From 3c97332fd8440cda2e95f1fc50a6b9755c5867dc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Adri=C3=A0=20Arrufat?= <adria.arrufat@gmail.com>
Date: Mon, 9 Mar 2026 18:23:52 +0900
Subject: [PATCH] feat(dump): add semantic_tree and semantic_tree_text formats

Adds support for dumping the semantic tree in JSON or text format
via the --dump option. Updates the Config enum and usage help.
---
 src/Config.zig     |  4 +++-
 src/lightpanda.zig | 19 +++++++++++++++++++
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/src/Config.zig b/src/Config.zig
index 5a4cc58e..f93c0efa 100644
--- a/src/Config.zig
+++ b/src/Config.zig
@@ -192,6 +192,8 @@ pub const DumpFormat = enum {
     html,
     markdown,
     wpt,
+    semantic_tree,
+    semantic_tree_text,
 };
 
 pub const Fetch = struct {
@@ -338,7 +340,7 @@ pub fn printUsageAndExit(self: *const Config, success: bool) void {
         \\
         \\Options:
         \\--dump          Dumps document to stdout.
-        \\                Argument must be 'html' or 'markdown'.
+        \\                Argument must be 'html', 'markdown', 'semantic_tree', or 'semantic_tree_text'.
         \\                Defaults to no dump.
         \\
         \\--strip_mode    Comma separated list of tag groups to remove from dump
diff --git a/src/lightpanda.zig b/src/lightpanda.zig
index e506e61b..d11a9ff5 100644
--- a/src/lightpanda.zig
+++ b/src/lightpanda.zig
@@ -32,6 +32,7 @@ pub const js = @import("browser/js/js.zig");
 pub const dump = @import("browser/dump.zig");
 pub const markdown = @import("browser/markdown.zig");
 pub const SemanticTree = @import("SemanticTree.zig");
+pub const CDPNode = @import("cdp/Node.zig");
 pub const mcp = @import("mcp.zig");
 pub const build_config = @import("build_config");
 pub const crash_handler = @import("crash_handler.zig");
@@ -108,6 +109,24 @@ pub fn fetch(app: *App, url: [:0]const u8, opts: FetchOpts) !void {
         switch (mode) {
             .html => try dump.root(page.window._document, opts.dump, writer, page),
             .markdown => try markdown.dump(page.window._document.asNode(), .{}, writer, page),
+            .semantic_tree, .semantic_tree_text => {
+                var registry = CDPNode.Registry.init(app.allocator);
+                defer registry.deinit();
+
+                const st = SemanticTree{
+                    .dom_node = page.window._document.asNode(),
+                    .registry = &registry,
+                    .page = page,
+                    .arena = page.call_arena,
+                    .prune = true,
+                };
+
+                if (mode == .semantic_tree) {
+                    try std.json.Stringify.value(st, .{}, writer);
+                } else {
+                    try st.textStringify(writer);
+                }
+            },
             .wpt => try dumpWPT(page, writer),
         }
     }