def searchQueryUnion(query,dictionary):
result=[]
IDresult=[]
postings=[]
DocID=[]
#Tokenise the query for process later
tokens=Tokenization.tokenization(query)
#Normalize the tokens for process later
for index in range(len(tokens)):
tokens[index] = Normalization.cleanStopWords150(tokens[index])
tokens[index] = Normalization.cleanedTokens(tokens[index])
tokens[index] = Normalization.caseFoldedTokens(tokens[index])
tokens[index] = Normalization.stemmedTokens(tokens[index])
if tokens[index] in dictionary:
DocID=DocID+dictionary.get(tokens[index])
if DocID!=[]:
#change docID from string to int
for index in range(len(DocID)):
DocID[index]=DocID[index].split(',')
DocID[index]=DocID[index][0].split()
DocID[index]=map(int, DocID[index])
#Getting the intersection of the DocID for different tokens in query
DocID=[set(id) for id in DocID]
#print DocID
finalID=sorted(set.union(*DocID))
return finalID
else:
finalID=DocID
return finalID
def getInvertedIndexTokens(fileNum):
invertedIndex={}
#loading the orginal documents for tokenization and normalization later
fileNum= '%0*d' % (3, fileNum)
resourcepath = 'reuters/reut2-' + fileNum + '.sgm'
file = open(resourcepath)
soup = BeautifulSoup(file, 'html.parser')
allReuters=soup.find_all('reuters')
for reuters in allReuters:
if reuters.body is not None:
#Tokenize the text inside the [body]tag in the files
tokenslist=reuters.body.text.rsplit('reuters',1)
for e in tokenslist:
tokens=''.join(e).encode('utf8')
tokens=Tokenization.tokenization(tokens)
for token in tokens:
#Normalization after get the tokens
token = Normalization.cleanedTokens(token)
token = Normalization.caseFoldedTokens(token)
token = Normalization.cleanStopWords150(token)
token = Normalization.stemmedTokens(token)
#Construct the inverted index for tokens
if token != '':
if invertedIndex.has_key(token):
if reuters['newid'] not in invertedIndex[token]:
invertedIndex[token].append(reuters['newid'])
else:
invertedIndex[token] = [reuters['newid']]
return invertedIndex
def purrify(query):
# purrify the query
normalizedTokens = []
tokens = Tokenization.tokenization(query)
for token in tokens:
token = Normalization.cleanedTokens(token)
token = Normalization.caseFoldedTokens(token)
token = Normalization.cleanStopWords150(token)
token = Normalization.stemmedTokens(token)
if token != "":
normalizedTokens.append(token)
#print normalizedTokens
return normalizedTokens
def getAllTokens(fileNum):
# Create inverted index, loop through all articles in one file
invertedIndex = {}
tokensLength= open('invertedIndex/tokensLength', 'a')
Content = open('invertedIndex/Content', 'a')
#loading the orginal documents for tokenization and normalization later
fileNum= '%0*d' % (3, fileNum)
resourcepath = 'reuters/reut2-' + fileNum + '.sgm'
file = open(resourcepath)
soup = BeautifulSoup(file, 'html.parser')
for doc in soup.find_all('reuters'):
docId = int(doc['newid'].encode('utf8'))
tokenCounter = 0
if doc.body is not None:
content = doc.body.text
length=len(content)
Content.write (str(docId) + ' Start ' + content.encode('utf8') + ' End ')
tokens = Tokenization.tokenization(content)
for token in tokens:
# Normalization
token = Normalization.cleanedTokens(token)
token = Normalization.caseFoldedTokens(token)
token = Normalization.cleanStopWords150(token)
token = Normalization.stemmedTokens(token)
if token != '':
tokenCounter += 1
# Add to the postings list if the word exists
if invertedIndex.has_key(token):
if invertedIndex[token].has_key(docId):
tf = invertedIndex[token][docId]
invertedIndex[token][docId] = tf +1
else:
invertedIndex[token][docId] = 1
else:
invertedIndex[token] = {docId:1}
tokensLength.write (str(docId) + ':' + str(tokenCounter) +'\n')
tokensLength.close()
Content.close()
return invertedIndex