@d-zero/page-cluster 0.5.7 → 0.6.0

package/dist/cli.js

@@ -6,6 +6,7 @@
 // animated header on a TTY, appended `[page-cluster] …` lines otherwise.
 import { writeFile } from 'node:fs/promises';
 import process from 'node:process';
+import { unwrapSuppressedError } from '@d-zero/cli-core';
 import { Lanes } from '@d-zero/dealer';
 import { resolvePageClusterKeys } from './resolve-page-cluster-keys.js';
 const HELP_TEXT = `Usage:
@@ -298,6 +299,20 @@ function errorLine(message) {
         verbose: `error: ${message}`,
     };
 }
+/**
+ * Formats a caught error for `errorLine()`. `SuppressedError` (thrown when a
+ * `using`-scoped body error and a disposal error occur together) hides the
+ * real cause behind a generic message, so its underlying causes are
+ * unwrapped and joined into one line — `errorLine()`/`renderProgress()` must
+ * still be called exactly once per catch site, since Lanes' TTY repaint only
+ * keeps the latest frame (see {@link errorLine}'s JSDoc).
+ * @param error
+ */
+function formatErrorMessage(error) {
+    return unwrapSuppressedError(error)
+        .map((cause) => (cause instanceof Error ? cause.message : String(cause)))
+        .join(' / ');
+}
 /**
  * Maps a library `ProgressEvent` to a human-facing `ProgressLine`. The
  * verbose arm keeps the historical `pass0:` / `pass1:` / `pass1b:` /
@@ -386,7 +401,10 @@ export async function runCli(options) {
     // pass in) does — reading it defensively lets both real usage and
     // unit-test doubles work without a separate `--no-progress` flag.
     const useTty = options.stderr.isTTY === true;
-    const lanes = new Lanes({ stream: options.stderr, verbose: !useTty });
+    // `using` により、この関数を抜けるすべての経路（下記の各 `return` は
+    // もちろん、想定外の例外を含む）で確実に lanes.close() が呼ばれ、
+    // Display の setTimeout タイマーが解放される。
+    using lanes = new Lanes({ stream: options.stderr, verbose: !useTty });
     // Verbose Lanes prepends `#header` to every `update()` line. Without
     // this seed call the header would be undefined and each progress line
     // would begin with the literal string `undefined ` — bug caught by
@@ -397,86 +415,77 @@ export async function runCli(options) {
     }
     const startTime = Date.now();
     const elapsed = () => Math.max(0, Math.round((Date.now() - startTime) / 1000));
-    // Every early return past this point must run through the finally block
-    // so `lanes.close()` releases the display's setTimeout timer — without
-    // it a `return 1` on a stdin parse error would leave the process
-    // hanging on the timer's next tick.
+    renderProgress(lanes, useTty, READING_INPUT);
+    // Load every JSONL line into memory once so the ids array stays
+    // parallel to the pages array — the streaming driver reads its
+    // factory twice, and stdin is a one-shot pipe.
+    const ids = [];
+    const pages = [];
+    try {
+        for await (const { id, page } of readJsonlPages(options.stdin)) {
+            ids.push(id);
+            pages.push(page);
+        }
+    }
+    catch (error) {
+        renderProgress(lanes, useTty, errorLine(formatErrorMessage(error)));
+        return 1;
+    }
+    renderProgress(lanes, useTty, readingDoneLine(pages.length));
+    // Only worth collecting when the caller asked for the file — a
+    // ClusterReason Map costs bookkeeping proportional to cluster count,
+    // not page count, but there's no reason to pay even that when unused.
+    const reasonsByClusterKey = args.clusterReasonsFile
+        ? new Map()
+        : undefined;
+    // Same opt-in gate as `reasonsByClusterKey` — `onPartitionReport`
+    // itself gates the underlying validation pass (see its own JSDoc).
+    let partitionReport;
+    const resolveOptions = {
+        contentBlockAttribute: args.contentBlockAttribute,
+        onProgress: (event) => {
+            renderProgress(lanes, useTty, formatProgressLine(event, elapsed()));
+        },
+        onClusterReason: reasonsByClusterKey
+            ? (key, reason) => reasonsByClusterKey.set(key, reason)
+            : undefined,
+        onPartitionReport: args.validationFile
+            ? (report) => (partitionReport = report)
+            : undefined,
+    };
+    let clusterKeys;
     try {
-        renderProgress(lanes, useTty, READING_INPUT);
-        // Load every JSONL line into memory once so the ids array stays
-        // parallel to the pages array — the streaming driver reads its
-        // factory twice, and stdin is a one-shot pipe.
-        const ids = [];
-        const pages = [];
+        clusterKeys = await resolvePageClusterKeys(() => pages, resolveOptions);
+    }
+    catch (error) {
+        renderProgress(lanes, useTty, errorLine(formatErrorMessage(error)));
+        return 1;
+    }
+    const clusterCount = new Set(clusterKeys).size;
+    renderProgress(lanes, useTty, doneLine(pages.length, clusterCount, elapsed()));
+    for (const [index, key] of clusterKeys.entries()) {
+        const row = { id: ids[index] ?? index, clusterKey: key };
+        options.stdout.write(`${JSON.stringify(row)}\n`);
+    }
+    if (args.clusterReasonsFile && reasonsByClusterKey) {
         try {
-            for await (const { id, page } of readJsonlPages(options.stdin)) {
-                ids.push(id);
-                pages.push(page);
-            }
+            await writeFile(args.clusterReasonsFile, JSON.stringify(Object.fromEntries(reasonsByClusterKey), null, 2));
         }
         catch (error) {
-            renderProgress(lanes, useTty, errorLine(error.message));
+            renderProgress(lanes, useTty, errorLine(formatErrorMessage(error)));
             return 1;
         }
-        renderProgress(lanes, useTty, readingDoneLine(pages.length));
-        // Only worth collecting when the caller asked for the file — a
-        // ClusterReason Map costs bookkeeping proportional to cluster count,
-        // not page count, but there's no reason to pay even that when unused.
-        const reasonsByClusterKey = args.clusterReasonsFile
-            ? new Map()
-            : undefined;
-        // Same opt-in gate as `reasonsByClusterKey` — `onPartitionReport`
-        // itself gates the underlying validation pass (see its own JSDoc).
-        let partitionReport;
-        const resolveOptions = {
-            contentBlockAttribute: args.contentBlockAttribute,
-            onProgress: (event) => {
-                renderProgress(lanes, useTty, formatProgressLine(event, elapsed()));
-            },
-            onClusterReason: reasonsByClusterKey
-                ? (key, reason) => reasonsByClusterKey.set(key, reason)
-                : undefined,
-            onPartitionReport: args.validationFile
-                ? (report) => (partitionReport = report)
-                : undefined,
-        };
-        let clusterKeys;
+    }
+    if (args.validationFile && partitionReport) {
         try {
-            clusterKeys = await resolvePageClusterKeys(() => pages, resolveOptions);
+            await writeFile(args.validationFile, JSON.stringify(toJsonSafePartitionReport(partitionReport), null, 2));
         }
         catch (error) {
-            renderProgress(lanes, useTty, errorLine(error.message));
+            renderProgress(lanes, useTty, errorLine(formatErrorMessage(error)));
             return 1;
         }
-        const clusterCount = new Set(clusterKeys).size;
-        renderProgress(lanes, useTty, doneLine(pages.length, clusterCount, elapsed()));
-        for (const [index, key] of clusterKeys.entries()) {
-            const row = { id: ids[index] ?? index, clusterKey: key };
-            options.stdout.write(`${JSON.stringify(row)}\n`);
-        }
-        if (args.clusterReasonsFile && reasonsByClusterKey) {
-            try {
-                await writeFile(args.clusterReasonsFile, JSON.stringify(Object.fromEntries(reasonsByClusterKey), null, 2));
-            }
-            catch (error) {
-                renderProgress(lanes, useTty, errorLine(error.message));
-                return 1;
-            }
-        }
-        if (args.validationFile && partitionReport) {
-            try {
-                await writeFile(args.validationFile, JSON.stringify(toJsonSafePartitionReport(partitionReport), null, 2));
-            }
-            catch (error) {
-                renderProgress(lanes, useTty, errorLine(error.message));
-                return 1;
-            }
-        }
-        return 0;
-    }
-    finally {
-        lanes.close();
     }
+    return 0;
 }
 /**
  * Reads the package version out of `package.json` at runtime. Kept as a

package/package.json

@@ -1,12 +1,15 @@
 {
 	"name": "@d-zero/page-cluster",
-	"version": "0.5.7",
+	"version": "0.6.0",
 	"description": "Clusters crawled HTML pages by DOM-structure similarity — assigns the same key to pages sharing a template, ignoring text content. CLI-first, with library APIs.",
 	"author": "D-ZERO",
 	"license": "MIT",
 	"publishConfig": {
 		"access": "public"
 	},
+	"engines": {
+		"node": ">=24.11.0"
+	},
 	"type": "module",
 	"exports": {
 		".": {
@@ -76,8 +79,9 @@
 		"clean": "tsc --build --clean"
 	},
 	"dependencies": {
-		"@d-zero/dealer": "1.10.4",
-		"@d-zero/shared": "0.22.5",
+		"@d-zero/cli-core": "1.4.0",
+		"@d-zero/dealer": "1.11.0",
+		"@d-zero/shared": "0.23.0",
 		"htmlparser2": "12.0.0"
 	},
 	"repository": {
@@ -85,5 +89,5 @@
 		"url": "https://github.com/d-zero-dev/tools.git",
 		"directory": "packages/@d-zero/page-cluster"
 	},
-	"gitHead": "1321d85f63db05896135599046924221f4f714c5"
+	"gitHead": "d48a3ed9c01d32f0ca1a5b00e4abc36c376ce880"
 }