#include "testing/testing.h"
#include "BLI_rand.h"
#include "BLI_string.h"
#include "BLI_string_cursor_utf8.h"
#include "BLI_string_utf8.h"
#include "BLI_utildefines.h"

Macros
#define	STR_MB_ALPHA_1 "\x41"

#define	STR_MB_ALPHA_2 "\xc2\xaa"

#define	STR_MB_ALPHA_3 "\xe0\xa0\x80"

#define	STR_MB_ALPHA_4 "\xf0\x90\x80\x80"

#define	STR_MB_ALPHA_5 "\xf8\x80\x80\x80\x80"

#define	STR_MB_ALPHA_6 "\xfc\x80\x80\x80\x80\x80"

#define	EXPECT_BYTE_OFFSET(truncate_ofs, expect_nchars)

Functions
Test #BLI_strnlen_utf8
	TEST (string, StringNLenUTF8)

	TEST (string, StringNLenUTF8_Incomplete)

Test #BLI_str_utf8_offset_from_index
	TEST (string, Utf8OffsetFromIndex_ClampedIndex)

Test #BLI_str_utf8_as_unicode_step_safe
static size_t	utf8_as_char32 (const char str, const char str_len, char32_t r_result)

template<size_t Size, size_t SizeWithPadding>
void	utf8_as_char32_test_compare_with_pad_bytes (const char utf8_src[Size])

template<size_t Size>
void	utf8_as_char32_test_compare (const char utf8_src[Size])

template<size_t Size>
void	utf8_as_char32_test_at_buffer_size ()

	TEST (string, Utf8AsUnicodeStep)

Test #BLI_str_cursor_step_next_utf32_empty
	TEST (string, StrCursorStepNextUtf32Empty)

Test #BLI_str_cursor_step_next_utf32_single
	TEST (string, StrCursorStepNextUtf32Single)

Test #BLI_str_cursor_step_next_utf32_simple
	TEST (string, StrCursorStepNextUtf32Simple)

Test #BLI_str_cursor_step_next_utf32_allcombining
	TEST (string, StrCursorStepNextUtf32AllCombining)

Test #BLI_str_cursor_step_next_utf32_complex
	TEST (string, StrCursorStepNextUtf32Complex)

Test #BLI_str_cursor_step_next_utf32_invalid
	TEST (string, StrCursorStepNextUtf32Invalid)

Test #BLI_str_cursor_step_prev_utf32_empty
	TEST (string, StrCursorStepPrevUtf32Empty)

Test #BLI_str_cursor_step_prev_utf32_single
	TEST (string, StrCursorStepPrevUtf32Single)

Test #BLI_str_cursor_step_prev_utf32_simple
	TEST (string, StrCursorStepPrevUtf32Simple)

Test #BLI_str_cursor_step_prev_utf32_allcombining
	TEST (string, StrCursorStepPrevUtf32AllCombining)

Test #BLI_str_cursor_step_prev_utf32_complex
	TEST (string, StrCursorStepPrevUtf32Complex)

Test #BLI_str_cursor_step_prev_utf32_invalid
	TEST (string, StrCursorStepPrevUtf32Invalid)

Test #BLI_str_cursor_step_next_utf8_empty
	TEST (string, StrCursorStepNextUtf8Empty)

Test #BLI_str_cursor_step_next_utf8_single
	TEST (string, StrCursorStepNextUtf8Single)

Test #BLI_str_cursor_step_next_utf8_simple
	TEST (string, StrCursorStepNextUtf8Simple)

Test #BLI_str_cursor_step_next_utf8_allcombining
	TEST (string, StrCursorStepNextUtf8AllCombining)

Test #BLI_str_cursor_step_next_utf8_complex
	TEST (string, StrCursorStepNextUtf8AllComplex)

Test #BLI_str_cursor_step_next_utf8_invalid
	TEST (string, StrCursorStepNextUtf8Invalid)

Test #BLI_str_cursor_step_prev_utf8_empty
	TEST (string, StrCursorStepPrevUtf8Empty)

Test #BLI_str_cursor_step_prev_utf8_single
	TEST (string, StrCursorStepPrevUtf8Single)

	TEST (string, StrCursorStepPrevUtf8Simple)

Test #BLI_str_cursor_step_prev_utf8_allcombining
	TEST (string, StrCursorStepPrevUtf8AllCombining)

Test #BLI_str_cursor_step_prev_utf8_complex
	TEST (string, StrCursorStepPrevUtf8Complex)

Test #BLI_str_cursor_step_prev_utf8_invalid
	TEST (string, StrCursorStepPrevUtf8Invalid)

Test #BLI_str_utf8_invalid_strip
static const char *	utf8_invalid_tests [][3]

	TEST (string, Utf8InvalidBytes)

Macro Definition Documentation

◆ EXPECT_BYTE_OFFSET

#define EXPECT_BYTE_OFFSET	(		truncate_ofs,
			expect_nchars )

Value:

  { \
    size_t buf_ofs = 0; \
    strcpy(buf, ref_str); \
    buf[truncate_ofs] = '\0'; \
    EXPECT_EQ(BLI_strnlen_utf8_ex(buf, ref_str_len, &buf_ofs), expect_nchars); \
    EXPECT_EQ(buf_ofs, truncate_ofs); \
  }

Referenced by TEST().

◆ STR_MB_ALPHA_1

#define STR_MB_ALPHA_1 "\x41"

Multi byte defies, use when the exact character isn't important, and when proper handling of multi-byte sequences is needed.

Define the first text character found in 1-4 bytes. We might want to generate other string tables too.

unicode_max = 0x110000
bytes_max = 4
sample_chars = dict()
for i in range(unicode_max):
    ch = chr(i)
    try:
        byte = ch.encode('utf-8')
        byte_len = len(byte)
    except UnicodeEncodeError:
        continue
    if byte_len not in sample_chars:
        # Not essential but useful if the character is printable.
        if ch.isalpha():
            sample_chars[byte_len] = byte
        if byte_len == bytes_max:
            break
 
assert tuple(sorted(sample_chars.keys())) == tuple(range(1, bytes_max + 1))
for i in range(1, bytes_max + 1):
    byte = sample_chars[i]
    print("#define STR_MB_ALPHA_%d \"" % i, end="")
    for x in byte:
        print("\\x%02x" % x, end="")
    print("\"")