CM-42771 - Add support of .gitignore files for a file excluding fro…

…m scans (#272)

.github/workflows/tests.yml

@@ -50,4 +50,4 @@ jobs:
         run: poetry install
 
       - name: Run Tests
-        run: poetry run pytest
+        run: poetry run python -m pytest

.github/workflows/tests_full.yml

@@ -50,7 +50,7 @@ jobs:
         uses: actions/cache@v3
         with:
           path: ~/.local
-          key: poetry-${{ matrix.os }}-${{ matrix.python-version }}-1  # increment to reset cache
+          key: poetry-${{ matrix.os }}-${{ matrix.python-version }}-2  # increment to reset cache
 
       - name: Setup Poetry
         if: steps.cached-poetry.outputs.cache-hit != 'true'
@@ -71,4 +71,4 @@ jobs:
           ./dist/cycode-cli version
 
       - name: Run pytest
-        run: poetry run pytest
+        run: poetry run python -m pytest

cycode/cli/files_collector/path_documents.py

@@ -1,7 +1,5 @@
 import os
-from typing import TYPE_CHECKING, Iterable, List, Tuple
-
-import pathspec
+from typing import TYPE_CHECKING, List, Tuple
 
 from cycode.cli.files_collector.excluder import exclude_irrelevant_files
 from cycode.cli.files_collector.iac.tf_content_generator import (
@@ -10,6 +8,7 @@
     is_iac,
     is_tfplan_file,
 )
+from cycode.cli.files_collector.walk_ignore import walk_ignore
 from cycode.cli.models import Document
 from cycode.cli.utils.path_utils import get_absolute_path, get_file_content
 from cycode.cyclient import logger
@@ -18,17 +17,18 @@
     from cycode.cli.utils.progress_bar import BaseProgressBar, ProgressBarSection
 
 
-def _get_all_existing_files_in_directory(path: str) -> List[str]:
+def _get_all_existing_files_in_directory(path: str, *, walk_with_ignore_patterns: bool = True) -> List[str]:
     files: List[str] = []
 
-    for root, _, filenames in os.walk(path):
+    walk_func = walk_ignore if walk_with_ignore_patterns else os.walk
+    for root, _, filenames in walk_func(path):
         for filename in filenames:
             files.append(os.path.join(root, filename))
 
     return files
 
 
-def _get_relevant_files_in_path(path: str, exclude_patterns: Iterable[str]) -> List[str]:
+def _get_relevant_files_in_path(path: str) -> List[str]:
     absolute_path = get_absolute_path(path)
 
     if not os.path.isfile(absolute_path) and not os.path.isdir(absolute_path):
@@ -37,24 +37,16 @@ def _get_relevant_files_in_path(path: str, exclude_patterns: Iterable[str]) -> L
     if os.path.isfile(absolute_path):
         return [absolute_path]
 
-    all_file_paths = set(_get_all_existing_files_in_directory(absolute_path))
-
-    path_spec = pathspec.PathSpec.from_lines(pathspec.patterns.GitWildMatchPattern, exclude_patterns)
-    excluded_file_paths = set(path_spec.match_files(all_file_paths))
-
-    relevant_file_paths = all_file_paths - excluded_file_paths
-
-    return [file_path for file_path in relevant_file_paths if os.path.isfile(file_path)]
+    file_paths = _get_all_existing_files_in_directory(absolute_path)
+    return [file_path for file_path in file_paths if os.path.isfile(file_path)]
 
 
 def _get_relevant_files(
     progress_bar: 'BaseProgressBar', progress_bar_section: 'ProgressBarSection', scan_type: str, paths: Tuple[str]
 ) -> List[str]:
     all_files_to_scan = []
     for path in paths:
-        all_files_to_scan.extend(
-            _get_relevant_files_in_path(path=path, exclude_patterns=['**/.git/**', '**/.cycode/**'])
-        )
+        all_files_to_scan.extend(_get_relevant_files_in_path(path))
 
     # we are double the progress bar section length because we are going to process the files twice
     # first time to get the file list with respect of excluded patterns (excluding takes seconds to execute)

cycode/cli/files_collector/walk_ignore.py

@@ -0,0 +1,42 @@
+import os
+from typing import Generator, Iterable, List, Tuple
+
+from cycode.cli.utils.ignore_utils import IgnoreFilterManager
+from cycode.cyclient import logger
+
+_SUPPORTED_IGNORE_PATTERN_FILES = {  # oneday we will bring .cycodeignore or something like that
+    '.gitignore',
+}
+_DEFAULT_GLOBAL_IGNORE_PATTERNS = [
+    '.git',
+    '.cycode',
+]
+
+
+def _walk_to_top(path: str) -> Iterable[str]:
+    while os.path.dirname(path) != path:
+        yield path
+        path = os.path.dirname(path)
+
+    if path:
+        yield path  # Include the top-level directory
+
+
+def _collect_top_level_ignore_files(path: str) -> List[str]:
+    ignore_files = []
+    for dir_path in _walk_to_top(path):
+        for ignore_file in _SUPPORTED_IGNORE_PATTERN_FILES:
+            ignore_file_path = os.path.join(dir_path, ignore_file)
+            if os.path.exists(ignore_file_path):
+                logger.debug('Apply top level ignore file: %s', ignore_file_path)
+                ignore_files.append(ignore_file_path)
+    return ignore_files
+
+
+def walk_ignore(path: str) -> Generator[Tuple[str, List[str], List[str]], None, None]:
+    ignore_filter_manager = IgnoreFilterManager.build(
+        path=path,
+        global_ignore_file_paths=_collect_top_level_ignore_files(path),
+        global_patterns=_DEFAULT_GLOBAL_IGNORE_PATTERNS,
+    )
+    yield from ignore_filter_manager.walk()