def small_fLoc_test3():
s1 = ", ?Van Daal ,"
tnt = NER()
ee = tnt(s1)
print ee
for e in ee:
print e[0], e[1], e[2], " : ", s1[e[1] : e[2] + 1]
# print "Entity: ", s1[e[1]: e[2] + 1]
m = DistanceMatrix(fLevenshteinDistance, s1, tnt._processed_text)
p = fMinPath()(m)
print m.toString(p)
t = time.time()
#prepare_data()
#step1_fetch_text(os.path.join(data_dir, "xml"))
#step2_run_tnt(os.path.join(data_dir, "txt"))
#step3_calc_lev_distance()
#step4_calc_minpath()
#step5_calc_minpath_dt()
#step6_cleantnt_txt()
#step5_calc_minpath_dt("cleaned-tnt", "txt", size_limit=1000)
from gravity.tae.match.lev_distance import fLevDistanceDiag
#s1 = "Song about Alice dream"
#s2 = "Song al?ce dream"
s1 = " abc d dfg rer klm"
s2 = "abc dfg klm"
m = DistanceMatrix(111)
#fLevDistanceDiag(1).fill_matrix(s2, s1, m)
fLevDistance().fill_matrix(s2, s1, m)
print m.toString(s2, s1, fMinPath()(m))
print "Elapsed time: ", (time.time() - t)
step1_fetch_text(os.path.join(data_dir, "xml"))
step2_run_tnt(os.path.join(data_dir, "txt"))
step6_cleantnt_txt()
t = time.time()
#prepare_data()
#step1_fetch_text(os.path.join(data_dir, "xml"))
#step2_run_tnt(os.path.join(data_dir, "txt"))
#step3_calc_lev_distance()
#step4_calc_minpath()
#step5_calc_minpath_dt()
#step6_cleantnt_txt()
#step5_calc_minpath_dt("cleaned-tnt", "txt", size_limit=1000)
from gravity.tae.match.lev_distance import fLevDistanceDiag
#s1 = "Song about Alice dream"
#s2 = "Song al?ce dream"
s1 = " abc d dfg rer klm"
s2 = "abc dfg klm"
m = DistanceMatrix(111)
#fLevDistanceDiag(1).fill_matrix(s2, s1, m)
fLevDistance().fill_matrix(s2, s1, m)
print m.toString(s2, s1, fMinPath()(m))
print "Elapsed time: ", (time.time() - t)
# small_fLoc_test3() # general_test() # lev_test() # levdiag_test0() # levdiag_test2() # levdiag_test1() # levdiag_test3() # levdiag_test4() # levdiag_test5() t1, t2 = "asdsdsa", "ssasasas" m = DistanceMatrix(fLevenshteinDistance2, t1, t2) print m.toString(t1, t2) t1, t2 = "asdsdsa", "ssasasas" m = DistanceMatrix(fLevenshteinDistance, t1, t2) print m.toString(t1, t2) t1, t2 = "asdsdsa", "ssasasas" m = DistanceMatrix(fClassicalLevenshteinDistance, t1, t2) print m.toString(t1, t2) t1, t2 = "asdsdsa", "ssasasas" m = DistanceMatrix(fDiagDistance(6), t1, t2, 111) print m.toString(t1, t2) s = s1 = s2 = read_file(data_dir + "/73632.agg.txt")
