diff options
Diffstat (limited to 'tests/unilbrk')
| -rw-r--r-- | tests/unilbrk/test-u16-possible-linebreaks.c | 181 | ||||
| -rw-r--r-- | tests/unilbrk/test-u16-width-linebreaks.c | 21 | ||||
| -rw-r--r-- | tests/unilbrk/test-u32-possible-linebreaks.c | 181 | ||||
| -rw-r--r-- | tests/unilbrk/test-u32-width-linebreaks.c | 21 | ||||
| -rw-r--r-- | tests/unilbrk/test-u8-possible-linebreaks.c | 172 | ||||
| -rw-r--r-- | tests/unilbrk/test-u8-width-linebreaks.c | 21 | ||||
| -rw-r--r-- | tests/unilbrk/test-ulc-possible-linebreaks.c | 36 | ||||
| -rw-r--r-- | tests/unilbrk/test-ulc-width-linebreaks.c | 21 |
8 files changed, 596 insertions, 58 deletions
diff --git a/tests/unilbrk/test-u16-possible-linebreaks.c b/tests/unilbrk/test-u16-possible-linebreaks.c index 2c99d5df..1d897a20 100644 --- a/tests/unilbrk/test-u16-possible-linebreaks.c +++ b/tests/unilbrk/test-u16-possible-linebreaks.c @@ -1,5 +1,5 @@ /* Test of line breaking of UTF-16 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_u16_possible_linebreaks) (const uint16_t *, size_t, const char *, char *_UC_RESTRICT), + int version) { /* Test case n = 0. */ - u16_possible_linebreaks (NULL, 0, "GB18030", NULL); + my_u16_possible_linebreaks (NULL, 0, "GB18030", NULL); { static const uint16_t input[61] = @@ -45,13 +46,13 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u16_possible_linebreaks (input, SIZEOF (input), "GB18030", p); + my_u16_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; - u16_possible_linebreaks (input, SIZEOF (input), "GB2312", p); + my_u16_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 uint16_t input[8] = + { 'a', '\n', 'b', '\r', 'c', '\r', '\n', 'd' }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u16_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; - u16_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + my_u16_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 uint16_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_u16_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 uint16_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_u16_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 uint16_t input[39] = + { + 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, 0xD83C, 0xDFFF, '\n', + 0x261D, 0x200D, 0xD83C, 0xDFFF, '\n', + }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u16_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 39; i++) + { + ASSERT (p[i] == (i == 8 || i == 20 + || i == 24 || i == 29 + || i == 33 || i == 38 ? 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 uint16_t input[8] = + { 0xD83C, 0xDDE9, 0xD83C, 0xDDEA, 0xD83C, 0xDDEB, 0xD83C, 0xDDF7 }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u16_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 8; i++) + { + ASSERT (p[i] == (i == 4 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test special behaviour of hyphen/break-after character after + Hebrew letter. */ + { + static const uint16_t input[10] = /* "ab-אב-αβ-ω" */ + { 'a', 'b', '-', 0x05D0, 0x05D1, '-', 0x03B1, 0x03B2, '-', 0x03C9 }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u16_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 uint16_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_u16_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 uint16_t input[4] = { 0xD83F, 0xDFFC, 0xD83C, 0xDFFF }; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u16_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 4; i++) + { + ASSERT (p[i] == UC_BREAK_PROHIBITED); + } + free (p); + } +} + +int +main () +{ + test_function (u16_possible_linebreaks, 2); +#undef u16_possible_linebreaks + test_function (u16_possible_linebreaks, 1); + return 0; } diff --git a/tests/unilbrk/test-u16-width-linebreaks.c b/tests/unilbrk/test-u16-width-linebreaks.c index f4465a44..a6a209fa 100644 --- a/tests/unilbrk/test-u16-width-linebreaks.c +++ b/tests/unilbrk/test-u16-width-linebreaks.c @@ -1,5 +1,5 @@ /* Test of line breaking of UTF-16 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 (int (*my_u16_width_linebreaks) (const uint16_t *, size_t, int, int, int, const char *, const char *, char *_UC_RESTRICT), + int version) { /* Test case n = 0. */ - u16_width_linebreaks (NULL, 0, 80, 0, 0, NULL, "GB18030", NULL); + my_u16_width_linebreaks (NULL, 0, 80, 0, 0, NULL, "GB18030", NULL); { static const uint16_t input[61] = @@ -45,7 +46,7 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u16_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB18030", p); + my_u16_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB18030", p); for (i = 0; i < 61; i++) { ASSERT (p[i] == (i == 60 ? UC_BREAK_MANDATORY : @@ -59,7 +60,7 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u16_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB2312", p); + my_u16_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB2312", p); for (i = 0; i < 61; i++) { ASSERT (p[i] == (i == 60 ? UC_BREAK_MANDATORY : @@ -69,6 +70,14 @@ main () free (p); } } +} + +int +main () +{ + test_function (u16_width_linebreaks, 2); +#undef u16_width_linebreaks + test_function (u16_width_linebreaks, 1); return 0; } diff --git a/tests/unilbrk/test-u32-possible-linebreaks.c b/tests/unilbrk/test-u32-possible-linebreaks.c index 0434889f..50e59109 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; } diff --git a/tests/unilbrk/test-u32-width-linebreaks.c b/tests/unilbrk/test-u32-width-linebreaks.c index a058b3e7..1543f313 100644 --- a/tests/unilbrk/test-u32-width-linebreaks.c +++ b/tests/unilbrk/test-u32-width-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 (int (*my_u32_width_linebreaks) (const uint32_t *, size_t, int, int, int, const char *, const char *, char *_UC_RESTRICT), + int version) { /* Test case n = 0. */ - u32_width_linebreaks (NULL, 0, 80, 0, 0, NULL, "GB18030", NULL); + my_u32_width_linebreaks (NULL, 0, 80, 0, 0, NULL, "GB18030", NULL); { static const uint32_t input[61] = @@ -45,7 +46,7 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u32_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB18030", p); + my_u32_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB18030", p); for (i = 0; i < 61; i++) { ASSERT (p[i] == (i == 60 ? UC_BREAK_MANDATORY : @@ -59,7 +60,7 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u32_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB2312", p); + my_u32_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB2312", p); for (i = 0; i < 61; i++) { ASSERT (p[i] == (i == 60 ? UC_BREAK_MANDATORY : @@ -69,6 +70,14 @@ main () free (p); } } +} + +int +main () +{ + test_function (u32_width_linebreaks, 2); +#undef u32_width_linebreaks + test_function (u32_width_linebreaks, 1); return 0; } diff --git a/tests/unilbrk/test-u8-possible-linebreaks.c b/tests/unilbrk/test-u8-possible-linebreaks.c index 7e1b4c51..3640e560 100644 --- a/tests/unilbrk/test-u8-possible-linebreaks.c +++ b/tests/unilbrk/test-u8-possible-linebreaks.c @@ -1,5 +1,5 @@ /* Test of line breaking of UTF-8 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_u8_possible_linebreaks) (const uint8_t *, size_t, const char *, char *_UC_RESTRICT), + int version) { /* Test case n = 0. */ - u8_possible_linebreaks (NULL, 0, "GB18030", NULL); + my_u8_possible_linebreaks (NULL, 0, "GB18030", NULL); { static const uint8_t input[91] = @@ -39,13 +40,13 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u8_possible_linebreaks (input, SIZEOF (input), "GB18030", p); + my_u8_possible_linebreaks (input, SIZEOF (input), "GB18030", p); for (i = 0; i < 91; i++) { ASSERT (p[i] == (i == 90 ? UC_BREAK_MANDATORY : i == 7 || i == 13 || i == 39 - || i == 43 || i == 44 + || i == 43 || i == 61 || i == 67 || i == 70 || i == 73 || i == 77 || i == 80 || i == 84 || i == 87 ? UC_BREAK_POSSIBLE : @@ -58,13 +59,13 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u8_possible_linebreaks (input, SIZEOF (input), "GB2312", p); + my_u8_possible_linebreaks (input, SIZEOF (input), "GB2312", p); for (i = 0; i < 91; i++) { ASSERT (p[i] == (i == 90 ? UC_BREAK_MANDATORY : i == 7 || i == 13 || i == 39 - || i == 43 || i == 44 + || i == 43 || i == 52 || i == 61 || i == 67 || i == 70 || i == 73 || i == 77 || i == 80 || i == 84 || i == 87 ? UC_BREAK_POSSIBLE : @@ -74,6 +75,22 @@ main () } } + /* CR LF handling. */ + { + static const uint8_t input[8] = "a\nb\rc\r\nd"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u8_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). */ { @@ -81,13 +98,148 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); - for (i = 0; i < 4; i++) + my_u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 6; i++) { ASSERT (p[i] == (i == 5 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED)); } free (p); } + /* Test line breaking in a string with HTML markup. */ + { + static const uint8_t input[21] = "<P>Some sentence.</P>"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u8_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 uint8_t input[24] = + "a\314\200\314\201e\314\200 \314\201o \314\200 o\302\240\314\200\n" + "\314\200"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 24; i++) + { + ASSERT (p[i] == (i == 21 ? UC_BREAK_MANDATORY : + i == 9 || i == 13 || i == 16 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test line breaking of zero-width joiners (U+200D). */ + { + static const uint8_t input[101] = + "\346\234\211\347\204\241\347\252\256\345\244\232\345\200\213\347\264\240\346\225\270\343\200\202\n" /* "有無窮多個素數。" */ + "\346\234\211\342\200\215\347\204\241\342\200\215\347\252\256\345\244\232\345\200\213\347\264\240\342\200\215\346\225\270\343\200\202\n" + "\344\275\240\342\200\224\344\270\215\n" /* "你—不" */ + "\344\275\240\342\200\224\342\200\215\344\270\215\n" + "\342\230\235\360\237\217\277\n" /* "☝🏿" */ + "\342\230\235\342\200\215\360\237\217\277\n"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 101; i++) + { + ASSERT (p[i] == (i == 24 || i == 58 + || i == 68 || i == 81 + || i == 89 || i == 100 ? UC_BREAK_MANDATORY : + i == 3 || i == 6 || i == 9 || i == 12 || i == 15 || i == 18 + || i == 40 || i == 43 || i == 46 + || i == 62 || i == 65 + || i == 72 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test line breaking of regional indicators. */ + { + static const uint8_t input[16] = + "\360\237\207\251\360\237\207\252\360\237\207\253\360\237\207\267"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 16; i++) + { + ASSERT (p[i] == (i == 8 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test special behaviour of hyphen/break-after character after + Hebrew letter. */ + { + static const uint8_t input[15] = /* "ab-אב-αβ-ω" */ + "ab-\327\220\327\221-\316\261\316\262-\317\211"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 15; i++) + { + ASSERT (p[i] == (i == 3 || i == 13 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test special behaviour before East Asian opening parenthesis (LB30). */ + { + static const uint8_t input[49] = /* "日中韓統合漢字拡張G「ユニコード」" */ + "\346\227\245\344\270\255\351\237\223\347\265\261\345\220\210\346\274\242" + "\345\255\227\346\213\241\345\274\265G\343\200\214\343\203\246" + "\343\203\213\343\202\263\343\203\274\343\203\211\343\200\215"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 49; i++) + { + ASSERT (p[i] == (i == 3 || i == 6 || i == 9 || i == 12 || i == 15 + || i == 18 || i == 21 || i == 24 || i == 27 + || i == 28 /* This is the desired break position. */ + || i == 34 || i == 37 || i == 43 ? UC_BREAK_POSSIBLE : + UC_BREAK_PROHIBITED)); + } + free (p); + } + + /* Test special behaviour of potential future emoji (LB30b). */ + { + static const uint8_t input[8] = "\360\237\277\274\360\237\217\277"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p); + for (i = 0; i < 8; i++) + { + ASSERT (p[i] == UC_BREAK_PROHIBITED); + } + free (p); + } +} + +int +main () +{ + test_function (u8_possible_linebreaks, 2); +#undef u8_possible_linebreaks + test_function (u8_possible_linebreaks, 1); + return 0; } diff --git a/tests/unilbrk/test-u8-width-linebreaks.c b/tests/unilbrk/test-u8-width-linebreaks.c index 8defc0e6..4fb97436 100644 --- a/tests/unilbrk/test-u8-width-linebreaks.c +++ b/tests/unilbrk/test-u8-width-linebreaks.c @@ -1,5 +1,5 @@ /* Test of line breaking of UTF-8 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 (int (*my_u8_width_linebreaks) (const uint8_t *, size_t, int, int, int, const char *, const char *, char *_UC_RESTRICT), + int version) { /* Test case n = 0. */ - u8_width_linebreaks (NULL, 0, 80, 0, 0, NULL, "GB18030", NULL); + my_u8_width_linebreaks (NULL, 0, 80, 0, 0, NULL, "GB18030", NULL); { static const uint8_t input[91] = @@ -39,7 +40,7 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u8_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB18030", p); + my_u8_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB18030", p); for (i = 0; i < 91; i++) { ASSERT (p[i] == (i == 90 ? UC_BREAK_MANDATORY : @@ -53,7 +54,7 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - u8_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB2312", p); + my_u8_width_linebreaks (input, SIZEOF (input), 25, 0, 0, NULL, "GB2312", p); for (i = 0; i < 91; i++) { ASSERT (p[i] == (i == 90 ? UC_BREAK_MANDATORY : @@ -63,6 +64,14 @@ main () free (p); } } +} + +int +main () +{ + test_function (u8_width_linebreaks, 2); +#undef u8_width_linebreaks + test_function (u8_width_linebreaks, 1); return 0; } diff --git a/tests/unilbrk/test-ulc-possible-linebreaks.c b/tests/unilbrk/test-ulc-possible-linebreaks.c index 5ff9133a..5e4381ef 100644 --- a/tests/unilbrk/test-ulc-possible-linebreaks.c +++ b/tests/unilbrk/test-ulc-possible-linebreaks.c @@ -1,5 +1,5 @@ /* Test of line breaking of 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_ulc_possible_linebreaks) (const char *, size_t, const char *, char *_UC_RESTRICT), + int version) { /* Test case n = 0. */ - ulc_possible_linebreaks (NULL, 0, "GB18030", NULL); + my_ulc_possible_linebreaks (NULL, 0, "GB18030", NULL); #if HAVE_ICONV { @@ -38,17 +39,40 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - ulc_possible_linebreaks (input, SIZEOF (input), "ISO-8859-1", p); + my_ulc_possible_linebreaks (input, SIZEOF (input), "ISO-8859-1", p); for (i = 0; i < 36; i++) { ASSERT (p[i] == (i == 35 ? UC_BREAK_MANDATORY : - i == 5 || i == 11 || i == 15 || i == 16 + i == 5 || i == 11 || i == 15 || i == 31 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED)); } free (p); } + + /* Test line breaking in a string with HTML markup. */ + { + static const char input[21] = "<P>Some sentence.</P>"; + char *p = (char *) malloc (SIZEOF (input)); + size_t i; + + my_ulc_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); + } #endif +} + +int +main () +{ + test_function (ulc_possible_linebreaks, 2); +#undef ulc_possible_linebreaks + test_function (ulc_possible_linebreaks, 1); return 0; } diff --git a/tests/unilbrk/test-ulc-width-linebreaks.c b/tests/unilbrk/test-ulc-width-linebreaks.c index c1d3398f..ed4909b1 100644 --- a/tests/unilbrk/test-ulc-width-linebreaks.c +++ b/tests/unilbrk/test-ulc-width-linebreaks.c @@ -1,5 +1,5 @@ /* Test of line breaking of 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 (int (*my_ulc_width_linebreaks) (const char *, size_t, int, int, int, const char *, const char *, char *_UC_RESTRICT), + int version) { /* Test case n = 0. */ - ulc_width_linebreaks (NULL, 0, 80, 0, 0, NULL, "GB18030", NULL); + my_ulc_width_linebreaks (NULL, 0, 80, 0, 0, NULL, "GB18030", NULL); #if HAVE_ICONV { @@ -38,16 +39,24 @@ main () char *p = (char *) malloc (SIZEOF (input)); size_t i; - ulc_width_linebreaks (input, SIZEOF (input), 12, 0, 0, NULL, "ISO-8859-1", p); + my_ulc_width_linebreaks (input, SIZEOF (input), 12, 0, 0, NULL, "ISO-8859-1", p); for (i = 0; i < 36; i++) { ASSERT (p[i] == (i == 35 ? UC_BREAK_MANDATORY : - i == 11 || i == 16 || i == 31 ? UC_BREAK_POSSIBLE : + i == 11 || i == 15 || i == 31 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED)); } free (p); } #endif +} + +int +main () +{ + test_function (ulc_width_linebreaks, 2); +#undef ulc_width_linebreaks + test_function (ulc_width_linebreaks, 1); return 0; } |