#!/usr/bin/env python # -*- coding: utf-8 -*- """ 工作空间管理器 负责工作目录文件扫描、步骤输出路径发现、配置裁剪等业务逻辑， 与 GUI 组件解耦，不直接引用任何 UI 类。 """ import copy from pathlib import Path from src.gui.core.event_bus import global_event_bus class WorkspaceManager: """管理步骤默认输出路径、文件扫描与配置裁剪""" # 白名单：科学数据格式后缀 SCIENTIFIC_EXTENSIONS = {'.dat', '.tif', '.tiff', '.shp'} # 临时文件关键词黑名单 TMP_KEYWORDS = ('__tmp', '_tmp') # 掩膜类型集合 MASK_TYPES = {'water_mask', 'glint_mask', 'boundary_mask'} def __init__(self): self.step_default_outputs = { 'step1': {'water_mask': [ "1_water_mask/water_mask_out.dat", "1_water_mask/water_mask_from_ndwi.dat", "1_water_mask/water_mask_from_shp.dat", ]}, 'step2': {'glint_mask': "2_Glint_Detection/severe_glint_area.dat"}, 'step3': {'deglint_image': [ "3_deglint/deglint_image.bsq", "3_deglint/deglint_goodman.bsq", ]}, 'step4_sampling': {'sampling_points': "4_sampling/sampling_spectra.csv"}, 'step5_clean': {'processed_data': "5_Data_Cleaning/processed_data.csv"}, 'step6_feature': {'training_spectra': "6_Spectral_Feature_Extraction/training_spectra.csv"}, 'step7_index': {'training_spectra_indices': "7_Water_Quality_Indices/training_spectra_indices.csv"}, 'step8_ml_train': {'Supervised_Model_Training': "8_Supervised_Model_Training/"}, 'step9_ml_predict': {'9_ML_Prediction': "9_ML_Prediction/"}, 'step10_watercolor': {'WaterIndex_CSV': "10_WaterIndex_CSV/"}, 'step11_map': {'11_Thematic_Map': "11_Thematic_Map/"}, } self.step_outputs = {} # ★ 2026-07-01：切换工作目录时清空缓存，防止旧目录的 OutputUpdated 重放 def clear_all_outputs(self): """清空所有缓存的步骤输出路径。工作目录切换时调用。""" self.step_outputs.clear() def _publish_outputs(self, step_id: str, outputs: dict): """将发现的产出发布到 EventBus。 Args: step_id: 面板 step_id（如 'step1', 'step5_clean'） outputs: {output_type: path_str} """ for output_type, path in outputs.items(): if path: global_event_bus.publish('OutputUpdated', { 'step_id': step_id, 'output_type': output_type, 'path': path, }) @staticmethod def _is_scientific_mask(path_str): """白名单判断：只有 .dat .tif .tiff .shp 才算科学数据格式""" p = Path(path_str) name_lower = str(path_str).lower() if any(kw in name_lower for kw in WorkspaceManager.TMP_KEYWORDS): return False return p.suffix.lower() in WorkspaceManager.SCIENTIFIC_EXTENSIONS def find_step_output(self, work_path, step_id, output_type, ref_img_path=None): """查找指定步骤的输出文件 Args: work_path: 工作目录 Path 对象 step_id: 步骤 ID output_type: 输出类型（如 'water_mask', 'deglint_image' 等） ref_img_path: 参考影像路径（仅 output_type='reference_img' 时需要） Returns: 找到的文件路径字符串，或 None """ if step_id not in self.step_default_outputs: return None raw = self.step_default_outputs[step_id] rel_path = None if isinstance(raw, str): rel_path = raw elif isinstance(raw, dict): rel_path = raw.get(output_type) or list(raw.values())[0] if not rel_path: return None # 特殊处理：从 step_outputs 记录中查找实际输出路径 if step_id in self.step_outputs: actual_outputs = self.step_outputs[step_id] if output_type in actual_outputs: candidate = actual_outputs[output_type] if output_type in self.MASK_TYPES and not self._is_scientific_mask(candidate): pass else: return candidate if output_type == 'water_mask': if isinstance(rel_path, list): for candidate in rel_path: mask_path = work_path / candidate if mask_path.exists(): return str(mask_path) elif rel_path: mask_path = work_path / rel_path if mask_path.exists(): return str(mask_path) elif output_type == 'reference_img': if ref_img_path and Path(ref_img_path).exists(): return ref_img_path elif output_type == 'deglint_image': if isinstance(rel_path, list): for candidate in rel_path: deglint_path = work_path / candidate if deglint_path.exists(): return str(deglint_path) elif rel_path: deglint_path = work_path / rel_path if deglint_path.exists(): return str(deglint_path) deglint_dir = work_path / "3_deglint" if deglint_dir.exists(): for file_path in deglint_dir.glob("deglint_*.bsq"): return str(file_path) for file_path in deglint_dir.glob("interpolated_*.bsq"): return str(file_path) elif isinstance(rel_path, str): if rel_path.endswith('/'): output_path = work_path / rel_path.rstrip('/') if output_path.exists() and output_path.is_dir(): return str(output_path) else: output_path = work_path / rel_path if output_path.exists(): return str(output_path) return None def scan_work_directory_for_files(self, work_path): """扫描工作目录，自动发现各步骤的输出文件 Returns: discovered_outputs: dict, {step_id: {output_type: path_str}} """ discovered_outputs = {} subdirs = { '1_water_mask': 'step1', '2_Glint_Detection': 'step2', '3_deglint': 'step3', '4_sampling': 'step4_sampling', '5_Data_Cleaning': 'step5_clean', '6_Spectral_Feature_Extraction': 'step6_feature', '7_Water_Quality_Indices': 'step7_index', '8_Supervised_Model_Training': 'step8_ml_train', '9_ML_Prediction': 'step9_ml_predict', '10_WaterIndex_CSV': 'step10_watercolor', '11_Thematic_Map': 'step11_map', '12_visualization': ['step12_viz', 'step13_report'], } for subdir, step_ids in subdirs.items(): subdir_path = work_path / subdir if not subdir_path.exists(): continue if isinstance(step_ids, str): step_ids = [step_ids] for file_path in subdir_path.rglob('*'): if file_path.is_file(): file_name = file_path.name.lower() file_stem = file_path.stem.lower() for step_id in step_ids: if step_id not in discovered_outputs: discovered_outputs[step_id] = {} # 2026-06-30 加强匹配：用更精确的边界匹配替代简单的子串包含 # water_mask 匹配：必须是独立文件名的一部分（如 water_mask_out.dat, water_mask_from_ndwi.dat） if step_id == 'step1' and self._is_scientific_mask(file_path): if ('water_mask' in file_stem and 'glint' not in file_stem): discovered_outputs[step_id]['water_mask'] = str(file_path) # glint_mask 匹配：必须同时含 glint 且文件名主体以 mask 或 area 结尾 elif step_id == 'step2' and self._is_scientific_mask(file_path): if ('glint' in file_stem and (file_stem.endswith('mask') or file_stem.endswith('area') or 'severe_glint' in file_stem)): discovered_outputs[step_id]['glint_mask'] = str(file_path) elif 'deglint' in file_stem and step_id == 'step3': discovered_outputs[step_id]['deglint_image'] = str(file_path) elif file_name == 'processed_data.csv' and step_id == 'step5_clean': discovered_outputs[step_id]['processed_data'] = str(file_path) elif ('training_spectra' in file_stem and file_path.suffix == '.csv' and step_id == 'step6_feature'): discovered_outputs[step_id]['training_spectra'] = str(file_path) elif ('water_quality_indices' in file_stem and file_path.suffix == '.csv' and step_id == 'step7_index'): discovered_outputs[step_id]['water_indices'] = str(file_path) elif file_name == 'sampling_spectra.csv' and step_id == 'step4_sampling': discovered_outputs[step_id]['sampling_points'] = str(file_path) elif file_name.endswith('.csv') and step_id in ['step9_ml_predict', 'step11_map', 'step12_viz']: discovered_outputs[step_id]['predictions'] = str(file_path) for step_id, outputs in discovered_outputs.items(): if step_id not in self.step_outputs: self.step_outputs[step_id] = {} self.step_outputs[step_id].update(outputs) # ★ 发布 EventBus 事件，驱动下游面板自动填充 self._publish_outputs(step_id, outputs) return discovered_outputs def update_step_outputs(self, step_name, work_path): """更新指定步骤的输出路径记录并发布 EventBus 事件。""" if step_name not in self.step_default_outputs: return step_outputs = self.step_default_outputs[step_name] published = {} for output_type, relative_path in step_outputs.items(): if isinstance(relative_path, list): for candidate in relative_path: output_path = work_path / candidate if output_path.exists(): path_str = str(output_path) self.step_outputs.setdefault(step_name, {})[output_type] = path_str published[output_type] = path_str break elif '*' in relative_path: pattern_path = work_path / relative_path.replace('*', '*') matching_files = list(pattern_path.parent.glob(pattern_path.name)) if matching_files: latest_file = max(matching_files, key=lambda p: p.stat().st_mtime) path_str = str(latest_file) self.step_outputs.setdefault(step_name, {})[output_type] = path_str published[output_type] = path_str else: output_path = work_path / relative_path if output_path.exists(): path_str = str(output_path) self.step_outputs.setdefault(step_name, {})[output_type] = path_str published[output_type] = path_str if published: self._publish_outputs(step_name, published) @staticmethod def prune_config_for_prediction_mode(config: dict) -> dict: """Prediction-only 模式：禁用训练相关步骤，保留预测和成图步骤。 2026-06-30 修复：步骤 ID 从旧的 PIPELINE_STEPS 体系改为 PANEL_REGISTRY 体系， 确保与 get_current_config() 返回的 key 一致，避免 enabled: False 写入无效 key。 被禁用的 step dict 中统一写入 'enabled': False， 这些配置最终传给 PipelineRunner，Runner 会跳过它们。 同时，被跳过的步骤的 required_input_files 在 build_missing_items 中不会被检查，从而自然规避了"CSV 缺失"等训练模式下的误报。 Args: config: 完整配置字典（来自 get_current_config，key 为 PANEL_REGISTRY step_id） Returns: 裁剪后的 config（深拷贝，原 config 不被修改） """ cfg = copy.deepcopy(config) training_steps = [ "step4_sampling", "step5_clean", "step6_feature", "step7_index", "step8_ml_train", ] for step_id in training_steps: step_cfg = cfg.setdefault(step_id, {}) step_cfg["enabled"] = False return cfg