aboutsummaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
Diffstat
-rw-r--r--src/CharClassify.cxx16
-rw-r--r--src/CharClassify.h15
-rw-r--r--src/Document.cxx50
-rw-r--r--src/Document.h6
-rw-r--r--src/Editor.cxx12
-rw-r--r--test/unit/testCharClassify.cxx28
6 files changed, 64 insertions, 63 deletions
diff --git a/src/CharClassify.cxx b/src/CharClassify.cxx
index b5e2870f3..f82fe75a6 100644
--- a/src/CharClassify.cxx
+++ b/src/CharClassify.cxx
@@ -21,29 +21,29 @@ CharClassify::CharClassify() : charClass{} {
void CharClassify::SetDefaultCharClasses(bool includeWordClass) {
// Initialize all char classes to default values
- for (int ch = 0; ch < 256; ch++) {
+ for (int ch = 0; ch < maxChar; ch++) {
if (ch == '\r' || ch == '\n')
- charClass[ch] = ccNewLine;
+ charClass[ch] = CharacterClass::newLine;
else if (ch < 0x20 || ch == ' ')
- charClass[ch] = ccSpace;
+ charClass[ch] = CharacterClass::space;
else if (includeWordClass && (ch >= 0x80 || IsAlphaNumeric(ch) || ch == '_'))
- charClass[ch] = ccWord;
+ charClass[ch] = CharacterClass::word;
else
- charClass[ch] = ccPunctuation;
+ charClass[ch] = CharacterClass::punctuation;
}
}
-void CharClassify::SetCharClasses(const unsigned char *chars, cc newCharClass) {
+void CharClassify::SetCharClasses(const unsigned char *chars, CharacterClass newCharClass) {
// Apply the newCharClass to the specified chars
if (chars) {
while (*chars) {
- charClass[*chars] = static_cast<unsigned char>(newCharClass);
+ charClass[*chars] = newCharClass;
chars++;
}
}
}
-int CharClassify::GetCharsOfClass(cc characterClass, unsigned char *buffer) const noexcept {
+int CharClassify::GetCharsOfClass(CharacterClass characterClass, unsigned char *buffer) const noexcept {
// Get characters belonging to the given char class; return the number
// of characters (if the buffer is NULL, don't write to it).
int count = 0;
diff --git a/src/CharClassify.h b/src/CharClassify.h
index 36cc34558..1fcdb9d5d 100644
--- a/src/CharClassify.h
+++ b/src/CharClassify.h
@@ -10,20 +10,21 @@
namespace Scintilla {
+enum class CharacterClass : unsigned char { space, newLine, word, punctuation };
+
class CharClassify {
public:
CharClassify();
- enum cc { ccSpace, ccNewLine, ccWord, ccPunctuation };
void SetDefaultCharClasses(bool includeWordClass);
- void SetCharClasses(const unsigned char *chars, cc newCharClass);
- int GetCharsOfClass(cc characterClass, unsigned char *buffer) const noexcept;
- cc GetClass(unsigned char ch) const noexcept { return static_cast<cc>(charClass[ch]);}
- bool IsWord(unsigned char ch) const noexcept { return static_cast<cc>(charClass[ch]) == ccWord;}
+ void SetCharClasses(const unsigned char *chars, CharacterClass newCharClass);
+ int GetCharsOfClass(CharacterClass characterClass, unsigned char *buffer) const noexcept;
+ CharacterClass GetClass(unsigned char ch) const noexcept { return charClass[ch];}
+ bool IsWord(unsigned char ch) const noexcept { return charClass[ch] == CharacterClass::word;}
private:
- enum { maxChar=256 };
- unsigned char charClass[maxChar]; // not type cc to save space
+ static constexpr int maxChar=256;
+ CharacterClass charClass[maxChar];
};
}
diff --git a/src/Document.cxx b/src/Document.cxx
index 4548064b5..0a4c8ca0b 100644
--- a/src/Document.cxx
+++ b/src/Document.cxx
@@ -1731,7 +1731,7 @@ Sci::Position Document::ParaDown(Sci::Position pos) const {
return LineEnd(line-1);
}
-CharClassify::cc Document::WordCharacterClass(unsigned int ch) const {
+CharacterClass Document::WordCharacterClass(unsigned int ch) const {
if (dbcsCodePage && (!UTF8IsAscii(ch))) {
if (SC_CP_UTF8 == dbcsCodePage) {
// Use hard coded Unicode class
@@ -1741,7 +1741,7 @@ CharClassify::cc Document::WordCharacterClass(unsigned int ch) const {
// Separator, Line/Paragraph
case ccZl:
case ccZp:
- return CharClassify::ccNewLine;
+ return CharacterClass::newLine;
// Separator, Space
case ccZs:
@@ -1751,7 +1751,7 @@ CharClassify::cc Document::WordCharacterClass(unsigned int ch) const {
case ccCs:
case ccCo:
case ccCn:
- return CharClassify::ccSpace;
+ return CharacterClass::space;
// Letter
case ccLu:
@@ -1767,7 +1767,7 @@ CharClassify::cc Document::WordCharacterClass(unsigned int ch) const {
case ccMn:
case ccMc:
case ccMe:
- return CharClassify::ccWord;
+ return CharacterClass::word;
// Punctuation
case ccPc:
@@ -1782,12 +1782,12 @@ CharClassify::cc Document::WordCharacterClass(unsigned int ch) const {
case ccSc:
case ccSk:
case ccSo:
- return CharClassify::ccPunctuation;
+ return CharacterClass::punctuation;
}
} else {
// Asian DBCS
- return CharClassify::ccWord;
+ return CharacterClass::word;
}
}
return charClass.GetClass(static_cast<unsigned char>(ch));
@@ -1798,7 +1798,7 @@ CharClassify::cc Document::WordCharacterClass(unsigned int ch) const {
* Finds the start of word at pos when delta < 0 or the end of the word when delta >= 0.
*/
Sci::Position Document::ExtendWordSelect(Sci::Position pos, int delta, bool onlyWordCharacters) const {
- CharClassify::cc ccStart = CharClassify::ccWord;
+ CharacterClass ccStart = CharacterClass::word;
if (delta < 0) {
if (!onlyWordCharacters) {
const CharacterExtracted ce = CharacterBefore(pos);
@@ -1836,13 +1836,13 @@ Sci::Position Document::NextWordStart(Sci::Position pos, int delta) const {
if (delta < 0) {
while (pos > 0) {
const CharacterExtracted ce = CharacterBefore(pos);
- if (WordCharacterClass(ce.character) != CharClassify::ccSpace)
+ if (WordCharacterClass(ce.character) != CharacterClass::space)
break;
pos -= ce.widthBytes;
}
if (pos > 0) {
CharacterExtracted ce = CharacterBefore(pos);
- const CharClassify::cc ccStart = WordCharacterClass(ce.character);
+ const CharacterClass ccStart = WordCharacterClass(ce.character);
while (pos > 0) {
ce = CharacterBefore(pos);
if (WordCharacterClass(ce.character) != ccStart)
@@ -1852,7 +1852,7 @@ Sci::Position Document::NextWordStart(Sci::Position pos, int delta) const {
}
} else {
CharacterExtracted ce = CharacterAfter(pos);
- const CharClassify::cc ccStart = WordCharacterClass(ce.character);
+ const CharacterClass ccStart = WordCharacterClass(ce.character);
while (pos < LengthNoExcept()) {
ce = CharacterAfter(pos);
if (WordCharacterClass(ce.character) != ccStart)
@@ -1861,7 +1861,7 @@ Sci::Position Document::NextWordStart(Sci::Position pos, int delta) const {
}
while (pos < LengthNoExcept()) {
ce = CharacterAfter(pos);
- if (WordCharacterClass(ce.character) != CharClassify::ccSpace)
+ if (WordCharacterClass(ce.character) != CharacterClass::space)
break;
pos += ce.widthBytes;
}
@@ -1880,8 +1880,8 @@ Sci::Position Document::NextWordEnd(Sci::Position pos, int delta) const {
if (delta < 0) {
if (pos > 0) {
CharacterExtracted ce = CharacterBefore(pos);
- const CharClassify::cc ccStart = WordCharacterClass(ce.character);
- if (ccStart != CharClassify::ccSpace) {
+ const CharacterClass ccStart = WordCharacterClass(ce.character);
+ if (ccStart != CharacterClass::space) {
while (pos > 0) {
ce = CharacterBefore(pos);
if (WordCharacterClass(ce.character) != ccStart)
@@ -1891,7 +1891,7 @@ Sci::Position Document::NextWordEnd(Sci::Position pos, int delta) const {
}
while (pos > 0) {
ce = CharacterBefore(pos);
- if (WordCharacterClass(ce.character) != CharClassify::ccSpace)
+ if (WordCharacterClass(ce.character) != CharacterClass::space)
break;
pos -= ce.widthBytes;
}
@@ -1899,13 +1899,13 @@ Sci::Position Document::NextWordEnd(Sci::Position pos, int delta) const {
} else {
while (pos < LengthNoExcept()) {
const CharacterExtracted ce = CharacterAfter(pos);
- if (WordCharacterClass(ce.character) != CharClassify::ccSpace)
+ if (WordCharacterClass(ce.character) != CharacterClass::space)
break;
pos += ce.widthBytes;
}
if (pos < LengthNoExcept()) {
CharacterExtracted ce = CharacterAfter(pos);
- const CharClassify::cc ccStart = WordCharacterClass(ce.character);
+ const CharacterClass ccStart = WordCharacterClass(ce.character);
while (pos < LengthNoExcept()) {
ce = CharacterAfter(pos);
if (WordCharacterClass(ce.character) != ccStart)
@@ -1926,10 +1926,10 @@ bool Document::IsWordStartAt(Sci::Position pos) const {
return false;
if (pos > 0) {
const CharacterExtracted cePos = CharacterAfter(pos);
- const CharClassify::cc ccPos = WordCharacterClass(cePos.character);
+ const CharacterClass ccPos = WordCharacterClass(cePos.character);
const CharacterExtracted cePrev = CharacterBefore(pos);
- const CharClassify::cc ccPrev = WordCharacterClass(cePrev.character);
- return (ccPos == CharClassify::ccWord || ccPos == CharClassify::ccPunctuation) &&
+ const CharacterClass ccPrev = WordCharacterClass(cePrev.character);
+ return (ccPos == CharacterClass::word || ccPos == CharacterClass::punctuation) &&
(ccPos != ccPrev);
}
return true;
@@ -1944,10 +1944,10 @@ bool Document::IsWordEndAt(Sci::Position pos) const {
return false;
if (pos < LengthNoExcept()) {
const CharacterExtracted cePos = CharacterAfter(pos);
- const CharClassify::cc ccPos = WordCharacterClass(cePos.character);
+ const CharacterClass ccPos = WordCharacterClass(cePos.character);
const CharacterExtracted cePrev = CharacterBefore(pos);
- const CharClassify::cc ccPrev = WordCharacterClass(cePrev.character);
- return (ccPrev == CharClassify::ccWord || ccPrev == CharClassify::ccPunctuation) &&
+ const CharacterClass ccPrev = WordCharacterClass(cePrev.character);
+ return (ccPrev == CharacterClass::word || ccPrev == CharacterClass::punctuation) &&
(ccPrev != ccPos);
}
return true;
@@ -2186,11 +2186,11 @@ void Document::SetDefaultCharClasses(bool includeWordClass) {
charClass.SetDefaultCharClasses(includeWordClass);
}
-void Document::SetCharClasses(const unsigned char *chars, CharClassify::cc newCharClass) {
+void Document::SetCharClasses(const unsigned char *chars, CharacterClass newCharClass) {
charClass.SetCharClasses(chars, newCharClass);
}
-int Document::GetCharsOfClass(CharClassify::cc characterClass, unsigned char *buffer) const {
+int Document::GetCharsOfClass(CharacterClass characterClass, unsigned char *buffer) const {
return charClass.GetCharsOfClass(characterClass, buffer);
}
@@ -2528,7 +2528,7 @@ static bool IsASCIIPunctuationCharacter(unsigned int ch) noexcept {
}
bool Document::IsWordPartSeparator(unsigned int ch) const {
- return (WordCharacterClass(ch) == CharClassify::ccWord) && IsASCIIPunctuationCharacter(ch);
+ return (WordCharacterClass(ch) == CharacterClass::word) && IsASCIIPunctuationCharacter(ch);
}
Sci::Position Document::WordPartLeft(Sci::Position pos) const {
diff --git a/src/Document.h b/src/Document.h
index 91163713b..e2d9eddce 100644
--- a/src/Document.h
+++ b/src/Document.h
@@ -448,8 +448,8 @@ public:
Sci::Line LinesTotal() const noexcept;
void SetDefaultCharClasses(bool includeWordClass);
- void SetCharClasses(const unsigned char *chars, CharClassify::cc newCharClass);
- int GetCharsOfClass(CharClassify::cc characterClass, unsigned char *buffer) const;
+ void SetCharClasses(const unsigned char *chars, CharacterClass newCharClass);
+ int GetCharsOfClass(CharacterClass characterClass, unsigned char *buffer) const;
void SetCharacterCategoryOptimization(int countCharacters);
int CharacterCategoryOptimization() const noexcept;
void SCI_METHOD StartStyling(Sci_Position position) override;
@@ -492,7 +492,7 @@ public:
bool AddWatcher(DocWatcher *watcher, void *userData);
bool RemoveWatcher(DocWatcher *watcher, void *userData);
- CharClassify::cc WordCharacterClass(unsigned int ch) const;
+ CharacterClass WordCharacterClass(unsigned int ch) const;
bool IsWordPartSeparator(unsigned int ch) const;
Sci::Position WordPartLeft(Sci::Position pos) const;
Sci::Position WordPartRight(Sci::Position pos) const;
diff --git a/src/Editor.cxx b/src/Editor.cxx
index 4f1add2c3..dcaa6fc6b 100644
--- a/src/Editor.cxx
+++ b/src/Editor.cxx
@@ -6294,33 +6294,33 @@ sptr_t Editor::WndProc(unsigned int iMessage, uptr_t wParam, sptr_t lParam) {
break;
case SCI_GETWORDCHARS:
- return pdoc->GetCharsOfClass(CharClassify::ccWord, UCharPtrFromSPtr(lParam));
+ return pdoc->GetCharsOfClass(CharacterClass::word, UCharPtrFromSPtr(lParam));
case SCI_SETWORDCHARS: {
pdoc->SetDefaultCharClasses(false);
if (lParam == 0)
return 0;
- pdoc->SetCharClasses(ConstUCharPtrFromSPtr(lParam), CharClassify::ccWord);
+ pdoc->SetCharClasses(ConstUCharPtrFromSPtr(lParam), CharacterClass::word);
}
break;
case SCI_GETWHITESPACECHARS:
- return pdoc->GetCharsOfClass(CharClassify::ccSpace, UCharPtrFromSPtr(lParam));
+ return pdoc->GetCharsOfClass(CharacterClass::space, UCharPtrFromSPtr(lParam));
case SCI_SETWHITESPACECHARS: {
if (lParam == 0)
return 0;
- pdoc->SetCharClasses(ConstUCharPtrFromSPtr(lParam), CharClassify::ccSpace);
+ pdoc->SetCharClasses(ConstUCharPtrFromSPtr(lParam), CharacterClass::space);
}
break;
case SCI_GETPUNCTUATIONCHARS:
- return pdoc->GetCharsOfClass(CharClassify::ccPunctuation, UCharPtrFromSPtr(lParam));
+ return pdoc->GetCharsOfClass(CharacterClass::punctuation, UCharPtrFromSPtr(lParam));
case SCI_SETPUNCTUATIONCHARS: {
if (lParam == 0)
return 0;
- pdoc->SetCharClasses(ConstUCharPtrFromSPtr(lParam), CharClassify::ccPunctuation);
+ pdoc->SetCharClasses(ConstUCharPtrFromSPtr(lParam), CharacterClass::punctuation);
}
break;
diff --git a/test/unit/testCharClassify.cxx b/test/unit/testCharClassify.cxx
index c44a7e973..e329c0378 100644
--- a/test/unit/testCharClassify.cxx
+++ b/test/unit/testCharClassify.cxx
@@ -27,13 +27,13 @@ protected:
pcc.reset(new CharClassify());
for (int ch = 0; ch < 256; ch++) {
if (ch == '\r' || ch == '\n')
- charClass[ch] = CharClassify::ccNewLine;
+ charClass[ch] = CharacterClass::newLine;
else if (ch < 0x20 || ch == ' ')
- charClass[ch] = CharClassify::ccSpace;
+ charClass[ch] = CharacterClass::space;
else if (ch >= 0x80 || isalnum(ch) || ch == '_')
- charClass[ch] = CharClassify::ccWord;
+ charClass[ch] = CharacterClass::word;
else
- charClass[ch] = CharClassify::ccPunctuation;
+ charClass[ch] = CharacterClass::punctuation;
}
}
@@ -41,15 +41,15 @@ protected:
}
std::unique_ptr<CharClassify> pcc;
- CharClassify::cc charClass[256];
+ CharacterClass charClass[256];
- static const char* GetClassName(CharClassify::cc charClass) {
+ static const char* GetClassName(CharacterClass charClass) {
switch(charClass) {
- #define CASE(c) case CharClassify::c: return #c
- CASE(ccSpace);
- CASE(ccNewLine);
- CASE(ccWord);
- CASE(ccPunctuation);
+ #define CASE(c) case CharacterClass::c: return #c
+ CASE(space);
+ CASE(newLine);
+ CASE(word);
+ CASE(punctuation);
#undef CASE
default:
return "<unknown>";
@@ -71,7 +71,7 @@ TEST_CASE_METHOD(CharClassifyTest, "Defaults") {
TEST_CASE_METHOD(CharClassifyTest, "Custom") {
unsigned char buf[2] = {0, 0};
for (int i = 0; i < 256; i++) {
- CharClassify::cc thisClass = CharClassify::cc(i % 4);
+ CharacterClass thisClass = CharacterClass(i % 4);
buf[0] = i;
pcc->SetCharClasses(buf, thisClass);
charClass[i] = thisClass;
@@ -89,13 +89,13 @@ TEST_CASE_METHOD(CharClassifyTest, "Custom") {
TEST_CASE_METHOD(CharClassifyTest, "CharsOfClass") {
unsigned char buf[2] = {0, 0};
for (int i = 1; i < 256; i++) {
- CharClassify::cc thisClass = CharClassify::cc(i % 4);
+ CharacterClass thisClass = CharacterClass(i % 4);
buf[0] = i;
pcc->SetCharClasses(buf, thisClass);
charClass[i] = thisClass;
}
for (int classVal = 0; classVal < 4; ++classVal) {
- CharClassify::cc thisClass = CharClassify::cc(classVal % 4);
+ CharacterClass thisClass = CharacterClass(classVal % 4);
int size = pcc->GetCharsOfClass(thisClass, NULL);
std::vector<unsigned char> buffer(size+1);
pcc->GetCharsOfClass(thisClass, &buffer[0]);
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-11 06:01:06 +0000