如何在不知道每行字符串长度的情况下使用 fscanf
How to use fscanf without knowing the length of strings in every line
据我了解，有一种方法可以这样解析输入：
A million $ exit $$$ 16
The Cheit and its Punishment $$$ 8
War and Remembrance $$$ 12
Winds of War $$$ 12
How to Play Football $$$ 12
Ultrashort
Pulses $$$ 8
Nonlinear Optics $$$ 8
etc..
其中“$$$”分隔数据字段。
我正在寻找升级短语：
sscanf(line, " %200[^$][^$][^$]$$$%ld", name, &copies);
所以它适合第 1 行。示例中的 1。
编辑：
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#define NAME_LENGTH 200
#define ERROR -1
typedef int BOOL;
#define TRUE 1
#define FALSE 0
typedef struct book{
char name[NAME_LENGTH];
long copies;
struct book *next;
} Book;
Book* create_book(char name[], long copies){
Book *new_book = (Book*) malloc(sizeof(Book));
if (new_book != NULL) {
strcpy(new_book->name, name);
new_book->next = NULL;
new_book->copies = copies;
}
return new_book;
}
Book* add_first(Book *head, char name[], long copies){
Book *new_book = create_book(name, copies);
if (new_book == NULL)
return NULL;
new_book->next = head;
return new_book;
}
Book* add_last(Book *head, char name[], long copies){
Book *tail;
Book *new_book = create_book(name, copies);
if (new_book == NULL)
return NULL;
if (head == NULL)
return new_book;
tail = head;
while (tail->next != NULL)
tail = tail->next;
tail->next = new_book;
return head;
}
Book* add_sorted(Book *head, char name[], long copies){
Book* iter, *prev = NULL;
Book* new_book = create_book(name, copies);
if(new_book == NULL)
return head;
if (head == NULL)
return new_book;
if (!strcmp(new_book->name, head->name)){
new_book->next = head;
return new_book;
}
iter = head;
while ((iter != NULL) && (strcmp(new_book->name, head->name))){
prev = iter;
iter = iter->next;
}
prev->next = new_book;
new_book->next = iter;
return head;
}
int length(const Book *head){
if (head == NULL)
return 0;
return 1 + length(head->next);
}
void free_library(Book *head_book){
if (head_book == NULL)
return;
free_library(head_book->next);
free(head_book);
}
Book* find_book(Book *head, char name[]){
if (head == NULL)
return NULL;
if (strcmp(head->name, name) == 0)
return head;
find_book(head->next, name);
return NULL;
}
Book* delete_book(Book *head, char name[]){
Book *iter = head, *prev = NULL;
if (head == NULL)
return head;
if ((!strcmp(head->name, name)) == 1){
iter = head->next;
free(head);
return iter;
}
while (iter->next != NULL){
if ((!strcmp(head->name, name)) == 1){
prev->next = iter->next;
free(iter);
break;
}
prev = iter;
iter = iter->next;
}
return head;
}
Book* initBooksList(FILE *input){
Book *head_book = NULL, *existing_book = NULL;
long copies = 0;
char line[256] = {0}, name[NAME_LENGTH];
if (input == NULL){
printf("File did not open. Exit..\n");
return NULL;
}
while(!feof(input)){
if((fgets(line, 256, input) != NULL) && (head_book == NULL)){
sscanf(line, " %200[^$][^$][^$]$$$%ld", name, &copies);
printf("%s\n%ld\n", name, copies);
head_book = create_book(name, copies);
strcpy(line, "");
strcpy(name, "");
copies = 0;
}
else{
sscanf(line, " %200[^$][^$][^$]$$$%ld", name, &copies);
existing_book = find_book(head_book, name);
if(existing_book != NULL){
existing_book->copies += copies;
printf("%s\n%ld\n", name, existing_book->copies);
}
else{
add_sorted(head_book, name, copies);
printf("%s\n%ld\n", name, copies);
strcpy(line, "");
strcpy(name, "");
copies = 0;
}
}
}
return head_book;
}
void storeBooks(Book *head_book){
}
void returnBook(Book *head_book){
}
void borrowBook(Book *head_book){
}
int main(int argc, char *argv[]){
int i = 0;
FILE *ptr;
printf("%d\n", argc);
for(i = 0; i < argc; i++)
printf("argv[%d] = %s\n", i, argv[i]);
ptr = fopen(argv[1], "r");
initBooksList(ptr);
return 0;
}
这应该让您知道您可以做什么：
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main()
{
char line[] = "The Cheit and its Punishment $$$ 8";
char *seppointer = strchr(line, '$');
*seppointer = 0;
int price = atoi(seppointer + 4);
printf("Title: %s\nPrice: %d\n", line, price);
}
免责声明：没有错误检查，假定该行具有所需的格式。
如果你知道最长的标题是200个字符，如your comment所示，你可以为此分配一个数组（包括space用于null-terminator）。
您可以使用 fscanf() 来解析格式字符串 " %200[^$]$$$%d" 的文件行。第一个 space 告诉 fscanf() 跳过前导的白色 space，这可能是之前 I/O 操作留下的。下一个转换说明符是 %200[^$]，它告诉 fscanf() 将任何字符读入字符串，直到遇到 $。 $ 留在输入流中。请注意，此处指定的最大宽度为 200，以防止缓冲区溢出。格式字符串中接下来的三个字符 $$$ 必须出现在输入中，并且在到达最终转换说明符 %d 之前匹配。
#include <stdio.h>
#include <stdlib.h>
#define MAX_TITLE 201
int main(void)
{
/* Open file, and check for success */
FILE *fp = fopen("data.txt", "r");
if (fp == NULL) {
perror("Unable to open file");
exit(EXIT_FAILURE);
}
char title[MAX_TITLE];
int price;
while (fscanf(fp, " %200[^$]$$$%d", title, &price) == 2) {
printf("Title: %s --- Price: $%d\n", title, price);
}
fclose(fp);
return 0;
}
这是当 运行 针对您的输入文件时的程序输出：
Title: The Cheit and its Punishment --- Price:
Title: War and Remembrance --- Price:
Title: Winds of War --- Price:
Title: How to Play Football --- Price:
Title: Ultrashort Pulses --- Price:
Title: Nonlinear Optics --- Price:
上述代码中对 fscanf() 的调用在输入流中的每一行的最后一个数字后面留下了白色 space 字符；这就是为什么格式字符串中需要前导 whitespace 的原因。更好的解决方案是使用 fgets() 获取一行输入，并使用 sscanf() 解析该行。应该分配一个 buffer 来保存读取的每一行的内容；此处的慷慨分配是好的，因为它减少了长输入在输入流中留下字符的机会。如果有可能输入更长的时间，则应添加代码以在下次调用 fgets().
之前清除输入流
这种方法的一个优点是，由于读取了包括 \n 在内的整行，因此无需像以前那样跳过前导白色 space 字符。另一个优点是可以忽略最终数字后的虚假字符，或者由代码处理；由于线路已存储，因此可以根据需要多次检查和扫描。最终数字后面的字符会给第一个版本带来问题，该版本只能跳过前导白色space.
#include <stdio.h>
#include <stdlib.h>
#define BUF_SZ 1000
#define MAX_TITLE 201
int main(void)
{
/* Open file, and check for success */
FILE *fp = fopen("data.txt", "r");
if (fp == NULL) {
perror("Unable to open file");
exit(EXIT_FAILURE);
}
char buffer[BUF_SZ];
char title[MAX_TITLE];
int price;
size_t lnum = 0;
while (fgets(buffer, BUF_SZ, fp) != NULL) {
++lnum;
if (sscanf(buffer, "%200[^$]$$$%d", title, &price) == 2) {
printf("Title: %s --- Price: $%d\n", title, price);
} else {
fprintf(stderr, "Format error in line %zu\n", lnum);
}
}
fclose(fp);
return 0;
}
此处使用 fgets() 可以更灵活地检查输入。要处理 $ 是标题的一部分的情况，您可以使用 strstr() 首先找到分隔符 " $$$"，然后将分隔符之前的字符复制到 title[] 数组中在一个循环中。由于 strstr() returns 指向找到的字符串的指针，因此可以将此指针提供给 sscanf() 以挑选出最终数字。如果未找到字符串，strstr() 函数 returns 一个空指针，这可用于识别有格式问题的行。请注意 strstr() 在 string.h:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define BUF_SZ 1000
#define MAX_TITLE 201
int main(void)
{
/* Open file, and check for success */
FILE *fp = fopen("data.txt", "r");
if (fp == NULL) {
perror("Unable to open file");
exit(EXIT_FAILURE);
}
char buffer[BUF_SZ];
char title[MAX_TITLE];
int copies;
size_t lnum = 0;
while (fgets(buffer, BUF_SZ, fp) != NULL) {
++lnum;
/* Find delimiter string in buffer */
char *title_end = strstr(buffer, " $$$");
if (title_end == NULL) {
fprintf(stderr, "Format error in line %zu\n", lnum);
continue;
} else {
/* Copy characters into title until space before delimiter */
char *curr = buffer;
size_t i = 0;
while (curr < title_end && i < MAX_TITLE) {
title[i] = buffer[i];
++curr;
++i;
}
title[i] = '[=13=]';
}
if (sscanf(title_end, " $$$%d", &copies) == 1) {
printf("Title: %s --- Copies: %d\n", title, copies);
} else {
fprintf(stderr, "Format error in line %zu\n", lnum);
}
}
fclose(fp);
return 0;
}
这是修改后的输入文件：
The Cheit and its Punishment $$$ 8
War and Remembrance $$$ 12
Winds of War $$$ 12
A million $ exit $$$ 16
How to Play Football $$$ 12
Ultrashort Pulses $$$ 8
Nonlinear Optics $$$ 8
和结果输出：
Title: The Cheit and its Punishment --- Copies: 8
Title: War and Remembrance --- Copies: 12
Title: Winds of War --- Copies: 12
Title: A million $ exit --- Copies: 16
Title: How to Play Football --- Copies: 12
Title: Ultrashort Pulses --- Copies: 8
Title: Nonlinear Optics --- Copies: 8
据我了解，有一种方法可以这样解析输入：
A million $ exit $$$ 16
The Cheit and its Punishment $$$ 8
War and Remembrance $$$ 12
Winds of War $$$ 12
How to Play Football $$$ 12
Ultrashort Pulses $$$ 8
Nonlinear Optics $$$ 8
etc..
其中“$$$”分隔数据字段。
我正在寻找升级短语：
sscanf(line, " %200[^$][^$][^$]$$$%ld", name, &copies);
所以它适合第 1 行。示例中的 1。
编辑：
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#define NAME_LENGTH 200
#define ERROR -1
typedef int BOOL;
#define TRUE 1
#define FALSE 0
typedef struct book{
char name[NAME_LENGTH];
long copies;
struct book *next;
} Book;
Book* create_book(char name[], long copies){
Book *new_book = (Book*) malloc(sizeof(Book));
if (new_book != NULL) {
strcpy(new_book->name, name);
new_book->next = NULL;
new_book->copies = copies;
}
return new_book;
}
Book* add_first(Book *head, char name[], long copies){
Book *new_book = create_book(name, copies);
if (new_book == NULL)
return NULL;
new_book->next = head;
return new_book;
}
Book* add_last(Book *head, char name[], long copies){
Book *tail;
Book *new_book = create_book(name, copies);
if (new_book == NULL)
return NULL;
if (head == NULL)
return new_book;
tail = head;
while (tail->next != NULL)
tail = tail->next;
tail->next = new_book;
return head;
}
Book* add_sorted(Book *head, char name[], long copies){
Book* iter, *prev = NULL;
Book* new_book = create_book(name, copies);
if(new_book == NULL)
return head;
if (head == NULL)
return new_book;
if (!strcmp(new_book->name, head->name)){
new_book->next = head;
return new_book;
}
iter = head;
while ((iter != NULL) && (strcmp(new_book->name, head->name))){
prev = iter;
iter = iter->next;
}
prev->next = new_book;
new_book->next = iter;
return head;
}
int length(const Book *head){
if (head == NULL)
return 0;
return 1 + length(head->next);
}
void free_library(Book *head_book){
if (head_book == NULL)
return;
free_library(head_book->next);
free(head_book);
}
Book* find_book(Book *head, char name[]){
if (head == NULL)
return NULL;
if (strcmp(head->name, name) == 0)
return head;
find_book(head->next, name);
return NULL;
}
Book* delete_book(Book *head, char name[]){
Book *iter = head, *prev = NULL;
if (head == NULL)
return head;
if ((!strcmp(head->name, name)) == 1){
iter = head->next;
free(head);
return iter;
}
while (iter->next != NULL){
if ((!strcmp(head->name, name)) == 1){
prev->next = iter->next;
free(iter);
break;
}
prev = iter;
iter = iter->next;
}
return head;
}
Book* initBooksList(FILE *input){
Book *head_book = NULL, *existing_book = NULL;
long copies = 0;
char line[256] = {0}, name[NAME_LENGTH];
if (input == NULL){
printf("File did not open. Exit..\n");
return NULL;
}
while(!feof(input)){
if((fgets(line, 256, input) != NULL) && (head_book == NULL)){
sscanf(line, " %200[^$][^$][^$]$$$%ld", name, &copies);
printf("%s\n%ld\n", name, copies);
head_book = create_book(name, copies);
strcpy(line, "");
strcpy(name, "");
copies = 0;
}
else{
sscanf(line, " %200[^$][^$][^$]$$$%ld", name, &copies);
existing_book = find_book(head_book, name);
if(existing_book != NULL){
existing_book->copies += copies;
printf("%s\n%ld\n", name, existing_book->copies);
}
else{
add_sorted(head_book, name, copies);
printf("%s\n%ld\n", name, copies);
strcpy(line, "");
strcpy(name, "");
copies = 0;
}
}
}
return head_book;
}
void storeBooks(Book *head_book){
}
void returnBook(Book *head_book){
}
void borrowBook(Book *head_book){
}
int main(int argc, char *argv[]){
int i = 0;
FILE *ptr;
printf("%d\n", argc);
for(i = 0; i < argc; i++)
printf("argv[%d] = %s\n", i, argv[i]);
ptr = fopen(argv[1], "r");
initBooksList(ptr);
return 0;
}
这应该让您知道您可以做什么：
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main()
{
char line[] = "The Cheit and its Punishment $$$ 8";
char *seppointer = strchr(line, '$');
*seppointer = 0;
int price = atoi(seppointer + 4);
printf("Title: %s\nPrice: %d\n", line, price);
}
免责声明：没有错误检查，假定该行具有所需的格式。
如果你知道最长的标题是200个字符，如your comment所示，你可以为此分配一个数组（包括space用于null-terminator）。
您可以使用 fscanf() 来解析格式字符串 " %200[^$]$$$%d" 的文件行。第一个 space 告诉 fscanf() 跳过前导的白色 space，这可能是之前 I/O 操作留下的。下一个转换说明符是 %200[^$]，它告诉 fscanf() 将任何字符读入字符串，直到遇到 $。 $ 留在输入流中。请注意，此处指定的最大宽度为 200，以防止缓冲区溢出。格式字符串中接下来的三个字符 $$$ 必须出现在输入中，并且在到达最终转换说明符 %d 之前匹配。
#include <stdio.h>
#include <stdlib.h>
#define MAX_TITLE 201
int main(void)
{
/* Open file, and check for success */
FILE *fp = fopen("data.txt", "r");
if (fp == NULL) {
perror("Unable to open file");
exit(EXIT_FAILURE);
}
char title[MAX_TITLE];
int price;
while (fscanf(fp, " %200[^$]$$$%d", title, &price) == 2) {
printf("Title: %s --- Price: $%d\n", title, price);
}
fclose(fp);
return 0;
}
这是当 运行 针对您的输入文件时的程序输出：
Title: The Cheit and its Punishment --- Price:
Title: War and Remembrance --- Price:
Title: Winds of War --- Price:
Title: How to Play Football --- Price:
Title: Ultrashort Pulses --- Price:
Title: Nonlinear Optics --- Price:
上述代码中对 fscanf() 的调用在输入流中的每一行的最后一个数字后面留下了白色 space 字符；这就是为什么格式字符串中需要前导 whitespace 的原因。更好的解决方案是使用 fgets() 获取一行输入，并使用 sscanf() 解析该行。应该分配一个 buffer 来保存读取的每一行的内容；此处的慷慨分配是好的，因为它减少了长输入在输入流中留下字符的机会。如果有可能输入更长的时间，则应添加代码以在下次调用 fgets().
这种方法的一个优点是，由于读取了包括 \n 在内的整行，因此无需像以前那样跳过前导白色 space 字符。另一个优点是可以忽略最终数字后的虚假字符，或者由代码处理；由于线路已存储，因此可以根据需要多次检查和扫描。最终数字后面的字符会给第一个版本带来问题，该版本只能跳过前导白色space.
#include <stdio.h>
#include <stdlib.h>
#define BUF_SZ 1000
#define MAX_TITLE 201
int main(void)
{
/* Open file, and check for success */
FILE *fp = fopen("data.txt", "r");
if (fp == NULL) {
perror("Unable to open file");
exit(EXIT_FAILURE);
}
char buffer[BUF_SZ];
char title[MAX_TITLE];
int price;
size_t lnum = 0;
while (fgets(buffer, BUF_SZ, fp) != NULL) {
++lnum;
if (sscanf(buffer, "%200[^$]$$$%d", title, &price) == 2) {
printf("Title: %s --- Price: $%d\n", title, price);
} else {
fprintf(stderr, "Format error in line %zu\n", lnum);
}
}
fclose(fp);
return 0;
}
此处使用 fgets() 可以更灵活地检查输入。要处理 $ 是标题的一部分的情况，您可以使用 strstr() 首先找到分隔符 " $$$"，然后将分隔符之前的字符复制到 title[] 数组中在一个循环中。由于 strstr() returns 指向找到的字符串的指针，因此可以将此指针提供给 sscanf() 以挑选出最终数字。如果未找到字符串，strstr() 函数 returns 一个空指针，这可用于识别有格式问题的行。请注意 strstr() 在 string.h:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define BUF_SZ 1000
#define MAX_TITLE 201
int main(void)
{
/* Open file, and check for success */
FILE *fp = fopen("data.txt", "r");
if (fp == NULL) {
perror("Unable to open file");
exit(EXIT_FAILURE);
}
char buffer[BUF_SZ];
char title[MAX_TITLE];
int copies;
size_t lnum = 0;
while (fgets(buffer, BUF_SZ, fp) != NULL) {
++lnum;
/* Find delimiter string in buffer */
char *title_end = strstr(buffer, " $$$");
if (title_end == NULL) {
fprintf(stderr, "Format error in line %zu\n", lnum);
continue;
} else {
/* Copy characters into title until space before delimiter */
char *curr = buffer;
size_t i = 0;
while (curr < title_end && i < MAX_TITLE) {
title[i] = buffer[i];
++curr;
++i;
}
title[i] = '[=13=]';
}
if (sscanf(title_end, " $$$%d", &copies) == 1) {
printf("Title: %s --- Copies: %d\n", title, copies);
} else {
fprintf(stderr, "Format error in line %zu\n", lnum);
}
}
fclose(fp);
return 0;
}
这是修改后的输入文件：
The Cheit and its Punishment $$$ 8
War and Remembrance $$$ 12
Winds of War $$$ 12
A million $ exit $$$ 16
How to Play Football $$$ 12
Ultrashort Pulses $$$ 8
Nonlinear Optics $$$ 8
和结果输出：
Title: The Cheit and its Punishment --- Copies: 8
Title: War and Remembrance --- Copies: 12
Title: Winds of War --- Copies: 12
Title: A million $ exit --- Copies: 16
Title: How to Play Football --- Copies: 12
Title: Ultrashort Pulses --- Copies: 8
Title: Nonlinear Optics --- Copies: 8