tablassert 11.0.0__tar.gz → 12.0.0__tar.gz

{tablassert-11.0.0 → tablassert-12.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tablassert
-Version: 11.0.0
+Version: 12.0.0
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
@@ -150,7 +150,7 @@ See the [Tutorial](https://skyeav.github.io/Tablassert/tutorial/) for the full w
 - **Declarative YAML configuration** — define data transformations without writing code
 - **Built-in entity resolution** — map free text to genes, diseases, and chemicals with standard
   CURIEs, taxonomic filtering, and provenance, backed by an embedded redb database
-- **Optional quality control** — a three-stage audit (exact → fuzzy → BioBERT embeddings) flags
+- **Optional quality control** — a four-stage audit (exact → fuzzy → abbreviation → SapBERT embeddings) flags
   low-confidence mappings
 - **KGX compliance** — emits NCATS Translator-compatible node/edge NDJSON with Biolink categories
   and predicates
@@ -171,7 +171,7 @@ CSV/TSV/Excel sources; optional extras add runtime and pipeline capabilities:
 | ----- | ---- | ------- |
 | `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]"` |
-| `qc` | three-stage QC audit (exact → fuzzy → BioBERT embeddings) | `pip install "tablassert[qc]"` |
+| `qc` | four-stage QC audit (exact → fuzzy → abbreviation → SapBERT embeddings) | `pip install "tablassert[qc]"` |
 | `agent` | autonomous agent (smolagents, litellm, PDF context) | `pip install "tablassert[agent]"` |
 | `optimize` | GEPA prompt optimization for `agent --optimize` (dspy) | `pip install "tablassert[optimize]"` |
 

{tablassert-11.0.0 → tablassert-12.0.0}/README.md

@@ -95,7 +95,7 @@ See the [Tutorial](https://skyeav.github.io/Tablassert/tutorial/) for the full w
 - **Declarative YAML configuration** — define data transformations without writing code
 - **Built-in entity resolution** — map free text to genes, diseases, and chemicals with standard
   CURIEs, taxonomic filtering, and provenance, backed by an embedded redb database
-- **Optional quality control** — a three-stage audit (exact → fuzzy → BioBERT embeddings) flags
+- **Optional quality control** — a four-stage audit (exact → fuzzy → abbreviation → SapBERT embeddings) flags
   low-confidence mappings
 - **KGX compliance** — emits NCATS Translator-compatible node/edge NDJSON with Biolink categories
   and predicates
@@ -116,7 +116,7 @@ CSV/TSV/Excel sources; optional extras add runtime and pipeline capabilities:
 | ----- | ---- | ------- |
 | `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]"` |
-| `qc` | three-stage QC audit (exact → fuzzy → BioBERT embeddings) | `pip install "tablassert[qc]"` |
+| `qc` | four-stage QC audit (exact → fuzzy → abbreviation → SapBERT embeddings) | `pip install "tablassert[qc]"` |
 | `agent` | autonomous agent (smolagents, litellm, PDF context) | `pip install "tablassert[agent]"` |
 | `optimize` | GEPA prompt optimization for `agent --optimize` (dspy) | `pip install "tablassert[optimize]"` |
 

{tablassert-11.0.0 → tablassert-12.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tablassert"
-version = "11.0.0"
+version = "12.0.0"
 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" }

{tablassert-11.0.0 → tablassert-12.0.0}/rust/Cargo.lock

@@ -45,6 +45,8 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c89588d05638b5b4594a3348a2d6c20277e43a7f5c5202b05cc56888475a47b8"
 dependencies = [
  "find-msvc-tools",
+ "jobserver",
+ "libc",
  "shlex",
 ]
 
@@ -127,6 +129,16 @@ version = "2.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f1f227452a390804cdb637b74a86990f2a7d7ba4b7d5693aac9b4dd6defd8d6"
 
+[[package]]
+name = "filetime"
+version = "0.2.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c287a33c7f0a620c38e641e7f60827713987b3c0f26e8ddc9462cc69cf75759"
+dependencies = [
+ "cfg-if",
+ "libc",
+]
+
 [[package]]
 name = "find-msvc-tools"
 version = "0.1.9"
@@ -216,6 +228,16 @@ version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
 
+[[package]]
+name = "jobserver"
+version = "0.1.35"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1c00acbd29eabad4a2392fa0e921c874934dbbf4194312ad20f04a0ed67a3cb3"
+dependencies = [
+ "getrandom",
+ "libc",
+]
+
 [[package]]
 name = "js-sys"
 version = "0.3.103"
@@ -304,6 +326,12 @@ version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
 
+[[package]]
+name = "pkg-config"
+version = "0.3.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6b464fbc74e149a392436b17d523f769e057cb6877f6a5c4618bc6f11800548"
+
 [[package]]
 name = "portable-atomic"
 version = "1.13.1"
@@ -541,9 +569,22 @@ dependencies = [
  "rustc-hash",
  "serde",
  "serde_json",
+ "tar",
  "tempfile",
  "uuid",
  "xxhash-rust",
+ "zstd",
+]
+
+[[package]]
+name = "tar"
+version = "0.4.46"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f6221d9a6003c78398e3b239969f352578258df48c8eb051caadae0015bc840"
+dependencies = [
+ "filetime",
+ "libc",
+ "xattr",
 ]
 
 [[package]]
@@ -654,6 +695,16 @@ dependencies = [
  "windows-link",
 ]
 
+[[package]]
+name = "xattr"
+version = "1.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32e45ad4206f6d2479085147f02bc2ef834ac85886624a23575ae137c8aa8156"
+dependencies = [
+ "libc",
+ "rustix",
+]
+
 [[package]]
 name = "xxhash-rust"
 version = "0.8.17"
@@ -671,3 +722,31 @@ name = "zmij"
 version = "1.0.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "29666d0abbfad1e3dc4dcf6144730dd3a3ab225bbbdac83319345b1b44ccfc1b"
+
+[[package]]
+name = "zstd"
+version = "0.13.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a"
+dependencies = [
+ "zstd-safe",
+]
+
+[[package]]
+name = "zstd-safe"
+version = "7.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f49c4d5f0abb602a93fb8736af2a4f4dd9512e36f7f570d66e65ff867ed3b9d"
+dependencies = [
+ "zstd-sys",
+]
+
+[[package]]
+name = "zstd-sys"
+version = "2.0.16+zstd.1.5.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91e19ebc2adc8f83e43039e79776e3fda8ca919132d68a1fed6a5faca2683748"
+dependencies = [
+ "cc",
+ "pkg-config",
+]

{tablassert-11.0.0 → tablassert-12.0.0}/rust/Cargo.toml

@@ -37,8 +37,13 @@ rlimit = "0.10"
 rustc-hash = "1"
 serde = { version = "1", features = ["derive"] }
 serde_json = { version = "1", features = ["preserve_order"] }
+tar = "0.4"
 uuid = { version = "1", features = ["v3"] }
 xxhash-rust = { version = "0.8", features = ["xxh64", "xxh3"] }
+# Streaming zstd decompression for the prebuilt `fullmap.tar.zst` archive
+# (`extract_prebuilt_fullmap`); the C-backed decoder is the fastest option and
+# `cc` is available in the build environment.
+zstd = "0.13"
 
 [dev-dependencies]
 bincode = "1"
@@ -46,7 +51,9 @@ flate2 = { version = "1", features = ["zlib-rs"], default-features = false }
 redb = { git = "https://github.com/cberner/redb.git", rev = "a35e7cc86f191d08a444d5973469b34673d586fc", features = ["experimental_cursor"] }
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
+tar = "0.4"
 tempfile = "3"
+zstd = "0.13"
 
 [lints.rust]
 unused_imports = "deny"