libpayload: UTF-16LE to ASCII conversion

This patch adds a simple function to convert a string in UTF-16LE
to ASCII.

TEST=Ran against a string found in a GPT with the intended outcome
BRANCH=none
BUG=none

Signed-off-by: Dan Ehrenberg <dehrenberg@chromium.org>
Change-Id: I50ca5bfdfbef9e084321b2beb1b8d4194ca5af9c
Reviewed-on: https://chromium-review.googlesource.com/231456
Reviewed-by: Julius Werner <jwerner@chromium.org>
This commit is contained in:
Dan Ehrenberg 2014-11-21 15:50:27 -08:00 committed by chrome-internal-fetch
commit 1104db8328
2 changed files with 26 additions and 0 deletions

View file

@ -67,6 +67,13 @@ char* strtok(char *str, const char *delim);
char* strtok_r(char *str, const char *delim, char **ptr);
/** @} */
/**
* @defgroup string Unicode functions
* @{
*/
char *utf16le_to_ascii(uint16_t *utf16_string, int maxlen);
/** @} */
/**
* @defgroup string OpenBSD based safe string functions
* @{

View file

@ -643,3 +643,22 @@ void perror(const char *s)
{
printf("%s: %d\n", s?s:"(none)", errno);
}
/**
* Simple routine to convert UTF-16 to ASCII, giving up with ? if too high.
* A single code point may convert to ?? if in not in the BMP.
* @param utf16_string A string encoded in UTF-16LE
* @param maxlen Maximum possible length of the string in code points
* @return Newly allocated ASCII string
*/
char *utf16le_to_ascii(uint16_t *utf16_string, int maxlen)
{
char *ascii_string = xmalloc(maxlen + 1); /* +1 for trailing \0 */
ascii_string[maxlen] = '\0';
int i;
for (i = 0; i < maxlen; i++) {
uint16_t wchar = utf16_string[i];
ascii_string[i] = wchar > 0x7f ? '?' : (char)wchar;
}
return ascii_string;
}