feat(regulatory-info-package): 实现材料包生成工作流

2026-06-10 19:49:44 +08:00
parent f0286264e2
commit dac8ce3c14
21 changed files with 1512 additions and 0 deletions
--- a/review_agent/regulatory_info_package/services/package_generate.py
+++ b/review_agent/regulatory_info_package/services/package_generate.py
@@ -0,0 +1,65 @@
+from __future__ import annotations
+
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from pathlib import Path
+
+from review_agent.models import RegulatoryInfoPackageBatch
+from review_agent.regulatory_info_package.constants import GENERATED_FILE_FAILED
+from review_agent.regulatory_info_package.schemas import GeneratedFileResult, MergedField, TemplateSpec
+from review_agent.regulatory_info_package.services.docx_document import write_docx_from_template
+from review_agent.regulatory_info_package.services.legacy_doc_document import write_legacy_doc_or_fallback
+from review_agent.regulatory_info_package.services.template_repository import copy_template_to_batch, template_specs
+from review_agent.regulatory_info_package.storage import ensure_batch_subdir
+
+
+def generate_package_documents(
+    batch: RegulatoryInfoPackageBatch,
+    config: dict,
+    merged_fields: dict[str, MergedField],
+) -> list[GeneratedFileResult]:
+    specs = template_specs(config)
+    with ThreadPoolExecutor(max_workers=min(4, len(specs) or 1)) as executor:
+        futures = [executor.submit(_generate_one, batch, config, spec, merged_fields) for spec in specs]
+        return [future.result() for future in as_completed(futures)]
+
+
+def _generate_one(
+    batch: RegulatoryInfoPackageBatch,
+    config: dict,
+    spec: TemplateSpec,
+    merged_fields: dict[str, MergedField],
+) -> GeneratedFileResult:
+    try:
+        template_path = copy_template_to_batch(batch, config, spec)
+        generated_dir = ensure_batch_subdir(batch, "generated")
+        output_path = generated_dir / spec.output_name
+        adapter_summary = {}
+        if spec.file_format == "doc":
+            actual_path, status, adapter_summary = write_legacy_doc_or_fallback(template_path, output_path, merged_fields)
+            actual_format = actual_path.suffix.lower().lstrip(".")
+            highlight_count = missing_count = llm_only_count = 0
+        else:
+            highlight_count, missing_count, llm_only_count = write_docx_from_template(template_path, output_path, merged_fields)
+            actual_path = output_path
+            actual_format = "docx"
+            status = "success"
+        return GeneratedFileResult(
+            template_code=spec.code,
+            file_name=actual_path.name,
+            requested_format=spec.file_format,
+            actual_format=actual_format,
+            status=status,
+            path=str(actual_path),
+            highlight_count=highlight_count,
+            missing_count=missing_count,
+            llm_only_count=llm_only_count,
+        )
+    except Exception as exc:
+        return GeneratedFileResult(
+            template_code=spec.code,
+            file_name=spec.output_name,
+            requested_format=spec.file_format,
+            actual_format=spec.file_format,
+            status=GENERATED_FILE_FAILED,
+            error_message=str(exc),
+        )