tablassert 7.4.1__tar.gz → 7.4.2__tar.gz

{tablassert-7.4.1 → tablassert-7.4.2}/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 All notable changes to this project are documented in this file.
 
+## 7.4.2 - 2026-05-07
+
+### Changes
+- Added Pydantic field and model validators to `models.py` that enforce configuration correctness at parse time: `url` fields are verified reachable via `httpx.head()`, `rows` and `row_slice` are mutually exclusive, `Reindex.comparator` type must match its `comparison` operator (`eq`/`ne` require `str`, numeric operators require `int`/`float`), `encoding` values under `method: column` must be Excel-style letters (`A`–`ZZZ`), `Regex` pattern/replacement strings are validated against the Polars regex engine, `remove` entries are validated as Polars-compatible regex, and `annotation` names have underscores replaced with spaces.
+- Changed `rows` and `row_slice` element type from `NonNegativeInt` to `PositiveInt` in `BaseSource`.
+
 ## 7.4.1 - 2026-05-05
 
 ### Bug Fixes

{tablassert-7.4.1 → tablassert-7.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tablassert
-Version: 7.4.1
+Version: 7.4.2
 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

{tablassert-7.4.1 → tablassert-7.4.2}/docs/changelog.md

@@ -4,6 +4,13 @@ The canonical release history lives in the repository root at [`CHANGELOG.md`](h
 
 ## Current Release Notes
 
+## 7.4.2 - 2026-05-07
+
+### Changes
+
+- Added Pydantic field and model validators to `models.py` that catch misconfigurations at parse time: unreachable `url` fields, mutually exclusive `rows`/`row_slice`, mismatched `Reindex` comparator types, non–Excel-style column letters under `method: column`, Polars-incompatible `regex`/`remove` patterns, and `annotation` name normalization (underscores → spaces).
+- Changed `rows` and `row_slice` element type from `NonNegativeInt` to `PositiveInt`.
+
 ## 7.4.1 - 2026-05-05
 
 ### Bug Fixes

{tablassert-7.4.1 → tablassert-7.4.2}/docs/configuration/table.md

@@ -139,10 +139,10 @@ Defines the data file location and format.
 |-------|------|----------|-------------|
 | `kind` | String | No | Source kind. Model default is `"excel"`, but specify it explicitly in configs. |
 | `local` | Path | Yes | Local file path for caching |
-| `url` | URL | Yes | Download URL (HTTP/HTTPS) |
+| `url` | URL | Yes | Download URL (HTTP/HTTPS). Validated as reachable at parse time. |
 | `sheet` | String | No | Sheet name. Defaults to `"Sheet1"`. |
-| `row_slice` | List[Int\|"auto"] | No | Two-value zero-based crop bounds: `[start, stop]`. Each value may be an integer or `"auto"`. |
-| `rows` | List[Int] | No | Zero-based row indices to keep after any `row_slice` crop. |
+| `row_slice` | List[Int\|"auto"] | No | Two-value zero-based crop bounds: `[start, stop]`. Each value may be an integer or `"auto"`. Mutually exclusive with `rows`. |
+| `rows` | List[Int] | No | Zero-based row indices to keep after any `row_slice` crop. Mutually exclusive with `row_slice`. |
 | `reindex` | List[Reindex] | No | Conditional row filtering |
 
 **Example:**
@@ -163,10 +163,10 @@ source:
 |-------|------|----------|-------------|
 | `kind` | String | No | Source kind. Model default is `"text"`, but specify it explicitly in configs. |
 | `local` | Path | Yes | Local file path for caching |
-| `url` | URL | Yes | Download URL |
+| `url` | URL | Yes | Download URL. Validated as reachable at parse time. |
 | `delimiter` | String | No | Field delimiter. Defaults to `","`. |
-| `row_slice` | List[Int\|"auto"] | No | Two-value zero-based crop bounds: `[start, stop]`. Each value may be an integer or `"auto"`. |
-| `rows` | List[Int] | No | Zero-based row indices to keep after any `row_slice` crop. |
+| `row_slice` | List[Int\|"auto"] | No | Two-value zero-based crop bounds: `[start, stop]`. Each value may be an integer or `"auto"`. Mutually exclusive with `rows`. |
+| `rows` | List[Int] | No | Zero-based row indices to keep after any `row_slice` crop. Mutually exclusive with `row_slice`. |
 | `reindex` | List[Reindex] | No | Conditional filtering |
 
 **Example:**
@@ -189,7 +189,7 @@ Filter rows based on column values.
 |-------|------|-------------|
 | `column` | String | Source column letters to evaluate (`A`-`ZZZ`) |
 | `comparison` | String | Operator. Defaults to `"ne"`; allowed values are `"eq"`, `"ne"`, `"lt"`, `"le"`, `"gt"`, `"ge"`. |
-| `comparator` | String\|Int\|Float | Value to compare against |
+| `comparator` | String\|Int\|Float | Value to compare against. Must be a string for `"eq"`/`"ne"`, or a number for `"lt"`/`"le"`/`"gt"`/`"ge"`. |
 
 **Example:**
 ```yaml
@@ -454,7 +454,7 @@ Optional edge attributes (statistical metadata, notes, etc.).
 
 | Field | Type | Description |
 |-------|------|-------------|
-| `annotation` | String | Attribute name (e.g., `"p value"`, `"sample size"`) |
+| `annotation` | String | Attribute name (e.g., `"p value"`, `"sample size"`). Underscores are automatically replaced with spaces at parse time. |
 | (inherits Encoding) | | All Encoding fields available (method, encoding, regex, etc.) |
 
 **Example:**

{tablassert-7.4.1 → tablassert-7.4.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tablassert"
-version = "7.4.1"
+version = "7.4.2"
 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-7.4.1 → tablassert-7.4.2}/src/tablassert/models.py

@@ -1,9 +1,12 @@
 from __future__ import annotations
 
+import re
+from operator import eq
 from pathlib import Path
-from typing import Literal, Optional, Union
+from typing import TYPE_CHECKING, Any, Literal, Optional, Self, Union
 
-from pydantic import BaseModel, ConfigDict, Field, HttpUrl, NonNegativeInt, PositiveInt
+import lazy_loader as Lazy
+from pydantic import BaseModel, ConfigDict, Field, HttpUrl, PositiveInt, field_validator, model_validator
 
 from tablassert.enums import (
     Categories,
@@ -21,6 +24,13 @@ from tablassert.enums import (
     Tokens,
 )
 
+if TYPE_CHECKING:
+    import httpx
+    import polars as pl
+else:
+    httpx = Lazy.load("httpx")
+    pl = Lazy.load("polars")
+
 
 class TablaBase(BaseModel):
     model_config: ConfigDict = ConfigDict(  # pyright: ignore
@@ -45,18 +55,58 @@ class Reindex(TablaBase):
         ..., description="Right-side value compared against the selected column.", examples=["N/A", 0, 1.5]
     )
 
+    @model_validator(mode="after")
+    def comparison_datatypes(self: Self) -> Self:
+        x: Comparisons = self.comparison
+        y: Union[str, int, float] = self.comparator
+
+        if eq(x, Comparisons.NE) or eq(x, Comparisons.EQ):
+            if not isinstance(y, str):
+                msg: str = f"14 | eq or ne comparisons must have a str comparator, got {type(y)}"
+                raise ValueError(msg)
+        else:
+            if not (isinstance(y, int) or isinstance(y, float)):
+                msg = f"15 | all comparisons other than eq or ne must have a float or an int comparator, got {type(y)}"
+                raise ValueError(msg)
+
+        return self
+
 
 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.")
-    rows: Optional[list[NonNegativeInt]] = Field(
+
+    @field_validator("url", mode="after")
+    @classmethod
+    def is_real_url(cls, url: HttpUrl, timeout: float = 3.0) -> HttpUrl:
+        s: str = str(url)
+
+        try:
+            r: Any = httpx.head(s, timeout=timeout, follow_redirects=True)
+            r.raise_for_status()
+        except Exception as e:
+            msg: str = f"12 | not a real url {s} | {e}"
+            raise ValueError(msg)
+
+        return url
+
+    rows: Optional[list[PositiveInt]] = Field(
         None, description="Zero-based row indices kept after any row_slice crop.", examples=[[0, 2, 5]]
     )
-    row_slice: Optional[list[Union[NonNegativeInt, Literal[Tokens.AUTO]]]] = Field(
+    row_slice: Optional[list[Union[PositiveInt, Literal[Tokens.AUTO]]]] = Field(
         None,
         description="Two-value row bounds [start, stop]; each value can be an index or 'auto'.",
         examples=[[1, 50], [Tokens.AUTO, 100], [5, Tokens.AUTO]],
     )
+
+    @model_validator(mode="after")
+    def no_rows_and_slice(self: Self) -> Self:
+        if self.rows and self.row_slice:
+            msg: str = "13 | cannot specify rows and row_slice in the same section"
+            raise ValueError(msg)
+
+        return self
+
     reindex: Optional[list[Reindex]] = Field(
         None,
         description="Sequential row filters applied using source column values.",
@@ -80,10 +130,33 @@ class Regex(TablaBase):
     pattern: Union[int, float, str] = Field(
         ..., description="Regex pattern passed to string replacement.", examples=["\\s+", "\\.$"]
     )
+
+    @field_validator("pattern", mode="after")
+    @classmethod
+    def polars_compatible_pattern(cls, pattern: Union[int, float, str]) -> Union[int, float, str]:
+        try:
+            pl.Series([""]).str.contains(str(pattern))
+        except Exception as e:
+            msg: str = f"17 | pattern must be a polars compatible regex, got {pattern} | {e}"
+            raise ValueError(msg)
+
+        return pattern
+
     replacement: Union[int, float, str] = Field(
         ..., description="Replacement value used when the pattern matches.", examples=[" ", "", 0]
     )
 
+    @field_validator("replacement", mode="after")
+    @classmethod
+    def polars_compatible_replacement(cls, replacement: Union[int, float, str]) -> Union[int, float, str]:
+        try:
+            pl.Series([""]).str.contains(str(replacement))
+        except Exception as e:
+            msg: str = f"18 | replacement must be a polars compatible regex, got {replacement} | {e}"
+            raise ValueError(msg)
+
+        return replacement
+
 
 class Math(TablaBase):
     function: Functions = Field(..., description="Math function applied during numeric transformation.")
@@ -103,6 +176,17 @@ class Encoding(TablaBase):
     encoding: Union[str, int, float] = Field(
         ..., description="Literal value or source column letters, depending on method.", examples=["A", "BRCA1", 1.0]
     )
+
+    @model_validator(mode="after")
+    def excel_style_columns(self: Self) -> Self:
+        if eq(self.method, EncodingMethods.COLUMN):
+            x: Union[str, int, float] = self.encoding
+            if not re.search(r"^[A-Z]{1,3}$", str(x)):
+                msg: str = f"16 | encoding must be an excel style alphanumeric column name like A to ZZ, got {x}"
+                raise ValueError(msg)
+
+        return self
+
     regex: Optional[list[Regex]] = Field(
         None,
         description="Ordered regex replacements applied to encoded text.",
@@ -113,11 +197,27 @@ class Encoding(TablaBase):
         description="Null fill strategy applied after value extraction.",
         examples=[FillMethods.FORWARD, FillMethods.ZERO],
     )
-    remove: Optional[list[str]] = Field(
+    remove: Optional[list[Union[int, float, str]]] = Field(
         None,
         description="Regex patterns removed from text (replace with empty string).",
         examples=[["\\[\\d+\\]", "\\s+"]],
     )
+
+    @field_validator("remove", mode="after")
+    @classmethod
+    def polars_compatible_replacement(
+        cls, remove: Optional[list[Union[int, float, str]]]
+    ) -> Optional[list[Union[int, float, str]]]:
+        if remove:
+            for r in remove:
+                try:
+                    pl.Series([""]).str.contains(str(r))
+                except Exception as e:
+                    msg: str = f"19 | remove must be contain polars compatible regular expressions, got {r} | {e}"
+                    raise ValueError(msg)
+
+        return remove
+
     prefix: Optional[str] = Field(None, description="String prepended to the encoded value.")
     suffix: Optional[str] = Field(None, description="String appended to the encoded value.")
     explode_by: Optional[str] = Field(
@@ -186,6 +286,11 @@ class Annotation(Encoding):
         ..., description="Output column name that receives this encoded annotation.", examples=["p_value", "cohort"]
     )
 
+    @field_validator("annotation", mode="after")
+    @classmethod
+    def clean_annotation(cls, annotation: str) -> str:
+        return annotation.replace("_", " ").strip()
+
 
 class Section(TablaBase):
     # ? Pydantic "Section" Model And Coercion

tablassert-7.4.2/tests/conftest.py

@@ -0,0 +1,28 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+import httpx
+import pytest
+
+
+class FakeHeadResponse:
+    status_code: int = 200
+
+    def raise_for_status(self) -> None:
+        return None
+
+
+def fakehead(url: str, *args: Any, **kwargs: Any) -> FakeHeadResponse:
+    return FakeHeadResponse()
+
+
+@pytest.fixture(autouse=True)
+def mockhttpxhead(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(httpx, "head", fakehead)
+
+
+@pytest.fixture
+def fixtures_path() -> Path:
+    return Path(__file__).parent / "fixtures"

{tablassert-7.4.1 → tablassert-7.4.2}/tests/test_models.py

@@ -230,8 +230,8 @@ def test_section_with_row_slice() -> None:
 
 # ? Section With Rows
 def test_section_with_rows() -> None:
-    source: Text = Text(local=Path("./test.tsv"), url="https://example.com/test.tsv", kind="text", rows=[0, 2, 5])  # pyright: ignore
-    assert source.rows == [0, 2, 5]
+    source: Text = Text(local=Path("./test.tsv"), url="https://example.com/test.tsv", kind="text", rows=[1, 2, 5])  # pyright: ignore
+    assert source.rows == [1, 2, 5]
 
 
 # ? Section With Reindex

{tablassert-7.4.1 → tablassert-7.4.2}/uv.lock

@@ -2351,7 +2351,7 @@ wheels = [
 
 [[package]]
 name = "tablassert"
-version = "7.4.0"
+version = "7.4.2"
 source = { editable = "." }
 dependencies = [
     { name = "cyclopts" },

tablassert-7.4.1/tests/conftest.py

@@ -1,10 +0,0 @@
-from __future__ import annotations
-
-from pathlib import Path
-
-import pytest
-
-
-@pytest.fixture
-def fixtures_path() -> Path:
-    return Path(__file__).parent / "fixtures"