fix: close independent verification findings on document parsing

Zip construction and member reads now share one narrow boundary so corrupt BZIP2, LZMA and version fields cannot leak native exceptions. Non-success statuses are read before classification, text-bearing blocks require lines, the size cap and reasoning contract are pinned by tests that fail under mutation, and the per-page timing claim is corrected to the observed range.

tests/unit/test_monkey_document.py

@@ -11,6 +11,7 @@ table/image 的嵌套 `blocks`、span 字段),一切识别文本替换为 `SYNTH
 
 import io
 import json
+import random
 import struct
 import zipfile
 
@@ -287,7 +288,7 @@ class TestPageStructure:
             pytest.param("missing", id="missing"),
             pytest.param("0", id="string"),
             pytest.param(0.0, id="float"),
-            pytest.param(True, id="bool"),
+            pytest.param(True, id="bool-true-off-position"),
             pytest.param(-1, id="negative"),
             pytest.param(3, id="out-of-position"),
         ],
@@ -301,6 +302,20 @@ class TestPageStructure:
             page["page_idx"] = page_idx
         _invalid([page])
 
+    @pytest.mark.parametrize(
+        "pages",
+        [
+            pytest.param([_page([], page_idx=False)], id="false-equals-0-on-first-page"),
+            pytest.param(
+                [_page([], page_idx=0), _page([], page_idx=True)], id="true-equals-1-on-second-page"
+            ),
+        ],
+    )
+    def test_bool_page_idx_is_rejected_even_when_it_equals_the_position(self, pages):
+        """`False == 0`、`True == 1`: 没有显式的 bool 守卫时它们恰好等于页序而被放行。"""
+        with pytest.raises(ResultInvalidError, match="page_idx"):
+            _parse(pages)
+
     def test_second_page_must_not_claim_the_first_index(self):
         _invalid([_page([], page_idx=0), _page([], page_idx=0)])
 
@@ -467,12 +482,15 @@ class TestExternalDataExceptionBoundary:
         deep = b'{"pdf_info": ' + b"[" * 100_000 + b"]" * 100_000 + b"}"
         _invalid(middle=deep)
 
-    @pytest.mark.parametrize("member", ["middle", "markdown"])
-    def test_declared_size_over_cap_is_rejected(self, member, monkeypatch):
-        monkeypatch.setattr(
-            _monkey_document, "MAX_MIDDLE_BYTES" if member == "middle" else "MAX_MARKDOWN_BYTES", 8
-        )
-        _invalid([_page([_text_block("A")])], md="# a markdown longer than eight bytes")
+    @pytest.mark.parametrize(
+        ("cap_name", "member"),
+        [("MAX_MIDDLE_BYTES", "doc_middle.json"), ("MAX_MARKDOWN_BYTES", "doc.md")],
+    )
+    def test_declared_size_over_cap_names_the_offending_member(self, cap_name, member, monkeypatch):
+        """断言消息里的成员名: 两个上限互换时,只断言异常类型的旧用例仍会通过。"""
+        monkeypatch.setattr(_monkey_document, cap_name, 8)
+        with pytest.raises(ResultInvalidError, match=member):
+            _parse([_page([_text_block("A")])], md="# a markdown longer than eight bytes")
 
     def test_existing_result_invalid_messages_pass_through_unchanged(self):
         with pytest.raises(ResultInvalidError, match="至少应有 1 页"):
@@ -499,3 +517,74 @@ class TestLayoutPathUntouched:
         assert accepted[0].page_index == 7
         fallback, _ = _parse_middle_json(_package([_page([_text_block()], page_idx="x")]))
         assert fallback[0].page_index == 0
+
+
+class TestZipLayerNeverLeaksNativeExceptions:
+    """独立验证发现: BZIP2/LZMA 成员数据损坏会漏出 `OSError`/`LZMAError`,中央目录版本字段损坏会在
+    `ZipFile` 构造阶段漏出 `NotImplementedError`——它们都不在外层边界里。漏出的后果与设计 §5 一致:
+    `OcrClient._call` 只接 `PolyGatewayError`,既不写终态遥测行,也不归还半开探针。"""
+
+    @staticmethod
+    def _zip(method: int) -> bytes:
+        payload = json.dumps({"pdf_info": [_page([_text_block("SYNTH")])]}).encode() * 20
+        buf = io.BytesIO()
+        with zipfile.ZipFile(buf, "w", compression=method) as zf:
+            zf.writestr("doc_middle.json", payload)
+            zf.writestr("doc.md", "# synth " * 50)
+        return buf.getvalue()
+
+    @pytest.mark.parametrize(
+        "method",
+        [
+            pytest.param(zipfile.ZIP_DEFLATED, id="deflated"),
+            pytest.param(zipfile.ZIP_BZIP2, id="bzip2"),
+            pytest.param(zipfile.ZIP_LZMA, id="lzma"),
+        ],
+    )
+    def test_single_bit_flips_never_escape_as_native_exceptions(self, method):
+        """确定性字节翻转(固定种子): 每个结果只能是成功或 `ResultInvalidError`。"""
+        base = self._zip(method)
+        rng = random.Random(34)
+        for _ in range(600):
+            data = bytearray(base)
+            position = rng.randrange(len(data))
+            data[position] ^= 1 << rng.randrange(8)
+            try:
+                parse_document_package(bytes(data))
+            except ResultInvalidError:
+                continue
+            except Exception as exc:  # noqa: BLE001 — 测试要抓的正是任何漏出的原生异常
+                pytest.fail(
+                    f"字节 {position} 翻转后漏出 {type(exc).__module__}.{type(exc).__name__}: {exc}"
+                )
+
+    @pytest.mark.parametrize("method", [zipfile.ZIP_BZIP2, zipfile.ZIP_LZMA])
+    def test_corrupt_non_deflate_member_data(self, method):
+        """压缩流内部损坏(而非 CRC 失败): 标准库抛 OSError / LZMAError。"""
+        data = bytearray(self._zip(method))
+        local = data.index(b"PK\x03\x04")
+        name_len, extra_len = struct.unpack_from("<HH", data, local + 26)
+        body = local + 30 + name_len + extra_len
+        for offset in range(body, body + 12):
+            data[offset] ^= 0xFF
+        with pytest.raises(ResultInvalidError):
+            parse_document_package(bytes(data))
+
+    def test_zipfile_construction_stage_is_inside_the_boundary(self):
+        """中央目录的 extract_version 损坏: `ZipFile(...)` 构造阶段抛 NotImplementedError。"""
+        data = bytearray(self._zip(zipfile.ZIP_STORED))
+        central = data.index(b"PK\x01\x02")
+        data[central + 6] = 99  # extract_version = 9.9 → "zip file version 9.9"
+        with pytest.raises(ResultInvalidError):
+            parse_document_package(bytes(data))
+
+
+class TestTextBearingBlocksRequireLines:
+    """text/title/interline_equation 缺 `lines` 不是「空文本」而是畸形: 与 table 缺内容就报错同口径,
+    否则下游分不清「服务识别出空块」和「服务给了坏结构」。"""
+
+    @pytest.mark.parametrize("block_type", ["text", "title", "interline_equation"])
+    def test_missing_lines_is_rejected_with_its_reason(self, block_type):
+        block = {"type": block_type, "bbox": list(_BBOX)}
+        with pytest.raises(ResultInvalidError, match="缺少 lines"):
+            _parse([_page([block])])