chore: add detailed example

README.md

@@ -1,21 +1,17 @@
-tantivy-jieba
-============================
+# tantivy-jieba
 
 [![Crates.io version][crate-img]][crate]
 [![docs.rs][docs-img]][docs]
 [![Changelog][changelog-img]][changelog]
 [![FOSSA Status](https://app.fossa.io/api/projects/git%2Bgithub.com%2Fjiegec%2Ftantivy-jieba.svg?type=shield)](https://app.fossa.io/projects/git%2Bgithub.com%2Fjiegec%2Ftantivy-jieba?ref=badge_shield)
 
-
 An adapter that bridges between tantivy and jieba-rs.
 
-Usage
-===========================
+## Usage
 
 Add dependency `tantivy-jieba` to your `Cargo.toml`.
 
-Example
----------------------------
+### Example
 
 ```rust
 use tantivy::tokenizer::*;
@@ -25,8 +21,7 @@ assert_eq!(token_stream.next().unwrap().text, "测试");
 assert!(token_stream.next().is_none());
 ```
 
-Register tantivy tokenizer
----------------------------
+### Register tantivy tokenizer
 
 ```rust
 use tantivy::schema::Schema;
@@ -38,13 +33,15 @@ index.tokenizers()
      .register("jieba", tokenizer);
 ```
 
+See [examples/mod.rs](examples/mod.rs) for detailed example.
+
 [crate-img]:     https://img.shields.io/crates/v/tantivy-jieba.svg
 [crate]:         https://crates.io/crates/tantivy-jieba
 [changelog-img]: https://img.shields.io/badge/changelog-online-blue.svg
 [changelog]:     https://github.com/jiegec/tantivy-jieba/blob/master/CHANGELOG.md
 [docs-img]:      https://docs.rs/tantivy-jieba/badge.svg
 [docs]:          https://docs.rs/tantivy-jieba
 
-
 ## License
+
 [![FOSSA Status](https://app.fossa.io/api/projects/git%2Bgithub.com%2Fjiegec%2Ftantivy-jieba.svg?type=large)](https://app.fossa.io/projects/git%2Bgithub.com%2Fjiegec%2Ftantivy-jieba?ref=badge_large)

examples/mod.rs

@@ -0,0 +1,63 @@
+use tantivy::collector::TopDocs;
+use tantivy::doc;
+use tantivy::query::QueryParser;
+use tantivy::schema::{IndexRecordOption, Schema, TextFieldIndexing, TextOptions, Value};
+use tantivy::tokenizer::*;
+use tantivy::Index;
+use tantivy::TantivyDocument;
+
+fn main() {
+    // Build schema
+    let mut schema_builder = Schema::builder();
+    let name = schema_builder.add_text_field(
+        "name",
+        TextOptions::default()
+            .set_indexing_options(
+                TextFieldIndexing::default()
+                    .set_tokenizer("jieba")
+                    .set_index_option(IndexRecordOption::WithFreqsAndPositions),
+            )
+            .set_stored(),
+    );
+    let schema = schema_builder.build();
+
+    // Register tantivy tokenizer
+    let tokenizer = tantivy_jieba::JiebaTokenizer {};
+    let index = Index::create_in_ram(schema);
+    let analyzer = TextAnalyzer::builder(tokenizer)
+        .filter(RemoveLongFilter::limit(40))
+        .filter(LowerCaser)
+        .filter(Stemmer::default())
+        .build();
+    index.tokenizers().register("jieba", analyzer);
+
+    // Index some documents
+    let mut index_writer = index.writer(50_000_000).unwrap();
+    index_writer.add_document(doc!(
+      name => "张华考上了北京大学；李萍进了中等技术学校；我在百货公司当售货员：我们都有光明的前途",
+    )).unwrap();
+    index_writer.commit().unwrap();
+
+    // Search keywords
+    let reader = index.reader().unwrap();
+    let searcher = reader.searcher();
+    let query_parser = QueryParser::for_index(&index, vec![name]);
+    let query = query_parser.parse_query("售货员").unwrap();
+    let top_docs = searcher.search(&query, &TopDocs::with_limit(10)).unwrap();
+    println!("Search Result:");
+    for (_, doc_address) in top_docs {
+        let retrieved_doc: TantivyDocument = searcher.doc(doc_address).unwrap();
+        let val = retrieved_doc.get_first(name).unwrap();
+        let res = val.as_str().unwrap_or_default().to_string();
+        println!("{res}");
+        assert_eq!(
+            res,
+            *"张华考上了北京大学；李萍进了中等技术学校；我在百货公司当售货员：我们都有光明的前途"
+        );
+    }
+}
+
+#[test]
+fn test() {
+    main();
+}