samplesheet-parser 1.3.0__tar.gz → 2.0.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/.zenodo.json +1 -1
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/CHANGELOG.md +61 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/CITATION.cff +2 -2
- samplesheet_parser-2.0.0/Makefile +81 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/PKG-INFO +31 -7
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/README.md +26 -4
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/parsing.md +31 -2
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/index.md +1 -1
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/installation.md +2 -2
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/convert/environment.yml +1 -1
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/convert/main.nf +4 -14
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/convert/meta.yml +31 -15
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/convert/tests/main.nf.test +10 -10
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/diff/environment.yml +1 -1
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/diff/main.nf +34 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/diff/meta.yml +28 -13
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/diff/tests/main.nf.test +10 -10
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/diff/tests/main.nf.test.snap +80 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/filter/environment.yml +1 -1
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/filter/main.nf +5 -15
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/filter/meta.yml +32 -15
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/filter/tests/main.nf.test +5 -5
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/info/environment.yml +1 -1
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/info/main.nf +34 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/info/meta.yml +28 -13
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/info/tests/main.nf.test +7 -7
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/info/tests/main.nf.test.snap +80 -0
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/merge/environment.yml +6 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/merge/main.nf +5 -15
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/merge/meta.yml +32 -15
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/merge/tests/main.nf.test +10 -10
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/split/environment.yml +6 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/split/main.nf +5 -15
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/split/meta.yml +32 -15
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/split/tests/main.nf.test +7 -7
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/validate/environment.yml +6 -0
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/validate/main.nf +34 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/validate/meta.yml +28 -13
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/validate/tests/main.nf.test +7 -7
- samplesheet_parser-2.0.0/modules/nf-core/samplesheetparser/validate/tests/main.nf.test.snap +80 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/pyproject.toml +15 -8
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/__init__.py +4 -1
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/converter.py +8 -3
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/diff.py +44 -43
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/enums.py +19 -15
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/factory.py +75 -11
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/filter.py +3 -2
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/instruments.py +35 -4
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/merger.py +5 -4
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/parsers/v1.py +89 -93
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/parsers/v2.py +178 -137
- samplesheet_parser-2.0.0/samplesheet_parser/protocol.py +102 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/splitter.py +3 -2
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/validators.py +35 -28
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/writer.py +6 -4
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_parsers/test_v1.py +16 -19
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_parsers/test_v2.py +20 -20
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_validators/test_hamming.py +155 -70
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/convert/tests/tags.yml +0 -4
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/diff/main.nf +0 -45
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/diff/tests/tags.yml +0 -4
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/filter/tests/tags.yml +0 -4
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/info/main.nf +0 -45
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/info/tests/tags.yml +0 -4
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/merge/environment.yml +0 -6
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/merge/tests/tags.yml +0 -4
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/split/environment.yml +0 -6
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/split/tests/tags.yml +0 -4
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/validate/environment.yml +0 -6
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/validate/main.nf +0 -45
- samplesheet_parser-1.3.0/modules/nf-core/samplesheetparser/validate/tests/tags.yml +0 -4
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/.github/workflows/ci.yml +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/.github/workflows/copilot-instructions.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/.gitignore +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/.pre-commit-config.yaml +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/.readthedocs.yaml +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/CONTRIBUTING.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/LICENSE +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/api.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/changelog.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/ci.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/cli.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/contributing.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/examples.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/conversion.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/diffing.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/filtering.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/index_utils.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/merging.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/quickstart.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/splitting.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/validation.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/guide/writing.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/docs/requirements.txt +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/demo_converter.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/demo_diff.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/demo_filter.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/demo_index_utils.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/demo_merger.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/demo_splitter.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/demo_writer.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/parse_examples.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/ProjectAlpha_SampleSheet.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/ProjectBeta_SampleSheet.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/ProjectDelta_SampleSheet_collision.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/ProjectGamma_SampleSheet.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/README.md +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/combined_clean.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/combined_collision_forced.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/combined_mixed_formats.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v1_dual_index.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v1_multi_lane.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v1_single_index.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v1_with_lab_qc_settings.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v1_with_manifests.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v2_nextseq_single_index.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v2_novaseq_x_dual_index.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v2_with_cloud_settings.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v2_with_index_umi.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v2_with_pipeline_settings.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/examples/sample_sheets/v2_with_read_umi.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/images/samplesheet_parser_arch_v03.png +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/images/samplesheet_parser_overview.png +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/mkdocs.yml +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/modules/nf-core/samplesheetparser/filter/tests/nextflow.config +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/recipes/meta.yaml +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/cli.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/index_utils.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/parsers/__init__.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/samplesheet_parser/py.typed +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/scripts/demo_converter.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/scripts/demo_diff.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/scripts/demo_writer.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/__init__.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/conftest.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/fixtures/SampleSheet_v1_dual_index.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/fixtures/SampleSheet_v2_dual_index.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/fixtures/SampleSheet_v2_modified.csv +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_cli.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_converter.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_diff.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_factory.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_filter.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_index_utils.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_instruments.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_merger.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_parsers/__init__.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_splitter.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_validators/__init__.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_validators/test_validators.py +0 -0
- {samplesheet_parser-1.3.0 → samplesheet_parser-2.0.0}/tests/test_writer.py +0 -0
|
@@ -8,6 +8,67 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
|
|
|
8
8
|
|
|
9
9
|
## [Unreleased]
|
|
10
10
|
|
|
11
|
+
_No unreleased changes._
|
|
12
|
+
|
|
13
|
+
---
|
|
14
|
+
|
|
15
|
+
## [2.0.0] - 2026-06-06
|
|
16
|
+
|
|
17
|
+
### Breaking changes
|
|
18
|
+
|
|
19
|
+
- **Python 3.10+ required** (was 3.12+). The `str, Enum` mixin replaces
|
|
20
|
+
`StrEnum` throughout `enums.py` and `instruments.py`, giving identical
|
|
21
|
+
behaviour on all supported versions.
|
|
22
|
+
- **`loguru` dependency removed.** The library now uses `logging.getLogger(__name__)`
|
|
23
|
+
in every module. Host applications retain full control of log configuration.
|
|
24
|
+
If you previously relied on `loguru` sinks seeing library log output, wire up
|
|
25
|
+
a standard `logging` handler instead.
|
|
26
|
+
- **`clean()` now returns the cleaned content as a `str` and never writes to
|
|
27
|
+
disk.** Previously `SampleSheetV1.clean()` and `SampleSheetV2.clean()` wrote
|
|
28
|
+
to the source file and created a `.backup` alongside it. The source file is
|
|
29
|
+
now untouched; the cleaned string is passed in-memory to `read()`. Callers
|
|
30
|
+
that relied on the side-effect (file written, `.backup` created) must adapt.
|
|
31
|
+
- **`samples()` deduplication key changed from `sample_id` to `(sample_id, lane)`.**
|
|
32
|
+
Multi-lane sheets where the same sample appears in multiple lanes now return
|
|
33
|
+
one record *per lane* rather than silently dropping all but the first row.
|
|
34
|
+
- **`SampleSheetFactory.create_parser()` return type is now `SampleSheetParser`**
|
|
35
|
+
(the new Protocol) rather than `SampleSheetV1 | SampleSheetV2`. Both concrete
|
|
36
|
+
types structurally satisfy the Protocol; the change only affects code with
|
|
37
|
+
explicit type annotations on the return value.
|
|
38
|
+
- **`_hamming_distance` renamed to `hamming_distance`** (underscore removed).
|
|
39
|
+
Import path: `from samplesheet_parser import hamming_distance` or
|
|
40
|
+
`from samplesheet_parser.validators import hamming_distance`.
|
|
41
|
+
|
|
42
|
+
### Fixed
|
|
43
|
+
|
|
44
|
+
- **V2 `parse_data()` no longer silently drops keys with empty-string values.**
|
|
45
|
+
The `{k: v for k, v in ... if v}` filter was removing keys whose value was
|
|
46
|
+
`""`, making V2 record dicts structurally inconsistent with V1. All keys are
|
|
47
|
+
now preserved; values are stripped of surrounding whitespace only.
|
|
48
|
+
- **`converter.to_v1()` bare `assert` replaced with explicit `TypeError`.**
|
|
49
|
+
`assert isinstance(sheet, SampleSheetV2)` is stripped by `python -O`; the
|
|
50
|
+
guard now raises `TypeError` unconditionally when the wrong type is passed.
|
|
51
|
+
|
|
52
|
+
### Added
|
|
53
|
+
|
|
54
|
+
- **`SampleSheetParser` Protocol** (`samplesheet_parser.protocol`) — a
|
|
55
|
+
`runtime_checkable` structural protocol satisfied by both `SampleSheetV1`
|
|
56
|
+
and `SampleSheetV2`. Third-party parsers that implement the same interface
|
|
57
|
+
can be registered with the factory without inheriting from any base class.
|
|
58
|
+
`isinstance(sheet, SampleSheetParser)` works at runtime.
|
|
59
|
+
- **`SampleSheetFactory.register(detector, parser_class, version)`** — class
|
|
60
|
+
method that registers a custom format detector. Registered detectors are
|
|
61
|
+
tried before the built-in V1/V2 detection in LIFO order. Useful for
|
|
62
|
+
supporting hypothetical V3 formats or vendor-specific variants.
|
|
63
|
+
- **`SampleSheetFactory.clear_registry()`** — removes all custom registrations.
|
|
64
|
+
Intended for use in tests to prevent cross-test contamination.
|
|
65
|
+
- **`detect_workflow()` accepts `extra_a` / `extra_b` keyword arguments** —
|
|
66
|
+
caller-supplied `frozenset[str]` of instrument names checked before the
|
|
67
|
+
built-in tables. Allows narrowing workflow classification without subclassing.
|
|
68
|
+
- **`hamming_distance` is now a public export** — available as
|
|
69
|
+
`from samplesheet_parser import hamming_distance` and documented in the API
|
|
70
|
+
reference.
|
|
71
|
+
|
|
11
72
|
---
|
|
12
73
|
|
|
13
74
|
## [1.3.0] - 2026-05-20
|
|
@@ -8,8 +8,8 @@ abstract: >
|
|
|
8
8
|
Provides format auto-detection, bidirectional V1/V2 conversion,
|
|
9
9
|
structural and index validation, sheet diffing, and cross-project
|
|
10
10
|
merging with Hamming-distance collision detection.
|
|
11
|
-
version:
|
|
12
|
-
date-released: 2026-
|
|
11
|
+
version: 2.0.0
|
|
12
|
+
date-released: 2026-06-06
|
|
13
13
|
license: Apache-2.0
|
|
14
14
|
url: "https://github.com/chaitanyakasaraneni/samplesheet-parser"
|
|
15
15
|
repository-code: "https://github.com/chaitanyakasaraneni/samplesheet-parser"
|
|
@@ -0,0 +1,81 @@
|
|
|
1
|
+
# Makefile for samplesheet-parser
|
|
2
|
+
# Keeps the version in sync across pyproject.toml, CITATION.cff, and .zenodo.json.
|
|
3
|
+
# Portable to GNU Make 3.81 (macOS default) — recipes are single POSIX-sh lines.
|
|
4
|
+
|
|
5
|
+
PKG := samplesheet_parser
|
|
6
|
+
PYPROJECT := pyproject.toml
|
|
7
|
+
CITATION := CITATION.cff
|
|
8
|
+
ZENODO := .zenodo.json
|
|
9
|
+
CHANGELOG := CHANGELOG.md
|
|
10
|
+
|
|
11
|
+
CURRENT_VERSION := $(shell sed -n -E 's/^version = "([0-9]+\.[0-9]+\.[0-9]+)".*/\1/p' $(PYPROJECT) | head -1)
|
|
12
|
+
|
|
13
|
+
.DEFAULT_GOAL := help
|
|
14
|
+
.PHONY: help version major minor patch tag test lint build clean
|
|
15
|
+
|
|
16
|
+
help:
|
|
17
|
+
@echo "samplesheet-parser — current version: $(CURRENT_VERSION)"
|
|
18
|
+
@echo ""
|
|
19
|
+
@echo "Version bumping (syncs $(PYPROJECT), $(CITATION), $(ZENODO); rolls $(CHANGELOG)):"
|
|
20
|
+
@echo " make patch patch bump (x.y.Z)"
|
|
21
|
+
@echo " make minor minor bump (x.Y.0)"
|
|
22
|
+
@echo " make major major bump (X.0.0)"
|
|
23
|
+
@echo ""
|
|
24
|
+
@echo "Other targets:"
|
|
25
|
+
@echo " make version print the current version"
|
|
26
|
+
@echo " make tag create git tag v$(CURRENT_VERSION)"
|
|
27
|
+
@echo " make test run pytest"
|
|
28
|
+
@echo " make lint run ruff"
|
|
29
|
+
@echo " make build build sdist + wheel"
|
|
30
|
+
@echo " make clean remove build artifacts"
|
|
31
|
+
|
|
32
|
+
version:
|
|
33
|
+
@echo $(CURRENT_VERSION)
|
|
34
|
+
|
|
35
|
+
patch minor major:
|
|
36
|
+
@$(MAKE) --no-print-directory _bump PART=$@
|
|
37
|
+
|
|
38
|
+
# internal: bump the version part named by PART across all files (one shell line)
|
|
39
|
+
_bump:
|
|
40
|
+
@cur="$(CURRENT_VERSION)"; \
|
|
41
|
+
[ -n "$$cur" ] || { echo "error: could not read version from $(PYPROJECT)"; exit 1; }; \
|
|
42
|
+
MA=$${cur%%.*}; rest=$${cur#*.}; MI=$${rest%%.*}; PA=$${rest##*.}; \
|
|
43
|
+
case "$(PART)" in \
|
|
44
|
+
major) MA=$$((MA + 1)); MI=0; PA=0 ;; \
|
|
45
|
+
minor) MI=$$((MI + 1)); PA=0 ;; \
|
|
46
|
+
patch) PA=$$((PA + 1)) ;; \
|
|
47
|
+
*) echo "error: unknown bump part '$(PART)'"; exit 1 ;; \
|
|
48
|
+
esac; \
|
|
49
|
+
new="$$MA.$$MI.$$PA"; today="$$(date +%F)"; \
|
|
50
|
+
sed -E 's/^version = "[0-9]+\.[0-9]+\.[0-9]+"/version = "'"$$new"'"/' $(PYPROJECT) > $(PYPROJECT).tmp && mv $(PYPROJECT).tmp $(PYPROJECT); \
|
|
51
|
+
sed -E -e 's/^version: .*/version: '"$$new"'/' -e 's/^date-released: .*/date-released: '"$$today"'/' $(CITATION) > $(CITATION).tmp && mv $(CITATION).tmp $(CITATION); \
|
|
52
|
+
sed -E 's/("version": )"[0-9]+\.[0-9]+\.[0-9]+"/\1"'"$$new"'"/' $(ZENODO) > $(ZENODO).tmp && mv $(ZENODO).tmp $(ZENODO); \
|
|
53
|
+
cl_note=""; \
|
|
54
|
+
if [ -f $(CHANGELOG) ] && grep -q '^## \[Unreleased\]' $(CHANGELOG); then \
|
|
55
|
+
awk -v v="$$new" -v d="$$today" '!done && /^## \[Unreleased\]/ {print "## [Unreleased]"; print ""; print "_No unreleased changes._"; print ""; print "## [" v "] - " d; done=1; next} {print}' $(CHANGELOG) > $(CHANGELOG).tmp && mv $(CHANGELOG).tmp $(CHANGELOG); \
|
|
56
|
+
cl_note=", $(CHANGELOG)"; \
|
|
57
|
+
else \
|
|
58
|
+
cl_note=" (warning: no [Unreleased] section in $(CHANGELOG) — not rolled)"; \
|
|
59
|
+
fi; \
|
|
60
|
+
echo "Bumped $$cur -> $$new (date-released: $$today)"; \
|
|
61
|
+
echo " updated: $(PYPROJECT), $(CITATION), $(ZENODO)$$cl_note"; \
|
|
62
|
+
echo "Next: review $(CHANGELOG), then: git commit -am \"release v$$new\" && make tag && git push --follow-tags"
|
|
63
|
+
|
|
64
|
+
tag:
|
|
65
|
+
@v="$(CURRENT_VERSION)"; \
|
|
66
|
+
if git rev-parse "v$$v" >/dev/null 2>&1; then echo "tag v$$v already exists"; exit 1; fi; \
|
|
67
|
+
git tag -a "v$$v" -m "Release v$$v"; \
|
|
68
|
+
echo "created annotated tag v$$v (push with: git push --follow-tags)"
|
|
69
|
+
|
|
70
|
+
test:
|
|
71
|
+
@pytest
|
|
72
|
+
|
|
73
|
+
lint:
|
|
74
|
+
@ruff check $(PKG)/
|
|
75
|
+
|
|
76
|
+
build:
|
|
77
|
+
@python3 -m hatchling build
|
|
78
|
+
|
|
79
|
+
clean:
|
|
80
|
+
@rm -rf dist build *.egg-info
|
|
81
|
+
@find . -type d -name __pycache__ -prune -exec rm -rf {} +
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: samplesheet-parser
|
|
3
|
-
Version:
|
|
3
|
+
Version: 2.0.0
|
|
4
4
|
Summary: Format-agnostic parser for Illumina SampleSheet.csv files — supports IEM V1 and BCLConvert V2
|
|
5
5
|
Project-URL: Homepage, https://github.com/chaitanyakasaraneni/samplesheet-parser
|
|
6
6
|
Project-URL: Documentation, https://illumina-samplesheet.readthedocs.io
|
|
@@ -33,11 +33,13 @@ Classifier: Intended Audience :: Developers
|
|
|
33
33
|
Classifier: Intended Audience :: Science/Research
|
|
34
34
|
Classifier: License :: OSI Approved :: Apache Software License
|
|
35
35
|
Classifier: Programming Language :: Python :: 3
|
|
36
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
37
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
36
38
|
Classifier: Programming Language :: Python :: 3.12
|
|
39
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
37
40
|
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
38
41
|
Classifier: Typing :: Typed
|
|
39
|
-
Requires-Python: >=3.
|
|
40
|
-
Requires-Dist: loguru>=0.7
|
|
42
|
+
Requires-Python: >=3.10
|
|
41
43
|
Provides-Extra: cli
|
|
42
44
|
Requires-Dist: typer>=0.12; extra == 'cli'
|
|
43
45
|
Provides-Extra: dev
|
|
@@ -59,7 +61,7 @@ Description-Content-Type: text/markdown
|
|
|
59
61
|
Supports both the classic IEM V1 format (bcl2fastq era) and the modern BCLConvert V2 format (NovaSeq X series) — with automatic format detection, bidirectional conversion, index validation, Hamming distance checking, diff comparison, multi-sheet merging, programmatic sheet creation, and a full-featured CLI.
|
|
60
62
|
|
|
61
63
|
[](https://pypi.org/project/samplesheet-parser/)
|
|
62
|
-
[](https://www.python.org/downloads/)
|
|
63
65
|
[](https://opensource.org/licenses/Apache-2.0)
|
|
64
66
|
[](http://bioconda.github.io/recipes/samplesheet-parser/README.html)
|
|
65
67
|
|
|
@@ -94,7 +96,7 @@ pip install samplesheet-parser
|
|
|
94
96
|
pip install "samplesheet-parser[cli]"
|
|
95
97
|
```
|
|
96
98
|
|
|
97
|
-
Requires Python 3.
|
|
99
|
+
Requires Python 3.10+. No mandatory runtime dependencies.
|
|
98
100
|
|
|
99
101
|
---
|
|
100
102
|
|
|
@@ -464,10 +466,21 @@ sheet.get_read_structure() # → ReadStructure dataclass
|
|
|
464
466
|
|
|
465
467
|
| Method / attribute | Returns | Description |
|
|
466
468
|
|---|---|---|
|
|
467
|
-
| `create_parser(path, *, clean, experiment_id, parse)` | `
|
|
469
|
+
| `create_parser(path, *, clean, experiment_id, parse)` | `SampleSheetParser` | Auto-detect format and return appropriate parser |
|
|
470
|
+
| `register(detector, parser_class, version)` | `None` | Register a custom format detector (class method, LIFO) |
|
|
471
|
+
| `clear_registry()` | `None` | Remove all custom registrations (class method) |
|
|
468
472
|
| `get_umi_length()` | `int` | UMI length from the current parser |
|
|
469
473
|
| `.version` | `SampleSheetVersion` | Detected format version |
|
|
470
474
|
|
|
475
|
+
### `SampleSheetParser` (Protocol)
|
|
476
|
+
|
|
477
|
+
A `runtime_checkable` structural protocol satisfied by both `SampleSheetV1` and `SampleSheetV2`. Third-party parsers that implement the same methods and attributes can be registered with `SampleSheetFactory.register()` without inheriting from any base class.
|
|
478
|
+
|
|
479
|
+
```python
|
|
480
|
+
from samplesheet_parser import SampleSheetParser, SampleSheetV1
|
|
481
|
+
assert isinstance(SampleSheetV1("sheet.csv"), SampleSheetParser)
|
|
482
|
+
```
|
|
483
|
+
|
|
471
484
|
### `SampleSheetV1` / `SampleSheetV2` (shared interface)
|
|
472
485
|
|
|
473
486
|
| Method / attribute | Returns | Description |
|
|
@@ -498,6 +511,17 @@ sheet.get_read_structure() # → ReadStructure dataclass
|
|
|
498
511
|
| `validate(sheet)` | `ValidationResult` | Run all checks; returns structured result |
|
|
499
512
|
| `_check_index_distances(samples, result, min_distance=3)` | `None` | Hamming distance check (callable directly for custom thresholds) |
|
|
500
513
|
|
|
514
|
+
### `hamming_distance`
|
|
515
|
+
|
|
516
|
+
```python
|
|
517
|
+
from samplesheet_parser import hamming_distance
|
|
518
|
+
|
|
519
|
+
hamming_distance("ATTACTCG", "ATTACTCA") # → 1
|
|
520
|
+
hamming_distance("ATTACTCG", "GCTAGCTA") # → 6
|
|
521
|
+
```
|
|
522
|
+
|
|
523
|
+
Public helper for computing the Hamming distance between two index sequences. Sequences of unequal length are compared up to the shorter length.
|
|
524
|
+
|
|
501
525
|
### `SampleSheetWriter`
|
|
502
526
|
|
|
503
527
|
| Method / attribute | Returns | Description |
|
|
@@ -593,7 +617,7 @@ jobs:
|
|
|
593
617
|
|
|
594
618
|
- uses: actions/setup-python@v5
|
|
595
619
|
with:
|
|
596
|
-
python-version: '3.
|
|
620
|
+
python-version: '3.10'
|
|
597
621
|
|
|
598
622
|
- run: pip install "samplesheet-parser[cli]"
|
|
599
623
|
|
|
@@ -5,7 +5,7 @@
|
|
|
5
5
|
Supports both the classic IEM V1 format (bcl2fastq era) and the modern BCLConvert V2 format (NovaSeq X series) — with automatic format detection, bidirectional conversion, index validation, Hamming distance checking, diff comparison, multi-sheet merging, programmatic sheet creation, and a full-featured CLI.
|
|
6
6
|
|
|
7
7
|
[](https://pypi.org/project/samplesheet-parser/)
|
|
8
|
-
[](https://www.python.org/downloads/)
|
|
9
9
|
[](https://opensource.org/licenses/Apache-2.0)
|
|
10
10
|
[](http://bioconda.github.io/recipes/samplesheet-parser/README.html)
|
|
11
11
|
|
|
@@ -40,7 +40,7 @@ pip install samplesheet-parser
|
|
|
40
40
|
pip install "samplesheet-parser[cli]"
|
|
41
41
|
```
|
|
42
42
|
|
|
43
|
-
Requires Python 3.
|
|
43
|
+
Requires Python 3.10+. No mandatory runtime dependencies.
|
|
44
44
|
|
|
45
45
|
---
|
|
46
46
|
|
|
@@ -410,10 +410,21 @@ sheet.get_read_structure() # → ReadStructure dataclass
|
|
|
410
410
|
|
|
411
411
|
| Method / attribute | Returns | Description |
|
|
412
412
|
|---|---|---|
|
|
413
|
-
| `create_parser(path, *, clean, experiment_id, parse)` | `
|
|
413
|
+
| `create_parser(path, *, clean, experiment_id, parse)` | `SampleSheetParser` | Auto-detect format and return appropriate parser |
|
|
414
|
+
| `register(detector, parser_class, version)` | `None` | Register a custom format detector (class method, LIFO) |
|
|
415
|
+
| `clear_registry()` | `None` | Remove all custom registrations (class method) |
|
|
414
416
|
| `get_umi_length()` | `int` | UMI length from the current parser |
|
|
415
417
|
| `.version` | `SampleSheetVersion` | Detected format version |
|
|
416
418
|
|
|
419
|
+
### `SampleSheetParser` (Protocol)
|
|
420
|
+
|
|
421
|
+
A `runtime_checkable` structural protocol satisfied by both `SampleSheetV1` and `SampleSheetV2`. Third-party parsers that implement the same methods and attributes can be registered with `SampleSheetFactory.register()` without inheriting from any base class.
|
|
422
|
+
|
|
423
|
+
```python
|
|
424
|
+
from samplesheet_parser import SampleSheetParser, SampleSheetV1
|
|
425
|
+
assert isinstance(SampleSheetV1("sheet.csv"), SampleSheetParser)
|
|
426
|
+
```
|
|
427
|
+
|
|
417
428
|
### `SampleSheetV1` / `SampleSheetV2` (shared interface)
|
|
418
429
|
|
|
419
430
|
| Method / attribute | Returns | Description |
|
|
@@ -444,6 +455,17 @@ sheet.get_read_structure() # → ReadStructure dataclass
|
|
|
444
455
|
| `validate(sheet)` | `ValidationResult` | Run all checks; returns structured result |
|
|
445
456
|
| `_check_index_distances(samples, result, min_distance=3)` | `None` | Hamming distance check (callable directly for custom thresholds) |
|
|
446
457
|
|
|
458
|
+
### `hamming_distance`
|
|
459
|
+
|
|
460
|
+
```python
|
|
461
|
+
from samplesheet_parser import hamming_distance
|
|
462
|
+
|
|
463
|
+
hamming_distance("ATTACTCG", "ATTACTCA") # → 1
|
|
464
|
+
hamming_distance("ATTACTCG", "GCTAGCTA") # → 6
|
|
465
|
+
```
|
|
466
|
+
|
|
467
|
+
Public helper for computing the Hamming distance between two index sequences. Sequences of unequal length are compared up to the shorter length.
|
|
468
|
+
|
|
447
469
|
### `SampleSheetWriter`
|
|
448
470
|
|
|
449
471
|
| Method / attribute | Returns | Description |
|
|
@@ -539,7 +561,7 @@ jobs:
|
|
|
539
561
|
|
|
540
562
|
- uses: actions/setup-python@v5
|
|
541
563
|
with:
|
|
542
|
-
python-version: '3.
|
|
564
|
+
python-version: '3.10'
|
|
543
565
|
|
|
544
566
|
- run: pip install "samplesheet-parser[cli]"
|
|
545
567
|
|
|
@@ -73,12 +73,41 @@ print(rs.read_structure)
|
|
|
73
73
|
|
|
74
74
|
## Shared interface
|
|
75
75
|
|
|
76
|
-
Both `SampleSheetV1` and `SampleSheetV2` expose:
|
|
76
|
+
Both `SampleSheetV1` and `SampleSheetV2` satisfy the `SampleSheetParser` Protocol and expose:
|
|
77
77
|
|
|
78
78
|
| Method / attribute | Returns | Description |
|
|
79
79
|
|---|---|---|
|
|
80
80
|
| `parse(do_clean=True)` | `None` | Parse all sections |
|
|
81
|
-
| `
|
|
81
|
+
| `clean()` | `str` | Return cleaned content as a string — source file is **never** modified |
|
|
82
|
+
| `samples()` | `list[dict]` | One record per unique `(sample_id, lane)` pair |
|
|
82
83
|
| `index_type()` | `str` | `"dual"`, `"single"`, or `"none"` |
|
|
84
|
+
| `parse_custom_section(name, *, required=False)` | `dict[str, str]` | Parse any non-standard section as key/value pairs |
|
|
83
85
|
| `.adapters` | `list[str]` | Adapter sequences |
|
|
84
86
|
| `.experiment_name` | `str \| None` | Run/experiment name |
|
|
87
|
+
|
|
88
|
+
### In-memory cleaning
|
|
89
|
+
|
|
90
|
+
`parse(do_clean=True)` (the default) cleans the file content in memory before parsing — stripping BOM, quotes, stray whitespace, and normalising V2 section names. **The source file on disk is never modified and no `.backup` files are created.**
|
|
91
|
+
|
|
92
|
+
```python
|
|
93
|
+
# Access the cleaned content directly
|
|
94
|
+
cleaned = sheet.clean() # returns str, no file I/O side-effects
|
|
95
|
+
|
|
96
|
+
# Parse with cleaning (default)
|
|
97
|
+
sheet.parse()
|
|
98
|
+
|
|
99
|
+
# Parse without cleaning (raw file)
|
|
100
|
+
sheet.parse(do_clean=False)
|
|
101
|
+
```
|
|
102
|
+
|
|
103
|
+
### Multi-lane deduplication
|
|
104
|
+
|
|
105
|
+
`samples()` deduplicates by `(sample_id, lane)` pair, not by `sample_id` alone. A sample appearing across multiple lanes produces one record per lane.
|
|
106
|
+
|
|
107
|
+
```python
|
|
108
|
+
sheet.parse()
|
|
109
|
+
samples = sheet.samples()
|
|
110
|
+
# Multi-lane sheet with Sample1 in lanes 1 and 2 → two records:
|
|
111
|
+
# [{"sample_id": "Sample1", "lane": "1", ...},
|
|
112
|
+
# {"sample_id": "Sample1", "lane": "2", ...}]
|
|
113
|
+
```
|
|
@@ -5,7 +5,7 @@
|
|
|
5
5
|
Supports both the classic IEM V1 format (bcl2fastq era) and the modern BCLConvert V2 format (NovaSeq X series) — with automatic format detection, bidirectional conversion, index validation, Hamming distance checking, diff comparison, multi-sheet merging, splitting, filtering, programmatic sheet creation, and a full-featured CLI.
|
|
6
6
|
|
|
7
7
|
[](https://pypi.org/project/samplesheet-parser/)
|
|
8
|
-
[](https://www.python.org/downloads/)
|
|
9
9
|
[](https://opensource.org/licenses/Apache-2.0)
|
|
10
10
|
[](https://github.com/chaitanyakasaraneni/samplesheet-parser/actions)
|
|
11
11
|
[](https://codecov.io/gh/chaitanyakasaraneni/samplesheet-parser)
|
|
@@ -3,9 +3,9 @@ process SAMPLESHEETPARSER_CONVERT {
|
|
|
3
3
|
label 'process_single'
|
|
4
4
|
|
|
5
5
|
conda "${moduleDir}/environment.yml"
|
|
6
|
-
container "${ workflow.containerEngine
|
|
7
|
-
'https://depot.galaxyproject.org/singularity/samplesheet-parser:1.
|
|
8
|
-
'biocontainers/samplesheet-parser:1.
|
|
6
|
+
container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
|
|
7
|
+
'https://depot.galaxyproject.org/singularity/samplesheet-parser:1.3.0--pyhdfd78af_0' :
|
|
8
|
+
'quay.io/biocontainers/samplesheet-parser:1.3.0--pyhdfd78af_0' }"
|
|
9
9
|
|
|
10
10
|
input:
|
|
11
11
|
tuple val(meta), path(samplesheet)
|
|
@@ -13,7 +13,7 @@ process SAMPLESHEETPARSER_CONVERT {
|
|
|
13
13
|
|
|
14
14
|
output:
|
|
15
15
|
tuple val(meta), path("*.converted.csv"), emit: samplesheet
|
|
16
|
-
|
|
16
|
+
tuple val("${task.process}"), val('samplesheet-parser'), eval("samplesheet --version | sed 's/samplesheet-parser //'"), topic: versions, emit: versions_samplesheetparser
|
|
17
17
|
|
|
18
18
|
when:
|
|
19
19
|
task.ext.when == null || task.ext.when
|
|
@@ -30,21 +30,11 @@ process SAMPLESHEETPARSER_CONVERT {
|
|
|
30
30
|
--output ${prefix}.converted.csv \\
|
|
31
31
|
${args} \\
|
|
32
32
|
${samplesheet}
|
|
33
|
-
|
|
34
|
-
cat <<-END_VERSIONS > versions.yml
|
|
35
|
-
"${task.process}":
|
|
36
|
-
samplesheet-parser: \$(samplesheet --version | sed 's/samplesheet-parser //')
|
|
37
|
-
END_VERSIONS
|
|
38
33
|
"""
|
|
39
34
|
|
|
40
35
|
stub:
|
|
41
36
|
def prefix = task.ext.prefix ?: "${meta.id}"
|
|
42
37
|
"""
|
|
43
38
|
touch ${prefix}.converted.csv
|
|
44
|
-
|
|
45
|
-
cat <<-END_VERSIONS > versions.yml
|
|
46
|
-
"${task.process}":
|
|
47
|
-
samplesheet-parser: \$(samplesheet --version | sed 's/samplesheet-parser //')
|
|
48
|
-
END_VERSIONS
|
|
49
39
|
"""
|
|
50
40
|
}
|
|
@@ -2,8 +2,9 @@ name: samplesheetparser_convert
|
|
|
2
2
|
description: |
|
|
3
3
|
Convert an Illumina SampleSheet.csv between IEM V1 (bcl2fastq) and
|
|
4
4
|
BCLConvert V2 formats. Format of the input is auto-detected.
|
|
5
|
-
V2 → V1 conversion is lossy: V2-only fields (OverrideCycles,
|
|
6
|
-
|
|
5
|
+
V2 → V1 conversion is lossy: V2-only fields (OverrideCycles, etc.)
|
|
6
|
+
are dropped with a warning. InstrumentPlatform / InstrumentType is
|
|
7
|
+
preserved across both directions.
|
|
7
8
|
keywords:
|
|
8
9
|
- illumina
|
|
9
10
|
- samplesheet
|
|
@@ -11,10 +12,9 @@ keywords:
|
|
|
11
12
|
- bclconvert
|
|
12
13
|
- bcl2fastq
|
|
13
14
|
- genomics
|
|
14
|
-
|
|
15
15
|
tools:
|
|
16
16
|
- samplesheet-parser:
|
|
17
|
-
description:
|
|
17
|
+
description: |
|
|
18
18
|
Format-agnostic parser for Illumina SampleSheet.csv files.
|
|
19
19
|
Supports IEM V1 (bcl2fastq) and BCLConvert V2 with auto-detection,
|
|
20
20
|
bidirectional conversion, index validation, and Hamming distance checking.
|
|
@@ -22,9 +22,9 @@ tools:
|
|
|
22
22
|
documentation: https://illumina-samplesheet.readthedocs.io
|
|
23
23
|
tool_dev_url: https://github.com/chaitanyakasaraneni/samplesheet-parser
|
|
24
24
|
doi: "10.5281/zenodo.18989694"
|
|
25
|
-
licence:
|
|
25
|
+
licence:
|
|
26
|
+
- "Apache-2.0"
|
|
26
27
|
identifier: biotools:samplesheet-parser
|
|
27
|
-
|
|
28
28
|
input:
|
|
29
29
|
- - meta:
|
|
30
30
|
type: map
|
|
@@ -40,22 +40,38 @@ input:
|
|
|
40
40
|
- - target_version:
|
|
41
41
|
type: string
|
|
42
42
|
description: Target format — either 'v1' or 'v2'
|
|
43
|
-
|
|
44
43
|
output:
|
|
45
|
-
|
|
46
|
-
|
|
44
|
+
samplesheet:
|
|
45
|
+
- - meta:
|
|
47
46
|
type: map
|
|
48
47
|
description: Groovy Map containing sample information
|
|
49
48
|
- "*.converted.csv":
|
|
50
49
|
type: file
|
|
51
50
|
description: Converted SampleSheet.csv in the requested format
|
|
52
51
|
pattern: "*.converted.csv"
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
52
|
+
ontologies:
|
|
53
|
+
- edam: "http://edamontology.org/format_3752"
|
|
54
|
+
versions_samplesheetparser:
|
|
55
|
+
- - ${task.process}:
|
|
56
|
+
type: string
|
|
57
|
+
description: The name of the process
|
|
58
|
+
- samplesheet-parser:
|
|
59
|
+
type: string
|
|
60
|
+
description: The name of the tool
|
|
61
|
+
- samplesheet --version | sed 's/samplesheet-parser //':
|
|
62
|
+
type: eval
|
|
63
|
+
description: The expression to obtain the version of the tool
|
|
64
|
+
topics:
|
|
65
|
+
versions:
|
|
66
|
+
- - ${task.process}:
|
|
67
|
+
type: string
|
|
68
|
+
description: The name of the process
|
|
69
|
+
- samplesheet-parser:
|
|
70
|
+
type: string
|
|
71
|
+
description: The name of the tool
|
|
72
|
+
- samplesheet --version | sed 's/samplesheet-parser //':
|
|
73
|
+
type: eval
|
|
74
|
+
description: The expression to obtain the version of the tool
|
|
59
75
|
authors:
|
|
60
76
|
- "@chaitanyakasaraneni"
|
|
61
77
|
maintainers:
|
|
@@ -5,18 +5,18 @@ nextflow_process {
|
|
|
5
5
|
process "SAMPLESHEETPARSER_CONVERT"
|
|
6
6
|
|
|
7
7
|
tag "samplesheetparser"
|
|
8
|
-
tag "
|
|
8
|
+
tag "samplesheetparser/convert"
|
|
9
9
|
tag "modules"
|
|
10
10
|
tag "modules_nfcore"
|
|
11
11
|
|
|
12
|
-
test("V1
|
|
12
|
+
test("V1 to V2 conversion") {
|
|
13
13
|
|
|
14
14
|
when {
|
|
15
15
|
process {
|
|
16
16
|
"""
|
|
17
17
|
input[0] = [
|
|
18
18
|
[ id: 'test_v1_to_v2' ],
|
|
19
|
-
file(params.modules_testdata_base_path + 'genomics/
|
|
19
|
+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bcl/flowcell_samplesheet.v1.csv', checkIfExists: true)
|
|
20
20
|
]
|
|
21
21
|
input[1] = 'v2'
|
|
22
22
|
"""
|
|
@@ -26,19 +26,19 @@ nextflow_process {
|
|
|
26
26
|
then {
|
|
27
27
|
assertAll(
|
|
28
28
|
{ assert process.success },
|
|
29
|
-
{ assert snapshot(process.out).match() }
|
|
29
|
+
{ assert snapshot(sanitizeOutput(process.out)).match() }
|
|
30
30
|
)
|
|
31
31
|
}
|
|
32
32
|
}
|
|
33
33
|
|
|
34
|
-
test("V2
|
|
34
|
+
test("V2 to V1 conversion") {
|
|
35
35
|
|
|
36
36
|
when {
|
|
37
37
|
process {
|
|
38
38
|
"""
|
|
39
39
|
input[0] = [
|
|
40
40
|
[ id: 'test_v2_to_v1' ],
|
|
41
|
-
file(params.modules_testdata_base_path + 'genomics/
|
|
41
|
+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bcl/flowcell_samplesheet.v2.csv', checkIfExists: true)
|
|
42
42
|
]
|
|
43
43
|
input[1] = 'v1'
|
|
44
44
|
"""
|
|
@@ -48,12 +48,12 @@ nextflow_process {
|
|
|
48
48
|
then {
|
|
49
49
|
assertAll(
|
|
50
50
|
{ assert process.success },
|
|
51
|
-
{ assert snapshot(process.out).match() }
|
|
51
|
+
{ assert snapshot(sanitizeOutput(process.out)).match() }
|
|
52
52
|
)
|
|
53
53
|
}
|
|
54
54
|
}
|
|
55
55
|
|
|
56
|
-
test("V1
|
|
56
|
+
test("V1 to V2 conversion - stub") {
|
|
57
57
|
|
|
58
58
|
options "-stub"
|
|
59
59
|
|
|
@@ -62,7 +62,7 @@ nextflow_process {
|
|
|
62
62
|
"""
|
|
63
63
|
input[0] = [
|
|
64
64
|
[ id: 'test_stub' ],
|
|
65
|
-
file(params.modules_testdata_base_path + 'genomics/
|
|
65
|
+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bcl/flowcell_samplesheet.v1.csv', checkIfExists: true)
|
|
66
66
|
]
|
|
67
67
|
input[1] = 'v2'
|
|
68
68
|
"""
|
|
@@ -72,7 +72,7 @@ nextflow_process {
|
|
|
72
72
|
then {
|
|
73
73
|
assertAll(
|
|
74
74
|
{ assert process.success },
|
|
75
|
-
{ assert snapshot(process.out).match() }
|
|
75
|
+
{ assert snapshot(sanitizeOutput(process.out)).match() }
|
|
76
76
|
)
|
|
77
77
|
}
|
|
78
78
|
}
|
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
process SAMPLESHEETPARSER_DIFF {
|
|
2
|
+
tag "$meta.id"
|
|
3
|
+
label 'process_single'
|
|
4
|
+
|
|
5
|
+
conda "${moduleDir}/environment.yml"
|
|
6
|
+
container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
|
|
7
|
+
'https://depot.galaxyproject.org/singularity/samplesheet-parser:1.3.0--pyhdfd78af_0' :
|
|
8
|
+
'quay.io/biocontainers/samplesheet-parser:1.3.0--pyhdfd78af_0' }"
|
|
9
|
+
|
|
10
|
+
input:
|
|
11
|
+
tuple val(meta), path(old_sheet, stageAs: "old/*"), path(new_sheet, stageAs: "new/*")
|
|
12
|
+
|
|
13
|
+
output:
|
|
14
|
+
tuple val(meta), path("*.diff.json"), emit: json
|
|
15
|
+
tuple val("${task.process}"), val('samplesheet-parser'), eval("samplesheet --version | sed 's/samplesheet-parser //'"), topic: versions, emit: versions_samplesheetparser
|
|
16
|
+
|
|
17
|
+
when:
|
|
18
|
+
task.ext.when == null || task.ext.when
|
|
19
|
+
|
|
20
|
+
script:
|
|
21
|
+
def args = task.ext.args ?: ''
|
|
22
|
+
def prefix = task.ext.prefix ?: "${meta.id}"
|
|
23
|
+
"""
|
|
24
|
+
samplesheet diff \\
|
|
25
|
+
${args} \\
|
|
26
|
+
${old_sheet} ${new_sheet} > ${prefix}.diff.json || true
|
|
27
|
+
"""
|
|
28
|
+
|
|
29
|
+
stub:
|
|
30
|
+
def prefix = task.ext.prefix ?: "${meta.id}"
|
|
31
|
+
"""
|
|
32
|
+
touch ${prefix}.diff.json
|
|
33
|
+
"""
|
|
34
|
+
}
|