From b3f8f25517df166ff3b48339ae61c1a47b811289 Mon Sep 17 00:00:00 2001
From: Tom Tankilevitch <59158507+Tankilevitch@users.noreply.github.com>
Date: Mon, 19 Aug 2024 12:40:22 +0300
Subject: [PATCH] [Gitlab] Fix still processing a file larger than the allowed
 size (#913)

---
 integrations/gitlab/CHANGELOG.md                |  9 +++++++++
 .../gitlab/gitlab_integration/gitlab_service.py | 17 +++++++++++++----
 integrations/gitlab/pyproject.toml              |  2 +-
 3 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/integrations/gitlab/CHANGELOG.md b/integrations/gitlab/CHANGELOG.md
index 1e23969075..3883ef0fce 100644
--- a/integrations/gitlab/CHANGELOG.md
+++ b/integrations/gitlab/CHANGELOG.md
@@ -7,6 +7,15 @@ this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 <!-- towncrier release notes start -->
 
+0.1.106 (2024-08-19)
+====================
+
+### Bug Fixes
+
+- Fixed an issue when we were still processing a file larger than the allowed file size
+- Added more verbosity to the logs of the file kind
+
+
 0.1.105 (2024-08-15)
 ===================
 
diff --git a/integrations/gitlab/gitlab_integration/gitlab_service.py b/integrations/gitlab/gitlab_integration/gitlab_service.py
index df32e0c4f8..326cdb0842 100644
--- a/integrations/gitlab/gitlab_integration/gitlab_service.py
+++ b/integrations/gitlab/gitlab_integration/gitlab_service.py
@@ -604,16 +604,25 @@ async def get_and_parse_single_file(
         self, project: Project, file_path: str, branch: str
     ) -> dict[str, Any] | None:
         try:
+            logger.info(
+                f"Processing file {file_path} in project {project.path_with_namespace}"
+            )
             project_file = await AsyncFetcher.fetch_single(
                 project.files.get, file_path, branch
             )
+            logger.info(
+                f"Fetched file {file_path} in project {project.path_with_namespace}"
+            )
             project_file = typing.cast(ProjectFile, project_file)
             parsed_file = self._parse_file_content(project_file)
             project_file_dict = project_file.asdict()
 
-            if parsed_file:
-                # Update the content with the parsed content. Useful for JSON and YAML files that can be further processed using itemsToParse
-                project_file_dict["content"] = parsed_file
+            if not parsed_file:
+                # if the file is too large to be processed, we return None
+                return None
+
+            # Update the content with the parsed content. Useful for JSON and YAML files that can be further processed using itemsToParse
+            project_file_dict["content"] = parsed_file
 
             return {"file": project_file_dict, "repo": project.asdict()}
         except Exception as e:
@@ -628,7 +637,7 @@ async def get_all_files_in_project(
         branch = project.default_branch
         try:
             file_paths = await self._get_file_paths(project, path, branch, True)
-            logger.debug(
+            logger.info(
                 f"Found {len(file_paths)} files in project {project.path_with_namespace} files: {file_paths}"
             )
             files = []
diff --git a/integrations/gitlab/pyproject.toml b/integrations/gitlab/pyproject.toml
index 6f33c9219a..f8b1ec5f6f 100644
--- a/integrations/gitlab/pyproject.toml
+++ b/integrations/gitlab/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gitlab"
-version = "0.1.105"
+version = "0.1.106"
 description = "Gitlab integration for Port using Port-Ocean Framework"
 authors = ["Yair Siman-Tov <yair@getport.io>"]