rawsql-ts 0.1.0-beta.1

package/.vs/CopilotSnapshots/C1E2C1A9C1DCFA46B1D5F1C6F36A152D/BC91C0FD38D8694BB992A8DEC1833670/148399016C7971F5592DAADBB9523118

@@ -0,0 +1,120 @@
+import { SqlTokenizer } from "../src/sqlTokenizer";
+
+test('tokenizes integer number', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('123');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('123');
+});
+
+test('tokenizes positive number', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('+123');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('123');
+});
+
+test('tokenizes decimal number', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('123.456');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('123.456');
+});
+
+test('tokenizes number starting with dot', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('.456');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('0.456');
+});
+
+test('tokenizes hexadecimal number', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('0x1A3F');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('0x1A3F');
+});
+
+test('tokenizes exponential notation', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('1.23e+10');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+});
+
+test('tokenizes negative integer number', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('-123');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('-123');
+});
+
+test('tokenizes negative decimal number', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('-123.456');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('-123.456');
+});
+
+test('tokenizes negative number starting with dot', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('-.456');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('-0.456');
+});
+
+test('tokenizes negative exponential notation', () => {
+    // Arrange
+    const tokenizer = new SqlTokenizer('-1.23e+10');
+
+    // Act
+    const tokens = tokenizer.readLexmes();
+
+    // Assert
+    expect(tokens.length).toBe(1);
+    expect(tokens[0].value).toBe('-1.23e+10');
+});

package/.vs/CopilotSnapshots/C1E2C1A9C1DCFA46B1D5F1C6F36A152D/state.mpack

@@ -0,0 +1 @@
+��SessionId��$a9c1e2c1-dcc1-46fa-b1d5-f1c6f36a152d��Id�4Microsoft.VisualStudio.Conversations.Chat.HelpWindow�CorrelationStates���CorrelationId�$fdc091bc-d838-4b69-b992-a8dec1833670�Snapshots�� 148399016C7971F5592DAADBB9523118��SavedFileName١C:\Users\mssgm\Documents\GitHub\ts-sample\.vs\CopilotSnapshots\C1E2C1A9C1DCFA46B1D5F1C6F36A152D\BC91C0FD38D8694BB992A8DEC1833670\148399016C7971F5592DAADBB9523118�OriginalFilePath�?C:\Users\mssgm\Documents\GitHub\ts-sample\tests\literal.test.ts�NewFileMarker�

package/.vs/CopilotSnapshots/C4D8E85893425E4F86F18850F5CA5C08/6C0950E97063C547A72D737E618436B0/1CF9939611B0D194AC81951A171DF046

@@ -0,0 +1,9 @@
+
+
+/*
+以下の記号で始まる文字列は演算子として扱う
+また、以下の記号が続く場合、それらをまとめて演算子として扱う
+        '+', '-', '*', '/', '%', // Arithmetic operators
+        '~', '@', '#', '$', '^', '&', // Special symbols
+        '!', '<', '>', '=', '|', '\\', // Other symbols
+  */

package/.vs/CopilotSnapshots/C4D8E85893425E4F86F18850F5CA5C08/6C0950E97063C547A72D737E618436B0/DFF70C60F68ECD9A4E4C3C74E4CC4DEE

@@ -0,0 +1,84 @@
+import { BaseTokenReader } from './BaseTokenReader';
+import { Lexeme } from '../models/Lexeme';
+
+/**
+ * Manages and coordinates multiple token readers
+ */
+export class TokenReaderManager {
+    private readers: BaseTokenReader[];
+    private input: string;
+    private position: number;
+
+    constructor(input: string, position: number = 0) {
+        this.input = input;
+        this.position = position;
+        this.readers = [];
+    }
+
+    /**
+     * Register a token reader
+     * @param reader The reader to register
+     * @returns This manager instance for chaining
+     */
+    public register(reader: BaseTokenReader): TokenReaderManager {
+        this.readers.push(reader);
+        return this;
+    }
+
+    /**
+     * Register multiple token readers
+     * @param readers The readers to register
+     * @returns This manager instance for chaining
+     */
+    public registerAll(readers: BaseTokenReader[]): TokenReaderManager {
+        readers.forEach(reader => this.register(reader));
+        return this;
+    }
+
+    /**
+     * Update the position for all readers
+     */
+    private setPosition(position: number): void {
+        this.position = position;
+        for (const reader of this.readers) {
+            reader.setPosition(position);
+        }
+    }
+
+    /**
+     * Try to read a token using all registered readers
+     * @param previous The previous token, if any
+     * @returns The lexeme if a reader could read it, null otherwise
+     */
+    public tryRead(position: number, previous: Lexeme | null): Lexeme | null {
+        this.setPosition(position);
+        for (const reader of this.readers) {
+            const lexeme = reader.tryRead(previous);
+            if (lexeme) {
+                return lexeme;
+            }
+        }
+        return null;
+    }
+
+    /**
+     * Get the maximum position among all readers
+     */
+    public getMaxPosition(): number {
+        let maxPosition = this.position;
+        for (const reader of this.readers) {
+            const position = reader.getPosition();
+            if (position > maxPosition) {
+                maxPosition = position;
+            }
+        }
+        return maxPosition;
+    }
+
+    /**
+     * Get the input string
+     */
+    public getInput(): string {
+        return this.input;
+    }
+}

package/.vs/CopilotSnapshots/C4D8E85893425E4F86F18850F5CA5C08/state.mpack

@@ -0,0 +1 @@
+��SessionId��$58e8d8c4-4293-4f5e-86f1-8850f5ca5c08��Id�4Microsoft.VisualStudio.Conversations.Chat.HelpWindow�CorrelationStates���CorrelationId�$e950096c-6370-47c5-a72d-737e618436b0�Snapshots�� DFF70C60F68ECD9A4E4C3C74E4CC4DEE��SavedFileName١C:\Users\mssgm\Documents\GitHub\ts-sample\.vs\CopilotSnapshots\C4D8E85893425E4F86F18850F5CA5C08\6C0950E97063C547A72D737E618436B0\DFF70C60F68ECD9A4E4C3C74E4CC4DEE�OriginalFilePath�PC:\Users\mssgm\Documents\GitHub\ts-sample\src\tokenReaders\TokenReaderManager.ts�NewFileMarker�� 1CF9939611B0D194AC81951A171DF046��SavedFileName١C:\Users\mssgm\Documents\GitHub\ts-sample\.vs\CopilotSnapshots\C4D8E85893425E4F86F18850F5CA5C08\6C0950E97063C547A72D737E618436B0\1CF9939611B0D194AC81951A171DF046�OriginalFilePath�QC:\Users\mssgm\Documents\GitHub\ts-sample\src\tokenReaders\OperatorTokenReader.ts�NewFileMarker�

package/.vs/CopilotSnapshots/C5C3CA4C37B14A47B6BC753D09F69117/03EA1376F04C0D468FD0851119159D34/44EB81A1663981E3F52FFFECE3A2918E

@@ -0,0 +1,148 @@
+import { StringUtils } from "./stringUtils";
+
+export enum KeywordMatchResult {
+    NotAKeyword,     // "キーワードではない"
+    PartialOnly,     // "途中（ここで終わることはない）"
+    PartialOrFinal,  // "途中または終端（ここで止まることはある）"
+    Final            // "終端（これ以上長いキーワードはない）"
+}
+
+export class KeywordTrieReader {
+    private input: string;
+    private trie: KeywordTrie;
+
+    constructor(input: string, trie: KeywordTrie) {
+        this.input = input;
+        this.trie = trie;
+        this.trie.reset();
+    }
+
+    private isEndOfInput(position: number, shift: number = 0): boolean {
+        return position + shift >= this.input.length;
+    }
+
+    private canRead(position: number, shift: number = 0): boolean {
+        return !this.isEndOfInput(position, shift);
+    }
+
+    public readKeyword(position: number): { keyword: string, newPosition: number } | null {
+        if (this.isEndOfInput(position)) {
+            return null;
+        }
+
+        // reset trie node
+        this.trie.reset();
+        const result = StringUtils.tryReadRegularIdentifier(this.input, position);
+
+        if (result === null) {
+            return null;
+        }
+
+        let matchResult = this.trie.pushLexeme(result.identifier);
+
+        if (matchResult === KeywordMatchResult.NotAKeyword) {
+            return null;
+        }
+
+        if (matchResult === KeywordMatchResult.Final) {
+            return {
+                keyword: result.identifier,
+                newPosition: result.newPosition
+            };
+        }
+
+        // multi-word keyword
+        let lexeme = result.identifier;
+        position = StringUtils.skipWhiteSpacesAndComments(this.input, result.newPosition);
+
+        while (this.canRead(position)) {
+            const previousMatchResult = matchResult;
+
+            const result = StringUtils.tryReadRegularIdentifier(this.input, position);
+
+            if (result !== null) {
+                matchResult = this.trie.pushLexeme(result.identifier);
+
+                if (matchResult === KeywordMatchResult.NotAKeyword) {
+                    if (previousMatchResult === KeywordMatchResult.PartialOrFinal) {
+                        break;
+                    } else {
+                        return null;
+                    }
+                }
+
+                lexeme += ' ' + result.identifier;
+                position = StringUtils.skipWhiteSpacesAndComments(this.input, result.newPosition);
+
+                if (matchResult === KeywordMatchResult.Final) {
+                    break;
+                }
+            } else if (previousMatchResult === KeywordMatchResult.PartialOrFinal) {
+                break;
+            } else {
+                return null;
+            }
+        }
+        return {
+            keyword: lexeme,
+            newPosition: position
+        };
+    }
+}
+
+export class KeywordTrie {
+    private root: Map<string, any> = new Map();
+    private currentNode: Map<string, any>;
+    
+    // Add a caching property to avoid regex pattern creation for each check
+    private hasEndProperty: boolean = false;
+    private hasMoreProperties: boolean = false;
+
+    constructor(keywords: string[][]) {
+        // initialize root node
+        for (const keyword of keywords) {
+            this.addKeyword(keyword);
+        }
+        // set current node to root
+        this.currentNode = this.root;
+    }
+
+    private addKeyword(keyword: string[]) {
+        let node = this.root;
+        for (const word of keyword) {
+            if (!node.has(word)) {
+                node.set(word, new Map());
+            }
+            node = node.get(word);
+        }
+        node.set("__end__", true);
+    }
+
+    public reset(): void {
+        this.currentNode = this.root;
+        this.hasEndProperty = false;
+        this.hasMoreProperties = false;
+    }
+
+    public pushLexeme(lexeme: string): KeywordMatchResult {
+        if (!this.currentNode.has(lexeme)) {
+            return KeywordMatchResult.NotAKeyword;
+        }
+
+        // move to next node
+        this.currentNode = this.currentNode.get(lexeme);
+        
+        // Cache property checks to avoid repeated operations
+        this.hasEndProperty = this.currentNode.has("__end__");
+        this.hasMoreProperties = this.currentNode.size > (this.hasEndProperty ? 1 : 0);
+
+        if (this.hasEndProperty && !this.hasMoreProperties) {
+            return KeywordMatchResult.Final;
+        }
+        if (this.hasEndProperty && this.hasMoreProperties) {
+            return KeywordMatchResult.PartialOrFinal;
+        }
+
+        return KeywordMatchResult.PartialOnly;
+    }
+}

package/.vs/CopilotSnapshots/C5C3CA4C37B14A47B6BC753D09F69117/03EA1376F04C0D468FD0851119159D34/E602628EF6D764C2C267810C92906DBA

@@ -0,0 +1,265 @@
+import { BaseTokenReader } from './BaseTokenReader';
+import { TokenType } from '../enums/tokenType';
+import { Lexeme } from '../models/Lexeme';
+import { CharLookupTable } from '../utils/charLookupTable';
+import { KeywordTrie, KeywordTrieReader } from '../utils/KeywordTrie';
+
+/**
+ * Reads SQL literal tokens (numbers, strings)
+ */
+
+const keywords = [
+    ["null"],
+    ["true"],
+    ["false"],
+    ["current_date"],
+    ["current_time"],
+    ["current_timestamp"],
+    ["localtime"],
+    ["localtimestamp"],
+    ["unbounded"],
+    ["normalized"],
+    ["nfc", "normalized"],
+    ["nfd", "normalized"],
+    ["nfkc", "normalized"],
+    ["nfkd", "normalized"],
+    ["nfc"],
+    ["nfd"],
+    ["nfkc"],
+    ["nfkd"]
+];
+const trie = new KeywordTrie(keywords);
+
+// Prefix sets for quick checks
+const SINGLE_CHAR_ESCAPED_PREFIX = new Set(['e\'', 'E\'', 'x\'', 'X\'', 'b\'',  'B\'']);
+const UNICODE_ESCAPED_PREFIX = new Set(['u&\'', 'U&\'']);
+
+export class LiteralTokenReader extends BaseTokenReader {
+    /**
+     * Try to read a literal token
+     */
+    public tryRead(previous: Lexeme | null): Lexeme | null {
+        if (this.isEndOfInput()) {
+            return null;
+        }
+
+        const char = this.input[this.position];
+
+        // Check for keyword literals    
+        const keyword = this.tryReadKeyword();
+        if (keyword) {
+            return keyword;
+        }
+
+        // Decimal token starting with a dot
+        if (char === '.' && this.canRead(1) && CharLookupTable.isDigit(this.input[this.position + 1])) {
+            return this.createLexeme(TokenType.Literal, this.readDigit());
+        }
+
+        // String literal
+        if (char === '\'') {
+            const value = this.readSingleQuotedString();
+            return this.createLexeme(TokenType.Literal, value);
+        }
+
+        // Digit tokens
+        if (CharLookupTable.isDigit(char)) {
+            return this.createLexeme(TokenType.Literal, this.readDigit());
+        }
+
+        // Signed number
+        if ((char === '+' || char === '-') && this.isValidNumericPrefix(previous)) {
+            const sign = char;
+            this.position++;
+
+            // Skip whitespace after sign
+            let pos = this.position;
+            while (this.canRead() && CharLookupTable.isWhitespace(this.input[this.position])) {
+                this.position++;
+            }
+
+            if (this.canRead() && (
+                CharLookupTable.isDigit(this.input[this.position]) ||
+                (this.input[this.position] === '.' &&
+                    this.canRead(1) &&
+                    CharLookupTable.isDigit(this.input[this.position + 1]))
+            )) {
+                return this.createLexeme(
+                    TokenType.Literal,
+                    sign === '-' ? sign + this.readDigit() : this.readDigit()
+                );
+            }
+
+            // Not a number, restore position
+            this.position = pos - 1; // Adjust for the increment at the beginning
+        }
+
+        // Check for prefixed literals
+        return this.tryReadEscapedLiteral();
+    }
+
+    private tryReadKeyword(): Lexeme | null {
+        // Check for keyword literals    
+        const reader = new KeywordTrieReader(this.input, trie);
+        const result = reader.readKeyword(this.position);
+        if (result) {
+            this.position = result.newPosition;
+            return this.createLexeme(TokenType.Literal, result.keyword);
+        }
+        return null;
+    }
+
+    /**
+     * Check if the current context allows for a signed number
+     */
+    private isValidNumericPrefix(previous: Lexeme | null): boolean {
+        return previous === null ||
+            (previous.type !== TokenType.Literal &&
+                previous.type !== TokenType.Identifier);
+    }
+
+    /**
+     * Read a numeric value
+     */
+    private readDigit(): string {
+        const start = this.position;
+        let hasDot = false;
+        let hasExponent = false;
+
+        // Consider 0x, 0b, 0o
+        if (this.canRead(1) &&
+            this.input[this.position] === '0' &&
+            "xbo".includes(this.input[this.position + 1].toLowerCase())) {
+
+            const prefixType = this.input[this.position + 1].toLowerCase();
+            this.position += 2;
+
+            // Continue to get numeric and hexadecimal notation strings
+            const isHex = prefixType === 'x';
+            while (this.canRead()) {
+                const c = this.input[this.position];
+                if (CharLookupTable.isDigit(c) || (isHex && CharLookupTable.isHexChar(c))) {
+                    this.position++;
+                } else {
+                    break;
+                }
+            }
+
+            return this.input.slice(start, this.position);
+        }
+
+        // If starting with dot, note it
+        if (this.input[start] === '.') {
+            hasDot = true;
+            this.position++;
+        }
+
+        // Consider decimal point and exponential notation
+        while (this.canRead()) {
+            const char = this.input[this.position];
+
+            if (char === '.' && !hasDot) {
+                hasDot = true;
+            } else if ((char === 'e' || char === 'E') && !hasExponent) {
+                hasExponent = true;
+                if (this.canRead(1) && (this.input[this.position + 1] === '+' || this.input[this.position + 1] === '-')) {
+                    this.position++;
+                }
+            } else if (!CharLookupTable.isDigit(char)) {
+                break;
+            }
+
+            this.position++;
+        }
+
+        if (start === this.position) {
+            throw new Error(`Unexpected character. position: ${start}\n${this.getDebugPositionInfo(start)}`);
+        }
+
+        if (this.input[start] === '.') {
+            // If the number starts with a dot, add 0 to the front
+            return '0' + this.input.slice(start, this.position);
+        }
+
+        return this.input.slice(start, this.position);
+    }
+
+    /**
+     * Read a string literal
+     */
+    private readSingleQuotedString(): string {
+        const start = this.position;
+
+        this.read('\'');
+
+        while (this.canRead()) {
+            const char = this.input[this.position];
+
+            // escape character check
+            if (char === '\\' && this.canRead(1) && this.input[this.position + 1] === '\'') {
+                this.position += 2;
+                continue;
+            }
+            else if (char === '\'') {
+                break;
+            }
+            this.position++;
+        }
+
+        if (this.isEndOfInput()) {
+            throw new Error(`Single quote is not closed. position: ${start}\n${this.getDebugPositionInfo(start)}`);
+        }
+
+        const value = this.input.slice(start, this.position);
+        this.position++;
+        return value;
+    }
+
+    /**
+     * Try to read an escaped literal like e'...', x'...', etc.
+     */
+    private tryReadEscapedLiteral(): Lexeme | null {
+        const start = this.position;
+
+        // Check for prefixed literals: e', x', b'
+        if (this.canRead(1) && SINGLE_CHAR_ESCAPED_PREFIX.has(this.input.slice(start, start + 2))) {
+            return this.readPrefixedLiteral(start, 2);
+        }
+
+        // Check for unicode literal: u&'
+        if (this.canRead(2) && UNICODE_ESCAPED_PREFIX.has( this.input.slice(start, start + 3))) {
+            return this.readPrefixedLiteral(start, 3);
+        }
+
+        return null;
+    }
+
+    private readPrefixedLiteral(start: number, prefixLength: number): Lexeme {
+        // Skip the prefix
+        this.position += prefixLength;
+
+        // Read until the closing quote
+        while (this.canRead()) {
+            if (this.input[this.position] === '\\' && this.canRead(1) && this.input[this.position + 1] === '\'') {
+                // Skip escaped single quote
+                this.position += 2;
+                continue;
+            }
+            else if (this.input[this.position] === '\'') {
+                // Found closing quote
+                this.position++;
+                break;
+            }
+            this.position++;
+        }
+
+        if (this.position <= start + prefixLength) {
+            throw new Error(`Closing delimiter is not found. position: ${start}\n${this.getDebugPositionInfo(start)}`);
+        }
+
+        return {
+            type: TokenType.Literal,
+            value: this.input.slice(start, this.position)
+        };
+    }
+}