Skip to content

fix: support unicode characters in HTML and XML tag names #237

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

Open
Akiyo974 wants to merge 1 commit into
base: main
Choose a base branch
from
+20 −4
Open

fix: support unicode characters in HTML and XML tag names #237

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 4 additions & 1 deletion src/Languages/Html/Patterns/HtmlCloseTagPattern.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,10 @@
#[PatternTest(input: '</CamelCase>', output: 'CamelCase')]
#[PatternTest(input: '</x-hello>', output: 'x-hello')]
#[PatternTest(input: '</a>', output: 'a')]
#[PatternTest(input: '</math-α>', output: 'math-α')]
#[PatternTest(input: '</emotion-😍-emoji>', output: 'emotion-😍-emoji')]
# The following are not HTML valid
#[PatternTest(input: '</αtag>', output: null)]
#[PatternTest(input: '</ns:tag>', output: null)]
#[PatternTest(input: '</point.x>', output: null)]
#[PatternTest(input: '</point_y>', output: null)]
Expand All @@ -27,7 +30,7 @@

public function getPattern(): string
{
return '<\/(?<match>[a-zA-Z][a-zA-Z0-9\-]*(?![:_\.\w]))';
return '<\/(?<match>[a-zA-Z][a-zA-Z0-9\-\x80-\xFF]*(?![:_\.\w\x80-\xFF]))';
}

public function getTokenType(): TokenTypeEnum
Expand Down
5 changes: 4 additions & 1 deletion src/Languages/Html/Patterns/HtmlOpenTagPattern.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,10 @@
#[PatternTest(input: '<CamelCase>', output: 'CamelCase')]
#[PatternTest(input: '<a-component>', output: 'a-component')]
#[PatternTest(input: '<a href="">', output: 'a')]
#[PatternTest(input: '<math-α>', output: 'math-α')]
#[PatternTest(input: '<emotion-😍-emoji>', output: 'emotion-😍-emoji')]
# The following are not HTML valid
#[PatternTest(input: '<αtag>', output: null)]
#[PatternTest(input: '<_private>', output: null)]
#[PatternTest(input: '<ns:tag>', output: null)]
#[PatternTest(input: '<point.x>', output: null)]
Expand All @@ -27,7 +30,7 @@

public function getPattern(): string
{
return '<(?<match>[a-zA-Z][a-zA-Z0-9\-]*(?![:_\.\w]))';
return '<(?<match>[a-zA-Z][a-zA-Z0-9\-\x80-\xFF]*(?![:_\.\w\x80-\xFF]))';
}

public function getTokenType(): TokenTypeEnum
Expand Down
5 changes: 4 additions & 1 deletion src/Languages/Xml/Patterns/XmlCloseTagPattern.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,9 @@
#[PatternTest(input: '</point.x>', output: 'point.x')]
#[PatternTest(input: '</point_y>', output: 'point_y')]
#[PatternTest(input: '</_private>', output: '_private')]
#[PatternTest(input: '</données>', output: 'données')]
#[PatternTest(input: '</élément>', output: 'élément')]
#[PatternTest(input: '</数据>', output: '数据')]
# The following are not valid XML tags
#[PatternTest(input: '</1tag>', output: null)]
#[PatternTest(input: '</-tag>', output: null)]
Expand All @@ -27,7 +30,7 @@

public function getPattern(): string
{
return '<\/(?<match>[a-zA-Z_][\w\-\:\.]*)';
return '<\/(?<match>[a-zA-Z_\x80-\xFF][\w\-\:\.\x80-\xFF]*)';
}

public function getTokenType(): TokenTypeEnum
Expand Down
5 changes: 4 additions & 1 deletion src/Languages/Xml/Patterns/XmlOpenTagPattern.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,9 @@
#[PatternTest(input: '<point.x>', output: 'point.x')]
#[PatternTest(input: '<point_y>', output: 'point_y')]
#[PatternTest(input: '<_private>', output: '_private')]
#[PatternTest(input: '<données>', output: 'données')]
#[PatternTest(input: '<élément>', output: 'élément')]
#[PatternTest(input: '<数据>', output: '数据')]
# The following are not valid XML tags
#[PatternTest(input: '<1tag>', output: null)]
#[PatternTest(input: '<-tag>', output: null)]
Expand All @@ -28,7 +31,7 @@

public function getPattern(): string
{
return '<(?<match>[a-zA-Z_][\w\-\:\.]*)';
return '<(?<match>[a-zA-Z_\x80-\xFF][\w\-\:\.\x80-\xFF]*)';
}

public function getTokenType(): TokenTypeEnum
Expand Down
2 changes: 2 additions & 0 deletions tests/Languages/Html/HtmlLanguageTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,8 @@ public static function provide_highlight_cases(): iterable
&lt;?php <span class="hl-property">foo</span>(); ?&gt;
&lt;/<span class="hl-keyword">tag</span>&gt;
TXT],
['<math-α></math-α>', '&lt;<span class="hl-keyword">math-α</span>&gt;&lt;/<span class="hl-keyword">math-α</span>&gt;'],
['<emotion-😍-emoji></emotion-😍-emoji>', '&lt;<span class="hl-keyword">emotion-😍-emoji</span>&gt;&lt;/<span class="hl-keyword">emotion-😍-emoji</span>&gt;'],
];
}
}
2 changes: 2 additions & 0 deletions tests/Languages/Xml/XmlLanguageTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,8 @@ public static function provide_highlight_cases(): iterable
TXT],
["<ns:tag><tag></tag></ns:tag>", '&lt;<span class="hl-keyword">ns:tag</span>&gt;&lt;<span class="hl-keyword">tag</span>&gt;&lt;/<span class="hl-keyword">tag</span>&gt;&lt;/<span class="hl-keyword">ns:tag</span>&gt;'],
['<root xmlns:ns="...">', '&lt;<span class="hl-keyword">root</span> <span class="hl-property">xmlns:ns</span>=&quot;...&quot;&gt;'],
['<données>1</données>', '&lt;<span class="hl-keyword">données</span>&gt;1&lt;/<span class="hl-keyword">données</span>&gt;'],
['<élément></élément>', '&lt;<span class="hl-keyword">élément</span>&gt;&lt;/<span class="hl-keyword">élément</span>&gt;'],
];
}
}
Loading