diff options
Diffstat (limited to '')
| -rw-r--r-- | bot/exts/info/doc/_markdown.py | 12 | ||||
| -rw-r--r-- | poetry.lock | 12 | ||||
| -rw-r--r-- | pyproject.toml | 6 | ||||
| -rw-r--r-- | tests/bot/exts/info/doc/test_parsing.py | 23 |
4 files changed, 40 insertions, 13 deletions
diff --git a/bot/exts/info/doc/_markdown.py b/bot/exts/info/doc/_markdown.py index 1b7d8232b..315adda66 100644 --- a/bot/exts/info/doc/_markdown.py +++ b/bot/exts/info/doc/_markdown.py @@ -1,10 +1,14 @@ +import re from urllib.parse import urljoin +import markdownify from bs4.element import PageElement -from markdownify import MarkdownConverter +# See https://github.com/matthewwithanm/python-markdownify/issues/31 +markdownify.whitespace_re = re.compile(r"[\r\n\s\t ]+") -class DocMarkdownConverter(MarkdownConverter): + +class DocMarkdownConverter(markdownify.MarkdownConverter): """Subclass markdownify's MarkdownCoverter to provide custom conversion methods.""" def __init__(self, *, page_url: str, **options): @@ -56,3 +60,7 @@ class DocMarkdownConverter(MarkdownConverter): if parent is not None and parent.name == "li": return f"{text}\n" return super().convert_p(el, text, convert_as_inline) + + def convert_hr(self, el: PageElement, text: str, convert_as_inline: bool) -> str: + """Ignore `hr` tag.""" + return "" diff --git a/poetry.lock b/poetry.lock index 8a718ab82..de777c828 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1041,19 +1041,19 @@ source = ["Cython (>=0.29.7)"] [[package]] name = "markdownify" -version = "0.6.1" +version = "0.11.6" description = "Convert HTML to markdown." category = "main" optional = false python-versions = "*" files = [ - {file = "markdownify-0.6.1-py3-none-any.whl", hash = "sha256:7489fd5c601536996a376c4afbcd1dd034db7690af807120681461e82fbc0acc"}, - {file = "markdownify-0.6.1.tar.gz", hash = "sha256:31d7c13ac2ada8bfc7535a25fee6622ca720e1b5f2d4a9cbc429d167c21f886d"}, + {file = "markdownify-0.11.6-py3-none-any.whl", hash = "sha256:ba35fe289d5e9073bcd7d2cad629278fe25f1a93741fcdc0bfb4f009076d8324"}, + {file = "markdownify-0.11.6.tar.gz", hash = "sha256:009b240e0c9f4c8eaf1d085625dcd4011e12f0f8cec55dedf9ea6f7655e49bfe"}, ] [package.dependencies] -beautifulsoup4 = "*" -six = "*" +beautifulsoup4 = ">=4.9,<5" +six = ">=1.15,<2" [[package]] name = "mccabe" @@ -2317,4 +2317,4 @@ multidict = ">=4.0" [metadata] lock-version = "2.0" python-versions = "3.10.*" -content-hash = "68bfdf2115a5242df097155a2660a1c0276cf25b4785bdb761580bd35b77383c" +content-hash = "4b3549e9e47535d1fea6015a0f7ebf056a42e4d27e766583ccd8b59ebe8297d6" diff --git a/pyproject.toml b/pyproject.toml index 71981e8d0..11e99ecbe 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -22,11 +22,7 @@ deepdiff = "6.2.1" emoji = "2.2.0" feedparser = "6.0.10" lxml = "4.9.1" - -# Must be kept on this version unless doc command output is fixed -# See https://github.com/python-discord/bot/pull/2156 -markdownify = "0.6.1" - +markdownify = "0.11.6" more-itertools = "9.0.0" python-dateutil = "2.8.2" python-frontmatter = "1.0.0" diff --git a/tests/bot/exts/info/doc/test_parsing.py b/tests/bot/exts/info/doc/test_parsing.py index 1663d8491..d2105a53c 100644 --- a/tests/bot/exts/info/doc/test_parsing.py +++ b/tests/bot/exts/info/doc/test_parsing.py @@ -1,6 +1,7 @@ from unittest import TestCase from bot.exts.info.doc import _parsing as parsing +from bot.exts.info.doc._markdown import DocMarkdownConverter class SignatureSplitter(TestCase): @@ -64,3 +65,25 @@ class SignatureSplitter(TestCase): for input_string, expected_output in test_cases: with self.subTest(input_string=input_string): self.assertEqual(list(parsing._split_parameters(input_string)), expected_output) + + +class MarkdownConverterTest(TestCase): + def test_hr_removed(self): + test_cases = ( + ('<hr class="docutils"/>', ""), + ("<hr>", ""), + ) + self._run_tests(test_cases) + + def test_whitespace_removed(self): + test_cases = ( + ("lines\nof\ntext", "lines of text"), + ("lines\n\nof\n\ntext", "lines of text"), + ) + self._run_tests(test_cases) + + def _run_tests(self, test_cases: tuple[tuple[str, str], ...]): + for input_string, expected_output in test_cases: + with self.subTest(input_string=input_string): + d = DocMarkdownConverter(page_url="https://example.com") + self.assertEqual(d.convert(input_string), expected_output) |