<!---
<cfdump var="#getWordsCount('http://ketanjetty.com/monitor/jvm-runtime/')#" />
--->

<cffunction name="getWordsCount" access="public" returntype="struct">
	<cfargument name="_page" type="string" required="true" />

	<cfset var page = arguments._page />
	<cfset var tempWord = "" />
	<cfset var i = 0 />
	<cfset var wordsCountStruct = StructNew() />
	<cfset var wordsToAvoidJSON = '{ "able":"", "about":"", "above":"", "abroad":"", "according":"", "accordingly":"", "across":"", "actually":"", "adj":"", "after":"", "afterwards":"", "again":"", "against":"", "ago":"", "ahead":"", "ain''t":"", "all":"", "allow":"", "allows":"", "almost":"", "alone":"", "along":"", "alongside":"", "already":"", "also":"", "although":"", "always":"", "am":"", "amid":"", "amidst":"", "among":"", "amongst":"", "an":"", "and":"", "another":"", "any":"", "anybody":"", "anyhow":"", "anyone":"", "anything":"", "anyway":"", "anyways":"", "anywhere":"", "apart":"", "appear":"", "appreciate":"", "appropriate":"", "are":"", "aren''t":"", "around":"", "as":"", "a''s":"", "aside":"", "ask":"", "asking":"", "associated":"", "at":"", "available":"", "away":"", "awfully":"", "back":"", "backward":"", "backwards":"", "be":"", "became":"", "because":"", "become":"", "becomes":"", "becoming":"", "been":"", "before":"", "beforehand":"", "begin":"", "behind":"", "being":"", "believe":"", "below":"", "beside":"", "besides":"", "best":"", "better":"", "between":"", "beyond":"", "both":"", "brief":"", "but":"", "by":"", "came":"", "can":"", "cannot":"", "cant":"", "can''t":"", "caption":"", "cause":"", "causes":"", "certain":"", "certainly":"", "changes":"", "clearly":"", "c''mon":"", "co":"", "co.":"", "com":"", "come":"", "comes":"", "completely":"", "concerning":"", "consequently":"", "consider":"", "considering":"", "contain":"", "containing":"", "contains":"", "corresponding":"", "could":"", "couldn''t":"", "course":"", "c''s":"", "currently":"", "dare":"", "daren''t":"", "decrease":"", "decreasingly":"", "definitely":"", "described":"", "despite":"", "did":"", "didn''t":"", "different":"", "directly":"", "do":"", "does":"", "doesn''t":"", "doing":"", "done":"", "don''t":"", "down":"", "downwards":"", "during":"", "each":"", "eg":"", "eight":"", "eighty":"", "either":"", "else":"", "elsewhere":"", "end":"", "ending":"", "enough":"", "entirely":"", "especially":"", "et":"", "etc":"", "even":"", "ever":"", "evermore":"", "every":"", "everybody":"", "everyone":"", "everything":"", "everywhere":"", "ex":"", "exactly":"", "example":"", "except":"", "fairly":"", "false":"", "far":"", "farther":"", "few":"", "fewer":"", "fifth":"", "first":"", "firstly":"", "five":"", "followed":"", "following":"", "follows":"", "for":"", "forever":"", "former":"", "formerly":"", "forth":"", "forward":"", "found":"", "four":"", "from":"", "further":"", "furthermore":"", "get":"", "gets":"", "getting":"", "given":"", "gives":"", "go":"", "goes":"", "going":"", "gone":"", "got":"", "gotten":"", "greetings":"", "had":"", "hadn''t":"", "half":"", "happens":"", "hardly":"", "has":"", "hasn''t":"", "have":"", "haven''t":"", "having":"", "he":"", "he''d":"", "he''ll":"", "hello":"", "help":"", "hence":"", "her":"", "here":"", "hereafter":"", "hereby":"", "herein":"", "here''s":"", "hereupon":"", "hers":"", "herself":"", "he''s":"", "hi":"", "him":"", "himself":"", "his":"", "hither":"", "hopefully":"", "how":"", "howbeit":"", "however":"", "hundred":"", "i":"", "i''d":"", "ie":"", "if":"", "ignored":"", "i''ll":"", "i''m":"", "immediate":"", "in":"", "inasmuch":"", "inc":"", "increase":"", "increasingly":"", "indeed":"", "indicate":"", "indicated":"", "indicates":"", "inner":"", "inside":"", "insofar":"", "instead":"", "into":"", "inward":"", "is":"", "isn''t":"", "it":"", "it''d":"", "it''ll":"", "its":"", "it''s":"", "itself":"", "i''ve":"", "just":"", "keep":"", "keeps":"", "kept":"", "know":"", "known":"", "knows":"", "last":"", "lastly":"", "lately":"", "later":"", "latter":"", "latterly":"", "least":"", "less":"", "lest":"", "let":"", "let''s":"", "like":"", "liked":"", "likely":"", "likewise":"", "little":"", "look":"", "looking":"", "looks":"", "low":"", "lower":"", "ltd":"", "made":"", "main":"", "mainly":"", "make":"", "makes":"", "many":"", "may":"", "maybe":"", "mayn''t":"", "me":"", "mean":"", "meantime":"", "meanwhile":"", "merely":"", "might":"", "mightn''t":"", "mine":"", "minus":"", "miss":"", "more":"", "moreover":"", "most":"", "mostly":"", "mr":"", "mrs":"", "ms":"", "much":"", "must":"", "mustn''t":"", "my":"", "myself":"", "name":"", "namely":"", "nd":"", "near":"", "nearly":"", "necessary":"", "need":"", "needn''t":"", "needs":"", "neither":"", "never":"", "never":"", "neverless":"", "nevertheless":"", "new":"", "next":"", "nine":"", "ninety":"", "no":"", "nobody":"", "non":"", "none":"", "nonetheless":"", "noone":"", "no-one":"", "nor":"", "normally":"", "not":"", "nothing":"", "notwithstanding":"", "novel":"", "now":"", "nowhere":"", "obviously":"", "of":"", "off":"", "often":"", "oh":"", "ok":"", "okay":"", "old":"", "on":"", "once":"", "one":"", "ones":"", "one''s":"", "only":"", "onto":"", "opposite":"", "or":"", "other":"", "others":"", "otherwise":"", "ought":"", "oughtn''t":"", "our":"", "ours":"", "ourselves":"", "out":"", "outside":"", "over":"", "overall":"", "own":"", "particular":"", "particularly":"", "past":"", "per":"", "perfectly":"", "perhaps":"", "placed":"", "please":"", "plus":"", "possible":"", "presumably":"", "probably":"", "provided":"", "provides":"", "que":"", "quick":"", "quickly":"", "quite":"", "qv":"", "rather":"", "rd":"", "re":"", "really":"", "reasonably":"", "recent":"", "recently":"", "regarding":"", "regardless":"", "regards":"", "relatively":"", "respectively":"", "right":"", "round":"", "said":"", "same":"", "saw":"", "say":"", "saying":"", "says":"", "second":"", "secondly":"", "see":"", "seeing":"", "seem":"", "seemed":"", "seeming":"", "seems":"", "seen":"", "self":"", "selves":"", "sensible":"", "sent":"", "serious":"", "seriously":"", "seven":"", "several":"", "shall":"", "shan''t":"", "she":"", "she''d":"", "she''ll":"", "she''s":"", "should":"", "shouldn''t":"", "since":"", "six":"", "so":"", "some":"", "somebody":"", "someday":"", "somehow":"", "someone":"", "something":"", "sometime":"", "sometimes":"", "somewhat":"", "somewhere":"", "soon":"", "sorry":"", "specified":"", "specify":"", "specifying":"", "still":"", "sub":"", "such":"", "sup":"", "sure":"", "surely":"", "take":"", "taken":"", "taking":"", "tell":"", "tends":"", "th":"", "than":"", "thank":"", "thanks":"", "thanx":"", "that":"", "that''ll":"", "thats":"", "that''s":"", "that''ve":"", "the":"", "their":"", "theirs":"", "them":"", "themselves":"", "then":"", "thence":"", "there":"", "thereafter":"", "thereby":"", "there''d":"", "therefore":"", "therein":"", "there''ll":"", "there''re":"", "theres":"", "there''s":"", "thereupon":"", "there''ve":"", "these":"", "they":"", "they''d":"", "they''ll":"", "they''re":"", "they''ve":"", "thing":"", "things":"", "think":"", "third":"", "thirty":"", "this":"", "thorough":"", "thoroughly":"", "those":"", "though":"", "three":"", "thrice":"", "through":"", "throughout":"", "thru":"", "thus":"", "thusly":"", "till":"", "to":"", "together":"", "too":"", "took":"", "toward":"", "towards":"", "tried":"", "tries":"", "true":"", "truly":"", "try":"", "trying":"", "t''s":"", "twice":"", "two":"", "un":"", "under":"", "underneath":"", "undoing":"", "unfortunately":"", "unless":"", "unlike":"", "unlikely":"", "until":"", "unto":"", "up":"", "upon":"", "upwards":"", "us":"", "use":"", "used":"", "useful":"", "uses":"", "using":"", "usually":"", "utterly":"", "value":"", "various":"", "versus":"", "very":"", "via":"", "viz":"", "vs":"", "want":"", "wants":"", "was":"", "wasn''t":"", "way":"", "we":"", "we''d":"", "welcome":"", "well":"", "we''ll":"", "went":"", "were":"", "we''re":"", "weren''t":"", "we''ve":"", "what":"", "whatever":"", "what''ll":"", "what''s":"", "what''ve":"", "when":"", "whence":"", "whenever":"", "where":"", "whereafter":"", "whereas":"", "whereby":"", "wherein":"", "where''s":"", "whereupon":"", "wherever":"", "whether":"", "which":"", "whichever":"", "while":"", "whilst":"", "whither":"", "who":"", "who''d":"", "whoever":"", "whole":"", "wholly":"", "who''ll":"", "whom":"", "whomever":"", "who''s":"", "whose":"", "why":"", "will":"", "willing":"", "wish":"", "with":"", "within":"", "without":"", "wonder":"", "wondered":"", "wondering":"", "won''t":"", "worst":"", "would":"", "wouldn''t":"", "yes":"", "yet":"", "you":"", "you''d":"", "you''ll":"", "your":"", "you''re":"", "yours":"", "yourself":"", "yourselves":"", "you''ve":"", "zero":"" }' >
	<cfset var wordsToAvoid = DeSerializeJSON(wordsToAvoidJSON) />
	<cfset var pc = "" />

	<cfhttp url="#trim(page)#" method="get"></cfhttp>
	
	<cfset pc = LCase(cfhttp.fileContent) />

	<cfset pc = Replace(pc,">",">","All") />
	<cfset pc = Replace(pc,"<","<","All") />
	<cfset pc = Replace(pc," "," ","All") />
	<cfset pc = REReplaceNoCase(pc,"<head[^>]*?>.*?</head>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<style[^>]*?>.*?</style>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<script[^>]*?.*?</script>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<object[^>]*?.*?</object>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<embed[^>]*?.*?</embed>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<applet[^>]*?.*?</applet>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<noframes[^>]*?.*?</noframes>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<noscript[^>]*?.*?</noscript>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<noembed[^>]*?.*?</noembed>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"<(.*?)>"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"[^a-zA-Z0-9.']"," ","ALL")>
	<cfset pc = REReplaceNoCase(pc,"\s+"," ","ALL")>
	<cfset pc = Replace(pc,"."," ","ALL")>
	<cfset pcArray = pc.split(" ") />
	
	<cfloop from="1" to="#ArrayLen(pcArray)#" index="i">
		<cfset tempWord = trim(pcArray[i]) />
		
		<cfif len(tempWord) GT 1  AND NOT IsNumeric(tempWord)>					
			<cfif NOT StructKeyExists(wordsToAvoid, tempWord)>
				<cfif StructKeyExists(wordsCountStruct, tempWord)>
					<cfset wordsCountStruct[tempWord] = wordsCountStruct[tempWord] + 1 />
				<cfelse>
					<cfset StructInsert(wordsCountStruct, tempWord, 1) />
				</cfif>
			</cfif>
		</cfif>
	</cfloop>
	
	<cfreturn wordsCountStruct />
</cffunction>