diff options
author | Jörg Frings-Fürst <debian@jff.email> | 2022-01-08 11:53:52 +0100 |
---|---|---|
committer | Jörg Frings-Fürst <debian@jff.email> | 2022-01-08 11:53:52 +0100 |
commit | fa838e76139763f902c7d27cb9e1d393ed6a15e4 (patch) | |
tree | 7d0ae09775ea950056193eaa2ca93844299d46f1 /tests/unilbrk/test-u32-possible-linebreaks.c | |
parent | c78359d9542c86b972aac373efcf7bc7a8a560e5 (diff) | |
parent | 2959e59fab3bab834368adefd90bd4b1b094366b (diff) |
Merge branch 'feature/upstream' into develop
Diffstat (limited to 'tests/unilbrk/test-u32-possible-linebreaks.c')
-rw-r--r-- | tests/unilbrk/test-u32-possible-linebreaks.c | 181 |
1 files changed, 172 insertions, 9 deletions
diff --git a/tests/unilbrk/test-u32-possible-linebreaks.c b/tests/unilbrk/test-u32-possible-linebreaks.c index 0434889..50e5910 100644 --- a/tests/unilbrk/test-u32-possible-linebreaks.c +++ b/tests/unilbrk/test-u32-possible-linebreaks.c @@ -1,5 +1,5 @@ /* Test of line breaking of UTF-32 strings. - Copyright (C) 2008-2018 Free Software Foundation, Inc. + Copyright (C) 2008-2022 Free Software Foundation, Inc. This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -24,11 +24,12 @@ #include "macros.h" -int -main () +static void +test_function (void (*my_u32_possible_linebreaks) (const uint32_t *, size_t, const char *, char *_UC_RESTRICT), + int version) { /* Test case n = 0. */ - u32_possible_linebreaks (NULL, 0, "GB18030", NULL); + my_u32_possible_linebreaks (NULL, 0, "GB18030", NULL); { static const uint32_t input[61] = @@ -45,13 +46,13 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u32_possible_linebreaks (input, SIZEOF (input), "GB18030", p); + my_u32_possible_linebreaks (input, SIZEOF (input), "GB18030", p); for (i = 0; i < 61; i++) { ASSERT (p[i] == (i == 60 ? UC_BREAK_MANDATORY : i == 5 || i == 11 || i == 25 - || i == 29 || i == 30 + || i == 29 || i == 45 || i == 51 || i == 52 || i == 53 || i == 55 || i == 56 || i == 58 || i == 59 ? UC_BREAK_POSSIBLE : @@ -64,13 +65,13 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u32_possible_linebreaks (input, SIZEOF (input), "GB2312", p); + my_u32_possible_linebreaks (input, SIZEOF (input), "GB2312", p); for (i = 0; i < 61; i++) { ASSERT (p[i] == (i == 60 ? UC_BREAK_MANDATORY : i == 5 || i == 11 || i == 25 - || i == 29 || i == 30 + || i == 29 || i == 37 || i == 45 || i == 51 || i == 52 || i == 53 || i == 55 || i == 56 || i == 58 || i == 59 ? UC_BREAK_POSSIBLE : @@ -80,6 +81,23 @@ main () } } + /* CR LF handling. */ + { + static const uint32_t input[8] = + { 'a', '\n', 'b', '\r', 'c', '\r', '\n', 'd' }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 8; i++) + { + ASSERT (p[i] == (i == 1 || i == 3 || i == 6 ? UC_BREAK_MANDATORY : + i == 5 ? (version < 2 ? UC_BREAK_MANDATORY : UC_BREAK_CR_BEFORE_LF) : + UC_BREAK_PROHIBITED)); + } + free (p); + } + /* Test that a break is possible after a zero-width space followed by some regular spaces (rule LB8 in Unicode TR#14 revision 26). */ { @@ -87,7 +105,7 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); for (i = 0; i < 4; i++) { ASSERT (p[i] == (i == 3 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED)); @@ -95,5 +113,150 @@ main () free (p); } + /* Test line breaking in a string with HTML markup. */ + { + static const uint32_t input[21] = + { + '<', 'P', '>', 'S', 'o', 'm', 'e', ' ', 's', 'e', 'n', 't', + 'e', 'n', 'c', 'e', '.', '<', '/', 'P', '>' + }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 21; i++) + { + ASSERT (p[i] == (i == 8 || i == 17 || i == 19 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test line breaking of combining marks. */ + { + static const uint32_t input[16] = + { + 'a', 0x0300, 0x0301, 'e', 0x0300, ' ', 0x0301, 'o', ' ', 0x0300, ' ', + 'o', 0x0A00, 0x0300, '\n', + 0x0300 + }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 16; i++) + { + ASSERT (p[i] == (i == 14 ? UC_BREAK_MANDATORY : + i == 6 || i == 9 || i == 11 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test line breaking of zero-width joiners (U+200D). */ + { + static const uint32_t input[37] = + { + 0x6709, 0x7121, 0x7AAE, 0x591A, 0x500B, 0x7D20, 0x6578, 0x3002, '\n', + 0x6709, 0x200D, 0x7121, 0x200D, 0x7AAE, 0x591A, 0x500B, 0x7D20, 0x200D, 0x6578, 0x3002, '\n', + 0x4F60, 0x2014, 0x4E0D, '\n', + 0x4F60, 0x2014, 0x200D, 0x4E0D, '\n', + 0x261D, 0x1F3FF, '\n', + 0x261D, 0x200D, 0x1F3FF, '\n', + }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 37; i++) + { + ASSERT (p[i] == (i == 8 || i == 20 + || i == 24 || i == 29 + || i == 32 || i == 36 ? UC_BREAK_MANDATORY : + i == 1 || i == 2 || i == 3 || i == 4 || i == 5 || i == 6 + || i == 14 || i == 15 || i == 16 + || i == 22 || i == 23 + || i == 26 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test line breaking of regional indicators. */ + { + static const uint32_t input[4] = + { 0x1F1E9, 0x1F1EA, 0x1F1EB, 0x1F1F7 }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 4; i++) + { + ASSERT (p[i] == (i == 2 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test special behaviour of hyphen/break-after character after + Hebrew letter. */ + { + static const uint32_t input[10] = /* "ab-אב-αβ-ω" */ + { 'a', 'b', '-', 0x05D0, 0x05D1, '-', 0x03B1, 0x03B2, '-', 0x03C9 }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 10; i++) + { + ASSERT (p[i] == (i == 3 || i == 9 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test special behaviour before East Asian opening parenthesis (LB30). */ + { + static const uint32_t input[17] = /* "日中韓統合漢字拡張G「ユニコード」" */ + { + 0x65E5, 0x4E2D, 0x97D3, 0x7D71, 0x5408, 0x6F22, 0x5B57, 0x62E1, 0x5F35, + 'G', 0x300C, 0x30E6, 0x30CB, 0x30B3, 0x30FC, 0x30C9, 0x300D + }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 17; i++) + { + ASSERT (p[i] == (i == 1 || i == 2 || i == 3 || i == 4 || i == 5 + || i == 6 || i == 7 || i == 8 || i == 9 + || i == 10 /* This is the desired break position. */ + || i == 12 || i == 13 || i == 15 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test special behaviour of potential future emoji (LB30b). */ + { + static const uint32_t input[2] = { 0x1FFFC, 0x1F3FF }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 2; i++) + { + ASSERT (p[i] == UC_BREAK_PROHIBITED); + } + free (p); + } +} + +int +main () +{ + test_function (u32_possible_linebreaks, 2); +#undef u32_possible_linebreaks + test_function (u32_possible_linebreaks, 1); + return 0; } |