qasm-ts 2.1.1 → 2.1.3

package/dist/qasm3/lexer.js

@@ -1,673 +0,0 @@
-"use strict";
-/* eslint-disable no-useless-escape */
-Object.defineProperty(exports, "__esModule", { value: true });
-/**
- * OpenQASM 3.0 Lexical Analyzer
- *
- * This module implements the lexer for OpenQASM 3.0, which transforms source code
- * into a stream of tokens. The lexer handles the significantly expanded syntax of
- * OpenQASM 3.0, including classical programming constructs, control flow, and
- * advanced quantum features.
- *
- * Key features of the OpenQASM 3.0 lexer:
- * - **Extended token set**: Classical types, control flow, functions
- * - **Complex operators**: Compound assignment, bitwise operations
- * - **Advanced literals**: Scientific notation, binary/hex/octal, durations
- * - **Gate modifiers**: ctrl, negctrl, inv, pow with @ syntax
- * - **Unicode support**: Mathematical constants (π, ℇ, τ)
- * - **Robust error handling**: Detailed syntax error reporting
- *
- * The lexer performs several validation passes:
- * - Semicolon verification for statement termination
- * - Comment handling (single-line // and multi-line /* *\/)
- * - String literal parsing with multiple quote styles
- * - Number format validation and conversion
- *
- * @module
- *
- * @example Basic lexing process
- * ```typescript
- * const lexer = new Lexer('qubit[2] q; h q[0];');
- * const tokens = lexer.lex();
- * // Returns: [
- * //   [Token.Id, 'qubit'], [Token.LSParen], [Token.NNInteger, 2],
- * //   [Token.RSParen], [Token.Id, 'q'], [Token.Semicolon], ...
- * // ]
- * ```
- */
-var token_1 = require("./token");
-var errors_1 = require("../errors");
-/**
- * Handles throwing lexer errors with basic stack trace.
- * @param error - The error to throw.
- * @param number - The line number in the source code.
- * @param code - The source code that the error is about.
- */
-function throwLexerError(error, line, code) {
-    throw new error("Line ".concat(line, ": ").concat(code));
-}
-/**
- * Returns whether a given character could be an element of a numeric value.
- * @param c - The character.
- * @return Whether the character is numeric.
- */
-function isNumeric(c) {
-    return c == "." || c == "e" || c == "_" || !isNaN(parseInt(c));
-}
-/**
- * Returns whether a given character is a letter.
- * @param c - The character.
- * @param matchCase - Whether to check for a letter that is upper case, lower case, or either. (optional)
- * @return Whether the character is a letter.
- */
-function isLetter(c, matchCase) {
-    switch (matchCase) {
-        case "upper":
-            return /^[A-Z]$/.test(c);
-        case "lower":
-            return /^[a-z]$/.test(c);
-        default:
-            return /^[A-Za-z]$/.test(c);
-    }
-}
-/**
- * Returns whether a given character is unicode.
- * @param c - The character.
- * @param excludePi - Whether to exclude the Pi symbol from consideration.
- * @return - Whether the given character is valid unicode.
- */
-function isUnicode(c, excludePi) {
-    var isBasicUnicode = /^\u0000-\u00ff/.test(c);
-    switch (excludePi) {
-        case true:
-            return isBasicUnicode && c !== "\u03C0";
-        case false:
-            return isBasicUnicode;
-        default:
-            return isBasicUnicode;
-    }
-}
-/**
- * Returns whether a given character is alphanumeric.
- * @param c - The character.
- * @return Whether the character is alphanumeric.
- */
-function isAlpha(c) {
-    return /^[0-9a-zA-Z]+$/.test(c);
-}
-/**
- * Returns whether a given character is a newline character.
- * @param c - The character.
- * @return Whether the character is a newline.
- */
-function isNewline(c) {
-    return /\n|\r(?!\n)|\u2028|\u2029|\r\n/.test(c);
-}
-/**
- * OpenQASM 3.0 Lexical Analyzer
- *
- * The main lexer class that processes OpenQASM 3.0 source code character by
- * character and produces a stream of tokens for the parser to consume.
- *
- * The lexer maintains state including:
- * - Current cursor position in the input
- * - Input validation status
- * - Error reporting context
- *
- * @example Creating and using a lexer
- * ```typescript
- * const source = `
- *   OPENQASM 3.0;
- *   include "stdgates.inc";
- *   qubit[2] q;
- *   h q[0];
- *   cx q[0], q[1];
- * `;
- *
- * const lexer = new Lexer(source);
- * const tokens = lexer.lex();
- * ```
- */
-var Lexer = /** @class */ (function () {
-    /**
-     * Creates a lexer.
-     * @param input - The string to lex.
-     * @param cursor - The starting cursor position.
-     */
-    function Lexer(input, cursor) {
-        if (cursor === void 0) { cursor = 0; }
-        var _this = this;
-        /**
-         * Verifies that all appropriate lines end with a semicolon.
-         * @return A tuple of the status and if False, returns the problematic line.
-         */
-        this.verifyInput = function () {
-            var lines = _this.input.split(/\n|\r(?!\n)|\u2028|\u2029|\r\n/g);
-            for (var i = 0; i < lines.length; i++) {
-                var trimmedLine = lines[i].trim();
-                if (!trimmedLine.startsWith("//") &&
-                    !trimmedLine.startsWith("/*") &&
-                    !trimmedLine.startsWith("*") &&
-                    !trimmedLine.startsWith("*/") &&
-                    trimmedLine.length > 0 &&
-                    !trimmedLine.startsWith("gate") &&
-                    trimmedLine !== "{" &&
-                    trimmedLine !== "}" &&
-                    !trimmedLine.includes(";") &&
-                    !trimmedLine.startsWith("def") &&
-                    !trimmedLine.startsWith("if") &&
-                    !trimmedLine.startsWith("else") &&
-                    !trimmedLine.startsWith("for") &&
-                    !trimmedLine.startsWith("while") &&
-                    !trimmedLine.startsWith("switch") &&
-                    !trimmedLine.startsWith("case") &&
-                    !trimmedLine.startsWith("box") &&
-                    !trimmedLine.startsWith("array") &&
-                    !trimmedLine.startsWith("{") &&
-                    !trimmedLine.startsWith("default")) {
-                    return [false, i + 1, lines[i]];
-                }
-            }
-            return [true, null, null];
-        };
-        /**
-         * Calling this method lexes the code represented by the provided string.
-         * @return An array of tokens and their corresponding values.
-         */
-        this.lex = function () {
-            var tokens = [];
-            var token;
-            var verifyInputResult = _this.verifyInput();
-            if (!verifyInputResult[0]) {
-                throwLexerError(errors_1.MissingSemicolonError, verifyInputResult[1], verifyInputResult[2]);
-            }
-            while (_this.cursor < _this.input.length) {
-                token = _this.nextToken();
-                if (token) {
-                    tokens.push(token);
-                }
-            }
-            return tokens;
-        };
-        /**
-         * Reads a character and advances the cursor.
-         * @param num - Optional cursor position modifier.
-         */
-        this.readChar = function (num) {
-            if (num === void 0) { num = 1; }
-            _this.cursor += num;
-            return _this.input[_this.cursor - num];
-        };
-        /**
-         * Advances the cusor past the next comment.
-         */
-        this.skipComment = function () {
-            var char = "";
-            while (!isNewline(char)) {
-                char = _this.readChar();
-            }
-        };
-        /**
-         * Advances the cursor past a multiline comment.
-         */
-        this.skipMultiLineComment = function () {
-            var char = "";
-            var nextChar = "";
-            var multiLineCommentTerminator = "*/";
-            while ("".concat(char).concat(nextChar) !== multiLineCommentTerminator) {
-                char = _this.readChar();
-                nextChar = _this.peek();
-            }
-            _this.readChar();
-        };
-        /**
-         * Determines whether the next character to process equals a given character.
-         * @param c - The given character.
-         * @return Whether the next character equals the given character.
-         */
-        this.peekEq = function (c) { return _this.peek() == c; };
-        /**
-         * Reads a character without advancing the cursor.
-         * @param index - Optional peek position offset.
-         */
-        this.peek = function () { return _this.input[_this.cursor]; };
-        /**
-         * Reads a numeric value.
-         * @return The numeric value as a string.
-         */
-        this.readNumeric = function () {
-            var num = "";
-            var char = _this.peek();
-            while (isNumeric(char) || char === "e") {
-                num += _this.readChar();
-                if (char === "e" && _this.peek() === "-") {
-                    num += _this.readChar();
-                }
-                char = _this.peek();
-            }
-            return num;
-        };
-        /**
-         * Reads an identifier.
-         * @return The identifier as a string.
-         */
-        this.readIdentifier = function () {
-            var id = "";
-            var next = _this.peek();
-            while (isAlpha(next) || next == "_" || isUnicode(next)) {
-                id += _this.readChar();
-                next = _this.peek();
-            }
-            return id;
-        };
-        /**
-         * Reds a keyword or identifier.
-         * If the character sequence matches a keyword, returns the corresponding token.
-         * Otherwise, treats the sequence as an identifier.
-         * @param char - The first character of the keyword or identifier.
-         * @return The corresponding token or identifier.
-         */
-        this.readKeywordOrIdentifier = function (char) {
-            var identifier = char + _this.readIdentifier();
-            return [(0, token_1.lookup)(identifier), identifier];
-        };
-        /**
-         * Reads a string literal.
-         * @param terminator - The literal's termination character.
-         * @return The literal as a string.
-         */
-        this.readStringLiteral = function (terminator) {
-            var lit = "";
-            var char = "";
-            while (!(terminator == char)) {
-                char = _this.readChar();
-                lit += char;
-            }
-            return lit;
-        };
-        /**
-         * Advances the cusor past the next block of whitespace.
-         */
-        this.skipWhitespace = function () {
-            while (" \t\n\r\v".indexOf(_this.peek()) > -1) {
-                _this.cursor += 1;
-            }
-            return null;
-        };
-        /**
-         * Lexes the next token.
-         * @return The next token and its corresponding value.
-         */
-        this.nextToken = function () {
-            _this.skipWhitespace();
-            if (_this.cursor == _this.input.length) {
-                return [token_1.Token.EndOfFile];
-            }
-            var char = _this.peek();
-            _this.readChar();
-            switch (char) {
-                case "π":
-                    return [token_1.Token.Pi];
-                case "ℇ":
-                    return [token_1.Token.Euler];
-                case "τ":
-                    return [token_1.Token.Tau];
-                case "@":
-                    return [token_1.Token.At];
-                case "θ":
-                    return _this.readKeywordOrIdentifier(char);
-                case "!":
-                    if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.BinaryOp, "!="];
-                    }
-                    else {
-                        return [token_1.Token.UnaryOp, "!"];
-                    }
-                case "~":
-                    return [token_1.Token.UnaryOp, "~"];
-                case "*":
-                    if (_this.peekEq("*")) {
-                        _this.readChar();
-                        if (_this.peekEq("=")) {
-                            _this.readChar();
-                            return [token_1.Token.CompoundArithmeticOp, "**="];
-                        }
-                        else {
-                            return [token_1.Token.ArithmeticOp, "**"];
-                        }
-                    }
-                    else if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.CompoundArithmeticOp, "*="];
-                    }
-                    else {
-                        return [token_1.Token.ArithmeticOp, "*"];
-                    }
-                case "/":
-                    if (_this.peekEq("/")) {
-                        _this.skipComment();
-                        return;
-                    }
-                    else if (_this.peekEq("*")) {
-                        _this.skipMultiLineComment();
-                        return;
-                    }
-                    else if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.CompoundArithmeticOp, "/="];
-                    }
-                    else {
-                        return [token_1.Token.ArithmeticOp, "/"];
-                    }
-                case "%":
-                    if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.CompoundArithmeticOp, "%="];
-                    }
-                    else {
-                        return [token_1.Token.ArithmeticOp, "%"];
-                    }
-                case "+":
-                    if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.CompoundArithmeticOp, "+="];
-                    }
-                    else if (_this.peekEq("+")) {
-                        _this.readChar();
-                        return [token_1.Token.ArithmeticOp, "++"];
-                    }
-                    return [token_1.Token.ArithmeticOp, "+"];
-                case "-": {
-                    if (_this.peekEq(">")) {
-                        _this.readChar();
-                        return [token_1.Token.Arrow];
-                    }
-                    else if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.CompoundArithmeticOp, "-="];
-                    }
-                    return [token_1.Token.UnaryOp, "-"];
-                }
-                case "&":
-                    if (_this.peekEq("&")) {
-                        _this.readChar();
-                        return [token_1.Token.BinaryOp, "&&"];
-                    }
-                    else {
-                        return [token_1.Token.BinaryOp, "&"];
-                    }
-                case "|":
-                    if (_this.peekEq("|")) {
-                        _this.readChar();
-                        return [token_1.Token.BinaryOp, "||"];
-                    }
-                    else {
-                        return [token_1.Token.BinaryOp, "|"];
-                    }
-                case "^":
-                    if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.CompoundBinaryOp, "^="];
-                    }
-                    return [token_1.Token.BinaryOp, "^"];
-                case "<":
-                    if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.BinaryOp, "<="];
-                    }
-                    else if (_this.input[_this.cursor] == "<" &&
-                        _this.input[_this.cursor + 1] == "=") {
-                        _this.readChar(2);
-                        return [token_1.Token.CompoundBinaryOp, "<<="];
-                    }
-                    else if (_this.peekEq("<")) {
-                        _this.readChar();
-                        return [token_1.Token.BinaryOp, "<<"];
-                    }
-                    else {
-                        return [token_1.Token.BinaryOp, "<"];
-                    }
-                case ">":
-                    if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.BinaryOp, ">="];
-                    }
-                    else if (_this.input[_this.cursor] == ">" &&
-                        _this.input[_this.cursor + 1] == "=") {
-                        _this.readChar(2);
-                        return [token_1.Token.CompoundBinaryOp, ">>="];
-                    }
-                    else if (_this.peekEq(">")) {
-                        _this.readChar();
-                        return [token_1.Token.BinaryOp, ">>"];
-                    }
-                    else {
-                        return [token_1.Token.BinaryOp, ">"];
-                    }
-                case "=":
-                    if (_this.peekEq("=")) {
-                        _this.readChar();
-                        return [token_1.Token.BinaryOp, "=="];
-                    }
-                    else {
-                        return [token_1.Token.EqualsAssmt];
-                    }
-                case ";":
-                    return [token_1.Token.Semicolon];
-                case ",":
-                    return [token_1.Token.Comma];
-                case ":":
-                    return [token_1.Token.Colon];
-                case "(":
-                    return [token_1.Token.LParen];
-                case "[":
-                    return [token_1.Token.LSParen];
-                case "{":
-                    return [token_1.Token.LCParen];
-                case ")":
-                    return [token_1.Token.RParen];
-                case "]":
-                    return [token_1.Token.RSParen];
-                case "}":
-                    return [token_1.Token.RCParen];
-                case "$":
-                    return [token_1.Token.Dollar];
-                case "#":
-                    if (_this.input[_this.cursor] == "d" &&
-                        _this.input[_this.cursor + 1] == "i" &&
-                        _this.input[_this.cursor + 2] == "m") {
-                        _this.readChar(3);
-                        return [token_1.Token.Dim];
-                    }
-                    return _this.readKeywordOrIdentifier(char);
-                case "c":
-                    if (_this.input[_this.cursor] == "t" &&
-                        _this.input[_this.cursor + 1] == "r" &&
-                        _this.input[_this.cursor + 2] == "l") {
-                        _this.readChar(3);
-                        return _this.lexGateModifier("ctrl");
-                    }
-                    return _this.readKeywordOrIdentifier(char);
-                case "n":
-                    if (_this.input[_this.cursor] == "e" &&
-                        _this.input[_this.cursor + 1] == "g" &&
-                        _this.input[_this.cursor + 2] == "c" &&
-                        _this.input[_this.cursor + 3] == "t" &&
-                        _this.input[_this.cursor + 4] == "r" &&
-                        _this.input[_this.cursor + 5] == "l") {
-                        _this.readChar(6);
-                        return _this.lexGateModifier("negctrl");
-                    }
-                    return _this.readKeywordOrIdentifier(char);
-                case "i":
-                    if (_this.input[_this.cursor] == "n" &&
-                        _this.input[_this.cursor + 1] == "v") {
-                        _this.readChar(2);
-                        return _this.lexGateModifier("inv");
-                    }
-                    return _this.readKeywordOrIdentifier(char);
-                case "p":
-                    if (_this.input[_this.cursor] == "o" &&
-                        _this.input[_this.cursor + 1] == "w" &&
-                        !isLetter(_this.input[_this.cursor + 2])) {
-                        _this.readChar(2);
-                        return _this.lexGateModifier("pow");
-                    }
-                    return _this.readKeywordOrIdentifier(char);
-                case "0":
-                    if (_this.peekEq("b") || _this.peekEq("B")) {
-                        var char_1 = _this.readChar(1);
-                        var binaryLit = _this.readIdentifier();
-                        return [token_1.Token.BinaryLiteral, "0".concat(char_1).concat(binaryLit)];
-                    }
-                    else if (_this.peekEq("o") || _this.peekEq("O")) {
-                        var char_2 = _this.readChar(1);
-                        var octalLit = _this.readIdentifier();
-                        return [token_1.Token.OctalLiteral, "0".concat(char_2).concat(octalLit)];
-                    }
-                    else if (_this.peekEq("x") || _this.peekEq("X")) {
-                        var char_3 = _this.readChar(1);
-                        var hexLit = _this.readIdentifier();
-                        return [token_1.Token.HexLiteral, "0".concat(char_3).concat(hexLit)];
-                    }
-                    else {
-                        var num = char + _this.readNumeric();
-                        if (num.indexOf(".") != -1) {
-                            return [token_1.Token.Real, parseFloat(num)];
-                        }
-                        else if (num.indexOf("_") != -1) {
-                            return [token_1.Token.Integer, num];
-                        }
-                        else {
-                            return [token_1.Token.NNInteger, parseInt(num)];
-                        }
-                    }
-                    return _this.readKeywordOrIdentifier(char);
-                case "O":
-                    if (_this.input[_this.cursor].toLowerCase() == "p" &&
-                        _this.input[_this.cursor + 1].toLowerCase() == "e" &&
-                        _this.input[_this.cursor + 2].toLowerCase() == "n" &&
-                        _this.input[_this.cursor + 3] == "Q" &&
-                        _this.input[_this.cursor + 4] == "A" &&
-                        _this.input[_this.cursor + 5] == "S" &&
-                        _this.input[_this.cursor + 6] == "M") {
-                        _this.readChar(7);
-                        var offset = 0;
-                        while (_this.cursor + offset < _this.input.length &&
-                            " \t".indexOf(_this.input[_this.cursor + offset]) > -1) {
-                            offset++;
-                        }
-                        // Read the major version
-                        var majorVersion = "";
-                        while (_this.cursor + offset < _this.input.length &&
-                            !isNaN(parseInt(_this.input[_this.cursor + offset], 10))) {
-                            majorVersion += _this.input[_this.cursor + offset];
-                            offset++;
-                        }
-                        // Attempt to read the minor version
-                        var minorVersion = undefined;
-                        if (_this.input[_this.cursor + offset] == ".") {
-                            offset++;
-                            minorVersion = "";
-                            while (_this.cursor + offset < _this.input.length &&
-                                !isNaN(parseInt(_this.input[_this.cursor + offset], 10))) {
-                                minorVersion += _this.input[_this.cursor + offset];
-                                offset++;
-                            }
-                        }
-                        // Parse major and minor versions
-                        var major = parseInt(majorVersion, 10);
-                        var minor = minorVersion ? parseInt(minorVersion, 10) : undefined;
-                        if (major !== 3) {
-                            throw new errors_1.UnsupportedOpenQASMVersionError("Unsupported OpenQASM version detected: ".concat(majorVersion, ".").concat(minor !== null && minor !== void 0 ? minor : 0));
-                        }
-                        return [token_1.Token.OpenQASM];
-                    }
-                    return _this.readKeywordOrIdentifier(char);
-                case '"': {
-                    var stringLiteral = char + _this.readStringLiteral('"');
-                    return [token_1.Token.String, stringLiteral];
-                }
-                case "’": {
-                    var singleStringLiteral = char + _this.readStringLiteral("’");
-                    return [token_1.Token.String, singleStringLiteral];
-                }
-                default:
-                    if (isLetter(char)) {
-                        return _this.readKeywordOrIdentifier(char);
-                    }
-                    else if (isNumeric(char)) {
-                        var num = char + _this.readNumeric();
-                        if (num.indexOf("e") != -1) {
-                            return [token_1.Token.ScientificNotation, num];
-                        }
-                        else if (num.indexOf(".") != -1) {
-                            return [token_1.Token.Real, parseFloat(num)];
-                        }
-                        else if (num.indexOf("_") != -1) {
-                            return [token_1.Token.Integer, num];
-                        }
-                        else {
-                            return [token_1.Token.NNInteger, parseInt(num)];
-                        }
-                    }
-                    else {
-                        return [token_1.Token.Illegal];
-                    }
-            }
-        };
-        /**
-         * Returns the line number where the current cursor is located.
-         * @param cursor - The current cursor position in the input string.
-         * @return The line number.
-         */
-        this.getLineNumber = function (cursor) {
-            return _this.input
-                .substring(0, cursor)
-                .split(/\n|\r(?!\n)|\u2028|\u2029|\r\n/).length;
-        };
-        /**
-         * Returns the current line of code where the cursor is located.
-         * @param cursor - The current cursor position in the input string.
-         * @return The specific line where the cursor is located.
-         */
-        this.getCurrentLine = function (cursor) {
-            var lines = _this.input.split(/\n|\r(?!\n)|\u2028|\u2029|\r\n/);
-            var lineNumber = _this.getLineNumber(cursor);
-            return lines[lineNumber - 1];
-        };
-        /**
-         * Retruns an identifier or gate modifier.
-         */
-        this.lexGateModifier = function (keyword) {
-            var offset = 1;
-            var currChar = "";
-            while (_this.cursor + offset < _this.input.length &&
-                _this.input[_this.cursor + offset] !== ";") {
-                currChar = _this.input[_this.cursor + offset];
-                if (currChar === "@") {
-                    break;
-                }
-                offset++;
-            }
-            if (currChar === "@") {
-                switch (keyword) {
-                    case "ctrl":
-                        return [token_1.Token.Ctrl];
-                    case "negctrl":
-                        return [token_1.Token.NegCtrl];
-                    case "inv":
-                        return [token_1.Token.Inv];
-                    case "pow":
-                        return [token_1.Token.PowM];
-                }
-            }
-            return _this.readKeywordOrIdentifier(keyword);
-        };
-        this.input = input;
-        this.cursor = cursor;
-    }
-    return Lexer;
-}());
-exports.default = Lexer;