REL sample for legal citation Sample for http://stackoverflow.com/questions/7054764/regular-expression-for-legal-citation

build.sbt

// in './'

organization := "com.stackoverflow"

name := "legal"

version := "0.1"

scalaVersion := "2.9.1"

resolvers += "Imaginatio" at "https://github.com/Imaginatio/Maven-repository/raw/master"

libraryDependencies += "fr.splayce" %% "rel" % "0.2.3"

libraryDependencies += "org.specs2" %% "specs2" % "1.10" % "test"

scalacOptions ++= Seq("-deprecation", "-unchecked", "-encoding", "UTF8")

Legal.scala

// in './src/main/scala'
package com.stackoverflow.legal

import fr.splayce.rel._
import Symbols._
import Implicits._


object Legal {

  val NAME = α+
  val VS   = """v\.?""" ~ """s\.?""".?
  val CASE = NAME("name1") ~ " " ~ VS ~ " " ~ NAME("name2")

  val NUM  = ß ~ (δ+) ~ ß
  val US   = """U\.? ?S\.? """
  val YEAR = ( ("1[7-9]" | "20") ~ δ{2} )("year")

  val REF = CASE ~ ", " ~           // "Doe v. Smith, "
            (NUM ~ " ").? ~         // "123 "           (optional)
            US ~ NUM ~              // "U.S. 456"
            (", " ~ NUM).* ~        // ", 678"          0 to N times
            " \\(" ~ YEAR ~ "\\)"   // "(1999)"

}

object Output extends App {

  println(Legal.REF)

}

LegalSpec.scala

// in './src/test/scala/'
package com.stackoverflow.legal

import fr.splayce.rel.Implicits.RE2Regex
import org.specs2.mutable._


class LegalSpec extends Specification {

  import Legal._


  "NAME" should {
    "Match plain names" in {
      "Doe"         must     be matching(NAME)
      "Smith"       must     be matching(NAME)
    }

    "Not match composed names" in {
      "Doe-Smith"   must not be matching(NAME)
    }

    "Not match diacritics" in {
      "Doë"         must not be matching(NAME)
    }
  }


  "CASE" should {
    "Match 'vs' form"   in { "Doe vs Smith"   must be matching(CASE) }
    "Match 'v.s' form"  in { "Doe v.s Smith"  must be matching(CASE) }
    "Match 'v.s.' form" in { "Doe v.s. Smith" must be matching(CASE) }
    "Match 'v' form"    in { "Doe v Smith"    must be matching(CASE) }
    "Match 'v.' form"   in { "Doe v. Smith"   must be matching(CASE) }
  }


  "NUM" should {
    "Match 1+ digits" in {
      "1"         must     be matching(NUM)
      "12"        must     be matching(NUM)
      "123"       must     be matching(NUM)
      "1234"      must     be matching(NUM)
      "12345"     must     be matching(NUM)
      "123456"    must     be matching(NUM)
    }

    "Match only standalone digits" in {
      NUM.findFirstIn("  123 ") must beSome("123")
      NUM.findFirstIn(" n123 ") must beNone
    }
  }


  "US" should {
    "Match 'US ' form"    in { "US "    must be matching(US) }
    "Match 'U.S. ' form"  in { "U.S. "  must be matching(US) }
    "Match 'U. S. ' form" in { "U. S. " must be matching(US) }
  }


  "YEAR" should {
    "Not match 1600s"      in {
      "1699" must not be matching(YEAR)
    }

    "Match 1700s to 1900s" in {
      "1700" must     be matching(YEAR)
      "1799" must     be matching(YEAR)
      "1800" must     be matching(YEAR)
      "1899" must     be matching(YEAR)
      "1900" must     be matching(YEAR)
      "1999" must     be matching(YEAR)
    }

    "Match 2000s"          in {
      "2000" must     be matching(YEAR)
      "2099" must     be matching(YEAR)
    }

    "Not match 2100s"      in {
      "2100" must not be matching(YEAR)
    }
  }


  "REF" should {
    "Match the full form" in {
      "Doe v. Smith, U.S. 456 (2003)"          must be matching(REF)
      "Doe v. Smith, 123 U.S. 456 (2003)"      must be matching(REF)
      "Doe v. Smith, 123 U.S. 456, 789 (2003)" must be matching(REF)

      "Doe v.s. Smith, 123 US 456 (2003)"    must be matching(REF)
    }
  }

}