feat: separate contents, abstract and body evidence

2026-10-01 00:07:40 +08:00
parent 540d0e2918
commit b7634c8374
25 changed files with 2592 additions and 172 deletions
@@ -0,0 +1,150 @@
+"""Evidence policy: which page types may support which kind of judgement.
+
+The policy is part of the versionable scoring rules. Each required-evidence target
+declares its ``use``:
+
+* ``structure`` — the target may be satisfied by a cover page, table of contents or
+  reference list (chapter completeness, bibliography, report layout).
+* ``content`` — the target may only be satisfied by substantive text, data or tables
+  on body or appendix pages.
+
+Rules still in the historical string form (``["问题定义", "需求分析"]``) are read with a
+permissive grammar: wording that names a structural artefact becomes a structure
+target, everything else becomes a content target. The exact grammar is recorded as
+``POLICY_VERSION`` in the batch snapshot so a batch can always be re-read against the
+rules it was scored with.
+"""
+from __future__ import annotations
+
+import re
+
+from .pages import (CONTENT_PAGE_TYPES, NAVIGATION_PAGE_TYPES, STORE_PAGE_TYPES,
+                    STRUCTURE_PAGE_TYPES)
+
+POLICY_VERSION = 1
+USE_STRUCTURE = "structure"
+USE_CONTENT = "content"
+
+#: Wording that names report packaging rather than what the student did.
+_STRUCTURE_WORDS = (
+    "标题", "封面", "目录", "章节", "参考文献", "引用规范", "格式", "规范性", "结构完整",
+    "排版", "页码", "附录", "图表编号", "摘要",
+)
+
+#: Appendix and body pages are the only pages allowed for a content judgement.
+CONTENT_ALLOWED = tuple(CONTENT_PAGE_TYPES)
+#: Structural targets may additionally use cover, contents and reference pages.
+STRUCTURE_ALLOWED = tuple(STRUCTURE_PAGE_TYPES)
+#: Navigation pages can never carry a content judgement.
+NAVIGATION = tuple(NAVIGATION_PAGE_TYPES)
+
+
+def _looks_structural(text: str) -> bool:
+    value = str(text or "").strip()
+    return bool(value) and any(word in value for word in _STRUCTURE_WORDS)
+
+
+def normalize_target(raw) -> dict:
+    """Read one required-evidence target in either the rich or the legacy string form."""
+    if isinstance(raw, dict):
+        label = str(raw.get("label") or raw.get("text") or raw.get("name") or "").strip()
+        use = str(raw.get("use") or "").strip().lower()
+        if use not in (USE_STRUCTURE, USE_CONTENT):
+            use = USE_STRUCTURE if _looks_structural(label) else USE_CONTENT
+        allowed = raw.get("allowed_page_types")
+        if not isinstance(allowed, list) or not allowed:
+            allowed = list(STRUCTURE_ALLOWED if use == USE_STRUCTURE else CONTENT_ALLOWED)
+        allowed = [str(item) for item in allowed if str(item) in STORE_PAGE_TYPES]
+        if not allowed:
+            allowed = list(STRUCTURE_ALLOWED if use == USE_STRUCTURE else CONTENT_ALLOWED)
+        if use == USE_CONTENT:
+            # A content target never admits navigation pages, whatever a rule claims.
+            allowed = [item for item in allowed if item not in NAVIGATION] or list(CONTENT_ALLOWED)
+        return {"label": label or "证据", "use": use, "allowed_page_types": allowed,
+                "query": str(raw.get("query") or label).strip() or (label or "证据")}
+    label = str(raw or "").strip()
+    use = USE_STRUCTURE if _looks_structural(label) else USE_CONTENT
+    return {"label": label or "证据", "use": use,
+            "allowed_page_types": list(STRUCTURE_ALLOWED if use == USE_STRUCTURE else CONTENT_ALLOWED),
+            "query": label or "证据"}
+
+
+def normalize_targets(required_evidence) -> list[dict]:
+    """Normalize a criterion's required evidence, preserving order and identity."""
+    values = required_evidence if isinstance(required_evidence, list) else [required_evidence]
+    targets = []
+    for index, raw in enumerate(values):
+        if raw is None or (isinstance(raw, str) and not raw.strip()):
+            continue
+        target = normalize_target(raw)
+        target["index"] = index
+        target["target_id"] = str((raw.get("target_id") if isinstance(raw, dict) else "") or f"t{index}")
+        targets.append(target)
+    if not targets:
+        targets.append({"label": "正文实质内容", "use": USE_CONTENT, "allowed_page_types": list(CONTENT_ALLOWED),
+                        "query": "正文实质内容", "index": 0, "target_id": "t0"})
+    return targets
+
+
+def content_targets(criterion: dict) -> list[dict]:
+    return [target for target in normalize_targets(criterion.get("required_evidence")) if target["use"] == USE_CONTENT]
+
+
+def any_content_target(criterion: dict) -> bool:
+    return bool(content_targets(criterion))
+
+
+def page_type_allowed(page_type: str, allowed: list[str]) -> bool:
+    """An ``unknown`` page is a body page only when the target already allows body text.
+
+    ``unknown`` marks a page whose reading is genuinely unsettled, so it may never be
+    used as the sole support for a content judgement, and it never widens a structural
+    target either. It stays retrievable so a teacher can inspect it.
+    """
+    if page_type == "unknown":
+        return "body" in allowed
+    return page_type in allowed
+
+
+def content_evidence_allowed(page_type: str) -> bool:
+    """Only substantive body and appendix pages support a content judgement."""
+    return page_type in CONTENT_ALLOWED
+
+
+def heading_only_text(text: str) -> bool:
+    """True when a passage is nothing but section titles, so it proves no content.
+
+    The test is structural, not a length test: a quotation is heading-only when every
+    line of it is a chapter/section heading or a contents entry. A short technical
+    quotation such as a measured value is content, so it must not be rejected here.
+    """
+    from .pages import heading_level, is_toc_entry
+
+    lines = [line.strip() for line in str(text or "").splitlines() if line.strip()]
+    if not lines:
+        return False
+    for line in lines:
+        if is_toc_entry(line) or heading_level(line):
+            continue
+        return False
+    return True
+
+
+_PLACEHOLDER = re.compile(r"^\s*(待确认|待定|未知|无|none|null|-+|—+)\s*$", re.IGNORECASE)
+
+
+def meaningful(value) -> bool:
+    text = str(value or "").strip()
+    return bool(text) and not _PLACEHOLDER.match(text)
+
+
+def plan_snapshot(criteria: list[dict]) -> dict:
+    """The policy attached to a batch snapshot, so old batches stay re-readable."""
+    return {
+        "version": POLICY_VERSION,
+        "content_allowed_page_types": list(CONTENT_ALLOWED),
+        "structure_allowed_page_types": list(STRUCTURE_ALLOWED),
+        "navigation_page_types": list(NAVIGATION),
+        "criteria": {criterion["criterion_id"]: normalize_targets(criterion.get("required_evidence"))
+                     for criterion in criteria},
+    }