streampile 0.1.0__tar.gz

streampile-0.1.0/.gitignore

@@ -0,0 +1,171 @@
+.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# VS Code
+.vscode/
+
+# Jupyter notebook files
+*.ipynb
+
+# Benchmark scratch files
+benchmarks/out/

streampile-0.1.0/CONTRIBUTING.md

@@ -0,0 +1,66 @@
+# Developer Documentation
+
+## Local Setup
+
+Install [uv](https://docs.astral.sh/uv/), then install the library and its development tools with:
+
+```console
+uv sync --locked
+```
+
+## Local Testing
+
+To ensure all tests pass, run:
+
+```console
+uv run poe check-tests
+```
+
+The tests run the examples in the README too, so keep them working.
+
+## Local Linting and Formatting
+
+To check the lockfile, project metadata, format, lint, and types of all the code, and run every test, run:
+
+```console
+uv run poe check-all
+```
+
+To fix what can be fixed automatically, run:
+
+```console
+uv run poe fix-all
+```
+
+## Benchmarks
+
+See [`benchmarks/README.md`](benchmarks/README.md) for how to run them and recent results.
+
+## Locking
+
+`[tool.uv]` in `pyproject.toml` ignores releases younger than a week, and `uv.lock` records that setting.
+Lock with the uv version pinned as `UV_VERSION` in [`tests.yml`](.github/workflows/tests.yml), and keep any user-level uv configuration out of the lock, or CI will find the lockfile stale:
+
+```console
+XDG_CONFIG_HOME="$(mktemp -d)" uvx uv@0.12.20 lock
+```
+
+## Commits
+
+Commit titles follow [Conventional Commits](https://www.conventionalcommits.org), which group the release notes that [git-cliff](https://git-cliff.org) generates from `pyproject.toml`.
+
+## Releasing
+
+Releases are published to PyPI by the [`publish_streampile.yml`](.github/workflows/publish_streampile.yml) workflow with PyPI Trusted Publishing, so no API token is stored in GitHub.
+
+To release:
+
+1. Merge a pull request titled `chore(release): bump to X.Y.Z` that sets the version in `pyproject.toml`.
+2. Tag the merge commit on `main` and push the tag:
+
+   ```console
+   git tag X.Y.Z
+   git push origin X.Y.Z
+   ```
+
+3. The workflow checks that the tag is on `main` and matches the version, runs the tests, builds the sdist and wheel, checks that each installs and imports on every supported Python, publishes to PyPI, and creates a GitHub release with notes generated by git-cliff.

streampile-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright © 2026 Clint Valentine
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

streampile-0.1.0/NOTICE

@@ -0,0 +1,12 @@
+streampile
+Copyright © 2026 Clint Valentine
+
+The forward-only, coordinate-advancing design of StreamingPileupBuilder follows
+StreamingPileupBuilder in fgbio (https://github.com/fulcrumgenomics/fgbio), which
+is distributed under the MIT License:
+
+  Copyright (c) 2015-2026 Fulcrum Genomics LLC
+
+Pileup entries follow the conventions of htslib (https://github.com/samtools/htslib)
+and pysam (https://github.com/pysam-developers/pysam), both distributed under the
+MIT License.

streampile-0.1.0/PKG-INFO

@@ -0,0 +1,184 @@
+Metadata-Version: 2.5
+Name: streampile
+Version: 0.1.0
+Summary: Forward-only pileups streamed from coordinate-sorted SAM, BAM, and CRAM records.
+Project-URL: homepage, https://github.com/clintval/streampile
+Project-URL: repository, https://github.com/clintval/streampile
+Project-URL: Bug Tracker, https://github.com/clintval/streampile/issues
+Author-email: Clint Valentine <valentine.clint@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+License-File: NOTICE
+Keywords: BAM,HTS,NGS,SAM,bioinformatics,genomics,pileup
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Requires-Dist: bedspec>=4.0.0
+Requires-Dist: pybgzf>=0.1.2
+Requires-Dist: pysam>=0.23
+Requires-Dist: typeline>=2.4.0
+Requires-Dist: typing-extensions>=4.12
+Description-Content-Type: text/markdown
+
+# streampile
+
+[![Build Status](https://github.com/clintval/streampile/actions/workflows/tests.yml/badge.svg?branch=main)](https://github.com/clintval/streampile/actions/workflows/tests.yml?query=branch%3Amain)
+[![Python Versions](https://img.shields.io/badge/python-3.11_|_3.12_|_3.13_|_3.14-blue)](https://github.com/clintval/streampile)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/clintval/streampile/blob/main/LICENSE)
+[![basedpyright](https://img.shields.io/badge/basedpyright-checked-42b983)](https://docs.basedpyright.com/latest/)
+[![mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://docs.astral.sh/uv/)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://docs.astral.sh/ruff/)
+
+Forward-only pileups streamed from coordinate-sorted BAM and CRAM records, and a table of the alleles at every base.
+
+## Installation
+
+```console
+pip install streampile
+```
+
+## Quickstart
+
+### Building Pileups
+
+A `StreamingPileupBuilder` reads records once and piles them up at the 0-based positions you ask for, moving forward only.
+
+```pycon
+>>> from pysam import AlignmentFile
+>>> from streampile import StreamingPileupBuilder
+>>>
+>>> with (
+...     AlignmentFile("tests/data/reads.bam") as reads,
+...     StreamingPileupBuilder(reads, min_base_quality=30) as builder,
+... ):
+...     first = builder.pileup("chr1", 10)
+...     second = builder.pileup("chr1", 12)
+>>>
+>>> first.filtered_depth, first.bases
+(4, ['A', 'T', 'G', 'A'])
+>>> second.filtered_depth, second.bases
+(3, ['G', 'G', 'G'])
+
+```
+
+Filter reads with `read_filter`, and count each template once with `without_overlaps()`:
+
+```pycon
+>>> with (
+...     AlignmentFile("tests/data/reads.bam") as reads,
+...     StreamingPileupBuilder(reads, read_filter=lambda read: read.is_paired) as builder,
+... ):
+...     pileup = builder.pileup("chr1", 50)
+>>>
+>>> pileup.bases, pileup.without_overlaps().bases
+(['T', 'T'], ['T'])
+
+```
+
+Pass `tap=writer.write` to receive every record, in input order, once the builder has moved past it.
+
+### Sweeping a Territory
+
+`columns` yields the pileup at every position of a span.
+
+```pycon
+>>> with AlignmentFile("tests/data/reads.bam") as reads, StreamingPileupBuilder(reads) as builder:
+...     sum(pileup.unfiltered_depth for pileup in builder.columns("chr1", 0, 20))
+73
+
+```
+
+### Tabulating Alleles
+
+`tabulate` counts the reads of every allele at every base of a [bedspec](https://github.com/clintval/bedspec) `Territory`.
+Alleles are normalized VCF alleles at 1-based positions, so they match a VCF by `CHROM`, `POS`, `REF`, and `ALT`.
+
+```pycon
+>>> from bedspec import Bed3
+>>> from bedspec import Territory
+>>> from pysam import FastaFile
+>>> from streampile import tabulate
+>>>
+>>> territory = Territory([Bed3("chr1", start=9, end=12)])
+>>> with (
+...     AlignmentFile("tests/data/reads.bam") as reads,
+...     FastaFile("tests/data/reference.fa") as reference,
+... ):
+...     bases = list(tabulate(reads, reference, territory, min_base_quality=30))
+>>>
+>>> for base in bases:
+...     print(base.pos, base.ref, base.depth, base.alts, base.alt_reads)
+10 A 4 () ()
+11 A 4 ('T', 'GG') (1, 1)
+12 C 4 () ()
+
+```
+
+Each base also splits its reads by strand and counts no-calls apart from its depth.
+
+### Reading a Table
+
+```pycon
+>>> from streampile import TabulationReader
+>>>
+>>> for base in TabulationReader.from_path("tests/data/counts.tsv"):
+...     print(base.pos, base.depth, base.alts, base.alt_reads)
+21 5 () ()
+22 5 () ()
+23 4 ('C',) (1,)
+24 4 () ()
+
+```
+
+## Command Line
+
+```console
+streampile tabulate \
+    --bam tests/data/reads.bam \
+    --ref tests/data/reference.fa \
+    --intervals tests/data/territory.bed \
+    --min-base-quality 30 \
+    --min-mapping-quality 20 \
+    --out counts.tsv
+```
+
+```text
+##streampile-tabulation=1
+##streampile-version=0.1.0
+##bam=tests/data/reads.bam
+##reference=tests/data/reference.fa
+##territory=tests/data/territory.bed
+##min_base_quality=30
+##min_mapping_quality=20
+##exclude_flags=0xf00
+#contig	pos	ref	depth	no_calls	ref_reads	ref_fwd	ref_rev	alt_refs	alts	alt_reads	alt_fwd	alt_rev
+chr1	21	T	5	0	5	3	2					
+chr1	22	G	5	0	5	3	2					
+chr1	23	C	4	0	3	2	1	CA	C	1	0	1
+chr1	24	A	4	0	3	2	1					
+```
+
+Write to a `.gz` path with `--index tbi` to compress and index the table, then read a region back:
+
+```python
+for base in TabulationReader.query("counts.tsv.gz", "chr1", 20, 24):
+    print(base.pos, base.depth, base.alts)
+```
+
+## Development and Testing
+
+See the [contributing guide](https://github.com/clintval/streampile/blob/main/CONTRIBUTING.md) for more information.
+
+The streaming design follows the `StreamingPileupBuilder` of [fgbio](https://github.com/fulcrumgenomics/fgbio); see [NOTICE](https://github.com/clintval/streampile/blob/main/NOTICE).

streampile-0.1.0/README.md

@@ -0,0 +1,151 @@
+# streampile
+
+[![Build Status](https://github.com/clintval/streampile/actions/workflows/tests.yml/badge.svg?branch=main)](https://github.com/clintval/streampile/actions/workflows/tests.yml?query=branch%3Amain)
+[![Python Versions](https://img.shields.io/badge/python-3.11_|_3.12_|_3.13_|_3.14-blue)](https://github.com/clintval/streampile)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/clintval/streampile/blob/main/LICENSE)
+[![basedpyright](https://img.shields.io/badge/basedpyright-checked-42b983)](https://docs.basedpyright.com/latest/)
+[![mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://docs.astral.sh/uv/)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://docs.astral.sh/ruff/)
+
+Forward-only pileups streamed from coordinate-sorted BAM and CRAM records, and a table of the alleles at every base.
+
+## Installation
+
+```console
+pip install streampile
+```
+
+## Quickstart
+
+### Building Pileups
+
+A `StreamingPileupBuilder` reads records once and piles them up at the 0-based positions you ask for, moving forward only.
+
+```pycon
+>>> from pysam import AlignmentFile
+>>> from streampile import StreamingPileupBuilder
+>>>
+>>> with (
+...     AlignmentFile("tests/data/reads.bam") as reads,
+...     StreamingPileupBuilder(reads, min_base_quality=30) as builder,
+... ):
+...     first = builder.pileup("chr1", 10)
+...     second = builder.pileup("chr1", 12)
+>>>
+>>> first.filtered_depth, first.bases
+(4, ['A', 'T', 'G', 'A'])
+>>> second.filtered_depth, second.bases
+(3, ['G', 'G', 'G'])
+
+```
+
+Filter reads with `read_filter`, and count each template once with `without_overlaps()`:
+
+```pycon
+>>> with (
+...     AlignmentFile("tests/data/reads.bam") as reads,
+...     StreamingPileupBuilder(reads, read_filter=lambda read: read.is_paired) as builder,
+... ):
+...     pileup = builder.pileup("chr1", 50)
+>>>
+>>> pileup.bases, pileup.without_overlaps().bases
+(['T', 'T'], ['T'])
+
+```
+
+Pass `tap=writer.write` to receive every record, in input order, once the builder has moved past it.
+
+### Sweeping a Territory
+
+`columns` yields the pileup at every position of a span.
+
+```pycon
+>>> with AlignmentFile("tests/data/reads.bam") as reads, StreamingPileupBuilder(reads) as builder:
+...     sum(pileup.unfiltered_depth for pileup in builder.columns("chr1", 0, 20))
+73
+
+```
+
+### Tabulating Alleles
+
+`tabulate` counts the reads of every allele at every base of a [bedspec](https://github.com/clintval/bedspec) `Territory`.
+Alleles are normalized VCF alleles at 1-based positions, so they match a VCF by `CHROM`, `POS`, `REF`, and `ALT`.
+
+```pycon
+>>> from bedspec import Bed3
+>>> from bedspec import Territory
+>>> from pysam import FastaFile
+>>> from streampile import tabulate
+>>>
+>>> territory = Territory([Bed3("chr1", start=9, end=12)])
+>>> with (
+...     AlignmentFile("tests/data/reads.bam") as reads,
+...     FastaFile("tests/data/reference.fa") as reference,
+... ):
+...     bases = list(tabulate(reads, reference, territory, min_base_quality=30))
+>>>
+>>> for base in bases:
+...     print(base.pos, base.ref, base.depth, base.alts, base.alt_reads)
+10 A 4 () ()
+11 A 4 ('T', 'GG') (1, 1)
+12 C 4 () ()
+
+```
+
+Each base also splits its reads by strand and counts no-calls apart from its depth.
+
+### Reading a Table
+
+```pycon
+>>> from streampile import TabulationReader
+>>>
+>>> for base in TabulationReader.from_path("tests/data/counts.tsv"):
+...     print(base.pos, base.depth, base.alts, base.alt_reads)
+21 5 () ()
+22 5 () ()
+23 4 ('C',) (1,)
+24 4 () ()
+
+```
+
+## Command Line
+
+```console
+streampile tabulate \
+    --bam tests/data/reads.bam \
+    --ref tests/data/reference.fa \
+    --intervals tests/data/territory.bed \
+    --min-base-quality 30 \
+    --min-mapping-quality 20 \
+    --out counts.tsv
+```
+
+```text
+##streampile-tabulation=1
+##streampile-version=0.1.0
+##bam=tests/data/reads.bam
+##reference=tests/data/reference.fa
+##territory=tests/data/territory.bed
+##min_base_quality=30
+##min_mapping_quality=20
+##exclude_flags=0xf00
+#contig	pos	ref	depth	no_calls	ref_reads	ref_fwd	ref_rev	alt_refs	alts	alt_reads	alt_fwd	alt_rev
+chr1	21	T	5	0	5	3	2					
+chr1	22	G	5	0	5	3	2					
+chr1	23	C	4	0	3	2	1	CA	C	1	0	1
+chr1	24	A	4	0	3	2	1					
+```
+
+Write to a `.gz` path with `--index tbi` to compress and index the table, then read a region back:
+
+```python
+for base in TabulationReader.query("counts.tsv.gz", "chr1", 20, 24):
+    print(base.pos, base.depth, base.alts)
+```
+
+## Development and Testing
+
+See the [contributing guide](https://github.com/clintval/streampile/blob/main/CONTRIBUTING.md) for more information.
+
+The streaming design follows the `StreamingPileupBuilder` of [fgbio](https://github.com/fulcrumgenomics/fgbio); see [NOTICE](https://github.com/clintval/streampile/blob/main/NOTICE).