simple random data generator for tests

Reliance on /dev/urandom produces test vectors that are, well, random.
This can cause problems impossible to track down when the data is
different from one test invokation to another.

The goal is not to have random data to test, but rather to have a
convenient way to create sets of large files with non compressible and
non deltifiable data in a reproducible way.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

3 files changed, 40 insertions, 2 deletions

diff --git a/.gitignore b/.gitignore
index 9229e918cd..fa7ac93594 100644
--- a/.gitignore
+++ b/.gitignore
@@ -149,6 +149,7 @@ test-chmtime
 test-date
 test-delta
 test-dump-cache-tree
+test-genrandom
 test-match-trees
 common-cmds.h
 *.tar.gz
diff --git a/Makefile b/Makefile
index a77d31de98..bd0ba95b1a 100644
--- a/Makefile
+++ b/Makefile
@@ -932,7 +932,7 @@ endif
 
 export NO_SVN_TESTS
 
-test: all test-chmtime$X
+test: all test-chmtime$X test-genrandom$X
 	$(MAKE) -C t/ all
 
 test-date$X: test-date.c date.o ctype.o
@@ -953,6 +953,9 @@ test-match-trees$X: test-match-trees.o $(GITLIBS)
 test-chmtime$X: test-chmtime.c
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $<
 
+test-genrandom$X: test-genrandom.c
+	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $<
+
 check-sha1:: test-sha1$X
 	./test-sha1.sh
 
@@ -1041,7 +1044,7 @@ dist-doc:
 
 clean:
 	rm -f *.o mozilla-sha1/*.o arm/*.o ppc/*.o compat/*.o xdiff/*.o \
-		test-chmtime$X $(LIB_FILE) $(XDIFF_LIB)
+		test-chmtime$X test-genrandom$X $(LIB_FILE) $(XDIFF_LIB)
 	rm -f $(ALL_PROGRAMS) $(BUILT_INS) git$X
 	rm -f *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags
 	rm -rf autom4te.cache
diff --git a/test-genrandom.c b/test-genrandom.c
new file mode 100644
index 0000000000..8cefe6cfed
--- /dev/null
+++ b/test-genrandom.c
@@ -0,0 +1,34 @@
+/*
+ * Simple random data generator used to create reproducible test files.
+ * This is inspired from POSIX.1-2001 implementation example for rand().
+ * Copyright (C) 2007 by Nicolas Pitre, licensed under the GPL version 2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+int main(int argc, char *argv[])
+{
+	unsigned long count, next = 0;
+	unsigned char *c;
+
+	if (argc < 2 || argc > 3) {
+		fprintf( stderr, "Usage: %s <seed_string> [<size>]", argv[0]);
+		return 1;
+	}
+
+	c = (unsigned char *) argv[1];
+	do {
+		next = next * 11 + *c;
+	} while (*c++);
+
+	count = (argc == 3) ? strtoul(argv[2], NULL, 0) : -1L;
+
+	while (count--) {
+		next = next * 1103515245 + 12345;
+		if (putchar((next >> 16) & 0xff) == EOF)
+			return -1;
+	}
+
+	return 0;
+}