From 83afd253b30fd9699970f9371bbeccb81f965114 Mon Sep 17 00:00:00 2001
From: 13315423919 <13315423919@qq.com>
Date: Wed, 19 Nov 2025 19:43:19 +0800
Subject: [PATCH] Add File

---
 doc/全文检索笔记.txt | 62 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 doc/全文检索笔记.txt

diff --git a/doc/全文检索笔记.txt b/doc/全文检索笔记.txt
new file mode 100644
index 0000000..8f61658
--- /dev/null
+++ b/doc/全文检索笔记.txt
@@ -0,0 +1,62 @@
+一、安装全文检索库
+    pip install xapian-bindings-binary -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+    文档：
+    https://xapian.org/docs/bindings/python3/
+  
+二、安装分词库
+    pip install jieba
+
+三、建立索引
+def create_index(words):
+
+    index_db = xapian.WritableDatabase("xapian.data",xapian.DB_CREATE_OR_OPEN)
+
+    for i,data in enumerate(words):
+        seg_list = jieba.cut_for_search(data)
+        seg_list_clean = list(set(seg_list).difference(set(bad_chars)))
+        print(seg_list_clean)
+        
+        doc = xapian.Document()
+        doc.set_data(data)
+        for seg in seg_list_clean:
+            #print seg
+            doc.add_term(seg)
+        doc.add_value(0,f"文档{i}")
+        index_db.add_document(doc)
+    index_db.flush()
+    index_db.close()
+
+同时注意Term too long (> 245)将引发错误, seg = seg[0:240]
+
+四、查询
+#带语法的查询,英文的,使用结巴分词对语义做了处理
+def search_index2(keyword):
+
+    #分词
+    seg_list = jieba.cut_for_search(keyword)
+    seg_list_clean = list(set(seg_list).difference(set(bad_chars)))
+    keyword = " ".join(seg_list_clean)
+
+    #打开数据库
+    db = xapian.Database("xapian.data")
+    enquire =xapian.Enquire(db)
+
+    #查询
+    qp = xapian.QueryParser()
+    stemmer = xapian.Stem("english")
+    qp.set_stemmer(stemmer)
+    qp.set_database(db)
+    #qp.set_stemming_strategy(xapian.QueryParser.STEM_SOME)
+    qp.set_stemming_strategy(xapian.QueryParser.STEM_ALL)
+    query = qp.parse_query(keyword)
+
+    #query =xapian.Query(keyword)
+    print("Parsed query is: %s" % str(query))
+
+    enquire.set_query(query)
+    matches = enquire.get_mset(0,50)
+    print(matches.size())
+    for m in matches:
+        print("%s %i %i%% docid=%i [%s]" % (m.document.get_value(0).decode("utf-8"),m.rank+1,m.percent,m.docid,m.document.get_data().decode("utf-8")))
+