csv-parse
Advanced tools
Comparing version 0.0.3 to 0.0.4
// Generated by CoffeeScript 1.7.1 | ||
var Parser, stream, util; | ||
stream = require('stream'); | ||
util = require('util'); | ||
module.exports = function() { | ||
@@ -16,5 +20,13 @@ var callback, called, chunks, data, options, parser; | ||
} | ||
callback = arguments[1]; | ||
if (typeof arguments[1] === 'function') { | ||
callback = arguments[1]; | ||
} else { | ||
options = arguments[1]; | ||
} | ||
} else if (arguments.length === 1) { | ||
options = arguments[0]; | ||
if (typeof arguments[0] === 'function') { | ||
callback = arguments[0]; | ||
} else { | ||
options = arguments[0]; | ||
} | ||
} | ||
@@ -25,11 +37,11 @@ if (options == null) { | ||
parser = new Parser(options); | ||
if (data || callback) { | ||
if (data) { | ||
process.nextTick(function() { | ||
parser.write(data); | ||
return parser.end(); | ||
}); | ||
} | ||
if (callback) { | ||
called = false; | ||
chunks = options.objname ? {} : []; | ||
if (data) { | ||
process.nextTick(function() { | ||
parser.write(data); | ||
return parser.end(); | ||
}); | ||
} | ||
parser.on('readable', function() { | ||
@@ -60,6 +72,2 @@ var chunk, _results; | ||
stream = require('stream'); | ||
util = require('util'); | ||
Parser = function(options) { | ||
@@ -189,3 +197,3 @@ var _base, _base1, _base10, _base2, _base3, _base4, _base5, _base6, _base7, _base8, _base9; | ||
Parser.prototype.__write = function(chars, end, callback) { | ||
var areNextCharsRowDelimiters, char, delimLength, escapeIsQuote, i, isDelimiter, isEscape, isQuote, isRowDelimiter, l, ltrim, nextNextCharPas, nextNextCharPos, rowDelimiter, rtrim, _results; | ||
var areNextCharsRowDelimiters, char, delimLength, escapeIsQuote, i, isDelimiter, isEscape, isQuote, isRowDelimiter, l, ltrim, nextCharPos, rowDelimiter, rtrim, _results; | ||
ltrim = this.options.trim || this.options.ltrim; | ||
@@ -213,12 +221,12 @@ rtrim = this.options.trim || this.options.rtrim; | ||
rowDelimiter = char; | ||
nextNextCharPos = i + 1; | ||
nextCharPos = i + 1; | ||
} else if (this.nextChar === '\n' || this.nextChar === '\r') { | ||
rowDelimiter = this.nextChar; | ||
nextNextCharPas = i + 2; | ||
nextCharPos = i + 2; | ||
} | ||
if (rowDelimiter) { | ||
if (rowDelimiter === '\r' && chars.charAt(nextCharPos) === '\n') { | ||
rowDelimiter += '\n'; | ||
} | ||
this.options.rowDelimiter = rowDelimiter; | ||
if (rowDelimiter === '\r' && chars.charAt(nextNextCharPas) === '\n') { | ||
this.options.rowDelimiter += '\n'; | ||
} | ||
delimLength = this.options.rowDelimiter.length; | ||
@@ -225,0 +233,0 @@ } |
{ | ||
"version": "0.0.3", | ||
"version": "0.0.4", | ||
"name": "csv-parse", | ||
"description": "CSV parsing implementing the Node.js `stream.Transform` API", | ||
"keywords": [ "csv", "parse", "parser" ], | ||
"contributors": [ | ||
"David Worms <david@adaltas.com> (http://www.adaltas.com)", | ||
"Will White (https://github.com/willwhite)", | ||
"Justin Latimer (https://github.com/justinlatimer)", | ||
"jonseymour (https://github.com/jonseymour)", | ||
"pascalopitz (https://github.com/pascalopitz)", | ||
"Josh Pschorr (https://github.com/jpschorr)", | ||
"Elad Ben-Israel (https://github.com/eladb)", | ||
"Philippe Plantier (https://github.com/phipla)", | ||
"Tim Oxley (https://github.com/timoxley)", | ||
"Damon Oehlman (https://github.com/DamonOehlman)", | ||
"Alexandru Topliceanu (https://github.com/topliceanu)", | ||
"Visup (https://github.com/visup)", | ||
"Edmund von der Burg (https://github.com/evdb)", | ||
"Douglas Christopher Wilson (https://github.com/dougwilson)", | ||
"Joe Eaves (https://github.com/Joeasaurus)", | ||
"Mark Stosberg (https://github.com/markstos)" | ||
], | ||
"licenses": [{ | ||
"type": "BSD", | ||
"url": "https://github.com/wdavidw/node-csv-parse/blob/master/LICENSE" | ||
}], | ||
"repository": { | ||
@@ -11,4 +34,6 @@ "type": "git", | ||
"devDependencies": { | ||
"each": "latest", | ||
"coffee-script": "latest", | ||
"csv-generate": "latest", | ||
"csv-spectrum": "latest", | ||
"mocha": "latest", | ||
@@ -15,0 +40,0 @@ "should": "latest" |
111
README.md
@@ -5,20 +5,21 @@ [![Build Status](https://secure.travis-ci.org/wdavidw/node-csv-parse.png)](http://travis-ci.org/wdavidw/node-csv-parse) | ||
parser converting CSV text input into arrays or objects. It implements the | ||
Node.js `stream.Transform` API. It also provides a simple callback-base API for | ||
converniency. It is both extremely easy to use and powerfull. It was first | ||
released in 2010 and is used against big datasets by a large community. | ||
Node.js [stream.Transform`API](http://nodejs.org/api/stream.html#stream_class_stream_transform). It also provides a simple callback-base API for convenience. It is both extremely easy to use and powerful. It was first | ||
released in 2010 and is used against big data sets by a large community. | ||
[The full documentation of the CSV parser is available here](http://www.adaltas.com/projects/node-csv/). | ||
Note | ||
---- | ||
## Features | ||
This module is to be considered in beta stage. It is part of an ongoing effort | ||
to split the current CSV module into complementary modules with a cleaner design | ||
and the latest stream implementation. However, the code has been imported with | ||
very little changes and you should feel confident to use it in your code. | ||
* Follow the Node.js streaming API | ||
* Support delimiters, quotes, escape characters and comments | ||
* Line breaks discovery | ||
* Support big datasets | ||
* Complete test coverage and samples for inspiration | ||
* no external dependencies | ||
* to be used conjointly with `csv-generate`, `stream-transform` and `csv-stringify` | ||
Usage | ||
----- | ||
Run `npm install csv` to install the full csv module or run | ||
## Usage | ||
Run `npm install csv` to install the full CSV package or run | ||
`npm install csv-parse` if you are only interested by the CSV parser. | ||
@@ -34,9 +35,12 @@ | ||
The parser receive a string and return an array inside a user-provided | ||
The parser receive a string and returns an array inside a user-provided | ||
callback. This example is available with the command `node samples/callback.js`. | ||
See the full list of supported parsing options below. | ||
```javascript | ||
var parse = require('csv-parse'); | ||
require('should'); | ||
input = '#Welcome\n"1","2","3","4"\n"a","b","c","d"'; | ||
var input = '#Welcome\n"1","2","3","4"\n"a","b","c","d"'; | ||
parse(input, {comment: '#'}, function(err, output){ | ||
@@ -48,17 +52,29 @@ output.should.eql([ [ '1', '2', '3', '4' ], [ 'a', 'b', 'c', 'd' ] ]); | ||
### Using the stream API | ||
The CSV parser implements the [stream.Transform`API][stream_transform]. | ||
CSV data is send through the `write` function and the resulted data is obtained | ||
within the "readable" event by calling the `read` function. This example is | ||
available with the command `node samples/stream.js`. | ||
See the full list of supported parser options below. | ||
```javascript | ||
// node samples/stream.js | ||
var parse = require('csv-parse'); | ||
require('should'); | ||
output = []; | ||
parser = parse({delimiter: ':'}) | ||
var output = []; | ||
// Create the parser | ||
var parser = parse({delimiter: ':'}); | ||
// Use the writable stream api | ||
parser.on('readable', function(){ | ||
while(row = parser.read()){ | ||
output.push(row) | ||
while(record = parser.read()){ | ||
output.push(record); | ||
} | ||
}); | ||
// Catch any error | ||
parser.on('error', function(err){ | ||
consol.log(err.message); | ||
console.log(err.message); | ||
}); | ||
// When we are done, test that the parsed output matched what expected | ||
parser.on('finish', function(){ | ||
@@ -70,5 +86,7 @@ output.should.eql([ | ||
}); | ||
// Now that setup is done, write data to the stream | ||
parser.write("root:x:0:0:root:/root:/bin/bash\n"); | ||
parser.write("someone:x:1022:1022:a funny cat:/home/someone:/bin/bash\n"); | ||
parser.end() | ||
// Close the readable stream | ||
parser.end(); | ||
``` | ||
@@ -78,14 +96,18 @@ | ||
One usefull function part of the Stream API is `pipe` to interact between | ||
One useful function part of the Stream API is `pipe` to interact between | ||
multiple streams. You may use this function to pipe a `stream.Readable` string | ||
source to a `stream.Writable` object destination. The next example available as | ||
source to a `stream.Writable` object destination. This example available as | ||
`node samples/pipe.js` read the file, parse its content and transform it. | ||
```javascript | ||
output = []; | ||
parser = parse({delimiter: ':'}) | ||
input = fs.createReadStream('/etc/passwd'); | ||
transformer = transform(function(row, callback){ | ||
var fs = require('fs'); | ||
var parse = require('csv-parse'); | ||
var transform = require('stream-transform'); | ||
var output = []; | ||
var parser = parse({delimiter: ':'}) | ||
var input = fs.createReadStream('/etc/passwd'); | ||
var transformer = transform(function(record, callback){ | ||
setTimeout(function(){ | ||
callback(null, row.join(' ')+'\n'); | ||
callback(null, record.join(' ')+'\n'); | ||
}, 500); | ||
@@ -96,5 +118,18 @@ }, {parallel: 10}); | ||
Migration | ||
--------- | ||
## Parser options | ||
* `delimiter` Set the field delimiter. One character only, defaults to comma. | ||
* `rowDelimiter` String used to delimit record rows or a special value; special values are 'auto', 'unix', 'mac', 'windows', 'unicode'; defaults to 'auto' (discovered in source or 'unix' if no source is specified). | ||
* `quote` Optionnal character surrounding a field, one character only, defaults to double quotes. | ||
* `escape` Set the escape character, one character only, defaults to double quotes. | ||
* `columns` List of fields as an array, a user defined callback accepting the first line and returning the column names or true if autodiscovered in the first CSV line, default to null, affect the result data set in the sense that records will be objects instead of arrays. | ||
* `comment` Treat all the characteres after this one as a comment, default to '#'. | ||
* `objname` Name of header-record title to name objects by. | ||
* `trim` If true, ignore whitespace immediately around the delimiter, defaults to false. | ||
* `ltrim` If true, ignore whitespace immediately following the delimiter (i.e. left-trim all fields), defaults to false. | ||
* `rtrim` If true, ignore whitespace immediately preceding the delimiter (i.e. right-trim all fields), defaults to false. | ||
* `auto_parse` If true, the parser will attempt to convert read data types to native types. | ||
## Migration | ||
Most of the generator is imported from its parent project [CSV][csv] in a effort | ||
@@ -104,5 +139,7 @@ to split it between the generator, the parser, the transformer and the | ||
Development | ||
----------- | ||
The "record" has disappeared, you are encouraged to use the "readable" event conjointly | ||
with the "read" function as documented above and in the [Stream API][stream_transform]. | ||
## Development | ||
Tests are executed with mocha. To install it, simple run `npm install` | ||
@@ -116,3 +153,3 @@ followed by `npm test`. It will install mocha and its dependencies in your | ||
The test suite is run online with [Travis][travis] against the versions | ||
0.9, 0.10 and 0.11 of Node.js. | ||
0.10 and 0.11 of Node.js. | ||
@@ -138,13 +175,9 @@ Contributors | ||
* Joeasaurus: <https://github.com/Joeasaurus> | ||
* Mark Stosberg: <https://github.com/markstos> | ||
Related projects | ||
---------------- | ||
* Pavel Kolesnikov "ya-csv": <http://github.com/koles/ya-csv> | ||
* Chris Williams "node-csv": <http://github.com/voodootikigod/node-csv> | ||
[csv]: https://github.com/wdavidw/node-csv | ||
[csv-samples]: https://github.com/wdavidw/node-csv-parse/tree/master/samples | ||
[csv-test]: https://github.com/wdavidw/node-csv-parse/tree/master/test | ||
[stream_transform]: http://nodejs.org/api/stream.html#stream_class_stream_transform | ||
[travis]: https://travis-ci.org/#!/wdavidw/node-csv-parse | ||
should = require('should'); | ||
parse = require('../lib'); | ||
var parse = require('../lib'); | ||
require('should'); | ||
input = '#Welcome\n"1","2","3","4"\n"a","b","c","d"'; | ||
var input = '#Welcome\n"1","2","3","4"\n"a","b","c","d"'; | ||
parse(input, {comment: '#'}, function(err, output){ | ||
output.should.eql([ [ '1', '2', '3', '4' ], [ 'a', 'b', 'c', 'd' ] ]); | ||
}); |
var fs = require('fs'); | ||
var parse = require('../lib'); | ||
var parse = require('..'); | ||
var transform = require('../../stream-transform'); | ||
output = []; | ||
parser = parse({delimiter: ':'}) | ||
input = fs.createReadStream('/etc/passwd'); | ||
transformer = transform(function(row, callback){ | ||
var output = []; | ||
var parser = parse({delimiter: ':'}) | ||
var input = fs.createReadStream('/etc/passwd'); | ||
var transformer = transform(function(record, callback){ | ||
setTimeout(function(){ | ||
callback(null, row.join(' ')+'\n'); | ||
callback(null, record.join(' ')+'\n'); | ||
}, 500); | ||
@@ -13,0 +13,0 @@ }, {parallel: 10}); |
var parse = require('../lib'); | ||
require('should'); | ||
var parse = require('../lib'); | ||
output = []; | ||
parser = parse({delimiter: ':'}) | ||
var output = []; | ||
// Create the parser | ||
var parser = parse({delimiter: ':'}); | ||
// Use the writable stream api | ||
parser.on('readable', function(){ | ||
while(row = parser.read()){ | ||
output.push(row) | ||
while(record = parser.read()){ | ||
output.push(record); | ||
} | ||
}); | ||
// Catch any error | ||
parser.on('error', function(err){ | ||
consol.log(err.message); | ||
console.log(err.message); | ||
}); | ||
// When we are done, test that the parsed output matched what expected | ||
parser.on('finish', function(){ | ||
@@ -21,5 +25,7 @@ output.should.eql([ | ||
}); | ||
// Now that setup is done, write data to the stream | ||
parser.write("root:x:0:0:root:/root:/bin/bash\n"); | ||
parser.write("someone:x:1022:1022:a funny cat:/home/someone:/bin/bash\n"); | ||
parser.end() | ||
// Close the readable stream | ||
parser.end(); | ||
# `Parser([options])` | ||
# CSV Parser | ||
@@ -16,26 +16,18 @@ This module provides a CSV parser tested and used against large datasets. Over | ||
## Legacy | ||
Please look at the [README], the [samples] and the [tests] for additional | ||
information. | ||
Important: this documentation covers the latest version (0.3.x) of | ||
`node-csv-parser`. Older version are available on GitHub: | ||
[0.1.x](https://github.com/wdavidw/node-csv/tree/v0.1), | ||
[0.2.x](https://github.com/wdavidw/node-csv/tree/v0.2). | ||
stream = require 'stream' | ||
util = require 'util' | ||
## Installation | ||
## Usage | ||
```bash | ||
npm install csv | ||
``` | ||
Callback approach, for ease of use: | ||
## Usage | ||
`parse(data, [options], callback)` | ||
There are two ways to use the parser: | ||
Stream API, for maximum of power: | ||
* `parse(data, [options], callback)` | ||
Callback approach, for ease of use. | ||
* `parse([options], [callback])` | ||
Stream API, for maximum of power. | ||
`parse([options], [callback])` | ||
Look at the examples below to discover the usage. | ||
module.exports = -> | ||
@@ -48,17 +40,20 @@ if arguments.length is 3 | ||
if typeof arguments[0] is 'string' | ||
data = arguments[0] | ||
else | ||
options = arguments[0] | ||
callback = arguments[1] | ||
then data = arguments[0] | ||
else options = arguments[0] | ||
if typeof arguments[1] is 'function' | ||
then callback = arguments[1] | ||
else options = arguments[1] | ||
else if arguments.length is 1 | ||
options = arguments[0] | ||
if typeof arguments[0] is 'function' | ||
then callback = arguments[0] | ||
else options = arguments[0] | ||
options ?= {} | ||
parser = new Parser options | ||
if data or callback | ||
if data | ||
process.nextTick -> | ||
parser.write data | ||
parser.end() | ||
if callback | ||
called = false | ||
chunks = if options.objname then {} else [] | ||
if data | ||
process.nextTick -> | ||
parser.write data | ||
parser.end() | ||
parser.on 'readable', -> | ||
@@ -77,4 +72,3 @@ while chunk = parser.read() | ||
stream = require 'stream' | ||
util = require 'util' | ||
## `Parser([options])` | ||
@@ -222,9 +216,9 @@ * `delimiter` Set the field delimiter. One character only, defaults to comma. | ||
rowDelimiter = char | ||
nextNextCharPos = i+1 | ||
nextCharPos = i+1 | ||
else if @nextChar is '\n' or @nextChar is '\r' | ||
rowDelimiter = @nextChar | ||
nextNextCharPas = i+2 | ||
nextCharPos = i+2 | ||
if rowDelimiter | ||
rowDelimiter += '\n' if rowDelimiter is '\r' and chars.charAt(nextCharPos) is '\n' | ||
@options.rowDelimiter = rowDelimiter | ||
@options.rowDelimiter += '\n' if rowDelimiter is '\r' and chars.charAt(nextNextCharPas) is '\n' | ||
delimLength = @options.rowDelimiter.length | ||
@@ -288,3 +282,2 @@ # Parse that damn char | ||
@field = @field.trimRight() | ||
if (@options.auto_parse and @floatRegexp.test(@field)) | ||
@@ -317,2 +310,5 @@ @line.push parseFloat(@field) | ||
[readme]: https://github.com/wdavidw/node-csv-parse | ||
[samples]: https://github.com/wdavidw/node-csv-parse/tree/master/samples | ||
[tests]: https://github.com/wdavidw/node-csv-parse/tree/master/test | ||
[transform]: (http://nodejs.org/api/stream.html#stream_class_stream_transform_1) |
Sorry, the diff of this file is not supported yet
Sorry, the diff of this file is not supported yet
Sorry, the diff of this file is not supported yet
License Policy Violation
LicenseThis package is not allowed per your license policy. Review the package's license to ensure compliance.
Found 1 instance in 1 package
License Policy Violation
LicenseThis package is not allowed per your license policy. Review the package's license to ensure compliance.
Found 1 instance in 1 package
No contributors or author data
MaintenancePackage does not specify a list of contributors or an author in package.json.
Found 1 instance in 1 package
No License Found
License(Experimental) License information could not be found.
Found 1 instance in 1 package
60159
31
0
392
1
175
6
3