Merge a0d1682 into 751a49b

Author: brown9804

src/.funcignore

@@ -0,0 +1,8 @@
+.git*
+.vscode
+__azurite_db*__.json
+__blobstorage__
+__queuestorage__
+local.settings.json
+test
+.venv

src/.gitignore

@@ -0,0 +1,135 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don’t work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Azure Functions artifacts
+bin
+obj
+appsettings.json
+local.settings.json
+
+# Azurite artifacts
+__blobstorage__
+__queuestorage__
+__azurite_db*__.json
+.python_packages

src/.vscode/extensions.json

@@ -0,0 +1,6 @@
+{
+  "recommendations": [
+    "ms-azuretools.vscode-azurefunctions",
+    "ms-python.python"
+  ]
+}

src/.vscode/launch.json

@@ -0,0 +1,15 @@
+{
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "name": "Attach to Python Functions",
+      "type": "debugpy",
+      "request": "attach",
+      "connect": {
+        "host": "localhost",
+        "port": 9091
+      },
+      "preLaunchTask": "func: host start"
+    }
+  ]
+}

src/function_app.py

@@ -0,0 +1,125 @@
+import azure.functions as func
+import logging
+import json
+import os
+import uuid
+import io
+from pdfminer.high_level import extract_text
+from azure.cosmos import CosmosClient, PartitionKey
+
+app = func.FunctionApp(http_auth_level=func.AuthLevel.FUNCTION)
+
+def read_pdf_content(myblob):
+    # Read the blob content into a BytesIO stream
+    blob_bytes = myblob.read()
+    pdf_stream = io.BytesIO(blob_bytes)
+    
+    # Extract text from the PDF stream
+    text = extract_text(pdf_stream)
+    return text
+
+def extract_invoice_data(text):
+    lines = text.split('\n')
+    invoice_data = {
+        "id": generate_id(),
+        "customer_name": "",
+        "customer_email": "",
+        "customer_address": "",
+        "company_name": "",
+        "company_phone": "",
+        "company_address": "",
+        "rentals": []
+    }
+
+    for i, line in enumerate(lines):
+        if "BILL TO:" in line:
+            invoice_data["customer_name"] = lines[i + 1].strip()
+            invoice_data["customer_email"] = lines[i + 2].strip()
+            invoice_data["customer_address"] = lines[i + 3].strip()
+        elif "Company Information:" in line:
+            invoice_data["company_name"] = lines[i + 1].strip()
+            invoice_data["company_phone"] = lines[i + 2].strip()
+            invoice_data["company_address"] = lines[i + 3].strip()
+        elif "Rental Date" in line:
+            for j in range(i + 1, len(lines)):
+                if lines[j].strip() == "":
+                    break
+                rental_details = lines[j].split()
+                rental_date = rental_details[0]
+                title = " ".join(rental_details[1:-3])
+                description = rental_details[-3]
+                quantity = rental_details[-2]
+                total_price = rental_details[-1]
+                invoice_data["rentals"].append({
+                    "rental_date": rental_date,
+                    "title": title,
+                    "description": description,
+                    "quantity": quantity,
+                    "total_price": total_price
+                })
+
+    logging.info("Successfully extracted invoice data.")
+    return invoice_data
+
+def save_invoice_data_to_cosmos(invoice_data, blob_name):
+    try:
+        endpoint = os.getenv("COSMOS_DB_ENDPOINT")
+        key = os.getenv("COSMOS_DB_KEY")
+        client = CosmosClient(endpoint, key)
+        logging.info("Successfully connected to Cosmos DB.")
+    except Exception as e:
+        logging.error(f"Error connecting to Cosmos DB: {e}")
+        return
+    
+    database_name = 'ContosoDBAIDemo'
+    container_name = 'Invoices'
+    
+    try:
+        database = client.create_database_if_not_exists(id=database_name)
+        container = database.create_container_if_not_exists(
+            id=container_name,
+            partition_key=PartitionKey(path="/invoice_number"),
+            offer_throughput=400
+        )
+        logging.info("Successfully ensured database and container exist.")
+    except Exception as e:
+        logging.error(f"Error creating database or container: {e}")
+        return
+    
+    try:
+        response = container.upsert_item(invoice_data)
+        logging.info(f"Saved processed invoice data to Cosmos DB: {response}")
+    except Exception as e:
+        logging.error(f"Error inserting item into Cosmos DB: {e}")
+
+def generate_id():
+    return str(uuid.uuid4())
+
+@app.blob_trigger(arg_name="myblob", path="pdfinvoices/{name}",
+                  connection="contosostorageaidemo_STORAGE")
+def BlobTriggerContosoPDFInvoicesRaw(myblob: func.InputStream):
+    logging.info(f"Python blob trigger function processed blob\n"
+                 f"Name: {myblob.name}\n"
+                 f"Blob Size: {myblob.length} bytes")
+
+    try:
+        text = read_pdf_content(myblob)
+        logging.info("Successfully read and extracted text from PDF.")
+    except Exception as e:
+        logging.error(f"Error reading PDF: {e}")
+        return
+
+    logging.info(f"Extracted text from PDF: {text}")
+
+    try:
+        invoice_data = extract_invoice_data(text)
+        logging.info(f"Extracted invoice data: {invoice_data}")
+    except Exception as e:
+        logging.error(f"Error extracting invoice data: {e}")
+        return
+
+    try:
+        save_invoice_data_to_cosmos(invoice_data, myblob.name)
+        logging.info("Successfully saved invoice data to Cosmos DB.")
+    except Exception as e:
+        logging.error(f"Error saving invoice data to Cosmos DB: {e}")

src/host.json

@@ -0,0 +1,15 @@
+{
+  "version": "2.0",
+  "logging": {
+    "applicationInsights": {
+      "samplingSettings": {
+        "isEnabled": true,
+        "excludedTypes": "Request"
+      }
+    }
+  },
+  "extensionBundle": {
+    "id": "Microsoft.Azure.Functions.ExtensionBundle",
+    "version": "[4.*, 5.0.0)"
+  }
+}

src/requirements.txt

@@ -0,0 +1,7 @@
+# DO NOT include azure-functions-worker in this file
+# The Python Worker is managed by Azure Functions platform
+# Manually managing azure-functions-worker may cause unexpected issues
+
+azure-functions
+pdfminer.six
+azure-cosmos==4.3.0