Initial commit for the domain name parser

This is the bare minimum of what we need.

Author: James Mishra

Diff for: LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 Neocrym Records Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Diff for: README.md

@@ -0,0 +1,25 @@
+# Terraform Domain Parser
+
+This is a Terraform module that breaks up a DNS name (like `www.google.co.uk`)
+into parts. Currently we return:
+
+- the domain (e.g. `google`)
+- the suffix (e.g. `co.uk`)
+
+## Usage
+
+```terraform
+# In Terraform, the module name can be whatever you want.
+# Here, we go with "parser_1".
+
+module "parser_1" {
+  source   = "github.com/provose/domain-name-parser?ref=1.0.0"
+  dns_name = "a.bunch.of.com.subdomain.google.co.uk"
+}
+
+# You can access the domain with
+# module.parser_1.domain
+
+# and the suffix with
+# module.parser_1.suffix
+```

Diff for: domain_regex.txt

@@ -0,0 +1,6 @@
+locals {
+  regex_output = regex(
+    file("${path.module}/domain_regex.txt"),
+    var.dns_name
+  )
+}

Diff for: main.tf

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+"""
+Parse a Public Suffix List (https://publicsuffix.org) file and outputs a regular expression.
+
+The Public Suffix List offers a list of top-level domains and hosting sites that
+offer subdomains that are in effect like top-level domainsp.
+
+We take only the ICANN TLDs from the Public Suffix List and turn them into a
+regular expression that this Terraform module can use.
+
+Usage:
+    python3 make_regex.py public_suffix_list.dat > regex.txt
+
+"""
+import fileinput
+
+BEGIN_LINE = "BEGIN ICANN DOMAINS"
+
+END_LINE = "END ICANN DOMAINS"
+
+def get_domains(input_iterator):
+    start_parsing = False
+    for line in input_iterator:
+        if BEGIN_LINE in line:
+            start_parsing = True
+            continue
+        if END_LINE in line:
+            break
+        if start_parsing:
+            if "//" in line:
+                continue
+            splitted = line.split()
+            if splitted:
+                first_part = splitted[0]
+                if first_part:
+                    if first_part[:2] == "*.":
+                        continue
+                        yield first_part[:2]
+                    else:
+                        yield first_part
+
+REGEX_STR = "".join([
+    r"(?P<domain>[^.:/@]+)\.",
+    r"(?P<suffix>",
+    r"|".join(
+        domain.replace(".", r"\.")
+        for domain in get_domains(fileinput.input())
+    ),
+    r")$",
+])
+
+print(REGEX_STR, end="")

Diff for: make_suffix_regex.py

@@ -0,0 +1,7 @@
+output "domain" {
+  value = local.regex_output["domain"]
+}
+
+output "suffix" {
+  value = local.regex_output["suffix"]
+}