From 9c6328659f9a4e3d500237ddb352992592dcf3d4 Mon Sep 17 00:00:00 2001
From: xenofem <xenofem@xeno.science>
Date: Wed, 7 Feb 2024 19:18:19 -0500
Subject: [PATCH] refactor checking file extensions

---
 dlibrary/dlibrary.py | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/dlibrary/dlibrary.py b/dlibrary/dlibrary.py
index b637bc7..bfe629a 100755
--- a/dlibrary/dlibrary.py
+++ b/dlibrary/dlibrary.py
@@ -329,8 +329,17 @@ def link_ordered_files(ordering, dest, start_index):
         link_path = dest / f'{idx:04d}{ext}'
         link_path.symlink_to(relpath(src_path, dest))
 
+def check_extension(path, exts):
+    return path.suffix.lower() in exts
+
+def is_pdf(path):
+    check_extension(path, ['.pdf'])
+
+def is_image(path):
+    check_extension(path, IMAGE_FILE_EXTENSIONS)
+
 def ignoreable(path):
-    return path.name in IGNOREABLE_FILES or path.suffix.lower() in IGNOREABLE_EXTENSIONS
+    return path.name in IGNOREABLE_FILES or check_extension(path, IGNOREABLE_EXTENSIONS)
 
 def ls_ignore(directory):
     return [
@@ -455,7 +464,7 @@ def try_collate_images_vs_pdf(srcs, dest, start_index):
         return False
     outer_pdf = pdfs[0]
 
-    inner_pdfs = [f for f in descendant_files_ignore(outer_pdf) if f.suffix.lower() == '.pdf']
+    inner_pdfs = [f for f in descendant_files_ignore(outer_pdf) if is_pdf(f)]
     if len(inner_pdfs) != 1:
         return False
     inner_pdf = inner_pdfs[0]
@@ -465,7 +474,7 @@ def try_collate_images_vs_pdf(srcs, dest, start_index):
     non_images = []
     descendant_files = [f for src in non_pdf_srcs for f in descendant_files_ignore(src)]
     for f in descendant_files:
-        if f.suffix.lower() in IMAGE_FILE_EXTENSIONS:
+        if is_image(f):
             images.append(f)
         else:
             non_images.append(f)
@@ -495,7 +504,7 @@ def collate_from_paths(srcs, dest, start_index):
     if len(srcs) == 1 and srcs[0].is_dir():
         return collate_from_paths(ls_ignore(srcs[0]), dest, start_index)
 
-    if len(srcs) == 1 and srcs[0].suffix.lower() == '.pdf':
+    if len(srcs) == 1 and is_pdf(srcs[0]):
         print(f'Extracting images from {srcs[0]}')
         return link_pdf(srcs[0], dest, start_index)
 
@@ -522,7 +531,7 @@ def collate_from_paths(srcs, dest, start_index):
     if cover_split != False:
         return cover_split
 
-    if all(src.is_file() and src.suffix.lower() in IMAGE_FILE_EXTENSIONS for src in srcs):
+    if all(src.is_file() and is_image(src) for src in srcs):
         ordering = complete_prefix_number_ordering(srcs)
         if ordering:
             print(f'Symlinking image files: {ordering[0]}...')
@@ -558,17 +567,17 @@ def manual_collate(args):
     index = 0
     for path in args.paths:
         if path.is_dir():
-            entries = [p for p in path.iterdir() if p.suffix.lower() in IMAGE_FILE_EXTENSIONS]
+            entries = [p for p in path.iterdir() if p.is_file() and is_image(p)]
             ordering = complete_prefix_number_ordering(entries)
             if ordering is None:
                 ordering = entries
                 ordering.sort()
             link_ordered_files(ordering, collation_dir, index)
             index += len(ordering)
-        elif path.suffix.lower() in IMAGE_FILE_EXTENSIONS:
+        elif is_image(path):
             link_ordered_files([path], collation_dir, index)
             index += 1
-        elif path.suffix.lower() == ".pdf":
+        elif is_pdf(path):
             pdf_page_count = link_pdf(path, collation_dir, index)
             if pdf_page_count is None:
                 return
@@ -587,10 +596,10 @@ def analyze(args):
 
     for f in files:
         print(f'{relpath(f, extract_dir)}', end='')
-        if f.suffix.lower() in IMAGE_FILE_EXTENSIONS:
+        if is_image(f):
             size = standalone_image_size(f)
             print(f'\t{fmt_size(size)}')
-        elif f.suffix.lower() == '.pdf':
+        elif is_pdf(f):
             sizes = pdf_image_sizes(f)
             if len(sizes) == 0:
                 print(f'\tContains no images')