feat: SP-1856 Fix skip dir

docs/source/scanoss_settings_schema.rst

@@ -25,6 +25,134 @@ The ``self`` section contains basic information about your project:
         }
     }
 
+
+Settings
+========
+The ``settings`` object allows you to configure various aspects of the scanning process. Currently, it provides control over which files should be skipped during scanning through the ``skip`` property.
+
+Skip Configuration
+------------------
+The ``skip`` object lets you define rules for excluding files from being scanned. This can be useful for improving scan performance and avoiding unnecessary processing of certain files.
+
+Properties
+~~~~~~~~~~
+
+skip.patterns
+^^^^^^^^^^^^^
+A list of patterns that determine which files should be skipped during scanning. The patterns follow the same format as ``.gitignore`` files. For more information, see the `gitignore patterns documentation <https://git-scm.com/docs/gitignore#_pattern_format>`_.
+
+:Type: Array of strings
+:Required: No
+:Example:
+    .. code-block:: json
+
+        {
+            "settings": {
+            "skip": {
+                "patterns": [
+                    "*.log",
+                    "!important.log",
+                    "temp/",
+                    "debug[0-9]*.txt",
+                    "src/client/specific-file.js",
+                    "src/nested/folder/"
+                ]
+            }
+        }
+
+Pattern Format Rules
+''''''''''''''''''''
+* Patterns are matched **relative to the scan root directory**
+* A trailing slash indicates a directory (e.g., ``path/`` matches only directories)
+* An asterisk ``*`` matches anything except a slash
+* Two asterisks ``**`` match zero or more directories (e.g., ``path/**/folder`` matches ``path/to``, ``path/to/folder``, ``path/to/folder/b``)
+* Range notations like ``[0-9]`` match any character in the range
+* Question mark ``?`` matches any single character except a slash
+
+
+Examples with Explanations
+''''''''''''''''''''''''''
+.. code-block:: none
+
+    # Match all .txt files
+    *.txt
+
+    # Match all .log files except important.log
+    *.log
+    !important.log
+
+    # Match all files in the build directory
+    build/
+
+    # Match all .pdf files in docs directory and its subdirectories
+    docs/**/*.pdf
+
+    # Match files like test1.js, test2.js, etc.
+    test[0-9].js
+
+skip.sizes
+^^^^^^^^^^
+Rules for skipping files based on their size.
+
+:Type: Object
+:Required: No
+:Properties:
+    * ``min`` (integer): Minimum file size in bytes
+    * ``max`` (integer): Maximum file size in bytes (Required)
+:Example:
+    .. code-block:: json
+
+        {
+          "settings": {
+            "skip": {
+              "sizes": {
+                "min": 100,
+                "max": 1000000
+              }
+            }
+          }
+        }
+
+Complete Example
+-------------------
+Here's a comprehensive example combining pattern and size-based skipping:
+
+.. code-block:: json
+
+    {
+      "settings": {
+        "skip": {
+          "patterns": [
+            "# Node.js dependencies",
+            "node_modules/",
+            
+            "# Build outputs",
+            "dist/",
+            "build/",
+            
+            "# Logs except important ones",
+            "*.log",
+            "!important.log",
+            
+            "# Temporary files",
+            "temp/",
+            "*.tmp",
+            
+            "# Debug files with numbers",
+            "debug[0-9]*.txt",
+            
+            "# All test files in any directory",
+            "**/*test.js"
+          ],
+          "sizes": {
+            "min": 512,
+            "max": 5242880
+          }
+        }
+      }
+    }
+
+
 BOM Rules
 ---------
 

src/scanoss/scan_filter.py

@@ -1,5 +1,5 @@
 import os
-from typing import List, Set, Tuple
+from typing import List
 
 from pathspec import PathSpec
 
@@ -230,6 +230,7 @@ def __init__(
         skip_patterns.extend(skip.get('patterns', []))
 
         self.skip_patterns = skip_patterns
+        self.path_spec = PathSpec.from_lines('gitwildmatch', self.skip_patterns)
         self.min_size = skip.get('sizes', {}).get('min', 0)
         self.max_size = skip.get('sizes', {}).get('max', float('inf'))
 
@@ -249,13 +250,11 @@ def _walk_with_ignore(self, scan_root: str) -> List[str]:
         files = []
         root = os.path.abspath(scan_root)
 
-        path_spec, dir_patterns = self._create_skip_path_matchers()
-
         for dirpath, dirnames, filenames in os.walk(root):
             rel_path = os.path.relpath(dirpath, root)
 
-            # Return early if the entire directory should be skipped
-            if any(rel_path.startswith(p) for p in dir_patterns):
+            # Early skip directories if they match any of the patterns
+            if self._should_skip_dir(rel_path):
                 self.print_debug(f'Skipping directory: {rel_path}')
                 dirnames.clear()
                 continue
@@ -268,17 +267,15 @@ def _walk_with_ignore(self, scan_root: str) -> List[str]:
                 if file_size < self.min_size or file_size > self.max_size:
                     self.print_debug(f'Skipping file: {file_rel_path} (size: {file_size})')
                     continue
-                if path_spec.match_file(file_rel_path):
+                if self.path_spec.match_file(file_rel_path):
                     self.print_debug(f'Skipping file: {file_rel_path}')
                     continue
                 else:
                     files.append(file_rel_path)
 
         return files
 
-    def _create_skip_path_matchers(self) -> Tuple[PathSpec, Set[str]]:
-        dir_patterns = {p.rstrip('/') for p in self.skip_patterns if p.endswith('/')}
-
-        path_spec = PathSpec.from_lines('gitwildmatch', self.skip_patterns)
-
-        return path_spec, dir_patterns
+    def _should_skip_dir(self, dir_rel_path: str) -> bool:
+        return any(dir_rel_path.startswith(p) for p in self.skip_patterns) or self.path_spec.match_file(
+            dir_rel_path + '/'
+        )

src/scanoss/scanner.py

@@ -401,7 +401,6 @@ def scan_folder(self, scan_dir: str) -> bool:
         if not os.path.exists(scan_dir) or not os.path.isdir(scan_dir):
             raise Exception(f'ERROR: Specified folder does not exist or is not a folder: {scan_dir}')
 
-        scan_dir_len = len(scan_dir) if scan_dir.endswith(os.path.sep) else len(scan_dir) + 1
         self.print_msg(f'Searching {scan_dir} for files to fingerprint...')
         spinner = None
         if not self.quiet and self.isatty: