feat(govdoc): 新增内部公文模块全链路（后端58+前端11文件）

2026-05-13 14:37:12 +08:00
parent 99699e20e1
commit 5d777599bf
63 changed files with 7608 additions and 0 deletions
@@ -0,0 +1,105 @@
+"""docx 标注：在原文加高亮 + 文末追加审核报告附页。"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from docx import Document as DocxDocument
+from docx.enum.text import WD_BREAK
+from docx.shared import Pt
+from docx.oxml.ns import qn
+from lxml import etree
+
+from fastapi_modules.fastapi_leaudit.govdoc_engine.engine.result import AuditResult
+
+
+_HIGHLIGHT_NAME = {
+    "error": "red",
+    "warning": "yellow",
+    "info": "cyan",
+}
+
+
+def _highlight_run(run, color_name: str) -> None:
+    rpr = run._element.get_or_add_rPr()
+    hl = rpr.find(qn("w:highlight"))
+    if hl is None:
+        hl = etree.SubElement(rpr, qn("w:highlight"))
+    hl.set(qn("w:val"), color_name)
+
+
+def _highlight_paragraph_range(paragraph, start: int, end: int, color_name: str) -> None:
+    """简化策略：高亮整段（精准 char range 留 v0.2 实现）。"""
+    for run in paragraph.runs:
+        _highlight_run(run, color_name)
+
+
+def _add_heading_with_fallback(doc, text: str, level: int = 1):
+    try:
+        return doc.add_heading(text, level=level)
+    except KeyError:
+        # Some uploaded documents don't include Word's built-in heading styles.
+        p = doc.add_paragraph()
+        run = p.add_run(text)
+        run.bold = True
+        if level == 1:
+            run.font.size = Pt(16)
+        elif level == 2:
+            run.font.size = Pt(13)
+        else:
+            run.font.size = Pt(12)
+        return p
+
+
+def _append_appendix(doc, result: AuditResult) -> None:
+    p = doc.add_paragraph()
+    p.add_run().add_break(WD_BREAK.PAGE)
+    _add_heading_with_fallback(doc, "审核报告附页", level=1)
+
+    s = result.summary
+    doc.add_paragraph(
+        f"得分: {s.score}/100   错误: {s.by_severity.get('error', 0)}   "
+        f"警告: {s.by_severity.get('warning', 0)}   提示: {s.by_severity.get('info', 0)}"
+    )
+
+    if not result.findings:
+        doc.add_paragraph("未发现问题。")
+        return
+
+    table = doc.add_table(rows=1, cols=5)
+    try:
+        table.style = "Light Grid"
+    except KeyError:
+        # Some source documents don't ship with the built-in table style set.
+        pass
+    hdr = table.rows[0].cells
+    for i, h in enumerate(["编号", "规则", "严重度", "类别", "位置 / 说明"]):
+        hdr[i].text = h
+
+    for f in result.findings:
+        row = table.add_row().cells
+        row[0].text = f.finding_id
+        row[1].text = f.rule_id
+        row[2].text = f.severity
+        row[3].text = f.category
+        loc = f.location
+        ctx = (loc.context or "")[:30]
+        row[4].text = f"P{loc.paragraph_index} ({loc.role}): {f.message}\n  原文: {ctx}"
+
+
+def annotate_docx(src: str | Path, dst: str | Path, result: AuditResult) -> None:
+    src = Path(src)
+    dst = Path(dst)
+    doc = DocxDocument(src)
+
+    for f in result.findings:
+        idx = f.location.paragraph_index
+        if 0 <= idx < len(doc.paragraphs):
+            color = _HIGHLIGHT_NAME.get(f.severity, "yellow")
+            _highlight_paragraph_range(
+                doc.paragraphs[idx], f.location.char_start, f.location.char_end, color
+            )
+
+    _append_appendix(doc, result)
+    dst.parent.mkdir(parents=True, exist_ok=True)
+    doc.save(dst)
@@ -0,0 +1,42 @@
+"""把 Document 渲染为带 inline style 的 HTML 段落，给前端用。"""
+
+from __future__ import annotations
+from html import escape
+from fastapi_modules.fastapi_leaudit.govdoc_engine.models import Document
+
+
+def _style(p) -> str:
+    s = p.style
+    parts = []
+    if s.font_size_pt:
+        sz = s.font_size_pt
+        sz_str = str(int(sz)) if sz == int(sz) else str(sz)
+        parts.append(f"font-size:{sz_str}pt")
+    if s.font_eastasia:
+        parts.append(f"font-family:'{s.font_eastasia}',serif")
+    if s.alignment and s.alignment != "left":
+        parts.append(f"text-align:{s.alignment}")
+    if s.bold:
+        parts.append("font-weight:700")
+    if s.first_line_indent_pt:
+        parts.append(f"text-indent:{s.first_line_indent_pt}pt")
+    return ";".join(parts)
+
+
+def paragraphs_to_html(doc: Document, finding_map: dict[int, list[str]]) -> str:
+    """把 doc 每个段落渲染成 <p> 带 data-pi / data-role / data-finding-ids。"""
+    out = ['<div class="doc-view">']
+    for p in doc.paragraphs:
+        style = _style(p)
+        finding_ids = finding_map.get(p.index, [])
+        attrs = [
+            f'data-pi="{p.index}"',
+            f'data-role="{escape(p.role or "")}"',
+        ]
+        if finding_ids:
+            attrs.append(f'data-finding-ids="{escape(",".join(finding_ids))}"')
+        if style:
+            attrs.append(f'style="{escape(style)}"')
+        out.append(f"<p {' '.join(attrs)}>{escape(p.text)}</p>")
+    out.append("</div>")
+    return "\n".join(out)
@@ -0,0 +1,76 @@
+"""把 AuditResult 渲染成单文件 HTML 报告。"""
+
+from __future__ import annotations
+from html import escape
+from fastapi_modules.fastapi_leaudit.govdoc_engine.engine.result import AuditResult
+
+
+_CSS = """
+body { font-family: -apple-system, "PingFang SC", sans-serif; margin: 0; padding: 24px;
+       background: #f7f7f9; color: #1a1a1a; }
+.header { display: flex; align-items: center; gap: 16px; margin-bottom: 24px; }
+.score { width: 96px; height: 96px; border-radius: 50%;
+         background: conic-gradient(#22c55e var(--p), #e5e7eb var(--p));
+         display: grid; place-items: center; font-weight: 700; font-size: 22px; color: #111; }
+.score-inner { background: white; width: 76px; height: 76px; border-radius: 50%;
+               display: grid; place-items: center; }
+.tag { padding: 2px 8px; border-radius: 999px; font-size: 12px; }
+.error { background: #fee2e2; color: #b91c1c; }
+.warning { background: #fef9c3; color: #a16207; }
+.info { background: #dbeafe; color: #1d4ed8; }
+table { width: 100%; border-collapse: collapse; background: white; border-radius: 8px;
+        overflow: hidden; box-shadow: 0 1px 3px rgba(0,0,0,0.06); }
+th, td { padding: 10px 12px; text-align: left; border-bottom: 1px solid #f1f5f9; vertical-align: top; }
+th { background: #f8fafc; font-size: 13px; }
+td.msg { max-width: 480px; }
+.context { color: #64748b; font-size: 12px; margin-top: 4px; }
+"""
+
+
+def render_html(result: AuditResult) -> str:
+    s = result.summary
+    score = s.score
+    pct = f"{score}%"
+    rows = []
+    for f in result.findings:
+        loc = f.location
+        suggest = (
+            f'<div style="color:#0369a1">建议: {escape(f.suggestion)}</div>'
+            if f.suggestion else ""
+        )
+        rows.append(f"""
+<tr>
+  <td>{escape(f.finding_id)}</td>
+  <td>{escape(f.rule_id)}<br><span style="color:#64748b;font-size:12px">{escape(f.rule_name)}</span></td>
+  <td><span class="tag {f.severity}">{f.severity}</span></td>
+  <td>{escape(f.category)}</td>
+  <td>P{loc.paragraph_index} ({escape(loc.role or '')})</td>
+  <td class="msg">{escape(f.message)}
+    <div class="context">原文: {escape((loc.context or '')[:80])}</div>
+    {suggest}
+  </td>
+</tr>""")
+
+    body = f"""<!doctype html>
+<html lang="zh"><head><meta charset="utf-8"><title>公文审核报告</title>
+<style>{_CSS}</style></head><body>
+<div class="header">
+  <div class="score" style="--p:{pct}"><div class="score-inner">{score}</div></div>
+  <div>
+    <h1 style="margin:0">公文格式审核报告</h1>
+    <div style="color:#64748b">{escape(result.document.get('filename', ''))} · 共 {s.total_findings} 项</div>
+    <div style="margin-top:6px">
+      <span class="tag error">错误 {s.by_severity.get('error', 0)}</span>
+      <span class="tag warning">警告 {s.by_severity.get('warning', 0)}</span>
+      <span class="tag info">提示 {s.by_severity.get('info', 0)}</span>
+    </div>
+  </div>
+</div>
+<table>
+  <thead><tr>
+    <th>编号</th><th>规则</th><th>严重度</th><th>类别</th><th>位置</th><th>说明</th>
+  </tr></thead>
+  <tbody>{''.join(rows) or '<tr><td colspan=6>未发现问题</td></tr>'}</tbody>
+</table>
+</body></html>"""
+    return body
@@ -0,0 +1,12 @@
+"""把 AuditResult 序列化为 JSON 字符串。"""
+
+import json
+from fastapi_modules.fastapi_leaudit.govdoc_engine.engine.result import AuditResult
+
+
+def to_json(result: AuditResult, indent: int = 2) -> str:
+    return json.dumps(
+        result.model_dump(mode="json"),
+        ensure_ascii=False,
+        indent=indent,
+    )