feat: fix file filters in folder hashing

matiasdaloia · matiasdaloia · commit eab81a4e5883 · 2025-03-24T16:27:24.000+01:00
diff --git a/src/scanoss/scanners/folder_hasher.py b/src/scanoss/scanners/folder_hasher.py
@@ -15,7 +15,7 @@
 
 MINIMUM_FILE_COUNT = 8
 MINIMUM_CONCATENATED_NAME_LENGTH = 32
-MINIMUM_FILE_NAME_LENGTH = 32
+MAXIMUM_FILE_NAME_LENGTH = 32
 
 
 class DirectoryNode:
@@ -141,7 +141,7 @@ def _build_root_node(self, path: str) -> DirectoryNode:
         filtered_files = [
             f
             for f in self.file_filters.get_filtered_files_from_folder(str(root))
-            if len(f.encode('utf-8')) < MINIMUM_FILE_NAME_LENGTH
+            if not len(os.path.basename(f).encode('utf-8')) > MAXIMUM_FILE_NAME_LENGTH
         ]
 
         # Sort the files by name to ensure the hash is the same for the same folder

Original file line number	Diff line number	Diff line change
`@@ -15,7 +15,7 @@`
`15`	`15`
`16`	`16`	`MINIMUM_FILE_COUNT = 8`
`17`	`17`	`MINIMUM_CONCATENATED_NAME_LENGTH = 32`
`18`		`-MINIMUM_FILE_NAME_LENGTH = 32`
	`18`	`+MAXIMUM_FILE_NAME_LENGTH = 32`
`19`	`19`
`20`	`20`
`21`	`21`	`class DirectoryNode:`
`@@ -141,7 +141,7 @@ def _build_root_node(self, path: str) -> DirectoryNode:`
`141`	`141`	`filtered_files = [`
`142`	`142`	`f`
`143`	`143`	`for f in self.file_filters.get_filtered_files_from_folder(str(root))`
`144`		`- if len(f.encode('utf-8')) < MINIMUM_FILE_NAME_LENGTH`
	`144`	`+ if not len(os.path.basename(f).encode('utf-8')) > MAXIMUM_FILE_NAME_LENGTH`
`145`	`145`	`]`
`146`	`146`
`147`	`147`	`# Sort the files by name to ensure the hash is the same for the same folder`