Skip to content

fix: regexp charset parsing #187

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

Merged
merged 1 commit into from
Aug 8, 2025
Merged

fix: regexp charset parsing #187

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: 5 additions & 0 deletions .changeset/funny-pens-peel.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"htmljs-parser": patch
---

Fix regexp charset parsing issue.
51 changes: 51 additions & 0 deletions ...ures/attr-regex-character-classes/__snapshots__/attr-regex-character-classes.expected.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
1╭─ <div pattern=/[abc/] /></div>
│ ││ │ ││ ││ │ ╰─ closeTagEnd(div)
│ ││ │ ││ ││ ╰─ closeTagName "div"
│ ││ │ ││ │╰─ closeTagStart "</"
│ ││ │ ││ ╰─ openTagEnd
│ ││ │ │╰─ attrValue.value "/[abc/] /"
│ ││ │ ╰─ attrValue "=/[abc/] /"
│ ││ ╰─ attrName "pattern"
│ │╰─ tagName "div"
╰─ ╰─ openTagStart
2╭─ <div pattern=/[a-z/] /></div>
│ ││ │ ││ ││ │ ╰─ closeTagEnd(div)
│ ││ │ ││ ││ ╰─ closeTagName "div"
│ ││ │ ││ │╰─ closeTagStart "</"
│ ││ │ ││ ╰─ openTagEnd
│ ││ │ │╰─ attrValue.value "/[a-z/] /"
│ ││ │ ╰─ attrValue "=/[a-z/] /"
│ ││ ╰─ attrName "pattern"
│ │╰─ tagName "div"
╰─ ╰─ openTagStart
3╭─ <div pattern=/[^abc/] /></div>
│ ││ │ ││ ││ │ ╰─ closeTagEnd(div)
│ ││ │ ││ ││ ╰─ closeTagName "div"
│ ││ │ ││ │╰─ closeTagStart "</"
│ ││ │ ││ ╰─ openTagEnd
│ ││ │ │╰─ attrValue.value "/[^abc/] /"
│ ││ │ ╰─ attrValue "=/[^abc/] /"
│ ││ ╰─ attrName "pattern"
│ │╰─ tagName "div"
╰─ ╰─ openTagStart
4╭─ <div pattern=/[a\]b/] /></div>
│ ││ │ ││ ││ │ ╰─ closeTagEnd(div)
│ ││ │ ││ ││ ╰─ closeTagName "div"
│ ││ │ ││ │╰─ closeTagStart "</"
│ ││ │ ││ ╰─ openTagEnd
│ ││ │ │╰─ attrValue.value "/[a\\]b/] /"
│ ││ │ ╰─ attrValue "=/[a\\]b/] /"
│ ││ ╰─ attrName "pattern"
│ │╰─ tagName "div"
╰─ ╰─ openTagStart
5╭─ <div pattern=/[\w\s/] /></div>
│ ││ │ ││ ││ │ ╰─ closeTagEnd(div)
│ ││ │ ││ ││ ╰─ closeTagName "div"
│ ││ │ ││ │╰─ closeTagStart "</"
│ ││ │ ││ ╰─ openTagEnd
│ ││ │ │╰─ attrValue.value "/[\\w\\s/] /"
│ ││ │ ╰─ attrValue "=/[\\w\\s/] /"
│ ││ ╰─ attrName "pattern"
│ │╰─ tagName "div"
╰─ ╰─ openTagStart
6╰─
5 changes: 5 additions & 0 deletions src/__tests__/fixtures/attr-regex-character-classes/input.marko
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
<div pattern=/[abc/] /></div>
<div pattern=/[a-z/] /></div>
<div pattern=/[^abc/] /></div>
<div pattern=/[a\]b/] /></div>
<div pattern=/[\w\s/] /></div>
27 changes: 17 additions & 10 deletions src/states/REGULAR_EXPRESSION.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,16 +18,23 @@ export const REGULAR_EXPRESSION: StateDefinition<RegExpMeta> = {
exit() {},

char(code, regExp) {
if (code === CODE.BACK_SLASH) {
// Handle escape sequence
this.pos++; // skip \
} else if (code === CODE.OPEN_SQUARE_BRACKET && regExp.isInCharSet) {
regExp.isInCharSet = true;
} else if (code === CODE.CLOSE_SQUARE_BRACKET && regExp.isInCharSet) {
regExp.isInCharSet = false;
} else if (code === CODE.FORWARD_SLASH && !regExp.isInCharSet) {
this.pos++; // skip /
this.exitState();
switch (code) {
case CODE.BACK_SLASH:
// Handle escape sequence
this.pos++; // skip \
break;
case CODE.OPEN_SQUARE_BRACKET:
regExp.isInCharSet = true;
break;
case CODE.CLOSE_SQUARE_BRACKET:
regExp.isInCharSet = false;
break;
case CODE.FORWARD_SLASH:
if (!regExp.isInCharSet) {
this.pos++; // skip /
this.exitState();
}
break;
}
},

Expand Down
Loading