summaryrefslogtreecommitdiff
path: root/source4/torture/local
diff options
context:
space:
mode:
authorAndrew Tridgell <tridge@samba.org>2004-10-08 08:13:00 +0000
committerGerald (Jerry) Carter <jerry@samba.org>2007-10-10 12:59:39 -0500
commit7d32679e9683c81aca538f0267684332a28a286f (patch)
tree445aecfad24e8dab1fe7a200904a712212fa7091 /source4/torture/local
parent48f960ab47707ca24898834da4da440d1f7fb0d9 (diff)
downloadsamba-7d32679e9683c81aca538f0267684332a28a286f.tar.gz
samba-7d32679e9683c81aca538f0267684332a28a286f.tar.bz2
samba-7d32679e9683c81aca538f0267684332a28a286f.zip
r2857: this commit gets rid of smb_ucs2_t, wpstring and fpstring, plus lots of associated functions.
The motivation for this change was to avoid having to convert to/from ucs2 strings for so many operations. Doing that was slow, used many static buffers, and was also incorrect as it didn't cope properly with unicode codepoints above 65536 (which could not be represented correctly as smb_ucs2_t chars) The two core functions that allowed this change are next_codepoint() and push_codepoint(). These functions allow you to correctly walk a arbitrary multi-byte string a character at a time without converting the whole string to ucs2. While doing this cleanup I also fixed several ucs2 string handling bugs. See the commit for details. The following code (which counts the number of occuraces of 'c' in a string) shows how to use the new interface: size_t count_chars(const char *s, char c) { size_t count = 0; while (*s) { size_t size; codepoint_t c2 = next_codepoint(s, &size); if (c2 == c) count++; s += size; } return count; } (This used to be commit 814881f0e50019196b3aa9fbe4aeadbb98172040)
Diffstat (limited to 'source4/torture/local')
-rw-r--r--source4/torture/local/iconv.c54
1 files changed, 49 insertions, 5 deletions
diff --git a/source4/torture/local/iconv.c b/source4/torture/local/iconv.c
index 84bca802e9..606ac3da5d 100644
--- a/source4/torture/local/iconv.c
+++ b/source4/torture/local/iconv.c
@@ -27,8 +27,8 @@
/*
generate a UTF-16LE buffer for a given unicode codepoint
*/
-static int gen_codepoint(unsigned int codepoint,
- char *buf, size_t *size)
+static int gen_codepoint_utf16(unsigned int codepoint,
+ char *buf, size_t *size)
{
static iconv_t cd;
uint8_t in[4];
@@ -254,6 +254,45 @@ static int test_buffer(uint8_t *inbuf, size_t size, const char *charset)
return ok;
}
+
+/*
+ test the push_codepoint() and next_codepoint() functions for a given
+ codepoint
+*/
+static int test_codepoint(unsigned int codepoint)
+{
+ uint8_t buf[10];
+ size_t size, size2;
+ codepoint_t c;
+
+ size = push_codepoint(buf, codepoint);
+ if (size == -1) {
+ if (codepoint < 0xd800 || codepoint > 0x10000) {
+ return 0;
+ }
+ return 1;
+ }
+ buf[size] = random();
+ buf[size+1] = random();
+ buf[size+2] = random();
+ buf[size+3] = random();
+
+ c = next_codepoint(buf, &size2);
+
+ if (c != codepoint) {
+ printf("next_codepoint(%u) failed - gave %u\n", codepoint, c);
+ return 0;
+ }
+
+ if (size2 != size) {
+ printf("next_codepoint(%u) gave wrong size %d (should be %d)\n",
+ codepoint, size2, size);
+ return 0;
+ }
+
+ return 1;
+}
+
BOOL torture_local_iconv(int dummy)
{
size_t size;
@@ -263,13 +302,18 @@ BOOL torture_local_iconv(int dummy)
srandom(time(NULL));
+ printf("Testing next_codepoint()\n");
+ for (codepoint=0;ok && codepoint<(1<<20);codepoint++) {
+ ok = test_codepoint(codepoint);
+ }
+
printf("Testing first 1M codepoints\n");
for (codepoint=0;ok && codepoint<(1<<20);codepoint++) {
- if (gen_codepoint(codepoint, inbuf, &size) != 0) {
+ if (gen_codepoint_utf16(codepoint, inbuf, &size) != 0) {
continue;
}
- if (codepoint % 100 == 0) {
+ if (codepoint % 1000 == 0) {
printf("codepoint=%u \r", codepoint);
}
@@ -279,7 +323,7 @@ BOOL torture_local_iconv(int dummy)
printf("Testing 5M random UTF-16LE sequences\n");
for (i=0;ok && i<500000;i++) {
- if (i % 100 == 0) {
+ if (i % 1000 == 0) {
printf("i=%u \r", i);
}