tablassert 7.4.4__tar.gz → 7.4.5__tar.gz

{tablassert-7.4.4 → tablassert-7.4.5}/.gitignore

@@ -9,6 +9,7 @@
 *specs/
 *.storassert/
 *.logassert/
+*.cachassert/
 *DATALAKE/
 *.onnxassert/
 *.claude/

{tablassert-7.4.4 → tablassert-7.4.5}/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 All notable changes to this project are documented in this file.
 
+## 7.4.5 - 2026-05-11
+
+### Changes
+- Cached `BaseSource.is_real_url` validator results to a `diskcache.Cache` at `.cachassert/` in `models.py`, so repeated config parses skip redundant `httpx.head()` round-trips against unchanged URLs.
+- Increased `is_real_url` `httpx.head()` timeout from 5.0s to 15.0s to further reduce spurious validation failures against slow upstreams.
+- Added `diskcache>=5.6.3` runtime dependency.
+
 ## 7.4.4 - 2026-05-11
 
 ### Changes

{tablassert-7.4.4 → tablassert-7.4.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tablassert
-Version: 7.4.4
+Version: 7.4.5
 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
@@ -25,6 +25,7 @@ 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

{tablassert-7.4.4 → tablassert-7.4.5}/docs/changelog.md

@@ -4,11 +4,12 @@ The canonical release history lives in the repository root at [`CHANGELOG.md`](h
 
 ## Current Release Notes
 
-## 7.4.4 - 2026-05-11
+## 7.4.5 - 2026-05-11
 
 ### Changes
 
-- Relaxed the `url` field validator in `BaseSource` to only fail on 4xx responses from `httpx.head()`. Sources whose servers return 5xx or other non-2xx statuses to `HEAD` requests now pass config validation, since the URL itself is still well-formed.
-- Increased the `httpx.head()` timeout in the `url` validator from 3.0s to 5.0s to tolerate slower upstreams.
+- Cached `url` field validator results in `BaseSource` to a `diskcache.Cache` stored at `.cachassert/`, so repeated config parses skip redundant `httpx.head()` round-trips against unchanged URLs.
+- Increased the `httpx.head()` timeout in the `url` validator from 5.0s to 15.0s to further tolerate slower upstreams.
+- Added `diskcache` as a runtime dependency.
 
 For older releases and the full project history, open the root `CHANGELOG.md` in the repository.

{tablassert-7.4.4 → tablassert-7.4.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tablassert"
-version = "7.4.4"
+version = "7.4.5"
 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" }
@@ -59,6 +59,7 @@ dependencies = [
     "cyclopts>=1.0.0",
     "rich>=13.0.0",
     "xxhash>=3.6.0",
+    "diskcache>=5.6.3",
 ]
 
 [project.urls]

{tablassert-7.4.4 → tablassert-7.4.5}/src/tablassert/models.py

@@ -6,6 +6,7 @@ from pathlib import Path
 from typing import TYPE_CHECKING, Any, Literal, Optional, Self, Union
 
 import lazy_loader as Lazy
+from diskcache import Cache
 from pydantic import BaseModel, ConfigDict, Field, HttpUrl, PositiveInt, field_validator, model_validator
 
 from tablassert.enums import (
@@ -72,19 +73,29 @@ class Reindex(TablaBase):
         return self
 
 
+CACHE: Path = Path(".cachassert/")
+CACHE.mkdir(parents=True, exist_ok=True)
+
+URL_CACHE: Cache = Cache(CACHE)
+
+
 class BaseSource(TablaBase):
     local: Path = Field(..., description="Local path to read from or download into.")
     url: HttpUrl = Field(..., description="Remote source URL fetched before parsing.")
 
     @field_validator("url", mode="after")
     @classmethod
-    def is_real_url(cls, url: HttpUrl, timeout: float = 5.0) -> HttpUrl:
+    def is_real_url(cls, url: HttpUrl) -> HttpUrl:
         s: str = str(url)
 
-        try:
+        @URL_CACHE.memoize()
+        def check_url(s: str, timeout: float = 15.0) -> None:
             r: Any = httpx.head(s, timeout=timeout, follow_redirects=True)
             if 400 <= r.status_code < 500:
                 r.raise_for_status()
+
+        try:
+            check_url(s)
         except Exception as e:
             msg: str = f"12 | not a real url {s} | {e}"
             raise ValueError(msg)

{tablassert-7.4.4 → tablassert-7.4.5}/uv.lock

@@ -293,6 +293,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/23/18/4cedda786e7da429e7489549a9e5461530d4133130e541f25fb94f015776/cyclopts-4.11.2-py3-none-any.whl", hash = "sha256:838020120b939549ff7c8423aca29c86764b5dd1d8a5d7f3753a6327861f537b", size = 213537, upload-time = "2026-05-04T00:11:56.103Z" },
 ]
 
+[[package]]
+name = "diskcache"
+version = "5.6.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3f/21/1c1ffc1a039ddcc459db43cc108658f32c57d271d7289a2794e401d0fdb6/diskcache-5.6.3.tar.gz", hash = "sha256:2c3a3fa2743d8535d832ec61c2054a1641f41775aa7c556758a109941e33e4fc", size = 67916, upload-time = "2023-08-31T06:12:00.316Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3f/27/4570e78fc0bf5ea0ca45eb1de3818a23787af9b390c0b0a0033a1b8236f9/diskcache-5.6.3-py3-none-any.whl", hash = "sha256:5e31b2d5fbad117cc363ebaf6b689474db18a1f6438bc82358b024abd4c2ca19", size = 45550, upload-time = "2023-08-31T06:11:58.822Z" },
+]
+
 [[package]]
 name = "distlib"
 version = "0.4.0"
@@ -2351,10 +2360,11 @@ wheels = [
 
 [[package]]
 name = "tablassert"
-version = "7.4.4"
+version = "7.4.5"
 source = { editable = "." }
 dependencies = [
     { name = "cyclopts" },
+    { name = "diskcache" },
     { name = "duckdb" },
     { name = "fastexcel" },
     { name = "httpx" },
@@ -2401,6 +2411,7 @@ dev = [
 [package.metadata]
 requires-dist = [
     { name = "cyclopts", specifier = ">=1.0.0" },
+    { name = "diskcache", specifier = ">=5.6.3" },
     { name = "duckdb", specifier = ">=1.5.0" },
     { name = "fastexcel", specifier = ">=0.19.0" },
     { name = "httpx", specifier = ">=0.28.1" },