v0.7.1: \u4fee\u590d emoji \u65b9\u6846 + \u5206\u9875\u95ee\u9898 + \u5220\u9664\u6458\u8981\u91cd\u590d

\u7528\u6237\u53cd\u9988\u4e09\u4e2a P0 bug\uff1a

1. \u8868\u683c\u4e2d\u7684 \u2705/\u274c/\ud83d\udd36 \u6e32\u67d3\u4e3a\u65b9\u6846
   \u539f\u56e0\uff1a\u601d\u6e90\u5b57\u4f53\u5b50\u96c6\u4e0d\u542b\u5f69\u8272 emoji\u7684 glyph\u3002\u9664\u975e\u6362\u5b57\u4f53\uff08\u8d85\u51fa\u9879\u76ee\u8303\u56f4\uff09\uff0c
   \u5426\u5219\u53ea\u80fd\u66ff\u6362\u6210\u5b57\u4f53\u6709\u7684\u7b26\u53f7\u3002
   \u65b0\u589e _EMOJI_FALLBACK \u6620\u5c04\u8868\uff0c\u6db5\u76d6 20+ \u5e38\u7528 emoji\uff08\u5bf9\u5e94 CHECK/CROSS/DIAMOND/CIRCLE/STAR \u7b49\uff09\u3002
   \u7528 fontTools \u9a8c\u8bc1\u8fc7\u5b57\u6bcd\u6709\u65e0\uff1a\u2713/\u00d7/\u25c6/\u25c7/\u25cf/\u25cb/\u2605/\u203b \u90fd\u6709\u3001\u2717/\u2611/\u2610 \u6ca1\u6709\uff0c\u5df2\u8c03\u6574\u76f8\u5e94\u66ff\u6362\u503c\u3002

2. \u76ee\u5f55/\u672f\u8bed\u8868\u4e0e\u4e0b\u4e00\u7ae0\u540c\u9875 / \u4e2d\u95f4\u7a7a\u9875
   \u539f\u56e0\uff1abuild_toc \u672b\u5c3e\u52a0 PageBreak\uff0c\u7136\u540e\u4e0b\u4e00\u4e2a\u7ae0\u8282 H1 \u53c8 PageBreak\uff0c\u4e24\u4e2a PageBreak \u5939\u51fa\u7a7a\u9875\u3002
   \u4fee\u590d\uff1abuild_toc / \u672f\u8bed\u8868\u6e32\u67d3\u672b\u5c3e\u53bb\u6389 PageBreak\uff0c\u4ec5\u9760\u4e0b\u4e2a H1 \u7684 PageBreak\u3002
   \u5f00\u5934\u7684 PageBreak \u4fdd\u7559\uff0c\u4fdd\u8bc1\u201c\u76ee\u5f55 / \u672f\u8bed\u8868\u72ec\u7acb\u7b2c\u4e00\u9875\u5f00\u59cb\u201d\u3002

3. \u201c\u6267\u884c\u6458\u8981\u201d\u548c\u201c\u6458\u8981\u201d\u91cd\u590d
   \u6839\u636e\u7528\u6237\u9009\u62e9\uff1a\u4fdd\u7559\u6267\u884c\u6458\u8981\uff08Executive Summary\uff09\uff0c\u5220\u6389\u6458\u8981\uff08Abstract\uff09\u3002
   build_body \u65b0\u589e\u201c\u8df3\u8fc7\u6574\u4e2a\u7ae0\u8282\u201d\u903b\u8f91\uff1a\u770b\u5230 "## \u6458\u8981" / "# \u6458\u8981" / "## Abstract" \u5c31\u8df3\u5230\u4e0b\u4e00\u4e2a H1/H2\u3002

\u91cd\u6784\u6e05\u7406\uff1a
- \u63d0\u53d6 _render_generic_block \u5e2e\u52a9\u51fd\u6570\uff0c\u4ee3\u66ff build_body \u5185\u8054\u7684 p/quote/bullet/hr/image/table \u6e32\u67d3\u4ee3\u7801
- \u672f\u8bed\u8868\u90e8\u5206\u5faa\u73af\u590d\u7528\u8be5\u51fd\u6570

\u9a8c\u8bc1\u7ed3\u679c\uff1aPDF \u4ece 56 \u9875 \u2192 54 \u9875\uff08\u5220\u6389\u91cd\u590d\u7684\u6458\u8981 + \u6d88\u9664\u7a7a\u9875\uff09\u3002
\u5c55\u5f00\u7ae0\u8282\u8d77\u59cb\u9875\u987a\u5e8f\uff1a\u5c01\u9762(1) - \u514d\u8d23(2) - \u6267\u884c\u6458\u8981(2) - \u672f\u8bed\u8868(4) - \u76ee\u5f55(9) - \u6b63\u6587\u7b2c\u4e00\u7ae0(11) - \u7b2c\u5341\u7ae0(47) - \u53c2\u8003\u6587\u732e\u3002

remote \u914d\u7f6e\u4e3a http://192.168.50.45:3000/kai/deep_research.git\u3002

Co-authored-by: User <human>

.opencode/templates/report-template.py

@@ -528,6 +528,37 @@ _UNICODE_SUB = {
 _SUPER_CHARS_RE = re.compile(f"([{''.join(_UNICODE_SUPER)}]+)")
 _SUB_CHARS_RE = re.compile(f"([{''.join(_UNICODE_SUB)}]+)")
 
+# 彩色 emoji / 特殊符号 → 文字替代。思源字体子集不含这些字形，直接放会渲染成方框。
+# 替换为字体里**实际存在**的符号（经过 fontTools 验证）。
+# 验证命令见 scripts/lib/verify_font_glyphs.py
+_EMOJI_FALLBACK = {
+    "✅": "✓",    # U+2705 → U+2713 CHECK MARK（思源有）
+    "❌": "×",    # U+274C → U+00D7 MULTIPLICATION SIGN（思源有，✗ U+2717 思源没有）
+    "✖": "×",
+    "✗": "×",
+    "🔶": "◆",    # U+1F536 → U+25C6 BLACK DIAMOND（思源有）
+    "🔷": "◇",    # U+25C7 WHITE DIAMOND（思源有）
+    "🟢": "●",    # U+25CF BLACK CIRCLE（思源有）
+    "🔴": "●",
+    "🟡": "○",    # U+25CB WHITE CIRCLE
+    "🟠": "○",
+    "⭐": "★",    # U+2605 BLACK STAR（思源有）
+    "✔": "✓",
+    "☑": "[✓]",  # U+2611 思源没有，用方括号包围替代
+    "☒": "[×]",
+    "☐": "[ ]",
+    "➔": "→",
+    "➜": "→",
+    "⚠️": "※",   # U+203B REFERENCE MARK（思源有）
+    "⚠": "※",
+    "💡": "※",
+    "📌": "•",
+    "🔑": "※",
+    "📊": "※",
+    "📈": "※",
+    "📉": "※",
+}
+
 
 def _replace_unicode_superscripts(text: str) -> str:
     """把连续的 Unicode 上标字符替换为 ReportLab <super> 标签。
@@ -549,10 +580,20 @@ def _replace_unicode_superscripts(text: str) -> str:
     return text
 
 
+def _replace_emoji(text: str) -> str:
+    """把字体里没有的 emoji 替换为字体里有的等价符号。"""
+    for emoji, fallback in _EMOJI_FALLBACK.items():
+        if emoji in text:
+            text = text.replace(emoji, fallback)
+    return text
+
+
 def md_inline_to_rl(text: str, *, add_cjk_space: bool = True) -> str:
     """Markdown inline → ReportLab mini HTML."""
     # 先做 Unicode 上/下标归一（字体子集不含这些字形，否则渲染为方框）
     text = _replace_unicode_superscripts(text)
+    # emoji 替换为字体里有的符号
+    text = _replace_emoji(text)
     # 然后在中英交界处加空格
     if add_cjk_space:
         text = _add_cjk_spaces(text)
@@ -711,8 +752,8 @@ def collect_toc_entries(blocks: List[Block]) -> List[tuple[int, str]]:
 def build_toc(blocks: List[Block], styles: StyleSheet1) -> List:
     """生成目录条目。
 
-    目录末尾 PageBreak 让后续内容独立成页。开头不 PageBreak，
+    不在本函数内部 PageBreak——前面由调用方（H1/H2 分支）插入 PageBreak；
-    调用方（H1 分支）已经负责在 H1 前另起一页。
+    后面靠下一个章节的 H1 PageBreak 自然起作用。避免"连续 PageBreak 产生空页"。
     """
     story: list = []
     story.append(Paragraph("目录", styles["h1"]))
@@ -720,7 +761,6 @@ def build_toc(blocks: List[Block], styles: StyleSheet1) -> List:
     for level, title in collect_toc_entries(blocks):
         style_name = "toc-h1" if level == 1 else "toc-h2"
         story.append(Paragraph(md_inline_to_rl(title), styles[style_name]))
-    story.append(PageBreak())
     return story
 
 
@@ -812,6 +852,19 @@ def format_gb7714(rec: dict) -> str:
     return body
 
 
+def _sort_src_id(sid: str) -> tuple:
+    """为 src_id 生成排序键：按字母段分组（A/B/C/E/...），组内按数字升序。"""
+    m = re.match(r"src_([A-Za-z]+)?(\d+)?([A-Za-z0-9_\-]*)", sid)
+    if not m:
+        return ("~", 0, sid)
+    alpha, num, rest = m.group(1) or "", m.group(2) or "0", m.group(3) or ""
+    try:
+        num_int = int(num)
+    except ValueError:
+        num_int = 0
+    return (alpha, num_int, rest)
+
+
 def build_references(
     blocks: List[Block],
     sources_path: Optional[Path],
@@ -819,7 +872,12 @@ def build_references(
 ) -> List:
     """生成参考文献段落。
 
-    引用顺序：按正文首次出现的先后排列（GB/T 7714 顺序编码制）。
+    v0.7 改变：**不再按出现顺序重编号**（之前会导致正文中 `[src_E43]` 和参考文献
+    区的 `[27]` 对不上）。改为：
+    - 参考文献条目直接用原始 `src_id` 作为编号（如 `[src_E43] Alnylam..., 2025.`）
+    - 按 src_id 字母数字排序分组
+    - 缺失的 src_id 单独一段列出，明显标注供人工核查
+    - 顶部给一条"引文健康状态"小结
     """
     story: list = []
     story.append(Paragraph("参考文献", styles["h1"]))
@@ -835,31 +893,67 @@ def build_references(
         ))
         return story
 
-    if not sources:
+    cited_set = set(cited_ids)
-        # 至少列出所有被引用的 ID，供人工回填
+    matched = [sid for sid in cited_ids if sid in sources]
+    missing = [sid for sid in cited_ids if sid not in sources]
+    # sources.jsonl 里有但正文没引用的——列为"备选"不展示，只统计
+    unused = [sid for sid in sources if sid not in cited_set]
+
+    # 头部健康状态
+    health = (
+        f"正文引用 <b>{len(cited_set)}</b> 条独立标识符；"
+        f"sources.jsonl 收录 <b>{len(sources)}</b> 条，"
+        f"<b>{len(matched)}</b> 条可对应，"
+        f"<b>{len(missing)}</b> 条在 sources.jsonl 中未找到。"
+    )
+    if unused:
+        health += f" 另有 {len(unused)} 条收录来源未在正文中引用，已省略展示。"
+    story.append(Paragraph(
+        f"<font color='#6b7280' size=8>引文健康状态：{health}</font>",
+        styles["caption"],
+    ))
+    story.append(Spacer(1, 0.3 * cm))
+
+    # 主列表：按 src_id 字母数字排序
+    if matched:
         story.append(Paragraph(
-            f"（未找到 sources.jsonl 或其内容为空。以下为正文出现的 {len(cited_ids)} 个引用标识符）",
+            "<b>收录来源</b>",
+            styles["h3"],
+        ))
+        for sid in sorted(matched, key=_sort_src_id):
+            rec = sources[sid]
+            text = format_gb7714(rec)
+            # 编号就是原始 sid，便于和正文中的 [src_E43] 上标对应
+            entry = f"<b>[{sid}]</b>  {text}"
+            story.append(Paragraph(entry, styles["footnote"]))
+
+    # 缺失列表：明显标注
+    if missing:
+        story.append(Spacer(1, 0.4 * cm))
+        story.append(Paragraph(
+            f"<b>未找到来源（{len(missing)} 条）</b>",
+            styles["h3"],
+        ))
+        story.append(Paragraph(
+            "<font color='#b45309' size=8>"
+            "以下标识符在正文中出现但未在 <code>sources.jsonl</code> 中找到对应记录。"
+            "可能是编写阶段的占位符未回填，或原始研究员引用不规范，请核查后补充。"
+            "</font>",
             styles["caption"],
         ))
-        for i, sid in enumerate(cited_ids, 1):
+        # 按字母数字排序分组展示，一行三个，节省篇幅
-            story.append(Paragraph(f"[{i}] {sid}", styles["footnote"]))
+        sorted_missing = sorted(missing, key=_sort_src_id)
-        return story
+        # 每 4 个一行
-
+        row_size = 4
-    missing: list[str] = []
+        for k in range(0, len(sorted_missing), row_size):
-    for i, sid in enumerate(cited_ids, 1):
+            chunk = sorted_missing[k : k + row_size]
-        rec = sources.get(sid)
+            row_text = "　　".join(f"[{sid}]" for sid in chunk)
-        if not rec:
-            missing.append(sid)
             story.append(Paragraph(
-                f"[{i}] {sid}（来源记录缺失，请核查 sources.jsonl）",
+                f"<font color='#b45309'>{row_text}</font>",
                 styles["footnote"],
             ))
-            continue
-        text = format_gb7714(rec)
-        # 前面加序号，后面追加 [sid] 便于正文回溯
-        entry = f"[{i}] {text}  <font color='#6b7280' size=7>【{sid}】</font>"
-        story.append(Paragraph(entry, styles["footnote"]))
 
+    # 打印到 stderr
     if missing:
         print(
             f"WARNING: {len(missing)} cited src_ids not found in sources.jsonl: "
@@ -939,6 +1033,49 @@ def render_table(md_table: str, styles: StyleSheet1) -> Table:
     return table
 
 
+def _render_generic_block(block: Block, story: list, base_dir: Path, styles: StyleSheet1, *, in_summary: bool) -> None:
+    """渲染一个非 H1/H2 的 block（p/quote/bullet/hr/image/table/h3）。
+
+    提取出来的帮助函数，给术语表内部循环和主循环复用。
+    """
+    if block.kind == "h3":
+        story.append(Paragraph(md_inline_to_rl(block.content), styles["h3"]))
+    elif block.kind == "p":
+        if _TOC_PLACEHOLDER_RE.search(block.content) or _REF_PLACEHOLDER_RE.search(block.content):
+            return
+        style = styles["summary"] if in_summary else styles["body"]
+        story.append(Paragraph(md_inline_to_rl(block.content), style))
+    elif block.kind == "quote":
+        story.append(Paragraph(md_inline_to_rl(block.content), styles["quote"]))
+    elif block.kind == "bullet":
+        story.append(Paragraph("• " + md_inline_to_rl(block.content), styles["bullet"]))
+    elif block.kind == "hr":
+        story.append(Spacer(1, 0.3 * cm))
+    elif block.kind == "image":
+        img_path = base_dir / block.content
+        if img_path.exists():
+            try:
+                img = Image(str(img_path), width=15 * cm, height=10 * cm, kind="proportional")
+                story.append(img)
+                if block.meta and block.meta.get("caption"):
+                    story.append(Paragraph(block.meta["caption"], styles["caption"]))
+            except Exception as e:
+                story.append(Paragraph(
+                    f"[图片加载失败：{block.content} — {e}]",
+                    styles["caption"],
+                ))
+        else:
+            story.append(Paragraph(
+                f"[图片未找到：{block.content}]",
+                styles["caption"],
+            ))
+    elif block.kind == "table":
+        try:
+            story.append(render_table(block.content, styles))
+        except Exception as e:
+            story.append(Paragraph(f"[表格渲染失败: {e}]", styles["caption"]))
+
+
 def build_body(
     blocks: List[Block],
     base_dir: Path,
@@ -955,62 +1092,45 @@ def build_body(
     - H1 triggers PageBreak；H2/H3 keepWithNext；表格 splitByRow
     """
     story: list = []
-    first_h1_seen = False           # 是否已跳过正文首个 H1
-    skipping_cover_meta = False     # 是否在吞掉封面元信息段
-
-    # Summary 样式
     in_summary = False
 
-    # 准备跳过标志：标题级别下一个 "目录""参考文献" 见到时替换掉它（包含其下紧跟的占位段）
+    # 第一步：跳过"封面块"——从正文开头一直跳到第一个 H2/H3 前。
-    # 采用简单索引遍历以便向前看。
+    # 封面块 = 首个 H1（主标题） + 副标题（加粗 p） + 元信息段（Confidentiality/Date/Version） + 分隔线（hr）。
-    i = 0
+    # 这些已由 build_cover 从 manifest 独立生成，正文里再出现就是重复。
+    # 规则简单可靠：跳过所有 block 直到遇到第一个 H2/H3（如 "## 免责声明"）。
     n = len(blocks)
+    first_section_idx = n
+    for k, b in enumerate(blocks):
+        if b.kind in ("h2", "h3"):
+            first_section_idx = k
+            break
+    i = first_section_idx  # 从第一个 section 开始处理
+
     while i < n:
         block = blocks[i]
 
-        # --- 跳过正文首个 H1（封面标题）+ 紧跟的元信息/hr ---
+        # --- H1 处理（非首个；本循环内 first_section_idx 之后的 H1 都是真正的章节 H1）---
-        if not first_h1_seen and block.kind == "h1":
+        if block.kind == "h1":
-            first_h1_seen = True
+            content = block.content
-            skipping_cover_meta = True
+            title_low = content.strip().lower()
-            i += 1
+
-            continue
+            # 跳过整章：Abstract（保留 Executive Summary）
-        if skipping_cover_meta:
+            if title_low in ("摘要", "abstract"):
-            # 吞掉 p（元信息）、hr、quote（副标题可能被当成加粗段）
+                j = i + 1
-            # 遇到 h1/h2/h3 就停止吞
+                while j < n and blocks[j].kind != "h1":
-            if block.kind in ("h1", "h2", "h3"):
+                    j += 1
-                skipping_cover_meta = False
+                i = j
-                # 不 continue，让当前 block 正常处理
-            elif block.kind == "p" and is_cover_frontmatter(block.content):
-                i += 1
-                continue
-            elif block.kind in ("hr", "quote", "p", "bullet"):
-                # 第一个 hr 标记封面结束
-                if block.kind == "hr":
-                    skipping_cover_meta = False
-                    i += 1
-                    continue
-                # 普通段落：如果不是封面元信息，就认为封面已结束
-                if block.kind == "p":
-                    skipping_cover_meta = False
-                    # fall through to normal handling
-                else:
-                    i += 1
-                    continue
-            else:
-                i += 1
                 continue
 
-        # --- H1 处理（非首个）---
+            # 所有非被替换的 H1 都 PageBreak
-        if block.kind == "h1":
             story.append(PageBreak())
-            content = block.content
+
             if any(k in content for k in ("执行摘要", "Executive Summary", "管理层摘要")):
                 in_summary = True
             else:
                 in_summary = False
 
-            # 目录 / 参考文献：替换为自动生成的内容
+            # 目录：已经 PageBreak 了，build_toc 内部再 PageBreak（独立页）
-            title_low = content.strip().lower()
             if any(s in title_low for s in ("目录", "table of contents")):
                 story.extend(build_toc(blocks, styles))
                 # 跳过紧随其后的占位段
@@ -1019,6 +1139,15 @@ def build_body(
                     j += 1
                 i = j
                 continue
+            # 术语表：H1 本身已 PageBreak，末尾靠下一个 H1 自然换页
+            if any(s in title_low for s in ("术语表", "glossary")):
+                story.append(Paragraph(md_inline_to_rl(content), styles["h1"]))
+                i += 1
+                while i < n and blocks[i].kind != "h1":
+                    sub = blocks[i]
+                    _render_generic_block(sub, story, base_dir, styles, in_summary=False)
+                    i += 1
+                continue
             if any(s in title_low for s in ("参考文献", "references")):
                 story.extend(build_references(blocks, sources_path, styles))
                 j = i + 1
@@ -1034,13 +1163,37 @@ def build_body(
         # --- H2 同样检测占位符 ---
         if block.kind == "h2":
             title_low = block.content.strip().lower()
+
+            # 跳过整段：Abstract（与 Executive Summary 重复，根据用户偏好保留 Executive Summary）
+            if title_low in ("摘要", "abstract"):
+                # 跳到下一个 H1/H2
+                j = i + 1
+                while j < n and blocks[j].kind not in ("h1", "h2"):
+                    j += 1
+                i = j
+                continue
+
+            # 目录：前后 PageBreak（独立成页）
             if any(s in title_low for s in ("目录", "table of contents")):
+                story.append(PageBreak())
                 story.extend(build_toc(blocks, styles))
                 j = i + 1
                 while j < n and blocks[j].kind == "p" and _TOC_PLACEHOLDER_RE.search(blocks[j].content):
                     j += 1
                 i = j
                 continue
+
+            # 术语表：前 PageBreak，后靠下一个 H1/H2 自然换页
+            if any(s in title_low for s in ("术语表", "glossary")):
+                story.append(PageBreak())
+                story.append(Paragraph(md_inline_to_rl(block.content), styles["h1"]))
+                i += 1
+                while i < n and blocks[i].kind not in ("h1", "h2"):
+                    sub = blocks[i]
+                    _render_generic_block(sub, story, base_dir, styles, in_summary=False)
+                    i += 1
+                continue
+
             if any(s in title_low for s in ("参考文献", "references")):
                 story.extend(build_references(blocks, sources_path, styles))
                 j = i + 1
@@ -1053,45 +1206,8 @@ def build_body(
             i += 1
             continue
 
-        if block.kind == "h3":
+        # 非 H1/H2 的 block：统一走 _render_generic_block
-            story.append(Paragraph(md_inline_to_rl(block.content), styles["h3"]))
+        _render_generic_block(block, story, base_dir, styles, in_summary=in_summary)
-        elif block.kind == "p":
-            # 跳过已识别但没有标题的孤立占位符（防御性）
-            if _TOC_PLACEHOLDER_RE.search(block.content) or _REF_PLACEHOLDER_RE.search(block.content):
-                i += 1
-                continue
-            style = styles["summary"] if in_summary else styles["body"]
-            story.append(Paragraph(md_inline_to_rl(block.content), style))
-        elif block.kind == "quote":
-            story.append(Paragraph(md_inline_to_rl(block.content), styles["quote"]))
-        elif block.kind == "bullet":
-            story.append(Paragraph("• " + md_inline_to_rl(block.content), styles["bullet"]))
-        elif block.kind == "hr":
-            story.append(Spacer(1, 0.3 * cm))
-        elif block.kind == "image":
-            img_path = base_dir / block.content
-            if img_path.exists():
-                try:
-                    img = Image(str(img_path), width=15 * cm, height=10 * cm, kind="proportional")
-                    story.append(img)
-                    if block.meta and block.meta.get("caption"):
-                        story.append(Paragraph(block.meta["caption"], styles["caption"]))
-                except Exception as e:
-                    story.append(Paragraph(
-                        f"[图片加载失败：{block.content} — {e}]",
-                        styles["caption"],
-                    ))
-            else:
-                story.append(Paragraph(
-                    f"[图片未找到：{block.content}]",
-                    styles["caption"],
-                ))
-        elif block.kind == "table":
-            try:
-                story.append(render_table(block.content, styles))
-            except Exception as e:
-                story.append(Paragraph(f"[表格渲染失败: {e}]", styles["caption"]))
-
         i += 1
 
     return story

pyproject.toml

@@ -19,6 +19,7 @@ dependencies = [
     "python-dateutil>=2.9.0",
     "PyYAML>=6.0.1",
     "rich>=13.7.0",
+    "pypdf>=6.10.2",
 ]
 
 [project.optional-dependencies]

uv.lock

@@ -374,6 +374,7 @@ dependencies = [
     { name = "pandas", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
     { name = "pandas", version = "3.0.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
     { name = "pillow" },
+    { name = "pypdf" },
     { name = "python-dateutil" },
     { name = "pyyaml" },
     { name = "reportlab" },
@@ -397,6 +398,7 @@ requires-dist = [
     { name = "numpy", specifier = ">=1.26.0" },
     { name = "pandas", specifier = ">=2.1.0" },
     { name = "pillow", specifier = ">=10.0.0" },
+    { name = "pypdf", specifier = ">=6.10.2" },
     { name = "pytest", marker = "extra == 'dev'", specifier = ">=7.4.0" },
     { name = "python-dateutil", specifier = ">=2.9.0" },
     { name = "pyyaml", specifier = ">=6.0.1" },
@@ -1292,6 +1294,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/10/bd/c038d7cc38edc1aa5bf91ab8068b63d4308c66c4c8bb3cbba7dfbc049f9c/pyparsing-3.3.2-py3-none-any.whl", hash = "sha256:850ba148bd908d7e2411587e247a1e4f0327839c40e2e5e6d05a007ecc69911d", size = 122781, upload-time = "2026-01-21T03:57:55.912Z" },
 ]
 
+[[package]]
+name = "pypdf"
+version = "6.10.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/7b/3f/9f2167401c2e94833ca3b69535bad89e533b5de75fefe4197a2c224baec2/pypdf-6.10.2.tar.gz", hash = "sha256:7d09ce108eff6bf67465d461b6ef352dcb8d84f7a91befc02f904455c6eea11d", size = 5315679, upload-time = "2026-04-15T16:37:36.978Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0c/d6/1d5c60cc17bbdf37c1552d9c03862fc6d32c5836732a0415b2d637edc2d0/pypdf-6.10.2-py3-none-any.whl", hash = "sha256:aa53be9826655b51c96741e5d7983ca224d898ac0a77896e64636810517624aa", size = 336308, upload-time = "2026-04-15T16:37:34.851Z" },
+]
+
 [[package]]
 name = "pytest"
 version = "9.0.3"