changed the pdfgeneration files

Author: Rodelph

.gitignore

@@ -10,16 +10,16 @@
 /[Ll]ogs/
 /[Uu]ser[Ss]ettings/
 
-/PdfGenerator/__pycache__/
-/PdfGenerator/build/
-/PdfGenerator/dist/
-/PdfGenerator/access.txt
-/PdfGenerator/*.spec
-/PdfGenerator/*.zip
-/PdfGenerator/_ARMarker/*
-!/PdfGenerator/_ARMarker/Markers
-/PdfGenerator/_ARMarker/Markers/*.meta
-/PdfGenerator/_ARMarker/Markers/*.asset
+/ARchivist_document_generator/__pycache__/
+/ARchivist_document_generator/build/
+/ARchivist_document_generator/dist/
+/ARchivist_document_generator/access.txt
+/ARchivist_document_generator/*.spec
+/ARchivist_document_generator/*.zip
+/ARchivist_document_generator/_ARMarker/*
+!ARchivist_document_generatorr/_ARMarker/Markers
+/ARchivist_document_generator/_ARMarker/Markers/*.meta
+/ARchivist_document_generator/_ARMarker/Markers/*.asset
 
 # MemoryCaptures can get excessive in size.
 # They also could contain extremely sensitive data

ARchivist_document_generator/PDFEngineGit.py

@@ -15,14 +15,21 @@
 from github import Github
 import json
 
+# Check which platform the program is being executed on
 if sys.platform == "win32":
     PATH_TO_WKHTMLTOPDF = r'./wkhtmltopdf/bin/wkhtmltopdf.exe'
 elif sys.platform in ["linux", "linux2"]:
     PATH_TO_WKHTMLTOPDF = r'./wkhtmltopdf/wkhtmltopdf'
 elif sys.platform in ["darwin", "os2", "os2emx"]:
     PATH_TO_WKHTMLTOPDF = r'./wkhtmltopdf/wkhtmltopdf-mcos'
 
+# Coordinates for where to place the qr code
+AP, BP, WID, HEI = 200, 660, 120, 120
+
+# Config setup that looks for the wktml executables within the project
 CONFIG = pdfkit.configuration(wkhtmltopdf=PATH_TO_WKHTMLTOPDF)
+
+# Parameter initialization for files and directories
 OPT = {
     'margin-top': '2in',
     'margin-bottom': '1in',
@@ -32,13 +39,17 @@
 }
 TEMP_PDF_PATH = "./PDF/temp.pdf"
 FINAL_PDF_PATH = "./PDF/output.pdf"
+
+# Creating a unique id for the json data
 UID = str(uuid.uuid4())
 
+# Returns the number of pages in a PDF file.
 def count_pdf_pages(temp_pdf_path):
     with open(temp_pdf_path, 'rb') as file:
         pdf_reader = PdfReader(file)
         return len(pdf_reader.pages)
 
+# Generates QR codes for each page in the PDF.
 def generate_qr_codes(num_pages, uid_folder_path):
     for p_no in range(num_pages):
         text = f'{{"id": "{UID}", "page": {p_no}}}'
@@ -48,12 +59,11 @@ def generate_qr_codes(num_pages, uid_folder_path):
         img = qr.make_image(fill='black', back_color='white')
         img.save(os.path.join(uid_folder_path, f"{p_no}.png"))
 
+# Embeds QR codes and AR markers into each page of the PDF.
 def add_qr_codes_to_pdf(num_pages, temp_pdf_path, final_pdf_path, uid_folder_path):
     pdf_reader = PdfReader(temp_pdf_path)
     pdf_writer = PdfWriter()
 
-    a, b = 200, 660
-    wid, hei = 120, 120
     ar_marker_path = './_ARMarker/Markers/MarkerIcons03.png'
 
     with open(ar_marker_path, 'rb') as marker_file:
@@ -70,8 +80,8 @@ def add_qr_codes_to_pdf(num_pages, temp_pdf_path, final_pdf_path, uid_folder_pat
 
         image_pdf_path = 'image_page.pdf'
         c = canvas.Canvas(image_pdf_path, pagesize=letter)
-        c.drawImage(f"data:image/png;base64,{marker_base64}", a, b, width=wid, height=hei)
-        c.drawImage(f"data:image/png;base64,{qr_base64}", a + wid + 5, b, width=wid, height=hei)
+        c.drawImage(f"data:image/png;base64,{marker_base64}", AP, BP, width=WID, height=HEI)
+        c.drawImage(f"data:image/png;base64,{qr_base64}", AP + WID + 5, BP, width=WID, height=HEI)
         c.save()
 
         with open(image_pdf_path, 'rb') as image_pdf_file:
@@ -85,13 +95,12 @@ def add_qr_codes_to_pdf(num_pages, temp_pdf_path, final_pdf_path, uid_folder_pat
     with open(final_pdf_path, 'wb') as output_pdf:
         pdf_writer.write(output_pdf)
 
+# Extracts hyperlinks from the PDF and updates the JSON bin with metadata.
 def process_pdf_metadata(pdf_path, url):
     doc = fitz.open(pdf_path)
-    a, b = 200, 660
-    wid, hei = 120, 120
     json_data = {
         'URL': url,
-        'ar_marker_coordinates': [a, (792 - (b + hei)), (a + wid), (792 - b)],
+        'ar_marker_coordinates': [AP, (792 - (BP + HEI)), (AP + WID), (792 - BP)],
         'pages': []
     }
 
@@ -115,14 +124,15 @@ def process_pdf_metadata(pdf_path, url):
 
     doc.close()
 
-    with open('github_access_key.txt', 'r') as file:
+    with open('access.txt', 'r') as file:
         access_token = file.read().strip()
     github = Github(access_token)
     repo = github.get_repo('seanscofield/archivist')
     file_content = json.dumps(json_data)
     file_path = f'Assets/CustomAssets/{UID}.json'
     repo.create_file(file_path, "Added entry", file_content)
 
+# Converts a URL to a PDF, generates QR codes, embeds them, processes metadata, and opens the final PDF.
 def making_pdf_qr(path):
     pdfkit.from_url(path, output_path=TEMP_PDF_PATH, configuration=CONFIG, options=OPT, verbose=False)
     num_pages = count_pdf_pages(TEMP_PDF_PATH)
@@ -137,6 +147,7 @@ def making_pdf_qr(path):
     process_pdf_metadata(FINAL_PDF_PATH, path)
     webbrowser.open(FINAL_PDF_PATH)
 
+# Converts a existing HTMLin a local diractory to a PDF, generates QR codes, embeds them, processes metadata, and opens the final PDF.
 def process_pdf_file(file_path):
     num_pages = count_pdf_pages(file_path)
     uid_folder_path = os.path.join("./QR", UID)
@@ -149,6 +160,7 @@ def process_pdf_file(file_path):
     process_pdf_metadata(FINAL_PDF_PATH, file_path)
     webbrowser.open(FINAL_PDF_PATH)
 
+# GUI Application
 class PDFGeneratorApp(QWidget):
     def __init__(self):
         super().__init__()

ARchivist_document_generator/PDFEngineIO.py

@@ -1,4 +1,4 @@
-import os
+import os, shutil
 import sys
 import pdfkit
 import base64
@@ -12,14 +12,21 @@
 from PyQt5.QtWidgets import (QApplication, QWidget, QVBoxLayout, QLineEdit, 
                              QPushButton, QLabel, QMessageBox, QFileDialog)
 
+# Check which platform the program is being executed on
 if sys.platform == "win32":
     PATH_TO_WKHTMLTOPDF = r'./wkhtmltopdf/bin/wkhtmltopdf.exe'
 elif sys.platform in ["linux", "linux2"]:
     PATH_TO_WKHTMLTOPDF = r'./wkhtmltopdf/wkhtmltopdf'
 elif sys.platform in ["darwin", "os2", "os2emx"]:
     PATH_TO_WKHTMLTOPDF = r'./wkhtmltopdf/wkhtmltopdf-mcos'
 
+# Config setup that looks for the wktml executables within the project
 CONFIG = pdfkit.configuration(wkhtmltopdf=PATH_TO_WKHTMLTOPDF)
+
+# Creating a new bin to hold the json on the JSONBIN Database
+BIN_ID = create_data()
+
+# Parameter initialization for files and directories
 OPT = {
     'margin-top': '2in',
     'margin-bottom': '1in',
@@ -29,21 +36,25 @@
 }
 TEMP_PDF_PATH = "./PDF/temp.pdf"
 FINAL_PDF_PATH = "./PDF/output.pdf"
-BIN_ID = create_data()
 QR_FOLDER_PATH = "./QR"
 UID_FOLDER_PATH = os.path.join(QR_FOLDER_PATH, BIN_ID)
 OUTPUT_FOLDER_PATH = "./PDF"
 AR_MARKER_PATH = './_ARMarker/Markers/MarkerIcons03.png'
 
+# Coordinates for where to place the qr code
+AP, BP, WID, HEI = 200, 660, 120, 120
+
 # Ensure directories exist
 os.makedirs(UID_FOLDER_PATH, exist_ok=True)
 os.makedirs(OUTPUT_FOLDER_PATH, exist_ok=True)
 
+# Returns the number of pages in a PDF file.
 def count_pdf_pages(temp_pdf_path):
     with open(temp_pdf_path, 'rb') as file:
         pdf_reader = PdfReader(file)
         return len(pdf_reader.pages)
 
+# Generates QR codes for each page in the PDF.
 def generate_qr_codes(num_pages):
     for p_no in range(num_pages):
         text = f'{{"id": "{BIN_ID}", "page": {p_no}}}'
@@ -53,13 +64,11 @@ def generate_qr_codes(num_pages):
         img = qr.make_image(fill='black', back_color='white')
         img.save(os.path.join(UID_FOLDER_PATH, f"{p_no}.png"))
 
+# Embeds QR codes and AR markers into each page of the PDF.
 def add_qr_codes_to_pdf(num_pages, temp_pdf_path, final_pdf_path):
     pdf_reader = PdfReader(temp_pdf_path)
     pdf_writer = PdfWriter()
 
-    a, b = 200, 660
-    wid, hei = 120, 120
-
     with open(AR_MARKER_PATH, 'rb') as marker_file:
         marker_data = marker_file.read()
         marker_base64 = base64.b64encode(marker_data).decode('utf-8')
@@ -74,8 +83,8 @@ def add_qr_codes_to_pdf(num_pages, temp_pdf_path, final_pdf_path):
 
         image_pdf_path = 'image_page.pdf'
         c = canvas.Canvas(image_pdf_path, pagesize=letter)
-        c.drawImage(f"data:image/png;base64,{marker_base64}", a, b, width=wid, height=hei)
-        c.drawImage(f"data:image/png;base64,{qr_base64}", a + wid + 5, b, width=wid, height=hei)
+        c.drawImage(f"data:image/png;base64,{marker_base64}", AP, BP, width=WID, height=HEI)
+        c.drawImage(f"data:image/png;base64,{qr_base64}", AP + WID + 5, BP, width=WID, height=HEI)
         c.save()
 
         with open(image_pdf_path, 'rb') as image_pdf_file:
@@ -89,20 +98,18 @@ def add_qr_codes_to_pdf(num_pages, temp_pdf_path, final_pdf_path):
     with open(final_pdf_path, 'wb') as output_pdf:
         pdf_writer.write(output_pdf)
 
+# Extracts hyperlinks from the PDF and updates the JSON bin with metadata.
 def process_pdf_metadata(pdf_path, url):
     doc = fitz.open(pdf_path)
-    a, b = 200, 660
-    wid, hei = 120, 120
     json_data = {
         'URL': url,
-        'ar_marker_coordinates': [a, (792 - (b + hei)), (a + wid), (792 - b)],
+        'ar_marker_coordinates': [AP, (792 - (BP + HEI)), (AP + WID), (792 - BP)],
         'pages': []
     }
 
     total_pages = doc.page_count
     item_count = 0
 
-    hyperlink_id = BIN_ID
     for page_idx in range(total_pages):
         cur_page = doc.load_page(page_idx)
         links = cur_page.get_links()
@@ -112,7 +119,7 @@ def process_pdf_metadata(pdf_path, url):
             x0, y0, x1, y1 = item['from']
             coordinates = [round(coord, 5) for coord in [x0, y0, x1, y1]]
             uri = item.get('uri', '')
-            hyperlink = {'id': f"{hyperlink_id}-{item_count}", 'uri': uri, 'coordinates': coordinates}
+            hyperlink = {'id': f"{BIN_ID}-{item_count}", 'uri': uri, 'coordinates': coordinates}
             hyperlinks.append(hyperlink)
             item_count += 1
 
@@ -121,22 +128,26 @@ def process_pdf_metadata(pdf_path, url):
     update_data(bin_id=BIN_ID, json_data=json_data)
     doc.close()
 
+# Converts a URL to a PDF, generates QR codes, embeds them, processes metadata, and opens the final PDF.
 def making_pdf_qr(path):
     pdfkit.from_url(path, output_path=TEMP_PDF_PATH, configuration=CONFIG, options=OPT, verbose=False)
     num_pages = count_pdf_pages(TEMP_PDF_PATH)
     generate_qr_codes(num_pages)
     add_qr_codes_to_pdf(num_pages, TEMP_PDF_PATH, FINAL_PDF_PATH)
     os.remove(TEMP_PDF_PATH)
+    shutil.rmtree(QR_FOLDER_PATH)
     process_pdf_metadata(FINAL_PDF_PATH, path)
     webbrowser.open(FINAL_PDF_PATH)  # Open the final PDF file
 
+# Converts a existing HTMLin a local diractory to a PDF, generates QR codes, embeds them, processes metadata, and opens the final PDF.
 def process_pdf_file(file_path):
     num_pages = count_pdf_pages(file_path)
     generate_qr_codes(num_pages)
     add_qr_codes_to_pdf(num_pages, file_path, FINAL_PDF_PATH)
     process_pdf_metadata(FINAL_PDF_PATH, file_path)
     webbrowser.open(FINAL_PDF_PATH)  # Open the final PDF file
 
+# GUI Application
 class PDFGeneratorApp(QWidget):
     def __init__(self):
         super().__init__()

ARchivist_document_generator/jsonio.py

@@ -1,12 +1,15 @@
 import requests
 
+#  URL: The base URL for JSONBin API.
 URL = 'https://api.jsonbin.io/v3/b'
 
+#  HEADERS: Headers required for the API requests, including the Content-Type and the X-Access-Key for authentication.
 HEADERS = {
   'Content-Type': 'application/json',
   'X-Access-Key': '$2a$10$/rAImv8LT5TYb0BGu6ur4eTcRlOCW1WgGk6PqM7SeVfnCW.lLG1qO'
 }
 
+# print_status: A decorator function that prints the status of the wrapped function execution.
 def print_status(func):
     def wrapper(*args, **kwargs):
         print(f"Executing {func.__name__}...")
@@ -18,6 +21,10 @@ def wrapper(*args, **kwargs):
         return result
     return wrapper
 
+#    Creates a new JSONBin with some initial data ({"empty": "empty"}).
+#    Uses a session to manage the request.
+#    Handles exceptions to print an error message and returns None if an error occurs.
+#    Returns the bin_id from the response if the request is successful.
 @print_status
 def create_data():
     session = requests.Session()
@@ -32,6 +39,10 @@ def create_data():
     finally:
         session.close()
 
+#     Updates the data in the specified JSONBin using its bin_id.
+#     Constructs the URL for the specific bin.
+#     Handles exceptions to print an error message and returns False if an error occurs.
+#     Returns True if the request is successful.
 @print_status
 def update_data(bin_id, json_data):
     session = requests.Session()