Skip to content

fix: resolve link hrefs in a single pass (O(n) instead of O(n^2)) #118

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
BrianWillows wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: resolve link hrefs in a single pass (O(n) instead of O(n^2)) #118

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
37 changes: 34 additions & 3 deletions src/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,15 @@ export default function parse(md, prevLinks) {
out = '',
links = prevLinks || {},
last = 0,
// Link hrefs are resolved in a single final pass instead of rewriting the
// whole output on every closing `]` (previously O(n^2) on link-heavy input).
// `linkOpens` records the offset of every `<a>` marker as output is
// appended; `linkPtr` consumes them left-to-right, preserving the original
// "first unresolved `<a>` wins" semantics. Offsets stay valid because we
// only ever append to `out`.
linkOpens = [],
linkPtr = 0,
linkEdits = null,
chunk, prev, token, inner, t;

function tag(token) {
Expand All @@ -47,6 +56,16 @@ export default function parse(md, prevLinks) {
return str;
}

// Append to `out`, recording the offset of every `<a>` link marker so hrefs
// can be filled in one final pass. Generated chunks never start with `>` nor
// end with `<a`, so no `<a>` can straddle an append boundary.
function emit(str) {
for (let k = str.indexOf('<a>'); k !== -1; k = str.indexOf('<a>', k + 1)) {
linkOpens.push(out.length + k);
}
out += str;
}

md = md.replace(/^\[(.+?)\]:\s*(.+)$/gm, (s, name, url) => {
links[name.toLowerCase()] = url;
return '';
Expand Down Expand Up @@ -82,7 +101,9 @@ export default function parse(md, prevLinks) {
}
// Links:
else if (token[10]) {
out = out.replace('<a>', `<a href="${encodeAttr(token[11] || links[prev.toLowerCase()])}">`);
if (linkPtr < linkOpens.length) {
(linkEdits || (linkEdits = [])).push([linkOpens[linkPtr++], `<a href="${encodeAttr(token[11] || links[prev.toLowerCase()])}">`]);
}
chunk = flush() + '</a>';
}
else if (token[9]) {
Expand All @@ -101,8 +122,18 @@ export default function parse(md, prevLinks) {
else if (token[17] || token[1]) {
chunk = tag(token[17] || '--');
}
out += prev;
out += chunk;
emit(prev);
emit(chunk);
}

// Fill in the deferred link hrefs in one left-to-right pass.
if (linkEdits) {
let merged = '', pos = 0;
for (let edit of linkEdits) {
merged += out.slice(pos, edit[0]) + edit[1];
pos = edit[0] + 3;
}
out = merged + out.slice(pos);
}

return (out + md.substring(last) + flush()).replace(/^\n+|\n+$/g, '');
Expand Down