字符串匹配

23-MSDSort-And-BucketSort/SortingHelper.dart

@@ -9,7 +9,7 @@ class SortingHelper {
     return true;
   }
 
-  static sortTest(String sortname, List? arr) {
+  static sortTest(String sortname, List arr) {
     var now = new DateTime.now();
     num startTime = now.millisecondsSinceEpoch;
 

24-SubString-Match/FileOperator.dart

@@ -0,0 +1,19 @@
+import 'dart:io';
+import 'dart:convert';
+
+/**
+ * 文件操作类
+ */
+class FileOperator{
+
+    static Future<List> getFileString(String filename) async{
+      Stream<List<int>> content = File(filename).openRead();
+      List<String> lines = await content.transform(utf8.decoder).transform(LineSplitter()).toList();
+      var words = [];
+      for(int i = 0;i<lines.length;i++){
+        words.addAll(lines[i].split(" ").toList());
+      }
+      words.removeWhere((element) => element == "");
+      return words;
+    }
+}

24-SubString-Match/LC1392-hash.dart

@@ -0,0 +1,42 @@
+class Solution2 {
+  double MOD = 1e9 + 7;
+
+  String longestPrefix(String s) {
+    List<int> pow26 = List.filled(s.length, 0, growable: true);
+    pow26[0] = 1;
+    for (int i = 1; i < pow26.length; i++)
+      pow26[i] = (pow26[i - 1] * 26 % MOD).toInt();
+
+    // prehash[i]: hash(s[0...i])
+    List<int> prehash = List.filled(s.length, 0, growable: true);
+    prehash[0] = s[0].codeUnits[0] - 'a'.codeUnits[0];
+    for (int i = 1; i < s.length; i++)
+      prehash[i] =
+          ((prehash[i - 1] * 26 + s[i].codeUnits[0] - 'a'.codeUnits[0]) % MOD)
+              .toInt();
+
+    // posthash[i]: hash(s[i...s.length - 1])
+    List<int> posthash = List.filled(s.length, 0, growable: true);
+    posthash[s.length - 1] = s[s.length - 1].codeUnits[0] - 'a'.codeUnits[0];
+    for (int i = s.length - 2; i >= 0; i--)
+      posthash[i] =
+          ((pow26[s.length - i - 1] * (s[i].codeUnits[0] - 'a'.codeUnits[0]) +
+                      posthash[i + 1]) %
+                  MOD)
+              .toInt();
+
+    // s[0...len - 1], s[s.length - len...s.length - 1]
+    for (int len = s.length - 1; len >= 1; len--) {
+      if (prehash[len - 1] == posthash[s.length - len] &&
+          _equal(s, 0, len - 1, s.length - len, s.length - 1))
+        return s.substring(0, len);
+    }
+    return "";
+  }
+
+  bool _equal(String s, int l1, int r1, int l2, int r2) {
+    for (int i = l1, j = l2; i <= r1 && j <= r2; i++, j++)
+      if (s[i] != s[j]) return false;
+    return true;
+  }
+}

24-SubString-Match/LC1392.dart

@@ -0,0 +1,25 @@
+class Solution {
+
+  String longestPrefix(String s) {
+
+    // s[0...len - 1], s[s.length - len...s.length - 1]
+    for(int len = s.length - 1; len >= 1; len --)
+      if(_equal(s, 0, len - 1, s.length - len, s.length - 1))
+        return s.substring(0, len);
+    return "";
+  }
+
+  bool _equal(String s, int l1, int r1, int l2, int r2){
+
+    for(int i = l1, j = l2; i <= r1 && j <= r2; i ++, j ++)
+      if(s[i] != s[j]) return false;
+    return true;
+  }
+
+
+}
+
+void main() {
+
+print((new Solution()).longestPrefix("level"));
+}

24-SubString-Match/LC187-RollingHash.dart

@@ -0,0 +1,35 @@
+import 'dart:collection';
+class Solution2 {
+  List<String> findRepeatedDnaSequences(String s) {
+
+    if(s.length < 10) {
+      return List.empty(growable: true);
+    };
+
+    List<int> map = List.filled(256,0, growable: true);
+    map['A'.codeUnits[0]] = 1;
+    map['C'.codeUnits[0]] = 2;
+    map['G'.codeUnits[0]] = 3;
+    map['T'.codeUnits[0]] = 4;
+
+    HashSet<int> seen = new HashSet<int>();
+    HashSet<String> res = new HashSet<String>();
+
+    int hash = 0;
+        double ten9 = 1e9;
+
+    for(int i = 0; i < 9; i ++)
+      hash = hash * 10 + map[s[i].codeUnits[0]];
+
+    for(int i = 9; i < s.length; i ++){
+
+      hash = hash * 10 + map[s[i].codeUnits[0]];
+
+      if(seen.contains(hash)) res.add(s.substring(i - 9, i + 1));
+      else seen.add(hash);
+
+      hash -= (map[s[i - 9].codeUnits[0]] * ten9).toInt();
+    }
+    return res.toList();
+  }
+}

24-SubString-Match/LC187.dart

@@ -0,0 +1,16 @@
+import 'dart:collection';
+class Solution {
+  List<String> findRepeatedDnaSequences(String s) {
+
+    HashSet<String> seen = HashSet<String>();
+    HashSet<String> res = HashSet<String>();
+    for(int i = 0; i + 10 <= s.length; i ++){
+      String key = s.substring(i, i + 10);
+      if(seen.contains(key))
+        res.add(key);
+      else
+        seen.add(key);
+    }
+    return res.toList();
+  }
+}

24-SubString-Match/Solution.dart

@@ -0,0 +1,23 @@
+/**
+ * 1147号问题使用遍历查询
+ */
+class Solution {
+  int longestDecomposition(String text) {
+    return _solve(text, 0, text.length - 1);
+  }
+
+  int _solve(String s, int left, int right) {
+    if (left > right) return 0;
+
+    for (int i = left, j = right; i < j; i++, j--) {
+      if (_equal(s, left, i, j, right)) return 2 + _solve(s, i + 1, j - 1);
+    }
+    return 1;
+  }
+
+  bool _equal(String s, int l1, int r1, int l2, int r2) {
+    for (int i = l1, j = l2; i <= r1 && j <= r2; i++, j++)
+      if (s[i] != s[j]) return false;
+    return true;
+  }
+}

24-SubString-Match/Solution2.dart

@@ -0,0 +1,41 @@
+/**
+ * 1147号问题使用hash值解决
+ */
+class Solution2 {
+  double MOD = 1e9 + 7;
+
+  List<double>? pow26;
+
+  int longestDecomposition(String text) {
+    pow26 = List.filled(text.length, 0, growable: true);
+    pow26![0] = 1;
+    for (int i = 1; i < pow26!.length; i++)
+      pow26![i] = pow26![i - 1] * 26 % MOD;
+
+    return _solve(text, 0, text.length - 1);
+  }
+
+  int _solve(String s, int left, int right) {
+    if (left > right) return 0;
+
+    int prehash = 0, posthash = 0;
+    for (int i = left, j = right; i < j; i++, j--) {
+      prehash = ((prehash * 26 + (s[i].codeUnits[0] - 'a'.codeUnits[0])) % MOD)
+          .toInt();
+      posthash = (((s[j].codeUnits[0] - 'a'.codeUnits[0]) * pow26![right - j] +
+                  posthash) %
+              MOD)
+          .toInt();
+
+      if (prehash == posthash && _equal(s, left, i, j, right))
+        return 2 + _solve(s, i + 1, j - 1);
+    }
+    return 1;
+  }
+
+  bool _equal(String s, int l1, int r1, int l2, int r2) {
+    for (int i = l1, j = l2; i <= r1 && j <= r2; i++, j++)
+      if (s[i] != s[j]) return false;
+    return true;
+  }
+}

24-SubString-Match/SubstringMatch.dart

@@ -0,0 +1,86 @@
+import 'SubstringMatchHelper.dart';
+import 'FileOperator.dart';
+
+/**
+ * 字符串匹配
+ */
+class SubstringMatch {
+  //粗暴强制
+  static int bruteforce(String s, String t) {
+    if (s.length < t.length) return -1;
+    // s[i, i + t.length - 1]
+    for (int i = 0; i + t.length - 1 < s.length; i++) {
+      int j = 0;
+      for (; j < t.length; j++)
+        if (s[i + j] != t[j]) break;
+      if (j == t.length) return i;
+    }
+    return -1;
+  }
+
+  static int rabinKarp(String s, String t) {
+    if (s.length < t.length) return -1;
+    if (t.length == 0) return 0;
+
+    int thash = 0,
+        B = 256;
+    double MOD = 1e9 + 7;
+    for(int i = 0; i < t.length; i ++){
+    thash = ((thash * B + t[i].codeUnits[0]) % MOD).toInt();
+    };
+    int hash = 0, P = 1;
+    for(int i = 0; i < t.length - 1; i ++)
+    P = (P * B % MOD).toInt();
+
+    for(int i = 0; i < t.length - 1; i ++)
+    hash = ((hash * B + s[i].codeUnits[0]) % MOD).toInt();
+
+    for(int i = t.length- 1; i < s.length; i ++){
+    hash = ((hash * B + s[i].codeUnits[0]) % MOD).toInt();
+    if(hash == thash && _equal(s, i - t.length + 1, t))
+    return i - t.length + 1;
+    hash = ((hash - s[i - t.length + 1].codeUnits[0] * P % MOD + MOD) % MOD).toInt();
+    }
+    return
+    -
+    1;
+  }
+
+  static bool _equal(String s, int l, String t) {
+    for (int i = 0; i < t.length; i ++)
+      if (s[l].codeUnits[0] + i != t[i].codeUnits[0]) return false;
+    return true;
+  }
+}
+
+void main() async {
+  String s1 = "hello, this is liuyubobobo.";
+  String t1 = "bo";
+  SubstringMatchHelper.matchTest("bruteforce", s1, t1);
+
+  List s2 = await FileOperator.getFileString("text2.txt");
+  String t2 = "china";
+  StringBuffer res = new StringBuffer();
+  for (int i = 0; i < s2.length; i++) {
+    res.write(s2[i]);
+  }
+
+  SubstringMatchHelper.matchTest("bruteforce", res.toString(), t2);
+
+  SubstringMatchHelper.matchTest("bruteforce", res.toString(), "zyx");
+
+  /// Worst case
+  int n = 1000000,
+      m = 1000;
+
+  StringBuffer s3 = new StringBuffer();
+  for (int i = 0; i < n; i++)
+    s3.write('a');
+
+  StringBuffer t3 = new StringBuffer();
+  for (int i = 0; i < m - 1; i++)
+    t3.write('a');
+  t3.write('b');
+
+  SubstringMatchHelper.matchTest("bruteforce", s3.toString(), t3.toString());
+}

24-SubString-Match/SubstringMatchHelper.dart

@@ -0,0 +1,25 @@
+import 'SubstringMatch.dart';
+class SubstringMatchHelper {
+
+  SubstringMatchHelper(){}
+
+  static void matchTest(String name, String s, String t){
+
+    int pos = -1;
+
+    int startTime = new DateTime.now().millisecondsSinceEpoch;
+    if(name == "bruteforce"){
+      pos = SubstringMatch.bruteforce(s, t);
+    }
+    int endTime = new DateTime.now().millisecondsSinceEpoch;
+
+    double time = (endTime - startTime) / 1000.0;
+
+    print(startTime);
+    print(endTime);
+    if(s.indexOf(t) != pos)
+      throw new Exception(name + " failed");
+    print("$name : res = $pos, time = $time s");
+  }
+
+}