POC: Tantivy documents as a trait (#2071)

* fix windows build (#1) * Fix windows build * Add doc traits * Add field value iter * Add value and serialization * Adjust order * Fix bug * Correct type * Fix generic bugs * Reformat code * Add generic to index writer which I forgot about * Fix missing generics on single segment writer * Add missing type export * Add default methods for convenience * Cleanup * Fix more-like-this query to use standard types * Update API and fix tests * Add doc traits * Add field value iter * Add value and serialization * Adjust order * Fix bug * Correct type * Rebase main and fix conflicts * Reformat code * Merge upstream * Fix missing generics on single segment writer * Add missing type export * Add default methods for convenience * Cleanup * Fix more-like-this query to use standard types * Update API and fix tests * Add tokenizer improvements from previous commits * Add tokenizer improvements from previous commits * Reformat * Fix unit tests * Fix unit tests * Use enum in changes * Stage changes * Add new deserializer logic * Add serializer integration * Add document deserializer * Implement new (de)serialization api for existing types * Fix bugs and type errors * Add helper implementations * Fix errors * Reformat code * Add unit tests and some code organisation for serialization * Add unit tests to deserializer * Add some small docs * Add support for deserializing serde values * Reformat * Fix typo * Fix typo * Change repr of facet * Remove unused trait methods * Add child value type * Resolve comments * Fix build * Fix more build errors * Fix more build errors * Fix the tests I missed * Fix examples * fix numerical order, serialize PreTok Str * fix coverage * rename Document to TantivyDocument, rename DocumentAccess to Document add Binary prefix to binary de/serialization * fix coverage --------- Co-authored-by: Pascal Seitz <pascal.seitz@gmail.com>
2025-12-23 02:29:57 +00:00 · 2023-10-02 09:01:16 +01:00
parent b525f653c0
commit 1c7c6fd591
96 changed files with 4191 additions and 1567 deletions
--- a/examples/aggregation.rs
+++ b/examples/aggregation.rs
@@ -12,7 +12,7 @@ use tantivy::aggregation::agg_result::AggregationResults;
 use tantivy::aggregation::AggregationCollector;
 use tantivy::query::AllQuery;
 use tantivy::schema::{self, IndexRecordOption, Schema, TextFieldIndexing, FAST};
-use tantivy::Index;
+use tantivy::{Index, IndexWriter, TantivyDocument};

 fn main() -> tantivy::Result<()> {
    // # Create Schema
@@ -132,10 +132,10 @@ fn main() -> tantivy::Result<()> {

    let stream = Deserializer::from_str(data).into_iter::<Value>();

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;
    let mut num_indexed = 0;
    for value in stream {
-        let doc = schema.parse_document(&serde_json::to_string(&value.unwrap())?)?;
+        let doc = TantivyDocument::parse_json(&schema, &serde_json::to_string(&value.unwrap())?)?;
        index_writer.add_document(doc)?;
        num_indexed += 1;
        if num_indexed > 4 {
--- a/examples/basic_search.rs
+++ b/examples/basic_search.rs
@@ -15,7 +15,7 @@
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
-use tantivy::{doc, Index, ReloadPolicy};
+use tantivy::{doc, Index, IndexWriter, ReloadPolicy};
 use tempfile::TempDir;

 fn main() -> tantivy::Result<()> {
@@ -75,7 +75,7 @@ fn main() -> tantivy::Result<()> {
    // Here we give tantivy a budget of `50MB`.
    // Using a bigger memory_arena for the indexer may increase
    // throughput, but 50 MB is already plenty.
-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;

    // Let's index our documents!
    // We first need a handle on the title and the body field.
@@ -87,7 +87,7 @@ fn main() -> tantivy::Result<()> {
    let title = schema.get_field("title").unwrap();
    let body = schema.get_field("body").unwrap();

-    let mut old_man_doc = Document::default();
+    let mut old_man_doc = TantivyDocument::default();
    old_man_doc.add_text(title, "The Old Man and the Sea");
    old_man_doc.add_text(
        body,
@@ -217,8 +217,8 @@ fn main() -> tantivy::Result<()> {
    // the document returned will only contain
    // a title.
    for (_score, doc_address) in top_docs {
-        let retrieved_doc = searcher.doc(doc_address)?;
-        println!("{}", schema.to_json(&retrieved_doc));
+        let retrieved_doc: TantivyDocument = searcher.doc(doc_address)?;
+        println!("{}", retrieved_doc.to_json(&schema));
    }

    // We can also get an explanation to understand
--- a/examples/custom_collector.rs
+++ b/examples/custom_collector.rs
@@ -13,7 +13,7 @@ use columnar::Column;
 use tantivy::collector::{Collector, SegmentCollector};
 use tantivy::query::QueryParser;
 use tantivy::schema::{Schema, FAST, INDEXED, TEXT};
-use tantivy::{doc, Index, Score, SegmentReader};
+use tantivy::{doc, Index, IndexWriter, Score, SegmentReader};

 #[derive(Default)]
 struct Stats {
@@ -142,7 +142,7 @@ fn main() -> tantivy::Result<()> {
    // this example.
    let index = Index::create_in_ram(schema);

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;
    index_writer.add_document(doc!(
        product_name => "Super Broom 2000",
        product_description => "While it is ok for short distance travel, this broom \
--- a/examples/custom_tokenizer.rs
+++ b/examples/custom_tokenizer.rs
@@ -6,7 +6,7 @@ use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
 use tantivy::tokenizer::NgramTokenizer;
-use tantivy::{doc, Index};
+use tantivy::{doc, Index, IndexWriter};

 fn main() -> tantivy::Result<()> {
    // # Defining the schema
@@ -62,7 +62,7 @@ fn main() -> tantivy::Result<()> {
    //
    // Here we use a buffer of 50MB per thread. Using a bigger
    // memory arena for the indexer can increase its throughput.
-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;
    index_writer.add_document(doc!(
    title => "The Old Man and the Sea",
    body => "He was an old man who fished alone in a skiff in the Gulf Stream and \
@@ -103,8 +103,8 @@ fn main() -> tantivy::Result<()> {
    let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;

    for (_, doc_address) in top_docs {
-        let retrieved_doc = searcher.doc(doc_address)?;
-        println!("{}", schema.to_json(&retrieved_doc));
+        let retrieved_doc: TantivyDocument = searcher.doc(doc_address)?;
+        println!("{}", retrieved_doc.to_json(&schema));
    }

    Ok(())
--- a/examples/date_time_field.rs
+++ b/examples/date_time_field.rs
@@ -5,7 +5,7 @@
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::{DateOptions, Schema, Value, INDEXED, STORED, STRING};
-use tantivy::Index;
+use tantivy::{Index, IndexWriter, TantivyDocument};

 fn main() -> tantivy::Result<()> {
    // # Defining the schema
@@ -22,16 +22,18 @@ fn main() -> tantivy::Result<()> {
    // # Indexing documents
    let index = Index::create_in_ram(schema.clone());

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;
    // The dates are passed as string in the RFC3339 format
-    let doc = schema.parse_document(
+    let doc = TantivyDocument::parse_json(
+        &schema,
        r#"{
        "occurred_at": "2022-06-22T12:53:50.53Z",
        "event": "pull-request"
    }"#,
    )?;
    index_writer.add_document(doc)?;
-    let doc = schema.parse_document(
+    let doc = TantivyDocument::parse_json(
+        &schema,
        r#"{
        "occurred_at": "2022-06-22T13:00:00.22Z",
        "event": "comment"
@@ -58,13 +60,13 @@ fn main() -> tantivy::Result<()> {
        let count_docs = searcher.search(&*query, &TopDocs::with_limit(4))?;
        assert_eq!(count_docs.len(), 1);
        for (_score, doc_address) in count_docs {
-            let retrieved_doc = searcher.doc(doc_address)?;
+            let retrieved_doc = searcher.doc::<TantivyDocument>(doc_address)?;
            assert!(matches!(
                retrieved_doc.get_first(occurred_at),
                Some(Value::Date(_))
            ));
            assert_eq!(
-                schema.to_json(&retrieved_doc),
+                retrieved_doc.to_json(&schema),
                r#"{"event":["comment"],"occurred_at":["2022-06-22T13:00:00.22Z"]}"#
            );
        }
--- a/examples/deleting_updating_documents.rs
+++ b/examples/deleting_updating_documents.rs
@@ -11,7 +11,7 @@
 use tantivy::collector::TopDocs;
 use tantivy::query::TermQuery;
 use tantivy::schema::*;
-use tantivy::{doc, Index, IndexReader};
+use tantivy::{doc, Index, IndexReader, IndexWriter};

 // A simple helper function to fetch a single document
 // given its id from our index.
@@ -19,7 +19,7 @@ use tantivy::{doc, Index, IndexReader};
 fn extract_doc_given_isbn(
    reader: &IndexReader,
    isbn_term: &Term,
-) -> tantivy::Result<Option<Document>> {
+) -> tantivy::Result<Option<TantivyDocument>> {
    let searcher = reader.searcher();

    // This is the simplest query you can think of.
@@ -69,10 +69,10 @@ fn main() -> tantivy::Result<()> {

    let index = Index::create_in_ram(schema.clone());

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;

    // Let's add a couple of documents, for the sake of the example.
-    let mut old_man_doc = Document::default();
+    let mut old_man_doc = TantivyDocument::default();
    old_man_doc.add_text(title, "The Old Man and the Sea");
    index_writer.add_document(doc!(
        isbn => "978-0099908401",
@@ -94,7 +94,7 @@ fn main() -> tantivy::Result<()> {
    // Oops our frankenstein doc seems misspelled
    let frankenstein_doc_misspelled = extract_doc_given_isbn(&reader, &frankenstein_isbn)?.unwrap();
    assert_eq!(
-        schema.to_json(&frankenstein_doc_misspelled),
+        frankenstein_doc_misspelled.to_json(&schema),
        r#"{"isbn":["978-9176370711"],"title":["Frankentein"]}"#,
    );

@@ -136,7 +136,7 @@ fn main() -> tantivy::Result<()> {
    // No more typo!
    let frankenstein_new_doc = extract_doc_given_isbn(&reader, &frankenstein_isbn)?.unwrap();
    assert_eq!(
-        schema.to_json(&frankenstein_new_doc),
+        frankenstein_new_doc.to_json(&schema),
        r#"{"isbn":["978-9176370711"],"title":["Frankenstein"]}"#,
    );

--- a/examples/faceted_search.rs
+++ b/examples/faceted_search.rs
@@ -17,7 +17,7 @@
 use tantivy::collector::FacetCollector;
 use tantivy::query::{AllQuery, TermQuery};
 use tantivy::schema::*;
-use tantivy::{doc, Index};
+use tantivy::{doc, Index, IndexWriter};

 fn main() -> tantivy::Result<()> {
    // Let's create a temporary directory for the sake of this example
@@ -30,7 +30,7 @@ fn main() -> tantivy::Result<()> {
    let schema = schema_builder.build();
    let index = Index::create_in_ram(schema);

-    let mut index_writer = index.writer(30_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(30_000_000)?;

    // For convenience, tantivy also comes with a macro to
    // reduce the boilerplate above.
--- a/examples/faceted_search_with_tweaked_score.rs
+++ b/examples/faceted_search_with_tweaked_score.rs
@@ -12,7 +12,7 @@ use std::collections::HashSet;
 use tantivy::collector::TopDocs;
 use tantivy::query::BooleanQuery;
 use tantivy::schema::*;
-use tantivy::{doc, DocId, Index, Score, SegmentReader};
+use tantivy::{doc, DocId, Index, IndexWriter, Score, SegmentReader};

 fn main() -> tantivy::Result<()> {
    let mut schema_builder = Schema::builder();
@@ -23,7 +23,7 @@ fn main() -> tantivy::Result<()> {
    let schema = schema_builder.build();
    let index = Index::create_in_ram(schema);

-    let mut index_writer = index.writer(30_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(30_000_000)?;

    index_writer.add_document(doc!(
        title => "Fried egg",
@@ -91,11 +91,10 @@ fn main() -> tantivy::Result<()> {
            .iter()
            .map(|(_, doc_id)| {
                searcher
-                    .doc(*doc_id)
+                    .doc::<TantivyDocument>(*doc_id)
                    .unwrap()
                    .get_first(title)
-                    .unwrap()
-                    .as_text()
+                    .and_then(|v| v.as_str())
                    .unwrap()
                    .to_owned()
            })
--- a/examples/fuzzy_search.rs
+++ b/examples/fuzzy_search.rs
@@ -14,7 +14,7 @@
 use tantivy::collector::{Count, TopDocs};
 use tantivy::query::FuzzyTermQuery;
 use tantivy::schema::*;
-use tantivy::{doc, Index, ReloadPolicy};
+use tantivy::{doc, Index, IndexWriter, ReloadPolicy};
 use tempfile::TempDir;

 fn main() -> tantivy::Result<()> {
@@ -66,7 +66,7 @@ fn main() -> tantivy::Result<()> {
    // Here we give tantivy a budget of `50MB`.
    // Using a bigger memory_arena for the indexer may increase
    // throughput, but 50 MB is already plenty.
-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;

    // Let's index our documents!
    // We first need a handle on the title and the body field.
@@ -151,10 +151,10 @@ fn main() -> tantivy::Result<()> {
        assert_eq!(count, 3);
        assert_eq!(top_docs.len(), 3);
        for (score, doc_address) in top_docs {
-            let retrieved_doc = searcher.doc(doc_address)?;
            // Note that the score is not lower for the fuzzy hit.
            // There's an issue open for that: https://github.com/quickwit-oss/tantivy/issues/563
-            println!("score {score:?} doc {}", schema.to_json(&retrieved_doc));
+            let retrieved_doc: TantivyDocument = searcher.doc(doc_address)?;
+            println!("score {score:?} doc {}", retrieved_doc.to_json(&schema));
            // score 1.0 doc {"title":["The Diary of Muadib"]}
            //
            // score 1.0 doc {"title":["The Diary of a Young Girl"]}
--- a/examples/index_with_json.rs
+++ b/examples/index_with_json.rs
@@ -21,7 +21,7 @@ fn main() -> tantivy::Result<()> {
    }"#;

    // We can parse our document
-    let _mice_and_men_doc = schema.parse_document(mice_and_men_doc_json)?;
+    let _mice_and_men_doc = TantivyDocument::parse_json(&schema, mice_and_men_doc_json)?;

    // Multi-valued field are allowed, they are
    // expressed in JSON by an array.
@@ -30,7 +30,7 @@ fn main() -> tantivy::Result<()> {
       "title": ["Frankenstein", "The Modern Prometheus"],
       "year": 1818
    }"#;
-    let _frankenstein_doc = schema.parse_document(frankenstein_json)?;
+    let _frankenstein_doc = TantivyDocument::parse_json(&schema, frankenstein_json)?;

    // Note that the schema is saved in your index directory.
    //
--- a/examples/integer_range_search.rs
+++ b/examples/integer_range_search.rs
@@ -5,7 +5,7 @@
 use tantivy::collector::Count;
 use tantivy::query::RangeQuery;
 use tantivy::schema::{Schema, INDEXED};
-use tantivy::{doc, Index, Result};
+use tantivy::{doc, Index, IndexWriter, Result};

 fn main() -> Result<()> {
    // For the sake of simplicity, this schema will only have 1 field
@@ -17,7 +17,7 @@ fn main() -> Result<()> {
    let index = Index::create_in_ram(schema);
    let reader = index.reader()?;
    {
-        let mut index_writer = index.writer_with_num_threads(1, 6_000_000)?;
+        let mut index_writer: IndexWriter = index.writer_with_num_threads(1, 6_000_000)?;
        for year in 1950u64..2019u64 {
            index_writer.add_document(doc!(year_field => year))?;
        }
--- a/examples/ip_field.rs
+++ b/examples/ip_field.rs
@@ -6,7 +6,7 @@
 use tantivy::collector::{Count, TopDocs};
 use tantivy::query::QueryParser;
 use tantivy::schema::{Schema, FAST, INDEXED, STORED, STRING};
-use tantivy::Index;
+use tantivy::{Index, IndexWriter, TantivyDocument};

 fn main() -> tantivy::Result<()> {
    // # Defining the schema
@@ -22,20 +22,22 @@ fn main() -> tantivy::Result<()> {
    // # Indexing documents
    let index = Index::create_in_ram(schema.clone());

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;

    // ### IPv4
    // Adding documents that contain an IPv4 address. Notice that the IP addresses are passed as
    // `String`. Since the field is of type ip, we parse the IP address from the string and store it
    // internally as IPv6.
-    let doc = schema.parse_document(
+    let doc = TantivyDocument::parse_json(
+        &schema,
        r#"{
            "ip": "192.168.0.33",
            "event_type": "login"
        }"#,
    )?;
    index_writer.add_document(doc)?;
-    let doc = schema.parse_document(
+    let doc = TantivyDocument::parse_json(
+        &schema,
        r#"{
            "ip": "192.168.0.80",
            "event_type": "checkout"
@@ -44,7 +46,8 @@ fn main() -> tantivy::Result<()> {
    index_writer.add_document(doc)?;
    // ### IPv6
    // Adding a document that contains an IPv6 address.
-    let doc = schema.parse_document(
+    let doc = TantivyDocument::parse_json(
+        &schema,
        r#"{
            "ip": "2001:0db8:85a3:0000:0000:8a2e:0370:7334",
            "event_type": "checkout"
--- a/examples/iterating_docs_and_positions.rs
+++ b/examples/iterating_docs_and_positions.rs
@@ -10,7 +10,7 @@
 // ---
 // Importing tantivy...
 use tantivy::schema::*;
-use tantivy::{doc, DocSet, Index, Postings, TERMINATED};
+use tantivy::{doc, DocSet, Index, IndexWriter, Postings, TERMINATED};

 fn main() -> tantivy::Result<()> {
    // We first create a schema for the sake of the
@@ -24,7 +24,7 @@ fn main() -> tantivy::Result<()> {

    let index = Index::create_in_ram(schema);

-    let mut index_writer = index.writer_with_num_threads(1, 50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer_with_num_threads(1, 50_000_000)?;
    index_writer.add_document(doc!(title => "The Old Man and the Sea"))?;
    index_writer.add_document(doc!(title => "Of Mice and Men"))?;
    index_writer.add_document(doc!(title => "The modern Promotheus"))?;
--- a/examples/json_field.rs
+++ b/examples/json_field.rs
@@ -7,7 +7,7 @@
 use tantivy::collector::{Count, TopDocs};
 use tantivy::query::QueryParser;
 use tantivy::schema::{Schema, FAST, STORED, STRING, TEXT};
-use tantivy::Index;
+use tantivy::{Index, IndexWriter, TantivyDocument};

 fn main() -> tantivy::Result<()> {
    // # Defining the schema
@@ -20,8 +20,9 @@ fn main() -> tantivy::Result<()> {
    // # Indexing documents
    let index = Index::create_in_ram(schema.clone());

-    let mut index_writer = index.writer(50_000_000)?;
-    let doc = schema.parse_document(
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;
+    let doc = TantivyDocument::parse_json(
+        &schema,
        r#"{
        "timestamp": "2022-02-22T23:20:50.53Z",
        "event_type": "click",
@@ -33,7 +34,8 @@ fn main() -> tantivy::Result<()> {
    }"#,
    )?;
    index_writer.add_document(doc)?;
-    let doc = schema.parse_document(
+    let doc = TantivyDocument::parse_json(
+        &schema,
        r#"{
        "timestamp": "2022-02-22T23:20:51.53Z",
        "event_type": "click",
--- a/examples/phrase_prefix_search.rs
+++ b/examples/phrase_prefix_search.rs
@@ -1,7 +1,7 @@
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
-use tantivy::{doc, Index, ReloadPolicy, Result};
+use tantivy::{doc, Index, IndexWriter, ReloadPolicy, Result};
 use tempfile::TempDir;

 fn main() -> Result<()> {
@@ -17,7 +17,7 @@ fn main() -> Result<()> {

    let index = Index::create_in_dir(&index_path, schema)?;

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;

    index_writer.add_document(doc!(
    title => "The Old Man and the Sea",
@@ -67,8 +67,12 @@ fn main() -> Result<()> {
    let mut titles = top_docs
        .into_iter()
        .map(|(_score, doc_address)| {
-            let doc = searcher.doc(doc_address)?;
-            let title = doc.get_first(title).unwrap().as_text().unwrap().to_owned();
+            let doc = searcher.doc::<TantivyDocument>(doc_address)?;
+            let title = doc
+                .get_first(title)
+                .and_then(|v| v.as_str())
+                .unwrap()
+                .to_owned();
            Ok(title)
        })
        .collect::<Result<Vec<_>>>()?;
--- a/examples/pre_tokenized_text.rs
+++ b/examples/pre_tokenized_text.rs
@@ -13,7 +13,7 @@ use tantivy::collector::{Count, TopDocs};
 use tantivy::query::TermQuery;
 use tantivy::schema::*;
 use tantivy::tokenizer::{PreTokenizedString, SimpleTokenizer, Token, TokenStream, Tokenizer};
-use tantivy::{doc, Index, ReloadPolicy};
+use tantivy::{doc, Index, IndexWriter, ReloadPolicy};
 use tempfile::TempDir;

 fn pre_tokenize_text(text: &str) -> Vec<Token> {
@@ -38,7 +38,7 @@ fn main() -> tantivy::Result<()> {

    let index = Index::create_in_dir(&index_path, schema.clone())?;

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;

    // We can create a document manually, by setting the fields
    // one by one in a Document object.
@@ -83,7 +83,7 @@ fn main() -> tantivy::Result<()> {
        }]
    }"#;

-    let short_man_doc = schema.parse_document(short_man_json)?;
+    let short_man_doc = TantivyDocument::parse_json(&schema, short_man_json)?;

    index_writer.add_document(short_man_doc)?;

@@ -115,8 +115,8 @@ fn main() -> tantivy::Result<()> {
    // Note that the tokens are not stored along with the original text
    // in the document store
    for (_score, doc_address) in top_docs {
-        let retrieved_doc = searcher.doc(doc_address)?;
-        println!("Document: {}", schema.to_json(&retrieved_doc));
+        let retrieved_doc: TantivyDocument = searcher.doc(doc_address)?;
+        println!("{}", retrieved_doc.to_json(&schema));
    }

    // In contrary to the previous query, when we search for the "man" term we
--- a/examples/snippet.rs
+++ b/examples/snippet.rs
@@ -10,7 +10,7 @@
 use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
-use tantivy::{doc, Index, Snippet, SnippetGenerator};
+use tantivy::{doc, Index, IndexWriter, Snippet, SnippetGenerator};
 use tempfile::TempDir;

 fn main() -> tantivy::Result<()> {
@@ -27,7 +27,7 @@ fn main() -> tantivy::Result<()> {
    // # Indexing documents
    let index = Index::create_in_dir(&index_path, schema)?;

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;

    // we'll only need one doc for this example.
    index_writer.add_document(doc!(
@@ -54,13 +54,10 @@ fn main() -> tantivy::Result<()> {
    let snippet_generator = SnippetGenerator::create(&searcher, &*query, body)?;

    for (score, doc_address) in top_docs {
-        let doc = searcher.doc(doc_address)?;
+        let doc = searcher.doc::<TantivyDocument>(doc_address)?;
        let snippet = snippet_generator.snippet_from_doc(&doc);
        println!("Document score {score}:");
-        println!(
-            "title: {}",
-            doc.get_first(title).unwrap().as_text().unwrap()
-        );
+        println!("title: {}", doc.get_first(title).unwrap().as_str().unwrap());
        println!("snippet: {}", snippet.to_html());
        println!("custom highlighting: {}", highlight(snippet));
    }
--- a/examples/stop_words.rs
+++ b/examples/stop_words.rs
@@ -15,7 +15,7 @@ use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::*;
 use tantivy::tokenizer::*;
-use tantivy::{doc, Index};
+use tantivy::{doc, Index, IndexWriter};

 fn main() -> tantivy::Result<()> {
    // this example assumes you understand the content in `basic_search`
@@ -60,7 +60,7 @@ fn main() -> tantivy::Result<()> {

    index.tokenizers().register("stoppy", tokenizer);

-    let mut index_writer = index.writer(50_000_000)?;
+    let mut index_writer: IndexWriter = index.writer(50_000_000)?;

    let title = schema.get_field("title").unwrap();
    let body = schema.get_field("body").unwrap();
@@ -105,9 +105,9 @@ fn main() -> tantivy::Result<()> {
    let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;

    for (score, doc_address) in top_docs {
-        let retrieved_doc = searcher.doc(doc_address)?;
+        let retrieved_doc: TantivyDocument = searcher.doc(doc_address)?;
        println!("\n==\nDocument score {score}:");
-        println!("{}", schema.to_json(&retrieved_doc));
+        println!("{}", retrieved_doc.to_json(&schema));
    }

    Ok(())
--- a/examples/warmer.rs
+++ b/examples/warmer.rs
@@ -6,8 +6,8 @@ use tantivy::collector::TopDocs;
 use tantivy::query::QueryParser;
 use tantivy::schema::{Schema, FAST, TEXT};
 use tantivy::{
-    doc, DocAddress, DocId, Index, Opstamp, Searcher, SearcherGeneration, SegmentId, SegmentReader,
-    Warmer,
+    doc, DocAddress, DocId, Index, IndexWriter, Opstamp, Searcher, SearcherGeneration, SegmentId,
+    SegmentReader, Warmer,
 };

 // This example shows how warmers can be used to
@@ -143,7 +143,7 @@ fn main() -> tantivy::Result<()> {
    const SNEAKERS: ProductId = 23222;

    let index = Index::create_in_ram(schema);
-    let mut writer = index.writer_with_num_threads(1, 15_000_000)?;
+    let mut writer: IndexWriter = index.writer_with_num_threads(1, 15_000_000)?;
    writer.add_document(doc!(product_id=>OLIVE_OIL, text=>"cooking olive oil from greece"))?;
    writer.add_document(doc!(product_id=>GLOVES, text=>"kitchen gloves, perfect for cooking"))?;
    writer.add_document(doc!(product_id=>SNEAKERS, text=>"uber sweet sneakers"))?;