diff options
Diffstat (limited to 'fs/unicode')
| -rw-r--r-- | fs/unicode/Makefile | 14 | ||||
| -rw-r--r-- | fs/unicode/README.utf8data | 8 | ||||
| -rw-r--r-- | fs/unicode/mkutf8data.c | 5 | ||||
| -rw-r--r-- | fs/unicode/utf8-core.c | 28 | ||||
| -rw-r--r-- | fs/unicode/utf8-selftest.c | 8 | ||||
| -rw-r--r-- | fs/unicode/utf8data.c_shipped | 3 | ||||
| -rw-r--r-- | fs/unicode/utf8n.h | 2 |
7 files changed, 47 insertions, 21 deletions
diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index 0e51c0025a16..e309afe2b2bb 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -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 If you are a kernel developer updating to a newer version of the Unicode Character Database, please update this README.utf8data file with the version of the UCD that was used, the md5sum and sha1sums of -the *.txt files,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/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-selftest.c b/fs/unicode/utf8-selftest.c index eb2bbdd688d7..5ddaf27b21a6 100644 --- a/fs/unicode/utf8-selftest.c +++ b/fs/unicode/utf8-selftest.c @@ -14,11 +14,8 @@ #include "utf8n.h" -unsigned int failed_tests; -unsigned int total_tests; - -/* Tests will be based on this version. */ -#define UTF8_LATEST UNICODE_AGE(12, 1, 0) +static unsigned int failed_tests; +static unsigned int total_tests; #define _test(cond, func, line, fmt, ...) do { \ total_tests++; \ @@ -307,4 +304,5 @@ module_init(init_test_ucd); module_exit(exit_test_ucd); MODULE_AUTHOR("Gabriel Krisman Bertazi <krisman@collabora.co.uk>"); +MODULE_DESCRIPTION("Kernel module for testing utf-8 support"); MODULE_LICENSE("GPL"); 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 */ |