jcoffey-dev
3f4b33cb51
The 143 the codemod refused turned out to be two different things, and only
one of them needed a person.
A third were phrases sitting next to an icon -- `<Plus /> New rule`. The
refusal rule was "has siblings", which is broader than the danger: what breaks
a translation is a sibling that renders *text*, splitting a sentence into
fragments no one can reorder. An element beside a phrase does not. Narrowing
the rule to text-producing siblings let the codemod take 73 more.
The rest were real sentences with values in the middle, rebuilt by hand as
named placeholders -- "Your active script “{name}” was written by hand",
"Waiting on the server — goes out {when}." Named rather than positional
because a translator moves the parts around; counted things go through
plural() so Russian and Ukrainian get their three forms rather than English's
two.
Sentences with an element inside them needed something new. `Open <code>mailto:
</code> links in ihasmail` has two obvious treatments and both are wrong:
splitting it into two t() calls hands over fragments that cannot be reordered,
and dropping the <code> keeps the sentence whole but loses the monospace that
said "this is a literal". tNode() keeps the sentence whole and makes the
element a named hole in it, so a translator sees one sentence and can put the
hole where their language wants it. The German test asserts exactly that: the
same call renders the code first when the catalogue says so.
The coverage number was also lying, and it is worth saying how. It counted
text inside <code> and inside translate="no" as untranslated work, and
placeholders like "123456" and "+1 555 0100" -- a one-time code and a phone
format. None of those will ever be translated, so the report sat at 21 with 6
real items left. A number with an unreachable floor is something to argue with
rather than act on, so the tool now applies the same rules the codemod does.
596 wrapped, nothing remaining. Verified in the browser across 15 views, which
is where the last bulk pass hid a bug the tests could not see: no entities, no
unfilled placeholders, no raw t( in rendered text, and the toggle switches that
looked like emptied labels are text-free by design.
73 lines
3.8 KiB
JavaScript
Executable File
73 lines
3.8 KiB
JavaScript
Executable File
#!/usr/bin/env node
|
|
/*
|
|
* How much of the interface is extracted, and what is left.
|
|
*
|
|
* Extraction is ~1,000 strings across ~56 files, which is far too many to
|
|
* carry in anyone's head or to eyeball in review. This counts what is still
|
|
* hardcoded so the work can be done a file at a time and the remainder is
|
|
* always a number rather than a feeling.
|
|
*
|
|
* It is a progress report, not a gate: run it, do a file, run it again. It
|
|
* exits non-zero only with --check, so CI can be told to fail on regressions
|
|
* later, once the number is low enough for that to mean something.
|
|
*/
|
|
import ts from "typescript";
|
|
import { readFileSync, globSync } from "node:fs";
|
|
|
|
/** Attributes a person reads. `className` and `key` are not among them. */
|
|
const ATTRS = new Set(["title", "aria-label", "placeholder", "alt", "label", "hint", "confirmLabel", "message", "description"]);
|
|
/* Text that is not prose: punctuation, separators, and the single glyphs used
|
|
as dividers. Counting these as untranslated would put a floor under the
|
|
number that no amount of work could reach. */
|
|
const NOT_PROSE = /^[\s·—–\-—:;,.()[\]{}/|+×✓~<>#*@0-9]*$/u;
|
|
/*
|
|
* Text that is deliberately not translated is not "remaining work". Counting
|
|
* it put a floor under the number that no amount of effort could reach -- the
|
|
* report sat at 21 with only 6 real items left, which makes the number
|
|
* something to argue with rather than act on. Same rule the codemod uses.
|
|
*/
|
|
const CODE_TAGS = new Set(["code", "kbd", "pre", "samp", "var"]);
|
|
const optedOut = (node, src) => {
|
|
const opening = ts.isJsxElement(node) ? node.openingElement : ts.isJsxSelfClosingElement(node) ? node : null;
|
|
return Boolean(opening?.attributes.properties.some((a) =>
|
|
ts.isJsxAttribute(a) && a.name.getText(src) === "translate" &&
|
|
a.initializer && ts.isStringLiteral(a.initializer) && a.initializer.text === "no"));
|
|
};
|
|
|
|
const files = globSync("web/src/**/*.tsx").filter((f) => !f.includes("__tests__"));
|
|
const rows = [];
|
|
let done = 0, todo = 0;
|
|
|
|
for (const file of files) {
|
|
const text = readFileSync(file, "utf8");
|
|
const src = ts.createSourceFile(file, text, ts.ScriptTarget.Latest, true, ts.ScriptKind.TSX);
|
|
let left = 0;
|
|
const wrapped = (text.match(/\bt\(\s*["'`]/g) || []).length + (text.match(/\bplural\(/g) || []).length;
|
|
const visit = (node) => {
|
|
if ((ts.isJsxElement(node) && CODE_TAGS.has(node.openingElement.tagName.getText(src).toLowerCase())) || optedOut(node, src)) return;
|
|
if (ts.isJsxText(node) && node.text.trim().length > 1 && !NOT_PROSE.test(node.text.trim())) left++;
|
|
if (ts.isJsxAttribute(node) && ATTRS.has(node.name.getText(src))) {
|
|
const i = node.initializer;
|
|
const lit = i && (ts.isStringLiteral(i) ? i : ts.isJsxExpression(i) && i.expression && ts.isStringLiteral(i.expression) ? i.expression : null);
|
|
// The same prose test the text nodes get. Without it, placeholders that
|
|
// are format examples -- "123456" for a one-time code, "+1 555 0100" for
|
|
// a phone -- counted as untranslated work forever.
|
|
if (lit && lit.text.trim().length > 1 && !NOT_PROSE.test(lit.text.trim())) left++;
|
|
}
|
|
ts.forEachChild(node, visit);
|
|
};
|
|
visit(src);
|
|
done += wrapped;
|
|
todo += left;
|
|
if (left) rows.push([file.replace("web/src/", ""), left, wrapped]);
|
|
}
|
|
|
|
rows.sort((a, b) => b[1] - a[1]);
|
|
const pct = done + todo === 0 ? 100 : Math.round((done / (done + todo)) * 100);
|
|
console.log(`i18n extraction: ${done} wrapped, ${todo} remaining across ${rows.length} files (${pct}%)\n`);
|
|
for (const [f, left, w] of rows.slice(0, Number(process.argv.find((a) => a.startsWith("--top="))?.slice(6) ?? 15))) {
|
|
console.log(` ${String(left).padStart(4)} left${w ? `, ${w} done` : " "} ${f}`);
|
|
}
|
|
if (rows.length > 15 && !process.argv.includes("--all")) console.log(`\n …and ${rows.length - 15} more (--all, or --top=N)`);
|
|
if (process.argv.includes("--check") && todo > 0) process.exit(1);
|