From 58bc54b1934b8788d62202dfbb7372aef76effb8 Mon Sep 17 00:00:00 2001
From: mrT23 <tal.r@codium.ai>
Date: Thu, 13 Jun 2024 12:27:10 +0300
Subject: [PATCH] Add file ignore functionality and update documentation for
 ignore patterns

---
 pr_agent/algo/file_filter.py                   |  3 +++
 pr_agent/algo/language_handler.py              |  2 +-
 pr_agent/git_providers/azuredevops_provider.py | 15 +++++++++++++++
 3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/pr_agent/algo/file_filter.py b/pr_agent/algo/file_filter.py
index 75d75c1d..9b705cd7 100644
--- a/pr_agent/algo/file_filter.py
+++ b/pr_agent/algo/file_filter.py
@@ -38,6 +38,9 @@ def filter_ignored(files):
             elif isinstance(files[0], dict) and 'new_path' in files[0]: # gitlab
                 for r in compiled_patterns:
                     files = [f for f in files if (f['new_path'] and not r.match(f['new_path']))]
+            elif isinstance(files[0], str): # azure devops
+                for r in compiled_patterns:
+                    files = [f for f in files if not r.match(f)]
 
     except Exception as e:
         print(f"Could not filter file list: {e}")
diff --git a/pr_agent/algo/language_handler.py b/pr_agent/algo/language_handler.py
index b4c02bee..83f7b85e 100644
--- a/pr_agent/algo/language_handler.py
+++ b/pr_agent/algo/language_handler.py
@@ -15,7 +15,7 @@ def filter_bad_extensions(files):
     return [f for f in files if f.filename is not None and is_valid_file(f.filename)]
 
 
-def is_valid_file(filename):
+def is_valid_file(filename: str):
     return filename.split('.')[-1] not in bad_extensions
 
 
diff --git a/pr_agent/git_providers/azuredevops_provider.py b/pr_agent/git_providers/azuredevops_provider.py
index ee3a116f..d27a5040 100644
--- a/pr_agent/git_providers/azuredevops_provider.py
+++ b/pr_agent/git_providers/azuredevops_provider.py
@@ -2,6 +2,7 @@ import os
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
+from ..algo.file_filter import filter_ignored
 from ..log import get_logger
 from ..algo.language_handler import is_valid_file
 from ..algo.utils import clip_tokens, find_line_number_of_relevant_line_in_file, load_large_diff
@@ -284,8 +285,20 @@ class AzureDevopsProvider(GitProvider):
             #
             # diffs = list(set(diffs))
 
+            diffs_original = diffs
+            diffs = filter_ignored(diffs_original)
+            if diffs_original != diffs:
+                try:
+                    get_logger().info(f"Filtered out [ignore] files for pull request:", extra=
+                    {"files": diffs_original,  # diffs is just a list of names
+                     "filtered_files": diffs})
+                except Exception:
+                    pass
+
+            invalid_files_names = []
             for file in diffs:
                 if not is_valid_file(file):
+                    invalid_files_names.append(file)
                     continue
 
                 version = GitVersionDescriptor(
@@ -350,6 +363,8 @@ class AzureDevopsProvider(GitProvider):
                         edit_type=edit_type,
                     )
                 )
+            get_logger().info(f"Invalid files: {invalid_files_names}")
+
             self.diff_files = diff_files
             return diff_files
         except Exception as e: