From 280ea308c321115445df610f1a75b05bbadca5f3 Mon Sep 17 00:00:00 2001
From: Dmitry Vyukov <dvyukov@google.com>
Date: Mon, 17 Nov 2025 11:17:23 +0100
Subject: pkg/codesearch: add skeleton for code searching tool

Add a clang tool that is used for code indexing (tools/clang/codesearch/).
It follows conventions and build procedure of the declextract tool.

Add pkg/codesearch package that aggregates the info exposed by the clang tools,
and allows doing simple queries:
 - show source code of an entity (function, struct, etc)
 - show entity comment
 - show all entities defined in a source file

Add tools/syz-codesearch wrapper tool that allows to create index for a kernel build,
and then run code queries on it.
---
 pkg/codesearch/database.go | 56 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 pkg/codesearch/database.go

(limited to 'pkg/codesearch/database.go')

diff --git a/pkg/codesearch/database.go b/pkg/codesearch/database.go
new file mode 100644
index 000000000..4757935e9
--- /dev/null
+++ b/pkg/codesearch/database.go
@@ -0,0 +1,56 @@
+// Copyright 2025 syzkaller project authors. All rights reserved.
+// Use of this source code is governed by Apache 2 LICENSE that can be found in the LICENSE file.
+
+package codesearch
+
+import (
+	"strings"
+
+	"github.com/google/syzkaller/pkg/clangtool"
+)
+
+type Database struct {
+	Definitions []*Definition `json:"definitions,omitempty"`
+}
+
+type Definition struct {
+	Kind     string    `json:"kind,omitempty"`
+	Name     string    `json:"name,omitempty"`
+	Type     string    `json:"type,omitempty"`
+	IsStatic bool      `json:"is_static,omitempty"`
+	Body     LineRange `json:"body,omitempty"`
+	Comment  LineRange `json:"comment,omitempty"`
+}
+
+type LineRange struct {
+	File      string `json:"file,omitempty"`
+	StartLine int    `json:"start_line,omitempty"`
+	EndLine   int    `json:"end_line,omitempty"`
+}
+
+func (db *Database) Merge(other *Database) {
+	db.Definitions = append(db.Definitions, other.Definitions...)
+}
+
+func (db *Database) Finalize(v *clangtool.Verifier) {
+	db.Definitions = clangtool.SortAndDedupSlice(db.Definitions)
+
+	for _, def := range db.Definitions {
+		v.LineRange(def.Body.File, def.Body.StartLine, def.Body.EndLine)
+		if def.Comment.File != "" {
+			v.LineRange(def.Comment.File, def.Comment.StartLine, def.Comment.EndLine)
+		}
+	}
+}
+
+// SetSoureFile attaches the source file to the entities that need it.
+// The clang tool could do it, but it looks easier to do it here.
+func (db *Database) SetSourceFile(file string, updatePath func(string) string) {
+	for _, def := range db.Definitions {
+		def.Body.File = updatePath(def.Body.File)
+		def.Comment.File = updatePath(def.Comment.File)
+		if strings.HasSuffix(def.Body.File, ".c") && def.Body.File != file {
+			def.IsStatic = false
+		}
+	}
+}
-- 
cgit mrf-deployment