commit 8463df1d08a0a1a3d98ed44e0bed3c683459c121 Author: Ed Sanders Date: Tue Jan 17 17:29:58 2023 +0000 Update papaparse to 5.3.2 Change-Id: I0c8a73b84fb8b8e86d28219acbd5b7f16d08f29f diff --git a/lib/papaparse/papaparse.js b/lib/papaparse/papaparse.js index b624e5031..1b9ea513d 100644 --- a/lib/papaparse/papaparse.js +++ b/lib/papaparse/papaparse.js @@ -1,6 +1,6 @@ /* @license Papa Parse -v5.1.0 +v5.3.2 https://github.com/mholt/PapaParse License: MIT */ @@ -282,6 +282,9 @@ License: MIT /** the columns (keys) we expect when we unparse objects */ var _columns = null; + /** whether to prevent outputting cells that can be parsed as formulae by spreadsheet software (Excel and LibreOffice) */ + var _escapeFormulae = false; + unpackConfig(); var quoteCharRegex = new RegExp(escapeRegExp(_quoteChar), 'g'); @@ -294,7 +297,7 @@ License: MIT if (!_input.length || Array.isArray(_input[0])) return serialize(null, _input, _skipEmptyLines); else if (typeof _input[0] === 'object') - return serialize(_columns || objectKeys(_input[0]), _input, _skipEmptyLines); + return serialize(_columns || Object.keys(_input[0]), _input, _skipEmptyLines); } else if (typeof _input === 'object') { @@ -304,12 +307,14 @@ License: MIT if (Array.isArray(_input.data)) { if (!_input.fields) - _input.fields = _input.meta && _input.meta.fields; + _input.fields = _input.meta && _input.meta.fields || _columns; if (!_input.fields) _input.fields = Array.isArray(_input.data[0]) ? _input.fields - : objectKeys(_input.data[0]); + : typeof _input.data[0] === 'object' + ? Object.keys(_input.data[0]) + : []; if (!(Array.isArray(_input.data[0])) && typeof _input.data[0] !== 'object') _input.data = [_input.data]; // handles input like [1,2,3] or ['asdf'] @@ -361,18 +366,10 @@ License: MIT if (_config.escapeChar !== undefined) { _escapedQuote = _config.escapeChar + _quoteChar; } - } - - /** Turns an object's keys into an array */ - function objectKeys(obj) - { - if (typeof obj !== 'object') - return []; - var keys = []; - for (var key in obj) - keys.push(key); - return keys; + if (typeof _config.escapeFormulae === 'boolean' || _config.escapeFormulae instanceof RegExp) { + _escapeFormulae = _config.escapeFormulae instanceof RegExp ? _config.escapeFormulae : /^[=+\-@\t\r].*$/; + } } /** The double for loop that iterates the data and writes out a CSV string including header row */ @@ -447,9 +444,17 @@ License: MIT if (str.constructor === Date) return JSON.stringify(str).slice(1, 25); + var needsQuotes = false; + + if (_escapeFormulae && typeof str === "string" && _escapeFormulae.test(str)) { + str = "'" + str; + needsQuotes = true; + } + var escapedQuoteStr = str.toString().replace(quoteCharRegex, _escapedQuote); - var needsQuotes = (typeof _quotes === 'boolean' && _quotes) + needsQuotes = needsQuotes + || _quotes === true || (typeof _quotes === 'function' && _quotes(str, col)) || (Array.isArray(_quotes) && _quotes[col]) || hasAny(escapedQuoteStr, Papa.BAD_DELIMITERS) @@ -642,7 +647,7 @@ License: MIT xhr.onerror = bindFunction(this._chunkError, this); } - xhr.open('GET', this._input, !IS_WORKER); + xhr.open(this._config.downloadRequestBody ? 'POST' : 'GET', this._input, !IS_WORKER); // Headers can only be set when once the request state is OPENED if (this._config.downloadRequestHeaders) { @@ -661,7 +666,7 @@ License: MIT } try { - xhr.send(); + xhr.send(this._config.downloadRequestBody); } catch (err) { this._chunkError(err.message); @@ -682,7 +687,8 @@ License: MIT return; } - this._start += xhr.responseText.length; + // Use chunckSize as it may be a diference on reponse lentgh due to characters with more than 1 byte + this._start += this._config.chunkSize ? this._config.chunkSize : xhr.responseText.length; this._finished = !this._config.chunkSize || this._start >= getFileSize(xhr); this.parseChunk(xhr.responseText); }; @@ -699,7 +705,7 @@ License: MIT if (contentRange === null) { // no content range, then finish! return -1; } - return parseInt(contentRange.substr(contentRange.lastIndexOf('/') + 1)); + return parseInt(contentRange.substring(contentRange.lastIndexOf('/') + 1)); } } NetworkStreamer.prototype = Object.create(ChunkStreamer.prototype); @@ -788,8 +794,14 @@ License: MIT { if (this._finished) return; var size = this._config.chunkSize; - var chunk = size ? remaining.substr(0, size) : remaining; - remaining = size ? remaining.substr(size) : ''; + var chunk; + if(size) { + chunk = remaining.substring(0, size); + remaining = remaining.substring(size); + } else { + chunk = remaining; + remaining = ''; + } this._finished = !remaining; return this.parseChunk(chunk); }; @@ -999,8 +1011,8 @@ License: MIT // One goal is to minimize the use of regular expressions... var MAX_FLOAT = Math.pow(2, 53); var MIN_FLOAT = -MAX_FLOAT; - var FLOAT = /^\s*-?(\d*\.?\d+|\d+\.?\d*)(e[-+]?\d+)?\s*$/i; - var ISO_DATE = /(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d\.\d+([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))/; + var FLOAT = /^\s*-?(\d+\.?|\.\d+|\d+\.\d+)([eE][-+]?\d+)?\s*$/; + var ISO_DATE = /^(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d\.\d+([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))$/; var self = this; var _stepCounter = 0; // Number of times step was called (number of rows parsed) var _rowCounter = 0; // Number of rows that have been parsed so far @@ -1036,8 +1048,10 @@ License: MIT _stepCounter += results.data.length; if (_config.preview && _stepCounter > _config.preview) _parser.abort(); - else + else { + _results.data = _results.data[0]; userStep(_results, self); + } } }; } @@ -1092,7 +1106,10 @@ License: MIT { _paused = true; _parser.abort(); - _input = _input.substr(_parser.getCharIndex()); + + // If it is streaming via "chunking", the reader will start appending correctly already so no need to substring, + // otherwise we can get duplicate content within a row + _input = isFunction(_config.chunk) ? "" : _input.substring(_parser.getCharIndex()); }; this.resume = function() @@ -1103,7 +1120,7 @@ License: MIT } else { // Bugfix: #636 In case the processing hasn't halted yet // wait for it to halt in order to resume - setTimeout(this.resume, 3); + setTimeout(self.resume, 3); } }; @@ -1146,9 +1163,9 @@ License: MIT if (_config.skipEmptyLines) { - for (var i = 0; i < _results.data.length; i++) - if (testEmptyLine(_results.data[i])) - _results.data.splice(i--, 1); + _results.data = _results.data.filter(function(d) { + return !testEmptyLine(d); + }); } if (needsHeaderRow()) @@ -1167,10 +1184,10 @@ License: MIT if (!_results) return; - function addHeder(header) + function addHeader(header, i) { if (isFunction(_config.transformHeader)) - header = _config.transformHeader(header); + header = _config.transformHeader(header, i); _fields.push(header); } @@ -1178,13 +1195,13 @@ License: MIT if (Array.isArray(_results.data[0])) { for (var i = 0; needsHeaderRow() && i < _results.data.length; i++) - _results.data[i].forEach(addHeder); + _results.data[i].forEach(addHeader); _results.data.splice(0, 1); } // if _results.data[0] is not an array, we are in a step where _results.data is the row. else - _results.data.forEach(addHeder); + _results.data.forEach(addHeader); } function shouldApplyDynamicTyping(field) { @@ -1330,7 +1347,7 @@ License: MIT function guessLineEndings(input, quoteChar) { - input = input.substr(0, 1024 * 1024); // max length 1 MB + input = input.substring(0, 1024 * 1024); // max length 1 MB // Replace all the text inside quotes var re = new RegExp(escapeRegExp(quoteChar) + '([^]*?)' + escapeRegExp(quoteChar), 'gm'); input = input.replace(re, ''); @@ -1356,12 +1373,15 @@ License: MIT function addError(type, code, msg, row) { - _results.errors.push({ + var error = { type: type, code: code, - message: msg, - row: row - }); + message: msg + }; + if(row !== undefined) { + error.row = row; + } + _results.errors.push(error); } } @@ -1383,8 +1403,7 @@ License: MIT var preview = config.preview; var fastMode = config.fastMode; var quoteChar; - /** Allows for no quoteChar by setting quoteChar to undefined in config */ - if (config.quoteChar === undefined) { + if (config.quoteChar === undefined || config.quoteChar === null) { quoteChar = '"'; } else { quoteChar = config.quoteChar; @@ -1448,7 +1467,7 @@ License: MIT cursor += newline.length; else if (ignoreLastRow) return returnable(); - if (comments && row.substr(0, commentsLen) === comments) + if (comments && row.substring(0, commentsLen) === comments) continue; if (stepIsFunction) { @@ -1528,12 +1547,18 @@ License: MIT continue; } + if(nextDelim !== -1 && nextDelim < (quoteSearch + 1)) { + nextDelim = input.indexOf(delim, (quoteSearch + 1)); + } + if(nextNewline !== -1 && nextNewline < (quoteSearch + 1)) { + nextNewline = input.indexOf(newline, (quoteSearch + 1)); + } // Check up to nextDelim or nextNewline, whichever is closest var checkUpTo = nextNewline === -1 ? nextDelim : Math.min(nextDelim, nextNewline); var spacesBetweenQuoteAndDelimiter = extraSpaces(checkUpTo); // Closing quote followed by delimiter or 'unnecessary spaces + delimiter' - if (input[quoteSearch + 1 + spacesBetweenQuoteAndDelimiter] === delim) + if (input.substr(quoteSearch + 1 + spacesBetweenQuoteAndDelimiter, delimLen) === delim) { row.push(input.substring(cursor, quoteSearch).replace(quoteCharRegex, quoteChar)); cursor = quoteSearch + 1 + spacesBetweenQuoteAndDelimiter + delimLen; @@ -1551,7 +1576,7 @@ License: MIT var spacesBetweenQuoteAndNewLine = extraSpaces(nextNewline); // Closing quote followed by newline or 'unnecessary spaces + newLine' - if (input.substr(quoteSearch + 1 + spacesBetweenQuoteAndNewLine, newlineLen) === newline) + if (input.substring(quoteSearch + 1 + spacesBetweenQuoteAndNewLine, quoteSearch + 1 + spacesBetweenQuoteAndNewLine + newlineLen) === newline) { row.push(input.substring(cursor, quoteSearch).replace(quoteCharRegex, quoteChar)); saveRow(quoteSearch + 1 + spacesBetweenQuoteAndNewLine + newlineLen); @@ -1590,7 +1615,7 @@ License: MIT } // Comment found at start of new line - if (comments && row.length === 0 && input.substr(cursor, commentsLen) === comments) + if (comments && row.length === 0 && input.substring(cursor, cursor + commentsLen) === comments) { if (nextNewline === -1) // Comment ends at EOF return returnable(); @@ -1603,27 +1628,11 @@ License: MIT // Next delimiter comes before next newline, so we've reached end of field if (nextDelim !== -1 && (nextDelim < nextNewline || nextNewline === -1)) { - // we check, if we have quotes, because delimiter char may be part of field enclosed in quotes - if (quoteSearch > nextDelim) { - // we have quotes, so we try to find the next delimiter not enclosed in quotes and also next starting quote char - var nextDelimObj = getNextUnqotedDelimiter(nextDelim, quoteSearch, nextNewline); - - // if we have next delimiter char which is not enclosed in quotes - if (nextDelimObj && typeof nextDelimObj.nextDelim !== 'undefined') { - nextDelim = nextDelimObj.nextDelim; - quoteSearch = nextDelimObj.quoteSearch; - row.push(input.substring(cursor, nextDelim)); - cursor = nextDelim + delimLen; - // we look for next delimiter char - nextDelim = input.indexOf(delim, cursor); - continue; - } - } else { - row.push(input.substring(cursor, nextDelim)); - cursor = nextDelim + delimLen; - nextDelim = input.indexOf(delim, cursor); - continue; - } + row.push(input.substring(cursor, nextDelim)); + cursor = nextDelim + delimLen; + // we look for next delimiter char + nextDelim = input.indexOf(delim, cursor); + continue; } // End of row @@ -1682,7 +1691,7 @@ License: MIT if (ignoreLastRow) return returnable(); if (typeof value === 'undefined') - value = input.substr(cursor); + value = input.substring(cursor); row.push(value); cursor = inputLen; // important in case parsing is paused pushRow(row); @@ -1706,11 +1715,10 @@ License: MIT } /** Returns an object with the results, errors, and meta. */ - function returnable(stopped, step) + function returnable(stopped) { - var isStep = step || false; return { - data: isStep ? data[0] : data, + data: data, errors: errors, meta: { delimiter: delim, @@ -1725,44 +1733,10 @@ License: MIT /** Executes the user's step function and resets data & errors. */ function doStep() { - step(returnable(undefined, true)); + step(returnable()); data = []; errors = []; } - - /** Gets the delimiter character, which is not inside the quoted field */ - function getNextUnqotedDelimiter(nextDelim, quoteSearch, newLine) { - var result = { - nextDelim: undefined, - quoteSearch: undefined - }; - // get the next closing quote character - var nextQuoteSearch = input.indexOf(quoteChar, quoteSearch + 1); - - // if next delimiter is part of a field enclosed in quotes - if (nextDelim > quoteSearch && nextDelim < nextQuoteSearch && (nextQuoteSearch < newLine || newLine === -1)) { - // get the next delimiter character after this one - var nextNextDelim = input.indexOf(delim, nextQuoteSearch); - - // if there is no next delimiter, return default result - if (nextNextDelim === -1) { - return result; - } - // find the next opening quote char position - if (nextNextDelim > nextQuoteSearch) { - nextQuoteSearch = input.indexOf(quoteChar, nextQuoteSearch + 1); - } - // try to get the next delimiter position - result = getNextUnqotedDelimiter(nextNextDelim, nextQuoteSearch, newLine); - } else { - result = { - nextDelim: nextDelim, - quoteSearch: quoteSearch - }; - } - - return result; - } }; /** Sets the abort flag */