def main():
transcript_directory = get_transcript_directory()
all_files = os.listdir(transcript_directory)
non_duplicated_files = [f for f in all_files if "(1)" not in f]
commands = []
for file_name in non_duplicated_files:
duplicated_file_name = get_duplicated_file_name(file_name)
original_file_path = os.path.join(transcript_directory, file_name)
duplicated_file_path = os.path.join(transcript_directory, duplicated_file_name)
if os.path.exists(original_file_path) and os.path.exists(duplicated_file_path):
t0: Transcript = get_transcript_by_filename(file_name)
t1: Transcript = get_transcript_by_filename(duplicated_file_name)
speaker0 = next(t0.paragraphs()).speaker
speaker1 = next(t1.paragraphs()).speaker
if speaker0 == "Unknown Speaker":
print(
f"Duplicate found: {file_name}->{speaker0}, {duplicated_file_name}->{speaker1}"
)
commands.append(f'cp "{duplicated_file_name}" {file_name}')
commands.append(f'git rm "{duplicated_file_name}"')
print("\n".join(commands))
def test_get_last_paragraph_for_transcript():
t: Transcript = get_transcript_by_filename(
filename="hooting_yard_2016-06-16.txt")
last_paragraph = list(t.paragraphs())[-1]
assert last_paragraph.text.startswith(
"Finally this week"), f"Wrong text: {last_paragraph.text}"
assert last_paragraph.time_code == datetime.timedelta(seconds=27 * 60 + 9)
def test_second_paragraph():
t: Transcript = get_transcript_by_filename(
filename="hooting_yard_2016-06-16.txt")
paragraphs = t.paragraphs()
_ = next(paragraphs)
second_paragraph = next(paragraphs)
assert second_paragraph.time_code == datetime.timedelta(seconds=43)
def test_get_id_for_transcript():
t: Transcript = get_transcript_by_filename(
filename="hooting_yard_2016-06-16.txt")
assert t.get_id() == "hooting_yard_2016-06-16"
def test_get_words_for_paragraphs_for_transcript():
t: Transcript = get_transcript_by_filename(
filename="hooting_yard_2016-06-16.txt")
first_paragraph = next(t.paragraphs())
assert first_paragraph.time_code == datetime.timedelta(seconds=13)
def test_get_transcript_by_filename():
t: Transcript = get_transcript_by_filename(
filename="hooting_yard_2016-06-16.txt")
assert isinstance(t, Transcript), f"Expected a Transcript, got {t}"
def test_matching():
t = get_transcript_by_filename("hooting_yard_2008-04-24.txt")
ngram_lookup_function = ngram_to_script_index()
match_result = match_single_transcript(ngram_lookup_function, t)