c# - Parsing tnsnames.ora using regex

Question

I am attempting to pull some information from my tnsnames file using regex. I started with the following pattern:

MYSCHEMA *? = *?[WwSs]*(HOST *?= *?(?<host>w+s?))s?(PORT *?= *?(?<port>d+)s?)[WwSs]*(SERVICE_NAME *?= *?(?<servicename>w+)s?)

which worked fine when MYSCHEMA was the only schema in the file, but when there are other schemas listed after MYSCHEMA it matches all the way to the last schema.

I have since created a new pattern:

MYSCHEMA *=s*(DESCRIPTION =s*(ADDRESS *= *(PROTOCOL *= *TCP)(HOST *= *(?<host>w+))(PORT *= *(?<port>d+)))s*(CONNECT_DATA *=s*(?<serverdedicated>(SERVER *= *DEDICATED))s*(SERVICE_NAME *= *(?<servicename>[w.]+) *)s*)s*)

This pattern matches MYSCHEMA only, but I had to add every element that appeared in MYSCHEMA entry, and it won't match MYOTHERSCHEMA if it does not contain all the same elements.

Ideally, I'd like a pattern that matches MYSCHEMA entry only, and captures HOST, PORT and SERVICE NAME, and optionally (SERVER = DEDICATED) (which I didn't have in the first pattern) to named groups.

Below is the sample tnsnames that I've been using for testing:

SOMESCHEMA =
  (DESCRIPTION =
    (ADDRESS_LIST =
      (ADDRESS = (PROTOCOL = TCP)(HOST = REMOTEHOST)(PORT = 1234))
    )
    (CONNECT_DATA = (SERVICE_NAME = REMOTE)
    )
  )

MYSCHEMA =
  (DESCRIPTION =
    (ADDRESS = (PROTOCOL = TCP)(HOST = MYHOST)(PORT = 1234))
    (CONNECT_DATA =
      (SERVER = DEDICATED)
      (SERVICE_NAME = MYSERVICE.LOCAL )
    )
  )

MYOTHERSCHEMA =
  (DESCRIPTION =
    (ADDRESS_LIST =
      (ADDRESS = (PROTOCOL = TCP)(HOST = MYHOST)(PORT = 1234))
    )
    (CONNECT_DATA = 
      (SERVICE_NAME = MYSERVICE.REMOTE)
    )

  )

SOMEOTHERSCHEMA = 
  (DESCRIPTION =
    (ADDRESS_LIST =
      (ADDRESS = (PROTOCOL = TCP)(HOST = LOCALHOST)(PORT = 1234))
    )
    (CONNECT_DATA =
      (SERVICE_NAME = LOCAL)
    )
  )

Answer 1

This should do it, using balanced groups. And modify the switch/case for your needs.

class TnsRegex
{
    public void Test()
    {
        Regex reTns = new Regex(_pattern, RegexOptions.Singleline | RegexOptions.IgnorePatternWhitespace);
        MatchCollection matchCollection = reTns.Matches(_text);

        foreach (Match match in matchCollection)
        {
            foreach (Capture capture in match.Groups["Settings"].Captures)
            {
                string[] setting = capture.Value.Split(new[] { '=' }, StringSplitOptions.RemoveEmptyEntries);
                string key = setting[0].Trim();
                string val = setting[1].Trim();
                if (val.Contains("(")) continue;
                switch (key)
                {
                    case "HOST":
                        break;
                    case "PORT":
                        break;
                    case "SERVICE_NAME":
                        break;
                    case "SERVER":
                        break;
                }
                Console.WriteLine(key + ":" + val);
            }
        }
    }
    string _pattern = @"
        MYSCHEMAs+=s+(
        [^()]*
        (
                    (
                                (?<Open>()
                                [^()]*
                    )+
                    (
                                (?<Settings-Open>))
                                [^()]*
                    )+
        )*
        (?(Open)(?!))
    )";

    string _text = @"
    MYSCHEMA =
      (DESCRIPTION =
        (ADDRESS = (PROTOCOL = TCP)(HOST = MYHOST)(PORT = 1234))
        (CONNECT_DATA =
          (SERVER = DEDICATED)
          (SERVICE_NAME = MYSERVICE.LOCAL )
        )
      )

    SOMESCHEMA =
      (DESCRIPTION =
        (ADDRESS_LIST =
          (ADDRESS = (PROTOCOL = TCP)(HOST = REMOTEHOST)(PORT = 1234))
        )
        (CONNECT_DATA = (SERVICE_NAME = REMOTE)
        )
      )
    ";
}