refactor: streamline JSON conversion functions and improve error hand…

…ling for unsupported file types

audiobook/main.py

@@ -6,17 +6,9 @@
 
 from audiobook.config import speed_dict
 from audiobook.utils import (
-    docs_to_json,
-    epub_to_json,
-    html_to_json,
     load_json,
-    mobi_to_json,
-    odt_to_json,
-    pdf_to_json,
     speak_text,
-    txt_to_json,
     write_json_file,
-    rtf_to_json
 )
 from audiobook.utils import get_json_metadata
 
@@ -73,10 +65,7 @@ def create_json_book(self, input_book_path, password=None, load_from_library=Fal
                 metadata["pages"] = len(json_book)
                 return json_book, metadata
 
-        if json_book:
-            json_book, metadata = get_json_metadata(input_book_path=input_book_path, password=password)
-        else:
-            raise NotImplementedError("Only PDF, TXT, EPUB, MOBI, ODT, HTTP, RTF, DOCX and DOC files are supported")
+        json_book, metadata = get_json_metadata(input_book_path=input_book_path, password=password)
 
         write_json_file(json_book, output_file_path)
 

audiobook/utils.py

@@ -1,7 +1,6 @@
 import json
 import os
 import re
-
 import docx2txt
 import ebooklib
 import html2text
@@ -11,235 +10,187 @@
 from odf import text, teletype
 from odf.opendocument import load
 from striprtf.striprtf import rtf_to_text
-
 from audiobook.doc_parser.web_parser import ArticleWebScraper
 from audiobook.doc_parser.pdf_parser import PyPDF2DocParser
-# from audiobook.doc_parser.pdf_parser import PdfMinerDocParser
-
 
+# Helper function to load JSON data from a file
 def load_json(filename):
     with open(filename, "r") as fp:
         return json.load(fp)
 
-
+# Helper function to write JSON data to a file
 def write_json_file(json_data, filename):
     with open(filename, "w") as fp:
         json.dump(json_data, fp)
 
-
+# Text preprocessing: removes unwanted characters and extra spaces
 def text_preprocessing(input_text):
-    """function to preprocess text"""
-    regex = re.compile(r"[\n\r\t]")
-    preprocessed_text = regex.sub("", input_text)
-    preprocessed_text = re.sub(" +", " ", preprocessed_text)
-    preprocessed_text = preprocessed_text.strip()
+    preprocessed_text = re.sub(r"[\n\r\t]", "", input_text)
+    preprocessed_text = re.sub(" +", " ", preprocessed_text).strip()
     return preprocessed_text
 
-
+# Extract text content from HTML, preprocess it
 def response_to_text(chapter):
-    """fuction to convert response to text
-
-    required for epub files
-    maybe required for html files
-    """
     soup = BeautifulSoup(chapter, "html.parser")
-    extracted_text = [para.get_text() for para in soup.find_all("p")]
-    extracted_text = " ".join(extracted_text)
-    preprocessed_text = text_preprocessing(extracted_text)
-    return preprocessed_text
-
+    extracted_text = " ".join([para.get_text() for para in soup.find_all("p")])
+    return text_preprocessing(extracted_text)
 
+# Speak the given text using the engine
 def speak_text(engine, text, display=True):
-    """function to speak text and display it"""
     if display:
         print(text)
     engine.say(text)
     engine.runAndWait()
 
-
+# Helper function to convert mobi files to JSON format
 def mobi_to_json(input_book_path):
-    """sub method to create json book from mobi file"""
     metadata = {}
     json_book = {}
     book_name = os.path.basename(input_book_path).split(".")[0]
     tempdir, filepath = mobi.extract(input_book_path)
+
     with open(filepath, "r", encoding="utf-8") as fp:
         content = fp.read()
+
     book_data = html2text.html2text(content)
     book_data = text_preprocessing(book_data)
 
-    for i in range(0, len(book_data), 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = book_data[i: i + 2000]
-
+    # Split content into chunks of 2000 characters
+    json_book = {str(i // 2000): book_data[i:i + 2000] for i in range(0, len(book_data), 2000)}
+
     metadata["pages"] = len(json_book)
     metadata["book_name"] = book_name
     return json_book, metadata
 
-
+# Helper function to convert PDF to JSON format
 def pdf_to_json(input_book_path, password=None):
-    """sub method to create json book from pdf file"""
-    metadata = {}
     json_book = {}
+    metadata = {}
     basename = os.path.basename(input_book_path).split(".")[0]
 
-    # removed pdf parser selection(only pydf2 is supported now)
-    # if extraction_engine is None or extraction_engine == "pdfminer":
-    #     print("Using pdfminer")
-    #     pdf_parser = PdfMinerDocParser()
-    # elif extraction_engine == "pypdf2":
-    #     print("Using pypdf2")
-    #     pdf_parser = PyPDF2DocParser()
-    # else:
-    #     raise NotImplementedError("Only pdfminer and pypdf2 are supported")
-
     pdf_parser = PyPDF2DocParser()
     text = pdf_parser.get_text(input_book_path, password=password)
     text = text_preprocessing(text)
 
-    for i in range(0, len(text), 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = text[i: i + 2000]
-
-    metadata['book_name'] = basename
-    metadata['pages'] = len(json_book)
+    json_book = {str(i // 2000): text[i:i + 2000] for i in range(0, len(text), 2000)}
+
+    metadata["book_name"] = basename
+    metadata["pages"] = len(json_book)
     return json_book, metadata
 
-
+# Helper function to convert ODT files to JSON format
 def odt_to_json(input_book_path):
-    """sub method to create json book from odt file"""
-    metadata = {}
     json_book = {}
+    metadata = {}
     basename = os.path.basename(input_book_path).split(".")[0]
 
     textdoc = load(input_book_path)
-    allparas = textdoc.getElementsByType(text.P)
-    output_text = ""
-    for i in range(len(allparas)):
-        output_text += " " + teletype.extractText(allparas[i])
+    output_text = " ".join([teletype.extractText(para) for para in textdoc.getElementsByType(text.P)])
     output_text = text_preprocessing(output_text)
 
-    for i in range(0, len(output_text), 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = output_text[i: i + 2000]
-
-    metadata['book_name'] = basename
-    metadata['pages'] = len(json_book)
-
+    json_book = {str(i // 2000): output_text[i:i + 2000] for i in range(0, len(output_text), 2000)}
+
+    metadata["book_name"] = basename
+    metadata["pages"] = len(json_book)
     return json_book, metadata
 
-
+# Helper function to convert TXT files to JSON format
 def txt_to_json(input_book_path):
-    """sub method to create json book from txt file"""
     json_book = {}
     metadata = {}
     book_name = os.path.basename(input_book_path).split(".")[0]
+
     with open(input_book_path, "r") as fp:
         file_txt_data = fp.read()
+
     file_txt_data = text_preprocessing(file_txt_data)
-
-    for i in range(0, len(file_txt_data), 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = file_txt_data[i: i + 2000]
-
+    json_book = {str(i // 2000): file_txt_data[i:i + 2000] for i in range(0, len(file_txt_data), 2000)}
+
     metadata["pages"] = len(json_book)
     metadata["book_name"] = book_name
     return json_book, metadata
 
-
+# Helper function to convert RTF files to JSON format
 def rtf_to_json(input_book_path):
-    """sub method to create json book from rtf file"""
     json_book = {}
     metadata = {}
     book_name = os.path.basename(input_book_path).split(".")[0]
+
     with open(input_book_path, "r") as fp:
         file_rtf_data = fp.read()
-    file_txt_data = rtf_to_text(file_rtf_data , errors="ignore")
+
+    file_txt_data = rtf_to_text(file_rtf_data, errors="ignore")
     file_txt_data = text_preprocessing(file_txt_data)
 
-    for i in range(0, len(file_txt_data), 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = file_txt_data[i: i + 2000]
-
+    json_book = {str(i // 2000): file_txt_data[i:i + 2000] for i in range(0, len(file_txt_data), 2000)}
+
     metadata["pages"] = len(json_book)
     metadata["book_name"] = book_name
     return json_book, metadata
 
-
+# Helper function to convert DOCX files to JSON format
 def docs_to_json(input_book_path):
-    """sub method to create json book from docs file"""
-    metadata = {}
     json_book = {}
+    metadata = {}
     book_name = os.path.basename(input_book_path).split(".")[0]
+
     book_data = docx2txt.process(input_book_path)
-    for i in range(0, len(book_data), 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = book_data[i: i + 2000]
-
+    json_book = {str(i // 2000): book_data[i:i + 2000] for i in range(0, len(book_data), 2000)}
+
     metadata["pages"] = len(json_book)
     metadata["book_name"] = book_name
     return json_book, metadata
 
-
+# Helper function to convert EPUB files to JSON format
 def epub_to_json(input_book_path):
-    metadata = {}
     json_book = {}
+    metadata = {}
     book_name = os.path.basename(input_book_path).split(".")[0]
+
     book = epub.read_epub(input_book_path)
-    text = " ".join(
-        [
-            response_to_text(chapter.get_body_content())
-            for chapter in book.get_items_of_type(ebooklib.ITEM_DOCUMENT)
-        ]
-    )
-    for i in range(1, len(text) + 1, 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = text[i: i + 2000]
-
+    text = " ".join([response_to_text(chapter.get_body_content()) for chapter in book.get_items_of_type(ebooklib.ITEM_DOCUMENT)])
+
+    json_book = {str(i // 2000): text[i:i + 2000] for i in range(1, len(text) + 1, 2000)}
+
     metadata["pages"] = len(json_book)
     metadata["book_name"] = book_name
     return json_book, metadata
 
-
+# Helper function to convert HTML (web) content to JSON format
 def html_to_json(url):
-    """method to create json book from web article"""
     metadata = {}
     json_book = {}
     book_name = os.path.basename(url).split(".")[0]
+
     article_scraper = ArticleWebScraper(url)
     page_data = article_scraper.get_page_data()
     page_data = text_preprocessing(page_data)
-    for i in range(0, len(page_data), 2000):
-        page_num = i // 2000
-        json_book[str(page_num)] = page_data[i: i + 2000]
-
+
+    json_book = {str(i // 2000): page_data[i:i + 2000] for i in range(0, len(page_data), 2000)}
+
     metadata["pages"] = len(json_book)
     metadata["book_name"] = book_name
     return json_book, metadata
 
-
-def get_json_metadata(input_book_path, password):
-    """ helper function to call the function based on the file type """
-    # get the file extension
-    json_book = {}
-    metadata = {}
-    file_extension = input_book_path.split(".")[-1]
-
-    if file_extension == "odt":
-        json_book, metadata = odt_to_json(input_book_path)
-    elif file_extension == "pdf":
-        json_book, metadata = pdf_to_json(input_book_path, password)
-    elif file_extension == "txt":
-        json_book, metadata = txt_to_json(input_book_path)
-    elif file_extension == "epub":
-        json_book, metadata = epub_to_json(input_book_path)
-    elif file_extension == "mobi":
-        json_book, metadata = mobi_to_json(input_book_path)
-    elif input_book_path.startswith(("http", "https")):
-        json_book, metadata = html_to_json(input_book_path)
-    elif input_book_path.endswith((".docx", ".doc")):
-        json_book, metadata = docs_to_json(input_book_path)
-    elif file_extension == "rtf":
-        json_book, metadata = rtf_to_json(input_book_path)
-
+# Main function to determine the file type and call respective methods
+def get_json_metadata(input_book_path, password=None):
+    file_extension = input_book_path.split(".")[-1].lower()
+    json_book, metadata = {}, {}
+
+    file_to_json = {
+        "odt": odt_to_json,
+        "pdf": pdf_to_json,
+        "txt": txt_to_json,
+        "epub": epub_to_json,
+        "mobi": mobi_to_json,
+        "html": html_to_json,
+        "docx": docs_to_json,
+        "rtf": rtf_to_json
+    }
+
+    if file_extension in file_to_json:
+        json_book, metadata = file_to_json[file_extension](input_book_path, password)
+    else:
+        raise NotImplementedError(f"Unsupported file type: {file_extension}")
+
     return json_book, metadata