DZone Snippets: parser code

ARGV Parser

Black_H (Black_H) — Sun, 03 Feb 2008 20:24:59 GMT

This function parse ARGV and return a string.
See exemples for more informations :

// Go : http://blackh.badfile.net/wordz/

Function :



  def options(param)

  

	i = 0

		ARGV.each  { |valeur|

		

    		if (valeur == '-' + param.to_s)

				return ARGV[i+1]

			elseif (valeur != '-' + param.to_s)

				return false

			end

		i += 1

		}

		

   end

Usage :

// cmd> ruby test.rb -o foo





	out =  self.options('o')



	if (out != false and out.empty? == false)

                   puts out # print -> foo

	end

Regex-based parsing technique

ntk () — Thu, 06 Dec 2007 15:43:11 GMT





#!/usr/local/bin/ruby -w



# Regular expressions and strings with embedded objects

# From: http://t-a-w.blogspot.com/2007/06/regular-expressions-and-strings-with.html

# Author: Tomasz Węgrzanowski

# License: 

# Creative Commons License, http://creativecommons.org/licenses/by-sa/3.0/

# GNU Free Documentation License, http://en.wikipedia.org/wiki/GNU_Free_Documentation_License





def hash_or_die(kw)

  Hash.new{|ht,k| raise "Unknown key: #{k}"}.merge(kw)

end



def parse(data)

  esc = hash_or_die "\\" => "A", "\"" => "B", "n" => "C", "'" => "D"

  rev_esc = hash_or_die "A" => "\\", 'B' => "\"", "C" => "n", "D" => "'"

  data = data.gsub(/\\(.)/) {"\x00" + esc[$1]}

  strs = []

  data = data.gsub(/('[^']*')/) { # '

    strs << $1

    "\x01<#{strs.size-1}>"

  }

  records = []

  data.scan(/\((.*?)\)/) {

    records << $1.split(/,/).map{|field|

      field.gsub(/\x01<(\d+)>/) {

        strs[$1.to_i]}.gsub(/\x00(.)/){ rev_esc[$1]

      }

    }

  }

  records

end



def sql_str_unquote(str)

  str =~ /\A'(.*)'\Z/ or raise "SQL string format is wrong: #{str}"

  $1.gsub(/\\(.)/) {$1}

end





=begin



page_fn = Dir["plwiki-*-page.sql"].sort[-1]

externallinks_fn = Dir["plwiki-*-externallinks.sql"].sort[-1]



pages = {}



File.open(page_fn).each{|line|

  next unless line =~ /\AINSERT INTO `page` VALUES (.*)\Z/

  parse($1).each{|id,ns,title,*stuff|

    next unless ns == "0"

    title = sql_str_unquote(title)

    pages[id] = title

  }

}



File.open(externallinks_fn).each{|line|

  next unless line =~ /\AINSERT INTO `externallinks` VALUES (.*)\Z/

  parse($1).each{|from,to,index|

    title = pages[from]

    next unless title

    to = sql_str_unquote(to)

    next unless to =~ /\Ahttp:\/\//

    puts "#{title}\t#{to}"

  }

}



=end





sql_dump = <<-EOS



INSERT INTO `page` VALUES (1,0,'Astronomia','',1800,0,0,0.600461925007833,'20070601091320',8076762,8584,0), (2,0,'AWK','',329,0,0,0.487812640599732,'20070530195555',8058046,4265,0), (4,0,'Alergologia','',108,0,0,0.580574716050713,'20070520093413',7912844,292,0), ...

INSERT INTO `page` VALUES (14880,0,'Dźwignica_linotorowa','',26,0,0,0.597327036408081,'20060814072401',4282357,727,0), (14881,0,'Urządzenia_transportowe','',91,0,0,0.176666489966834,'20070527090143',2976610,1041,0), ...



EOS





pages = {}



sql_dump.each{|line|

  next unless line =~ /\AINSERT INTO `page` VALUES (.*)\Z/

  parse($1).each{|id,ns,title,*stuff|

    next unless ns == "0"

    title = sql_str_unquote(title)

    pages[id] = title

  }

}





p pages



=begin



sql_dump.each{|line|

  next unless line =~ /\AINSERT INTO `externallinks` VALUES (.*)\Z/

  parse($1).each{|from,to,index|

    title = pages[from]

    next unless title

    to = sql_str_unquote(to)

    next unless to =~ /\Ahttp:\/\//

    puts "#{title}\t#{to}"

  }

}



=end





#-----------------





require 'pp'



lisp_code = '(a (b c) (d (e) f g) (((h))))'

nodes = []



lisp_code.gsub!(/([a-z]+)/) {

  nodes << [:atom, $1]

  "<#{nodes.size-1}>"

}



#p nodes



lisp_code.gsub!(/\s/,"")

#puts lisp_code



true while lisp_code.gsub!(/\(((?:<\d+>)*)\)/) {

  #p nodes

  nodes << [:app, *$1.scan(/<(\d+)>/).map{|x,| nodes[x.to_i]}]

  "<#{nodes.size-1}>"

}

lisp_code =~ /<(\d+)>/



#puts

#p nodes

#puts



pp nodes[$1.to_i]



# Output:

#  [:app,

#  [:atom, "a"],

#  [:app, [:atom, "b"], [:atom, "c"]],

#  [:app, [:atom, "d"], [:app, [:atom, "e"]], [:atom, "f"], [:atom, "g"]],

#  [:app, [:app, [:app, [:atom, "h"]]]]]





#------------------





math_code = '(2 + 2 * 2) / ((2 + 2) * 2)'

nodes = []



math_code.gsub!(/(\d+)/) {

  nodes << $1.to_i

  "<#{nodes.size-1}>"

}

math_code.gsub!(/\s/,"")



until math_code =~ /\A<(\d+)>\Z/

  next if math_code.gsub!(/\((<\d+>)\)/) { $1 }

  next if math_code.gsub!(/<(\d+)>([\*\/])<(\d+)>/) {

    nodes << [$2, nodes[$1.to_i], nodes[$3.to_i]]

    "<#{nodes.size-1}>"

  }

  next if math_code.gsub!(/<(\d+)>([\+\-])<(\d+)>/) {

    nodes << [$2, nodes[$1.to_i], nodes[$3.to_i]]

    "<#{nodes.size-1}>"

  }

end



pp nodes[$1.to_i]



# Output:

# ["/", ["+", 2, ["*", 2, 2]], ["*", ["+", 2, 2], 2]]

basic parser

druid (Geoff) — Sun, 25 Nov 2007 07:39:12 GMT

This is a very basic parser, reads each line and creates a string of ':'-separated id nos for mass-mailing a set of accounts in an online game



def joinIds(fin, fout):

    """reads a page from input file, joins Ids with ':'

    

    returns strings to output file, max of 50 ids in each"""

    lines = 0

    outlist = []

    for line in fin:

      if line.strip() != '':

        lines += 1

        outlist.append(line.split()[2])

        if lines % 50 == 0:

            fout.write(":".join(["%s" % Id for Id in outlist]) + "\n\n")

            outlist = []

    fout.write(":".join(["%s" % Id for Id in outlist]) + "\n\n")



try:

    SIA = raw_input('Enter a file to read: ')

    pages = open(SIA, 'r')

except IOError:

    print 'Cannot open file %s for reading. Check file exists and try again.' % SIA

    import sys

    sys.exit(0)

    



default = 'idFile.txt'

out = raw_input('File name for output: ')

if out == '':

    oFile = open(default, 'a')

else:

    default = out

    oFile = open(default, 'a')



joinIds(pages, oFile)

pages.close()

oFile.close()



print 'Id strings have been output to %s. Happy mass-mailing! ;)' % default

Python: NMEA GPGGA parser

ejot (Magnus Persson) — Fri, 16 Nov 2007 14:12:36 GMT

Not tested extensivly, use with caution! I used an LD-1W and it seems to work alright with this parser.



class GPGGAParser(object):

	import logging

	

	def __init__(self, sentance):

		import time, logging

		

		logging.debug("GPPGAParser started")

		logging.debug("Trying to parse: "+sentance)

		(self.format,

		 self.utc,

		 self.latitude, 

		 self.northsouth, 

		 self.longitude, 

		 self.eastwest, 

		 self.quality, 

		 self.number_of_satellites_in_use, 

		 self.horizontal_dilution, 

		 self.altitude, 

		 self.above_sea_unit, 

		 self.geoidal_separation, 

		 self.geoidal_separation_unit, 

		 self.data_age, 

		 self.diff_ref_stationID) = sentance.split(",")



		latitude_in=float(self.latitude)

		longitude_in=float(self.longitude)

		if self.northsouth == 'S':

			latitude_in = -latitude_in

		if self.eastwest == 'W':

			longitude_in = -longitude_in



		latitude_degrees = int(latitude_in/100)

		latitude_minutes = latitude_in - latitude_degrees*100

		

		longitude_degrees = int(longitude_in/100)

		longitude_minutes = longitude_in - longitude_degrees*100

		

		self.latitude = latitude_degrees + (latitude_minutes/60)

		self.longitude = longitude_degrees + (longitude_minutes/60)

		

		self.timeOfFix = time.strftime("%H:%M:%S", time.strptime(self.utc.split(".")[0],"%H%M%S"))

		self.altitude = float(self.altitude)

		logging.debug("GPPGAParser finished")

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

PHP : Parsea HTML inyectado / Parser HTML inject

Ricardo (Ricardo m. García) — Mon, 23 Jul 2007 11:16:14 GMT

Parsea HTML Inyectado. Esto es útil cuando nos escriben código HTML o Javascript maligno en un texarea. Para más información www.php.net / Parser HTML inject. This is good when we write HTML code or bad javascript on a textarea. For more info www.php.net (sorry english)
Código fuente / Source code :



function parsearHTMLInjectado($texto)

{

	return nl2br( htmlentities($texto) );	

}

Java - Dom Parser Example

whitetiger () — Fri, 23 Feb 2007 19:08:17 GMT

// Simple Parser XML with DOM



package parser;



import java.io.File;

import java.io.IOException;



import javax.xml.parsers.DocumentBuilderFactory;

import javax.xml.parsers.ParserConfigurationException;



import org.w3c.dom.Document;

import org.w3c.dom.Node;

import org.w3c.dom.NodeList;

import org.xml.sax.SAXException;



public class DOMParser

{

	private Document doc = null;

	

	public DOMParser()

	{

		try

		{

			doc = parserXML(new File("parser/file.xml"));

			

			visit(doc, 0);

		}

		catch(Exception error)

		{

			error.printStackTrace();

		}

	}

	

	public void visit(Node node, int level)

	{

		NodeList nl = node.getChildNodes();

		

		for(int i=0, cnt=nl.getLength(); i		{

			System.out.println("["+nl.item(i)+"]");

			

			visit(nl.item(i), level+1);

		}

	}

	

	public Document parserXML(File file) throws SAXException, IOException, ParserConfigurationException

	{

		return DocumentBuilderFactory.newInstance().newDocumentBuilder().parse(file);

	}

	

	public static void main(String[] args)

	{

		new DOMParser();

	}

}

Python - Very Simple Parser

whitetiger () — Tue, 09 Jan 2007 23:21:59 GMT

// Very Simple Parser



from sgmllib import SGMLParser



import urllib



class ParserHTML(SGMLParser):



	def scrivi(self):

		self.f = open('/tmp/fileOUT.html', 'w')



	def unknown_starttag(self, tag, attrs):



		value = 0

		startTAG = '<' + tag

		

		for i in attrs:

			if(i[0].lower() == i[1].lower() and not i[0] == i[1]):

				startTAG = startTAG[:-1] + ' ' + str(i[1])

				value = 1

			else:

				startTAG += ' ' + str(i[0]) + '="' + str(i[1]) + '"'

				value = 0

		

		if(value == 1): startTAG += '"'



		startTAG += '>'

		self.f.write(startTAG + "\n")



	def handle_data(self, data):



		self.f.write(data + "\n")



	def unknown_endtag(self, tag):



		self.f.write('' + "\n")



if __name__ == '__main__':



	p = ParserHTML()

	p.scrivi()

	p.feed(open('/tmp/fileIN.html', 'r').read())

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;

	}

}

?>

Math Parser //JavaScript Class

jonasraoni (Jonas Raoni Soares Silva) — Thu, 15 Jun 2006 20:34:52 GMT

This class is able to parse math expressions and also run user defined functions.

On JavaScript there's the "eval" function, that can do such things well, but this code objective was just to give me fun or a new challenge =)~

[UPDATED CODE AND HELP CAN BE FOUND HERE]

Usage:



x = new MathProcessor;

try{alert(x.parse("1+2-(3*4) + medium(2,3) - frac( 2.2231)"));}

catch(e){alert(e);}

It's possible to add more functions to the class, just add them into the "methods" property ;]

Well, that's it :)



//+ Jonas Raoni Soares Silva

//@ http://jsfromhell.com/classes/math-processor [v1.0]



MathProcessor = function(){ //v1.0

    var o = this;

    o.o = {

        "+": function(a, b){ return +a + b; },

        "-": function(a, b){ return a - b; },

        "%": function(a, b){ return a % b; },

        "/": function(a, b){ return a / b; },

        "*": function(a, b){ return a * b; },

        "^": function(a, b){ return Math.pow(a, b); },

        "~": function(a, b){ return Math.sqrt(a, b); }

    };

    o.s = { "^": 3, "~": 3, "*": 2, "/": 2, "%": 1, "+": 0, "-": 0 };

    o.u = {"+": 1, "-": -1}, o.p = {"(": 1, ")": -1};

};



MathProcessor.prototype.parse = function(e){

    for(var n, x, o = [], s = [x = this.RPN(e.replace(/ /g, "").split(""))]; s.length;)

        for((n = s[s.length-1], --s.length); n[2]; o[o.length] = n, s[s.length] = n[3], n = n[2]);

    for(; (n = o.pop()) != undefined; n[0] = this.o[n[0]](isNaN(n[2][0]) ? this.f(n[2][0]) : n[2][0], isNaN(n[3][0]) ? this.f(n[3][0]) : n[3][0]));

    return +x[0];

};



MathProcessor.prototype.methods = {

    "div": function(a, b){ return parseInt(a / b); },

    "frac": function(a){ return a - parseInt(a); },

    "sum": function(n1, n2, n3, n){ for(var r = 0, a, l = (a = arguments).length; l; r += a[--l]); return r; },

    "medium": function(a, b){ return (a + b) / 2; }

};



MathProcessor.prototype.error = function(s){

    throw new Error("MathProcessor: " + (s || "Erro na expressão"));

}



MathProcessor.prototype.RPN = function(e){

    var _, r, c = r = [, , , 0];

    if(e[0] in this.u || !e.unshift("+"))

        for(; e[1] in this.u; e[0] = this.u[e.shift()] * this.u[e[0]] + 1 ? "+" : "-");

    (c[3] = [this.u[e.shift()], c, , 0])[1][0] = "*", (r = [, , c, 0])[2][1] = r;

    (c[2] = this.v(e))[1] = c;

    (!e.length && (r = c)) || (e[0] in this.s && ((c = r)[0] = e.shift(), !e.length && this.error()));

     while(e.length){

        if(e[0] in this.u){

            for(; e[1] in this.u; e[0] = this.u[e.shift()] * this.u[e[0]] + 1 ? "+" : "-");

            (c = c[3] = ["*", c, , 0])[2] = [-1, c, , 0];

        }

        (c[3] = this.v(e))[1] = c;

        e[0] in this.s && (c = this.s[e[0]] > this.s[c[0]] ?

            ((c[3] = (_ = c[3], c[2]))[1][2] = [e.shift(), c, _, 0])[2][1] = c[2]

            : r == c ? (r = [e.shift(), , c, 0])[2][1] = r

            : ((r[2] = (_ = r[2], [e.shift(), r, ,0]))[2] = _)[1] = r[2]);

    }

    return r;

};



MathProcessor.prototype.v = function(e){

    if("0123456789.".indexOf(e[0]) + 1){

        for(var i = -1, l = e.length; ++i < l && "0123456789.".indexOf(e[i]) + 1;);

        return [+e.splice(0,i).join(""), , , 0];

    }

    else if(e[0] == "("){

        for(var i = 0, l = e.length, j = 1; ++i < l && (e[i] in this.p && (j += this.p[e[i]]), j););

        return this.RPN(l = e.splice(0,i), l.shift(), !j && e.shift());

    }

    else{

        var i = 0, c = e[0].toLowerCase();

        if((c >= "a" && c <= "z") || c == "_"){

            while(((c = e[++i].toLowerCase()) >= "a" && c <= "z") || c == "_" || (c >= 0 && c <= 9));

            if(c == "("){

                for(var l = e.length, j = 1; ++i < l && (e[i] in this.p && (j += this.p[e[i]]), j););

                return [e.splice(0,i+1).join(""), , , 0];

            }

        }

    }

    this.error();

}



MathProcessor.prototype.f = function(e){

    var i = 0, n;

    if(((e = e.split(""))[i] >= "a" && e[i] <= "z") || e[i] == "_"){

        while((e[++i] >= "a" && e[i] <= "z") || e[i] == "_" || (e[i] >= 0 && e[i] <= 9));

        if(e[i] == "("){

            !this.methods[n = e.splice(0, i).join("")] && this.error("Função \"" + n + "\" não encontrada"), e.shift();

            for(var a = [], i = -1, j = 1; e[++i] && (e[i] in this.p && (j += this.p[e[i]]), j);)

                j == 1 && e[i] == "," && (a.push(this.parse(e.splice(0, i).join(""))), e.shift(), i = -1);

            a.push(this.parse(e.splice(0,i).join(""))), !j && e.shift();

        }

        return this.methods[n].apply(this, a);

    }

};