4 files changed, 43 insertions, 20 deletions

diff --git a/src/internal/shgetc.c b/src/internal/shgetc.c
index e878b00a..ebd5fae7 100644
--- a/src/internal/shgetc.c
+++ b/src/internal/shgetc.c
@@ -1,10 +1,16 @@
 #include "shgetc.h"
 
+/* The shcnt field stores the number of bytes read so far, offset by
+ * the value of buf-rpos at the last function call (__shlim or __shgetc),
+ * so that between calls the inline shcnt macro can add rpos-buf to get
+ * the actual count. */
+
 void __shlim(FILE *f, off_t lim)
 {
 	f->shlim = lim;
-	f->shcnt = f->rend - f->rpos;
-	if (lim && f->shcnt > lim)
+	f->shcnt = f->buf - f->rpos;
+	/* If lim is nonzero, rend must be a valid pointer. */
+	if (lim && f->rend - f->rpos > lim)
 		f->shend = f->rpos + lim;
 	else
 		f->shend = f->rend;
@@ -13,15 +19,18 @@ void __shlim(FILE *f, off_t lim)
 int __shgetc(FILE *f)
 {
 	int c;
-	if (f->shlim && f->shcnt >= f->shlim || (c=__uflow(f)) < 0) {
+	off_t cnt = shcnt(f);
+	if (f->shlim && cnt >= f->shlim || (c=__uflow(f)) < 0) {
+		f->shcnt = f->buf - f->rpos + cnt;
 		f->shend = 0;
 		return EOF;
 	}
-	if (f->shlim && f->rend - f->rpos > f->shlim - f->shcnt - 1)
-		f->shend = f->rpos + (f->shlim - f->shcnt - 1);
+	cnt++;
+	if (f->shlim && f->rend - f->rpos > f->shlim - cnt)
+		f->shend = f->rpos + (f->shlim - cnt);
 	else
 		f->shend = f->rend;
-	if (f->rend) f->shcnt += f->rend - f->rpos + 1;
+	f->shcnt = f->buf - f->rpos + cnt;
 	if (f->rpos[-1] != c) f->rpos[-1] = c;
 	return c;
 }
diff --git a/src/internal/shgetc.h b/src/internal/shgetc.h
index 210f6468..1c30f75f 100644
--- a/src/internal/shgetc.h
+++ b/src/internal/shgetc.h
@@ -1,9 +1,32 @@
 #include "stdio_impl.h"
 
+/* Scan helper "stdio" functions for use by scanf-family and strto*-family
+ * functions. These accept either a valid stdio FILE, or a minimal pseudo
+ * FILE whose buffer pointers point into a null-terminated string. In the
+ * latter case, the sh_fromstring macro should be used to setup the FILE;
+ * the rest of the structure can be left uninitialized.
+ *
+ * To begin using these functions, shlim must first be called on the FILE
+ * to set a field width limit, or 0 for no limit. For string pseudo-FILEs,
+ * a nonzero limit is not valid and produces undefined behavior. After that,
+ * shgetc, shunget, and shcnt are valid as long as no other stdio functions
+ * are called on the stream.
+ *
+ * When used with a real FILE object, shunget has only one byte of pushback
+ * available. Further shunget (up to a limit of the stdio UNGET buffer size)
+ * will adjust the position but will not restore the data to be read again.
+ * This functionality is needed for the wcsto*-family functions, where it's
+ * okay because the FILE will be discarded immediately anyway. When used
+ * with string pseudo-FILEs, shunget has unlimited pushback, back to the
+ * beginning of the string. */
+
 hidden void __shlim(FILE *, off_t);
 hidden int __shgetc(FILE *);
 
-#define shcnt(f) ((f)->shcnt + ((f)->rpos - (f)->rend))
+#define shcnt(f) ((f)->shcnt + ((f)->rpos - (f)->buf))
 #define shlim(f, lim) __shlim((f), (lim))
-#define shgetc(f) (((f)->rpos < (f)->shend) ? *(f)->rpos++ : __shgetc(f))
+#define shgetc(f) (((f)->rpos != (f)->shend) ? *(f)->rpos++ : __shgetc(f))
 #define shunget(f) ((f)->shend ? (void)(f)->rpos-- : (void)0)
+
+#define sh_fromstring(f, s) \
+	((f)->buf = (f)->rpos = (void *)(s), (f)->rend = (void*)-1)
diff --git a/src/stdlib/strtod.c b/src/stdlib/strtod.c
index a898b1d4..a5d0118a 100644
--- a/src/stdlib/strtod.c
+++ b/src/stdlib/strtod.c
@@ -5,10 +5,8 @@
 
 static long double strtox(const char *s, char **p, int prec)
 {
-	FILE f = {
-		.buf = (void *)s, .rpos = (void *)s,
-		.rend = (void *)-1, .lock = -1
-	};
+	FILE f;
+	sh_fromstring(&f, s);
 	shlim(&f, 0);
 	long double y = __floatscan(&f, prec, 1);
 	off_t cnt = shcnt(&f);
diff --git a/src/stdlib/strtol.c b/src/stdlib/strtol.c
index d82ecf7f..bfefea69 100644
--- a/src/stdlib/strtol.c
+++ b/src/stdlib/strtol.c
@@ -7,15 +7,8 @@
 
 static unsigned long long strtox(const char *s, char **p, int base, unsigned long long lim)
 {
-	/* FIXME: use a helper function or macro to setup the FILE */
 	FILE f;
-	f.flags = 0;
-	f.buf = f.rpos = (void *)s;
-	if ((size_t)s > (size_t)-1/2)
-		f.rend = (void *)-1;
-	else
-		f.rend = (unsigned char *)s+(size_t)-1/2;
-	f.lock = -1;
+	sh_fromstring(&f, s);
 	shlim(&f, 0);
 	unsigned long long y = __intscan(&f, base, 1, lim);
 	if (p) {