Add pattern matching for gitignore files in ddev size (DataDog#22838)

* Add pattern matching to ignore gitignore files

* Add changelog

Author: lucia-sb

ddev/changelog.d/22838.fixed

@@ -0,0 +1 @@
+Fixed `ddev size` ignore filtering to correctly interpret gitignore entries, ensuring excluded files are omitted from size calculations.

ddev/src/ddev/cli/size/utils/common_funcs.py

@@ -3,6 +3,7 @@
 # Licensed under a 3-clause BSD style license (see LICENSE)
 from __future__ import annotations
 
+import fnmatch
 import json
 import os
 import re
@@ -160,7 +161,7 @@ def is_valid_integration_file(
         included_folder = "datadog_checks" + os.sep
 
     if git_ignore is None:
-        git_ignore = get_gitignore_files(repo_path)
+        git_ignore = get_gitignore_files(Path(repo_path))
     # It is not an integration
     if path.startswith("."):
         return False
@@ -171,20 +172,34 @@ def is_valid_integration_file(
     elif any(ignore in path for ignore in ignored_files):
         return False
     # This file is contained in .gitignore
-    elif any(ignore in path for ignore in git_ignore):
+    elif _matches_gitignore(path, git_ignore):
         return False
     else:
         return True
 
 
-def get_gitignore_files(repo_path: str | Path) -> list[str]:
-    gitignore_path = os.path.join(repo_path, ".gitignore")
-    with open(gitignore_path, "r", encoding="utf-8") as file:
-        gitignore_content = file.read()
-        ignored_patterns = [
-            line.strip() for line in gitignore_content.splitlines() if line.strip() and not line.startswith("#")
-        ]
-        return ignored_patterns
+def _matches_gitignore(path: str, patterns: list[str]) -> bool:
+    parts = path.replace(os.sep, "/").split("/")
+    for pattern in patterns:
+        norm = pattern.rstrip("/")
+        if fnmatch.fnmatch(path, norm):
+            return True
+        if fnmatch.fnmatch(os.path.basename(path), norm):
+            return True
+        if any(fnmatch.fnmatch(part, norm) for part in parts):
+            return True
+    return False
+
+
+def get_gitignore_files(repo_path: Path) -> list[str]:
+    gitignore_path = repo_path / ".gitignore"
+    if not gitignore_path.is_file():
+        return []
+
+    with gitignore_path.open(mode="r", encoding="utf-8") as f:
+        lines = [line.strip() for line in f.read().splitlines() if line.strip() and not line.startswith("#")]
+
+    return lines
 
 
 def convert_to_human_readable_size(size_bytes: float) -> str:

ddev/tests/size/test_common.py

@@ -7,6 +7,7 @@
 import pytest
 
 from ddev.cli.size.utils.common_funcs import (
+    _matches_gitignore,
     check_python_version,
     compress,
     convert_to_human_readable_size,
@@ -115,14 +116,34 @@ def test_convert_to_human_readable_size(size_bytes, expected_string):
         pytest.param("__pycache__/file.py", False, id="pycache"),
         pytest.param("datadog_checks_dev/example.py", False, id="checks_dev"),
         pytest.param(".git/config", False, id="git"),
+        pytest.param("datadog_checks/module/cache.pyc", False, id="gitignore_glob_ext"),
+        pytest.param("datadog_checks/module/__pycache__/foo.py", False, id="gitignore_glob_dir"),
     ],
 )
 def test_is_valid_integration_file(file_path, expected):
     repo_path = "fake_repo"
-    with patch("ddev.cli.size.utils.common_funcs.get_gitignore_files", return_value=set()):
+    gitignore_patterns = ["*.pyc", "__pycache__"]
+    with patch("ddev.cli.size.utils.common_funcs.get_gitignore_files", return_value=gitignore_patterns):
         assert is_valid_integration_file(to_native_path(file_path), repo_path) is expected
 
 
+@pytest.mark.parametrize(
+    "path, patterns, expected",
+    [
+        pytest.param("foo/bar/baz.pyc", ["*.pyc"], True, id="glob_extension_match"),
+        pytest.param("foo/bar/baz.py", ["*.pyc"], False, id="glob_extension_no_match"),
+        pytest.param("foo/__pycache__/module.py", ["__pycache__"], True, id="dir_segment_match"),
+        pytest.param("foo/bar/module.py", ["__pycache__"], False, id="dir_segment_no_match"),
+        pytest.param("foo/bar/notes.log", ["*.log"], True, id="glob_log_match"),
+        pytest.param("foo/bar/notes.txt", ["*.log"], False, id="glob_log_no_match"),
+        pytest.param("foo/bar/baz.py", ["*.pyc", "__pycache__", "*.log"], False, id="no_pattern_matches"),
+        pytest.param("foo/__pycache__/baz.pyc", ["*.pyc", "__pycache__"], True, id="multiple_patterns_first_matches"),
+    ],
+)
+def test_matches_gitignore(path, patterns, expected):
+    assert _matches_gitignore(to_native_path(path), patterns) is expected
+
+
 def test_get_dependencies_list():
     file_content = "dependency1 @ https://example.com/dependency1/dependency1-1.1.1-.whl\ndependency2 @ https://example.com/dependency2/dependency2-1.1.1-.whl"
     mock_open_obj = mock_open(read_data=file_content)
@@ -267,13 +288,10 @@ def test_check_version(py_version, expected):
         assert check_python_version("fake_repo", "integration1", py_version) is expected
 
 
-def test_get_gitignore_files():
-    mock_gitignore = f"__pycache__{os.sep}\n*.log\n"  # Sample .gitignore file
-    repo_path = "fake_repo"
-    with patch("builtins.open", mock_open(read_data=mock_gitignore)):
-        with patch("ddev.cli.size.utils.common_funcs.os.path.exists", return_value=True):
-            ignored_patterns = get_gitignore_files(repo_path)
-    assert ignored_patterns == ["__pycache__" + os.sep, "*.log"]
+def test_get_gitignore_files(tmp_path):
+    gitignore = tmp_path / ".gitignore"
+    gitignore.write_text(f"__pycache__{os.sep}\n*.log\n")
+    assert get_gitignore_files(tmp_path) == ["__pycache__" + os.sep, "*.log"]
 
 
 def test_compress():