// 圐圙文化网络 - Neo4j Cypher 查询集合

// ===== 基础查询 =====

// 1. 查看所有词汇节点
MATCH (w:Word) 
RETURN w.name, w.category, w.meaning, w.region, w.dynasty
ORDER BY w.category, w.name;

// 2. 查看所有关系类型
MATCH ()-[r]-() 
RETURN DISTINCT type(r) as relationship_types;

// ===== 圐圙词根网络分析 =====

// 3. 以"昆仑"为中心的词汇网络
MATCH (center:Word {name: '昆仑'})-[r]-(connected:Word)
RETURN center, r, connected;

// 4. 查找所有音转关系
MATCH (source:Word)-[r:SOUND_SHIFT]->(target:Word)
RETURN source.name as 源词, target.name as 目标词, r.type as 关系类型;

// 5. 查找音转路径（最多3步）
MATCH path = (start:Word {name: '昆仑'})-[:SOUND_SHIFT*1..3]-(end:Word)
RETURN 
  start.name as 起点,
  [node in nodes(path) | node.name] as 路径,
  end.name as 终点,
  length(path) as 步数
ORDER BY 步数;

// ===== 语义分析 =====

// 6. 按类别分组的词汇分布
MATCH (w:Word)
RETURN w.category as 类别, collect(w.name) as 词汇列表, count(w) as 数量
ORDER BY 数量 DESC;

// 7. 按朝代分组的词汇演化
MATCH (w:Word)
RETURN w.dynasty as 朝代, collect(w.name) as 词汇, count(w) as 数量
ORDER BY 
  CASE w.dynasty 
    WHEN '先秦' THEN 1
    WHEN '汉' THEN 2
    WHEN '唐' THEN 3
    WHEN '宋' THEN 4
    WHEN '元' THEN 5
    WHEN '明' THEN 6
    WHEN '清' THEN 7
    ELSE 8
  END;

// 8. 按地区分布的词汇地理分析
MATCH (w:Word)
WHERE w.region IS NOT NULL
RETURN w.region as 地区, collect(w.name) as 词汇, count(w) as 数量
ORDER BY 数量 DESC;

// ===== 高级分析查询 =====

// 9. 查找"圐圙"的完整关联网络
MATCH (kulue:Word {name: '圐圙'})-[r*1..2]-(related:Word)
RETURN kulue, r, related;

// 10. 查找同时具有音转和语义关系的词汇对
MATCH (w1:Word)-[:SOUND_SHIFT]-(w2:Word)
MATCH (w1)-[:SEMANTIC]-(w2)
RETURN w1.name, w2.name, '既有音转又有语义关系' as 关系特征;

// 11. 查找每个类别中的核心词汇（关联最多的）
MATCH (w:Word)-[r]-(connected:Word)
WITH w, count(r) as connections
WHERE connections > 1
RETURN w.category as 类别, w.name as 核心词汇, w.meaning as 含义, connections as 关联数
ORDER BY 类别, connections DESC;

// 12. 查找跨类别的关联模式
MATCH (w1:Word)-[r]-(w2:Word)
WHERE w1.category <> w2.category
RETURN w1.category as 类别1, w2.category as 类别2, count(r) as 关联数
ORDER BY 关联数 DESC;

// ===== 历史演化分析 =====

// 13. 三个帝国的词汇分布
MATCH (w:Word)
WITH w,
  CASE 
    WHEN w.dynasty IN ['先秦', '秦汉', '汉', '三国', '南北朝'] THEN '长城帝国'
    WHEN w.dynasty IN ['隋唐', '隋', '唐', '五代', '辽', '金', '夏', '宋'] THEN '运河帝国'
    WHEN w.dynasty IN ['元', '明', '清', '民国'] THEN '圐圙帝国'
    ELSE '其他'
  END as empire
RETURN empire as 帝国, collect(w.name) as 词汇, count(w) as 数量;

// 14. 查找词汇的时空分布模式
MATCH (w:Word)
RETURN w.dynasty as 朝代, w.region as 地区, collect(w.name) as 词汇
ORDER BY w.dynasty, w.region;

// ===== 可视化查询 =====

// 15. 生成完整的圐圙网络图（用于可视化）
MATCH (w:Word)-[r]-(connected:Word)
RETURN w, r, connected;

// 16. 生成核心概念的星形图
MATCH (core:Word {category: '核心'})-[r]-(related:Word)
RETURN core, r, related;

// 17. 生成音转关系的有向图
MATCH (source:Word)-[r:SOUND_SHIFT]->(target:Word)
RETURN source, r, target;

// ===== 数据统计 =====

// 18. 网络统计信息
MATCH (w:Word) 
WITH count(w) as total_words
MATCH ()-[r]-()
WITH total_words, count(r)/2 as total_relationships
MATCH (w:Word)-[r]-(connected:Word)
WITH total_words, total_relationships, w, count(r) as degree
RETURN 
  total_words as 总词汇数,
  total_relationships as 总关系数,
  avg(degree) as 平均度数,
  max(degree) as 最大度数,
  min(degree) as 最小度数;

// 19. 查找孤立节点（没有关系的词汇）
MATCH (w:Word)
WHERE NOT (w)-[]-()
RETURN w.name as 孤立词汇, w.category as 类别;

// 20. 查找关联度最高的词汇（网络中心）
MATCH (w:Word)-[r]-(connected:Word)
WITH w, count(r) as degree
ORDER BY degree DESC
LIMIT 5
RETURN w.name as 中心词汇, w.meaning as 含义, degree as 关联度;