tablassert 18.0.0__tar.gz → 19.0.0__tar.gz

{tablassert-18.0.0 → tablassert-19.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tablassert
-Version: 18.0.0
+Version: 19.0.0
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
@@ -27,12 +27,12 @@ Requires-Dist: polars>=1.39.0
 Requires-Dist: rapidfuzz>=3.14.3
 Requires-Dist: pydantic>=2.12.5
 Requires-Dist: pyyaml>=6.0.3
-Requires-Dist: cyclopts>=1.0.0
-Requires-Dist: rich>=13.0.0
 Requires-Dist: fastexcel>=0.20.2
 Requires-Dist: smolagents>=1.26.0 ; extra == 'agent'
 Requires-Dist: litellm>=1.93.0 ; extra == 'agent'
 Requires-Dist: aria2==0.0.1b0 ; extra == 'aria2'
+Requires-Dist: cyclopts>=1.0.0 ; extra == 'cli'
+Requires-Dist: rich>=13.0.0 ; extra == 'cli'
 Requires-Dist: datasets>=3.0.0 ; extra == 'distill'
 Requires-Dist: loguru>=0.7.3 ; extra == 'log'
 Requires-Dist: dspy>=3.2.1 ; extra == 'optimize'
@@ -41,6 +41,7 @@ Requires-Dist: sentence-transformers>=5.3.0 ; extra == 'qc'
 Requires-Dist: polars[rtcompat]>=1.40.1 ; extra == 'rt'
 Provides-Extra: agent
 Provides-Extra: aria2
+Provides-Extra: cli
 Provides-Extra: distill
 Provides-Extra: log
 Provides-Extra: optimize
@@ -60,7 +61,6 @@ Project-URL: Source, https://github.com/SkyeAv/Tablassert
 # Tablassert
 
 [![PyPI](https://img.shields.io/pypi/v/tablassert.svg)](https://pypi.org/project/tablassert/)
-[![Downloads](https://img.shields.io/pypi/dm/tablassert.svg)](https://pypi.org/project/tablassert/)
 [![Python](https://img.shields.io/pypi/pyversions/tablassert.svg)](https://pypi.org/project/tablassert/)
 [![CI](https://github.com/SkyeAv/Tablassert/actions/workflows/ci.yml/badge.svg)](https://github.com/SkyeAv/Tablassert/actions/workflows/ci.yml)
 [![License](https://img.shields.io/pypi/l/tablassert.svg)](https://github.com/SkyeAv/Tablassert/blob/main/LICENSE)
@@ -170,23 +170,24 @@ See the [Tutorial](https://skyeav.github.io/Tablassert/tutorial/) for the full w
 pip install tablassert
 ```
 
-Or with uv: `uv tool install tablassert`. The base install builds knowledge graphs from
-CSV/TSV/Excel sources; optional extras add runtime and pipeline capabilities:
+Or with uv: `uv tool install "tablassert[cli]"`. The base install provides the Python API;
+install `[cli]` to use the `tablassert` command and optional extras for additional runtime and pipeline capabilities:
 
 | Extra | Adds | Install |
 | ----- | ---- | ------- |
+| `cli` | `tablassert` command and rich terminal progress | `pip install "tablassert[cli]"` |
 | `rt` | CPU-compatible Polars runtime | `pip install "tablassert[rt]"` |
-| `aria2` | bundled aria2c downloader for `build-fullmap --aria2c` (Linux/Windows wheels only) | `pip install "tablassert[aria2]"` |
+| `aria2` | bundled aria2c downloader, used automatically by `build-fullmap` when installed (Linux/Windows wheels only) | `pip install "tablassert[aria2]"` |
 | `qc` | four-stage QC audit (exact → fuzzy → abbreviation → SapBERT embeddings) | `pip install "tablassert[qc]"` |
 | `agent` | autonomous agent (smolagents, litellm, article/table context) | `pip install "tablassert[agent]"` |
 | `optimize` | GEPA prompt optimization for `agent --optimize` (dspy) | `pip install "tablassert[optimize]"` |
 | `distill` | distillation dataset export (`tablassert distill-export`, HF `datasets`) | `pip install "tablassert[distill]"` |
 | `log` | loguru-backed file/progress logging (rotation, enqueue) | `pip install "tablassert[log]"` |
 
-QC is opt-in at build time (`build-kg --qc`). Reaching a feature whose extra is not installed never
+The `tablassert` command requires `[cli]`; without it, the console launcher reports the exact install command. QC is opt-in at build time (`build-kg --qc`). Reaching a feature whose extra is not installed never
 produces a bare `ModuleNotFoundError`: the failure names the missing package and the exact install
 command, and for `build-kg --qc` and `tablassert agent` it arrives before the run starts rather than
-partway through. Logging is the exception: without the `log` extra it degrades to a stdlib fallback
+partway through. Logging is the exception: without the `log` extra Tablassert produces no logs
 instead of failing. See the
 [Installation guide](https://skyeav.github.io/Tablassert/installation/) for the full matrix and the
 [CLI Reference](https://skyeav.github.io/Tablassert/cli/) for every flag.
@@ -226,7 +227,7 @@ no LazyFrame setup or NLP preprocessing required. See the
 ## Developing
 
 ```bash
-uv sync --group dev --extra qc --extra log
+uv sync --group dev --extra cli --extra qc --extra log
 uv run maturin develop --manifest-path rust/Cargo.toml
 make check
 ```

{tablassert-18.0.0 → tablassert-19.0.0}/README.md

@@ -1,7 +1,6 @@
 # Tablassert
 
 [![PyPI](https://img.shields.io/pypi/v/tablassert.svg)](https://pypi.org/project/tablassert/)
-[![Downloads](https://img.shields.io/pypi/dm/tablassert.svg)](https://pypi.org/project/tablassert/)
 [![Python](https://img.shields.io/pypi/pyversions/tablassert.svg)](https://pypi.org/project/tablassert/)
 [![CI](https://github.com/SkyeAv/Tablassert/actions/workflows/ci.yml/badge.svg)](https://github.com/SkyeAv/Tablassert/actions/workflows/ci.yml)
 [![License](https://img.shields.io/pypi/l/tablassert.svg)](https://github.com/SkyeAv/Tablassert/blob/main/LICENSE)
@@ -111,23 +110,24 @@ See the [Tutorial](https://skyeav.github.io/Tablassert/tutorial/) for the full w
 pip install tablassert
 ```
 
-Or with uv: `uv tool install tablassert`. The base install builds knowledge graphs from
-CSV/TSV/Excel sources; optional extras add runtime and pipeline capabilities:
+Or with uv: `uv tool install "tablassert[cli]"`. The base install provides the Python API;
+install `[cli]` to use the `tablassert` command and optional extras for additional runtime and pipeline capabilities:
 
 | Extra | Adds | Install |
 | ----- | ---- | ------- |
+| `cli` | `tablassert` command and rich terminal progress | `pip install "tablassert[cli]"` |
 | `rt` | CPU-compatible Polars runtime | `pip install "tablassert[rt]"` |
-| `aria2` | bundled aria2c downloader for `build-fullmap --aria2c` (Linux/Windows wheels only) | `pip install "tablassert[aria2]"` |
+| `aria2` | bundled aria2c downloader, used automatically by `build-fullmap` when installed (Linux/Windows wheels only) | `pip install "tablassert[aria2]"` |
 | `qc` | four-stage QC audit (exact → fuzzy → abbreviation → SapBERT embeddings) | `pip install "tablassert[qc]"` |
 | `agent` | autonomous agent (smolagents, litellm, article/table context) | `pip install "tablassert[agent]"` |
 | `optimize` | GEPA prompt optimization for `agent --optimize` (dspy) | `pip install "tablassert[optimize]"` |
 | `distill` | distillation dataset export (`tablassert distill-export`, HF `datasets`) | `pip install "tablassert[distill]"` |
 | `log` | loguru-backed file/progress logging (rotation, enqueue) | `pip install "tablassert[log]"` |
 
-QC is opt-in at build time (`build-kg --qc`). Reaching a feature whose extra is not installed never
+The `tablassert` command requires `[cli]`; without it, the console launcher reports the exact install command. QC is opt-in at build time (`build-kg --qc`). Reaching a feature whose extra is not installed never
 produces a bare `ModuleNotFoundError`: the failure names the missing package and the exact install
 command, and for `build-kg --qc` and `tablassert agent` it arrives before the run starts rather than
-partway through. Logging is the exception: without the `log` extra it degrades to a stdlib fallback
+partway through. Logging is the exception: without the `log` extra Tablassert produces no logs
 instead of failing. See the
 [Installation guide](https://skyeav.github.io/Tablassert/installation/) for the full matrix and the
 [CLI Reference](https://skyeav.github.io/Tablassert/cli/) for every flag.
@@ -167,7 +167,7 @@ no LazyFrame setup or NLP preprocessing required. See the
 ## Developing
 
 ```bash
-uv sync --group dev --extra qc --extra log
+uv sync --group dev --extra cli --extra qc --extra log
 uv run maturin develop --manifest-path rust/Cargo.toml
 make check
 ```

{tablassert-18.0.0 → tablassert-19.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tablassert"
-version = "18.0.0"
+version = "19.0.0"
 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" }
@@ -52,8 +52,6 @@ dependencies = [
     "rapidfuzz>=3.14.3",
     "pydantic>=2.12.5",
     "pyyaml>=6.0.3",
-    "cyclopts>=1.0.0",
-    "rich>=13.0.0",
     "fastexcel>=0.20.2",
 ]
 
@@ -72,11 +70,16 @@ module-name = "tablassert.rs"
 bindings = "pyo3"
 manifest-path = "rust/Cargo.toml"
 features = ["extension-module"]
+include = ["src/tablassert/data/experimental_taxa.yaml"]
 
 [project.scripts]
-tablassert = "tablassert.cli:APP"
+tablassert = "tablassert.cli_entry:main"
 
 [project.optional-dependencies]
+cli = [
+    "cyclopts>=1.0.0",
+    "rich>=13.0.0",
+]
 rt = [
     "polars[rtcompat]>=1.40.1",
 ]

{tablassert-18.0.0 → tablassert-19.0.0}/rust/Cargo.lock

@@ -456,6 +456,16 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "rust-stemmers"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e46a2036019fdb888131db7a4c847a1063a7493f971ed94ea82c67eada63ca54"
+dependencies = [
+ "serde",
+ "serde_derive",
+]
+
 [[package]]
 name = "rustc-hash"
 version = "1.1.0"
@@ -566,6 +576,7 @@ dependencies = [
  "rayon",
  "redb",
  "rlimit",
+ "rust-stemmers",
  "rustc-hash",
  "serde",
  "serde_json",

{tablassert-18.0.0 → tablassert-19.0.0}/rust/Cargo.toml

@@ -35,6 +35,11 @@ rayon = "1"
 redb = { git = "https://github.com/cberner/redb.git", rev = "a35e7cc86f191d08a444d5973469b34673d586fc", features = ["experimental_cursor"] }
 rlimit = "0.10"
 rustc-hash = "1"
+# English (Porter2) stemmer for `nlp::normalize_l1` term normalization: pure
+# Rust (no dictionaries, no C deps) and fast enough for the per-token hot path;
+# it requires already-lowercased input, which the pipeline guarantees by
+# lowercasing the whole term before splitting/stemming.
+rust-stemmers = "1"
 serde = { version = "1", features = ["derive"] }
 serde_json = { version = "1", features = ["preserve_order"] }
 tar = "0.4"