import sys
sys.path.insert(0,'../')
import db.litebase
if __name__ == '__main__':
#you can create the dictionary using arramouz database (http://arramooz.sourceforge.net/)
# ory ou can find it by downloading
#"http://sourceforge.net/projects/mishkal/files/mishkal2013-05-18.tar.bz2/download"
# in ./lib/qalsadi/data/arabicdictionary.sqlite
srcdb = litebase.liteBase('arabicdictionary.sqlite')
dstdb = litebase.liteBase('words.sqlite')
tab = litebase.liteTable()
tab.beginTable("nouns")
tab.addColumn('id', litebase.litePK_INT_INC(), u'', False)
tab.addColumn('word', litebase.liteVARCHAR(20), u'DEFAULT NULL', True)
tab.addColumn('pattern', litebase.liteVARCHAR(20), u'DEFAULT NULL', True)
tab.endTable()
print tab.getSqlQuery()
dstdb.addTable(tab)
src = srcdb.getTable('nouns')
rows = src.getData()
first = True
for row in rows:
if first:
from db.litebase import liteBase, liteINTEGER, liteVARCHAR
from db.litebase import liteTable
if __name__ == '__main__':
dstdb = liteBase('tatoeba.db')
f = codecs.open("sentences.csv", "r", "utf-8")
i = 0;
for line in f:
e = line.split("\t");
if len(e) < 3:
continue
if e[1] in ("ara", "fra", "eng", "jpn"):
if not dstdb.containsTable(e[1]):
tab = liteTable()
tab.beginTable(e[1])
tab.addColumn('id', liteINTEGER(), u'', False)
tab.addColumn('sent', liteVARCHAR(60), u'DEFAULT NULL', True)
tab.endTable()
dstdb.addTable(tab)
#print tab.getSqlQuery()
data = u'%s, "%s"' % (e[0],e[2])
print data
dst = dstdb.getTable(e[1])
dst.insertData(data, u'id, sent')
i = i + 1
if (i>=1000):
dstdb.commit()
i=0
dstdb.commit()
from trans.buckwalter import Buckwalter
import pattern
if __name__ == '__main__':
#
'''theword = "AbotAE"
theword_u = "AbtAE"
print distance(theword, "AfotaAEa")
print getTemplate(theword, theword_u)
exit()'''
srcdb = litebase.liteBase(os.path.realpath('../test/ardic.sqlite'))
dstdb = litebase.liteBase(os.path.realpath('../test/words.sqlite'))
tab = litebase.liteTable()
tab.beginTable("words")
tab.addColumn('id', litebase.litePK_INT_INC(), u'', False)
tab.addColumn('word', litebase.liteVARCHAR(20), u'DEFAULT NULL', True)
tab.addColumn('pattern', litebase.liteVARCHAR(20), u'DEFAULT NULL', True)
tab.addColumn('vocalized', litebase.liteVARCHAR(20), u'DEFAULT NULL', True)
tab.endTable()
# print tab.getSqlQuery()
dstdb.addTable(tab)
src = srcdb.getTable('ardict')
print src.getSqlQuery()
rows = src.getData()
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
import sys
import os
import codecs
from db.litebase import liteBase, liteINTEGER, liteVARCHAR
from db.litebase import liteTable
if __name__ == '__main__':
path = os.path.realpath("tatoeba.db")
tatodb = liteBase(path)
linksTable = liteTable()
if not tatodb.containsTable("links"):
linksTable.beginTable("links")
linksTable.addColumn('jpnId', liteINTEGER(), u'', True)
linksTable.addColumn('id', liteINTEGER(), u'', False)
linksTable.endTable()
tatodb.addTable(linksTable)
else:
linksTable = tatodb.getTable("links")
f = codecs.open("links.csv", "r", "utf-8")
lastskip = "0"
jpnTable = tatodb.getTable('jpn')
i = 0
for line in f:
