pidatametrics1 0.3.5__tar.gz → 0.3.7__tar.gz

{pidatametrics1-0.3.5 → pidatametrics1-0.3.7}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: pidatametrics1
-Version: 0.3.5
-Summary: A wrapper for Pi Datametrics API with CSV and BigQuery support.
+Version: 0.3.7
+Summary: A test wrapper for Pi Datametrics API with CSV and BigQuery support.
 Requires-Dist: google-auth
 Requires-Dist: google-cloud-bigquery
 Requires-Dist: gspread

{pidatametrics1-0.3.5 → pidatametrics1-0.3.7}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "hatchling.build"
 
 [project]
 name = "pidatametrics1"
-version = "0.3.5"
-description = "A wrapper for Pi Datametrics API with CSV and BigQuery support."
+version = "0.3.7"
+description = "A test wrapper for Pi Datametrics API with CSV and BigQuery support."
 dependencies = [
     "requests",
     "google-cloud-bigquery",

{pidatametrics1-0.3.5 → pidatametrics1-0.3.7}/src/pidatametrics/exporter.py

@@ -1,12 +1,15 @@
 import csv
-import json
+import re
+import math
 from google.cloud import bigquery
 
-# Optional imports with error handling
+# Optional imports
 try:
     import pandas as pd
+    from openpyxl.cell.cell import ILLEGAL_CHARACTERS_RE
 except ImportError:
     pd = None
+    ILLEGAL_CHARACTERS_RE = None
 
 try:
     import gspread
@@ -15,6 +18,17 @@ except ImportError:
     gspread = None
 
 class PiExporter:
+    
+    @staticmethod
+    def _clean_for_excel(text):
+        """Removes characters that cause Excel to crash/corrupt."""
+        if not isinstance(text, str):
+            return text
+        # Remove illegal control characters (null bytes, etc.)
+        if ILLEGAL_CHARACTERS_RE:
+            return ILLEGAL_CHARACTERS_RE.sub('', text)
+        return text
+
     @staticmethod
     def to_csv(data, filename):
         if not data:
@@ -33,9 +47,11 @@ class PiExporter:
 
     @staticmethod
     def to_excel(data, filename):
-        """Exports data to Excel. Requires pandas and openpyxl."""
+        """
+        Exports to Excel with sanitization to prevent 'Corrupted File' errors.
+        """
         if pd is None:
-            print("Error: Pandas not installed. Run: pip install pandas openpyxl")
+            print("Error: Pandas/Openpyxl not installed.")
             return
         if not data:
             print("No data to export.")
@@ -44,58 +60,87 @@ class PiExporter:
         if not filename.endswith('.xlsx'):
             filename += '.xlsx'
 
+        print(f"Preparing Excel file: {filename} ({len(data)} rows)...")
+
         try:
+            # 1. Create DataFrame
             df = pd.DataFrame(data)
-            df.to_excel(filename, index=False)
+
+            # 2. Sanitize Data (Fixes "Excel found a problem with content")
+            # Apply cleaning to all string columns
+            for col in df.select_dtypes(include=['object']).columns:
+                df[col] = df[col].apply(PiExporter._clean_for_excel)
+
+            # 3. Export
+            df.to_excel(filename, index=False, engine='openpyxl')
             print(f"Successfully saved {len(data)} rows to {filename}")
+            
         except Exception as e:
             print(f"Excel Export Failed: {e}")
 
     @staticmethod
     def to_google_sheet(data, spreadsheet_name, tab_name="Sheet1"):
-        """
-        Exports to Google Sheet using the Filename (not ID).
-        Uses the active Colab authentication.
-        """
         if gspread is None:
-            print("Error: gspread not installed. Run: pip install gspread google-auth")
+            print("Error: gspread not installed.")
             return
         if not data:
             print("No data to upload.")
             return
 
-        print(f"Connecting to Google Sheet: '{spreadsheet_name}'...")
+        row_count = len(data)
+        print(f"Preparing Google Sheet upload: {row_count} rows...")
+
+        # --- WARNING FOR LARGE DATASETS ---
+        if row_count > 50000:
+            print(f"⚠️  WARNING: You are uploading {row_count} rows.")
+            print("   Google Sheets may become slow. Uploading in chunks...")
 
         try:
-            # 1. Get Default Credentials (works with Colab auth.authenticate_user)
+            # 1. Auth
             creds, _ = google.auth.default()
             client = gspread.authorize(creds)
 
-            # 2. Open by Name (Title)
+            # 2. Open Sheet
             try:
                 sh = client.open(spreadsheet_name)
             except gspread.SpreadsheetNotFound:
                 print(f"Sheet '{spreadsheet_name}' not found. Creating it...")
                 sh = client.create(spreadsheet_name)
 
-            # 3. Select or Create Worksheet (Tab)
+            # 3. Setup Tab
             try:
                 worksheet = sh.worksheet(tab_name)
-                worksheet.clear() # Clear old data
+                worksheet.clear()
             except gspread.WorksheetNotFound:
-                worksheet = sh.add_worksheet(title=tab_name, rows=len(data)+100, cols=20)
+                worksheet = sh.add_worksheet(title=tab_name, rows=row_count+100, cols=20)
 
             # 4. Prepare Data
             headers = list(data[0].keys())
             rows = [[row.get(col, '') for col in headers] for row in data]
-            all_values = [headers] + rows
+            
+            # 5. Upload Headers first
+            worksheet.update([headers], 'A1')
+
+            # 6. CHUNKED UPLOAD (To prevent timeouts on large data)
+            chunk_size = 5000  # Safe limit for gspread
+            total_chunks = math.ceil(len(rows) / chunk_size)
+
+            print(f"Starting upload in {total_chunks} chunks...")
+
+            for i in range(total_chunks):
+                start = i * chunk_size
+                end = start + chunk_size
+                chunk = rows[start:end]
+                
+                # Append rows is safer for large datasets than update range
+                worksheet.append_rows(chunk, value_input_option='RAW')
+                
+                print(f"   - Uploaded chunk {i+1}/{total_chunks} ({len(chunk)} rows)")
 
-            # 5. Update
-            worksheet.update(all_values)
-            print(f"Successfully uploaded {len(data)} rows to '{spreadsheet_name}' (Tab: {tab_name})")
+            print(f"✅ Successfully uploaded {row_count} rows to '{spreadsheet_name}' (Tab: {tab_name})")
 
         except Exception as e:
-            print(f"Google Sheet Upload Failed: {e}")
+            print(f"❌ Google Sheet Upload Failed: {e}")
 
     @staticmethod
     def to_bigquery(data, project_id, dataset_id, table_id):

{pidatametrics1-0.3.5 → pidatametrics1-0.3.7}/src/pidatametrics/manager.py

@@ -6,22 +6,21 @@ from dateutil.relativedelta import relativedelta
 
 class PiReportManager(PiDataMetrics):
     
-    # --- HELPER: Generate Unique Tab Name ---
-    def _generate_tab_name(self, base_name, workspace_ref=None):
+    # --- HELPER: Generate Unique Name ---
+    def _generate_unique_name(self, base_name, workspace_ref=None):
         """
-        Creates a tab name like: Volume_12345_0502_1430
+        Creates a unique name like: Hist_51780_0502_1430
         (Base_WorkspaceID_Date_Time)
         """
         now = datetime.datetime.now()
-        timestamp = now.strftime("%d%m_%H%M") # e.g., 0502_1430 (5th Feb, 14:30)
+        timestamp = now.strftime("%d%m_%H%M") # e.g., 0502_1430
         
         ws_part = f"_{workspace_ref}" if workspace_ref else ""
         
-        # Google Sheets tab limit is 31 chars. 
-        # Timestamp (9) + Base (approx 10) leaves ~10 for ID.
+        # Combine parts
         full_name = f"{base_name}{ws_part}_{timestamp}"
         
-        # Truncate to 31 chars to avoid API errors
+        # Truncate to 31 chars (Google Sheets limit) just in case
         return full_name[:31]
 
     def _resolve_workspaces(self, ids_str=None, name_pattern=None):
@@ -62,20 +61,34 @@ class PiReportManager(PiDataMetrics):
                 current_date -= relativedelta(months=1)
         return dates
 
-    def _export_data(self, data, output_mode, filename, bq_config, spreadsheet_name, tab_name):
+    # --- UPDATED EXPORT LOGIC ---
+    def _export_data(self, data, output_mode, bq_config, spreadsheet_name, unique_name):
+        """
+        Handles export routing.
+        unique_name is used for:
+        - CSV Filename
+        - Excel Filename
+        - Google Sheet Tab Name
+        """
         if not data:
             print("No data to export.")
             return
 
         if output_mode == 'bigquery' and bq_config:
+            # BigQuery doesn't use filenames, it uses the Table ID in config
             PiExporter.to_bigquery(data, bq_config['project'], bq_config['dataset'], bq_config['table'])
+        
         elif output_mode == 'excel':
-            PiExporter.to_excel(data, filename)
+            # Use unique_name as filename
+            PiExporter.to_excel(data, unique_name)
+            
         elif output_mode == 'gsheet' and spreadsheet_name:
-            # tab_name is already generated with ID and Timestamp before calling this
-            PiExporter.to_google_sheet(data, spreadsheet_name, tab_name)
+            # Use unique_name as Tab Name
+            PiExporter.to_google_sheet(data, spreadsheet_name, tab_name=unique_name)
+            
         else:
-            PiExporter.to_csv(data, filename)
+            # Default to CSV, use unique_name as filename
+            PiExporter.to_csv(data, unique_name)
 
     def run_volume_report(self, filename, workspace_ids=None, workspace_name=None, output_mode='csv', bq_config=None, spreadsheet_name=None):
         targets = self._resolve_workspaces(workspace_ids, workspace_name)
@@ -89,11 +102,11 @@ class PiReportManager(PiDataMetrics):
                 rows = PiParsers.parse_volume_data(vol_data, stg['name'], terms, ws_name)
                 all_rows.extend(rows)
         
-        # Get the first Workspace ID found to use in the tab name
+        # Generate Unique Name
         ws_ref = list(targets.keys())[0] if targets else "Multi"
-        unique_tab = self._generate_tab_name("Vol", ws_ref)
+        unique_name = self._generate_unique_name("Vol", ws_ref)
 
-        self._export_data(all_rows, output_mode, filename, bq_config, spreadsheet_name, tab_name=unique_tab)
+        self._export_data(all_rows, output_mode, bq_config, spreadsheet_name, unique_name)
 
     def run_serp_report(self, data_sources, output_mode='csv', bq_config=None, filename=None, manual_duplication=None, spreadsheet_name=None):
         yesterday = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
@@ -105,11 +118,11 @@ class PiReportManager(PiDataMetrics):
             rows = PiParsers.parse_serp_response(raw_data, market, w_name, se_name, yesterday, cat_map, manual_duplication)
             all_rows.extend(rows)
         
-        # Use the Workspace ID from the first data source
+        # Generate Unique Name
         ws_ref = data_sources[0][1] if data_sources else "All"
-        unique_tab = self._generate_tab_name("SERP", ws_ref)
+        unique_name = self._generate_unique_name("SERP", ws_ref)
 
-        self._export_data(all_rows, output_mode, filename or "serp_output", bq_config, spreadsheet_name, tab_name=unique_tab)
+        self._export_data(all_rows, output_mode, bq_config, spreadsheet_name, unique_name)
 
     def run_historical_serp_report(self, data_sources, duration, frequency, start_date=None, features=None, num_results=25, output_mode='csv', bq_config=None, filename="historical_data", spreadsheet_name=None):
         if features is None:
@@ -141,19 +154,21 @@ class PiReportManager(PiDataMetrics):
                 except Exception as e:
                     print(f"Failed to fetch {w_name} on {date}: {e}")
 
+            # BigQuery uploads immediately per day
             if output_mode == 'bigquery' and bq_config:
                 if daily_rows:
                     print(f"Uploading {len(daily_rows)} rows for {date} to BigQuery...")
                     PiExporter.to_bigquery(daily_rows, bq_config['project'], bq_config['dataset'], bq_config['table'])
+            # Others accumulate
             elif output_mode in ['csv', 'excel', 'gsheet']:
                 all_file_rows.extend(daily_rows)
 
+        # Final Export for Files
         if output_mode in ['csv', 'excel', 'gsheet']:
-            # Use the Workspace ID from the first data source
             ws_ref = data_sources[0][1] if data_sources else "All"
-            unique_tab = self._generate_tab_name("Hist", ws_ref)
+            unique_name = self._generate_unique_name("Hist", ws_ref)
             
-            self._export_data(all_file_rows, output_mode, filename, bq_config, spreadsheet_name, tab_name=unique_tab)
+            self._export_data(all_file_rows, output_mode, bq_config, spreadsheet_name, unique_name)
 
     def run_llm_report(self, data_sources, start_period, end_period, stg_ids=None, output_mode='csv', bq_config=None, filename="llm_output", spreadsheet_name=None):
         all_rows = []
@@ -170,8 +185,8 @@ class PiReportManager(PiDataMetrics):
             except Exception as e:
                 print(f"Failed to fetch LLM data for {w_name}: {e}")
 
-        # Use the Workspace ID from the first data source
+        # Generate Unique Name
         ws_ref = data_sources[0][1] if data_sources else "All"
-        unique_tab = self._generate_tab_name("LLM", ws_ref)
+        unique_name = self._generate_unique_name("LLM", ws_ref)
 
-        self._export_data(all_rows, output_mode, filename, bq_config, spreadsheet_name, tab_name=unique_tab)
+        self._export_data(all_rows, output_mode, bq_config, spreadsheet_name, unique_name)