Begin refactoring classes used by add-grammar

script/add-grammar

@@ -3,39 +3,85 @@
 require "optparse"
 require "open3"
 
+class GrammarRepo
+
+  # Whitelist of trusted hosting providers
+  HOSTS = Regexp.union %w[github.com bitbucket.org gitlab.com]
+
+  # Public: Define a repository source by upstream URL.
+  #
+  # url - an HTTPS, HTTP, or SSH address accepted by git-remote(1)
+  #       Only domains listed in HOSTS are accepted; unrecognised
+  #       hostnames or invalid URLs will raise an ArgumentError.
+  #
+  #       Assumption: Repo URLs will never include subdomains.
+  #       We only check for a possible `www`, nothing else.
+  #
+  # module_path - path of submodule as registered in `.gitmodules`
+  #               Omit this unless grammar is being replaced.
+  def initialize(url, module_path = nil)
+    if https? url
+      @host = $1.downcase
+      @user = $2
+      @repo = $3.sub /\.git$/, ""
+    elsif ssh?(url) || shorthand?(url)
+      @host = $1.downcase
+      @user = $2
+      @repo = $3
+    elsif implicit_shorthand? url
+      @host = "github.com"
+      @user = $1
+      @repo = $2
+    else
+      raise ArgumentError, "Unsupported URL: #{url}"
+    end
+  end
+
+  # Match a well-formed HTTP or HTTPS address
+  def https?(url)
+    nil unless url =~ /
+      ^  (?<protocol>   https? ://)?
+         (?<userauth>   [^@.]+ @  )?
+         (?<subdomain>  www    \. )?
+         (?<hostname>   #{HOSTS}  )
+      \/ (?<user>       [^\/]+    )
+      \/ (?<repo>       [^\/]+    ) /xi
+  end
+
+  # Match an SSH address starting with `git@`
+  def ssh?(url)
+    nil unless url =~ /
+      ^ git@
+        (?<hostname> #{HOSTS}) :
+        (?<user>     [^\/]+)  \/
+        (?<repo>     [^\/]+)  \.git $/xi
+  end
+
+  # Match `provider:user/repo`
+  def shorthand?(url)
+    nil unless url =~ /
+      ^ (?<hostname> #{HOSTS}) : \/?
+        (?<user>     [^\/]+) \/
+        (?<repo>     [^\/]+) \/? $ /xi
+  end
+
+  # Match `user/repo` shorthand, assumed to be GitHub
+  def implicit_shorthand?(url)
+    nil unless url =~ /
+      ^ \/? (?<user>[^\/]+)
+        \/  (?<repo>[^\/]+)
+        \/? $/xi
+  end
+end
+
+
+class GrammarGuardian
+
   ROOT = File.expand_path("../../", __FILE__)
 
-
+  def initialize
-# Break a repository URL into its separate components
+    # Track each change so we can roll back after a failed command
-def parse_url(input)
+    @changes = Hash.new
-  hosts = "github\.com|bitbucket\.org|gitlab\.com"
-
-  # HTTPS/HTTP link pointing to recognised hosts
-  if input =~ /^(?:https?:\/\/)?(?:[^.@]+@)?(?:www\.)?(#{hosts})\/([^\/]+)\/([^\/]+)/i
-    { host: $1.downcase(), user: $2, repo: $3.sub(/\.git$/, "") }
-  # SSH
-  elsif input =~ /^git@(#{hosts}):([^\/]+)\/([^\/]+)\.git$/i
-    { host: $1.downcase(), user: $2, repo: $3 }
-  # provider:user/repo
-  elsif input =~ /^(github|bitbucket|gitlab):\/?([^\/]+)\/([^\/]+)\/?$/i
-    { host: $1.downcase(), user: $2, repo: $3 }
-  # user/repo - Common GitHub shorthand
-  elsif input =~ /^\/?([^\/]+)\/([^\/]+)\/?$/
-    { host: "github.com", user: $1, repo: $2 }
-  else
-    raise "Unsupported URL: #{input}"
-  end
-end
-
-# Isolate the vendor-name component of a submodule path
-def parse_submodule(name)
-  name =~ /^(?:.*(?:vendor\/)?grammars\/)?([^\/]+)/i
-  path = "vendor/grammars/#{$1}"
-  unless File.exist?("#{ROOT}/" + path)
-    warn "Submodule '#{path}' does not exist. Aborting."
-    exit 1
-  end
-  path
   end
 
   # Print debugging feedback to STDOUT if running with --verbose
@@ -54,6 +100,19 @@ def command(*args)
       exit 1
     end
   end
+end
+
+# Isolate the vendor-name component of a submodule path
+def parse_submodule(name)
+  name =~ /^(?:.*(?:vendor\/)?grammars\/)?([^\/]+)/i
+  path = "vendor/grammars/#{$1}"
+  unless File.exist?("#{ROOT}/" + path)
+    warn "Submodule '#{path}' does not exist. Aborting."
+    exit 1
+  end
+  path
+end
+
 
 usage = """Usage:
   #{$0} [-v|--verbose] [--replace grammar] url