Class: ArAutoSummarize

Source Location: /sub/ArAutoSummarize.class.php

Class Overview

This PHP class do automatic keyphrase extraction to provide a quick mini-summary for a long Arabic document

Author(s):

Khaled Al-Shamaa <khaled.alshamaa@gmail.com>

Copyright:

2006-2010 Khaled Al-Shamaa

Variables

Methods

Class Details

[line 146]
This PHP class do automatic keyphrase extraction to provide a quick mini-summary for a long Arabic document

Tags:

author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
copyright:	2006-2010 Khaled Al-Shamaa
link:	http://www.ar-php.org
license:	LGPL

[ Top ]

Class Variables

$cleanCommonInput = 'windows-1256'

[line 277]

"cleanCommon" method input charset

Tags:

access:

public

Type:

String

[ Top ]

$cleanCommonOutput = 'windows-1256'

[line 271]

"cleanCommon" method output charset

Tags:

access:

public

Type:

String

[ Top ]

$cleanCommonVars = array('str')

[line 283]

Name of the textual "cleanCommon" method parameters

Tags:

access:

public

Type:

Array

[ Top ]

$commonChars = array('É','å','í','ä','æ','Ê','á','Ç','Ó','ã',
'e', 't', 'a', 'o', 'i', 'n', 's')

[line 151]

Tags:

access:

protected

Type:

mixed

[ Top ]

$commonWords = array()

[line 156]

Tags:

access:

protected

Type:

mixed

[ Top ]

$doRateSummarizeInput = 'windows-1256'

[line 205]

"doRateSummarize" method input charset

Tags:

access:

public

Type:

String

[ Top ]

$doRateSummarizeOutput = 'windows-1256'

[line 199]

"doRateSummarize" method output charset

Tags:

access:

public

Type:

String

[ Top ]

$doRateSummarizeVars = array('str', 'keywords')

[line 211]

Name of the textual "doRateSummarize" method parameters

Tags:

access:

public

Type:

Array

[ Top ]

$doSummarizeInput = 'windows-1256'

[line 187]

"doSummarize" method input charset

Tags:

access:

public

Type:

String

[ Top ]

$doSummarizeOutput = 'windows-1256'

[line 181]

"doSummarize" method output charset

Tags:

access:

public

Type:

String

[ Top ]

$doSummarizeVars = array('str', 'keywords')

[line 193]

Name of the textual "doSummarize" method parameters

Tags:

access:

public

Type:

Array

[ Top ]

$getMetaKeywordsInput = 'windows-1256'

[line 259]

"getMetaKeywords" method input charset

Tags:

access:

public

Type:

String

[ Top ]

$getMetaKeywordsOutput = 'windows-1256'

[line 253]

"getMetaKeywords" method output charset

Tags:

access:

public

Type:

String

[ Top ]

$getMetaKeywordsVars = array('str')

[line 265]

Name of the textual "getMetaKeywords" method parameters

Tags:

access:

public

Type:

Array

[ Top ]

$highlightRateSummaryInput = 'windows-1256'

[line 241]

"highlightRateSummary" method input charset

Tags:

access:

public

Type:

String

[ Top ]

$highlightRateSummaryOutput = 'windows-1256'

[line 235]

"highlightRateSummary" method output charset

Tags:

access:

public

Type:

String

[ Top ]

$highlightRateSummaryVars = array('str', 'keywords')

[line 247]

Name of the textual "highlightRateSummary" method parameters

Tags:

access:

public

Type:

Array

[ Top ]

$highlightSummaryInput = 'windows-1256'

[line 223]

"highlightSummary" method input charset

Tags:

access:

public

Type:

String

[ Top ]

$highlightSummaryOutput = 'windows-1256'

[line 217]

"highlightSummary" method output charset

Tags:

access:

public

Type:

String

[ Top ]

$highlightSummaryVars = array('str', 'keywords')

[line 229]

Name of the textual "highlightSummary" method parameters

Tags:

access:

public

Type:

Array

[ Top ]

$importantWords = array()

[line 157]

Tags:

access:

protected

Type:

mixed

[ Top ]

$normalizeAlef = array('Ã','Å','Â')

[line 148]

Tags:

access:

protected

Type:

mixed

[ Top ]

$normalizeDiacritics = array('ó','ð','õ','ñ','ö','ò','ú','ø')

[line 149]

Tags:

access:

protected

Type:

mixed

[ Top ]

$separators = array('.',"\n",'¡','º','(','[','{',')',']','}',',',';')

[line 154]

Tags:

access:

protected

Type:

mixed

[ Top ]

$summarizeInput = 'windows-1256'

[line 169]

"summarize" method input charset

Tags:

access:

public

Type:

String

[ Top ]

$summarizeOutput = 'windows-1256'

[line 163]

"summarize" method output charset

Tags:

access:

public

Type:

String

[ Top ]

$summarizeVars = array('str', 'keywords')

[line 175]

Name of the textual "summarize" method parameters

Tags:

access:

public

Type:

Array

[ Top ]

Class Methods

constructor __construct [line 288]

ArAutoSummarize __construct(
)

Loads initialize values

Tags:

access:

public

[ Top ]

method acceptedWord [line 753]

boolean acceptedWord(
string
$word)

Check some conditions to know if a given string is a formal valid word or not

Tags:

return:	True if passed string is accepted as a valid word else it will return False
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	protected

Parameters:

string

$word

String to be checked if it is a valid word or not

[ Top ]

method cleanCommon [line 576]

string cleanCommon(
string
$str)

Extracting common Arabic words (roughly) from input Arabic string (document content)

Tags:

return:	Arabic document as a string free of common words (roughly)
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	public

Parameters:

string

$str

Input normalized Arabic document as a string

[ Top ]

method doNormalize [line 556]

string doNormalize(
string
$str)

Normalized Arabic document

Tags:

return:	Normalized Arabic document
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	protected

Parameters:

string

$str

Input Arabic document as a string

[ Top ]

method doRateSummarize [line 428]

string doRateSummarize(
string
$str, integer
$rate, string
$keywords)

Summarize percentage of the input Arabic string (document content) into output

Tags:

return:	Output summary requested
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	public

Parameters:

string	$str	Input Arabic document as a string
integer	$rate	Rate of output summary sentence number as percentage of the input Arabic string (document content)
string	$keywords	List of keywords higlited by search process

[ Top ]

method doSummarize [line 408]

string doSummarize(
string
$str, integer
$int, string
$keywords)

Summarize input Arabic string (document content) into specific number of sentences in the output

Tags:

return:	Output summary requested
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	public

Parameters:

string	$str	Input Arabic document as a string
integer	$int	Number of sentences required in output summary
string	$keywords	List of keywords higlited by search process

[ Top ]

method draftStem [line 593]

string draftStem(
string
$str)

Remove less significant Arabic letter from given string (document content).

Please note that output will not be human readable.

Tags:

return:	Output string after removing less significant Arabic letter (not human readable output)
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	protected

Parameters:

string

$str

Input Arabic document as a string

[ Top ]

method getMetaKeywords [line 491]

string getMetaKeywords(
string
$str, integer
$int)

Extract keywords from a given Arabic string (document content)

Tags:

return:	List of the keywords extracting from input Arabic string (document content)
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	public

Parameters:

string	$str	Input Arabic document as a string
integer	$int	Number of keywords required to be extracting from input string (document content)

[ Top ]

method highlightRateSummary [line 472]

string highlightRateSummary(
string
$str, integer
$rate, string
$keywords, string
$style)

Highlight key sentences (summary) as percentage of the input string (document content) using CSS and send the result back as an output.

Tags:

return:	Output highlighted key sentences summary (using CSS)
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	public

Parameters:

string	$str	Input Arabic document as a string
integer	$rate	Rate of highlighted key sentences summary number as percentage of the input Arabic string (document content)
string	$keywords	List of keywords higlited by search process
string	$style	Name of the CSS class you would like to apply

[ Top ]

method highlightSummary [line 450]

string highlightSummary(
string
$str, integer
$int, string
$keywords, string
$style)

Highlight key sentences (summary) of the input string (document content) using CSS and send the result back as an output

Tags:

return:	Output highlighted key sentences summary (using CSS)
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	public

Parameters:

string	$str	Input Arabic document as a string
integer	$int	Number of key sentences required to be highlighted in the input string (document content)
string	$keywords	List of keywords higlited by search process
string	$style	Name of the CSS class you would like to apply

[ Top ]

method loadExtra [line 311]

void loadExtra(
)

Load enhanced Arabic stop words list

Tags:

access:

public

[ Top ]

method minAcceptedRank [line 731]

integer minAcceptedRank(
array
$arr, integer
$int)

Calculate minimum rank for sentences which will be including in the summary

Tags:

return:	Minimum accepted sentence rank (sentences with rank more than this will be listed in the document summary)
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	protected

Parameters:

array	$arr	Sentences ranks
integer	$int	Number of sentences you need to include in your summary

[ Top ]

method rankSentences [line 652]

array rankSentences(
array
$sentences, array
$stemmedSentences, array
$arr)

Ranks sentences in a given Arabic string (document content).

Tags:

return:	Two dimension array, first item is an array of document sentences, second item is an array of ranks of document sentences.
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	protected

Parameters:

array	$sentences	Sentences of the input Arabic document as an array
array	$stemmedSentences	Stemmed sentences of the input Arabic document as an array
array	$arr	Words ranks array (word as an index and value refer to the word frequency)

[ Top ]

method rankWords [line 609]

hash rankWords(
string
$str)

Ranks words in a given Arabic string (document content). That rank refers to the frequency of that word appears in that given document.

Tags:

return:	Associated array where document words referred by index and those words ranks referred by values of those array items.
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	protected

Parameters:

string

$str

Input Arabic document as a string

[ Top ]

method summarize [line 332]

string summarize(
string
$str, string
$keywords, integer
$int, string
$mode, string
$output, [string
$style = null])

Core summarize function that implement required steps in the algorithm

Tags:

return:	Output summary requested
author:	Khaled Al-Shamaa <khaled.alshamaa@gmail.com>
access:	protected

Parameters:

string	$str	Input Arabic document as a string
string	$keywords	List of keywords higlited by search process
integer	$int	Sentences value (see $mode effect also)
string	$mode	Mode of sentences count [number\|rate]
string	$output	Output mode [summary\|highlight]
string	$style	Name of the CSS class you would like to apply

[ Top ]

Documentation generated on Sat, 14 Aug 2010 13:23:52 -0700 by phpDocumentor 1.4.0

Class: ArAutoSummarize

Class Overview

Author(s):

Copyright:

Variables

Methods

Class Details

Tags:

Class Variables

$cleanCommonInput = 'windows-1256'

Tags:

$cleanCommonOutput = 'windows-1256'

Tags:

$cleanCommonVars = array('str')

Tags:

$commonChars = array('É','å','í','ä','æ','Ê','á','Ç','Ó','ã', 'e', 't', 'a', 'o', 'i', 'n', 's')

Tags:

$commonWords = array()

Tags:

$doRateSummarizeInput = 'windows-1256'

Tags:

$doRateSummarizeOutput = 'windows-1256'

Tags:

$doRateSummarizeVars = array('str', 'keywords')

Tags:

$doSummarizeInput = 'windows-1256'

Tags:

$doSummarizeOutput = 'windows-1256'

Tags:

$doSummarizeVars = array('str', 'keywords')

Tags:

$getMetaKeywordsInput = 'windows-1256'

Tags:

$getMetaKeywordsOutput = 'windows-1256'

Tags:

$getMetaKeywordsVars = array('str')

Tags:

$highlightRateSummaryInput = 'windows-1256'

Tags:

$highlightRateSummaryOutput = 'windows-1256'

Tags:

$highlightRateSummaryVars = array('str', 'keywords')

Tags:

$highlightSummaryInput = 'windows-1256'

Tags:

$highlightSummaryOutput = 'windows-1256'

Tags:

$highlightSummaryVars = array('str', 'keywords')

Tags:

$importantWords = array()

Tags:

$normalizeAlef = array('Ã','Å','Â')

Tags:

$normalizeDiacritics = array('ó','ð','õ','ñ','ö','ò','ú','ø')

Tags:

$separators = array('.',"\n",'¡','º','(','[','{',')',']','}',',',';')

Tags:

$summarizeInput = 'windows-1256'

Tags:

$summarizeOutput = 'windows-1256'

Tags:

$summarizeVars = array('str', 'keywords')

Tags:

Class Methods

constructor __construct [line 288]

Tags:

method acceptedWord [line 753]

Tags:

Parameters:

method cleanCommon [line 576]

Tags:

Parameters:

method doNormalize [line 556]

Tags:

Parameters:

method doRateSummarize [line 428]

Tags:

Parameters:

method doSummarize [line 408]

Tags:

$commonChars = array('É','å','í','ä','æ','Ê','á','Ç','Ó','ã',
'e', 't', 'a', 'o', 'i', 'n', 's')