From 754bbf7a25a8dda49b5d08ef0d0443bbf5af0e36 Mon Sep 17 00:00:00 2001 From: Craig Jennings Date: Sun, 7 Apr 2024 13:41:34 -0500 Subject: new repository --- devdocs/c/string%2Fmultibyte%2Fmbrtowc.html | 67 +++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 devdocs/c/string%2Fmultibyte%2Fmbrtowc.html (limited to 'devdocs/c/string%2Fmultibyte%2Fmbrtowc.html') diff --git a/devdocs/c/string%2Fmultibyte%2Fmbrtowc.html b/devdocs/c/string%2Fmultibyte%2Fmbrtowc.html new file mode 100644 index 00000000..9f8d4dea --- /dev/null +++ b/devdocs/c/string%2Fmultibyte%2Fmbrtowc.html @@ -0,0 +1,67 @@ +

mbrtowc

Defined in header <wchar.h> 
size_t mbrtowc( wchar_t* pwc, const char* s, size_t n, mbstate_t* ps );
+		 (since C95) 
size_t mbrtowc( wchar_t *restrict pwc, const char *restrict s, size_t n,
+                mbstate_t *restrict ps );
+		 (since C99)

Converts a narrow multibyte character to its wide character representation.

+

If s is not a null pointer, inspects at most n bytes of the multibyte character string, beginning with the byte pointed to by s to determine the number of bytes necessary to complete the next multibyte character (including any shift sequences, and taking into account the current multibyte conversion state *ps). If the function determines that the next multibyte character in s is complete and valid, converts it to the corresponding wide character and stores it in *pwc (if pwc is not null).

+

If s is a null pointer, the values of n and pwc are ignored and call is equivalent to mbrtowc(NULL, "", 1, ps).

+

If the wide character produced is the null character, the conversion state stored in *ps is the initial shift state.

+

If the environment macro __STDC_ISO_10646__ is defined, the values of type wchar_t are the same as the short identifiers of the characters in the Unicode required set (typically UTF-32 encoding); otherwise, it is implementation-defined. In any case, the multibyte character encoding used by this function is specified by the currently active C locale.

+

Parameters

+ + + + +
pwc - pointer to the location where the resulting wide character will be written
s - pointer to the multibyte character string used as input
n - limit on the number of bytes in s that can be examined
ps - pointer to the conversion state used when interpreting the multibyte character string

Return value

The first of the following that applies:

+

Example

#include <stdio.h>
+#include <locale.h>
+#include <string.h>
+#include <wchar.h>
+ 
+int main(void)
+{
+    setlocale(LC_ALL, "en_US.utf8");
+    mbstate_t state;
+    memset(&state, 0, sizeof state);
+    char in[] = u8"z\u00df\u6c34\U0001F34C"; // or u8"zß水🍌"
+    size_t in_sz = sizeof in / sizeof *in;
+ 
+    printf("Processing %zu UTF-8 code units: [ ", in_sz);
+    for(size_t n = 0; n < in_sz; ++n) printf("%#x ", (unsigned char)in[n]);
+    puts("]");
+ 
+    wchar_t out[in_sz];
+    char *p_in = in, *end = in + in_sz;
+    wchar_t *p_out = out;
+    int rc;
+    while((rc = mbrtowc(p_out, p_in, end - p_in, &state)) > 0)
+    {
+        p_in += rc;
+        p_out += 1;
+    }
+ 
+    size_t out_sz = p_out - out + 1;
+    printf("into %zu wchar_t units: [ ", out_sz);
+    for(size_t x = 0; x < out_sz; ++x) printf("%#x ", out[x]);
+    puts("]");
+}

Output:

+
Processing 11 UTF-8 code units: [ 0x7a 0xc3 0x9f 0xe6 0xb0 0xb4 0xf0 0x9f 0x8d 0x8c 0 ]
+into 5 wchar_t units: [ 0x7a 0xdf 0x6c34 0x1f34c 0 ]

References

See also

+ + +
converts the next multibyte character to wide character
(function)
+
(C95)(C11)
 converts a wide character to its multibyte representation, given state
(function)
C++ documentation for mbrtowc
+

+ © cppreference.com
Licensed under the Creative Commons Attribution-ShareAlike Unported License v3.0.
+ https://en.cppreference.com/w/c/string/multibyte/mbrtowc +

+
-- cgit v1.2.3