PyString_FromFormat() and PyString_FromFormatV(): Largely ripped from

    PyErr_Format() these new C API methods can be used instead of
    sprintf()'s into hardcoded char* buffers.  This allows us to fix
    many situation where long package, module, or class names get
    truncated in reprs.

    PyString_FromFormat() is the varargs variety.
    PyString_FromFormatV() is the va_list variety

    Original PyErr_Format() code was modified to allow %p and %ld
    expansions.

    Many reprs were converted to this, checkins coming soo.  Not
    changed: complex_repr(), float_repr(), float_print(), float_str(),
    int_repr().  There may be other candidates not yet converted.

    Closes patch #454743.

2 files changed, 159 insertions, 0 deletions

diff --git a/Include/stringobject.h b/Include/stringobject.h
index 96f371e..2d9ed2d 100644
--- a/Include/stringobject.h
+++ b/Include/stringobject.h
@@ -7,6 +7,8 @@
 extern "C" {
 #endif
 
+#include <stdarg.h>
+
 /*
 Type PyStringObject represents a character string.  An extra zero byte is
 reserved at the end to ensure it is zero-terminated, but a size is
@@ -53,6 +55,8 @@ extern DL_IMPORT(PyTypeObject) PyString_Type;
 
 extern DL_IMPORT(PyObject *) PyString_FromStringAndSize(const char *, int);
 extern DL_IMPORT(PyObject *) PyString_FromString(const char *);
+extern DL_IMPORT(PyObject *) PyString_FromFormatV(const char*, va_list);
+extern DL_IMPORT(PyObject *) PyString_FromFormat(const char*, ...);
 extern DL_IMPORT(int) PyString_Size(PyObject *);
 extern DL_IMPORT(char *) PyString_AsString(PyObject *);
 extern DL_IMPORT(void) PyString_Concat(PyObject **, PyObject *);
diff --git a/Objects/stringobject.c b/Objects/stringobject.c
index a8e063e..3acc69f 100644
--- a/Objects/stringobject.c
+++ b/Objects/stringobject.c
@@ -147,6 +147,161 @@ PyString_FromString(const char *str)
 	return (PyObject *) op;
 }
 
+PyObject *
+PyString_FromFormatV(const char *format, va_list vargs)
+{
+	va_list count = vargs;
+	int n = 0;
+	const char* f;
+	char *s;
+	PyObject* string;
+
+	/* step 1: figure out how large a buffer we need */
+	for (f = format; *f; f++) {
+		if (*f == '%') {
+			const char* p = f;
+			while (*++f && *f != '%' && !isalpha(Py_CHARMASK(*f)))
+				;
+
+			/* skip the 'l' in %ld, since it doesn't change the
+			   width.  although only %d is supported (see
+			   "expand" section below), others can be easily
+			   add */
+			if (*f == 'l' && *(f+1) == 'd')
+				++f;
+			
+			switch (*f) {
+			case 'c':
+				(void)va_arg(count, int);
+				/* fall through... */
+			case '%':
+				n++;
+				break;
+			case 'd': case 'i': case 'x':
+				(void) va_arg(count, int);
+				/* 20 bytes should be enough to hold a 64-bit
+				   integer */
+				n += 20;
+				break;
+			case 's':
+				s = va_arg(count, char*);
+				n += strlen(s);
+				break;
+			case 'p':
+				(void) va_arg(count, int);
+				/* maximum 64-bit pointer representation:
+				 * 0xffffffffffffffff
+				 * so 19 characters is enough.
+				 */
+				n += 19;
+				break;
+			default:
+				/* if we stumble upon an unknown
+				   formatting code, copy the rest of
+				   the format string to the output
+				   string. (we cannot just skip the
+				   code, since there's no way to know
+				   what's in the argument list) */ 
+				n += strlen(p);
+				goto expand;
+			}
+		} else
+			n++;
+	}
+ expand:
+	/* step 2: fill the buffer */
+	string = PyString_FromStringAndSize(NULL, n);
+	if (!string)
+		return NULL;
+	
+	s = PyString_AsString(string);
+
+	for (f = format; *f; f++) {
+		if (*f == '%') {
+			const char* p = f++;
+			int i, longflag = 0;
+			/* parse the width.precision part (we're only
+			   interested in the precision value, if any) */
+			n = 0;
+			while (isdigit(Py_CHARMASK(*f)))
+				n = (n*10) + *f++ - '0';
+			if (*f == '.') {
+				f++;
+				n = 0;
+				while (isdigit(Py_CHARMASK(*f)))
+					n = (n*10) + *f++ - '0';
+			}
+			while (*f && *f != '%' && !isalpha(Py_CHARMASK(*f)))
+				f++;
+			/* handle the long flag, but only for %ld.  others
+			   can be added when necessary. */
+			if (*f == 'l' && *(f+1) == 'd') {
+				longflag = 1;
+				++f;
+			}
+			
+			switch (*f) {
+			case 'c':
+				*s++ = va_arg(vargs, int);
+				break;
+			case 'd':
+				if (longflag)
+					sprintf(s, "%ld", va_arg(vargs, long));
+				else
+					sprintf(s, "%d", va_arg(vargs, int));
+				s += strlen(s);
+				break;
+			case 'i':
+				sprintf(s, "%i", va_arg(vargs, int));
+				s += strlen(s);
+				break;
+			case 'x':
+				sprintf(s, "%x", va_arg(vargs, int));
+				s += strlen(s);
+				break;
+			case 's':
+				p = va_arg(vargs, char*);
+				i = strlen(p);
+				if (n > 0 && i > n)
+					i = n;
+				memcpy(s, p, i);
+				s += i;
+				break;
+			case 'p':
+				sprintf(s, "%p", va_arg(vargs, void*));
+				s += strlen(s);
+				break;
+			case '%':
+				*s++ = '%';
+				break;
+			default:
+				strcpy(s, p);
+				s += strlen(s);
+				goto end;
+			}
+		} else
+			*s++ = *f;
+	}
+	
+ end:
+	_PyString_Resize(&string, s - PyString_AsString(string));
+	return string;
+}
+	
+PyObject *
+PyString_FromFormat(const char *format, ...) 
+{
+	va_list vargs;
+
+#ifdef HAVE_STDARG_PROTOTYPES
+	va_start(vargs, format);
+#else
+	va_start(vargs);
+#endif
+	return PyString_FromFormatV(format, vargs);
+}
+
+
 PyObject *PyString_Decode(const char *s,
 			  int size,
 			  const char *encoding,