feat(test): pin fixture grammars to specific commits

crates/xtask/src/fetch.rs

@@ -1,33 +1,24 @@
-use crate::{bail_on_err, root_dir, EMSCRIPTEN_VERSION};
+use crate::{bail_on_err, root_dir, FetchFixtures, EMSCRIPTEN_VERSION};
 use anyhow::Result;
-use std::process::Command;
+use std::{
+    fs,
+    process::{Command, Stdio},
+};
 
-pub fn run_fixtures() -> Result<()> {
-    let grammars_dir = root_dir().join("test").join("fixtures").join("grammars");
+pub fn run_fixtures(args: &FetchFixtures) -> Result<()> {
+    let fixtures_dir = root_dir().join("test").join("fixtures");
+    let grammars_dir = fixtures_dir.join("grammars");
+    let fixtures_path = fixtures_dir.join("fixtures.json");
 
-    [
-        ("bash", "master"),
-        ("c", "master"),
-        ("cpp", "master"),
-        ("embedded-template", "master"),
-        ("go", "master"),
-        ("html", "master"),
-        ("java", "master"),
-        ("javascript", "master"),
-        ("jsdoc", "master"),
-        ("json", "master"),
-        ("php", "master"),
-        ("python", "master"),
-        ("ruby", "master"),
-        ("rust", "master"),
-        ("typescript", "master"),
-    ]
-    .iter()
-    .try_for_each(|(grammar, r#ref)| {
-        let grammar_dir = grammars_dir.join(grammar);
+    // grammar name, tag
+    let mut fixtures: Vec<(String, String)> =
+        serde_json::from_str(&fs::read_to_string(&fixtures_path)?)?;
+
+    for (grammar, tag) in &mut fixtures {
+        let grammar_dir = grammars_dir.join(&grammar);
         let grammar_url = format!("https://github.com/tree-sitter/tree-sitter-{grammar}");
 
-        println!("Updating the {grammar} grammar...");
+        println!("Fetching the {grammar} grammar...");
 
         if !grammar_dir.exists() {
             let mut command = Command::new("git");
@@ -47,21 +38,54 @@ pub fn run_fixtures() -> Result<()> {
         std::env::set_current_dir(&grammar_dir)?;
 
         let mut command = Command::new("git");
-        command.args(["fetch", "origin", r#ref, "--depth", "1"]);
+        command.args(["fetch", "origin", "--tags"]);
         bail_on_err(
             &command.spawn()?.wait_with_output()?,
-            &format!("Failed to fetch the {grammar} grammar"),
+            &format!("Failed to fetch the {grammar} grammar's tags"),
         )?;
 
+        if args.update {
+            let mut command = Command::new("git");
+            command
+                .args(["tag", "--sort=-creatordate"])
+                .stdout(Stdio::piped());
+            let update_out = command.spawn()?.wait_with_output()?;
+            bail_on_err(
+                &update_out,
+                &format!("Failed to parse the {grammar} grammar's latest commit"),
+            )?;
+            let new_tag = String::from_utf8(update_out.stdout)?
+                .lines()
+                .next()
+                .expect("No tags found")
+                .trim()
+                .to_string();
+            if !new_tag.eq(tag) {
+                println!("Updating the {grammar} grammar from {tag} to {new_tag}...");
+                *tag = new_tag;
+            }
+        }
         let mut command = Command::new("git");
-        command.args(["reset", "--hard", "FETCH_HEAD"]);
+        command.args(["reset", "--hard", tag]);
         bail_on_err(
             &command.spawn()?.wait_with_output()?,
             &format!("Failed to reset the {grammar} grammar"),
         )?;
+    }
 
-        Ok(())
-    })
+    if args.update {
+        println!("Updating the fixtures lock file");
+        fs::write(
+            &fixtures_path,
+            // format the JSON without extra newlines
+            serde_json::to_string(&fixtures)?
+                .replace("[[", "[\n  [")
+                .replace("],", "],\n  ")
+                .replace("]]", "]\n]"),
+        )?;
+    }
+
+    Ok(())
 }
 
 pub fn run_emscripten() -> Result<()> {

crates/xtask/src/main.rs

@@ -35,7 +35,7 @@ enum Commands {
     /// Fetches emscripten.
     FetchEmscripten,
     /// Fetches the fixtures for testing tree-sitter.
-    FetchFixtures,
+    FetchFixtures(FetchFixtures),
     /// Generate the Rust bindings from the C library.
     GenerateBindings,
     /// Generates the fixtures for testing tree-sitter.
@@ -115,6 +115,13 @@ struct Clippy {
     package: Option<String>,
 }
 
+#[derive(Args)]
+struct FetchFixtures {
+    /// Update all fixtures to the latest tag
+    #[arg(long, short)]
+    update: bool,
+}
+
 #[derive(Args)]
 struct GenerateFixtures {
     /// Generates the parser to Wasm
@@ -222,7 +229,9 @@ fn run() -> Result<()> {
         Commands::CheckWasmExports(check_options) => check_wasm_exports::run(&check_options)?,
         Commands::Clippy(clippy_options) => clippy::run(&clippy_options)?,
         Commands::FetchEmscripten => fetch::run_emscripten()?,
-        Commands::FetchFixtures => fetch::run_fixtures()?,
+        Commands::FetchFixtures(fetch_fixture_options) => {
+            fetch::run_fixtures(&fetch_fixture_options)?;
+        }
         Commands::GenerateBindings => generate::run_bindings()?,
         Commands::GenerateFixtures(generate_fixtures_options) => {
             generate::run_fixtures(&generate_fixtures_options)?;

test/fixtures/fixtures.json

@@ -0,0 +1,17 @@
+[
+  ["bash","v0.25.0"],
+  ["c","v0.24.1"],
+  ["cpp","v0.23.4"],
+  ["embedded-template","v0.25.0"],
+  ["go","v0.25.0"],
+  ["html","v0.23.2"],
+  ["java","v0.23.5"],
+  ["javascript","v0.23.1"],
+  ["jsdoc","v0.23.2"],
+  ["json","v0.24.8"],
+  ["php","v0.24.2"],
+  ["python","v0.23.6"],
+  ["ruby","v0.23.1"],
+  ["rust","v0.24.0"],
+  ["typescript","v0.23.2"]
+]