File size: 1,950 Bytes
a73045d 4db9499 a73045d 4db9499 a73045d 4db9499 a73045d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | """CSV parsing utilities for the Annotation Management System."""
import csv
import hashlib
import os
def sample_id(conversation_cut):
"""Return an ID that stays the same when CSV rows are reordered."""
digest = hashlib.sha256(conversation_cut.strip().encode('utf-8')).hexdigest()
return f'ES-{digest[:12].upper()}'
def parse_csv_file(filepath):
"""Parse a CSV file and return list of row dicts with only conversation samples."""
rows = []
with open(filepath, 'r', encoding='utf-8') as f:
reader = csv.DictReader(f)
for row in reader:
# Only include rows that have conversation_cut data
if row.get('conversation_cut', '').strip():
sample = dict(row)
sample['sample_index'] = len(rows)
sample['sample_id'] = sample_id(row['conversation_cut'])
rows.append(sample)
return rows
def count_samples(filepath):
"""Count the number of valid conversation samples in a CSV file."""
count = 0
with open(filepath, 'r', encoding='utf-8') as f:
reader = csv.DictReader(f)
for row in reader:
if row.get('conversation_cut', '').strip():
count += 1
return count
def get_sample(filepath, index):
"""Get a specific sample by index from a CSV file."""
rows = parse_csv_file(filepath)
if 0 <= index < len(rows):
return rows[index]
return None
def scan_csv_folder(folder_path):
"""Scan a folder and return list of CSV file info dicts."""
files = []
if not os.path.isdir(folder_path):
return files
for fname in sorted(os.listdir(folder_path)):
if fname.lower().endswith('.csv'):
fpath = os.path.join(folder_path, fname)
files.append({
'filename': fname,
'filepath': fpath,
'size_bytes': os.path.getsize(fpath),
})
return files
|