tablassert 7.5.2__tar.gz → 8.0.0__tar.gz

{tablassert-7.5.2 → tablassert-8.0.0}/PKG-INFO

@@ -1,58 +1,53 @@
 Metadata-Version: 2.4
 Name: tablassert
-Version: 7.5.2
-Summary: Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in.
-Project-URL: Homepage, https://github.com/SkyeAv/Tablassert
-Project-URL: Source, https://github.com/SkyeAv/Tablassert
-Project-URL: Documentation, https://skyeav.github.io/Tablassert/
-Author-email: Skye Lane Goetz <sgoetz@isbscience.org>
-License-Expression: Apache-2.0
-License-File: LICENSE
-Keywords: bioinformatics,data quality control,declarative pipeline,entity resolution,kgx,knowledge graph,ncats translator,ner,tablassert,table mining,yaml configuration
+Version: 8.0.0
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Development Status :: 5 - Production/Stable
-Classifier: Environment :: Console
-Classifier: Framework :: Pydantic
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Healthcare Industry
 Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Healthcare Industry
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Database
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Requires-Python: >=3.11
-Requires-Dist: cyclopts>=1.0.0
-Requires-Dist: diskcache>=5.6.3
-Requires-Dist: duckdb>=1.5.0
-Requires-Dist: fastexcel>=0.19.0
-Requires-Dist: httpx>=0.28.1
-Requires-Dist: lazy-loader>=0.5
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Rust
+Classifier: Framework :: Pydantic
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Environment :: Console
+Requires-Dist: biolink-model>=4.4.3
 Requires-Dist: loguru>=0.7.3
-Requires-Dist: optimum-onnx>=0.1.0
-Requires-Dist: orjson>=3.11.7
-Requires-Dist: playwright<1.59,>=1.58.0
-Requires-Dist: polars-hash>=0.5.6
 Requires-Dist: polars>=1.39.0
-Requires-Dist: pyarrow>=23.0.1
+Requires-Dist: rapidfuzz>=3.14.3
 Requires-Dist: pydantic>=2.12.5
-Requires-Dist: pyexcel>=0.7.4
 Requires-Dist: pyyaml>=6.0.3
-Requires-Dist: rapidfuzz>=3.14.3
+Requires-Dist: cyclopts>=1.0.0
 Requires-Dist: rich>=13.0.0
-Requires-Dist: scikit-learn>=1.8.0
-Requires-Dist: sentence-transformers>=5.3.0
-Requires-Dist: sqlite-utils>=3.39
-Requires-Dist: xxhash>=3.6.0
+Requires-Dist: fastexcel>=0.20.2
+Requires-Dist: smolagents>=1.26.0 ; extra == 'agent'
+Requires-Dist: dspy>=3.2.1 ; extra == 'agent'
+Requires-Dist: litellm>=1.93.0 ; extra == 'agent'
+Requires-Dist: scikit-learn>=1.8.0 ; extra == 'qc'
+Requires-Dist: sentence-transformers>=5.3.0 ; extra == 'qc'
+Requires-Dist: polars[rtcompat]>=1.40.1 ; extra == 'rt'
+Provides-Extra: agent
 Provides-Extra: qc
-Requires-Dist: onnxruntime>=1.24.4; extra == 'qc'
-Provides-Extra: qc-cuda
-Requires-Dist: onnxruntime-gpu>=1.24.4; extra == 'qc-cuda'
 Provides-Extra: rt
-Requires-Dist: polars[rtcompat]>=1.40.1; extra == 'rt'
-Description-Content-Type: text/markdown
+License-File: LICENSE
+Summary: Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in.
+Keywords: knowledge graph,bioinformatics,entity resolution,ner,ncats translator,kgx,yaml configuration,table mining,declarative pipeline,data quality control,tablassert
+Author-email: Skye Lane Goetz <sgoetz@isbscience.org>
+License-Expression: Apache-2.0
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Documentation, https://skyeav.github.io/Tablassert/
+Project-URL: Homepage, https://github.com/SkyeAv/Tablassert
+Project-URL: Source, https://github.com/SkyeAv/Tablassert
 
 # Tablassert
 
@@ -65,7 +60,7 @@ Extract knowledge assertions from tabular data into NCATS Translator-compliant K
 
 ```bash
 pip install tablassert
-tablassert build config.yaml
+tablassert build-kg config.yaml
 ```
 
 **[Full Documentation](https://skyeav.github.io/Tablassert/)** — installation guides, tutorials, configuration reference, and API docs.
@@ -76,30 +71,16 @@ tablassert build config.yaml
 pip install tablassert
 ```
 
-Base install includes web and Excel support. Optional extras are available for CPU compatibility and QC runtime selection:
+The base install includes everything needed to build knowledge graphs from CSV/TSV sources. Optional extras are available for CPU compatibility and quality control:
 
 ```bash
-pip install "tablassert[rt]"       # Polars build for CPUs without required instructions
-pip install "tablassert[qc]"       # Enable QC with CPU ONNX Runtime
-pip install "tablassert[qc-cuda]"  # Enable QC with CUDA ONNX Runtime on GPU 0
+pip install "tablassert[rt]"  # Polars build for CPUs without the required instructions
+pip install "tablassert[qc]"  # Enable QC (torch + sentence-transformers BioBERT, scikit-learn)
 ```
 
-QC is disabled by default at the graph level. Set `qc: true` in a graph config to enable the audit stage.
-
-<details>
-<summary><strong>Docker</strong></summary>
-
-```bash
-docker pull ghcr.io/skyeav/tablassert:latest
-
-docker run --rm \
-  -v /path/to/config:/data \
-  -v /path/to/datassert:/datassert \
-  ghcr.io/skyeav/tablassert:latest \
-  build /data/graph-config.yaml
-```
+Excel (`.xlsx`) inputs are read through Polars' `calamine` engine and additionally require `python-calamine` (`pip install python-calamine`).
 
-</details>
+QC is opt-in: pass `--qc` to `build-kg` to run the three-stage audit (exact → fuzzy → BioBERT). See the [CLI Reference](https://skyeav.github.io/Tablassert/cli/) for the full flag reference.
 
 ## Quick Demo
 
@@ -107,22 +88,22 @@ docker run --rm \
 from pathlib import Path
 from tablassert.lib import resolve_many
 
-# Resolve gene names to CURIEs against a datassert database
+# Resolve gene names to CURIEs against a fullmap database
 results = resolve_many(
     col="gene",
     entities=["TP53", "BRCA1", "EGFR"],
-    datassert=Path("/path/to/datassert"),
+    fullmap=Path("/path/to/fullmap"),
     taxon="9606",
 )
 
 for row in results:
-    print(f"{row['original gene']} → {row['gene']} ({row['gene name']})")
+    print(f"{row['original_gene']} → {row['gene']} ({row['gene_name']})")
 # TP53 → HGNC:11998 (TP53)
 # BRCA1 → HGNC:1100 (BRCA1)
 # EGFR → HGNC:3236 (EGFR)
 ```
 
-Point `resolve_many()` at a datassert database and resolve any iterable of entity strings to CURIEs — no LazyFrame setup, NLP preprocessing, or DuckDB connection management required. For full pipeline builds with YAML configuration, use `tablassert build config.yaml`.
+Point `resolve_many()` at a fullmap database and resolve any iterable of entity strings to CURIEs — no LazyFrame setup or NLP preprocessing required. For full pipeline builds with YAML configuration, use `tablassert build-kg config.yaml`.
 
 ## Key Features
 
@@ -130,11 +111,17 @@ Point `resolve_many()` at a datassert database and resolve any iterable of entit
 - **Entity Resolution** — Maps text to biological entities (genes, diseases, chemicals)
 - **Quality Control** — Optional three-stage validation (exact → fuzzy → BERT embeddings)
 - **KGX Compliance** — NCATS Translator-compatible NDJSON output
-- **Performance** — Lazy evaluation pipelines with Polars and DuckDB-accelerated entity resolution
+- **Performance** — Lazy evaluation pipelines with Polars and an embedded redb-accelerated entity resolution database
 
-## Contributing
+## Developing
 
-See **[CONTRIBUTING.md](CONTRIBUTING.md)** for development setup, code style, and pull request guidelines.
+```bash
+uv sync --group dev --extra qc
+uv run maturin develop --manifest-path rust/Cargo.toml
+make check
+```
+
+See **[CONTRIBUTING.md](CONTRIBUTING.md)** for the full development loop, quality gates, and pull request guidelines.
 
 ## License
 
@@ -142,8 +129,9 @@ See **[CONTRIBUTING.md](CONTRIBUTING.md)** for development setup, code style, an
 
 ## Contributors
 
-[Skye Lane Goetz](mailto:sgoetz@isbscience.org) — Institute for Systems Biology, CalPoly SLO
+[Skye Lane Goetz](mailto:sgoetz@isbscience.org) — Institute for Systems Biology
 
 [Gwênlyn Glusman](mailto:gglusman@isbscience.org) — Institute for Systems Biology
 
 Jared C. Roach — Institute for Systems Biology
+

{tablassert-7.5.2 → tablassert-8.0.0}/README.md

@@ -9,7 +9,7 @@ Extract knowledge assertions from tabular data into NCATS Translator-compliant K
 
 ```bash
 pip install tablassert
-tablassert build config.yaml
+tablassert build-kg config.yaml
 ```
 
 **[Full Documentation](https://skyeav.github.io/Tablassert/)** — installation guides, tutorials, configuration reference, and API docs.
@@ -20,30 +20,16 @@ tablassert build config.yaml
 pip install tablassert
 ```
 
-Base install includes web and Excel support. Optional extras are available for CPU compatibility and QC runtime selection:
+The base install includes everything needed to build knowledge graphs from CSV/TSV sources. Optional extras are available for CPU compatibility and quality control:
 
 ```bash
-pip install "tablassert[rt]"       # Polars build for CPUs without required instructions
-pip install "tablassert[qc]"       # Enable QC with CPU ONNX Runtime
-pip install "tablassert[qc-cuda]"  # Enable QC with CUDA ONNX Runtime on GPU 0
+pip install "tablassert[rt]"  # Polars build for CPUs without the required instructions
+pip install "tablassert[qc]"  # Enable QC (torch + sentence-transformers BioBERT, scikit-learn)
 ```
 
-QC is disabled by default at the graph level. Set `qc: true` in a graph config to enable the audit stage.
+Excel (`.xlsx`) inputs are read through Polars' `calamine` engine and additionally require `python-calamine` (`pip install python-calamine`).
 
-<details>
-<summary><strong>Docker</strong></summary>
-
-```bash
-docker pull ghcr.io/skyeav/tablassert:latest
-
-docker run --rm \
-  -v /path/to/config:/data \
-  -v /path/to/datassert:/datassert \
-  ghcr.io/skyeav/tablassert:latest \
-  build /data/graph-config.yaml
-```
-
-</details>
+QC is opt-in: pass `--qc` to `build-kg` to run the three-stage audit (exact → fuzzy → BioBERT). See the [CLI Reference](https://skyeav.github.io/Tablassert/cli/) for the full flag reference.
 
 ## Quick Demo
 
@@ -51,22 +37,22 @@ docker run --rm \
 from pathlib import Path
 from tablassert.lib import resolve_many
 
-# Resolve gene names to CURIEs against a datassert database
+# Resolve gene names to CURIEs against a fullmap database
 results = resolve_many(
     col="gene",
     entities=["TP53", "BRCA1", "EGFR"],
-    datassert=Path("/path/to/datassert"),
+    fullmap=Path("/path/to/fullmap"),
     taxon="9606",
 )
 
 for row in results:
-    print(f"{row['original gene']} → {row['gene']} ({row['gene name']})")
+    print(f"{row['original_gene']} → {row['gene']} ({row['gene_name']})")
 # TP53 → HGNC:11998 (TP53)
 # BRCA1 → HGNC:1100 (BRCA1)
 # EGFR → HGNC:3236 (EGFR)
 ```
 
-Point `resolve_many()` at a datassert database and resolve any iterable of entity strings to CURIEs — no LazyFrame setup, NLP preprocessing, or DuckDB connection management required. For full pipeline builds with YAML configuration, use `tablassert build config.yaml`.
+Point `resolve_many()` at a fullmap database and resolve any iterable of entity strings to CURIEs — no LazyFrame setup or NLP preprocessing required. For full pipeline builds with YAML configuration, use `tablassert build-kg config.yaml`.
 
 ## Key Features
 
@@ -74,11 +60,17 @@ Point `resolve_many()` at a datassert database and resolve any iterable of entit
 - **Entity Resolution** — Maps text to biological entities (genes, diseases, chemicals)
 - **Quality Control** — Optional three-stage validation (exact → fuzzy → BERT embeddings)
 - **KGX Compliance** — NCATS Translator-compatible NDJSON output
-- **Performance** — Lazy evaluation pipelines with Polars and DuckDB-accelerated entity resolution
+- **Performance** — Lazy evaluation pipelines with Polars and an embedded redb-accelerated entity resolution database
+
+## Developing
 
-## Contributing
+```bash
+uv sync --group dev --extra qc
+uv run maturin develop --manifest-path rust/Cargo.toml
+make check
+```
 
-See **[CONTRIBUTING.md](CONTRIBUTING.md)** for development setup, code style, and pull request guidelines.
+See **[CONTRIBUTING.md](CONTRIBUTING.md)** for the full development loop, quality gates, and pull request guidelines.
 
 ## License
 
@@ -86,7 +78,7 @@ See **[CONTRIBUTING.md](CONTRIBUTING.md)** for development setup, code style, an
 
 ## Contributors
 
-[Skye Lane Goetz](mailto:sgoetz@isbscience.org) — Institute for Systems Biology, CalPoly SLO
+[Skye Lane Goetz](mailto:sgoetz@isbscience.org) — Institute for Systems Biology
 
 [Gwênlyn Glusman](mailto:gglusman@isbscience.org) — Institute for Systems Biology
 

{tablassert-7.5.2 → tablassert-8.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tablassert"
-version = "7.5.2"
+version = "8.0.0"
 description = "Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON — declaratively, with entity resolution and quality control built in."
 authors = [
     { name = "Skye Lane Goetz", email = "sgoetz@isbscience.org" }
@@ -20,6 +20,7 @@ keywords = [
 ]
 readme = "README.md"
 license = "Apache-2.0"
+license-files = ["LICENSE"]
 classifiers = [
     "License :: OSI Approved :: Apache Software License",
     "Development Status :: 5 - Production/Stable",
@@ -28,38 +29,30 @@ classifiers = [
     "Intended Audience :: Developers",
     "Topic :: Scientific/Engineering :: Bio-Informatics",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+    "Topic :: Database",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: Implementation :: CPython",
+    "Programming Language :: Rust",
     "Framework :: Pydantic",
-    "Operating System :: OS Independent",
+    "Operating System :: POSIX :: Linux",
+    "Operating System :: MacOS :: MacOS X",
     "Environment :: Console",
 ]
 requires-python = ">=3.11"
 dependencies = [
-    "duckdb>=1.5.0",
-    "fastexcel>=0.19.0",
-    "httpx>=0.28.1",
-    "lazy-loader>=0.5",
+    "biolink-model>=4.4.3",
     "loguru>=0.7.3",
-    "optimum-onnx>=0.1.0",
-    "orjson>=3.11.7",
-    "playwright>=1.58.0,<1.59",
     "polars>=1.39.0",
-    "polars-hash>=0.5.6",
-    "pyarrow>=23.0.1",
+    "rapidfuzz>=3.14.3",
     "pydantic>=2.12.5",
-    "pyexcel>=0.7.4",
     "pyyaml>=6.0.3",
-    "rapidfuzz>=3.14.3",
-    "scikit-learn>=1.8.0",
-    "sentence-transformers>=5.3.0",
-    "sqlite-utils>=3.39",
     "cyclopts>=1.0.0",
     "rich>=13.0.0",
-    "xxhash>=3.6.0",
-    "diskcache>=5.6.3",
+    "fastexcel>=0.20.2",
 ]
 
 [project.urls]
@@ -68,11 +61,15 @@ Source = "https://github.com/SkyeAv/Tablassert"
 Documentation = "https://skyeav.github.io/Tablassert/"
 
 [build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
+requires = ["maturin>=1.10,<2.0"]
+build-backend = "maturin"
 
-[tool.hatch.build.targets.wheel]
-packages = ["./src/tablassert"]
+[tool.maturin]
+python-source = "src"
+module-name = "tablassert.rs"
+bindings = "pyo3"
+manifest-path = "rust/Cargo.toml"
+features = ["extension-module"]
 
 [project.scripts]
 tablassert = "tablassert.cli:APP"
@@ -82,15 +79,20 @@ rt = [
     "polars[rtcompat]>=1.40.1",
 ]
 qc = [
-    "onnxruntime>=1.24.4",
+    "scikit-learn>=1.8.0",
+    "sentence-transformers>=5.3.0",
 ]
-qc-cuda = [
-    "onnxruntime-gpu>=1.24.4",
+agent = [
+    "smolagents>=1.26.0",
+    "dspy>=3.2.1",
+    "litellm>=1.93.0",
 ]
 
 [dependency-groups]
 dev = [
     "mkdocs>=1.6.1",
+    "mkdocs-material>=9.6.0",
+    "maturin>=1.10,<2.0",
     "pre-commit>=4.5.1",
     "pyright>=1.1.411",
     "pytest>=9.0.2",
@@ -100,14 +102,55 @@ dev = [
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
-markers = ["network: requires internet", "gpu: requires CUDAExecutionProvider"]
+addopts = "--cov=tablassert --cov-report=term-missing"
+markers = ["network: requires internet"]
+
+[tool.coverage.run]
+source = ["src/tablassert"]
 
 [tool.ruff]
-line-length = 120
+line-length = 150
 indent-width = 4
 target-version = "py311"
 
+[tool.ruff.lint]
+select = [
+    "E4", # pycodestyle E4xx
+    "E7", # pycodestyle E7xx
+    "E9", # pycodestyle E9xx
+    "F", # pyflakes
+    "RUF100", # stale noqa
+    "B", # flake8-bugbear
+    "SIM", # flake8-simplify
+    "C4", # flake8-comprehensions
+    "PT", # flake8-pytest-style
+    "RUF", # ruff-specific
+    "TID", # flake8-tidy-imports
+    "I", # isort
+    "PIE", # flake8-pie
+    "RET", # flake8-return
+    "UP", # pyupgrade
+]
+ignore = [
+    "UP042", # keep enum/str-conversion behavior as-is
+]
+
+[tool.ruff.lint.isort]
+# Align isort with `format.skip-magic-trailing-comma = true` (avoids the ruff incompatibility warning).
+split-on-trailing-comma = false
+
 [tool.ruff.format]
 quote-style = "double"
 indent-style = "space"
 skip-magic-trailing-comma = true
+
+[tool.pyright]
+include = ["src", "tests"]
+pythonVersion = "3.11"
+strictListInference = true
+strictDictionaryInference = true
+strictSetInference = true
+reportMissingTypeStubs = false
+reportUnusedImport = true
+reportUnusedVariable = true
+reportDuplicateImport = true