Related
I want to pipe a string to a program that read input only from file, but not from stdin. Using it from bash, i can do something like
echo "hi" | program /dev/stdin
and I wanted to replicate this behaviour from C code. What I did is this
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/wait.h>
#include <string.h>
int main() {
pid_t pid;
int rv;
int to_ext_program_pipe[2];
int to_my_program_pipe[2];
if(pipe(to_ext_program_pipe)) {
fprintf(stderr,"Pipe error!\n");
exit(1);
}
if(pipe(to_my_program_pipe)) {
fprintf(stderr,"Pipe error!\n");
exit(1);
}
if( (pid=fork()) == -1) {
fprintf(stderr,"Fork error. Exiting.\n");
exit(1);
}
if(pid) {
close(to_my_program_pipe[1]);
close(to_ext_program_pipe[0]);
char string_to_write[] = "this is the string to write";
write(to_ext_program_pipe[1], string_to_write, strlen(string_to_write) + 1);
close(to_ext_program_pipe[1]);
wait(&rv);
if(rv != 0) {
fprintf(stderr, "%s %d\n", "phantomjs exit status ", rv);
exit(1);
}
char *string_to_read;
char ch[1];
size_t len = 0;
string_to_read = malloc(sizeof(char));
if(!string_to_read) {
fprintf(stderr, "%s\n", "Error while allocating memory");
exit(1);
}
while(read(to_my_program_pipe[0], ch, 1) == 1) {
string_to_read[len]=ch[0];
len++;
string_to_read = realloc(string_to_read, len*sizeof(char));
if(!string_to_read) {
fprintf(stderr, "%s\n", "Error while allocating memory");
}
string_to_read[len] = '\0';
}
close(to_my_program_pipe[0]);
printf("Output: %s\n", string_to_read);
free(string_to_read);
} else {
close(to_ext_program_pipe[1]);
close(to_my_program_pipe[0]);
dup2(to_ext_program_pipe[0],0);
dup2(to_my_program_pipe[1],1);
if(execlp("ext_program", "ext_program", "/dev/stdin" , NULL) == -1) {
fprintf(stderr,"execlp Error!");
exit(1);
}
close(to_ext_program_pipe[0]);
close(to_my_program_pipe[1]);
}
return 0;
}
It is not working.
EDIT
I don't get the ext_program output, that should be saved in string_to_read. The program just hangs. I can see that ext_program is executed, but I don't get anything
I would like to know if there is an error, or if what I want cannot be done. Also I know that the alternative is to use named pipes.
EDIT 2: more details
As I still can not get my program working, I post the complete code
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/wait.h>
int main() {
pid_t pid;
int rv;
int to_phantomjs_pipe[2];
int to_my_program_pipe[2];
if(pipe(to_phantomjs_pipe)) {
fprintf(stderr,"Pipe error!\n");
exit(1);
}
if(pipe(to_my_program_pipe)) {
fprintf(stderr,"Pipe error!\n");
exit(1);
}
if( (pid=fork()) == -1) {
fprintf(stderr,"Fork error. Exiting.\n");
exit(1);
}
if(pid) {
close(to_my_program_pipe[1]);
close(to_phantomjs_pipe[0]);
char jsToExectue[] = "var page=require(\'webpage\').create();page.onInitialized=function(){page.evaluate(function(){delete window._phantom;delete window.callPhantom;});};page.onResourceRequested=function(requestData,request){if((/http:\\/\\/.+\?\\\\.css/gi).test(requestData[\'url\'])||requestData.headers[\'Content-Type\']==\'text/css\'){request.abort();}};page.settings.loadImage=false;page.settings.userAgent=\'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36\';page.open(\'https://stackoverflow.com\',function(status){if(status!==\'success\'){phantom.exit(1);}else{console.log(page.content);phantom.exit();}});";
write(to_phantomjs_pipe[1], jsToExectue, strlen(jsToExectue) + 1);
close(to_phantomjs_pipe[1]);
int read_chars;
int BUFF=1024;
char *str;
char ch[BUFF];
size_t len = 0;
str = malloc(sizeof(char));
if(!str) {
fprintf(stderr, "%s\n", "Error while allocating memory");
exit(1);
}
str[0] = '\0';
while( (read_chars = read(to_my_program_pipe[0], ch, BUFF)) > 0)
{
len += read_chars;
str = realloc(str, (len + 1)*sizeof(char));
if(!str) {
fprintf(stderr, "%s\n", "Error while allocating memory");
}
strcat(str, ch);
str[len] = '\0';
memset(ch, '\0', BUFF*sizeof(ch[0]));
}
close(to_my_program_pipe[0]);
printf("%s\n", str);
free(str);
wait(&rv);
if(rv != 0) {
fprintf(stderr, "%s %d\n", "phantomjs exit status ", rv);
exit(1);
}
} else {
dup2(to_phantomjs_pipe[0],0);
dup2(to_my_program_pipe[1],1);
close(to_phantomjs_pipe[1]);
close(to_my_program_pipe[0]);
close(to_phantomjs_pipe[0]);
close(to_my_program_pipe[1]);
execlp("phantomjs", "phantomjs", "--ssl-protocol=TLSv1", "/dev/stdin" , (char *)NULL);
}
return 0;
}
What I am trying to do is to pass to phantomjs a script to execute through pipe and then read the resulting HTML as a string. I modified the code as told, but phantomjs still does not read from stdin.
I tested the script string by creating a dumb program that writes it to a file and then executed phantomjs normally and that works.
I also tryed to execute execlp("phantomjs", "phantomjs", "--ssl-protocol=TLSv1", "path_to_script_file" , (char *)NULL); and that works too, the output HTML is showed.
It does not work when using pipe.
An Explanation At Last
Some experimentation with PhantomJS shows that the problem is writing a null byte at the end of the JavaScript program sent to PhantomJS.
This highlights two bugs:
The program in the question sends an unnecessary null byte.
PhantomJS 2.1.1 (on a Mac running macOS High Sierra 10.13.3) hangs when an otherwise valid program is followed by a null byte
The code in the question contains:
write(to_phantomjs_pipe[1], jsToExectue, strlen(jsToExectue) + 1);
The + 1 means that the null byte terminating the string is also written to phantomjs. And writing that null byte causes phantomjs to hang. That is tantamount to a bug — it certainly isn't clear why PhantomJS hangs without detecting EOF (there is no more data to come), and without giving an error, etc.
Change that line to:
write(to_phantomjs_pipe[1], jsToExectue, strlen(jsToExectue));
and the code works as expected — at least with PhantomJS 2.1.1 on a Mac running macOS High Sierra 10.13.3.
Initial analysis
You aren't closing enough file descriptors in the child.
Rule of thumb: If you
dup2()
one end of a pipe to standard input or standard output, close both of the
original file descriptors returned by
pipe()
as soon as possible.
In particular, you should close them before using any of the
exec*()
family of functions.
The rule also applies if you duplicate the descriptors with either
dup()
or
fcntl()
with F_DUPFD
The child code shown is:
} else {
close(to_ext_program_pipe[1]);
close(to_my_program_pipe[0]);
dup2(to_ext_program_pipe[0],0);
dup2(to_my_program_pipe[1],1);
if(execlp("ext_program", "ext_program", "/dev/stdin" , NULL) == -1) {
fprintf(stderr,"execlp Error!");
exit(1);
}
close(to_ext_program_pipe[0]);
close(to_my_program_pipe[1]);
}
The last two close() statements are never executed; they need to appear before the execlp().
What you need is:
} else {
dup2(to_ext_program_pipe[0], 0);
dup2(to_my_program_pipe[1], 1);
close(to_ext_program_pipe[0]);
close(to_ext_program_pipe[1]);
close(to_my_program_pipe[0]);
close(to_my_program_pipe[1]);
execlp("ext_program", "ext_program", "/dev/stdin" , NULL);
fprintf(stderr, "execlp Error!\n");
exit(1);
}
You can resequence it splitting the close() calls, but it is probably better to regroup them as shown.
Note that there is no need to test whether execlp() failed. If it returns, it failed. If it succeeds, it does not return.
There could be another problem. The parent process waits for the child to exit before reading anything from the child. However, if the child tries to write more data than will fit in the pipe, the process will hang, waiting for some process (which will have to be the parent) to read the pipe. Since they're both waiting for the other to do something before they will do what the other is waiting for, it is (or, at least, could be) a deadlock.
You should also revise the parent process to do the reading before the waiting.
if (pid) {
close(to_my_program_pipe[1]);
close(to_ext_program_pipe[0]);
char string_to_write[] = "this is the string to write";
write(to_ext_program_pipe[1], string_to_write, strlen(string_to_write) + 1);
close(to_ext_program_pipe[1]);
char *string_to_read;
char ch[1];
size_t len = 0;
string_to_read = malloc(sizeof(char));
if(!string_to_read) {
fprintf(stderr, "%s\n", "Error while allocating memory");
exit(1);
}
while (read(to_my_program_pipe[0], ch, 1) == 1) {
string_to_read[len] = ch[0];
len++;
string_to_read = realloc(string_to_read, len*sizeof(char));
if (!string_to_read) {
fprintf(stderr, "%s\n", "Error while allocating memory\n");
exit(1);
}
string_to_read[len] = '\0';
}
close(to_my_program_pipe[0]);
printf("Output: %s\n", string_to_read);
free(string_to_read);
wait(&rv);
if (rv != 0) {
fprintf(stderr, "%s %d\n", "phantomjs exit status ", rv);
exit(1);
}
} …
I'd also rewrite the code to read in big chunks (1024 bytes or more). Just don't copy more data than the read returns, that's all. Repeatedly using realloc() to allocate one more byte to the buffer is ultimately excruciatingly slow. It won't matter much if there's only a few bytes of data; it will matter if there are kilobytes or more data to process.
Later: Since the PhantomJS program generates over 90 KiB of data in response to the message it was sent, this was a factor in the problems — or would have been were it not for the hang-on-null-byte bug in PhantomJS.
Still having problems 2018-02-03
I extracted the code, as amended, into a program (pipe89.c, compiled to pipe89). I got inconsistent crashes when the space allocated changed. I eventually realized that you're reallocating one byte too little space — it took a lot longer than it should have done (but it would help if Valgrind was available for macOS High Sierra — it isn't yet).
Here's the fixed code with debugging information commented output:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/wait.h>
#include <unistd.h>
int main(void)
{
pid_t pid;
int rv;
int to_ext_program_pipe[2];
int to_my_program_pipe[2];
if (pipe(to_ext_program_pipe))
{
fprintf(stderr, "Pipe error!\n");
exit(1);
}
if (pipe(to_my_program_pipe))
{
fprintf(stderr, "Pipe error!\n");
exit(1);
}
if ((pid = fork()) == -1)
{
fprintf(stderr, "Fork error. Exiting.\n");
exit(1);
}
if (pid)
{
close(to_my_program_pipe[1]);
close(to_ext_program_pipe[0]);
char string_to_write[] = "this is the string to write";
write(to_ext_program_pipe[1], string_to_write, sizeof(string_to_write) - 1);
close(to_ext_program_pipe[1]);
char ch[1];
size_t len = 0;
char *string_to_read = malloc(sizeof(char));
if (string_to_read == 0)
{
fprintf(stderr, "%s\n", "Error while allocating memory");
exit(1);
}
string_to_read[len] = '\0';
while (read(to_my_program_pipe[0], ch, 1) == 1)
{
//fprintf(stderr, "%3zu: got %3d [%c]\n", len, ch[0], ch[0]); fflush(stderr);
string_to_read[len++] = ch[0];
char *new_space = realloc(string_to_read, len + 1); // KEY CHANGE is " + 1"
//if (new_space != string_to_read)
// fprintf(stderr, "Move: len %zu old %p vs new %p\n", len, (void *)string_to_read, (void *)new_space);
if (new_space == 0)
{
fprintf(stderr, "Error while allocating %zu bytes memory\n", len);
exit(1);
}
string_to_read = new_space;
string_to_read[len] = '\0';
}
close(to_my_program_pipe[0]);
printf("Output: %zu (%zu) [%s]\n", len, strlen(string_to_read), string_to_read);
free(string_to_read);
wait(&rv);
if (rv != 0)
{
fprintf(stderr, "%s %d\n", "phantomjs exit status ", rv);
exit(1);
}
}
else
{
dup2(to_ext_program_pipe[0], 0);
dup2(to_my_program_pipe[1], 1);
close(to_ext_program_pipe[0]);
close(to_ext_program_pipe[1]);
close(to_my_program_pipe[0]);
close(to_my_program_pipe[1]);
execlp("ext_program", "ext_program", "/dev/stdin", NULL);
fprintf(stderr, "execlp Error!\n");
exit(1);
}
return 0;
}
It was tested on a program which wrote 5590 byte out for 27 bytes of input. That isn't as massive a multiplier as in your program, but it proves a point.
I still think you'd do better not reallocating a single extra byte at a time — the scanning loop should use a buffer of, say, 1 KiB and read up to 1 KiB at a time, and allocate the extra space all at once. That's a much less intensive workout for the memory allocation system.
Problems continuing on 2018-02-05
Taking the code from the Edit 2 and changing only the function definition from int main() { to int main(void) { (because the compilation options I use don't allow old-style non-prototype function declarations or definitions, and without the void, that is not a prototype), the code is
working fine for me. I created a surrogate phantomjs program (from another I already have lying around), like this:
#include <stdio.h>
int main(int argc, char **argv, char **envp)
{
for (int i = 0; i < argc; i++)
printf("argv[%d] = <<%s>>\n", i, argv[i]);
for (int i = 0; envp[i] != 0; i++)
printf("envp[%d] = <<%s>>\n", i, envp[i]);
FILE *fp = fopen(argv[argc - 1], "r");
if (fp != 0)
{
int c;
while ((c = getc(fp)) != EOF)
putchar(c);
fclose(fp);
}
else
fprintf(stderr, "%s: failed to open file %s for reading\n",
argv[0], argv[argc-1]);
return(0);
}
This code echoes the argument list, the environment, and then opens the file named as the last argument and copies that to standard output. (It is highly specialized because of the special treatment for argv[argc-1], but the code before that is occasionally useful for debugging complex shell scripts.)
When I run your program with this 'phantomjs', I get the output I'd expect:
argv[0] = <<phantomjs>>
argv[1] = <<--ssl-protocol=TLSv1>>
argv[2] = <</dev/stdin>>
envp[0] = <<MANPATH=/Users/jleffler/man:/Users/jleffler/share/man:/Users/jleffler/oss/share/man:/Users/jleffler/oss/rcs/man:/usr/local/mysql/man:/opt/gcc/v7.3.0/share/man:/Users/jleffler/perl/v5.24.0/man:/usr/local/man:/usr/local/share/man:/usr/share/man:/opt/gnu/share/man>>
envp[1] = <<IXH=/opt/informix/12.10.FC6/etc/sqlhosts>>
…
envp[49] = <<HISTFILE=/Users/jleffler/.bash.jleffler>>
envp[50] = <<_=./pipe31>>
var page=require('webpage').create();page.onInitialized=function(){page.evaluate(function(){delete window._phantom;delete window.callPhantom;});};page.onResourceRequested=function(requestData,request){if((/http:\/\/.+?\\.css/gi).test(requestData['url'])||requestData.headers['Content-Type']=='text/css'){request.abort();}};page.settings.loadImage=false;page.settings.userAgent='Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36';page.open('https://stackoverflow.com',function(status){if(status!=='success'){phantom.exit(1);}else{console.log(page.content);phantom.exit();}});
At this point, I have to point the finger at phantomjs in your environment; it doesn't seem to behave as expected when you do the equivalent of:
echo "$JS_PROG" | phantomjs /dev/stdin | cat
Certainly, I cannot reproduce your problem any more.
You should take my surrogate phantomjs code and use that instead of the real phantomjs and see what you get.
If you get output analogous to what I showed, then the problem is with the real phantomjs.
If you don't get output analogous to what I showed, then maybe there is a problem with your code from the update to the question.
Later: Note that because the printf() uses %s to print the data, it would not notice the extraneous null byte being sent to the child.
In the pipe(7) man it is written that you should read from pipe ASAP:
If a process attempts to write to a
full pipe (see below), then write(2) blocks until sufficient data has
been read from the pipe to allow the write to complete. Nonblocking
I/O is possible by using the fcntl(2) F_SETFL operation to enable the
O_NONBLOCK open file status flag.
and
A pipe has a limited capacity. If the pipe is full, then a write(2)
will block or fail, depending on whether the O_NONBLOCK flag is set
(see below). Different implementations have different limits for the
pipe capacity. Applications should not rely on a particular
capacity: an application should be designed so that a reading process
consumes data as soon as it is available, so that a writing process
does not remain blocked.
In your code you write, wait and only then read
write(to_ext_program_pipe[1], string_to_write, strlen(string_to_write) + 1);
close(to_ext_program_pipe[1]);
wait(&rv);
//...
while(read(to_my_program_pipe[0], ch, 1) == 1) {
//...
Maybe the pipe is full or ext_program is waiting for the data to be read, you should wait() only after the read.
In the following code, I need a unique filename, do some stuff with it, and let it be. It is about converting a .class file to binary, let us call it compilation.
It works perfectly when run in isolation or done 3 times at a time; however, I run into issues when I start up many multiple processes (e.g., 7) where one or more of my compilations fail.
This is the code:
#include <stdio.h>
#include <errno.h>
#include <stdlib.h>
#include <string.h>
static unsigned int numFiles = 0;
static unsigned long numBytes = 0;
FILE* rawf;
char* raw_file_name_end = ".raw_ujc";
char * rawfilename;
static void byte(unsigned char v){
if(numBytes) printf(", ");
printf((numBytes & 0x0F) ? "0x%02X" : "\n\t0x%02X", v);
fwrite(&v,sizeof(v),1,rawf);
numBytes++;
}
int main(int argc, char** argv){
const char* self = argv[0];
int c;
const char* classCvt = 0;
long len;
if(argc == 1){
fprintf(stderr, "USAGE: %s [-c <path_to_classCvt>] <file 1> [<file 2> [ <file 3> [...]]] > result.c\n", self);
return -1;
}
argv++;
argc--;
if(argv[0][0] == '-' && argv[0][1] == 'c' && !argv[0][2]){
classCvt = argv[1];
argv += 2;
argc -= 2;
}
printf("\nService optimized bytecode = {\n\t");
while(argc--){
char* filename = *argv;
rawfilename = malloc(sizeof(char) * (strlen(filename)-strlen(".class")) + sizeof(char) * strlen(raw_file_name_end)+1);
strncpy(rawfilename,filename,(strlen(filename)-strlen(".class")));
strcat(rawfilename,raw_file_name_end);
fprintf(stderr, "rawfilename after alloc: %s \n", rawfilename);
if(classCvt){
char* t;
filename = tempnam(NULL, NULL);
if(!filename){
fprintf(stderr, "%s: failed to create a tempfile: %d\n", self, errno);
return -10;
}
t = malloc(strlen(filename) + strlen(classCvt) + strlen(*argv) + 32);
if(!t){
fprintf(stderr, "%s: failed to alloc a small string. This is unlikely\n", self);
free(t);
return -11;
}
sprintf(t, "%s < %s > %s", classCvt, *argv, filename);
if(system(t)){
fprintf(stderr, "%s: system() fail: %d\n", self, errno);
free(t);
return -12;
}
free(t);
}
printf("filename is %s\n",filename);
FILE* f = fopen(filename, "r");
rawf = fopen(rawfilename, "wb");
if(filename != *argv){
unlink(filename);
free(filename);
}
if(!f){
fprintf(stderr, "%s: failed to open '%s': %d\n", self, *argv, errno);
fclose(f);
return -2;
}
if(!f){
fprintf(stderr, "%s: failed to open '%s': %d\n", self, *argv, errno);
fclose(f);
return -2;
}
if(fseek(f, 0, SEEK_END)){
fprintf(stderr, "%s: failed to seek(1) in '%s': %d\n", self, *argv, errno);
fclose(f);
return -3;
}
len = ftell(f);
if(len < 0){
fprintf(stderr, "%s: failed to tell in '%s': %d\n", self, *argv, errno);
fclose(f);
return -4;
}
if(fseek(f, 0, SEEK_SET)){
fprintf(stderr, "%s: failed to seek(2) in '%s': %d\n", self, *argv, errno);
fclose(f);
return -5;
}
if(len > 0x00FFFFFFUL){
fprintf(stderr, "%s: file '%s' is %lu bytes, while maximum allowable size is %lu.\n", self, *argv, len, 0x00FFFFFFUL);
fclose(f);
return -6;
}
byte(len >> 16);
byte(len >> 8);
byte(len);
while((c = fgetc(f)) != EOF){
byte(c);
}
numFiles++;
fclose(f);
fclose(rawf);
argv++;
}
byte(0);
byte(0);
byte(0);
printf("\n};\n");
fprintf(stderr, "%s: processed %u files, producing %lu (0x%lX) bytes of output\n", self, numFiles, numBytes, numBytes);
fprintf(stderr, "rawfilename at end: %s \n", rawfilename);
free(rawfilename);
return 0;
}
After looking around, people recommend using mkstemp(); however, as you can see, I actually do need the filename in several places.
I tried adjusting this but keep running into errors. How can I safely adjust this work method?
From the manpage for mkstemp
int mkstemp(char *template);
The mkstemp() function generates a unique temporary filename from template, creates and opens the file, and returns an open file descriptor for the file.
The last six characters of template must be "XXXXXX" and these are
replaced with a string that makes the filename unique. Since it will
be modified, template must not be a string constant, but should be
declared as a character array.
The file is created with permissions 0600, that is, read plus write
for owner only. The returned file descriptor provides both read and
write access to the file. The file is opened with the open(2) O_EXCL
flag, guaranteeing that the caller is the process that creates the
file.
so if you need the filename, you can find it in the template argument passed to mkstemp.
I have the following code which reads an file name from the command line and opens this file:
#include <stdio.h>
#include <stdlib.h>
int main(int argc, char **argv){
FILE *datei;
char filename[255];
//filename = argv[1];
//datei=fopen(filename, "r");
datei=fopen(argv[1], "r");
if(datei != NULL)
printf("File opened");
else{
printf("Fehler beim öffnen von %s\n", filename);
return EXIT_FAILURE;
}
return EXIT_SUCCESS;
}
This example works, but I want to write the string from the command line to the char array and pass that char array to to fopen(), but i get the compiler error
Error: assignment to expression with array type filename = argv[1];
What does this error mean and what can I do to fix it?
You must copy the string into the char array, this cannot be done with a simple assignment.
The simplistic answer is strcpy(filename, argv[1]);.
There is a big problem with this method: the command line parameter might be longer than the filename array, leading to a buffer overflow.
The correct answer therefore:
if (argc < 2) {
printf("missing filename\n");
exit(1);
}
if (strlen(argv[1]) >= sizeof(filename)) {
printf("filename too long: %s\n", argv[1]);
exit(1);
}
strcpy(filename, argv[1]);
...
You might want to output the error messages to stderr.
As a side note, you probably want to choose English or German, but not use both at the same time ;-)
An even simpler solution is to just keep a copy of the pointer argv[1] in a char *filename. Unless you modify it yourself, a very bad idea, its contents will not change for the duration of the program execution.
Here is a modified version:
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main(int argc, char *argv[]) {
FILE *datei;
char *filename;
if (argc < 2) {
fprintf(stderr, "Fehlendes Dateiname-Befehlszeilenargument\n");
return EXIT_FAILURE;
}
filename = argv[1];
datei = fopen(filename, "r");
if (datei != NULL) {
printf("Datei erfolgreich geöffnet\n");
} else {
fprintf(stderr, "Fehler beim öffnen von %s: %s\n",
filename, strerror(errno));
return EXIT_FAILURE;
}
// ...
fclose(datei);
return EXIT_SUCCESS;
}
I am trying to run a simulation program to test the FIFO algorithm, however my program is just crashing. this is the main, other functions not shown. Can anyone spot for me the problem.Am not so familiar with using the main Argument[ int main(int argc, char *argv[])]
I have the testing files in a folder
int main(int argc, char *argv[])
{
FILE *stream;
if (argc != 3)
{
printf("The format is: pager file_name memory_size.\n");
//exit(1);
}
printf("File used %s, resident set size %d\n", argv[1], atoi(argv[2]));
if ((stream = fopen(argv[1], "r")) == NULL)
{
perror("File open failed");
//exit(1);
}
mem_size = atoi(argv[2]);
start_simulation(stream);
fclose(stream);
system("pause");
}
Uncomment the calls to exit.
if (argc != 3) {
// insufficient arguments passed..print error and exit.
printf("The format is: pager file_name memory_size.\n");
exit(1);
}
In your case (exit commented) if you don't provide command line arguments, argv[1] will be NULL and this can cause crash when used in fopen
I have some gzipped files that I want to read in C via fopen and fscanf. Is there anyway to do this without having to gunzip the files to temporary files?
Thanks.
You can use libzlib to open the gzipped files directly.
It also offers a "gzopen" function that behaves similar to fopen but operates on gzipped files. However, fscanf would probably not work on such a handle, since it expects normal FILE pointers.
If popen is fair game, you can do it with fopen and fscanf:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
int main(int argc, char *argv[])
{
const char prefix[] = "zcat ";
const char *arg;
char *cmd;
FILE *in;
char buf[4096];
if (argc != 2) {
fprintf(stderr, "Usage: %s file\n", argv[0]);
return 1;
}
arg = argv[1];
cmd = malloc(sizeof(prefix) + strlen(arg) + 1);
if (!cmd) {
fprintf(stderr, "%s: malloc: %s\n", argv[0], strerror(errno));
return 1;
}
sprintf(cmd, "%s%s", prefix, arg);
in = popen(cmd, "r");
if (!in) {
fprintf(stderr, "%s: popen: %s\n", argv[0], strerror(errno));
return 1;
}
while (fscanf(in, "%s", buf) == 1)
printf("%s: got [%s]\n", argv[0], buf);
if (ferror(in)) {
fprintf(stderr, "%s: fread: %s\n", argv[0], strerror(errno));
return 1;
}
else if (!feof(in)) {
fprintf(stderr, "%s: %s: unconsumed input\n", argv[0], argv[1]);
return 1;
}
return 0;
}
For example:
$ zcat file.gz
Every good boy does fine.
$ ./gzread file.gz
./gzread: got [Every]
./gzread: got [good]
./gzread: got [boy]
./gzread: got [does]
./gzread: got [fine.]
Do not use
sprintf(cmd, "zcat %s", argv[1]);
popen(cmd,"r");
to open .gz files. Properly escape argv[1] instead. You may otherwise end up with a vulnerability, especially when some injects an argument argv[1] such as
123;rm -rf /
It already helps to change the above instruction into
sprintf(cmd, "zcat \'%s\'",argv[1]);
You may also want to escape characters such as '\0', '\'', '\;' etc.
Newbie attempt at gzscanf():
#include <stdio.h>
#include <stdarg.h>
#include <zlib.h>
#define MAXLEN 256
int gzscanf(gzFile *stream, const char *fmt, ...) {
/* read one line from stream (up to newline) and parse with sscanf */
va_list args;
va_start(args, fmt);
int n;
static char buf[MAXLEN];
if (NULL == gzgets(stream, buf, MAXLEN)) {
printf("gzscanf: Failed to read line from gz file.\n");
exit(EXIT_FAILURE);
}
n = vsscanf(buf, fmt, args);
va_end(args);
return n;
}
You can use zlib and wrap it to a regular file pointer, this way you can use fscanf,fread,etc. transparently.
FILE *myfopen(const char *path, const char *mode)
{
#ifdef WITH_ZLIB
gzFile *zfp;
/* try gzopen */
zfp = gzopen(path,mode);
if (zfp == NULL)
return fopen(path,mode);
/* open file pointer */
return funopen(zfp,
(int(*)(void*,char*,int))gzread,
(int(*)(void*,const char*,int))gzwrite,
(fpos_t(*)(void*,fpos_t,int))gzseek,
(int(*)(void*))gzclose);
#else
return fopen(path,mode);
#endif
}
You can use zlib, but it will require you to replace your I/O calls to be zlib-specific.
you have to open a pipe to do this. The basic flow in pseudo code is:
create pipe // man pipe
fork // man fork
if (parent) {
close the writing end of the pipe // man 2 close
read from the pipe // man 2 read
} else if (child) {
close the reading end of the pipe // man 2 close
overwrite the file descriptor for stdout with the writing end of the pipe // man dup2
call exec() with gzip and the relevant parameters // man 3 exec
}
You can use the man pages in the comments for more details on how to do this.
It's quite simple to use zlib to open .gz files. There's a reasonable manual over at zlib.net.
Here's a quick example to get you started:
#include <stdio.h>
#include <zlib.h>
int main( int argc, char **argv )
{
// we're reading 2 text lines, and a binary blob from the given file
char line1[1024];
char line2[1024];
int blob[64];
if (argc > 1)
{
const char *filename = argv[1];
gzFile gz_in = gzopen( filename, "rb" ); // same as fopen()
if (gz_in != NULL)
{
if ( gzgets( gz_in, line1, sizeof(line1) ) != NULL ) // same as fgets()
{
if ( gzgets( gz_in, line2, sizeof(line2) ) != NULL )
{
if ( gzfread( blob, sizeof(int), 64, gz_in ) == 64 ) // same as fread()
{
printf("Line1: %s", line1);
printf("Line2: %s", line2);
// ...etc
}
}
}
gzclose(gz_in); // same as fclose()
}
else
{
printf( "Failed to GZ-open [%s]\n", filename );
}
}
return 0;
}
Remember to link with zlib, under UNIX gcc ... -lz