scribe-org#14 cldr package downloads

.gitignore

@@ -17,3 +17,8 @@ dist
 *.egg-info
 # Caches
 __pycache__
+
+# NPM files
+###########
+node_modules
+package-lock.json

package.json

@@ -0,0 +1,5 @@
+{
+  "dependencies": {
+    "cldr-annotations-derived-full": "latest"
+  }
+}

src/scribe_data/extract_transform/process_unicode.py

@@ -8,6 +8,10 @@
     gen_emoji_autosuggestions
 """
 
+import json
+
+from scribe_data.load.update_utils import get_language_iso
+
 def gen_emoji_autosuggestions(
     language="English",
     num_emojis=500,
@@ -42,6 +46,19 @@ def gen_emoji_autosuggestions(
 
     autosuggest_dict = {}
 
-    # TODO
+    ### TODO further updates - here for data loading illustration
+
+    language = get_language_iso(language)
+
+    cldr_file_path = f'node_modules/cldr-annotations-derived-full/annotationsDerived/{language}/annotations.json'
+
+    with open(cldr_file_path, 'r') as file:
+        cldr_data = json.load(file)
+
+    emoji_dict = cldr_data['annotationsDerived']['annotations']
+
+    print("Number of emojis loaded:", len(emoji_dict))
+
+    ###
 
     return autosuggest_dict

src/scribe_data/load/gen_emoji_suggestions.ipynb

@@ -71,6 +71,26 @@
     "pwd = pwd.split(\"scribe_data\")[0]\n",
     "sys.path.append(pwd)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2add942e",
+   "metadata": {},
+   "source": [
+    "# Download Latest Unicode"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8e166da1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%bash\n",
+    ". $HOME/.nvm/nvm.sh # Pick up the 'npm' command\n",
+    "npm install"
+   ]
   }
  ],
  "metadata": {