Add report rebuild mode and improve histogram buckets

tests/test_analysis.py

@@ -121,6 +121,30 @@ def test_build_summary_uses_adaptive_buckets_for_compact_ranges() -> None:
     ]
 
 
+def test_build_summary_uses_finer_buckets_for_large_sample_sets_with_outliers() -> None:
+    records = [
+        _build_record(
+            f"clip-{index}.mp4",
+            size_mb=80 + (index % 8) * 60,
+            duration_seconds=300 + (index % 9) * 300,
+        )
+        for index in range(1_499)
+    ]
+    records.append(
+        _build_record(
+            "feature-film.mkv",
+            size_mb=6 * 1024,
+            duration_seconds=6 * 3600,
+            codec="hevc",
+        )
+    )
+
+    summary = build_summary(records)
+
+    assert summary.duration_histogram[0].label == "0-15 min"
+    assert summary.size_histogram[0].label == "0-500 MB"
+
+
 def test_build_summary_tracks_successful_and_failed_files() -> None:
     records = [
         VideoMetadata(

tests/test_cli.py

@@ -166,3 +166,65 @@ def test_main_reports_scan_progress_to_stderr(tmp_path: Path, capsys) -> None:
     assert "已发现 2 个视频文件" in captured.err
     assert "2/2" in captured.err
     assert "02-second.mp4" in captured.err
+
+
+def test_main_rebuilds_html_from_existing_report_json_without_running_probe(tmp_path: Path) -> None:
+    output_dir = tmp_path / "report"
+    output_dir.mkdir()
+    report_json = output_dir / "report.json"
+    report_json.write_text(
+        json.dumps(
+            {
+                "generated_at": "2026-04-02T12:00:00",
+                "scanned_inputs": ["videos"],
+                "tool_versions": {"ffprobe": "cached ffprobe", "ffmpeg": "cached ffmpeg"},
+                "summary": {
+                    "total_files": 500,
+                    "successful_files": 500,
+                    "failed_files": 0,
+                    "total_size_bytes": 0,
+                    "total_duration_seconds": 0,
+                    "duration_histogram": [{"label": "0-1 h", "count": 500}],
+                    "size_histogram": [{"label": "0-1 GB", "count": 500}],
+                    "video_codecs": [],
+                    "resolutions": [],
+                },
+                "files": [
+                    {
+                        "path": "videos/sample.mp4",
+                        "size_bytes": 60 * 1024 * 1024,
+                        "duration_seconds": 120.0,
+                        "format_name": "mov,mp4,m4a,3gp,3g2,mj2",
+                        "bit_rate": 1024000,
+                        "video_codec": "h264",
+                        "audio_codec": "aac",
+                        "width": 1280,
+                        "height": 720,
+                        "frame_rate": 25.0,
+                        "video_stream_count": 1,
+                        "audio_stream_count": 1,
+                        "subtitle_stream_count": 0,
+                    }
+                ],
+                "failures": [],
+            },
+            ensure_ascii=False,
+            indent=2,
+        ),
+        encoding="utf-8",
+    )
+
+    def forbidden_runner(command: list[str]) -> str:
+        raise AssertionError(f"should not invoke external command: {command}")
+
+    exit_code = main(
+        ["--report-json", str(report_json)],
+        command_runner=forbidden_runner,
+    )
+
+    assert exit_code == 0
+    payload = json.loads(report_json.read_text(encoding="utf-8"))
+    html_text = (output_dir / "report.html").read_text(encoding="utf-8")
+    assert payload["summary"]["duration_histogram"] == [{"label": "0-2 min", "count": 1}]
+    assert payload["summary"]["size_histogram"] == [{"label": "0-100 MB", "count": 1}]
+    assert "0-2 min" in html_text

tests/test_report.py

@@ -5,7 +5,7 @@ from pathlib import Path
 
 from video_metadata_analyzer.analysis import build_summary
 from video_metadata_analyzer.models import ProbeFailure, VideoMetadata
-from video_metadata_analyzer.reporting import write_report_bundle
+from video_metadata_analyzer.reporting import rebuild_report_bundle_from_json, write_report_bundle
 
 
 def test_write_report_bundle_creates_json_csv_and_html(tmp_path: Path) -> None:
@@ -70,3 +70,64 @@ def test_write_report_bundle_creates_json_csv_and_html(tmp_path: Path) -> None:
     assert "grid-template-columns: repeat(auto-fit, minmax(520px, 1fr));" in html_text
     assert "font-size: 16px;" in html_text
     assert "font-size: 18px;" in html_text
+
+
+def test_rebuild_report_bundle_from_json_recomputes_summary_and_html(tmp_path: Path) -> None:
+    report_dir = tmp_path / "report"
+    report_dir.mkdir()
+    report_json = report_dir / "report.json"
+    payload = {
+        "generated_at": "2026-04-02T12:00:00",
+        "scanned_inputs": ["videos"],
+        "tool_versions": {"ffprobe": "ffprobe version x", "ffmpeg": "ffmpeg version y"},
+        "summary": {
+            "total_files": 999,
+            "successful_files": 999,
+            "failed_files": 0,
+            "total_size_bytes": 0,
+            "total_duration_seconds": 0,
+            "duration_histogram": [{"label": "0-1 h", "count": 999}],
+            "size_histogram": [{"label": "0-1 GB", "count": 999}],
+            "video_codecs": [],
+            "resolutions": [],
+        },
+        "files": [
+            {
+                "path": "videos/a.mp4",
+                "size_bytes": 60 * 1024 * 1024,
+                "duration_seconds": 120.0,
+                "format_name": "mov,mp4,m4a,3gp,3g2,mj2",
+                "bit_rate": 1500000,
+                "video_codec": "h264",
+                "audio_codec": "aac",
+                "width": 1920,
+                "height": 1080,
+                "frame_rate": 30.0,
+                "video_stream_count": 1,
+                "audio_stream_count": 1,
+                "subtitle_stream_count": 0,
+            }
+        ],
+        "failures": [
+            {
+                "path": "videos/broken.mp4",
+                "error_type": "CalledProcessError",
+                "error_message": "moov atom not found",
+            }
+        ],
+    }
+    report_json.write_text(json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8")
+
+    paths = rebuild_report_bundle_from_json(report_json)
+
+    rebuilt_payload = json.loads(paths["json"].read_text(encoding="utf-8"))
+    rebuilt_html = paths["html"].read_text(encoding="utf-8")
+
+    assert rebuilt_payload["summary"]["total_files"] == 2
+    assert rebuilt_payload["summary"]["successful_files"] == 1
+    assert rebuilt_payload["summary"]["failed_files"] == 1
+    assert rebuilt_payload["summary"]["duration_histogram"] == [{"label": "0-2 min", "count": 1}]
+    assert rebuilt_payload["summary"]["size_histogram"] == [{"label": "0-100 MB", "count": 1}]
+    assert "视频元数据分析报告" in rebuilt_html
+    assert "0-2 min" in rebuilt_html
+    assert "0-1 h" not in rebuilt_html