Spaces:
Sleeping
Sleeping
File size: 3,881 Bytes
cfd3735 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 |
from typing import Any
import pytest
from langchain.document_loaders import SitemapLoader
def test_sitemap() -> None:
"""Test sitemap loader."""
loader = SitemapLoader("https://langchain.readthedocs.io/sitemap.xml")
documents = loader.load()
assert len(documents) > 1
assert "🦜🔗" in documents[0].page_content
def test_sitemap_block() -> None:
"""Test sitemap loader."""
loader = SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml", blocksize=1, blocknum=1
)
documents = loader.load()
assert len(documents) == 1
assert "🦜🔗" in documents[0].page_content
def test_sitemap_block_only_one() -> None:
"""Test sitemap loader."""
loader = SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml", blocksize=1000000, blocknum=0
)
documents = loader.load()
assert len(documents) > 1
assert "🦜🔗" in documents[0].page_content
def test_sitemap_block_blocknum_default() -> None:
"""Test sitemap loader."""
loader = SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml", blocksize=1000000
)
documents = loader.load()
assert len(documents) > 1
assert "🦜🔗" in documents[0].page_content
def test_sitemap_block_size_to_small() -> None:
"""Test sitemap loader."""
with pytest.raises(ValueError, match="Sitemap blocksize should be at least 1"):
SitemapLoader("https://langchain.readthedocs.io/sitemap.xml", blocksize=0)
def test_sitemap_block_num_to_small() -> None:
"""Test sitemap loader."""
with pytest.raises(ValueError, match="Sitemap blocknum can not be lower then 0"):
SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml",
blocksize=1000000,
blocknum=-1,
)
def test_sitemap_block_does_not_exists() -> None:
"""Test sitemap loader."""
loader = SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml", blocksize=1000000, blocknum=15
)
with pytest.raises(
ValueError,
match="Selected sitemap does not contain enough blocks for given blocknum",
):
loader.load()
def test_filter_sitemap() -> None:
"""Test sitemap loader."""
loader = SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml",
filter_urls=["https://python.langchain.com/en/stable/"],
)
documents = loader.load()
assert len(documents) == 1
assert "🦜🔗" in documents[0].page_content
def test_sitemap_metadata() -> None:
def sitemap_metadata_one(meta: dict, _content: None) -> dict:
return {**meta, "mykey": "Super Important Metadata"}
"""Test sitemap loader."""
loader = SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml",
meta_function=sitemap_metadata_one,
)
documents = loader.load()
assert len(documents) > 1
assert "mykey" in documents[0].metadata
assert "Super Important Metadata" in documents[0].metadata["mykey"]
def test_sitemap_metadata_extraction() -> None:
def sitemap_metadata_two(meta: dict, content: Any) -> dict:
title = content.find("title")
if title:
return {**meta, "title": title.get_text()}
return meta
"""Test sitemap loader."""
loader = SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml",
meta_function=sitemap_metadata_two,
)
documents = loader.load()
assert len(documents) > 1
assert "title" in documents[0].metadata
assert "LangChain" in documents[0].metadata["title"]
def test_sitemap_metadata_default() -> None:
"""Test sitemap loader."""
loader = SitemapLoader("https://langchain.readthedocs.io/sitemap.xml")
documents = loader.load()
assert len(documents) > 1
assert "source" in documents[0].metadata
assert "loc" in documents[0].metadata
|