update

module3.ipynb

@@ -672,6 +672,96 @@
     "print(convert_phone_number(\"123-123-12345\")) # 123-123-12345\n",
     "print(convert_phone_number(\"Phone number of Buckingham Palace is +44 303 123 7300\")) # Phone number of Buckingham Palace is +44 303 123 7300"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Glossary\n",
+    "### Terms and definitions from Course 2, Module 3\n",
+    "**Alteration:** RegEx that matches any one of the alternatives separated by the pipe symbol.\n",
+    "\n",
+    "**Backreference:** This is applied when using re.sub( ) to substitute the value of a capture group into the output.\n",
+    "\n",
+    "**Character classes:** These are written inside square brackets and let us list the characters we want to match inside of those brackets.\n",
+    "\n",
+    "**Character ranges:** Ranges used to match a single character against a set of possibilities.\n",
+    "\n",
+    "**grep:** An especially easy to use yet extremely powerful tool for applying RegExes.\n",
+    "\n",
+    "**Lookahead:** RegEx that matches a pattern only if it’s followed by another pattern.\n",
+    "\n",
+    "**Regular expression:** A search query for text that's expressed by string pattern, also known as RegEx or RegExp.\n",
+    "\n",
+    "**Wildcard:** A character that can match more than one character.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Lab"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!/usr/bin/env python3\n",
+    "import re\n",
+    "import csv\n",
+    "\n",
+    "def contains_domain(address, domain):\n",
+    "  \"\"\"Returns True if the email address contains the given,domain,in the domain position, false if not.\"\"\"\n",
+    "  domain_pattern = r'[\\w\\.-]+@'+domain+'$'\n",
+    "  if re.match(domain_pattern,address):\n",
+    "    return True\n",
+    "  return False\n",
+    "\n",
+    "def replace_domain(address, old_domain, new_domain):\n",
+    "  \"\"\"Replaces the old domain with the new domain in the received address.\"\"\"\n",
+    "  old_domain_pattern = r'' + old_domain + '$'\n",
+    "  address = re.sub(old_domain_pattern, new_domain, address)\n",
+    "  return address\n",
+    "\n",
+    "def main():\n",
+    "  \"\"\"Processes the list of emails, replacing any instances of the old domain with the new domain.\"\"\"\n",
+    "  old_domain, new_domain = 'abc.edu', 'xyz.edu'\n",
+    "  csv_file_location = '<csv_file_location>'\n",
+    "  report_file = '<data-directory>' + '/updated_user_emails.csv'\n",
+    "  user_email_list = []\n",
+    "  old_domain_email_list = []\n",
+    "  new_domain_email_list = []\n",
+    "\n",
+    "  with open(csv_file_location, 'r') as f:\n",
+    "    user_data_list = list(csv.reader(f))\n",
+    "    user_email_list = [data[1].strip() for data in user_data_list[1:]]\n",
+    "\n",
+    "    for email_address in user_email_list:\n",
+    "      if contains_domain(email_address, old_domain):\n",
+    "        old_domain_email_list.append(email_address)\n",
+    "        replaced_email = replace_domain(email_address,old_domain,new_domain)\n",
+    "        new_domain_email_list.append(replaced_email)\n",
+    "\n",
+    "    email_key = ' ' + 'Email Address'\n",
+    "    email_index = user_data_list[0].index(email_key)\n",
+    "\n",
+    "    for user in user_data_list[1:]:\n",
+    "      for old_domain, new_domain in zip(old_domain_email_list, new_domain_email_list):\n",
+    "        if user[email_index] == ' ' + old_domain:\n",
+    "          user[email_index] = ' ' + new_domain\n",
+    "  f.close()\n",
+    "\n",
+    "  with open(report_file, 'w+') as output_file:\n",
+    "    writer = csv.writer(output_file)\n",
+    "    writer.writerows(user_data_list)\n",
+    "    output_file.close()\n",
+    "\n",
+    "main()"
+   ]
   }
  ],
  "metadata": {