Hi!
----
Attached (as "astksh20130727_printf_w_gb18030_001.diff.txt") is a
prototype patch which handles two issues related to GB18030:
1. Currently ksh93 supports "\u[codepoint]" in printf(1) to write a
unicode character to stdout. However the current code assumes that
|wchar_t| in the current locale represents an unicode code point...
which isn't true for all locales (for example zn_CN.GB18030 on Solaris
uses GB18030 codepoints for |wchar_t| and not unicode codepoints). In
that case printf "\u[codepoint]" doesn't work.
The patch fixes this by using |iconv()| to convert between the UTF32
codepoint value and the locale's character set. If the requested
character can not be represented in the current locale/encoding printf
"\u[codepoint]" will return an empty string
2. The other issue is that some users greatly wish to use the
codepoint values of their locale and _not_ the unicode codepoint
value. Therefore the patch adds printf "\w[codepoint]" that a
codepoint can be specified using the wchar_t value.
Note that the patch is a _prototype_ ... if the general idea is OK
I'll craft a better patch...
* Questions (mainly for David&&Glenn):
- Is the patch OK so far ?
- Does libast have any code to detect whether the locale is a unicode locale ?
- Is there any reason that printf(1)'s "%b" format does not support
"\u[codepoint], e.g. bug or feature ? :-)
- Somehow I can't include <iconv.h> ... it seems the AST <iconv.h>
header is build later than src/lib/libast/string/chresc.c which causes
the build to fail... any idea why ?
----
Bye,
Roland
--
__ . . __
(o.\ \/ /.o) [email protected]
\__\/\/__/ MPEG specialist, C&&JAVA&&Sun&&Unix programmer
/O /==\ O\ TEL +49 641 3992797
(;O/ \/ \O;)
diff -r -u original/src/cmd/ksh93/data/builtins.c
build_print_w/src/cmd/ksh93/data/builtins.c
--- original/src/cmd/ksh93/data/builtins.c 2013-06-26 20:29:58.000000000
+0200
+++ build_print_w/src/cmd/ksh93/data/builtins.c 2013-08-05 03:53:00.744434090
+0200
@@ -1214,8 +1214,16 @@
"the collating element \aname\a.]"
"[+-?The escape sequence \b\\x{\b\ahex\a\b}\b expands to the "
"character corresponding to the hexidecimal value \ahex\a.]"
- "[+-?The escape sequence \b\\u{\b\ahex\a\b}\b expands to the unicode "
- "character corresponding to the hexidecimal value \ahex\a.]"
+ "[+-?The escape sequence \b\\u[\b\ahex\a\b]]\b or "
+ "\b\\u{\b\ahex\a\b}\b expands to the unicode character "
+ "corresponding to the unicode code point defined "
+ "by the hexidecimal value \ahex\a. If the character is "
+ "not available in the current locale the escape sequence "
+ "will return an empty string.]"
+ "[+-?The escape sequence \b\\w[\b\ahex\a\b]]\b or "
+ "\b\\w{\b\ahex\a\b}\b expands to the character "
+ "corresponding to the (wchar_t) code point defined "
+ "by the hexidecimal value \ahex\a in the current locale.]"
"[+-?The format modifier flag \b=\b can be used to center a field to "
"a specified width.]"
"[+-?The format modifier flag \bL\b can be used with the \bc\b and "
diff -r -u original/src/lib/libast/string/chresc.c
build_print_w/src/lib/libast/string/chresc.c
--- original/src/lib/libast/string/chresc.c 2013-07-16 20:02:13.000000000
+0200
+++ build_print_w/src/lib/libast/string/chresc.c 2013-08-05
03:04:27.063316193 +0200
@@ -38,6 +38,115 @@
#include <regex.h>
#endif
+#include <errno.h>
+#include <wchar.h>
+#include <endian.h>
+#include "/usr/include/iconv.h" // WHY ?
+#include <langinfo.h>
+#include <locale.h>
+
+
+static
+ssize_t ucs4_to_wchar(uint32_t *ucs4, size_t ucs4_len, wchar_t *wchar)
+{
+#ifdef HAS_ICONV_WCHAR_T
+ iconv_t cd;
+ char *inbuf;
+ char *outbuf;
+ size_t inbytesleft,
+ outbytesleft,
+ res,
+ wchar_buf_len;
+ int saved_errno;
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ cd = iconv_open("WCHAR_T", "UTF32LE");
+#elif __BYTE_ORDER == __BIG_ENDIAN
+ cd = iconv_open("WCHAR_T", "UTF32BE");
+#else
+#error Unknown __BYTE_ORDER
+#endif
+ if (cd == (iconv_t)-1)
+ return (-1);
+
+ inbytesleft = ucs4_len * sizeof(uint32_t);
+ wchar_buf_len = ucs4_len * sizeof(wchar_t);
+ inbuf = (char *)ucs4;
+ outbytesleft = wchar_buf_len;
+ outbuf = (char *)wchar;
+
+ res = iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+
+ saved_errno = errno;
+ (void)iconv_close(cd);
+ errno = saved_errno;
+
+#else /* HAS_ICONV_WCHAR_T */
+
+ iconv_t cd;
+ char *inbuf;
+ char *outbuf,
+ *outbuf_start;
+ size_t inbytesleft,
+ outbytesleft,
+ res,
+ mb_buf_len;
+ int saved_errno;
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ cd = iconv_open(nl_langinfo(CODESET), "UTF32LE");
+#elif __BYTE_ORDER == __BIG_ENDIAN
+ cd = iconv_open(nl_langinfo(CODESET), "UTF32BE");
+#else
+#error Unknown __BYTE_ORDER
+#endif
+ if (cd == (iconv_t)-1)
+ return (-1);
+
+ inbytesleft = ucs4_len * sizeof(uint32_t);
+ mb_buf_len = ucs4_len * MB_CUR_MAX;
+ inbuf = (char *)ucs4;
+ outbytesleft = mb_buf_len;
+ outbuf_start = (char *)malloc(mb_buf_len+2);
+ if(!outbuf_start)
+ {
+ saved_errno = errno;
+ (void)iconv_close(cd);
+ errno = saved_errno;
+ return(-1);
+ }
+
+ outbuf = outbuf_start;
+
+ res = iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+
+ if (res >= 0)
+ {
+ ssize_t len;
+ size_t i;
+
+ for(outbuf = outbuf_start, i = 0 ;
+ i < ucs4_len ;
+ i++, outbuf += len)
+ {
+ len = mbtowc(&wchar[i], outbuf, MB_CUR_MAX);
+ if (len < 0)
+ {
+ wchar[i]=L'\0';
+ break;
+ }
+ }
+ }
+
+ saved_errno = errno;
+ (void)iconv_close(cd);
+ free(outbuf_start);
+ errno = saved_errno;
+#endif
+ return (res);
+}
+
+
int
chrexp(register const char* s, char** p, int* m, register int flags)
{
@@ -47,9 +156,10 @@
const char* b;
char* r;
int n;
- int w;
+ bool w;
+ bool unicode;
- w = 0;
+ w = unicode = false;
for (;;)
{
b = s;
@@ -153,14 +263,18 @@
c = CC_vt;
break;
case 'u':
+ unicode = true;
+ case 'w':
q = s + 4;
goto wex;
case 'U':
+ unicode = true;
+ case 'W':
q = s + 8;
wex:
if (!(flags & FMT_EXP_WIDE))
goto noexpand;
- w = 1;
+ w = true;
goto hex;
case 'x':
q = s + 2;
@@ -191,7 +305,7 @@
break;
e = 0;
s++;
- if (w && *s == 'U' && *(s + 1)
== '+')
+ if (w && ((*s == 'U') || (*s ==
'W')) && *(s + 1) == '+')
s += 2;
continue;
case '}':
@@ -204,7 +318,7 @@
}
break;
}
- if (n <= 2 && !(flags & FMT_EXP_CHAR) || n > 2
&& (w = 1) && !(flags & FMT_EXP_WIDE))
+ if (n <= 2 && !(flags & FMT_EXP_CHAR) || n > 2
&& (w = true) && !(flags & FMT_EXP_WIDE))
{
c = '\\';
s = b;
@@ -217,7 +331,7 @@
break;
default:
if ((s - b) > 1)
- w = 1;
+ w = true;
break;
}
break;
@@ -226,7 +340,18 @@
if (p)
*p = (char*)s;
if (m)
- *m = w;
+ *m = w?1:0;
+
+ if (w && unicode && (c > 127))
+ {
+ uint32_t in = c;
+ wchar_t out = -1;
+
+ if (ucs4_to_wchar(&in, 1, &out) < 0)
+ c = -1;
+ else
+ c = out;
+ }
return c;
noexpand:
c = '\\';
diff -r -u original/src/lib/libast/string/stresc.c
build_print_w/src/lib/libast/string/stresc.c
--- original/src/lib/libast/string/stresc.c 2010-05-01 07:46:26.000000000
+0200
+++ build_print_w/src/lib/libast/string/stresc.c 2013-08-05
00:22:26.918700000 +0200
@@ -36,7 +36,7 @@
strexp(register char* s, int flags)
{
register char* t;
- register unsigned int c;
+ register int c;
char* b;
char* e;
int w;
@@ -48,6 +48,12 @@
{
c = chrexp(s - 1, &e, &w, flags);
s = e;
+
+ if (c < 0)
+ {
+ /* conversion failed == empty string */
+ continue;
+ }
if (w)
{
t += mbwide() ? mbconv(t, c) : wc2utf8(t, c);
_______________________________________________
ast-developers mailing list
[email protected]
http://lists.research.att.com/mailman/listinfo/ast-developers
