mirror of
https://github.com/Ark0N/Codeman.git
synced 2026-11-14 10:39:32 +01:00
fix(terminal): keep code, fields and measurements out of wrapped URLs
A URL ending in `/` still took the next indented row when that row was code, a label, a log or config field, a measurement or the end of a sentence. A side-by-side sweep against master turned up shapes such as `ready.` under a codex `Listening on` line, `expect(x).toBe(y)` under a jest title, `Failure/Error:` under an rspec title, `API_KEY=...` under `BASE_URL=...`, `level=info` log fields, `45%|####` tqdm bars, `12.3MB/45.0MB`, `12.3ms` and `10:00:00.123`. A continuation is now refused when it ends with a colon, when it is a measurement or clock time, or when it is a `name=value` token under a URL ending in `/` (a query needs `?` first). A token with only `-`, `_` or `.` is also refused when it carries a call paren or ends a sentence. Wiki titles such as `Mercury_(planet)`, a file name before its period, query parameters after `?`, `&` or `_`, and percent-encoding that starts with digits still join. `self-hosted.` moves from the pinned trade-offs to the negatives; the trade-off is now a lone word without sentence punctuation.
This commit is contained in:
Aamer Akhter committed
1 parent
2a90fb8118
commit
1bdc341784
4 files changed
+135
-17
No files matched your search
@@ -171,7 +171,7 @@ const TABLE_LAST_COLUMN_ROWS: [string, string, string, string, string | null][]
|
||||
// Known trade-offs: a row end counts as a cell end, so a short indented word
|
||||
// with URL punctuation still continues the URL. Pinned so a change is deliberate.
|
||||
const TRADE_OFF_ROWS: [string, string, string][] = [
|
||||
['⏺ Docs live at https://example.com/guide/', ' self-hosted.', 'https://example.com/guide/self-hosted'],
|
||||
['⏺ Docs live at https://example.com/guide/', ' self-hosted', 'https://example.com/guide/self-hosted'],
|
||||
[
|
||||
'⏺ The docs are at https://example.com/guide/',
|
||||
' and/or the API reference covers it.',
|
||||
@@ -179,6 +179,69 @@ const TRADE_OFF_ROWS: [string, string, string][] = [
|
||||
],
|
||||
];
|
||||
|
||||
// Indented rows under a URL ending in `/` that carry URL punctuation but are
|
||||
// code, a label, a `name=value` field, a measurement or a clock time, or a word
|
||||
// ending a sentence. Each third element is the URL on the first row.
|
||||
const FIELD_AND_CODE_ROWS: [string, string, string][] = [
|
||||
[' └ Listening on http://127.0.0.1:8080/', ' ready.', 'http://127.0.0.1:8080/'],
|
||||
['⏺ Deployed to https://app.example.com/', ' Done.', 'https://app.example.com/'],
|
||||
['⏺ Docs live at https://example.com/guide/', ' self-hosted.', 'https://example.com/guide/'],
|
||||
[' Fetching https://example.com/files/', ' done...', 'https://example.com/files/'],
|
||||
[
|
||||
' ● fetch › handles https://api.example.com/v1/',
|
||||
' expect(received).toBe(expected)',
|
||||
'https://api.example.com/v1/',
|
||||
],
|
||||
[' See https://example.com/api/', ' client.get()', 'https://example.com/api/'],
|
||||
[
|
||||
'/home/u/.venv/lib/urllib3/__init__.py:35: Warning: see https://github.com/urllib3/urllib3/issues/',
|
||||
' warnings.warn(',
|
||||
'https://github.com/urllib3/urllib3/issues/',
|
||||
],
|
||||
[
|
||||
' 1) Client fetches https://api.example.com/v1/',
|
||||
' Failure/Error: expect(res.code).to eq(200)',
|
||||
'https://api.example.com/v1/',
|
||||
],
|
||||
[
|
||||
'Annotations: link.argocd.argoproj.io/external-link: https://grafana.example.com/d/',
|
||||
' prometheus.io/scrape: true',
|
||||
'https://grafana.example.com/d/',
|
||||
],
|
||||
[' BASE_URL=https://api.example.com/', ' API_KEY=your-key-here', 'https://api.example.com/'],
|
||||
[' AUTH_URL=https://auth.example.com/', ' LOG_LEVEL=debug', 'https://auth.example.com/'],
|
||||
[
|
||||
' level=info msg="request" url=https://api.example.com/v1/',
|
||||
' level=info msg="done" status=200',
|
||||
'https://api.example.com/v1/',
|
||||
],
|
||||
[' url=https://api.example.com/v1/', ' request_id=abc-123', 'https://api.example.com/v1/'],
|
||||
[
|
||||
' Callback: https://example.com/oauth/callback/',
|
||||
' state=abc123 must match',
|
||||
'https://example.com/oauth/callback/',
|
||||
],
|
||||
[
|
||||
' Downloading https://huggingface.co/org/model/resolve/main/',
|
||||
' 45%|████▌ | 450M/1.00G [00:10<00:12, 45.0MB/s]',
|
||||
'https://huggingface.co/org/model/resolve/main/',
|
||||
],
|
||||
[' Downloading https://example.com/files/', ' 12.3MB/45.0MB', 'https://example.com/files/'],
|
||||
[' GET https://example.com/api/', ' 12.3ms', 'https://example.com/api/'],
|
||||
[' https://example.com/blog/', ' 10:00:00.123', 'https://example.com/blog/'],
|
||||
];
|
||||
// Continuations at the edge of those rules that are still the rest of the URL:
|
||||
// a wiki title with parens, a file name before a sentence period, a query
|
||||
// parameter after `?`, `&` or `_`, and percent-encoding that starts with digits.
|
||||
const STILL_CONTINUES_ROWS: [string, string, string][] = [
|
||||
[' https://en.wikipedia.org/wiki/', ' Mercury_(planet)', 'https://en.wikipedia.org/wiki/Mercury_(planet)'],
|
||||
['⏺ The guide is at https://example.com/docs/', ' install.html.', 'https://example.com/docs/install.html'],
|
||||
[' https://example.com/oauth?client_', ' id=abc&scope=read', 'https://example.com/oauth?client_id=abc&scope=read'],
|
||||
[' https://example.com/cb?code=abc&', ' state=xyz', 'https://example.com/cb?code=abc&state=xyz'],
|
||||
[' Docs: https://example.com/guide?', ' x=1&y=2 more text', 'https://example.com/guide?x=1&y=2'],
|
||||
[' https://example.com/files/', ' 2026%20Plan.xlsx', 'https://example.com/files/2026%20Plan.xlsx'],
|
||||
];
|
||||
|
||||
describe('findTerminalUrls (grammar)', () => {
|
||||
const { findTerminalUrls } = loadPure();
|
||||
const urls = (text: string) => findTerminalUrls(text).map((u) => u.url);
|
||||
@@ -291,6 +354,20 @@ describe('terminalUrlContinuationExtent (wrap joining)', () => {
|
||||
for (const row of [0, 1]) expect(terminalUrlContinuationExtent(buffer, row, 100, 12)).toBeNull();
|
||||
});
|
||||
|
||||
it.each(FIELD_AND_CODE_ROWS)(
|
||||
'does not join code, a field, a measurement or a sentence end after %s',
|
||||
(first, next) => {
|
||||
const buffer = fakeBuffer([{ text: first }, { text: next }], 100);
|
||||
for (const row of [0, 1]) expect(terminalUrlContinuationExtent(buffer, row, 100, 12)).toBeNull();
|
||||
}
|
||||
);
|
||||
|
||||
it.each(STILL_CONTINUES_ROWS)('still joins the continuation after %s', (first, next) => {
|
||||
const buffer = fakeBuffer([{ text: first }, { text: next }], 100);
|
||||
for (const row of [0, 1])
|
||||
expect(terminalUrlContinuationExtent(buffer, row, 100, 12)).toMatchObject({ startRow: 0, endRow: 1 });
|
||||
});
|
||||
|
||||
it('does not join an indented email address', () => {
|
||||
const buffer = fakeBuffer([{ text: ' https://example.com/' }, { text: ' user@example.com' }], 100);
|
||||
for (const row of [0, 1]) expect(terminalUrlContinuationExtent(buffer, row, 100, 12)).toBeNull();
|
||||
@@ -323,16 +400,13 @@ describe('terminalUrlContinuationExtent (wrap joining)', () => {
|
||||
}
|
||||
);
|
||||
|
||||
it.each(['part%20two', 'x=1&y=2', 'path/slug', 'query?x=1'])(
|
||||
'keeps stronger URL punctuation followed by prose: %s',
|
||||
(token) => {
|
||||
const buffer = fakeBuffer(
|
||||
[{ text: 'Docs: https://example.com/guide/' }, { text: ' ' + token + ' more text' }],
|
||||
100
|
||||
);
|
||||
expect(terminalUrlContinuationExtent(buffer, 0, 100, 12)).toMatchObject({ startRow: 0, endRow: 1 });
|
||||
}
|
||||
);
|
||||
it.each(['part%20two', 'path/slug', 'query?x=1'])('keeps stronger URL punctuation followed by prose: %s', (token) => {
|
||||
const buffer = fakeBuffer(
|
||||
[{ text: 'Docs: https://example.com/guide/' }, { text: ' ' + token + ' more text' }],
|
||||
100
|
||||
);
|
||||
expect(terminalUrlContinuationExtent(buffer, 0, 100, 12)).toMatchObject({ startRow: 0, endRow: 1 });
|
||||
});
|
||||
|
||||
it('does not glue a following prose line onto a URL that ends a line', () => {
|
||||
const buffer = fakeBuffer(
|
||||
@@ -485,6 +559,30 @@ describe('terminal link provider with wrapped table URLs', () => {
|
||||
}
|
||||
);
|
||||
|
||||
it.each(FIELD_AND_CODE_ROWS)(
|
||||
'keeps code, a field, a measurement or a sentence end separate: %s',
|
||||
(first, next, url) => {
|
||||
const { provide, openSpy } = harness([{ text: first }, { text: next }], 100);
|
||||
const links = provide(1).filter((link) => /^https?:/.test(link.text));
|
||||
expect(links.map((link) => link.text)).toEqual([url]);
|
||||
links[0].activate(null, links[0].text);
|
||||
expect(openSpy).toHaveBeenCalledExactlyOnceWith(url, '_blank', 'noopener,noreferrer');
|
||||
expect(provide(2).filter((link) => /^https?:/.test(link.text))).toEqual([]);
|
||||
}
|
||||
);
|
||||
|
||||
it.each(STILL_CONTINUES_ROWS)('links the whole URL from both rows after %s', (first, next, joined) => {
|
||||
const { provide, openSpy } = harness([{ text: first }, { text: next }], 100);
|
||||
for (const line of [1, 2]) {
|
||||
// One link per row the URL covers, each opening the whole URL.
|
||||
const links = provide(line).filter((link) => /^https?:/.test(link.text));
|
||||
expect(new Set(links.map((link) => link.text))).toEqual(new Set([joined]));
|
||||
}
|
||||
const [link] = provide(2).filter((l) => /^https?:/.test(l.text));
|
||||
link.activate(null, link.text);
|
||||
expect(openSpy).toHaveBeenCalledExactlyOnceWith(joined, '_blank', 'noopener,noreferrer');
|
||||
});
|
||||
|
||||
it('keeps an indented email address out of the URL above it', () => {
|
||||
const { provide } = harness([{ text: ' https://example.com/' }, { text: ' user@example.com' }], 100);
|
||||
expect(
|
||||
|
||||
Reference in new issue
Block a user