fix: resolve all pre-commit hook issues and lint warnings

Author: NicolasIRAGNE

src/gitingest/entrypoint.py

@@ -28,7 +28,6 @@
     from types import TracebackType
 
     from gitingest.schemas import IngestionQuery
-    from gitingest.schemas import ContextV1
 
 # Initialize logger for this module
 logger = get_logger(__name__)
@@ -138,7 +137,6 @@ async def ingest_async(
             _apply_gitignores(query)
 
         logger.info("Processing files and generating output")
-        summary, tree, content = ingest_query(query)
 
         if output:
             logger.debug("Writing output to file", extra={"output_path": output})
@@ -205,19 +203,20 @@ def ingest(
     ``ingest_async`` : The asynchronous version of this function.
 
     """
-    digest = asyncio.run(ingest_async(
-        source,
-        max_file_size=max_file_size,
-        include_patterns=include_patterns,
-        exclude_patterns=exclude_patterns,
-        branch=branch,
-        tag=tag,
-        include_gitignored=include_gitignored,
-        include_submodules=include_submodules,
-        token=token,
-        output=output,
-    ))
-    return digest
+    return asyncio.run(
+        ingest_async(
+            source,
+            max_file_size=max_file_size,
+            include_patterns=include_patterns,
+            exclude_patterns=exclude_patterns,
+            branch=branch,
+            tag=tag,
+            include_gitignored=include_gitignored,
+            include_submodules=include_submodules,
+            token=token,
+            output=output,
+        ),
+    )
 
 
 def _override_branch_and_tag(query: IngestionQuery, branch: str | None, tag: str | None) -> None:

src/gitingest/format/DebugFormatter/Source.j2

@@ -1,4 +1,4 @@
 {{ SEPARATOR }}
 DEBUG: {{ class_name }}
 Fields: {{ fields_str }}
-{{ SEPARATOR }}
+{{ SEPARATOR }}

src/gitingest/format/DefaultFormatter/FileSystemDirectory.j2

@@ -4,4 +4,4 @@
 {% endif -%}
 {%- for child in node.children -%}
 {{ formatter.format(child, query) }}
-{%- endfor -%}
+{%- endfor -%}

src/gitingest/format/DefaultFormatter/FileSystemFile.j2

@@ -1,4 +1,4 @@
 {{ SEPARATOR }}
 {{ node.name }}
 {{ SEPARATOR }}
-{{ node.content }}
+{{ node.content }}

src/gitingest/format/DefaultFormatter/FileSystemSymlink.j2

@@ -1,3 +1,3 @@
 {{ SEPARATOR }}
 {{ node.name }}{% if node.target %} -> {{ node.target }}{% endif %}
-{{ SEPARATOR }}
+{{ SEPARATOR }}

src/gitingest/format/DefaultFormatter/GitRepository.j2

@@ -4,4 +4,4 @@
 {% endif -%}
 {%- for child in node.children -%}
 {{ formatter.format(child, query) }}
-{%- endfor -%}
+{%- endfor -%}

src/gitingest/format/SummaryFormatter/FileSystemDirectory.j2

@@ -1,2 +1,2 @@
 Directory structure:
-{{ node.tree }}
+{{ node.tree }}

src/gitingest/ingestion.py

@@ -26,8 +26,10 @@ def _is_git_repository(path: Path) -> bool:
 def ingest_query(query: IngestionQuery) -> ContextV1:
     """Run the ingestion process for a parsed query.
 
-    This is the main entry point for analyzing a codebase directory or single file. It processes the query
-    parameters, reads the file or directory content, and returns a ContextV1 object that can generate the final output digest on demand.
+    This is the main entry point for analyzing a codebase directory or single file.
+
+    It processes the query parameters, reads the file or directory content, and returns
+    a ContextV1 object that can generate the final output digest on demand.
 
     Parameters
     ----------
@@ -37,7 +39,9 @@ def ingest_query(query: IngestionQuery) -> ContextV1:
     Returns
     -------
     ContextV1
-        A ContextV1 object representing the ingested file system nodes. Use generate_digest(context) to get the summary, directory structure, and file contents.
+        A ContextV1 object representing the ingested file system nodes.
+        Use generate_digest(context) to get the summary, directory structure,
+        and file contents.
 
     Raises
     ------
@@ -126,7 +130,7 @@ def ingest_query(query: IngestionQuery) -> ContextV1:
     return ContextV1([root_node], query)
 
 
-def _process_node(node: FileSystemNode, query: IngestionQuery, stats: FileSystemStats) -> None:
+def _process_node(node: FileSystemNode, query: IngestionQuery, stats: FileSystemStats) -> None:  # noqa: C901
     """Process a file or directory item within a directory.
 
     This function handles each file or directory item, checking if it should be included or excluded based on the

src/server/query_processor.py

@@ -8,7 +8,7 @@
 
 from gitingest.clone import clone_repo
 from gitingest.ingestion import ingest_query
-from gitingest.output_formatter import DebugFormatter, DefaultFormatter, SummaryFormatter
+from gitingest.output_formatter import DefaultFormatter, SummaryFormatter, generate_digest
 from gitingest.query_parser import parse_remote_repo
 from gitingest.utils.git_utils import resolve_commit, validate_github_token
 from gitingest.utils.logging_config import get_logger
@@ -23,7 +23,6 @@
     upload_metadata_to_s3,
     upload_to_s3,
 )
-from gitingest.schemas import ContextV1
 from server.server_config import MAX_DISPLAY_SIZE
 
 # Initialize logger for this module
@@ -314,17 +313,18 @@ async def process_query(
                 source=query.url,
                 user_name=cast("str", query.user_name),
                 repo_name=cast("str", query.repo_name),
+                subpath=query.subpath,
                 commit=query.commit,
                 include_patterns=query.include_patterns,
                 ignore_patterns=query.ignore_patterns,
             )
-            s3_url = upload_to_s3(content=context.digest, s3_file_path=s3_file_path, ingest_id=query.id)
+            s3_url = upload_to_s3(content=generate_digest(context), s3_file_path=s3_file_path, ingest_id=query.id)
             # Store S3 URL in query for later use
             query.s3_url = s3_url
         else:
             # Store locally
             local_txt_file = Path(clone_config.local_path).with_suffix(".txt")
-            print(f"Writing to {local_txt_file}")
+            logger.info("Writing digest to local file", extra={"file_path": str(local_txt_file)})
             with local_txt_file.open("w", encoding="utf-8") as f:
                 f.write(digest)
 
@@ -340,14 +340,6 @@ async def process_query(
             "download full ingest to see more)\n" + digest[:MAX_DISPLAY_SIZE]
         )
 
-    # _print_success(
-    #     url=query.url,
-    #     max_file_size=max_file_size,
-    #     pattern_type=pattern_type,
-    #     pattern=pattern,
-    #     summary=digest,
-    # )
-
     digest_url = _generate_digest_url(query)
 
     # Clean up the repository after successful processing
@@ -358,7 +350,7 @@ async def process_query(
         short_repo_url=short_repo_url,
         summary=summary,
         digest_url=digest_url,
-        tree=context.sources[0].tree, # TODO: this is a hack to get the tree of the first source
+        tree=context.sources[0].tree,  # TODO: this is a hack to get the tree of the first source
         content=digest,
         default_max_file_size=max_file_size,
         pattern_type=pattern_type,

src/server/routers_utils.py

@@ -8,9 +8,13 @@
 from fastapi import status
 from fastapi.responses import JSONResponse
 
+from gitingest.utils.logging_config import get_logger
 from server.models import IngestErrorResponse, IngestSuccessResponse, PatternType
 from server.query_processor import process_query
 
+# Initialize logger for this module
+logger = get_logger(__name__)
+
 COMMON_INGEST_RESPONSES: dict[int | str, dict[str, Any]] = {
     status.HTTP_200_OK: {"model": IngestSuccessResponse, "description": "Successful ingestion"},
     status.HTTP_400_BAD_REQUEST: {"model": IngestErrorResponse, "description": "Bad request or processing error"},
@@ -41,8 +45,8 @@ async def _perform_ingestion(
         )
 
         if isinstance(result, IngestErrorResponse):
-            # print stack trace to console for debugging
-            print(traceback.format_exc())
+            # Log stack trace for debugging
+            logger.error("Ingest processing failed", extra={"traceback": traceback.format_exc()})
             # Return structured error response with 400 status code
             return JSONResponse(status_code=status.HTTP_400_BAD_REQUEST, content=result.model_dump())
 
@@ -52,13 +56,13 @@ async def _perform_ingestion(
     except ValueError as ve:
         # Handle validation errors with 400 status code
         error_response = IngestErrorResponse(error=f"Validation error: {ve!s}")
-        # print stack trace to console for debugging
-        print(traceback.format_exc())
+        # Log stack trace for debugging
+        logger.exception("Validation error during ingest", extra={"error": str(ve)})
         return JSONResponse(status_code=status.HTTP_400_BAD_REQUEST, content=error_response.model_dump())
 
     except Exception as exc:
         # Handle unexpected errors with 500 status code
         error_response = IngestErrorResponse(error=f"Internal server error: {exc!s}")
-        # print stack trace to console for debugging
-        print(traceback.format_exc())
+        # Log stack trace for debugging
+        logger.exception("Unexpected error during ingest", extra={"error": str(exc)})
         return JSONResponse(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, content=error_response.model_dump())