diff options
Diffstat (limited to 'fs/unicode')
| -rw-r--r-- | fs/unicode/Kconfig | 5 | ||||
| -rw-r--r-- | fs/unicode/Makefile | 16 | ||||
| -rw-r--r-- | fs/unicode/README.utf8data | 8 | ||||
| -rw-r--r-- | fs/unicode/mkutf8data.c | 5 | ||||
| -rw-r--r-- | fs/unicode/tests/.kunitconfig | 3 | ||||
| -rw-r--r-- | fs/unicode/tests/utf8_kunit.c (renamed from fs/unicode/utf8-selftest.c) | 153 | ||||
| -rw-r--r-- | fs/unicode/utf8-core.c | 28 | ||||
| -rw-r--r-- | fs/unicode/utf8-norm.c | 2 | ||||
| -rw-r--r-- | fs/unicode/utf8data.c_shipped | 3 | ||||
| -rw-r--r-- | fs/unicode/utf8n.h | 2 |
10 files changed, 122 insertions, 103 deletions
diff --git a/fs/unicode/Kconfig b/fs/unicode/Kconfig index da786a687fdc..4ad2c36550f1 100644 --- a/fs/unicode/Kconfig +++ b/fs/unicode/Kconfig @@ -10,6 +10,7 @@ config UNICODE be a separate loadable module that gets requested only when a file system actually use it. -config UNICODE_NORMALIZATION_SELFTEST +config UNICODE_NORMALIZATION_KUNIT_TEST tristate "Test UTF-8 normalization support" - depends on UNICODE + depends on UNICODE && KUNIT + default KUNIT_ALL_TESTS diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index 0e51c0025a16..d95be7fb9f6b 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -4,7 +4,7 @@ ifneq ($(CONFIG_UNICODE),) obj-y += unicode.o endif obj-$(CONFIG_UNICODE) += utf8data.o -obj-$(CONFIG_UNICODE_NORMALIZATION_SELFTEST) += utf8-selftest.o +obj-$(CONFIG_UNICODE_NORMALIZATION_KUNIT_TEST) += tests/utf8_kunit.o unicode-y := utf8-norm.o utf8-core.o @@ -18,13 +18,13 @@ ifdef REGENERATE_UTF8DATA quiet_cmd_utf8data = GEN $@ cmd_utf8data = $< \ - -a $(srctree)/$(src)/DerivedAge.txt \ - -c $(srctree)/$(src)/DerivedCombiningClass.txt \ - -p $(srctree)/$(src)/DerivedCoreProperties.txt \ - -d $(srctree)/$(src)/UnicodeData.txt \ - -f $(srctree)/$(src)/CaseFolding.txt \ - -n $(srctree)/$(src)/NormalizationCorrections.txt \ - -t $(srctree)/$(src)/NormalizationTest.txt \ + -a $(src)/DerivedAge.txt \ + -c $(src)/DerivedCombiningClass.txt \ + -p $(src)/DerivedCoreProperties.txt \ + -d $(src)/UnicodeData.txt \ + -f $(src)/CaseFolding.txt \ + -n $(src)/NormalizationCorrections.txt \ + -t $(src)/NormalizationTest.txt \ -o $@ $(obj)/utf8data.c: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE diff --git a/fs/unicode/README.utf8data b/fs/unicode/README.utf8data index c73786807d3b..f75567e28138 100644 --- a/fs/unicode/README.utf8data +++ b/fs/unicode/README.utf8data @@ -1,4 +1,4 @@ -The utf8data.h file in this directory is generated from the Unicode +The utf8data.c file in this directory is generated from the Unicode Character Database for version 12.1.0 of the Unicode standard. The full set of files can be found here: @@ -45,13 +45,13 @@ Then, build under fs/unicode/ with REGENERATE_UTF8DATA=1: make REGENERATE_UTF8DATA=1 fs/unicode/ -After sanity checking the newly generated utf8data.h file (the +After sanity checking the newly generated utf8data.c file (the version generated from the 12.1.0 UCD should be 4,109 lines long, and have a total size of 324k) and/or comparing it with the older version -of utf8data.h_shipped, rename it to utf8data.h_shipped. +of utf8data.c_shipped, rename it to utf8data.c_shipped. If you are a kernel developer updating to a newer version of the Unicode Character Database, please update this README.utf8data file with the version of the UCD that was used, the md5sum and sha1sums of -the *.txt files, before checking in the new versions of the utf8data.h +the *.txt files, before checking in the new versions of the utf8data.c and README.utf8data files. diff --git a/fs/unicode/mkutf8data.c b/fs/unicode/mkutf8data.c index bc1a7c8b5c8d..401f5d3aeb0c 100644 --- a/fs/unicode/mkutf8data.c +++ b/fs/unicode/mkutf8data.c @@ -36,7 +36,7 @@ #define FOLD_NAME "CaseFolding.txt" #define NORM_NAME "NormalizationCorrections.txt" #define TEST_NAME "NormalizationTest.txt" -#define UTF8_NAME "utf8data.h" +#define UTF8_NAME "utf8data.c" const char *age_name = AGE_NAME; const char *ccc_name = CCC_NAME; @@ -3338,7 +3338,7 @@ static void write_file(void) } fprintf(file, "};\n"); fprintf(file, "\n"); - fprintf(file, "struct utf8data_table utf8_data_table = {\n"); + fprintf(file, "const struct utf8data_table utf8_data_table = {\n"); fprintf(file, "\t.utf8agetab = utf8agetab,\n"); fprintf(file, "\t.utf8agetab_size = ARRAY_SIZE(utf8agetab),\n"); fprintf(file, "\n"); @@ -3352,6 +3352,7 @@ static void write_file(void) fprintf(file, "};\n"); fprintf(file, "EXPORT_SYMBOL_GPL(utf8_data_table);"); fprintf(file, "\n"); + fprintf(file, "MODULE_DESCRIPTION(\"UTF8 data table\");\n"); fprintf(file, "MODULE_LICENSE(\"GPL v2\");\n"); fclose(file); } diff --git a/fs/unicode/tests/.kunitconfig b/fs/unicode/tests/.kunitconfig new file mode 100644 index 000000000000..62dd5c171f9c --- /dev/null +++ b/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/utf8-selftest.c b/fs/unicode/tests/utf8_kunit.c index eb2bbdd688d7..5063e8138aec 100644 --- a/fs/unicode/utf8-selftest.c +++ b/fs/unicode/tests/utf8_kunit.c @@ -1,37 +1,14 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Kernel module for testing utf-8 support. + * KUnit tests for utf-8 support. * * Copyright 2017 Collabora Ltd. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/module.h> -#include <linux/printk.h> #include <linux/unicode.h> -#include <linux/dcache.h> - -#include "utf8n.h" - -unsigned int failed_tests; -unsigned int total_tests; +#include <kunit/test.h> -/* Tests will be based on this version. */ -#define UTF8_LATEST UNICODE_AGE(12, 1, 0) - -#define _test(cond, func, line, fmt, ...) do { \ - total_tests++; \ - if (!cond) { \ - failed_tests++; \ - pr_err("test %s:%d Failed: %s%s", \ - func, line, #cond, (fmt?":":".")); \ - if (fmt) \ - pr_err(fmt, ##__VA_ARGS__); \ - } \ - } while (0) -#define test_f(cond, fmt, ...) _test(cond, __func__, __LINE__, fmt, ##__VA_ARGS__) -#define test(cond) _test(cond, __func__, __LINE__, "") +#include "../utf8n.h" static const struct { /* UTF-8 strings in this vector _must_ be NULL-terminated. */ @@ -170,69 +147,74 @@ static int utf8cursor(struct utf8cursor *u8c, const struct unicode_map *um, return utf8ncursor(u8c, um, n, s, (unsigned int)-1); } -static void check_utf8_nfdi(struct unicode_map *um) +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); - test((utf8len(um, UTF8_NFDI, nfdi_test_data[i].str) == nlen)); - test((utf8nlen(um, UTF8_NFDI, nfdi_test_data[i].str, len) == - nlen)); - if (utf8cursor(&u8c, um, UTF8_NFDI, nfdi_test_data[i].str) < 0) - pr_err("can't create cursor\n"); + 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) { - test_f((c == nfdi_test_data[i].dec[j]), - "Unexpected byte 0x%x should be 0x%x\n", - c, nfdi_test_data[i].dec[j]); + 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++; } - test((j == nlen)); + KUNIT_EXPECT_EQ(test, j, nlen); } } -static void check_utf8_nfdicf(struct unicode_map *um) +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; - test((utf8len(um, UTF8_NFDICF, nfdicf_test_data[i].str) == - nlen)); - test((utf8nlen(um, UTF8_NFDICF, nfdicf_test_data[i].str, len) == - nlen)); + 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); - if (utf8cursor(&u8c, um, UTF8_NFDICF, - nfdicf_test_data[i].str) < 0) - pr_err("can't create cursor\n"); + 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) { - test_f((c == nfdicf_test_data[i].ncf[j]), - "Unexpected byte 0x%x should be 0x%x\n", - c, nfdicf_test_data[i].ncf[j]); + 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++; } - test((j == nlen)); + KUNIT_EXPECT_EQ(test, j, nlen); } } -static void check_utf8_comparisons(struct unicode_map *table) +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, @@ -240,8 +222,9 @@ static void check_utf8_comparisons(struct unicode_map *table) const struct qstr s2 = {.name = nfdi_test_data[i].dec, .len = sizeof(nfdi_test_data[i].dec)}; - test_f(!utf8_strncmp(table, &s1, &s2), - "%s %s comparison mismatch\n", s1.name, s2.name); + /* 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++) { @@ -250,61 +233,65 @@ static void check_utf8_comparisons(struct unicode_map *table) const struct qstr s2 = {.name = nfdicf_test_data[i].ncf, .len = sizeof(nfdicf_test_data[i].ncf)}; - test_f(!utf8_strncasecmp(table, &s1, &s2), - "%s %s comparison mismatch\n", s1.name, s2.name); + /* 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 unicode_map *um) +static void check_supported_versions(struct kunit *test) { + struct unicode_map *um = test->priv; /* Unicode 7.0.0 should be supported. */ - test(utf8version_is_supported(um, UNICODE_AGE(7, 0, 0))); + KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UNICODE_AGE(7, 0, 0))); /* Unicode 9.0.0 should be supported. */ - test(utf8version_is_supported(um, UNICODE_AGE(9, 0, 0))); + KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UNICODE_AGE(9, 0, 0))); /* Unicode 1x.0.0 (the latest version) should be supported. */ - test(utf8version_is_supported(um, UTF8_LATEST)); + KUNIT_EXPECT_TRUE(test, utf8version_is_supported(um, UTF8_LATEST)); /* Next versions don't exist. */ - test(!utf8version_is_supported(um, UNICODE_AGE(13, 0, 0))); - test(!utf8version_is_supported(um, UNICODE_AGE(0, 0, 0))); - test(!utf8version_is_supported(um, UNICODE_AGE(-1, -1, -1))); + 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 int __init init_test_ucd(void) +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; + struct unicode_map *um = utf8_load(UTF8_LATEST); - failed_tests = 0; - total_tests = 0; + test->priv = um; - um = utf8_load(UTF8_LATEST); - if (IS_ERR(um)) { - pr_err("%s: Unable to load utf8 table.\n", __func__); - return PTR_ERR(um); - } + KUNIT_EXPECT_EQ_MSG(test, IS_ERR(um), 0, + "%s: Unable to load utf8 table.\n", __func__); - check_supported_versions(um); - check_utf8_nfdi(um); - check_utf8_nfdicf(um); - check_utf8_comparisons(um); - - if (!failed_tests) - pr_info("All %u tests passed\n", total_tests); - else - pr_err("%u out of %u tests failed\n", failed_tests, - total_tests); - utf8_unload(um); return 0; } -static void __exit exit_test_ucd(void) +static void exit_test_ucd(struct kunit *test) { + utf8_unload(test->priv); } -module_init(init_test_ucd); -module_exit(exit_test_ucd); +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@collabora.co.uk>"); +MODULE_DESCRIPTION("KUnit tests for utf-8 support."); MODULE_LICENSE("GPL"); diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c index 8395066341a4..6fc9ab8667e6 100644 --- a/fs/unicode/utf8-core.c +++ b/fs/unicode/utf8-core.c @@ -198,7 +198,7 @@ struct unicode_map *utf8_load(unsigned int version) return um; out_symbol_put: - symbol_put(um->tables); + symbol_put(utf8_data_table); out_free_um: kfree(um); return ERR_PTR(-EINVAL); @@ -214,3 +214,29 @@ void utf8_unload(struct unicode_map *um) } EXPORT_SYMBOL(utf8_unload); +/** + * utf8_parse_version - Parse a UTF-8 version number from a string + * + * @version: input string + * + * Returns the parsed version on success, negative code on error + */ +int utf8_parse_version(char *version) +{ + substring_t args[3]; + unsigned int maj, min, rev; + static const struct match_token token[] = { + {1, "%d.%d.%d"}, + {0, NULL} + }; + + if (match_token(version, token, args) != 1) + return -EINVAL; + + if (match_int(&args[0], &maj) || match_int(&args[1], &min) || + match_int(&args[2], &rev)) + return -EINVAL; + + return UNICODE_AGE(maj, min, rev); +} +EXPORT_SYMBOL(utf8_parse_version); diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c index 768f8ab448b8..7b998c99c88d 100644 --- a/fs/unicode/utf8-norm.c +++ b/fs/unicode/utf8-norm.c @@ -586,7 +586,7 @@ ccc_mismatch: } } -#ifdef CONFIG_UNICODE_NORMALIZATION_SELFTEST_MODULE +#if IS_MODULE(CONFIG_UNICODE_NORMALIZATION_KUNIT_TEST) EXPORT_SYMBOL_GPL(utf8version_is_supported); EXPORT_SYMBOL_GPL(utf8nlen); EXPORT_SYMBOL_GPL(utf8ncursor); diff --git a/fs/unicode/utf8data.c_shipped b/fs/unicode/utf8data.c_shipped index d9b62901aa96..73a93d49b3ba 100644 --- a/fs/unicode/utf8data.c_shipped +++ b/fs/unicode/utf8data.c_shipped @@ -4107,7 +4107,7 @@ static const unsigned char utf8data[64256] = { 0x81,0x80,0xcf,0x86,0x85,0x84,0xcf,0x86,0xcf,0x06,0x02,0x00,0x00,0x00,0x00,0x00 }; -struct utf8data_table utf8_data_table = { +const struct utf8data_table utf8_data_table = { .utf8agetab = utf8agetab, .utf8agetab_size = ARRAY_SIZE(utf8agetab), @@ -4120,4 +4120,5 @@ struct utf8data_table utf8_data_table = { .utf8data = utf8data, }; EXPORT_SYMBOL_GPL(utf8_data_table); +MODULE_DESCRIPTION("UTF8 data table"); MODULE_LICENSE("GPL v2"); diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h index bd00d587747a..fc703aa4b28e 100644 --- a/fs/unicode/utf8n.h +++ b/fs/unicode/utf8n.h @@ -78,6 +78,6 @@ struct utf8data_table { const unsigned char *utf8data; }; -extern struct utf8data_table utf8_data_table; +extern const struct utf8data_table utf8_data_table; #endif /* UTF8NORM_H */ |