The patch titled
Subject: unicode: kunit: change tests filename and path
has been added to the -mm mm-nonmm-unstable branch. Its filename is
unicode-kunit-change-tests-filename-and-path.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/unicode-kunit-change-tests-filename-and-path.patch
This patch will later appear in the mm-nonmm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Gabriela Bittencourt <gbittencourt@xxxxxxxxxx>
Subject: unicode: kunit: change tests filename and path
Date: Fri, 11 Oct 2024 15:25:10 +0800
Change utf8 kunit test filename and path to follow the style convention on
Documentation/dev-tools/kunit/style.rst
[davidgow@xxxxxxxxxx: rebased, fixed module build (Gabriel Krisman Bertazi)]
Link: https://lkml.kernel.org/r/20241011072509.3068328-8-davidgow@xxxxxxxxxx
Co-developed-by: Pedro Orlando <porlando@xxxxxxxxxx>
Signed-off-by: Pedro Orlando <porlando@xxxxxxxxxx>
Co-developed-by: Danilo Pereira <dpereira@xxxxxxxxxx>
Signed-off-by: Danilo Pereira <dpereira@xxxxxxxxxx>
Signed-off-by: Gabriela Bittencourt <gbittencourt@xxxxxxxxxx>
Signed-off-by: David Gow <davidgow@xxxxxxxxxx>
Reviewed-by: David Gow <davidgow@xxxxxxxxxx>
Acked-by: Shuah Khan <skhan@xxxxxxxxxxxxxxxxxxx>
Cc: Andy Shevchenko <andy@xxxxxxxxxx>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@xxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Brendan Higgins <brendanhiggins@xxxxxxxxxx>
Cc: Bruno Sobreira Fran=C3=A7a <brunofrancadevsec@xxxxxxxxx>
Cc: Charlie Jenkins <charlie@xxxxxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: Daniel Latypov <dlatypov@xxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Diego Vieira <diego.daniel.professional@xxxxxxxxx>
Cc: Fangrui Song <maskray@xxxxxxxxxx>
Cc: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>
Cc: Guenter Roeck <linux@xxxxxxxxxxxx>
Cc: Gustavo A. R. Silva <gustavoars@xxxxxxxxxx>
Cc: Jakub Kicinski <kuba@xxxxxxxxxx>
Cc: Jason A. Donenfeld <Jason@xxxxxxxxx>
Cc: Kees Cook <kees@xxxxxxxxxx>
Cc: Luis Felipe Hernandez <luis.hernandez093@xxxxxxxxx>
Cc: Marco Elver <elver@xxxxxxxxxx>
Cc: Mark Brown <broonie@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: "Masami Hiramatsu (Google)" <mhiramat@xxxxxxxxxx>
Cc: Mickaël Salaün <mic@xxxxxxxxxxx>
Cc: Nathan Chancellor <nathan@xxxxxxxxxx>
Cc: Naveen N. Rao <naveen.n.rao@xxxxxxxxxxxxx>
Cc: Nicolas Pitre <npitre@xxxxxxxxxxxx>
Cc: Palmer Dabbelt <palmer@xxxxxxxxxxxx>
Cc: Rae Moar <rmoar@xxxxxxxxxx>
Cc: Rasmus Villemoes <linux@xxxxxxxxxxxxxxxxxx>
Cc: Simon Horman <horms@xxxxxxxxxx>
Cc: Stephen Rothwell <sfr@xxxxxxxxxxxxxxxx>
Cc: "Steven Rostedt (Google)" <rostedt@xxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Yury Norov <yury.norov@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/unicode/.kunitconfig | 3
fs/unicode/Makefile | 2
fs/unicode/tests/.kunitconfig | 3
fs/unicode/tests/utf8_kunit.c | 300 ++++++++++++++++++++++++++++++++
fs/unicode/utf8-selftest.c | 300 --------------------------------
5 files changed, 304 insertions(+), 304 deletions(-)
diff --git a/fs/unicode/.kunitconfig a/fs/unicode/.kunitconfig
deleted file mode 100644
--- a/fs/unicode/.kunitconfig
+++ /dev/null
@@ -1,3 +0,0 @@
-CONFIG_KUNIT=y
-CONFIG_UNICODE=y
-CONFIG_UNICODE_NORMALIZATION_KUNIT_TEST=y
--- a/fs/unicode/Makefile~unicode-kunit-change-tests-filename-and-path
+++ a/fs/unicode/Makefile
@@ -4,7 +4,7 @@ ifneq ($(CONFIG_UNICODE),)
obj-y += unicode.o
endif
obj-$(CONFIG_UNICODE) += utf8data.o
-obj-$(CONFIG_UNICODE_NORMALIZATION_KUNIT_TEST) += utf8-selftest.o
+obj-$(CONFIG_UNICODE_NORMALIZATION_KUNIT_TEST) += tests/utf8_kunit.o
unicode-y := utf8-norm.o utf8-core.o
diff --git a/fs/unicode/tests/.kunitconfig a/fs/unicode/tests/.kunitconfig
new file mode 100644
--- /dev/null
+++ a/fs/unicode/tests/.kunitconfig
@@ -0,0 +1,3 @@
+CONFIG_KUNIT=y
+CONFIG_UNICODE=y
+CONFIG_UNICODE_NORMALIZATION_KUNIT_TEST=y
diff --git a/fs/unicode/tests/utf8_kunit.c a/fs/unicode/tests/utf8_kunit.c
new file mode 100664
--- /dev/null
+++ a/fs/unicode/tests/utf8_kunit.c
@@ -0,0 +1,300 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KUnit tests for utf-8 support.
+ *
+ * Copyright 2017 Collabora Ltd.
+ */
+
+#include <linux/unicode.h>
+#include <kunit/test.h>
+
+#include "utf8n.h"
+
+/* Tests will be based on this version. */
+#define UTF8_LATEST UNICODE_AGE(12, 1, 0)
+
+static const struct {
+ /* UTF-8 strings in this vector _must_ be NULL-terminated. */
+ unsigned char str[10];
+ unsigned char dec[10];
+} nfdi_test_data[] = {
+ /* Trivial sequence */
+ {
+ /* "ABba" decomposes to itself */
+ .str = "aBba",
+ .dec = "aBba",
+ },
+ /* Simple equivalent sequences */
+ {
+ /* 'VULGAR FRACTION ONE QUARTER' cannot decompose to
+ 'NUMBER 1' + 'FRACTION SLASH' + 'NUMBER 4' on
+ canonical decomposition */
+ .str = {0xc2, 0xbc, 0x00},
+ .dec = {0xc2, 0xbc, 0x00},
+ },
+ {
+ /* 'LATIN SMALL LETTER A WITH DIAERESIS' decomposes to
+ 'LETTER A' + 'COMBINING DIAERESIS' */
+ .str = {0xc3, 0xa4, 0x00},
+ .dec = {0x61, 0xcc, 0x88, 0x00},
+ },
+ {
+ /* 'LATIN SMALL LETTER LJ' can't decompose to
+ 'LETTER L' + 'LETTER J' on canonical decomposition */
+ .str = {0xC7, 0x89, 0x00},
+ .dec = {0xC7, 0x89, 0x00},
+ },
+ {
+ /* GREEK ANO TELEIA decomposes to MIDDLE DOT */
+ .str = {0xCE, 0x87, 0x00},
+ .dec = {0xC2, 0xB7, 0x00}
+ },
+ /* Canonical ordering */
+ {
+ /* A + 'COMBINING ACUTE ACCENT' + 'COMBINING OGONEK' decomposes
+ to A + 'COMBINING OGONEK' + 'COMBINING ACUTE ACCENT' */
+ .str = {0x41, 0xcc, 0x81, 0xcc, 0xa8, 0x0},
+ .dec = {0x41, 0xcc, 0xa8, 0xcc, 0x81, 0x0},
+ },
+ {
+ /* 'LATIN SMALL LETTER A WITH DIAERESIS' + 'COMBINING OGONEK'
+ decomposes to
+ 'LETTER A' + 'COMBINING OGONEK' + 'COMBINING DIAERESIS' */
+ .str = {0xc3, 0xa4, 0xCC, 0xA8, 0x00},
+
+ .dec = {0x61, 0xCC, 0xA8, 0xcc, 0x88, 0x00},
+ },
+
+};
+
+static const struct {
+ /* UTF-8 strings in this vector _must_ be NULL-terminated. */
+ unsigned char str[30];
+ unsigned char ncf[30];
+} nfdicf_test_data[] = {
+ /* Trivial sequences */
+ {
+ /* "ABba" folds to lowercase */
+ .str = {0x41, 0x42, 0x62, 0x61, 0x00},
+ .ncf = {0x61, 0x62, 0x62, 0x61, 0x00},
+ },
+ {
+ /* All ASCII folds to lower-case */
+ .str = "ABCDEFGHIJKLMNOPQRSTUVWXYZ0.1",
+ .ncf = "abcdefghijklmnopqrstuvwxyz0.1",
+ },
+ {
+ /* LATIN SMALL LETTER SHARP S folds to
+ LATIN SMALL LETTER S + LATIN SMALL LETTER S */
+ .str = {0xc3, 0x9f, 0x00},
+ .ncf = {0x73, 0x73, 0x00},
+ },
+ {
+ /* LATIN CAPITAL LETTER A WITH RING ABOVE folds to
+ LATIN SMALL LETTER A + COMBINING RING ABOVE */
+ .str = {0xC3, 0x85, 0x00},
+ .ncf = {0x61, 0xcc, 0x8a, 0x00},
+ },
+ /* Introduced by UTF-8.0.0. */
+ /* Cherokee letters are interesting test-cases because they fold
+ to upper-case. Before 8.0.0, Cherokee lowercase were
+ undefined, thus, the folding from LC is not stable between
+ 7.0.0 -> 8.0.0, but it is from UC. */
+ {
+ /* CHEROKEE SMALL LETTER A folds to CHEROKEE LETTER A */
+ .str = {0xea, 0xad, 0xb0, 0x00},
+ .ncf = {0xe1, 0x8e, 0xa0, 0x00},
+ },
+ {
+ /* CHEROKEE SMALL LETTER YE folds to CHEROKEE LETTER YE */
+ .str = {0xe1, 0x8f, 0xb8, 0x00},
+ .ncf = {0xe1, 0x8f, 0xb0, 0x00},
+ },
+ {
+ /* OLD HUNGARIAN CAPITAL LETTER AMB folds to
+ OLD HUNGARIAN SMALL LETTER AMB */
+ .str = {0xf0, 0x90, 0xb2, 0x83, 0x00},
+ .ncf = {0xf0, 0x90, 0xb3, 0x83, 0x00},
+ },
+ /* Introduced by UTF-9.0.0. */
+ {
+ /* OSAGE CAPITAL LETTER CHA folds to
+ OSAGE SMALL LETTER CHA */
+ .str = {0xf0, 0x90, 0x92, 0xb5, 0x00},
+ .ncf = {0xf0, 0x90, 0x93, 0x9d, 0x00},
+ },
+ {
+ /* LATIN CAPITAL LETTER SMALL CAPITAL I folds to
+ LATIN LETTER SMALL CAPITAL I */
+ .str = {0xea, 0x9e, 0xae, 0x00},
+ .ncf = {0xc9, 0xaa, 0x00},
+ },
+ /* Introduced by UTF-11.0.0. */
+ {
+ /* GEORGIAN SMALL LETTER AN folds to GEORGIAN MTAVRULI
+ CAPITAL LETTER AN */
+ .str = {0xe1, 0xb2, 0x90, 0x00},
+ .ncf = {0xe1, 0x83, 0x90, 0x00},
+ }
+};
+
+static ssize_t utf8len(const struct unicode_map *um, enum utf8_normalization n,
+ const char *s)
+{
+ return utf8nlen(um, n, s, (size_t)-1);
+}
+
+static int utf8cursor(struct utf8cursor *u8c, const struct unicode_map *um,
+ enum utf8_normalization n, const char *s)
+{
+ return utf8ncursor(u8c, um, n, s, (unsigned int)-1);
+}
+
+static void check_utf8_nfdi(struct kunit *test)
+{
+ int i;
+ struct utf8cursor u8c;
+ struct unicode_map *um = test->priv;
+
+ for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) {
+ int len = strlen(nfdi_test_data[i].str);
+ int nlen = strlen(nfdi_test_data[i].dec);
+ int j = 0;
+ unsigned char c;
+ int ret;
+
+ KUNIT_EXPECT_EQ(test, utf8len(um, UTF8_NFDI, nfdi_test_data[i].str), nlen);
+ KUNIT_EXPECT_EQ(test, utf8nlen(um, UTF8_NFDI, nfdi_test_data[i].str, len),
+ nlen);
+
+
+ ret = utf8cursor(&u8c, um, UTF8_NFDI, nfdi_test_data[i].str);
+ KUNIT_EXPECT_TRUE_MSG(test, ret >= 0, "Can't create cursor\n");
+
+ while ((c = utf8byte(&u8c)) > 0) {
+ KUNIT_EXPECT_EQ_MSG(test, c, nfdi_test_data[i].dec[j],
+ "Unexpected byte 0x%x should be 0x%x\n",
+ c, nfdi_test_data[i].dec[j]);
+ j++;
+ }
+
+ KUNIT_EXPECT_EQ(test, j, nlen);
+ }
+}
+
+static void check_utf8_nfdicf(struct kunit *test)
+{
+ int i;
+ struct utf8cursor u8c;
+ struct unicode_map *um = test->priv;
+
+ for (i = 0; i < ARRAY_SIZE(nfdicf_test_data); i++) {
+ int len = strlen(nfdicf_test_data[i].str);
+ int nlen = strlen(nfdicf_test_data[i].ncf);
+ int j = 0;
+ int ret;
+ unsigned char c;
+
+ KUNIT_EXPECT_EQ(test, utf8len(um, UTF8_NFDICF, nfdicf_test_data[i].str),
+ nlen);
+ KUNIT_EXPECT_EQ(test, utf8nlen(um, UTF8_NFDICF, nfdicf_test_data[i].str, len),
+ nlen);
+
+ ret = utf8cursor(&u8c, um, UTF8_NFDICF, nfdicf_test_data[i].str);
+ KUNIT_EXPECT_TRUE_MSG(test, ret >= 0, "Can't create cursor\n");
+
+ while ((c = utf8byte(&u8c)) > 0) {
+ KUNIT_EXPECT_EQ_MSG(test, c, nfdicf_test_data[i].ncf[j],
+ "Unexpected byte 0x%x should be 0x%x\n",
+ c, nfdicf_test_data[i].ncf[j]);
+ j++;
+ }
+
+ KUNIT_EXPECT_EQ(test, j, nlen);
+ }
+}
+
+static void check_utf8_comparisons(struct kunit *test)
+{
+ int i;
+ struct unicode_map *um = test->priv;
+
+ for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) {
+ const struct qstr s1 = {.name = nfdi_test_data[i].str,
+ .len = sizeof(nfdi_test_data[i].str)};
+ const struct qstr s2 = {.name = nfdi_test_data[i].dec,
+ .len = sizeof(nfdi_test_data[i].dec)};
+
+ /* strncmp returns 0 when strings are equal */
+ KUNIT_EXPECT_TRUE_MSG(test, utf8_strncmp(um, &s1, &s2) == 0,
+ "%s %s comparison mismatch\n", s1.name, s2.name);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(nfdicf_test_data); i++) {
+ const struct qstr s1 = {.name = nfdicf_test_data[i].str,
+ .len = sizeof(nfdicf_test_data[i].str)};
+ const struct qstr s2 = {.name = nfdicf_test_data[i].ncf,
+ .len = sizeof(nfdicf_test_data[i].ncf)};
+
+ /* strncasecmp returns 0 when strings are equal */
+ KUNIT_EXPECT_TRUE_MSG(test, utf8_strncasecmp(um, &s1, &s2) == 0,
+ "%s %s comparison mismatch\n", s1.name, s2.name);
+ }
+}
+
+static void check_supported_versions(struct kunit *test)
+{
+ struct unicode_map *um = test->priv;
+ /* Unicode 7.0.0 should be supported. */
+ KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UNICODE_AGE(7, 0, 0)));
+
+ /* Unicode 9.0.0 should be supported. */
+ KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UNICODE_AGE(9, 0, 0)));
+
+ /* Unicode 1x.0.0 (the latest version) should be supported. */
+ KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UTF8_LATEST));
+
+ /* Next versions don't exist. */
+ KUNIT_EXPECT_FALSE(test, utf8version_is_supported(um, UNICODE_AGE(13, 0, 0)));
+ KUNIT_EXPECT_FALSE(test, utf8version_is_supported(um, UNICODE_AGE(0, 0, 0)));
+ KUNIT_EXPECT_FALSE(test, utf8version_is_supported(um, UNICODE_AGE(-1, -1, -1)));
+}
+
+static struct kunit_case unicode_normalization_test_cases[] = {
+ KUNIT_CASE(check_supported_versions),
+ KUNIT_CASE(check_utf8_comparisons),
+ KUNIT_CASE(check_utf8_nfdicf),
+ KUNIT_CASE(check_utf8_nfdi),
+ {}
+};
+
+static int init_test_ucd(struct kunit *test)
+{
+ struct unicode_map *um = utf8_load(UTF8_LATEST);
+
+ test->priv = um;
+
+ KUNIT_EXPECT_EQ_MSG(test, IS_ERR(um), 0,
+ "%s: Unable to load utf8 table.\n", __func__);
+
+ return 0;
+}
+
+static void exit_test_ucd(struct kunit *test)
+{
+ utf8_unload(test->priv);
+}
+
+static struct kunit_suite unicode_normalization_test_suite = {
+ .name = "unicode_normalization",
+ .test_cases = unicode_normalization_test_cases,
+ .init = init_test_ucd,
+ .exit = exit_test_ucd,
+};
+
+kunit_test_suite(unicode_normalization_test_suite);
+
+
+MODULE_AUTHOR("Gabriel Krisman Bertazi <krisman@xxxxxxxxxxxxxxx>");
+MODULE_DESCRIPTION("KUnit tests for utf-8 support.");
+MODULE_LICENSE("GPL");
diff --git a/fs/unicode/utf8-selftest.c a/fs/unicode/utf8-selftest.c
deleted file mode 100644
--- a/fs/unicode/utf8-selftest.c
+++ /dev/null
@@ -1,300 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * KUnit tests for utf-8 support.
- *
- * Copyright 2017 Collabora Ltd.
- */
-
-#include <linux/unicode.h>
-#include <kunit/test.h>
-
-#include "utf8n.h"
-
-/* Tests will be based on this version. */
-#define UTF8_LATEST UNICODE_AGE(12, 1, 0)
-
-static const struct {
- /* UTF-8 strings in this vector _must_ be NULL-terminated. */
- unsigned char str[10];
- unsigned char dec[10];
-} nfdi_test_data[] = {
- /* Trivial sequence */
- {
- /* "ABba" decomposes to itself */
- .str = "aBba",
- .dec = "aBba",
- },
- /* Simple equivalent sequences */
- {
- /* 'VULGAR FRACTION ONE QUARTER' cannot decompose to
- 'NUMBER 1' + 'FRACTION SLASH' + 'NUMBER 4' on
- canonical decomposition */
- .str = {0xc2, 0xbc, 0x00},
- .dec = {0xc2, 0xbc, 0x00},
- },
- {
- /* 'LATIN SMALL LETTER A WITH DIAERESIS' decomposes to
- 'LETTER A' + 'COMBINING DIAERESIS' */
- .str = {0xc3, 0xa4, 0x00},
- .dec = {0x61, 0xcc, 0x88, 0x00},
- },
- {
- /* 'LATIN SMALL LETTER LJ' can't decompose to
- 'LETTER L' + 'LETTER J' on canonical decomposition */
- .str = {0xC7, 0x89, 0x00},
- .dec = {0xC7, 0x89, 0x00},
- },
- {
- /* GREEK ANO TELEIA decomposes to MIDDLE DOT */
- .str = {0xCE, 0x87, 0x00},
- .dec = {0xC2, 0xB7, 0x00}
- },
- /* Canonical ordering */
- {
- /* A + 'COMBINING ACUTE ACCENT' + 'COMBINING OGONEK' decomposes
- to A + 'COMBINING OGONEK' + 'COMBINING ACUTE ACCENT' */
- .str = {0x41, 0xcc, 0x81, 0xcc, 0xa8, 0x0},
- .dec = {0x41, 0xcc, 0xa8, 0xcc, 0x81, 0x0},
- },
- {
- /* 'LATIN SMALL LETTER A WITH DIAERESIS' + 'COMBINING OGONEK'
- decomposes to
- 'LETTER A' + 'COMBINING OGONEK' + 'COMBINING DIAERESIS' */
- .str = {0xc3, 0xa4, 0xCC, 0xA8, 0x00},
-
- .dec = {0x61, 0xCC, 0xA8, 0xcc, 0x88, 0x00},
- },
-
-};
-
-static const struct {
- /* UTF-8 strings in this vector _must_ be NULL-terminated. */
- unsigned char str[30];
- unsigned char ncf[30];
-} nfdicf_test_data[] = {
- /* Trivial sequences */
- {
- /* "ABba" folds to lowercase */
- .str = {0x41, 0x42, 0x62, 0x61, 0x00},
- .ncf = {0x61, 0x62, 0x62, 0x61, 0x00},
- },
- {
- /* All ASCII folds to lower-case */
- .str = "ABCDEFGHIJKLMNOPQRSTUVWXYZ0.1",
- .ncf = "abcdefghijklmnopqrstuvwxyz0.1",
- },
- {
- /* LATIN SMALL LETTER SHARP S folds to
- LATIN SMALL LETTER S + LATIN SMALL LETTER S */
- .str = {0xc3, 0x9f, 0x00},
- .ncf = {0x73, 0x73, 0x00},
- },
- {
- /* LATIN CAPITAL LETTER A WITH RING ABOVE folds to
- LATIN SMALL LETTER A + COMBINING RING ABOVE */
- .str = {0xC3, 0x85, 0x00},
- .ncf = {0x61, 0xcc, 0x8a, 0x00},
- },
- /* Introduced by UTF-8.0.0. */
- /* Cherokee letters are interesting test-cases because they fold
- to upper-case. Before 8.0.0, Cherokee lowercase were
- undefined, thus, the folding from LC is not stable between
- 7.0.0 -> 8.0.0, but it is from UC. */
- {
- /* CHEROKEE SMALL LETTER A folds to CHEROKEE LETTER A */
- .str = {0xea, 0xad, 0xb0, 0x00},
- .ncf = {0xe1, 0x8e, 0xa0, 0x00},
- },
- {
- /* CHEROKEE SMALL LETTER YE folds to CHEROKEE LETTER YE */
- .str = {0xe1, 0x8f, 0xb8, 0x00},
- .ncf = {0xe1, 0x8f, 0xb0, 0x00},
- },
- {
- /* OLD HUNGARIAN CAPITAL LETTER AMB folds to
- OLD HUNGARIAN SMALL LETTER AMB */
- .str = {0xf0, 0x90, 0xb2, 0x83, 0x00},
- .ncf = {0xf0, 0x90, 0xb3, 0x83, 0x00},
- },
- /* Introduced by UTF-9.0.0. */
- {
- /* OSAGE CAPITAL LETTER CHA folds to
- OSAGE SMALL LETTER CHA */
- .str = {0xf0, 0x90, 0x92, 0xb5, 0x00},
- .ncf = {0xf0, 0x90, 0x93, 0x9d, 0x00},
- },
- {
- /* LATIN CAPITAL LETTER SMALL CAPITAL I folds to
- LATIN LETTER SMALL CAPITAL I */
- .str = {0xea, 0x9e, 0xae, 0x00},
- .ncf = {0xc9, 0xaa, 0x00},
- },
- /* Introduced by UTF-11.0.0. */
- {
- /* GEORGIAN SMALL LETTER AN folds to GEORGIAN MTAVRULI
- CAPITAL LETTER AN */
- .str = {0xe1, 0xb2, 0x90, 0x00},
- .ncf = {0xe1, 0x83, 0x90, 0x00},
- }
-};
-
-static ssize_t utf8len(const struct unicode_map *um, enum utf8_normalization n,
- const char *s)
-{
- return utf8nlen(um, n, s, (size_t)-1);
-}
-
-static int utf8cursor(struct utf8cursor *u8c, const struct unicode_map *um,
- enum utf8_normalization n, const char *s)
-{
- return utf8ncursor(u8c, um, n, s, (unsigned int)-1);
-}
-
-static void check_utf8_nfdi(struct kunit *test)
-{
- int i;
- struct utf8cursor u8c;
- struct unicode_map *um = test->priv;
-
- for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) {
- int len = strlen(nfdi_test_data[i].str);
- int nlen = strlen(nfdi_test_data[i].dec);
- int j = 0;
- unsigned char c;
- int ret;
-
- KUNIT_EXPECT_EQ(test, utf8len(um, UTF8_NFDI, nfdi_test_data[i].str), nlen);
- KUNIT_EXPECT_EQ(test, utf8nlen(um, UTF8_NFDI, nfdi_test_data[i].str, len),
- nlen);
-
-
- ret = utf8cursor(&u8c, um, UTF8_NFDI, nfdi_test_data[i].str);
- KUNIT_EXPECT_TRUE_MSG(test, ret >= 0, "Can't create cursor\n");
-
- while ((c = utf8byte(&u8c)) > 0) {
- KUNIT_EXPECT_EQ_MSG(test, c, nfdi_test_data[i].dec[j],
- "Unexpected byte 0x%x should be 0x%x\n",
- c, nfdi_test_data[i].dec[j]);
- j++;
- }
-
- KUNIT_EXPECT_EQ(test, j, nlen);
- }
-}
-
-static void check_utf8_nfdicf(struct kunit *test)
-{
- int i;
- struct utf8cursor u8c;
- struct unicode_map *um = test->priv;
-
- for (i = 0; i < ARRAY_SIZE(nfdicf_test_data); i++) {
- int len = strlen(nfdicf_test_data[i].str);
- int nlen = strlen(nfdicf_test_data[i].ncf);
- int j = 0;
- int ret;
- unsigned char c;
-
- KUNIT_EXPECT_EQ(test, utf8len(um, UTF8_NFDICF, nfdicf_test_data[i].str),
- nlen);
- KUNIT_EXPECT_EQ(test, utf8nlen(um, UTF8_NFDICF, nfdicf_test_data[i].str, len),
- nlen);
-
- ret = utf8cursor(&u8c, um, UTF8_NFDICF, nfdicf_test_data[i].str);
- KUNIT_EXPECT_TRUE_MSG(test, ret >= 0, "Can't create cursor\n");
-
- while ((c = utf8byte(&u8c)) > 0) {
- KUNIT_EXPECT_EQ_MSG(test, c, nfdicf_test_data[i].ncf[j],
- "Unexpected byte 0x%x should be 0x%x\n",
- c, nfdicf_test_data[i].ncf[j]);
- j++;
- }
-
- KUNIT_EXPECT_EQ(test, j, nlen);
- }
-}
-
-static void check_utf8_comparisons(struct kunit *test)
-{
- int i;
- struct unicode_map *um = test->priv;
-
- for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) {
- const struct qstr s1 = {.name = nfdi_test_data[i].str,
- .len = sizeof(nfdi_test_data[i].str)};
- const struct qstr s2 = {.name = nfdi_test_data[i].dec,
- .len = sizeof(nfdi_test_data[i].dec)};
-
- /* strncmp returns 0 when strings are equal */
- KUNIT_EXPECT_TRUE_MSG(test, utf8_strncmp(um, &s1, &s2) == 0,
- "%s %s comparison mismatch\n", s1.name, s2.name);
- }
-
- for (i = 0; i < ARRAY_SIZE(nfdicf_test_data); i++) {
- const struct qstr s1 = {.name = nfdicf_test_data[i].str,
- .len = sizeof(nfdicf_test_data[i].str)};
- const struct qstr s2 = {.name = nfdicf_test_data[i].ncf,
- .len = sizeof(nfdicf_test_data[i].ncf)};
-
- /* strncasecmp returns 0 when strings are equal */
- KUNIT_EXPECT_TRUE_MSG(test, utf8_strncasecmp(um, &s1, &s2) == 0,
- "%s %s comparison mismatch\n", s1.name, s2.name);
- }
-}
-
-static void check_supported_versions(struct kunit *test)
-{
- struct unicode_map *um = test->priv;
- /* Unicode 7.0.0 should be supported. */
- KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UNICODE_AGE(7, 0, 0)));
-
- /* Unicode 9.0.0 should be supported. */
- KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UNICODE_AGE(9, 0, 0)));
-
- /* Unicode 1x.0.0 (the latest version) should be supported. */
- KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UTF8_LATEST));
-
- /* Next versions don't exist. */
- KUNIT_EXPECT_FALSE(test, utf8version_is_supported(um, UNICODE_AGE(13, 0, 0)));
- KUNIT_EXPECT_FALSE(test, utf8version_is_supported(um, UNICODE_AGE(0, 0, 0)));
- KUNIT_EXPECT_FALSE(test, utf8version_is_supported(um, UNICODE_AGE(-1, -1, -1)));
-}
-
-static struct kunit_case unicode_normalization_test_cases[] = {
- KUNIT_CASE(check_supported_versions),
- KUNIT_CASE(check_utf8_comparisons),
- KUNIT_CASE(check_utf8_nfdicf),
- KUNIT_CASE(check_utf8_nfdi),
- {}
-};
-
-static int init_test_ucd(struct kunit *test)
-{
- struct unicode_map *um = utf8_load(UTF8_LATEST);
-
- test->priv = um;
-
- KUNIT_EXPECT_EQ_MSG(test, IS_ERR(um), 0,
- "%s: Unable to load utf8 table.\n", __func__);
-
- return 0;
-}
-
-static void exit_test_ucd(struct kunit *test)
-{
- utf8_unload(test->priv);
-}
-
-static struct kunit_suite unicode_normalization_test_suite = {
- .name = "unicode_normalization",
- .test_cases = unicode_normalization_test_cases,
- .init = init_test_ucd,
- .exit = exit_test_ucd,
-};
-
-kunit_test_suite(unicode_normalization_test_suite);
-
-
-MODULE_AUTHOR("Gabriel Krisman Bertazi <krisman@xxxxxxxxxxxxxxx>");
-MODULE_DESCRIPTION("KUnit tests for utf-8 support.");
-MODULE_LICENSE("GPL");
_
Patches currently in -mm which might be from gbittencourt@xxxxxxxxxx are
unicode-kunit-refactor-selftest-to-kunit-tests.patch
unicode-kunit-change-tests-filename-and-path.patch
