Merge #604

604: Speed up debug builds r=Kerollmops a=loiclec

Note: this draft PR is based on https://github.com/meilisearch/milli/pull/601 , for no particular reason.

## What does this PR do?
Make a series of changes with the goal of speeding up debug builds:

1. Add an `all_languages` feature which compiles charabia with its `default` features activated.
The `all_languages` feature is activated by default. But running:
```
cargo build --no-default-features
```
on `milli` is now much faster.

2. Reduce the debug optimisation level from 3 to 0, except for a few critical dependencies.

3.  Compile the build dependencies quicker as well. Previously, all build dependencies were compiled with `opt-level = 3`. Now, only the critical build dependencies are compiled with optimisations.

4. Reduce the amount of code generated by the `documents!` macro

5. Make the "progress update" closure provided to indexing functions a trait object instead of a generic parameter. This avoids monomorphising the indexing code multiple times needlessly.

## Results
Initial build times on my computer before and after these changes:
|        | cargo check | cargo check --no-default-features | cargo test | cargo test --lib | cargo test --no-default-features | cargo test --lib --no-default-features |
|--------|-------------|-----------------------------------|------------|------------------|----------------------------------|----------------------------------------|
| before | 1m05s       | 1m05s                             | 2m06s      | 1m47s            | 2m06                             | 1m47s                                  |
| after  | 28.9s       | 13.1s                             | 40s      | 38s            | 23s                              | 21s                                  |



Co-authored-by: Loïc Lecrenier <loic@meilisearch.com>

Cargo.toml

@@ -4,19 +4,34 @@ members = ["milli", "filter-parser", "flatten-serde-json", "json-depth-checker",
 default-members = ["milli"]
 
 [profile.dev]
-opt-level = 3
+opt-level = 0 
 
 [profile.release]
 debug = true
 codegen-units = 1
 
-# Make sure that the build scripts and proc-macros are compiled with
-# all the optimizations. It speeds up the zip crate that we use in the build.rs.
-[profile.dev.build-override]
+[profile.dev.package.grenad]
 opt-level = 3
-[profile.release.build-override]
+[profile.dev.package.roaring]
 opt-level = 3
-[profile.bench.build-override]
+
+[profile.dev.package.lindera-ipadic-builder]
 opt-level = 3
-[profile.test.build-override]
+[profile.dev.package.encoding]
+opt-level = 3
+[profile.dev.package.yada]
+opt-level = 3
+
+[profile.release.package.lindera-ipadic-builder]
+opt-level = 3
+[profile.release.package.encoding]
+opt-level = 3
+[profile.release.package.yada]
+opt-level = 3
+
+[profile.bench.package.lindera-ipadic-builder]
+opt-level = 3
+[profile.bench.package.encoding]
+opt-level = 3
+[profile.bench.package.yada]
 opt-level = 3

benchmarks/Cargo.toml

@@ -7,7 +7,7 @@ publish = false
 [dependencies]
 anyhow = "1.0.56"
 csv = "1.1.6"
-milli = { path = "../milli" }
+milli = { path = "../milli", default-features = false }
 mimalloc = { version = "0.1.29", default-features = false }
 serde_json = { version = "1.0.79", features = ["preserve_order"] }
 
@@ -24,6 +24,9 @@ convert_case = "0.5.0"
 flate2 = "1.0.22"
 reqwest = { version = "0.11.9", features = ["blocking", "rustls-tls"], default-features = false }
 
+[features]
+default = ["milli/default"]
+
 [[bench]]
 name = "search_songs"
 harness = false

cli/Cargo.toml

@@ -12,9 +12,12 @@ color-eyre = "0.6.1"
 csv = "1.1.6"
 eyre = "0.6.7"
 indicatif = "0.16.2"
-milli = { path = "../milli" }
+milli = { path = "../milli", default-features = false }
 mimalloc = { version = "0.1.29", default-features = false }
 serde = "1.0.136"
 serde_json = "1.0.79"
 stderrlog = "0.5.1"
 structopt = "0.3.26"
+
+[features]
+default = ["milli/default"]

milli/src/documents/mod.rs

@@ -152,30 +152,33 @@ impl fmt::Display for Error {
 
 impl std::error::Error for Error {}
 
+#[cfg(test)]
+pub fn objects_from_json_value(json: serde_json::Value) -> Vec<crate::Object> {
+    let documents = match json {
+        object @ serde_json::Value::Object(_) => vec![object],
+        serde_json::Value::Array(objects) => objects,
+        invalid => {
+            panic!("an array of objects must be specified, {:#?} is not an array", invalid)
+        }
+    };
+    let mut objects = vec![];
+    for document in documents {
+        let object = match document {
+            serde_json::Value::Object(object) => object,
+            invalid => panic!("an object must be specified, {:#?} is not an object", invalid),
+        };
+        objects.push(object);
+    }
+    objects
+}
+
 /// Macro used to generate documents, with the same syntax as `serde_json::json`
 #[cfg(test)]
 macro_rules! documents {
     ($data:tt) => {{
         let documents = serde_json::json!($data);
-        let documents = match documents {
-            object @ serde_json::Value::Object(_) => vec![object],
-            serde_json::Value::Array(objects) => objects,
-            invalid => {
-                panic!("an array of objects must be specified, {:#?} is not an array", invalid)
-            }
-        };
-
-        let mut builder = crate::documents::DocumentsBatchBuilder::new(Vec::new());
-        for document in documents {
-            let object = match document {
-                serde_json::Value::Object(object) => object,
-                invalid => panic!("an object must be specified, {:#?} is not an object", invalid),
-            };
-            builder.append_json_object(&object).unwrap();
-        }
-
-        let vector = builder.into_inner().unwrap();
-        crate::documents::DocumentsBatchReader::from_reader(std::io::Cursor::new(vector)).unwrap()
+        let documents = $crate::documents::objects_from_json_value(documents);
+        $crate::documents::documents_batch_reader_from_objects(documents)
     }};
 }
 
@@ -187,7 +190,8 @@ pub fn documents_batch_reader_from_objects(
     for object in objects {
         builder.append_json_object(&object).unwrap();
     }
-    DocumentsBatchReader::from_reader(std::io::Cursor::new(builder.into_inner().unwrap())).unwrap()
+    let vector = builder.into_inner().unwrap();
+    DocumentsBatchReader::from_reader(std::io::Cursor::new(vector)).unwrap()
 }
 
 #[cfg(test)]