neuralworm's picture
better populate speed, refactor, fix
d07d4c9
raw
history blame
1.25 kB
import json
import re
def process_json_files(start, end):
"""
Processes JSON files containing Tanach text and returns a dictionary
mapping book IDs to their data.
Args:
start: The starting book ID (inclusive).
end: The ending book ID (inclusive).
Returns:
A dictionary where keys are book IDs and values are dictionaries
containing 'title' and 'text' fields.
"""
base_path = "texts"
results = {} # Use a dictionary to store results
for i in range(start, end + 1):
file_name = f"{base_path}/{i:02}.json"
try:
with open(file_name, 'r', encoding='utf-8') as file:
data = json.load(file)
if data:
# Store book ID as key and book data as value
results[i] = {"title": data.get("title", "No title"), "text": data.get("text", [])}
except FileNotFoundError:
logging.warning(f"File {file_name} not found.")
except json.JSONDecodeError as e:
logging.warning(f"File {file_name} could not be read as JSON: {e}")
except KeyError as e:
logging.warning(f"Expected key 'text' is missing in {file_name}: {e}")
return results