Improving docker & gsheet publishing (#149)

* Update export_sheets.py (don't clear wk content)

* rename sheet_id arg to sheet_name (to match content)

* small docker using reorganization

* improving gsheet publishing (updated start_cell logic, add clear_sheet logic)

Author: HadronCollider

.dockerignore

@@ -0,0 +1,5 @@
+.github
+.git
+forgejo
+Industrial_Nikolaev_AA_9381
+reports

Dockerfile

@@ -1,13 +1,13 @@
-FROM python:3.10-slim
+FROM python:3.12-slim
 
+ENV GIT_PYTHON_GIT_EXECUTABLE=/usr/bin/git
 WORKDIR /app
 
 RUN apt-get update && apt-get install -y git && rm -rf /var/lib/apt/lists/*
 
-COPY . /app
-
+COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-ENV GIT_PYTHON_GIT_EXECUTABLE=/usr/bin/git
+COPY . /app
 
 ENTRYPOINT ["python", "main.py"]

main.py

@@ -41,7 +41,7 @@ def parse_args():
         type=str,
         required=False,
         help='Starting cell for Google Sheets export (e.g., "A1", "B3")',
-        default=None
+        default="A1"
     )
 
     parser.add_argument(
@@ -117,11 +117,17 @@ def parse_args():
         help='Specify Google sheet document id (can find in url)',
     )
     parser.add_argument(
-        '--sheet_id',
+        '--sheet_name',
         type=str,
         required=False,
         help='Specify title for a sheet in a document in which data will be printed',
     )
+    parser.add_argument(
+        "--clear_sheet",
+        action="store_true",
+        required=False,
+        help="Specify to clear sheet content before printing",
+    )
     args = parser.parse_args()
 
     if args.export_google_sheets:
@@ -130,7 +136,7 @@ def parse_args():
                 action.required = True
             if action.dest == 'table_id':
                 action.required = True
-            if action.dest == 'sheet_id':
+            if action.dest == 'sheet_name':
                 action.required = True
     return parser.parse_args()
 
@@ -170,25 +176,24 @@ def run(args, binded_repos, repos_for_wiki=None):
     if args.wikis:
         wikipars.wikiparser(repos_for_wiki, args.download_repos, args.out)
     if args.export_google_sheets:
-        if args.start_cell:
-            export_sheets.write_data_to_table(
-                args.out, args.google_token, args.table_id, args.sheet_id, args.start_cell
-            )
-        else:
-            export_sheets.write_data_to_table(
-                args.out, args.google_token, args.table_id, args.sheet_id
-            )
+        export_sheets.write_data_to_table(
+            csv_path=args.out,
+            google_token=args.google_token,
+            table_id=args.table_id,
+            sheet_name=args.sheet_name,
+            start_cell=args.start_cell,
+            clear_content=args.clear_sheet,
+        )
 
 
 def main():
     args = parse_args()
 
-    if args.start_cell is not None:
-        try:
-            args.start_cell = validate_and_normalize_cell(args.start_cell)
-        except ValueError as e:
-            print(f"Error in start_cell argument: {e}")
-            sys.exit(1)
+    try:
+        args.start_cell = validate_and_normalize_cell(args.start_cell)
+    except ValueError as e:
+        print(f"Error in start_cell argument: {e}")
+        sys.exit(1)
 
     if args.token:
         tokens = [args.token]

src/export_sheets.py

@@ -4,25 +4,26 @@
 INT_MASS = [{"one": 1, "two": 2, "what?": 3}]
 
 
-def write_data_to_table(csv_path, google_token, table_id, sheet_id, start_cell="A1"):
-    if google_token and sheet_id and table_id:
+def write_data_to_table(csv_path, google_token, table_id, sheet_name, start_cell="A1", clear_content=False):
+    if google_token and sheet_name and table_id:
         gc = pygsheets.authorize(service_file=google_token)
         sh = gc.open_by_key(table_id)
 
     try:
-        sh.worksheets('title', sheet_id)
+        sh.worksheets('title', sheet_name)
     except Exception:
-        sh.add_worksheet(sheet_id)
+        sh.add_worksheet(sheet_name)
 
-    wk_content = sh.worksheet_by_title(sheet_id)
+    wk_content = sh.worksheet_by_title(sheet_name)
 
     if csv_path:
         df = pd.read_csv(csv_path, delimiter=',', encoding='utf-8')
     else:
         df = pd.DataFrame(INT_MASS)
 
     # Очистка существующих данных
-    wk_content.clear()
+    if clear_content:
+        wk_content.clear()
 
     # Запись новых данных
-    wk_content.set_dataframe(df, start_cell, copy_head=True)
+    wk_content.set_dataframe(df=df, start=start_cell, copy_head=True, nan='')