Trie树实现字符串前缀统计

题目

字符串前缀统计

Description

给定N个单词，建立 Trie 树；
求所有长度为M的前缀中出现的次数最多的前缀。

Input

第一行：N,M
接下来N行每行一个单词,单词的长度不超过15

Output

长度为M的字符串，表示前缀长度为M的出现次数最多的字符串前缀

Sample Input

3 2
abc
abd
acd

Sample Output

ab

解题思路

用Trie树实现，定义树的节点为一个结构体。元素包括：一个字符型数据，27个指向该类型节点的指针，以及一个整型元素（记录经过这个点的字符串数）。
难点在于插入字符串和统计字符串前缀这两个函数的实现。

代码如下

Trie_node.h

#include<iostream>
using namespace std;
const int num_chars = 27;
struct Trie_node 
{
	char data;
	Trie_node* branch[num_chars];
	int numpass;
	Trie_node() {
		data = '\0';
		for (int i = 0; i < num_chars; i++)
			branch[i] = NULL;
		numpass = 0;
	}
};

Key.h

#pragma once
#include"Trie_node.h"
class Key {
public:
	Key(string s);
	char* the_key() ;
	char key_letter(int position);
private:
	char str[10];
};

Key.cpp

#include "Key.h"
Key::Key(string s) 
{
	int i;
	for (i = 0; i <= s.size(); i++)
		str[i] = s[i];
}
char* Key::the_key()
{
	return (char*)str;
}
char Key::key_letter(int position)
{    //返回字符串中该位置的字符
	if (position < strlen(str)) 
		return str[position];
	else 
		return '\0';
}

Trie.h

#pragma once
#include"Key.h"
enum Error_code { not_present, overflow, underflow, duplicate_error, success };
class Trie
{
public: 
	Error_code insert(Key& new_entry);
	Trie();
	int countPrefix(Key s,int num);
private: 
	Trie_node* root;
};
int alphabetic_order(char c);

Trie.cpp

#include "Trie.h"
int alphabetic_order(char c)
//返回字符c是在字典序中的第几个位置
{
	if (c == ' ' || c == '\0') return 0;
	if ('a' <= c && c <= 'z') return c - 'a' + 1;
	if ('A' <= c && c <= 'Z') return c - 'A' + 1;
}
Trie::Trie() {
	root = NULL;
}
Error_code Trie::insert(Key& new_entry)
{
	Error_code result = success;
	if (root == NULL) root = new Trie_node; //如果根节点不存在，生成新的根节点
	int position = 0; 
	char next_char;
	Trie_node* location = root; 
	while (location != NULL &&(next_char = new_entry.key_letter(position)) != '\0') 
	{
		int next_position = alphabetic_order(next_char);
		if (location->branch[next_position] == NULL)
			location->branch[next_position] = new Trie_node;
		location = location->branch[next_position];
		location->data = 'a' + next_position - 1;
		location->numpass++;
		position++;
	}
	return result;
}
int Trie::countPrefix(Key s,int num)
{
	int i;
	Trie_node* location = root;
	for (i = 0; i < num; i++)
	{
		int next_position = alphabetic_order(s.key_letter(i));
		location = location->branch[next_position];
	}
	return location->numpass;
}

main.cpp

#include<vector>
#include"Trie.h"
using namespace std;
int main()
{
	Trie t;
	int N,M,i;
	cin >> N>>M;
	string str[10];
	for (i = 0; i < N; i++)
	{
		cin >> str[i];
		Key* k=new Key(str[i]);
		t.insert(*k);
	}
	vector<int> v;
	int m;
	for (i = 0; i < N; i++)
	{
		Key* k = new Key(str[i]);
		m=t.countPrefix(*k, M);
		v.push_back(m);
	}
	int max = v[0];
	for (i = 0; i < N; i++)
	{
		if (v[i] > max)
			max = v[i];
	}
	int j;
	for (j = 0; j < N; j++)
	{
		if (v[j] == max)
			break;
	}
	cout << str[j].substr(0, M);
	return 0;
}