Steve Block | a7e24c1 | 2009-10-30 11:49:00 +0000 | [diff] [blame] | 1 | // Copyright 2009 the V8 project authors. All rights reserved. |
| 2 | // Redistribution and use in source and binary forms, with or without |
| 3 | // modification, are permitted provided that the following conditions are |
| 4 | // met: |
| 5 | // |
| 6 | // * Redistributions of source code must retain the above copyright |
| 7 | // notice, this list of conditions and the following disclaimer. |
| 8 | // * Redistributions in binary form must reproduce the above |
| 9 | // copyright notice, this list of conditions and the following |
| 10 | // disclaimer in the documentation and/or other materials provided |
| 11 | // with the distribution. |
| 12 | // * Neither the name of Google Inc. nor the names of its |
| 13 | // contributors may be used to endorse or promote products derived |
| 14 | // from this software without specific prior written permission. |
| 15 | // |
| 16 | // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 17 | // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 18 | // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 19 | // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
| 20 | // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 21 | // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 22 | // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
| 23 | // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
| 24 | // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 25 | // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 26 | // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 27 | |
| 28 | |
Steve Block | a7e24c1 | 2009-10-30 11:49:00 +0000 | [diff] [blame] | 29 | /** |
| 30 | * Creates a CSV lines parser. |
| 31 | */ |
Steve Block | 1e0659c | 2011-05-24 12:43:12 +0100 | [diff] [blame] | 32 | function CsvParser() { |
Steve Block | a7e24c1 | 2009-10-30 11:49:00 +0000 | [diff] [blame] | 33 | }; |
| 34 | |
| 35 | |
| 36 | /** |
Leon Clarke | 4515c47 | 2010-02-03 11:58:03 +0000 | [diff] [blame] | 37 | * A regex for matching a CSV field. |
Steve Block | a7e24c1 | 2009-10-30 11:49:00 +0000 | [diff] [blame] | 38 | * @private |
| 39 | */ |
Steve Block | 1e0659c | 2011-05-24 12:43:12 +0100 | [diff] [blame] | 40 | CsvParser.CSV_FIELD_RE_ = /^"((?:[^"]|"")*)"|([^,]*)/; |
Steve Block | a7e24c1 | 2009-10-30 11:49:00 +0000 | [diff] [blame] | 41 | |
| 42 | |
| 43 | /** |
| 44 | * A regex for matching a double quote. |
| 45 | * @private |
| 46 | */ |
Steve Block | 1e0659c | 2011-05-24 12:43:12 +0100 | [diff] [blame] | 47 | CsvParser.DOUBLE_QUOTE_RE_ = /""/g; |
Steve Block | a7e24c1 | 2009-10-30 11:49:00 +0000 | [diff] [blame] | 48 | |
| 49 | |
| 50 | /** |
| 51 | * Parses a line of CSV-encoded values. Returns an array of fields. |
| 52 | * |
| 53 | * @param {string} line Input line. |
| 54 | */ |
Steve Block | 1e0659c | 2011-05-24 12:43:12 +0100 | [diff] [blame] | 55 | CsvParser.prototype.parseLine = function(line) { |
| 56 | var fieldRe = CsvParser.CSV_FIELD_RE_; |
| 57 | var doubleQuoteRe = CsvParser.DOUBLE_QUOTE_RE_; |
Leon Clarke | 4515c47 | 2010-02-03 11:58:03 +0000 | [diff] [blame] | 58 | var pos = 0; |
| 59 | var endPos = line.length; |
Steve Block | a7e24c1 | 2009-10-30 11:49:00 +0000 | [diff] [blame] | 60 | var fields = []; |
Leon Clarke | 4515c47 | 2010-02-03 11:58:03 +0000 | [diff] [blame] | 61 | if (endPos > 0) { |
| 62 | do { |
| 63 | var fieldMatch = fieldRe.exec(line.substr(pos)); |
| 64 | if (typeof fieldMatch[1] === "string") { |
| 65 | var field = fieldMatch[1]; |
| 66 | pos += field.length + 3; // Skip comma and quotes. |
| 67 | fields.push(field.replace(doubleQuoteRe, '"')); |
| 68 | } else { |
| 69 | // The second field pattern will match anything, thus |
| 70 | // in the worst case the match will be an empty string. |
| 71 | var field = fieldMatch[2]; |
| 72 | pos += field.length + 1; // Skip comma. |
| 73 | fields.push(field); |
| 74 | } |
| 75 | } while (pos <= endPos); |
Steve Block | a7e24c1 | 2009-10-30 11:49:00 +0000 | [diff] [blame] | 76 | } |
| 77 | return fields; |
| 78 | }; |