@trawlme/cli 3.8.0 → 3.8.1

package/dist/commands/scraps.js

@@ -47,6 +47,58 @@ function tryValidateUrl(value, opts) {
         throw err;
     }
 }
+/**
+ * One-line rendering of an emptyContext blob for the run-info table. Two
+ * buckets are actionable and must stay distinct: selectors that matched zero
+ * nodes (the page changed) and selectors the browser rejected outright
+ * (`-1`, a bug in the scrap script). Folding the second into "all matched"
+ * would report a broken selector as healthy. `--json` still emits the full
+ * object, `page.topClasses` / `topAnchorPaths` included.
+ */
+function summarizeEmptyContext(ctx) {
+    if (!ctx || typeof ctx !== 'object')
+        return null;
+    const parts = [];
+    const selectors = ctx.selectors && typeof ctx.selectors === 'object' ? ctx.selectors : {};
+    const names = Object.keys(selectors);
+    // Selectors may themselves contain a comma (`div, span`), so quote each one
+    // — a raw join renders one grouping selector as if it were two.
+    const list = (ns) => `${ns.slice(0, 3).map((s) => `\`${s}\``).join(', ')}${ns.length > 3 ? ` (+${ns.length - 3})` : ''}`;
+    // Four disjoint, exhaustive buckets — every selector lands in exactly one, so
+    // no count is ever dropped and none is summarised as something it is not.
+    // `selectors` comes from a Mongoose Mixed field, so a count may be `null` or
+    // a string: that is `unreadable`, which is neither healthy nor zero-match and
+    // must be named as its own thing next to the others, not collapsed into them.
+    const isCount = (v) => typeof v === 'number' && Number.isFinite(v);
+    const zero = names.filter((s) => selectors[s] === 0);
+    const invalid = names.filter((s) => selectors[s] === -1);
+    const matched = names.filter((s) => isCount(selectors[s]) && selectors[s] > 0);
+    const unreadable = names.filter((s) => !zero.includes(s) && !invalid.includes(s) && !matched.includes(s));
+    const mixed = zero.length > 0 || invalid.length > 0 || unreadable.length > 0;
+    if (zero.length)
+        parts.push(`0-match: ${list(zero)}`);
+    if (invalid.length)
+        parts.push(`invalid: ${list(invalid)}`);
+    if (unreadable.length)
+        parts.push(`unreadable: ${list(unreadable)}`);
+    if (matched.length) {
+        // Named even in a mixed set: "3 of the selectors still work" is the
+        // difference between a page that moved and a page that vanished.
+        parts.push(mixed ? `${matched.length} matched` : `${matched.length} selector(s), all matched`);
+    }
+    // Same Mixed-field caution on the title: coerce before calling a string
+    // method (a numeric title would otherwise crash `run-info` on the very run
+    // it exists to explain), and test against null/undefined rather than
+    // truthiness so a falsy-but-real title like `0` still shows. Inner double
+    // quotes would close the wrapper early and corrupt the line.
+    const title = ctx.page?.title;
+    if (title !== undefined && title !== null && String(title) !== '') {
+        parts.push(`title="${String(title).replace(/"/g, "'")}"`);
+    }
+    if (typeof ctx.page?.totalAnchors === 'number')
+        parts.push(`${ctx.page.totalAnchors} anchors`);
+    return parts.length ? parts.join(' | ') : null;
+}
 function lastStatus(scrap) {
     const last = scrap.history?.[0];
     if (!last)
@@ -1118,14 +1170,15 @@ export function attachRunInfoCommand(parent, attachOpts = {}) {
             blockType: h.blockType ?? null,
             errorMessage: h.errorSnapshot?.errorMessage ?? null,
             selector: h.errorSnapshot?.selector ?? null,
-            emptyContext: h.errorSnapshot?.emptyContext ?? null,
+            emptyContext: h.emptyContext ?? null,
             createdAt: h.createdAt ?? null,
         };
         if (opts.json) {
             json(info);
             return;
         }
-        table([info], ['hid', 'status', 'time', 'tier', 'failureKind', 'blockType', 'errorMessage', 'selector', 'emptyContext', 'createdAt']);
+        // The blob is an object; the table needs one line. --json keeps it whole.
+        table([{ ...info, emptyContext: summarizeEmptyContext(info.emptyContext) }], ['hid', 'status', 'time', 'tier', 'failureKind', 'blockType', 'errorMessage', 'selector', 'emptyContext', 'createdAt']);
     });
 }
 attachRunInfoCommand(scraps, { hidden: true });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trawlme/cli",
-  "version": "3.8.0",
+  "version": "3.8.1",
   "description": "Trawl CLI — manage scraps from the terminal",
   "type": "module",
   "bin": {