github-mirror/discourse
2
0
Fork 0
mirror of https://github.com/discourse/discourse.git synced 2025-05-24 03:36:18 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

FEATURE: Use basic HTML table if it can't be converted to Markdown

Browse Source 
Previously `HtmlToMarkdown` always converted HTML tables into Markdown tables. That lead to some badly formatted Markdown tables, e.g. when the table contained `rowspan` or `colspan`. This solves the issue by using very basic HTML tables in those cases.
This commit is contained in:
Gerhard Schlager
2024-06-09 13:11:37 +02:00
committed by Gerhard Schlager
parent b8f2cbf41c
commit 52e81582b4
2 changed files with 194 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

150
spec/lib/html_to_markdown_spec.rb
View File

@ -544,7 +544,7 @@ RSpec.describe HtmlToMarkdown do
)
end
it "doesn't swallow badly formatted <table>" do
it "keeps HTML for badly formatted <table>" do
html = <<~HTML
<table>
<tr>
@ -554,13 +554,153 @@ RSpec.describe HtmlToMarkdown do
<th>4</th>
</tr>
<tr>
<td>One</td>
<td>Two</td>
<td>Three</td>
<td>&lt;One&gt;</td>
<td><strong>Two</strong></td>
<td>Three<script>alert("foo")</script></td>
</tr>
</table>
HTML
expect(html_to_markdown(html)).to eq("1 2 3 4 \nOne Two Three")
markdown = <<~MD
<table>
<tr>
<th>
1
</th>
<th>
2
</th>
<th>
3
</th>
<th>
4
</th>
</tr>
<tr>
<td>
&lt;One&gt;
</td>
<td>
**Two**
</td>
<td>
Three
</td>
</tr>
</table>
MD
expect(html_to_markdown(html)).to eq(markdown.strip)
end
it "keeps HTML for <table> with colspan" do
html = <<~HTML
<table>
<tr>
<th>1</th>
<th>2</th>
</tr>
<tr>
<td colspan="2">One / Two</td>
</tr>
</table>
HTML
markdown = <<~MD
<table>
<tr>
<th>
1
</th>
<th>
2
</th>
</tr>
<tr>
<td colspan="2">
One / Two
</td>
</tr>
</table>
MD
expect(html_to_markdown(html)).to eq(markdown.strip)
end
it "keeps HTML for <table> with rowspan" do
html = <<~HTML
<table>
<tr>
<th>1</th>
<th>2</th>
</tr>
<tr>
<td>A</td>
<td rowspan="2">B</td>
</tr>
<tr>
<td>C</td>
</tr>
</table>
HTML
markdown = <<~MD
<table>
<tr>
<th>
1
</th>
<th>
2
</th>
</tr>
<tr>
<td>
A
</td>
<td rowspan="2">
B
</td>
</tr>
<tr>
<td>
C
</td>
</tr>
</table>
MD
expect(html_to_markdown(html)).to eq(markdown.strip)
end
end