UpsilonNumworks/Upsilon
1
0
Fork 0
mirror of https://github.com/UpsilonNumworks/Upsilon.git synced 2026-01-18 16:27:34 +01:00
Code Issues Packages Projects Releases Wiki Activity

[ion/utf8] next/previousGlyphPosition methods and tests

Browse Source
This commit is contained in:
Léa Saviot
2019-06-21 11:34:33 +02:00
committed by EmilieNumworks
parent fb80cd3271
commit 1043426c40
3 changed files with 52 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ion/include/ion/unicode/utf8_decoder.h
View File

@@ -38,6 +38,8 @@ public:
}
CodePoint nextCodePoint();
CodePoint previousCodePoint();
const char * nextGlyphPosition();
const char * previousGlyphPosition();
const char * stringPosition() const { return m_stringPosition; }
static size_t CharSizeOfCodePoint(CodePoint c);
static size_t CodePointToChars(CodePoint c, char * buffer, size_t bufferSize);

24
ion/src/shared/unicode/utf8_decoder.cpp
View File

@@ -63,6 +63,30 @@ CodePoint UTF8Decoder::previousCodePoint() {
return CodePoint(result);
}
const char * UTF8Decoder::nextGlyphPosition() {
assert(*m_stringPosition != 0 && (m_stringPosition == m_string || *(m_stringPosition - 1) != 0));
CodePoint followingCodePoint = nextCodePoint();
const char * resultGlyphPosition = m_stringPosition;
followingCodePoint = nextCodePoint();
while (followingCodePoint != UCodePointNull && followingCodePoint.isCombining()) {
resultGlyphPosition = m_stringPosition;
followingCodePoint = nextCodePoint();
}
m_stringPosition = resultGlyphPosition;
return resultGlyphPosition;
}
const char * UTF8Decoder::previousGlyphPosition() {
assert(m_stringPosition > m_string);
CodePoint previousCP = previousCodePoint();
const char * resultGlyphPosition = m_stringPosition;
while (m_stringPosition > m_string && previousCP.isCombining()) {
previousCP = previousCodePoint();
resultGlyphPosition = m_stringPosition;
}
return resultGlyphPosition;
}
size_t UTF8Decoder::CharSizeOfCodePoint(CodePoint c) {
if (c <= 0x7F) {
return 1;

26
ion/test/utf8_decoder.cpp
View File

@@ -1,5 +1,6 @@
#include <quiz.h>
#include <ion/unicode/utf8_decoder.h>
#include <ion/unicode/utf8_helper.h>
void assert_decodes_to(const char * string, CodePoint c) {
UTF8Decoder d(string);
@@ -12,6 +13,18 @@ void assert_previous_code_point_is_to(const char * string, const char * stringPo
quiz_assert(d.previousCodePoint() == c);
}
void assert_code_point_at_next_glyph_position_is(const char * string, CodePoint c) {
UTF8Decoder d(string);
d.nextGlyphPosition();
quiz_assert(d.nextCodePoint() == c);
}
void assert_code_point_at_previous_glyph_position_is(const char * string, const char * stringPosition, CodePoint c) {
UTF8Decoder d(string, stringPosition);
d.previousGlyphPosition();
quiz_assert(d.nextCodePoint() == c);
}
QUIZ_CASE(ion_utf8_decode_forward) {
assert_decodes_to("\x20", 0x20);
assert_decodes_to("\xC2\xA2", 0xA2);
@@ -25,3 +38,16 @@ QUIZ_CASE(ion_utf8_decode_backwards) {
assert_previous_code_point_is_to(a, a+4, *(a+3));
assert_previous_code_point_is_to(a, a+6, *(a+5));
}
QUIZ_CASE(ion_utf8_decoder_next_glyph) {
const char * string = u8"a\u0065\u0301i";
assert_code_point_at_next_glyph_position_is(string, 'e');
assert_code_point_at_next_glyph_position_is(string+1, 'i');
}
QUIZ_CASE(ion_utf8_decoder_previous_glyph) {
const char * string = u8"a\u0065\u0301i";
const char * iPosition = UTF8Helper::CodePointSearch(string, 'i');
assert_code_point_at_previous_glyph_position_is(string, iPosition, 'e');
assert_code_point_at_previous_glyph_position_is(string,string+1, 'a');
}