feat: filter GF3 production by scene date

backend/app/routers/monitor.py

@@ -74,6 +74,7 @@ class GF3SarscapeSyncRequest(BaseModel):
 
 class GF3SarscapeProduceRequest(BaseModel):
     max_archives_per_run: Optional[int] = Field(default=None, ge=0)
+    selected_dates: List[str] = []
     auto_standardize: Optional[bool] = None
     clean_after_success: Optional[bool] = None
     force_standardize: bool = False
@@ -250,6 +251,16 @@ async def run_gf3_sarscape_produce(
         raise HTTPException(status_code=400, detail="GF3_SARSCAPE_DEM_PATH or GF3_GEO_DEM_PATH is not configured.")
 
     options = request_data or GF3SarscapeProduceRequest()
+    selected_dates = []
+    for raw_date in options.selected_dates or []:
+        text = str(raw_date or "").strip()
+        if not text:
+            continue
+        normalized = text.replace("-", "").replace("_", "")
+        if len(normalized) != 8 or not normalized.isdigit():
+            raise HTTPException(status_code=400, detail=f"Invalid GF3 scene date: {raw_date}")
+        if normalized not in selected_dates:
+            selected_dates.append(normalized)
     task_type = "GF3_SARSCAPE_PRODUCE"
     task_name = "GF3 SARscape production"
     auto_standardize = settings.GF3_SARSCAPE_AUTO_STANDARDIZE if options.auto_standardize is None else bool(options.auto_standardize)
@@ -265,6 +276,7 @@ async def run_gf3_sarscape_produce(
         "polarizations": settings.GF3_SARSCAPE_POLARIZATIONS,
         "archive_exts": split_env_paths(settings.GF3_ARCHIVE_EXTS),
         "max_archives_per_run": int(options.max_archives_per_run or 0),
+        "selected_dates": selected_dates,
         "timeout_seconds": int(settings.GF3_SARSCAPE_PRODUCE_TIMEOUT_SECONDS or 0),
         "keep_extracted": bool(settings.GF3_SARSCAPE_KEEP_EXTRACTED),
         "auto_standardize": bool(auto_standardize),
@@ -279,13 +291,55 @@ async def run_gf3_sarscape_produce(
         task_id = await task_service.create_task(task_type, task_name, params=payload)
         await job_queue_service.create_job(task_type, payload=payload, task_id=task_id)
         return {
-            "message": "GF3 SARscape production task submitted",
+            "message": (
+                f"GF3 SARscape production task submitted for {', '.join(selected_dates)}"
+                if selected_dates
+                else "GF3 SARscape production task submitted"
+            ),
             "task_id": task_id,
         }
     except ValueError as e:
         raise HTTPException(status_code=409, detail=str(e))
 
 
+@router.get("/monitor/gf3-sarscape-dates")
+async def list_gf3_sarscape_dates(admin_user: AuthUserORM = Depends(_require_admin)):
+    """
+    List available GF3 SARscape source dates from configured raw archive roots.
+    """
+    from ..services.gf3_sarscape_production_service import discover_gf3_sarscape_inputs
+
+    gf3_archive_source_dirs = MONITOR_CONFIG.get("gf3_archive_source_dirs") or []
+    if not gf3_archive_source_dirs:
+        raise HTTPException(status_code=400, detail="GF3_ARCHIVE_SOURCE_DIRS is not configured.")
+
+    discovery = discover_gf3_sarscape_inputs(
+        gf3_archive_source_dirs,
+        archive_exts=split_env_paths(settings.GF3_ARCHIVE_EXTS),
+    )
+    by_date: dict[str, dict[str, object]] = {}
+    undated = 0
+    for item in discovery.get("inputs") or []:
+        scene_name = str(item.get("scene_name") or "")
+        date_text = str(item.get("scene_date") or "")
+        if not date_text:
+            undated += 1
+            continue
+        bucket = by_date.setdefault(date_text, {"date": date_text, "scene_count": 0, "scenes": []})
+        bucket["scene_count"] = int(bucket.get("scene_count") or 0) + 1
+        scenes = bucket.get("scenes")
+        if isinstance(scenes, list) and len(scenes) < 20:
+            scenes.append(scene_name)
+
+    dates = sorted(by_date.values(), key=lambda item: str(item.get("date") or ""), reverse=True)
+    return {
+        "dates": dates,
+        "input_count": discovery.get("input_count") or 0,
+        "undated_count": undated,
+        "missing_roots": discovery.get("missing_roots") or [],
+    }
+
+
 @router.post("/monitor/gf3-sarscape-clean", status_code=202)
 async def run_gf3_sarscape_clean(
     request_data: GF3SarscapeCleanRequest | None = None,

backend/app/services/gf3_sarscape_production_service.py

@@ -85,6 +85,30 @@ def _safe_slug(value: Any, *, default: str = "unknown") -> str:
     return safe or default
 
 
+def _date_from_scene_name(scene_name: str) -> str | None:
+    match = re.search(r"(20\d{6})", str(scene_name or ""))
+    return match.group(1) if match else None
+
+
+def _normalize_scene_date(value: Any) -> str | None:
+    text = _clean_text(value)
+    if not text:
+        return None
+    match = re.search(r"(20\d{2})[-_]?(\d{2})[-_]?(\d{2})", text)
+    if not match:
+        return None
+    return "".join(match.groups())
+
+
+def _normalize_scene_dates(values: list[str] | tuple[str, ...] | None) -> set[str]:
+    dates: set[str] = set()
+    for value in values or []:
+        normalized = _normalize_scene_date(value)
+        if normalized:
+            dates.add(normalized)
+    return dates
+
+
 def _resolve_existing_dirs(values: list[str] | tuple[str, ...] | None) -> tuple[list[Path], list[str]]:
     roots: list[Path] = []
     missing: list[str] = []
@@ -223,6 +247,7 @@ def discover_gf3_sarscape_inputs(
                 {
                     "path": str(resolved),
                     "scene_name": _scene_name_from_input(path),
+                    "scene_date": _date_from_scene_name(_scene_name_from_input(path)),
                     "ext": ext,
                     "source_root": str(root),
                 }
@@ -268,6 +293,36 @@ def _scene_complete(scene_dir: Path, polarizations: list[str]) -> bool:
     return all(_completed_geo_product(scene_dir, pol) is not None for pol in polarizations)
 
 
+def _standardized_scene_complete(storage_root: Path | None, scene_name: str, polarizations: list[str]) -> tuple[bool, Path | None, str]:
+    if storage_root is None:
+        return False, None, "storage_root_not_configured"
+    date_text = _date_from_scene_name(scene_name)
+    candidate_dirs = []
+    if date_text:
+        candidate_dirs.append(storage_root / _safe_slug(date_text) / _safe_slug(scene_name))
+    candidate_dirs.append(storage_root / "unknown_batch" / _safe_slug(scene_name))
+
+    for scene_dir in candidate_dirs:
+        manifest_path = scene_dir / STANDARD_MANIFEST_NAME
+        manifest = _read_json(manifest_path)
+        if manifest and str(manifest.get("status") or "").upper() in {"DONE", "PARTIAL"}:
+            assets = manifest.get("assets") or []
+            complete_pols = {
+                str(asset.get("polarization") or "").upper()
+                for asset in assets
+                if str(asset.get("status") or "").lower() in {"converted", "skipped"}
+                and _is_nonempty_file(Path(str(asset.get("path") or "")))
+            }
+            if all(str(pol or "").upper() in complete_pols for pol in polarizations):
+                return True, scene_dir, "standard_manifest_complete"
+
+        if scene_dir.is_dir():
+            if all(_is_nonempty_file(scene_dir / f"{str(pol).upper()}_L2.tif") for pol in polarizations):
+                return True, scene_dir, "standard_tifs_complete"
+
+    return False, None, "standardized_result_missing"
+
+
 def _missing_geo_polarizations(scene_dir: Path, polarizations: list[str]) -> list[str]:
     if not scene_dir.is_dir():
         return list(polarizations)
@@ -396,6 +451,7 @@ def run_gf3_sarscape_production(
     polarizations: str | None = None,
     archive_exts: list[str] | None = None,
     max_archives_per_run: int | None = None,
+    selected_dates: list[str] | None = None,
     timeout_seconds: int | None = None,
     keep_extracted: bool | None = None,
     log_callback: LogCallback | None = None,
@@ -420,15 +476,26 @@ def run_gf3_sarscape_production(
     ext_config = archive_exts if archive_exts is not None else split_env_paths(settings.GF3_ARCHIVE_EXTS)
     discovery = discover_gf3_sarscape_inputs(source_dirs, archive_exts=ext_config)
     inputs = discovery.get("inputs") or []
+    selected_date_set = _normalize_scene_dates(selected_dates)
+    if selected_date_set:
+        inputs = [
+            item
+            for item in inputs
+            if _normalize_scene_date(item.get("scene_date") or item.get("scene_name")) in selected_date_set
+        ]
     max_to_process = int(max_archives_per_run or 0)
     timeout = int(timeout_seconds or 0)
     keep = bool(settings.GF3_SARSCAPE_KEEP_EXTRACTED if keep_extracted is None else keep_extracted)
+    storage_root = Path(os.path.normpath(settings.GF3_STORAGE_DIRS)).resolve() if settings.GF3_STORAGE_DIRS else None
 
     _emit_log(log_callback, "INFO", f"GF3 SARscape source roots: {source_dirs}")
     _emit_log(log_callback, "INFO", f"GF3 SARscape native root: {native_root_path}")
+    _emit_log(log_callback, "INFO", f"GF3 SARscape standardized root: {storage_root or '(not configured)'}")
     _emit_log(log_callback, "INFO", f"GF3 SARscape wrapper: {wrapper_path}")
     _emit_log(log_callback, "INFO", f"GF3 SARscape DEM: {dem}")
     _emit_log(log_callback, "INFO", f"GF3 SARscape polarizations: {pol_text}")
+    if selected_date_set:
+        _emit_log(log_callback, "INFO", f"GF3 SARscape selected dates: {', '.join(sorted(selected_date_set))}")
 
     if not inputs:
         _emit_progress(progress_callback, 100, "GF3 SARscape production found no supported inputs.")
@@ -440,6 +507,7 @@ def run_gf3_sarscape_production(
             "failed_count": 0,
             "deferred_count": 0,
             "missing_roots": discovery.get("missing_roots") or [],
+            "selected_dates": sorted(selected_date_set),
             "results": [],
         }
 
@@ -469,6 +537,26 @@ def run_gf3_sarscape_production(
         progress = 5 + int((idx / max(total, 1)) * 60)
         _emit_progress(progress_callback, progress, f"GF3 SARscape checking {idx + 1}/{total}: {scene_name}")
 
+        standardized_complete, standardized_dir, standardized_reason = _standardized_scene_complete(storage_root, scene_name, pols)
+        if standardized_complete:
+            skipped += 1
+            _emit_log(
+                log_callback,
+                "INFO",
+                f"GF3 SARscape skipping {scene_name}: standardized result already exists ({standardized_reason})",
+            )
+            results.append(
+                {
+                    "scene_name": scene_name,
+                    "input_path": str(input_path),
+                    "scene_dir": str(scene_dir),
+                    "standardized_dir": str(standardized_dir) if standardized_dir else None,
+                    "status": "skipped_standardized_complete",
+                    "skip_reason": standardized_reason,
+                }
+            )
+            continue
+
         if _scene_complete(scene_dir, pols):
             skipped += 1
             results.append(
@@ -585,6 +673,7 @@ def run_gf3_sarscape_production(
         "deferred_count": deferred,
         "native_root": str(native_root_path),
         "missing_roots": discovery.get("missing_roots") or [],
+        "selected_dates": sorted(selected_date_set),
         "results": results,
     }
 

backend/app/services/job_handlers.py

@@ -4051,6 +4051,7 @@ async def _handle_gf3_sarscape_produce(job: SystemJobORM) -> None:
                 polarizations=payload.get("polarizations"),
                 archive_exts=payload.get("archive_exts") or [],
                 max_archives_per_run=payload.get("max_archives_per_run"),
+                selected_dates=payload.get("selected_dates") or [],
                 timeout_seconds=payload.get("timeout_seconds"),
                 keep_extracted=payload.get("keep_extracted"),
                 log_callback=_log_cb,

docs/GF3_SARSCAPE_NATIVE_TO_GEOTIFF_DESIGN_20260530.md

@@ -479,3 +479,23 @@ GF3_SARSCAPE_PRODUCE_TIMEOUT_SECONDS=0
 - 不删除 `GF3_ARCHIVE_SOURCE_DIRS` 中的原始压缩包，也不删除 `GF3_STORAGE_DIRS` 中的标准 GeoTIFF。
 
 这样 `D:\production_results\gf3\sarscape_native` 只长期保存可追溯的最终 `_geo` 原生结果组，中间过程文件在标准化完成后自动释放空间；wrapper 配置和临时运行文件放在 `D:\production_runtime\gf3\sarscape_runtime`。
+
+## 2026-06-15 Production Preflight Rule
+
+GF3 SARscape production must check existing results before invoking the external wrapper.
+
+Skip production when either condition is true:
+
+- SARscape native output is already complete in `GF3_SARSCAPE_NATIVE_DIRS` for every requested polarization.
+- Standardized L2 output already exists in `GF3_STORAGE_DIRS/<imaging_date>/<scene_name>` with `gf3_standard_manifest.json` status `DONE`/`PARTIAL` and every requested polarization has a valid `*_L2.tif`.
+
+This prevents reprocessing when native intermediates were cleaned but registered/standardized results still exist. The standardized L2 and registered assets are the durable result layer; source archives on UNC should not be reprocessed unless the operator explicitly removes or invalidates the existing result.
+
+## 2026-06-15 Date-Scoped Production
+
+GF3 SARscape production now supports an optional scene-date filter.
+
+- `GET /api/monitor/gf3-sarscape-dates` scans `GF3_ARCHIVE_SOURCE_DIRS`, groups wrapper-supported raw archives by the `YYYYMMDD` date embedded in the GF3 scene name, and returns scene counts per date.
+- `POST /api/monitor/gf3-sarscape-produce` accepts `selected_dates: ["YYYYMMDD"]`. When omitted or empty, production keeps the previous all-date behavior.
+- The frontend monitor panel exposes a date selector in the GF3 SARscape production section. Operators can select one image date before starting production, or leave it as all dates.
+- The existing duplicate-result preflight still runs after date filtering. A selected date will not reprocess scenes whose standardized L2 result or complete native `_geo` outputs already exist.

frontend/src/DataMonitorPanel.jsx

@@ -37,6 +37,14 @@ const DEFAULT_UNPACK_CONFIG = {
 
 const toArray = (value) => (Array.isArray(value) ? value : []);
 
+const formatGf3Date = (value) => {
+  const text = String(value || '').replace(/\D/g, '');
+  if (text.length !== 8) {
+    return value || '';
+  }
+  return `${text.slice(0, 4)}-${text.slice(4, 6)}-${text.slice(6, 8)}`;
+};
+
 const createUnpackRunOptions = (config = DEFAULT_UNPACK_CONFIG) => ({
   max_files_per_run: String(config?.max_files_per_run ?? 0),
   max_runtime_minutes: String(config?.max_runtime_minutes ?? 0),
@@ -81,6 +89,9 @@ const DataMonitorPanel = ({ apiEndpoint, onTaskStart, readOnly = false, enabled
   const [gf3SarscapeSyncLoading, setGf3SarscapeSyncLoading] = useState(false);
   const [gf3SarscapeCleanLoading, setGf3SarscapeCleanLoading] = useState(false);
   const [gf3ScanLoading, setGf3ScanLoading] = useState(false);
+  const [gf3DateLoading, setGf3DateLoading] = useState(false);
+  const [gf3SarscapeDates, setGf3SarscapeDates] = useState([]);
+  const [gf3SelectedDate, setGf3SelectedDate] = useState('');
   const [gf3Message, setGf3Message] = useState('');
   const logEndRef = useRef(null);
 
@@ -321,6 +332,49 @@ const DataMonitorPanel = ({ apiEndpoint, onTaskStart, readOnly = false, enabled
   const canRunGf3SarscapeClean = !readOnly && configLoaded && hasGf3SarscapeNativeDirs && hasGf3StorageDirs;
   const canOpenUnpackDialog = !readOnly && unpackConfig.source_dirs.length > 0;
 
+  useEffect(() => {
+    if (!enabled || !configLoaded || !hasGf3ArchiveSourceDirs) {
+      setGf3SarscapeDates([]);
+      setGf3SelectedDate('');
+      return;
+    }
+
+    let canceled = false;
+    const fetchGf3Dates = async () => {
+      setGf3DateLoading(true);
+      try {
+        const res = await fetch(`${apiEndpoint}/monitor/gf3-sarscape-dates`, { credentials: 'include' });
+        const data = await parseJsonSafe(res, {});
+        if (canceled) {
+          return;
+        }
+        if (!res.ok) {
+          throw new Error(data?.detail || `HTTP ${res.status}`);
+        }
+        const nextDates = toArray(data?.dates);
+        setGf3SarscapeDates(nextDates);
+        setGf3SelectedDate((prev) => (
+          prev && nextDates.some((item) => String(item?.date || '') === prev) ? prev : ''
+        ));
+      } catch (err) {
+        if (!canceled) {
+          console.error('Failed to fetch GF3 SARscape dates:', err);
+          setGf3SarscapeDates([]);
+        }
+      } finally {
+        if (!canceled) {
+          setGf3DateLoading(false);
+        }
+      }
+    };
+
+    fetchGf3Dates();
+
+    return () => {
+      canceled = true;
+    };
+  }, [apiEndpoint, enabled, configLoaded, hasGf3ArchiveSourceDirs]);
+
   const handleS1Run = async () => {
     if (readOnly) {
       setS1Message('当前账户为只读模式，无法触发 Sentinel-1 任务。');
@@ -480,13 +534,14 @@ const DataMonitorPanel = ({ apiEndpoint, onTaskStart, readOnly = false, enabled
     setGf3SarscapeProduceLoading(true);
     setGf3Message('GF3 SARscape 生产链路启动中...');
     try {
+      const payload = gf3SelectedDate ? { selected_dates: [gf3SelectedDate] } : {};
       const res = await fetch(`${apiEndpoint}/monitor/gf3-sarscape-produce`, {
         method: 'POST',
         credentials: 'include',
         headers: {
           'Content-Type': 'application/json',
         },
-        body: JSON.stringify({}),
+        body: JSON.stringify(payload),
       });
       const data = await parseJsonSafe(res, {});
       if (res.ok) {
@@ -507,6 +562,32 @@ const DataMonitorPanel = ({ apiEndpoint, onTaskStart, readOnly = false, enabled
     }
   };
 
+  const handleRefreshGf3Dates = async () => {
+    if (!hasGf3ArchiveSourceDirs) {
+      setGf3Message('GF3_ARCHIVE_SOURCE_DIRS 未配置。');
+      return;
+    }
+    setGf3DateLoading(true);
+    setGf3Message('正在刷新 GF3 影像日期...');
+    try {
+      const res = await fetch(`${apiEndpoint}/monitor/gf3-sarscape-dates`, { credentials: 'include' });
+      const data = await parseJsonSafe(res, {});
+      if (!res.ok) {
+        throw new Error(data?.detail || `HTTP ${res.status}`);
+      }
+      const nextDates = toArray(data?.dates);
+      setGf3SarscapeDates(nextDates);
+      setGf3SelectedDate((prev) => (
+        prev && nextDates.some((item) => String(item?.date || '') === prev) ? prev : ''
+      ));
+      setGf3Message(`GF3 影像日期已刷新：${nextDates.length} 个日期。`);
+    } catch (err) {
+      setGf3Message(`失败：${err.message || '未知错误'}`);
+    } finally {
+      setGf3DateLoading(false);
+    }
+  };
+
   const handleGf3SarscapeSync = async () => {
     if (readOnly) {
       setGf3Message('当前账户为只读模式，无法触发 GF3 SARscape 标准化。');
@@ -902,6 +983,32 @@ const DataMonitorPanel = ({ apiEndpoint, onTaskStart, readOnly = false, enabled
             <div style={rowStyle}><span style={labelStyle}>SARscape DEM</span><span style={{ wordBreak: 'break-all' }}>{config.gf3_sarscape_dem_path || '未配置'}</span></div>
             <div style={rowStyle}><span style={labelStyle}>极化</span><span>{config.gf3_sarscape_polarizations || 'HH,HV'}</span></div>
             <div style={rowStyle}><span style={labelStyle}>Legacy GDAL</span><span>{gf3LegacyGdalEnabled ? '启用' : '关闭'}</span></div>
+            <div style={rowStyle}>
+              <span style={labelStyle}>影像日期</span>
+              <span style={{ display: 'flex', gap: '8px', alignItems: 'center', flexWrap: 'wrap' }}>
+                <select
+                  value={gf3SelectedDate}
+                  onChange={(event) => setGf3SelectedDate(event.target.value)}
+                  disabled={gf3DateLoading || gf3SarscapeProduceLoading || readOnly || !canRunGf3SarscapeProduce}
+                  style={{ minWidth: '180px', padding: '4px 6px' }}
+                >
+                  <option value="">全部可用日期</option>
+                  {gf3SarscapeDates.map((item) => (
+                    <option key={item.date} value={item.date}>
+                      {formatGf3Date(item.date)} ({item.scene_count || 0})
+                    </option>
+                  ))}
+                </select>
+                <button
+                  type="button"
+                  onClick={handleRefreshGf3Dates}
+                  disabled={gf3DateLoading || readOnly || !hasGf3ArchiveSourceDirs}
+                  style={actionBtnStyle(gf3DateLoading, readOnly || !hasGf3ArchiveSourceDirs)}
+                >
+                  {gf3DateLoading ? '加载中...' : '刷新日期'}
+                </button>
+              </span>
+            </div>
           </div>
           <div style={{ display: 'flex', gap: '10px', flexWrap: 'wrap' }}>
             {gf3LegacyGdalEnabled && (