logging

README.md

@@ -24,4 +24,4 @@ PosixPath('/Users/genomicmedlab/.local/share/wagstails/mondo/mondo_v2023-09-12.o
 
 ## Configuration
 
-All data is stored within source-specific subdirectories of a designated WagsTails data directory. By default, this location is `~/.local/share/wagstails/`, but it can be configured by passing a Path directly to a data class on initialization, via the `$WAGSTAILS` environment variable, or via [XDG data environment variables](https://specifications.freedesktop.org/basedir-spec/basedir-spec-0.6.html).
+All data is stored within source-specific subdirectories of a designated WagsTails data directory. By default, this location is `~/.local/share/wagstails/`, but it can be configured by passing a Path directly to a data class on initialization, via the `$WAGSTAILS_DIR` environment variable, or via [XDG data environment variables](https://specifications.freedesktop.org/basedir-spec/basedir-spec-0.6.html).

src/wagstails/base_source.py

@@ -1,5 +1,6 @@
 """Define base data source class."""
 import abc
+import logging
 import os
 import tempfile
 from pathlib import Path
@@ -8,6 +9,8 @@
 import requests
 from tqdm import tqdm
 
+_logger = logging.getLogger(__name__)
+
 
 class RemoteDataError(Exception):
     """Raise when unable to parse, navigate, or extract information from a remote
@@ -112,6 +115,7 @@ def _http_download(
         :param handler: provide if downloaded file requires additional action, e.g.
             it's a zip file.
         """
+        _logger.info(f"Downloading {outfile_path.name} from {url}...")
         if handler:
             dl_path = Path(tempfile.gettempdir()) / "wagstails_tmp"
         else:
@@ -133,6 +137,7 @@ def _http_download(
                             progress_bar.update(len(chunk))
         if handler:
             handler(dl_path, outfile_path)
+        _logger.info(f"Successfully downloaded {outfile_path.name}.")
 
     def _get_latest_local_file(self, glob: str) -> Path:
         """Get most recent locally-available file.
@@ -141,10 +146,13 @@ def _get_latest_local_file(self, glob: str) -> Path:
         :return: Path to most recent file
         :raise FileNotFoundError: if no local data is available
         """
+        _logger.debug(f"Getting local match against pattern {glob}...")
         files = list(sorted(self._data_dir.glob(glob)))
         if len(files) < 1:
             raise FileNotFoundError(f"No source data found for {self._src_name}")
-        return files[-1]
+        latest = files[-1]
+        _logger.debug(f"Returning {latest} as most recent locally-available file.")
+        return latest
 
 
 class SpecificVersionDataSource(DataSource):
@@ -154,17 +162,16 @@ class SpecificVersionDataSource(DataSource):
     Useful for sources where the most recent data source sometimes gives us trouble.
     Enables a workflow where we could try the newest version of data, and if it parses
     incorrectly, try the next-most-recent until something works.
+
+    These methods probably aren't necessary for every source, though, so I put them
+    in a child class rather than the main ``DataSource`` class.
     """
 
     @abc.abstractmethod
     def iterate_versions(self) -> Generator:
         """Lazily get versions (i.e. not the files themselves, just their version
         strings), starting with the most recent value and moving backwards.
 
-        I don't know if every source can feasibly implement this, so I haven't marked
-        it as an abstractmethod, but I think it could be useful (e.g. retry with a
-        prior version if something fails in the latest version.)
-
         :return: Generator yielding version strings
         """
         raise NotImplementedError
@@ -175,9 +182,6 @@ def get_specific(
     ) -> Path:
         """Get specified version of data.
 
-        Like ``iterate_version()``, probably not necessary to implement for every class.
-
-
         :param from_local: if True, use matching local file, don't try to fetch from remote
         :param force_refresh: if True, fetch and return data from remote regardless of
             whether a local copy is present

src/wagstails/chembl.py

@@ -1,5 +1,6 @@
 """Provide source fetching for ChEMBL."""
 import fnmatch
+import logging
 import re
 import tarfile
 from pathlib import Path
@@ -9,6 +10,8 @@
 
 from .base_source import DataSource
 
+_logger = logging.getLogger(__name__)
+
 
 class ChemblData(DataSource):
     """Provide access to ChEMBL database."""
@@ -80,6 +83,9 @@ def get_latest(self, from_local: bool = False, force_refresh: bool = False) -> P
         latest_version = self._get_latest_version()
         latest_file = self._data_dir / f"chembl_{latest_version}.db"
         if (not force_refresh) and latest_file.exists():
+            _logger.debug(
+                f"Found existing file, {latest_file.name}, matching latest version {latest_version}."
+            )
             return latest_file
         self._http_download(
             f"https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/chembl_{latest_version}_sqlite.tar.gz",

src/wagstails/mondo.py

@@ -1,11 +1,14 @@
 """Provide source fetching for Mondo Disease Ontology."""
+import logging
 from pathlib import Path
 from typing import Optional, Tuple
 
 import requests
 
 from .base_source import GitHubDataSource
 
+_logger = logging.getLogger(__name__)
+
 
 class MondoData(GitHubDataSource):
     """Provide access to Mondo disease ontology data."""
@@ -68,6 +71,9 @@ def get_latest(self, from_local: bool = False, force_refresh: bool = False) -> P
         latest_version, data_url = self._get_latest_version()
         latest_file = self._data_dir / f"mondo_{latest_version}.owl"
         if (not force_refresh) and latest_file.exists():
+            _logger.debug(
+                f"Found existing file, {latest_file.name}, matching latest version {latest_version}."
+            )
             return latest_file
         else:
             self._http_download(data_url, latest_file)  # type: ignore