Merge pull request #22195 from github/tausbn/swift-syntax-rs

unified: Add Swift parser based on `swift-syntax`

Author: tausbn

Cargo.lock

@@ -10,6 +10,7 @@ members = [
     "ruby/extractor",
     "unified/extractor",
     "unified/extractor/tree-sitter-swift",
+    "unified/swift-syntax-rs",
     "rust/extractor",
     "rust/extractor/macros",
     "rust/ast-generator",

Cargo.toml

@@ -31,6 +31,13 @@ bazel_dep(name = "gazelle", version = "0.50.0")
 bazel_dep(name = "rules_dotnet", version = "0.21.5-codeql.1")
 bazel_dep(name = "googletest", version = "1.17.0.bcr.2")
 bazel_dep(name = "rules_rust", version = "0.69.0")
+bazel_dep(name = "rules_swift", version = "4.0.0-rc4")
+bazel_dep(name = "swift-syntax", version = "603.0.2")
+
+# Needed so we can `use_repo` `local_config_xcode` and
+# `local_config_apple_cc_toolchains` below (referenced by the per-target
+# Xcode-config transition in `unified/swift-syntax-rs/xcode_transition.bzl`).
+bazel_dep(name = "apple_support", version = "2.6.1")
 bazel_dep(name = "zstd", version = "1.5.7.bcr.1")
 
 bazel_dep(name = "buildifier_prebuilt", version = "6.4.0", dev_dependency = True)
@@ -219,6 +226,41 @@ use_repo(
     "swift-resource-dir-macos",
 )
 
+# Swift toolchain for building `unified/swift-syntax-rs`. On Linux we register
+# a hermetic swift.org toolchain as the exec toolchain; on macOS `rules_swift`
+# auto-registers `xcode_swift_toolchain` (host Xcode + OS-provided Swift
+# runtime), which is not hermetic.
+#
+# The version is pinned as a literal rather than read from
+# `unified/swift-syntax-rs/.swift-version` via `swift_version_file`: the latter
+# makes the extension `module_ctx.read` a `//unified/...` label, which fails to
+# resolve when this repo is consumed as a dependency module (`@@ql+`) whose
+# `unified/swift-syntax-rs` package is not loadable in that context. Keep this
+# in sync with `unified/swift-syntax-rs/.swift-version` (used by the `cargo`
+# build) and the `swift-syntax` release in `swift/Package.swift`.
+swift = use_extension("@rules_swift//swift:extensions.bzl", "swift")
+swift.toolchain(
+    name = "swift_toolchain",
+    swift_version = "6.3.2",
+)
+use_repo(
+    swift,
+    "swift_toolchain",
+    "swift_toolchain_ubuntu22.04",
+)
+
+register_toolchains(
+    "@swift_toolchain//:swift_toolchain_exec_ubuntu22.04",
+)
+
+# `apple_support`'s xcode_config and CC toolchains, needed by the Xcode
+# transition in `unified/swift-syntax-rs/xcode_transition.bzl`.
+xcode_configure = use_extension("@apple_support//xcode:xcode_configure.bzl", "xcode_configure_extension")
+use_repo(xcode_configure, "local_config_xcode")
+
+apple_cc_configure = use_extension("@apple_support//crosstool:setup.bzl", "apple_cc_configure_extension")
+use_repo(apple_cc_configure, "local_config_apple_cc_toolchains")
+
 node = use_extension("@rules_nodejs//nodejs:extensions.bzl", "node")
 node.toolchain(
     name = "nodejs",

MODULE.bazel

@@ -81,10 +81,18 @@ impl AstNode for yeast::Node {
         yeast::Node::is_extra(self)
     }
     fn start_position(&self) -> tree_sitter::Point {
-        yeast::Node::start_position(self)
+        let p = yeast::Node::start_position(self);
+        tree_sitter::Point {
+            row: p.row,
+            column: p.column,
+        }
     }
     fn end_position(&self) -> tree_sitter::Point {
-        yeast::Node::end_position(self)
+        let p = yeast::Node::end_position(self);
+        tree_sitter::Point {
+            row: p.row,
+            column: p.column,
+        }
     }
     fn byte_range(&self) -> std::ops::Range<usize> {
         yeast::Node::byte_range(self)

misc/bazel/3rdparty/tree_sitter_extractors_deps/BUILD.bazel

@@ -903,7 +903,7 @@ pub fn parse_rule_top(input: TokenStream) -> Result<TokenStream> {
     Ok(quote! {
         {
             let __query = #query_code;
-            yeast::Rule::new(__query, Box::new(|__ast: &mut yeast::Ast, mut __captures: yeast::captures::Captures, __fresh: &yeast::tree_builder::FreshScope, __source_range: Option<tree_sitter::Range>, __user_ctx: &mut _, __translator: yeast::TranslatorHandle<'_, _>| {
+            yeast::Rule::new(__query, Box::new(|__ast: &mut yeast::Ast, mut __captures: yeast::captures::Captures, __fresh: &yeast::tree_builder::FreshScope, __source_range: Option<yeast::Range>, __user_ctx: &mut _, __translator: yeast::TranslatorHandle<'_, _>| {
                 // Auto-translation prefix: recursively translate every
                 // captured node before invoking the user's transform body,
                 // except for `@@name` captures listed in `__skip` which the

misc/bazel/3rdparty/tree_sitter_extractors_deps/defs.bzl

@@ -167,6 +167,28 @@ impl Schema {
         id
     }
 
+    /// Register every kind (named and unnamed) and field *name* from `other`
+    /// into this schema (idempotent). Ids are assigned in this schema's own id
+    /// space; existing ids are unchanged.
+    ///
+    /// This is used when running desugaring rules over an AST that was built
+    /// against a different schema (e.g. from an external parser): the rules
+    /// build output nodes whose kind/field names come from `other`, and those
+    /// names must resolve in the AST's own schema. Only names are needed — the
+    /// rule engine resolves kinds/fields by name and does not consult
+    /// `other`'s field-type or supertype information.
+    pub fn register_names_from(&mut self, other: &Schema) {
+        for name in other.kind_ids.keys() {
+            self.register_kind(name);
+        }
+        for name in other.unnamed_kind_ids.keys() {
+            self.register_unnamed_kind(name);
+        }
+        for name in other.field_ids.keys() {
+            self.register_field(name);
+        }
+    }
+
     /// Track a name for a kind ID without registering it as named or
     /// unnamed. Useful when importing tree-sitter ID tables that may
     /// contain duplicate IDs across the named/unnamed split.

shared/tree-sitter-extractor/src/extractor/mod.rs

@@ -2,7 +2,7 @@ use std::collections::BTreeMap;
 
 use crate::captures::Captures;
 use crate::tree_builder::FreshScope;
-use crate::{Ast, FieldId, Id, NodeContent, TranslatorHandle};
+use crate::{Ast, FieldId, Id, NodeContent, Range, TranslatorHandle};
 
 /// Context for building new AST nodes during a transformation.
 ///
@@ -34,7 +34,7 @@ pub struct BuildCtx<'a, C: 'a = ()> {
     pub captures: &'a Captures,
     pub fresh: &'a FreshScope,
     /// Source range of the matched node, inherited by synthetic nodes.
-    pub source_range: Option<tree_sitter::Range>,
+    pub source_range: Option<Range>,
     /// User-supplied context, accessible directly via `ctx.field` (via Deref).
     pub user_ctx: &'a mut C,
     /// Optional translator handle, populated when the context is built by
@@ -63,7 +63,7 @@ impl<'a, C> BuildCtx<'a, C> {
         ast: &'a mut Ast,
         captures: &'a Captures,
         fresh: &'a FreshScope,
-        source_range: Option<tree_sitter::Range>,
+        source_range: Option<Range>,
         user_ctx: &'a mut C,
     ) -> Self {
         Self {
@@ -82,7 +82,7 @@ impl<'a, C> BuildCtx<'a, C> {
         ast: &'a mut Ast,
         captures: &'a Captures,
         fresh: &'a FreshScope,
-        source_range: Option<tree_sitter::Range>,
+        source_range: Option<Range>,
         user_ctx: &'a mut C,
         translator: TranslatorHandle<'a, C>,
     ) -> Self {
@@ -143,7 +143,7 @@ impl<'a, C> BuildCtx<'a, C> {
         &mut self,
         kind: &'static str,
         value: &str,
-        source_range: Option<tree_sitter::Range>,
+        source_range: Option<Range>,
     ) -> Id {
         self.ast.create_named_token_with_range(
             kind,