gtfreader 0.1.0__tar.gz

gtfreader-0.1.0/MANIFEST.in

@@ -0,0 +1,5 @@
+include README.md
+include pyproject.toml
+include setup.py
+recursive-include gtfreader *.py *.pyx *.c
+recursive-include tests *.py

gtfreader-0.1.0/PKG-INFO

@@ -0,0 +1,66 @@
+Metadata-Version: 2.4
+Name: gtfreader
+Version: 0.1.0
+Summary: Fast Cython-backed parsing for GTF attribute columns.
+Author: Endre Bakken Stovner
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Cython
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: pandas>=2.0
+
+# gtfreader
+
+`gtfreader` is a small package for parsing and reading GTF files into pandas dataframes.
+
+## Install
+
+```bash
+python -m pip install -e .
+```
+
+## Usage
+
+```python
+from gtfreader import read_gtf, read_gtf_python
+
+df = read_gtf("annotation.gtf")
+df_python = read_gtf_python("annotation.gtf")
+```
+
+`read_gtf(...)` uses the compiled parser path when available. `read_gtf_python(...)` uses the high-level pure Python parser path used by the current `pyrunges` reader style.
+
+If you want to use the compiled low-level parser directly, pass it raw attribute strings from column 9 of the GTF before they have been expanded:
+
+```python
+import pandas as pd
+
+from gtfreader import find_first_data_line_index, parse_chunk_columns
+
+skiprows = find_first_data_line_index("annotation.gtf")
+attribute_lines = pd.read_csv(
+    "annotation.gtf",
+    sep="\t",
+    header=None,
+    usecols=[8],
+    names=["Attribute"],
+    skiprows=skiprows,
+)["Attribute"].tolist()
+
+compiled_columns = parse_chunk_columns(attribute_lines)
+```
+
+## Build
+
+```bash
+python -m build
+```
+
+## Test
+
+```bash
+python -m pytest -q
+```

gtfreader-0.1.0/README.md

@@ -0,0 +1,52 @@
+# gtfreader
+
+`gtfreader` is a small package for parsing and reading GTF files into pandas dataframes.
+
+## Install
+
+```bash
+python -m pip install -e .
+```
+
+## Usage
+
+```python
+from gtfreader import read_gtf, read_gtf_python
+
+df = read_gtf("annotation.gtf")
+df_python = read_gtf_python("annotation.gtf")
+```
+
+`read_gtf(...)` uses the compiled parser path when available. `read_gtf_python(...)` uses the high-level pure Python parser path used by the current `pyrunges` reader style.
+
+If you want to use the compiled low-level parser directly, pass it raw attribute strings from column 9 of the GTF before they have been expanded:
+
+```python
+import pandas as pd
+
+from gtfreader import find_first_data_line_index, parse_chunk_columns
+
+skiprows = find_first_data_line_index("annotation.gtf")
+attribute_lines = pd.read_csv(
+    "annotation.gtf",
+    sep="\t",
+    header=None,
+    usecols=[8],
+    names=["Attribute"],
+    skiprows=skiprows,
+)["Attribute"].tolist()
+
+compiled_columns = parse_chunk_columns(attribute_lines)
+```
+
+## Build
+
+```bash
+python -m build
+```
+
+## Test
+
+```bash
+python -m pytest -q
+```

gtfreader-0.1.0/gtfreader/__init__.py

@@ -0,0 +1,35 @@
+"""Public package API for gtfreader."""
+
+try:
+    from ._parser import parse_chunk_columns
+except ImportError:
+    def parse_chunk_columns(*_args, **_kwargs):
+        msg = "gtfreader.parse_chunk_columns requires the compiled extension. Use read_gtf_python or read_gtf_full_python for the pure Python fallback."
+        raise ImportError(msg)
+
+from .readers import (
+    find_first_data_line_index,
+    parse_kv_fields,
+    read_gtf,
+    read_gtf_full,
+    read_gtf_full_python,
+    read_gtf_python,
+    read_gtf_restricted,
+    read_gtf_restricted_python,
+    to_rows,
+    to_rows_keep_duplicates,
+)
+
+__all__ = [
+    "find_first_data_line_index",
+    "parse_chunk_columns",
+    "parse_kv_fields",
+    "read_gtf",
+    "read_gtf_full",
+    "read_gtf_full_python",
+    "read_gtf_python",
+    "read_gtf_restricted",
+    "read_gtf_restricted_python",
+    "to_rows",
+    "to_rows_keep_duplicates",
+]