Scala =选项范围(p=>p.priority val(之前、之后)=选项范围(!=可能匹配) (possibleMatch.possibleTransations**Set(transitions.keys.toList:*).toList foreach(t=> 转换(t.get.removeOption(option)) _选项=之前:::之后 可计算的可能跃迁 案例无=> } } } 类可能匹配(val选项:字符串, 此优先级:Int, 匹配:匹配, 剩余:列表[字符串]){ 私有变量_优先级=此优先级 私有var匹配选项=列表(新匹配选项(优先级、匹配、剩余)) private var_possibleTransations=matchOptions映射(u.possibleTransations)reduceLeft(u++) 私有def ComputePossibleTransformations={ _PossibleTransations=matchOptions映射(0.PossibleTransations)reduceLeft(0++) } def优先级:Int=_优先级 def hasMatchOption(matched:matched):布尔值=matchOptions存在(u.matched==matched) def addMatchOption(优先级:Int,已匹配:已匹配,剩余:列表[字符串]):单位={ 如果(优先级(“”,w)) def possibleTransfions:Set[Char]=\u possibleTransfions def计算(s:状态,c:字符):单位={ def computeOptions(状态:状态, c:Char, 优先权:Int, 匹配:匹配, 剩余:列表[字符串]:单位={ 剩余比赛{ 案例w::ws=> 如果(!w.isEmpty&&w(0).toLowerCase==c.toLowerCase){ val newMatched=(w(0)+匹配的.head.\u 1,匹配的.head.\u 2.子字符串(1))::matched.tail val newPriority=if(匹配的.head.\u 1为空)(优先级-1)else优先级 如果(w.drop(1)为空) s、 addOption(option,newPriority-1,(“”,ws.head)::newMatched,ws) 其他的 s、 addOption(option,newPriority,newMatched,w.substring(1)::ws) } 如果(ws!=Nil)计算选项(s,c,优先级,(“”,ws.head)::匹配,ws) 案例无=> } } if(可能的转换包含c) matchOptions foreach(mO=>computeOptions(s、c、mO.priority、mO.matched、mO.remaining)) } } 类匹配选项(val优先级:Int, 匹配:匹配, 剩余val:列表[字符串]){ lazy val PossibleTransations:Set[Char]=Set(剩余映射((0)到小写):*) }
不过,它确实需要一些重构。当我开始在博客上解释它时,我总是这样做。好吧,我刚刚意识到你想要的正是我的一个朋友对另一个问题的建议。所以,这是他的答案,根据你的需要简化了Scala =选项范围(p=>p.priority val(之前、之后)=选项范围(!=可能匹配) (possibleMatch.possibleTransations**Set(transitions.keys.toList:*).toList foreach(t=> 转换(t.get.removeOption(option)) _选项=之前:::之后 可计算的可能跃迁 案例无=> } } } 类可能匹配(val选项:字符串, 此优先级:Int, 匹配:匹配, 剩余:列表[字符串]){ 私有变量_优先级=此优先级 私有var匹配选项=列表(新匹配选项(优先级、匹配、剩余)) private var_possibleTransations=matchOptions映射(u.possibleTransations)reduceLeft(u++) 私有def ComputePossibleTransformations={ _PossibleTransations=matchOptions映射(0.PossibleTransations)reduceLeft(0++) } def优先级:Int=_优先级 def hasMatchOption(matched:matched):布尔值=matchOptions存在(u.matched==matched) def addMatchOption(优先级:Int,已匹配:已匹配,剩余:列表[字符串]):单位={ 如果(优先级(“”,w)) def possibleTransfions:Set[Char]=\u possibleTransfions def计算(s:状态,c:字符):单位={ def computeOptions(状态:状态, c:Char, 优先权:Int, 匹配:匹配, 剩余:列表[字符串]:单位={ 剩余比赛{ 案例w::ws=> 如果(!w.isEmpty&&w(0).toLowerCase==c.toLowerCase){ val newMatched=(w(0)+匹配的.head.\u 1,匹配的.head.\u 2.子字符串(1))::matched.tail val newPriority=if(匹配的.head.\u 1为空)(优先级-1)else优先级 如果(w.drop(1)为空) s、 addOption(option,newPriority-1,(“”,ws.head)::newMatched,ws) 其他的 s、 addOption(option,newPriority,newMatched,w.substring(1)::ws) } 如果(ws!=Nil)计算选项(s,c,优先级,(“”,ws.head)::匹配,ws) 案例无=> } } if(可能的转换包含c) matchOptions foreach(mO=>computeOptions(s、c、mO.priority、mO.matched、mO.remaining)) } } 类匹配选项(val优先级:Int, 匹配:匹配, 剩余val:列表[字符串]){ lazy val PossibleTransations:Set[Char]=Set(剩余映射((0)到小写):*) },scala,string-matching,trie,Scala,String Matching,Trie,不过,它确实需要一些重构。当我开始在博客上解释它时,我总是这样做。好吧,我刚刚意识到你想要的正是我的一个朋友对另一个问题的建议。所以,这是他的答案,根据你的需要简化了 class PrefixMatcher { // import scala.collection.Set // Scala 2.7 needs this -- and returns a gimped Set private var set = new scala.collection.immutable.TreeSet[
class PrefixMatcher {
// import scala.collection.Set // Scala 2.7 needs this -- and returns a gimped Set
private var set = new scala.collection.immutable.TreeSet[String]()
private def succ(s : String) = s.take(s.length - 1) + ((s.charAt(s.length - 1) + 1)).toChar
def add(s: String) = set += s
def findMatches(prefix: String): Set[String] =
if (prefix.isEmpty) set else set.range(prefix, succ(prefix))
}
使用Trie。尽管有些人发布了被错误命名为tries的排序树映射数据结构,但实际上还没有人在这里发布Trie。是Java中Trie实现的一个相当有代表性的示例。我不知道斯卡拉有什么。另请参阅关于尝试的解释。@pyo:看起来您的for循环遍历了集合中的所有字符串,对吗?在java代码中,我调用了tailSet,它的作用类似于:向以按顺序指定的前缀开头的节点返回一个迭代器,这样我们找到匹配项的速度比比较集合中的每个项快得多。@Alex Black:的确,我在序列理解中错过了对.from的调用,现在编辑。@pyo:还有一个问题,当s.startsWith(prefix)像我发布的一样返回false时,您的实现是否会中断?不,它将在从前缀到集合末尾的每个字符串上测试startsWith。老实说,我不知道这个术语的意义,我只是从原始问题中保留了它。我现在将适时地编辑它;)有趣的东西,我现在不需要匹配前缀的组合,我会记住的。谢谢!我不允许别人这么容易看到这么难看的代码感谢您的建议,我认为对于这个场景,from语法看起来比子集更简单。在集合上迭代更简单。:-)不同之处在于运行时行为。为前缀选择子集是非常有选择性的,它将跳过树的大部分部分。我将使用“from”方法得到一个没有结尾的子集(因此您必须检查是否已到达结尾)与您建议的使用子集进行比较,我认为两者都跳过了树的大部分。是的,您是对的。我添加了一个from版本,当到达前缀末尾时(使用takeWhile)该版本会中止。我想这与您的实现和子集实现具有相同的运行时行为。很可读,很好。我试图给你投票,结果我已经给了你投票,所以它给了你投票,现在它说太老了,不能改变,对不起!!虽然尝试是树结构的,但我不认为树集将如何帮助您实现trie。在树集合中使用树只是为了利用元素的顺序来加速测试和插入。树方面不是它的API的一部分
import scala.collection.jcl.TreeSet;
class PrefixMatcher
{
private val _set = new TreeSet[String]
def add(s: String) = _set.add(s)
def findMatches(prefix: String): Iterable[String] =
for (s <- _set.from(prefix) if s.startsWith(prefix)) yield s
}
object Main
{
def main(args: Array[String]): Unit =
{
val pm = new PrefixMatcher()
pm.add("fooBar")
pm.add("fooCow")
pm.add("barFoo")
pm.findMatches("foo").foreach(println)
}
}
class PrefixMatcher {
private val _set = new TreeSet[String]
def add(s: String) = _set.add(s)
def findMatches(prefix: String): Iterable[String] =
_set from prefix takeWhile(_ startsWith prefix)
}
class PrefixMatcher {
private val _set = new java.util.TreeSet[String]
def add(s: String) = _set.add(s)
def findMatches(prefix: String) : Set[String] = {
def inc(x : String) = { //ignores overflow
assert(x.length > 0)
val last = x.length - 1
(x take last) + (x(last) + 1).asInstanceOf[Char]
}
_set.subSet(prefix, inc(prefix))
}
}
package com.blogspot.dcsobral.matcher.DFA
object DFA {
type Matched = List[(String, String)]
def words(s : String) = s.split("\\W").filter(! _.isEmpty).toList
}
import DFA._
import scala.runtime.RichString
class DFA {
private val initialState : State = new State(None, "")
private var currState : State = initialState
private var _input : RichString = ""
private var _badInput : RichString = ""
private var _accepted : Boolean = true
def accepted : Boolean = _accepted
def input : String = _input.reverse + _badInput.reverse
def transition(c : Char) : List[(String, Matched)] = {
if (c == '\b') backtrack
else {
if (accepted) {
val newState = currState(c)
newState match {
case Some(s) => _input = c + _input; currState = s
case None => _badInput = c + _badInput; _accepted = false
}
} else {
_badInput = c + _badInput
}
optionList
}
}
def transition(s : String) : List[(String, Matched)] = {
s foreach (c => transition(c))
optionList
}
def apply(c : Char) : List[(String, Matched)] = transition(c)
def apply(s : String) : List[(String,Matched)] = transition(s)
def backtrack : List[(String, Matched)] = {
if(_badInput isEmpty) {
_input = _input drop 1
currState.backtrack match {
case Some(s) => currState = s
case None =>
}
} else {
_badInput = _badInput drop 1
if (_badInput isEmpty) _accepted = true
}
optionList
}
def optionList : List[(String, Matched)] = if (accepted) currState.optionList else Nil
def possibleTransitions : Set[Char] = if (accepted) (currState possibleTransitions) else Set.empty
def reset : Unit = {
currState = initialState
_input = ""
_badInput = ""
_accepted = true
}
def addOption(s : String) : Unit = {
initialState addOption s
val saveInput = input
reset
transition(saveInput)
}
def removeOption(s : String) : Unit = {
initialState removeOption s
val saveInput = input
reset
transition(saveInput)
}
}
class State (val backtrack : Option[State],
val input : String) {
private var _options : List[PossibleMatch] = Nil
private val transitions : scala.collection.mutable.Map[Char, State] = scala.collection.mutable.Map.empty
private var _possibleTransitions : Set[Char] = Set.empty
private def computePossibleTransitions = {
if (! options.isEmpty)
_possibleTransitions = options map (_.possibleTransitions) reduceLeft (_++_)
else
_possibleTransitions = Set.empty
}
private def computeTransition(c : Char) : State = {
val newState = new State(Some(this), input + c)
options foreach (o => if (o.possibleTransitions contains c) (o computeTransition (newState, c)))
newState
}
def options : List[PossibleMatch] = _options
def optionList : List[(String, Matched)] = options map (pm => (pm.option, pm.bestMatch))
def possibleTransitions : Set[Char] = _possibleTransitions
def transition(c : Char) : Option[State] = {
val t = c.toLowerCase
if (possibleTransitions contains t) Some(transitions getOrElseUpdate (t, computeTransition(t))) else None
}
def apply(c : Char) : Option[State] = transition(c)
def addOption(option : String) : Unit = {
val w = words(option)
addOption(option, w.size, List(("", w.head)), w)
}
def addOption(option : String, priority : Int, matched : Matched, remaining : List[String]) : Unit = {
options find (_.option == option) match {
case Some(pM) =>
if (!pM.hasMatchOption(matched)) {
pM.addMatchOption(priority, matched, remaining)
if (priority < pM.priority) {
val (before, _ :: after) = options span (_ != pM)
val (highPriority, lowPriority) = before span (p => p.priority < priority ||
(p.priority == priority && p.option < option))
_options = highPriority ::: (pM :: lowPriority) ::: after
}
transitions foreach (t => pM computeTransition (t._2, t._1))
}
case None =>
val (highPriority, lowPriority) = options span (p => p.priority < priority ||
(p.priority == priority && p.option < option))
val newPM = new PossibleMatch(option, priority, matched, remaining)
_options = highPriority ::: (newPM :: lowPriority)
transitions foreach (t => newPM computeTransition (t._2, t._1))
}
computePossibleTransitions
}
def removeOption(option : String) : Unit = {
options find (_.option == option) match {
case Some(possibleMatch) =>
val (before, _ :: after) = options span (_ != possibleMatch)
(possibleMatch.possibleTransitions ** Set(transitions.keys.toList : _*)).toList foreach (t =>
transition(t).get.removeOption(option))
_options = before ::: after
computePossibleTransitions
case None =>
}
}
}
class PossibleMatch (val option : String,
thisPriority : Int,
matched : Matched,
remaining : List[String]) {
private var _priority = thisPriority
private var matchOptions = List(new MatchOption(priority, matched, remaining))
private var _possibleTransitions = matchOptions map (_.possibleTransitions) reduceLeft (_++_)
private def computePossibleTransitions = {
_possibleTransitions = matchOptions map (_.possibleTransitions) reduceLeft (_++_)
}
def priority : Int = _priority
def hasMatchOption(matched : Matched) : Boolean = matchOptions exists (_.matched == matched)
def addMatchOption(priority : Int, matched : Matched, remaining : List[String]) : Unit = {
if (priority < _priority) _priority = priority
val (highPriority, lowPriority) = matchOptions span (_.priority < priority)
val newMO = new MatchOption(priority, matched, remaining)
matchOptions = highPriority ::: (newMO :: lowPriority)
computePossibleTransitions
}
def bestMatch : Matched = matchOptions.head.matched.reverse.map(p => (p._1.reverse.toString, p._2)) :::
remaining.tail.map(w => ("", w))
def possibleTransitions : Set[Char] = _possibleTransitions
def computeTransition(s: State, c : Char) : Unit = {
def computeOptions(state : State,
c : Char,
priority : Int,
matched : Matched,
remaining : List[String]) : Unit = {
remaining match {
case w :: ws =>
if (!w.isEmpty && w(0).toLowerCase == c.toLowerCase) {
val newMatched = (w(0) + matched.head._1, matched.head._2.substring(1)) :: matched.tail
val newPriority = if (matched.head._1 isEmpty) (priority - 1) else priority
if (w.drop(1) isEmpty)
s.addOption(option, newPriority - 1, ("", ws.head) :: newMatched , ws)
else
s.addOption(option, newPriority, newMatched, w.substring(1) :: ws)
}
if (ws != Nil) computeOptions(s, c, priority, ("", ws.head) :: matched, ws)
case Nil =>
}
}
if(possibleTransitions contains c)
matchOptions foreach (mO => computeOptions(s, c, mO.priority, mO.matched, mO.remaining))
}
}
class MatchOption (val priority : Int,
val matched : Matched,
val remaining : List[String]) {
lazy val possibleTransitions : Set[Char] = Set( remaining map (_(0) toLowerCase) : _* )
}
class PrefixMatcher {
// import scala.collection.Set // Scala 2.7 needs this -- and returns a gimped Set
private var set = new scala.collection.immutable.TreeSet[String]()
private def succ(s : String) = s.take(s.length - 1) + ((s.charAt(s.length - 1) + 1)).toChar
def add(s: String) = set += s
def findMatches(prefix: String): Set[String] =
if (prefix.isEmpty) set else set.range(prefix, succ(prefix))
}