingly.
+ *
+ * This is needed to avoid ambiguity in parser which expects function names
+ * to always be followed by open-paren, and to distinguish between
+ * array accessor `foo[1]` and array literal `[1, 2, 3]`.
+ */
+function disambiguateTokens(tokens) {
+    return tokens
+        .map(propertyNameKeywordToIdent)
+        .map(funcNameToIdent)
+        .map(dataTypeToParameterizedDataType)
+        .map(identToArrayIdent)
+        .map(dataTypeToArrayKeyword);
+}
+exports.disambiguateTokens = disambiguateTokens;
+const propertyNameKeywordToIdent = (token, i, tokens) => {
+    if ((0, token_js_1.isReserved)(token.type)) {
+        const prevToken = prevNonCommentToken(tokens, i);
+        if (prevToken && prevToken.type === token_js_1.TokenType.PROPERTY_ACCESS_OPERATOR) {
+            return Object.assign(Object.assign({}, token), { type: token_js_1.TokenType.IDENTIFIER, text: token.raw });
+        }
+        const nextToken = nextNonCommentToken(tokens, i);
+        if (nextToken && nextToken.type === token_js_1.TokenType.PROPERTY_ACCESS_OPERATOR) {
+            return Object.assign(Object.assign({}, token), { type: token_js_1.TokenType.IDENTIFIER, text: token.raw });
+        }
+    }
+    return token;
+};
+const funcNameToIdent = (token, i, tokens) => {
+    if (token.type === token_js_1.TokenType.RESERVED_FUNCTION_NAME) {
+        const nextToken = nextNonCommentToken(tokens, i);
+        if (!nextToken || !isOpenParen(nextToken)) {
+            return Object.assign(Object.assign({}, token), { type: token_js_1.TokenType.IDENTIFIER, text: token.raw });
+        }
+    }
+    return token;
+};
+const dataTypeToParameterizedDataType = (token, i, tokens) => {
+    if (token.type === token_js_1.TokenType.RESERVED_DATA_TYPE) {
+        const nextToken = nextNonCommentToken(tokens, i);
+        if (nextToken && isOpenParen(nextToken)) {
+            return Object.assign(Object.assign({}, token), { type: token_js_1.TokenType.RESERVED_PARAMETERIZED_DATA_TYPE });
+        }
+    }
+    return token;
+};
+const identToArrayIdent = (token, i, tokens) => {
+    if (token.type === token_js_1.TokenType.IDENTIFIER) {
+        const nextToken = nextNonCommentToken(tokens, i);
+        if (nextToken && isOpenBracket(nextToken)) {
+            return Object.assign(Object.assign({}, token), { type: token_js_1.TokenType.ARRAY_IDENTIFIER });
+        }
+    }
+    return token;
+};
+const dataTypeToArrayKeyword = (token, i, tokens) => {
+    if (token.type === token_js_1.TokenType.RESERVED_DATA_TYPE) {
+        const nextToken = nextNonCommentToken(tokens, i);
+        if (nextToken && isOpenBracket(nextToken)) {
+            return Object.assign(Object.assign({}, token), { type: token_js_1.TokenType.ARRAY_KEYWORD });
+        }
+    }
+    return token;
+};
+const prevNonCommentToken = (tokens, index) => nextNonCommentToken(tokens, index, -1);
+const nextNonCommentToken = (tokens, index, dir = 1) => {
+    let i = 1;
+    while (tokens[index + i * dir] && isComment(tokens[index + i * dir])) {
+        i++;
+    }
+    return tokens[index + i * dir];
+};
+const isOpenParen = (t) => t.type === token_js_1.TokenType.OPEN_PAREN && t.text === '(';
+const isOpenBracket = (t) => t.type === token_js_1.TokenType.OPEN_PAREN && t.text === '[';
+const isComment = (t) => t.type === token_js_1.TokenType.BLOCK_COMMENT || t.type === token_js_1.TokenType.LINE_COMMENT;
+//# sourceMappingURL=disambiguateTokens.js.map

package/dist/cjs/lexer/disambiguateTokens.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"disambiguateTokens.js","sourceRoot":"","sources":["../../../src/lexer/disambiguateTokens.ts"],"names":[],"mappings":";;;AAAA,yCAA0D;AAE1D;;;;;;;;;;;;;;;GAeG;AACH,SAAgB,kBAAkB,CAAC,MAAe;IAChD,OAAO,MAAM;SACV,GAAG,CAAC,0BAA0B,CAAC;SAC/B,GAAG,CAAC,eAAe,CAAC;SACpB,GAAG,CAAC,+BAA+B,CAAC;SACpC,GAAG,CAAC,iBAAiB,CAAC;SACtB,GAAG,CAAC,sBAAsB,CAAC,CAAC;AACjC,CAAC;AAPD,gDAOC;AAED,MAAM,0BAA0B,GAAG,CAAC,KAAY,EAAE,CAAS,EAAE,MAAe,EAAS,EAAE;IACrF,IAAI,IAAA,qBAAU,EAAC,KAAK,CAAC,IAAI,CAAC,EAAE;QAC1B,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,SAAS,IAAI,SAAS,CAAC,IAAI,KAAK,oBAAS,CAAC,wBAAwB,EAAE;YACtE,uCAAY,KAAK,KAAE,IAAI,EAAE,oBAAS,CAAC,UAAU,EAAE,IAAI,EAAE,KAAK,CAAC,GAAG,IAAG;SAClE;QACD,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,SAAS,IAAI,SAAS,CAAC,IAAI,KAAK,oBAAS,CAAC,wBAAwB,EAAE;YACtE,uCAAY,KAAK,KAAE,IAAI,EAAE,oBAAS,CAAC,UAAU,EAAE,IAAI,EAAE,KAAK,CAAC,GAAG,IAAG;SAClE;KACF;IACD,OAAO,KAAK,CAAC;AACf,CAAC,CAAC;AAEF,MAAM,eAAe,GAAG,CAAC,KAAY,EAAE,CAAS,EAAE,MAAe,EAAS,EAAE;IAC1E,IAAI,KAAK,CAAC,IAAI,KAAK,oBAAS,CAAC,sBAAsB,EAAE;QACnD,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,CAAC,SAAS,IAAI,CAAC,WAAW,CAAC,SAAS,CAAC,EAAE;YACzC,uCAAY,KAAK,KAAE,IAAI,EAAE,oBAAS,CAAC,UAAU,EAAE,IAAI,EAAE,KAAK,CAAC,GAAG,IAAG;SAClE;KACF;IACD,OAAO,KAAK,CAAC;AACf,CAAC,CAAC;AAEF,MAAM,+BAA+B,GAAG,CAAC,KAAY,EAAE,CAAS,EAAE,MAAe,EAAS,EAAE;IAC1F,IAAI,KAAK,CAAC,IAAI,KAAK,oBAAS,CAAC,kBAAkB,EAAE;QAC/C,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,SAAS,IAAI,WAAW,CAAC,SAAS,CAAC,EAAE;YACvC,uCAAY,KAAK,KAAE,IAAI,EAAE,oBAAS,CAAC,gCAAgC,IAAG;SACvE;KACF;IACD,OAAO,KAAK,CAAC;AACf,CAAC,CAAC;AAEF,MAAM,iBAAiB,GAAG,CAAC,KAAY,EAAE,CAAS,EAAE,MAAe,EAAS,EAAE;IAC5E,IAAI,KAAK,CAAC,IAAI,KAAK,oBAAS,CAAC,UAAU,EAAE;QACvC,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,SAAS,IAAI,aAAa,CAAC,SAAS,CAAC,EAAE;YACzC,uCAAY,KAAK,KAAE,IAAI,EAAE,oBAAS,CAAC,gBAAgB,IAAG;SACvD;KACF;IACD,OAAO,KAAK,CAAC;AACf,CAAC,CAAC;AAEF,MAAM,sBAAsB,GAAG,CAAC,KAAY,EAAE,CAAS,EAAE,MAAe,EAAS,EAAE;IACjF,IAAI,KAAK,CAAC,IAAI,KAAK,oBAAS,CAAC,kBAAkB,EAAE;QAC/C,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;QACjD,IAAI,SAAS,IAAI,aAAa,CAAC,SAAS,CAAC,EAAE;YACzC,uCAAY,KAAK,KAAE,IAAI,EAAE,oBAAS,CAAC,aAAa,IAAG;SACpD;KACF;IACD,OAAO,KAAK,CAAC;AACf,CAAC,CAAC;AAEF,MAAM,mBAAmB,GAAG,CAAC,MAAe,EAAE,KAAa,EAAqB,EAAE,CAChF,mBAAmB,CAAC,MAAM,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC,CAAC;AAEzC,MAAM,mBAAmB,GAAG,CAC1B,MAAe,EACf,KAAa,EACb,MAAc,CAAC,EACI,EAAE;IACrB,IAAI,CAAC,GAAG,CAAC,CAAC;IACV,OAAO,MAAM,CAAC,KAAK,GAAG,CAAC,GAAG,GAAG,CAAC,IAAI,SAAS,CAAC,MAAM,CAAC,KAAK,GAAG,CAAC,GAAG,GAAG,CAAC,CAAC,EAAE;QACpE,CAAC,EAAE,CAAC;KACL;IACD,OAAO,MAAM,CAAC,KAAK,GAAG,CAAC,GAAG,GAAG,CAAC,CAAC;AACjC,CAAC,CAAC;AAEF,MAAM,WAAW,GAAG,CAAC,CAAQ,EAAW,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,oBAAS,CAAC,UAAU,IAAI,CAAC,CAAC,IAAI,KAAK,GAAG,CAAC;AAE7F,MAAM,aAAa,GAAG,CAAC,CAAQ,EAAW,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,oBAAS,CAAC,UAAU,IAAI,CAAC,CAAC,IAAI,KAAK,GAAG,CAAC;AAE/F,MAAM,SAAS,GAAG,CAAC,CAAQ,EAAW,EAAE,CACtC,CAAC,CAAC,IAAI,KAAK,oBAAS,CAAC,aAAa,IAAI,CAAC,CAAC,IAAI,KAAK,oBAAS,CAAC,YAAY,CAAC"}

package/dist/cjs/lexer/lineColFromIndex.d.ts

@@ -0,0 +1,8 @@
+/**
+ * Determines line and column number of character index in source code.
+ */
+export declare function lineColFromIndex(source: string, index: number): LineCol;
+export interface LineCol {
+    line: number;
+    col: number;
+}

package/dist/cjs/lexer/lineColFromIndex.js

@@ -0,0 +1,12 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.lineColFromIndex = void 0;
+/**
+ * Determines line and column number of character index in source code.
+ */
+function lineColFromIndex(source, index) {
+    const lines = source.slice(0, index).split(/\n/);
+    return { line: lines.length, col: lines[lines.length - 1].length + 1 };
+}
+exports.lineColFromIndex = lineColFromIndex;
+//# sourceMappingURL=lineColFromIndex.js.map

package/dist/cjs/lexer/lineColFromIndex.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"lineColFromIndex.js","sourceRoot":"","sources":["../../../src/lexer/lineColFromIndex.ts"],"names":[],"mappings":";;;AAAA;;GAEG;AACH,SAAgB,gBAAgB,CAAC,MAAc,EAAE,KAAa;IAC5D,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IACjD,OAAO,EAAE,IAAI,EAAE,KAAK,CAAC,MAAM,EAAE,GAAG,EAAE,KAAK,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;AACzE,CAAC;AAHD,4CAGC"}

package/dist/cjs/lexer/regexFactory.d.ts

@@ -0,0 +1,55 @@
+import { IdentChars, QuoteType, VariableType } from './TokenizerOptions.js';
+/**
+ * Builds a RegExp for valid line comments in a SQL dialect
+ * @param {string[]} lineCommentTypes - list of character strings that denote line comments
+ */
+export declare const lineComment: (lineCommentTypes: string[]) => RegExp;
+/**
+ * Builds a RegExp for matching either open- or close-parenthesis patterns
+ */
+export declare const parenthesis: (kind: 'open' | 'close', extraParens?: ('[]' | '{}')[]) => RegExp;
+/**
+ * Builds a RegExp containing all operators for a SQL dialect
+ */
+export declare const operator: (operators: string[]) => RegExp;
+/**
+ * Builds a RegExp for all Reserved Keywords in a SQL dialect
+ */
+export declare const reservedWord: (reservedKeywords: string[], identChars?: IdentChars) => RegExp;
+/**
+ * Builds a RegExp for parameter placeholder patterns
+ * @param {string[]} paramTypes - list of strings that denote placeholder types
+ * @param {string} pattern - string that denotes placeholder pattern
+ */
+export declare const parameter: (paramTypes: string[], pattern: string) => RegExp | undefined;
+export declare const quotePatterns: {
+    '``': string;
+    '[]': string;
+    '""-qq': string;
+    '""-bs': string;
+    '""-qq-bs': string;
+    '""-raw': string;
+    "''-qq": string;
+    "''-bs": string;
+    "''-qq-bs": string;
+    "''-raw": string;
+    $$: string;
+    "'''..'''": string;
+    '""".."""': string;
+    '{}': string;
+    "q''": string;
+};
+/** Builds a RegExp for matching variables */
+export declare const variable: (varTypes: VariableType[]) => RegExp;
+/** Builds a quote-delimited pattern for matching all given quote types */
+export declare const stringPattern: (quoteTypes: QuoteType[]) => string;
+/** Builds a RegExp for matching quote-delimited patterns */
+export declare const string: (quoteTypes: QuoteType[]) => RegExp;
+/**
+ * Builds a RegExp for valid identifiers in a SQL dialect
+ */
+export declare const identifier: (specialChars?: IdentChars) => RegExp;
+/**
+ * Builds a RegExp string for valid identifiers in a SQL dialect
+ */
+export declare const identifierPattern: ({ first, rest, dashes, allowFirstCharNumber, }?: IdentChars) => string;

package/dist/cjs/lexer/regexFactory.js

@@ -0,0 +1,153 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.identifierPattern = exports.identifier = exports.string = exports.stringPattern = exports.variable = exports.quotePatterns = exports.parameter = exports.reservedWord = exports.operator = exports.parenthesis = exports.lineComment = void 0;
+const utils_js_1 = require("../utils.js");
+const regexUtil_js_1 = require("./regexUtil.js");
+/**
+ * Builds a RegExp for valid line comments in a SQL dialect
+ * @param {string[]} lineCommentTypes - list of character strings that denote line comments
+ */
+const lineComment = (lineCommentTypes) => new RegExp(`(?:${lineCommentTypes.map(regexUtil_js_1.escapeRegExp).join('|')}).*?(?=\r\n|\r|\n|$)`, 'uy');
+exports.lineComment = lineComment;
+/**
+ * Builds a RegExp for matching either open- or close-parenthesis patterns
+ */
+const parenthesis = (kind, extraParens = []) => {
+    const index = kind === 'open' ? 0 : 1;
+    const parens = ['()', ...extraParens].map(pair => pair[index]);
+    return (0, regexUtil_js_1.patternToRegex)(parens.map(regexUtil_js_1.escapeRegExp).join('|'));
+};
+exports.parenthesis = parenthesis;
+/**
+ * Builds a RegExp containing all operators for a SQL dialect
+ */
+const operator = (operators) => (0, regexUtil_js_1.patternToRegex)(`${(0, utils_js_1.sortByLengthDesc)(operators).map(regexUtil_js_1.escapeRegExp).join('|')}`);
+exports.operator = operator;
+// Negative lookahead to avoid matching a keyword that's actually part of identifier,
+// which can happen when identifier allows word-boundary characters inside it.
+//
+// For example "SELECT$ME" should be tokenized as:
+// - ["SELECT$ME"] when $ is allowed inside identifiers
+// - ["SELECT", "$", "ME"] when $ can't be part of identifiers.
+const rejectIdentCharsPattern = ({ rest, dashes }) => rest || dashes ? `(?![${rest || ''}${dashes ? '-' : ''}])` : '';
+/**
+ * Builds a RegExp for all Reserved Keywords in a SQL dialect
+ */
+const reservedWord = (reservedKeywords, identChars = {}) => {
+    if (reservedKeywords.length === 0) {
+        return /^\b$/u;
+    }
+    const avoidIdentChars = rejectIdentCharsPattern(identChars);
+    const reservedKeywordsPattern = (0, utils_js_1.sortByLengthDesc)(reservedKeywords)
+        .map(regexUtil_js_1.escapeRegExp)
+        .join('|')
+        .replace(/ /gu, '\\s+');
+    return new RegExp(`(?:${reservedKeywordsPattern})${avoidIdentChars}\\b`, 'iuy');
+};
+exports.reservedWord = reservedWord;
+/**
+ * Builds a RegExp for parameter placeholder patterns
+ * @param {string[]} paramTypes - list of strings that denote placeholder types
+ * @param {string} pattern - string that denotes placeholder pattern
+ */
+const parameter = (paramTypes, pattern) => {
+    if (!paramTypes.length) {
+        return undefined;
+    }
+    const typesRegex = paramTypes.map(regexUtil_js_1.escapeRegExp).join('|');
+    return (0, regexUtil_js_1.patternToRegex)(`(?:${typesRegex})(?:${pattern})`);
+};
+exports.parameter = parameter;
+const buildQStringPatterns = () => {
+    const specialDelimiterMap = {
+        '<': '>',
+        '[': ']',
+        '(': ')',
+        '{': '}',
+    };
+    // base pattern for special delimiters, left must correspond with right
+    const singlePattern = "{left}(?:(?!{right}').)*?{right}";
+    // replace {left} and {right} with delimiters, collect as array
+    const patternList = Object.entries(specialDelimiterMap).map(([left, right]) => singlePattern.replace(/{left}/g, (0, regexUtil_js_1.escapeRegExp)(left)).replace(/{right}/g, (0, regexUtil_js_1.escapeRegExp)(right)));
+    const specialDelimiters = (0, regexUtil_js_1.escapeRegExp)(Object.keys(specialDelimiterMap).join(''));
+    // standard pattern for common delimiters, ignores special delimiters
+    const standardDelimiterPattern = String.raw `(?<tag>[^\s${specialDelimiters}])(?:(?!\k<tag>').)*?\k<tag>`;
+    // constructs final pattern by joining all cases
+    const qStringPattern = `[Qq]'(?:${standardDelimiterPattern}|${patternList.join('|')})'`;
+    return qStringPattern;
+};
+// Regex patterns for all supported quote styles.
+//
+// Most of them have a single escaping-style built in,
+// but "" and '' support multiple versions of escapes,
+// which must be selected with suffixes: -qq, -bs, -qq-bs, -raw
+exports.quotePatterns = {
+    // - backtick quoted (using `` to escape)
+    '``': '(?:`[^`]*`)+',
+    // - Transact-SQL square bracket quoted (using ]] to escape)
+    '[]': String.raw `(?:\[[^\]]*\])(?:\][^\]]*\])*`,
+    // double-quoted
+    '""-qq': String.raw `(?:"[^"]*")+`,
+    '""-bs': String.raw `(?:"[^"\\]*(?:\\.[^"\\]*)*")`,
+    '""-qq-bs': String.raw `(?:"[^"\\]*(?:\\.[^"\\]*)*")+`,
+    '""-raw': String.raw `(?:"[^"]*")`,
+    // single-quoted
+    "''-qq": String.raw `(?:'[^']*')+`,
+    "''-bs": String.raw `(?:'[^'\\]*(?:\\.[^'\\]*)*')`,
+    "''-qq-bs": String.raw `(?:'[^'\\]*(?:\\.[^'\\]*)*')+`,
+    "''-raw": String.raw `(?:'[^']*')`,
+    // PostgreSQL dollar-quoted
+    '$$': String.raw `(?<tag>\$\w*\$)[\s\S]*?\k<tag>`,
+    // BigQuery '''triple-quoted''' (using \' to escape)
+    "'''..'''": String.raw `'''[^\\]*?(?:\\.[^\\]*?)*?'''`,
+    // BigQuery """triple-quoted""" (using \" to escape)
+    '""".."""': String.raw `"""[^\\]*?(?:\\.[^\\]*?)*?"""`,
+    // Hive and Spark variables: ${name}
+    '{}': String.raw `(?:\{[^\}]*\})`,
+    // Oracle q'' strings: q'<text>' q'|text|' ...
+    "q''": buildQStringPatterns(),
+};
+const singleQuotePattern = (quoteTypes) => {
+    if (typeof quoteTypes === 'string') {
+        return exports.quotePatterns[quoteTypes];
+    }
+    else if ('regex' in quoteTypes) {
+        return quoteTypes.regex;
+    }
+    else {
+        return (0, regexUtil_js_1.prefixesPattern)(quoteTypes) + exports.quotePatterns[quoteTypes.quote];
+    }
+};
+/** Builds a RegExp for matching variables */
+const variable = (varTypes) => (0, regexUtil_js_1.patternToRegex)(varTypes
+    .map(varType => ('regex' in varType ? varType.regex : singleQuotePattern(varType)))
+    .join('|'));
+exports.variable = variable;
+/** Builds a quote-delimited pattern for matching all given quote types */
+const stringPattern = (quoteTypes) => quoteTypes.map(singleQuotePattern).join('|');
+exports.stringPattern = stringPattern;
+/** Builds a RegExp for matching quote-delimited patterns */
+const string = (quoteTypes) => (0, regexUtil_js_1.patternToRegex)((0, exports.stringPattern)(quoteTypes));
+exports.string = string;
+/**
+ * Builds a RegExp for valid identifiers in a SQL dialect
+ */
+const identifier = (specialChars = {}) => (0, regexUtil_js_1.patternToRegex)((0, exports.identifierPattern)(specialChars));
+exports.identifier = identifier;
+/**
+ * Builds a RegExp string for valid identifiers in a SQL dialect
+ */
+const identifierPattern = ({ first, rest, dashes, allowFirstCharNumber, } = {}) => {
+    // Unicode letters, diacritical marks and underscore
+    const letter = '\\p{Alphabetic}\\p{Mark}_';
+    // Numbers 0..9, plus various unicode numbers
+    const number = '\\p{Decimal_Number}';
+    const firstChars = (0, regexUtil_js_1.escapeRegExp)(first !== null && first !== void 0 ? first : '');
+    const restChars = (0, regexUtil_js_1.escapeRegExp)(rest !== null && rest !== void 0 ? rest : '');
+    const pattern = allowFirstCharNumber
+        ? `[${letter}${number}${firstChars}][${letter}${number}${restChars}]*`
+        : `[${letter}${firstChars}][${letter}${number}${restChars}]*`;
+    return dashes ? (0, regexUtil_js_1.withDashes)(pattern) : pattern;
+};
+exports.identifierPattern = identifierPattern;
+//# sourceMappingURL=regexFactory.js.map

package/dist/cjs/lexer/regexFactory.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"regexFactory.js","sourceRoot":"","sources":["../../../src/lexer/regexFactory.ts"],"names":[],"mappings":";;;AAAA,0CAA+C;AAG/C,iDAA2F;AAE3F;;;GAGG;AACI,MAAM,WAAW,GAAG,CAAC,gBAA0B,EAAE,EAAE,CACxD,IAAI,MAAM,CAAC,MAAM,gBAAgB,CAAC,GAAG,CAAC,2BAAY,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,sBAAsB,EAAE,IAAI,CAAC,CAAC;AADhF,QAAA,WAAW,eACqE;AAE7F;;GAEG;AACI,MAAM,WAAW,GAAG,CAAC,IAAsB,EAAE,cAA+B,EAAE,EAAU,EAAE;IAC/F,MAAM,KAAK,GAAG,IAAI,KAAK,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;IACtC,MAAM,MAAM,GAAG,CAAC,IAAI,EAAE,GAAG,WAAW,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC;IAC/D,OAAO,IAAA,6BAAc,EAAC,MAAM,CAAC,GAAG,CAAC,2BAAY,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;AAC5D,CAAC,CAAC;AAJW,QAAA,WAAW,eAItB;AAEF;;GAEG;AACI,MAAM,QAAQ,GAAG,CAAC,SAAmB,EAAE,EAAE,CAC9C,IAAA,6BAAc,EAAC,GAAG,IAAA,2BAAgB,EAAC,SAAS,CAAC,CAAC,GAAG,CAAC,2BAAY,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;AADlE,QAAA,QAAQ,YAC0D;AAE/E,qFAAqF;AACrF,8EAA8E;AAC9E,EAAE;AACF,kDAAkD;AAClD,uDAAuD;AACvD,+DAA+D;AAC/D,MAAM,uBAAuB,GAAG,CAAC,EAAE,IAAI,EAAE,MAAM,EAAc,EAAU,EAAE,CACvE,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,OAAO,IAAI,IAAI,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;AAElE;;GAEG;AACI,MAAM,YAAY,GAAG,CAAC,gBAA0B,EAAE,aAAyB,EAAE,EAAU,EAAE;IAC9F,IAAI,gBAAgB,CAAC,MAAM,KAAK,CAAC,EAAE;QACjC,OAAO,OAAO,CAAC;KAChB;IAED,MAAM,eAAe,GAAG,uBAAuB,CAAC,UAAU,CAAC,CAAC;IAE5D,MAAM,uBAAuB,GAAG,IAAA,2BAAgB,EAAC,gBAAgB,CAAC;SAC/D,GAAG,CAAC,2BAAY,CAAC;SACjB,IAAI,CAAC,GAAG,CAAC;SACT,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;IAE1B,OAAO,IAAI,MAAM,CAAC,MAAM,uBAAuB,IAAI,eAAe,KAAK,EAAE,KAAK,CAAC,CAAC;AAClF,CAAC,CAAC;AAbW,QAAA,YAAY,gBAavB;AAEF;;;;GAIG;AACI,MAAM,SAAS,GAAG,CAAC,UAAoB,EAAE,OAAe,EAAsB,EAAE;IACrF,IAAI,CAAC,UAAU,CAAC,MAAM,EAAE;QACtB,OAAO,SAAS,CAAC;KAClB;IACD,MAAM,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,2BAAY,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IAE1D,OAAO,IAAA,6BAAc,EAAC,MAAM,UAAU,OAAO,OAAO,GAAG,CAAC,CAAC;AAC3D,CAAC,CAAC;AAPW,QAAA,SAAS,aAOpB;AAEF,MAAM,oBAAoB,GAAG,GAAG,EAAE;IAChC,MAAM,mBAAmB,GAAG;QAC1B,GAAG,EAAE,GAAG;QACR,GAAG,EAAE,GAAG;QACR,GAAG,EAAE,GAAG;QACR,GAAG,EAAE,GAAG;KACT,CAAC;IAEF,uEAAuE;IACvE,MAAM,aAAa,GAAG,kCAAkC,CAAC;IAEzD,+DAA+D;IAC/D,MAAM,WAAW,GAAG,MAAM,CAAC,OAAO,CAAC,mBAAmB,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,EAAE,EAAE,CAC5E,aAAa,CAAC,OAAO,CAAC,SAAS,EAAE,IAAA,2BAAY,EAAC,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,UAAU,EAAE,IAAA,2BAAY,EAAC,KAAK,CAAC,CAAC,CAC9F,CAAC;IAEF,MAAM,iBAAiB,GAAG,IAAA,2BAAY,EAAC,MAAM,CAAC,IAAI,CAAC,mBAAmB,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;IAClF,qEAAqE;IACrE,MAAM,wBAAwB,GAAG,MAAM,CAAC,GAAG,CAAA,cAAc,iBAAiB,8BAA8B,CAAC;IAEzG,gDAAgD;IAChD,MAAM,cAAc,GAAG,WAAW,wBAAwB,IAAI,WAAW,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC;IAExF,OAAO,cAAc,CAAC;AACxB,CAAC,CAAC;AAEF,iDAAiD;AACjD,EAAE;AACF,sDAAsD;AACtD,sDAAsD;AACtD,+DAA+D;AAClD,QAAA,aAAa,GAAG;IAC3B,yCAAyC;IACzC,IAAI,EAAE,cAAc;IACpB,4DAA4D;IAC5D,IAAI,EAAE,MAAM,CAAC,GAAG,CAAA,+BAA+B;IAC/C,gBAAgB;IAChB,OAAO,EAAE,MAAM,CAAC,GAAG,CAAA,cAAc;IACjC,OAAO,EAAE,MAAM,CAAC,GAAG,CAAA,8BAA8B;IACjD,UAAU,EAAE,MAAM,CAAC,GAAG,CAAA,+BAA+B;IACrD,QAAQ,EAAE,MAAM,CAAC,GAAG,CAAA,aAAa;IACjC,gBAAgB;IAChB,OAAO,EAAE,MAAM,CAAC,GAAG,CAAA,cAAc;IACjC,OAAO,EAAE,MAAM,CAAC,GAAG,CAAA,8BAA8B;IACjD,UAAU,EAAE,MAAM,CAAC,GAAG,CAAA,+BAA+B;IACrD,QAAQ,EAAE,MAAM,CAAC,GAAG,CAAA,aAAa;IACjC,2BAA2B;IAC3B,IAAI,EAAE,MAAM,CAAC,GAAG,CAAA,gCAAgC;IAChD,oDAAoD;IACpD,UAAU,EAAE,MAAM,CAAC,GAAG,CAAA,+BAA+B;IACrD,oDAAoD;IACpD,UAAU,EAAE,MAAM,CAAC,GAAG,CAAA,+BAA+B;IACrD,oCAAoC;IACpC,IAAI,EAAE,MAAM,CAAC,GAAG,CAAA,gBAAgB;IAChC,8CAA8C;IAC9C,KAAK,EAAE,oBAAoB,EAAE;CAC9B,CAAC;AAEF,MAAM,kBAAkB,GAAG,CAAC,UAAqB,EAAU,EAAE;IAC3D,IAAI,OAAO,UAAU,KAAK,QAAQ,EAAE;QAClC,OAAO,qBAAa,CAAC,UAAU,CAAC,CAAC;KAClC;SAAM,IAAI,OAAO,IAAI,UAAU,EAAE;QAChC,OAAO,UAAU,CAAC,KAAK,CAAC;KACzB;SAAM;QACL,OAAO,IAAA,8BAAe,EAAC,UAAU,CAAC,GAAG,qBAAa,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC;KACtE;AACH,CAAC,CAAC;AAEF,6CAA6C;AACtC,MAAM,QAAQ,GAAG,CAAC,QAAwB,EAAU,EAAE,CAC3D,IAAA,6BAAc,EACZ,QAAQ;KACL,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,OAAO,IAAI,OAAO,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,kBAAkB,CAAC,OAAO,CAAC,CAAC,CAAC;KAClF,IAAI,CAAC,GAAG,CAAC,CACb,CAAC;AALS,QAAA,QAAQ,YAKjB;AAEJ,0EAA0E;AACnE,MAAM,aAAa,GAAG,CAAC,UAAuB,EAAU,EAAE,CAC/D,UAAU,CAAC,GAAG,CAAC,kBAAkB,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AADlC,QAAA,aAAa,iBACqB;AAE/C,4DAA4D;AACrD,MAAM,MAAM,GAAG,CAAC,UAAuB,EAAU,EAAE,CACxD,IAAA,6BAAc,EAAC,IAAA,qBAAa,EAAC,UAAU,CAAC,CAAC,CAAC;AAD/B,QAAA,MAAM,UACyB;AAE5C;;GAEG;AACI,MAAM,UAAU,GAAG,CAAC,eAA2B,EAAE,EAAU,EAAE,CAClE,IAAA,6BAAc,EAAC,IAAA,yBAAiB,EAAC,YAAY,CAAC,CAAC,CAAC;AADrC,QAAA,UAAU,cAC2B;AAElD;;GAEG;AACI,MAAM,iBAAiB,GAAG,CAAC,EAChC,KAAK,EACL,IAAI,EACJ,MAAM,EACN,oBAAoB,MACN,EAAE,EAAU,EAAE;IAC5B,oDAAoD;IACpD,MAAM,MAAM,GAAG,2BAA2B,CAAC;IAC3C,6CAA6C;IAC7C,MAAM,MAAM,GAAG,qBAAqB,CAAC;IAErC,MAAM,UAAU,GAAG,IAAA,2BAAY,EAAC,KAAK,aAAL,KAAK,cAAL,KAAK,GAAI,EAAE,CAAC,CAAC;IAC7C,MAAM,SAAS,GAAG,IAAA,2BAAY,EAAC,IAAI,aAAJ,IAAI,cAAJ,IAAI,GAAI,EAAE,CAAC,CAAC;IAE3C,MAAM,OAAO,GAAG,oBAAoB;QAClC,CAAC,CAAC,IAAI,MAAM,GAAG,MAAM,GAAG,UAAU,KAAK,MAAM,GAAG,MAAM,GAAG,SAAS,IAAI;QACtE,CAAC,CAAC,IAAI,MAAM,GAAG,UAAU,KAAK,MAAM,GAAG,MAAM,GAAG,SAAS,IAAI,CAAC;IAEhE,OAAO,MAAM,CAAC,CAAC,CAAC,IAAA,yBAAU,EAAC,OAAO,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC;AAChD,CAAC,CAAC;AAnBW,QAAA,iBAAiB,qBAmB5B"}

package/dist/cjs/lexer/regexUtil.d.ts

@@ -0,0 +1,7 @@
+import { PrefixedQuoteType } from './TokenizerOptions.js';
+export declare const escapeRegExp: (string: string) => string;
+export declare const WHITESPACE_REGEX: RegExp;
+export declare const patternToRegex: (pattern: string) => RegExp;
+export declare const toCaseInsensitivePattern: (prefix: string) => string;
+export declare const withDashes: (pattern: string) => string;
+export declare const prefixesPattern: ({ prefixes, requirePrefix }: PrefixedQuoteType) => string;

package/dist/cjs/lexer/regexUtil.js

@@ -0,0 +1,21 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.prefixesPattern = exports.withDashes = exports.toCaseInsensitivePattern = exports.patternToRegex = exports.WHITESPACE_REGEX = exports.escapeRegExp = void 0;
+// Escapes regex special chars
+const escapeRegExp = (string) => string.replace(/[.*+?^${}()|[\]\\]/gu, '\\$&');
+exports.escapeRegExp = escapeRegExp;
+exports.WHITESPACE_REGEX = /\s+/uy;
+const patternToRegex = (pattern) => new RegExp(`(?:${pattern})`, 'uy');
+exports.patternToRegex = patternToRegex;
+// Converts "ab" to "[Aa][Bb]"
+const toCaseInsensitivePattern = (prefix) => prefix
+    .split('')
+    .map(char => (/ /gu.test(char) ? '\\s+' : `[${char.toUpperCase()}${char.toLowerCase()}]`))
+    .join('');
+exports.toCaseInsensitivePattern = toCaseInsensitivePattern;
+const withDashes = (pattern) => pattern + '(?:-' + pattern + ')*';
+exports.withDashes = withDashes;
+// Converts ["a", "b"] to "(?:[Aa]|[Bb]|)" or "(?:[Aa]|[Bb])" when required = true
+const prefixesPattern = ({ prefixes, requirePrefix }) => `(?:${prefixes.map(exports.toCaseInsensitivePattern).join('|')}${requirePrefix ? '' : '|'})`;
+exports.prefixesPattern = prefixesPattern;
+//# sourceMappingURL=regexUtil.js.map

package/dist/cjs/lexer/regexUtil.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"regexUtil.js","sourceRoot":"","sources":["../../../src/lexer/regexUtil.ts"],"names":[],"mappings":";;;AAEA,8BAA8B;AACvB,MAAM,YAAY,GAAG,CAAC,MAAc,EAAE,EAAE,CAAC,MAAM,CAAC,OAAO,CAAC,sBAAsB,EAAE,MAAM,CAAC,CAAC;AAAlF,QAAA,YAAY,gBAAsE;AAElF,QAAA,gBAAgB,GAAG,OAAO,CAAC;AAEjC,MAAM,cAAc,GAAG,CAAC,OAAe,EAAU,EAAE,CAAC,IAAI,MAAM,CAAC,MAAM,OAAO,GAAG,EAAE,IAAI,CAAC,CAAC;AAAjF,QAAA,cAAc,kBAAmE;AAE9F,8BAA8B;AACvB,MAAM,wBAAwB,GAAG,CAAC,MAAc,EAAU,EAAE,CACjE,MAAM;KACH,KAAK,CAAC,EAAE,CAAC;KACT,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC,WAAW,EAAE,GAAG,IAAI,CAAC,WAAW,EAAE,GAAG,CAAC,CAAC;KACzF,IAAI,CAAC,EAAE,CAAC,CAAC;AAJD,QAAA,wBAAwB,4BAIvB;AAEP,MAAM,UAAU,GAAG,CAAC,OAAe,EAAU,EAAE,CAAC,OAAO,GAAG,MAAM,GAAG,OAAO,GAAG,IAAI,CAAC;AAA5E,QAAA,UAAU,cAAkE;AAEzF,kFAAkF;AAC3E,MAAM,eAAe,GAAG,CAAC,EAAE,QAAQ,EAAE,aAAa,EAAqB,EAAU,EAAE,CACxF,MAAM,QAAQ,CAAC,GAAG,CAAC,gCAAwB,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,aAAa,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC;AAD1E,QAAA,eAAe,mBAC2D"}