UNPKG

prettier-sql

Version:

Format whitespace in a SQL query to make it more readable

260 lines (211 loc) 16.1 kB
"use strict"; function _typeof(obj) { "@babel/helpers - typeof"; if (typeof Symbol === "function" && typeof Symbol.iterator === "symbol") { _typeof = function _typeof(obj) { return typeof obj; }; } else { _typeof = function _typeof(obj) { return obj && typeof Symbol === "function" && obj.constructor === Symbol && obj !== Symbol.prototype ? "symbol" : typeof obj; }; } return _typeof(obj); } Object.defineProperty(exports, "__esModule", { value: true }); exports["default"] = void 0; var regexFactory = _interopRequireWildcard(require("./regexFactory")); var _utils = require("../utils"); var _token = require("./token"); function _getRequireWildcardCache(nodeInterop) { if (typeof WeakMap !== "function") return null; var cacheBabelInterop = new WeakMap(); var cacheNodeInterop = new WeakMap(); return (_getRequireWildcardCache = function _getRequireWildcardCache(nodeInterop) { return nodeInterop ? cacheNodeInterop : cacheBabelInterop; })(nodeInterop); } function _interopRequireWildcard(obj, nodeInterop) { if (!nodeInterop && obj && obj.__esModule) { return obj; } if (obj === null || _typeof(obj) !== "object" && typeof obj !== "function") { return { "default": obj }; } var cache = _getRequireWildcardCache(nodeInterop); if (cache && cache.has(obj)) { return cache.get(obj); } var newObj = {}; var hasPropertyDescriptor = Object.defineProperty && Object.getOwnPropertyDescriptor; for (var key in obj) { if (key !== "default" && Object.prototype.hasOwnProperty.call(obj, key)) { var desc = hasPropertyDescriptor ? Object.getOwnPropertyDescriptor(obj, key) : null; if (desc && (desc.get || desc.set)) { Object.defineProperty(newObj, key, desc); } else { newObj[key] = obj[key]; } } } newObj["default"] = obj; if (cache) { cache.set(obj, newObj); } return newObj; } function ownKeys(object, enumerableOnly) { var keys = Object.keys(object); if (Object.getOwnPropertySymbols) { var symbols = Object.getOwnPropertySymbols(object); if (enumerableOnly) { symbols = symbols.filter(function (sym) { return Object.getOwnPropertyDescriptor(object, sym).enumerable; }); } keys.push.apply(keys, symbols); } return keys; } function _objectSpread(target) { for (var i = 1; i < arguments.length; i++) { var source = arguments[i] != null ? arguments[i] : {}; if (i % 2) { ownKeys(Object(source), true).forEach(function (key) { _defineProperty(target, key, source[key]); }); } else if (Object.getOwnPropertyDescriptors) { Object.defineProperties(target, Object.getOwnPropertyDescriptors(source)); } else { ownKeys(Object(source)).forEach(function (key) { Object.defineProperty(target, key, Object.getOwnPropertyDescriptor(source, key)); }); } } return target; } function _toConsumableArray(arr) { return _arrayWithoutHoles(arr) || _iterableToArray(arr) || _unsupportedIterableToArray(arr) || _nonIterableSpread(); } function _nonIterableSpread() { throw new TypeError("Invalid attempt to spread non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method."); } function _unsupportedIterableToArray(o, minLen) { if (!o) return; if (typeof o === "string") return _arrayLikeToArray(o, minLen); var n = Object.prototype.toString.call(o).slice(8, -1); if (n === "Object" && o.constructor) n = o.constructor.name; if (n === "Map" || n === "Set") return Array.from(o); if (n === "Arguments" || /^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n)) return _arrayLikeToArray(o, minLen); } function _iterableToArray(iter) { if (typeof Symbol !== "undefined" && iter[Symbol.iterator] != null || iter["@@iterator"] != null) return Array.from(iter); } function _arrayWithoutHoles(arr) { if (Array.isArray(arr)) return _arrayLikeToArray(arr); } function _arrayLikeToArray(arr, len) { if (len == null || len > arr.length) len = arr.length; for (var i = 0, arr2 = new Array(len); i < len; i++) { arr2[i] = arr[i]; } return arr2; } function _classCallCheck(instance, Constructor) { if (!(instance instanceof Constructor)) { throw new TypeError("Cannot call a class as a function"); } } function _defineProperties(target, props) { for (var i = 0; i < props.length; i++) { var descriptor = props[i]; descriptor.enumerable = descriptor.enumerable || false; descriptor.configurable = true; if ("value" in descriptor) descriptor.writable = true; Object.defineProperty(target, descriptor.key, descriptor); } } function _createClass(Constructor, protoProps, staticProps) { if (protoProps) _defineProperties(Constructor.prototype, protoProps); if (staticProps) _defineProperties(Constructor, staticProps); return Constructor; } function _defineProperty(obj, key, value) { if (key in obj) { Object.defineProperty(obj, key, { value: value, enumerable: true, configurable: true, writable: true }); } else { obj[key] = value; } return obj; } // convert to partial type import in TS 4.5 var NULL_REGEX = /(?!)/; // zero-width negative lookahead, matches nothing /** Struct that defines how a SQL language can be broken into tokens */ /** Converts SQL language string into a token stream */ var Tokenizer = /*#__PURE__*/function () { /** * @param {TokenizerOptions} cfg * @param {string[]} cfg.reservedKeywords - Reserved words in SQL * @param {string[]} cfg.reservedDependentClauses - Words that following a specific Statement and must have data attached * @param {string[]} cfg.reservedLogicalOperators - Words that are set to newline * @param {string[]} cfg.reservedCommands - Words that are set to new line separately * @param {string[]} cfg.reservedBinaryCommands - Words that are top level but have no indentation * @param {string[]} cfg.stringTypes - string types to enable - "", '', ``, [], N'' * @param {string[]} cfg.blockStart - Opening parentheses to enable, like (, [ * @param {string[]} cfg.blockEnd - Closing parentheses to enable, like ), ] * @param {string[]} cfg.indexedPlaceholderTypes - Prefixes for indexed placeholders, like ? * @param {string[]} cfg.namedPlaceholderTypes - Prefixes for named placeholders, like @ and : * @param {string[]} cfg.lineCommentTypes - Line comments to enable, like # and -- * @param {string[]} cfg.specialWordChars - Special chars that can be found inside of words, like @ and # * @param {string[]} cfg.operators - Additional operators to recognize */ function Tokenizer(cfg) { var _this = this, _cfg$specialWordChars, _cfg$reservedDependen, _cfg$operators, _this$REGEX_MAP, _cfg$indexedPlacehold; _classCallCheck(this, Tokenizer); _defineProperty(this, "WHITESPACE_REGEX", void 0); _defineProperty(this, "REGEX_MAP", void 0); _defineProperty(this, "INDEXED_PLACEHOLDER_REGEX", void 0); _defineProperty(this, "IDENT_NAMED_PLACEHOLDER_REGEX", void 0); _defineProperty(this, "STRING_NAMED_PLACEHOLDER_REGEX", void 0); _defineProperty(this, "matchToken", function (tokenType) { return function (input) { return _this.getTokenOnFirstMatch({ input: input, type: tokenType, regex: _this.REGEX_MAP[tokenType] }); }; }); this.WHITESPACE_REGEX = /^([\t-\r \xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]+)/; var specialWordCharsAll = Object.values((_cfg$specialWordChars = cfg.specialWordChars) !== null && _cfg$specialWordChars !== void 0 ? _cfg$specialWordChars : {}).join(''); this.REGEX_MAP = (_this$REGEX_MAP = {}, _defineProperty(_this$REGEX_MAP, _token.TokenType.WORD, regexFactory.createWordRegex(cfg.specialWordChars)), _defineProperty(_this$REGEX_MAP, _token.TokenType.STRING, regexFactory.createStringRegex(cfg.stringTypes)), _defineProperty(_this$REGEX_MAP, _token.TokenType.RESERVED_KEYWORD, regexFactory.createReservedWordRegex(cfg.reservedKeywords, specialWordCharsAll)), _defineProperty(_this$REGEX_MAP, _token.TokenType.RESERVED_DEPENDENT_CLAUSE, regexFactory.createReservedWordRegex((_cfg$reservedDependen = cfg.reservedDependentClauses) !== null && _cfg$reservedDependen !== void 0 ? _cfg$reservedDependen : [], specialWordCharsAll)), _defineProperty(_this$REGEX_MAP, _token.TokenType.RESERVED_LOGICAL_OPERATOR, regexFactory.createReservedWordRegex(cfg.reservedLogicalOperators, specialWordCharsAll)), _defineProperty(_this$REGEX_MAP, _token.TokenType.RESERVED_COMMAND, regexFactory.createReservedWordRegex(cfg.reservedCommands, specialWordCharsAll)), _defineProperty(_this$REGEX_MAP, _token.TokenType.RESERVED_BINARY_COMMAND, regexFactory.createReservedWordRegex(cfg.reservedBinaryCommands, specialWordCharsAll)), _defineProperty(_this$REGEX_MAP, _token.TokenType.OPERATOR, regexFactory.createOperatorRegex('+-/*%&|^><=.,;[]{}`:$', ['<>', '<=', '>=', '!='].concat(_toConsumableArray((_cfg$operators = cfg.operators) !== null && _cfg$operators !== void 0 ? _cfg$operators : [])))), _defineProperty(_this$REGEX_MAP, _token.TokenType.BLOCK_START, regexFactory.createParenRegex(cfg.blockStart)), _defineProperty(_this$REGEX_MAP, _token.TokenType.BLOCK_END, regexFactory.createParenRegex(cfg.blockEnd)), _defineProperty(_this$REGEX_MAP, _token.TokenType.LINE_COMMENT, regexFactory.createLineCommentRegex(cfg.lineCommentTypes)), _defineProperty(_this$REGEX_MAP, _token.TokenType.BLOCK_COMMENT, /^(\/\*(?:(?![])[\s\S])*?(?:\*\/|$))/), _defineProperty(_this$REGEX_MAP, _token.TokenType.NUMBER, /^((\x2D[\t-\r \xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]*)?[0-9]+(\.[0-9]*)?([Ee][\+\x2D]?[0-9]+(\.[0-9]+)?)?|0x[0-9A-Fa-f]+|0b[01]+)/), _defineProperty(_this$REGEX_MAP, _token.TokenType.PLACEHOLDER, NULL_REGEX), _this$REGEX_MAP); this.INDEXED_PLACEHOLDER_REGEX = regexFactory.createPlaceholderRegex((_cfg$indexedPlacehold = cfg.indexedPlaceholderTypes) !== null && _cfg$indexedPlacehold !== void 0 ? _cfg$indexedPlacehold : [], '[0-9]*'); this.IDENT_NAMED_PLACEHOLDER_REGEX = regexFactory.createPlaceholderRegex(cfg.namedPlaceholderTypes, '[a-zA-Z0-9._$]+'); this.STRING_NAMED_PLACEHOLDER_REGEX = regexFactory.createPlaceholderRegex(cfg.namedPlaceholderTypes, regexFactory.createStringPattern(cfg.stringTypes)); } /** * 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 */ _createClass(Tokenizer, [{ key: "tokenize", value: function tokenize(input) { var tokens = []; var token; // Keep processing the string until it is empty while (input.length) { // grab any preceding whitespace var whitespaceBefore = this.getWhitespace(input); input = input.substring(whitespaceBefore.length); if (input.length) { // Get the next token and the token type token = this.getNextToken(input, token); // Advance the string input = input.substring(token.value.length); tokens.push(_objectSpread(_objectSpread({}, token), {}, { whitespaceBefore: whitespaceBefore })); } } return tokens; } /** Matches preceding whitespace if present */ }, { key: "getWhitespace", value: function getWhitespace(input) { var matches = input.match(this.WHITESPACE_REGEX); return matches ? matches[1] : ''; } /** Curried function of `getTokenOnFirstMatch` that allows token type to be passed first */ }, { key: "getNextToken", value: /** Attempts to match next token from input string, tests RegExp patterns in decreasing priority */ function getNextToken(input, previousToken) { return this.matchToken(_token.TokenType.LINE_COMMENT)(input) || this.matchToken(_token.TokenType.BLOCK_COMMENT)(input) || this.matchToken(_token.TokenType.STRING)(input) || this.matchToken(_token.TokenType.BLOCK_START)(input) || this.matchToken(_token.TokenType.BLOCK_END)(input) || this.getPlaceholderToken(input) || this.matchToken(_token.TokenType.NUMBER)(input) || this.getReservedWordToken(input, previousToken) || this.matchToken(_token.TokenType.WORD)(input) || this.matchToken(_token.TokenType.OPERATOR)(input); } /** * Attempts to match a placeholder token pattern * @return {Token | undefined} - The placeholder token if found, otherwise undefined */ }, { key: "getPlaceholderToken", value: function getPlaceholderToken(input) { var _this$IDENT_NAMED_PLA, _this$STRING_NAMED_PL, _this2 = this, _this$INDEXED_PLACEHO; var placeholderTokenRegexMap = [// pattern for placeholder with identifier name { regex: (_this$IDENT_NAMED_PLA = this.IDENT_NAMED_PLACEHOLDER_REGEX) !== null && _this$IDENT_NAMED_PLA !== void 0 ? _this$IDENT_NAMED_PLA : NULL_REGEX, parseKey: function parseKey(v) { return v.slice(1); } }, // pattern for placeholder with string name { regex: (_this$STRING_NAMED_PL = this.STRING_NAMED_PLACEHOLDER_REGEX) !== null && _this$STRING_NAMED_PL !== void 0 ? _this$STRING_NAMED_PL : NULL_REGEX, parseKey: function parseKey(v) { return _this2.getEscapedPlaceholderKey({ key: v.slice(2, -1), quoteChar: v.slice(-1) }); } }, // pattern for placeholder with numeric index { regex: (_this$INDEXED_PLACEHO = this.INDEXED_PLACEHOLDER_REGEX) !== null && _this$INDEXED_PLACEHO !== void 0 ? _this$INDEXED_PLACEHO : NULL_REGEX, parseKey: function parseKey(v) { return v.slice(1); } }]; return placeholderTokenRegexMap.reduce(function (acc, _ref) { var regex = _ref.regex, parseKey = _ref.parseKey; var token = _this2.getTokenOnFirstMatch({ input: input, regex: regex, type: _token.TokenType.PLACEHOLDER }); return token ? _objectSpread(_objectSpread({}, token), {}, { key: parseKey(token.value) }) : acc; }, undefined); } }, { key: "getEscapedPlaceholderKey", value: function getEscapedPlaceholderKey(_ref2) { var key = _ref2.key, quoteChar = _ref2.quoteChar; return key.replace(new RegExp((0, _utils.escapeRegExp)('\\' + quoteChar), 'gu'), quoteChar); } /** * Attempts to match a Reserved word token pattern, avoiding edge cases of Reserved words within string tokens * @return {Token | undefined} - The Reserved word token if found, otherwise undefined */ }, { key: "getReservedWordToken", value: function getReservedWordToken(input, previousToken) { var _this3 = this; // A reserved word cannot be preceded by a '.', '[', '`', or '"' // this makes it so for "mytable.from", [from], `from`, "from" - from is not considered a Reserved word if (previousToken && ['.', '[', '`', '"'].includes(previousToken.value)) { return undefined; } // prioritised list of Reserved token types var reservedTokenList = [_token.TokenType.RESERVED_COMMAND, _token.TokenType.RESERVED_BINARY_COMMAND, _token.TokenType.RESERVED_DEPENDENT_CLAUSE, _token.TokenType.RESERVED_LOGICAL_OPERATOR, _token.TokenType.RESERVED_KEYWORD]; return reservedTokenList.reduce(function (matchedToken, tokenType) { return matchedToken || _this3.matchToken(tokenType)(input); }, undefined); } /** * Attempts to match RegExp from head of input, returning undefined if not found * @param {string} _.input - The string to match * @param {TokenType} _.type - The type of token to match against * @param {RegExp} _.regex - The regex to match * @return {Token | undefined} - The matched token if found, otherwise undefined */ }, { key: "getTokenOnFirstMatch", value: function getTokenOnFirstMatch(_ref3) { var input = _ref3.input, type = _ref3.type, regex = _ref3.regex; var matches = input.match(regex); return matches ? { type: type, value: matches[1] } : undefined; } }]); return Tokenizer; }(); exports["default"] = Tokenizer; module.exports = exports.default; //# sourceMappingURL=Tokenizer.js.map