refactor(logging): replace warnings with logger across codebase

Author: MickaelCa

src/gitingest/entrypoint.py

@@ -7,7 +7,6 @@
 import shutil
 import stat
 import sys
-import warnings
 from contextlib import asynccontextmanager
 from pathlib import Path
 from typing import TYPE_CHECKING, AsyncGenerator, Callable
@@ -241,19 +240,19 @@ def _override_branch_and_tag(query: IngestionQuery, branch: str | None, tag: str
     """
     if tag and query.tag and tag != query.tag:
         msg = f"Warning: The specified tag '{tag}' overrides the tag found in the URL '{query.tag}'."
-        warnings.warn(msg, RuntimeWarning, stacklevel=3)
+        logger.warning(msg)
 
     query.tag = tag or query.tag
 
     if branch and query.branch and branch != query.branch:
         msg = f"Warning: The specified branch '{branch}' overrides the branch found in the URL '{query.branch}'."
-        warnings.warn(msg, RuntimeWarning, stacklevel=3)
+        logger.warning(msg)
 
     query.branch = branch or query.branch
 
     if tag and branch:
         msg = "Warning: Both tag and branch are specified. The tag will be used."
-        warnings.warn(msg, RuntimeWarning, stacklevel=3)
+        logger.warning(msg)
 
     # Tag wins over branch if both supplied
     if query.tag:

src/gitingest/output_formatter.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 import ssl
-import warnings
 from typing import TYPE_CHECKING
 
 import requests.exceptions
@@ -197,11 +196,11 @@ def _format_token_count(text: str) -> str | None:
         encoding = tiktoken.get_encoding("o200k_base")  # gpt-4o, gpt-4o-mini
         total_tokens = len(encoding.encode(text, disallowed_special=()))
     except (ValueError, UnicodeEncodeError) as exc:
-        warnings.warn(f"Failed to estimate token size: {exc}", RuntimeWarning, stacklevel=3)
+        logger.warning("Failed to estimate token size", extra={"error": str(exc)})
         return None
     except (requests.exceptions.RequestException, ssl.SSLError) as exc:
         # If network errors, skip token count estimation instead of erroring out
-        warnings.warn(f"Failed to download tiktoken model: {exc}", RuntimeWarning, stacklevel=3)
+        logger.warning("Failed to download tiktoken model", extra={"error": str(exc)})
         return None
 
     for threshold, suffix in _TOKEN_THRESHOLDS:

src/gitingest/query_parser.py

@@ -3,13 +3,13 @@
 from __future__ import annotations
 
 import uuid
-import warnings
 from pathlib import Path
 from typing import Literal
 
 from gitingest.config import TMP_BASE_PATH
 from gitingest.schemas import IngestionQuery
 from gitingest.utils.git_utils import fetch_remote_branches_or_tags, resolve_commit
+from gitingest.utils.logging_config import get_logger
 from gitingest.utils.query_parser_utils import (
     PathKind,
     _fallback_to_root,
@@ -18,6 +18,9 @@
     _normalise_source,
 )
 
+# Initialize logger for this module
+logger = get_logger(__name__)
+
 
 async def parse_remote_repo(source: str, token: str | None = None) -> IngestionQuery:
     """Parse a repository URL and return an ``IngestionQuery`` object.
@@ -169,7 +172,7 @@ async def _configure_branch_or_tag(
     except RuntimeError as exc:
         # If remote discovery fails, we optimistically treat the first path segment as the branch/tag.
         msg = f"Warning: Failed to fetch {_ref_type}: {exc}"
-        warnings.warn(msg, RuntimeWarning, stacklevel=2)
+        logger.warning(msg)
         return path_parts.pop(0) if path_parts else None
 
     # Iterate over the path components and try to find a matching branch/tag

src/gitingest/utils/notebook.py

@@ -3,15 +3,18 @@
 from __future__ import annotations
 
 import json
-import warnings
 from itertools import chain
 from typing import TYPE_CHECKING, Any
 
 from gitingest.utils.exceptions import InvalidNotebookError
+from gitingest.utils.logging_config import get_logger
 
 if TYPE_CHECKING:
     from pathlib import Path
 
+# Initialize logger for this module
+logger = get_logger(__name__)
+
 
 def process_notebook(file: Path, *, include_output: bool = True) -> str:
     """Process a Jupyter notebook file and return an executable Python script as a string.
@@ -44,20 +47,16 @@ def process_notebook(file: Path, *, include_output: bool = True) -> str:
     # Check if the notebook contains worksheets
     worksheets = notebook.get("worksheets")
     if worksheets:
-        warnings.warn(
+        logger.warning(
             "Worksheets are deprecated as of IPEP-17. Consider updating the notebook. "
             "(See: https://github.com/jupyter/nbformat and "
             "https://github.com/ipython/ipython/wiki/IPEP-17:-Notebook-Format-4#remove-multiple-worksheets "
             "for more information.)",
-            DeprecationWarning,
-            stacklevel=2,
         )
 
         if len(worksheets) > 1:
-            warnings.warn(
+            logger.warning(
                 "Multiple worksheets detected. Combining all worksheets into a single script.",
-                UserWarning,
-                stacklevel=2,
             )
 
         cells = list(chain.from_iterable(ws["cells"] for ws in worksheets))

src/gitingest/utils/query_parser_utils.py

@@ -3,16 +3,18 @@
 from __future__ import annotations
 
 import string
-import warnings
 from typing import TYPE_CHECKING, cast
 from urllib.parse import ParseResult, unquote, urlparse
 
 from gitingest.utils.compat_typing import StrEnum
 from gitingest.utils.git_utils import _resolve_ref_to_sha, check_repo_exists
+from gitingest.utils.logging_config import get_logger
 
 if TYPE_CHECKING:
     from gitingest.schemas import IngestionQuery
 
+# Initialize logger for this module
+logger = get_logger(__name__)
 
 HEX_DIGITS: set[str] = set(string.hexdigits)
 
@@ -56,7 +58,7 @@ async def _fallback_to_root(query: IngestionQuery, token: str | None, warn_msg:
     url = cast("str", query.url)
     query.commit = await _resolve_ref_to_sha(url, pattern="HEAD", token=token)
     if warn_msg:
-        warnings.warn(warn_msg, RuntimeWarning, stacklevel=3)
+        logger.warning(warn_msg)
     return query