cryptorugmunch
8d25702eca
Squashed from chore/license-relicense. Full message preserved in the original branch commitbb77eb5. See ADR-0002 for the decision rationale. Refs: ADR-0002, commitbb77eb5
61 lines
2.1 KiB
Python
61 lines
2.1 KiB
Python
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
#
|
|
# Part of Pry — https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
# Licensed under MIT. See LICENSE.
|
|
import pytest
|
|
|
|
from extractor import SchemaExtractor
|
|
|
|
|
|
@pytest.fixture
|
|
def extractor() -> SchemaExtractor:
|
|
return SchemaExtractor()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_extract_pattern_mode(extractor: SchemaExtractor, sample_markdown: str) -> None:
|
|
schema = {"price": "price in USD", "email": "contact email"}
|
|
result = await extractor.extract(sample_markdown, schema, mode="pattern")
|
|
assert "price" in result
|
|
assert result["price"] is not None
|
|
assert "email" in result
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_extract_empty_content(extractor: SchemaExtractor) -> None:
|
|
result = await extractor.extract("", {"name": "product name"})
|
|
assert result == {}
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_extract_empty_schema(extractor: SchemaExtractor, sample_markdown: str) -> None:
|
|
result = await extractor.extract(sample_markdown, {})
|
|
assert result == {}
|
|
|
|
|
|
def test_pattern_extract_email(extractor: SchemaExtractor) -> None:
|
|
content = "Contact us at support@example.com or call 555-0100"
|
|
result = extractor._pattern_extract(content, {"email": "email address"})
|
|
assert "email" in result
|
|
assert "@" in result["email"]
|
|
|
|
|
|
def test_pattern_extract_price(extractor: SchemaExtractor) -> None:
|
|
content = "Price: $49.99 USD"
|
|
result = extractor._pattern_extract(content, {"price": "price in usd"})
|
|
assert "price" in result
|
|
assert "$" in result["price"] or "USD" in result["price"]
|
|
|
|
|
|
def test_pattern_extract_url(extractor: SchemaExtractor) -> None:
|
|
content = "Visit https://example.com/page for details"
|
|
result = extractor._pattern_extract(content, {"url": "website link"})
|
|
assert "url" in result
|
|
assert result["url"].startswith("http")
|
|
|
|
|
|
def test_pattern_extract_labeled_value(extractor: SchemaExtractor) -> None:
|
|
content = "product_name: SuperWidget\nprice: $19.99"
|
|
result = extractor._pattern_extract(content, {"product_name": "name"})
|
|
assert result.get("product_name") == "SuperWidget"
|