fix(manifest_ingest): resolve inherited groupId and ${...} properties in pom.xml (#3806)

(cherry picked from commit 292b9d8465)

graphify/manifest_ingest.py

@@ -289,17 +289,39 @@ def _parse_pom(text: str) -> dict | None:
     text = re.sub(r'\sxmlns="[^"]*"', '', text, count=1)
     root = ET.fromstring(text)
     aid = root.findtext("artifactId")
-    gid = root.findtext("groupId")
+    gid = root.findtext("groupId") or root.findtext("parent/groupId")
+    version = root.findtext("version") or root.findtext("parent/version")
     if not aid:
         return None
+    props: dict[str, str] = {}
+    for prop in root.findall("properties/*"):
+        if isinstance(prop.tag, str) and prop.text:
+            props[prop.tag] = prop.text.strip()
+    for key, value in (
+        ("project.groupId", gid),
+        ("project.artifactId", aid),
+        ("project.version", version),
+        ("project.parent.groupId", root.findtext("parent/groupId")),
+        ("project.parent.version", root.findtext("parent/version")),
+    ):
+        if value:
+            props.setdefault(key, value.strip())
+
+    def _resolve(value: str | None) -> str | None:
+        if not value:
+            return value
+        return re.sub(r"\$\{([^}]+)\}", lambda m: props.get(m.group(1), m.group(0)), value.strip())
+
+    gid = _resolve(gid)
+    version = _resolve(version)
     name = f"{gid}:{aid}" if gid else aid
     deps: list[str] = []
     for dep in root.findall(".//dependencies/dependency"):
-        da = dep.findtext("artifactId")
-        dg = dep.findtext("groupId")
+        da = _resolve(dep.findtext("artifactId"))
+        dg = _resolve(dep.findtext("groupId"))
         if da:
             deps.append(f"{dg}:{da}" if dg else da)
-    return {"name": name, "version": root.findtext("version"), "deps": deps}
+    return {"name": name, "version": version, "deps": deps}
 
 
 _PARSERS = {

tests/test_manifest_ingest.py

@@ -163,3 +163,42 @@ def test_cargo_workspace_inherited_version_does_not_crash(tmp_path):
                '[package]\nname = "member"\nversion.workspace = true\n')
     pkg = _pkg_nodes(extract_package_manifest(p))[0]
     assert pkg["label"] == "member" and "version" not in pkg
+
+
+# ── #3806: inherited groupId and ${...} properties in pom.xml ────────────────
+
+def test_pom_inherits_groupid_and_resolves_properties(tmp_path):
+    _write(tmp_path / "rsc/pom.xml",
+           '<project xmlns="http://maven.apache.org/POM/4.0.0">\n'
+           '  <parent><groupId>org.acme</groupId><artifactId>main</artifactId><version>1.0</version></parent>\n'
+           '  <groupId>org.acme</groupId>\n  <artifactId>acme-rsc</artifactId>\n</project>\n')
+    _write(tmp_path / "server/pom.xml",
+           '<project xmlns="http://maven.apache.org/POM/4.0.0">\n'
+           '  <parent><groupId>org.acme</groupId><artifactId>main</artifactId><version>1.0</version></parent>\n'
+           '  <artifactId>acme-server</artifactId>\n'
+           '  <properties><core.suffix>2.12</core.suffix></properties>\n'
+           '  <dependencies>\n'
+           '    <dependency><groupId>${project.groupId}</groupId><artifactId>acme-rsc</artifactId></dependency>\n'
+           '    <dependency><groupId>org.acme</groupId><artifactId>acme-core_${core.suffix}</artifactId></dependency>\n'
+           '  </dependencies>\n</project>\n')
+    _write(tmp_path / "web/pom.xml",
+           '<project xmlns="http://maven.apache.org/POM/4.0.0">\n'
+           '  <parent><groupId>org.acme</groupId><artifactId>main</artifactId><version>1.0</version></parent>\n'
+           '  <artifactId>acme-web</artifactId>\n'
+           '  <dependencies>\n'
+           '    <dependency><groupId>org.acme</groupId><artifactId>acme-server</artifactId></dependency>\n'
+           '  </dependencies>\n</project>\n')
+
+    server = extract_package_manifest(tmp_path / "server/pom.xml")
+    pkg = _pkg_nodes(server)[0]
+    assert pkg["label"] == "org.acme:acme-server" and pkg["version"] == "1.0"
+    targets = {e["target"] for e in server["edges"] if e["relation"] == "depends_on"}
+    assert {"pkg_org_acme_acme_rsc", "pkg_org_acme_acme_core_2_12"} <= targets
+
+    result = extract(sorted(tmp_path.rglob("pom.xml")), cache_root=tmp_path)
+    g = build_from_json(result)
+    labels = {n: d.get("label") for n, d in g.nodes(data=True)}
+    dep_edges = {frozenset((labels[u], labels[v])) for u, v, d in g.edges(data=True)
+                 if d.get("relation") == "depends_on"}
+    assert frozenset(("org.acme:acme-server", "org.acme:acme-rsc")) in dep_edges
+    assert frozenset(("org.acme:acme-web", "org.acme:acme-server")) in dep_edges