Fille descriptor in this function - c

I know what a descriptor file is, however I saw a des file. implemented in a function\o and I couldn't understand very well, how it works in that context.
this function is basically fetching phrases from different files and returning them.
It is working perfectly, but I would like to understand the logic of using the file_descriptor in str[].
If the file_descriptor number is let's imagine 106. It will be str[106], what is the logic of this?
thanks for all the help.
type here
char *get_next_line(int file_descriptor)
{
char *line;
static char *left_str[4096];
if (file_descriptor < 0 || BUFFER_SIZE <= 0)
return (0);
left_str[file_descriptor] = ft_read_to_left_str(file_descriptor, left_str[file_descriptor]);
if (!left_str[file_descriptor])
return (NULL);
line = ft_get_line(left_str[file_descriptor]);
left_str[file_descriptor] = ft_new_left_str(left_str[file_descriptor]);
return (line);
}
the objective is to open 3 text files and return one sentence at a time, being 1 sentence from file 1, 1 sentence from file 2, 1 sentence from file 3 etc etc etc
/*int main(void)
{
char *line;
int i;
int filed1;
int filed2;
int filed3;
filed1 = open("tests/test.txt", O_RDONLY);
filed2 = open("tests/test2.txt", O_RDONLY);
filed3 = open("tests/test3.txt", O_RDONLY);
i = 1;
while (i < 7)
{
line = get_next_line(filed1);
printf("line [%02d]: %s", i, line);
free(line);
line = get_next_line(filed2);
printf("line [%02d]: %s", i, line);
free(line);
line = get_next_line(filed3);
printf("line [%02d]: %s", i, line);
free(line);
i++;
}
close(filed1);
close(filed2);
close(filed3);
return (0);
}*/

Related

Compare two binary files in C

I am writing a program to compare two binary files and plot the first difference. I want to read 16 bytes of data from each file continuously and compare them. For that I am storing 16 bytes from both file into char *buffer1, buffer2. When I print the output I am getting that buffer1 has both the data of file1 and file2.
The code is as follows:
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
void printConversion(char *buf1, char *buf2) {
size_t len = strlen(buf1);
char *binary = malloc(len * 8 + 1);
binary[0] = '\0';
for (size_t i = 0; i < len; ++i) {
char ch = buf1[i];
for (int j = 7; j >= 0; --j) {
if (ch & (1 << j)) {
strcat(binary,"1");
} else {
strcat(binary,"0");
}
}
}
printf("File1: %s\t", binary);
free(binary);
printf("File2:");
for (int i = 0; i < sizeof(buf2); i++) {
printf("%x", buf2[i] - '0');
}
}
void fileRead(FILE *fp, char *buf, int count) {
fseek(fp, count, SEEK_SET);
fread(buf, 1, 16, fp);
}
int fileSize(FILE *fp) {
fseek(fp, 0, SEEK_END);
int size = ftell(fp) + 1;
return size;
}
int main(int argc, char *argv[]) {
printf("***Binary File Comparator***\n ");
int count = 0;
int index = 0;
char buffer1[16];
char buffer2[16];
char buffer3[16];
char buffer4[16];
// Invalid Number of Arguments
if (argc < 3 || argc > 3) {
printf("Invalid Number of Arguments\n");
}
FILE *fp1, *fp2;
fp1 = fopen(argv[1], "rb");
int size = fileSize(fp1);
int size1 = size;
fclose(fp1);
while (size > 1) {
fp1 = fopen(argv[1], "rb");
fileRead(fp1, buffer1, count);
fclose(fp1);
fp2 = fopen(argv[2], "rb");
fileRead(fp2, buffer2, count);
if (size1 < count) {
int lastSize = count - size1;
count = count + lastSize;
fclose(fp2);
} else {
count = count+16;
fclose(fp2);
}
**printf("buffer1:%s\tbuffer2:%s\n", buffer1, buffer2)**;
size = size - 16;
int result = strcmp(buffer1, buffer2);
if (result != 0) {
for (int i = 0; i < sizeof(buffer1); i++) {
if (buffer1[i] != buffer2[i]) {
int count1 = (count - 16) + i;
index++;
if (index == 1) {
printf("Byte_Offset:%x\n", count1);
fp1 = fopen(argv[1], "rb");
fileRead(fp1, buffer3, count1);
fclose(fp1);
fp2 = fopen(argv[2], "rb");
fileRead(fp2, buffer4, count1);
fclose(fp2);
printConversion(buffer3, buffer4);
break;
}
} else {
continue;
}
}
}
}
}
I have tried to highlight the printf part that is printing my buffer1 and buffer2
The output is as follows:
buffer1:83867715933586928386771593358692 buffer2:8386771593358692
buffer1:49216227905963264921622790596326 buffer2:4921622790596326
buffer1:40267236116867294026723611686729 buffer2:4026723611686729
buffer1:82306223673529228230622367352922 buffer2:8230622367352922
buffer1:25869679356114222586967935611422 buffer2:2586967935611422
Can anybody help what I am doing wrong. Please point me the error and what optimization changes could be done in code. I am at learning stage your feedback will be very helpful.
You are complicating the task by reading 16 bytes at a time. If the goal is to indicate the first difference, just read one byte at a time from both files with getc() this way:
int compare_files(FILE *fp1, FILE *fp2) {
unsigned long pos;
int c1, c2;
for (pos = 0;; pos++) {
c1 = getc(fp1);
c2 = getc(fp2);
if (c1 != c2 || c1 == EOF)
break;
}
if (c1 == c2) {
printf("files are identical and have %lu bytes\n", pos);
return 0; // files are identical
} else
if (c1 == EOF) {
printf("file1 is included in file2, the first %lu bytes are identical\n", pos);
return 1;
} else
if (c2 == EOF) {
printf("file2 is included in file1, the first %lu bytes are identical\n", pos);
return 2;
} else {
printf("file1 and file2 differ at position %lu: 0x%02X <> 0x%02X\n", pos, c1, c2);
return 3;
}
}
In terms of efficiency, reading one byte at a time does not pose a problem if the streams are buffered. For large files, you can get better performance by memory mapping the file contents if available on the target system and for the given input streams.
Not an actual answer, but a word on optimisation. You can increase the speed of the program if you have a bigger buffer. Basically the larger the buffer the faster the program runs HOWEVER the speed you gain from just making it larger will increase logarithmically.
Here is a picture of a graph that will help you understand. Also, what i mentioned applies to any simmilar situation. This includes: Copying files, filling the sound buffer etc. Loading the entire file in your RAM first and operationg on it will usually be faster than loading parts of it. Ofc this is not possible with larger files but still this is what you should aim for if you want speed.
PS: I'm writting here because i don't have rep to comment.
EDIT: I came up with solution but since you did not state what you need to do with your buffer3 and buffer4 i packed it up inside a function.
If you are sure that you are only going to use 16 bytes as a buffer size, remove the nBufferSize parameter and replace the buffer dynamic allocation with a static one.
If after the execution you need the buffers, add them as parameters and keep the nBufferSize param. Keep in mind that if you intend to use them outside the function, you should also allocate them outside the function, so things don't get messy.
/** Returns 0 if files are identical, 1 if they are different and -1 if there
is an error. */
int FileCmp(char* szFile1, char* szFile2, int nBufferSize)
{
FILE *f1, *f2;
f1 = fopen(szFile1, "rb");
f2 = fopen(szFile2, "rb");
// Some error checking?
if (f1 == NULL || f2 == NULL)
return -1;
// You can check here for file sizes before you start comparing them.
// ...
// Start the comparrison.
/// Replace this part with static allocation. --------
char* lpBuffer1 = malloc(sizeof(char)*nBufferSize);
if (lpBuffer1 == NULL) // close the files and return error.
{
fclose(f1);
fclose(f2);
return -1;
}
char* lpBuffer2 = malloc(sizeof(char)*nBufferSize);
if (lpBuffer2 == NULL) // close the files, free buffer1 and return error.
{
free(lpBuffer1);
fclose(f1);
fclose(f2);
return -1;
}
/// --------------------------------------------------
while(1)
{
unsigned int uRead1 = fread(lpBuffer1, sizeof(char), nBufferSize, f1);
unsigned int uRead2 = fread(lpBuffer2, sizeof(char), nBufferSize, f2);
if (uRead1 != uRead2)
goto lFilesAreDifferent;
for(unsigned int i = 0; i < uRead1; i++)
if (lpBuffer1[i] != lpBuffer2[i])
goto lFilesAreDifferent;
if ((feof(f1) != 0) && (feof(f2) != 0))
break; // both files have nothing more to read and are identical.
goto lSkip;
lFilesAreDifferent:
free(lpBuffer1);
free(lpBuffer2);
fclose(f1);
fclose(f2);
return 1;
lSkip:;
}
// The files are the same. Close them, free the buffers and return 0.
free(lpBuffer1);
free(lpBuffer2);
fclose(f1);
fclose(f2);
return 0;
}
A simple Demo:
#define BUFFER_SIZE 16
int main(int nArgs, char** szArgs)
{
if (nArgs != 3)
{
printf("Invalid number of arguments.");
return 0;
}
int nResult = FileCmp(szArgs[1], szArgs[2], BUFFER_SIZE);
switch (nResult)
{
case 0: printf("Files [%s] and [%s] are identical.", szArgs[1], szArgs[2]); break;
case 1: printf("Files [%s] and [%s] are different.", szArgs[1], szArgs[2]); break;
case -1: printf("Error."); break;
}
return 0;
}
EDIT II: Personally, i have never used the C standard FILE library (it was either C++ fstream or pure win32 fileapi) so don't take my word here for granted but fread is the fastest function i could find (faster than fgets or fgetc). If you want even faster than this you should get into OS dependant functions (like ReadFile() for Windows).
chqrlie's solution using getc is absolutely the right way to do this. I wanted to address some points brought up in comments, and find it's best to do that with code. In one comment, I recommend pseudo code which could be confusing (namely, you can't write fwrite(file1...) || fwrite(file2 ...) because of the short circuit. But you can implement the idea of that with:
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
/*
* Compare two files, 16 bytes at a time. (Purely to demonstrate memcmp.
* Clearly, this should be implemented with getc.)
*/
FILE * xfopen(const char *, const char *);
size_t xfread(void *, FILE *, const char *);
int
main(int argc, char **argv)
{
FILE *fp[2];
size_t n[2];
char buf[2][16];
unsigned count = 0;
if(argc != 3) { return EXIT_FAILURE; }
fp[0] = xfopen(argv[1], "r");
fp[1] = xfopen(argv[2], "r");
do {
n[0] = xfread(buf[0], fp[0], argv[1]);
n[1] = xfread(buf[1], fp[1], argv[2]);
if( n[0] != n[1] || (n[0] && memcmp(buf[0], buf[1], n[0]))) {
fprintf(stderr, "files differ in block %u\n", count);
return 1;
}
count += 1;
} while(n[0]);
puts("files are identical");
return 0;
}
size_t
xfread(void *b, FILE *fp, const char *name)
{
size_t n = fread(b, 1, 16, fp);
if(n == 0 && ferror(fp)) {
fprintf(stderr, "Error reading %s\n", name);
exit(EXIT_FAILURE);
}
return n;
}
FILE *
xfopen(const char *path, const char *mode)
{
FILE *fp = strcmp(path, "-") ? fopen(path, mode) : stdin;
if( fp == NULL ) {
perror(path);
exit(EXIT_FAILURE);
}
return fp;
}

fgets is returning a blank screen

I am new to C, this is my first project and have been teaching myself. Within my program, one of my functions needs to read a line from a file, and store it in a char array. When I trace the program with gdb the array (line[]) is simply zeros. This leads to my program returning the error "Error: a line in the asset file lacks a ':' separator\n"
Here is my code:
//return the line number (0 based) that the cmd is on, -1 if absent
int locateCmd(char cmd[]) {
int lineIndex = -1; //-1, because lineIndex is incramented before the posible return
char cmdTemp[10] = "\0";
//create a compareable cmd with correct cmd that has its remaining values zeroed out
char cmdCmp[10] = "\0";
memset(cmdCmp, 0, sizeof(cmdCmp));
for (int i = 0; i < strlen(cmd); i++) {
cmdCmp[i] = cmd[i];
}
FILE *file = fopen(ASSET_FILE, "r");
//loop until target line is reached
while (strcmp(cmdTemp, cmdCmp) != 0) {
//check if last line is read
if (lineIndex == lineCounter(file)-1) {
return -1;
}
memset(cmdTemp, 0, sizeof(cmdTemp));
char line[61];
fgets(line, 61, file);
//set cmdTemp to the command on current line
lineIndex++;
for (int i = 0; line[i] != ':'; i++) {
cmdTemp[i] = line[i];
//return error if line doesn't contain a ':'
if (line[i] = '\n') {
printf("Error: a line in the asset file lacks a ':' separator\n");
exit(1);
}
}
}
return lineIndex;
}
Some context, this function is passed a command, and its job is to read a document that appears like this:
command:aBunchOfInfoOnTheComand
anotherCommand:aBunchOfInfoOnTheComand
and pick out the line that the passed command (cmd[]) is stored on.
The issue is with the fgets on line 24. I have separated the relevant portion of this code out into a smaller test program and it works fine.
The test program that works is:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main (int argc, char *argv[]) {
FILE *file = fopen("tutorInfo.txt", "r");
char line[61];
fgets(line, 61, file);
printf("%s\n", line);
}
The proper exicution of my test program leads me to believe other code in my function is causing the issue, but i'm not sure what. It may be important to note, the problematic code has the same imports as my sample program. Any help would be much appreciated.
As OP didn't provide a Minimal, Complete, and Verifiable example, I have to base my answer on the functional description provided in the question.
I already covered some error and corner cases, but I'm sure I missed some. The approach is also inefficient, as the file is read over and over again, instead of parsing it once and returning a hash/map/directory for easy lookup. In real life code I would use something like GLib instead of wasting my time trying to re-invent the wheel(s)...
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define LINE_BUFFER_LENGTH 200
unsigned int locateCmd(FILE *fh, const char *key, const char **cmd_line) {
unsigned int found = 0;
size_t key_length = strlen(key);
*cmd_line = NULL;
/* make sure to start read from start of file */
rewind(fh);
unsigned int line_no = 0;
static char buffer[LINE_BUFFER_LENGTH];
while (!feof(fh) && (found == 0)) {
// NOTE: EOF condition will be checked on the next iteration
fgets(buffer, sizeof(buffer), fh);
size_t length = strlen(buffer);
line_no++;
if (buffer[length - 1] != '\n') {
printf("line %u is too long, aborting!\n", line_no);
return(0);
}
if ((strncmp(key, buffer, key_length) == 0) &&
(buffer[key_length] == ':')) {
found = line_no;
buffer[length - 1] = '\0'; // strip line ending
*cmd_line = &buffer[key_length + 1];
}
}
return(found);
}
int main(int argc, char *argv[]) {
FILE *fh = fopen("dummy.txt", "r");
if (!fh) {
perror("file open");
return(1);
}
int ret = 0;
while (--argc > 0) {
const char *cmd;
const char *key = *++argv;
unsigned line_no = locateCmd(fh, key, &cmd);
if (line_no != 0) {
printf("key '%s' found on line %u: %s\n", key, line_no, cmd);
ret = 0;
} else {
printf("key '%s' not found!\n", key);
};
}
if (fclose(fh) != 0) {
perror("file close");
return(1);
}
return(ret);
}
Test input dummy.txt:
command:aBunchOfInfoOnTheComand
anotherCommand:aBunchOfInfoOnTheComand
brokenline
foo:bar
toolong:sadflkjaLKFJASDJFLKASJDFLKSAJ DLFKJ SLDKJFLKASDFASDFKJASKLDJFLKASJDFLKJASDLKFJASLKDFJLKASDJFLKASJDLFKJASDKLFJKLASDJFLKSAJDFLKJASDLKFJKLASDJFLKASJDFKLJASDLKFJLKASDJFLKASJDFLKJSADLKFJASLKDJFLKC
Some test runs:
$ gcc -Wall -o dummy dummy.c
$ ./dummy command foo bar
key 'command' found on line 1: aBunchOfInfoOnTheComand
key 'foo' found on line 5: bar
line 6 is too long, aborting!
key 'bar' not found!

C project with files

I need some help with my C project:
I need to write a c program who receives 2 parameters:
1) The name of a text file(infile) which is in the same catalog
2) A number k>0
And creates 2 new files,outfile1 & outfile 2 as:
Outfile 1: k,2*k,3*k…. character of infile
Outfile 2: k,2*k,3*k…..line of infile
Example:
INFILE
Abcdefg
123456
XXXXXX
01010101
OUTFILE 1:
Cf25XX101
OUTFILE 2:
XXXXXX
I wrote some code ,but its not working. Any ideas?
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
char** read_lines(FILE* txt, int* count) {
char** array = NULL;
int i;
char line[100];
int line_count;
int line_length;
*count = 0;
line_count = 0;
while (fgets(line, sizeof(line), txt) != NULL) {
line_count++;
}
rewind(txt);
array = malloc(line_count * sizeof(char *));
if (array == NULL) {
return NULL;
}
for (i = 0; i < line_count; i++) {
fgets(line, sizeof(line), txt);
line_length = strlen(line);
line[line_length - 1] = '\0';
line_length--;
array[i] = malloc(line_length + 1);
strcpy(array[i], line);
}
*count = line_count;
return array;
}
int main(int argc, char * argv[]) {
char** array = NULL;
FILE* file = NULL;
const char* filename = NULL;
int i;
int line_count;
int k;
char c;
printf("ENTER ONE PHYSICAL NUMBER\n");
do{
if(k>0)
scanf("%d",&k);
else{
printf("ENTER ONE PHYSICAL NUMBER\n");
scanf("%d",&k);
}
}while(k<=0);
file = fopen("LEIT.txt", "rt");
if (file == NULL) {
printf("CANT OPEN FILE %s.\n", filename);
return 1;
}
array = read_lines(file, &line_count);
printf("ARRAY:\n");
for (i = 0; i < line_count; i++) {
printf("[%d]: %s\n", (i+1), array[i]);
}
printf("CALCULATING OUTFILE1 AND OUTFILE2\n");
printf("OUTFILE1:\n");
for(i=0;i<line_count;i++){
c=i*k;
printf("%c\n",array[c]);
}
printf("WRITING OUTFILE1 COMPLETE!\n");
printf("OUTFILE2:\n");
for(i=0;i<line_count;i++){
c=i*k;
printf("%c\n",array[c]);
}
printf("WRITING OUTFILE2 COMPLETE!\n");
return 0;
}
My actual problem is calculate and write into files (outfile1 and outfile2) the result...
You need to close file after finishing reading/writing it with fclose.
You can create and write strings to a file using fopen with correct mode.
You can output formatted string to a file by using fprintf.
It seems that you don't want to print the 0th character/line, so in the last for loop, i should start from 1 (or start from 0 but add 1 later).
array[c] is a string, not a character. So when printing it, you should use %s specifier instead of %c.
It is not a good idea using char as count in later for loops unless you know input file will be very short. signed char can only count to 127 before overflow (unsigned char can count to 255). But if you have a very long file, for example thousands of lines, this program would not work properly.
array is malloced in function char** read_lines(FILE* txt, int* count). After finish using it, you need to dealloc, or free it by calling
for (i = 0; i < line_count; i++) {
free(array[i]);
}
and followed by free(array). This avoids memory leakage.
Modified code is here. In the following code, char c is not used. This is the part where you process output files, and before return 0; in main function.
printf("CALCULATING OUTFILE1 AND OUTFILE2\n");
printf("OUTFILE1:\n");
// Since we finished using LEIT.txt, close it here.
fclose(file);
// Mode: "w" - Write file. "+" - Create if not exist.
// You can lso use "a+" (append file) here if previous record need to be preserved.
FILE *out1 = fopen("OUTFILE1.txt", "w+");
FILE *out2 = fopen("OUTFILE2.txt", "w+");
if ((out1 == NULL) || (out2 == NULL)) {
printf("CANT CREATE OUTPUT FILES.\n");
return 1;
}
// Out file 1.
unsigned int count = k;
for (i = 0; i < line_count; i++){
while (count < strlen(array[i])) {
// This just prints to stdout, but is good for debug.
printf("%c", array[i][count]);
// Write to the file.
fprintf(out1, "%c", array[i][count]);
// Calculate c for next char.
count += k + 1;
}
// Before go to next line, minus string length of current line.
count -= strlen(array[i]);
}
printf("\n");
printf("WRITING OUTFILE1 COMPLETE!\n");
// Close file.
fclose(out1);
// Out file 2.
printf("OUTFILE2:\n");
for (i = 1;i < line_count / k; i++){
count = i * k;
// This just prints to stdout, but is good for debug.
printf("%s\n", array[count]);
// Write to the file.
fprintf(out2, "%s\n", array[count]);
}
printf("WRITING OUTFILE2 COMPLETE!\n");
//Close file.
fclose(out2);
// dealloc malloced memory.
for (i = 0; i < line_count; i++) {
free(array[i]);
}
free(array);

Compare each line from two different files and print the lines that are different in C

Supposing that I have two files like this:
file1.txt
john
is
the new
guy
file2.txt
man
the old
is
rick
cat
dog
I'd like to compare first line from file1 with all the lines from file2 and verify if it exist. If not, go two the second line from file1 and compare it with all the lines from file2.. and so on until eof is reached by file1.
The output that I expect is:
john
the new
guy
How I thought this should be done:
read file1 and file2
create a function which returns the line number of each of them
take the first line from file1 and compare it to all the lines from file2
do this until all the lines from file1 are wasted
Now, I don't know what I'm doing wrong, but I don't get the result that I expect:
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
int countlines(char *filename)
{
int ch = 0, lines = 0;
FILE *fp = fopen(filename, "r");
if (fp == NULL)
return 0;
do {
ch = fgetc(fp);
if (ch == '\n')
lines++;
} while (ch != EOF);
if (ch != '\n' && lines != 0)
lines++;
fclose(fp);
return lines;
}
int main(int argc, char *argv[])
{
FILE *template_file = fopen(argv[1], "r");
FILE *data_file = fopen(argv[2], "r");
char buffer_line_template_file[100];
char buffer_line_data_file[100];
if (argc != 3)
{
perror("You didn't insert all the arguments!\n\n");
exit(EXIT_FAILURE);
}
if (template_file == NULL || data_file == NULL)
{
perror("Error while opening the file!\n\n");
exit(EXIT_FAILURE);
}
int counter = 0;
for (int i = 0; i < countlines(argv[1]); i++)
{
fgets(buffer_line_template_file, 100, template_file);
for (int j = 0; j < countlines(argv[2]); j++)
{
fgets(buffer_line_data_file, 100, data_file);
if (strcmp(buffer_line_template_file, buffer_line_data_file) != 0)
{
counter++;
printf("%d", counter);
}
}
}
printf("\n\n");
return 0;
}
Could someone please point me into the right direction ? For testing purposes I created a counter at the end which was a part of a small debug. There should be the print() function
As per #chux answer I got the following simplified code:
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
int main(int argc, char *argv[])
{
FILE *template_file = fopen(argv[1], "r");
FILE *data_file = fopen(argv[2], "r");
char buffer_line_template_file[100];
char buffer_line_data_file[100];
if (argc != 3)
{
perror("You didn't insert all the arguments!\n\n");
exit(EXIT_FAILURE);
}
if (template_file == NULL || data_file == NULL)
{
perror("Error while opening the file!\n\n");
exit(EXIT_FAILURE);
}
while(fgets(buffer_line_template_file, 100, template_file))
{
buffer_line_template_file[strcspn(buffer_line_template_file, "\n")] = '\0';
rewind(data_file);
while (fgets(buffer_line_data_file, 100, data_file))
{
buffer_line_data_file[strcspn(buffer_line_data_file, "\n")] = '\0';
if (strcmp(buffer_line_template_file, buffer_line_data_file) != 0)
{
printf("%s\n", buffer_line_template_file);
}
}
}
printf("\n\n");
return 0;
}
The above code is giving me the following output, which is not what is expected:
john
john
john
john
john
john
is
is
is
is
is
the new
the new
the new
the new
the new
the new
guy
guy
guy
guy
guy
guy
Problems with OP's code
Imprecise definition of line.
Excessive recalculation
Fuzzy determination of the number of lines in a file.
Unlike string, which has a precise definition in C, reading a line is not so well defined. The primary specificity issue: does a line contain the trailing '\n'. If the first answer is Yes, then does the last text in a file after a '\n' constitute a line? (Excessively long lines are another issue, but let us not deal with that today.)
Thus possibly some lines end with '\n' and others do not, fooling strcmp("dog", "dog\n").
The easiest solution is to read a line until either 1) a '\n' is encountered, 2) EOF occurs or 3) line buffer is full. Then after getting a line, lop off the potential trailing '\n'.
Now all lines code subsequently works with have no '\n'.
fgets(buffer_line_template_file, 100, template_file);
buffer_line_template_file[strcspn(buffer_line_template_file, "\n")] = '\0';
OP's loop is incredible wasteful. Consider a file with 1000 lines. Code will loop, calling 1000 times countlines() (each countlines() call reads 1000 lines) times when one countlines() call would suffice.
// for (int j = 0; j < countlines(argv[2]); j++)
int j_limit = countlines(argv[2]);
for (int j = 0; j < j_limit; j++)
There really is no need to count the line anyways, just continue until EOF (fgets() returns NULL). So no need to fix its fuzzy definition. (fuzzy-ness concerns same issues as #1)
int counter = 0;
for (fgets(buffer_line_template_file, 100, template_file)) {
buffer_line_template_file[strcspn(buffer_line_template_file, "\n")] = '\0';
rewind(data_file);
while ((fgets(buffer_line_data_file, 100, data_file)) {
buffer_line_data_file[strcspn(buffer_line_data_file, "\n")] = '\0';
if (strcmp(buffer_line_template_file, buffer_line_data_file) != 0) {
counter++;
printf("%d", counter);
}
}
}
Other simplifications possible - for another day.
FWIW, following counts lines of text allowing the last line in the file to optionally end with a '\n'.
unsigned long long FileLineCount(FILE *istream) {
unsigned long long LineCount = 0;
rewind(istream);
int previous = '\n';
int ch;
while ((ch = fgetc(inf)) != EOF) {
if (previous == '\n') LineCount++;
previous = ch;
}
return LineCount;
}
Note that this function may get a different result that fgets() calls. Consider a file of one line of 150 characters. fgets(..., 100,...) will report 2 lines. FileLineCount() reports 1.
[Edit] Updated code to conform to OP functionality.
int found = 0;
while (fgets(buffer_line_data_file, 100, data_file))
{
buffer_line_data_file[strcspn(buffer_line_data_file, "\n")] = '\0';
if (strcmp(buffer_line_template_file, buffer_line_data_file) == 0)
{
found = 1;
break;
}
}
if (!found) printf("%s\n", buffer_line_template_file);
This program prints the diff of two files file1.txt and file2.txt.
#include<stdio.h>
#include <stdlib.h>
#include <memory.h>
int main() {
FILE *fp1, *fp2;
int ch1, ch2;
char fname1[40], fname2[40];
char *line = NULL;
size_t len = 0;
ssize_t read;
char *line2 = NULL;
size_t len2 = 0;
ssize_t read2;
fp1 = fopen("file1.txt", "r");
fp2 = fopen("file2.txt", "r");
if (fp1 == NULL) {
printf("Cannot open %s for reading ", fname1);
exit(1);
} else if (fp2 == NULL) {
printf("Cannot open %s for reading ", fname2);
exit(1);
} else {
while ((read = getline(&line, &len, fp1)) != -1 && (read2 = getline(&line2, &len2, fp2)) != -1) {
if (!strcmp(line, line2)) {
printf("Retrieved diff on line %zu :\n", read);
printf("%s", line);
}
}
if (ch1 == ch2)
printf("Files are identical \n");
else if (ch1 != ch2)
printf("Files are Not identical \n");
fclose(fp1);
fclose(fp2);
}
return (0);
}
You already have a very good answer (and always will from chux), but here is a slightly different approach to the problem. It uses automatic storage to reading file2 into an array of strings and then compares each line in file1 against every line in file2 to determine whether it is unique. You can easily convert the code to dynamically allocate memory, but for sake of complexity that was omitted:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
enum { MAXC = 256, MAXL = 512 };
void file1infile2 (FILE *fp2, FILE *fp1, size_t *n2, size_t *n1);
int main (int argc, char **argv) {
FILE *fp1 = fopen (argc > 1 ? argv[1] : "file1.txt", "r");
FILE *fp2 = fopen (argc > 2 ? argv[2] : "file2.txt", "r");
size_t n1 = 0, n2 = 0;
if (!fp1 || !fp2) {
fprintf (stderr, "error: file open failed.\n");
return 1;
}
printf ("\nunique words in file1, not in file 2.\n\n");
file1infile2 (fp2, fp1, &n2, &n1);
printf ("\nanalyzed %zu lines in file1 against %zu lines in file2.\n\n",
n1, n2);
return 0;
}
void file1infile2 (FILE *fp2, FILE *fp1, size_t *n2, size_t *n1)
{
char buf[MAXC] = "";
char f2buf[MAXL][MAXC] = { "" };
size_t i;
*n1 = *n2 = 0;
while (*n2 < MAXL && fgets (buf, MAXC, fp2)) {
char *np = 0;
if (!(np = strchr (buf, '\n'))) {
fprintf (stderr, "error: line exceeds MAXC chars.\n");
exit (EXIT_FAILURE);
}
*np = 0;
strcpy (f2buf[(*n2)++], buf);
}
while (*n1 < MAXL && fgets (buf, MAXC, fp1)) {
char *np = 0;
if (!(np = strchr (buf, '\n'))) {
fprintf (stderr, "error: line exceeds MAXC chars.\n");
exit (EXIT_FAILURE);
}
*np = 0, (*n1)++;
for (i = 0; i < *n2; i++)
if (!(strcmp (f2buf[i], buf)))
goto matched;
printf (" %s\n", buf);
matched:;
}
}
Look over the code and let me know if you have any questions.
Example Use/Output
$ ./bin/f1inf2 dat/f1 dat/f2
unique words in file1, not in file 2.
john
the new
guy
analyzed 4 lines in file1 against 6 lines in file2.

How do I find a string in a file?

I'm new at C and recently finished my work with files. I tried to create a program which will find an entered name in a file but it does not work. Could you try to repair it? I'll be thankful.
#include <stdio.h>
#include <string.h>
int main()
{
FILE *fr;
int i,p,counter,final,length,j,c,k = 0;
char name[256];
char buffer[1024];
fr = fopen("C:/Users/prixi/Desktop/HESLA.TXT","r");
while ((c = fgetc(fr)) != EOF)
counter++;
printf("Enter the name");
scanf("%s",&name);
length = strlen(name);
while (fscanf(fr, " %1023[^\n]", buffer) != EOF) {
for (i = 0; i <= counter; i++)
if (name[0] == buffer[i]){
for (j = 0;j < length; j++ )
if (name[j] == buffer[i+j])
p++;
else
p = 0;
/* The 2nd condition is there because after every name there is ' '. */
if (p == length && buffer[i+j+1] == ' ')
final = 1;
}
}
if ( final == 1 )
printf("its there");
else
printf("its not there");
return 0;
}
It loads the inside of the file to the buffer and then scans char by char depending on how long the file is. I know that it's inefficient and slow, but I have been learning C only for like 4 days. I would really like you to help me fixing my own code otherwise :D I probably wont be able to fall asleep.
There are a lot of way to search a string into a File.
Try this:
#include<stdio.h>
#include<string.h>
#include<stdlib.h>
char *loadFile(const char *fileName);
int main (void) {
const char *fileName = "test.txt";
const char *stringToSearch = "Addams";
char *fileContent = loadFile(fileName);
if (strstr(fileContent, stringToSearch)){
printf("%s was Found\n",stringToSearch);
}else{
printf("%s was not Found\n",stringToSearch);
}
free(fileContent);
return 0;
}
char *loadFile(const char *fileName){
size_t length,size;
char *buffer;
FILE *file;
file = fopen (fileName , "r" );
if (file == NULL){
printf("Error fopen, please check the file\t%s\n",fileName);
exit(EXIT_FAILURE);
}
fseek (file , 0 , SEEK_END);
length = (size_t)ftell (file);
fseek (file , 0 , SEEK_SET);
buffer = malloc(length+1);
if (buffer == NULL){
fputs ("Memory error",stderr);
exit (2);
}
size = fread (buffer,1,length,file);
if (size != length){
fputs ("Reading error",stderr);
exit(3);
}
buffer[length] = '\0';
fclose (file);
return buffer;
}
Output:
Addams was Found
I have inside the file "test.txt" the following:
Michael Jackson
Bryan Addams
Jack Sparrow
There are multiple problems with your code. You did not post the variable definitions, so we cannot verify if they are used consistently, especially name that should be an array of char.
The main issue is this: you count the number of bytes in fr by reading it, but you do not rewind the stream before scanning it for instances of the string.

Resources