Unsure of parameter to store BIGNUM in char - BN_bn2bin() - c

I have the following code:
/*
* Special note about BN_bn2bin():
* OpenSSL's BN_bn2bin() will truncate numbers at the front, but ISAKMP
* wants leading zero's instead.
*/
void _BN_encode(BIGNUM *bn, unsigned char *p, int len)
{
int pad;
assert(bn);
if ((pad = len - BN_num_bytes(bn))) {
if (pad < 0) {
assert(1);
return;
}
memset(p, '\0', 1);
BN_bn2bin(bn, p + pad);
} else {
BN_bn2bin(bn, p);
}
}
And I gather that *bn is the BIGNUM I want to convert, *p is where I want to store it, but what should the argument len be?
I was also looking at this question which seems related. Any advice would be appreciated!
Edit
Would something along the lines of this be correct?
_BN_encode(bignum, bin_bignum, sizeof(char));

len is the length of the buffer pointed to by p. The function pads out the converted bignum to len bytes (with zeroes, which doesn't change the mathematical value of the number represented).
That function appears to have a bug, by the way - I strongly suspect that the memset() call should be memset(p, 0, pad);.

Related

Stray characters seen at output of snprintf

I have a string creating function in C which accepts an array of structs as it's argument and outputs a string based on a predefined format (like a list of list in python).
Here's the function
typedef struct
{
PacketInfo_t PacketInfo;
char Gnss60[1900];
//and other stuff...
} Track_json_t;
typedef struct
{
double latitude;
double longitude;
} GPSPoint_t;
typedef struct
{
UInt16 GPS_StatusCode;
UInt32 fixtime;
GPSPoint_t point;
double altitude;
unsigned char GPS_Satilite_Num;
} GPS_periodic_t;
unsigned short SendTrack()
{
Track_json_t i_sTrack_S;
memset(&i_sTrack_S, 0x00, sizeof(Track_json_t));
getEvent_Track(&i_sTrack_S);
//Many other stuff added to the i_sTrack_S struct...
//Make a JSON format out of it
BuildTrackPacket_json(&i_sTrack_S, XPORT_MODE_GPRS);
}
Track_json_t *getEvent_Track(Track_json_t *trk)
{
GPS_periodic_t l_gps_60Sec[60];
memset(&l_gps_60Sec, 0x00,
sizeof(GPS_periodic_t) * GPS_PERIODIC_ARRAY_SIZE);
getLastMinGPSdata(l_gps_60Sec, o_gps_base);
get_gps60secString(l_gps_60Sec, trk->Gnss60);
return trk;
}
void get_gps60secString(GPS_periodic_t input[60], char *output)
{
int i = 0;
memcpy(output, "[", 1); ///< Copy the first char as [
char temp[31];
for (i = 0; i < 59; i++) { //Run for n-1 elements
memset(temp, 0, sizeof(temp));
snprintf(temp, sizeof(temp), "[%0.8f,%0.8f],",
input[i].point.latitude, input[i].point.longitude);
strncat(output, temp, sizeof(temp));
}
memset(temp, 0, sizeof(temp)); //assign last element
snprintf(temp, sizeof(temp), "[%0.8f,%0.8f]]",
input[i].point.latitude, input[i].point.longitude);
strncat(output, temp, sizeof(temp));
}
So the output of the function must be a string of format
[[12.12345678,12.12345678],[12.12345678,12.12345678],...]
But at times I get a string which looks like
[[12.12345678,12.12345678],[55.01[12.12345678,12.12345678],...]
[[21.28211567,84.13454083],[21.28211533,21.22[21.28211517,84.13454000],..]
Previously, I had a buffer overflow at the function get_gps60secString, I fixed that by using snprintf and strncat.
Note: This is an embedded application and this error occur once or twice a day (out of 1440 packets)
Question
1. Could this be caused by an interrupt during the snprintf/strncat process?
2. Could this be caused by a memory leak, overwriting the stack or some other segmentation issue caused else where?
Basically I would like to understand what might be causing a corrupt string.
Having a hard time finding the cause and fixing this bug.
EDIT:
I used chux's function. Below is the Minimal, Complete, and Verifiable Example
/*
* Test code for SO question https://stackoverflow.com/questions/5216413
* A Minimal, Complete, and Verifiable Example
*/
#include <stdio.h>
#include <stdlib.h>
#include <memory.h>
#include <stdbool.h>
#include <signal.h>
#include <unistd.h>
typedef unsigned short UInt16;
typedef unsigned long UInt32;
#define GPS_PERIODIC_ARRAY_SIZE 60
#define GPS_STRING_SIZE 1900
/* ---------------------- Data Structs --------------------------*/
typedef struct
{
char Gnss60[GPS_STRING_SIZE];
} Track_json_t;
typedef struct
{
double latitude;
double longitude;
} GPSPoint_t;
typedef struct
{
UInt16 GPS_StatusCode;
UInt32 fixtime;
GPSPoint_t point;
double altitude;
unsigned char GPS_Satilite_Num;
} GPS_periodic_t;
/* ----------------------- Global --------------------------------*/
FILE *fptr; //Global file pointer
int res = 0;
int g_last = 0;
GPS_periodic_t l_gps_60Sec[GPS_PERIODIC_ARRAY_SIZE];
/* ----------------------- Function defs --------------------------*/
/* At signal interrupt this function is called.
* Flush and close the file. And safly exit the program */
void userSignalInterrupt()
{
fflush(fptr);
fclose(fptr);
res = 1;
exit(0);
}
/* #brief From the array of GPS structs we create a string of the format
* [[lat,long],[lat,long],..]
* #param input The input array of GPS structs
* #param output The output string which will contain lat, long
* #param sz Size left in the output buffer
* #return 0 Successfully completed operation
* 1 Failed / Error
*/
int get_gps60secString(GPS_periodic_t input[GPS_PERIODIC_ARRAY_SIZE],
char *output, size_t sz)
{
int cnt = snprintf(output, sz, "[");
if (cnt < 0 || cnt >= sz)
return 1;
output += cnt;
sz -= cnt;
int i = 0;
for (i = 0; i < GPS_PERIODIC_ARRAY_SIZE; i++) {
cnt = snprintf(output, sz, "[%0.8f,%0.8f]%s",
input[i].point.latitude, input[i].point.longitude,
i + 1 == GPS_PERIODIC_ARRAY_SIZE ? "" : ",");
if (cnt < 0 || cnt >= sz)
return 1;
output += cnt;
sz -= cnt;
}
cnt = snprintf(output, sz, "]");
if (cnt < 0 || cnt >= sz)
return 1;
return 0; // no error
}
/* #brief Create a GPS struct with data for testing. It will populate the
* point field of GPS_periodic_t. Lat starts from 0.0 and increases by 1*10^(-8)
* and Long will dstart at 99.99999999 and dec by 1*10^(-8)
*
* #param o_gps_60sec Output array of GPS structs
*/
void getLastMinGPSdata(GPS_periodic_t *o_gps_60sec)
{
//Fill in GPS related data here
int i = 0;
double latitude = o_gps_60sec[0].point.latitude;
double longitude = o_gps_60sec[0].point.longitude;
for (i = 0; i < 60; i++)
{
o_gps_60sec[i].point.latitude = latitude + (0.00000001 * (float)g_last +
0.00000001 * (float)i);
o_gps_60sec[i].point.longitude = longitude - (0.00000001 * (float)g_last +
0.00000001 * (float)i);
}
g_last = 60;
}
/* #brief Get the GPS data and convert it into a string
* #param trk Track structure with GPS string
*/
int getEvent_Track(Track_json_t *trk)
{
getLastMinGPSdata(l_gps_60Sec);
get_gps60secString(l_gps_60Sec, trk->Gnss60, GPS_STRING_SIZE);
return 0;
}
int main()
{
fptr = fopen("gpsAno.txt", "a");
if (fptr == NULL) {
printf("Error!!\n");
exit(1);
}
//Quit at signal interrupt
signal(SIGINT, userSignalInterrupt);
Track_json_t trk;
memset(&l_gps_60Sec, 0x00, sizeof(GPS_periodic_t) * GPS_PERIODIC_ARRAY_SIZE);
//Init Points to be zero and 99.99999999
int i = 0;
for (i = 0; i < 60; i++) {
l_gps_60Sec[i].point.latitude = 00.00000000;
l_gps_60Sec[i].point.longitude = 99.99999999;
}
do {
memset(&trk, 0, sizeof(Track_json_t));
getEvent_Track(&trk);
//Write to file
fprintf(fptr, "%s", trk.Gnss60);
fflush(fptr);
sleep(1);
} while (res == 0);
//close and exit
fclose(fptr);
return 0;
}
Note: Error was not recreated in the above code.
Because this doesn't have the strcat pitfalls.
I tested this function in the embedded application.
Through this I was able to find that the snprintf returns an error and the string created ended up to be:
[17.42401750,78.46098717],[17.42402083,53.62
It ended there (because of the return 1).
Does this mean that the data which was passed to snprints corrupted? It's a float value. How can it get corrupted?
Solution
The error have not been seen since I changed the sprintf function with one that doesn't directly deal with 64 bits of data.
Here's the function modp_dtoa2
/** \brief convert a floating point number to char buffer with a
* variable-precision format, and no trailing zeros
*
* This is similar to "%.[0-9]f" in the printf style, except it will
* NOT include trailing zeros after the decimal point. This type
* of format oddly does not exists with printf.
*
* If the input value is greater than 1<<31, then the output format
* will be switched exponential format.
*
* \param[in] value
* \param[out] buf The allocated output buffer. Should be 32 chars or more.
* \param[in] precision Number of digits to the right of the decimal point.
* Can only be 0-9.
*/
void modp_dtoa2(double value, char* str, int prec)
{
/* if input is larger than thres_max, revert to exponential */
const double thres_max = (double)(0x7FFFFFFF);
int count;
double diff = 0.0;
char* wstr = str;
int neg= 0;
int whole;
double tmp;
uint32_t frac;
/* Hacky test for NaN
* under -fast-math this won't work, but then you also won't
* have correct nan values anyways. The alternative is
* to link with libmath (bad) or hack IEEE double bits (bad)
*/
if (! (value == value)) {
str[0] = 'n'; str[1] = 'a'; str[2] = 'n'; str[3] = '\0';
return;
}
if (prec < 0) {
prec = 0;
} else if (prec > 9) {
/* precision of >= 10 can lead to overflow errors */
prec = 9;
}
/* we'll work in positive values and deal with the
negative sign issue later */
if (value < 0) {
neg = 1;
value = -value;
}
whole = (int) value;
tmp = (value - whole) * pow10[prec];
frac = (uint32_t)(tmp);
diff = tmp - frac;
if (diff > 0.5) {
++frac;
/* handle rollover, e.g. case 0.99 with prec 1 is 1.0 */
if (frac >= pow10[prec]) {
frac = 0;
++whole;
}
} else if (diff == 0.5 && ((frac == 0) || (frac & 1))) {
/* if halfway, round up if odd, OR
if last digit is 0. That last part is strange */
++frac;
}
/* for very large numbers switch back to native sprintf for exponentials.
anyone want to write code to replace this? */
/*
normal printf behavior is to print EVERY whole number digit
which can be 100s of characters overflowing your buffers == bad
*/
if (value > thres_max) {
sprintf(str, "%e", neg ? -value : value);
return;
}
if (prec == 0) {
diff = value - whole;
if (diff > 0.5) {
/* greater than 0.5, round up, e.g. 1.6 -> 2 */
++whole;
} else if (diff == 0.5 && (whole & 1)) {
/* exactly 0.5 and ODD, then round up */
/* 1.5 -> 2, but 2.5 -> 2 */
++whole;
}
//vvvvvvvvvvvvvvvvvvv Diff from modp_dto2
} else if (frac) {
count = prec;
// now do fractional part, as an unsigned number
// we know it is not 0 but we can have leading zeros, these
// should be removed
while (!(frac % 10)) {
--count;
frac /= 10;
}
//^^^^^^^^^^^^^^^^^^^ Diff from modp_dto2
// now do fractional part, as an unsigned number
do {
--count;
*wstr++ = (char)(48 + (frac % 10));
} while (frac /= 10);
// add extra 0s
while (count-- > 0) *wstr++ = '0';
// add decimal
*wstr++ = '.';
}
// do whole part
// Take care of sign
// Conversion. Number is reversed.
do *wstr++ = (char)(48 + (whole % 10)); while (whole /= 10);
if (neg) {
*wstr++ = '-';
}
*wstr='\0';
strreverse(str, wstr-1);
}
Here's (part of) my unabashedly opinionated guide on safe string handling in C. Normally, I would promote dynamic memory allocation instead of fixed-length strings, but in this case I'm assuming that in the embedded environment that might be problematic. (Although assumptions like that should always be checked.)
So, first things first:
Any function which creates a string in a buffer must be told explicitly how long the buffer is. This is non-negotiable.
As should be obvious, it's impossible for a function filling a buffer to check for buffer overflow unless it knows where the buffer ends. "Hope that the buffer is long enough" is not a viable strategy. "Document the needed buffer length" would be fine if everyone carefully read the documentation (they don't) and if the required length never changes (it will). The only thing that's left is an extra argument, which should be of type size_t (because that's the type of buffer lengths in the C library functions which require lengths).
Forget that strncpy and strncat exist. Also forget about strcat. They are not your friends.
strncpy is designed for a specific use case: ensuring that an entire fixed-length buffer is initialised. It is not designed for normal strings, and since it doesn't guarantee that the output is NUL-terminated, it doesn't produce a string.
If you're going to NUL-terminate yourself anyway, you might as well use memmove, or memcpy if you know that the source and destination don't overlap, which should almost always be the case. Since you'll want the memmove to stop at the end of the string for short strings (which strncpy does not do), measure the string length first with strnlen: strnlen takes a maximum length, which is precisely what you want in the case that you are going move a maximum number of characters.
Sample code:
/* Safely copy src to dst where dst has capacity dstlen. */
if (dstlen) {
/* Adjust to_move will have maximum value dstlen - 1 */
size_t to_move = strnlen(src, dstlen - 1);
/* copy the characters */
memmove(dst, src, to_move);
/* NUL-terminate the string */
dst[to_move] = 0;
}
strncat has a slightly more sensible semantic, but it's practically never useful because in order to use it, you already have to know how many bytes you could copy. In order to know that, in practice, you need to know how much space is left in your output buffer, and to know that you need to know where in the output buffer the copy will start. [Note 1]. But if you already know where the copy will start, what's the point of searching through the buffer from the beginning to find the copy point? And if you do let strncat do the search, how sure are you that your previously computed start point is correct?
In the above code snippet, we already computed the length of the copy. We can extend that to do an append without rescanning:
/* Safely copy src1 and then src2 to dst where dst has capacity dstlen. */
/* Assumes that src1 and src2 are not contained in dst. */
if (dstlen) {
/* Adjust to_move will have maximum value dstlen - 1 */
size_t to_move = strnlen(src1, dstlen - 1);
/* Copy the characters from src1 */
memcpy(dst, src1, to_move);
/* Adjust the output pointer and length */
dst += to_move;
dstlen -= to_move;
/* Now safely copy src2 to just after src1. */
to_move = strnlen(src2, dstlen - 1);
memcpy(dst, src2, to_move);
/* NUL-terminate the string */
dst[to_move] = 0;
}
It might be that we want the original values of dst and dstlen after creating the string, and it might also be that we want to know how many bytes we inserted into dst in all. In that case, we would probably want to make copies of those variables before doing the copies, and save the cumulative sum of moves.
The above assumes that we're starting with an empty output buffer, but perhaps that isn't the case. Since we still need to know where the copy will start in order to know how many characters we can put at the end, we can still use memcpy; we just need to scan the output buffer first to find the copy point. (Only do this if there is no alternative. Doing it in a loop instead of recording the next copy point is Shlemiel the Painter's algorithm.)
/* Safely append src to dst where dst has capacity dstlen and starts
* with a string of unknown length.
*/
if (dstlen) {
/* The following code will "work" even if the existing string
* is not correctly NUL-terminated; the code will not copy anything
* from src, but it will put a NUL terminator at the end of the
* output buffer.
*/
/* Figure out where the existing string ends. */
size_t prefixlen = strnlen(dst, dstlen - 1);
/* Update dst and dstlen */
dst += prefixlen;
dstlen -= prefixlen;
/* Proceed with the append, as above. */
size_t to_move = strnlen(src, dstlen - 1);
memmove(dst, src, to_move);
dst[to_move] = 0;
}
Embrace snprintf. It really is your friend. But always check its return value.
Using memmove, as above, is slightly awkward. It requires you to manually check that the buffer's length is not zero (otherwise subtracting one would be disastrous since the length is unsigned), and it requires you to manually NUL-terminate the output buffer, which is easy to forget and the source of many bugs. It is very efficient, but sometimes it's worth sacrificing a little efficiency so that your code is easier to write and easier to read and verify.
And that leads us directly to snprintf. For example, you can replace:
if (dstlen) {
size_t to_move = strnlen(src, dstlen - 1);
memcpy(dst, src, to_move);
dst[to_move] = 0;
}
with the much simpler
int copylen = snprintf(dst, dstlen, "%s", src);
That does everything: checks that dstlen is not 0; only copies the characters from src which can fit in dst, and correctly NUL-terminates dst (unless dstlen was 0). And the cost is minimal; it takes very little time to parse the format string "%s" and most implementations are pretty well optimised for this case. [Note 2]
But snprintf is not a panacea. There are still a couple of really important warnings.
First, the documentation for snprintf makes clear that it is not permitted for any input argument to overlap the output range. (So it replaces memcpy but not memmove.) Remember that overlap includes NUL-terminators, so the following code which attempts to double the string in str instead leads to Undefined Behaviour:
char str[BUFLEN];
/* Put something into str */
get_some_data(str, BUFLEN);
/* DO NOT DO THIS: input overlaps output */
int result = snprintf(str, BUFLEN, "%s%s", str, str);
/* DO NOT DO THIS EITHER; IT IS STILL UB */
size_t len = strnlen(str, cap - 1);
int result = snprintf(str + len, cap - len, "%s", str);
The problem with the second invocation of snprintf is that the NUL which terminates str is precisely at str + len, the first byte of the output buffer. That's an overlap, so it's illegal.
The second important note about snprintf is that it returns a value, which must not be ignored. The value returned is not the length of the string created by snprintf. It's the length the string would have been had it not been truncated to fit in the output buffer.
If no truncation occurred, then the result is the length of the result, which must be strictly less than the size of the output buffer (because there must be room for a NUL terminator, which is not considered part of the length of the result.) You can use this fact to check whether truncation occurred:
if (result >= dstlen) /* Output was truncated */
This can be used, for example, to redo the snprintf with a larger, dynamically-allocated buffer (of size result + 1; never forget the need to NUL-terminate).
But remember that the result is an int -- that is, a signed value. That means that snprintf cannot cope with very long strings. That's not likely to be an issue in embedded code, but on systems where it's conceivable that strings exceed 2GB, you may not be able to safely use %s formats in snprintf. It also means that snprintf is allowed to return a negative value to indicate an error. Very old implementations of snprintf returned -1 to indicate truncation, or in response to being called with buffer length 0. That's not standard behaviour according to C99 (nor recent versions of Posix), but you should be prepared for it.
Standard-compliant implementations of snprintf will return a negative value if the buffer length argument is too big to fit in a (signed) int; it's not clear to me what the expected return value is if the buffer length is OK but the untruncated length is too big for an int. A negative value will also be returned if you used a conversion which resulted in an encoding error; for example, a %lc conversion whose corresponding argument contains an integer which cannot be converted to a multibyte (typically UTF-8) sequence.
In short, you should always check the return value of snprintf (recent gcc/glibc versions will produce a warning if you do not), and you should be prepared for it to be negative.
So, with all that behind us, let's write a function which produces a string of co-ordinate pairs:
/* Arguments:
* buf the output buffer.
* buflen the capacity of buf (including room for trailing NUL).
* points a vector of struct Point pairs.
* npoints the number of objects in points.
* Description:
* buf is overwritten with a comma-separated list of points enclosed in
* square brackets. Each point is output as a comma-separated pair of
* decimal floating point numbers enclosed in square brackets. No more
* than buflen - 1 characters are written. Unless buflen is 0, a NUL is
* written following the (possibly-truncated) output.
* Return value:
* If the output buffer contains the full output, the number of characters
* written to the output buffer, not including the NUL terminator.
* If the output was truncated, (size_t)(-1) is returned.
*/
size_t sprint_points(char* buf, size_t buflen,
struct Point const* points, size_t npoints)
{
if (buflen == 0) return (size_t)(-1);
size_t avail = buflen;
char delim = '['
while (npoints) {
int res = snprintf(buf, avail, "%c[%f,%f]",
delim, points->lat, points->lon);
if (res < 0 || res >= avail) return (size_t)(-1);
buf += res; avail -= res;
++points; --npoints;
delim = ',';
}
if (avail <= 1) return (size_t)(-1);
strcpy(buf, "]");
return buflen - (avail - 1);
}
Notes
You will often see code like this:
strncat(dst, src, sizeof(src)); /* NEVER EVER DO THIS! */
Telling strncat not to append more characters from src than can fit in src is obviously pointless (unless src is not correctly NUL-terminated, in which case you have a bigger problem). More importantly, it does absolutely nothing to protect you from writing beyond the end of the output buffer, since you have not done anything to check that dst has room for all those characters. So about all it does is get rid of compiler warnings about the unsafety of strcat. Since this code is exactly as unsafe as strcat was, you probably would be better off with the warning.
You might even find a compiler which understands snprintf will enough to parse the format string at compile time, so the convenience comes at no cost at all. (And if your current compiler doesn't do this, no doubt a future version will.) As with any use of the *printf family, you should never try to economize keystrokes by
leaving out the format string (snprintf(dst, dstlen, src) instead of snprintf(dst, dstlen, "%s", src).) That's unsafe (it has undefined behaviour if src contains an unduplicated %). And it's much slower because the library function has to parse the entire string to be copied looking for percent signs, instead of just copying it to the output.
Code is using functions that expect pointers to string, yet not always passing pointers to strings as arguments.
Stray characters seen at output of snprintf
A string must have a terminating null character.
strncat(char *, .... expects the first parameter to be a pointer to a string. memcpy(output, "[",1); does not insure that. #Jeremy
memcpy(output, "[",1);
...
strncat(output, temp,sizeof(temp));
This is a candidate source of stray characters.
strncat(...., ..., size_t size). itself is a problem as the size is the amount of space available for concatenating (minus the null character). The size available to char * output is not passed in. #Jonathan Leffler. Might as well do strcat() here.
Instead, pass in the size available to output to prevent buffer overflow.
#define N 60
int get_gps60secString(GPS_periodic_t input[N], char *output, size_t sz) {
int cnt = snprintf(output, sz, "[");
if (cnt < 0 || cnt >= sz)
return 1;
output += cnt;
sz -= cnt;
int i = 0;
for (i = 0; i < N; i++) {
cnt = snprintf(output, size, "[%0.8f,%0.8f]%s", input[i].point.latitude,
input[i].point.longitude, i + 1 == N ? "" : ",");
if (cnt < 0 || cnt >= sz)
return 1;
output += cnt;
sz -= cnt;
}
cnt = snprintf(output, sz, "]");
if (cnt < 0 || cnt >= sz)
return 1;
return 0; // no error
}
OP has posted more code - will review.
Apparently the buffer char *output is pre-filled with 0 before the get_gps60secString() so the missing null character from memcpy(output, "[",1); should not cause the issue - hmmmmmm
unsigned short SendTrack() does not return a value. 1) Using its result value is UB. 2) Enable all compiler warnings.

How to Hash CPU ID in C

I'm trying to short the cpu id of my microcontroller (STM32F1).
The cpu id is composed by 3 word ( 3 x 4 bytes). This is the id string built from the 3 word: 980416578761680031125348904
I found a very useful library that do this.
The library is Hashids and there is a C code.
I try to build a test code on PC with "Code Blocks IDE" and the code works.
But when I move the code into the embedded side (Keil v5 IDE), I get an error on strdup() function: "strdup implicit declaration of function".
The problem is related to the strdup function isn't a standard library function and ins't included into string.h.
I will avoid to replace the strdup function with a custom function (that mimic the behaviour of strdup) to avoid memory leak because strdup copy strings using malloc.
Is there a different approach to compress long numbers?
Thanks for the help!
<---Appendix--->
This is the function that uses the strdup.
/* common init */
struct hashids_t *
hashids_init3(const char *salt, size_t min_hash_length, const char *alphabet)
{
struct hashids_t *result;
unsigned int i, j;
size_t len;
char ch, *p;
hashids_errno = HASHIDS_ERROR_OK;
/* allocate the structure */
result = _hashids_alloc(sizeof(struct hashids_t));
if (HASHIDS_UNLIKELY(!result)) {
hashids_errno = HASHIDS_ERROR_ALLOC;
return NULL;
}
/* allocate enough space for the alphabet and its copies */
len = strlen(alphabet) + 1;
result->alphabet = _hashids_alloc(len);
result->alphabet_copy_1 = _hashids_alloc(len);
result->alphabet_copy_2 = _hashids_alloc(len);
if (HASHIDS_UNLIKELY(!result->alphabet || !result->alphabet_copy_1
|| !result->alphabet_copy_2)) {
hashids_free(result);
hashids_errno = HASHIDS_ERROR_ALLOC;
return NULL;
}
/* extract only the unique characters */
result->alphabet[0] = '\0';
for (i = 0, j = 0; i < len; ++i) {
ch = alphabet[i];
if (!strchr(result->alphabet, ch)) {
result->alphabet[j++] = ch;
}
}
result->alphabet[j] = '\0';
/* store alphabet length */
result->alphabet_length = j;
/* check length and whitespace */
if (result->alphabet_length < HASHIDS_MIN_ALPHABET_LENGTH) {
hashids_free(result);
hashids_errno = HASHIDS_ERROR_ALPHABET_LENGTH;
return NULL;
}
if (strchr(result->alphabet, ' ')) {
hashids_free(result);
hashids_errno = HASHIDS_ERROR_ALPHABET_SPACE;
return NULL;
}
/* copy salt */
result->salt = strdup(salt ? salt : HASHIDS_DEFAULT_SALT);
result->salt_length = (unsigned int) strlen(result->salt);
/* allocate enough space for separators */
result->separators = _hashids_alloc((size_t)
(ceil((float)result->alphabet_length / HASHIDS_SEPARATOR_DIVISOR) + 1));
if (HASHIDS_UNLIKELY(!result->separators)) {
hashids_free(result);
hashids_errno = HASHIDS_ERROR_ALLOC;
return NULL;
}
/* non-alphabet characters cannot be separators */
for (i = 0, j = 0; i < strlen(HASHIDS_DEFAULT_SEPARATORS); ++i) {
ch = HASHIDS_DEFAULT_SEPARATORS[i];
if ((p = strchr(result->alphabet, ch))) {
result->separators[j++] = ch;
/* also remove separators from alphabet */
memmove(p, p + 1,
strlen(result->alphabet) - (p - result->alphabet));
}
}
/* store separators length */
result->separators_count = j;
/* subtract separators count from alphabet length */
result->alphabet_length -= result->separators_count;
/* shuffle the separators */
hashids_shuffle(result->separators, result->separators_count,
result->salt, result->salt_length);
/* check if we have any/enough separators */
if (!result->separators_count
|| (((float)result->alphabet_length / (float)result->separators_count)
> HASHIDS_SEPARATOR_DIVISOR)) {
unsigned int separators_count = (unsigned int)ceil(
(float)result->alphabet_length / HASHIDS_SEPARATOR_DIVISOR);
if (separators_count == 1) {
separators_count = 2;
}
if (separators_count > result->separators_count) {
/* we need more separators - get some from alphabet */
int diff = separators_count - result->separators_count;
strncat(result->separators, result->alphabet, diff);
memmove(result->alphabet, result->alphabet + diff,
result->alphabet_length - diff + 1);
result->separators_count += diff;
result->alphabet_length -= diff;
} else {
/* we have more than enough - truncate */
result->separators[separators_count] = '\0';
result->separators_count = separators_count;
}
}
/* shuffle alphabet */
hashids_shuffle(result->alphabet, result->alphabet_length,
result->salt, result->salt_length);
/* allocate guards */
result->guards_count = (unsigned int) ceil((float)result->alphabet_length
/ HASHIDS_GUARD_DIVISOR);
result->guards = _hashids_alloc(result->guards_count + 1);
if (HASHIDS_UNLIKELY(!result->guards)) {
hashids_free(result);
hashids_errno = HASHIDS_ERROR_ALLOC;
return NULL;
}
if (HASHIDS_UNLIKELY(result->alphabet_length < 3)) {
/* take some from separators */
strncpy(result->guards, result->separators, result->guards_count);
memmove(result->separators, result->separators + result->guards_count,
result->separators_count - result->guards_count + 1);
result->separators_count -= result->guards_count;
} else {
/* take them from alphabet */
strncpy(result->guards, result->alphabet, result->guards_count);
memmove(result->alphabet, result->alphabet + result->guards_count,
result->alphabet_length - result->guards_count + 1);
result->alphabet_length -= result->guards_count;
}
/* set min hash length */
result->min_hash_length = min_hash_length;
/* return result happily */
return result;
}
The true question seems to be
Is there a different approach to compress long numbers?
There are many. They differ in several respects, including which bits of the input contribute to the output, how many inputs map to the same output, and what manner of transformations of the input leave the output unchanged.
As a trivial examples, you can compress the input to a single bit by any of these approaches:
Choose the lowest-order bit of the input
Choose the highest-order bit of the input
The output is always 1
etc
Or you can compress to 7 bits by using using the number of 1 bits in the input as the output.
None of those particular options is likely to be of interest to you, of course.
Perhaps you would be more interested in producing 32-bit outputs for your 96-bit inputs. Do note that in that case on average there will be at least 264 possible inputs that map to each possible output. That depends only on the sizes of input and output, not on any details of the conversion.
For example, suppose that you have
uint32_t *cpuid = ...;
pointing to the hardware CPU ID. You can produce a 32-bit value from it that depends on all the bits of the input simply by doing this:
uint32_t cpuid32 = cpuid[0] ^ cpuid[1] ^ cpuid[2];
Whether that would suit your purpose depends on how you intend to use it.
You can easily implement strdup yourself like this:
char* strdup (const char* str)
{
size_t size = strlen(str);
char* result = malloc(size);
if(result != NULL)
{
memcpy(result, str, size+1);
}
return result;
}
That being said, using malloc or strdup on an embedded system is most likely just nonsense practice, see this. Nor would you use float numbers. Overall, that library seems to have been written by a desktop-minded person.
If you are implementing something like for example a chained hash table on an embedded system, you would use a statically allocated memory pool and not malloc. I'd probably go with a non-chained one for that reason (upon duplicates, pick next free spot in the buffer).
Unique device ID register (96 bits) is located under address 0x1FFFF7E8. It is factory programmed and is read-only. You can read it directly without using any other external library. For example:
unsigned int b = *(0x1FFFF7E8);
should give you the first 32 bits (31:0) of the unique device ID. If you want to retrieve a string as in case of the library mentioned, the following should work:
sprintf(id, "%08X%08X%08X", *(0x1FFFF7E8), *(0x1FFFF7E8 + 4), *(0x1FFFF7E8 + 8);
Some additional casting may be required, but generally that's what the library did. Please refer to STM32F1xx Reference Manual (RM0008), section 30.2 for more details. The exact memory location to read from is different in case of Cortex-M4 family of the MCUs.

Why doesn't malloc allocate enough memory?

I am really stuck with one very simple piece of code.
This program takes argument like ./a.out -t=1,32,45,2 and prints quantity of commas in stdout. But from time to time execution works correctly and and more often throws segmentation fault.
I figured out that problem in this line of function substr_cnt (I also placed corresponding commentaries in code below):
target_counting = (char *)malloc(sizeof(char)*(strlen(target)));
In fact malloc returns NULL. If I change sizeof(char) by sizeof(char *) all starts work like a charm but I can't understand why is that. Furthermore in main function I also use malloc, and even with the same line
arg_parameter = (char *) malloc(sizeof(char)*(strlen(argv[1] - 3)));
all works just fine.
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#define strindex(target, source) ((size_t) strstr(target, source) - (size_t) target)
int substr_cnt( char *target, char *source ) {
int i=0;
int cnt=0;
char *target_counting;
//this is NOT working
target_counting = (char *)malloc(sizeof(char)*(strlen(target)));
//this is working
//target_counting = (char *)malloc(sizeof(char *)*(strlen(target)));
if (target_counting == NULL) {
printf("malloc failed\n");
return -1;
}
strcpy(target_counting, target);
while ((i=strindex(target_counting, source)) > 0) {
strncpy(target_counting, target_counting + i + 1, strlen(target_counting));
cnt++;
}
free(target_counting);
return cnt;
}
int main( int argc, char *argv[] )
{
int i;
int default_behavior = 0;
int arg_parametr_cnt;
char *arg_parameter;
if (argc == 1) {
default_behavior = 1;
} else if (argv[1][0] == '-' && argv[1][1] == 't' && argv[1][2] == '=') {
//this is working
arg_parameter = (char *) malloc(sizeof(char)*(strlen(argv[1] - 3)));
strncpy(arg_parameter, argv[1]+3, strlen(argv[1]));
printf("%s\n", arg_parameter);
arg_parametr_cnt = substr_cnt(arg_parameter, ",");
printf("commas: %d\n", arg_parametr_cnt);
}
else {
printf("wrong command line");
return 1;
}
return 0;
}
You have several issues here, the main point, you don't need to allocate memory at all. You can implement searching for a given substring without modifying the string and therefore work directly on the given argv parameters, e.g.
int substr_cnt(const char *haystack, const char *needle)
{
int cnt = 0;
const char *found = haystack;
while ((found = strstr(found, needle)) != NULL) {
++found;
++cnt;
}
return cnt;
}
Same for the call in main, just pass argv directly
arg_parametr_cnt = substr_cnt(argv[1] + 3, ",");
Now to answer your question, unless you really see the output of
printf("malloc failed\n");
I don't believe, malloc returns NULL, because when you allocate an even larger amount of memory, sizeof(char*) vs sizeof(char), it works.
The reasons, why your program crashes, are already covered in the other answers. To summarize
target_counting = (char *)malloc(sizeof(char)*(strlen(target))); allocates one char less than it should
while ((i=strindex(target_counting, source)) > 0) I'm not sure, what happens, when the result of strstr is NULL. strindex might return a negative number, depending on your memory layout, but I am not sure.
strncpy(target_counting, target_counting + i + 1, strlen(target_counting)); This is not really an issue, but since you copy the rest of the string, you could use strcpy(target_counting, target_counting + i + 1) instead.
arg_parameter = (char *) malloc(sizeof(char)*(strlen(argv[1] - 3))); this should be malloc(sizeof(char) * strlen(argv[1]) - 3 + 1)
strncpy(arg_parameter, argv[1]+3, strlen(argv[1])); again strcpy(arg_parameter, argv[1]+3) would be sufficient
Update:
In this version
int strindex(char *target, char *source)
{
char *idx;
if ((idx = strstr(target, source)) != NULL) {
return idx - target;
} else {
return -1;
}
}
you have an explicit test for NULL and act accordingly.
In the macro version
#define strindex(target, source) ((size_t) strstr(target, source) - (size_t) target)
there is no such test. You determine the index by calculating the difference between strstr() and the base address target. This is fine so far, but what happens, when strstr() returns NULL?
Pointer arithmetic is defined with two pointers, pointing into the same array. As soon as the two pointers point into different arrays, or one pointing into an array and the other somewhere else, the behaviour is undefined.
Technically, when you calculate NULL - target, it might yield a negative value, but it also might not. If target points to the address of 0x0f0a3a90, you could have 0x0 - 0x0f0a3a90 and get a negative value. If target points to 0xfe830780 however, it might be interpreted as a negative number, and then 0x0 - 0xfe830780 could result in a positive number.
But the main point is, you have undefined behaviour. For further reading look for pointer arithmetic, e.g. C++: Pointer Arithmetic
your malloc is not allocating space for the null terminator, you need to malloc (strlen(string)+1).
The malloc with a char* works because a pointer (is normal) 4 bytes long, so you are allocating 4 times more memory than required - minus the 1 byte need for a null terminator.
The problem may lie here: malloc(sizeof(char)*(strlen(argv[1] - 3)) in main. You are subtracting 3 from argv[1].
I think you intended to use:
malloc(sizeof(char)*(strlen(argv[1]) - 2)); // Allocate one more space for '\0' character
Doing this makes strlen to access unallocated memory.
Your program may not fail here, but later, because it is simply undefined behavior.
There are several buffer overruns, but I think that the bug that makes you program crash is the following:
strncpy(target_counting, target_counting + i + 1, strlen(target_counting));
Note that the strings in strncpy may not overlap!
I suggest that you do a memmove instead, because memmove can handle overlapping buffers:
memmove(target_counting, target_counting + i + 1, strlen(target_counting + i + 1) + 1);
I think your main issue is here :
arg_parameter = (char *) malloc(sizeof(char)*(strlen(argv[1] - 3)));
especially here
strlen(argv[1] - 3)
you pass to strlen address of argv[1]-3 which is not valid address.
actually what you meant is strlen(argv[1]) - 3. As others said you also should add one char for \0 so strlen(argv[1]) - 2

Initializing an infinite number of char **

I'm making a raytracing engine in C using the minilibX library.
I want to be able to read in a .conf file the configuration for the scene to display:
For example:
(Az#Az 117)cat universe.conf
#randomcomment
obj:eye:x:y:z
light:sun:100
light:moon:test
The number of objects can vary between 1 and the infinite.
From now on, I'm reading the file, copying each line 1 by 1 in a char **tab, and mallocing by the number of objects found, like this:
void open_file(int fd, struct s_img *m)
{
int i;
char *s;
int curs_obj;
int curs_light;
i = 0;
curs_light = 0;
curs_obj = 0;
while (s = get_next_line(fd))
{
i = i + 1;
if (s[0] == 'l')
{
m->lights[curs_light] = s;
curs_light = curs_light + 1;
}
else if (s[0] == 'o')
{
m->objs[curs_obj] = s;
curs_obj = curs_obj + 1;
}
else if (s[0] != '#')
{
show_error(i, s);
stop_parsing(m);
}
}
Now, I want to be able to store each information of each tab[i] in a new char **tab, 1 for each object, using the ':' as a separation.
So I need to initialize and malloc an undetermined number of char **tab. How can I do that?
(Ps: I hope my code and my english are good enough for you to understand. And I'm using only the very basic function, like read, write, open, malloc... and I'm re-building everything else, like printf, get_line, and so on)
You can't allocate an indeterminate amount of memory; malloc doesn't support it. What you can do is to allocate enough memory for now and revise that later:
size_t buffer = 10;
char **tab = malloc(buffer);
//...
if (indexOfObjectToCreate > buffer) {
buffer *= 2;
tab = realloc(tab, buffer);
}
I'd use an alternative approach (as this is c, not c++) and allocate simply large buffers as we go by:
char *my_malloc(size_t n) {
static size_t space_left = 0;
static char *base = NULL;
if (base==NULL || space_left < n) base=malloc(space_left=BIG_N);
base +=n; return base-n;
}
Disclaimer: I've omitted the garbage collection stuff and testing return values and all safety measures to keep the routine short.
Another way to think this is to read the file in to a large enough mallocated array (you can check it with ftell), scan the buffer, replace delimiters, line feeds etc. with ascii zero characters and remember the starting locations of keywords.

join() or implode() in C

One thing I love about Python and PHP is the ability to make a string from array easily:
Python: ', '.join(['a', 'b', 'c'])
PHP: implode(', ', array('a', 'b', 'c'));
However, I was wondering if anybody had an intuitive and clear way to implement this in C. Thanks!
Sure, there are ways - just nothing built-in. Many C utility libraries have functions for this - eg, glib's g_strjoinv. You can also roll your own, for example:
static char *util_cat(char *dest, char *end, const char *str)
{
while (dest < end && *str)
*dest++ = *str++;
return dest;
}
size_t join_str(char *out_string, size_t out_bufsz, const char *delim, char **chararr)
{
char *ptr = out_string;
char *strend = out_string + out_bufsz;
while (ptr < strend && *chararr)
{
ptr = util_cat(ptr, strend, *chararr);
chararr++;
if (*chararr)
ptr = util_cat(ptr, strend, delim);
}
return ptr - out_string;
}
The main reason it's not built in is because the C standard library is very minimal; they wanted to make it easy to make new implementations of C, so you don't find as many utility functions. There's also the problem that C doesn't give you many guidelines about how to, for example, decide how many elements are in arrays (I used a NULL-array-element terminator convention in the example above).
For example there is such a function in GLib: g_strjoin and g_strjoinv. Probably any bigger library has such functions.
The easiest way is to use such libraries and be happy. It's also not too hard to write this by yourself (look at the other answers). The "big" problem is just that you have to be careful while allocating and freeing those strings. It's C ;-)
Edit: I just see that you used in both examples arrays. So just that you know: g_strjoinv is what you asked for.
I found a function that does this in ANSI C here. I adapted it and added a seperator argument. Make sure to free() the string after using it.
char* join_strings(char* strings[], char* seperator, int count) {
char* str = NULL; /* Pointer to the joined strings */
size_t total_length = 0; /* Total length of joined strings */
int i = 0; /* Loop counter */
/* Find total length of joined strings */
for (i = 0; i < count; i++) total_length += strlen(strings[i]);
total_length++; /* For joined string terminator */
total_length += strlen(seperator) * (count - 1); // for seperators
str = (char*) malloc(total_length); /* Allocate memory for joined strings */
str[0] = '\0'; /* Empty string we can append to */
/* Append all the strings */
for (i = 0; i < count; i++) {
strcat(str, strings[i]);
if (i < (count - 1)) strcat(str, seperator);
}
return str;
}

Resources