Add largefile support for Linux64 and WIn64. Add test_largefile and some minor

change to regrtest.py to allow optional running of test_largefile ('cause it's
slow on Win64).

This closes patches:
http://sourceforge.net/patch/index.php?func=detailpatch&patch_id=100510&group_id=5470
and
http://sourceforge.net/patch/index.php?func=detailpatch&patch_id=100511&group_id=5470

4 files changed, 287 insertions, 44 deletions

diff --git a/Lib/test/output/test_largefile b/Lib/test/output/test_largefile
new file mode 100644
index 0000000..6cbf082
--- /dev/null
+++ b/Lib/test/output/test_largefile
@@ -0,0 +1 @@
+test_largefile
diff --git a/Lib/test/regrtest.py b/Lib/test/regrtest.py
index 9b2466f..3bebca4 100755
--- a/Lib/test/regrtest.py
+++ b/Lib/test/regrtest.py
@@ -15,6 +15,7 @@ Command line options:
 -s: single    -- run only a single test (see below)
 -r: random    -- randomize test execution order
 -l: leakdebug -- if cycle garbage collection is enabled, run with DEBUG_LEAK
+--have-resources   -- run tests that require large resources (time/space)
 
 If non-option arguments are present, they are names for tests to run,
 unless -x is given, in which case they are names for tests not to run.
@@ -40,7 +41,8 @@ import random
 import test_support
 
 def main(tests=None, testdir=None, verbose=0, quiet=0, generate=0,
-         exclude=0, single=0, randomize=0, leakdebug=0):
+         exclude=0, single=0, randomize=0, leakdebug=0,
+         use_large_resources=0):
     """Execute a test suite.
 
     This also parses command-line options and modifies its behavior
@@ -65,7 +67,7 @@ def main(tests=None, testdir=None, verbose=0, quiet=0, generate=0,
     """
     
     try:
-        opts, args = getopt.getopt(sys.argv[1:], 'vgqxsrl')
+        opts, args = getopt.getopt(sys.argv[1:], 'vgqxsrl', ['have-resources'])
     except getopt.error, msg:
         print msg
         print __doc__
@@ -78,6 +80,7 @@ def main(tests=None, testdir=None, verbose=0, quiet=0, generate=0,
         if o == '-s': single = 1
         if o == '-r': randomize = 1
         if o == '-l': leakdebug = 1
+        if o == '--have-resources': use_large_resources = 1
     if generate and verbose:
         print "-g and -v don't go together!"
         return 2
@@ -121,19 +124,17 @@ def main(tests=None, testdir=None, verbose=0, quiet=0, generate=0,
     if randomize:
         random.shuffle(tests)
     test_support.verbose = verbose      # Tell tests to be moderately quiet
+    test_support.use_large_resources = use_large_resources
     save_modules = sys.modules.keys()
     for test in tests:
         if not quiet:
             print test
-        ok = runtest(test, generate, verbose, testdir)
+        ok = runtest(test, generate, verbose, quiet, testdir)
         if ok > 0:
             good.append(test)
         elif ok == 0:
             bad.append(test)
         else:
-            if not quiet:
-                print "test", test,
-                print "skipped -- an optional feature could not be imported"
             skipped.append(test)
         # Unload the newly imported modules (best effort finalization)
         for module in sys.modules.keys():
@@ -194,12 +195,13 @@ def findtests(testdir=None, stdtests=STDTESTS, nottests=NOTTESTS):
     tests.sort()
     return stdtests + tests
 
-def runtest(test, generate, verbose, testdir = None):
+def runtest(test, generate, verbose, quiet, testdir = None):
     """Run a single test.
     test -- the name of the test
     generate -- if true, generate output, instead of running the test
     and comparing it to a previously created output file
     verbose -- if true, print more messages
+    quiet -- if true, don't print 'skipped' messages (probably redundant)
     testdir -- test directory
     """
     test_support.unload(test)
@@ -228,6 +230,9 @@ def runtest(test, generate, verbose, testdir = None):
         finally:
             sys.stdout = save_stdout
     except (ImportError, test_support.TestSkipped), msg:
+        if not quiet:
+            print "test", test,
+            print "skipped -- ", msg
         return -1
     except KeyboardInterrupt, v:
         raise KeyboardInterrupt, v, sys.exc_info()[2]
diff --git a/Lib/test/test_largefile.py b/Lib/test/test_largefile.py
new file mode 100644
index 0000000..5b65237
--- /dev/null
+++ b/Lib/test/test_largefile.py
@@ -0,0 +1,129 @@
+#!python
+
+#----------------------------------------------------------------------
+# test largefile support on system where this makes sense
+#
+#XXX how to only run this when support is there
+#XXX how to only optionally run this, it will take along time
+#----------------------------------------------------------------------
+
+import test_support
+import os, struct, stat, sys
+
+
+# only run if the current system support large files
+f = open(test_support.TESTFN, 'w')
+try:
+	# 2**31 == 2147483648
+	f.seek(2147483649L)
+except OverflowError:
+	raise test_support.TestSkipped, "platform does not have largefile support"
+else:
+	f.close()
+
+
+# create >2GB file (2GB = 2147483648 bytes)
+size = 2500000000L
+name = test_support.TESTFN
+
+
+# on Windows this test comsumes large resources:
+#  it takes a long time to build the >2GB file and takes >2GB of disk space
+# therefore test_support.use_large_resources must be defined to run this test
+if sys.platform[:3] == 'win' and not test_support.use_large_resources:
+	raise test_support.TestSkipped, \
+		"test requires %s bytes and a long time to run" % str(size)
+
+
+
+def expect(got_this, expect_this):
+	if test_support.verbose:
+		print '%s =?= %s ...' % (`got_this`, `expect_this`),
+	if got_this != expect_this:
+		if test_support.verbose:
+			print 'no'
+		raise test_support.TestFailed, 'got %s, but expected %s' %\
+			(str(got_this), str(expect_this))
+	else:
+		if test_support.verbose:
+			print 'yes'
+
+
+# test that each file function works as expected for a large (i.e. >2GB, do
+# we have to check >4GB) files
+
+if test_support.verbose:
+	print 'create large file via seek (may be sparse file) ...'
+f = open(name, 'w')
+f.seek(size)
+f.write('a')
+f.flush()
+expect(os.fstat(f.fileno())[stat.ST_SIZE], size+1)
+if test_support.verbose:
+	print 'check file size with os.fstat'
+f.close()
+if test_support.verbose:
+	print 'check file size with os.stat'
+expect(os.stat(name)[stat.ST_SIZE], size+1)
+
+if test_support.verbose:
+	print 'play around with seek() and read() with the built largefile'
+f = open(name, 'r')
+expect(f.tell(), 0)
+expect(f.read(1), '\000')
+expect(f.tell(), 1)
+f.seek(0)
+expect(f.tell(), 0)
+f.seek(0, 0)
+expect(f.tell(), 0)
+f.seek(42)
+expect(f.tell(), 42)
+f.seek(42, 0)
+expect(f.tell(), 42)
+f.seek(42, 1)
+expect(f.tell(), 84)
+f.seek(0, 1)
+expect(f.tell(), 84)
+f.seek(0, 2) # seek from the end
+expect(f.tell(), size + 1 + 0)
+f.seek(-10, 2)
+expect(f.tell(), size + 1 - 10)
+f.seek(-size-1, 2)
+expect(f.tell(), 0)
+f.seek(size)
+expect(f.tell(), size)
+expect(f.read(1), 'a') # the 'a' that was written at the end of the file above
+f.close()
+
+if test_support.verbose:
+	print 'play around with os.lseek() with the built largefile'
+f = open(name, 'r')
+expect(os.lseek(f.fileno(), 0, 0), 0)
+expect(os.lseek(f.fileno(), 42, 0), 42)
+expect(os.lseek(f.fileno(), 42, 1), 84)
+expect(os.lseek(f.fileno(), 0, 1), 84)
+expect(os.lseek(f.fileno(), 0, 2), size+1+0)
+expect(os.lseek(f.fileno(), -10, 2), size+1-10)
+expect(os.lseek(f.fileno(), -size-1, 2), 0)
+expect(os.lseek(f.fileno(), size, 0), size)
+expect(f.read(1), 'a') # the 'a' that was written at the end of the file above
+f.close()
+
+
+# XXX add tests for truncate if it exists
+# XXX has truncate ever worked on Windows? specifically on WinNT I get:
+#     "IOError: [Errno 13] Permission denied"
+##try:
+##	newsize = size - 10
+##	f.seek(newsize)
+##	f.truncate()
+##	expect(f.tell(), newsize)
+##	newsize = newsize - 1
+##	f.seek(0)
+##	f.truncate(newsize)
+##	expect(f.tell(), newsize)
+##except AttributeError:
+##	pass
+
+os.unlink(name)
+
diff --git a/Objects/fileobject.c b/Objects/fileobject.c
index 3458f8e..dd2ede0 100644
--- a/Objects/fileobject.c
+++ b/Objects/fileobject.c
@@ -42,8 +42,8 @@ redistribution of this file, and for a DISCLAIMER OF ALL WARRANTIES.
 #endif
 
 #ifdef MS_WIN32
-#define ftruncate _chsize
 #define fileno _fileno
+/* can (almost fully) duplicate with _chsize, see file_truncate */
 #define HAVE_FTRUNCATE
 #endif
 
@@ -64,6 +64,12 @@ redistribution of this file, and for a DISCLAIMER OF ALL WARRANTIES.
 #include <errno.h>
 #endif
 
+/* define the appropriate 64-bit capable tell() function */
+#ifdef MS_WIN64
+#	define TELL64 _telli64
+#endif
+
+
 typedef struct {
 	PyObject_HEAD
 	FILE *f_fp;
@@ -239,12 +245,87 @@ file_close(PyFileObject *f, PyObject *args)
 	return Py_None;
 }
 
+
+/* a portable fseek() function
+   return 0 on success, non-zero on failure (with errno set) */
+int
+_portable_fseek(fp, offset, whence)
+	FILE* fp;
+#if defined(HAVE_LARGEFILE_SUPPORT) && SIZEOF_OFF_T < 8 && SIZEOF_FPOS_T >= 8 
+	fpos_t offset;
+#else
+	off_t offset;
+#endif
+	int whence;
+{
+#if defined(HAVE_FSEEKO)
+	return fseeko(fp, offset, whence);
+#elif defined(HAVE_FSEEK64)
+	return fseek64(fp, offset, whence);
+#elif defined(HAVE_LARGEFILE_SUPPORT) && SIZEOF_FPOS_T >= 8 
+	/* lacking a 64-bit capable fseek() (as Win64 does) use a 64-bit capable
+		fsetpos() and tell() to implement fseek()*/
+	fpos_t pos;
+	switch (whence) {
+		case SEEK_CUR:
+			if (fgetpos(fp, &pos) != 0)
+				return -1;
+			offset += pos;
+			break;
+		case SEEK_END:
+			/* do a "no-op" seek first to sync the buffering so that
+			   the low-level tell() can be used correctly */
+			if (fseek(fp, 0, SEEK_END) != 0)
+				return -1;
+			if ((pos = TELL64(fileno(fp))) == -1L)
+				return -1;
+			offset += pos;
+			break;
+		/* case SEEK_SET: break; */
+	}
+	return fsetpos(fp, &offset);
+#else
+	return fseek(fp, offset, whence);
+#endif
+}
+
+
+/* a portable ftell() function
+   Return -1 on failure with errno set appropriately, current file
+   position on success */
+#if defined(HAVE_LARGEFILE_SUPPORT) && SIZEOF_OFF_T < 8 && SIZEOF_FPOS_T >= 8 
+fpos_t
+#else
+off_t
+#endif
+_portable_ftell(fp)
+	FILE* fp;
+{
+#if defined(HAVE_FTELLO) && defined(HAVE_LARGEFILE_SUPPORT)
+	return ftello(fp);
+#elif defined(HAVE_FTELL64) && defined(HAVE_LARGEFILE_SUPPORT)
+	return ftell64(fp);
+#elif SIZEOF_FPOS_T >= 8 && defined(HAVE_LARGEFILE_SUPPORT)
+	fpos_t pos;
+	if (fgetpos(fp, &pos) != 0)
+		return -1;
+	return pos;
+#else
+	return ftell(fp);
+#endif
+}
+
+
 static PyObject *
 file_seek(PyFileObject *f, PyObject *args)
 {
 	int whence;
 	int ret;
+#if defined(HAVE_LARGEFILE_SUPPORT) && SIZEOF_OFF_T < 8 && SIZEOF_FPOS_T >= 8 
+	fpos_t offset, pos;
+#else
 	off_t offset;
+#endif /* !MS_WIN64 */
 	PyObject *offobj;
 	
 	if (f->f_fp == NULL)
@@ -260,16 +341,12 @@ file_seek(PyFileObject *f, PyObject *args)
 #endif
 	if (PyErr_Occurred())
 		return NULL;
+	
 	Py_BEGIN_ALLOW_THREADS
 	errno = 0;
-#if defined(HAVE_FSEEKO)
-	ret = fseeko(f->f_fp, offset, whence);
-#elif defined(HAVE_FSEEK64)
-	ret = fseek64(f->f_fp, offset, whence);
-#else
-	ret = fseek(f->f_fp, offset, whence);
-#endif
+	ret = _portable_fseek(f->f_fp, offset, whence);
 	Py_END_ALLOW_THREADS
+
 	if (ret != 0) {
 		PyErr_SetFromErrno(PyExc_IOError);
 		clearerr(f->f_fp);
@@ -279,12 +356,17 @@ file_seek(PyFileObject *f, PyObject *args)
 	return Py_None;
 }
 
+
 #ifdef HAVE_FTRUNCATE
 static PyObject *
 file_truncate(PyFileObject *f, PyObject *args)
 {
 	int ret;
+#if defined(HAVE_LARGEFILE_SUPPORT) && SIZEOF_OFF_T < 8 && SIZEOF_FPOS_T >= 8 
+	fpos_t newsize;
+#else
 	off_t newsize;
+#endif
 	PyObject *newsizeobj;
 	
 	if (f->f_fp == NULL)
@@ -306,13 +388,7 @@ file_truncate(PyFileObject *f, PyObject *args)
 		/* Default to current position*/
 		Py_BEGIN_ALLOW_THREADS
 		errno = 0;
-#if defined(HAVE_FTELLO) && defined(HAVE_LARGEFILE_SUPPORT)
-		newsize =  ftello(f->f_fp);
-#elif defined(HAVE_FTELL64) && defined(HAVE_LARGEFILE_SUPPORT)
-		newsize =  ftell64(f->f_fp);
-#else
-		newsize =  ftell(f->f_fp);
-#endif
+		newsize = _portable_ftell(f->f_fp);
 		Py_END_ALLOW_THREADS
 		if (newsize == -1) {
 		        PyErr_SetFromErrno(PyExc_IOError);
@@ -324,49 +400,66 @@ file_truncate(PyFileObject *f, PyObject *args)
 	errno = 0;
 	ret = fflush(f->f_fp);
 	Py_END_ALLOW_THREADS
-	if (ret == 0) {
-	        Py_BEGIN_ALLOW_THREADS
+	if (ret != 0) goto onioerror;
+
+#ifdef MS_WIN32
+	/* can use _chsize; if, however, the newsize overflows 32-bits then
+	   _chsize is *not* adequate; in this case, an OverflowError is raised */
+	if (newsize > LONG_MAX) {
+		PyErr_SetString(PyExc_OverflowError,
+			"the new size is too long for _chsize (it is limited to 32-bit values)");
+		return NULL;
+	} else {
+		Py_BEGIN_ALLOW_THREADS
 		errno = 0;
-		ret = ftruncate(fileno(f->f_fp), newsize);
+		ret = _chsize(fileno(f->f_fp), newsize);
 		Py_END_ALLOW_THREADS
+		if (ret != 0) goto onioerror;
 	}
-	if (ret != 0) {
-		PyErr_SetFromErrno(PyExc_IOError);
-		clearerr(f->f_fp);
-		return NULL;
-	}
+#else
+	Py_BEGIN_ALLOW_THREADS
+	errno = 0;
+	ret = ftruncate(fileno(f->f_fp), newsize);
+	Py_END_ALLOW_THREADS
+	if (ret != 0) goto onioerror;
+#endif /* !MS_WIN32 */
+	
 	Py_INCREF(Py_None);
 	return Py_None;
+
+onioerror:
+	PyErr_SetFromErrno(PyExc_IOError);
+	clearerr(f->f_fp);
+	return NULL;
 }
 #endif /* HAVE_FTRUNCATE */
 
 static PyObject *
 file_tell(PyFileObject *f, PyObject *args)
 {
-	off_t offset;
+#if defined(HAVE_LARGEFILE_SUPPORT) && SIZEOF_OFF_T < 8 && SIZEOF_FPOS_T >= 8 
+	fpos_t pos;
+#else
+	off_t pos;
+#endif
+
 	if (f->f_fp == NULL)
 		return err_closed();
 	if (!PyArg_NoArgs(args))
 		return NULL;
 	Py_BEGIN_ALLOW_THREADS
 	errno = 0;
-#if defined(HAVE_FTELLO) && defined(HAVE_LARGEFILE_SUPPORT)
-	offset = ftello(f->f_fp);
-#elif defined(HAVE_FTELL64) && defined(HAVE_LARGEFILE_SUPPORT)
-	offset = ftell64(f->f_fp);
-#else
-	offset = ftell(f->f_fp);
-#endif
+	pos = _portable_ftell(f->f_fp);
 	Py_END_ALLOW_THREADS
-	if (offset == -1) {
+	if (pos == -1) {
 		PyErr_SetFromErrno(PyExc_IOError);
 		clearerr(f->f_fp);
 		return NULL;
 	}
 #if !defined(HAVE_LARGEFILE_SUPPORT)
-	return PyInt_FromLong(offset);
+	return PyInt_FromLong(pos);
 #else
-	return PyLong_FromLongLong(offset);
+	return PyLong_FromLongLong(pos);
 #endif
 }
 
@@ -482,6 +575,11 @@ file_read(PyFileObject *f, PyObject *args)
 		buffersize = new_buffersize(f, (size_t)0);
 	else
 		buffersize = bytesrequested;
+	if (buffersize > INT_MAX) {
+		PyErr_SetString(PyExc_OverflowError,
+			"requested number of bytes is more than a Python string can hold");
+		return NULL;
+	}
 	v = PyString_FromStringAndSize((char *)NULL, buffersize);
 	if (v == NULL)
 		return NULL;
@@ -518,7 +616,7 @@ static PyObject *
 file_readinto(PyFileObject *f, PyObject *args)
 {
 	char *ptr;
-	int ntodo, ndone, nnow;
+	size_t ntodo, ndone, nnow;
 	
 	if (f->f_fp == NULL)
 		return err_closed();
@@ -540,7 +638,7 @@ file_readinto(PyFileObject *f, PyObject *args)
 		ndone += nnow;
 		ntodo -= nnow;
 	}
-	return PyInt_FromLong(ndone);
+	return PyInt_FromLong((long)ndone);
 }
 
 
@@ -557,7 +655,7 @@ get_line(PyFileObject *f, int n)
 	register FILE *fp;
 	register int c;
 	register char *buf, *end;
-	int n1, n2;
+	size_t n1, n2;
 	PyObject *v;
 
 	fp = f->f_fp;
@@ -596,6 +694,11 @@ get_line(PyFileObject *f, int n)
 				break;
 			n1 = n2;
 			n2 += 1000;
+			if (n2 > INT_MAX) {
+				PyErr_SetString(PyExc_OverflowError,
+					"line is longer than a Python string can hold");
+				return NULL;
+			}
 			Py_BLOCK_THREADS
 			if (_PyString_Resize(&v, n2) < 0)
 				return NULL;
@@ -735,6 +838,11 @@ file_readlines(PyFileObject *f, PyObject *args)
 			/* Need a larger buffer to fit this line */
 			nfilled += nread;
 			buffersize *= 2;
+			if (buffersize > INT_MAX) {
+				PyErr_SetString(PyExc_OverflowError,
+					"line is too long for a Python string");
+				goto error;
+			}
 			if (big_buffer == NULL) {
 				/* Create the big buffer */
 				big_buffer = PyString_FromStringAndSize(