def test_ilg_basic(graph_db, ilg_test_dir):
basic_path = os.path.join(ilg_test_dir, 'basic.txt')
parser = inspect_ilg(basic_path)
with CorpusContext('basic_ilg', **graph_db) as c:
c.reset()
c.load(parser, basic_path)
def test_ilg_basic(graph_db, ilg_test_dir):
basic_path = os.path.join(ilg_test_dir, 'basic.txt')
parser = inspect_ilg(basic_path)
with CorpusContext('basic_ilg', **graph_db) as c:
c.reset()
c.load(parser, basic_path)
def loading(config, corpus_dir, textgrid_format):
with CorpusContext(config) as c:
exists = c.exists()
if exists:
print('Corpus already loaded, skipping import.')
return
if not os.path.exists(corpus_dir):
print('The path {} does not exist.'.format(corpus_dir))
sys.exit(1)
with CorpusContext(config) as c:
print('loading')
if textgrid_format == "buckeye":
parser = pgio.inspect_buckeye(corpus_dir)
elif textgrid_format == "csv":
parser = pgio.inspect_buckeye(corpus_dir)
elif textgrid_format.lower() == "fave":
parser = pgio.inspect_fave(corpus_dir)
elif textgrid_format == "ilg":
parser = pgio.inspect_ilg(corpus_dir)
elif textgrid_format == "labbcat":
parser = pgio.inspect_labbcat(corpus_dir)
elif textgrid_format == "partitur":
parser = pgio.inspect_partitur(corpus_dir)
elif textgrid_format == "timit":
parser = pgio.inspect_timit(corpus_dir)
else:
parser = pgio.inspect_mfa(corpus_dir)
c.load(parser, corpus_dir)
def loading(config, corpus_dir, textgrid_format):
with CorpusContext(config) as c:
exists = c.exists()
if exists:
print('Corpus already loaded, skipping import.')
return
if not os.path.exists(corpus_dir):
print('The path {} does not exist.'.format(corpus_dir))
sys.exit(1)
with CorpusContext(config) as c:
print('loading')
if textgrid_format == "buckeye":
parser = pgio.inspect_buckeye(corpus_dir)
elif textgrid_format == "csv":
parser = pgio.inspect_buckeye(corpus_dir)
elif textgrid_format.lower() == "fave":
parser = pgio.inspect_fave(corpus_dir)
elif textgrid_format == "ilg":
parser = pgio.inspect_ilg(corpus_dir)
elif textgrid_format == "labbcat":
parser = pgio.inspect_labbcat(corpus_dir)
elif textgrid_format == "partitur":
parser = pgio.inspect_partitur(corpus_dir)
elif textgrid_format == "timit":
parser = pgio.inspect_timit(corpus_dir)
else:
parser = pgio.inspect_mfa(corpus_dir)
parser.call_back = call_back
beg = time.time()
c.load(parser, corpus_dir)
end = time.time()
time_taken = end - beg
print('Loading took: {}'.format(time_taken))
save_performance_benchmark(config, 'import', time_taken)
def test_ilg_mismatched(graph_db, ilg_test_dir):
mismatched_path = os.path.join(ilg_test_dir, 'mismatched.txt')
basic_path = os.path.join(ilg_test_dir, 'basic.txt')
parser = inspect_ilg(basic_path)
with CorpusContext('mismatch', **graph_db) as c:
c.reset()
with pytest.raises(ILGWordMismatchError):
c.load(parser, mismatched_path)
def test_ilg_mismatched(graph_db, ilg_test_dir):
mismatched_path = os.path.join(ilg_test_dir, 'mismatched.txt')
basic_path = os.path.join(ilg_test_dir, 'basic.txt')
parser = inspect_ilg(basic_path)
with CorpusContext('mismatch', **graph_db) as c:
c.reset()
with pytest.raises(ILGWordMismatchError):
c.load(parser, mismatched_path)
def loading(config, corpus_dir, textgrid_format):
"""Load the corpus"""
## first check if a database for the corpus
## has already been created
with CorpusContext(config) as c:
exists = c.exists()
if exists:
print('Corpus already loaded, skipping import.')
return
if not os.path.exists(corpus_dir):
print('The path {} does not exist.'.format(corpus_dir))
sys.exit(1)
## if there is no database file,
## begin with importing the corpus
textgrid_format = textgrid_format.upper()
with CorpusContext(config) as c:
print('loading')
## Use the appropriate importer based
## on the format of the corpus
if textgrid_format in ["BUCKEYE", "B"]:
parser = pgio.inspect_buckeye(corpus_dir)
elif textgrid_format == "CSV":
parser = pgio.inspect_buckeye(corpus_dir)
elif textgrid_format.lower() in ["FAVE", "F"]:
parser = pgio.inspect_fave(corpus_dir)
elif textgrid_format == "ILG":
parser = pgio.inspect_ilg(corpus_dir)
elif textgrid_format in ["LABBCAT", "L"]:
parser = pgio.inspect_labbcat(corpus_dir)
elif textgrid_format in ["P", "PARTITUR"]:
parser = pgio.inspect_partitur(corpus_dir)
elif textgrid_format in ["MAUS", "W"]:
parser = pgio.inspect_maus(corpus_dir)
elif textgrid_format in ["TIMIT", "T"]:
parser = pgio.inspect_timit(corpus_dir)
elif textgrid_format in ["W", "maus"]:
parser = pgio.inspect_maus(corpus_dir)
else:
parser = pgio.inspect_mfa(corpus_dir)
parser.call_back = call_back
beg = time.time()
c.load(parser, corpus_dir)
end = time.time()
time_taken = end - beg
print('Loading took: {}'.format(time_taken))
save_performance_benchmark(config, 'import', time_taken)
def test_inspect_ilg_directory(ilg_test_dir):
parser = inspect_ilg(ilg_test_dir)
assert(len(parser.annotation_types) == 2)
def test_inspect_ilg(ilg_test_dir):
basic_path = os.path.join(ilg_test_dir, 'basic.txt')
parser = inspect_ilg(basic_path)
assert(len(parser.annotation_types) == 2)
assert(parser.annotation_types[1].trans_delimiter == '.')
def test_inspect_ilg_directory(ilg_test_dir):
parser = inspect_ilg(ilg_test_dir)
assert (len(parser.annotation_tiers) == 2)
def test_inspect_ilg(ilg_test_dir):
basic_path = os.path.join(ilg_test_dir, 'basic.txt')
parser = inspect_ilg(basic_path)
assert (len(parser.annotation_tiers) == 2)
assert (parser.annotation_tiers[1].trans_delimiter == '.')