fix(gitmost-bridge): нейтрализовать сплошные thematic breaks в транскрипте
Round-1 нейтрализация ловила только spaced-разделители (`- - -`),
но пропускала сплошные `---`/`***`/`___`: на git-sync round-trip такая
строка становится horizontalRule, а он не несёт текста — строка терялась
целиком (хуже list/quote-порчи). Символ `_` вообще отсутствовал в regexе.
GITMOST_MD_BLOCK_TRIGGER_RE дополнен альтернативой на целую строку-
thematic-break `([-*_])(?:\s*\1){2,}\s*$` (3+ одинаковых `-`/`*`/`_`,
solid или через пробел); прежние группы переведены в non-capturing,
чтобы `\1` ссылался на единственную capture-группу. Обе копии regexа
(bridge и pm-markdown тест) синхронны.
Тесты: bare `---`/`***`/`___` документированы как text-losing
horizontalRule; ZWSP-нейтрализованная форма round-trip'ится параграфом
с сохранённым текстом. Кейсы падают на старом regexе.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -103,6 +103,9 @@ describe("gitmostInsertTranscriptIntoEditor", () => {
|
||||
"1. one",
|
||||
"> [!info] note",
|
||||
"```js",
|
||||
"---", // solid thematic break -> horizontalRule (text-losing) if unneutralized
|
||||
"***",
|
||||
"___",
|
||||
"You: normal line",
|
||||
].join("\n"),
|
||||
);
|
||||
@@ -122,6 +125,9 @@ describe("gitmostInsertTranscriptIntoEditor", () => {
|
||||
ZWSP + "1. one",
|
||||
ZWSP + "> [!info] note",
|
||||
ZWSP + "```js",
|
||||
ZWSP + "---",
|
||||
ZWSP + "***",
|
||||
ZWSP + "___",
|
||||
"You: normal line",
|
||||
]);
|
||||
|
||||
|
||||
@@ -253,11 +253,15 @@ const GITMOST_ZWSP = "";
|
||||
// verbatim with NO block-escape (the pre-existing root cause), so a leading
|
||||
// `#`/`-`/`*`/`+`/`>`, an ordered-list `N.`/`N)`, a code fence ```/~~~, a table
|
||||
// `|`, or a `> [!info]` callout opener would silently become a heading / list /
|
||||
// quote / code block / table / callout. This matches a TRIMMED line's start;
|
||||
// the transcript's own `You:` / `Speaker N:` prefix begins with a letter and
|
||||
// never matches, so prefixed lines are left byte-exact.
|
||||
// quote / code block / table / callout. The final alternative matches a WHOLE-
|
||||
// LINE thematic break — solid `---`/`***`/`___` or spaced `- - -`/`_ _ _` (3+ of
|
||||
// the same `-`/`*`/`_`) — which round-trips into a `horizontalRule`; because
|
||||
// that node carries NO text, an un-neutralized separator line would LOSE its
|
||||
// text entirely (worse than the list/quote case). This matches a TRIMMED line's
|
||||
// start; the transcript's own `You:` / `Speaker N:` prefix begins with a letter
|
||||
// and never matches, so prefixed lines are left byte-exact.
|
||||
const GITMOST_MD_BLOCK_TRIGGER_RE =
|
||||
/^(#{1,6}(\s|$)|[-*+](\s|$)|>|\d+[.)](\s|$)|```|~~~|\|)/;
|
||||
/^(?:#{1,6}(?:\s|$)|[-*+](?:\s|$)|>|\d+[.)](?:\s|$)|```|~~~|\||([-*_])(?:\s*\1){2,}\s*$)/;
|
||||
|
||||
// Append a transcript block BELOW the recording's audio node in a live editor:
|
||||
// a "Transcript" heading followed by one paragraph per non-empty transcript
|
||||
|
||||
@@ -29,7 +29,7 @@ const ZWSP = ""; // U+200B
|
||||
|
||||
// MUST stay in sync with GITMOST_MD_BLOCK_TRIGGER_RE in the client bridge.
|
||||
const MD_BLOCK_TRIGGER_RE =
|
||||
/^(#{1,6}(\s|$)|[-*+](\s|$)|>|\d+[.)](\s|$)|```|~~~|\|)/;
|
||||
/^(?:#{1,6}(?:\s|$)|[-*+](?:\s|$)|>|\d+[.)](?:\s|$)|```|~~~|\||([-*_])(?:\s*\1){2,}\s*$)/;
|
||||
|
||||
const doc = (...nodes: any[]) => ({ type: "doc", content: nodes });
|
||||
const para = (t: string) => ({
|
||||
@@ -57,6 +57,14 @@ describe("gitmost transcript neutralization (git-sync round-trip)", () => {
|
||||
"> [!info] note",
|
||||
"```js",
|
||||
"~~~",
|
||||
// Solid + spaced thematic breaks — these re-parse into a `horizontalRule`,
|
||||
// which carries NO text, so a bare separator line LOSES its text entirely
|
||||
// (round-2 finding). `_` also only forms a block via this construct.
|
||||
"---",
|
||||
"***",
|
||||
"___",
|
||||
"- - -", // spaced dash break (solid form is caught by [-*+]\s too, but this is the break)
|
||||
"_ _ _",
|
||||
];
|
||||
|
||||
it("BARE trigger lines corrupt into non-paragraph blocks (root cause)", async () => {
|
||||
@@ -71,6 +79,18 @@ describe("gitmost transcript neutralization (git-sync round-trip)", () => {
|
||||
}
|
||||
});
|
||||
|
||||
it("BARE solid thematic breaks corrupt into a text-LOSING horizontalRule", async () => {
|
||||
// The severe case: no text node survives. Documents why neutralization
|
||||
// matters more here than for list/quote (where the text survived).
|
||||
for (const line of ["---", "***", "___"]) {
|
||||
const blocks = await roundtrip(line);
|
||||
expect(blocks.map((b) => b.type)).toContain("horizontalRule");
|
||||
// No block carries the original text anywhere.
|
||||
const flat = JSON.stringify(blocks);
|
||||
expect(flat).not.toContain(line);
|
||||
}
|
||||
});
|
||||
|
||||
it("ZWSP-neutralized trigger lines round-trip as a single paragraph, text preserved", async () => {
|
||||
for (const line of triggerLines) {
|
||||
// The regex must actually classify each as a trigger.
|
||||
|
||||
Reference in New Issue
Block a user