Merge pull request #357 from jamesrom/feat/file_ignores

Add support for ignoring files

INSTALL.md

@@ -89,10 +89,10 @@ chmod 600 pr_agent/settings/.secrets.toml
 
 ```
 export PYTHONPATH=[$PYTHONPATH:]<PATH to pr_agent folder>
-python3 -m pr_agent.cli --pr_url <pr_url> /review
+python3 -m pr_agent.cli --pr_url <pr_url> review
-python3 -m pr_agent.cli --pr_url <pr_url> /ask <your question>
+python3 -m pr_agent.cli --pr_url <pr_url> ask <your question>
-python3 -m pr_agent.cli --pr_url <pr_url> /describe
+python3 -m pr_agent.cli --pr_url <pr_url> describe
-python3 -m pr_agent.cli --pr_url <pr_url> /improve
+python3 -m pr_agent.cli --pr_url <pr_url> improve
 ```
 
 ---

Usage.md

@@ -29,6 +29,16 @@ In addition to general configuration options, each tool has its own configuratio
 
 The [Tools Guide](./docs/TOOLS_GUIDE.md) provides a detailed description of the different tools and their configurations.
 
+#### Ignoring files from analysis
+In some cases, you may want to exclude specific files or directories from the analysis performed by CodiumAI PR-Agent. This can be useful, for example, when you have files that are generated automatically or files that shouldn't be reviewed, like vendored code.
+
+To ignore files or directories, edit the **[ignore.toml](/pr_agent/settings/ignore.toml)** configuration file. This setting is also exposed the following environment variables:
+
+ - `IGNORE.GLOB`
+ - `IGNORE.REGEX`
+
+See [dynaconf envvars documentation](https://www.dynaconf.com/envvars/).
+
 #### git provider
 The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configuration file determines the GIT provider that will be used by PR-Agent. Currently, the following providers are supported:
 `

pr_agent/algo/file_filter.py

@@ -0,0 +1,31 @@
+import fnmatch
+import re
+
+from pr_agent.config_loader import get_settings
+
+def filter_ignored(files):
+    """
+    Filter out files that match the ignore patterns.
+    """
+
+    try:
+        # load regex patterns, and translate glob patterns to regex
+        patterns = get_settings().ignore.regex
+        patterns += [fnmatch.translate(glob) for glob in get_settings().ignore.glob]
+
+        # compile all valid patterns
+        compiled_patterns = []
+        for r in patterns:
+            try:
+                compiled_patterns.append(re.compile(r))
+            except re.error:
+                pass
+
+        # keep filenames that _don't_ match the ignore regex
+        for r in compiled_patterns:
+            files = [f for f in files if not r.match(f.filename)]
+
+    except Exception as e:
+        print(f"Could not filter file list: {e}")
+
+    return files

pr_agent/algo/pr_processing.py

@@ -11,6 +11,7 @@ from github import RateLimitExceededException
 from pr_agent.algo import MAX_TOKENS
 from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
 from pr_agent.algo.language_handler import sort_files_by_main_languages
+from pr_agent.algo.file_filter import filter_ignored
 from pr_agent.algo.token_handler import TokenHandler, get_token_encoder
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider
@@ -53,6 +54,8 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
         logging.error(f"Rate limit exceeded for git provider API. original message {e}")
         raise
 
+    diff_files = filter_ignored(diff_files)
+
     # get pr languages
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 
@@ -367,6 +370,8 @@ def get_pr_multi_diffs(git_provider: GitProvider,
         logging.error(f"Rate limit exceeded for git provider API. original message {e}")
         raise
 
+    diff_files = filter_ignored(diff_files)
+
     # Sort files by main language
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 

pr_agent/config_loader.py

@@ -14,6 +14,7 @@ global_settings = Dynaconf(
     settings_files=[join(current_dir, f) for f in [
         "settings/.secrets.toml",
         "settings/configuration.toml",
+        "settings/ignore.toml",
         "settings/language_extensions.toml",
         "settings/pr_reviewer_prompts.toml",
         "settings/pr_questions_prompts.toml",

pr_agent/settings/ignore.toml

@@ -0,0 +1,11 @@
+[ignore]
+
+glob = [
+    # Ignore files and directories matching these glob patterns.
+    # See https://docs.python.org/3/library/glob.html
+    'vendor/**',
+]
+regex = [
+    # Ignore files and directories matching these regex patterns.
+    # See https://learnbyexample.github.io/python-regex-cheatsheet/
+]

tests/unittest/test_file_filter.py

@@ -0,0 +1,80 @@
+import pytest
+from pr_agent.algo.file_filter import filter_ignored
+from pr_agent.config_loader import global_settings
+
+class TestIgnoreFilter:
+    def test_no_ignores(self):
+        """
+        Test no files are ignored when no patterns are specified.
+        """
+        files = [
+            type('', (object,), {'filename': 'file1.py'})(),
+            type('', (object,), {'filename': 'file2.java'})(),
+            type('', (object,), {'filename': 'file3.cpp'})(),
+            type('', (object,), {'filename': 'file4.py'})(),
+            type('', (object,), {'filename': 'file5.py'})()
+        ]
+        assert filter_ignored(files) == files, "Expected all files to be returned when no ignore patterns are given."
+
+    def test_glob_ignores(self, monkeypatch):
+        """
+        Test files are ignored when glob patterns are specified.
+        """
+        monkeypatch.setattr(global_settings.ignore, 'glob', ['*.py'])
+
+        files = [
+            type('', (object,), {'filename': 'file1.py'})(),
+            type('', (object,), {'filename': 'file2.java'})(),
+            type('', (object,), {'filename': 'file3.cpp'})(),
+            type('', (object,), {'filename': 'file4.py'})(),
+            type('', (object,), {'filename': 'file5.py'})()
+        ]
+        expected = [
+            files[1],
+            files[2]
+        ]
+
+        filtered_files = filter_ignored(files)
+        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."
+
+    def test_regex_ignores(self, monkeypatch):
+        """
+        Test files are ignored when regex patterns are specified.
+        """
+        monkeypatch.setattr(global_settings.ignore, 'regex', ['^file[2-4]\..*$'])
+
+        files = [
+            type('', (object,), {'filename': 'file1.py'})(),
+            type('', (object,), {'filename': 'file2.java'})(),
+            type('', (object,), {'filename': 'file3.cpp'})(),
+            type('', (object,), {'filename': 'file4.py'})(),
+            type('', (object,), {'filename': 'file5.py'})()
+        ]
+        expected = [
+            files[0],
+            files[4]
+        ]
+
+        filtered_files = filter_ignored(files)
+        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."
+
+    def test_invalid_regex(self, monkeypatch):
+        """
+        Test invalid patterns are quietly ignored.
+        """
+        monkeypatch.setattr(global_settings.ignore, 'regex', ['(((||', '^file[2-4]\..*$'])
+
+        files = [
+            type('', (object,), {'filename': 'file1.py'})(),
+            type('', (object,), {'filename': 'file2.java'})(),
+            type('', (object,), {'filename': 'file3.cpp'})(),
+            type('', (object,), {'filename': 'file4.py'})(),
+            type('', (object,), {'filename': 'file5.py'})()
+        ]
+        expected = [
+            files[0],
+            files[4]
+        ]
+
+        filtered_files = filter_ignored(files)
+        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."