decoupled

This commit is contained in:
B.J. Dweck 2023-09-11 20:35:55 +03:00
parent a24d0ea96f
commit 28e6c8d611
7 changed files with 74 additions and 106 deletions

View File

@ -2,18 +2,18 @@ import sys
import logging
from logging_config import setup_logging
from images2text import main as ocr_images
from prompt4cards import prompt_for_card_content, response_to_json
from json2deck import to_package
from image_processing import process_images
from deck_creation import prompt_for_card_content, response_to_json, to_package
APKG_FILE = "out.apkg"
setup_logging()
def images_to_package(directory_path, outfile):
ocr_text = ocr_images(directory_path)
def images_to_package(directory_path):
ocr_text = process_images(directory_path)
response_text = prompt_for_card_content(ocr_text)
deck_json = response_to_json(response_text)
to_package(deck_json).write_to_file(outfile)
logging.info(f"Deck created at: {outfile}")
return to_package(deck_json)
if __name__ == "__main__":
@ -21,4 +21,5 @@ if __name__ == "__main__":
print("Usage: python ankiai.py <directory_path_containing_images>")
sys.exit(1)
images_to_package(sys.argv[1])
images_to_package(sys.argv[1]).write_to_file(APKG_FILE)
logging.info(f"Deck created at: {APKG_FILE}")

View File

@ -1,8 +1,10 @@
# File and Directory Constants
IMAGE_KEY="image"
APKG_FILE="out.apkg"
CONVERTED_DIR = "converted"
FINAL_OUTPUT = "final.txt"
TEXT_OCR_FILE = "final.txt"
IMAGE_EXTENSIONS = ['.png', '.jpg', '.jpeg']
OUTPUT_FILENAME = "output_deck.json"
DECK_JSON_FILE = "output_deck.json"
# API Constants
API_KEY_ENV = "OPENAI_API_KEY"

View File

@ -1,8 +1,12 @@
import openai
import os
import sys
import json
from constants import API_KEY_ENV, CHAT_MODEL, OUTPUT_FILENAME
import genanki
from logging_config import setup_logging
from constants import API_KEY_ENV, CHAT_MODEL
setup_logging()
API_KEY = os.environ.get(API_KEY_ENV)
@ -83,21 +87,44 @@ def response_to_json(response_text):
}
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python prompt4cards.py <text_file_path>")
sys.exit(1)
# Create a new model for our cards. This is necessary for genanki.
MY_MODEL = genanki.Model(
1607372319,
"Simple Model",
fields=[
{"name": "Title"},
{"name": "Question"},
{"name": "Answer"},
],
templates=[
{
"name": "{{Title}}",
"qfmt": "{{Question}}",
"afmt": "{{FrontSide}}<hr id='answer'>{{Answer}}",
},
])
text_file_path = sys.argv[1]
def json_file_to_package(json_path):
with open(json_path, 'r', encoding='utf-8') as f:
json_data = json.load(f)
package = to_package(json_data)
# Read the text content
with open(text_file_path, 'r') as file:
text_content = file.read()
return package
response_text = prompt_for_card_content(text_content)
deck_json = response_to_json(response_text)
def to_package(deck_json):
deck_title = deck_json["DeckTitle"]
deck = genanki.Deck(1607372319, deck_title)
with open(OUTPUT_FILENAME, 'w') as json_file:
json.dump(deck_json, json_file)
for card_json in deck_json["Cards"]:
title = card_json["Title"]
question = card_json["Question"]
answer = card_json["Answer"]
print(f"Saved generated deck to {OUTPUT_FILENAME}")
note = genanki.Note(
model=MY_MODEL,
fields=[title, question, answer]
)
deck.add_note(note)
return genanki.Package(deck)

20
images2text.py → image_processing.py Executable file → Normal file
View File

@ -5,13 +5,21 @@ import logging
from logging_config import setup_logging
from subprocess import run, CalledProcessError
from concurrent.futures import ThreadPoolExecutor
from utilities import is_image_file, ensure_directory_exists
from constants import CONVERTED_DIR, FINAL_OUTPUT
from constants import CONVERTED_DIR, TEXT_OCR_FILE, IMAGE_EXTENSIONS
setup_logging()
def is_image_file(path):
return any(path.lower().endswith(ext) for ext in IMAGE_EXTENSIONS)
def ensure_directory_exists(directory):
if not os.path.exists(directory):
os.mkdir(directory)
def convert_image(image_path):
logging.info(f"Converting {image_path}...")
converted_path = os.path.join(CONVERTED_DIR, os.path.basename(image_path))
@ -62,7 +70,7 @@ def process_image(image_path):
return None
def main(directory_path):
def process_images(directory_path):
final_text = []
ensure_directory_exists(CONVERTED_DIR)
@ -80,10 +88,10 @@ def main(directory_path):
# Filter out any None values and write the text to final.txt
final_text = [text for text in final_text if text is not None]
with open(FINAL_OUTPUT, 'w') as f:
with open(TEXT_OCR_FILE, 'w') as f:
f.write("\n".join(final_text))
logging.info(f"All images processed! Final output saved to {FINAL_OUTPUT}")
logging.info(f"All images processed! Final output saved to {TEXT_OCR_FILE}")
return final_text # Add this line
@ -91,4 +99,4 @@ if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python images2text.py <directory_path>")
sys.exit(1)
main(sys.argv[1])
process_images(sys.argv[1])

View File

@ -1,61 +0,0 @@
import json
import genanki
import sys
import logging
from logging_config import setup_logging
setup_logging()
# Create a new model for our cards. This is necessary for genanki.
MY_MODEL = genanki.Model(
1607372319,
"Simple Model",
fields=[
{"name": "Title"},
{"name": "Question"},
{"name": "Answer"},
],
templates=[
{
"name": "{{Title}}",
"qfmt": "{{Question}}",
"afmt": "{{FrontSide}}<hr id='answer'>{{Answer}}",
},
])
def json_file_to_package(json_path):
with open(json_path, 'r', encoding='utf-8') as f:
json_data = json.load(f)
package = to_package(json_data)
return package
def to_package(deck_json):
deck_title = deck_json["DeckTitle"]
deck = genanki.Deck(1607372319, deck_title)
for card_json in deck_json["Cards"]:
title = card_json["Title"]
question = card_json["Question"]
answer = card_json["Answer"]
note = genanki.Note(
model=MY_MODEL,
fields=[title, question, answer]
)
deck.add_note(note)
return genanki.Package(deck)
if __name__ == "__main__":
if len(sys.argv) != 3:
print("Usage: python convert.py <input_json> <output_apkg>")
sys.exit(1)
input_json = sys.argv[1]
output_apkg = sys.argv[2]
json_file_to_package(input_json).write_to_file(output_apkg)
logging.info(f"Deck created at: {output_apkg}")

View File

@ -7,8 +7,7 @@ from logging_config import setup_logging
from flask import Flask, request, send_from_directory, jsonify
from werkzeug.utils import secure_filename
from ankiai import images_to_package
from constants import IMAGE_KEY, OUTPUT_FILE, NO_IMAGE_PART_ERROR, NO_SELECTED_FILE_ERROR, INVALID_FILENAME_ERROR
from constants import IMAGE_KEY, APKG_FILE, NO_IMAGE_PART_ERROR, NO_SELECTED_FILE_ERROR, INVALID_FILENAME_ERROR
setup_logging()
@ -41,8 +40,9 @@ def deck_from_images():
save_uploaded_images(images, temp_dir)
try:
images_to_package(temp_dir, OUTPUT_FILE)
return send_from_directory('.', OUTPUT_FILE, as_attachment=True)
images_to_package(temp_dir).write_to_file(APKG_FILE)
logging.info(f"Anki package written to {APKG_FILE}")
return send_from_directory('.', APKG_FILE, as_attachment=True)
except Exception as e:
logging.error("Exception occurred: "+str(e), exc_info=True)
return jsonify({'error': str(e)}), 500

View File

@ -1,9 +0,0 @@
import os
from constants import IMAGE_EXTENSIONS
def is_image_file(path):
return any(path.lower().endswith(ext) for ext in IMAGE_EXTENSIONS)
def ensure_directory_exists(directory):
if not os.path.exists(directory):
os.mkdir(directory)