implement wprintf family of functions

this implementation is extremely ugly and inefficient, but it avoids a
good deal of code duplication and bloat. it may be cleaned up later to
eliminate the remaining code duplication and some of the warts, but i
don't really care about its performance.

note that swprintf is not yet implemented.

4 files changed, 387 insertions, 0 deletions

diff --git a/src/stdio/fwprintf.c b/src/stdio/fwprintf.c
new file mode 100644
index 00000000..26d9729a
--- /dev/null
+++ b/src/stdio/fwprintf.c
@@ -0,0 +1,13 @@
+#include <stdio.h>
+#include <stdarg.h>
+#include <wchar.h>
+
+int fwprintf(FILE *f, const wchar_t *fmt, ...)
+{
+	int ret;
+	va_list ap;
+	va_start(ap, fmt);
+	ret = vfwprintf(f, fmt, ap);
+	va_end(ap);
+	return ret;
+}
diff --git a/src/stdio/vfwprintf.c b/src/stdio/vfwprintf.c
new file mode 100644
index 00000000..42ce304f
--- /dev/null
+++ b/src/stdio/vfwprintf.c
@@ -0,0 +1,354 @@
+#include "stdio_impl.h"
+
+/* Convenient bit representation for modifier flags, which all fall
+ * within 31 codepoints of the space character. */
+
+#define ALT_FORM   (1U<<'#'-' ')
+#define ZERO_PAD   (1U<<'0'-' ')
+#define LEFT_ADJ   (1U<<'-'-' ')
+#define PAD_POS    (1U<<' '-' ')
+#define MARK_POS   (1U<<'+'-' ')
+#define GROUPED    (1U<<'\''-' ')
+
+#define FLAGMASK (ALT_FORM|ZERO_PAD|LEFT_ADJ|PAD_POS|MARK_POS|GROUPED)
+
+#if UINT_MAX == ULONG_MAX
+#define LONG_IS_INT
+#endif
+
+#if SIZE_MAX != ULONG_MAX || UINTMAX_MAX != ULLONG_MAX
+#define ODD_TYPES
+#endif
+
+/* State machine to accept length modifiers + conversion specifiers.
+ * Result is 0 on failure, or an argument type to pop on success. */
+
+enum {
+	BARE, LPRE, LLPRE, HPRE, HHPRE, BIGLPRE,
+	ZTPRE, JPRE,
+	STOP,
+	PTR, INT, UINT, ULLONG,
+#ifndef LONG_IS_INT
+	LONG, ULONG,
+#else
+#define LONG INT
+#define ULONG UINT
+#endif
+	SHORT, USHORT, CHAR, UCHAR,
+#ifdef ODD_TYPES
+	LLONG, SIZET, IMAX, UMAX, PDIFF, UIPTR,
+#else
+#define LLONG ULLONG
+#define SIZET ULONG
+#define IMAX LLONG
+#define UMAX ULLONG
+#define PDIFF LONG
+#define UIPTR ULONG
+#endif
+	DBL, LDBL,
+	NOARG,
+	MAXSTATE
+};
+
+#define S(x) [(x)-'A']
+
+static const unsigned char states[]['z'-'A'+1] = {
+	{ /* 0: bare types */
+		S('d') = INT, S('i') = INT,
+		S('o') = UINT, S('u') = UINT, S('x') = UINT, S('X') = UINT,
+		S('e') = DBL, S('f') = DBL, S('g') = DBL, S('a') = DBL,
+		S('E') = DBL, S('F') = DBL, S('G') = DBL, S('A') = DBL,
+		S('c') = CHAR, S('C') = INT,
+		S('s') = PTR, S('S') = PTR, S('p') = UIPTR, S('n') = PTR,
+		S('m') = NOARG,
+		S('l') = LPRE, S('h') = HPRE, S('L') = BIGLPRE,
+		S('z') = ZTPRE, S('j') = JPRE, S('t') = ZTPRE,
+	}, { /* 1: l-prefixed */
+		S('d') = LONG, S('i') = LONG,
+		S('o') = ULONG, S('u') = ULONG, S('x') = ULONG, S('X') = ULONG,
+		S('c') = INT, S('s') = PTR, S('n') = PTR,
+		S('l') = LLPRE,
+	}, { /* 2: ll-prefixed */
+		S('d') = LLONG, S('i') = LLONG,
+		S('o') = ULLONG, S('u') = ULLONG,
+		S('x') = ULLONG, S('X') = ULLONG,
+		S('n') = PTR,
+	}, { /* 3: h-prefixed */
+		S('d') = SHORT, S('i') = SHORT,
+		S('o') = USHORT, S('u') = USHORT,
+		S('x') = USHORT, S('X') = USHORT,
+		S('n') = PTR,
+		S('h') = HHPRE,
+	}, { /* 4: hh-prefixed */
+		S('d') = CHAR, S('i') = CHAR,
+		S('o') = UCHAR, S('u') = UCHAR,
+		S('x') = UCHAR, S('X') = UCHAR,
+		S('n') = PTR,
+	}, { /* 5: L-prefixed */
+		S('e') = LDBL, S('f') = LDBL, S('g') = LDBL, S('a') = LDBL,
+		S('E') = LDBL, S('F') = LDBL, S('G') = LDBL, S('A') = LDBL,
+		S('n') = PTR,
+	}, { /* 6: z- or t-prefixed (assumed to be same size) */
+		S('d') = PDIFF, S('i') = PDIFF,
+		S('o') = SIZET, S('u') = SIZET,
+		S('x') = SIZET, S('X') = SIZET,
+		S('n') = PTR,
+	}, { /* 7: j-prefixed */
+		S('d') = IMAX, S('i') = IMAX,
+		S('o') = UMAX, S('u') = UMAX,
+		S('x') = UMAX, S('X') = UMAX,
+		S('n') = PTR,
+	}
+};
+
+#define OOB(x) ((unsigned)(x)-'A' > 'z'-'A')
+
+union arg
+{
+	uintmax_t i;
+	long double f;
+	void *p;
+};
+
+static void pop_arg(union arg *arg, int type, va_list *ap)
+{
+	/* Give the compiler a hint for optimizing the switch. */
+	if ((unsigned)type > MAXSTATE) return;
+	switch (type) {
+	       case PTR:	arg->p = va_arg(*ap, void *);
+	break; case INT:	arg->i = va_arg(*ap, int);
+	break; case UINT:	arg->i = va_arg(*ap, unsigned int);
+#ifndef LONG_IS_INT
+	break; case LONG:	arg->i = va_arg(*ap, long);
+	break; case ULONG:	arg->i = va_arg(*ap, unsigned long);
+#endif
+	break; case ULLONG:	arg->i = va_arg(*ap, unsigned long long);
+	break; case SHORT:	arg->i = (short)va_arg(*ap, int);
+	break; case USHORT:	arg->i = (unsigned short)va_arg(*ap, int);
+	break; case CHAR:	arg->i = (signed char)va_arg(*ap, int);
+	break; case UCHAR:	arg->i = (unsigned char)va_arg(*ap, int);
+#ifdef ODD_TYPES
+	break; case LLONG:	arg->i = va_arg(*ap, long long);
+	break; case SIZET:	arg->i = va_arg(*ap, size_t);
+	break; case IMAX:	arg->i = va_arg(*ap, intmax_t);
+	break; case UMAX:	arg->i = va_arg(*ap, uintmax_t);
+	break; case PDIFF:	arg->i = va_arg(*ap, ptrdiff_t);
+	break; case UIPTR:	arg->i = (uintptr_t)va_arg(*ap, void *);
+#endif
+	break; case DBL:	arg->f = va_arg(*ap, double);
+	break; case LDBL:	arg->f = va_arg(*ap, long double);
+	}
+}
+
+static void out(FILE *f, const wchar_t *s, size_t l)
+{
+	while (l--) fputwc(*s++, f);
+}
+
+static int getint(wchar_t **s) {
+	int i;
+	for (i=0; iswdigit(**s); (*s)++)
+		i = 10*i + (**s-'0');
+	return i;
+}
+
+static const char sizeprefix['y'-'a'] = {
+['a'-'a']='L', ['e'-'a']='L', ['f'-'a']='L', ['g'-'a']='L',
+['d'-'a']='j', ['i'-'a']='j', ['o'-'a']='j', ['u'-'a']='j', ['x'-'a']='j',
+['p'-'a']='j'
+};
+
+static int wprintf_core(FILE *f, const wchar_t *fmt, va_list *ap, union arg *nl_arg, int *nl_type)
+{
+	wchar_t *a, *z, *s=(wchar_t *)fmt, *s0;
+	unsigned l10n=0, litpct, fl;
+	int w, p;
+	union arg arg;
+	int argpos;
+	unsigned st, ps;
+	int cnt=0, l=0;
+	int i;
+	int t;
+	char *bs;
+	char charfmt[16];
+	wchar_t wc;
+
+	for (;;) {
+		/* Update output count, end loop when fmt is exhausted */
+		if (cnt >= 0) {
+			if (l > INT_MAX - cnt) {
+				if (!ferror(f)) errno = EOVERFLOW;
+				cnt = -1;
+			} else cnt += l;
+		}
+		if (!*s) break;
+
+		/* Handle literal text and %% format specifiers */
+		for (a=s; *s && *s!='%'; s++);
+		litpct = wcsspn(s, L"%")/2; /* Optimize %%%% runs */
+		z = s+litpct;
+		s += 2*litpct;
+		l = z-a;
+		if (f) out(f, a, l);
+		if (l) continue;
+
+		if (iswdigit(s[1]) && s[2]=='$') {
+			l10n=1;
+			argpos = s[1]-'0';
+			s+=3;
+		} else {
+			argpos = -1;
+			s++;
+		}
+
+		/* Read modifier flags */
+		for (fl=0; (unsigned)*s-' '<32 && (FLAGMASK&(1U<<*s-' ')); s++)
+			fl |= 1U<<*s-' ';
+
+		/* Read field width */
+		if (*s=='*') {
+			if (iswdigit(s[1]) && s[2]=='$') {
+				l10n=1;
+				nl_type[s[1]-'0'] = INT;
+				w = nl_arg[s[1]-'0'].i;
+				s+=3;
+			} else if (!l10n) {
+				w = f ? va_arg(*ap, int) : 0;
+				s++;
+			} else return -1;
+			if (w<0) fl|=LEFT_ADJ, w=-w;
+		} else if ((w=getint(&s))<0) return -1;
+
+		/* Read precision */
+		if (*s=='.' && s[1]=='*') {
+			if (isdigit(s[2]) && s[3]=='$') {
+				nl_type[s[2]-'0'] = INT;
+				p = nl_arg[s[2]-'0'].i;
+				s+=4;
+			} else if (!l10n) {
+				p = f ? va_arg(*ap, int) : 0;
+				s+=2;
+			} else return -1;
+		} else if (*s=='.') {
+			s++;
+			p = getint(&s);
+		} else p = -1;
+
+		/* Format specifier state machine */
+		s0=s;
+		st=0;
+		do {
+			if (OOB(*s)) return -1;
+			ps=st;
+			st=states[st]S(*s++);
+		} while (st-1<STOP);
+		if (!st) return -1;
+
+		/* Check validity of argument type (nl/normal) */
+		if (st==NOARG) {
+			if (argpos>=0) return -1;
+			else if (!f) continue;
+		} else {
+			if (argpos>=0) nl_type[argpos]=st, arg=nl_arg[argpos];
+			else if (f) pop_arg(&arg, st, ap);
+			else return 0;
+		}
+
+		if (!f) continue;
+		t = s[-1];
+		if (ps && (t&15)==3) t&=~32;
+
+		switch (t) {
+		case 'n':
+			switch(ps) {
+			case BARE: *(int *)arg.p = cnt; break;
+			case LPRE: *(long *)arg.p = cnt; break;
+			case LLPRE: *(long long *)arg.p = cnt; break;
+			case HPRE: *(unsigned short *)arg.p = cnt; break;
+			case HHPRE: *(unsigned char *)arg.p = cnt; break;
+			case ZTPRE: *(size_t *)arg.p = cnt; break;
+			case JPRE: *(uintmax_t *)arg.p = cnt; break;
+			}
+			continue;
+		case 'c':
+			fputwc(btowc(arg.i), f);
+			l = 1;
+			continue;
+		case 'C':
+			fputwc(arg.i, f);
+			l = 1;
+			continue;
+		case 'S':
+			a = arg.p;
+			z = wmemchr(a, 0, p);
+			if (!z) z=a+p;
+			else p=z-a;
+			if (w<p) w=p;
+			if (!(fl&LEFT_ADJ)) fprintf(f, "%.*s", w-p, "");
+			out(f, a, p);
+			if ((fl&LEFT_ADJ)) fprintf(f, "%.*s", w-p, "");
+			l=w;
+			continue;
+		case 's':
+			bs = arg.p;
+			if (p<0) p = INT_MAX;
+			for (l=0; l<p && (i=mbtowc(&wc, bs, MB_LEN_MAX))>0; bs+=i, l++);
+			if (i<0) return -1;
+			p=l;
+			if (w<p) w=p;
+			if (!(fl&LEFT_ADJ)) fprintf(f, "%.*s", w-p, "");
+			bs = arg.p;
+			while (l--) {
+				i=mbtowc(&wc, bs, MB_LEN_MAX);
+				bs+=i;
+				fputwc(wc, f);
+			}
+			if ((fl&LEFT_ADJ)) fprintf(f, "%.*s", w-p, "");
+			l=w;
+			continue;
+		}
+
+		snprintf(charfmt, sizeof charfmt, "%%%s%s%s%s%s*.*%c%c",
+			"#"+!(fl & ALT_FORM),
+			"+"+!(fl & MARK_POS),
+			"-"+!(fl & LEFT_ADJ),
+			" "+!(fl & PAD_POS),
+			"0"+!(fl & ZERO_PAD),
+			sizeprefix[(t|32)-'a'], t);
+
+		switch (t|32) {
+		case 'a': case 'e': case 'f': case 'g':
+			l = fprintf(f, charfmt, w, p, arg.f);
+			break;
+		case 'd': case 'i': case 'o': case 'u': case 'x': case 'p':
+			l = fprintf(f, charfmt, w, p, arg.i);
+			break;
+		}
+	}
+
+	if (f) return cnt;
+	if (!l10n) return 0;
+
+	for (i=1; i<=NL_ARGMAX && nl_type[i]; i++)
+		pop_arg(nl_arg+i, nl_type[i], ap);
+	for (; i<=NL_ARGMAX && !nl_type[i]; i++);
+	if (i<=NL_ARGMAX) return -1;
+	return 1;
+}
+
+int vfwprintf(FILE *f, const wchar_t *fmt, va_list ap)
+{
+	va_list ap2;
+	int nl_type[NL_ARGMAX] = {0};
+	union arg nl_arg[NL_ARGMAX];
+	int ret;
+
+	va_copy(ap2, ap);
+	if (wprintf_core(0, fmt, &ap2, nl_arg, nl_type) < 0) return -1;
+
+	FLOCK(f);
+	ret = wprintf_core(f, fmt, &ap2, nl_arg, nl_type);
+	FUNLOCK(f);
+	va_end(ap2);
+	return ret;
+}
diff --git a/src/stdio/vwprintf.c b/src/stdio/vwprintf.c
new file mode 100644
index 00000000..c1923e62
--- /dev/null
+++ b/src/stdio/vwprintf.c
@@ -0,0 +1,7 @@
+#include <stdio.h>
+#include <wchar.h>
+
+int vwprintf(const wchar_t *fmt, va_list ap)
+{
+	return vfwprintf(stdout, fmt, ap);
+}
diff --git a/src/stdio/wprintf.c b/src/stdio/wprintf.c
new file mode 100644
index 00000000..20ca61a0
--- /dev/null
+++ b/src/stdio/wprintf.c
@@ -0,0 +1,13 @@
+#include <stdio.h>
+#include <stdarg.h>
+#include <wchar.h>
+
+int wprintf(const wchar_t *fmt, ...)
+{
+	int ret;
+	va_list ap;
+	va_start(ap, fmt);
+	ret = vwprintf(fmt, ap);
+	va_end(ap);
+	return ret;
+}