DZone Snippets: comma code

CSV parsing regex

ntk () — Sat, 18 Aug 2007 17:17:23 GMT

The regular expression is taken from Raimond Brookman, Regex fun with CSV.
For a good general CSV overview see The Comma Separated Value (CSV) File Format.
A complete Ruby CSV parsing library is FasterCSV (sudo gem install fastercsv).





csv_data = <<-EOS



fname,lname,age,salary

nancy,davolio,33,$30000

erin,borakova,28,$25250

tony,raphael,35,$28700



"Date","Pupil","Grade"

"25 May","Bloggs, Fred","C"

"25 May","Doe, Jane","B"

"15 July","Bloggs, Fred","D"



123456789,"Carr, Lisa",100000.00

444556666,"Barr, Clark",87000.00

777227878,"Parr, Jack",123000.00

998877665,"Charr, Lee",123000.00



Conference room 1, "John,  

Please bring the M. Mathers file for review  

-J.L.

"

10/18/2002,...



John,Doe,120 jefferson st.,Riverside, NJ, 08075

Jack,McGinnis,220 hobo Av.,Phila, PA,09119

"John ""Da Man""",Repici,120 Jefferson St.,Riverside, NJ,08075

Stephen,Tyler,"7452 Terrace ""At the Plaza"" road",SomeTown,SD, 91234

,Blankman,,SomeTown, SD, 00298

"Joan ""the bone"", Anne",Jet,"9th, at Terrace plc",Desert City,CO,00123



XXXX,D,3-May-02,83.01,83.58,71.13,78.04,9645300

XXXX,D,2-May-02,82.47,85.76,82.05,83.84,7210000,

XXXX,D,1-May-02,86.80,90.83,81.74,85.50,14253300



"1997",car model,E350

1997,car model,E350,"  Super luxurious truck    "

1997,car model,E350,"Go get one now

they are going fast"

1997,car model,E350,"Super ""luxurious"" truck"

1997,car model,E350,"Super, luxurious truck"



1997,car model,E350,"ac, abs, moon",3000.00

1999, car model,"Venture ""Extended Edition""",,4900.00,

1996, car model,Old Car,"BEYOND REPAIR!

air, moon roof, loaded",4799.00



This,is,a test,CSV, file," from ""http://lorance.freeshell.org/csv/test.csv""."

It contains,"quoted text",and,numbers 1234,5678

It also has,"quoted text with an embedded quote""<- right there"

Then there are a few,,blank fields like these here ->,,,

A quoted blank field,"",<- there.

A quoted blank field with newline,"\n",<- there.

This next one causes an error if newline handling is turned off.

"There is a newline here ->

<- and it should be processed correctly."

ABCD

"And here,,, is an""Error - no"

"And here,,, is an"Error - yes

"And here,,, is an",Error - no



1,2,3

ab,"c,d","e""f", "g"",""","h

jk",kl



"aaa","bbb","ccc"

zzz,yyy,xxx

"aaa","b

bb","ccc"

zzz,yyy,xxx



"aaa","b""bb","ccc"



EOS







csv_data.split(/(,|\r\n|\n|\r)(?=(?:[^\"]*\"[^\"]*\")*(?![^\"]*\"))/m).each do |csv|

#csv_data.split(/[,\n\r]+(?=(?:[^\"]*\"[^\"]*\")*(?![^\"]*\"))/m).each do |csv|



   next if csv.empty?



   csv = csv.strip



   if csv =~ /\A(".*[^"]|[^"].*")\z/m then     # examples: csv => "ab\nc"def  or  abc"de\nf"

       puts

       puts "Error:" 

       p csv 

       puts csv[/\A./mu], csv[/.\z/mu] 

       #puts csv[0..0], csv[-1..-1] 

       puts

       next

   end



   if csv =~ /\A".*"\z/m then csv.gsub!(/\A"(.*)"\z/m, '\1') end  # remove double-quotes at string beginning & end

   if csv =~ /""/m then csv.gsub!(/""/m, '"') end                 # remove a double-quote from double double-quotes



   p csv



end

CSV Parser / Writer for PHP

jonasraoni (Jonas Raoni Soares Silva) — Mon, 11 Dec 2006 22:36:10 GMT

CSV Parser / Writer

Example A:



//cell separator, row separator, value enclosure

$csv = new CSV(';', "\r\n", '"');



//parse the string content

$csv->setContent(file_get_contents('data.csv'));



//returns an array with the CSV data

print_r($csv->getArray());

Exemple B:



$csv = new CSV(';', "\r\n", '"');

//sets up the content through an array

$csv->setArray(

	array(

		array('col"una1', "colu\r\nna2"),

		array('col;una3', 'coluna4')

	)

);

//retorns string with the CSV representation

print $csv->getContent();



//+ Jonas Raoni Soares Silva

//@ http://jsfromhell.com

class CSV{

	var $cellDelimiter;

	var $valueEnclosure;

	var $rowDelimiter;



	function CSV($cellDelimiter, $rowDelimiter, $valueEnclosure){

		$this->cellDelimiter = $cellDelimiter;

		$this->valueEnclosure = $valueEnclosure;

		$this->rowDelimiter = $rowDelimiter;

		$this->o = array();

	}

	function getArray(){

		return $this->o;

	}

	function setArray($o){

		$this->o = $o;

	}

	function getContent(){

		if(!(($bl = strlen($b = $this->rowDelimiter)) && ($dl = strlen($d = $this->cellDelimiter)) && ($ql = strlen($q = $this->valueEnclosure))))

			return '';

		for($o = $this->o, $i = -1; ++$i < count($o);){

			for($e = 0, $j = -1; ++$j < count($o[$i]);)

				(($e = strpos($o[$i][$j], $q) !== false) || strpos($o[$i][$j], $b) !== false || strpos($o[$i][$j], $d) !== false)

				&& $o[$i][$j] = $q . ($e ? str_replace($q, $q . $q, $o[$i][$j]) : $o[$i][$j]) . $q;

			$o[$i] = implode($d, $o[$i]);

		}

		return implode($b, $o);

	}

	function setContent($s){

		$this->o = array();

		if(!strlen($s))

			return true;

		if(!(($bl = strlen($b = $this->rowDelimiter)) && ($dl = strlen($d = $this->cellDelimiter)) && ($ql = strlen($q = $this->valueEnclosure))))

			return false;

		for($o = array(array('')), $this->o = &$o, $e = $r = $c = 0, $i = -1, $l = strlen($s); ++$i < $l;){

			if(!$e && substr($s, $i, $bl) == $b){

				$o[++$r][$c = 0] = '';

				$i += $bl - 1;

			}

			elseif(substr($s, $i, $ql) == $q){

				$e ? (substr($s, $i + $ql, $ql) == $q ?

				$o[$r][$c] .= substr($s, $i += $ql, $ql) : $e = 0)

				: (strlen($o[$r][$c]) == 0 ? $e = 1 : $o[$r][$c] .= substr($s, $i, $ql));

				$i += $ql - 1;

			}

			elseif(!$e && substr($s, $i, $dl) == $d){

				$o[$r][++$c] = '';

				$i += $dl - 1;

			}

			else

				$o[$r][$c] .= $s[$i];

		}

		return true;

	}

}

?>

Adding commas to digits

korakot (Korakot Chaovavanich) — Thu, 18 Aug 2005 22:14:20 GMT

Copy from Marek Baczynski's code here
http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/439357



def group(n, sep = ','):

    s = str(n)[::-1]

    groups = []

    i = 0

    while i < len(s):

        groups.append(s[i:i+3])

        i += 3

    return sep.join(groups)[::-1]



#>>> group(42424242)

#'42,424,242'