From 217cb5f76d75a6a3c77dfd24dfc84cb53626fa9c Mon Sep 17 00:00:00 2001
From: swapnil <78632212+swapnilpaliwal-sd@users.noreply.github.com>
Date: Thu, 17 Sep 2026 23:08:53 -0700
Subject: [PATCH] fix: pin tree-sitter-java to the version tree-sitter-groovy
 pins, so it stays deduped

tree-sitter-groovy depends on tree-sitter-java@0.23.4 exactly while the parser
asked for ^0.21.0. Two versions npm cannot reconcile, so it nests a second copy
under tree-sitter-groovy, and the nested copy's gyp config resolves
node-addon-api by a relative path whose ../ count is wrong once nested. It
cannot build even with a full toolchain.

That is invisible wherever a prebuilt binary exists, because nothing compiles.
On linux-arm64 the 0.21.x tree-sitter generation ships no prebuilt core, so the
build runs, hits the nested copy and fails outright.

Pinning to the same version leaves one hoisted copy. Measured on a clean arm64
VM: before, npm install failed with a toolchain installed; after, it succeeds and
the parser produces 39 csv files and 48128 rows on a real Java project, matching
macOS exactly. The IR is byte for byte identical to 0.21.0 on real Java and
Python projects, so the grammar change is behaviour neutral.

A caret range is not enough: ^0.23.4 resolves to 0.23.5 and nests again. The two
have to name the same version, which is what the new check in
package-contents-test.sh asserts. Verified it fails on the old value.

This does NOT make linux-arm64 installable without a compiler. No 0.21.x core
ships an arm64 prebuild, and no published tree-sitter-java or tree-sitter-groovy
accepts a core above 0.21.x, so there is no version set that reaches one. arm64
still needs build-essential; this only removes the failure that a toolchain could
not fix.

Refs #901
---
 graph/test/tools/package-contents-test.sh | 16 ++++++++++++++++
 package.json                              |  2 +-
 parser/package.json                       |  4 ++--
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/graph/test/tools/package-contents-test.sh b/graph/test/tools/package-contents-test.sh
index 82b603fe..13c580ac 100755
--- a/graph/test/tools/package-contents-test.sh
+++ b/graph/test/tools/package-contents-test.sh
@@ -36,6 +36,22 @@ const deps=j.dependencies||{}, pdeps=JSON.parse(fs.readFileSync(root+"/parser/pa
 Object.keys(deps).length ? ok("runtime dependencies are declared") : bad("package.json declares no runtime dependencies");
 for(const k of Object.keys(pdeps)) deps[k] ? ok("dependency hoisted: "+k) : bad("runtime dependency not hoisted from the parser workspace: "+k);
 
+// ---- the native grammar must not be duplicated ----
+// tree-sitter-groovy pins tree-sitter-java to an exact version. Asking for a different one
+// leaves npm two versions to satisfy and it nests a second copy, whose gyp config resolves
+// node-addon-api by a relative path that is wrong once nested -- so it cannot build even
+// with a full toolchain, and linux-arm64, which has no prebuilt core and must build, fails
+// outright. A caret range is not enough: ^0.23.4 resolves to 0.23.5 and nests again. The two
+// have to name the SAME version. See #901.
+try{
+  const groovy=JSON.parse(fs.readFileSync(root+"/node_modules/tree-sitter-groovy/package.json","utf8"));
+  const want=(groovy.dependencies||{})["tree-sitter-java"];
+  const have=(JSON.parse(fs.readFileSync(root+"/parser/package.json","utf8")).dependencies||{})["tree-sitter-java"];
+  if(!want) ok("tree-sitter-groovy no longer depends on tree-sitter-java");
+  else if(have===want) ok("tree-sitter-java matches the version tree-sitter-groovy pins ("+want+"), so it stays deduped");
+  else bad("tree-sitter-java is "+have+" but tree-sitter-groovy pins "+want+"; npm will nest a second copy that cannot build (#901)");
+}catch(e){ console.log("  skip  tree-sitter-groovy not installed; run npm install to assert the pin"); }
+
 // ---- what the tarball would contain ----
 let files;
 try{
diff --git a/package.json b/package.json
index 500d357b..a6c2dda7 100644
--- a/package.json
+++ b/package.json
@@ -50,7 +50,7 @@
     "tree-sitter": "^0.21.1",
     "tree-sitter-c-sharp": "0.23.1",
     "tree-sitter-groovy": "^0.1.2",
-    "tree-sitter-java": "^0.21.0",
+    "tree-sitter-java": "0.23.4",
     "tree-sitter-python": "^0.21.0",
     "typescript": "^6.0.0",
     "yaml": "^2.8.2"
diff --git a/parser/package.json b/parser/package.json
index a7a5dedf..7c28c154 100644
--- a/parser/package.json
+++ b/parser/package.json
@@ -1,7 +1,7 @@
 {
   "name": "@axiomcode/parser",
   "version": "0.1.0",
-  "description": "AxiomCode Parser \u2014 extracts Java/Python/TypeScript/Gradle/XML/YAML/Properties facts from a codebase.",
+  "description": "AxiomCode Parser — extracts Java/Python/TypeScript/Gradle/XML/YAML/Properties facts from a codebase.",
   "main": "dist/extract.js",
   "types": "dist/extract.d.ts",
   "scripts": {
@@ -20,7 +20,7 @@
     "tree-sitter": "^0.21.1",
     "tree-sitter-c-sharp": "0.23.1",
     "tree-sitter-groovy": "^0.1.2",
-    "tree-sitter-java": "^0.21.0",
+    "tree-sitter-java": "0.23.4",
     "tree-sitter-python": "^0.21.0",
     "typescript": "^6.0.0",
     "yaml": "^2.8.2"