"""Serve the local GeoAI Workbench console and its narrow local-run APIs."""
|
|
from __future__ import annotations
|
|
import argparse
|
import base64
|
import binascii
|
import hashlib
|
import json
|
import os
|
import re
|
import shutil
|
import subprocess
|
import threading
|
from datetime import UTC, datetime
|
from http import HTTPStatus
|
from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
|
from pathlib import Path, PurePosixPath
|
from typing import Any
|
from urllib.parse import parse_qs, unquote, urlsplit
|
from uuid import uuid4
|
|
|
DEFAULT_HOST = "127.0.0.1"
|
DEFAULT_PORT = 6173
|
# Uploads are sent as Base64 JSON. Keep the request limit above two 1 GiB
|
# files after encoding while retaining a per-file bound for local experiments.
|
MAX_REQUEST_BYTES = 3072 * 1024 * 1024
|
MAX_FILE_BYTES = 1024 * 1024 * 1024
|
MAX_IMAGES_PER_RUN = 12
|
MAX_SEGMENTATION_IMAGES_PER_RUN = 6
|
MAX_MEASUREMENT_RASTERS_PER_RUN = 4
|
MAX_ANOMALY_IMAGES_PER_ROLE = 6
|
CHANGE_THRESHOLD_DEFAULT = 0.5
|
CHANGE_THRESHOLD_MIN = 0.01
|
CHANGE_THRESHOLD_MAX = 0.99
|
CHANGE_MAX_DIMENSION_DEFAULT = 1024
|
CHANGE_MAX_DIMENSION_AUTO = 0
|
CHANGE_MAX_DIMENSION_MIN = 512
|
CHANGE_MAX_DIMENSION_MAX = 4096
|
CHANGE_PROCESSING_MODE_DEFAULT = "auto"
|
CHANGE_PROCESSING_MODES = {"auto", "image", "geotiff"}
|
SCAN_DEFAULT_THRESHOLDS = [0.3, 0.4, 0.5]
|
SCAN_DEFAULT_AREAS = [64, 256, 686]
|
SCAN_MAX_THRESHOLDS = 6
|
SCAN_MAX_AREAS = 6
|
SCAN_MAX_COMBINATIONS = 24
|
SCAN_JOB_TIMEOUT = 1800
|
ALLOWED_PATH_PREFIXES = (
|
"apps/workbench-console",
|
"shared/outputs",
|
"shared/data/raw/00-change-detection",
|
"shared/data/raw/01-object-detection",
|
"shared/data/raw/02-semantic-mapping",
|
"shared/data/raw/09-anomaly-detection",
|
)
|
SAFE_FILE_NAME = re.compile(r"[^\w.-]+", re.UNICODE)
|
SAFE_UPLOAD_ID = re.compile(r"^[0-9a-f]{32}$")
|
SAFE_SCAN_ID = re.compile(r"^[A-Za-z0-9._-]{1,100}$")
|
SAFE_SCAN_RESULT_ID = re.compile(r"^threshold-\d+(?:\.\d+)?_area-\d+$")
|
RUN_LOCK = threading.Lock()
|
SCAN_JOBS: dict[str, dict[str, Any]] = {}
|
SCAN_JOBS_LOCK = threading.Lock()
|
ANOMALY_JOB_LOCK = threading.Lock()
|
ANOMALY_JOBS: dict[str, dict[str, Any]] = {}
|
|
|
class ApiError(ValueError):
|
"""A request error that can be shown to the local console user."""
|
|
|
def safe_file_name(value: str, expected_suffixes: set[str]) -> str:
|
name = Path(value).name
|
suffix = Path(name).suffix.lower()
|
if suffix not in expected_suffixes:
|
raise ApiError(f"Unsupported file type: {suffix or '(none)'}.")
|
stem = SAFE_FILE_NAME.sub("_", Path(name).stem).strip("._") or "upload"
|
return f"{stem[:80]}{suffix}"
|
|
|
def decode_upload(payload: dict[str, Any], expected_suffixes: set[str]) -> tuple[str, bytes]:
|
if not isinstance(payload, dict) or not isinstance(payload.get("name"), str) or not isinstance(payload.get("content"), str):
|
raise ApiError("Each uploaded file must include name and Base64 content.")
|
name = safe_file_name(payload["name"], expected_suffixes)
|
try:
|
content = base64.b64decode(payload["content"], validate=True)
|
except (binascii.Error, ValueError) as exc:
|
raise ApiError(f"Invalid Base64 file content for {name}.") from exc
|
if not content:
|
raise ApiError(f"Uploaded file is empty: {name}.")
|
if len(content) > MAX_FILE_BYTES:
|
raise ApiError(f"Uploaded file exceeds {MAX_FILE_BYTES // (1024 * 1024)} MB: {name}.")
|
return name, content
|
|
|
def make_run_id(prefix: str) -> str:
|
return f"{prefix}-{datetime.now(UTC):%Y%m%d-%H%M%S}-{uuid4().hex[:6]}"
|
|
|
def relative_path(root: Path, path: Path) -> str:
|
return path.relative_to(root).as_posix()
|
|
|
def load_json(path: Path) -> dict[str, Any]:
|
try:
|
payload = json.loads(path.read_text(encoding="utf-8"))
|
except (OSError, json.JSONDecodeError):
|
return {}
|
return payload if isinstance(payload, dict) else {}
|
|
|
def file_sha256(path: Path) -> str:
|
digest = hashlib.sha256()
|
with path.open("rb") as stream:
|
for chunk in iter(lambda: stream.read(8 * 1024 * 1024), b""):
|
digest.update(chunk)
|
return digest.hexdigest()
|
|
|
def trajectory_runs(root: Path) -> list[dict[str, Any]]:
|
output_root = root / "shared" / "outputs" / "15-trajectory-analysis"
|
records: list[dict[str, Any]] = []
|
for metadata_path in output_root.rglob("run_metadata.json"):
|
artifact = metadata_path.parent
|
if not (artifact / "trajectory_summary.csv").is_file() or not (artifact / "events.json").is_file():
|
continue
|
metadata = load_json(metadata_path)
|
case_id = str(metadata.get("case_id") or artifact.name)
|
is_real = case_id == "tian-dun-flight-19578"
|
records.append(
|
{
|
"id": case_id,
|
"label": "田墩实飞" if is_real else case_id,
|
"note": "区域相交是来源数据的空间结果，不是违规结论。" if is_real else "本地实验运行结果，可继续查看结构化输出。",
|
"artifactRoot": relative_path(root, artifact),
|
"showSpatialContext": (artifact / "zones.geojson").is_file() and (artifact / "reference_routes.geojson").is_file(),
|
"showFlyableZones": (artifact / "flyable_zones.geojson").is_file(),
|
"createdAt": str(metadata.get("created_at") or ""),
|
}
|
)
|
return sorted(records, key=lambda item: (item["createdAt"], item["id"]), reverse=True)
|
|
|
def detection_runs(root: Path) -> list[dict[str, Any]]:
|
output_root = root / "shared" / "outputs" / "01-object-detection"
|
records: list[dict[str, Any]] = []
|
for metadata_path in output_root.rglob("run_metadata.json"):
|
artifact = metadata_path.parent
|
if not (artifact / "detections.json").is_file():
|
continue
|
metadata = load_json(metadata_path)
|
input_value = str(metadata.get("input_dir") or "")
|
input_dir = Path(input_value) if input_value else root / "shared" / "data" / "raw" / "01-object-detection"
|
try:
|
input_root = relative_path(root, input_dir.resolve())
|
except ValueError:
|
continue
|
run_id = artifact.name if artifact != output_root else "baseline"
|
records.append(
|
{
|
"id": run_id,
|
"label": "既有基线结果" if run_id == "baseline" else run_id,
|
"note": "CPU 基线：人员与常见车辆；树木不在当前模型有效类别内。",
|
"artifactRoot": relative_path(root, artifact),
|
"inputRoot": input_root,
|
"createdAt": str(metadata.get("created_at") or ""),
|
}
|
)
|
return sorted(records, key=lambda item: (item["createdAt"], item["id"]), reverse=True)
|
|
|
def change_runs(root: Path) -> list[dict[str, Any]]:
|
output_root = root / "shared" / "outputs" / "00-change-detection"
|
records: list[dict[str, Any]] = []
|
for metadata_path in output_root.rglob("run_metadata.json"):
|
artifact = metadata_path.parent
|
metadata = load_json(metadata_path)
|
artifacts = metadata.get("artifacts")
|
if metadata.get("capability") != "00-change-detection" or metadata.get("schema_version") != 1 or metadata.get("kind") == "parameter-scan-inference" or not isinstance(artifacts, dict):
|
continue
|
if not (artifact / str(artifacts.get("overlay") or "")).is_file() or not (artifact / str(artifacts.get("vector") or "")).is_file():
|
continue
|
raw_root_value = str(metadata.get("raw_input_dir") or "shared/data/raw/00-change-detection/validation-20260817")
|
raw_root = root / Path(raw_root_value)
|
input_files = metadata.get("input_files")
|
if not isinstance(input_files, list) or len(input_files) != 2:
|
continue
|
before_value = str(metadata.get("raw_before") or (Path(raw_root_value) / str(input_files[0])).as_posix())
|
after_value = str(metadata.get("raw_after") or (Path(raw_root_value) / str(input_files[1])).as_posix())
|
try:
|
before_path = (root / before_value).resolve()
|
after_path = (root / after_value).resolve()
|
allowed_raw = (root / "shared" / "data" / "raw" / "00-change-detection").resolve()
|
before_path.relative_to(allowed_raw)
|
after_path.relative_to(allowed_raw)
|
except ValueError:
|
continue
|
if not before_path.is_file() or not after_path.is_file():
|
continue
|
run_id = artifact.name
|
records.append(
|
{
|
"id": run_id,
|
"label": run_id,
|
"note": "ChangeStar CPU 变化栅格与 GeoAI 像素坐标图斑；结果需人工复核。",
|
"artifactRoot": relative_path(root, artifact),
|
"beforeImage": relative_path(root, before_path),
|
"afterImage": relative_path(root, after_path),
|
"createdAt": str(metadata.get("created_at") or ""),
|
}
|
)
|
return sorted(records, key=lambda item: (item["createdAt"], item["id"]), reverse=True)
|
|
|
def change_parameter_scans(root: Path) -> list[dict[str, Any]]:
|
"""Discover read-only parameter scans produced from an existing change run."""
|
output_root = root / "shared" / "outputs" / "00-change-detection"
|
records: list[dict[str, Any]] = []
|
for summary_path in output_root.rglob("scan_summary.json"):
|
scan_root = summary_path.parent
|
summary = load_json(summary_path)
|
results: list[dict[str, Any]] = []
|
for item in summary.get("results", []):
|
if not isinstance(item, dict) or not isinstance(item.get("directory"), str):
|
continue
|
directory = scan_root / item["directory"]
|
overlay = directory / "overlay_preview.jpg"
|
mask = directory / "change_mask.tif"
|
regions = directory / "regions.json"
|
if not overlay.is_file() or not mask.is_file() or not regions.is_file():
|
continue
|
results.append(
|
{
|
"id": item["directory"],
|
"label": f"T={float(item.get('threshold', 0.5)):.2f} / 面积={int(item.get('minimum_area_pixels', 0))} px",
|
"threshold": item.get("threshold"),
|
"minimumAreaPixels": item.get("minimum_area_pixels"),
|
"cleanedComponents": item.get("cleaned_components"),
|
"changedPixels": item.get("changed_pixels"),
|
"changedPixelRatio": item.get("changed_pixel_ratio"),
|
"vectorFeatureCount": item.get("vector_feature_count"),
|
"fullVectorFeatureCount": (load_json(directory / "full_result.json").get("full_vector_feature_count") if (directory / "full_result.json").is_file() else None),
|
"rectangleFeatureCount": (
|
load_json(directory / "full_result.json").get("rectangle_vector_feature_count")
|
if (directory / "full_result.json").is_file() and load_json(directory / "full_result.json").get("rectangle_vector_feature_count") is not None
|
else len(load_json(directory / "changes_rectangles.geojson").get("features", [])) if (directory / "changes_rectangles.geojson").is_file() else None
|
),
|
"overlay": relative_path(root, overlay),
|
"mask": relative_path(root, mask),
|
"regions": relative_path(root, regions),
|
"vector": (relative_path(root, directory / "changes.geojson") if (directory / "changes.geojson").is_file() else None),
|
"rectangleVector": (relative_path(root, directory / "changes_rectangles.geojson") if (directory / "changes_rectangles.geojson").is_file() else None),
|
"rectangleVectorWgs84": (relative_path(root, directory / "changes_rectangles_wgs84.geojson") if (directory / "changes_rectangles_wgs84.geojson").is_file() else None),
|
}
|
)
|
# A failed job may have been repaired or materialized later. Keep it
|
# discoverable whenever at least one complete candidate exists; only
|
# hide scans that still have no usable result.
|
if not results:
|
continue
|
scan_metadata = load_json(scan_root / "scan_metadata.json")
|
contact_sheet = scan_root / "parameter_scan_contact_sheet.jpg"
|
records.append(
|
{
|
"id": scan_root.name,
|
"label": f"低成本参数扫描 · {scan_root.name}",
|
"note": f"复用已有变化概率结果，不重新运行 ChangeStar；源运行：{summary.get('source_run', '未知')}",
|
"artifactRoot": relative_path(root, scan_root),
|
"sourceRun": summary.get("source_run"),
|
"userSubmitted": bool(scan_metadata),
|
"contactSheet": relative_path(root, contact_sheet) if contact_sheet.is_file() else None,
|
"results": results,
|
}
|
)
|
return sorted(records, key=lambda item: item["id"], reverse=True)
|
|
|
def semantic_runs(root: Path) -> list[dict[str, Any]]:
|
output_root = root / "shared" / "outputs" / "02-semantic-mapping"
|
records: list[dict[str, Any]] = []
|
for metadata_path in output_root.rglob("run_metadata.json"):
|
artifact = metadata_path.parent
|
metadata = load_json(metadata_path)
|
if metadata.get("capability") != "02-semantic-mapping" or not isinstance(metadata.get("images"), list):
|
continue
|
run_id = artifact.name if artifact != output_root else "baseline"
|
records.append(
|
{
|
"id": run_id,
|
"label": "语义分割基线" if run_id == "baseline" else run_id,
|
"note": f"{metadata.get('task_name') or '通用颜色规则基线'}，输出栅格掩膜与 GeoAI 矢量结果。",
|
"artifactRoot": relative_path(root, artifact),
|
"inputRoot": str(metadata.get("input_dir") or "shared/data/processed/02-semantic-mapping"),
|
"rawInputRoot": str(metadata.get("raw_input_dir") or "shared/data/raw/02-semantic-mapping"),
|
"createdAt": str(metadata.get("created_at") or ""),
|
}
|
)
|
return sorted(records, key=lambda item: (item["createdAt"], item["id"]), reverse=True)
|
|
|
def measurement_runs(root: Path) -> list[dict[str, Any]]:
|
output_root = root / "shared" / "outputs" / "04-spatial-measurement"
|
records: list[dict[str, Any]] = []
|
for metadata_path in output_root.rglob("run_metadata.json"):
|
artifact = metadata_path.parent
|
metadata = load_json(metadata_path)
|
if metadata.get("capability") != "04-spatial-measurement" or not isinstance(metadata.get("images"), list):
|
continue
|
run_id = artifact.name
|
records.append(
|
{
|
"id": run_id,
|
"label": run_id,
|
"note": "GeoAI 栅格转矢量后进行对象计数、面积和周长测量。",
|
"artifactRoot": relative_path(root, artifact),
|
"createdAt": str(metadata.get("created_at") or ""),
|
}
|
)
|
return sorted(records, key=lambda item: (item["createdAt"], item["id"]), reverse=True)
|
|
|
def anomaly_runs(root: Path) -> list[dict[str, Any]]:
|
output_root = root / "shared" / "outputs" / "09-anomaly-detection"
|
allowed_raw = (root / "shared" / "data" / "raw" / "09-anomaly-detection").resolve()
|
records: list[dict[str, Any]] = []
|
for metadata_path in output_root.rglob("run_metadata.json"):
|
artifact = metadata_path.parent
|
metadata = load_json(metadata_path)
|
images = metadata.get("images")
|
if metadata.get("capability") != "09-anomaly-detection" or not isinstance(images, list):
|
continue
|
raw_input_value = str(metadata.get("raw_input_dir") or "")
|
raw_reference_value = str(metadata.get("raw_reference_dir") or "")
|
if not raw_input_value or not raw_reference_value:
|
continue
|
try:
|
raw_input = (root / raw_input_value).resolve()
|
raw_reference = (root / raw_reference_value).resolve()
|
raw_input.relative_to(allowed_raw)
|
raw_reference.relative_to(allowed_raw)
|
except ValueError:
|
continue
|
if not raw_input.is_dir() or not raw_reference.is_dir():
|
continue
|
if any(not (artifact / str(item.get("overlay_file") or "")).is_file() for item in images if isinstance(item, dict)):
|
continue
|
run_id = artifact.name
|
records.append(
|
{
|
"id": run_id,
|
"label": str(metadata.get("display_name") or run_id),
|
"note": str(metadata.get("case_note") or "规则基线与 Isolation Forest 的视觉离群候选，只供人工复核。"),
|
"artifactRoot": relative_path(root, artifact),
|
"inputRoot": relative_path(root, raw_input),
|
"referenceRoot": relative_path(root, raw_reference),
|
"createdAt": str(metadata.get("created_at") or ""),
|
}
|
)
|
return sorted(records, key=lambda item: (item["createdAt"], item["id"]), reverse=True)
|
|
|
def anomaly_job(job_id: str) -> dict[str, Any] | None:
|
with ANOMALY_JOB_LOCK:
|
value = ANOMALY_JOBS.get(job_id)
|
return dict(value) if value else None
|
|
|
def validate_anomaly_parameters(payload: dict[str, Any]) -> tuple[int, int, float, int]:
|
tile_size = payload.get("tileSize", 256)
|
stride = payload.get("stride", 128)
|
threshold_quantile = payload.get("thresholdQuantile", 0.995)
|
random_state = payload.get("randomState", 42)
|
if isinstance(tile_size, bool) or not isinstance(tile_size, int) or not 128 <= tile_size <= 1024:
|
raise ApiError("Tile size must be an integer between 128 and 1024.")
|
if isinstance(stride, bool) or not isinstance(stride, int) or not 32 <= stride <= tile_size:
|
raise ApiError("Stride must be an integer between 32 and tile size.")
|
if isinstance(threshold_quantile, bool) or not isinstance(threshold_quantile, (int, float)) or not 0.9 <= float(threshold_quantile) <= 0.9999:
|
raise ApiError("Threshold quantile must be between 0.9 and 0.9999.")
|
if isinstance(random_state, bool) or not isinstance(random_state, int) or not 0 <= random_state <= 2_147_483_647:
|
raise ApiError("Random state must be a non-negative integer.")
|
return tile_size, stride, float(threshold_quantile), random_state
|
|
|
def execute_anomaly_job(
|
root: Path,
|
job_id: str,
|
run_id: str,
|
raw_reference: Path,
|
raw_input: Path,
|
processed_reference: Path,
|
processed_input: Path,
|
output: Path,
|
tile_size: int,
|
stride: int,
|
threshold_quantile: float,
|
random_state: int,
|
) -> None:
|
with ANOMALY_JOB_LOCK:
|
ANOMALY_JOBS[job_id]["status"] = "running"
|
python = root / ".venvs" / "09-anomaly-detection" / "Scripts" / "python.exe"
|
command = [
|
str(python),
|
str(root / "capabilities" / "09-anomaly-detection" / "run_anomaly_detection.py"),
|
"--reference", str(processed_reference),
|
"--input", str(processed_input),
|
"--output", str(output),
|
"--tile-size", str(tile_size),
|
"--stride", str(stride),
|
"--threshold-quantile", f"{threshold_quantile:.6f}",
|
"--random-state", str(random_state),
|
"--spatial-mode", "auto",
|
]
|
try:
|
with RUN_LOCK:
|
completed = subprocess.run(command, cwd=root, capture_output=True, text=True, timeout=1800, check=False)
|
if completed.returncode:
|
message = (completed.stderr or completed.stdout or "Unknown script error.").strip().splitlines()[-1]
|
raise ApiError(f"Processing failed: {message[:600]}")
|
metadata_path = output / "run_metadata.json"
|
if not metadata_path.is_file():
|
raise ApiError("Anomaly-detection script finished without the expected result metadata.")
|
metadata = load_json(metadata_path)
|
metadata["raw_input_dir"] = relative_path(root, raw_input)
|
metadata["raw_reference_dir"] = relative_path(root, raw_reference)
|
metadata["processed_input_dir"] = relative_path(root, processed_input)
|
metadata["processed_reference_dir"] = relative_path(root, processed_reference)
|
metadata_path.write_text(json.dumps(metadata, ensure_ascii=False, indent=2), encoding="utf-8")
|
definition = next(item for item in anomaly_runs(root) if item["id"] == run_id)
|
with ANOMALY_JOB_LOCK:
|
ANOMALY_JOBS[job_id].update({"status": "complete", "run": definition, "finishedAt": datetime.now(UTC).isoformat()})
|
except Exception as exc: # pragma: no cover - background boundary
|
with ANOMALY_JOB_LOCK:
|
ANOMALY_JOBS[job_id].update({"status": "failed", "error": str(exc), "finishedAt": datetime.now(UTC).isoformat()})
|
|
|
def semantic_tasks(root: Path) -> list[dict[str, Any]]:
|
catalog = load_json(root / "capabilities" / "02-semantic-mapping" / "configs" / "task-catalog.json")
|
tasks = catalog.get("tasks")
|
if not isinstance(tasks, list):
|
return []
|
return [item for item in tasks if isinstance(item, dict) and isinstance(item.get("id"), str)]
|
|
|
class WorkbenchConsoleHandler(SimpleHTTPRequestHandler):
|
"""Static UI plus fixed, local-only ingestion and experiment commands."""
|
|
server_version = "GeoAIWorkbench/1.0"
|
|
@property
|
def root(self) -> Path:
|
return Path(self.directory).resolve()
|
|
def do_GET(self) -> None: # noqa: N802 - inherited standard-library method name
|
path = urlsplit(self.path).path
|
if path == "/api/change-detection/runs":
|
self.send_json(HTTPStatus.OK, {"runs": change_runs(self.root)})
|
return
|
if path == "/api/change-detection/scans":
|
self.send_json(HTTPStatus.OK, {"scans": change_parameter_scans(self.root)})
|
return
|
if path.startswith("/api/change-detection/scan-jobs/"):
|
job_id = path.rstrip("/").rsplit("/", 1)[-1]
|
with SCAN_JOBS_LOCK:
|
job = dict(SCAN_JOBS.get(job_id, {}))
|
if not job:
|
self.send_json(HTTPStatus.NOT_FOUND, {"error": "Unknown change-detection scan job."})
|
else:
|
self.send_json(HTTPStatus.OK, {"job": job})
|
return
|
if path == "/api/trajectory/runs":
|
self.send_json(HTTPStatus.OK, {"runs": trajectory_runs(self.root)})
|
return
|
if path == "/api/object-detection/runs":
|
self.send_json(HTTPStatus.OK, {"runs": detection_runs(self.root)})
|
return
|
if path == "/api/semantic-mapping/runs":
|
self.send_json(HTTPStatus.OK, {"runs": semantic_runs(self.root)})
|
return
|
if path == "/api/semantic-mapping/tasks":
|
self.send_json(HTTPStatus.OK, {"tasks": semantic_tasks(self.root)})
|
return
|
if path == "/api/spatial-measurement/runs":
|
self.send_json(HTTPStatus.OK, {"runs": measurement_runs(self.root)})
|
return
|
if path == "/api/anomaly-detection/runs":
|
self.send_json(HTTPStatus.OK, {"runs": anomaly_runs(self.root)})
|
return
|
if path.startswith("/api/anomaly-detection/jobs/"):
|
job_id = path.rstrip("/").rsplit("/", 1)[-1]
|
job = anomaly_job(job_id)
|
self.send_json(HTTPStatus.OK if job else HTTPStatus.NOT_FOUND, {"job": job} if job else {"error": "Unknown anomaly-detection job."})
|
return
|
if path == "/":
|
self.send_response(HTTPStatus.FOUND)
|
self.send_header("Location", "/apps/workbench-console/")
|
self.end_headers()
|
return
|
super().do_GET()
|
|
def do_POST(self) -> None: # noqa: N802 - inherited standard-library method name
|
path = urlsplit(self.path).path
|
try:
|
payload = self.read_json_body()
|
if path == "/api/change-detection/runs":
|
self.send_json(HTTPStatus.CREATED, {"run": self.create_change_run(payload)})
|
return
|
if path == "/api/change-detection/scans":
|
self.send_json(HTTPStatus.ACCEPTED, {"job": self.create_change_scan(payload)})
|
return
|
if path.startswith("/api/change-detection/scans/") and path.endswith("/promote"):
|
scan_id = path.split("/")[-2]
|
self.send_json(HTTPStatus.CREATED, {"run": self.promote_change_scan(scan_id, payload)})
|
return
|
if path == "/api/trajectory/runs":
|
self.send_json(HTTPStatus.CREATED, {"run": self.create_trajectory_run(payload)})
|
return
|
if path == "/api/object-detection/runs":
|
self.send_json(HTTPStatus.CREATED, {"run": self.create_detection_run(payload)})
|
return
|
if path == "/api/semantic-mapping/runs":
|
self.send_json(HTTPStatus.CREATED, {"run": self.create_semantic_run(payload)})
|
return
|
if path == "/api/spatial-measurement/runs":
|
self.send_json(HTTPStatus.CREATED, {"run": self.create_measurement_run(payload)})
|
return
|
if path == "/api/anomaly-detection/runs":
|
self.send_json(HTTPStatus.ACCEPTED, {"job": self.create_anomaly_run(payload)})
|
return
|
self.send_json(HTTPStatus.NOT_FOUND, {"error": "Unknown local API endpoint."})
|
except ApiError as exc:
|
self.send_json(HTTPStatus.BAD_REQUEST, {"error": str(exc)})
|
except subprocess.TimeoutExpired:
|
self.send_json(HTTPStatus.GATEWAY_TIMEOUT, {"error": "The local run exceeded its time limit; no existing result was overwritten."})
|
except Exception as exc: # pragma: no cover - defensive server boundary
|
self.log_error("local run failed: %s", exc)
|
self.send_json(HTTPStatus.INTERNAL_SERVER_ERROR, {"error": "Local run failed. Check the console terminal for details."})
|
|
def do_PUT(self) -> None: # noqa: N802 - binary upload endpoint
|
path = urlsplit(self.path).path
|
if not path.startswith("/api/change-detection/uploads/") and not path.startswith("/api/anomaly-detection/uploads/"):
|
self.send_json(HTTPStatus.NOT_FOUND, {"error": "Unknown local API endpoint."})
|
return
|
try:
|
if path.startswith("/api/anomaly-detection/uploads/"):
|
result = self.receive_anomaly_upload(path)
|
else:
|
result = self.receive_change_upload(path)
|
self.send_json(HTTPStatus.CREATED, result)
|
except ApiError as exc:
|
self.send_json(HTTPStatus.BAD_REQUEST, {"error": str(exc)})
|
except Exception as exc: # pragma: no cover - defensive server boundary
|
self.log_error("binary upload failed: %s", exc)
|
self.send_json(HTTPStatus.INTERNAL_SERVER_ERROR, {"error": "Binary upload failed. Check the console terminal for details."})
|
|
def do_OPTIONS(self) -> None: # noqa: N802
|
self.send_response(HTTPStatus.NO_CONTENT)
|
self.send_header("Allow", "GET, POST, PUT, OPTIONS")
|
self.end_headers()
|
|
def read_json_body(self) -> dict[str, Any]:
|
content_length = self.headers.get("Content-Length")
|
if content_length is None or not content_length.isdigit():
|
raise ApiError("A JSON request body with Content-Length is required.")
|
size = int(content_length)
|
if size <= 0 or size > MAX_REQUEST_BYTES:
|
raise ApiError(f"Request must be between 1 byte and {MAX_REQUEST_BYTES // (1024 * 1024)} MB.")
|
if "application/json" not in self.headers.get("Content-Type", ""):
|
raise ApiError("Content-Type must be application/json.")
|
try:
|
payload = json.loads(self.rfile.read(size).decode("utf-8"))
|
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
|
raise ApiError("Request body is not valid UTF-8 JSON.") from exc
|
if not isinstance(payload, dict):
|
raise ApiError("JSON request body must be an object.")
|
return payload
|
|
def run_command(self, command: list[str], timeout: int) -> None:
|
completed = subprocess.run(command, cwd=self.root, capture_output=True, text=True, timeout=timeout, check=False)
|
if completed.returncode:
|
message = (completed.stderr or completed.stdout or "Unknown script error.").strip().splitlines()[-1]
|
raise ApiError(f"Processing failed: {message[:600]}")
|
|
def receive_change_upload(self, path: str) -> dict[str, Any]:
|
return self.receive_binary_upload(path, "00-change-detection", {"before", "after"}, "change-detection")
|
|
def receive_anomaly_upload(self, path: str) -> dict[str, Any]:
|
return self.receive_binary_upload(path, "09-anomaly-detection", {"reference", "input"}, "anomaly-detection")
|
|
def receive_binary_upload(
|
self,
|
path: str,
|
capability: str,
|
allowed_roles: set[str],
|
label: str,
|
) -> dict[str, Any]:
|
upload_id = path.rstrip("/").rsplit("/", 1)[-1]
|
if not SAFE_UPLOAD_ID.fullmatch(upload_id):
|
raise ApiError(f"Invalid {label} upload id.")
|
query = parse_qs(urlsplit(self.path).query)
|
role = query.get("role", [""])[0]
|
if role not in allowed_roles:
|
raise ApiError(f"Invalid {label} upload role.")
|
encoded_name = self.headers.get("X-Upload-Name", "")
|
if len(encoded_name) > 2048:
|
raise ApiError("Encoded upload name is too long.")
|
try:
|
name = unquote(encoded_name, encoding="utf-8", errors="strict")
|
except UnicodeError as exc:
|
raise ApiError("Upload name is not valid UTF-8 percent encoding.") from exc
|
safe_name = safe_file_name(name, {".jpg", ".jpeg", ".png", ".tif", ".tiff"})
|
content_length = self.headers.get("Content-Length")
|
if content_length is None or not content_length.isdigit():
|
raise ApiError("Binary upload requires a Content-Length header.")
|
size = int(content_length)
|
if size <= 0 or size > MAX_FILE_BYTES:
|
raise ApiError(f"Uploaded file must be between 1 byte and {MAX_FILE_BYTES // (1024 * 1024)} MB: {safe_name}.")
|
staging = self.root / "shared" / "data" / "raw" / capability / "uploads" / upload_id
|
staging.mkdir(parents=True, exist_ok=False)
|
part = staging / f"{role}.part"
|
target = staging / f"{role}{Path(safe_name).suffix.lower()}"
|
remaining = size
|
digest = hashlib.sha256()
|
try:
|
with part.open("wb") as stream:
|
while remaining:
|
chunk = self.rfile.read(min(8 * 1024 * 1024, remaining))
|
if not chunk:
|
raise ApiError("Binary upload ended before Content-Length was reached.")
|
stream.write(chunk)
|
digest.update(chunk)
|
remaining -= len(chunk)
|
part.replace(target)
|
(staging / f"{role}.json").write_text(json.dumps({"role": role, "name": safe_name, "size": size, "sha256": digest.hexdigest()}), encoding="utf-8")
|
except Exception:
|
part.unlink(missing_ok=True)
|
target.unlink(missing_ok=True)
|
raise
|
return {"uploadId": upload_id, "role": role, "name": safe_name, "size": size, "sha256": digest.hexdigest()}
|
|
def resolve_change_upload(self, payload: Any, role: str) -> tuple[str, Path]:
|
return self.resolve_binary_upload(payload, role, "00-change-detection", "change-detection")
|
|
def resolve_anomaly_upload(self, payload: Any, role: str) -> tuple[str, Path, str]:
|
name, path = self.resolve_binary_upload(payload, role, "09-anomaly-detection", "anomaly-detection")
|
manifest = load_json(path.parent / f"{role}.json")
|
return name, path, str(manifest.get("sha256") or "")
|
|
def resolve_binary_upload(self, payload: Any, role: str, capability: str, label: str) -> tuple[str, Path]:
|
if not isinstance(payload, dict) or not isinstance(payload.get("uploadId"), str):
|
raise ApiError(f"{label} uploads must include a {role} uploadId.")
|
upload_id = payload["uploadId"]
|
if not SAFE_UPLOAD_ID.fullmatch(upload_id):
|
raise ApiError(f"Invalid {label} upload id.")
|
staging = self.root / "shared" / "data" / "raw" / capability / "uploads" / upload_id
|
manifest = load_json(staging / f"{role}.json")
|
name = str(manifest.get("name") or "")
|
path = staging / f"{role}{Path(name).suffix.lower()}"
|
if manifest.get("role") != role or not name or not path.is_file():
|
raise ApiError(f"The staged {role} upload is unavailable or incomplete.")
|
return name, path
|
|
def create_trajectory_run(self, payload: dict[str, Any]) -> dict[str, Any]:
|
files = payload.get("files")
|
if not isinstance(files, dict):
|
raise ApiError("Trajectory request must contain a files object.")
|
required = {
|
"flight": {".xlsx"},
|
"route": {".kmz"},
|
"restricted": {".geojson"},
|
}
|
decoded = {key: decode_upload(files.get(key), suffixes) for key, suffixes in required.items()}
|
flyable = decode_upload(files["flyable"], {".gzip"}) if files.get("flyable") else None
|
run_id = make_run_id("trajectory")
|
raw_root = self.root / "shared" / "data" / "raw" / "15-trajectory-analysis" / "runs" / run_id
|
paths = {"flight": raw_root / "tracks" / decoded["flight"][0], "route": raw_root / "routes" / decoded["route"][0], "restricted": raw_root / "areas" / decoded["restricted"][0]}
|
for key, path in paths.items():
|
path.parent.mkdir(parents=True, exist_ok=True)
|
path.write_bytes(decoded[key][1])
|
if flyable:
|
flyable_path = raw_root / "areas" / flyable[0]
|
flyable_path.write_bytes(flyable[1])
|
processed = self.root / "shared" / "data" / "processed" / "15-trajectory-analysis" / run_id
|
output_parent = self.root / "shared" / "outputs" / "15-trajectory-analysis" / "runs" / run_id
|
python = self.root / ".venvs" / "15-trajectory-analysis" / "Scripts" / "python.exe"
|
if not python.is_file():
|
raise ApiError("Trajectory virtual environment is unavailable. Run the capability setup first.")
|
with RUN_LOCK:
|
self.run_command([str(python), str(self.root / "capabilities" / "15-trajectory-analysis" / "prepare_real_flight.py"), "--raw-dir", str(raw_root), "--output", str(processed), "--case-id", run_id], 300)
|
self.run_command([str(python), str(self.root / "capabilities" / "15-trajectory-analysis" / "run_trajectory_analysis.py"), "--input", str(processed / f"{run_id}.case.json"), "--output", str(output_parent)], 300)
|
artifact = output_parent / run_id
|
if not (artifact / "run_metadata.json").is_file():
|
raise ApiError("Trajectory script finished without the expected result metadata.")
|
return next(item for item in trajectory_runs(self.root) if item["id"] == run_id)
|
|
def create_detection_run(self, payload: dict[str, Any]) -> dict[str, Any]:
|
uploads = payload.get("images")
|
if not isinstance(uploads, list) or not uploads:
|
raise ApiError("Object-detection request must include at least one image.")
|
if len(uploads) > MAX_IMAGES_PER_RUN:
|
raise ApiError(f"A local run accepts at most {MAX_IMAGES_PER_RUN} images.")
|
decoded = [decode_upload(item, {".jpg", ".jpeg", ".png"}) for item in uploads]
|
if len({name.casefold() for name, _ in decoded}) != len(decoded):
|
raise ApiError("Uploaded image names must be unique within one run.")
|
run_id = make_run_id("detection")
|
raw_root = self.root / "shared" / "data" / "raw" / "01-object-detection" / "runs" / run_id
|
raw_root.mkdir(parents=True, exist_ok=False)
|
for name, content in decoded:
|
(raw_root / name).write_bytes(content)
|
output = self.root / "shared" / "outputs" / "01-object-detection" / "runs" / run_id
|
python = self.root / ".venvs" / "01-object-detection" / "Scripts" / "python.exe"
|
if not python.is_file():
|
raise ApiError("Object-detection virtual environment is unavailable. Run the capability setup first.")
|
with RUN_LOCK:
|
self.run_command([str(python), str(self.root / "capabilities" / "01-object-detection" / "run_detection.py"), "--input", str(raw_root), "--output", str(output)], 1200)
|
if not (output / "run_metadata.json").is_file():
|
raise ApiError("Detection script finished without the expected result metadata.")
|
return next(item for item in detection_runs(self.root) if item["id"] == run_id)
|
|
def create_change_run(self, payload: dict[str, Any]) -> dict[str, Any]:
|
files = payload.get("files")
|
uploads = payload.get("uploads")
|
staged: dict[str, tuple[str, Path]] = {}
|
if isinstance(uploads, dict):
|
staged["before"] = self.resolve_change_upload(uploads.get("before"), "before")
|
staged["after"] = self.resolve_change_upload(uploads.get("after"), "after")
|
elif isinstance(files, dict):
|
decoded_before = decode_upload(files.get("before"), {".jpg", ".jpeg", ".png", ".tif", ".tiff"})
|
decoded_after = decode_upload(files.get("after"), {".jpg", ".jpeg", ".png", ".tif", ".tiff"})
|
else:
|
raise ApiError("Change-detection request must contain before and after files or uploads.")
|
threshold_value = payload.get("threshold", CHANGE_THRESHOLD_DEFAULT)
|
if isinstance(threshold_value, bool) or not isinstance(threshold_value, (int, float)):
|
raise ApiError("Change-detection threshold must be a number between 0.01 and 0.99.")
|
threshold = float(threshold_value)
|
if not CHANGE_THRESHOLD_MIN <= threshold <= CHANGE_THRESHOLD_MAX:
|
raise ApiError("Change-detection threshold must be between 0.01 and 0.99.")
|
processing_mode = payload.get("processingMode", CHANGE_PROCESSING_MODE_DEFAULT)
|
if not isinstance(processing_mode, str) or processing_mode not in CHANGE_PROCESSING_MODES:
|
raise ApiError("Change-detection processing mode must be auto, image, or geotiff.")
|
max_dimension_value = payload.get("maxDimension", CHANGE_MAX_DIMENSION_AUTO)
|
if isinstance(max_dimension_value, bool) or not isinstance(max_dimension_value, int):
|
raise ApiError("Change-detection resolution must be an integer: 0 or between 512 and 4096.")
|
max_dimension = int(max_dimension_value)
|
if max_dimension != CHANGE_MAX_DIMENSION_AUTO and not CHANGE_MAX_DIMENSION_MIN <= max_dimension <= CHANGE_MAX_DIMENSION_MAX:
|
raise ApiError("Change-detection resolution must be 0 or between 512 and 4096.")
|
if staged:
|
before_name, after_name = staged["before"][0], staged["after"][0]
|
else:
|
before_name, after_name = decoded_before[0], decoded_after[0]
|
run_id = make_run_id("change")
|
raw_root = self.root / "shared" / "data" / "raw" / "00-change-detection" / "runs" / run_id
|
before_path = raw_root / "before" / before_name
|
after_path = raw_root / "after" / after_name
|
before_path.parent.mkdir(parents=True, exist_ok=False)
|
after_path.parent.mkdir(parents=True, exist_ok=False)
|
if staged:
|
shutil.copyfile(staged["before"][1], before_path)
|
shutil.copyfile(staged["after"][1], after_path)
|
else:
|
before_path.write_bytes(decoded_before[1])
|
after_path.write_bytes(decoded_after[1])
|
processed_root = self.root / "shared" / "data" / "processed" / "00-change-detection" / run_id
|
output = self.root / "shared" / "outputs" / "00-change-detection" / "runs" / run_id
|
python = self.root / ".venvs" / "00-change-detection" / "Scripts" / "python.exe"
|
if not python.is_file():
|
raise ApiError("Change-detection virtual environment is unavailable. Run the capability setup first.")
|
with RUN_LOCK:
|
self.run_command(
|
[
|
str(python),
|
str(self.root / "capabilities" / "00-change-detection" / "run_change_detection.py"),
|
"--before", str(before_path),
|
"--after", str(after_path),
|
"--threshold", f"{threshold:.4f}",
|
"--max-dimension", str(max_dimension),
|
"--processing-mode", processing_mode,
|
"--processed-output", str(processed_root),
|
"--output", str(output),
|
],
|
1200,
|
)
|
metadata_path = output / "run_metadata.json"
|
if not metadata_path.is_file():
|
raise ApiError("Change-detection script finished without the expected result metadata.")
|
metadata = load_json(metadata_path)
|
metadata["raw_input_dir"] = relative_path(self.root, raw_root)
|
metadata["processed_input_dir"] = relative_path(self.root, processed_root)
|
metadata["raw_before"] = relative_path(self.root, before_path)
|
metadata["raw_after"] = relative_path(self.root, after_path)
|
metadata_path.write_text(json.dumps(metadata, ensure_ascii=False, indent=2), encoding="utf-8")
|
return next(item for item in change_runs(self.root) if item["id"] == run_id)
|
|
def _scan_parameters(self, payload: dict[str, Any]) -> tuple[list[float], list[int]]:
|
raw_thresholds = payload.get("thresholds", SCAN_DEFAULT_THRESHOLDS)
|
raw_areas = payload.get("minimumAreas", SCAN_DEFAULT_AREAS)
|
if not isinstance(raw_thresholds, list) or not raw_thresholds or len(raw_thresholds) > SCAN_MAX_THRESHOLDS:
|
raise ApiError(f"Parameter scan thresholds must contain 1-{SCAN_MAX_THRESHOLDS} values.")
|
if not isinstance(raw_areas, list) or not raw_areas or len(raw_areas) > SCAN_MAX_AREAS:
|
raise ApiError(f"Parameter scan minimum areas must contain 1-{SCAN_MAX_AREAS} values.")
|
thresholds: list[float] = []
|
for value in raw_thresholds:
|
if isinstance(value, bool) or not isinstance(value, (int, float)):
|
raise ApiError("Each scan threshold must be a number between 0.01 and 0.99.")
|
number = round(float(value), 4)
|
if not CHANGE_THRESHOLD_MIN <= number <= CHANGE_THRESHOLD_MAX:
|
raise ApiError("Each scan threshold must be between 0.01 and 0.99.")
|
if number not in thresholds:
|
thresholds.append(number)
|
areas: list[int] = []
|
for value in raw_areas:
|
if isinstance(value, bool) or not isinstance(value, int) or not 16 <= value <= 200000:
|
raise ApiError("Each scan minimum area must be an integer between 16 and 200000 pixels.")
|
if value not in areas:
|
areas.append(value)
|
if len(thresholds) * len(areas) > SCAN_MAX_COMBINATIONS:
|
raise ApiError(f"A parameter scan accepts at most {SCAN_MAX_COMBINATIONS} combinations.")
|
return thresholds, areas
|
|
def _scan_root(self, scan_id: str) -> Path:
|
if not SAFE_SCAN_ID.fullmatch(scan_id):
|
raise ApiError("Invalid parameter-scan id.")
|
scan_root = self.root / "shared" / "outputs" / "00-change-detection" / "parameter-scans" / scan_id
|
if not scan_root.is_dir() or not (scan_root / "scan_summary.json").is_file():
|
raise ApiError("The parameter-scan result is unavailable.")
|
return scan_root
|
|
def promote_change_scan(self, scan_id: str, payload: dict[str, Any]) -> dict[str, Any]:
|
scan_root = self._scan_root(scan_id)
|
result_id = payload.get("resultId")
|
if not isinstance(result_id, str) or not SAFE_SCAN_RESULT_ID.fullmatch(result_id):
|
raise ApiError("A valid parameter-scan resultId is required.")
|
result_dir = scan_root / result_id
|
summary = load_json(result_dir / "summary.json")
|
full_result = load_json(result_dir / "full_result.json")
|
inference_run_id = str(load_json(scan_root / "scan_summary.json").get("source_run") or "")
|
inference_output = self.root / "shared" / "outputs" / "00-change-detection" / "runs" / inference_run_id
|
inference_metadata = load_json(inference_output / "run_metadata.json")
|
if not result_dir.is_dir() or not (result_dir / "changes.geojson").is_file() or not inference_metadata:
|
raise ApiError("The selected scan result is incomplete and cannot be promoted.")
|
run_id = make_run_id("change")
|
output = self.root / "shared" / "outputs" / "00-change-detection" / "runs" / run_id
|
output.mkdir(parents=True, exist_ok=False)
|
for source_name, destination_name in (
|
("change_probability.tif", "change_probability.tif"),
|
("change_mask.tif", "change_mask.tif"),
|
("changes.geojson", "changes.geojson"),
|
("changes_rectangles.geojson", "changes_rectangles.geojson"),
|
("changes_rectangles_wgs84.geojson", "changes_rectangles_wgs84.geojson"),
|
):
|
source = result_dir / source_name if source_name.startswith("change_mask") or source_name.startswith("changes") else inference_output / source_name
|
if source.is_file():
|
shutil.copyfile(source, output / destination_name)
|
overlay_source = result_dir / "overlay_preview.jpg"
|
if not overlay_source.is_file():
|
raise ApiError("The selected scan preview is unavailable.")
|
shutil.copyfile(overlay_source, output / "change_overlay.jpg")
|
metadata = dict(inference_metadata)
|
scan_raw_root = self.root / "shared" / "data" / "raw" / "00-change-detection" / "runs" / scan_id
|
before_raw = scan_raw_root / "before" / str(inference_metadata.get("input_files", ["before.tif", "after.tif"])[0])
|
after_raw = scan_raw_root / "after" / str(inference_metadata.get("input_files", ["before.tif", "after.tif"])[1])
|
rectangle_count = int(full_result.get("rectangle_vector_feature_count") or 0)
|
if rectangle_count == 0 and (result_dir / "changes_rectangles.geojson").is_file():
|
rectangle_count = len(load_json(result_dir / "changes_rectangles.geojson").get("features", []))
|
metadata.update(
|
{
|
"kind": "formal-change-run",
|
"created_at": datetime.now(UTC).isoformat(),
|
"thresholds": {"change_probability": float(summary.get("threshold", 0.5)), "minimum_component_pixels": int(summary.get("minimum_area_pixels", 16))},
|
"raw_changed_pixels": int(summary.get("raw_changed_pixels", 0)),
|
"changed_pixels": int(summary.get("changed_pixels", 0)),
|
"changed_pixel_ratio": float(summary.get("changed_pixel_ratio", 0)),
|
"vector_feature_count": int(full_result.get("full_vector_feature_count", summary.get("vector_feature_count", 0))),
|
"rectangle_feature_count": rectangle_count,
|
"promoted_from_scan": scan_id,
|
"promoted_result": result_id,
|
"raw_input_dir": relative_path(self.root, scan_raw_root),
|
"raw_before": relative_path(self.root, before_raw),
|
"raw_after": relative_path(self.root, after_raw),
|
"artifacts": {
|
"probability_raster": "change_probability.tif",
|
"raw_mask_raster": "change_mask.tif",
|
"mask_raster": "change_mask.tif",
|
"overlay": "change_overlay.jpg",
|
"vector": "changes.geojson",
|
"rectangle_vector": "changes_rectangles.geojson",
|
"rectangle_vector_wgs84": "changes_rectangles_wgs84.geojson" if (output / "changes_rectangles_wgs84.geojson").is_file() else None,
|
"features": "full_result.json",
|
},
|
}
|
)
|
(output / "full_result.json").write_text(json.dumps(full_result, ensure_ascii=False, indent=2), encoding="utf-8")
|
(output / "run_metadata.json").write_text(json.dumps(metadata, ensure_ascii=False, indent=2), encoding="utf-8")
|
return next(item for item in change_runs(self.root) if item["id"] == run_id)
|
|
def create_change_scan(self, payload: dict[str, Any]) -> dict[str, Any]:
|
uploads = payload.get("uploads")
|
if not isinstance(uploads, dict):
|
raise ApiError("Parameter scan must contain staged before and after uploads.")
|
staged = {
|
"before": self.resolve_change_upload(uploads.get("before"), "before"),
|
"after": self.resolve_change_upload(uploads.get("after"), "after"),
|
}
|
thresholds, areas = self._scan_parameters(payload)
|
processing_mode = payload.get("processingMode", CHANGE_PROCESSING_MODE_DEFAULT)
|
if not isinstance(processing_mode, str) or processing_mode not in CHANGE_PROCESSING_MODES:
|
raise ApiError("Change-detection processing mode must be auto, image, or geotiff.")
|
max_dimension_value = payload.get("maxDimension", CHANGE_MAX_DIMENSION_AUTO)
|
if isinstance(max_dimension_value, bool) or not isinstance(max_dimension_value, int):
|
raise ApiError("Change-detection resolution must be an integer: 0 or between 512 and 4096.")
|
max_dimension = int(max_dimension_value)
|
if max_dimension != CHANGE_MAX_DIMENSION_AUTO and not CHANGE_MAX_DIMENSION_MIN <= max_dimension <= CHANGE_MAX_DIMENSION_MAX:
|
raise ApiError("Change-detection resolution must be 0 or between 512 and 4096.")
|
run_id = make_run_id("scan")
|
raw_root = self.root / "shared" / "data" / "raw" / "00-change-detection" / "runs" / run_id
|
before_path = raw_root / "before" / staged["before"][0]
|
after_path = raw_root / "after" / staged["after"][0]
|
before_path.parent.mkdir(parents=True, exist_ok=False)
|
after_path.parent.mkdir(parents=True, exist_ok=False)
|
shutil.copyfile(staged["before"][1], before_path)
|
shutil.copyfile(staged["after"][1], after_path)
|
processed_root = self.root / "shared" / "data" / "processed" / "00-change-detection" / run_id
|
inference_output = self.root / "shared" / "outputs" / "00-change-detection" / "runs" / run_id
|
scan_output = self.root / "shared" / "outputs" / "00-change-detection" / "parameter-scans" / run_id
|
with SCAN_JOBS_LOCK:
|
SCAN_JOBS[run_id] = {
|
"id": run_id,
|
"status": "queued",
|
"createdAt": datetime.now(UTC).isoformat(),
|
"thresholds": thresholds,
|
"minimumAreas": areas,
|
"processingMode": processing_mode,
|
"maxDimension": max_dimension,
|
}
|
thread = threading.Thread(
|
target=self._run_change_scan,
|
args=(run_id, before_path, after_path, processed_root, inference_output, scan_output, thresholds, areas, processing_mode, max_dimension),
|
daemon=True,
|
name=f"change-scan-{run_id}",
|
)
|
thread.start()
|
return dict(SCAN_JOBS[run_id])
|
|
def _update_scan_job(self, job_id: str, **values: Any) -> None:
|
with SCAN_JOBS_LOCK:
|
if job_id in SCAN_JOBS:
|
SCAN_JOBS[job_id].update(values)
|
|
def _run_change_scan(
|
self,
|
run_id: str,
|
before_path: Path,
|
after_path: Path,
|
processed_root: Path,
|
inference_output: Path,
|
scan_output: Path,
|
thresholds: list[float],
|
areas: list[int],
|
processing_mode: str,
|
max_dimension: int,
|
) -> None:
|
python = self.root / ".venvs" / "00-change-detection" / "Scripts" / "python.exe"
|
try:
|
if not python.is_file():
|
raise ApiError("Change-detection virtual environment is unavailable. Run the capability setup first.")
|
self._update_scan_job(run_id, status="running", phase="inference")
|
with RUN_LOCK:
|
self.run_command(
|
[
|
str(python),
|
str(self.root / "capabilities" / "00-change-detection" / "run_change_detection.py"),
|
"--before", str(before_path),
|
"--after", str(after_path),
|
"--threshold", "0.5000",
|
"--max-dimension", str(max_dimension),
|
"--processing-mode", processing_mode,
|
"--processed-output", str(processed_root),
|
"--output", str(inference_output),
|
],
|
SCAN_JOB_TIMEOUT,
|
)
|
inference_metadata_path = inference_output / "run_metadata.json"
|
inference_metadata = load_json(inference_metadata_path)
|
inference_metadata["kind"] = "parameter-scan-inference"
|
inference_metadata["scan_job_id"] = run_id
|
inference_metadata_path.write_text(json.dumps(inference_metadata, ensure_ascii=False, indent=2), encoding="utf-8")
|
self._update_scan_job(run_id, phase="parameter-scan")
|
command = [
|
str(python),
|
str(self.root / "capabilities" / "00-change-detection" / "scan_change_detection_parameters.py"),
|
"--run-dir", str(inference_output),
|
"--output", str(scan_output),
|
]
|
for threshold in thresholds:
|
command.extend(["--threshold", f"{threshold:.4f}"])
|
for area in areas:
|
command.extend(["--minimum-area", str(area)])
|
self.run_command(command, SCAN_JOB_TIMEOUT)
|
self._update_scan_job(run_id, phase="vectorization")
|
vector_command = [
|
str(python),
|
str(self.root / "capabilities" / "00-change-detection" / "materialize_parameter_scan_candidates.py"),
|
"--scan-dir", str(scan_output),
|
]
|
for threshold in thresholds:
|
for area in areas:
|
vector_command.extend(["--candidate", f"threshold-{threshold:.2f}_area-{area}"])
|
self.run_command(vector_command, SCAN_JOB_TIMEOUT)
|
metadata = {
|
"capability": "00-change-detection",
|
"kind": "parameter-scan",
|
"source_run": run_id,
|
"created_at": datetime.now(UTC).isoformat(),
|
"thresholds": thresholds,
|
"minimum_areas": areas,
|
"processing_mode": processing_mode,
|
"max_dimension": max_dimension,
|
"raw_input_dir": relative_path(self.root, before_path.parent.parent),
|
"processed_input_dir": relative_path(self.root, processed_root),
|
}
|
scan_output.mkdir(parents=True, exist_ok=True)
|
(scan_output / "scan_metadata.json").write_text(json.dumps(metadata, ensure_ascii=False, indent=2), encoding="utf-8")
|
self._update_scan_job(run_id, status="completed", phase="done", scanId=run_id)
|
except Exception as exc: # background errors are returned through polling
|
scan_output.mkdir(parents=True, exist_ok=True)
|
(scan_output / "scan_failed.json").write_text(json.dumps({"job_id": run_id, "error": str(exc)[:600]}, ensure_ascii=False, indent=2), encoding="utf-8")
|
self._update_scan_job(run_id, status="failed", phase="error", error=str(exc)[:600])
|
|
def create_semantic_run(self, payload: dict[str, Any]) -> dict[str, Any]:
|
task_id = str(payload.get("taskId") or "color_baseline")
|
task = next((item for item in semantic_tasks(self.root) if item["id"] == task_id), None)
|
if task is None:
|
raise ApiError(f"Unknown semantic-mapping task: {task_id}.")
|
if task.get("selectable") is not True:
|
raise ApiError(f"Semantic-mapping task is not runnable yet: {task_id}.")
|
uploads = payload.get("images")
|
if not isinstance(uploads, list) or not uploads:
|
raise ApiError("Semantic-mapping request must include at least one image.")
|
if len(uploads) > MAX_SEGMENTATION_IMAGES_PER_RUN:
|
raise ApiError(f"A semantic-mapping run accepts at most {MAX_SEGMENTATION_IMAGES_PER_RUN} images.")
|
decoded = [decode_upload(item, {".jpg", ".jpeg", ".png", ".tif", ".tiff"}) for item in uploads]
|
if len({name.casefold() for name, _ in decoded}) != len(decoded):
|
raise ApiError("Uploaded image names must be unique within one run.")
|
run_id = make_run_id("semantic")
|
raw_root = self.root / "shared" / "data" / "raw" / "02-semantic-mapping" / "runs" / run_id
|
processed_root = self.root / "shared" / "data" / "processed" / "02-semantic-mapping" / run_id
|
raw_root.mkdir(parents=True, exist_ok=False)
|
processed_root.mkdir(parents=True, exist_ok=False)
|
for name, content in decoded:
|
(raw_root / name).write_bytes(content)
|
(processed_root / name).write_bytes(content)
|
output = self.root / "shared" / "outputs" / "02-semantic-mapping" / "runs" / run_id
|
python = self.root / ".venvs" / "02-semantic-mapping" / "Scripts" / "python.exe"
|
if not python.is_file():
|
raise ApiError("Semantic-mapping virtual environment is unavailable. Run the capability setup first.")
|
with RUN_LOCK:
|
self.run_command([str(python), str(self.root / "capabilities" / "02-semantic-mapping" / "run_semantic_segmentation.py"), "--input", str(processed_root), "--output", str(output)], 900)
|
metadata_path = output / "run_metadata.json"
|
if not metadata_path.is_file():
|
raise ApiError("Semantic-mapping script finished without the expected result metadata.")
|
metadata = load_json(metadata_path)
|
metadata["task_id"] = task_id
|
metadata["task_name"] = str(task.get("name") or task_id)
|
metadata["input_dir"] = relative_path(self.root, processed_root)
|
metadata["raw_input_dir"] = relative_path(self.root, raw_root)
|
metadata_path.write_text(json.dumps(metadata, ensure_ascii=False, indent=2), encoding="utf-8")
|
return next(item for item in semantic_runs(self.root) if item["id"] == run_id)
|
|
def create_anomaly_run(self, payload: dict[str, Any]) -> dict[str, Any]:
|
tile_size, stride, threshold_quantile, random_state = validate_anomaly_parameters(payload)
|
uploads = payload.get("uploads")
|
if not isinstance(uploads, dict):
|
raise ApiError("Anomaly-detection request must contain reference and input uploads.")
|
reference_values = uploads.get("reference")
|
input_values = uploads.get("input")
|
if not isinstance(reference_values, list) or not reference_values:
|
raise ApiError("Select at least one normal reference image.")
|
if not isinstance(input_values, list) or not input_values:
|
raise ApiError("Select at least one image to inspect.")
|
if len(reference_values) > MAX_ANOMALY_IMAGES_PER_ROLE or len(input_values) > MAX_ANOMALY_IMAGES_PER_ROLE:
|
raise ApiError(f"An anomaly-detection run accepts at most {MAX_ANOMALY_IMAGES_PER_ROLE} images in each group.")
|
references = [self.resolve_anomaly_upload(value, "reference") for value in reference_values]
|
inputs = [self.resolve_anomaly_upload(value, "input") for value in input_values]
|
if len({name.casefold() for name, _, _ in references}) != len(references):
|
raise ApiError("Normal reference image names must be unique within one run.")
|
if len({name.casefold() for name, _, _ in inputs}) != len(inputs):
|
raise ApiError("Input image names must be unique within one run.")
|
|
python = self.root / ".venvs" / "09-anomaly-detection" / "Scripts" / "python.exe"
|
if not python.is_file():
|
raise ApiError("Anomaly-detection virtual environment is unavailable. Run the capability setup first.")
|
run_id = make_run_id("anomaly")
|
job_id = uuid4().hex
|
raw_root = self.root / "shared" / "data" / "raw" / "09-anomaly-detection" / "runs" / run_id
|
raw_reference = raw_root / "reference"
|
raw_input = raw_root / "input"
|
processed_root = self.root / "shared" / "data" / "processed" / "09-anomaly-detection" / run_id
|
processed_reference = processed_root / "reference"
|
processed_input = processed_root / "input"
|
output = self.root / "shared" / "outputs" / "09-anomaly-detection" / "runs" / run_id
|
for directory in (raw_reference, raw_input, processed_reference, processed_input):
|
directory.mkdir(parents=True, exist_ok=False)
|
for group, raw_dir, processed_dir in ((references, raw_reference, processed_reference), (inputs, raw_input, processed_input)):
|
for name, staged_path, expected_sha256 in group:
|
raw_path = raw_dir / name
|
processed_path = processed_dir / name
|
shutil.copyfile(staged_path, raw_path)
|
if expected_sha256 and file_sha256(raw_path) != expected_sha256:
|
raise ApiError(f"Uploaded file checksum changed while staging: {name}.")
|
shutil.copyfile(raw_path, processed_path)
|
for _, staged_path, _ in references + inputs:
|
shutil.rmtree(staged_path.parent)
|
|
created_at = datetime.now(UTC).isoformat()
|
job = {"id": job_id, "runId": run_id, "status": "queued", "createdAt": created_at}
|
with ANOMALY_JOB_LOCK:
|
ANOMALY_JOBS[job_id] = job
|
thread = threading.Thread(
|
target=execute_anomaly_job,
|
args=(self.root, job_id, run_id, raw_reference, raw_input, processed_reference, processed_input, output, tile_size, stride, threshold_quantile, random_state),
|
daemon=True,
|
name=f"anomaly-{run_id}",
|
)
|
thread.start()
|
return dict(job)
|
|
def create_measurement_run(self, payload: dict[str, Any]) -> dict[str, Any]:
|
uploads = payload.get("rasters")
|
if not isinstance(uploads, list) or not uploads:
|
raise ApiError("Spatial-measurement request must include at least one label raster.")
|
if len(uploads) > MAX_MEASUREMENT_RASTERS_PER_RUN:
|
raise ApiError(f"A spatial-measurement run accepts at most {MAX_MEASUREMENT_RASTERS_PER_RUN} rasters.")
|
decoded = [decode_upload(item, {".png", ".tif", ".tiff"}) for item in uploads]
|
if len({name.casefold() for name, _ in decoded}) != len(decoded):
|
raise ApiError("Uploaded raster names must be unique within one run.")
|
run_id = make_run_id("measurement")
|
raw_root = self.root / "shared" / "data" / "raw" / "04-spatial-measurement" / "runs" / run_id
|
processed_root = self.root / "shared" / "data" / "processed" / "04-spatial-measurement" / run_id
|
raw_root.mkdir(parents=True, exist_ok=False)
|
processed_root.mkdir(parents=True, exist_ok=False)
|
for name, content in decoded:
|
(raw_root / name).write_bytes(content)
|
(processed_root / name).write_bytes(content)
|
output = self.root / "shared" / "outputs" / "04-spatial-measurement" / "runs" / run_id
|
python = self.root / ".venvs" / "04-spatial-measurement" / "Scripts" / "python.exe"
|
if not python.is_file():
|
raise ApiError("Spatial-measurement virtual environment is unavailable. Run the capability setup first.")
|
with RUN_LOCK:
|
self.run_command([str(python), str(self.root / "capabilities" / "04-spatial-measurement" / "run_spatial_measurement.py"), "--input", str(processed_root), "--output", str(output)], 900)
|
metadata_path = output / "run_metadata.json"
|
if not metadata_path.is_file():
|
raise ApiError("Spatial-measurement script finished without the expected result metadata.")
|
metadata = load_json(metadata_path)
|
metadata["input_dir"] = relative_path(self.root, processed_root)
|
metadata["raw_input_dir"] = relative_path(self.root, raw_root)
|
metadata_path.write_text(json.dumps(metadata, ensure_ascii=False, indent=2), encoding="utf-8")
|
return next(item for item in measurement_runs(self.root) if item["id"] == run_id)
|
|
def send_json(self, status: HTTPStatus, payload: dict[str, Any]) -> None:
|
body = json.dumps(payload, ensure_ascii=False).encode("utf-8")
|
self.send_response(status)
|
self.send_header("Content-Type", "application/json; charset=utf-8")
|
self.send_header("Content-Length", str(len(body)))
|
self.end_headers()
|
self.wfile.write(body)
|
|
def translate_path(self, path: str) -> str:
|
"""Expose only the static UI and artifacts required by the local console."""
|
decoded_path = unquote(urlsplit(path).path).lstrip("/")
|
requested = PurePosixPath(decoded_path)
|
is_allowed = any(decoded_path == prefix or decoded_path.startswith(f"{prefix}/") for prefix in ALLOWED_PATH_PREFIXES)
|
if ".." in requested.parts or not is_allowed:
|
return os.fspath(Path(self.directory) / ".console-forbidden")
|
if decoded_path == "apps/workbench-console" or decoded_path.startswith("apps/workbench-console/"):
|
console_relative = requested.parts[2:]
|
return os.fspath(Path(self.directory) / "apps" / "workbench-console" / "dist" / Path(*console_relative))
|
return os.fspath(Path(self.directory).joinpath(*requested.parts))
|
|
def end_headers(self) -> None:
|
self.send_header("Cache-Control", "no-store")
|
self.send_header("X-Content-Type-Options", "nosniff")
|
super().end_headers()
|
|
|
def parse_args() -> argparse.Namespace:
|
root = Path(__file__).resolve().parents[1]
|
parser = argparse.ArgumentParser(description="Serve the local GeoAI Workbench console.")
|
parser.add_argument("--host", default=DEFAULT_HOST, help="Bind address. Defaults to loopback only.")
|
parser.add_argument("--port", type=int, default=DEFAULT_PORT, help="TCP port in the 6000-6999 range.")
|
parser.add_argument("--root", type=Path, default=root, help="Workbench repository root to serve.")
|
return parser.parse_args()
|
|
|
def main() -> int:
|
args = parse_args()
|
if not 6000 <= args.port <= 6999:
|
raise SystemExit("Port must be in the 6000-6999 range.")
|
if args.host not in {"127.0.0.1", "localhost", "::1"}:
|
raise SystemExit("This console is local-only. Use 127.0.0.1, localhost, or ::1.")
|
root = args.root.resolve()
|
app_dir = root / "apps" / "workbench-console"
|
if not (root / "shared").is_dir() or not (app_dir / "dist" / "index.html").is_file():
|
raise SystemExit(f"Not a GeoAI Workbench root: {root}")
|
handler = lambda *handler_args, **handler_kwargs: WorkbenchConsoleHandler(*handler_args, directory=os.fspath(root), **handler_kwargs) # noqa: E731
|
server = ThreadingHTTPServer((args.host, args.port), handler)
|
print(f"GeoAI Workbench console: http://{args.host}:{args.port}")
|
print("Local runs use fixed capability scripts and create a new run directory.")
|
try:
|
server.serve_forever()
|
except KeyboardInterrupt:
|
print("\nConsole stopped.")
|
finally:
|
server.server_close()
|
return 0
|
|
|
if __name__ == "__main__":
|
raise SystemExit(main())
|
