Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Feature: Markdown escape all #1754

Merged
merged 7 commits into from
Oct 20, 2021
Merged

Feature: Markdown escape all #1754

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
f75f30a
Added escape all markdown characters method to MarkdownSanitizer
sofiadparamo Aug 2, 2021
f13ed20
Implemented Unit Testing for MarkdownSanitizer escape
sofiadparamo Aug 2, 2021
6876677
Fixed escaping invalid tokens matching `>` character
sofiadparamo Aug 3, 2021
3d7902b
Ignore single pipe when escaping
sofiadparamo Sep 19, 2021
0a97992
Add test for single-middle quotation symbol and reformat file spacing
sofiadparamo Sep 19, 2021
054a8a5
Code cleanup
sofiadparamo Sep 23, 2021
0c4869f
Merge branch 'DV8FromTheWorld:development' into markdown-escape-all
sofiadparamo Sep 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
89 changes: 89 additions & 0 deletions src/main/java/net/dv8tion/jda/api/utils/MarkdownSanitizer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,6 +188,95 @@ public static String escape(@Nonnull String sequence, int ignored)
.compute(sequence);
}

/**
* Escapes every single markdown formatting token found in the provided string.
* <br>Example: {@code escape("**Hello _World_", true)}
*
* @param sequence
* The string to sanitize
* @param single
* Whether it should scape single tokens or not.
*
* @throws java.lang.IllegalArgumentException
* If provided with null sequence
*
* @return The string with escaped markdown
*/
@Nonnull
public static String escape(@Nonnull String sequence, boolean single)
{
Checks.notNull(sequence, "Input");
if(!single) return escape(sequence);

StringBuilder builder = new StringBuilder();
boolean escaped = false;
boolean newline = true;
for (int i = 0; i < sequence.length(); i++)
{
char current = sequence.charAt(i);
if (newline)
{
newline = Character.isWhitespace(current); // might still be a quote if prefixed by whitespace
if (current == '>')
{
// Check for quote if line starts with angle bracket
if (i + 1 < sequence.length() && Character.isWhitespace(sequence.charAt(i+1)))
{
builder.append("\\>"); // simple quote
}
else if (i + 3 < sequence.length() && sequence.startsWith(">>>", i) && Character.isWhitespace(sequence.charAt(i+3)))
{
builder.append("\\>\\>\\>").append(sequence.charAt(i+3)); // block quote
i += 3; // since we include 3 angle brackets AND whitespace
}
else
{
builder.append(current); // just a normal angle bracket
}
continue;
}
}

if (escaped)
{
builder.append(current);
escaped = false;
continue;
}
// Handle average case
switch (current)
{
case '*': // simple markdown escapes for single characters
case '_':
case '`':
builder.append('\\').append(current);
break;
case '|': // cases that require at least 2 characters in sequence
case '~':
if (i + 1 < sequence.length() && sequence.charAt(i+1) == current)
{
builder.append('\\').append(current)
.append('\\').append(current);
i++;
}
else
builder.append(current);
break;
case '\\': // escape character
builder.append(current);
escaped = true;
break;
case '\n': // linefeed is a special case for quotes
builder.append(current);
newline = true;
break;
default:
builder.append(current);
}
}
return builder.toString();
}

/**
* Switches the used {@link net.dv8tion.jda.api.utils.MarkdownSanitizer.SanitizationStrategy}.
*
Expand Down
70 changes: 70 additions & 0 deletions src/test/java/MarkdownTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -391,3 +391,73 @@ public void testQuote()
Assertions.assertEquals("\\> \\_Hello \n\\> World\\_", markdown.compute("> _Hello \n> World_"));
}
}

class EscapeMarkdownAllTest
{
@Test
public void testAsterisk()
{
Assertions.assertEquals("Hello\\*World", MarkdownSanitizer.escape("Hello*World", true));
Assertions.assertEquals("Hello\\*\\*World", MarkdownSanitizer.escape("Hello**World", true));
Assertions.assertEquals("Hello\\*\\*\\*World", MarkdownSanitizer.escape("Hello***World", true));

MinnDevelopment marked this conversation as resolved.
Show resolved Hide resolved
Assertions.assertEquals("Hello\\*World", MarkdownSanitizer.escape("Hello\\*World", true));
Assertions.assertEquals("Hello\\*\\*World", MarkdownSanitizer.escape("Hello\\*\\*World", true));
Assertions.assertEquals("Hello\\*\\*\\*World", MarkdownSanitizer.escape("Hello\\*\\*\\*World", true));
}

@Test
public void testUnderscore()
{
Assertions.assertEquals("Hello\\_World", MarkdownSanitizer.escape("Hello_World", true));
Assertions.assertEquals("Hello\\_\\_World", MarkdownSanitizer.escape("Hello__World", true));
Assertions.assertEquals("Hello\\_\\_\\_World", MarkdownSanitizer.escape("Hello___World", true));

Assertions.assertEquals("Hello\\_World", MarkdownSanitizer.escape("Hello\\_World", true));
Assertions.assertEquals("Hello\\_\\_World", MarkdownSanitizer.escape("Hello\\_\\_World", true));
Assertions.assertEquals("Hello\\_\\_\\_World", MarkdownSanitizer.escape("Hello\\_\\_\\_World", true));
}

@Test
public void testCodeBlock()
{
Assertions.assertEquals("Hello\\`World", MarkdownSanitizer.escape("Hello`World", true));
Assertions.assertEquals("Hello\\`\\`World", MarkdownSanitizer.escape("Hello``World", true));
Assertions.assertEquals("Hello\\`\\`\\`World", MarkdownSanitizer.escape("Hello```World", true));

Assertions.assertEquals("Hello\\`World", MarkdownSanitizer.escape("Hello\\`World", true));
Assertions.assertEquals("Hello\\`\\`World", MarkdownSanitizer.escape("Hello\\`\\`World", true));
Assertions.assertEquals("Hello\\`\\`\\`World", MarkdownSanitizer.escape("Hello\\`\\`\\`World", true));
}

@Test
public void testSpoiler()
{
Assertions.assertEquals("Hello\\|\\|World", MarkdownSanitizer.escape("Hello||World", true));
Assertions.assertEquals("Hello|World", MarkdownSanitizer.escape("Hello|World", true));

Assertions.assertEquals("Hello\\|\\|World", MarkdownSanitizer.escape("Hello\\|\\|World", true));
Assertions.assertEquals("Hello\\|World", MarkdownSanitizer.escape("Hello\\|World", true));
}

@Test
public void testStrike()
{
Assertions.assertEquals("Hello\\~\\~World", MarkdownSanitizer.escape("Hello~~World", true));
Assertions.assertEquals("Hello\\~\\~World", MarkdownSanitizer.escape("Hello\\~\\~World", true));
}

@Test
public void testQuote()
{
Assertions.assertEquals("\\> Hello World", MarkdownSanitizer.escape("> Hello World", true));
Assertions.assertEquals(">Hello World", MarkdownSanitizer.escape(">Hello World", true));
Assertions.assertEquals("\\>\\>\\> Hello World", MarkdownSanitizer.escape(">>> Hello World", true));
Assertions.assertEquals(">>>Hello World", MarkdownSanitizer.escape(">>>Hello World", true));
Assertions.assertEquals("\\>\\>\\> Hello > World\n\\> Hello >>> World\n<@12345> > Hello\n \\> Hello world", MarkdownSanitizer.escape(">>> Hello > World\n> Hello >>> World\n<@12345> > Hello\n > Hello world", true));

Assertions.assertEquals("\\> Hello World", MarkdownSanitizer.escape("\\> Hello World", true));
Assertions.assertEquals("\\>\\>\\> Hello World", MarkdownSanitizer.escape("\\>\\>\\> Hello World", true));
Assertions.assertEquals("Hello > World", MarkdownSanitizer.escape("Hello > World"));
}
}