aboutsummaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
Diffstat
-rw-r--r--src/Document.cxx9
-rw-r--r--src/Editor.cxx2
-rw-r--r--src/UniConversion.cxx62
-rw-r--r--src/UniConversion.h10
-rw-r--r--test/unit/testUniConversion.cxx48
-rw-r--r--win32/PlatWin.cxx12
-rw-r--r--win32/ScintillaWin.cxx46
7 files changed, 97 insertions, 92 deletions
diff --git a/src/Document.cxx b/src/Document.cxx
index fbe387f6d..bcc368a68 100644
--- a/src/Document.cxx
+++ b/src/Document.cxx
@@ -2939,12 +2939,13 @@ Sci::Position Cxx11RegexFindText(const Document *doc, Sci::Position minPos, Sci:
bool matched = false;
if (SC_CP_UTF8 == doc->dbcsCodePage) {
- const size_t lenS = strlen(s);
- std::vector<wchar_t> ws(lenS + 1);
+ const std::string_view sv(s);
+ const size_t lenS = sv.length();
+ std::vector<wchar_t> ws(sv.length() + 1);
#if WCHAR_T_IS_16
- const size_t outLen = UTF16FromUTF8(s, lenS, &ws[0], lenS);
+ const size_t outLen = UTF16FromUTF8(sv, &ws[0], lenS);
#else
- const size_t outLen = UTF32FromUTF8(s, lenS, reinterpret_cast<unsigned int *>(&ws[0]), lenS);
+ const size_t outLen = UTF32FromUTF8(sv, reinterpret_cast<unsigned int *>(&ws[0]), lenS);
#endif
ws[outLen] = 0;
std::wregex regexp;
diff --git a/src/Editor.cxx b/src/Editor.cxx
index 36ebc5cea..7a61d503a 100644
--- a/src/Editor.cxx
+++ b/src/Editor.cxx
@@ -1957,7 +1957,7 @@ void Editor::AddCharUTF(const char *s, unsigned int len, bool treatAsDBCS) {
// characters representing themselves.
} else {
unsigned int utf32[1] = { 0 };
- UTF32FromUTF8(s, len, utf32, ELEMENTS(utf32));
+ UTF32FromUTF8(std::string_view(s, len), utf32, ELEMENTS(utf32));
byte = utf32[0];
}
NotifyChar(byte);
diff --git a/src/UniConversion.cxx b/src/UniConversion.cxx
index a6830f950..1287aa612 100644
--- a/src/UniConversion.cxx
+++ b/src/UniConversion.cxx
@@ -17,10 +17,10 @@ using namespace Scintilla;
namespace Scintilla {
-size_t UTF8Length(const wchar_t *uptr, size_t tlen) {
+size_t UTF8Length(std::wstring_view wsv) {
size_t len = 0;
- for (size_t i = 0; i < tlen && uptr[i];) {
- const unsigned int uch = uptr[i];
+ for (size_t i = 0; i < wsv.length() && wsv[i];) {
+ const unsigned int uch = wsv[i];
if (uch < 0x80) {
len++;
} else if (uch < 0x800) {
@@ -37,10 +37,10 @@ size_t UTF8Length(const wchar_t *uptr, size_t tlen) {
return len;
}
-void UTF8FromUTF16(const wchar_t *uptr, size_t tlen, char *putf, size_t len) {
+void UTF8FromUTF16(std::wstring_view wsv, char *putf, size_t len) {
size_t k = 0;
- for (size_t i = 0; i < tlen && uptr[i];) {
- const unsigned int uch = uptr[i];
+ for (size_t i = 0; i < wsv.length() && wsv[i];) {
+ const unsigned int uch = wsv[i];
if (uch < 0x80) {
putf[k++] = static_cast<char>(uch);
} else if (uch < 0x800) {
@@ -50,7 +50,7 @@ void UTF8FromUTF16(const wchar_t *uptr, size_t tlen, char *putf, size_t len) {
(uch <= SURROGATE_TRAIL_LAST)) {
// Half a surrogate pair
i++;
- const unsigned int xch = 0x10000 + ((uch & 0x3ff) << 10) + (uptr[i] & 0x3ff);
+ const unsigned int xch = 0x10000 + ((uch & 0x3ff) << 10) + (wsv[i] & 0x3ff);
putf[k++] = static_cast<char>(0xF0 | (xch >> 18));
putf[k++] = static_cast<char>(0x80 | ((xch >> 12) & 0x3f));
putf[k++] = static_cast<char>(0x80 | ((xch >> 6) & 0x3f));
@@ -86,14 +86,14 @@ void UTF8FromUTF32Character(int uch, char *putf) {
putf[k] = '\0';
}
-size_t UTF16Length(const char *s, size_t len) {
+size_t UTF16Length(std::string_view sv) {
size_t ulen = 0;
- for (size_t i = 0; i < len;) {
- const unsigned char ch = s[i];
+ for (size_t i = 0; i<sv.length();) {
+ const unsigned char ch = sv[i];
const unsigned int byteCount = UTF8BytesOfLead[ch];
const unsigned int utf16Len = UTF16LengthFromUTF8ByteCount(byteCount);
i += byteCount;
- ulen += (i > len) ? 1 : utf16Len;
+ ulen += (i > sv.length()) ? 1 : utf16Len;
}
return ulen;
}
@@ -104,14 +104,14 @@ constexpr unsigned char TrailByteValue(unsigned char c) {
return c & 0b0011'1111;
}
-size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen) {
+size_t UTF16FromUTF8(std::string_view sv, wchar_t *tbuf, size_t tlen) {
size_t ui = 0;
- for (size_t i = 0; i < len;) {
- unsigned char ch = s[i];
+ for (size_t i = 0; i < sv.length();) {
+ unsigned char ch = sv[i];
const unsigned int byteCount = UTF8BytesOfLead[ch];
unsigned int value;
- if (i + byteCount > len) {
+ if (i + byteCount > sv.length()) {
// Trying to read past end but still have space to write
if (ui < tlen) {
tbuf[ui] = ch;
@@ -132,26 +132,26 @@ size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen) {
break;
case 2:
value = (ch & 0x1F) << 6;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch);
tbuf[ui] = static_cast<wchar_t>(value);
break;
case 3:
value = (ch & 0xF) << 12;
- ch = s[i++];
+ ch = sv[i++];
value += (TrailByteValue(ch) << 6);
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch);
tbuf[ui] = static_cast<wchar_t>(value);
break;
default:
// Outside the BMP so need two surrogates
value = (ch & 0x7) << 18;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch) << 12;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch) << 6;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch);
tbuf[ui] = static_cast<wchar_t>(((value - 0x10000) >> 10) + SURROGATE_LEAD_FIRST);
ui++;
@@ -163,14 +163,14 @@ size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen) {
return ui;
}
-size_t UTF32FromUTF8(const char *s, size_t len, unsigned int *tbuf, size_t tlen) {
+size_t UTF32FromUTF8(std::string_view sv, unsigned int *tbuf, size_t tlen) {
size_t ui = 0;
- for (size_t i = 0; i < len;) {
- unsigned char ch = s[i];
+ for (size_t i = 0; i < sv.length();) {
+ unsigned char ch = sv[i];
const unsigned int byteCount = UTF8BytesOfLead[ch];
unsigned int value;
- if (i + byteCount > len) {
+ if (i + byteCount > sv.length()) {
// Trying to read past end but still have space to write
if (ui < tlen) {
tbuf[ui] = ch;
@@ -190,23 +190,23 @@ size_t UTF32FromUTF8(const char *s, size_t len, unsigned int *tbuf, size_t tlen)
break;
case 2:
value = (ch & 0x1F) << 6;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch);
break;
case 3:
value = (ch & 0xF) << 12;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch) << 6;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch);
break;
default:
value = (ch & 0x7) << 18;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch) << 12;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch) << 6;
- ch = s[i++];
+ ch = sv[i++];
value += TrailByteValue(ch);
break;
}
diff --git a/src/UniConversion.h b/src/UniConversion.h
index 4cdfe1fac..1b84b8f81 100644
--- a/src/UniConversion.h
+++ b/src/UniConversion.h
@@ -14,12 +14,12 @@ const int UTF8MaxBytes = 4;
const int unicodeReplacementChar = 0xFFFD;
-size_t UTF8Length(const wchar_t *uptr, size_t tlen);
-void UTF8FromUTF16(const wchar_t *uptr, size_t tlen, char *putf, size_t len);
+size_t UTF8Length(std::wstring_view wsv);
+void UTF8FromUTF16(std::wstring_view wsv, char *putf, size_t len);
void UTF8FromUTF32Character(int uch, char *putf);
-size_t UTF16Length(const char *s, size_t len);
-size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen);
-size_t UTF32FromUTF8(const char *s, size_t len, unsigned int *tbuf, size_t tlen);
+size_t UTF16Length(std::string_view sv);
+size_t UTF16FromUTF8(std::string_view sv, wchar_t *tbuf, size_t tlen);
+size_t UTF32FromUTF8(std::string_view sv, unsigned int *tbuf, size_t tlen);
unsigned int UTF16FromUTF32Character(unsigned int val, wchar_t *tbuf) noexcept;
std::string FixInvalidUTF8(const std::string &text);
diff --git a/test/unit/testUniConversion.cxx b/test/unit/testUniConversion.cxx
index efea2d8f4..a23d799e3 100644
--- a/test/unit/testUniConversion.cxx
+++ b/test/unit/testUniConversion.cxx
@@ -23,53 +23,53 @@ TEST_CASE("UTF16Length") {
SECTION("UTF16Length ASCII") {
// Latin Small Letter A
const char *s = "a";
- size_t len = UTF16Length(s, strlen(s));
+ size_t len = UTF16Length(s);
REQUIRE(len == 1U);
}
SECTION("UTF16Length Example1") {
// Dollar Sign
const char *s = "\x24";
- size_t len = UTF16Length(s, strlen(s));
+ size_t len = UTF16Length(s);
REQUIRE(len == 1U);
}
SECTION("UTF16Length Example2") {
// Cent Sign
const char *s = "\xC2\xA2";
- size_t len = UTF16Length(s, strlen(s));
+ size_t len = UTF16Length(s);
REQUIRE(len == 1U);
}
SECTION("UTF16Length Example3") {
// Euro Sign
const char *s = "\xE2\x82\xAC";
- size_t len = UTF16Length(s, strlen(s));
+ size_t len = UTF16Length(s);
REQUIRE(len == 1U);
}
SECTION("UTF16Length Example4") {
// Gothic Letter Hwair
const char *s = "\xF0\x90\x8D\x88";
- size_t len = UTF16Length(s, strlen(s));
+ size_t len = UTF16Length(s);
REQUIRE(len == 2U);
}
SECTION("UTF16Length Invalid Trail byte in lead position") {
const char *s = "a\xB5yz";
- size_t len = UTF16Length(s, strlen(s));
+ size_t len = UTF16Length(s);
REQUIRE(len == 4U);
}
SECTION("UTF16Length Invalid Lead byte at end") {
const char *s = "a\xC2";
- size_t len = UTF16Length(s, strlen(s));
+ size_t len = UTF16Length(s);
REQUIRE(len == 2U);
}
SECTION("UTF16Length Invalid Lead byte implies 3 trails but only 2") {
const char *s = "a\xF1yz";
- size_t len = UTF16Length(s, strlen(s));
+ size_t len = UTF16Length(s);
REQUIRE(len == 2U);
}
}
@@ -108,7 +108,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF16FromUTF8 ASCII") {
const char s[] = {'a', 0};
wchar_t tbuf[1] = {0};
- size_t tlen = UTF16FromUTF8(s, 1, tbuf, 1);
+ size_t tlen = UTF16FromUTF8(s, tbuf, 1);
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == 'a');
}
@@ -116,7 +116,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF16FromUTF8 Example1") {
const char s[] = {'\x24', 0};
wchar_t tbuf[1] = {0};
- size_t tlen = UTF16FromUTF8(s, 1, tbuf, 1);
+ size_t tlen = UTF16FromUTF8(s, tbuf, 1);
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == 0x24);
}
@@ -124,7 +124,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF16FromUTF8 Example2") {
const char s[] = {'\xC2', '\xA2', 0};
wchar_t tbuf[1] = {0};
- size_t tlen = UTF16FromUTF8(s, 2, tbuf, 1);
+ size_t tlen = UTF16FromUTF8(s, tbuf, 1);
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == 0xA2);
}
@@ -132,7 +132,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF16FromUTF8 Example3") {
const char s[] = {'\xE2', '\x82', '\xAC', 0};
wchar_t tbuf[1] = {0};
- size_t tlen = UTF16FromUTF8(s, 3, tbuf, 1);;
+ size_t tlen = UTF16FromUTF8(s, tbuf, 1);;
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == 0x20AC);
}
@@ -140,7 +140,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF16FromUTF8 Example4") {
const char s[] = {'\xF0', '\x90', '\x8D', '\x88', 0};
wchar_t tbuf[2] = {0, 0};
- size_t tlen = UTF16FromUTF8(s, 4, tbuf, 2);
+ size_t tlen = UTF16FromUTF8(s, tbuf, 2);
REQUIRE(tlen == 2U);
REQUIRE(tbuf[0] == 0xD800);
REQUIRE(tbuf[1] == 0xDF48);
@@ -149,7 +149,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF16FromUTF8 Invalid Trail byte in lead position") {
const char s[] = "a\xB5yz";
wchar_t tbuf[4] = {};
- size_t tlen = UTF16FromUTF8(s, 4, tbuf, 4);
+ size_t tlen = UTF16FromUTF8(s, tbuf, 4);
REQUIRE(tlen == 4U);
REQUIRE(tbuf[0] == 'a');
REQUIRE(tbuf[1] == 0xB5);
@@ -160,7 +160,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF16FromUTF8 Invalid Lead byte at end") {
const char s[] = "a\xC2";
wchar_t tbuf[2] = {};
- size_t tlen = UTF16FromUTF8(s, 2, tbuf, 2);
+ size_t tlen = UTF16FromUTF8(s, tbuf, 2);
REQUIRE(tlen == 2U);
REQUIRE(tbuf[0] == 'a');
REQUIRE(tbuf[1] == 0xC2);
@@ -169,7 +169,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF16FromUTF8 Invalid Lead byte implies 3 trails but only 2") {
const char *s = "a\xF1yz";
wchar_t tbuf[4] = {};
- size_t tlen = UTF16FromUTF8(s, 4, tbuf, 4);
+ size_t tlen = UTF16FromUTF8(s, tbuf, 4);
REQUIRE(tlen == 2U);
REQUIRE(tbuf[0] == 'a');
REQUIRE(tbuf[1] == 0xF1);
@@ -180,7 +180,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF32FromUTF8 ASCII") {
const char s[] = {'a', 0};
unsigned int tbuf[1] = {0};
- size_t tlen = UTF32FromUTF8(s, 1, tbuf, 1);
+ size_t tlen = UTF32FromUTF8(s, tbuf, 1);
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == static_cast<unsigned int>('a'));
}
@@ -188,7 +188,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF32FromUTF8 Example1") {
const char s[] = {'\x24', 0};
unsigned int tbuf[1] = {0};
- size_t tlen = UTF32FromUTF8(s, 1, tbuf, 1);
+ size_t tlen = UTF32FromUTF8(s, tbuf, 1);
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == 0x24);
}
@@ -196,7 +196,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF32FromUTF8 Example2") {
const char s[] = {'\xC2', '\xA2', 0};
unsigned int tbuf[1] = {0};
- size_t tlen = UTF32FromUTF8(s, 2, tbuf, 1);
+ size_t tlen = UTF32FromUTF8(s, tbuf, 1);
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == 0xA2);
}
@@ -204,7 +204,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF32FromUTF8 Example3") {
const char s[] = {'\xE2', '\x82', '\xAC', 0};
unsigned int tbuf[1] = {0};
- size_t tlen = UTF32FromUTF8(s, 3, tbuf, 1);
+ size_t tlen = UTF32FromUTF8(s, tbuf, 1);
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == 0x20AC);
}
@@ -212,7 +212,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF32FromUTF8 Example4") {
const char s[] = {'\xF0', '\x90', '\x8D', '\x88', 0};
unsigned int tbuf[1] = {0};
- size_t tlen = UTF32FromUTF8(s, 4, tbuf, 1);
+ size_t tlen = UTF32FromUTF8(s, tbuf, 1);
REQUIRE(tlen == 1U);
REQUIRE(tbuf[0] == 0x10348);
}
@@ -220,7 +220,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF32FromUTF8 Invalid Trail byte in lead position") {
const char s[] = "a\xB5yz";
unsigned int tbuf[4] = {};
- size_t tlen = UTF32FromUTF8(s, 4, tbuf, 4);
+ size_t tlen = UTF32FromUTF8(s, tbuf, 4);
REQUIRE(tlen == 4U);
REQUIRE(tbuf[0] == static_cast<unsigned int>('a'));
REQUIRE(tbuf[1] == 0xB5);
@@ -231,7 +231,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF32FromUTF8 Invalid Lead byte at end") {
const char s[] = "a\xC2";
unsigned int tbuf[2] = {};
- size_t tlen = UTF32FromUTF8(s, 2, tbuf, 2);
+ size_t tlen = UTF32FromUTF8(s, tbuf, 2);
REQUIRE(tlen == 2U);
REQUIRE(tbuf[0] == static_cast<unsigned int>('a'));
REQUIRE(tbuf[1] == 0xC2);
@@ -240,7 +240,7 @@ TEST_CASE("UniConversion") {
SECTION("UTF32FromUTF8 Invalid Lead byte implies 3 trails but only 2") {
const char *s = "a\xF1yz";
unsigned int tbuf[4] = {};
- size_t tlen = UTF32FromUTF8(s, 4, tbuf, 4);
+ size_t tlen = UTF32FromUTF8(s, tbuf, 4);
REQUIRE(tlen == 2U);
REQUIRE(tbuf[0] == static_cast<unsigned int>('a'));
REQUIRE(tbuf[1] == 0xF1);
diff --git a/win32/PlatWin.cxx b/win32/PlatWin.cxx
index 388002c70..beacc26fb 100644
--- a/win32/PlatWin.cxx
+++ b/win32/PlatWin.cxx
@@ -291,7 +291,7 @@ void SetLogFont(LOGFONTW &lf, const char *faceName, int characterSet, float size
lf.lfItalic = italic ? 1 : 0;
lf.lfCharSet = static_cast<BYTE>(characterSet);
lf.lfQuality = Win32MapFontQuality(extraFontFlag);
- UTF16FromUTF8(faceName, strlen(faceName)+1, lf.lfFaceName, LF_FACESIZE);
+ UTF16FromUTF8(faceName, lf.lfFaceName, LF_FACESIZE);
}
/**
@@ -345,8 +345,8 @@ FontCached::FontCached(const FontParameters &fp) :
#if defined(USE_D2D)
IDWriteTextFormat *pTextFormat;
const int faceSize = 200;
- WCHAR wszFace[faceSize];
- UTF16FromUTF8(fp.faceName, strlen(fp.faceName)+1, wszFace, faceSize);
+ WCHAR wszFace[faceSize] = L"";
+ UTF16FromUTF8(fp.faceName, wszFace, faceSize);
const FLOAT fHeight = fp.size;
const DWRITE_FONT_STYLE style = fp.italic ? DWRITE_FONT_STYLE_ITALIC : DWRITE_FONT_STYLE_NORMAL;
HRESULT hr = pIDWriteFactory->CreateTextFormat(wszFace, NULL,
@@ -395,8 +395,8 @@ bool FontCached::SameAs(const FontParameters &fp) {
(lf.lfCharSet == fp.characterSet) &&
(lf.lfQuality == Win32MapFontQuality(fp.extraFontFlag)) &&
(technology == fp.technology)) {
- wchar_t wszFace[LF_FACESIZE];
- UTF16FromUTF8(fp.faceName, strlen(fp.faceName)+1, wszFace, LF_FACESIZE);
+ wchar_t wszFace[LF_FACESIZE] = L"";
+ UTF16FromUTF8(fp.faceName, wszFace, LF_FACESIZE);
return 0 == wcscmp(lf.lfFaceName,wszFace);
}
return false;
@@ -503,7 +503,7 @@ public:
TextWide(std::string_view text, bool unicodeMode, int codePage=0) :
VarBuffer<wchar_t, stackBufferLength>(text.length()) {
if (unicodeMode) {
- tlen = static_cast<int>(UTF16FromUTF8(text.data(), text.length(), buffer, text.length()));
+ tlen = static_cast<int>(UTF16FromUTF8(text, buffer, text.length()));
} else {
// Support Asian string display in 9x English
tlen = ::MultiByteToWideChar(codePage, 0, text.data(), static_cast<int>(text.length()),
diff --git a/win32/ScintillaWin.cxx b/win32/ScintillaWin.cxx
index 869b1909a..c0b6fb3e2 100644
--- a/win32/ScintillaWin.cxx
+++ b/win32/ScintillaWin.cxx
@@ -803,9 +803,10 @@ Sci::Position ScintillaWin::EncodedFromUTF8(const char *utf8, char *encoded) con
// the current codepage. Code is similar to HandleCompositionWindowed().
void ScintillaWin::AddCharUTF16(wchar_t const *wcs, unsigned int wclen) {
if (IsUnicodeMode()) {
- size_t len = UTF8Length(wcs, wclen);
+ const std::wstring_view wsv(wcs, wclen);
+ size_t len = UTF8Length(wsv);
char utfval[maxLenInputIME * 3];
- UTF8FromUTF16(wcs, wclen, utfval, len);
+ UTF8FromUTF16(wsv, utfval, len);
utfval[len] = '\0';
AddCharUTF(utfval, static_cast<unsigned int>(len));
} else {
@@ -1207,7 +1208,7 @@ sptr_t ScintillaWin::GetTextLength() {
std::vector<char> docBytes(pdoc->Length(), '\0');
pdoc->GetCharRange(&docBytes[0], 0, pdoc->Length());
if (IsUnicodeMode()) {
- return UTF16Length(&docBytes[0], docBytes.size());
+ return UTF16Length(std::string_view(&docBytes[0], docBytes.size()));
} else {
return ::MultiByteToWideChar(CodePageOfDocument(), 0, &docBytes[0],
static_cast<int>(docBytes.size()), NULL, 0);
@@ -1223,12 +1224,13 @@ sptr_t ScintillaWin::GetText(uptr_t wParam, sptr_t lParam) {
std::vector<char> docBytes(pdoc->Length(), '\0');
pdoc->GetCharRange(&docBytes[0], 0, pdoc->Length());
if (IsUnicodeMode()) {
- const size_t lengthUTF16 = UTF16Length(&docBytes[0], docBytes.size());
+ const std::string_view sv(&docBytes[0], docBytes.size());
+ const size_t lengthUTF16 = UTF16Length(sv);
if (lParam == 0)
return lengthUTF16;
if (wParam == 0)
return 0;
- size_t uLen = UTF16FromUTF8(&docBytes[0], docBytes.size(),
+ size_t uLen = UTF16FromUTF8(sv,
ptr, wParam - 1);
ptr[uLen] = L'\0';
return uLen;
@@ -2051,8 +2053,7 @@ public:
if (foldedUTF8) {
// Maximum length of a case conversion is 6 bytes, 3 characters
wchar_t wFolded[20];
- const size_t charsConverted = UTF16FromUTF8(foldedUTF8,
- strlen(foldedUTF8),
+ const size_t charsConverted = UTF16FromUTF8(std::string_view(foldedUTF8),
wFolded, ELEMENTS(wFolded));
for (size_t j=0; j<charsConverted; j++)
utf16Folded[lenFlat++] = wFolded[j];
@@ -2096,8 +2097,7 @@ CaseFolder *ScintillaWin::CaseFolderForEncoding() {
const char *caseFolded = CaseConvert(wCharacter[0], CaseConversionFold);
if (caseFolded) {
wchar_t wLower[20];
- const size_t charsConverted = UTF16FromUTF8(caseFolded,
- strlen(caseFolded),
+ const size_t charsConverted = UTF16FromUTF8(std::string_view(caseFolded),
wLower, ELEMENTS(wLower));
if (charsConverted == 1) {
char sCharacterLowered[20];
@@ -2262,9 +2262,10 @@ void ScintillaWin::Paste() {
// Default Scintilla behaviour in Unicode mode
if (IsUnicodeMode()) {
const size_t bytes = memUSelection.Size();
- len = UTF8Length(uptr, bytes / 2);
+ const std::wstring_view wsv(uptr, bytes / 2);
+ len = UTF8Length(wsv);
putf.resize(len + 1);
- UTF8FromUTF16(uptr, bytes / 2, &putf[0], len);
+ UTF8FromUTF16(wsv, &putf[0], len);
} else {
// CF_UNICODETEXT available, but not in Unicode mode
// Convert from Unicode to current Scintilla code page
@@ -2300,9 +2301,10 @@ void ScintillaWin::Paste() {
const size_t ulen = ::MultiByteToWideChar(CP_ACP, 0,
ptr, ilen, &uptr[0], ilen +1);
- const size_t mlen = UTF8Length(&uptr[0], ulen);
+ const std::wstring_view wsv(&uptr[0], ulen);
+ const size_t mlen = UTF8Length(wsv);
std::vector<char> putf(mlen+1);
- UTF8FromUTF16(&uptr[0], ulen, &putf[0], mlen);
+ UTF8FromUTF16(wsv, &putf[0], mlen);
InsertPasteShape(&putf[0], mlen, pasteShape);
} else {
@@ -2684,7 +2686,7 @@ void ScintillaWin::ImeStartComposition() {
lf.lfFaceName[0] = L'\0';
if (vs.styles[styleHere].fontName) {
const char* fontName = vs.styles[styleHere].fontName;
- UTF16FromUTF8(fontName, strlen(fontName)+1, lf.lfFaceName, LF_FACESIZE);
+ UTF16FromUTF8(std::string_view(fontName), lf.lfFaceName, LF_FACESIZE);
}
::ImmSetCompositionFontW(imc.hIMC, &lf);
@@ -2796,11 +2798,11 @@ void ScintillaWin::CopyToClipboard(const SelectionText &selectedText) {
// Default Scintilla behaviour in Unicode mode
if (IsUnicodeMode()) {
- const size_t uchars = UTF16Length(selectedText.Data(),
- selectedText.LengthWithTerminator());
+ const std::string_view sv(selectedText.Data(), selectedText.LengthWithTerminator());
+ const size_t uchars = UTF16Length(sv);
uniText.Allocate(2 * uchars);
if (uniText) {
- UTF16FromUTF8(selectedText.Data(), selectedText.LengthWithTerminator(),
+ UTF16FromUTF8(sv,
static_cast<wchar_t *>(uniText.ptr), uchars);
}
} else {
@@ -3101,9 +3103,10 @@ STDMETHODIMP ScintillaWin::Drop(LPDATAOBJECT pIDataSource, DWORD grfKeyState,
if (IsUnicodeMode()) {
const size_t tlen = memUDrop.Size();
// Convert UTF-16 to UTF-8
- const size_t dataLen = UTF8Length(udata, tlen/2);
+ const std::wstring_view wsv(udata, tlen / 2);
+ const size_t dataLen = UTF8Length(wsv);
data.resize(dataLen+1);
- UTF8FromUTF16(udata, tlen/2, &data[0], dataLen);
+ UTF8FromUTF16(wsv, &data[0], dataLen);
} else {
// Convert UTF-16 to ANSI
//
@@ -3176,10 +3179,11 @@ STDMETHODIMP ScintillaWin::GetData(FORMATETC *pFEIn, STGMEDIUM *pSTM) {
GlobalMemory text;
if (pFEIn->cfFormat == CF_UNICODETEXT) {
- const size_t uchars = UTF16Length(drag.Data(), drag.LengthWithTerminator());
+ const std::string_view sv(drag.Data(), drag.LengthWithTerminator());
+ const size_t uchars = UTF16Length(sv);
text.Allocate(2 * uchars);
if (text) {
- UTF16FromUTF8(drag.Data(), drag.LengthWithTerminator(),
+ UTF16FromUTF8(sv,
static_cast<wchar_t *>(text.ptr), uchars);
}
} else {
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-31 12:32:57 +0000