diff --git a/README.md b/README.md index 58522d853..2ba0e4a5f 100644 --- a/README.md +++ b/README.md @@ -28,7 +28,7 @@ This library provide fast Unicode functions such as - From an UTF-16 string, compute the size of the UTF-32 equivalent string (equivalent to UTF-16 character counting), - UTF-8 and UTF-16LE character counting. -The functions are accelerated using SIMD instructions (e.g., ARM NEON, SSE, AVX, etc.). When your strings contain hundreds of characters, we can often transcode them at speeds exceeding a billion caracters per second. You should expect high speeds not only with English strings (ASCII) but also Chinese, Japanese, Arabic, and so forth. We handle the full character range (including, for example, emojis). +The functions are accelerated using SIMD instructions (e.g., ARM NEON, SSE, AVX, etc.). When your strings contain hundreds of characters, we can often transcode them at speeds exceeding a billion characters per second. You should expect high speeds not only with English strings (ASCII) but also Chinese, Japanese, Arabic, and so forth. We handle the full character range (including, for example, emojis). The library compiles down to tens of kilobytes. Our functions are exception-free and non allocating. We have extensive tests. diff --git a/scripts/sse_validate_utf16le_proof.py b/scripts/sse_validate_utf16le_proof.py index 37a62724d..ca47e459e 100644 --- a/scripts/sse_validate_utf16le_proof.py +++ b/scripts/sse_validate_utf16le_proof.py @@ -38,7 +38,7 @@ def find_error_in_words(words): prev = None if words[0] == 'H': - # We assume that our vector algoritm loads proper data into vectors. + # We assume that our vector algorithm loads proper data into vectors. # In the case low surrogate was the last item in the previous iteration. return 'high surrogate must not start a chunk' @@ -112,7 +112,7 @@ def proof(): case2_hit = True # all 15 words are valid (either 'V' or pairs 'L', 'H') # the last words is either 'L' or 'H' (the word will be - # re-examined in the next iteration of an algorihm) + # re-examined in the next iteration of an algorithm) if words[-1] == 'H': assert find_error_in_words(words) == 'high surrogate 7 must be preceded by low surrogate' elif words[-1] == 'L': diff --git a/tests/helpers/transcode_test_base.h b/tests/helpers/transcode_test_base.h index a499bc7e3..9e882cf8f 100644 --- a/tests/helpers/transcode_test_base.h +++ b/tests/helpers/transcode_test_base.h @@ -27,7 +27,7 @@ namespace simdutf { namespace tests { namespace helpers { public: using GenerateCodepoint = std::function; - std::vector input_utf8; // source-encoded mesage: what we're going to transcode + std::vector input_utf8; // source-encoded message: what we're going to transcode std::vector output_utf16; // what the procedure under test produced std::vector reference_output_utf16; // what we are expecting @@ -81,7 +81,7 @@ namespace simdutf { namespace tests { namespace helpers { public: using GenerateCodepoint = std::function; - std::vector input_utf8; // source-encoded mesage: what we're going to transcode + std::vector input_utf8; // source-encoded message: what we're going to transcode std::vector output_utf32; // what the procedure under test produced std::vector reference_output_utf32; // what we are expecting @@ -138,7 +138,7 @@ namespace simdutf { namespace tests { namespace helpers { std::vector output_utf8; // what the procedure under test produced std::vector reference_output_utf8; // what we are expecting - std::vector input_utf16; // source-encoded mesage: what we're going to transcode + std::vector input_utf16; // source-encoded message: what we're going to transcode static constexpr size_t output_size_margin = 0; // extra room for buggy procedures @@ -192,7 +192,7 @@ namespace simdutf { namespace tests { namespace helpers { std::vector output_utf8; // what the procedure under test produced std::vector reference_output_utf8; // what we are expecting - std::vector input_utf32; // source-encoded mesage: what we're going to transcode + std::vector input_utf32; // source-encoded message: what we're going to transcode static constexpr size_t output_size_margin = 0; // extra room for buggy procedures @@ -246,7 +246,7 @@ namespace simdutf { namespace tests { namespace helpers { std::vector output_utf16; // what the procedure under test produced std::vector reference_output_utf16; // what we are expecting - std::vector input_utf32; // source-encoded mesage: what we're going to transcode + std::vector input_utf32; // source-encoded message: what we're going to transcode static constexpr size_t output_size_margin = 0; // extra room for buggy procedures @@ -299,7 +299,7 @@ namespace simdutf { namespace tests { namespace helpers { std::vector output_utf32; // what the procedure under test produced std::vector reference_output_utf32; // what we are expecting - std::vector input_utf16; // source-encoded mesage: what we're going to transcode + std::vector input_utf16; // source-encoded message: what we're going to transcode static constexpr size_t output_size_margin = 0; // extra room for buggy procedures