feat(toggl): project info file can override project name

Author: thekaveman

.env.sample

@@ -1,4 +1,5 @@
 HARVEST_CLIENT_NAME=Client1
 HARVEST_DATA=data/harvest-sample.csv
 TOGGL_DATA=data/toggl-sample.csv
+TOGGL_PROJECT_INFO_FILE=data/toggl-project-info-sample.json
 TOGGL_USER_INFO_FILE=data/toggl-user-info-sample.json

.gitignore

@@ -10,5 +10,6 @@ __pycache__
 *.egg-info
 notebooks/data/*
 !notebooks/data/harvest-sample.csv
+!notebooks/data/toggl-project-info-sample.json
 !notebooks/data/toggl-sample.csv
 !notebooks/data/toggl-user-info-sample.json

notebooks/data/toggl-project-info-sample.json

@@ -0,0 +1,4 @@
+{
+  "Project1": "WT1-01 - Project1",
+  "Project3": "WT3-01 - Project3"
+}

notebooks/toggl-to-harvest.ipynb

@@ -17,6 +17,7 @@
         "DATA_DIR = Path(\"./data\")\n",
         "DATA_SOURCE = Path(os.environ.get(\"TOGGL_DATA\", \"./data/toggl-sample.csv\"))\n",
         "\n",
+        "PROJECT_INFO_FILE = os.environ.get(\"TOGGL_PROJECT_INFO_FILE\")\n",
         "USER_INFO_FILE = os.environ.get(\"TOGGL_USER_INFO_FILE\")\n",
         "\n",
         "CLIENT_NAME = os.environ.get(\"HARVEST_CLIENT_NAME\")\n",
@@ -29,13 +30,13 @@
         "    return pd.to_timedelta(pd.to_datetime(td, format=\"%H:%M:%S\").strftime(\"%H:%M:%S\"))\n",
         "\n",
         "\n",
-        "def read_user_info():\n",
-        "    with open(USER_INFO_FILE, \"r\") as ui:\n",
+        "def read_info_file(file):\n",
+        "    with open(file, \"r\") as ui:\n",
         "        return json.load(ui)\n",
         "\n",
         "\n",
-        "def write_user_info(info):\n",
-        "    with open(USER_INFO_FILE, \"w\") as ui:\n",
+        "def write_info_file(file, info):\n",
+        "    with open(file, \"w\") as ui:\n",
         "        json.dump(info, ui, indent=2)"
       ]
     },
@@ -88,6 +89,31 @@
         "source[\"Task\"] = source[\"Task\"].astype(\"category\")"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# cache of previously seen project information, keyed on Toggl project name\n",
+        "PROJECT_INFO = {}\n",
+        "\n",
+        "if PROJECT_INFO_FILE:\n",
+        "    file_info = read_info_file(PROJECT_INFO_FILE)\n",
+        "    PROJECT_INFO.update(file_info)\n",
+        "    print(f\"Project info: {', '.join(PROJECT_INFO.keys())}\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# get cached project name if any\n",
+        "source[\"Project\"] = source[\"Project\"].apply(lambda x: PROJECT_INFO.get(x, x))"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -99,7 +125,7 @@
         "NOT_FOUND = \"NOT FOUND\"\n",
         "\n",
         "if USER_INFO_FILE:\n",
-        "    file_info = read_user_info()\n",
+        "    file_info = read_info_file(USER_INFO_FILE)\n",
         "    USER_INFO.update(file_info)\n",
         "    print(f\"User info: {', '.join(USER_INFO.keys())}\")"
       ]
@@ -158,7 +184,7 @@
       "outputs": [],
       "source": [
         "if len(USER_INFO) > 0 and USER_INFO_FILE:\n",
-        "    write_user_info(USER_INFO)"
+        "    write_info_file(USER_INFO_FILE, USER_INFO)"
       ]
     },
     {