feat: add optional S3 directory prefix support

Author: MickaelCa

.env.example

@@ -54,3 +54,5 @@ S3_BUCKET_NAME=gitingest-bucket
 S3_REGION=us-east-1
 # Public URL/CDN for accessing S3 resources
 S3_ALIAS_HOST=127.0.0.1:9000/gitingest-bucket
+# Optional prefix for S3 file paths (if set, prefixes all S3 paths with this value)
+# S3_DIRECTORY_PREFIX=my-prefix

README.md

@@ -234,6 +234,7 @@ The application can be configured using the following environment variables:
 - **GITINGEST_SENTRY_PROFILE_LIFECYCLE**: Profile lifecycle mode (default: "trace")
 - **GITINGEST_SENTRY_SEND_DEFAULT_PII**: Send default personally identifiable information (default: "true")
 - **S3_ALIAS_HOST**: Public URL/CDN for accessing S3 resources (default: "127.0.0.1:9000/gitingest-bucket")
+- **S3_DIRECTORY_PREFIX**: Optional prefix for S3 file paths (if set, prefixes all S3 paths with this value)
 
 ### Using Docker Compose
 

src/gitingest/utils/s3_utils.py

@@ -52,7 +52,9 @@ def generate_s3_file_path(
     """Generate S3 file path with proper naming convention.
 
     The file path is formatted as:
-    /ingest/<provider>/<repo-owner>/<repo-name>/<branch>/<commit-ID>/<exclude&include hash>.txt
+    [<S3_DIRECTORY_PREFIX>/]ingest/<provider>/<repo-owner>/<repo-name>/<branch>/<commit-ID>/<exclude&include hash>.txt
+
+    If S3_DIRECTORY_PREFIX environment variable is set, it will be prefixed to the path.
     The commit-ID is always included in the URL.
     If no specific commit is provided, the actual commit hash from the cloned repository is used.
 
@@ -98,7 +100,17 @@ def generate_s3_file_path(
 
     patterns_hash = hashlib.sha256(patterns_str.encode()).hexdigest()[:16]
 
-    return f"ingest/{git_source}/{user_name}/{repo_name}/{branch_name}/{commit}/{patterns_hash}.txt"
+    # Build the base path
+    base_path = f"ingest/{git_source}/{user_name}/{repo_name}/{branch_name}/{commit}/{patterns_hash}.txt"
+
+    # Check for S3_DIRECTORY_PREFIX environment variable
+    s3_directory_prefix = os.getenv("S3_DIRECTORY_PREFIX")
+    if s3_directory_prefix:
+        # Remove trailing slash if present and add the prefix
+        s3_directory_prefix = s3_directory_prefix.rstrip("/")
+        return f"{s3_directory_prefix}/{base_path}"
+
+    return base_path
 
 
 def create_s3_client() -> boto_client:  # type: ignore[name-defined]