chore: Implement settings dump schema to update firefox remote servic…, p=#11579

* chore: Implement settings dump schema to update firefox remote services data, b=no-bug, c=configs, scripts

* feat: Also update with timestamps, b=no-bug, c=configs, scripts

* chore: Move JSON with comments to a new module, b=no-bug, c=scripts, tests

---------

Signed-off-by: mr. m <91018726+mr-cheffy@users.noreply.github.com>

configs/dumps/search-config-v2.json

@@ -0,0 +1,20 @@
+// This Source Code Form is subject to the terms of the Mozilla Public
+// License, v. 2.0. If a copy of the MPL was not distributed with this file,
+// You can obtain one at http://mozilla.org/MPL/2.0/.
+{
+  "remove": {
+    "identifiers": [
+      // Firefox adds Perplexity by default, we don't want it as
+      // its not very privacy focused.
+      "perplexity",
+
+      // These are not search engines, Firefox adds them by default
+      // but we don't want them.
+      "wikipedia",
+      "wikipedia-*",
+      "ebay",
+      "ebay-*"
+    ]
+  },
+  "timestamp": 1765455207275
+}

package.json

@@ -10,7 +10,8 @@
     "build": "surfer build",
     "build:ui": "surfer build --ui",
     "start": "cd engine && python3 ./mach run --noprofile",
-    "import": "npm run ffprefs && surfer import",
+    "import": "npm run ffprefs && npm run import:dumps && surfer import",
+    "import:dumps": "python3 scripts/update_service_dumps.py",
     "export": "surfer export",
     "init": "npm run download && npm run import && npm run bootstrap",
     "download": "surfer download",

prefs/firefox/ai.yaml

@@ -20,3 +20,6 @@
 
 - name: browser.ml.chat.menu
   value: false
+
+- name: browser.ml.linkPreview.enabled
+  value: false

scripts/json_with_comments.py

@@ -0,0 +1,14 @@
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+import json
+
+
+class JSONWithCommentsDecoder(json.JSONDecoder):
+  def __init__(self, **kw):
+    super().__init__(**kw)
+
+  def decode(self, s: str) -> Any:
+    s = '\n'.join(l for l in s.split('\n') if not l.lstrip(' ').startswith('//'))
+    return super().decode(s)

scripts/run_tests.py

@@ -7,6 +7,7 @@ import sys
 import json
 from pathlib import Path
 from typing import Any
+from json_with_comments import JSONWithCommentsDecoder
 
 IGNORE_PREFS_FILE_IN = os.path.join(
     'src', 'zen', 'tests', 'ignorePrefs.json'
@@ -16,15 +17,6 @@ IGNORE_PREFS_FILE_OUT = os.path.join(
 )
 
 
-class JSONWithCommentsDecoder(json.JSONDecoder):
-  def __init__(self, **kw):
-    super().__init__(**kw)
-
-  def decode(self, s: str) -> Any:
-    s = '\n'.join(l for l in s.split('\n') if not l.lstrip(' ').startswith('//'))
-    return super().decode(s)
-
-
 def copy_ignore_prefs():
   print("Copying ignorePrefs.json from src/zen/tests to engine/testing/mochitest...")
   # if there are prefs that dont exist on output file, copy them from input file

scripts/update_service_dumps.py

@@ -0,0 +1,63 @@
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+import os
+import json
+from json_with_comments import JSONWithCommentsDecoder
+
+DUMPS_FOLDER = os.path.join(
+    'configs', 'dumps'
+)
+ENGINE_DUMPS_FOLDER = os.path.join(
+    'engine', 'services', 'settings', 'dumps', 'main'
+)
+
+
+def merge_dumps(original, updates):
+  """Filters entries from the original dump, removing those whose identifiers are specified in the updates removal list."""
+  remove_ids = updates.get('remove', {"identifiers": []}).get('identifiers', [])
+
+  # Filter out entries in original that are in remove_ids.
+  #  We may find example-* patterns, so we need to handle that as well.
+  merged_data = [
+      entry for entry in original.get('data', [])
+      if not any(
+          entry.get('identifier', '') == rid or
+          (rid.endswith('*') and entry.get('identifier', '').startswith(rid[:-1]))
+          for rid in remove_ids
+      )
+  ]
+
+  return {
+      'data': merged_data,
+      **{k: v for k, v in original.items() if k != 'data'},
+      'timestamp': updates.get('timestamp', original.get('timestamp'))
+  }
+
+
+def main():
+  for filename in os.listdir(DUMPS_FOLDER):
+    if filename.endswith('.json'):
+      #  parse json with comments
+      with open(os.path.join(DUMPS_FOLDER, filename), 'r') as f:
+        data = json.load(f, cls=JSONWithCommentsDecoder)
+      original_path = os.path.join(ENGINE_DUMPS_FOLDER, filename)
+      if os.path.exists(original_path):
+        with open(original_path, 'r', encoding='utf-8') as f:
+          original_content = f.read()
+          original_content = '\n'.join(
+              line for line in original_content.split('\n') if not line.lstrip(' ').startswith('//')
+          )
+          original_data = json.loads(original_content)
+        merged_data = merge_dumps(original_data, data)
+        with open(original_path, 'w', encoding='utf-8') as f:
+          json.dump(merged_data, f, indent=2, ensure_ascii=False)
+        print(f"Updated dump: {filename}")
+      else:
+        print(f"Original dump file not found: {original_path}")
+        exit(1)
+
+
+if __name__ == "__main__":
+  main()