[POJ] #1003# 487-3279 : 桶排序/字典树(Trie树)/快速排序
Posted
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了[POJ] #1003# 487-3279 : 桶排序/字典树(Trie树)/快速排序相关的知识,希望对你有一定的参考价值。
一. 题目
Time Limit: 2000MS | Memory Limit: 65536K | |
Total Submissions: 274040 | Accepted: 48891 |
Description
The standard form of a telephone number is seven decimal digits with a hyphen between the third and fourth digits (e.g. 888-1200). The keypad of a phone supplies the mapping of letters to numbers, as follows:
A, B, and C map to 2
D, E, and F map to 3
G, H, and I map to 4
J, K, and L map to 5
M, N, and O map to 6
P, R, and S map to 7
T, U, and V map to 8
W, X, and Y map to 9
There is no mapping for Q or Z. Hyphens are not dialed, and can be added and removed as necessary. The standard form of TUT-GLOP is 888-4567, the standard form of 310-GINO is 310-4466, and the standard form of 3-10-10-10 is 310-1010.
Two telephone numbers are equivalent if they have the same standard form. (They dial the same number.)
Your company is compiling a directory of telephone numbers from local businesses. As part of the quality control process you want to check that no two (or more) businesses in the directory have the same telephone number.
Input
Output
No duplicates.
Sample Input
12 4873279 ITS-EASY 888-4567 3-10-10-10 888-GLOP TUT-GLOP 967-11-11 310-GINO F101010 888-1200 -4-8-7-3-2-7-9- 487-3279
Sample Output
310-1010 2 487-3279 4 888-4567 3
Source
二. 题意
1.电话簿上的电话号码为了方便记忆,并非全用数字表示,有些用字母表示或用 “ - ” 符号分割
2.字母与数字之间存在一定的映射关系,“ - ” 没有实际意义
3. 通过转换后得到统一标准的电话号码,其构成为"xxx-xxxx", 总共由八位字符(七位数字和一个"-")符号构成
5. 现在给定一个电话清单,从中找出重复的电话号码
三. 分析
1. 算法核心: 三种解决方法
1.1 桶排序
1.2 字典树(Trie树)
1.3 快速排序
2. 实现细节:
2.1 桶排序
2.1.1 桶的大小为七位数的上限(10000000)
2.1.2 每个桶存储对应7位数的电话号码出现的次数
2.1.3 将电话号码转换为7位数,递增对应该七位数的桶元素的值
2.1.4 遍历所有桶,得到和输出大于1的所有桶元素
2.1.5 小细节: 字符到数的转换,输出格式的正确转换
2.2 字典树(Trie树)
2.2.1 建立Trie树: 用静态数组存储每个node, 简化代码实现
2.2.2 遍历所有输入电话号码,转换为数字,将该数字插入Trie树
2.2.3 每插入一个完整电话号码,在其最后插入的node中设置两个标记:出现次数 和 完整电话号码的结束标记
2.2.4 深度遍历(dfs)Trie树, 输出所有出现次数大于1的完整电话号码
2.2.5 Trie树的所有child构成为从左到右(0 - 9),遍历的顺序也是如此,从而保证了电话号码的输出顺序也是从小到大
2.3 快速排序
2.3.1 用一个二维字符数组存储所有的电话号码
2.3.2 对该数组进行快速排序
2.3.3 遍历该有序数组,顺序输出大于1的所有电话号码
2.3.4 个人实现算法的宗旨是尽量少用库,能实现的尽量自己实现
2.3.4.1 对于此题,发现如果用自己实现的快速排序,发现会超时
2.3.4.2 换成库的qsort则可以通过
2.3.4.3 分析发现实际上库对于qsort做了很多的优化,并非基本的快排,有时间可以研究一下
2.3.4.4 两个qsort优化的参考文档:
http://blog.chinaunix.net/uid-25510439-id-275436.html
http://blog.csdn.net/insistgogo/article/details/7785038
四. 题解
4.1 桶排序
1 #include <stdio.h> 2 3 #define PHONE_NUMBER 256 4 #define MAX_NUMBER 10000000 5 #define BASE_NUMBER 1000000 6 #define LENGTH_NUMBER 8 7 #define MAP_SIZE (‘Z‘ - ‘A‘ + 1) 8 int map_num[MAP_SIZE] = {2, 2, 2, 3, 3, 3, 4, 4, 4, 9 5, 5, 5, 6, 6, 6, 7, -1, 7, 10 7, 8, 8, 8, 9, 9, 9, -1}; 11 int bucket[MAX_NUMBER]; 12 13 int main() 14 { 15 int i = 0, j = 0, count = 0, nums = 0; 16 17 scanf("%d\n", &count); 18 for (j = 0; j < count; j++) { 19 char phone_number[PHONE_NUMBER]; 20 int tmp = 0; 21 22 scanf("%s\n", phone_number); 23 24 for (i = 0; phone_number[i] != ‘\0‘; i++) { 25 if (‘-‘ == phone_number[i]) continue; 26 tmp = tmp * 10 + 27 ((phone_number[i] >= ‘A‘ && phone_number[i] <= ‘Z‘) ? 28 map_num[phone_number[i] - ‘A‘] : phone_number[i] - ‘0‘); 29 } 30 bucket[tmp]++; 31 } 32 33 for (i = 0; i < MAX_NUMBER; i++) { 34 int b_tmp, base_number = BASE_NUMBER; 35 36 if (bucket[i] < 2) continue; 37 38 b_tmp = i; 39 nums++; 40 41 for (j = 0; j < LENGTH_NUMBER; j++) { 42 if (3 == j) { printf("-"); continue; } 43 printf("%d", b_tmp / base_number); 44 b_tmp %= base_number; 45 base_number /= 10; 46 } 47 printf(" %d\n", bucket[i]); 48 } 49 50 if (0 == nums) printf("No duplicates.\n"); 51 52 return 0; 53 }
4.2 字典树(Trie树)
1 #include <stdio.h> 2 3 #define BASE_NUMBER 1000000 4 #define MAP_SIZE (‘Z‘ - ‘A‘ + 1) 5 #define TRIE_CHILD_CNTS 10 6 #define PHONE_NUMBER 256 7 #define PHONE_NUMBER_LENGTH 7 8 #define BASE_NUMBER 1000000 9 10 int map_num[MAP_SIZE] = {2, 2, 2, 3, 3, 3, 4, 4, 4, 11 5, 5, 5, 6, 6, 6, 7, -1, 7, 12 7, 8, 8, 8, 9, 9, 9, -1}; 13 int tree_index = 0; 14 int is_duplicated = 0; 15 16 typedef struct Trie { 17 int is_word; 18 int word_cnts; 19 struct Trie* childs[TRIE_CHILD_CNTS]; 20 } trie_tree_t; 21 22 trie_tree_t trie_nodes[BASE_NUMBER]; 23 24 void new_trie_tree(int index) { 25 int i; 26 trie_nodes[index].is_word = 0; 27 trie_nodes[index].word_cnts = 0; 28 for (i = 0; i < TRIE_CHILD_CNTS; i++) trie_nodes[index].childs[i] = NULL; 29 } 30 31 void add_trie_node(int num) { 32 int i, j, base_number = BASE_NUMBER; 33 trie_tree_t* tree = &trie_nodes[0]; 34 35 for (i = 0; i < PHONE_NUMBER_LENGTH; i++) { 36 j = num / base_number; 37 num %= base_number; 38 base_number /= 10; 39 if (NULL == tree->childs[j]) { 40 new_trie_tree(++tree_index); 41 tree->childs[j] = &trie_nodes[tree_index]; 42 } 43 tree = tree->childs[j]; 44 } 45 46 tree->is_word = 1; 47 tree->word_cnts++; 48 } 49 50 void dfs(int phone_number[PHONE_NUMBER_LENGTH], int number_index, trie_tree_t *tree_p) 51 { 52 int i; 53 if (tree_p->is_word && 1 < tree_p->word_cnts) { 54 for (i = 0; i < PHONE_NUMBER_LENGTH; i++) { 55 if (3 == i) printf("-"); 56 57 printf("%d", phone_number[i]); 58 } 59 60 printf(" %d\n", tree_p->word_cnts); 61 is_duplicated = 1; 62 } 63 64 for (i = 0; i < TRIE_CHILD_CNTS; i++) { 65 if (tree_p->childs[i] && number_index < PHONE_NUMBER_LENGTH) { 66 phone_number[number_index] = i; 67 dfs(phone_number, number_index + 1, tree_p->childs[i]); 68 } 69 } 70 } 71 72 int main() 73 { 74 int i = 0, j = 0, tmp = 0, count = 0; 75 int number[PHONE_NUMBER_LENGTH]; 76 77 scanf("%d\n", &count); 78 for (j = 0; j < count; j++) { 79 char phone_number[PHONE_NUMBER]; 80 int tmp = 0; 81 scanf("%s\n", phone_number); 82 83 for (i = 0; phone_number[i] != ‘\0‘; i++) { 84 if (‘-‘ == phone_number[i]) continue; 85 tmp = tmp * 10 + 86 ((phone_number[i] >= ‘A‘ && phone_number[i] <= ‘Z‘) ? 87 map_num[phone_number[i] - ‘A‘] : phone_number[i] - ‘0‘); 88 } 89 90 add_trie_node(tmp); 91 } 92 93 dfs(number, 0, &trie_nodes[0]); 94 95 if (0 == is_duplicated) printf("No duplicates.\n"); 96 97 return 0; 98 }
4.3 快速排序
1 #include <stdio.h> 2 #include <stdlib.h> 3 #include <string.h> 4 5 #define PHONE_NUMBER 256 6 #define MAX_NUMBERS 100000 7 #define LENGTH_NUMBER 9 8 #define MAP_SIZE (‘Z‘ - ‘A‘ + 1) 9 #define SEP_INDEX 3 10 11 #define CUSTOM 0 12 #define USING_POINTER_FOR_COMPARE 0 13 14 char map_num[MAP_SIZE] = {‘2‘, ‘2‘, ‘2‘, ‘3‘, ‘3‘, ‘3‘, ‘4‘, ‘4‘, ‘4‘, 15 ‘5‘, ‘5‘, ‘5‘, ‘6‘, ‘6‘, ‘6‘, ‘7‘, ‘-1‘, ‘7‘, 16 ‘7‘, ‘8‘, ‘8‘, ‘8‘, ‘9‘, ‘9‘, ‘9‘, ‘-1‘}; 17 18 char numbers[MAX_NUMBERS][LENGTH_NUMBER]; 19 20 #if USING_POINTER_FOR_COMPARE 21 char *p_numbers[MAX_NUMBERS]; 22 #endif 23 24 int is_duplicate = 0; 25 26 int mystrcmp(const char *str1, const char *str2) 27 { 28 while (*str1 == *str2) { 29 if (*str1 == ‘\0‘) return 0; 30 str1++; str2++; 31 } 32 33 return *str1 - *str2; 34 } 35 36 #if CUSTOM 37 38 #if USING_POINTER_FOR_COMPARE 39 40 void quicksort(char *A[], int left, int right, int(*func)(const char*, const char*)) { 41 int i = left, j = right; 42 char *t, *tmp; 43 tmp = A[i]; 44 45 if (i > j) return; 46 47 while (i != j) { 48 while (func(tmp, A[j]) <= 0 && i < j) j--; 49 while (func(A[i], tmp) <= 0 && i < j) i++; 50 51 if (i < j) { 52 t = A[i]; 53 A[i] = A[j]; 54 A[j] = t; 55 } 56 } 57 A[left] = A[i]; 58 A[i] = tmp; 59 60 quicksort(A, left, i - 1, func); 61 quicksort(A, i + 1, right, func); 62 } 63 64 #else 65 66 void mystrcpy(char *str1, const char *str2) 67 { 68 while (*str2 != ‘\0‘) { 69 *str1 = *str2; 70 str1++; str2++; 71 } 72 73 *str1 = ‘\0‘; 74 } 75 76 void quicksort(char A[][LENGTH_NUMBER], int left, int right, int(*func)(const char*, const char*)) { 77 int i = left, j = right; 78 char t[LENGTH_NUMBER], tmp[LENGTH_NUMBER]; 79 mystrcpy(tmp, A[i]); 80 81 if (i > j) return; 82 83 while (i != j) { 84 while (func(tmp, A[j]) <= 0 && i < j) j--; 85 while (func(A[i], tmp) <= 0 && i < j) i++; 86 87 if (i < j) { 88 mystrcpy(t, A[i]); 89 mystrcpy(A[i], A[j]); 90 mystrcpy(A[j], t); 91 } 92 } 93 mystrcpy(A[left], A[i]); 94 mystrcpy(A[i], tmp); 95 96 quicksort(A, left, i - 1, func); 97 quicksort(A, i + 1, right, func); 98 } 99 100 #endif 101 102 #endif 103 104 int sort_function(const void *a,const void *b) 105 { 106 return(strcmp((char*)a,(char*)b)); 107 } 108 109 int main() 110 { 111 int i = 0, j = 0, count = 0, nums = 1, number_index = 0; 112 113 scanf("%d\n", &count); 114 for (j = 0; j < count; j++) { 115 char phone_number[PHONE_NUMBER]; 116 117 scanf("%s\n", phone_number); 118 119 for (i = 0; phone_number[i] != ‘\0‘; i++) { 120 if (‘-‘ == phone_number[i]) continue; 121 if (SEP_INDEX == number_index) numbers[j][number_index++] = ‘-‘; 122 numbers[j][number_index++] = ((phone_number[i] >= ‘A‘ && phone_number[i] <= ‘Z‘) ? 123 map_num[phone_number[i] - ‘A‘] : phone_number[i]); 124 } 125 number_index = 0; 126 127 #if USING_POINTER_FOR_COMPARE 128 p_numbers[j] = numbers[j]; 129 #endif 130 131 } 132 133 #if CUSTOM 134 quicksort(p_numbers, 0, count - 1, mystrcmp); 135 136 #if USING_POINTER_FOR_COMPARE 137 138 for (j = 0; j < count - 1; j++) { 139 if (0 == mystrcmp(p_numbers[j], p_numbers[j + 1])) { 140 is_duplicate = 1; 141 nums++; 142 } else { 143 if (1 < nums) printf("%s %d\n", p_numbers[j], nums); 144 nums = 1; 145 } 146 } 147 148 if (1 < nums) printf("%s %d\n", p_numbers[j], nums); 149 150 #else 151 152 for (j = 0; j < count - 1; j++) { 153 if (0 == mystrcmp(numbers[j], numbers[j + 1])) { 154 is_duplicate = 1; 155 nums++; 156 } else { 157 if (1 < nums) printf("%s %d\n", numbers[j], nums); 158 nums = 1; 159 } 160 } 161 162 if (1 < nums) printf("%s %d\n", numbers[j], nums); 163 164 #endif 165 166 167 #else 168 169 qsort(numbers, count, LENGTH_NUMBER, sort_function); 170 171 for (j = 0; j < count - 1; j++) { 172 if (0 == mystrcmp(numbers[j], numbers[j + 1])) { 173 is_duplicate = 1; 174 nums++; 175 } else { 176 if (1 < nums) printf("%s %d\n", numbers[j], nums); 177 nums = 1; 178 } 179 } 180 181 if (1 < nums) printf("%s %d\n", numbers[j], nums); 182 183 #endif 184 185 if (0 == is_duplicate) printf("No duplicates.\n"); 186 187 return 0; 188 }
以上是关于[POJ] #1003# 487-3279 : 桶排序/字典树(Trie树)/快速排序的主要内容,如果未能解决你的问题,请参考以下文章