+upd: Lexilla Lib v5.1.5

.editorconfig

@@ -21,8 +21,13 @@ indent_style = space
 indent_size = 4
 tab_width = 4
 
-[**.{ini}]
-charset = utf-8-sig
+[lexilla/**.{h,c,cpp,hpp,cxx}]
+# Set default charset
+#charset = utf-8
+# space (w=2) indentation
+indent_style = tab
+indent_size = 4
+tab_width = 4
 
 [language/**.{h,rc}]
 charset = utf-8
@@ -33,3 +38,7 @@ tab_width = 4
 
 [language/common_res.rc]
 charset = latin1
+
+[**.{ini}]
+charset = utf-8-sig
+

lexilla/doc/Lexilla.html

@@ -9,7 +9,7 @@
  <meta name="keywords" content="Scintilla, SciTE, Editing Component, Text Editor" />
  <meta name="Description"
  content="www.scintilla.org is the home of the Scintilla editing component and SciTE text editor application." />
- <meta name="Date.Modified" content="20211207" />
+ <meta name="Date.Modified" content="20220209" />
  <meta name="viewport" content="width=device-width, initial-scale=1" />
  <style type="text/css">
  .logo {
@@ -61,8 +61,8 @@
  <font color="#FFCC99" size="4"> A library of language lexers for use with Scintilla</font>
  </td>
  <td width="40%" align="right">
- <font color="#FFCC99" size="3">Release version 5.1.4<br />
- Site last modified December 7 2021</font>
+ <font color="#FFCC99" size="3">Release version 5.1.5<br />
+ Site last modified February 9 2022</font>
  </td>
  <td width="20%">
  &nbsp;
@@ -77,13 +77,10 @@
  </tr>
  </table>
  <ul id="versionlist">
+ <li>Version 5.1.5 improves Bash, Batch, F#, HTML, Inno Setup, and Python.</li>
  <li>Version 5.1.4 adds lexers for AsciiDoc and GDScript.</li>
  <li>Version 5.1.3 improves Rust.</li>
  <li>Version 5.1.2 improves CSS, F#, Inno Setup, Markdown, and PHP.</li>
- <li>Version 5.1.1 improves C++, Julia, Markdown, Matlab, and PHP.</li>
- <li>Version 5.1.0 is a stable release: the interfaces between Scintilla and Lexilla and between
- platform-independent code and platform layers should remain compatible through 5.x releases.
- Improvements were made for ASP, Erlang, F#, Raku, Ruby, Tcl, and YAML.</li>
  </ul>
  <ul id="menu">
  <li id="remote1"><a href="https://www.scintilla.org/SciTEImage.html">Screenshot</a></li>

lexilla/doc/LexillaDownload.html

@@ -26,9 +26,9 @@
  <table bgcolor="#CCCCCC" width="100%" cellspacing="0" cellpadding="8" border="0">
  <tr>
  <td>
- <font size="4"> <a href="https://www.scintilla.org/lexilla514.zip">
+ <font size="4"> <a href="https://www.scintilla.org/lexilla515.zip">
  Windows</a>&nbsp;&nbsp;
- <a href="https://www.scintilla.org/lexilla514.tgz">
+ <a href="https://www.scintilla.org/lexilla515.tgz">
  GTK/Linux</a>&nbsp;&nbsp;
  </font>
  </td>
@@ -42,16 +42,16 @@ <h2>
  containing very few restrictions.
  </p>
  <h3>
- Release 4.4.6
+ Release 5.1.5
  </h3>
  <h4>
  Source Code
  </h4>
  The source code package contains all of the source code for Lexilla but no binary
  executable code and is available in
  <ul>
- <li><a href="https://www.scintilla.org/lexilla514.zip">zip format</a> (1.1M) commonly used on Windows</li>
- <li><a href="https://www.scintilla.org/lexilla514.tgz">tgz format</a> (0.8M) commonly used on Linux and compatible operating systems</li>
+ <li><a href="https://www.scintilla.org/lexilla515.zip">zip format</a> (1.1M) commonly used on Windows</li>
+ <li><a href="https://www.scintilla.org/lexilla515.tgz">tgz format</a> (0.9M) commonly used on Linux and compatible operating systems</li>
  </ul>
  Instructions for building on both Windows and Linux are included in the readme file.
  <h4>

lexilla/doc/LexillaHistory.html

@@ -574,9 +574,54 @@ <h2>Contributors</h2>
  <td>Michael Heath</td>
  <td>Antonio Cebrián</td>
  <td>David Yu Yang</td>
+ <td>Arkadiusz Michalski</td>
+ </tr><tr>
+ <td>Red_M</td>
  </tr>
  </table>
  <h2>Releases</h2>
+ <h3>
+ <a href="https://www.scintilla.org/lexilla515.zip">Release 5.1.5</a>
+ </h3>
+ <ul>
+ <li>
+ Released 9 February 2022.
+ </li>
+ <li>
+ Bash: Treat \r\n line ends the same as \n. This makes testing easier.
+ <a href="https://github.com/ScintillaOrg/lexilla/issues/57">Issue #57</a>.
+ </li>
+ <li>
+ Batch: Recognise "::" comments when second command on line.
+ <a href="https://sourceforge.net/p/scintilla/bugs/2304/">Bug #2304</a>.
+ </li>
+ <li>
+ F#: Recognise format specifiers in interpolated strings and %B for binary.
+ <a href="https://github.com/ScintillaOrg/lexilla/issues/46">Issue #46</a>.
+ </li>
+ <li>
+ F#: More accurate line-based folding.
+ <a href="https://github.com/ScintillaOrg/lexilla/issues/56">Issue #56</a>.
+ </li>
+ <li>
+ HTML: Fix folding inside script blocks.
+ <a href="https://github.com/ScintillaOrg/lexilla/issues/47">Issue #47</a>,
+ <a href="https://github.com/ScintillaOrg/lexilla/issues/53">Issue #53</a>.
+ </li>
+ <li>
+ Inno Setup: Fix multiline comments in code.
+ <a href="https://github.com/ScintillaOrg/lexilla/issues/44">Issue #44</a>.
+ </li>
+ <li>
+ Python: Add attribute style with properties lexer.python.identifier.attributes and
+ lexer.python.decorator.attributes.
+ <a href="https://github.com/ScintillaOrg/lexilla/pull/49">Pull request #49</a>.
+ </li>
+ <li>
+ Allow choice of object file directory with makefile by setting DIR_O.
+ <a href="https://github.com/ScintillaOrg/lexilla/issues/50">Issue #50</a>.
+ </li>
+ </ul>
  <h3>
  <a href="https://www.scintilla.org/lexilla514.zip">Release 5.1.4</a>
  </h3>
@@ -595,7 +640,7 @@ <h3>
  </li>
  <li>
  Fix strings ending in escaped '\' in F#.
- <a href="https://github.com/ScintillaOrg/lexilla/issues/38">Issue #38</a>,
+ <a href="https://github.com/ScintillaOrg/lexilla/issues/38">Issue #38</a>.
  </li>
  <li>
  Better handling of bad terminators and folding for X12.

lexilla/include/LexicalStyles.iface

@@ -171,6 +171,7 @@ val SCE_P_FSTRING=16
 val SCE_P_FCHARACTER=17
 val SCE_P_FTRIPLE=18
 val SCE_P_FTRIPLEDOUBLE=19
+val SCE_P_ATTRIBUTE=20
 # Lexical states for SCLEX_CPP
 # Lexical states for SCLEX_BULLANT
 # Lexical states for SCLEX_COBOL

lexilla/include/SciLexer.h

@@ -169,6 +169,7 @@
 #define SCE_P_FCHARACTER 17
 #define SCE_P_FTRIPLE 18
 #define SCE_P_FTRIPLEDOUBLE 19
+#define SCE_P_ATTRIBUTE 20
 #define SCE_C_DEFAULT 0
 #define SCE_C_COMMENT 1
 #define SCE_C_COMMENTLINE 2

lexilla/lexers/LexBash.cxx

@@ -609,7 +609,7 @@ void SCI_METHOD LexerBash::Lex(Sci_PositionU startPos, Sci_Position length, int
  sc.SetState(SCE_SH_DEFAULT);
  break;
  case SCE_SH_COMMENTLINE:
- if (sc.atLineEnd && sc.chPrev != '\\') {
+ if (sc.MatchLineEnd() && sc.chPrev != '\\') {
  sc.SetState(SCE_SH_DEFAULT);
  }
  break;
@@ -678,13 +678,13 @@ void SCI_METHOD LexerBash::Lex(Sci_PositionU startPos, Sci_Position length, int
  if (sc.atLineStart) {
  sc.SetState(SCE_SH_HERE_Q);
  int prefixws = 0;
- while (sc.ch == '\t' && !sc.atLineEnd) { // tabulation prefix
+ while (sc.ch == '\t' && !sc.MatchLineEnd()) { // tabulation prefix
  sc.Forward();
  prefixws++;
  }
  if (prefixws > 0)
  sc.SetState(SCE_SH_HERE_Q);
- while (!sc.atLineEnd) {
+ while (!sc.MatchLineEnd()) {
  sc.Forward();
  }
  char s[HERE_DELIM_MAX];
@@ -794,7 +794,7 @@ void SCI_METHOD LexerBash::Lex(Sci_PositionU startPos, Sci_Position length, int
  }
 
  // Must check end of HereDoc state 1 before default state is handled
- if (HereDoc.State == 1 && sc.atLineEnd) {
+ if (HereDoc.State == 1 && sc.MatchLineEnd()) {
  // Begin of here-doc (the line after the here-doc delimiter):
  // Lexically, the here-doc starts from the next line after the >>, but the
  // first line of here-doc seem to follow the style of the last EOL sequence

lexilla/lexers/LexBatch.cxx

@@ -194,9 +194,12 @@ void ColouriseBatchDoc(
  Sci_PositionU wbo = 0; // Word Buffer Offset - also Special Keyword Buffer Length
 
  // Check for Comment - return if found
- if ((CompareCaseInsensitive(wordBuffer, "rem") == 0) && continueProcessing) {
- styler.ColourTo(endPos, SCE_BAT_COMMENT);
- break;
+ if (continueProcessing) {
+ if ((CompareCaseInsensitive(wordBuffer, "rem") == 0) || (wordBuffer[0] == ':' && wordBuffer[1] == ':')) {
+ styler.ColourTo(startLine + offset - strlen(wordBuffer) - 1, SCE_BAT_DEFAULT);
+ styler.ColourTo(endPos, SCE_BAT_COMMENT);
+ break;
+ }
  }
  // Check for Separator
  if (IsBSeparator(wordBuffer[0])) {

lexilla/lexers/LexHTML.cxx

@@ -99,15 +99,13 @@ script_type segIsScriptingIndicator(Accessor &styler, Sci_PositionU start, Sci_P
  char s[100];
  GetTextSegment(styler, start, end, s, sizeof(s));
  //Platform::DebugPrintf("Scripting indicator [%s]\n", s);
- if (strstr(s, "src")) // External script
- return eScriptNone;
  if (strstr(s, "vbs"))
  return eScriptVBS;
  if (strstr(s, "pyth"))
  return eScriptPython;
- if (strstr(s, "javas"))
-  return eScriptJS;
- if (strstr(s, "jscr"))
+ // https://html.spec.whatwg.org/multipage/scripting.html#attr-script-type
+ // https://mimesniff.spec.whatwg.org/#javascript-mime-type
+ if (strstr(s, "javas") || strstr(s, "ecmas") || strstr(s, "module") || strstr(s, "jscr"))
  return eScriptJS;
  if (strstr(s, "php"))
  return eScriptPHP;
@@ -183,9 +181,8 @@ int stateForPrintState(int StateToPrint) {
  return state;
 }
 
-inline bool IsNumber(Sci_PositionU start, Accessor &styler) {
- return IsADigit(styler[start]) || (styler[start] == '.') ||
- (styler[start] == '-') || (styler[start] == '#');
+constexpr bool IsNumberChar(char ch) noexcept {
+ return IsADigit(ch) || ch == '.' || ch == '-' || ch == '#';
 }
 
 inline bool isStringState(int state) {
@@ -254,20 +251,27 @@ inline bool isCommentASPState(int state) {
  return bResult;
 }
 
-void classifyAttribHTML(Sci_PositionU start, Sci_PositionU end, const WordList &keywords, Accessor &styler) {
- const bool wordIsNumber = IsNumber(start, styler);
+bool classifyAttribHTML(script_mode inScriptType, Sci_PositionU start, Sci_PositionU end, const WordList &keywords, Accessor &styler) {
  char chAttr = SCE_H_ATTRIBUTEUNKNOWN;
- if (wordIsNumber) {
+ bool isLanguageType = false;
+ if (IsNumberChar(styler[start])) {
  chAttr = SCE_H_NUMBER;
  } else {
- std::string s = GetStringSegment(styler, start, end);
+ const std::string s = GetStringSegment(styler, start, end);
  if (keywords.InList(s.c_str()))
  chAttr = SCE_H_ATTRIBUTE;
+ if (inScriptType == eNonHtmlScript) {
+ // see https://html.spec.whatwg.org/multipage/scripting.html#script-processing-model
+ if (s == "type" || s == "language") {
+ isLanguageType = true;
+ }
+ }
  }
  if ((chAttr == SCE_H_ATTRIBUTEUNKNOWN) && !keywords)
  // No keywords -> all are known
  chAttr = SCE_H_ATTRIBUTE;
  styler.ColourTo(end, chAttr);
+ return isLanguageType;
 }
 
 // https://html.spec.whatwg.org/multipage/custom-elements.html#custom-elements-core-concepts
@@ -1129,6 +1133,7 @@ void SCI_METHOD LexerHTML::Lex(Sci_PositionU startPos, Sci_Position length, int
  script_type aspScript = static_cast<script_type>((lineState >> 4) & 0x0F); // 4 bits of script name
  script_type clientScript = static_cast<script_type>((lineState >> 8) & 0x0F); // 4 bits of script name
  int beforePreProc = (lineState >> 12) & 0xFF; // 8 bits of state
+ bool isLanguageType = (lineState >> 20) & 1; // type or language attribute for script tag
 
  script_type scriptLanguage = ScriptOfState(state);
  // If eNonHtmlScript coincides with SCE_H_COMMENT, assume eScriptComment
@@ -1210,7 +1215,9 @@ void SCI_METHOD LexerHTML::Lex(Sci_PositionU startPos, Sci_Position length, int
  case eScriptPHP:
  //not currently supported case eScriptVBS:
 
- if ((state != SCE_HPHP_COMMENT) && (state != SCE_HPHP_COMMENTLINE) && (state != SCE_HJ_COMMENT) && (state != SCE_HJ_COMMENTLINE) && (state != SCE_HJ_COMMENTDOC) && (!isStringState(state))) {
+ if (!(state == SCE_HPHP_COMMENT || state == SCE_HPHP_COMMENTLINE) &&
+ !(state == SCE_HJ_REGEX || state == SCE_HJ_COMMENT || state == SCE_HJ_COMMENTLINE || state == SCE_HJ_COMMENTDOC) &&
+ !isStringState(state)) {
  //Platform::DebugPrintf("state=%d, StateToPrint=%d, initStyle=%d\n", state, StateToPrint, initStyle);
  //if ((state == SCE_HPHP_OPERATOR) || (state == SCE_HPHP_DEFAULT) || (state == SCE_HJ_SYMBOLS) || (state == SCE_HJ_START) || (state == SCE_HJ_DEFAULT)) {
  if (ch == '#') {
@@ -1282,7 +1289,8 @@ void SCI_METHOD LexerHTML::Lex(Sci_PositionU startPos, Sci_Position length, int
  ((tagClosing ? 1 : 0) << 3) |
  ((aspScript & 0x0F) << 4) |
  ((clientScript & 0x0F) << 8) |
- ((beforePreProc & 0xFF) << 12));
+ ((beforePreProc & 0xFF) << 12) |
+ ((isLanguageType ? 1 : 0) << 20));
  lineCurrent++;
  lineStartVisibleChars = 0;
  }
@@ -1355,6 +1363,7 @@ void SCI_METHOD LexerHTML::Lex(Sci_PositionU startPos, Sci_Position length, int
  inScriptType = eHtml;
  scriptLanguage = eScriptNone;
  clientScript = eScriptJS;
+ isLanguageType = false;
  i += 2;
  visibleChars += 2;
  tagClosing = true;
@@ -1880,6 +1889,7 @@ void SCI_METHOD LexerHTML::Lex(Sci_PositionU startPos, Sci_Position length, int
  } else {
  scriptLanguage = eScriptNone;
  }
+ isLanguageType = false;
  eClass = SCE_H_TAG;
  }
  if (ch == '>') {
@@ -1925,14 +1935,7 @@ void SCI_METHOD LexerHTML::Lex(Sci_PositionU startPos, Sci_Position length, int
  break;
  case SCE_H_ATTRIBUTE:
  if (!setAttributeContinue.Contains(ch)) {
- if (inScriptType == eNonHtmlScript) {
- const int scriptLanguagePrev = scriptLanguage;
- clientScript = segIsScriptingIndicator(styler, styler.GetStartSegment(), i - 1, scriptLanguage);
- scriptLanguage = clientScript;
- if ((scriptLanguagePrev != scriptLanguage) && (scriptLanguage == eScriptNone))
- inScriptType = eHtml;
- }
- classifyAttribHTML(styler.GetStartSegment(), i - 1, keywords, styler);
+ isLanguageType = classifyAttribHTML(inScriptType, styler.GetStartSegment(), i - 1, keywords, styler);
  if (ch == '>') {
  styler.ColourTo(i, SCE_H_TAG);
  if (inScriptType == eNonHtmlScript) {
@@ -2007,17 +2010,21 @@ void SCI_METHOD LexerHTML::Lex(Sci_PositionU startPos, Sci_Position length, int
  break;
  case SCE_H_DOUBLESTRING:
  if (ch == '\"') {
- if (inScriptType == eNonHtmlScript) {
+ if (isLanguageType) {
  scriptLanguage = segIsScriptingIndicator(styler, styler.GetStartSegment(), i, scriptLanguage);
+ clientScript = scriptLanguage;
+ isLanguageType = false;
  }
  styler.ColourTo(i, SCE_H_DOUBLESTRING);
  state = SCE_H_OTHER;
  }
  break;
  case SCE_H_SINGLESTRING:
  if (ch == '\'') {
- if (inScriptType == eNonHtmlScript) {
+ if (isLanguageType) {
  scriptLanguage = segIsScriptingIndicator(styler, styler.GetStartSegment(), i, scriptLanguage);
+ clientScript = scriptLanguage;
+ isLanguageType = false;
  }
  styler.ColourTo(i, SCE_H_SINGLESTRING);
  state = SCE_H_OTHER;
@@ -2031,7 +2038,7 @@ void SCI_METHOD LexerHTML::Lex(Sci_PositionU startPos, Sci_Position length, int
  } else if (ch == '\'' && chPrev == '=') {
  state = SCE_H_SINGLESTRING;
  } else {
- if (IsNumber(styler.GetStartSegment(), styler)) {
+ if (IsNumberChar(styler[styler.GetStartSegment()])) {
  styler.ColourTo(i - 1, SCE_H_NUMBER);
  } else {
  styler.ColourTo(i - 1, StateToPrint);