mapkgsutils 0.1.2__tar.gz → 0.2.1__tar.gz

{mapkgsutils-0.1.2 → mapkgsutils-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mapkgsutils
-Version: 0.1.2
+Version: 0.2.1
 Summary: Utils shared by several mapping set generation tools for biomedical databases
 Keywords: snekpack,cookiecutter
 Author: Javier Millan Acosta

{mapkgsutils-0.1.2 → mapkgsutils-0.2.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "mapkgsutils"
-version = "0.1.2"
+version = "0.2.1"
 description = "Utils shared by several mapping set generation tools for biomedical databases"
 readme = "README.md"
 authors = [
@@ -236,7 +236,7 @@ known-first-party = [
 docstring-code-format = true
 
 [tool.bumpversion]
-current_version = "0.1.2"
+current_version = "0.2.1"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)(?:-(?P<release>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?(?:\\+(?P<build>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?"
 serialize = [
     "{major}.{minor}.{patch}-{release}+{build}",

{mapkgsutils-0.1.2 → mapkgsutils-0.2.1}/src/mapkgsutils/consolidate.py

@@ -142,29 +142,15 @@ def load_mapping_dates(cache_path: Path) -> dict[str, str]:
         cache_path: Path to the cache TSV (see :func:`write_cache`).
 
     Returns:
-        Dict mapping each ``record_id`` to its best available ISO date
-        string: the mapping's own per-row ``mapping_date`` when the parser
-        produced one, else the first-seen release date. Records with no date
-        at all are omitted, leaving their ``mapping_date`` unset rather than
-        passing through a non-date value.
+        Dict mapping each ``record_id`` to the mapping's ``mapping_date``,
+        else the first-seen release date.
     """
     records = read_cache(cache_path)
     return {rid: date for rid, fields in records.items() if (date := _best_date(fields))}
 
 
 def _mapping_fields_json(m: Any) -> str:
-    """JSON-encode a mapping's own fields (excluding record_id).
-
-    Snapshots a mapping's current shape (subject_id, object_id,
-    predicate_id, mapping_date, ...) so :func:`build_consolidated_mapping_set`
-    can rebuild it into a real SSSOM mapping set later. The parser's own
-    per-row ``mapping_date`` is kept (it's release-independent), distinct
-    from the first-seen release version. ``default=str`` handles
-    enum-valued fields like ``mapping_cardinality``, which round-trip
-    cleanly back through ``Mapping(**fields)``. Returns ``"{}"`` for
-    non-dataclass stand-ins (e.g. test doubles); callers skip those rows
-    rather than materializing them.
-    """
+    """JSON-encode a mapping's own fields (excluding record_id)."""
     from dataclasses import fields as dataclass_fields
     from dataclasses import is_dataclass
 
@@ -193,16 +179,6 @@ def consolidate(
 
     Keeps every mapping and every available piece of provenance.
 
-    - **``list_versions`` provided** (versioned archive, e.g. ChEBI/HGNC/
-      UniProt/Ensembl): walk every release oldest-first, calling
-      ``run_one_version(v)`` per release and recording the first/last release
-      each mapping was seen in. Resumes from :func:`read_meta` unless
-      *force*. This collects the full historical set.
-    - **``list_versions`` is ``None``** (no versioned archive, e.g. NCBI/
-      VGNC): a single current parse via ``run_one_version(None)`` caching the
-      *full* mapping set — every mapping kept, stamped with its own per-row
-      date when present and left undated otherwise.
-
     Args:
         cache_path: Path to the cache TSV to read/write.
         meta_path: Path to the ``last_version`` sidecar to read/write.
@@ -257,8 +233,7 @@ def _consolidate_single_parse(
         pair_key = str(getattr(m, "record_id", None) or "")[-16:]
         if not pair_key:
             continue
-        # The mapping's own per-row date survives in fields_json; first_seen_date
-        # mirrors it so undated rows simply stay undated rather than dropping out.
+        # The mapping's own per-row date is taken from fields_json
         date_str = str(m.mapping_date) if getattr(m, "mapping_date", None) else ""
         records[pair_key] = {
             "first_seen_version": version_label,

{mapkgsutils-0.1.2 → mapkgsutils-0.2.1}/src/mapkgsutils/diff.py

@@ -170,7 +170,7 @@ def _read_sssom_to_dataframe(path: Path) -> pl.DataFrame:
     """
     # Count header lines
     header_lines = 0
-    with path.open() as f:
+    with path.open(encoding="utf-8") as f:
         for line in f:
             if line.startswith("#"):
                 header_lines += 1
@@ -200,7 +200,7 @@ def _extract_sssom_version(path: Path) -> str | None:
     Returns:
         Version string or None if not found.
     """
-    with path.open() as f:
+    with path.open(encoding="utf-8") as f:
         for line in f:
             if not line.startswith("#"):
                 break

{mapkgsutils-0.1.2 → mapkgsutils-0.2.1}/src/mapkgsutils/download.py

@@ -68,6 +68,7 @@ def _is_cloudflare_blocked(response: httpx.Response) -> bool:
         # header being present, check the body.
         content_type = response.headers.get("content-type", "")
         if "text/html" in content_type:
+            response.read()  # body is unread on a streamed response; .text needs it
             text = response.text
             if "cloudflare" in text.lower() or "cf-ray" in text.lower():
                 return True
@@ -558,8 +559,7 @@ def download_datasource_with_release(
         keys: Optional list of file-key names to download.
         tar_extractors: ``{datasource_name: extractor}`` registry for
             datasources that publish a ``.tar.gz`` archive needing
-            member-level extraction rather than a plain download (e.g.
-            UniProt). Datasources without one are downloaded as-is.
+            member-level extraction.
         **kwargs: Datasource-specific knobs forwarded to the resolved hook.
 
     Returns:

{mapkgsutils-0.1.2 → mapkgsutils-0.2.1}/src/mapkgsutils/exports.py

@@ -5,9 +5,9 @@ from __future__ import annotations
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, TypeVar
 
-from sssom import MappingSetDataFrame
-
 if TYPE_CHECKING:
+    from sssom import MappingSetDataFrame
+
     from mapkgsutils.parsers.base import BaseMappingSet
 
 _M = TypeVar("_M", bound="BaseMappingSet")

mapkgsutils-0.2.1/src/mapkgsutils/logging.py

@@ -0,0 +1,68 @@
+"""Logging configuration.
+
+Provides a configured package logger. Only CRITICAL messages show by default;
+call :func:`set_log_level` to raise verbosity.
+"""
+
+from __future__ import annotations
+
+import logging
+import sys
+
+__all__ = [
+    "LOG_LEVELS",
+    "get_logger",
+    "logger",
+    "set_log_level",
+]
+
+# Map of log level names to logging constants
+LOG_LEVELS: dict[str, int] = {
+    "critical": logging.CRITICAL,
+    "error": logging.ERROR,
+    "warning": logging.WARNING,
+    "warn": logging.WARNING,
+    "info": logging.INFO,
+    "debug": logging.DEBUG,
+}
+
+
+def get_logger(name: str) -> logging.Logger:
+    """Return a stderr-handled logger for *name*, defaulting to CRITICAL."""
+    log = logging.getLogger(name)
+    log.setLevel(logging.CRITICAL)
+    if not log.handlers:
+        handler = logging.StreamHandler(sys.stderr)
+        handler.setFormatter(
+            logging.Formatter(
+                "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+                datefmt="%Y-%m-%d %H:%M:%S",
+            )
+        )
+        log.addHandler(handler)
+    return log
+
+
+logger = get_logger("mapkgsutils")
+
+
+def set_log_level(level: str | int, target: logging.Logger | None = None) -> None:
+    """Set the log level on *target* (the mapkgsutils logger by default).
+
+    Args:
+        level: Level name (``"debug"``/``"info"``/``"warning"``/``"error"``/
+            ``"critical"``) or an integer such as ``logging.INFO``.
+        target: Logger to configure.
+
+    Example:
+        >>> from mapkgsutils.logging import set_log_level
+        >>> set_log_level("warning")
+    """
+    log = target if target is not None else logger
+    if isinstance(level, str):
+        level_int = LOG_LEVELS.get(level.lower())
+        if level_int is None:
+            raise ValueError(f"Unknown log level: {level}. Available: {list(LOG_LEVELS.keys())}")
+        log.setLevel(level_int)
+    else:
+        log.setLevel(level)