Route Scala and Rust through the structural matcher; fix root-wrapper unwrap

ober

8b254864da543a13c1cdfe14f82d4ec5a1c394c0

diff --git a/lib/semgrep/match/structural.sls b/lib/semgrep/match/structural.sls
index 49b2ecb..3fb2e84 100644
--- a/lib/semgrep/match/structural.sls
+++ b/lib/semgrep/match/structural.sls
@@ -571,6 +571,15 @@
          [(go-language? language)
           (or (string=? type "source_file")
               (string=? type "expression_statement"))]
+         [(string=? language "java")
+          (or (string=? type "program")
+              (string=? type "expression_statement"))]
+         [(string=? language "scala")
+          (or (string=? type "compilation_unit")
+              (string=? type "expression_statement"))]
+         [(string=? language "rust")
+          (or (string=? type "source_file")
+              (string=? type "expression_statement"))]
          [else #f]))
   (def (normalized-pattern-root language root)
        (let loop ([current root] [owned '()])
diff --git a/lib/semgrep/parse/parse-target.sls b/lib/semgrep/parse/parse-target.sls
index 017cc2f..433a82f 100644
--- a/lib/semgrep/parse/parse-target.sls
+++ b/lib/semgrep/parse/parse-target.sls
@@ -26,6 +26,8 @@
            [(string=? canonical "go") 'go]
            [(string=? canonical "php") 'php]
            [(string=? canonical "java") 'java]
+           [(string=? canonical "scala") 'scala]
+           [(string=? canonical "rust") 'rust]
            [else
             (error 'parse-target-string
               "unsupported language in current MVP"
diff --git a/lib/semgrep/scan.sls b/lib/semgrep/scan.sls
index a8eace9..099b7dc 100644
--- a/lib/semgrep/scan.sls
+++ b/lib/semgrep/scan.sls
@@ -750,8 +750,6 @@
              (string=? canonical "julia")
              (string=? canonical "kotlin")
              (string=? canonical "ruby")
-             (string=? canonical "rust")
-             (string=? canonical "scala")
              (string=? canonical "cpp"))))
   (def (c-language? language)
        (let ([canonical (or (canonical-language language)
@@ -31276,6 +31274,10 @@
              "$L[$I] = $R"
              "for $L in $R:\n  ..."
              "def $F(..., $L = $R, ...):\n  ...")]
+         [(string=? language "scala")
+          '("$L = $R" "$L[$I] = $R" "val $L = $R" "var $L = $R")]
+         [(string=? language "rust")
+          '("$L = $R" "$L[$I] = $R" "let $L = $R" "let mut $L = $R")]
          [else '("$L = $R" "$L[$I] = $R")]))
   (def (scan-implicit-assignment-propagators rule language
          path source target-root)
diff --git a/src/.jerbuild-hashes b/src/.jerbuild-hashes
index e69d31d..bacd135 100644
--- a/src/.jerbuild-hashes
+++ b/src/.jerbuild-hashes
@@ -2,12 +2,12 @@
   ("src/semgrep/result.ss" . "22D23E40B49BA529")
   ("src/semgrep/output/json.ss" . "293881CFA2ADB7BC")
   ("src/semgrep/lang.ss" . "6982E07679D20836")
-  ("src/semgrep/parse/parse-target.ss" . "DD1EF1A5E883A90D")
-  ("src/semgrep/scan.ss" . "4EA92FEDD236FE4F")
-  ("src/semgrep/schema/lang.ss" . "CAE2CA859C9A9FD0")
-  ("src/semgrep/rule.ss" . "E12C108153C181FA")
+  ("src/semgrep/parse/parse-target.ss" . "3FE8E8985B2E3461")
+  ("src/semgrep/scan.ss" . "70E81C1629B569BB")
   ("src/semgrep/fix.ss" . "2E5B65B1FEF3B2B1")
   ("src/semgrep/output/text.ss" . "BE476CB84B807FBA")
-  ("src/semgrep/match/structural.ss" . "DF9CD3E0C00E5D40")
+  ("src/semgrep/rule.ss" . "E12C108153C181FA")
+  ("src/semgrep/schema/lang.ss" . "CAE2CA859C9A9FD0")
+  ("src/semgrep/match/structural.ss" . "331D07881B8C8C56")
   ("src/semgrep/main.ss" . "A4EC9E7F2A09D25E")
   ("src/semgrep/cli.ss" . "EBDC4B1DAD3F13CC"))
diff --git a/src/semgrep/match/structural.ss b/src/semgrep/match/structural.ss
index 221408a..3d2e185 100644
--- a/src/semgrep/match/structural.ss
+++ b/src/semgrep/match/structural.ss
@@ -595,6 +595,15 @@
     [(go-language? language)
      (or (string=? type "source_file")
          (string=? type "expression_statement"))]
+    [(string=? language "java")
+     (or (string=? type "program")
+         (string=? type "expression_statement"))]
+    [(string=? language "scala")
+     (or (string=? type "compilation_unit")
+         (string=? type "expression_statement"))]
+    [(string=? language "rust")
+     (or (string=? type "source_file")
+         (string=? type "expression_statement"))]
     [else #f]))
 
 (def (normalized-pattern-root language root)
diff --git a/src/semgrep/parse/parse-target.ss b/src/semgrep/parse/parse-target.ss
index f72abcb..3b2b0da 100644
--- a/src/semgrep/parse/parse-target.ss
+++ b/src/semgrep/parse/parse-target.ss
@@ -18,6 +18,8 @@
       [(string=? canonical "go") 'go]
       [(string=? canonical "php") 'php]
       [(string=? canonical "java") 'java]
+      [(string=? canonical "scala") 'scala]
+      [(string=? canonical "rust") 'rust]
       [else
        (error 'parse-target-string "unsupported language in current MVP" language)])))
 
diff --git a/src/semgrep/scan.ss b/src/semgrep/scan.ss
index 11ebbeb..bc4e4bd 100644
--- a/src/semgrep/scan.ss
+++ b/src/semgrep/scan.ss
@@ -822,8 +822,6 @@
         (string=? canonical "julia")
         (string=? canonical "kotlin")
         (string=? canonical "ruby")
-        (string=? canonical "rust")
-        (string=? canonical "scala")
         (string=? canonical "cpp"))))
 
 (def (c-language? language)
@@ -31254,6 +31252,18 @@
        "$L[$I] = $R"
        "for $L in $R:\n  ..."
        "def $F(..., $L = $R, ...):\n  ...")]
+    [(string=? language "scala")
+     ;; Scala bindings are val/var definitions, not bare assignments.
+     '("$L = $R"
+       "$L[$I] = $R"
+       "val $L = $R"
+       "var $L = $R")]
+    [(string=? language "rust")
+     ;; Rust bindings are let declarations.
+     '("$L = $R"
+       "$L[$I] = $R"
+       "let $L = $R"
+       "let mut $L = $R")]
     [else '("$L = $R"
             "$L[$I] = $R")]))