fileDirectory,
fileName).readText() # looking to the file and return html text
parser = DataParser(data) # create a parser class
parser.processData() #process the given data
visibleText = parser.getProcessTexts(
) # get all the visibletext in the document
wordList = Tokenize(visibleText).extractToken() #extra all the text
wPost.addWord(
wordList) #add the word, word's frequency, word's position to Posting
parser.updatePostingTagScore(wPost) # update the tag score of the Posting
# Dictionary class will extract information from the Posting as well as update term id for Posting
wDict.extractAndUpdatePosting(wPost)
totalWordCount = wPost.counter # the total Number of word found in document
numOfUniqueTerm = wPost.uniqueTerm # total number of unique term found in document
wDict.updateDictionaryDB() # update the dictionary Table
docID = Location(
location, urlLink, numOfUniqueTerm, parser.getTitleTagContent(),
totalWordCount).insertToDatabase() #insert data into location table
wPost.insertDataToDatabase(
docID) # insert new information in Posting Table
# use to show indexing process
myCounter.increment()
myCounter.printPercentforEveryHundred()
