prematureTaggingPositiveThreshold = 0.0
prematureTaggingNegativeThreshold = -0.0
overdureTaggingThreshold = None
overdureTaggingTopReservants = None
'''
The next few parameters are fixed do not change them.
'''
procliticsXmlFile = baseDirectoryOfQutufDB + 'MorphologyTransducers\\Proclitics.xml'
encliticsXmlFile = baseDirectoryOfQutufDB + 'MorphologyTransducers\\Enclitics.xml'
prematureTaggingRulesXmlFile = baseDirectoryOfQutufDB + 'TaggingRepository\\PrematureTaggingRules.xml'
overdueTaggingRulesXmlFile = baseDirectoryOfQutufDB + 'TaggingRepository\\OverdueTaggingRules.xml'
rootsFolder = 'roots2'
#Initialize:
text = TextEncapsulator()
#Load Data from Files:
text.LoadFromFiles(baseDirectoryOfAlKhalilDB, rootsFolder, \
procliticsXmlFile, encliticsXmlFile,\
prematureTaggingRulesXmlFile, \
overdueTaggingRulesXmlFile)
#Read input text into Qutuf:
f = codecs.open(inputTextFile, 'r', 'utf-8')
string = f.read()
f.close()
text.String = string
#Operate:
text.Tokenize()
from Controllers.TextEntities.Word import *;
from Controllers.Tokenization.Tokenizer import *;
from Controllers.Normalization.Normalizer import *;
from Controllers.Morphology.AffixParser import *;
from Controllers.Morphology.MorphologicalAnalyzer import *;
import codecs;
import io;
procliticsXmlFile = '..\\..\\Data\\MorphologyTransducers\\Proclitics.xml';
encliticsXmlFile = '..\\..\\Data\\MorphologyTransducers\\Enclitics.xml';
text = TextEncapsulator();
text.LoadFromFiles(None, None, \
procliticsXmlFile, encliticsXmlFile,\
None, \
None);
f = codecs.open('..\\..\\Data\\Cliticalization_test.txt', 'r', 'utf-8');
string = f.read();
f.close();
text.String = string;
text.Tokenize();
text.Normalize(2);
import io;
import os;
from os.path import join, getsize;
compoundNounsXmlFile = '../../Data/MorphologyTransducers/Proclitics.xml';
procliticsXmlFile = '../../Data/MorphologyTransducers/Proclitics.xml';
encliticsXmlFile = '../../Data/MorphologyTransducers/Enclitics.xml';
prematureTaggingRulesXmlFile = '../../Data/TaggingRepository/PrematureTaggingRules.xml';
overdueTaggingRulesXmlFile = '../../Data/TaggingRepository/OverdueTaggingRules.xml';
baseDirectoryOfAlKhalil = 'D:/temp/AlKhalil_1/db/'
rootsFolder = 'roots2'
text = TextEncapsulator();
text.LoadFromFiles(baseDirectoryOfAlKhalil, rootsFolder, \
procliticsXmlFile, encliticsXmlFile,\
prematureTaggingRulesXmlFile, \
overdueTaggingRulesXmlFile);
base = 'D:/temp/Latifa2/'
for root, dirs, files in os.walk(base):
for dir in dirs:
print('Start parsing directory: ['+dir+']');
for subroot, subdirs, subfiles in os.walk(root+dir):
for file in subfiles:
from os.path import join, getsize
compoundNounsXmlFile = '..\\..\\Data\\MorphologyTransducers\\Proclitics.xml'
procliticsXmlFile = '..\\..\\Data\\MorphologyTransducers\\Proclitics.xml'
encliticsXmlFile = '..\\..\\Data\\MorphologyTransducers\\Enclitics.xml'
prematureTaggingRulesXmlFile = '..\\..\\Data\\TaggingRepository\\PrematureTaggingRules.xml'
overdueTaggingRulesXmlFile = '..\\..\\Data\\TaggingRepository\\OverdueTaggingRules.xml'
baseDirectoryOfAlKhalil = 'D:\\temp\\AlKhalil_1\\db\\'
rootsFolder = 'roots2'
prematureTaggingPositiveThreshold = None
overdureTaggingThreshold = None
overdureTaggingTopReservants = None
text = TextEncapsulator()
text.LoadFromFiles(baseDirectoryOfAlKhalil, rootsFolder, \
procliticsXmlFile, encliticsXmlFile,\
prematureTaggingRulesXmlFile, \
overdueTaggingRulesXmlFile)
base = 'D:\\temp\\Latifa2\\'
for root, dirs, files in os.walk(base):
for file in files:
if file.endswith('.txt') and file.find('-') == -1:
print('\tStart parsing file: [' + file + ']')
f = codecs.open('\\'.join([root, file]), 'r', 'utf-8')
string = f.read()
f.close()