def test_it_supports_nested_unordered_lists():
assert html_to_text("<ul>"
"<li>boop<ul><li>oof</li></ul></li>"
"<li>bap</li>"
"</ul>") == ("* boop\n\n"
"- oof\n\n"
"* bap")
def react_render_email(
site_type: str,
locale: str,
url: str,
user: Optional[JustfixUser] = None,
session: Optional[Dict[str, Any]] = None,
locale_prefix_url: bool = True,
is_html_email: bool = False,
) -> Email:
"""
Renders an email in the front-end, using the given locale,
and returns it.
"""
lr = react_render(
site_type,
locale,
url,
ContentType.HTML if is_html_email else ContentType.PLAINTEXT,
user=user,
session=session,
locale_prefix_url=locale_prefix_url,
)
return Email(
subject=lr.http_headers["X-JustFix-Email-Subject"],
body=html_to_text(lr.html),
html_body=lr.html if is_html_email else None,
)
def test_it_supports_nested_mixed_lists():
assert html_to_text("<ol>"
"<li>boop<ul><li>oof</li></ul></li>"
"<li>bap</li>"
"</ol>") == ("1. boop\n\n"
"* oof\n\n"
"2. bap")
def test_it_supports_nested_ordered_lists():
assert html_to_text(
"<ol>"
'<li>boop<ol type="a"><li>hi</li><li>bye</li></ol></li>'
"<li>bap</li>"
"</ol>") == ("1. boop\n\n"
"a. hi\n\n"
"b. bye\n\n"
"2. bap")
def render_lambda_static_content(lr: LambdaResponse):
ctype = lr.http_headers.get("Content-Type")
if ctype is None:
res = HttpResponse(lr.html, status=lr.status)
elif ctype == "application/pdf":
from loc.views import pdf_response
res = pdf_response(lr.html)
elif ctype == "text/plain; charset=utf-8":
from project.util.html_to_text import html_to_text
res = HttpResponse(html_to_text(lr.html).encode("utf-8"), status=lr.status)
else:
raise ValueError(f"Invalid Content-Type from lambda response: {ctype}")
for key, value in lr.http_headers.items():
res[key] = value
return res
def test_it_ignores_style_tags():
assert html_to_text("<style>html { color: pink; }</style>") == ""
def test_it_shows_hrefs_only():
assert (html_to_text(
'<p>visit <a href="https://boop.com" '
"data-jf-show-href-only-in-plaintext>boop.com</a>.</p>") ==
"visit https://boop.com.")
def test_it_supports_ordered_lists():
assert html_to_text("<ol><li>boop</li><li>bap</li></ol>") == ("1. boop\n\n"
"2. bap")
def test_it_replaces_non_decorative_images_with_urls():
assert html_to_text('<img src="blah.jpg" alt="Blah" />') == "blah.jpg"
def test_it_supports_lists_with_blocks():
assert html_to_text(
"<ul><li><p>boop</p><p>hi</p></li><li>bap</li></ul>") == ("* boop\n\n"
"hi\n\n"
"* bap")
def test_it_ignores_decorative_images():
assert html_to_text('<img src="blah.jpg" alt="" />') == ""
def test_it_ignores_useless_hrefs(href, text):
assert html_to_text(f'<p><a href="{href}">{text}</a></p>') == text
def test_it_ignores_anchors_without_hrefs():
assert html_to_text("<p><a>visit it</a></p>") == ("visit it")
def test_it_works():
assert html_to_text("<p>paragraph one</p><p>paragraph two</p>") == (
"paragraph one\n\n"
"paragraph two")
def test_it_raises_value_error_on_unsupported_type():
with pytest.raises(ValueError, match='Unknown <ol> type "z"'):
html_to_text('<ol type="z"></ol>')
def test_it_adds_anchor_hrefs():
assert html_to_text('<p><a href="https://boop">visit it</a></p>') == (
"visit it: https://boop")
def test_it_ignores_empty_blocks():
assert html_to_text("<p>bop</p><p></p><p>bop</p>") == ("bop\n\nbop")
def test_it_supports_br():
assert html_to_text("<p>paragraph<br/>one</p>") == ("paragraph\none")
def test_it_ignores_class_name():
assert html_to_text('<p class="blah">a</p>') == "a"
def test_it_embellishes_headings(html, text):
assert html_to_text(html) == text
def test_it_ignores_title_tags():
assert html_to_text("<title>boop</title>") == ""
def test_it_does_not_currently_support_roman_numerals():
with pytest.raises(NotImplementedError,
match="Roman numerals in <ol> are unsupported"):
html_to_text('<ol type="i"></ol>')