hitlist 2.1.0__tar.gz → 2.1.2__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.
- {hitlist-2.1.0/hitlist.egg-info → hitlist-2.1.2}/PKG-INFO +1 -1
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/provenance.py +62 -24
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/scanner.py +44 -36
- hitlist-2.1.2/hitlist/version.py +1 -0
- {hitlist-2.1.0 → hitlist-2.1.2/hitlist.egg-info}/PKG-INFO +1 -1
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist.egg-info/SOURCES.txt +1 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/pyproject.toml +3 -0
- hitlist-2.1.2/tests/test_benchmark_network.py +148 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_provenance.py +45 -0
- hitlist-2.1.0/hitlist/version.py +0 -1
- {hitlist-2.1.0 → hitlist-2.1.2}/LICENSE +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/MANIFEST.in +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/README.md +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/__init__.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/aggregate.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/apm.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/assay_adjudication.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/assays.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/atlas.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/binding_assay_context.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/binding_context_availability.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/builder.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/bulk_fractionation.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/bulk_proteomics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/bulk_replicates.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/cache_inventory.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/canine_bulk.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/canine_ligands.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/canine_orfdata.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/canine_peptide_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/cell_name_parser.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/cli.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/cli_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/cli_evidence_store.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/cli_help.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/cli_uniprot.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/condition_categories.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/conditions.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/context_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/cta_expression.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/curation.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/curation_yaml.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/__init__.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/assay_adjudications.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/atlas_community_crosswalk.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/bulk_proteomics/__init__.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/bulk_proteomics/detectability.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/bulk_proteomics/sources.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/canine_bulk.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/canine_ligands.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/cell_lines.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/condition_vocabulary.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/data_assets.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/binding_assay_protocols.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/digestion_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/digestion_contract.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/dilution_observer.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/goldberg_mapp.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/goldberg_mapp_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/hap1_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/hap1_contract.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/intact_degradomics.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/mapp_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/mapp_contract.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/mapp_controlled_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/mapp_controlled_contract.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/mapp_pbmc_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/mapp_pbmc_contract.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/ms_calibration_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/ms_calibration_contract.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/nanaware_lymph.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/native_peptidomics.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/nontryptic_calibration.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/pmid_overrides_1_78.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/precursor_context_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/proteometools_ms1_core.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/pxd057588_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/pxd057588_contract.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/pxd057588_retrieval_receipts.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/pxd057588_workbook_inventory.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/supporting_v4_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/tmab_assets.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/wolf_levy_companion_crosswalk_audit.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/gene_sets.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/hla_ligand_atlas.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/line_expression/__init__.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/line_expression/apm_rna_build_report.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/line_expression/ensembl_gene_id_symbol.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/line_expression/gm12878_encode_rnaseq_tpm.csv.gz +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/line_expression/hap1_depmap24q4_gene_tpm.csv.gz +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/line_expression/sources.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/line_expression_anchors.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/monoallelic_lines.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/peptide_attributions/connelley_2022_bola_a19.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/peptide_attributions/sarkizova_2020_patient_cohort.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/pmid_overrides.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/pxd013455.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/pxd013455_publication.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/species_contexts.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/specimen_lineage.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/abelin_2019_dr_tissue.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/abelin_2019_maptac_class1.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/gomez_zepeda_2024_hela.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/gomez_zepeda_2024_jy.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/gomez_zepeda_2024_plasma.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/gomez_zepeda_2024_raji.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/gomez_zepeda_2024_skmel37.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_b2m_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_calr_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_canx_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_erap1_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_ganab_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_irf2_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_pdia3_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_sppl3_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_tap1_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_tap2_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_tapbp_ko.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary/shapiro_2025_hap1_wildtype.csv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/supplementary.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/tcell_audit_sources.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/tissue_blacklist.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/tissue_categories.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/uniprot_references.yaml +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/dataset.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/detectability.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/digestion_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/digestion_processing_package.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/digestion_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/dilution_observer.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/dilution_observer_compiler.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/dilution_observer_metadata.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/dilution_observer_schema.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/distribution_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/downloads.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/evidence_audit.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/evidence_bindings.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/evidence_bundle.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/evidence_catalog.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/evidence_package.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/evidence_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/evidence_snapshot.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/evidence_store.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/export.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/expression_inputs.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/external_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/external_successor.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/genes.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/goldberg_candidates.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/goldberg_composition.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/goldberg_mapp.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/goldberg_workbooks.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/gomez_arm_projection.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/gomez_prediction_panel.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/gomez_source_lineage.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/hap1_quantitative.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/hap1_response_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/indexer.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/intact_degradomics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/intact_degradomics_schema.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/intact_degradomics_workbook.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/intact_kinetics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/intact_organ_method.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/intact_organ_transfer.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/line_expression.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/lineage.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/lymph_composition.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/managed_assets.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/mapp_canonical.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/mapp_composition.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/mapp_controlled_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/mapp_controlled_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/mapp_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/mapp_pbmc_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/mappings.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/material_context.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/mhc_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/ms_calibration_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/ms_calibration_response.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/nanaware_lymph.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/native_contrast.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/native_contrast_compiler.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/native_contrast_schema.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/native_peptidomics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/native_peptidomics_compiler.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/native_peptidomics_reference.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/native_peptidomics_schema.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/nontryptic_calibration.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/nontryptic_calibration_compiler.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/nontryptic_calibration_schema.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/nontryptic_workbooks.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/observations.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/pandas_utils.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/parquet_io.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/pbmc_composition.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/peptide_modifications.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/pmhc_query.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/precursor_context_package.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/precursor_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/predict.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/proteome.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/proteometools_ms1.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/proteometools_response.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/pxd013455.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/pxd013455_download.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/pxd013455_publication.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/pxd057588_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/qc.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/reference_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/report.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/sample_identity.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/samples.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/sequence_reference_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/species_contexts.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/species_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/species_expression.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/split_audit.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/supplement.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/supporting_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/supporting_numeric_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tcell_assays.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tcell_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tcell_functional.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tcell_multimer.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tcell_peptides.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tcell_processing_package.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tcell_training.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tissue_blacklist.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tmab_peptidomics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/tmab_response_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/training_bundle.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist/uniprot.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist.egg-info/dependency_links.txt +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist.egg-info/entry_points.txt +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist.egg-info/requires.txt +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/hitlist.egg-info/top_level.txt +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/scripts/verify_binding_assay_context.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/scripts/verify_canine_peptide_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/scripts/verify_digestion_arithmetic.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/scripts/verify_digestion_roundtrip.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/scripts/verify_digestion_timecourses.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/setup.cfg +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/setup.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/data/canine_orfdata/README.md +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/data/canine_orfdata/manifest.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/data/canine_orfdata/protein.tsv +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/data/canine_orfdata/search.fasta +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/data/canine_peptide_evidence/README.md +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/data/canine_peptide_evidence/dataset.sqlite.gz +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/data/canine_peptide_evidence/expected.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/data/canine_peptide_evidence/manifest.json +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_aggregate.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_allele_candidate_audit.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_allele_candidates.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_allele_identity.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_apm.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_apm_host_expression.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_apply_winners_vectorized.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_arm_resolution.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_assay_adjudication.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_assays.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_atlas_crosswalk.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_atlas_lineage.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_attribution_query_context.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_binding_assay_context.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_binding_context_availability.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_build_smoke.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_build_uniprot_reference.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_builder.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_bulk_fractionation.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_bulk_proteomics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_bulk_proteomics_unit.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_bulk_replicates.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cache_current.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cache_inventory.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_canine_bulk.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_canine_ligands.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_canine_orfdata.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_canine_peptide_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_canine_peptide_runtime.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_categorical_consumers.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cell_name_parser.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_check_dev_install.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_ci_corpus.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cli_build_group.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cli_data_dirs.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cli_export_cleanup.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cli_help.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cli_mhc_allele_split.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cli_pmhc_samples.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cli_version.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_compare_corpus_generations.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_compare_reliability_outputs.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_condition_categories.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_conditions.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_context_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_corpus_qualification.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_corpus_v3_arm_contexts.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cta_evidence_bundle.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_cta_expression.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_curated_erap2_lines.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_curated_study_sources.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_curation.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_curation_sanity_pass.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_curation_source_followup.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_curation_yaml.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_data_assets.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_data_dir_resolution.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_dataset_generations.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_deploy_script.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_depmap_expression_fetch.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_deposited_elution_conditions.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_detectability.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_digestion_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_digestion_processing_package.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_digestion_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_dilution_observer.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_download_http.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_download_to_file.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_downloads_timeout.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_ensembl_cache_only.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_evidence_catalog.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_evidence_package.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_evidence_recipes.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_evidence_snapshot.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_evidence_store.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_exclude_from_ms.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_export.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_export_filter_parity.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_export_join_lifetime.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_export_species_filters.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_expression_source_provenance.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_external_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_external_successor.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_genes.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_genotype_attribution.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_goldberg_composition.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_goldberg_mapp.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_gomez_arm_projection.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_gomez_prediction_panel.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_gomez_source_lineage.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_hap1_quantitative.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_hap1_response_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_human_cohort_qualification.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_intact_degradomics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_intact_kinetics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_intact_organ_method.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_intact_organ_transfer.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_line_expression.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_lineage_audit.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_local_supplement.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_long_peptide_mapping.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_lymph_composition.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mapp_canonical.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mapp_controlled_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mapp_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mapp_pbmc_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mapping_worker_cache.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mappings.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_material_context.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mhc_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mhc_typing_contract.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mhcgnomes_floor_check.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_ms_calibration_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_ms_calibration_response.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_multi_proteome_flanking.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_mutant_sample_genotypes.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_nanaware_lymph.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_native_contrast.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_native_peptidomics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_netmhcpan_invocation.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_nontryptic_calibration.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_nontryptic_workbooks.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_observations.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_pbmc_composition.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_peptide_attribution_scope.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_peptide_modifications.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_pmhc_query.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_precursor_context_package.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_predict.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_profile_build.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_proteome.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_proteome_cache_resolution.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_proteometools_ms1.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_public_api.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_pxd013455.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_qc.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_reassign_genotypes.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_release_artifacts.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_release_diagnostics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_report.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_sample_attribution_audit.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_sample_group.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_sample_identity.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_sample_inventory.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_sample_override_and_note.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_samples.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_scanner.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_sequence_reference_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_source_verification.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_species_contexts.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_species_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_study_identity_corrections.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_supplement.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_supplementary_build_e2e.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_supporting_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_supporting_numeric_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_tcell_assays.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_tcell_availability.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_tcell_evidence.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_tcell_processing_package.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_test_script.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_tissue_blacklist.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_tmab_peptidomics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_tmab_response_recipe.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_tmab_semantics.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_training_binding_filters.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_training_bundle.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_training_identity.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_training_preflight.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_training_qc_metadata.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_uniprot.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_unit_isolation.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_versioned_datasets.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_wolf_levy_crosswalk_audit.py +0 -0
- {hitlist-2.1.0 → hitlist-2.1.2}/tests/test_xdist_cache.py +0 -0
|
@@ -70,6 +70,11 @@ def _record_prefix(dataset):
|
|
|
70
70
|
return f"record:{quote(dataset, safe='')}:row:"
|
|
71
71
|
|
|
72
72
|
|
|
73
|
+
@lru_cache(maxsize=32)
|
|
74
|
+
def _relationship_json(flags):
|
|
75
|
+
return json.dumps([name for name, value in RELATIONS.items() if flags & value] or ["retained"])
|
|
76
|
+
|
|
77
|
+
|
|
73
78
|
class ProvenanceStorageError(RuntimeError):
|
|
74
79
|
"""The disposable contributor graph or output filesystem ran out of capacity."""
|
|
75
80
|
|
|
@@ -264,11 +269,44 @@ class ContributorCollector:
|
|
|
264
269
|
self.sources[dataset] = snapshot
|
|
265
270
|
|
|
266
271
|
def record(self, dataset, row_number, fields, row_values) -> str:
|
|
267
|
-
record_id = f"{_record_prefix(dataset)}{row_number}"
|
|
268
272
|
# Keep the original JSON strings byte-for-byte, including Unicode
|
|
269
273
|
# escaping and unmapped cells. Compress bounded groups so repeated
|
|
270
274
|
# source metadata shares one dictionary instead of one per row.
|
|
271
275
|
payload = (self._fields_encoder.encode(fields) + "\n" + json.dumps(row_values)).encode()
|
|
276
|
+
pmid = str(fields.get("pmid", fields.get("manifest", {}).get("pmid", "")))
|
|
277
|
+
return self._record_payload(dataset, row_number, payload, pmid)
|
|
278
|
+
|
|
279
|
+
def csv_record_writer(self, dataset, columns):
|
|
280
|
+
"""Bind a CSV layout and encode each string cell once for both JSON views.
|
|
281
|
+
|
|
282
|
+
CSV readers return only strings. The general record method still owns
|
|
283
|
+
nested/typed supplementary payloads. Reusing JSON's string encoder here
|
|
284
|
+
preserves its exact escaping, spaces, key order and unmapped cells.
|
|
285
|
+
No source values are cached across rows.
|
|
286
|
+
"""
|
|
287
|
+
prefixes = tuple(
|
|
288
|
+
(json.dumps(name) + ": ", index) for name, index in sorted(columns.items())
|
|
289
|
+
)
|
|
290
|
+
pmid_index = columns.get("pmid")
|
|
291
|
+
escape = json.encoder.encode_basestring_ascii
|
|
292
|
+
|
|
293
|
+
def record_row(row_number, row_values):
|
|
294
|
+
encoded = list(map(escape, row_values))
|
|
295
|
+
n_columns = len(encoded)
|
|
296
|
+
fields = ", ".join(
|
|
297
|
+
prefix + (encoded[index] if index < n_columns else '""')
|
|
298
|
+
for prefix, index in prefixes
|
|
299
|
+
)
|
|
300
|
+
payload = ("{" + fields + "}\n[" + ", ".join(encoded) + "]").encode()
|
|
301
|
+
pmid = (
|
|
302
|
+
row_values[pmid_index] if pmid_index is not None and pmid_index < n_columns else ""
|
|
303
|
+
)
|
|
304
|
+
return self._record_payload(dataset, row_number, payload, pmid)
|
|
305
|
+
|
|
306
|
+
return record_row
|
|
307
|
+
|
|
308
|
+
def _record_payload(self, dataset, row_number, payload, pmid):
|
|
309
|
+
record_id = f"{_record_prefix(dataset)}{row_number}"
|
|
272
310
|
if (
|
|
273
311
|
self._pending_payloads
|
|
274
312
|
and self._pending_bytes + len(payload) > self._CAPTURE_BATCH_BYTES
|
|
@@ -283,7 +321,7 @@ class ContributorCollector:
|
|
|
283
321
|
self._block_id,
|
|
284
322
|
self._pending_bytes,
|
|
285
323
|
len(payload),
|
|
286
|
-
|
|
324
|
+
pmid,
|
|
287
325
|
),
|
|
288
326
|
)
|
|
289
327
|
self._pending_payloads.append(payload)
|
|
@@ -462,26 +500,18 @@ class ContributorCollector:
|
|
|
462
500
|
fields, values = decoded.decode().split("\n", 1)
|
|
463
501
|
batch_bytes += len(decoded) + len(node) + len(source) + len(label)
|
|
464
502
|
records.append(
|
|
465
|
-
|
|
466
|
-
|
|
467
|
-
|
|
468
|
-
|
|
469
|
-
|
|
470
|
-
|
|
471
|
-
|
|
472
|
-
|
|
473
|
-
|
|
474
|
-
|
|
475
|
-
|
|
476
|
-
|
|
477
|
-
"curated_peptide_map" if label else "not_attributed",
|
|
478
|
-
json.dumps(
|
|
479
|
-
[k for k, v in RELATIONS.items() if flags & v]
|
|
480
|
-
or ["retained"]
|
|
481
|
-
),
|
|
482
|
-
"overlap_unresolved" if flags & 28 else "source_record",
|
|
483
|
-
),
|
|
484
|
-
)
|
|
503
|
+
(
|
|
504
|
+
node,
|
|
505
|
+
source,
|
|
506
|
+
dataset,
|
|
507
|
+
row,
|
|
508
|
+
pmid,
|
|
509
|
+
fields,
|
|
510
|
+
values,
|
|
511
|
+
label,
|
|
512
|
+
"curated_peptide_map" if label else "not_attributed",
|
|
513
|
+
_relationship_json(flags),
|
|
514
|
+
"overlap_unresolved" if flags & 28 else "source_record",
|
|
485
515
|
)
|
|
486
516
|
)
|
|
487
517
|
if (
|
|
@@ -489,13 +519,21 @@ class ContributorCollector:
|
|
|
489
519
|
or len(records) >= self._OUTPUT_BATCH_ROWS
|
|
490
520
|
):
|
|
491
521
|
self._check_space(force=True)
|
|
492
|
-
writer.write_table(
|
|
522
|
+
writer.write_table(
|
|
523
|
+
pa.Table.from_pydict(
|
|
524
|
+
dict(zip(CONTRIBUTOR_COLUMNS, zip(*records))), schema=schema
|
|
525
|
+
)
|
|
526
|
+
)
|
|
493
527
|
n_links += len(records)
|
|
494
528
|
records.clear()
|
|
495
529
|
batch_bytes = 0
|
|
496
530
|
if records:
|
|
497
531
|
self._check_space(force=True)
|
|
498
|
-
writer.write_table(
|
|
532
|
+
writer.write_table(
|
|
533
|
+
pa.Table.from_pydict(
|
|
534
|
+
dict(zip(CONTRIBUTOR_COLUMNS, zip(*records))), schema=schema
|
|
535
|
+
)
|
|
536
|
+
)
|
|
499
537
|
n_links += len(records)
|
|
500
538
|
# Catch source replacement during a long build instead of binding
|
|
501
539
|
# rows to the digest of bytes that were never actually scanned.
|
|
@@ -25,6 +25,7 @@ from __future__ import annotations
|
|
|
25
25
|
import csv
|
|
26
26
|
import os
|
|
27
27
|
import warnings
|
|
28
|
+
from operator import itemgetter
|
|
28
29
|
from pathlib import Path
|
|
29
30
|
|
|
30
31
|
import pandas as pd
|
|
@@ -389,6 +390,10 @@ def scan(
|
|
|
389
390
|
if provenance is not None:
|
|
390
391
|
provenance.register_source(dataset, source_path)
|
|
391
392
|
reader, c, p, fh = _open_csv(source_path)
|
|
393
|
+
field_names = tuple(c)
|
|
394
|
+
project = itemgetter(*c.values())
|
|
395
|
+
max_column = max(c.values())
|
|
396
|
+
record_csv = provenance.csv_record_writer(dataset, c) if provenance is not None else None
|
|
392
397
|
for row_number, row in enumerate(_progress(reader, p, f"Scanning {p.name}", fh=fh), 1):
|
|
393
398
|
if peptides is not None:
|
|
394
399
|
pep_raw = _safe_col(row, c["epitope_name"])
|
|
@@ -403,12 +408,15 @@ def scan(
|
|
|
403
408
|
# Dedup only on a *present* Assay IRI. A blank IRI is not an
|
|
404
409
|
# identity — deduping on "" would collapse every blank-IRI row
|
|
405
410
|
# (distinct observations) into one. _safe_col guards short rows.
|
|
406
|
-
|
|
411
|
+
fields = (
|
|
412
|
+
dict(zip(field_names, project(row)))
|
|
413
|
+
if len(row) > max_column
|
|
414
|
+
else {name: _safe_col(row, index) for name, index in c.items()}
|
|
415
|
+
)
|
|
416
|
+
iri = fields["assay_iri"]
|
|
407
417
|
record_id = ""
|
|
408
418
|
if provenance is not None:
|
|
409
|
-
record_id =
|
|
410
|
-
dataset, row_number, {name: _safe_col(row, col) for name, col in c.items()}, row
|
|
411
|
-
)
|
|
419
|
+
record_id = record_csv(row_number, row)
|
|
412
420
|
if iri:
|
|
413
421
|
if provenance is not None:
|
|
414
422
|
if provenance.duplicate_assay(scan_id, iri, record_id):
|
|
@@ -418,10 +426,10 @@ def scan(
|
|
|
418
426
|
continue
|
|
419
427
|
seen.add(iri)
|
|
420
428
|
|
|
421
|
-
src_org =
|
|
422
|
-
species =
|
|
423
|
-
host =
|
|
424
|
-
raw_pmid =
|
|
429
|
+
src_org = fields["source_organism"]
|
|
430
|
+
species = fields["species"]
|
|
431
|
+
host = fields["host"]
|
|
432
|
+
raw_pmid = fields["pmid"].strip()
|
|
425
433
|
pmid: str | int = ""
|
|
426
434
|
if raw_pmid:
|
|
427
435
|
try:
|
|
@@ -429,8 +437,8 @@ def scan(
|
|
|
429
437
|
except ValueError:
|
|
430
438
|
pmid = raw_pmid
|
|
431
439
|
|
|
432
|
-
mhc_res_raw =
|
|
433
|
-
reported_mhc_class =
|
|
440
|
+
mhc_res_raw = fields["mhc_restriction"]
|
|
441
|
+
reported_mhc_class = fields["mhc_class"]
|
|
434
442
|
mhc_species_context = pmid_mhc_species_context(pmid)
|
|
435
443
|
mhc_annotation = resolve_mhc_annotation(
|
|
436
444
|
mhc_res_raw,
|
|
@@ -477,11 +485,11 @@ def scan(
|
|
|
477
485
|
if not species or species.strip().lower() == "unidentified":
|
|
478
486
|
species = curated_spc
|
|
479
487
|
|
|
480
|
-
process_type =
|
|
481
|
-
disease =
|
|
482
|
-
culture_condition =
|
|
483
|
-
source_tissue =
|
|
484
|
-
cell_name =
|
|
488
|
+
process_type = fields["process_type"]
|
|
489
|
+
disease = fields["disease"]
|
|
490
|
+
culture_condition = fields["culture_condition"]
|
|
491
|
+
source_tissue = fields["source_tissue"]
|
|
492
|
+
cell_name = fields["cell_name"]
|
|
485
493
|
|
|
486
494
|
# Per-PMID provenance curation (#314): fill blank source_tissue /
|
|
487
495
|
# cell_name / disease / culture_condition for epitope-ID papers IEDB
|
|
@@ -518,7 +526,7 @@ def scan(
|
|
|
518
526
|
peptide_modifications_str,
|
|
519
527
|
has_ptm,
|
|
520
528
|
peptide_extended,
|
|
521
|
-
) = parse_peptide_modifications(
|
|
529
|
+
) = parse_peptide_modifications(fields["epitope_name"])
|
|
522
530
|
|
|
523
531
|
record: dict = {
|
|
524
532
|
"peptide": bare_peptide,
|
|
@@ -527,24 +535,24 @@ def scan(
|
|
|
527
535
|
"peptide_extended": peptide_extended,
|
|
528
536
|
**mhc_annotation.as_record_fields(),
|
|
529
537
|
"assay_iri": iri,
|
|
530
|
-
"reference_iri":
|
|
538
|
+
"reference_iri": fields["ref_iri"],
|
|
531
539
|
"pmid": pmid,
|
|
532
|
-
"submission_id":
|
|
533
|
-
"reference_title":
|
|
540
|
+
"submission_id": fields["submission_id"],
|
|
541
|
+
"reference_title": fields["ref_title"],
|
|
534
542
|
"source_organism": src_org,
|
|
535
543
|
"species": species,
|
|
536
|
-
"host":
|
|
537
|
-
"host_age":
|
|
538
|
-
"host_mhc_types":
|
|
544
|
+
"host": fields["host"],
|
|
545
|
+
"host_age": fields["host_age"],
|
|
546
|
+
"host_mhc_types": fields["host_mhc_types"],
|
|
539
547
|
"process_type": process_type,
|
|
540
548
|
"disease": disease,
|
|
541
|
-
"disease_stage":
|
|
549
|
+
"disease_stage": fields["disease_stage"],
|
|
542
550
|
"source_tissue": source_tissue,
|
|
543
551
|
"cell_name": cell_name,
|
|
544
552
|
"culture_condition": culture_condition,
|
|
545
|
-
"antigen_processing_comments":
|
|
546
|
-
"assay_comments":
|
|
547
|
-
"qualitative_measurement":
|
|
553
|
+
"antigen_processing_comments": fields["antigen_processing_comments"],
|
|
554
|
+
"assay_comments": fields["assay_comments"],
|
|
555
|
+
"qualitative_measurement": fields["qualitative_measurement"],
|
|
548
556
|
# Structured quantitative binding-assay fields from IEDB /
|
|
549
557
|
# CEDAR (issue #148, issue #135). The raw string is preserved
|
|
550
558
|
# so consumers can audit parsing; ``quantitative_value`` is the
|
|
@@ -557,17 +565,17 @@ def scan(
|
|
|
557
565
|
# KD") is the readout type — combined with ``assay_method``
|
|
558
566
|
# and ``measurement_units`` it tells consumers whether a
|
|
559
567
|
# numeric value is IC50 vs Kd vs t_half vs Tm.
|
|
560
|
-
"assay_method":
|
|
561
|
-
"response_measured":
|
|
562
|
-
"measurement_units":
|
|
563
|
-
"measurement_inequality":
|
|
564
|
-
"quantitative_measurement":
|
|
565
|
-
"quantitative_value": _parse_float(
|
|
568
|
+
"assay_method": fields["assay_method"],
|
|
569
|
+
"response_measured": fields["response_measured"],
|
|
570
|
+
"measurement_units": fields["measurement_units"],
|
|
571
|
+
"measurement_inequality": fields["measurement_inequality"],
|
|
572
|
+
"quantitative_measurement": fields["quantitative_measurement"],
|
|
573
|
+
"quantitative_value": _parse_float(fields["quantitative_measurement"]),
|
|
566
574
|
**assay_annotations(
|
|
567
|
-
|
|
568
|
-
|
|
569
|
-
|
|
570
|
-
|
|
575
|
+
fields["qualitative_measurement"],
|
|
576
|
+
fields["assay_comments"],
|
|
577
|
+
fields["assay_method"],
|
|
578
|
+
fields["response_measured"],
|
|
571
579
|
),
|
|
572
580
|
# Flags rows whose MHC molecule presents lipids / metabolites
|
|
573
581
|
# rather than peptides (CD1, MR1, MIC, ULBP, etc. — see #228).
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
__version__ = "2.1.2"
|
|
@@ -249,6 +249,7 @@ tests/test_assays.py
|
|
|
249
249
|
tests/test_atlas_crosswalk.py
|
|
250
250
|
tests/test_atlas_lineage.py
|
|
251
251
|
tests/test_attribution_query_context.py
|
|
252
|
+
tests/test_benchmark_network.py
|
|
252
253
|
tests/test_binding_assay_context.py
|
|
253
254
|
tests/test_binding_context_availability.py
|
|
254
255
|
tests/test_build_smoke.py
|
|
@@ -157,6 +157,9 @@ include = [
|
|
|
157
157
|
"scripts/profile_mapping_workers.py",
|
|
158
158
|
"scripts/reliability_benchmark.py",
|
|
159
159
|
"scripts/reliability_modal.py",
|
|
160
|
+
"scripts/profile_csv_serialization.py",
|
|
161
|
+
"scripts/paired_build_benchmark.py",
|
|
162
|
+
"scripts/benchmark_site/sitecustomize.py",
|
|
160
163
|
"scripts/check_dev_install.py",
|
|
161
164
|
"scripts/build_uniprot_reference.py",
|
|
162
165
|
"scripts/benchmark_provenance.py",
|
|
@@ -0,0 +1,148 @@
|
|
|
1
|
+
"""Timed-build audits reject attempted network access even if code catches it."""
|
|
2
|
+
|
|
3
|
+
import importlib
|
|
4
|
+
import os
|
|
5
|
+
import subprocess
|
|
6
|
+
import sys
|
|
7
|
+
from pathlib import Path
|
|
8
|
+
|
|
9
|
+
import pytest
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
@pytest.fixture
|
|
13
|
+
def benchmark(monkeypatch):
|
|
14
|
+
scripts = Path(__file__).resolve().parents[1] / "scripts"
|
|
15
|
+
monkeypatch.syspath_prepend(str(scripts))
|
|
16
|
+
module = importlib.import_module("paired_build_benchmark")
|
|
17
|
+
monkeypatch.setattr(module, "GUARD_DIRECTORY", scripts / "benchmark_site")
|
|
18
|
+
return module
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
def test_benchmark_audit_preserves_run_environment(tmp_path, benchmark):
|
|
22
|
+
env = benchmark.audited_environment(
|
|
23
|
+
tmp_path, {"HITLIST_DATA_DIR": "/run/cache", "PYTHONPATH": "/producer"}
|
|
24
|
+
)
|
|
25
|
+
assert env["HITLIST_DATA_DIR"] == "/run/cache"
|
|
26
|
+
assert env["PYTHONPATH"].endswith(os.pathsep + "/producer")
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
def test_network_audit_allows_local_ipc(tmp_path, benchmark):
|
|
30
|
+
code = "import socket; a,b=socket.socketpair(); a.send(b'x'); assert b.recv(1)==b'x'; a.close(); b.close()"
|
|
31
|
+
process = subprocess.Popen(
|
|
32
|
+
[sys.executable, "-c", code], env=benchmark.audited_environment(tmp_path)
|
|
33
|
+
)
|
|
34
|
+
assert process.wait(timeout=20) == 0
|
|
35
|
+
benchmark.check_network_audit(tmp_path, process.pid)
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
@pytest.mark.parametrize(
|
|
39
|
+
"operation",
|
|
40
|
+
["socket.getaddrinfo('example.invalid', 443)", "socket.socket().connect(('127.0.0.1', 9))"],
|
|
41
|
+
)
|
|
42
|
+
def test_caught_network_attempt_still_invalidates_benchmark(tmp_path, benchmark, operation):
|
|
43
|
+
code = f"import socket\ntry:\n {operation}\nexcept RuntimeError:\n pass\n"
|
|
44
|
+
process = subprocess.Popen(
|
|
45
|
+
[sys.executable, "-c", code], env=benchmark.audited_environment(tmp_path)
|
|
46
|
+
)
|
|
47
|
+
assert process.wait(timeout=20) == 0
|
|
48
|
+
with pytest.raises(ValueError, match="attempted network"):
|
|
49
|
+
benchmark.check_network_audit(tmp_path, process.pid)
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
def test_network_guard_reaches_child_interpreters(tmp_path, benchmark):
|
|
53
|
+
child = (
|
|
54
|
+
"import socket\ntry: socket.getaddrinfo('example.invalid', 80)\nexcept RuntimeError: pass"
|
|
55
|
+
)
|
|
56
|
+
parent = f"import subprocess,sys; subprocess.run([sys.executable,'-c',{child!r}],check=True)"
|
|
57
|
+
process = subprocess.Popen(
|
|
58
|
+
[sys.executable, "-c", parent], env=benchmark.audited_environment(tmp_path)
|
|
59
|
+
)
|
|
60
|
+
assert process.wait(timeout=20) == 0
|
|
61
|
+
assert len(list(tmp_path.glob("*.installed"))) == 2
|
|
62
|
+
with pytest.raises(ValueError, match="attempted network"):
|
|
63
|
+
benchmark.check_network_audit(tmp_path, process.pid)
|
|
64
|
+
|
|
65
|
+
|
|
66
|
+
def test_missing_audit_marker_is_not_a_verified_run(tmp_path, benchmark):
|
|
67
|
+
with pytest.raises(ValueError, match="did not install"):
|
|
68
|
+
benchmark.check_network_audit(tmp_path, 123)
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
@pytest.mark.skipif(os.name != "posix", reason="POSIX process-group signal cleanup")
|
|
72
|
+
def test_interrupted_experiment_records_failure_and_reaps_child(tmp_path, benchmark):
|
|
73
|
+
import json
|
|
74
|
+
import signal
|
|
75
|
+
import time
|
|
76
|
+
|
|
77
|
+
config, base, producers = (tmp_path / name for name in ("config", "results", "producers"))
|
|
78
|
+
for directory in (config, base, producers):
|
|
79
|
+
directory.mkdir()
|
|
80
|
+
for name in ("baseline-env", "candidate-env"):
|
|
81
|
+
bin_directory = producers / name / "bin"
|
|
82
|
+
bin_directory.mkdir(parents=True)
|
|
83
|
+
(bin_directory / "python").symlink_to(sys.executable)
|
|
84
|
+
for name in ("baseline.tar.gz", "producer.tar.gz", "sitecustomize.py"):
|
|
85
|
+
(config / name).write_bytes(b"fixture")
|
|
86
|
+
marker = tmp_path / "child.pid"
|
|
87
|
+
(config / "reliability_benchmark.py").write_text(
|
|
88
|
+
"import os,time\nfrom pathlib import Path\n"
|
|
89
|
+
f"marker=Path({str(marker)!r})\ntemporary=marker.with_suffix('.tmp')\n"
|
|
90
|
+
"temporary.write_text(str(os.getpid()))\ntemporary.replace(marker)\ntime.sleep(120)\n"
|
|
91
|
+
)
|
|
92
|
+
code = (
|
|
93
|
+
f"import sys,signal\nsys.path.insert(0,{str(Path(benchmark.__file__).parent)!r})\n"
|
|
94
|
+
"from pathlib import Path\nimport paired_build_benchmark as b\n"
|
|
95
|
+
f"b.CONFIG=Path({str(config)!r}); b.BASE=Path({str(base)!r})\n"
|
|
96
|
+
f"b.GUARD_DIRECTORY=b.CONFIG; b.PRODUCER_ROOT=Path({str(producers)!r})\n"
|
|
97
|
+
"signal.signal(signal.SIGTERM,b.interrupted)\nb.run('interrupted',False)\n"
|
|
98
|
+
)
|
|
99
|
+
with (tmp_path / "parent.log").open("w") as log:
|
|
100
|
+
parent = subprocess.Popen([sys.executable, "-c", code], stdout=log, stderr=log)
|
|
101
|
+
try:
|
|
102
|
+
deadline = time.monotonic() + 15
|
|
103
|
+
while not marker.exists() and time.monotonic() < deadline:
|
|
104
|
+
if parent.poll() is not None:
|
|
105
|
+
pytest.fail((tmp_path / "parent.log").read_text())
|
|
106
|
+
time.sleep(0.02)
|
|
107
|
+
assert marker.exists()
|
|
108
|
+
child_pid = int(marker.read_text())
|
|
109
|
+
parent.send_signal(signal.SIGTERM)
|
|
110
|
+
assert parent.wait(timeout=15) != 0
|
|
111
|
+
with pytest.raises(ProcessLookupError):
|
|
112
|
+
os.kill(child_pid, 0)
|
|
113
|
+
finally:
|
|
114
|
+
if parent.poll() is None:
|
|
115
|
+
parent.send_signal(signal.SIGTERM)
|
|
116
|
+
parent.wait(timeout=15)
|
|
117
|
+
receipt = json.loads((base / "interrupted/experiment.json").read_text())
|
|
118
|
+
assert receipt["status"] == "failed"
|
|
119
|
+
assert receipt["active_run"] == "interrupted-1-baseline"
|
|
120
|
+
assert receipt["runs"] == []
|
|
121
|
+
assert "received signal 15" in (base / "interrupted/failure.txt").read_text()
|
|
122
|
+
|
|
123
|
+
|
|
124
|
+
def test_scan_diagnostic_uses_builder_pmid_projection_and_keeps_originals(tmp_path, benchmark):
|
|
125
|
+
import json
|
|
126
|
+
|
|
127
|
+
import pandas as pd
|
|
128
|
+
|
|
129
|
+
from tests.test_provenance import _row
|
|
130
|
+
from tests.test_scanner import _write_tiny_iedb_csv
|
|
131
|
+
|
|
132
|
+
source = tmp_path / "iedb.csv"
|
|
133
|
+
rows = [_row("integer"), _row("missing"), _row("noninteger")]
|
|
134
|
+
rows[1][2], rows[2][2] = "", "reported-reference"
|
|
135
|
+
_write_tiny_iedb_csv(source, rows)
|
|
136
|
+
output = tmp_path / "result"
|
|
137
|
+
output.mkdir()
|
|
138
|
+
benchmark.scan_child(source, output)
|
|
139
|
+
frame = pd.read_parquet(output / "observations.parquet")
|
|
140
|
+
assert str(frame.pmid.dtype) == "Int64"
|
|
141
|
+
assert frame.pmid.notna().sum() == 1
|
|
142
|
+
links = pd.read_parquet(output / "contributors.parquet").sort_values("source_row")
|
|
143
|
+
assert [json.loads(value)["pmid"] for value in links.original_fields] == [
|
|
144
|
+
"99999999",
|
|
145
|
+
"",
|
|
146
|
+
"reported-reference",
|
|
147
|
+
]
|
|
148
|
+
assert json.loads((output / "report.json").read_text())["status"] == "success"
|
|
@@ -34,6 +34,51 @@ def _row(assay, sample="original sample"):
|
|
|
34
34
|
return row
|
|
35
35
|
|
|
36
36
|
|
|
37
|
+
def test_csv_capture_matches_general_json_bytes_including_short_rows(tmp_path):
|
|
38
|
+
columns = {"z_field": 0, "pmid": 2, 'quoted"key': 1, "a_field": 5}
|
|
39
|
+
rows = [
|
|
40
|
+
[],
|
|
41
|
+
[""],
|
|
42
|
+
['quote" slash\\ control\x00\n\r\t', "café 😀 \ud800", "000123", "unmapped"],
|
|
43
|
+
["a", "b", "paper-id", "", "", "tail", "extra trailing cell"],
|
|
44
|
+
["x" * 20000, "", "42"],
|
|
45
|
+
] * 60
|
|
46
|
+
for variant in ("general", "csv"):
|
|
47
|
+
with ContributorCollector(scratch_dir=tmp_path) as collector:
|
|
48
|
+
collector._OUTPUT_BATCH_BYTES = 12000
|
|
49
|
+
capture_csv = collector.csv_record_writer("test / é", columns)
|
|
50
|
+
roots = []
|
|
51
|
+
for row_number, row in enumerate(rows, 1):
|
|
52
|
+
if variant == "csv":
|
|
53
|
+
record = capture_csv(row_number, row)
|
|
54
|
+
else:
|
|
55
|
+
fields = {
|
|
56
|
+
name: row[index] if index < len(row) else ""
|
|
57
|
+
for name, index in columns.items()
|
|
58
|
+
}
|
|
59
|
+
record = collector.record("test / é", row_number, fields, row)
|
|
60
|
+
roots.append(collector.observe(record, "donor" if row_number % 2 else ""))
|
|
61
|
+
collector.write(
|
|
62
|
+
[pd.DataFrame({"provenance_id": roots})], tmp_path / f"{variant}.parquet"
|
|
63
|
+
)
|
|
64
|
+
assert (tmp_path / "csv.parquet").read_bytes() == (tmp_path / "general.parquet").read_bytes()
|
|
65
|
+
actual = pd.read_parquet(tmp_path / "csv.parquet").sort_values("source_row")
|
|
66
|
+
for record, row in zip(actual.itertuples(), rows):
|
|
67
|
+
expected_fields = {
|
|
68
|
+
name: row[index] if index < len(row) else "" for name, index in columns.items()
|
|
69
|
+
}
|
|
70
|
+
assert record.original_fields == json.dumps(expected_fields, sort_keys=True)
|
|
71
|
+
assert record.source_row_values == json.dumps(row)
|
|
72
|
+
|
|
73
|
+
|
|
74
|
+
def test_csv_capture_rejects_duplicate_record_immediately(tmp_path):
|
|
75
|
+
with ContributorCollector(scratch_dir=tmp_path) as collector:
|
|
76
|
+
capture = collector.csv_record_writer("iedb", {"pmid": 0})
|
|
77
|
+
capture(1, ["1"])
|
|
78
|
+
with pytest.raises(sqlite3.IntegrityError):
|
|
79
|
+
capture(1, ["2"])
|
|
80
|
+
|
|
81
|
+
|
|
37
82
|
def test_chained_dedup_retains_sources_without_reweighting(tmp_path, monkeypatch):
|
|
38
83
|
iedb, cedar = tmp_path / "iedb.csv", tmp_path / "cedar.csv"
|
|
39
84
|
_write_tiny_iedb_csv(
|
hitlist-2.1.0/hitlist/version.py
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
__version__ = "2.1.0"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{hitlist-2.1.0 → hitlist-2.1.2}/hitlist/data/evidence_revisions/binding_assay_protocols.json
RENAMED
|
File without changes
|
|
File without changes
|