diff --git a/codes/c/chapter_array_and_linkedlist/linked_list.c b/codes/c/chapter_array_and_linkedlist/linked_list.c index a8de0873..94bbe3a5 100644 --- a/codes/c/chapter_array_and_linkedlist/linked_list.c +++ b/codes/c/chapter_array_and_linkedlist/linked_list.c @@ -1,6 +1,6 @@ /** * File: linked_list.c - * Created Time: 2022-01-12 + * Created Time: 2023-01-12 * Author: Zero (glj0@outlook.com) */ diff --git a/codes/c/chapter_array_and_linkedlist/my_list.c b/codes/c/chapter_array_and_linkedlist/my_list.c index 879d7433..820a6814 100644 --- a/codes/c/chapter_array_and_linkedlist/my_list.c +++ b/codes/c/chapter_array_and_linkedlist/my_list.c @@ -1,62 +1,64 @@ /** - * File: list.c - * Created Time: 2022-01-12 + * File: my_list.c + * Created Time: 2023-01-12 * Author: Zero (glj0@outlook.com) */ #include "../include/include.h" - // 用数组实现 list -struct mylist { - int* nums; // 数组（存储列表元素） +struct myList { + int *nums; // 数组（存储列表元素） int capacity; // 列表容量 int size; // 列表大小 int extendRatio; // 列表每次扩容的倍数 }; -typedef struct mylist MyList; +typedef struct myList myList; + /* 前置声明 */ -void extendCapacity(MyList *list); +void extendCapacity(myList *list); /* 构造函数 */ -void newMyList(MyList *list) { +myList *newMyList() { + myList *list = malloc(sizeof(myList)); list->capacity = 10; list->nums = malloc(sizeof(int) * list->capacity); list->size = 0; list->extendRatio = 2; + return list; } /* 析构函数 */ -void delMyList(MyList *list) { - list->size = 0; +void delMyList(myList *list) { free(list->nums); + free(list); } /* 获取列表长度 */ -int size(MyList *list) { +int size(myList *list) { return list->size; } /* 获取列表容量 */ -int capacity(MyList *list) { +int capacity(myList *list) { return list->capacity; } /* 访问元素 */ -int get(MyList *list, int index) { +int get(myList *list, int index) { assert(index < list->size); return list->nums[index]; } /* 更新元素 */ -void set(MyList *list, int index, int num) { +void set(myList *list, int index, int num) { assert(index < list->size); list->nums[index] = num; } /* 尾部添加元素 */ -void add(MyList *list, int num) { +void add(myList *list, int num) { if (size(list) == capacity(list)) { extendCapacity(list); // 扩容 } @@ -65,10 +67,10 @@ void add(MyList *list, int num) { } /* 中间插入元素 */ -void insert(MyList *list, int index, int num) { +void insert(myList *list, int index, int num) { assert(index < size(list)); for (int i = size(list); i > index; --i) { - list->nums[i] = list->nums[i-1]; + list->nums[i] = list->nums[i - 1]; } list->nums[index] = num; list->size++; @@ -77,25 +79,25 @@ void insert(MyList *list, int index, int num) { /* 删除元素 */ // 由于引入了 stdio.h ，此处无法使用 remove 关键词 // 详见 https://github.com/krahets/hello-algo/pull/244#discussion_r1067863888 -int removeNum(MyList *list, int index) { +int removeNum(myList *list, int index) { assert(index < size(list)); int num = list->nums[index]; for (int i = index; i < size(list) - 1; i++) { - list->nums[i] = list->nums[i+1]; + list->nums[i] = list->nums[i + 1]; } list->size--; return num; } /* 列表扩容 */ -void extendCapacity(MyList *list) { +void extendCapacity(myList *list) { // 先分配空间 int newCapacity = capacity(list) * list->extendRatio; - int *extend = (int *)malloc(sizeof(int) * newCapacity); + int *extend = (int *) malloc(sizeof(int) * newCapacity); int *temp = list->nums; // 拷贝旧数据到新数据 - for(int i = 0; i < size(list); i++) + for (int i = 0; i < size(list); i++) extend[i] = list->nums[i]; // 释放旧数据 @@ -107,53 +109,52 @@ void extendCapacity(MyList *list) { } /* 将列表转换为 Array 用于打印 */ -int* toArray(MyList *list) { +int *toArray(myList *list) { return list->nums; } int main() { /* 初始化列表 */ - MyList list; - newMyList(&list); + myList *list = newMyList(); /* 尾部添加元素 */ - add(&list, 1); - add(&list, 3); - add(&list, 2); - add(&list, 5); - add(&list, 4); + add(list, 1); + add(list, 3); + add(list, 2); + add(list, 5); + add(list, 4); printf("列表 list = "); - printArray(toArray(&list), size(&list)); - printf("容量 = %d ，长度 = %d\r\n", capacity(&list), size(&list)); + printArray(toArray(list), size(list)); + printf("容量 = %d ，长度 = %d\n", capacity(list), size(list)); /* 中间插入元素 */ - insert(&list, 3, 6); + insert(list, 3, 6); printf("在索引 3 处插入数字 6 ，得到 list = "); - printArray(toArray(&list), size(&list)); + printArray(toArray(list), size(list)); /* 删除元素 */ - removeNum(&list, 3); + removeNum(list, 3); printf("删除索引 3 处的元素，得到 list = "); - printArray(toArray(&list), size(&list)); + printArray(toArray(list), size(list)); /* 访问元素 */ - int num = get(&list, 1); - printf("访问索引 1 处的元素，得到 num = %d\r\n", num); + int num = get(list, 1); + printf("访问索引 1 处的元素，得到 num = %d\n", num); /* 更新元素 */ - set(&list, 1, 0); + set(list, 1, 0); printf("将索引 1 处的元素更新为 0 ，得到 list = "); - printArray(toArray(&list), size(&list)); + printArray(toArray(list), size(list)); /* 测试扩容机制 */ for (int i = 0; i < 10; i++) { // 在 i = 5 时，列表长度将超出列表容量，此时触发扩容机制 - add(&list, i); + add(list, i); } printf("扩容后的列表 list = "); - printArray(toArray(&list), size(&list)); - printf("容量 = %d ，长度 = %d\r\n", capacity(&list), size(&list)); + printArray(toArray(list), size(list)); + printf("容量 = %d ，长度 = %d\n", capacity(list), size(list)); - /* 析构函数，释放分配内存 */ - delMyList(&list); + /* 释放分配内存 */ + delMyList(list); } \ No newline at end of file diff --git a/codes/c/chapter_computational_complexity/CMakeLists.txt b/codes/c/chapter_computational_complexity/CMakeLists.txt index d9e55dcf..6fb1dee0 100644 --- a/codes/c/chapter_computational_complexity/CMakeLists.txt +++ b/codes/c/chapter_computational_complexity/CMakeLists.txt @@ -1,2 +1,3 @@ add_executable(time_complexity time_complexity.c ) -add_executable(worst_best_time_complexity worst_best_time_complexity.c) \ No newline at end of file +add_executable(worst_best_time_complexity worst_best_time_complexity.c) +add_executable(leetcode_two_sum leetcode_two_sum.c) \ No newline at end of file diff --git a/codes/c/chapter_computational_complexity/leetcode_two_sum.c b/codes/c/chapter_computational_complexity/leetcode_two_sum.c new file mode 100644 index 00000000..bfc621aa --- /dev/null +++ b/codes/c/chapter_computational_complexity/leetcode_two_sum.c @@ -0,0 +1,85 @@ +/** + * File: leetcode_two_sum.c + * Created Time: 2023-01-19 + * Author: Reanon (793584285@qq.com) + */ + +#include "../include/include.h" + +/* 暴力解法 */ +int *twoSumBruteForce(int *nums, int numsSize, int target, int *returnSize) { + for (int i = 0; i < numsSize; ++i) { + for (int j = i + 1; j < numsSize; ++j) { + if (nums[i] + nums[j] == target) { + int *ret = malloc(sizeof(int) * 2); + ret[0] = i, ret[1] = j; + *returnSize = 2; + return ret; + } + } + } + *returnSize = 0; + return NULL; +} + +/* 哈希表 */ +struct hashTable { + int key; + int val; + // 借助 LetCode 上常用的哈希表 + UT_hash_handle hh; +}; + +typedef struct hashTable hashTable; + +hashTable *find(hashTable *h, int key) { + hashTable *tmp; + HASH_FIND_INT(h, &key, tmp); + return tmp; +} + +void insert(hashTable *h, int key, int val) { + hashTable *t = find(h, key); + if (t == NULL) { + hashTable *tmp = malloc(sizeof(hashTable)); + tmp->key = key, tmp->val = val; + HASH_ADD_INT(h, key, tmp); + } else { + t->val = val; + } +} + + +int *twoSumHashTable(int *nums, int numsSize, int target, int *returnSize) { + hashTable *hashtable = NULL; + for (int i = 0; i < numsSize; i++) { + hashTable *t = find(hashtable, target - nums[i]); + if (t != NULL) { + int *ret = malloc(sizeof(int) * 2); + ret[0] = t->val, ret[1] = i; + *returnSize = 2; + return ret; + } + insert(hashtable, nums[i], i); + } + *returnSize = 0; + return NULL; +} + +int main() { + // ======= Test Case ======= + int nums[] = {2, 7, 11, 15}; + int target = 9; + // ====== Driver Code ====== + int returnSize; + int *res = twoSumBruteForce(nums, sizeof(nums) / sizeof(int), target, &returnSize); + // 方法一 + printf("方法一 res = "); + printArray(res, returnSize); + + // 方法二 + res = twoSumHashTable(nums, sizeof(nums) / sizeof(int), target, &returnSize); + printf("方法二 res = "); + printArray(res, returnSize); + return 0; +} \ No newline at end of file diff --git a/codes/c/chapter_sorting/quick_sort.c b/codes/c/chapter_sorting/quick_sort.c index f3c7498c..4268575a 100644 --- a/codes/c/chapter_sorting/quick_sort.c +++ b/codes/c/chapter_sorting/quick_sort.c @@ -63,7 +63,7 @@ int medianThree(int nums[], int left, int mid, int right) { } // 哨兵划分（三数取中值） -int QuickSortMedianPartition(int nums[], int left, int right) { +int quickSortMedianPartition(int nums[], int left, int right) { // 选取三个候选元素的中位数 int med = medianThree(nums, left, (left + right) / 2, right); // 将中位数交换至数组最左端 @@ -87,7 +87,7 @@ void quickSortMedian(int nums[], int left, int right) { if (left >= right) return; // 哨兵划分 - int pivot = QuickSortMedianPartition(nums, left, right); + int pivot = quickSortMedianPartition(nums, left, right); // 递归左子数组、右子数组 quickSortMedian(nums, left, pivot - 1); quickSortMedian(nums, pivot + 1, right); diff --git a/codes/c/chapter_stack_and_queue/array_stack.c b/codes/c/chapter_stack_and_queue/array_stack.c index 5ae21125..0727b91d 100644 --- a/codes/c/chapter_stack_and_queue/array_stack.c +++ b/codes/c/chapter_stack_and_queue/array_stack.c @@ -1,123 +1,103 @@ /** * File: array_stack.c - * Created Time: 2022-01-12 + * Created Time: 2023-01-12 * Author: Zero (glj0@outlook.com) */ #include "../include/include.h" +#define MAX_SIZE 5000 + /* 基于数组实现的栈 */ -struct ArrayStack { - int *stackTop; +struct arrayStack { + int *data; int size; - int capacity; }; -typedef struct ArrayStack ArrayStack; +typedef struct arrayStack arrayStack; -/* 内部调用 */ -/* 获取栈容量 */ -static int capacity(ArrayStack *stk) { - return stk->capacity; -} - -/* 栈自动扩容 */ -static void extendCapacity(ArrayStack *stk) { - // 先分配空间 - int newCapacity = capacity(stk) * 2; - int *extend = (int *)malloc(sizeof(int) * newCapacity); - int *temp = stk->stackTop; - - // 拷贝旧数据到新数据 - for(int i=0; isize; i++) - extend[i] = temp[i]; - - // 释放旧数据 - free(temp); - - // 更新新数据 - stk->stackTop = extend; - stk->capacity = newCapacity; -} - -/* 构造函数 */ -void newArrayStack(ArrayStack *stk) { - stk->capacity = 10; - stk->size = 0; - stk->stackTop = (int *)malloc(sizeof(int) * stk->capacity); -} - -/* 析构函数 */ -void delArrayStack(ArrayStack *stk) { - stk->capacity = 0; - stk->size = 0; - free(stk->stackTop); +arrayStack *newArrayStack() { + arrayStack *s = malloc(sizeof(arrayStack)); + // 初始化一个大容量，避免扩容 + s->data = malloc(sizeof(int) * MAX_SIZE); + s->size = 0; + return s; } /* 获取栈的长度 */ -int size(ArrayStack *stk) { - return stk->size; +int size(arrayStack *s) { + return s->size; } /* 判断栈是否为空 */ -bool empty(ArrayStack *stk) { - return size(stk) == 0; -} - -/* 访问栈顶元素 */ -int top(ArrayStack *stk) { - return stk->stackTop[size(stk) - 1]; +bool isEmpty(arrayStack *s) { + return s->size == 0; } /* 入栈 */ -void push(ArrayStack *stk, int num) { - if (size(stk) == capacity(stk)) - extendCapacity(stk); // 需要扩容 +void push(arrayStack *s, int num) { + if (s->size == MAX_SIZE) { + printf("stack is full.\n"); + return; + } + s->data[s->size] = num; + s->size++; +} - stk->stackTop[size(stk)] = num; - stk->size++; +/* 访问栈顶元素 */ +int peek(arrayStack *s) { + if (s->size == 0) { + printf("stack is empty.\n"); + return NIL; + } + return s->data[s->size - 1]; } /* 出栈 */ -void pop(ArrayStack *stk) { - int num = stk->stackTop[size(stk) - 1]; - stk->size--; +int pop(arrayStack *s) { + if (s->size == 0) { + printf("stack is empty.\n"); + return NIL; + } + int val = peek(s); + s->size--; + return val; } /* Driver Code */ int main() { /* 初始化栈 */ - ArrayStack stack; - newArrayStack(&stack); + arrayStack * stack = newArrayStack(); /* 元素入栈 */ - push(&stack, 1); - push(&stack, 3); - push(&stack, 2); - push(&stack, 5); - push(&stack, 4); - + push(stack, 1); + push(stack, 3); + push(stack, 2); + push(stack, 5); + push(stack, 4); printf("栈 stack = "); - printArray(stack.stackTop, size(&stack)); + printArray(stack->data, stack->size); /* 访问栈顶元素 */ - int stackTop = top(&stack); - printf("栈顶元素 top = %d\r\n", stackTop); + int val = peek(stack); + printf("栈顶元素 top = %d\n", val); /* 元素出栈 */ - pop(&stack); - printf("出栈元素 pop = %d, 出栈后 stack = ", stackTop); - printArray(stack.stackTop, size(&stack)); + val = pop(stack); + printf("出栈元素 pop = %d，出栈后 stack = ", val); + printArray(stack->data, stack->size); /* 获取栈的长度 */ - int stackSize = size(&stack); - printf("栈的长度 size = %d\r\n", stackSize); + int size = stack->size; + printf("栈的长度 size = %d\n", size); /* 判断是否为空 */ - bool isEmpty = empty(&stack); - printf("栈是否为空 = %s\r\n", isEmpty ? "yes" : "no"); + bool empty = isEmpty(stack); + printf("栈是否为空 = %s\n", empty ? "true" : "false"); + + // 释放内存 + free(stack->data); + free(stack); - /* 析构函数 */ - delArrayStack(&stack); return 0; } \ No newline at end of file diff --git a/codes/c/chapter_stack_and_queue/linkedlist_stack.c b/codes/c/chapter_stack_and_queue/linkedlist_stack.c index a63ea191..7463ea73 100644 --- a/codes/c/chapter_stack_and_queue/linkedlist_stack.c +++ b/codes/c/chapter_stack_and_queue/linkedlist_stack.c @@ -1,110 +1,115 @@ /** * File: linkedlist_stack.c - * Created Time: 2022-01-12 + * Created Time: 2023-01-12 * Author: Zero (glj0@outlook.com) */ #include "../include/include.h" /* 基于链表实现的栈 */ -struct LinkedListStack { - ListNode* stackTop; // 将头结点作为栈顶 +struct linkedListStack { + ListNode *top; // 将头结点作为栈顶 int size; // 栈的长度 }; -typedef struct LinkedListStack LinkedListStack; +typedef struct linkedListStack linkedListStack; /* 构造函数 */ -void newLinkedListStack(LinkedListStack* stk) { - stk->stackTop = NULL; - stk->size = 0; +linkedListStack *newLinkedListStack() { + linkedListStack *s = malloc(sizeof(linkedListStack)); + s->top = NULL; + s->size = 0; + return s; } /* 析构函数 */ -void delLinkedListStack(LinkedListStack* stk) { - while(stk->stackTop) { - ListNode *n = stk->stackTop->next; - free(stk->stackTop); - stk->stackTop = n; +void delLinkedListStack(linkedListStack *s) { + while (s->top) { + ListNode *n = s->top->next; + free(s->top); + s->top = n; } - stk->size = 0; + free(s); } /* 获取栈的长度 */ -int size(LinkedListStack* stk) { - assert(stk); - return stk->size; +int size(linkedListStack *s) { + assert(s); + return s->size; } /* 判断栈是否为空 */ -bool empty(LinkedListStack* stk) { - assert(stk); - return size(stk) == 0; +bool isEmpty(linkedListStack *s) { + assert(s); + return size(s) == 0; } /* 访问栈顶元素 */ -int top(LinkedListStack* stk) { - assert(stk); - assert(size(stk) != 0); - return stk->stackTop->val; +int peek(linkedListStack *s) { + assert(s); + assert(size(s) != 0); + return s->top->val; } /* 入栈 */ -void push(LinkedListStack* stk, int num) { - assert(stk); - ListNode *node = (ListNode *)malloc(sizeof(ListNode)); - node->next = stk->stackTop; // 更新新加结点指针域 - node->val = num; // 更新新加结点数据域 - stk->stackTop = node; // 更新栈顶 - stk->size++; // 更新栈大小 +void push(linkedListStack *s, int num) { + assert(s); + ListNode *node = (ListNode *) malloc(sizeof(ListNode)); + node->next = s->top; // 更新新加结点指针域 + node->val = num; // 更新新加结点数据域 + s->top = node; // 更新栈顶 + s->size++; // 更新栈大小 } /* 出栈 */ -void pop(LinkedListStack* stk) { - assert(stk); - int num = top(stk); - ListNode *tmp = stk->stackTop; - stk->stackTop = stk->stackTop->next; +int pop(linkedListStack *s) { + if (s->size == 0) { + printf("stack is empty.\n"); + return NIL; + } + assert(s); + int val = peek(s); + ListNode *tmp = s->top; + s->top = s->top->next; // 释放内存 free(tmp); - stk->size--; + s->size--; + return val; } /* Driver Code */ int main() { /* 初始化栈 */ - LinkedListStack stack; - /* 构造函数 */ - newLinkedListStack(&stack); + // 构造函数 + linkedListStack *stack = newLinkedListStack(); /* 元素入栈 */ - push(&stack, 1); - push(&stack, 3); - push(&stack, 2); - push(&stack, 5); - push(&stack, 4); + push(stack, 1); + push(stack, 3); + push(stack, 2); + push(stack, 5); + push(stack, 4); printf("栈 stack = "); - printLinkedList(stack.stackTop); + printLinkedList(stack->top); /* 访问栈顶元素 */ - int stackTop = top(&stack); - printf("栈顶元素 top = %d\r\n", stackTop); + int val = peek(stack); + printf("栈顶元素 top = %d\r\n", val); /* 元素出栈 */ - pop(&stack); - printf("出栈元素 pop = %d, 出栈后 stack = ", stackTop); - printLinkedList(stack.stackTop); + val = pop(stack); + printf("出栈元素 pop = %d, 出栈后 stack = ", val); + printLinkedList(stack->top); /* 获取栈的长度 */ - int stackSize = size(&stack); - printf("栈的长度 size = %d\r\n", stackSize); + printf("栈的长度 size = %d\n", size(stack)); /* 判断是否为空 */ - bool isEmpty = empty(&stack); - printf("栈是否为空 = %s\r\n", isEmpty ? "yes" : "no"); + bool empty = isEmpty(stack); + printf("栈是否为空 = %s\n", empty ? "true" : "false"); /* 析构函数 */ - delLinkedListStack(&stack); + delLinkedListStack(stack); return 0; } diff --git a/codes/c/include/CMakeLists.txt b/codes/c/include/CMakeLists.txt index 4189ae33..58d337bb 100644 --- a/codes/c/include/CMakeLists.txt +++ b/codes/c/include/CMakeLists.txt @@ -1,4 +1,5 @@ add_executable(include include_test.c + uthash.h include.h print_util.h list_node.h tree_node.h) \ No newline at end of file diff --git a/codes/c/include/include.h b/codes/c/include/include.h index e3919a9f..ad17a536 100644 --- a/codes/c/include/include.h +++ b/codes/c/include/include.h @@ -14,6 +14,8 @@ #include #include +#include "uthash.h" + #include "list_node.h" #include "tree_node.h" #include "print_util.h" diff --git a/codes/c/include/uthash.h b/codes/c/include/uthash.h new file mode 100644 index 00000000..68693bf3 --- /dev/null +++ b/codes/c/include/uthash.h @@ -0,0 +1,1140 @@ +/* +Copyright (c) 2003-2022, Troy D. Hanson https://troydhanson.github.io/uthash/ +All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS +IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED +TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A +PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER +OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, +EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, +PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +*/ + +#ifndef UTHASH_H +#define UTHASH_H + +#define UTHASH_VERSION 2.3.0 + +#include /* memcmp, memset, strlen */ +#include /* ptrdiff_t */ +#include /* exit */ + +#if defined(HASH_DEFINE_OWN_STDINT) && HASH_DEFINE_OWN_STDINT +/* This codepath is provided for backward compatibility, but I plan to remove it. */ +#warning "HASH_DEFINE_OWN_STDINT is deprecated; please use HASH_NO_STDINT instead" +typedef unsigned int uint32_t; +typedef unsigned char uint8_t; +#elif defined(HASH_NO_STDINT) && HASH_NO_STDINT +#else +#include /* uint8_t, uint32_t */ +#endif + +/* These macros use decltype or the earlier __typeof GNU extension. + As decltype is only available in newer compilers (VS2010 or gcc 4.3+ + when compiling c++ source) this code uses whatever method is needed + or, for VS2008 where neither is available, uses casting workarounds. */ +#if !defined(DECLTYPE) && !defined(NO_DECLTYPE) +#if defined(_MSC_VER) /* MS compiler */ +#if _MSC_VER >= 1600 && defined(__cplusplus) /* VS2010 or newer in C++ mode */ +#define DECLTYPE(x) (decltype(x)) +#else /* VS2008 or older (or VS2010 in C mode) */ +#define NO_DECLTYPE +#endif +#elif defined(__MCST__) /* Elbrus C Compiler */ +#define DECLTYPE(x) (__typeof(x)) +#elif defined(__BORLANDC__) || defined(__ICCARM__) || defined(__LCC__) || defined(__WATCOMC__) +#define NO_DECLTYPE +#else /* GNU, Sun and other compilers */ +#define DECLTYPE(x) (__typeof(x)) +#endif +#endif + +#ifdef NO_DECLTYPE +#define DECLTYPE(x) +#define DECLTYPE_ASSIGN(dst,src) \ +do { \ + char **_da_dst = (char**)(&(dst)); \ + *_da_dst = (char*)(src); \ +} while (0) +#else +#define DECLTYPE_ASSIGN(dst,src) \ +do { \ + (dst) = DECLTYPE(dst)(src); \ +} while (0) +#endif + +#ifndef uthash_malloc +#define uthash_malloc(sz) malloc(sz) /* malloc fcn */ +#endif +#ifndef uthash_free +#define uthash_free(ptr,sz) free(ptr) /* free fcn */ +#endif +#ifndef uthash_bzero +#define uthash_bzero(a,n) memset(a,'\0',n) +#endif +#ifndef uthash_strlen +#define uthash_strlen(s) strlen(s) +#endif + +#ifndef HASH_FUNCTION +#define HASH_FUNCTION(keyptr,keylen,hashv) HASH_JEN(keyptr, keylen, hashv) +#endif + +#ifndef HASH_KEYCMP +#define HASH_KEYCMP(a,b,n) memcmp(a,b,n) +#endif + +#ifndef uthash_noexpand_fyi +#define uthash_noexpand_fyi(tbl) /* can be defined to log noexpand */ +#endif +#ifndef uthash_expand_fyi +#define uthash_expand_fyi(tbl) /* can be defined to log expands */ +#endif + +#ifndef HASH_NONFATAL_OOM +#define HASH_NONFATAL_OOM 0 +#endif + +#if HASH_NONFATAL_OOM +/* malloc failures can be recovered from */ + +#ifndef uthash_nonfatal_oom +#define uthash_nonfatal_oom(obj) do {} while (0) /* non-fatal OOM error */ +#endif + +#define HASH_RECORD_OOM(oomed) do { (oomed) = 1; } while (0) +#define IF_HASH_NONFATAL_OOM(x) x + +#else +/* malloc failures result in lost memory, hash tables are unusable */ + +#ifndef uthash_fatal +#define uthash_fatal(msg) exit(-1) /* fatal OOM error */ +#endif + +#define HASH_RECORD_OOM(oomed) uthash_fatal("out of memory") +#define IF_HASH_NONFATAL_OOM(x) + +#endif + +/* initial number of buckets */ +#define HASH_INITIAL_NUM_BUCKETS 32U /* initial number of buckets */ +#define HASH_INITIAL_NUM_BUCKETS_LOG2 5U /* lg2 of initial number of buckets */ +#define HASH_BKT_CAPACITY_THRESH 10U /* expand when bucket count reaches */ + +/* calculate the element whose hash handle address is hhp */ +#define ELMT_FROM_HH(tbl,hhp) ((void*)(((char*)(hhp)) - ((tbl)->hho))) +/* calculate the hash handle from element address elp */ +#define HH_FROM_ELMT(tbl,elp) ((UT_hash_handle*)(void*)(((char*)(elp)) + ((tbl)->hho))) + +#define HASH_ROLLBACK_BKT(hh, head, itemptrhh) \ +do { \ + struct UT_hash_handle *_hd_hh_item = (itemptrhh); \ + unsigned _hd_bkt; \ + HASH_TO_BKT(_hd_hh_item->hashv, (head)->hh.tbl->num_buckets, _hd_bkt); \ + (head)->hh.tbl->buckets[_hd_bkt].count++; \ + _hd_hh_item->hh_next = NULL; \ + _hd_hh_item->hh_prev = NULL; \ +} while (0) + +#define HASH_VALUE(keyptr,keylen,hashv) \ +do { \ + HASH_FUNCTION(keyptr, keylen, hashv); \ +} while (0) + +#define HASH_FIND_BYHASHVALUE(hh,head,keyptr,keylen,hashval,out) \ +do { \ + (out) = NULL; \ + if (head) { \ + unsigned _hf_bkt; \ + HASH_TO_BKT(hashval, (head)->hh.tbl->num_buckets, _hf_bkt); \ + if (HASH_BLOOM_TEST((head)->hh.tbl, hashval) != 0) { \ + HASH_FIND_IN_BKT((head)->hh.tbl, hh, (head)->hh.tbl->buckets[ _hf_bkt ], keyptr, keylen, hashval, out); \ + } \ + } \ +} while (0) + +#define HASH_FIND(hh,head,keyptr,keylen,out) \ +do { \ + (out) = NULL; \ + if (head) { \ + unsigned _hf_hashv; \ + HASH_VALUE(keyptr, keylen, _hf_hashv); \ + HASH_FIND_BYHASHVALUE(hh, head, keyptr, keylen, _hf_hashv, out); \ + } \ +} while (0) + +#ifdef HASH_BLOOM +#define HASH_BLOOM_BITLEN (1UL << HASH_BLOOM) +#define HASH_BLOOM_BYTELEN (HASH_BLOOM_BITLEN/8UL) + (((HASH_BLOOM_BITLEN%8UL)!=0UL) ? 1UL : 0UL) +#define HASH_BLOOM_MAKE(tbl,oomed) \ +do { \ + (tbl)->bloom_nbits = HASH_BLOOM; \ + (tbl)->bloom_bv = (uint8_t*)uthash_malloc(HASH_BLOOM_BYTELEN); \ + if (!(tbl)->bloom_bv) { \ + HASH_RECORD_OOM(oomed); \ + } else { \ + uthash_bzero((tbl)->bloom_bv, HASH_BLOOM_BYTELEN); \ + (tbl)->bloom_sig = HASH_BLOOM_SIGNATURE; \ + } \ +} while (0) + +#define HASH_BLOOM_FREE(tbl) \ +do { \ + uthash_free((tbl)->bloom_bv, HASH_BLOOM_BYTELEN); \ +} while (0) + +#define HASH_BLOOM_BITSET(bv,idx) (bv[(idx)/8U] |= (1U << ((idx)%8U))) +#define HASH_BLOOM_BITTEST(bv,idx) (bv[(idx)/8U] & (1U << ((idx)%8U))) + +#define HASH_BLOOM_ADD(tbl,hashv) \ + HASH_BLOOM_BITSET((tbl)->bloom_bv, ((hashv) & (uint32_t)((1UL << (tbl)->bloom_nbits) - 1U))) + +#define HASH_BLOOM_TEST(tbl,hashv) \ + HASH_BLOOM_BITTEST((tbl)->bloom_bv, ((hashv) & (uint32_t)((1UL << (tbl)->bloom_nbits) - 1U))) + +#else +#define HASH_BLOOM_MAKE(tbl,oomed) +#define HASH_BLOOM_FREE(tbl) +#define HASH_BLOOM_ADD(tbl,hashv) +#define HASH_BLOOM_TEST(tbl,hashv) (1) +#define HASH_BLOOM_BYTELEN 0U +#endif + +#define HASH_MAKE_TABLE(hh,head,oomed) \ +do { \ + (head)->hh.tbl = (UT_hash_table*)uthash_malloc(sizeof(UT_hash_table)); \ + if (!(head)->hh.tbl) { \ + HASH_RECORD_OOM(oomed); \ + } else { \ + uthash_bzero((head)->hh.tbl, sizeof(UT_hash_table)); \ + (head)->hh.tbl->tail = &((head)->hh); \ + (head)->hh.tbl->num_buckets = HASH_INITIAL_NUM_BUCKETS; \ + (head)->hh.tbl->log2_num_buckets = HASH_INITIAL_NUM_BUCKETS_LOG2; \ + (head)->hh.tbl->hho = (char*)(&(head)->hh) - (char*)(head); \ + (head)->hh.tbl->buckets = (UT_hash_bucket*)uthash_malloc( \ + HASH_INITIAL_NUM_BUCKETS * sizeof(struct UT_hash_bucket)); \ + (head)->hh.tbl->signature = HASH_SIGNATURE; \ + if (!(head)->hh.tbl->buckets) { \ + HASH_RECORD_OOM(oomed); \ + uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ + } else { \ + uthash_bzero((head)->hh.tbl->buckets, \ + HASH_INITIAL_NUM_BUCKETS * sizeof(struct UT_hash_bucket)); \ + HASH_BLOOM_MAKE((head)->hh.tbl, oomed); \ + IF_HASH_NONFATAL_OOM( \ + if (oomed) { \ + uthash_free((head)->hh.tbl->buckets, \ + HASH_INITIAL_NUM_BUCKETS*sizeof(struct UT_hash_bucket)); \ + uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ + } \ + ) \ + } \ + } \ +} while (0) + +#define HASH_REPLACE_BYHASHVALUE_INORDER(hh,head,fieldname,keylen_in,hashval,add,replaced,cmpfcn) \ +do { \ + (replaced) = NULL; \ + HASH_FIND_BYHASHVALUE(hh, head, &((add)->fieldname), keylen_in, hashval, replaced); \ + if (replaced) { \ + HASH_DELETE(hh, head, replaced); \ + } \ + HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh, head, &((add)->fieldname), keylen_in, hashval, add, cmpfcn); \ +} while (0) + +#define HASH_REPLACE_BYHASHVALUE(hh,head,fieldname,keylen_in,hashval,add,replaced) \ +do { \ + (replaced) = NULL; \ + HASH_FIND_BYHASHVALUE(hh, head, &((add)->fieldname), keylen_in, hashval, replaced); \ + if (replaced) { \ + HASH_DELETE(hh, head, replaced); \ + } \ + HASH_ADD_KEYPTR_BYHASHVALUE(hh, head, &((add)->fieldname), keylen_in, hashval, add); \ +} while (0) + +#define HASH_REPLACE(hh,head,fieldname,keylen_in,add,replaced) \ +do { \ + unsigned _hr_hashv; \ + HASH_VALUE(&((add)->fieldname), keylen_in, _hr_hashv); \ + HASH_REPLACE_BYHASHVALUE(hh, head, fieldname, keylen_in, _hr_hashv, add, replaced); \ +} while (0) + +#define HASH_REPLACE_INORDER(hh,head,fieldname,keylen_in,add,replaced,cmpfcn) \ +do { \ + unsigned _hr_hashv; \ + HASH_VALUE(&((add)->fieldname), keylen_in, _hr_hashv); \ + HASH_REPLACE_BYHASHVALUE_INORDER(hh, head, fieldname, keylen_in, _hr_hashv, add, replaced, cmpfcn); \ +} while (0) + +#define HASH_APPEND_LIST(hh, head, add) \ +do { \ + (add)->hh.next = NULL; \ + (add)->hh.prev = ELMT_FROM_HH((head)->hh.tbl, (head)->hh.tbl->tail); \ + (head)->hh.tbl->tail->next = (add); \ + (head)->hh.tbl->tail = &((add)->hh); \ +} while (0) + +#define HASH_AKBI_INNER_LOOP(hh,head,add,cmpfcn) \ +do { \ + do { \ + if (cmpfcn(DECLTYPE(head)(_hs_iter), add) > 0) { \ + break; \ + } \ + } while ((_hs_iter = HH_FROM_ELMT((head)->hh.tbl, _hs_iter)->next)); \ +} while (0) + +#ifdef NO_DECLTYPE +#undef HASH_AKBI_INNER_LOOP +#define HASH_AKBI_INNER_LOOP(hh,head,add,cmpfcn) \ +do { \ + char *_hs_saved_head = (char*)(head); \ + do { \ + DECLTYPE_ASSIGN(head, _hs_iter); \ + if (cmpfcn(head, add) > 0) { \ + DECLTYPE_ASSIGN(head, _hs_saved_head); \ + break; \ + } \ + DECLTYPE_ASSIGN(head, _hs_saved_head); \ + } while ((_hs_iter = HH_FROM_ELMT((head)->hh.tbl, _hs_iter)->next)); \ +} while (0) +#endif + +#if HASH_NONFATAL_OOM + +#define HASH_ADD_TO_TABLE(hh,head,keyptr,keylen_in,hashval,add,oomed) \ +do { \ + if (!(oomed)) { \ + unsigned _ha_bkt; \ + (head)->hh.tbl->num_items++; \ + HASH_TO_BKT(hashval, (head)->hh.tbl->num_buckets, _ha_bkt); \ + HASH_ADD_TO_BKT((head)->hh.tbl->buckets[_ha_bkt], hh, &(add)->hh, oomed); \ + if (oomed) { \ + HASH_ROLLBACK_BKT(hh, head, &(add)->hh); \ + HASH_DELETE_HH(hh, head, &(add)->hh); \ + (add)->hh.tbl = NULL; \ + uthash_nonfatal_oom(add); \ + } else { \ + HASH_BLOOM_ADD((head)->hh.tbl, hashval); \ + HASH_EMIT_KEY(hh, head, keyptr, keylen_in); \ + } \ + } else { \ + (add)->hh.tbl = NULL; \ + uthash_nonfatal_oom(add); \ + } \ +} while (0) + +#else + +#define HASH_ADD_TO_TABLE(hh,head,keyptr,keylen_in,hashval,add,oomed) \ +do { \ + unsigned _ha_bkt; \ + (head)->hh.tbl->num_items++; \ + HASH_TO_BKT(hashval, (head)->hh.tbl->num_buckets, _ha_bkt); \ + HASH_ADD_TO_BKT((head)->hh.tbl->buckets[_ha_bkt], hh, &(add)->hh, oomed); \ + HASH_BLOOM_ADD((head)->hh.tbl, hashval); \ + HASH_EMIT_KEY(hh, head, keyptr, keylen_in); \ +} while (0) + +#endif + + +#define HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh,head,keyptr,keylen_in,hashval,add,cmpfcn) \ +do { \ + IF_HASH_NONFATAL_OOM( int _ha_oomed = 0; ) \ + (add)->hh.hashv = (hashval); \ + (add)->hh.key = (char*) (keyptr); \ + (add)->hh.keylen = (unsigned) (keylen_in); \ + if (!(head)) { \ + (add)->hh.next = NULL; \ + (add)->hh.prev = NULL; \ + HASH_MAKE_TABLE(hh, add, _ha_oomed); \ + IF_HASH_NONFATAL_OOM( if (!_ha_oomed) { ) \ + (head) = (add); \ + IF_HASH_NONFATAL_OOM( } ) \ + } else { \ + void *_hs_iter = (head); \ + (add)->hh.tbl = (head)->hh.tbl; \ + HASH_AKBI_INNER_LOOP(hh, head, add, cmpfcn); \ + if (_hs_iter) { \ + (add)->hh.next = _hs_iter; \ + if (((add)->hh.prev = HH_FROM_ELMT((head)->hh.tbl, _hs_iter)->prev)) { \ + HH_FROM_ELMT((head)->hh.tbl, (add)->hh.prev)->next = (add); \ + } else { \ + (head) = (add); \ + } \ + HH_FROM_ELMT((head)->hh.tbl, _hs_iter)->prev = (add); \ + } else { \ + HASH_APPEND_LIST(hh, head, add); \ + } \ + } \ + HASH_ADD_TO_TABLE(hh, head, keyptr, keylen_in, hashval, add, _ha_oomed); \ + HASH_FSCK(hh, head, "HASH_ADD_KEYPTR_BYHASHVALUE_INORDER"); \ +} while (0) + +#define HASH_ADD_KEYPTR_INORDER(hh,head,keyptr,keylen_in,add,cmpfcn) \ +do { \ + unsigned _hs_hashv; \ + HASH_VALUE(keyptr, keylen_in, _hs_hashv); \ + HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh, head, keyptr, keylen_in, _hs_hashv, add, cmpfcn); \ +} while (0) + +#define HASH_ADD_BYHASHVALUE_INORDER(hh,head,fieldname,keylen_in,hashval,add,cmpfcn) \ + HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh, head, &((add)->fieldname), keylen_in, hashval, add, cmpfcn) + +#define HASH_ADD_INORDER(hh,head,fieldname,keylen_in,add,cmpfcn) \ + HASH_ADD_KEYPTR_INORDER(hh, head, &((add)->fieldname), keylen_in, add, cmpfcn) + +#define HASH_ADD_KEYPTR_BYHASHVALUE(hh,head,keyptr,keylen_in,hashval,add) \ +do { \ + IF_HASH_NONFATAL_OOM( int _ha_oomed = 0; ) \ + (add)->hh.hashv = (hashval); \ + (add)->hh.key = (const void*) (keyptr); \ + (add)->hh.keylen = (unsigned) (keylen_in); \ + if (!(head)) { \ + (add)->hh.next = NULL; \ + (add)->hh.prev = NULL; \ + HASH_MAKE_TABLE(hh, add, _ha_oomed); \ + IF_HASH_NONFATAL_OOM( if (!_ha_oomed) { ) \ + (head) = (add); \ + IF_HASH_NONFATAL_OOM( } ) \ + } else { \ + (add)->hh.tbl = (head)->hh.tbl; \ + HASH_APPEND_LIST(hh, head, add); \ + } \ + HASH_ADD_TO_TABLE(hh, head, keyptr, keylen_in, hashval, add, _ha_oomed); \ + HASH_FSCK(hh, head, "HASH_ADD_KEYPTR_BYHASHVALUE"); \ +} while (0) + +#define HASH_ADD_KEYPTR(hh,head,keyptr,keylen_in,add) \ +do { \ + unsigned _ha_hashv; \ + HASH_VALUE(keyptr, keylen_in, _ha_hashv); \ + HASH_ADD_KEYPTR_BYHASHVALUE(hh, head, keyptr, keylen_in, _ha_hashv, add); \ +} while (0) + +#define HASH_ADD_BYHASHVALUE(hh,head,fieldname,keylen_in,hashval,add) \ + HASH_ADD_KEYPTR_BYHASHVALUE(hh, head, &((add)->fieldname), keylen_in, hashval, add) + +#define HASH_ADD(hh,head,fieldname,keylen_in,add) \ + HASH_ADD_KEYPTR(hh, head, &((add)->fieldname), keylen_in, add) + +#define HASH_TO_BKT(hashv,num_bkts,bkt) \ +do { \ + bkt = ((hashv) & ((num_bkts) - 1U)); \ +} while (0) + +/* delete "delptr" from the hash table. + * "the usual" patch-up process for the app-order doubly-linked-list. + * The use of _hd_hh_del below deserves special explanation. + * These used to be expressed using (delptr) but that led to a bug + * if someone used the same symbol for the head and deletee, like + * HASH_DELETE(hh,users,users); + * We want that to work, but by changing the head (users) below + * we were forfeiting our ability to further refer to the deletee (users) + * in the patch-up process. Solution: use scratch space to + * copy the deletee pointer, then the latter references are via that + * scratch pointer rather than through the repointed (users) symbol. + */ +#define HASH_DELETE(hh,head,delptr) \ + HASH_DELETE_HH(hh, head, &(delptr)->hh) + +#define HASH_DELETE_HH(hh,head,delptrhh) \ +do { \ + const struct UT_hash_handle *_hd_hh_del = (delptrhh); \ + if ((_hd_hh_del->prev == NULL) && (_hd_hh_del->next == NULL)) { \ + HASH_BLOOM_FREE((head)->hh.tbl); \ + uthash_free((head)->hh.tbl->buckets, \ + (head)->hh.tbl->num_buckets * sizeof(struct UT_hash_bucket)); \ + uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ + (head) = NULL; \ + } else { \ + unsigned _hd_bkt; \ + if (_hd_hh_del == (head)->hh.tbl->tail) { \ + (head)->hh.tbl->tail = HH_FROM_ELMT((head)->hh.tbl, _hd_hh_del->prev); \ + } \ + if (_hd_hh_del->prev != NULL) { \ + HH_FROM_ELMT((head)->hh.tbl, _hd_hh_del->prev)->next = _hd_hh_del->next; \ + } else { \ + DECLTYPE_ASSIGN(head, _hd_hh_del->next); \ + } \ + if (_hd_hh_del->next != NULL) { \ + HH_FROM_ELMT((head)->hh.tbl, _hd_hh_del->next)->prev = _hd_hh_del->prev; \ + } \ + HASH_TO_BKT(_hd_hh_del->hashv, (head)->hh.tbl->num_buckets, _hd_bkt); \ + HASH_DEL_IN_BKT((head)->hh.tbl->buckets[_hd_bkt], _hd_hh_del); \ + (head)->hh.tbl->num_items--; \ + } \ + HASH_FSCK(hh, head, "HASH_DELETE_HH"); \ +} while (0) + +/* convenience forms of HASH_FIND/HASH_ADD/HASH_DEL */ +#define HASH_FIND_STR(head,findstr,out) \ +do { \ + unsigned _uthash_hfstr_keylen = (unsigned)uthash_strlen(findstr); \ + HASH_FIND(hh, head, findstr, _uthash_hfstr_keylen, out); \ +} while (0) +#define HASH_ADD_STR(head,strfield,add) \ +do { \ + unsigned _uthash_hastr_keylen = (unsigned)uthash_strlen((add)->strfield); \ + HASH_ADD(hh, head, strfield[0], _uthash_hastr_keylen, add); \ +} while (0) +#define HASH_REPLACE_STR(head,strfield,add,replaced) \ +do { \ + unsigned _uthash_hrstr_keylen = (unsigned)uthash_strlen((add)->strfield); \ + HASH_REPLACE(hh, head, strfield[0], _uthash_hrstr_keylen, add, replaced); \ +} while (0) +#define HASH_FIND_INT(head,findint,out) \ + HASH_FIND(hh,head,findint,sizeof(int),out) +#define HASH_ADD_INT(head,intfield,add) \ + HASH_ADD(hh,head,intfield,sizeof(int),add) +#define HASH_REPLACE_INT(head,intfield,add,replaced) \ + HASH_REPLACE(hh,head,intfield,sizeof(int),add,replaced) +#define HASH_FIND_PTR(head,findptr,out) \ + HASH_FIND(hh,head,findptr,sizeof(void *),out) +#define HASH_ADD_PTR(head,ptrfield,add) \ + HASH_ADD(hh,head,ptrfield,sizeof(void *),add) +#define HASH_REPLACE_PTR(head,ptrfield,add,replaced) \ + HASH_REPLACE(hh,head,ptrfield,sizeof(void *),add,replaced) +#define HASH_DEL(head,delptr) \ + HASH_DELETE(hh,head,delptr) + +/* HASH_FSCK checks hash integrity on every add/delete when HASH_DEBUG is defined. + * This is for uthash developer only; it compiles away if HASH_DEBUG isn't defined. + */ +#ifdef HASH_DEBUG +#include /* fprintf, stderr */ +#define HASH_OOPS(...) do { fprintf(stderr, __VA_ARGS__); exit(-1); } while (0) +#define HASH_FSCK(hh,head,where) \ +do { \ + struct UT_hash_handle *_thh; \ + if (head) { \ + unsigned _bkt_i; \ + unsigned _count = 0; \ + char *_prev; \ + for (_bkt_i = 0; _bkt_i < (head)->hh.tbl->num_buckets; ++_bkt_i) { \ + unsigned _bkt_count = 0; \ + _thh = (head)->hh.tbl->buckets[_bkt_i].hh_head; \ + _prev = NULL; \ + while (_thh) { \ + if (_prev != (char*)(_thh->hh_prev)) { \ + HASH_OOPS("%s: invalid hh_prev %p, actual %p\n", \ + (where), (void*)_thh->hh_prev, (void*)_prev); \ + } \ + _bkt_count++; \ + _prev = (char*)(_thh); \ + _thh = _thh->hh_next; \ + } \ + _count += _bkt_count; \ + if ((head)->hh.tbl->buckets[_bkt_i].count != _bkt_count) { \ + HASH_OOPS("%s: invalid bucket count %u, actual %u\n", \ + (where), (head)->hh.tbl->buckets[_bkt_i].count, _bkt_count); \ + } \ + } \ + if (_count != (head)->hh.tbl->num_items) { \ + HASH_OOPS("%s: invalid hh item count %u, actual %u\n", \ + (where), (head)->hh.tbl->num_items, _count); \ + } \ + _count = 0; \ + _prev = NULL; \ + _thh = &(head)->hh; \ + while (_thh) { \ + _count++; \ + if (_prev != (char*)_thh->prev) { \ + HASH_OOPS("%s: invalid prev %p, actual %p\n", \ + (where), (void*)_thh->prev, (void*)_prev); \ + } \ + _prev = (char*)ELMT_FROM_HH((head)->hh.tbl, _thh); \ + _thh = (_thh->next ? HH_FROM_ELMT((head)->hh.tbl, _thh->next) : NULL); \ + } \ + if (_count != (head)->hh.tbl->num_items) { \ + HASH_OOPS("%s: invalid app item count %u, actual %u\n", \ + (where), (head)->hh.tbl->num_items, _count); \ + } \ + } \ +} while (0) +#else +#define HASH_FSCK(hh,head,where) +#endif + +/* When compiled with -DHASH_EMIT_KEYS, length-prefixed keys are emitted to + * the descriptor to which this macro is defined for tuning the hash function. + * The app can #include to get the prototype for write(2). */ +#ifdef HASH_EMIT_KEYS +#define HASH_EMIT_KEY(hh,head,keyptr,fieldlen) \ +do { \ + unsigned _klen = fieldlen; \ + write(HASH_EMIT_KEYS, &_klen, sizeof(_klen)); \ + write(HASH_EMIT_KEYS, keyptr, (unsigned long)fieldlen); \ +} while (0) +#else +#define HASH_EMIT_KEY(hh,head,keyptr,fieldlen) +#endif + +/* The Bernstein hash function, used in Perl prior to v5.6. Note (x<<5+x)=x*33. */ +#define HASH_BER(key,keylen,hashv) \ +do { \ + unsigned _hb_keylen = (unsigned)keylen; \ + const unsigned char *_hb_key = (const unsigned char*)(key); \ + (hashv) = 0; \ + while (_hb_keylen-- != 0U) { \ + (hashv) = (((hashv) << 5) + (hashv)) + *_hb_key++; \ + } \ +} while (0) + + +/* SAX/FNV/OAT/JEN hash functions are macro variants of those listed at + * http://eternallyconfuzzled.com/tuts/algorithms/jsw_tut_hashing.aspx + * (archive link: https://archive.is/Ivcan ) + */ +#define HASH_SAX(key,keylen,hashv) \ +do { \ + unsigned _sx_i; \ + const unsigned char *_hs_key = (const unsigned char*)(key); \ + hashv = 0; \ + for (_sx_i=0; _sx_i < keylen; _sx_i++) { \ + hashv ^= (hashv << 5) + (hashv >> 2) + _hs_key[_sx_i]; \ + } \ +} while (0) +/* FNV-1a variation */ +#define HASH_FNV(key,keylen,hashv) \ +do { \ + unsigned _fn_i; \ + const unsigned char *_hf_key = (const unsigned char*)(key); \ + (hashv) = 2166136261U; \ + for (_fn_i=0; _fn_i < keylen; _fn_i++) { \ + hashv = hashv ^ _hf_key[_fn_i]; \ + hashv = hashv * 16777619U; \ + } \ +} while (0) + +#define HASH_OAT(key,keylen,hashv) \ +do { \ + unsigned _ho_i; \ + const unsigned char *_ho_key=(const unsigned char*)(key); \ + hashv = 0; \ + for(_ho_i=0; _ho_i < keylen; _ho_i++) { \ + hashv += _ho_key[_ho_i]; \ + hashv += (hashv << 10); \ + hashv ^= (hashv >> 6); \ + } \ + hashv += (hashv << 3); \ + hashv ^= (hashv >> 11); \ + hashv += (hashv << 15); \ +} while (0) + +#define HASH_JEN_MIX(a,b,c) \ +do { \ + a -= b; a -= c; a ^= ( c >> 13 ); \ + b -= c; b -= a; b ^= ( a << 8 ); \ + c -= a; c -= b; c ^= ( b >> 13 ); \ + a -= b; a -= c; a ^= ( c >> 12 ); \ + b -= c; b -= a; b ^= ( a << 16 ); \ + c -= a; c -= b; c ^= ( b >> 5 ); \ + a -= b; a -= c; a ^= ( c >> 3 ); \ + b -= c; b -= a; b ^= ( a << 10 ); \ + c -= a; c -= b; c ^= ( b >> 15 ); \ +} while (0) + +#define HASH_JEN(key,keylen,hashv) \ +do { \ + unsigned _hj_i,_hj_j,_hj_k; \ + unsigned const char *_hj_key=(unsigned const char*)(key); \ + hashv = 0xfeedbeefu; \ + _hj_i = _hj_j = 0x9e3779b9u; \ + _hj_k = (unsigned)(keylen); \ + while (_hj_k >= 12U) { \ + _hj_i += (_hj_key[0] + ( (unsigned)_hj_key[1] << 8 ) \ + + ( (unsigned)_hj_key[2] << 16 ) \ + + ( (unsigned)_hj_key[3] << 24 ) ); \ + _hj_j += (_hj_key[4] + ( (unsigned)_hj_key[5] << 8 ) \ + + ( (unsigned)_hj_key[6] << 16 ) \ + + ( (unsigned)_hj_key[7] << 24 ) ); \ + hashv += (_hj_key[8] + ( (unsigned)_hj_key[9] << 8 ) \ + + ( (unsigned)_hj_key[10] << 16 ) \ + + ( (unsigned)_hj_key[11] << 24 ) ); \ + \ + HASH_JEN_MIX(_hj_i, _hj_j, hashv); \ + \ + _hj_key += 12; \ + _hj_k -= 12U; \ + } \ + hashv += (unsigned)(keylen); \ + switch ( _hj_k ) { \ + case 11: hashv += ( (unsigned)_hj_key[10] << 24 ); /* FALLTHROUGH */ \ + case 10: hashv += ( (unsigned)_hj_key[9] << 16 ); /* FALLTHROUGH */ \ + case 9: hashv += ( (unsigned)_hj_key[8] << 8 ); /* FALLTHROUGH */ \ + case 8: _hj_j += ( (unsigned)_hj_key[7] << 24 ); /* FALLTHROUGH */ \ + case 7: _hj_j += ( (unsigned)_hj_key[6] << 16 ); /* FALLTHROUGH */ \ + case 6: _hj_j += ( (unsigned)_hj_key[5] << 8 ); /* FALLTHROUGH */ \ + case 5: _hj_j += _hj_key[4]; /* FALLTHROUGH */ \ + case 4: _hj_i += ( (unsigned)_hj_key[3] << 24 ); /* FALLTHROUGH */ \ + case 3: _hj_i += ( (unsigned)_hj_key[2] << 16 ); /* FALLTHROUGH */ \ + case 2: _hj_i += ( (unsigned)_hj_key[1] << 8 ); /* FALLTHROUGH */ \ + case 1: _hj_i += _hj_key[0]; /* FALLTHROUGH */ \ + default: ; \ + } \ + HASH_JEN_MIX(_hj_i, _hj_j, hashv); \ +} while (0) + +/* The Paul Hsieh hash function */ +#undef get16bits +#if (defined(__GNUC__) && defined(__i386__)) || defined(__WATCOMC__) \ + || defined(_MSC_VER) || defined (__BORLANDC__) || defined (__TURBOC__) +#define get16bits(d) (*((const uint16_t *) (d))) +#endif + +#if !defined (get16bits) +#define get16bits(d) ((((uint32_t)(((const uint8_t *)(d))[1])) << 8) \ + +(uint32_t)(((const uint8_t *)(d))[0]) ) +#endif +#define HASH_SFH(key,keylen,hashv) \ +do { \ + unsigned const char *_sfh_key=(unsigned const char*)(key); \ + uint32_t _sfh_tmp, _sfh_len = (uint32_t)keylen; \ + \ + unsigned _sfh_rem = _sfh_len & 3U; \ + _sfh_len >>= 2; \ + hashv = 0xcafebabeu; \ + \ + /* Main loop */ \ + for (;_sfh_len > 0U; _sfh_len--) { \ + hashv += get16bits (_sfh_key); \ + _sfh_tmp = ((uint32_t)(get16bits (_sfh_key+2)) << 11) ^ hashv; \ + hashv = (hashv << 16) ^ _sfh_tmp; \ + _sfh_key += 2U*sizeof (uint16_t); \ + hashv += hashv >> 11; \ + } \ + \ + /* Handle end cases */ \ + switch (_sfh_rem) { \ + case 3: hashv += get16bits (_sfh_key); \ + hashv ^= hashv << 16; \ + hashv ^= (uint32_t)(_sfh_key[sizeof (uint16_t)]) << 18; \ + hashv += hashv >> 11; \ + break; \ + case 2: hashv += get16bits (_sfh_key); \ + hashv ^= hashv << 11; \ + hashv += hashv >> 17; \ + break; \ + case 1: hashv += *_sfh_key; \ + hashv ^= hashv << 10; \ + hashv += hashv >> 1; \ + break; \ + default: ; \ + } \ + \ + /* Force "avalanching" of final 127 bits */ \ + hashv ^= hashv << 3; \ + hashv += hashv >> 5; \ + hashv ^= hashv << 4; \ + hashv += hashv >> 17; \ + hashv ^= hashv << 25; \ + hashv += hashv >> 6; \ +} while (0) + +/* iterate over items in a known bucket to find desired item */ +#define HASH_FIND_IN_BKT(tbl,hh,head,keyptr,keylen_in,hashval,out) \ +do { \ + if ((head).hh_head != NULL) { \ + DECLTYPE_ASSIGN(out, ELMT_FROM_HH(tbl, (head).hh_head)); \ + } else { \ + (out) = NULL; \ + } \ + while ((out) != NULL) { \ + if ((out)->hh.hashv == (hashval) && (out)->hh.keylen == (keylen_in)) { \ + if (HASH_KEYCMP((out)->hh.key, keyptr, keylen_in) == 0) { \ + break; \ + } \ + } \ + if ((out)->hh.hh_next != NULL) { \ + DECLTYPE_ASSIGN(out, ELMT_FROM_HH(tbl, (out)->hh.hh_next)); \ + } else { \ + (out) = NULL; \ + } \ + } \ +} while (0) + +/* add an item to a bucket */ +#define HASH_ADD_TO_BKT(head,hh,addhh,oomed) \ +do { \ + UT_hash_bucket *_ha_head = &(head); \ + _ha_head->count++; \ + (addhh)->hh_next = _ha_head->hh_head; \ + (addhh)->hh_prev = NULL; \ + if (_ha_head->hh_head != NULL) { \ + _ha_head->hh_head->hh_prev = (addhh); \ + } \ + _ha_head->hh_head = (addhh); \ + if ((_ha_head->count >= ((_ha_head->expand_mult + 1U) * HASH_BKT_CAPACITY_THRESH)) \ + && !(addhh)->tbl->noexpand) { \ + HASH_EXPAND_BUCKETS(addhh,(addhh)->tbl, oomed); \ + IF_HASH_NONFATAL_OOM( \ + if (oomed) { \ + HASH_DEL_IN_BKT(head,addhh); \ + } \ + ) \ + } \ +} while (0) + +/* remove an item from a given bucket */ +#define HASH_DEL_IN_BKT(head,delhh) \ +do { \ + UT_hash_bucket *_hd_head = &(head); \ + _hd_head->count--; \ + if (_hd_head->hh_head == (delhh)) { \ + _hd_head->hh_head = (delhh)->hh_next; \ + } \ + if ((delhh)->hh_prev) { \ + (delhh)->hh_prev->hh_next = (delhh)->hh_next; \ + } \ + if ((delhh)->hh_next) { \ + (delhh)->hh_next->hh_prev = (delhh)->hh_prev; \ + } \ +} while (0) + +/* Bucket expansion has the effect of doubling the number of buckets + * and redistributing the items into the new buckets. Ideally the + * items will distribute more or less evenly into the new buckets + * (the extent to which this is true is a measure of the quality of + * the hash function as it applies to the key domain). + * + * With the items distributed into more buckets, the chain length + * (item count) in each bucket is reduced. Thus by expanding buckets + * the hash keeps a bound on the chain length. This bounded chain + * length is the essence of how a hash provides constant time lookup. + * + * The calculation of tbl->ideal_chain_maxlen below deserves some + * explanation. First, keep in mind that we're calculating the ideal + * maximum chain length based on the *new* (doubled) bucket count. + * In fractions this is just n/b (n=number of items,b=new num buckets). + * Since the ideal chain length is an integer, we want to calculate + * ceil(n/b). We don't depend on floating point arithmetic in this + * hash, so to calculate ceil(n/b) with integers we could write + * + * ceil(n/b) = (n/b) + ((n%b)?1:0) + * + * and in fact a previous version of this hash did just that. + * But now we have improved things a bit by recognizing that b is + * always a power of two. We keep its base 2 log handy (call it lb), + * so now we can write this with a bit shift and logical AND: + * + * ceil(n/b) = (n>>lb) + ( (n & (b-1)) ? 1:0) + * + */ +#define HASH_EXPAND_BUCKETS(hh,tbl,oomed) \ +do { \ + unsigned _he_bkt; \ + unsigned _he_bkt_i; \ + struct UT_hash_handle *_he_thh, *_he_hh_nxt; \ + UT_hash_bucket *_he_new_buckets, *_he_newbkt; \ + _he_new_buckets = (UT_hash_bucket*)uthash_malloc( \ + sizeof(struct UT_hash_bucket) * (tbl)->num_buckets * 2U); \ + if (!_he_new_buckets) { \ + HASH_RECORD_OOM(oomed); \ + } else { \ + uthash_bzero(_he_new_buckets, \ + sizeof(struct UT_hash_bucket) * (tbl)->num_buckets * 2U); \ + (tbl)->ideal_chain_maxlen = \ + ((tbl)->num_items >> ((tbl)->log2_num_buckets+1U)) + \ + ((((tbl)->num_items & (((tbl)->num_buckets*2U)-1U)) != 0U) ? 1U : 0U); \ + (tbl)->nonideal_items = 0; \ + for (_he_bkt_i = 0; _he_bkt_i < (tbl)->num_buckets; _he_bkt_i++) { \ + _he_thh = (tbl)->buckets[ _he_bkt_i ].hh_head; \ + while (_he_thh != NULL) { \ + _he_hh_nxt = _he_thh->hh_next; \ + HASH_TO_BKT(_he_thh->hashv, (tbl)->num_buckets * 2U, _he_bkt); \ + _he_newbkt = &(_he_new_buckets[_he_bkt]); \ + if (++(_he_newbkt->count) > (tbl)->ideal_chain_maxlen) { \ + (tbl)->nonideal_items++; \ + if (_he_newbkt->count > _he_newbkt->expand_mult * (tbl)->ideal_chain_maxlen) { \ + _he_newbkt->expand_mult++; \ + } \ + } \ + _he_thh->hh_prev = NULL; \ + _he_thh->hh_next = _he_newbkt->hh_head; \ + if (_he_newbkt->hh_head != NULL) { \ + _he_newbkt->hh_head->hh_prev = _he_thh; \ + } \ + _he_newbkt->hh_head = _he_thh; \ + _he_thh = _he_hh_nxt; \ + } \ + } \ + uthash_free((tbl)->buckets, (tbl)->num_buckets * sizeof(struct UT_hash_bucket)); \ + (tbl)->num_buckets *= 2U; \ + (tbl)->log2_num_buckets++; \ + (tbl)->buckets = _he_new_buckets; \ + (tbl)->ineff_expands = ((tbl)->nonideal_items > ((tbl)->num_items >> 1)) ? \ + ((tbl)->ineff_expands+1U) : 0U; \ + if ((tbl)->ineff_expands > 1U) { \ + (tbl)->noexpand = 1; \ + uthash_noexpand_fyi(tbl); \ + } \ + uthash_expand_fyi(tbl); \ + } \ +} while (0) + + +/* This is an adaptation of Simon Tatham's O(n log(n)) mergesort */ +/* Note that HASH_SORT assumes the hash handle name to be hh. + * HASH_SRT was added to allow the hash handle name to be passed in. */ +#define HASH_SORT(head,cmpfcn) HASH_SRT(hh,head,cmpfcn) +#define HASH_SRT(hh,head,cmpfcn) \ +do { \ + unsigned _hs_i; \ + unsigned _hs_looping,_hs_nmerges,_hs_insize,_hs_psize,_hs_qsize; \ + struct UT_hash_handle *_hs_p, *_hs_q, *_hs_e, *_hs_list, *_hs_tail; \ + if (head != NULL) { \ + _hs_insize = 1; \ + _hs_looping = 1; \ + _hs_list = &((head)->hh); \ + while (_hs_looping != 0U) { \ + _hs_p = _hs_list; \ + _hs_list = NULL; \ + _hs_tail = NULL; \ + _hs_nmerges = 0; \ + while (_hs_p != NULL) { \ + _hs_nmerges++; \ + _hs_q = _hs_p; \ + _hs_psize = 0; \ + for (_hs_i = 0; _hs_i < _hs_insize; ++_hs_i) { \ + _hs_psize++; \ + _hs_q = ((_hs_q->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_q->next) : NULL); \ + if (_hs_q == NULL) { \ + break; \ + } \ + } \ + _hs_qsize = _hs_insize; \ + while ((_hs_psize != 0U) || ((_hs_qsize != 0U) && (_hs_q != NULL))) { \ + if (_hs_psize == 0U) { \ + _hs_e = _hs_q; \ + _hs_q = ((_hs_q->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_q->next) : NULL); \ + _hs_qsize--; \ + } else if ((_hs_qsize == 0U) || (_hs_q == NULL)) { \ + _hs_e = _hs_p; \ + if (_hs_p != NULL) { \ + _hs_p = ((_hs_p->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_p->next) : NULL); \ + } \ + _hs_psize--; \ + } else if ((cmpfcn( \ + DECLTYPE(head)(ELMT_FROM_HH((head)->hh.tbl, _hs_p)), \ + DECLTYPE(head)(ELMT_FROM_HH((head)->hh.tbl, _hs_q)) \ + )) <= 0) { \ + _hs_e = _hs_p; \ + if (_hs_p != NULL) { \ + _hs_p = ((_hs_p->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_p->next) : NULL); \ + } \ + _hs_psize--; \ + } else { \ + _hs_e = _hs_q; \ + _hs_q = ((_hs_q->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_q->next) : NULL); \ + _hs_qsize--; \ + } \ + if ( _hs_tail != NULL ) { \ + _hs_tail->next = ((_hs_e != NULL) ? \ + ELMT_FROM_HH((head)->hh.tbl, _hs_e) : NULL); \ + } else { \ + _hs_list = _hs_e; \ + } \ + if (_hs_e != NULL) { \ + _hs_e->prev = ((_hs_tail != NULL) ? \ + ELMT_FROM_HH((head)->hh.tbl, _hs_tail) : NULL); \ + } \ + _hs_tail = _hs_e; \ + } \ + _hs_p = _hs_q; \ + } \ + if (_hs_tail != NULL) { \ + _hs_tail->next = NULL; \ + } \ + if (_hs_nmerges <= 1U) { \ + _hs_looping = 0; \ + (head)->hh.tbl->tail = _hs_tail; \ + DECLTYPE_ASSIGN(head, ELMT_FROM_HH((head)->hh.tbl, _hs_list)); \ + } \ + _hs_insize *= 2U; \ + } \ + HASH_FSCK(hh, head, "HASH_SRT"); \ + } \ +} while (0) + +/* This function selects items from one hash into another hash. + * The end result is that the selected items have dual presence + * in both hashes. There is no copy of the items made; rather + * they are added into the new hash through a secondary hash + * hash handle that must be present in the structure. */ +#define HASH_SELECT(hh_dst, dst, hh_src, src, cond) \ +do { \ + unsigned _src_bkt, _dst_bkt; \ + void *_last_elt = NULL, *_elt; \ + UT_hash_handle *_src_hh, *_dst_hh, *_last_elt_hh=NULL; \ + ptrdiff_t _dst_hho = ((char*)(&(dst)->hh_dst) - (char*)(dst)); \ + if ((src) != NULL) { \ + for (_src_bkt=0; _src_bkt < (src)->hh_src.tbl->num_buckets; _src_bkt++) { \ + for (_src_hh = (src)->hh_src.tbl->buckets[_src_bkt].hh_head; \ + _src_hh != NULL; \ + _src_hh = _src_hh->hh_next) { \ + _elt = ELMT_FROM_HH((src)->hh_src.tbl, _src_hh); \ + if (cond(_elt)) { \ + IF_HASH_NONFATAL_OOM( int _hs_oomed = 0; ) \ + _dst_hh = (UT_hash_handle*)(void*)(((char*)_elt) + _dst_hho); \ + _dst_hh->key = _src_hh->key; \ + _dst_hh->keylen = _src_hh->keylen; \ + _dst_hh->hashv = _src_hh->hashv; \ + _dst_hh->prev = _last_elt; \ + _dst_hh->next = NULL; \ + if (_last_elt_hh != NULL) { \ + _last_elt_hh->next = _elt; \ + } \ + if ((dst) == NULL) { \ + DECLTYPE_ASSIGN(dst, _elt); \ + HASH_MAKE_TABLE(hh_dst, dst, _hs_oomed); \ + IF_HASH_NONFATAL_OOM( \ + if (_hs_oomed) { \ + uthash_nonfatal_oom(_elt); \ + (dst) = NULL; \ + continue; \ + } \ + ) \ + } else { \ + _dst_hh->tbl = (dst)->hh_dst.tbl; \ + } \ + HASH_TO_BKT(_dst_hh->hashv, _dst_hh->tbl->num_buckets, _dst_bkt); \ + HASH_ADD_TO_BKT(_dst_hh->tbl->buckets[_dst_bkt], hh_dst, _dst_hh, _hs_oomed); \ + (dst)->hh_dst.tbl->num_items++; \ + IF_HASH_NONFATAL_OOM( \ + if (_hs_oomed) { \ + HASH_ROLLBACK_BKT(hh_dst, dst, _dst_hh); \ + HASH_DELETE_HH(hh_dst, dst, _dst_hh); \ + _dst_hh->tbl = NULL; \ + uthash_nonfatal_oom(_elt); \ + continue; \ + } \ + ) \ + HASH_BLOOM_ADD(_dst_hh->tbl, _dst_hh->hashv); \ + _last_elt = _elt; \ + _last_elt_hh = _dst_hh; \ + } \ + } \ + } \ + } \ + HASH_FSCK(hh_dst, dst, "HASH_SELECT"); \ +} while (0) + +#define HASH_CLEAR(hh,head) \ +do { \ + if ((head) != NULL) { \ + HASH_BLOOM_FREE((head)->hh.tbl); \ + uthash_free((head)->hh.tbl->buckets, \ + (head)->hh.tbl->num_buckets*sizeof(struct UT_hash_bucket)); \ + uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ + (head) = NULL; \ + } \ +} while (0) + +#define HASH_OVERHEAD(hh,head) \ + (((head) != NULL) ? ( \ + (size_t)(((head)->hh.tbl->num_items * sizeof(UT_hash_handle)) + \ + ((head)->hh.tbl->num_buckets * sizeof(UT_hash_bucket)) + \ + sizeof(UT_hash_table) + \ + (HASH_BLOOM_BYTELEN))) : 0U) + +#ifdef NO_DECLTYPE +#define HASH_ITER(hh,head,el,tmp) \ +for(((el)=(head)), ((*(char**)(&(tmp)))=(char*)((head!=NULL)?(head)->hh.next:NULL)); \ + (el) != NULL; ((el)=(tmp)), ((*(char**)(&(tmp)))=(char*)((tmp!=NULL)?(tmp)->hh.next:NULL))) +#else +#define HASH_ITER(hh,head,el,tmp) \ +for(((el)=(head)), ((tmp)=DECLTYPE(el)((head!=NULL)?(head)->hh.next:NULL)); \ + (el) != NULL; ((el)=(tmp)), ((tmp)=DECLTYPE(el)((tmp!=NULL)?(tmp)->hh.next:NULL))) +#endif + +/* obtain a count of items in the hash */ +#define HASH_COUNT(head) HASH_CNT(hh,head) +#define HASH_CNT(hh,head) ((head != NULL)?((head)->hh.tbl->num_items):0U) + +typedef struct UT_hash_bucket { + struct UT_hash_handle *hh_head; + unsigned count; + + /* expand_mult is normally set to 0. In this situation, the max chain length + * threshold is enforced at its default value, HASH_BKT_CAPACITY_THRESH. (If + * the bucket's chain exceeds this length, bucket expansion is triggered). + * However, setting expand_mult to a non-zero value delays bucket expansion + * (that would be triggered by additions to this particular bucket) + * until its chain length reaches a *multiple* of HASH_BKT_CAPACITY_THRESH. + * (The multiplier is simply expand_mult+1). The whole idea of this + * multiplier is to reduce bucket expansions, since they are expensive, in + * situations where we know that a particular bucket tends to be overused. + * It is better to let its chain length grow to a longer yet-still-bounded + * value, than to do an O(n) bucket expansion too often. + */ + unsigned expand_mult; + +} UT_hash_bucket; + +/* random signature used only to find hash tables in external analysis */ +#define HASH_SIGNATURE 0xa0111fe1u +#define HASH_BLOOM_SIGNATURE 0xb12220f2u + +typedef struct UT_hash_table { + UT_hash_bucket *buckets; + unsigned num_buckets, log2_num_buckets; + unsigned num_items; + struct UT_hash_handle *tail; /* tail hh in app order, for fast append */ + ptrdiff_t hho; /* hash handle offset (byte pos of hash handle in element */ + + /* in an ideal situation (all buckets used equally), no bucket would have + * more than ceil(#items/#buckets) items. that's the ideal chain length. */ + unsigned ideal_chain_maxlen; + + /* nonideal_items is the number of items in the hash whose chain position + * exceeds the ideal chain maxlen. these items pay the penalty for an uneven + * hash distribution; reaching them in a chain traversal takes >ideal steps */ + unsigned nonideal_items; + + /* ineffective expands occur when a bucket doubling was performed, but + * afterward, more than half the items in the hash had nonideal chain + * positions. If this happens on two consecutive expansions we inhibit any + * further expansion, as it's not helping; this happens when the hash + * function isn't a good fit for the key domain. When expansion is inhibited + * the hash will still work, albeit no longer in constant time. */ + unsigned ineff_expands, noexpand; + + uint32_t signature; /* used only to find hash tables in external analysis */ +#ifdef HASH_BLOOM + uint32_t bloom_sig; /* used only to test bloom exists in external analysis */ + uint8_t *bloom_bv; + uint8_t bloom_nbits; +#endif + +} UT_hash_table; + +typedef struct UT_hash_handle { + struct UT_hash_table *tbl; + void *prev; /* prev element in app order */ + void *next; /* next element in app order */ + struct UT_hash_handle *hh_prev; /* previous hh in bucket order */ + struct UT_hash_handle *hh_next; /* next hh in bucket order */ + const void *key; /* ptr to enclosing struct's key */ + unsigned keylen; /* enclosing struct's key len */ + unsigned hashv; /* result of hash-fcn(key) */ +} UT_hash_handle; + +#endif /* UTHASH_H */ diff --git a/codes/rust/Cargo.lock b/codes/rust/Cargo.lock index ae2b69a8..6de3eabd 100644 --- a/codes/rust/Cargo.lock +++ b/codes/rust/Cargo.lock @@ -8,6 +8,13 @@ version = "1.0.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" +[[package]] +name = "chapter_array_and_linkedlist" +version = "0.1.0" +dependencies = [ + "rand", +] + [[package]] name = "chapter_computational_complexity" version = "0.1.0" diff --git a/codes/rust/Cargo.toml b/codes/rust/Cargo.toml index 91b54bc3..c2e0db42 100644 --- a/codes/rust/Cargo.toml +++ b/codes/rust/Cargo.toml @@ -2,4 +2,5 @@ [workspace] members = [ "chapter_computational_complexity", + "chapter_array_and_linkedlist" ] \ No newline at end of file diff --git a/codes/rust/chapter_array_and_linkedlist/Cargo.toml b/codes/rust/chapter_array_and_linkedlist/Cargo.toml new file mode 100644 index 00000000..a83a67b0 --- /dev/null +++ b/codes/rust/chapter_array_and_linkedlist/Cargo.toml @@ -0,0 +1,16 @@ +[package] +name = "chapter_array_and_linkedlist" +version = "0.1.0" +edition = "2021" + + +[[bin]] +name = "array" +path = "array.rs" + +[[bin]] +name = "list" +path = "list.rs" + +[dependencies] +rand = "0.8.5" diff --git a/codes/rust/chapter_array_and_linkedlist/array.rs b/codes/rust/chapter_array_and_linkedlist/array.rs new file mode 100644 index 00000000..e23c6a4f --- /dev/null +++ b/codes/rust/chapter_array_and_linkedlist/array.rs @@ -0,0 +1,102 @@ +/** + * File: array.rs + * Created Time: 2023-01-15 + * Author: xBLACICEx (xBLACKICEx@outlook.com) +*/ + +/* 随机返回一个数组元素 */ +fn random_access(nums: &[i32]) -> i32 { + // 在区间 [0, nums.len()) 中随机抽取一个数字 + let random_index = rand::random::() % nums.len(); + // 获取并返回随机元素 + let random_num = nums[random_index]; + random_num +} + +/* 扩展数组长度 */ +fn extend(nums: Vec, enlarge: usize) -> Vec { + // 创建一个长度为 nums.len() + enlarge 的新 Vec + let mut res: Vec = vec![0; nums.len() + enlarge]; + // 将原数组中的所有元素复制到新 + for i in 0..nums.len() { + res[i] = nums[i]; + } + // 返回扩展后的新数组 + res +} + +/* 在数组的索引 index 处插入元素 num */ +fn insert(nums: &mut Vec, num: i32, index: usize) { + // 把索引 index 以及之后的所有元素向后移动一位 + for i in (index + 1..nums.len()).rev() { + nums[i] = nums[i - 1]; + } + // 将 num 赋给 index 处元素 + nums[index] = num; +} + +/* 删除索引 index 处元素 */ +fn remove(nums: &mut Vec, index: usize) { + // 把索引 index 之后的所有元素向前移动一位 + for i in index..nums.len() - 1 { + nums[i] = nums[i + 1]; + } +} + +#[allow(unused_variables)] +/* 遍历数组 */ +fn traverse(nums: &[i32]) { + let mut count = 0; + // 通过索引遍历数组 + for _ in 0..nums.len() { + count += 1; + } + // 直接遍历数组 + for _ in nums { + count += 1; + } +} + +/* 在数组中查找指定元素 */ +fn find(nums: &[i32], target: i32) -> Option { + for i in 0..nums.len() { + if nums[i] == target { + return Some(i); + } + } + None +} + +/* Driver Code */ +fn main() { + let arr = [0; 5]; + println!("数组 arr = {:?}", arr); + // 在 Rust 中，指定长度时（[i32; 5]）为数组 + // 由于 Rust 的数组被设计为在编译期确定长度，因此只能使用常量来指定长度 + // 为了方便实现扩容 extend() 方法，以下将(Vec) 看作数组（Array）也是rust一般情况下使用动态数组的类型 + let nums = vec![1, 3, 2, 5, 4]; + println!("数组 nums = {:?}", nums); + + /* 随机访问 */ + let random_num = random_access(&nums); + println!("在 nums 中获取随机元素 {}", random_num); + + /* 长度扩展 */ + let mut nums = extend(nums, 3); + println!("将数组长度扩展至 8 ，得到 nums = {:?}", nums); + + /* 插入元素 */ + insert(&mut nums, 6, 3); + println!("在索引 3 处插入数字 6 ，得到 nums = {:?}", nums); + + /* 删除元素 */ + remove(&mut nums, 2); + println!("删除索引 2 处的元素，得到 nums = {:?}", nums); + + /* 遍历数组 */ + traverse(&nums); + + /* 查找元素 */ + let index = find(&nums, 3); + println!("在 nums 中查找元素 3 ，得到索引 = {:?}", index); +} \ No newline at end of file diff --git a/codes/rust/chapter_array_and_linkedlist/list.rs b/codes/rust/chapter_array_and_linkedlist/list.rs new file mode 100644 index 00000000..b9b3d1ee --- /dev/null +++ b/codes/rust/chapter_array_and_linkedlist/list.rs @@ -0,0 +1,67 @@ +/** + * File: array.rs + * Created Time: 2023-01-18 + * Author: xBLACICEx (xBLACKICEx@outlook.com) + */ + +#[allow(unused_variables)] + +/* Driver Code */ +fn main() { + /* 初始化列表 */ + let mut list: Vec = vec![1, 3, 2, 5, 4]; + println!("列表 list = {:?}", list); + + /* 访问元素 */ + let num = list[1]; + println!("访问索引 1 处的元素，得到 num = {num}"); + + /* 更新元素 */ + list[1] = 0; + println!("将索引 1 处的元素更新为 0 ，得到 list = {:?}", list); + + /* 清空列表 */ + list.clear(); + println!("清空列表后 list = {:?}", list); + + /* 尾部添加元素 */ + list.push(1); + list.push(3); + list.push(2); + list.push(5); + list.push(4); + println!("添加元素后 list = {:?}", list); + + /* 中间插入元素 */ + list.insert(3, 6); + println!("在索引 3 处插入数字 6 ，得到 list = {:?}", list); + + /* 删除元素 */ + list.remove(3); + println!("删除索引 3 处的元素，得到 list = {:?}", list); + + /* 通过索引遍历列表 */ + let mut count = 0; + for _ in 0..list.len() { + count += 1; + } + + /* 直接遍历列表元素 */ + count = 0; + for _ in &list { + count += 1; + } // 或者 + // list.iter().for_each(|_| count += 1); + // let count = list.iter().fold(0, |count, _| count + 1); + + /* 拼接两个列表 */ + let mut list1 = vec![6, 8, 7, 10, 9]; + list.append(&mut list1); // append（移动） 之后 list1 为空！ + // list.extend(&list1); // extend（借用） list1 能继续使用 + + println!("将列表 list1 拼接到 list 之后，得到 list = {:?}", list); + + /* 排序列表 */ + list.sort(); + println!("排序列表后 list = {:?}", list); +} \ No newline at end of file diff --git a/codes/swift/Package.swift b/codes/swift/Package.swift index 1dc64032..ad035475 100644 --- a/codes/swift/Package.swift +++ b/codes/swift/Package.swift @@ -26,6 +26,7 @@ let package = Package( .executable(name: "binary_tree_bfs", targets: ["binary_tree_bfs"]), .executable(name: "binary_tree_dfs", targets: ["binary_tree_dfs"]), .executable(name: "binary_search_tree", targets: ["binary_search_tree"]), + .executable(name: "avl_tree", targets: ["avl_tree"]), ], targets: [ .target(name: "utils", path: "utils"), @@ -50,5 +51,6 @@ let package = Package( .executableTarget(name: "binary_tree_bfs", dependencies: ["utils"], path: "chapter_tree", sources: ["binary_tree_bfs.swift"]), .executableTarget(name: "binary_tree_dfs", dependencies: ["utils"], path: "chapter_tree", sources: ["binary_tree_dfs.swift"]), .executableTarget(name: "binary_search_tree", dependencies: ["utils"], path: "chapter_tree", sources: ["binary_search_tree.swift"]), + .executableTarget(name: "avl_tree", dependencies: ["utils"], path: "chapter_tree", sources: ["avl_tree.swift"]), ] ) diff --git a/codes/swift/chapter_tree/avl_tree.swift b/codes/swift/chapter_tree/avl_tree.swift new file mode 100644 index 00000000..f0ea2fca --- /dev/null +++ b/codes/swift/chapter_tree/avl_tree.swift @@ -0,0 +1,242 @@ +/** + * File: avl_tree.swift + * Created Time: 2023-01-28 + * Author: nuomi1 (nuomi1@qq.com) + */ + +import utils + +// Tree class +class AVLTree { + fileprivate var root: TreeNode? // 根节点 + + /* 获取结点高度 */ + func height(node: TreeNode?) -> Int { + // 空结点高度为 -1 ，叶结点高度为 0 + node == nil ? -1 : node!.height + } + + /* 更新结点高度 */ + private func updateHeight(node: TreeNode?) { + // 结点高度等于最高子树高度 + 1 + node?.height = max(height(node: node?.left), height(node: node?.right)) + 1 + } + + /* 获取平衡因子 */ + func balanceFactor(node: TreeNode?) -> Int { + // 空结点平衡因子为 0 + guard let node = node else { return 0 } + // 结点平衡因子 = 左子树高度 - 右子树高度 + return height(node: node.left) - height(node: node.right) + } + + /* 右旋操作 */ + private func rightRotate(node: TreeNode?) -> TreeNode? { + let child = node?.left + let grandChild = child?.right + // 以 child 为原点，将 node 向右旋转 + child?.right = node + node?.left = grandChild + // 更新结点高度 + updateHeight(node: node) + updateHeight(node: child) + // 返回旋转后子树的根节点 + return child + } + + /* 左旋操作 */ + private func leftRotate(node: TreeNode?) -> TreeNode? { + let child = node?.right + let grandChild = child?.left + // 以 child 为原点，将 node 向左旋转 + child?.left = node + node?.right = grandChild + // 更新结点高度 + updateHeight(node: node) + updateHeight(node: child) + // 返回旋转后子树的根节点 + return child + } + + /* 执行旋转操作，使该子树重新恢复平衡 */ + private func rotate(node: TreeNode?) -> TreeNode? { + // 获取结点 node 的平衡因子 + let balanceFactor = balanceFactor(node: node) + // 左偏树 + if balanceFactor > 1 { + if self.balanceFactor(node: node?.left) >= 0 { + // 右旋 + return rightRotate(node: node) + } else { + // 先左旋后右旋 + node?.left = leftRotate(node: node?.left) + return rightRotate(node: node) + } + } + // 右偏树 + if balanceFactor < -1 { + if self.balanceFactor(node: node?.right) <= 0 { + // 左旋 + return leftRotate(node: node) + } else { + // 先右旋后左旋 + node?.right = rightRotate(node: node?.right) + return leftRotate(node: node) + } + } + // 平衡树，无需旋转，直接返回 + return node + } + + /* 插入结点 */ + @discardableResult + func insert(val: Int) -> TreeNode? { + root = insertHelper(node: root, val: val) + return root + } + + /* 递归插入结点（辅助函数） */ + private func insertHelper(node: TreeNode?, val: Int) -> TreeNode? { + var node = node + if node == nil { + return TreeNode(x: val) + } + /* 1. 查找插入位置，并插入结点 */ + if val < node!.val { + node?.left = insertHelper(node: node?.left, val: val) + } else if val > node!.val { + node?.right = insertHelper(node: node?.right, val: val) + } else { + return node // 重复结点不插入，直接返回 + } + updateHeight(node: node) // 更新结点高度 + /* 2. 执行旋转操作，使该子树重新恢复平衡 */ + node = rotate(node: node) + // 返回子树的根节点 + return node + } + + /* 删除结点 */ + @discardableResult + func remove(val: Int) -> TreeNode? { + root = removeHelper(node: root, val: val) + return root + } + + /* 递归删除结点（辅助函数） */ + private func removeHelper(node: TreeNode?, val: Int) -> TreeNode? { + var node = node + if node == nil { + return nil + } + /* 1. 查找结点，并删除之 */ + if val < node!.val { + node?.left = removeHelper(node: node?.left, val: val) + } else if val > node!.val { + node?.right = removeHelper(node: node?.right, val: val) + } else { + if node?.left == nil || node?.right == nil { + let child = node?.left != nil ? node?.left : node?.right + // 子结点数量 = 0 ，直接删除 node 并返回 + if child == nil { + return nil + } + // 子结点数量 = 1 ，直接删除 node + else { + node = child + } + } else { + // 子结点数量 = 2 ，则将中序遍历的下个结点删除，并用该结点替换当前结点 + let temp = getInOrderNext(node: node?.right) + node?.right = removeHelper(node: node?.right, val: temp!.val) + node?.val = temp!.val + } + } + updateHeight(node: node) // 更新结点高度 + /* 2. 执行旋转操作，使该子树重新恢复平衡 */ + node = rotate(node: node) + // 返回子树的根节点 + return node + } + + /* 获取中序遍历中的下一个结点（仅适用于 root 有左子结点的情况） */ + private func getInOrderNext(node: TreeNode?) -> TreeNode? { + var node = node + if node == nil { + return node + } + // 循环访问左子结点，直到叶结点时为最小结点，跳出 + while node?.left != nil { + node = node?.left + } + return node + } + + /* 查找结点 */ + func search(val: Int) -> TreeNode? { + var cur = root + while cur != nil { + // 目标结点在 cur 的右子树中 + if cur!.val < val { + cur = cur?.right + } + // 目标结点在 cur 的左子树中 + else if cur!.val > val { + cur = cur?.left + } + // 找到目标结点，跳出循环 + else { + break + } + } + // 返回目标结点 + return cur + } +} + +@main +enum _AVLTree { + static func testInsert(tree: AVLTree, val: Int) { + tree.insert(val: val) + print("\n插入结点 \(val) 后，AVL 树为") + PrintUtil.printTree(root: tree.root) + } + + static func testRemove(tree: AVLTree, val: Int) { + tree.remove(val: val) + print("\n删除结点 \(val) 后，AVL 树为") + PrintUtil.printTree(root: tree.root) + } + + /* Driver Code */ + static func main() { + /* 初始化空 AVL 树 */ + let avlTree = AVLTree() + + /* 插入结点 */ + // 请关注插入结点后，AVL 树是如何保持平衡的 + testInsert(tree: avlTree, val: 1) + testInsert(tree: avlTree, val: 2) + testInsert(tree: avlTree, val: 3) + testInsert(tree: avlTree, val: 4) + testInsert(tree: avlTree, val: 5) + testInsert(tree: avlTree, val: 8) + testInsert(tree: avlTree, val: 7) + testInsert(tree: avlTree, val: 9) + testInsert(tree: avlTree, val: 10) + testInsert(tree: avlTree, val: 6) + + /* 插入重复结点 */ + testInsert(tree: avlTree, val: 7) + + /* 删除结点 */ + // 请关注删除结点后，AVL 树是如何保持平衡的 + testRemove(tree: avlTree, val: 8) // 删除度为 0 的结点 + testRemove(tree: avlTree, val: 5) // 删除度为 1 的结点 + testRemove(tree: avlTree, val: 4) // 删除度为 2 的结点 + + /* 查询结点 */ + let node = avlTree.search(val: 7) + print("\n查找到的结点对象为 \(node!)，结点值 = \(node!.val)") + } +} diff --git a/docs/chapter_tree/avl_tree.md b/docs/chapter_tree/avl_tree.md index 6f627264..95c818c0 100644 --- a/docs/chapter_tree/avl_tree.md +++ b/docs/chapter_tree/avl_tree.md @@ -103,7 +103,18 @@ G. M. Adelson-Velsky 和 E. M. Landis 在其 1962 年发表的论文 "An algorit === "Swift" ```swift title="avl_tree.swift" + /* AVL 树结点类 */ + class TreeNode { + var val: Int // 结点值 + var height: Int // 结点高度 + var left: TreeNode? // 左子结点 + var right: TreeNode? // 右子结点 + init(x: Int) { + val = x + height = 0 + } + } ``` 「结点高度」是最远叶结点到该结点的距离，即走过的「边」的数量。需要特别注意，**叶结点的高度为 0 ，空结点的高度为 -1**。我们封装两个工具函数，分别用于获取与更新结点的高度。 @@ -210,7 +221,17 @@ G. M. Adelson-Velsky 和 E. M. Landis 在其 1962 年发表的论文 "An algorit === "Swift" ```swift title="avl_tree.swift" + /* 获取结点高度 */ + func height(node: TreeNode?) -> Int { + // 空结点高度为 -1 ，叶结点高度为 0 + node == nil ? -1 : node!.height + } + /* 更新结点高度 */ + func updateHeight(node: TreeNode?) { + // 结点高度等于最高子树高度 + 1 + node?.height = max(height(node: node?.left), height(node: node?.right)) + 1 + } ``` ### 结点平衡因子 @@ -295,7 +316,13 @@ G. M. Adelson-Velsky 和 E. M. Landis 在其 1962 年发表的论文 "An algorit === "Swift" ```swift title="avl_tree.swift" - + /* 获取平衡因子 */ + func balanceFactor(node: TreeNode?) -> Int { + // 空结点平衡因子为 0 + guard let node = node else { return 0 } + // 结点平衡因子 = 左子树高度 - 右子树高度 + return height(node: node.left) - height(node: node.right) + } ``` !!! note @@ -427,7 +454,19 @@ AVL 树的独特之处在于「旋转 Rotation」的操作，其可 **在不影 === "Swift" ```swift title="avl_tree.swift" - + /* 右旋操作 */ + func rightRotate(node: TreeNode?) -> TreeNode? { + let child = node?.left + let grandChild = child?.right + // 以 child 为原点，将 node 向右旋转 + child?.right = node + node?.left = grandChild + // 更新结点高度 + updateHeight(node: node) + updateHeight(node: child) + // 返回旋转后子树的根节点 + return child + } ``` ### Case 2 - 左旋 @@ -541,7 +580,19 @@ AVL 树的独特之处在于「旋转 Rotation」的操作，其可 **在不影 === "Swift" ```swift title="avl_tree.swift" - + /* 左旋操作 */ + func leftRotate(node: TreeNode?) -> TreeNode? { + let child = node?.right + let grandChild = child?.left + // 以 child 为原点，将 node 向左旋转 + child?.left = node + node?.right = grandChild + // 更新结点高度 + updateHeight(node: node) + updateHeight(node: child) + // 返回旋转后子树的根节点 + return child + } ``` ### Case 3 - 先左后右 @@ -745,7 +796,35 @@ AVL 树的独特之处在于「旋转 Rotation」的操作，其可 **在不影 === "Swift" ```swift title="avl_tree.swift" - + /* 执行旋转操作，使该子树重新恢复平衡 */ + func rotate(node: TreeNode?) -> TreeNode? { + // 获取结点 node 的平衡因子 + let balanceFactor = balanceFactor(node: node) + // 左偏树 + if balanceFactor > 1 { + if self.balanceFactor(node: node?.left) >= 0 { + // 右旋 + return rightRotate(node: node) + } else { + // 先左旋后右旋 + node?.left = leftRotate(node: node?.left) + return rightRotate(node: node) + } + } + // 右偏树 + if balanceFactor < -1 { + if self.balanceFactor(node: node?.right) <= 0 { + // 左旋 + return leftRotate(node: node) + } else { + // 先右旋后左旋 + node?.right = rightRotate(node: node?.right) + return leftRotate(node: node) + } + } + // 平衡树，无需旋转，直接返回 + return node + } ``` ## AVL 树常用操作 @@ -894,7 +973,33 @@ AVL 树的独特之处在于「旋转 Rotation」的操作，其可 **在不影 === "Swift" ```swift title="avl_tree.swift" + /* 插入结点 */ + @discardableResult + func insert(val: Int) -> TreeNode? { + root = insertHelper(node: root, val: val) + return root + } + /* 递归插入结点（辅助函数） */ + func insertHelper(node: TreeNode?, val: Int) -> TreeNode? { + var node = node + if node == nil { + return TreeNode(x: val) + } + /* 1. 查找插入位置，并插入结点 */ + if val < node!.val { + node?.left = insertHelper(node: node?.left, val: val) + } else if val > node!.val { + node?.right = insertHelper(node: node?.right, val: val) + } else { + return node // 重复结点不插入，直接返回 + } + updateHeight(node: node) // 更新结点高度 + /* 2. 执行旋转操作，使该子树重新恢复平衡 */ + node = rotate(node: node) + // 返回子树的根节点 + return node + } ``` ### 删除结点 @@ -1100,7 +1205,48 @@ AVL 树的独特之处在于「旋转 Rotation」的操作，其可 **在不影 === "Swift" ```swift title="avl_tree.swift" + /* 删除结点 */ + @discardableResult + func remove(val: Int) -> TreeNode? { + root = removeHelper(node: root, val: val) + return root + } + /* 递归删除结点（辅助函数） */ + func removeHelper(node: TreeNode?, val: Int) -> TreeNode? { + var node = node + if node == nil { + return nil + } + /* 1. 查找结点，并删除之 */ + if val < node!.val { + node?.left = removeHelper(node: node?.left, val: val) + } else if val > node!.val { + node?.right = removeHelper(node: node?.right, val: val) + } else { + if node?.left == nil || node?.right == nil { + let child = node?.left != nil ? node?.left : node?.right + // 子结点数量 = 0 ，直接删除 node 并返回 + if child == nil { + return nil + } + // 子结点数量 = 1 ，直接删除 node + else { + node = child + } + } else { + // 子结点数量 = 2 ，则将中序遍历的下个结点删除，并用该结点替换当前结点 + let temp = getInOrderNext(node: node?.right) + node?.right = removeHelper(node: node?.right, val: temp!.val) + node?.val = temp!.val + } + } + updateHeight(node: node) // 更新结点高度 + /* 2. 执行旋转操作，使该子树重新恢复平衡 */ + node = rotate(node: node) + // 返回子树的根节点 + return node + } ``` ### 查找结点