mirror of
https://github.com/pbakaus/impeccable.git
synced 2026-09-11 21:57:14 +03:00
Merge pull request #632 from pbakaus/fix/589-comment-strip-markup-css
Fix: strip comments in markup and stylesheets before regex matchers (#589)
This commit is contained in:
Abdul Wahab
@@ -42,6 +42,7 @@ function shouldRunPageAnalyzers(content, filePath) {
|
||||
}
|
||||
|
||||
const JS_SOURCE_EXTS = new Set(['.js', '.jsx', '.ts', '.tsx', '.mjs', '.cjs']);
|
||||
const STYLESHEET_EXTS = new Set(['.css', '.scss', '.sass', '.less']);
|
||||
const REGEX_PREFIX_KEYWORDS = new Set(['await', 'case', 'default', 'delete', 'do', 'else', 'in', 'instanceof', 'new', 'of', 'return', 'throw', 'typeof', 'void', 'yield']);
|
||||
const BLOCK_BRACE_PREFIX_KEYWORDS = new Set(['do', 'else', 'finally', 'try']);
|
||||
|
||||
@@ -256,6 +257,153 @@ function stripCssComments(content) {
|
||||
return content.replace(/\/\*[\s\S]*?\*\//g, comment => comment.replace(/[^\n]/g, ' '));
|
||||
}
|
||||
|
||||
function blankHtmlComments(text) {
|
||||
return text.replace(/<!--[\s\S]*?-->/g, comment => comment.replace(/[^\n]/g, ' '));
|
||||
}
|
||||
|
||||
function blankCssLineCommentsInStyleBlocks(text) {
|
||||
const re = /<style\b[^>]*>([\s\S]*?)<\/style>/gi;
|
||||
let output = '';
|
||||
let lastIndex = 0;
|
||||
let match;
|
||||
while ((match = re.exec(text)) !== null) {
|
||||
const inner = match[1];
|
||||
const openLength = match[0].length - inner.length - '</style>'.length;
|
||||
output += text.slice(lastIndex, match.index);
|
||||
output += match[0].slice(0, openLength);
|
||||
output += blankCssLineComments(inner);
|
||||
output += match[0].slice(openLength + inner.length);
|
||||
lastIndex = re.lastIndex;
|
||||
}
|
||||
return output + text.slice(lastIndex);
|
||||
}
|
||||
|
||||
function blankHtmlAndCssCommentsOutsideScripts(text) {
|
||||
const re = /<script\b[^>]*>[\s\S]*?<\/script>/gi;
|
||||
let output = '';
|
||||
let lastIndex = 0;
|
||||
let match;
|
||||
while ((match = re.exec(text)) !== null) {
|
||||
output += blankCssLineCommentsInStyleBlocks(stripCssComments(blankHtmlComments(text.slice(lastIndex, match.index))));
|
||||
output += match[0];
|
||||
lastIndex = re.lastIndex;
|
||||
}
|
||||
return output + blankCssLineCommentsInStyleBlocks(stripCssComments(blankHtmlComments(text.slice(lastIndex))));
|
||||
}
|
||||
|
||||
function blankCssLineComments(text) {
|
||||
let output = '';
|
||||
let state = 'code';
|
||||
let urlDepth = 0;
|
||||
for (let i = 0; i < text.length; i++) {
|
||||
const char = text[i];
|
||||
const next = text[i + 1];
|
||||
if (state === 'line') {
|
||||
if (char === '\n') {
|
||||
output += '\n';
|
||||
state = 'code';
|
||||
} else {
|
||||
output += ' ';
|
||||
}
|
||||
continue;
|
||||
}
|
||||
if (state === 'single' || state === 'double') {
|
||||
output += char;
|
||||
if (char === '\\' && next) {
|
||||
output += next;
|
||||
i++;
|
||||
} else if ((state === 'single' && char === "'") || (state === 'double' && char === '"')) {
|
||||
state = 'code';
|
||||
}
|
||||
continue;
|
||||
}
|
||||
const prev = output.length ? output[output.length - 1] : '';
|
||||
if (char === '/' && next === '/' && urlDepth === 0 && prev !== ':' && prev !== '(' && prev !== '\\') {
|
||||
output += ' ';
|
||||
i++;
|
||||
state = 'line';
|
||||
continue;
|
||||
}
|
||||
if (char === "'") state = 'single';
|
||||
else if (char === '"') state = 'double';
|
||||
if (char === '(') {
|
||||
const behind = output.replace(/\s+$/, '');
|
||||
if (urlDepth > 0 || /url$/i.test(behind)) urlDepth++;
|
||||
} else if (char === ')' && urlDepth) {
|
||||
urlDepth--;
|
||||
}
|
||||
output += char;
|
||||
}
|
||||
return output;
|
||||
}
|
||||
|
||||
function findAstroFrontmatterClose(text) {
|
||||
if (!text.startsWith('---')) return -1;
|
||||
let cursor = text.indexOf('\n');
|
||||
if (cursor === -1) return -1;
|
||||
cursor += 1;
|
||||
while (cursor < text.length) {
|
||||
if (text[cursor - 1] === '\n' && text.startsWith('---', cursor)) {
|
||||
let end = cursor + 3;
|
||||
while (text[end] === ' ' || text[end] === '\t') end++;
|
||||
if (end >= text.length || text[end] === '\n' || text[end] === '\r') return cursor - 1;
|
||||
}
|
||||
const char = text[cursor];
|
||||
const next = text[cursor + 1];
|
||||
if (char === "'" || char === '"') {
|
||||
const close = findQuotedStringEnd(text, cursor, char);
|
||||
if (close === -1) return -1;
|
||||
cursor = close + 1;
|
||||
continue;
|
||||
}
|
||||
if (char === '`') {
|
||||
const close = findTemplateLiteralEnd(text, cursor);
|
||||
if (close === -1) return -1;
|
||||
cursor = close + 1;
|
||||
continue;
|
||||
}
|
||||
if (char === '/' && next === '/') {
|
||||
const lineEnd = text.indexOf('\n', cursor);
|
||||
if (lineEnd === -1) return -1;
|
||||
cursor = lineEnd;
|
||||
continue;
|
||||
}
|
||||
if (char === '/' && next === '*') {
|
||||
const commentEnd = text.indexOf('*/', cursor + 2);
|
||||
if (commentEnd === -1) return -1;
|
||||
cursor = commentEnd + 2;
|
||||
continue;
|
||||
}
|
||||
if (char === '/' && next !== '/' && next !== '*') {
|
||||
const close = findRegexLiteralEnd(text, cursor);
|
||||
if (close !== -1) {
|
||||
cursor = close + 1;
|
||||
continue;
|
||||
}
|
||||
}
|
||||
cursor++;
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
|
||||
function blankAstroFrontmatterComments(text) {
|
||||
const close = findAstroFrontmatterClose(text);
|
||||
if (close === -1) return text;
|
||||
return stripJsComments(text.slice(0, close)) + text.slice(close);
|
||||
}
|
||||
|
||||
function blankCommentsForMatchers(text, ext) {
|
||||
if (PAGE_ANALYZER_EXTS.has(ext)) {
|
||||
const withFrontmatter = ext === '.astro' ? blankAstroFrontmatterComments(text) : text;
|
||||
return blankHtmlAndCssCommentsOutsideScripts(withFrontmatter);
|
||||
}
|
||||
if (STYLESHEET_EXTS.has(ext)) {
|
||||
const withoutBlocks = stripCssComments(text);
|
||||
return ext === '.css' ? withoutBlocks : blankCssLineComments(withoutBlocks);
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
function firstOverusedGoogleFont(text) {
|
||||
return extractGoogleFontFamilies(text).find(f => OVERUSED_FONTS.has(f)) || '';
|
||||
}
|
||||
@@ -1028,14 +1176,13 @@ function detectText(content, filePath, options = {}) {
|
||||
const ext = extFromFilePath(filePath);
|
||||
const commentStrippedSource = JS_SOURCE_EXTS.has(ext) ? stripJsComments(content, {
|
||||
jsx: ext === '.js' || ext === '.jsx' || ext === '.tsx',
|
||||
}) : content;
|
||||
}) : blankCommentsForMatchers(content, ext);
|
||||
const source = stripCssInJsComments(commentStrippedSource, ext);
|
||||
const lines = source.split('\n');
|
||||
|
||||
// Run regex matchers on the full file content (catches Tailwind classes, inline styles)
|
||||
// Enable block context for CSS files where related properties span multiple lines
|
||||
const cssLike = new Set(['.css', '.scss', '.sass', '.less']);
|
||||
findings.push(...runRegexMatchers(lines, filePath, 0, cssLike.has(ext) || null, {
|
||||
findings.push(...runRegexMatchers(lines, filePath, 0, STYLESHEET_EXTS.has(ext) || null, {
|
||||
profile,
|
||||
phase: 'source',
|
||||
}));
|
||||
@@ -1050,7 +1197,7 @@ function detectText(content, filePath, options = {}) {
|
||||
scanCssTextForPseudoStripe(text).map(hit =>
|
||||
finding(hit.id, filePath, hit.snippet, lineOffset + text.slice(0, hit.index).split('\n').length));
|
||||
|
||||
if (cssLike.has(ext)) {
|
||||
if (STYLESHEET_EXTS.has(ext)) {
|
||||
findings.push(...scanInsetStripeCss(content, filePath));
|
||||
findings.push(...pseudoStripeFindings(content, 0));
|
||||
}
|
||||
@@ -1078,7 +1225,8 @@ function detectText(content, filePath, options = {}) {
|
||||
}, () => extractStyleBlocks(content, ext))
|
||||
: extractStyleBlocks(content, ext);
|
||||
for (const block of styleBlocks) {
|
||||
const blockLines = block.content.split('\n');
|
||||
const blockContent = blankCssLineComments(stripCssComments(block.content));
|
||||
const blockLines = blockContent.split('\n');
|
||||
findings.push(...runRegexMatchers(blockLines, filePath, block.startLine - 1, true, {
|
||||
profile,
|
||||
phase: 'style-block',
|
||||
@@ -1089,8 +1237,8 @@ function detectText(content, filePath, options = {}) {
|
||||
// 1-based, so the offset is startLine - 2; startLine - 1 double-counted and
|
||||
// reported every selector one line low. runRegexMatchers keeps startLine - 1
|
||||
// because it indexes its split lines from zero.
|
||||
findings.push(...scanInsetStripeCss(block.content, filePath, block.startLine - 2));
|
||||
findings.push(...pseudoStripeFindings(block.content, block.startLine - 2));
|
||||
findings.push(...scanInsetStripeCss(blockContent, filePath, block.startLine - 2));
|
||||
findings.push(...pseudoStripeFindings(blockContent, block.startLine - 2));
|
||||
}
|
||||
|
||||
// Extract and scan CSS-in-JS template literals
|
||||
|
||||
@@ -382,6 +382,228 @@ describe('detectText — broken images in source comments', () => {
|
||||
|
||||
expect(findings.filter(r => r.antipattern === 'broken-image')).toHaveLength(0);
|
||||
});
|
||||
|
||||
test('ignores img tags in Astro style block comments', () => {
|
||||
const source = [
|
||||
'---',
|
||||
'const title = "Hero";',
|
||||
'---',
|
||||
'<style>',
|
||||
' /*',
|
||||
' * Example markup: <img src="">',
|
||||
' */',
|
||||
' .hero { color: red; }',
|
||||
'</style>',
|
||||
].join('\n');
|
||||
|
||||
const findings = detectText(source, 'hero.astro');
|
||||
|
||||
expect(findings.filter(r => r.antipattern === 'broken-image')).toHaveLength(0);
|
||||
});
|
||||
|
||||
test('ignores img tags in Astro HTML comments', () => {
|
||||
const source = [
|
||||
'---',
|
||||
'const title = "Hero";',
|
||||
'---',
|
||||
'<!-- <img src="" alt="Comment-only image" /> -->',
|
||||
'<img src="/logo.png" alt="Logo" />',
|
||||
].join('\n');
|
||||
|
||||
const findings = detectText(source, 'hero.astro');
|
||||
|
||||
expect(findings.filter(r => r.antipattern === 'broken-image')).toHaveLength(0);
|
||||
});
|
||||
|
||||
test('ignores img tags in Astro frontmatter line comments', () => {
|
||||
const source = [
|
||||
'---',
|
||||
'// <img src="" alt="Comment-only image" />',
|
||||
'const site = "https://example.com";',
|
||||
'---',
|
||||
'<img src="/logo.png" alt="Logo" />',
|
||||
].join('\n');
|
||||
|
||||
const findings = detectText(source, 'hero.astro');
|
||||
|
||||
expect(findings.filter(r => r.antipattern === 'broken-image')).toHaveLength(0);
|
||||
});
|
||||
|
||||
test('ignores img tags in CSS block comments', () => {
|
||||
const source = [
|
||||
'/*',
|
||||
' * Example markup: <img src="">',
|
||||
' */',
|
||||
'.hero { color: red; }',
|
||||
].join('\n');
|
||||
|
||||
const findings = detectText(source, 'hero.css');
|
||||
|
||||
expect(findings.filter(r => r.antipattern === 'broken-image')).toHaveLength(0);
|
||||
});
|
||||
|
||||
test('still detects real img tags after an HTML comment in Astro', () => {
|
||||
const source = [
|
||||
'---',
|
||||
'const title = "Hero";',
|
||||
'---',
|
||||
'<!-- decorative only -->',
|
||||
'<img src="" alt="Empty source" />',
|
||||
].join('\n');
|
||||
|
||||
const findings = detectText(source, 'hero.astro');
|
||||
|
||||
const broken = findings.filter(r => r.antipattern === 'broken-image');
|
||||
expect(broken).toHaveLength(1);
|
||||
expect(broken[0].line).toBe(5);
|
||||
});
|
||||
|
||||
test('does not blank https URLs in Astro frontmatter', () => {
|
||||
const source = [
|
||||
'---',
|
||||
'const site = "https://example.com/logo.png";',
|
||||
'---',
|
||||
'<img src="" alt="Empty source" />',
|
||||
].join('\n');
|
||||
|
||||
const findings = detectText(source, 'hero.astro');
|
||||
|
||||
expect(findings.filter(r => r.antipattern === 'broken-image')).toHaveLength(1);
|
||||
});
|
||||
|
||||
test('keeps same-line img visible after a bare https URL in Astro markup', () => {
|
||||
const source = '<p>https://example.com <img src="" alt="Empty source" /></p>';
|
||||
|
||||
const findings = detectText(source, 'hero.astro');
|
||||
|
||||
expect(findings.filter(r => r.antipattern === 'broken-image')).toHaveLength(1);
|
||||
});
|
||||
|
||||
test('preserves line numbers after comment blanking in Astro', () => {
|
||||
const source = [
|
||||
'---',
|
||||
'const title = "Hero";',
|
||||
'---',
|
||||
'<!-- <img src="" alt="Comment-only image" /> -->',
|
||||
'<p>Intro copy</p>',
|
||||
'<img src="" alt="Empty source" />',
|
||||
].join('\n');
|
||||
|
||||
const findings = detectText(source, 'hero.astro');
|
||||
|
||||
const broken = findings.filter(r => r.antipattern === 'broken-image');
|
||||
expect(broken).toHaveLength(1);
|
||||
expect(broken[0].line).toBe(6);
|
||||
});
|
||||
|
||||
test('does not treat comment markers inside script strings as markup comments', () => {
|
||||
const htmlDelimiters = [
|
||||
'<script>const open = "<!--";</script>',
|
||||
'<img>',
|
||||
'<script>const close = "-->";</script>',
|
||||
].join('\n');
|
||||
const cssDelimiters = [
|
||||
'<script>const open = "/*";</script>',
|
||||
'<img>',
|
||||
'<script>const close = "*/";</script>',
|
||||
].join('\n');
|
||||
|
||||
for (const filePath of ['hero.astro', 'hero.vue', 'hero.svelte']) {
|
||||
expect(detectText(htmlDelimiters, filePath).filter(r => r.antipattern === 'broken-image')).toHaveLength(1);
|
||||
expect(detectText(cssDelimiters, filePath).filter(r => r.antipattern === 'broken-image')).toHaveLength(1);
|
||||
}
|
||||
});
|
||||
|
||||
test('ignores preprocessor line comments in stylesheets', () => {
|
||||
const source = '// font-family: Inter\n.hero { color: red; }';
|
||||
|
||||
for (const filePath of ['hero.scss', 'hero.sass', 'hero.less']) {
|
||||
expect(detectText(source, filePath).filter(r => r.antipattern === 'overused-font')).toHaveLength(0);
|
||||
}
|
||||
});
|
||||
|
||||
test('still detects live font-family after a preprocessor line comment', () => {
|
||||
const source = '// skip this\n.hero { font-family: Inter; }';
|
||||
|
||||
const findings = detectText(source, 'hero.scss').filter(r => r.antipattern === 'overused-font');
|
||||
expect(findings).toHaveLength(1);
|
||||
expect(findings[0].line).toBe(2);
|
||||
});
|
||||
|
||||
test('does not blank https URLs in SCSS', () => {
|
||||
const source = '.hero { background: url(https://example.com/i.png); }\n.hero { font-family: Inter; }';
|
||||
|
||||
const findings = detectText(source, 'hero.scss').filter(r => r.antipattern === 'overused-font');
|
||||
expect(findings).toHaveLength(1);
|
||||
expect(findings[0].line).toBe(2);
|
||||
});
|
||||
|
||||
test('ignores frontmatter comments after a --- line inside a template literal', () => {
|
||||
const source = [
|
||||
'---',
|
||||
'const md = `',
|
||||
'---',
|
||||
'`;',
|
||||
'// <img src="" alt="Comment-only image" />',
|
||||
'---',
|
||||
'<div>ok</div>',
|
||||
].join('\n');
|
||||
|
||||
expect(detectText(source, 'hero.astro').filter(r => r.antipattern === 'broken-image')).toHaveLength(0);
|
||||
});
|
||||
|
||||
test('ignores preprocessor line comments in component style blocks', () => {
|
||||
const source = [
|
||||
'<style lang="scss">',
|
||||
'// font-family: Inter',
|
||||
'.hero { color: red; }',
|
||||
'</style>',
|
||||
].join('\n');
|
||||
|
||||
for (const filePath of ['hero.astro', 'hero.vue', 'hero.svelte']) {
|
||||
expect(detectText(source, filePath).filter(r => r.antipattern === 'overused-font')).toHaveLength(0);
|
||||
}
|
||||
});
|
||||
|
||||
test('still detects live font-family after a style-block line comment', () => {
|
||||
const source = [
|
||||
'<style lang="scss">',
|
||||
'// skip this',
|
||||
'.hero { font-family: Inter; }',
|
||||
'</style>',
|
||||
].join('\n');
|
||||
|
||||
const findings = detectText(source, 'hero.vue').filter(r => r.antipattern === 'overused-font');
|
||||
expect(findings).toHaveLength(1);
|
||||
expect(findings[0].line).toBe(3);
|
||||
});
|
||||
|
||||
test('ignores frontmatter comments after a regex literal that contains quotes', () => {
|
||||
const source = [
|
||||
'---',
|
||||
'const re = /["\']/;',
|
||||
'// <img src="" alt="Comment-only image" />',
|
||||
'---',
|
||||
'<div>ok</div>',
|
||||
].join('\n');
|
||||
|
||||
expect(detectText(source, 'hero.astro').filter(r => r.antipattern === 'broken-image')).toHaveLength(0);
|
||||
});
|
||||
|
||||
test('keeps live font-family after a protocol-relative URL in SCSS', () => {
|
||||
const sources = [
|
||||
'.hero { background: url( //cdn.example.com/i.png); font-family: Inter; }',
|
||||
'.hero { background: url(#{$prefix}//cdn.example.com/i.png); font-family: Inter; }',
|
||||
];
|
||||
|
||||
for (const source of sources) {
|
||||
expect(detectText(source, 'hero.scss').filter(r => r.antipattern === 'overused-font')).toHaveLength(1);
|
||||
}
|
||||
expect(detectText(
|
||||
'.hero { background: url(@{prefix}//cdn.example.com/i.png); font-family: Inter; }',
|
||||
'hero.less',
|
||||
).filter(r => r.antipattern === 'overused-font')).toHaveLength(1);
|
||||
});
|
||||
});
|
||||
|
||||
describe('detectText — CSS borders', () => {
|
||||
|
||||
Reference in New Issue
Block a user