repos/website
1
Fork 0
Code Issues 1 Pull requests 27 Activity

Add basic tests for extract_text

Browse source
This commit is contained in:
Jake Howard 2022-07-04 09:21:12 +01:00
parent 51be747103
commit 60e4913e43
Signed by: jake
GPG key ID: 57AFB45680EDD477
2 changed files with 17 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
website/common/tests.py
View file

@ -2,7 +2,7 @@ from django.test import SimpleTestCase
from .embed import YouTubeLiteEmbedFinder
from .models import BasePage
from .utils import get_page_models, get_table_of_contents
from .utils import extract_text, get_page_models, get_table_of_contents
class BasePageTestCase(SimpleTestCase):
@ -92,3 +92,15 @@ class TableOfContentsTestCase(SimpleTestCase):
sub_entry = first_entry.children[1]
self.assertEqual(len(sub_entry.children), 1)
self.assertEqual([entry.title for entry in sub_entry.children], ["2.2.1"])
class ExtractTextTestCase(SimpleTestCase):
def test_extracts_text(self) -> None:
self.assertEqual(extract_text("<p><b>Hello</b> there!</p>"), "Hello there!")
self.assertEqual(
extract_text("<p>Paragraph 1</p>\n<p>Paragraph 2</p>"),
"Paragraph 1 Paragraph 2",
)
def test_plain_text(self) -> None:
self.assertEqual(extract_text("Hello there!"), "Hello there!")

5
website/common/utils.py
View file

@ -78,7 +78,10 @@ def extract_text(html: str) -> str:
"""
Get the plain text of some HTML.
"""
return " ".join(BeautifulSoup(html, "lxml").find_all(text=True))
lines = (
text.strip(" \n") for text in BeautifulSoup(html, "lxml").find_all(text=True)
)
return " ".join(line for line in lines if line)
def truncate_string(text: str, words: int) -> str: