From 77c4a27c4c37b3620defcab94ffd1b2f536c88cb Mon Sep 17 00:00:00 2001
From: Jules Aguillon
Date: Mon, 2 Feb 2026 00:20:00 +0100
Subject: Spell checking (#1137)

This adds dictionary-based spell checking to the keyboard. The keyboard looks at the word being typed and matches it against a dictionary to either complete the rest of the word or find alternative spellings.

The core of this feature is implemented in cdict, which is included as a
submodule in vendor/cidct.

Cdict is developped at https://github.com/Julow/cdict
The dictionaries are hosted at https://github.com/Julow/Unexpected-Keyboard-dictionaries/
The wordlists used to build the dictionaries are the same ones used by
HeliBoard from https://codeberg.org/Helium314/aosp-dictionaries

- Add an activity accessible from the launcher app that lists available
  dictionaries with a download button.
  The DictionaryListView view shows the list of available dictionaries and
  handles downloading and installing them.

- The Dictionaries class manages installed dictionaries. Dictionaries are
  installed as individual files into the app's private directory.

- Available dictionaries are listed in dictionaries.xml, which is generated
  when building Unexpected-Keyboard-dictionaries.
  method.xml mentions the dictionary name for each locales.
---
 gen_method_xml.py | 63 ++++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 48 insertions(+), 15 deletions(-)

(limited to 'gen_method_xml.py')

diff --git a/gen_method_xml.py b/gen_method_xml.py
index 3b1962f..c01f212 100644
--- a/gen_method_xml.py
+++ b/gen_method_xml.py
@@ -1,3 +1,4 @@
+import xml.etree.ElementTree as ET
 import itertools as it
 
 # This script generates res/xml/method.xml.
@@ -78,37 +79,69 @@ LOCALES = [
 ]
 
 # The locale that is at the beginning of the list
-DEFAULT_LOCALE = loc("en", "latin", "latn_qwerty_us", tag="en")
+DEFAULT_LOCALE = loc("en", "latin", "latn_qwerty_us", tag="en", dictionary="en_US")
 
-def loc_to_subtype(loc):
+def parse_dictionaries():
+    tree = ET.parse("res/values/dictionaries.xml")
+    root = tree.getroot()
+    return set(( it.text for it in root.findall('*[@name="dictionaries_locale"]/item') ))
+
+# Available dictionares of the form "de" or "de_CH".
+available_dictionaries = parse_dictionaries()
+
+def subtype_elem(root, loc):
     tag = loc["tag"].replace("_", "-")
     extra_keys = ",extra_keys=" + loc["extra_keys"] if "extra_keys" in loc else ""
-    return f'<subtype android:label="%s" android:languageTag="{tag}" android:imeSubtypeLocale="{loc["name"]}" android:imeSubtypeMode="keyboard" android:isAsciiCapable="true" android:imeSubtypeExtraValue="script={loc["script"]},default_layout={loc["default_layout"]}{extra_keys}"/>'
+    dictionaries = ",dictionary=" + loc["dictionary"] if loc["dictionary"] != None else ""
+    extra_value = f'script={loc["script"]},default_layout={loc["default_layout"]}{dictionaries}{extra_keys}'
+    ET.SubElement(root, "subtype", attrib={
+        "android:label": "%s",
+        "android:languageTag": tag,
+        "android:imeSubtypeLocale": loc["name"],
+        "android:imeSubtypeMode": "keyboard",
+        "android:isAsciiCapable": "true",
+        "android:imeSubtypeExtraValue": extra_value
+        })
 
-# Return locales in sorted order with the 'tag' item added.
-def compute_tags():
+# Return locales in sorted order with the "tag" and "dictionary" attributes
+# added.
+def compute_attrs():
+    locales_grouped = {} # Locales grouped by language tag
     def lang(loc):
         return loc["name"].split("_")[0]
-    locales_grouped = { k: list(v) for k, v in it.groupby(sorted(LOCALES, key=lang), lang) }
+    for loc in LOCALES:
+        locales_grouped.setdefault(lang(loc), []).append(loc)
     def tag(loc):
         if "tag" in loc: return loc["tag"]
         l = lang(loc)
         if loc["name"] == f"{l}_{l.upper()}": return l # Locales like "fr_FR"
         # Return a short tag when it's not shared between several locales
         return l if len(locales_grouped[l]) == 1 else loc["name"]
-    return [ dict(tag=tag(loc), **loc) for loc in LOCALES ]
+    def dictionary(loc):
+        if loc["name"] in available_dictionaries: return loc["name"]
+        l = lang(loc)
+        if l in available_dictionaries: return l
+        return None
+    def add_attrs(loc):
+        return dict(tag=tag(loc), dictionary=dictionary(loc), **loc)
+    return map(add_attrs, LOCALES)
 
 def gen():
-    locales = compute_tags()
-    print(f"""<?xml version="1.0" encoding="utf-8"?>
-<input-method xmlns:android="http://schemas.android.com/apk/res/android" android:settingsActivity="juloo.keyboard2.SettingsActivity" android:supportsSwitchingToNextInputMethod="true">
-  <!-- This file is automatically generated. DO NOT EDIT.
+    locales = compute_attrs()
+    root = ET.Element("input-method", attrib={
+        "xmlns:android": "http://schemas.android.com/apk/res/android",
+        "android:settingsActivity": "juloo.keyboard2.SettingsActivity",
+        "android:supportsSwitchingToNextInputMethod": "true",
+        })
+    root.append(ET.Comment(text=""" This file is automatically generated. DO NOT EDIT.
        Locales definitions should go into 'gen_method_xml.py'.
        Update this file with 'gradle test'.
 
-  -->
-  {loc_to_subtype(DEFAULT_LOCALE)}
-  {"\n  ".join(sorted(map(loc_to_subtype, locales)))}
-</input-method>""")
+  """))
+    subtype_elem(root, DEFAULT_LOCALE)
+    for loc in sorted(locales, key=lambda loc: loc["name"]):
+        subtype_elem(root, loc)
+    ET.indent(root)
+    print(ET.tostring(root, encoding="utf-8", xml_declaration=True).decode("UTF-8"))
 
 gen()
-- 
cgit v1.2.3