gtfparse 2.7.0__tar.gz → 2.7.2__tar.gz

{gtfparse-2.7.0 → gtfparse-2.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gtfparse
-Version: 2.7.0
+Version: 2.7.2
 Summary: Parsing library for extracting data frames of genomic features from GTF files
 Author-email: Alex Rubinsteyn <alex.rubinsteyn@unc.edu>
 Project-URL: Homepage, https://github.com/openvax/gtfparse

{gtfparse-2.7.0 → gtfparse-2.7.2}/gtfparse/__init__.py

@@ -23,7 +23,7 @@ from .read_gtf import (
     read_gtf,
 )
 
-__version__ = "2.7.0"
+__version__ = "2.7.2"
 
 __all__ = [
     "GENCODE_BIOTYPE_ALIASES",

{gtfparse-2.7.0 → gtfparse-2.7.2}/gtfparse/attribute_parsing.py

@@ -14,7 +14,6 @@ import logging
 from collections import OrderedDict
 from sys import intern
 
-logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 
@@ -103,5 +102,5 @@ def expand_attribute_strings(attribute_strings, quote_char="'", missing_value=""
                 extra_columns[column_name] = column
                 column_order.append(column_name)
 
-    logging.info("Extracted GTF attributes: %s" % column_order)
+    logger.info("Extracted GTF attributes: %s", column_order)
     return OrderedDict((column_name, extra_columns[column_name]) for column_name in column_order)

{gtfparse-2.7.0 → gtfparse-2.7.2}/gtfparse/create_missing_features.py

@@ -15,7 +15,6 @@ from collections import OrderedDict
 
 import pandas as pd
 
-logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 
@@ -58,9 +57,9 @@ def create_missing_features(dataframe, unique_keys={}, extra_columns={}, missing
 
     for feature_name, groupby_key in unique_keys.items():
         if feature_name in existing_features:
-            logging.info("Feature '%s' already exists in GTF data" % feature_name)
+            logger.info("Feature '%s' already exists in GTF data", feature_name)
             continue
-        logging.info("Creating rows for missing feature '%s'" % feature_name)
+        logger.info("Creating rows for missing feature '%s'", feature_name)
 
         # don't include rows where the groupby key was missing
         missing = pd.Series([x is None or x == "" for x in dataframe[groupby_key]])

{gtfparse-2.7.0 → gtfparse-2.7.2}/gtfparse/read_gtf.py

@@ -19,7 +19,6 @@ import polars
 from .attribute_parsing import expand_attribute_strings
 from .parsing_error import ParsingError
 
-logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 
@@ -354,7 +353,10 @@ def read_gtf(
             features=features,
         )
     else:
-        result_df = parse_gtf(result_df, features=features)
+        # When the caller opts out of attribute expansion they want the raw
+        # 'attribute' column verbatim — no need to also produce the
+        # 'attribute_split' helper that parse_gtf adds by default.
+        result_df = parse_gtf(filepath_or_buffer, features=features, split_attributes=False)
 
     # converting back to pandas here because Polars bugs manifest
     # as `pyo3_runtime.PanicException: assertion `left == right` failed: impl error`
@@ -403,10 +405,10 @@ def read_gtf(
             # the 2nd column is the transcript_biotype (otherwise, it's the
             # gene_biotype)
             if "gene_biotype" not in column_names:
-                logging.info("Using column 'source' to replace missing 'gene_biotype'")
+                logger.info("Using column 'source' to replace missing 'gene_biotype'")
                 result_df["gene_biotype"] = result_df["source"]
             if "transcript_biotype" not in column_names:
-                logging.info("Using column 'source' to replace missing 'transcript_biotype'")
+                logger.info("Using column 'source' to replace missing 'transcript_biotype'")
                 result_df["transcript_biotype"] = result_df["source"]
 
     if usecols is not None:

{gtfparse-2.7.0 → gtfparse-2.7.2}/gtfparse.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gtfparse
-Version: 2.7.0
+Version: 2.7.2
 Summary: Parsing library for extracting data frames of genomic features from GTF files
 Author-email: Alex Rubinsteyn <alex.rubinsteyn@unc.edu>
 Project-URL: Homepage, https://github.com/openvax/gtfparse

{gtfparse-2.7.0 → gtfparse-2.7.2}/gtfparse.egg-info/SOURCES.txt

@@ -15,6 +15,7 @@ gtfparse.egg-info/top_level.txt
 gtfparse/../requirements.txt
 tests/test_create_missing_features.py
 tests/test_ensembl_gtf.py
+tests/test_expand_attribute_column_false.py
 tests/test_expand_attributes.py
 tests/test_gencode_gtf.py
 tests/test_multiple_values_for_tag_attribute.py

gtfparse-2.7.2/tests/test_expand_attribute_column_false.py

@@ -0,0 +1,74 @@
+"""Regression tests for #56: read_gtf(expand_attribute_column=False)
+used to raise NameError because the else branch referenced `result_df`
+before it had been assigned.
+"""
+
+import pandas as pd
+
+from gtfparse import read_gtf
+
+from .data import data_path
+
+GTF_PATH = data_path("ensembl_grch37.head.gtf")
+
+
+def test_expand_attribute_column_false_returns_raw_attribute_pandas():
+    df = read_gtf(GTF_PATH, expand_attribute_column=False, result_type="pandas")
+    assert isinstance(df, pd.DataFrame)
+    # raw attribute column is preserved verbatim
+    assert "attribute" in df.columns
+    # none of the per-key attribute columns are produced
+    assert "gene_name" not in df.columns
+    assert "transcript_id" not in df.columns
+    # the helper 'attribute_split' column from parse_gtf is also suppressed
+    assert "attribute_split" not in df.columns
+    # core GTF columns are present and populated
+    for col in ("seqname", "source", "feature", "start", "end", "strand"):
+        assert col in df.columns
+    assert len(df) > 0
+    # spot-check that the raw attribute string carries the original key/value form
+    assert any("gene_id" in val for val in df["attribute"].astype(str))
+
+
+def test_expand_attribute_column_false_returns_polars():
+    df = read_gtf(GTF_PATH, expand_attribute_column=False, result_type="polars")
+    # polars dataframe — has columns attribute but no per-key columns
+    assert "attribute" in df.columns
+    assert "gene_name" not in df.columns
+    assert "attribute_split" not in df.columns
+
+
+def test_expand_attribute_column_false_returns_dict():
+    result = read_gtf(GTF_PATH, expand_attribute_column=False, result_type="dict")
+    assert isinstance(result, dict)
+    assert "attribute" in result
+    assert "gene_name" not in result
+
+
+def test_expand_attribute_column_false_with_features_filter():
+    """The features filter must still apply when not expanding."""
+    df = read_gtf(
+        GTF_PATH,
+        expand_attribute_column=False,
+        features={"gene"},
+        result_type="pandas",
+    )
+    assert set(df["feature"]) == {"gene"}
+
+
+def test_expand_attribute_column_false_skips_alias_and_version_logic():
+    """When attribute columns aren't expanded, attribute_aliases has
+    nothing to rename and cast_version_columns has nothing to cast.
+    Neither should raise — both must be graceful no-ops on the raw
+    'attribute'-column-only frame."""
+    df = read_gtf(
+        GTF_PATH,
+        expand_attribute_column=False,
+        attribute_aliases={"gene_type": "gene_biotype"},
+        cast_version_columns=True,
+        result_type="pandas",
+    )
+    # alias source wasn't in columns → no rename happened → no canonical added
+    assert "gene_biotype" not in df.columns
+    # version columns weren't present → no cast → still nothing
+    assert "gene_version" not in df.columns