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

review_agent/regulatory_info_package/services/docx_document.py

@@ -0,0 +1,70 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from docx import Document
+from docx.enum.text import WD_COLOR_INDEX
+from docx.shared import RGBColor
+
+from review_agent.regulatory_info_package.schemas import MergedField
+
+
+def write_docx_from_template(
+    source_path: str | Path,
+    output_path: str | Path,
+    merged_fields: dict[str, MergedField],
+) -> tuple[int, int, int]:
+    source = Path(source_path)
+    output = Path(output_path)
+    output.parent.mkdir(parents=True, exist_ok=True)
+    if source.exists():
+        document = Document(source)
+    else:
+        document = Document()
+    replacements = {f"{{{{{key}}}}}": field for key, field in merged_fields.items()}
+    highlight_count = 0
+    missing_count = 0
+    llm_only_count = 0
+    for paragraph in document.paragraphs:
+        for placeholder, field in replacements.items():
+            if placeholder in paragraph.text:
+                _replace_paragraph_text(paragraph, paragraph.text.replace(placeholder, field.value), field)
+                if field.highlight_reason != "none":
+                    highlight_count += 1
+                if field.highlight_reason == "missing":
+                    missing_count += 1
+                if field.highlight_reason == "llm_only":
+                    llm_only_count += 1
+    document.add_page_break()
+    heading = document.add_paragraph()
+    heading_run = heading.add_run("预生成字段")
+    heading_run.bold = True
+    table = document.add_table(rows=1, cols=4)
+    table.rows[0].cells[0].text = "字段"
+    table.rows[0].cells[1].text = "值"
+    table.rows[0].cells[2].text = "来源"
+    table.rows[0].cells[3].text = "待确认"
+    for field in merged_fields.values():
+        cells = table.add_row().cells
+        cells[0].text = field.label
+        cells[1].text = field.value
+        cells[2].text = field.source
+        cells[3].text = "是" if field.needs_review else "否"
+        if field.highlight_reason != "none":
+            highlight_count += 1
+        if field.highlight_reason == "missing":
+            missing_count += 1
+        if field.highlight_reason == "llm_only":
+            llm_only_count += 1
+    document.save(output)
+    return highlight_count, missing_count, llm_only_count
+
+
+def _replace_paragraph_text(paragraph, text: str, field: MergedField) -> None:
+    for run in paragraph.runs:
+        run.text = ""
+    run = paragraph.add_run(text)
+    if field.highlight_reason != "none":
+        run.font.highlight_color = WD_COLOR_INDEX.YELLOW
+    if field.highlight_reason == "conflict":
+        run.font.color.rgb = RGBColor(255, 0, 0)