Fix CSV processing errors

MyFunctionProject/additional_functions.py

@@ -1,13 +1,10 @@
 import logging
 import azure.functions as func
 
-bp = func.Blueprint()
+def main(myblob: func.InputStream):
+    logging.info(f"Processing blob: Name={myblob.name}, Size={myblob.length} bytes")
 
-@bp.function_name('AdditionalHTTPFunction')
-@bp.route(route="brandnewroute")
-def test_function(req: func.HttpRequest) -> func.HttpResponse:
-    logging.info('Python HTTP trigger function processed a request.')
-    return func.HttpResponse(
-        "Wow hello this worked!!!",
-        status_code=200
-        )
+    blob_bytes = myblob.read()
+    summary = process_csv(blob_bytes)
+
+    logging.info(f"Processing completed. Summary: {summary}")

MyFunctionProject/function_app.py

@@ -5,85 +5,39 @@
 import csv
 import codecs
 import os
+import io
 from azure.storage.blob import BlobServiceClient
 from additional_functions import bp
 
-app = func.FunctionApp()
 
-app.register_blueprint(bp) 
-
-@app.function_name('FirstHTTPFunction')
-@app.route(route="myroute", auth_level=func.AuthLevel.ANONYMOUS)
-def test_function(req: func.HttpRequest) -> func.HttpResponse:
-    logging.info('Python HTTP trigger function processed a request.')
-    return func.HttpResponse(
-        "Wow this first HTTP Function works!!!!",
-        status_code=200
-    )
-
-@app.function_name('SecondHTTPFunction')
-@app.route(route="newroute")
-def test_function(req: func.HttpRequest) -> func.HttpResponse:
-    logging.info('Starting the second HTTP Function request.')
+def process_csv(blob_content):
+    summary = {"processed": 0, "errors": 0}
 
-    name = req.params.get('name')
-    if name:
-        message = f"Hello, {name}, so glad this Function worked!!"
-    else:
-        message = "Hello, so glad this Function worked!!"
-    return func.HttpResponse(
-        message,
-        status_code=200
-    )
-
-
-@app.function_name(name="MyFirstBlobFunction")
-@app.blob_trigger(arg_name="myblob", 
-                  path="newcontainer/People.csv",
-                  connection="AzureWebJobsStorage")
-def test_function(myblob: func.InputStream):
-   logging.info(f"Python blob Function triggered after the People.csv file was uploaded to the newcontainer. So cool!!!! \n"
-                f"Printing the name of the blob path: {myblob.name}"
-                )
-   blob_name = myblob.name.split('/')[-1]
-   metadata_log = f"Blob: {blob_name}, Size: {myblob.length} bytes, Last Modified: {myblob.last_modified}"
-   logging.info(metadata_log)
-
-   # Optional: Append metadata to log file in blob storage
-   try:
-       # Get connection string from app settings
-       connection_string = os.environ.get('AzureWebJobsStorage')
-       if connection_string:
-           # Create a BlobServiceClient
-           blob_service_client = BlobServiceClient.from_connection_string(connection_string)
-           # Get container client
-           container_client = blob_service_client.get_container_client("newcontainer")
-
-           # Get the metadata log blob client
-           log_blob_name = "metadata.log"
-           blob_client = container_client.get_blob_client(log_blob_name)
-
-           # Check if the log file exists, if not create it
-           try:
-               # Try to download the existing log
-               existing_log = blob_client.download_blob().readall().decode('utf-8')
-               log_content = existing_log + "\n" + metadata_log
-           except Exception:
-               # Log file doesn't exist yet, create new log content
-               log_content = metadata_log
-
-           # Upload the updated log
-           blob_client.upload_blob(log_content, overwrite=True)
-           logging.info(f"Metadata appended to {log_blob_name}")
-   except Exception as e:
-       logging.error(f"Error appending to metadata log: {str(e)}")
-
-
-@app.function_name(name="ReadFileBlobFunction")
-@app.blob_trigger(arg_name="readfile",
-                  path="newcontainer/People2.csv",
-                  connection="AzureWebJobsStorage")
-def main(readfile: func.InputStream):
-    reader=csv.reader(codecs.iterdecode(readfile,'utf-8'))
-    for line in reader:
-        print(line)
+    try:
+        # Try to decode CSV content safely
+        decoded_content = blob_content.decode('utf-8-sig', errors='replace')
+        reader = csv.DictReader(io.StringIO(decoded_content))
+
+        # Check for headers
+        if not reader.fieldnames:
+            raise csv.Error("Missing headers in CSV file.")
+
+        for row in reader:
+            try:
+                # Your row processing logic here
+                # Example: print(row)
+                summary["processed"] += 1
+            except Exception as e:
+                summary["errors"] += 1
+                logging.error(f"Row processing error: {e}")
+
+    except (csv.Error, UnicodeDecodeError) as e:
+        summary["errors"] += 1
+        logging.error(f"Failed to read CSV: {e}")
+    except Exception as e:
+        summary["errors"] += 1
+        logging.error(f"Unexpected error: {e}")
+    finally:
+        logging.info(f"CSV Summary: {summary}")
+
+    return summary