Updated this to the latest version of develop, got rid of most of the duplication, might be missing some packages in toml, needs testing

This commit is contained in:
Carlos Mesquita
2024-08-30 02:35:11 +01:00
parent 3cf9fa5cba
commit f92a803d96
73 changed files with 3642 additions and 2703 deletions

View File

@@ -1,11 +1,13 @@
from .io import IOHelper
from .text_helper import TextHelper
from .file import FileHelper
from .text import TextHelper
from .token_counter import count_tokens
from .exercises_helper import ExercisesHelper
from .exercises import ExercisesHelper
from .logger import LoggerHelper
__all__ = [
"IOHelper",
"FileHelper",
"TextHelper",
"count_tokens",
"ExercisesHelper"
"ExercisesHelper",
"LoggerHelper"
]

View File

@@ -4,7 +4,7 @@ import re
import string
from wonderwords import RandomWord
from .text_helper import TextHelper
from .text import TextHelper
class ExercisesHelper:
@@ -70,7 +70,12 @@ class ExercisesHelper:
random.shuffle(combined_array)
return combined_array
result = []
for i, word in enumerate(combined_array):
letter = chr(65 + i) # chr(65) is 'A'
result.append({"letter": letter, "word": word})
return result
@staticmethod
def fillblanks_build_solutions_array(words, start_id):
@@ -187,9 +192,58 @@ class ExercisesHelper:
@staticmethod
def fix_writing_overall(overall: float, task_response: dict):
if overall > max(task_response.values()) or overall < min(task_response.values()):
total_sum = sum(task_response.values())
average = total_sum / len(task_response.values())
grades = [category["grade"] for category in task_response.values()]
if overall > max(grades) or overall < min(grades):
total_sum = sum(grades)
average = total_sum / len(grades)
rounded_average = round(average, 0)
return rounded_average
return overall
@staticmethod
def build_options(ideas):
options = []
letters = iter(string.ascii_uppercase)
for idea in ideas:
options.append({
"id": next(letters),
"sentence": idea["from"]
})
return options
@staticmethod
def build_sentences(ideas, start_id):
sentences = []
letters = iter(string.ascii_uppercase)
for idea in ideas:
sentences.append({
"solution": next(letters),
"sentence": idea["idea"]
})
random.shuffle(sentences)
for i, sentence in enumerate(sentences, start=start_id):
sentence["id"] = i
return sentences
@staticmethod
def randomize_mc_options_order(questions):
option_ids = ['A', 'B', 'C', 'D']
for question in questions:
# Store the original solution text
original_solution_text = next(
option['text'] for option in question['options'] if option['id'] == question['solution'])
# Shuffle the options
random.shuffle(question['options'])
# Update the option ids and find the new solution id
for idx, option in enumerate(question['options']):
option['id'] = option_ids[idx]
if option['text'] == original_solution_text:
question['solution'] = option['id']
return questions

95
app/helpers/file.py Normal file
View File

@@ -0,0 +1,95 @@
import datetime
from pathlib import Path
import base64
import io
import os
import shutil
import subprocess
from typing import Optional
import numpy as np
import pypandoc
from PIL import Image
import aiofiles
class FileHelper:
@staticmethod
def delete_files_older_than_one_day(directory: str):
current_time = datetime.datetime.now()
for entry in os.scandir(directory):
if entry.is_file():
file_path = Path(entry)
file_name = file_path.name
file_modified_time = datetime.datetime.fromtimestamp(file_path.stat().st_mtime)
time_difference = current_time - file_modified_time
if time_difference.days > 1 and "placeholder" not in file_name:
file_path.unlink()
print(f"Deleted file: {file_path}")
# Supposedly pandoc covers a wide range of file extensions only tested with docx
@staticmethod
def convert_file_to_pdf(input_path: str, output_path: str):
pypandoc.convert_file(input_path, 'pdf', outputfile=output_path, extra_args=[
'-V', 'geometry:paperwidth=5.5in',
'-V', 'geometry:paperheight=8.5in',
'-V', 'geometry:margin=0.5in',
'-V', 'pagestyle=empty'
])
@staticmethod
def convert_file_to_html(input_path: str, output_path: str):
pypandoc.convert_file(input_path, 'html', outputfile=output_path)
@staticmethod
def pdf_to_png(path_id: str):
to_png = f"pdftoppm -png exercises.pdf page"
result = subprocess.run(to_png, shell=True, cwd=f'./tmp/{path_id}', capture_output=True, text=True)
if result.returncode != 0:
raise Exception(
f"Couldn't convert pdf to png. Failed to run command '{to_png}' -> ```cmd {result.stderr}```")
@staticmethod
def is_page_blank(image_bytes: bytes, image_threshold=10) -> bool:
with Image.open(io.BytesIO(image_bytes)) as img:
img_gray = img.convert('L')
img_array = np.array(img_gray)
non_white_pixels = np.sum(img_array < 255)
return non_white_pixels <= image_threshold
@classmethod
async def _encode_image(cls, image_path: str, image_threshold=10) -> Optional[str]:
async with aiofiles.open(image_path, "rb") as image_file:
image_bytes = await image_file.read()
if cls.is_page_blank(image_bytes, image_threshold):
return None
return base64.b64encode(image_bytes).decode('utf-8')
@classmethod
def b64_pngs(cls, path_id: str, files: list[str]):
png_messages = []
for filename in files:
b64_string = cls._encode_image(os.path.join(f'./tmp/{path_id}', filename))
if b64_string:
png_messages.append({
"type": "image_url",
"image_url": {
"url": f"data:image/png;base64,{b64_string}"
}
})
return png_messages
@staticmethod
def remove_directory(path):
try:
if os.path.exists(path):
if os.path.isdir(path):
shutil.rmtree(path)
except Exception as e:
print(f"An error occurred while trying to remove {path}: {str(e)}")

View File

@@ -1,20 +0,0 @@
import datetime
import os
from pathlib import Path
class IOHelper:
@staticmethod
def delete_files_older_than_one_day(directory: str):
current_time = datetime.datetime.now()
for entry in os.scandir(directory):
if entry.is_file():
file_path = Path(entry)
file_name = file_path.name
file_modified_time = datetime.datetime.fromtimestamp(file_path.stat().st_mtime)
time_difference = current_time - file_modified_time
if time_difference.days > 1 and "placeholder" not in file_name:
file_path.unlink()
print(f"Deleted file: {file_path}")

23
app/helpers/logger.py Normal file
View File

@@ -0,0 +1,23 @@
import logging
from functools import wraps
class LoggerHelper:
@staticmethod
def suppress_loggers():
def decorator(f):
@wraps(f)
def wrapped(*args, **kwargs):
root_logger = logging.getLogger()
original_level = root_logger.level
root_logger.setLevel(logging.ERROR)
try:
return f(*args, **kwargs)
finally:
root_logger.setLevel(original_level)
return wrapped
return decorator