Check for tooSmall <1KB and tooLarge >10MB files.

.gitignore

@@ -1,5 +1,3 @@
 myenv
 __pycache__
-dups.txt
-alike.txt
-invalid.txt
+*.txt

README.md

@@ -66,6 +66,6 @@ python dedup.py 0.jpg 1.jpg scores
 ```
 
 ### Files made by get_dups Scripts:
-error level: 0 = NOT a Dup, 1 = Duplicate, 2 = Close Match, 5 = Same GPS GEO-location, 8 = Invalid Image. Possible files: dups.txt, alike.txt, sameGPS.txt, and invalid.txt
+error level: 0 = NOT a Dup, 1 = Duplicate, 2 = Close Match, 5 = Same GPS GEO-location, 8 = Invalid Image, 9 = File Too small/big. Possible files: dups.txt, alike.txt, sameGPS.txt, invalid.txt, size.txt.
 
 [![Image of ScreenShot](Screenshot2025-04-26.png)]

TooSmall.jpg

@@ -0,0 +1 @@
+adsfkjnhdsfljdkfsljdsklfdsjflds

dedup.py

@@ -29,6 +29,8 @@ Memory usage significantly reduced
 """
 
 within_one_mile_check = True
+too_small = 1024 # 1KB
+too_large = 10 * 1024 * 1024 # 10MB
 
 def handle_GPS(location1, location2):
     camera_info1, latitude1, longitude1 = location1
@@ -71,6 +73,17 @@ def main():
     file1 = sys.argv[1]
     file2 = sys.argv[2]
     
+    with delibs.Timer("Getting File Size"):
+        size1 = delibs.check_file_size_bytes(file1, too_small, too_large)
+        size2 = delibs.check_file_size_bytes(file2, too_small, too_large)
+        
+    if size1 != None:
+        print(f"ERROR: {size1}")
+        delibs.exit_timer(9)
+    if size2 != None:
+        print(f"ERROR: {size2}")
+        delibs.exit_timer(4) # Mark as Skipped
+    
     with delibs.Timer("Hashing"):
         # Quick hashes
         hash1 = delibs.quick_file_hash(file1)
@@ -102,15 +115,14 @@ def main():
     
     w, h = delibs.get_image_dimensions_cv(large_img1)
     w2, h2 = delibs.get_image_dimensions_cv(large_img2)
-    if w == None or w2 == None or h == None or h2 == None:
+    if w == None or h == None: 
         print("❌Aborting❌...Invalid Image!")
         delibs.exit_timer(8)
-    if w != w2 and w != h2:
-        print("Diffent Resolutions")
-        print("👌Not a Duplicate")
-        delibs.exit_timer(0)
-    
-    if h != h2 and h != w2:
+    if w2 == None or h2 == None:
+        print("❌Aborting❌...Invalid Image!")
+        delibs.exit_timer(4) # Mark as Skipped
+        
+    if w != w2 and w != h2 and h != h2 and h != w2:
         print("Diffent Resolutions")
         print("👌Not a Duplicate")
         delibs.exit_timer(0)

delibs.py

@@ -392,7 +392,23 @@ def get_image_dimensions_cv(img):
     if img is not None:
         height, width = img.shape[:2]
         return width, height
-    return None, None    
+    return None, None 
+    
+def check_file_size_bytes(file_path, too_small, too_large):
+    try:
+        file_size = os.path.getsize(file_path)
+        
+        if file_size < too_small:
+            return f"File is ({file_size} bytes) must be over {too_small}"
+        elif file_size > too_large:
+            return f"File is ({file_size} bytes) must be less than {too_large}"
+        else:
+            return None
+    
+    except FileNotFoundError:
+        return "File not found"
+    except Exception as e:
+        return f"Error checking file size: {str(e)}"       
                     
 """
 xxhash is about 5–10x faster than SHA256, non-cryptographic.

get_dups.bat

@@ -46,6 +46,9 @@ for /l %%i in (1,1,%count%) do (
             echo %~1\!outer_image!>> alike.txt
             goto :break_inner
         )
+        if !errorlevel! equ 4 (
+            goto :break_inner
+        )
         if !errorlevel! equ 5 (
             echo %~1\!outer_image!>> sameGPS.txt
             goto :break_inner
@@ -54,11 +57,14 @@ for /l %%i in (1,1,%count%) do (
             echo %~1\!outer_image!>> sameGPSmile.txt
             goto :break_inner
         )
-
         if !errorlevel! equ 8 (
             echo %~1\!outer_image!>> invalid.txt
             goto :break_inner
         )
+        if !errorlevel! equ 9 (
+            echo %~1\!outer_image!>> size.txt
+            goto :break_inner
+        )
     )
     :break_inner
 )

get_dups.sh

@@ -29,7 +29,7 @@ for ((i = 0; i < ${#images[@]}; i++)); do
     for ((j = i + 1; j < ${#images[@]}; j++)); do
         inner_image="${images[$j]}"
 		
-		echo -e "Compairing files: $outer_image TO $inner_image \n"
+		echo -e "\nCompairing files: $outer_image TO $inner_image"
         python3 dedup.py "$1/$outer_image" "$1/$inner_image" "$2"
         exit_code=$?
         if [ $exit_code -eq 1 ]; then
@@ -40,6 +40,9 @@ for ((i = 0; i < ${#images[@]}; i++)); do
             echo "$1/$outer_image # $inner_image" >> alike.txt
             break   # No need to check more once found close match to duplicate
         fi
+        if [ $exit_code -eq 4 ]; then
+            break   # Skip Invaild inner Image
+        fi
         if [ $exit_code -eq 5 ]; then
             echo "$1/$outer_image # $inner_image" >> sameGPS.txt
             break   # No need to check more once found matching GPS image
@@ -48,11 +51,14 @@ for ((i = 0; i < ${#images[@]}; i++)); do
             echo "$1/$outer_image # $inner_image" >> sameGPSmile.txt
             break   # No need to check more once found matching GPS image
         fi
-
         if [ $exit_code -eq 8 ]; then
-            echo "$1/$outer_image # $inner_image" >> invalid.txt
+            echo "$1/$outer_image" >> invalid.txt
             break   # No need to check more once found bad image
         fi
+        if [ $exit_code -eq 9 ]; then
+            echo "$1/$outer_image" >> size.txt
+            break   # No need to check more once found image too Small or Large
+        fi
         
     done
 done