难度:中等
在给定单词列表 wordlist
的情况下,我们希望实现一个拼写检查器,将查询单词转换为正确的单词。
对于给定的查询单词 query
,拼写检查器将会处理两类拼写错误:
- 大小写:如果查询匹配单词列表中的某个单词(不区分大小写 ),则返回的正确单词与单词列表中的大小写相同。
- 例如:
wordlist = ["yellow"]
,query = "YellOw"
:correct = "yellow"
- 例如:
wordlist = ["Yellow"]
,query = "yellow"
:correct = "Yellow"
- 例如:
wordlist = ["yellow"]
,query = "yellow"
:correct = "yellow"
- 例如:
- 元音错误:如果在将查询单词中的元音
('a', 'e', 'i', 'o', 'u')
分别替换为任何元音后,能与单词列表中的单词匹配(不区分大小写 ),则返回的正确单词与单词列表中的匹配项大小写相同。- 例如:
wordlist = ["YellOw"]
,query = "yollow"
:correct = "YellOw"
- 例如:
wordlist = ["YellOw"]
,query = "yeellow"
:correct = ""
(无匹配项) - 例如:
wordlist = ["YellOw"]
,query = "yllw"
:correct = ""
(无匹配项)
- 例如:
此外,拼写检查器还按照以下优先级规则操作:
- 当查询完全匹配单词列表中的某个单词(区分大小写)时,应返回相同的单词。
- 当查询匹配到大小写问题的单词时,您应该返回单词列表中的第一个这样的匹配项。
- 当查询匹配到元音错误的单词时,您应该返回单词列表中的第一个这样的匹配项。
- 如果该查询在单词列表中没有匹配项,则应返回空字符串。
给出一些查询 queries
,返回一个单词列表 answer
,其中 answer[i]
是由查询 query = queries[i]
得到的正确单词。
示例 1:
输入:wordlist = ["KiTe","kite","hare","Hare"], queries = ["kite","Kite","KiTe","Hare","HARE","Hear","hear","keti","keet","keto"]
输出:["kite","KiTe","KiTe","Hare","hare","","","KiTe","","KiTe"]
示例 2:
输入:wordlist = ["yellow"], queries = ["YellOw"]
输出:["yellow"]
提示:
1 <= wordlist.length, queries.length <= 5000
1 <= wordlist[i].length, queries[i].length <= 7
wordlist[i]
和queries[i]
只包含英文字母
代码
cpp
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#define HASH_SIZE 10007
typedef struct MapNode {
char* key;
char* value;
struct MapNode* next;
} MapNode;
unsigned long hash_func(const char* str) {
unsigned long hash = 0;
while (*str) {
hash = (hash * 131 + (unsigned char)(*str)) % HASH_SIZE;
str++;
}
return hash;
}
void set_insert(MapNode** hashtable, const char* key) {
unsigned long idx = hash_func(key);
MapNode* p = hashtable[idx];
while (p) {
if (strcmp(p->key, key) == 0) {
return;
}
p = p->next;
}
MapNode* node = (MapNode*)malloc(sizeof(MapNode));
node->key = strdup(key);
node->value = NULL;
node->next = hashtable[idx];
hashtable[idx] = node;
}
int set_contains(MapNode** hashtable, const char* key) {
unsigned long idx = hash_func(key);
MapNode* p = hashtable[idx];
while (p) {
if (strcmp(p->key, key) == 0) {
return 1;
}
p = p->next;
}
return 0;
}
void map_insert(MapNode** hashtable, const char* key, const char* value) {
unsigned long idx = hash_func(key);
MapNode* p = hashtable[idx];
while (p) {
if (strcmp(p->key, key) == 0) {
return;
}
p = p->next;
}
MapNode* node = (MapNode*)malloc(sizeof(MapNode));
node->key = strdup(key);
node->value = strdup(value);
node->next = hashtable[idx];
hashtable[idx] = node;
}
char* map_get(MapNode** hashtable, const char* key) {
unsigned long idx = hash_func(key);
MapNode* p = hashtable[idx];
while (p) {
if (strcmp(p->key, key) == 0) {
return p->value;
}
p = p->next;
}
return NULL;
}
char* tolower_string(const char* str) {
int len = strlen(str);
char* res = (char*)malloc(len + 1);
for (int i = 0; i < len; i++) {
res[i] = tolower(str[i]);
}
res[len] = '\0';
return res;
}
char* replace_vowel(const char* str) {
int len = strlen(str);
char* res = (char*)malloc(len + 1);
for (int i = 0; i < len; i++) {
char c = str[i];
if (c == 'a' || c == 'e' || c == 'i' || c == 'o' || c == 'u') {
res[i] = '*';
} else {
res[i] = c;
}
}
res[len] = '\0';
return res;
}
void free_hashtable(MapNode** hashtable) {
for (int i = 0; i < HASH_SIZE; i++) {
MapNode* p = hashtable[i];
while (p) {
MapNode* tmp = p;
p = p->next;
free(tmp->key);
if (tmp->value) free(tmp->value);
free(tmp);
}
}
}
char** spellchecker(char** wordlist, int wordlistSize, char** queries, int queriesSize, int* returnSize) {
MapNode* set_exact[HASH_SIZE] = {0};
MapNode* map_lower[HASH_SIZE] = {0};
MapNode* map_vowel[HASH_SIZE] = {0};
for (int i = 0; i < wordlistSize; i++) {
char* word = wordlist[i];
if (!set_contains(set_exact, word)) {
set_insert(set_exact, word);
}
char* lower = tolower_string(word);
if (map_get(map_lower, lower) == NULL) {
map_insert(map_lower, lower, word);
}
free(lower);
char* lower2 = tolower_string(word);
char* vow_str = replace_vowel(lower2);
if (map_get(map_vowel, vow_str) == NULL) {
map_insert(map_vowel, vow_str, word);
}
free(lower2);
free(vow_str);
}
char** ans = (char**)malloc(queriesSize * sizeof(char*));
*returnSize = queriesSize;
for (int i = 0; i < queriesSize; i++) {
char* q = queries[i];
if (set_contains(set_exact, q)) {
ans[i] = strdup(q);
} else {
char* q_lower = tolower_string(q);
char* candidate = map_get(map_lower, q_lower);
if (candidate) {
ans[i] = strdup(candidate);
free(q_lower);
continue;
}
char* q_vow = replace_vowel(q_lower);
candidate = map_get(map_vowel, q_vow);
if (candidate) {
ans[i] = strdup(candidate);
} else {
ans[i] = strdup("");
}
free(q_lower);
free(q_vow);
}
}
free_hashtable(set_exact);
free_hashtable(map_lower);
free_hashtable(map_vowel);
return ans;
}