diff options
Diffstat (limited to 'manual')
-rw-r--r-- | manual/charset.texi | 71 | ||||
-rw-r--r-- | manual/examples/mbstouwcs.c | 49 |
2 files changed, 77 insertions, 43 deletions
diff --git a/manual/charset.texi b/manual/charset.texi index 6831ebec27..a63d67045f 100644 --- a/manual/charset.texi +++ b/manual/charset.texi @@ -643,8 +643,8 @@ and they also do not require it to be in the initial state. @cindex stateful The @code{mbrtowc} function (``multibyte restartable to wide character'') converts the next multibyte character in the string pointed -to by @var{s} into a wide character and stores it in the wide character -string pointed to by @var{pwc}. The conversion is performed according +to by @var{s} into a wide character and stores it in the location +pointed to by @var{pwc}. The conversion is performed according to the locale currently selected for the @code{LC_CTYPE} category. If the conversion for the character set used in the locale requires a state, the multibyte string is interpreted in the state represented by the @@ -652,7 +652,7 @@ object pointed to by @var{ps}. If @var{ps} is a null pointer, a static, internal state variable used only by the @code{mbrtowc} function is used. -If the next multibyte character corresponds to the NUL wide character, +If the next multibyte character corresponds to the null wide character, the return value of the function is @math{0} and the state object is afterwards in the initial state. If the next @var{n} or fewer bytes form a correct multibyte character, the return value is the number of @@ -665,50 +665,59 @@ by @var{pwc} if @var{pwc} is not null. If the first @var{n} bytes of the multibyte string possibly form a valid multibyte character but there are more than @var{n} bytes needed to complete it, the return value of the function is @code{(size_t) -2} and -no value is stored. Please note that this can happen even if @var{n} -has a value greater than or equal to @code{MB_CUR_MAX} since the input -might contain redundant shift sequences. +no value is stored in @code{*@var{pwc}}. The conversion state is +updated and all @var{n} input bytes are consumed and should not be +submitted again. Please note that this can happen even if @var{n} has a +value greater than or equal to @code{MB_CUR_MAX} since the input might +contain redundant shift sequences. If the first @code{n} bytes of the multibyte string cannot possibly form a valid multibyte character, no value is stored, the global variable @code{errno} is set to the value @code{EILSEQ}, and the function returns @code{(size_t) -1}. The conversion state is afterwards undefined. +As specified, the @code{mbrtowc} function could deal with multibyte +sequences which contain embedded null bytes (which happens in Unicode +encodings such as UTF-16), but @theglibc{} does not support such +multibyte encodings. When encountering a null input byte, the function +will either return zero, or return @code{(size_t) -1)} and report a +@code{EILSEQ} error. The @code{iconv} function can be used for +converting between arbitrary encodings. @xref{Generic Conversion +Interface}. + @pindex wchar.h @code{mbrtowc} was introduced in @w{Amendment 1} to @w{ISO C90} and is declared in @file{wchar.h}. @end deftypefun -Use of @code{mbrtowc} is straightforward. A function that copies a -multibyte string into a wide character string while at the same time -converting all lowercase characters into uppercase could look like this -(this is not the final version, just an example; it has no error -checking, and sometimes leaks memory): +A function that copies a multibyte string into a wide character string +while at the same time converting all lowercase characters into +uppercase could look like this: @smallexample @include mbstouwcs.c.texi @end smallexample -The use of @code{mbrtowc} should be clear. A single wide character is -stored in @code{@var{tmp}[0]}, and the number of consumed bytes is stored -in the variable @var{nbytes}. If the conversion is successful, the -uppercase variant of the wide character is stored in the @var{result} -array and the pointer to the input string and the number of available -bytes is adjusted. - -The only non-obvious thing about @code{mbrtowc} might be the way memory -is allocated for the result. The above code uses the fact that there -can never be more wide characters in the converted result than there are -bytes in the multibyte input string. This method yields a pessimistic -guess about the size of the result, and if many wide character strings -have to be constructed this way or if the strings are long, the extra -memory required to be allocated because the input string contains -multibyte characters might be significant. The allocated memory block can -be resized to the correct size before returning it, but a better solution -might be to allocate just the right amount of space for the result right -away. Unfortunately there is no function to compute the length of the wide -character string directly from the multibyte string. There is, however, a -function that does part of the work. +In the inner loop, a single wide character is stored in @code{wc}, and +the number of consumed bytes is stored in the variable @code{nbytes}. +If the conversion is successful, the uppercase variant of the wide +character is stored in the code{result} array and the pointer to the +input string and the number of available bytes is adjusted. If the +@code{mbrtowc} function returns zero, the null input byte has not been +converted, so it must be stored explicitly in the result. + +The above code uses the fact that there can never be more wide +characters in the converted result than there are bytes in the multibyte +input string. This method yields a pessimistic guess about the size of +the result, and if many wide character strings have to be constructed +this way or if the strings are long, the extra memory required to be +allocated because the input string contains multibyte characters might +be significant. The allocated memory block can be resized to the +correct size before returning it, but a better solution might be to +allocate just the right amount of space for the result right away. +Unfortunately there is no function to compute the length of the wide +character string directly from the multibyte string. There is, however, +a function that does part of the work. @deftypefun size_t mbrlen (const char *restrict @var{s}, size_t @var{n}, mbstate_t *@var{ps}) @standards{ISO, wchar.h} diff --git a/manual/examples/mbstouwcs.c b/manual/examples/mbstouwcs.c index 5d223da2ae..c94e1fa790 100644 --- a/manual/examples/mbstouwcs.c +++ b/manual/examples/mbstouwcs.c @@ -1,3 +1,4 @@ +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <wchar.h> @@ -7,22 +8,46 @@ wchar_t * mbstouwcs (const char *s) { - size_t len = strlen (s); - wchar_t *result = malloc ((len + 1) * sizeof (wchar_t)); + /* Include the null terminator in the conversion. */ + size_t len = strlen (s) + 1; + wchar_t *result = reallocarray (NULL, len, sizeof (wchar_t)); + if (result == NULL) + return NULL; + wchar_t *wcp = result; - wchar_t tmp[1]; mbstate_t state; - size_t nbytes; - memset (&state, '\0', sizeof (state)); - while ((nbytes = mbrtowc (tmp, s, len, &state)) > 0) + + while (true) { - if (nbytes >= (size_t) -2) - /* Invalid input string. */ - return NULL; - *wcp++ = towupper (tmp[0]); - len -= nbytes; - s += nbytes; + wchar_t wc; + size_t nbytes = mbrtowc (&wc, s, len, &state); + if (nbytes == 0) + { + /* Terminate the result string. */ + *wcp = L'\0'; + break; + } + else if (nbytes == (size_t) -2) + { + /* Truncated input string. */ + errno = EILSEQ; + free (result); + return NULL; + } + else if (nbytes == (size_t) -1) + { + /* Some other error (including EILSEQ). */ + free (result); + return NULL; + } + else + { + /* A character was converted. */ + *wcp++ = towupper (wc); + len -= nbytes; + s += nbytes; + } } return result; } |