Refactor parsers. Create a new sorter module.

__main__.py

@@ -11,22 +11,23 @@
     ✓ Search bar in toolbar
     ✓ Drop down for TOC (book view)
     ✓ Image reflow
+    ✓ Implement book view settings with a(nother) toolbar
+    ✓ Use format* icons for toolbar buttons
+    ✓ Image delegates
 
-    Implement book view settings with a(nother) toolbar
     Options:
         Ignore a and the for sorting purposes
         Check files (hashes) upon restart
         Recursive file addition
         Show what on startup
-    mobi support
-    txt, doc support
+    mobi, azw support
+    txt, doc, djvu support
     pdf support?
     Goodreads API: Ratings, Read, Recommendations
     Get ISBN using python-isbnlib
     All ebooks should first be added to the database and then returned as HTML
     Theming
     Pagination
-    Use format* icons for toolbar buttons
     Information dialog widget
     Library context menu: Cache, Read, Edit database, delete
     Set context menu for definitions and the like
@@ -39,7 +40,7 @@ from PyQt5 import QtWidgets, QtGui, QtCore
 
 import mainwindow
 import database
-import book_parser
+import sorter
 
 from widgets import LibraryToolBar, BookToolBar, Tab, LibraryDelegate
 from subclasses import Settings, Library
@@ -144,7 +145,7 @@ class MainUI(QtWidgets.QMainWindow, mainwindow.Ui_MainWindow):
         if my_file[0]:
             self.listView.setEnabled(False)
             self.last_open_path = os.path.dirname(my_file[0][0])
-            books = book_parser.BookSorter(my_file[0])
+            books = sorter.BookSorter(my_file[0])
             parsed_books = books.initiate_threads()
             database.DatabaseFunctions(self.database_path).add_to_database(parsed_books)
             self.listView.setEnabled(True)

parsers/epub.py

@@ -1,9 +1,15 @@
 #!/usr/bin/env python3
+# Every parser is supposed to have the following methods, even if they return None:
+# read_book()
+# get_title()
+# get_author()
+# get_year()
+# get_cover_image()
+# get_isbn
+# TODO More for get contents, get TOC
 
 import os
 import re
-import hashlib
-from multiprocessing.dummy import Pool
 
 import ebooklib.epub
 
@@ -15,7 +21,7 @@ class ParseEPUB:
         self.filename = filename
         self.book = None
 
-    def read_epub(self):
+    def read_book(self):
         try:
             self.book = ebooklib.epub.read_epub(self.filename)
         except (KeyError, AttributeError):
@@ -94,54 +100,3 @@ class ParseEPUB:
                     return isbn
         except KeyError:
             return
-
-
-class BookSorter:
-    def __init__(self, file_list):
-        # Have the GUI pass a list of files straight to here
-        # Then, on the basis of what is needed, pass the
-        # filenames to the requisite functions
-        # This includes getting file info for the database
-        # Parsing for the reader proper
-        # Caching upon closing
-        self.file_list = file_list
-        self.all_books = {}
-
-    def read_book(self, filename):
-        # filename is expected as a string containg the
-        # full path of the ebook file
-
-        # TODO
-        # See if you want to include a hash of the book's name and author
-        with open(filename, 'rb') as current_book:
-            file_md5 = hashlib.md5(current_book.read()).hexdigest()
-
-        if file_md5 in self.all_books.items():
-            return
-
-        # TODO
-        # See if tags can be generated from book content
-        book_ref = ParseEPUB(filename)
-        book_ref.read_epub()
-        if book_ref.book:
-            title = book_ref.get_title()
-            author = book_ref.get_author()
-            year = book_ref.get_year()
-            cover_image = book_ref.get_cover_image()
-            isbn = book_ref.get_isbn()
-
-            self.all_books[file_md5] = {
-                'title': title,
-                'author': author,
-                'year': year,
-                'isbn': isbn,
-                'path': filename,
-                'cover_image': cover_image}
-
-    def initiate_threads(self):
-        _pool = Pool(5)
-        _pool.map(self.read_book, self.file_list)
-        _pool.close()
-        _pool.join()
-
-        return self.all_books

sorter.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+
+# TODO
+# Methods that return None must be quantified here if needed
+
+import hashlib
+from multiprocessing.dummy import Pool
+
+from parsers.epub import ParseEPUB
+
+
+class BookSorter:
+    def __init__(self, file_list):
+        # Have the GUI pass a list of files straight to here
+        # Then, on the basis of what is needed, pass the
+        # filenames to the requisite functions
+        # This includes getting file info for the database
+        # Parsing for the reader proper
+        # Caching upon closing
+        self.file_list = file_list
+        self.all_books = {}
+
+    def read_book(self, filename):
+        # filename is expected as a string containg the
+        # full path of the ebook file
+
+        # TODO
+        # See if you want to include a hash of the book's name and author
+        with open(filename, 'rb') as current_book:
+            file_md5 = hashlib.md5(current_book.read()).hexdigest()
+
+        if file_md5 in self.all_books.items():
+            return
+
+        # TODO
+        # See if tags can be generated from book content
+        # Sort according to to file extension here
+        book_ref = ParseEPUB(filename)
+
+        # Everything following this is standard
+        # Some of the None returns will have to have
+        # values associated with them, though
+        book_ref.read_book()
+        if book_ref.book:
+            title = book_ref.get_title()
+            author = book_ref.get_author()
+            year = book_ref.get_year()
+            cover_image = book_ref.get_cover_image()
+            isbn = book_ref.get_isbn()
+
+            self.all_books[file_md5] = {
+                'title': title,
+                'author': author,
+                'year': year,
+                'isbn': isbn,
+                'path': filename,
+                'cover_image': cover_image}
+
+    def initiate_threads(self):
+        _pool = Pool(5)
+        _pool.map(self.read_book, self.file_list)
+        _pool.close()
+        _pool.join()
+
+        return self.all_books