mgnify-pipelines-toolkit 1.2.11__py3-none-any.whl → 1.3.0__py3-none-any.whl

mgnify_pipelines_toolkit/schemas/dataframes.py

@@ -0,0 +1,325 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# Copyright 2024-2025 EMBL - European Bioinformatics Institute
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import logging
+from typing import Type
+
+import pandas as pd
+import pandera as pa
+from pandera.typing import Series
+from pandera.typing.common import DataFrameBase
+
+from mgnify_pipelines_toolkit.constants.tax_ranks import (
+    SHORT_MOTUS_TAX_RANKS,
+    SHORT_PR2_TAX_RANKS,
+    SHORT_TAX_RANKS,
+)
+
+
+class CoerceBaseDataFrameSchema(pa.DataFrameModel):
+    """Base schema for all dataframe models.
+
+    Provides common configuration for automatic type coercion.
+    """
+
+    class Config:
+        """Pandera configuration.
+
+        coerce: Automatically convert column dtypes to match schema
+        """
+
+        coerce = True
+
+
+# This is the schema for the whole DF
+class AmpliconPassedRunsSchema(CoerceBaseDataFrameSchema):
+    """Class modelling a Pandera dataframe schema for amplicon passed runs.
+    Validates the generated dataframe when read by pandas.read_csv.
+    """
+
+    run: Series[str] = pa.Field(str_matches=r"(E|D|S)RR[0-9]{6,}", unique=True)
+    status: Series[str] = pa.Field(isin=["all_results", "no_asvs", "dada2_stats_fail"])
+
+
+class CompletedAnalysisSchema(CoerceBaseDataFrameSchema):
+    """Class modelling a Pandera dataframe schema for completed assemblies.
+    Validates the generated dataframe when read by pandas.read_csv.
+    """
+
+    assembly: Series[str] = pa.Field(str_matches=r"ERZ\d{6,}", unique=True)
+    status: Series[str] = pa.Field(isin=["success"])
+
+
+class BaseSummarySchema(CoerceBaseDataFrameSchema):
+    """Base schema for summary files.
+
+    All summary schemas inherit from this base and use coerce=True by default.
+    """
+
+
+class InterProSummarySchema(BaseSummarySchema):
+    """Schema for InterPro summary file validation."""
+
+    count: Series[int] = pa.Field(ge=0)
+    interpro_accession: Series[str] = pa.Field(str_matches=r"IPR\d{6}", unique=True)
+    description: Series[str]
+
+
+class GOSummarySchema(BaseSummarySchema):
+    """Schema for GO or GOslim summary file validation."""
+
+    go: Series[str] = pa.Field(str_matches=r"GO:\d{7}", unique=True)
+    term: Series[str]
+    category: Series[str]
+    count: Series[int] = pa.Field(ge=0)
+
+
+class SanntisSummarySchema(BaseSummarySchema):
+    """Schema for Sanntis summary file validation."""
+
+    nearest_mibig: Series[str] = pa.Field(str_matches=r"BGC\d{7}", unique=True)
+    nearest_mibig_class: Series[str]
+    description: Series[str]
+    count: Series[int] = pa.Field(ge=0)
+
+
+class AntismashSummarySchema(BaseSummarySchema):
+    """Schema for Antismash summary file validation."""
+
+    label: Series[str] = pa.Field(unique=True)
+    description: Series[str]
+    count: Series[int] = pa.Field(ge=0)
+
+
+class KOSummarySchema(BaseSummarySchema):
+    """Schema for KEGG Orthology summary file validation."""
+
+    ko: Series[str] = pa.Field(str_matches=r"K\d{5,}", unique=True)
+    description: Series[str]
+    count: Series[int] = pa.Field(ge=0)
+
+
+class PFAMSummarySchema(BaseSummarySchema):
+    """Schema for PFAM summary file validation."""
+
+    pfam: Series[str] = pa.Field(str_matches=r"PF\d{5}", unique=True)
+    description: Series[str]
+    count: Series[int] = pa.Field(ge=0)
+
+
+class KEGGModulesSummarySchema(BaseSummarySchema):
+    """Schema for KEGG Modules summary file validation."""
+
+    module_accession: Series[str] = pa.Field(str_matches=r"M\d{5}", unique=True)
+    completeness: Series[float] = pa.Field(ge=0)
+    pathway_name: Series[str]
+    pathway_class: Series[str]
+
+
+class GOStudySummarySchema(BaseSummarySchema):
+    GO: Series[str] = pa.Field(str_matches=r"^GO:\d{7}$", unique=True)
+    description: Series[str]
+    category: Series[str]
+
+
+class InterProStudySummarySchema(BaseSummarySchema):
+    IPR: Series[str] = pa.Field(str_matches=r"^IPR\d{6}$", unique=True)
+    description: Series[str]
+
+
+class AntismashStudySummarySchema(BaseSummarySchema):
+    label: Series[str] = pa.Field(unique=True)
+
+
+class SanntisStudySummarySchema(BaseSummarySchema):
+    # TODO: limit mibig to the avaiable mibig categories
+    nearest_mibig: Series[str] = pa.Field(unique=True)
+
+
+class KOStudySummarySchema(BaseSummarySchema):
+    KO: Series[str] = pa.Field(unique=True)
+
+
+class PFAMStudySummarySchema(BaseSummarySchema):
+    PFAM: Series[str] = pa.Field(unique=True)
+
+
+class KEGGModulesStudySummarySchema(BaseSummarySchema):
+    module_accession: Series[str] = pa.Field(unique=True)
+
+
+class TaxonomyStudySummarySchema(BaseSummarySchema):
+    pass
+
+
+class AmpliconNonINSDCPassedRunsSchema(CoerceBaseDataFrameSchema):
+    """Class modelling the same dataframe schema as the preceding one, except with no INSDC validation."""
+
+    run: Series[str]
+    status: Series[str] = pa.Field(isin=["all_results", "no_asvs"])
+
+
+# This is the schema for the whole DF
+class TaxonSchema(CoerceBaseDataFrameSchema):
+    """Class modelling a Pandera dataframe schema for taxonomy records.
+    Validates the generated dataframe when read by pandas.read_csv.
+    """
+
+    Superkingdom: Series[str] = pa.Field(nullable=True)
+    Kingdom: Series[str] = pa.Field(nullable=True)
+    Phylum: Series[str] = pa.Field(nullable=True)
+    Class: Series[str] = pa.Field(nullable=True)
+    Order: Series[str] = pa.Field(nullable=True)
+    Family: Series[str] = pa.Field(nullable=True)
+    Genus: Series[str] = pa.Field(nullable=True)
+    Species: Series[str] = pa.Field(nullable=True)
+    Count: Series[int]
+
+    @pa.check(r"Superkingdom|Kingdom|Phylum|Class|Order|Family|Genus|Species", regex=True)
+    def validate_tax_rank_format(self, series: Series[str]) -> Series[bool]:
+        """Validate that taxonomy rank values follow the format: ${rank}__${taxon}
+        or are 'Unclassified' or empty/null.
+
+        :param series: Column series to validate
+        :return: Boolean series indicating valid rows
+        """
+        valid_ranks = ["sk", "k", "p", "c", "o", "f", "g", "s"]
+
+        def check_format(val):
+            if pd.isna(val) or val == "" or val.capitalize() == "Unclassified":
+                return True
+            if "__" not in val:
+                return False
+            rank = val.split("__")[0]
+            return rank in valid_ranks or rank == ""
+
+        return series.apply(check_format)
+
+
+class PR2TaxonSchema(CoerceBaseDataFrameSchema):
+    """Class modelling a Pandera dataframe schema for PR2 taxonomy records."""
+
+    Domain: Series[str] = pa.Field(nullable=True)
+    Supergroup: Series[str] = pa.Field(nullable=True)
+    Division: Series[str] = pa.Field(nullable=True)
+    Subdivision: Series[str] = pa.Field(nullable=True)
+    Class: Series[str] = pa.Field(nullable=True)
+    Order: Series[str] = pa.Field(nullable=True)
+    Family: Series[str] = pa.Field(nullable=True)
+    Genus: Series[str] = pa.Field(nullable=True)
+    Species: Series[str] = pa.Field(nullable=True)
+    Count: Series[int]
+
+    @pa.check(r"Domain|Supergroup|Division|Subdivision|Class|Order|Family|Genus|Species", regex=True)
+    def validate_pr2_tax_rank_format(self, series: Series[str]) -> Series[bool]:
+        """Validate that PR2 taxonomy rank values follow the format: ${rank}__${taxon}
+        or are 'Unclassified' or empty/null.
+
+        :param series: Column series to validate
+        :return: Boolean series indicating valid rows
+        """
+        valid_ranks = SHORT_TAX_RANKS + SHORT_PR2_TAX_RANKS
+
+        def check_format(val):
+            if pd.isna(val) or val == "" or val.capitalize() == "Unclassified":
+                return True
+            if "__" not in val:
+                return False
+            rank = val.split("__")[0]
+            return rank in valid_ranks or rank == ""
+
+        return series.apply(check_format)
+
+
+# This is the schema for the whole DF
+class RawReadsPassedRunsSchema(CoerceBaseDataFrameSchema):
+    """Class modelling a Pandera dataframe schema for raw reads passed runs.
+    Validates the generated dataframe when read by pandas.read_csv.
+    """
+
+    run: Series[str] = pa.Field(str_matches=r"(E|D|S)RR[0-9]{6,}", unique=True)
+    status: Series[str] = pa.Field(isin=["all_results", "no_reads", "all_empty_results", "some_empty_results"])
+
+
+class RawReadsNonINSDCPassedRunsSchema(CoerceBaseDataFrameSchema):
+    """Class modelling the same dataframe schema as the preceding one, except with no INSDC validation."""
+
+    run: Series[str]
+    status: Series[str] = pa.Field(isin=["all_results", "no_reads", "all_empty_results", "some_empty_results"])
+
+
+class MotusTaxonSchema(CoerceBaseDataFrameSchema):
+    """Class for modelling a single Taxonomic Rank in mOTUs output.
+    Essentially is just a special string with validation of the structure:
+    `${rank}__${taxon}`
+    Where `${rank}` is one of the allowed short ranks defined by the imported
+    `SHORT_MOTUS_TAX_RANKS` variables.
+    And `${taxon}` is the actual taxon for that rank (this isn't validated).
+    It will also validate if the whole string is the permitted "unassigned" or "unclassified".
+    """
+
+    Kingdom: Series[str] = pa.Field(nullable=True)
+    Phylum: Series[str] = pa.Field(nullable=True)
+    Class: Series[str] = pa.Field(nullable=True)
+    Order: Series[str] = pa.Field(nullable=True)
+    Family: Series[str] = pa.Field(nullable=True)
+    Genus: Series[str] = pa.Field(nullable=True)
+    Species: Series[str] = pa.Field(nullable=True)
+    Count: Series[int]
+
+    @pa.check(r"Kingdom|Phylum|Class|Order|Family|Genus|Species", regex=True)
+    def validate_motus_tax_rank_format(self, series: Series[str]) -> Series[bool]:
+        """Validate that mOTUs taxonomy rank values follow the format: ${rank}__${taxon}
+        or are 'Unclassified', 'Unassigned', or empty/null.
+
+        :param series: Column series to validate
+        :return: Boolean series indicating valid rows
+        """
+        valid_ranks = SHORT_MOTUS_TAX_RANKS
+
+        def check_format(val):
+            if pd.isna(val) or val == "":
+                return True
+            if val.capitalize() in {"Unclassified", "Unassigned"}:
+                return True
+            if "__" not in val:
+                return False
+            rank = val.split("__")[0]
+            return rank in valid_ranks or rank == ""
+
+        return series.apply(check_format)
+
+
+class FunctionProfileSchema(CoerceBaseDataFrameSchema):
+    """Class modelling a Pandera dataframe schema for functional profile data.
+    This is what actually validates the generated dataframe when read by pandas.read_csv.
+    """
+
+    read_count: Series[int]
+    coverage_depth: Series[float]
+    coverage_breadth: Series[float]
+
+
+def validate_dataframe(df: pd.DataFrame, schema: Type[pa.DataFrameModel], df_metadata: str) -> DataFrameBase:
+    """
+    Validate a pandas dataframe using a pandera schema.
+    df_metadata will be shown in logs on failure: example, the TSV filename from which the df was read.
+    """
+    try:
+        dfs = schema.validate(df, lazy=True)
+    except pa.errors.SchemaError as e:
+        logging.error(f"{schema.__name__} validation failure for {df_metadata}")
+        raise e
+    return dfs

{mgnify_pipelines_toolkit-1.2.11.dist-info → mgnify_pipelines_toolkit-1.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.2.11
+Version: 1.3.0
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -19,6 +19,7 @@ Requires-Dist: click<9,>=8.1.8
 Requires-Dist: pandera<0.24,>=0.23.1
 Requires-Dist: pyfastx<3,>=2.2.0
 Requires-Dist: intervaltree<4,>=3.1.0
+Requires-Dist: isort>=6.1.0
 Provides-Extra: test
 Requires-Dist: pytest<9,>=8.3.5; extra == "test"
 Requires-Dist: pytest-md>=0.2.0; extra == "test"
@@ -26,8 +27,7 @@ Requires-Dist: pytest-workflow==2.1.0; extra == "test"
 Provides-Extra: dev
 Requires-Dist: pre-commit>=4.2.0; extra == "dev"
 Requires-Dist: black>=25.1.0; extra == "dev"
-Requires-Dist: flake8>=7.1.2; extra == "dev"
-Requires-Dist: pep8-naming>=0.14.1; extra == "dev"
+Requires-Dist: ruff>=0.8.4; extra == "dev"
 Dynamic: license-file
 
 # mgnify-pipelines-toolkit
@@ -57,16 +57,29 @@ You should then be able to run the packages from the command-line. For example t
 
 `get_subunits -i ${easel_coords} -n ${meta.id}`
 
-## Adding a new script to the package
+## Development
 
-### Local development requirements
-Before starting any development, you should do these few steps:
-- Clone the repo if you haven't already and create a feature branch from the `dev` branch (NOT `main`).
-- Create a virtual environment with the tool of your choice (i.e. `conda create --name my_new_env`)
-- Activate you new environment (i.e. `conda activate my_new_env`)
-- Install dev dependencies `pip install -e '.[tests,dev]'`
-- Install pre-commit hooks `pre-commit install`
-- Run unit tests `pytest`
+### Quick Start with uv and Taskfile
+
+This project uses [uv](https://docs.astral.sh/uv/) for fast Python environment management and [Task](https://taskfile.dev/) for task automation.
+
+Prerequisites:
+- Install [uv](https://docs.astral.sh/uv/getting-started/installation/)
+- Install [Task](https://taskfile.dev/installation/)
+
+Common tasks:
+
+```bash
+task: Available tasks for this project:
+* clean:            Clean up generated files and caches
+* lint:             Run linters (ruff check only)
+* lint-fix:         Run linters and fix issues automatically
+* pre-commit:       Install pre-commit hooks
+* run:              Run toolkit scripts with uv (usage: task run -- <script_name> [args])
+* test:             Run tests with uv
+* testk:            Run specific tests from a file (usage: task testk -- test_path)
+* venv:             Create a virtual environment with uv
+```
 
 When doing these steps above, you ensure that the code you add will be linted and formatted properly.
 

{mgnify_pipelines_toolkit-1.2.11.dist-info → mgnify_pipelines_toolkit-1.3.0.dist-info}/RECORD

@@ -7,7 +7,7 @@ mgnify_pipelines_toolkit/analysis/amplicon/permute_primers.py,sha256=1aGOJX9tC7M
 mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=uGlQ0595rammsW-rnhh1UAEkoRUjLqCQ-tp377Mj180,5345
 mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py,sha256=Wu4tRtuRkgd3hoeuwPl_E5ghxIW7e_1vrcvFGWv_U4A,3173
 mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py,sha256=yLpzkRJXAeXRUNgz60zopEwHcdprM2UDjquE-GkrFys,1722
-mgnify_pipelines_toolkit/analysis/amplicon/study_summary_generator.py,sha256=epVClL10QcllL8yu7YGjx0rXNVHL2GxHi-Ek0MOjsjo,13859
+mgnify_pipelines_toolkit/analysis/amplicon/study_summary_generator.py,sha256=ZiLSW1zFkYkbEeS6ZJb5GlxhsfDvbJ7JraqPgPUaI68,13473
 mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py,sha256=NZSNY2bqs_TQyz8riDqiEFPLKcwTgzh1C7DeVHT6V8Q,4366
 mgnify_pipelines_toolkit/analysis/assembly/antismash_gff_builder.py,sha256=2Zkm3KJ1Borzch5XSZbsVNTPej3J5QYkqTQQACkRDVo,6944
 mgnify_pipelines_toolkit/analysis/assembly/combined_gene_caller_merge.py,sha256=Pq-9RSt3RCxzDMQVW1VHlHF4NtpVwCWFbg2CMkvpZZc,19089
@@ -19,12 +19,12 @@ mgnify_pipelines_toolkit/analysis/assembly/go_utils.py,sha256=eay9e3Xdc8XxnlC_4S
 mgnify_pipelines_toolkit/analysis/assembly/krona_txt_from_cat_classification.py,sha256=uex2T6GagtYFBIc39-Xm4SFHL06KAQ5v0_loOmY_eaw,4289
 mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_cazys.py,sha256=5m5AwWEKidJx1FI0y93AFka7z0zEE8dBf1ofgP8TV_Y,7108
 mgnify_pipelines_toolkit/analysis/assembly/process_dbcan_result_clusters.py,sha256=DYZhChGD49M-zAtGkCmNHXDoVTnd5Qy6amG-oePO8Ek,5981
-mgnify_pipelines_toolkit/analysis/assembly/study_summary_generator.py,sha256=eNichqFFmfPsa2J10IUm_PemVs9fBhbKa2vpDqEvJNU,21791
+mgnify_pipelines_toolkit/analysis/assembly/study_summary_generator.py,sha256=YBZ5ARXKLMBnZZmbFaQP75kmUuADfUhdye3QU9qUVWY,21506
 mgnify_pipelines_toolkit/analysis/assembly/summarise_antismash_bgcs.py,sha256=jUeA7I12YrtIqnm3hUxpdgsWfa2pP1ALGjb9OMKPcgY,10643
 mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.py,sha256=TPaKlYkoy37_XgYNOskWCCoXtPNku_k5ygSeK4fT1VQ,6689
 mgnify_pipelines_toolkit/analysis/assembly/summarise_sanntis_bgcs.py,sha256=lxe7R2RQFyNCzEm6YuNRrqKZLZOUPq5W1P23Pt2sKBU,4570
 mgnify_pipelines_toolkit/analysis/genomes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mgnify_pipelines_toolkit/analysis/rawreads/study_summary_generator.py,sha256=ltyNHwzaZZkK1ScH2vV2QV1eUXTHQUMYyadJwO-zSQY,16028
+mgnify_pipelines_toolkit/analysis/rawreads/study_summary_generator.py,sha256=obZnZ4uyVR0ckVCpqflZd_tdxA2-uCnFkubkM1Zj1ZY,15545
 mgnify_pipelines_toolkit/analysis/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/analysis/shared/convert_cmscan_to_cmsearch_tblout.py,sha256=kAGU5kQyj-Hlcdx32i-xOJSuHYYUDj-kqnyYHMohHGc,4477
 mgnify_pipelines_toolkit/analysis/shared/dwc_summary_generator.py,sha256=RaFopUjJI4UO1ttnSEHj7iUXpAL5-2FTbDXlhOmNy0s,25534
@@ -40,13 +40,13 @@ mgnify_pipelines_toolkit/constants/regex_fasta_header.py,sha256=G-xrc9b8zdmPTaOI
 mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=ekZN5OcMBhDRcj7XB_27wQ8fEnmAqMJc4aQ3pv4BRmI,1229
 mgnify_pipelines_toolkit/constants/thresholds.py,sha256=1AMBmoHBR0WjXZpkwJ7_Q-gfJtHXuCA4tZ-uvPhF0Xc,1085
 mgnify_pipelines_toolkit/constants/var_region_coordinates.py,sha256=0bM4MwarFiM5yTcp5AbAmQ0o-q-gWy7kknir9zJ9R0A,1312
-mgnify_pipelines_toolkit/schemas/schemas.py,sha256=0l1hOkF4AeN0YOm4CVGPoP-U8kEzAxbhNEk3VEezZ4g,23177
+mgnify_pipelines_toolkit/schemas/dataframes.py,sha256=gpWA5RlQpsOkjixF_21UsEKPLrpt4_8Ik-ANb1b9DEU,11523
 mgnify_pipelines_toolkit/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/utils/fasta_to_delimited.py,sha256=lgYIR1S4crURY7C7nFtgE6QMV4u4zCNsUrVkcRnsEEo,3996
 mgnify_pipelines_toolkit/utils/get_mpt_version.py,sha256=aS9bWrC9CP7tpxoEVg6eEYt18-pmjG7fJl5Mchz4YOU,798
-mgnify_pipelines_toolkit-1.2.11.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-1.2.11.dist-info/METADATA,sha256=xziE8NaQ8tsUlY9JTEOX4Sf5KO4xnzD2hRL-nvHFryw,5776
-mgnify_pipelines_toolkit-1.2.11.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mgnify_pipelines_toolkit-1.2.11.dist-info/entry_points.txt,sha256=7TJ8GgbKoX1xnQsOdWwMvwhIv4uuHCx7pMxKmZabPOs,3228
-mgnify_pipelines_toolkit-1.2.11.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-1.2.11.dist-info/RECORD,,
+mgnify_pipelines_toolkit-1.3.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.3.0.dist-info/METADATA,sha256=CYk4aiET00z22Dhti78aroegnq-ZlDCvWkPLQDFqEVY,6098
+mgnify_pipelines_toolkit-1.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mgnify_pipelines_toolkit-1.3.0.dist-info/entry_points.txt,sha256=7TJ8GgbKoX1xnQsOdWwMvwhIv4uuHCx7pMxKmZabPOs,3228
+mgnify_pipelines_toolkit-1.3.0.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.3.0.dist-info/RECORD,,