tablassert 8.1.0__tar.gz → 8.2.0__tar.gz

tablassert-8.2.0/PKG-INFO

@@ -0,0 +1,221 @@
+Metadata-Version: 2.4
+Name: tablassert
+Version: 8.2.0
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+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: 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: 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: pdfminer-six>=20221105 ; extra == 'agent'
+Requires-Dist: dspy>=3.2.1 ; extra == 'optimize'
+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: optimize
+Provides-Extra: qc
+Provides-Extra: rt
+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
+
+[![PyPI](https://img.shields.io/pypi/v/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)
+[![Docs](https://img.shields.io/github/deployments/SkyeAv/Tablassert/github-pages?label=docs)](https://skyeav.github.io/Tablassert/)
+
+> Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON —
+> declaratively, with entity resolution built in and optional quality control.
+
+Tablassert turns biomedical spreadsheets (Excel, CSV, TSV) into knowledge graphs ready for NCATS
+Translator. Declare how your columns map to subject–predicate–object statements in YAML; Tablassert
+resolves free text to standard CURIEs, attaches provenance and statistical annotations, and emits
+KGX-compliant nodes and edges.
+
+**[Full Documentation](https://skyeav.github.io/Tablassert/)** — installation guides, tutorial,
+configuration reference, and API docs.
+
+## Quick Start
+
+```bash
+pip install tablassert
+```
+
+Given a CSV of gene–disease associations with p-values and sample sizes, declare the mapping in a
+table config (`table.yaml`):
+
+```yaml
+template:
+  source:
+    kind: text
+    local: ./gene-disease.csv
+    url: https://example.com/data.csv
+    row_slice: [1, auto]
+    delimiter: ","
+  statement:
+    subject: { method: column, encoding: A, prioritize: [Gene] }
+    predicate: associated_with
+    object: { method: column, encoding: B, prioritize: [Disease] }
+  provenance: { repo: PMID, publication: "12345678" }
+  annotations:
+    - { annotation: p_value, method: column, encoding: C }
+    - { annotation: supporting_study_size, method: column, encoding: D }
+```
+
+Wrap it in a graph config (`graph.yaml`) pointing at your fullmap entity-resolution database:
+
+```yaml
+name: MY_KG
+version: 1.0.0
+description: Gene–disease associations extracted from tabular sources.
+tables:
+  - ./table.yaml
+fullmap: /path/to/fullmap
+```
+
+Build the knowledge graph:
+
+```bash
+tablassert build-kg graph.yaml
+```
+
+Output is one JSON object per line — nodes with Biolink categories, edges with annotations:
+
+```json
+{"id":"HGNC:11998","name":"TP53","category":["biolink:Gene"],"taxon":"NCBITaxon:9606"}
+{"id":"MONDO:0008903","name":"lung cancer","category":["biolink:Disease"]}
+```
+
+```json
+{"subject":"HGNC:11998","predicate":"biolink:associated_with","object":"MONDO:0008903","p_value":"1.0000e-03","supporting_study_size":"450"}
+```
+
+See the [Tutorial](https://skyeav.github.io/Tablassert/tutorial/) for the full walkthrough.
+
+## Key Features
+
+- **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
+  low-confidence mappings
+- **KGX compliance** — emits NCATS Translator-compatible node/edge NDJSON with Biolink categories
+  and predicates
+- **Autonomous agent** — `tablassert agent` derives, builds, and refines configs for whole papers
+- **Performance & reproducibility** — lazy Polars pipelines and a deterministic UV-based
+  development environment
+
+## Installation
+
+```bash
+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:
+
+| Extra | Adds | Install |
+| ----- | ---- | ------- |
+| `rt` | CPU-compatible Polars runtime | `pip install "tablassert[rt]"` |
+| `qc` | three-stage QC audit (exact → fuzzy → BioBERT 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]"` |
+
+QC is opt-in at build time (`build-kg --qc`). 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.
+
+## Entity Resolution API
+
+```python
+from pathlib import Path
+from tablassert.lib import resolve_many
+
+results = resolve_many(
+    col="gene",
+    entities=["TP53", "BRCA1"],
+    fullmap=Path("/path/to/fullmap"),
+    taxon="9606",
+)
+# [{"original_gene": "TP53", "gene": "HGNC:11998", "gene_name": "TP53", ...}, ...]
+```
+
+Point `resolve_many()` at a fullmap database to resolve any iterable of entity strings to CURIEs —
+no LazyFrame setup or NLP preprocessing required. See the
+[Batch Resolution API](https://skyeav.github.io/Tablassert/api/lib/) for the full reference.
+
+## Documentation
+
+- **[Installation](https://skyeav.github.io/Tablassert/installation/)** — install methods, extras, and development setup
+- **[Tutorial](https://skyeav.github.io/Tablassert/tutorial/)** — step-by-step example with synthetic data
+- **[CLI Reference](https://skyeav.github.io/Tablassert/cli/)** — complete command-line flag reference
+- **[Use Case Gallery](https://skyeav.github.io/Tablassert/examples/)** — real-world configuration patterns
+- **[Configuration](https://skyeav.github.io/Tablassert/configuration/graph/)** — graph and table configuration reference
+- **[Agent](https://skyeav.github.io/Tablassert/agent/)** — the autonomous agent pipeline
+- **[API Reference](https://skyeav.github.io/Tablassert/api/fullmap/)** — core functions documentation
+
+## Developing
+
+```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.
+
+## Citation
+
+If you use Tablassert, please cite it as described in [CITATION.cff](CITATION.cff). The approach is
+described in:
+
+> Skye Lane Goetz, Alex K. Glen, and Gwênlyn Glusman. “MicrobiomeKG: bridging microbiome research
+> and host health through knowledge graphs.” *Frontiers in Systems Biology* 5 (2025).
+> [doi:10.3389/fsysb.2025.1544432](https://doi.org/10.3389/fsysb.2025.1544432)
+
+## License
+
+[Apache License 2.0](LICENSE)
+
+## Contributors
+
+- [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-8.2.0/README.md

@@ -0,0 +1,167 @@
+# Tablassert
+
+[![PyPI](https://img.shields.io/pypi/v/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)
+[![Docs](https://img.shields.io/github/deployments/SkyeAv/Tablassert/github-pages?label=docs)](https://skyeav.github.io/Tablassert/)
+
+> Extract knowledge assertions from tabular data into NCATS Translator-compliant KGX NDJSON —
+> declaratively, with entity resolution built in and optional quality control.
+
+Tablassert turns biomedical spreadsheets (Excel, CSV, TSV) into knowledge graphs ready for NCATS
+Translator. Declare how your columns map to subject–predicate–object statements in YAML; Tablassert
+resolves free text to standard CURIEs, attaches provenance and statistical annotations, and emits
+KGX-compliant nodes and edges.
+
+**[Full Documentation](https://skyeav.github.io/Tablassert/)** — installation guides, tutorial,
+configuration reference, and API docs.
+
+## Quick Start
+
+```bash
+pip install tablassert
+```
+
+Given a CSV of gene–disease associations with p-values and sample sizes, declare the mapping in a
+table config (`table.yaml`):
+
+```yaml
+template:
+  source:
+    kind: text
+    local: ./gene-disease.csv
+    url: https://example.com/data.csv
+    row_slice: [1, auto]
+    delimiter: ","
+  statement:
+    subject: { method: column, encoding: A, prioritize: [Gene] }
+    predicate: associated_with
+    object: { method: column, encoding: B, prioritize: [Disease] }
+  provenance: { repo: PMID, publication: "12345678" }
+  annotations:
+    - { annotation: p_value, method: column, encoding: C }
+    - { annotation: supporting_study_size, method: column, encoding: D }
+```
+
+Wrap it in a graph config (`graph.yaml`) pointing at your fullmap entity-resolution database:
+
+```yaml
+name: MY_KG
+version: 1.0.0
+description: Gene–disease associations extracted from tabular sources.
+tables:
+  - ./table.yaml
+fullmap: /path/to/fullmap
+```
+
+Build the knowledge graph:
+
+```bash
+tablassert build-kg graph.yaml
+```
+
+Output is one JSON object per line — nodes with Biolink categories, edges with annotations:
+
+```json
+{"id":"HGNC:11998","name":"TP53","category":["biolink:Gene"],"taxon":"NCBITaxon:9606"}
+{"id":"MONDO:0008903","name":"lung cancer","category":["biolink:Disease"]}
+```
+
+```json
+{"subject":"HGNC:11998","predicate":"biolink:associated_with","object":"MONDO:0008903","p_value":"1.0000e-03","supporting_study_size":"450"}
+```
+
+See the [Tutorial](https://skyeav.github.io/Tablassert/tutorial/) for the full walkthrough.
+
+## Key Features
+
+- **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
+  low-confidence mappings
+- **KGX compliance** — emits NCATS Translator-compatible node/edge NDJSON with Biolink categories
+  and predicates
+- **Autonomous agent** — `tablassert agent` derives, builds, and refines configs for whole papers
+- **Performance & reproducibility** — lazy Polars pipelines and a deterministic UV-based
+  development environment
+
+## Installation
+
+```bash
+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:
+
+| Extra | Adds | Install |
+| ----- | ---- | ------- |
+| `rt` | CPU-compatible Polars runtime | `pip install "tablassert[rt]"` |
+| `qc` | three-stage QC audit (exact → fuzzy → BioBERT 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]"` |
+
+QC is opt-in at build time (`build-kg --qc`). 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.
+
+## Entity Resolution API
+
+```python
+from pathlib import Path
+from tablassert.lib import resolve_many
+
+results = resolve_many(
+    col="gene",
+    entities=["TP53", "BRCA1"],
+    fullmap=Path("/path/to/fullmap"),
+    taxon="9606",
+)
+# [{"original_gene": "TP53", "gene": "HGNC:11998", "gene_name": "TP53", ...}, ...]
+```
+
+Point `resolve_many()` at a fullmap database to resolve any iterable of entity strings to CURIEs —
+no LazyFrame setup or NLP preprocessing required. See the
+[Batch Resolution API](https://skyeav.github.io/Tablassert/api/lib/) for the full reference.
+
+## Documentation
+
+- **[Installation](https://skyeav.github.io/Tablassert/installation/)** — install methods, extras, and development setup
+- **[Tutorial](https://skyeav.github.io/Tablassert/tutorial/)** — step-by-step example with synthetic data
+- **[CLI Reference](https://skyeav.github.io/Tablassert/cli/)** — complete command-line flag reference
+- **[Use Case Gallery](https://skyeav.github.io/Tablassert/examples/)** — real-world configuration patterns
+- **[Configuration](https://skyeav.github.io/Tablassert/configuration/graph/)** — graph and table configuration reference
+- **[Agent](https://skyeav.github.io/Tablassert/agent/)** — the autonomous agent pipeline
+- **[API Reference](https://skyeav.github.io/Tablassert/api/fullmap/)** — core functions documentation
+
+## Developing
+
+```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.
+
+## Citation
+
+If you use Tablassert, please cite it as described in [CITATION.cff](CITATION.cff). The approach is
+described in:
+
+> Skye Lane Goetz, Alex K. Glen, and Gwênlyn Glusman. “MicrobiomeKG: bridging microbiome research
+> and host health through knowledge graphs.” *Frontiers in Systems Biology* 5 (2025).
+> [doi:10.3389/fsysb.2025.1544432](https://doi.org/10.3389/fsysb.2025.1544432)
+
+## License
+
+[Apache License 2.0](LICENSE)
+
+## Contributors
+
+- [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-8.1.0 → tablassert-8.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tablassert"
-version = "8.1.0"
+version = "8.2.0"
 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" }
@@ -84,10 +84,12 @@ qc = [
 ]
 agent = [
     "smolagents>=1.26.0",
-    "dspy>=3.2.1",
     "litellm>=1.93.0",
     "pdfminer.six>=20221105",
 ]
+optimize = [
+    "dspy>=3.2.1",
+]
 
 [dependency-groups]
 dev = [

{tablassert-8.1.0 → tablassert-8.2.0}/rust/Cargo.lock

@@ -54,15 +54,6 @@ version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
 
-[[package]]
-name = "crc32fast"
-version = "1.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511"
-dependencies = [
- "cfg-if",
-]
-
 [[package]]
 name = "crossbeam-deque"
 version = "0.8.7"
@@ -148,8 +139,8 @@ version = "1.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c"
 dependencies = [
- "crc32fast",
  "miniz_oxide",
+ "zlib-rs",
 ]
 
 [[package]]
@@ -422,9 +413,8 @@ dependencies = [
 
 [[package]]
 name = "redb"
-version = "2.6.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8eca1e9d98d5a7e9002d0013e18d5a9b000aee942eb134883a82f06ebffb6c01"
+version = "4.1.0"
+source = "git+https://github.com/cberner/redb.git?rev=a35e7cc86f191d08a444d5973469b34673d586fc#a35e7cc86f191d08a444d5973469b34673d586fc"
 dependencies = [
  "libc",
 ]
@@ -670,6 +660,12 @@ version = "0.8.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "985eec839aaf2a1270af8f4ebcf63cf9401cfd90f0902f97c28d9f104ffbde72"
 
+[[package]]
+name = "zlib-rs"
+version = "0.6.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34b31d188d9d685a4f9c7b46d6e36631b07058d2cfe190267adce54dc230bf12"
+
 [[package]]
 name = "zmij"
 version = "1.0.23"

tablassert-8.2.0/rust/Cargo.toml

@@ -0,0 +1,65 @@
+[package]
+name = "tablassert-rs"
+version = "0.1.0"
+edition = "2021"
+
+[lib]
+name = "tablassert_rs"
+crate-type = ["cdylib", "rlib"]
+
+[features]
+default = []
+extension-module = ["pyo3/extension-module"]
+
+[dependencies]
+bincode = "1"
+# `zlib-rs` backend: the fastest api-compatible DEFLATE decompressor (pure
+# Rust, runtime SIMD multiversioning — no C toolchain needed for wheels).
+# The fullmap build's producer threads decompress ~30-40 GB of BABEL `.gz`;
+# the default miniz_oxide backend is the slowest option.  See the flate2
+# README ("if you want maximum performance... use zlib-rs").
+flate2 = { version = "1", features = ["zlib-rs"], default-features = false }
+memmap2 = "0.9"
+mimalloc = { version = "0.1", default-features = false }
+pyo3 = "0.29"
+rayon = "1"
+# Pinned to cberner/redb master (the 4.2.0-to-be, rev a35e7cc 2026-08-10) for
+# two Phase-4 wins not yet published on crates.io (latest stable is 4.1.0):
+#   1. automatic ascending-key insert optimization (~half the pages -> ~half-
+#      size shard files + faster reads; our shard inserts are hash-ascending);
+#   2. the experimental cursor API (~3x faster sorted bulk inserts), used by
+#      `write_shard_records` via `experimental_cursor`.
+# The file format is still v3, so this is a drop-in engine swap (no schema
+# bump, existing DBs keep opening).  Swap back to `redb = "4.2"` once 4.2.0
+# publishes and re-verify the changelog.
+redb = { git = "https://github.com/cberner/redb.git", rev = "a35e7cc86f191d08a444d5973469b34673d586fc", features = ["experimental_cursor"] }
+rlimit = "0.10"
+rustc-hash = "1"
+serde = { version = "1", features = ["derive"] }
+serde_json = { version = "1", features = ["preserve_order"] }
+uuid = { version = "1", features = ["v3"] }
+xxhash-rust = { version = "0.8", features = ["xxh64", "xxh3"] }
+
+[dev-dependencies]
+bincode = "1"
+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"
+tempfile = "3"
+
+[lints.rust]
+unused_imports = "deny"
+unused_variables = "deny"
+dead_code = "deny"
+
+# Curated low-false-positive clippy lints enforced across the crate (lib +
+# tests + examples).  Deliberately NOT denied: needless_pass_by_value and
+# doc_markdown (too noisy / stylistic for this codebase).
+[lints.clippy]
+use_self = "deny"
+uninlined_format_args = "deny"
+redundant_closure_for_method_calls = "deny"
+explicit_iter_loop = "deny"
+match_same_arms = "deny"
+unnested_or_patterns = "deny"

{tablassert-8.1.0 → tablassert-8.2.0}/rust/examples/count_tables.rs

@@ -1,5 +1,6 @@
 //! Count rows in each table of one or more fullmap redb files.
 //! Usage: cargo run --release --example count_tables -- <db1> [db2 ...]
+use redb::ReadableDatabase;
 use redb::ReadableTableMetadata;
 use redb::TableDefinition;
 
@@ -11,7 +12,7 @@ const CURIES: TableDefinition<u32, &[u8]> = TableDefinition::new("curies");
 
 fn main() {
     for arg in std::env::args().skip(1) {
-        let db = redb::Database::open(&arg).expect("open db");
+        let db = redb::ReadOnlyDatabase::open(&arg).expect("open db");
         let read = db.begin_read().expect("begin read");
         let records = read
             .open_table(RECORDS)