Ruby/QL: unconditionally generate discard predicates

ql/extractor/src/generator.rs

@@ -36,5 +36,5 @@ pub fn run(options: Options) -> std::io::Result<()> {
         },
     ];
 
-    generate(languages, options.dbscheme, options.library, false)
+    generate(languages, options.dbscheme, options.library)
 }

ql/ql/src/codeql_ql/ast/internal/TreeSitter.qll

@@ -5,6 +5,10 @@
 
 import codeql.Locations as L
 
+/** Holds if the database is an overlay. */
+overlay[local]
+private predicate isOverlay() { databaseMetadata("isOverlay", "true") }
+
 module QL {
   /** The base class for all AST nodes */
   class AstNode extends @ql_ast_node {
@@ -48,6 +52,30 @@ module QL {
     final override string getAPrimaryQlClass() { result = "ReservedWord" }
   }
 
+  /** Gets the file containing the given `node`. */
+  overlay[local]
+  private @file getNodeFile(@ql_ast_node node) {
+    exists(@location_default loc | ql_ast_node_location(node, loc) |
+      locations_default(loc, result, _, _, _, _)
+    )
+  }
+
+  /** Holds if `file` was extracted as part of the overlay database. */
+  overlay[local]
+  private predicate discardFile(@file file) { isOverlay() and file = getNodeFile(_) }
+
+  /** Holds if `node` is in the `file` and is part of the overlay base database. */
+  overlay[local]
+  private predicate discardableAstNode(@file file, @ql_ast_node node) {
+    not isOverlay() and file = getNodeFile(node)
+  }
+
+  /** Holds if `node` should be discarded, because it is part of the overlay base and is in a file that was also extracted as part of the overlay database. */
+  overlay[discard_entity]
+  private predicate discardAstNode(@ql_ast_node node) {
+    exists(@file file | discardableAstNode(file, node) and discardFile(file))
+  }
+
   /** A class representing `add_expr` nodes. */
   class AddExpr extends @ql_add_expr, AstNode {
     /** Gets the name of the primary QL class for this element. */
@@ -1318,6 +1346,30 @@ module Dbscheme {
     final override string getAPrimaryQlClass() { result = "ReservedWord" }
   }
 
+  /** Gets the file containing the given `node`. */
+  overlay[local]
+  private @file getNodeFile(@dbscheme_ast_node node) {
+    exists(@location_default loc | dbscheme_ast_node_location(node, loc) |
+      locations_default(loc, result, _, _, _, _)
+    )
+  }
+
+  /** Holds if `file` was extracted as part of the overlay database. */
+  overlay[local]
+  private predicate discardFile(@file file) { isOverlay() and file = getNodeFile(_) }
+
+  /** Holds if `node` is in the `file` and is part of the overlay base database. */
+  overlay[local]
+  private predicate discardableAstNode(@file file, @dbscheme_ast_node node) {
+    not isOverlay() and file = getNodeFile(node)
+  }
+
+  /** Holds if `node` should be discarded, because it is part of the overlay base and is in a file that was also extracted as part of the overlay database. */
+  overlay[discard_entity]
+  private predicate discardAstNode(@dbscheme_ast_node node) {
+    exists(@file file | discardableAstNode(file, node) and discardFile(file))
+  }
+
   /** A class representing `annotName` tokens. */
   class AnnotName extends @dbscheme_token_annot_name, Token {
     /** Gets the name of the primary QL class for this element. */
@@ -1654,6 +1706,30 @@ module Blame {
     final override string getAPrimaryQlClass() { result = "ReservedWord" }
   }
 
+  /** Gets the file containing the given `node`. */
+  overlay[local]
+  private @file getNodeFile(@blame_ast_node node) {
+    exists(@location_default loc | blame_ast_node_location(node, loc) |
+      locations_default(loc, result, _, _, _, _)
+    )
+  }
+
+  /** Holds if `file` was extracted as part of the overlay database. */
+  overlay[local]
+  private predicate discardFile(@file file) { isOverlay() and file = getNodeFile(_) }
+
+  /** Holds if `node` is in the `file` and is part of the overlay base database. */
+  overlay[local]
+  private predicate discardableAstNode(@file file, @blame_ast_node node) {
+    not isOverlay() and file = getNodeFile(node)
+  }
+
+  /** Holds if `node` should be discarded, because it is part of the overlay base and is in a file that was also extracted as part of the overlay database. */
+  overlay[discard_entity]
+  private predicate discardAstNode(@blame_ast_node node) {
+    exists(@file file | discardableAstNode(file, node) and discardFile(file))
+  }
+
   /** A class representing `blame_entry` nodes. */
   class BlameEntry extends @blame_blame_entry, AstNode {
     /** Gets the name of the primary QL class for this element. */
@@ -1767,6 +1843,30 @@ module JSON {
     final override string getAPrimaryQlClass() { result = "ReservedWord" }
   }
 
+  /** Gets the file containing the given `node`. */
+  overlay[local]
+  private @file getNodeFile(@json_ast_node node) {
+    exists(@location_default loc | json_ast_node_location(node, loc) |
+      locations_default(loc, result, _, _, _, _)
+    )
+  }
+
+  /** Holds if `file` was extracted as part of the overlay database. */
+  overlay[local]
+  private predicate discardFile(@file file) { isOverlay() and file = getNodeFile(_) }
+
+  /** Holds if `node` is in the `file` and is part of the overlay base database. */
+  overlay[local]
+  private predicate discardableAstNode(@file file, @json_ast_node node) {
+    not isOverlay() and file = getNodeFile(node)
+  }
+
+  /** Holds if `node` should be discarded, because it is part of the overlay base and is in a file that was also extracted as part of the overlay database. */
+  overlay[discard_entity]
+  private predicate discardAstNode(@json_ast_node node) {
+    exists(@file file | discardableAstNode(file, node) and discardFile(file))
+  }
+
   class UnderscoreValue extends @json_underscore_value, AstNode { }
 
   /** A class representing `array` nodes. */

ruby/extractor/src/generator.rs

@@ -28,5 +28,5 @@ pub fn run(options: Options) -> std::io::Result<()> {
         },
     ];
 
-    generate(languages, options.dbscheme, options.library, true)
+    generate(languages, options.dbscheme, options.library)
 }

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

@@ -17,7 +17,6 @@ pub fn generate(
     languages: Vec<language::Language>,
     dbscheme_path: PathBuf,
     ql_library_path: PathBuf,
-    overlay_support: bool,
 ) -> std::io::Result<()> {
     let dbscheme_file = File::create(dbscheme_path).map_err(|e| {
         tracing::error!("Failed to create dbscheme file: {}", e);
@@ -50,14 +49,12 @@ pub fn generate(
         })],
     )?;
 
-    if overlay_support {
     ql::write(
         &mut ql_writer,
         &[ql::TopLevel::Predicate(
             ql_gen::create_is_overlay_predicate(),
         )],
     )?;
-    }
 
     for language in languages {
         let prefix = node_types::to_snake_case(&language.name);
@@ -103,7 +100,7 @@ pub fn generate(
             ql::TopLevel::Class(ql_gen::create_reserved_word_class(&reserved_word_name)),
         ];
 
-        if overlay_support {
+        // Overlay discard predicates
         body.push(ql::TopLevel::Predicate(
             ql_gen::create_get_node_file_predicate(&ast_node_name, &node_location_table_name),
         ));
@@ -116,7 +113,6 @@ pub fn generate(
         body.push(ql::TopLevel::Predicate(
             ql_gen::create_discard_ast_node_predicate(&ast_node_name),
         ));
-        }
 
         body.append(&mut ql_gen::convert_nodes(&nodes));
         ql::write(