Rollup merge of #131647 - jieyouxu:unicode-table-generator, r=Mark-Simulacrum

Register `src/tools/unicode-table-generator` as a runnable tool

It seems like `src/tools/unicode-table-generator` is not currently managed by bootstrap. This PR wires it up with bootstrap as a runnable tool.

This tool seems to take two possible args:

1. (Mandatory) path to `library/core/src/unicode/unicode_data.rs`, and
2. (Optional) path to generate a test file.

I only passed the mandatory path to `unicode_data.rs` in bootstrap and didn't do anything about (2). I'm not sure about how this tool is supposed to be run.

`Cargo.lock` is modified because I renamed `unicode-table-generator`'s bin name to match the tool name, as bootstrap's tool running logic expects the bin name to be derived from the tool name.

I also added a triagebot message to remind to not manually edit the library source file and edit the tool then regenerate instead, but this should probably be a tidy check (if that's desirable then that can be in a follow-up PR, though may be overkill).

Helps with #131640 but does not close it because still no docs.

r? `@Mark-Simulacrum` (since I think you authored this tool?)

Cargo.lock

@@ -5570,13 +5570,6 @@ dependencies = [
  "version_check",
 ]
 
-[[package]]
-name = "unicode-bdd"
-version = "0.1.0"
-dependencies = [
- "ucd-parse",
-]
-
 [[package]]
 name = "unicode-bidi"
 version = "0.3.15"
@@ -5626,6 +5619,13 @@ version = "1.12.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493"
 
+[[package]]
+name = "unicode-table-generator"
+version = "0.1.0"
+dependencies = [
+ "ucd-parse",
+]
+
 [[package]]
 name = "unicode-width"
 version = "0.1.14"

src/bootstrap/src/core/build_steps/run.rs

@@ -283,3 +283,25 @@ fn make_run(run: RunConfig<'_>) {
         run.builder.ensure(GenerateCompletions);
     }
 }
+
+#[derive(Debug, PartialOrd, Ord, Clone, Hash, PartialEq, Eq)]
+pub struct UnicodeTableGenerator;
+
+impl Step for UnicodeTableGenerator {
+    type Output = ();
+    const ONLY_HOSTS: bool = true;
+
+    fn should_run(run: ShouldRun<'_>) -> ShouldRun<'_> {
+        run.path("src/tools/unicode-table-generator")
+    }
+
+    fn make_run(run: RunConfig<'_>) {
+        run.builder.ensure(UnicodeTableGenerator);
+    }
+
+    fn run(self, builder: &Builder<'_>) {
+        let mut cmd = builder.tool_cmd(Tool::UnicodeTableGenerator);
+        cmd.arg(builder.src.join("library/core/src/unicode/unicode_data.rs"));
+        cmd.run(builder);
+    }
+}

src/bootstrap/src/core/build_steps/tool.rs

@@ -360,6 +360,7 @@ fn run(self, builder: &Builder<'_>) -> PathBuf {
     CoverageDump, "src/tools/coverage-dump", "coverage-dump";
     RustcPerfWrapper, "src/tools/rustc-perf-wrapper", "rustc-perf-wrapper";
     WasmComponentLd, "src/tools/wasm-component-ld", "wasm-component-ld", is_unstable_tool = true, allow_features = "min_specialization";
+    UnicodeTableGenerator, "src/tools/unicode-table-generator", "unicode-table-generator";
 );
 
 /// These are the submodules that are required for rustbook to work due to

src/bootstrap/src/core/builder.rs

@@ -1010,6 +1010,7 @@ macro_rules! describe {
                 run::GenerateCopyright,
                 run::GenerateWindowsSys,
                 run::GenerateCompletions,
+                run::UnicodeTableGenerator,
             ),
             Kind::Setup => {
                 describe!(setup::Profile, setup::Hook, setup::Link, setup::Editor)

src/tools/unicode-table-generator/Cargo.toml

@@ -1,5 +1,5 @@
 [package]
-name = "unicode-bdd"
+name = "unicode-table-generator"
 version = "0.1.0"
 edition = "2021"
 

src/tools/unicode-table-generator/src/range_search.rs

@@ -16,16 +16,14 @@ const fn bitset_search<
     let bucket_idx = (needle / 64) as usize;
     let chunk_map_idx = bucket_idx / CHUNK_SIZE;
     let chunk_piece = bucket_idx % CHUNK_SIZE;
-    // FIXME: const-hack: Revert to `slice::get` after `const_slice_index`
-    // feature stabilizes.
+    // FIXME(const-hack): Revert to `slice::get` when slice indexing becomes possible in const.
     let chunk_idx = if chunk_map_idx < chunk_idx_map.len() {
         chunk_idx_map[chunk_map_idx]
     } else {
         return false;
     };
     let idx = bitset_chunk_idx[chunk_idx as usize][chunk_piece] as usize;
-    // FIXME: const-hack: Revert to `slice::get` after `const_slice_index`
-    // feature stabilizes.
+    // FIXME(const-hack): Revert to `slice::get` when slice indexing becomes possible in const.
     let word = if idx < bitset_canonical.len() {
         bitset_canonical[idx]
     } else {

triagebot.toml

@@ -679,6 +679,15 @@ instead.
 """
 cc = ["@calebzulawski", "@programmerjake"]
 
+[mentions."library/core/src/unicode/unicode_data.rs"]
+message = """
+`library/core/src/unicode/unicode_data.rs` is generated by
+`src/tools/unicode-table-generator` via `./x run
+src/tools/unicode-table-generator`. If you want to modify `unicode_data.rs`,
+please modify the tool then regenerate the library source file with the tool
+instead of editing the library source file manually.
+"""
+
 [mentions."src/librustdoc/clean/types.rs"]
 cc = ["@camelid"]