Autogenerated literator docs for v0.1.0

docs/src/main/scala/entry.scala.md

@@ -0,0 +1,35 @@
+
+```scala
+package com.bio4j.data.enzyme
+
+trait AnyEntry extends Any {
+
+  def ID: String
+  def subSubClassID: String
+
+  def description: String
+  def alternativeNames: Seq[String]
+  def cofactors: Seq[String]
+  def catalyticActivity: String
+  def comments: Seq[String]
+}
+
+sealed trait EnzymeClasses extends Any {
+
+  def ID: String
+  def description: String
+}
+  case class EnzymeClass(val ID: String, val description: String) extends EnzymeClasses
+  case class EnzymeSubClass(val ID: String, val description: String) extends EnzymeClasses
+  case class EnzymeSubSubClass(val ID: String, val description: String) extends EnzymeClasses
+
+```
+
+
+
+
+[test/scala/EnzymeEntries.scala]: ../../test/scala/EnzymeEntries.scala.md
+[test/scala/EnzymeClasses.scala]: ../../test/scala/EnzymeClasses.scala.md
+[main/scala/entry.scala]: entry.scala.md
+[main/scala/flat/entry.scala]: flat/entry.scala.md
+[main/scala/flat/classes.scala]: flat/classes.scala.md

docs/src/main/scala/flat/classes.scala.md

@@ -0,0 +1,112 @@
+
+```scala
+package com.bio4j.data.enzyme.flat
+
+import com.bio4j.data.enzyme._
+
+case class ClassLine(val line: String) {
+
+  final def asEnzymeClass: EnzymeClasses = {
+
+    ID match {
+      // the order is important here
+      case id if (id == classID)        => EnzymeClass(id, description)
+      case id if (id == subClassID)     => EnzymeSubClass(id, description)
+      case id if (id == subSubClassID)  => EnzymeSubSubClass(id, description)
+    }
+  }
+```
+
+
+In the `enzclass.txt` source file the id always takes 9 characters, but it has funny empty spaces around.
+
+
+```scala
+  private lazy val ID: String =
+    line
+      .take(9)
+      .filter(_ != ' ')
+
+  private lazy val IDFragments: (String,String,String,String) = {
+
+    val fragments = ID.split('.').take(4)
+
+    (fragments(0), fragments(1), fragments(2), fragments(3))
+  }
+
+  private def classID: String =
+    s"${IDFragments._1}.-.-.-"
+
+  private def subClassID: String =
+    s"${IDFragments._1}.${IDFragments._2}.-.-"
+
+  private def subSubClassID: String =
+    s"${IDFragments._1}.${IDFragments._2}.${IDFragments._3}.-"
+```
+
+
+We don't want to store the description with a dot at the end!
+
+
+```scala
+  private lazy val description: String =
+    line
+      .drop(9)
+      .trim
+      .stripSuffix(".")
+}
+
+case object enzymeClasses {
+```
+
+
+The Enzyme source file `enzclass.txt` starts with:
+
+```
+---------------------------------------------------------------------------
+        ENZYME nomenclature database
+        SIB Swiss Institute of Bioinformatics; Geneva, Switzerland
+----------------------------------------------------------------------------
+
+Description: Definition of enzyme classes, subclasses and sub-subclasses
+Name:        enzclass.txt
+Release:     07-Sep-2016
+
+----------------------------------------------------------------------------
+
+1. -. -.-  Oxidoreductases.
+1. 1. -.-   Acting on the CH-OH group of donors.
+```
+
+it also ends with:
+
+```
+----------------------------------------------------------------------------
+Copyrighted by the SIB Swiss Institute of Bioinformatics.
+There are no restrictions on its use by any institutions as long as
+its content is in no way modified.
+----------------------------------------------------------------------------
+```
+
+so we are only picking lines with a dot in the second char.
+
+Note that there empty lines now and then, which need to be filtered out too.
+
+
+```scala
+  def fromLines(lines: Iterator[String]): Iterator[EnzymeClasses] =
+    lines
+      .filter(_.nonEmpty)
+      .collect { case line if(line(1) == '.') => ClassLine(line).asEnzymeClass }
+}
+
+```
+
+
+
+
+[test/scala/EnzymeEntries.scala]: ../../../test/scala/EnzymeEntries.scala.md
+[test/scala/EnzymeClasses.scala]: ../../../test/scala/EnzymeClasses.scala.md
+[main/scala/entry.scala]: ../entry.scala.md
+[main/scala/flat/entry.scala]: entry.scala.md
+[main/scala/flat/classes.scala]: classes.scala.md

docs/src/main/scala/flat/entry.scala.md

@@ -0,0 +1,170 @@
+
+```scala
+package com.bio4j.data.enzyme.flat
+
+import com.bio4j.data.enzyme._
+
+case class Entry(val lines: Seq[String]) extends AnyEntry {
+
+  def ID: String =
+    id.value
+
+  def subSubClassID: String =
+    id.subSubClassID
+
+  def description: String =
+    de.description
+
+  def alternativeNames: Seq[String] =
+    an.alternativeNames
+
+  def cofactors: Seq[String] =
+    cf.cofactors
+
+  def catalyticActivity: String =
+    ca.catalyticActivity
+
+  def comments: Seq[String] =
+    cc.comments
+
+  private lazy val id: ID =
+    new ID(linesWith(prefix = "ID").head)
+
+  private lazy val de: DE =
+    DE(linesWith(prefix = "DE"))
+
+  private lazy val an: AN =
+    AN(linesWith(prefix = "AN"))
+
+  private lazy val cf: CF =
+    CF(linesWith(prefix = "CF"))
+
+  private lazy val ca: CA =
+    CA(linesWith(prefix = "CA"))
+
+  private lazy val cc: CC =
+    CC(linesWith(prefix = "CC"))
+
+  private def linesWith(prefix: String): Seq[String] =
+    lines collect { case line if(line startsWith prefix) => line.stripPrefix(prefix).trim  }
+}
+
+private case class ID(val value: String) extends AnyVal {
+
+  def subSubClassID: String =
+    s"${value.reverse.dropWhile(_ != '.').reverse}-"
+}
+
+private case class DE(val lines: Seq[String]) extends AnyVal {
+
+  def description: String =
+    lines
+      .map(_.trim.stripSuffix("."))
+      .mkString(" ")
+}
+
+private case class AN(val lines: Seq[String]) extends AnyVal {
+
+  def alternativeNames: Seq[String] =
+    lines
+      .mkString(" ")
+      .split('.')
+}
+
+private case class CF(val lines: Seq[String]) extends AnyVal {
+
+  def cofactors: Seq[String] =
+    lines
+      .mkString("")
+      .split(';')
+      .map(_.trim.stripSuffix("."))
+}
+
+private case class CA(val lines: Seq[String]) extends AnyVal {
+
+  def catalyticActivity: String =
+    lines.mkString(" ")
+}
+
+private case class CC(val lines: Seq[String]) extends AnyVal {
+
+  def comments: Seq[String] =
+    lines.mkString(" ")
+      .split("-!-")
+      .collect { case txt if(txt.nonEmpty) => txt.trim.stripSuffix(".") }
+}
+
+case object entries {
+```
+
+
+ENZYME entries file have a "header" consisting on CC lines and an end of entry // line.
+
+
+```scala
+  def fromLines(lines: Seq[String]): Seq[Entry] =
+    entryLines(lines.dropWhile( l => l.startsWith("CC") || l.startsWith("//") )).map { Entry(_) }
+
+  def validFromLines(lines: Seq[String]): Seq[Entry] =
+    fromLines(lines) filter isValid
+```
+
+
+See ftp://ftp.expasy.org/databases/enzyme/enzuser.txt
+
+
+```scala
+  private def isValid(entry: Entry): Boolean =
+    !( entry.description.startsWith("Deleted entry") || entry.description.startsWith("Transferred entry") )
+
+  @annotation.tailrec
+  private def entryLinesRec(
+    currentLine: Option[String],
+    linesLeft: Seq[String],
+    entryAcc: Seq[String],
+    acc: Seq[Seq[String]]
+  )
+  : Seq[Seq[String]] =
+    currentLine match {
+      case None       => acc
+      case Some(line) => {
+
+        if(isEndLine(line))
+          entryLinesRec(
+            currentLine = linesLeft.headOption,
+            linesLeft   = if(linesLeft.isEmpty) Seq() else linesLeft.tail,
+            entryAcc    = Seq(),
+            acc         = acc :+ entryAcc
+          )
+        else
+          entryLinesRec(
+            currentLine = linesLeft.headOption,
+            linesLeft   = if(linesLeft.isEmpty) Seq() else linesLeft.tail,
+            entryAcc    = entryAcc :+ line,
+            acc         = acc
+          )
+      }
+    }
+
+  private def entryLines(lines: Seq[String]): Seq[Seq[String]] =
+    entryLinesRec(
+      currentLine = lines.headOption,
+      linesLeft   = lines.tail,
+      entryAcc    = Seq(),
+      acc         = Seq()
+    )
+
+  private def isEndLine(line: String) =
+    line.startsWith("//")
+}
+
+```
+
+
+
+
+[test/scala/EnzymeEntries.scala]: ../../../test/scala/EnzymeEntries.scala.md
+[test/scala/EnzymeClasses.scala]: ../../../test/scala/EnzymeClasses.scala.md
+[main/scala/entry.scala]: ../entry.scala.md
+[main/scala/flat/entry.scala]: entry.scala.md
+[main/scala/flat/classes.scala]: classes.scala.md

docs/src/test/scala/EnzymeClasses.scala.md

@@ -0,0 +1,56 @@
+
+```scala
+package com.bio4j.data.enzyme.test
+
+import org.scalatest.FunSuite
+
+import com.bio4j.data.enzyme._
+
+class ParseEnzymeClasses extends FunSuite {
+
+  def lines =
+    io.Source.fromFile("enzclass.txt").getLines
+
+  def allEnzymeClasses = flat.enzymeClasses.fromLines(lines)
+
+  test("parse all enzyme classes") {
+
+    allEnzymeClasses.foreach { e =>
+
+      val clazz = e
+    }
+  }
+```
+
+
+This is unlikely to change
+
+
+```scala
+  test("check first classes") {
+
+    val firstFive = (allEnzymeClasses take 5).toList
+
+    assert {
+
+      firstFive === List[EnzymeClasses](
+        EnzymeClass("1.-.-.-", "Oxidoreductases"),
+        EnzymeSubClass("1.1.-.-", "Acting on the CH-OH group of donors"),
+        EnzymeSubSubClass("1.1.1.-", "With NAD(+) or NADP(+) as acceptor"),
+        EnzymeSubSubClass("1.1.2.-", "With a cytochrome as acceptor"),
+        EnzymeSubSubClass("1.1.3.-", "With oxygen as acceptor")
+      )
+    }
+  }
+}
+
+```
+
+
+
+
+[test/scala/EnzymeEntries.scala]: EnzymeEntries.scala.md
+[test/scala/EnzymeClasses.scala]: EnzymeClasses.scala.md
+[main/scala/entry.scala]: ../../main/scala/entry.scala.md
+[main/scala/flat/entry.scala]: ../../main/scala/flat/entry.scala.md
+[main/scala/flat/classes.scala]: ../../main/scala/flat/classes.scala.md