From 9f739e831db6e8db4a63be3f4af101f250f1ebc3 Mon Sep 17 00:00:00 2001
From: iomgaa <iomgaaycz@gmail.com>
Date: Sat, 11 Jul 2026 23:33:48 -0400
Subject: [PATCH] refactor(question_gen): reduce cyclomatic complexity in
 sampler_v2

Extract shared _resolve_subtree helper to eliminate repeated tri-level
node resolution. Break _validate_sampling_constraints into focused
single-purpose helpers:
- _count_l3_descendants
- _has_frames
- _count_subtitles
- _resolve_subtree / _find_l3_parent

Extract _subtitles_from_l2_list and _frames_from_l2_list to simplify
collection functions.

Complexity improvements:
- _validate_sampling_constraints: D(23) -> B(8)
- _collect_subtitle_sentences: C(16) -> A(3)
- _collect_frame_paths: C(13) -> A(2)

All functions now grade B or better per radon cc.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 app/question_gen/sampler_v2.py | 260 +++++++++++++++++++--------------
 1 file changed, 152 insertions(+), 108 deletions(-)

diff --git a/app/question_gen/sampler_v2.py b/app/question_gen/sampler_v2.py
index ca40393..52e8800 100644
--- a/app/question_gen/sampler_v2.py
+++ b/app/question_gen/sampler_v2.py
@@ -95,6 +95,19 @@ class MaterialContext:
 # ---------------------------------------------------------------------------
 
 
+@dataclass(frozen=True)
+class _ResolvedSubtree:
+    """节点解析结果 — 将任意层级 node_id 统一解析为 L2 节点列表 + 父 L1。
+
+    属性:
+        l2_nodes: 与目标节点关联的 L2 节点列表。
+        parent_l1: 父 L1 节点（用于跨 L2 判断）。
+    """
+
+    l2_nodes: list[L2Node]
+    parent_l1: L1Node | None
+
+
 def _find_l2_node(tree: TreeIndex, l2_id: str) -> tuple[L2Node, L1Node] | None:
     """按 ID 定位 L2 节点及其父 L1。
 
@@ -128,6 +141,100 @@ def _find_l1_node(tree: TreeIndex, l1_id: str) -> L1Node | None:
     return None
 
 
+def _find_l3_parent(tree: TreeIndex, l3_id: str) -> tuple[L2Node, L1Node] | None:
+    """按 L3 ID 定位其所属的 L2 和 L1 节点。
+
+    参数:
+        tree: 三层树索引。
+        l3_id: L3 节点 ID。
+
+    返回:
+        (L2Node, L1Node) 元组；未找到返回 None。
+    """
+    for l1 in tree.roots:
+        for l2 in l1.children:
+            for l3 in l2.children:
+                if l3.id == l3_id:
+                    return (l2, l1)
+    return None
+
+
+def _resolve_subtree(tree: TreeIndex, node_id: str) -> _ResolvedSubtree | None:
+    """将任意层级节点 ID 解析为关联的 L2 节点列表和父 L1。
+
+    参数:
+        tree: 三层树索引。
+        node_id: 任意层级的节点 ID。
+
+    返回:
+        _ResolvedSubtree 实例；节点不存在时返回 None。
+    """
+    # 尝试作为 L2
+    result = _find_l2_node(tree, node_id)
+    if result is not None:
+        l2_node, parent_l1 = result
+        return _ResolvedSubtree(l2_nodes=[l2_node], parent_l1=parent_l1)
+
+    # 尝试作为 L1
+    l1_node = _find_l1_node(tree, node_id)
+    if l1_node is not None:
+        return _ResolvedSubtree(l2_nodes=list(l1_node.children), parent_l1=l1_node)
+
+    # 尝试作为 L3
+    l3_result = _find_l3_parent(tree, node_id)
+    if l3_result is not None:
+        l2_node, parent_l1 = l3_result
+        return _ResolvedSubtree(l2_nodes=[l2_node], parent_l1=parent_l1)
+
+    return None
+
+
+# ---------------------------------------------------------------------------
+# 约束检查辅助（单一职责）
+# ---------------------------------------------------------------------------
+
+
+def _count_l3_descendants(l2_nodes: list[L2Node]) -> int:
+    """统计 L2 节点列表下的 L3 总数。
+
+    参数:
+        l2_nodes: L2 节点列表。
+
+    返回:
+        L3 节点总数。
+    """
+    return sum(len(l2.children) for l2 in l2_nodes)
+
+
+def _has_frames(l2_nodes: list[L2Node]) -> bool:
+    """检查 L2 节点列表的子树中是否有可用帧。
+
+    参数:
+        l2_nodes: L2 节点列表。
+
+    返回:
+        True 表示至少有一个 L3 有 frame_path。
+    """
+    return any(l3.frame_path for l2 in l2_nodes for l3 in l2.children)
+
+
+def _count_subtitles(l2_nodes: list[L2Node]) -> int:
+    """统计 L2 节点列表中全部字幕数（L2 + L3）。
+
+    参数:
+        l2_nodes: L2 节点列表。
+
+    返回:
+        非空字幕总数。
+    """
+    count = 0
+    for l2 in l2_nodes:
+        if l2.card.subtitle:
+            count += 1
+        count += sum(1 for l3 in l2.children if l3.card.subtitle)
+    return count
+
+
 # ---------------------------------------------------------------------------
 # 公开辅助函数
 # ---------------------------------------------------------------------------
@@ -151,62 +258,39 @@ def _validate_sampling_constraints(
     返回:
         True 表示满足所有约束，False 表示至少一项不满足。
     """
-    # Phase 1: 确定目标 L2 节点列表
-    target_l2_nodes: list[L2Node] = []
-    parent_l1: L1Node | None = None
-
-    # 先尝试作为 L2
-    result = _find_l2_node(tree, node_id)
-    if result is not None:
-        l2_node, parent_l1 = result
-        target_l2_nodes = [l2_node]
-    else:
-        # 尝试作为 L1
-        l1_node = _find_l1_node(tree, node_id)
-        if l1_node is not None:
-            target_l2_nodes = list(l1_node.children)
-            parent_l1 = l1_node
-        else:
-            # 尝试作为 L3 — 找到其所属 L2
-            for l1 in tree.roots:
-                for l2 in l1.children:
-                    for l3 in l2.children:
-                        if l3.id == node_id:
-                            target_l2_nodes = [l2]
-                            parent_l1 = l1
-                            break
-                    if target_l2_nodes:
-                        break
-                if target_l2_nodes:
-                    break
-
-    if not target_l2_nodes:
+    resolved = _resolve_subtree(tree, node_id)
+    if resolved is None:
         return False
 
-    # Phase 2: 统计 L3 节点数
-    total_l3 = sum(len(l2.children) for l2 in target_l2_nodes)
-    if total_l3 < constraint.min_l3_nodes:
+    if _count_l3_descendants(resolved.l2_nodes) < constraint.min_l3_nodes:
         return False
+    if constraint.require_frames and not _has_frames(resolved.l2_nodes):
+        return False
+    if _count_subtitles(resolved.l2_nodes) < constraint.min_subtitles:
+        return False
+    return not (
+        constraint.cross_l2_span
+        and (resolved.parent_l1 is None or len(resolved.parent_l1.children) < 2)
+    )
 
-    # Phase 3: 检查帧路径可用性
-    if constraint.require_frames:
-        has_frame = any(l3.frame_path for l2 in target_l2_nodes for l3 in l2.children)
-        if not has_frame:
-            return False
 
-    # Phase 4: 统计字幕数
-    subtitle_count = 0
-    for l2 in target_l2_nodes:
+def _subtitles_from_l2_list(l2_nodes: list[L2Node]) -> list[str]:
+    """从 L2 节点列表收集全部非空字幕。
+
+    参数:
+        l2_nodes: L2 节点列表。
+
+    返回:
+        非空字幕字符串列表。
+    """
+    sentences: list[str] = []
+    for l2 in l2_nodes:
         if l2.card.subtitle:
-            subtitle_count += 1
+            sentences.append(l2.card.subtitle)
         for l3 in l2.children:
             if l3.card.subtitle:
-                subtitle_count += 1
-    if subtitle_count < constraint.min_subtitles:
-        return False
-
-    # Phase 5: 检查跨 L2 可用性
-    return not (constraint.cross_l2_span and (parent_l1 is None or len(parent_l1.children) < 2))
+                sentences.append(l3.card.subtitle)
+    return sentences
 
 
 def _collect_subtitle_sentences(tree: TreeIndex, node_ids: tuple[str, ...]) -> list[str]:
@@ -220,40 +304,13 @@ def _collect_subtitle_sentences(tree: TreeIndex, node_ids: tuple[str, ...]) -> l
         node_ids: 待收集字幕的节点 ID 元组。
 
     返回:
-        非空字幕句列表（去除空白后非空的字幕）。
+        非空字幕句列表。
     """
     sentences: list[str] = []
-
     for nid in node_ids:
-        # 尝试作为 L2
-        result = _find_l2_node(tree, nid)
-        if result is not None:
-            l2_node, _ = result
-            if l2_node.card.subtitle:
-                sentences.append(l2_node.card.subtitle)
-            for l3 in l2_node.children:
-                if l3.card.subtitle:
-                    sentences.append(l3.card.subtitle)
-            continue
-
-        # 尝试作为 L1
-        l1_node = _find_l1_node(tree, nid)
-        if l1_node is not None:
-            for l2 in l1_node.children:
-                if l2.card.subtitle:
-                    sentences.append(l2.card.subtitle)
-                for l3 in l2.children:
-                    if l3.card.subtitle:
-                        sentences.append(l3.card.subtitle)
-            continue
-
-        # 尝试作为 L3
-        for l1 in tree.roots:
-            for l2 in l1.children:
-                for l3 in l2.children:
-                    if l3.id == nid and l3.card.subtitle:
-                        sentences.append(l3.card.subtitle)
-
+        resolved = _resolve_subtree(tree, nid)
+        if resolved is not None:
+            sentences.extend(_subtitles_from_l2_list(resolved.l2_nodes))
     return sentences
 
 
@@ -369,6 +426,18 @@ def _sample_l1_node(
     return rng.choice(candidates)
 
 
+def _frames_from_l2_list(l2_nodes: list[L2Node]) -> list[str]:
+    """从 L2 节点列表收集全部可用帧路径。
+
+    参数:
+        l2_nodes: L2 节点列表。
+
+    返回:
+        帧路径字符串列表。
+    """
+    return [l3.frame_path for l2 in l2_nodes for l3 in l2.children if l3.frame_path]
+
+
 def _collect_frame_paths(tree: TreeIndex, node_id: str) -> list[str]:
     """收集节点子树下的所有可用帧路径。
 
@@ -379,35 +448,10 @@ def _collect_frame_paths(tree: TreeIndex, node_id: str) -> list[str]:
     返回:
         帧路径列表。
     """
-    paths: list[str] = []
-
-    # L2 节点
-    result = _find_l2_node(tree, node_id)
-    if result is not None:
-        l2_node, _ = result
-        for l3 in l2_node.children:
-            if l3.frame_path:
-                paths.append(l3.frame_path)
-        return paths
-
-    # L1 节点
-    l1_node = _find_l1_node(tree, node_id)
-    if l1_node is not None:
-        for l2 in l1_node.children:
-            for l3 in l2.children:
-                if l3.frame_path:
-                    paths.append(l3.frame_path)
-        return paths
-
-    # L3 节点
-    for l1 in tree.roots:
-        for l2 in l1.children:
-            for l3 in l2.children:
-                if l3.id == node_id and l3.frame_path:
-                    paths.append(l3.frame_path)
-                    return paths
-
-    return paths
+    resolved = _resolve_subtree(tree, node_id)
+    if resolved is None:
+        return []
+    return _frames_from_l2_list(resolved.l2_nodes)
 
 
 def _collect_source_nodes(tree: TreeIndex, node_id: str) -> tuple[str, ...]: