feat: add pcf analysis web app and api

2026-06-30 14:29:02 +08:00
commit e600a73e48
44 changed files with 12412 additions and 0 deletions
@@ -0,0 +1,115 @@
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any
+
+
+@dataclass
+class PcfBlock:
+    """PCF 中的一个顶层段。"""
+
+    block_type: str
+    value: str = ""
+    fields: dict[str, list[str]] = field(default_factory=dict)
+    line_no: int = 0
+
+    def first(self, key: str, default: str = "") -> str:
+        values = self.fields.get(key, [])
+        return values[0] if values else default
+
+
+@dataclass
+class WeldRecord:
+    """内部标准焊口记录。"""
+
+    source_file: str
+    pipeline_reference: str = ""
+    piping_spec: str = ""
+    line_no: str = ""
+    weld_no: str = ""
+    diameter: str = ""
+    outside_diameter: str = ""
+    wall_thickness: str = ""
+    spec: str = ""
+    weld_area_raw: str = ""
+    weld_area: str = ""
+    contractor_raw: str = ""
+    component_identifier: str = ""
+    master_component_identifier: str = ""
+    skey: str = ""
+    uci: str = ""
+    material_1: str = ""
+    material_2: str = ""
+    issues: list[str] = field(default_factory=list)
+    raw_fields: dict[str, list[str]] = field(default_factory=dict)
+
+    def set_if_empty(self, field_name: str, value: str) -> None:
+        if hasattr(self, field_name) and not getattr(self, field_name) and value:
+            setattr(self, field_name, value)
+
+
+@dataclass
+class UnknownFieldCandidate:
+    """等待 DeepSeek 识别的非标准字段候选。"""
+
+    source_field: str
+    section: str
+    sample_values: list[str]
+    context: str
+
+
+@dataclass
+class MappingDecision:
+    """DeepSeek 字段映射结果。"""
+
+    source_field: str
+    target_field: str
+    confidence: float
+    reason: str = ""
+    sample_values: list[str] = field(default_factory=list)
+
+    @property
+    def is_usable(self) -> bool:
+        return bool(self.source_field and self.target_field and self.confidence >= 0)
+
+
+@dataclass
+class JobResult:
+    job_id: str
+    input_files: int
+    weld_count: int
+    warning_count: int
+    error_count: int
+    output_xls: Path
+    issues_csv: Path
+    report_json: Path
+    messages: list[str] = field(default_factory=list)
+    llm_enabled: bool = False
+    llm_mappings: list[MappingDecision] = field(default_factory=list)
+    import_headers: list[str] = field(default_factory=list)
+    import_columns: list[dict[str, str]] = field(default_factory=list)
+    import_rows: list[dict[str, str]] = field(default_factory=list)
+    issue_rows: list[dict[str, str]] = field(default_factory=list)
+
+    def to_public_dict(self) -> dict[str, Any]:
+        return {
+            "job_id": self.job_id,
+            "input_files": self.input_files,
+            "weld_count": self.weld_count,
+            "warning_count": self.warning_count,
+            "error_count": self.error_count,
+            "messages": self.messages,
+            "llm_enabled": self.llm_enabled,
+            "tables": {
+                "import_headers": self.import_headers,
+                "import_columns": self.import_columns,
+                "import_rows": self.import_rows,
+                "issue_rows": self.issue_rows,
+            },
+            "downloads": {
+                "xls": f"/api/jobs/{self.job_id}/download/xls",
+                "issues": f"/api/jobs/{self.job_id}/download/issues",
+                "report": f"/api/jobs/{self.job_id}/download/report",
+            },
+        }