Last active
September 7, 2021 09:32
-
-
Save gushogg-blake/0da06259ee2a2802cf619ca3fe03f9fe to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
let Parser = require("tree-sitter"); | |
let HTML = require("tree-sitter-html"); | |
let parser = new Parser(); | |
parser.setLanguage(HTML); | |
let code = dedent(` | |
<!doctype html> | |
<html> | |
<body> | |
<script> | |
</script> | |
</body> | |
</html> | |
`); | |
let tree = parser.parse(code); | |
console.log("cursor: " + [...generateNodes_cursor(tree.rootNode)].map(n => n.type).join(" ")); | |
console.log("pointers: " + [...generateNodes_pointers(tree.rootNode)].map(n => n.type).join(" ")); | |
function *generateNodes_cursor(node) { | |
let cursor = node.walk(); | |
while (true) { | |
let node = cursor.currentNode; | |
yield node; | |
if (!advanceCursor(cursor)) { | |
break; | |
} | |
} | |
} | |
function *generateNodes_pointers(node) { | |
while (true) { | |
yield node; | |
node = next(node); | |
if (!node) { | |
break; | |
} | |
} | |
} | |
function advanceCursor(cursor) { | |
if (cursor.gotoFirstChild()) { | |
return true; | |
} | |
if (cursor.gotoNextSibling()) { | |
return true; | |
} | |
while (cursor.gotoParent()) { | |
if (cursor.gotoNextSibling()) { | |
return true; | |
} | |
} | |
return false; | |
} | |
function next(node) { | |
if (node.firstChild) { | |
return node.firstChild; | |
} | |
if (node.nextSibling) { | |
return node.nextSibling; | |
} | |
while (node = node.parent) { | |
if (node.nextSibling) { | |
return node.nextSibling; | |
} | |
} | |
return null; | |
} | |
function dedent(str) { | |
str = str.substr(1); | |
let minIndent = str.split("\n").reduce(function(min, line) { | |
return Math.min(min, line.match(/^\t*/)[0].length); | |
}, Infinity) + 1; | |
let re = new RegExp("^\t{" + minIndent + "}", "gm"); | |
str = str.replace(re, ""); | |
// final indent (up to closing `) is one less so doesn't match above | |
str = str.replace(/\n\s+$/, "\n"); | |
return str; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment