|
|
|
|
|
import os |
|
|
import time |
|
|
from datetime import datetime |
|
|
from digest_segment import process_segment |
|
|
from export_to_spreadsheet import export_to_csv |
|
|
|
|
|
SEGMENT_PATH = os.path.join(os.path.dirname(__file__), "digest_paths") |
|
|
CSV_PATH = os.path.join(os.path.dirname(__file__), "digs_results.csv") |
|
|
PROCESSED_LOG = os.path.join(os.path.dirname(__file__), ".digested_files.log") |
|
|
|
|
|
def load_processed(): |
|
|
if os.path.exists(PROCESSED_LOG): |
|
|
with open(PROCESSED_LOG, 'r') as f: |
|
|
return set(line.strip() for line in f.readlines()) |
|
|
return set() |
|
|
|
|
|
def save_processed(filename): |
|
|
with open(PROCESSED_LOG, 'a') as f: |
|
|
f.write(filename + "\n") |
|
|
|
|
|
def append_to_csv(result): |
|
|
import csv |
|
|
exists = os.path.exists(CSV_PATH) |
|
|
with open(CSV_PATH, 'a', newline='', encoding='utf-8') as csvfile: |
|
|
writer = csv.DictWriter(csvfile, fieldnames=["timestamp", "filename", "char_count", "processed_paths"]) |
|
|
if not exists: |
|
|
writer.writeheader() |
|
|
writer.writerow({ |
|
|
"timestamp": datetime.utcnow().isoformat(), |
|
|
**result |
|
|
}) |
|
|
|
|
|
def watch_and_digs(): |
|
|
print("DIGS Daemon running. Watching for new .txt files...") |
|
|
seen = load_processed() |
|
|
|
|
|
while True: |
|
|
for file in os.listdir(SEGMENT_PATH): |
|
|
if file.endswith(".txt") and file not in seen: |
|
|
full_path = os.path.join(SEGMENT_PATH, file) |
|
|
print(f"Processing new file: {file}") |
|
|
try: |
|
|
result = process_segment(full_path) |
|
|
if result: |
|
|
append_to_csv(result) |
|
|
save_processed(file) |
|
|
print(f"Done: {file}") |
|
|
except Exception as e: |
|
|
print(f"Error processing {file}: {e}") |
|
|
time.sleep(2) |
|
|
|
|
|
if __name__ == "__main__": |
|
|
watch_and_digs() |
|
|
|
