def transfer_vocalizations( self ):
""" load indexed vocalized words from the main index and save them as a list in a dynamic py """
QSE = QuranicSearchEngine( self.__ixpath )
if QSE.OK:
mfw = QSE.most_frequent_words( 9999999, "aya_" )
else:
mfw = []
V = QArabicSymbolsFilter( \
shaping = False, \
tashkil = True, \
spellerrors = False, \
hamza = False \
).normalize_all
vocalization_dict = {}
for w in mfw:
word = w[1]
if vocalization_dict.has_key( V( word ) ):
vocalization_dict[V( word )].append( word )
else:
vocalization_dict[V( word )] = [word]
raw_str = self.dheader + u"\nvocalization_dict=" + str( vocalization_dict ).replace( ",", ",\n" )
fich = open( self.__dypypath + "vocalizations_dyn.py", "w+" )
fich.write( raw_str )
return raw_str
def transfer_vocalizations(self):
""" load indexed vocalized words from the main index and save them as a list in a dynamic py """
QSE = QuranicSearchEngine(self.__ixpath)
if QSE.OK:
mfw = QSE.most_frequent_words(9999999, "aya_")
else:
mfw = []
V = QArabicSymbolsFilter( \
shaping = False, \
tashkil = True, \
spellerrors = False, \
hamza = False \
).normalize_all
vocalization_dict = {}
for w in mfw:
word = w[1]
if vocalization_dict.has_key(V(word)):
vocalization_dict[V(word)].append(word)
else:
vocalization_dict[V(word)] = [word]
raw_str = self.dheader + u"\nvocalization_dict=" + str(
vocalization_dict).replace(",", ",\n")
fich = open(self.__dypypath + "vocalizations_dyn.py", "w+")
fich.write(raw_str)
return raw_str
print "\t", term[1], " - frequence = ", term[0], "."
RESULTS, TERMS = QWSE.search_all( "word_id:1",
limit = 6236,
sortedby = "score",
reverse = True )
print len( RESULTS )
print "\n#list field stored VALUES# type"
print ",".join( [str( item ) for item in QWSE.list_values( "type" )] )
if QSE.OK:
print "\n#most frequent words#"
MFW = QSE.most_frequent_words( 9999999, "uth_" )
print len( MFW )
MFW_CSVFILE = open( "./uthmani_vocalized.csv", "w+" )
for term in MFW:
pass
#print "\t", term[1], " - frequence = ", term[0], "."
#print>>MFW_CSVFILE,"\t", term[1]," ;\t",term[0],"\n"
print "\n#list field stored values#"
print ",".join( [str( item ) for item in QSE.list_values( "gid" )] )
if TSE.OK:
for term in MFW:
print("\t", term[1], " - frequence = ", term[0], ".")
RESULTS, TERMS = QWSE.search_all("word_id:1",
limit=6236,
sortedby="score",
reverse=True)
print(len(RESULTS))
print("\n#list field stored VALUES# type")
print(",".join([str(item) for item in QWSE.list_values("type")]))
if QSE.OK:
print("\n#most frequent words#")
MFW = QSE.most_frequent_words(9999999, "uth_")
print(len(MFW))
MFW_CSVFILE = open("./uthmani_vocalized.csv", "w+")
for term in MFW:
pass
#print "\t", term[1], " - frequence = ", term[0], "."
#print>>MFW_CSVFILE,"\t", term[1]," ;\t",term[0],"\n"
print("\n#list field stored values#")
print(",".join([str(item) for item in QSE.list_values("gid")]))
if TSE.OK:
print("\n#extended search#", end='')
RESULTS = TSE.find_extended("gid:1 OR gid:2", defaultfield="gid")
print("\n".join([str(result) for result in RESULTS]))