+ upd: Lexilla: Batch-Lexer (commit: 28cadb3101)

+ pch: patching Markdown-Lexer (eolfilled header lines)
This commit is contained in:
Rainer Kottenhoff 2021-05-26 09:18:24 +02:00
parent 0b6d9c42f2
commit 9563b3c478
12 changed files with 989 additions and 32 deletions

View File

@ -70,7 +70,6 @@
<ClCompile Include="lexers\LexLaTeX.cxx" />
<ClCompile Include="lexers\LexLua.cxx" />
<ClCompile Include="lexers\LexMake.cxx" />
<ClCompile Include="lexers\LexMarkdown.cxx" />
<ClCompile Include="lexers\LexMatlab.cxx" />
<ClCompile Include="lexers\LexNim.cxx" />
<ClCompile Include="lexers\LexNsis.cxx" />
@ -94,6 +93,7 @@
<ClCompile Include="lexers_x\LexerUtils.cxx" />
<ClCompile Include="lexers_x\LexJSON.cxx" />
<ClCompile Include="lexers_x\LexKotlin.cxx" />
<ClCompile Include="lexers_x\LexMarkdown.cxx" />
<ClCompile Include="lexers_x\LexPython.cxx" />
<ClCompile Include="lexers_x\LexTOML.cxx" />
<ClCompile Include="lexlib\Accessor.cxx" />

View File

@ -152,9 +152,6 @@
<ClCompile Include="lexers\LexMake.cxx">
<Filter>lexers</Filter>
</ClCompile>
<ClCompile Include="lexers\LexMarkdown.cxx">
<Filter>lexers</Filter>
</ClCompile>
<ClCompile Include="lexers\LexMatlab.cxx">
<Filter>lexers</Filter>
</ClCompile>
@ -266,6 +263,9 @@
<ClCompile Include="lexers\LexJulia.cxx">
<Filter>lexers</Filter>
</ClCompile>
<ClCompile Include="lexers_x\LexMarkdown.cxx">
<Filter>lexers_x</Filter>
</ClCompile>
</ItemGroup>
<ItemGroup>
<ResourceCompile Include="src\LexillaVersion.rc">

View File

@ -500,6 +500,14 @@ static void ColouriseBatchDoc(
styler.ColourTo(startLine + offset - 1 - (wbl - 3), SCE_BAT_IDENTIFIER);
// Reset Offset to re-process remainder of word
offset -= (wbl - 3);
// escaped %
} else if (
(wbl > 1) &&
(wordBuffer[1] == '%')) {
// Reset Offset to re-process remainder of word
styler.ColourTo(startLine + offset - 1 - (wbl - 2), SCE_BAT_DEFAULT);
offset -= (wbl - 2);
}
// Check for Environment Variable (!x...!)
} else if (wordBuffer[0] == '!') {

View File

@ -30,8 +30,8 @@
#include "CharSetX.h"
#include "SciXLexer.h"
using namespace Lexilla;
using namespace Scintilla;
using namespace Lexilla;
static const char *const JSONWordListDesc[] = {
"JSON Keywords",
@ -590,4 +590,7 @@ void SCI_METHOD LexerJSON::Fold(Sci_PositionU startPos,
}
}
LexerModule lmJSON(SCLEX_JSON, LexerJSON::LexerFactoryJSON, "json", JSONWordListDesc);
LexerModule lmJSON(SCLEX_JSON,
LexerJSON::LexerFactoryJSON,
"json",
JSONWordListDesc);

View File

@ -0,0 +1,442 @@
/******************************************************************
* LexMarkdown.cxx
*
* A simple Markdown lexer for scintilla.
*
* Includes highlighting for some extra features from the
* Pandoc implementation; strikeout, using '#.' as a default
* ordered list item marker, and delimited code blocks.
*
* Limitations:
*
* Standard indented code blocks are not highlighted at all,
* as it would conflict with other indentation schemes. Use
* delimited code blocks for blanket highlighting of an
* entire code block. Embedded HTML is not highlighted either.
* Blanket HTML highlighting has issues, because some Markdown
* implementations allow Markdown markup inside of the HTML. Also,
* there is a following blank line issue that can't be ignored,
* explained in the next paragraph. Embedded HTML and code
* blocks would be better supported with language specific
* highlighting.
*
* The highlighting aims to accurately reflect correct syntax,
* but a few restrictions are relaxed. Delimited code blocks are
* highlighted, even if the line following the code block is not blank.
* Requiring a blank line after a block, breaks the highlighting
* in certain cases, because of the way Scintilla ends up calling
* the lexer.
*
* Written by Jon Strait - jstrait@moonloop.net
*
* The License.txt file describes the conditions under which this
* software may be distributed.
*
*****************************************************************/
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <stdarg.h>
#include <assert.h>
#include "ILexer.h"
#include "Scintilla.h"
#include "SciLexer.h"
#include "WordList.h"
#include "LexAccessor.h"
#include "Accessor.h"
#include "StyleContext.h"
#include "CharacterSet.h"
#include "LexerModule.h"
using namespace Lexilla;
static inline bool IsNewline(const int ch) {
return (ch == '\n' || ch == '\r');
}
// True if can follow ch down to the end with possibly trailing whitespace
static bool FollowToLineEnd(const int ch, const int state, const Sci_PositionU endPos, StyleContext &sc) {
Sci_PositionU i = 0;
while (sc.GetRelative(++i) == ch)
;
// Skip over whitespace
while (IsASpaceOrTab(sc.GetRelative(i)) && sc.currentPos + i < endPos)
++i;
if (IsNewline(sc.GetRelative(i)) || sc.currentPos + i == endPos) {
sc.Forward(i);
sc.ChangeState(state);
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
return true;
}
else return false;
}
#if 0
// Set the state on text section from current to length characters,
// then set the rest until the newline to default, except for any characters matching token
static void SetStateAndZoom(const int state, const Sci_Position length, const int token, StyleContext &sc) {
sc.SetState(state);
sc.Forward(length);
sc.SetState(SCE_MARKDOWN_DEFAULT);
sc.Forward();
bool started = false;
while (sc.More() && !IsNewline(sc.ch)) {
if (sc.ch == token && !started) {
sc.SetState(state);
started = true;
}
else if (sc.ch != token) {
sc.SetState(SCE_MARKDOWN_DEFAULT);
started = false;
}
sc.Forward();
}
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
}
#else
static void SetStateAndZoom(const int state, const Sci_Position length, const int token, StyleContext& sc) {
sc.SetState(state);
sc.Forward(length);
bool started = false;
while (sc.More() && !sc.atLineStart) {
if (sc.ch == token) {
sc.SetState(state);
started = !started;
}
else {
sc.SetState(started ? SCE_MARKDOWN_HDRTEXT : state);
}
sc.Forward();
}
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
}
#endif
// Does the previous line have more than spaces and tabs?
static bool HasPrevLineContent(StyleContext &sc) {
Sci_Position i = 0;
// Go back to the previous newline
while ((--i + (Sci_Position)sc.currentPos) >= 0 && !IsNewline(sc.GetRelative(i)))
;
while ((--i + (Sci_Position)sc.currentPos) >= 0) {
const int ch = sc.GetRelative(i);
if (ch == '\n')
break;
if (!((ch == '\r' || IsASpaceOrTab(ch))))
return true;
}
return false;
}
static bool AtTermStart(StyleContext &sc) {
return sc.currentPos == 0 || sc.chPrev == 0 || isspacechar(sc.chPrev);
}
static bool IsValidHrule(const Sci_PositionU endPos, StyleContext &sc) {
int count = 1;
Sci_PositionU i = 0;
for (;;) {
++i;
int c = sc.GetRelative(i);
if (c == sc.ch)
++count;
// hit a terminating character
else if (!IsASpaceOrTab(c) || sc.currentPos + i == endPos) {
// Are we a valid HRULE
if ((IsNewline(c) || sc.currentPos + i == endPos) &&
count >= 3 && !HasPrevLineContent(sc)) {
sc.SetState(SCE_MARKDOWN_HRULE);
sc.Forward(i);
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
return true;
}
else {
sc.SetState(SCE_MARKDOWN_DEFAULT);
return false;
}
}
}
}
static void ColorizeMarkdownDoc(Sci_PositionU startPos, Sci_Position length, int initStyle,
WordList **, Accessor &styler) {
Sci_PositionU endPos = startPos + length;
int precharCount = 0;
bool isLinkNameDetecting = false;
// Don't advance on a new loop iteration and retry at the same position.
// Useful in the corner case of having to start at the beginning file position
// in the default state.
bool freezeCursor = false;
StyleContext sc(startPos, length, initStyle, styler);
while (sc.More()) {
// Skip past escaped characters
if (sc.ch == '\\') {
sc.Forward();
continue;
}
// A blockquotes resets the line semantics
if (sc.state == SCE_MARKDOWN_BLOCKQUOTE)
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
// Conditional state-based actions
if (sc.state == SCE_MARKDOWN_CODE2) {
if (sc.Match("``") && sc.GetRelative(-2) != ' ') {
sc.Forward(2);
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
}
else if (sc.state == SCE_MARKDOWN_CODE) {
if (sc.ch == '`' && sc.chPrev != ' ')
sc.ForwardSetState(SCE_MARKDOWN_DEFAULT);
}
/* De-activated because it gets in the way of other valid indentation
* schemes, for example multiple paragraphs inside a list item.
// Code block
else if (sc.state == SCE_MARKDOWN_CODEBK) {
bool d = true;
if (IsNewline(sc.ch)) {
if (sc.chNext != '\t') {
for (int c = 1; c < 5; ++c) {
if (sc.GetRelative(c) != ' ')
d = false;
}
}
}
else if (sc.atLineStart) {
if (sc.ch != '\t' ) {
for (int i = 0; i < 4; ++i) {
if (sc.GetRelative(i) != ' ')
d = false;
}
}
}
if (!d)
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
}
*/
// Strong
else if (sc.state == SCE_MARKDOWN_STRONG1) {
if (sc.Match("**") && sc.chPrev != ' ') {
sc.Forward(2);
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
}
else if (sc.state == SCE_MARKDOWN_STRONG2) {
if (sc.Match("__") && sc.chPrev != ' ') {
sc.Forward(2);
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
}
// Emphasis
else if (sc.state == SCE_MARKDOWN_EM1) {
if (sc.ch == '*' && sc.chPrev != ' ')
sc.ForwardSetState(SCE_MARKDOWN_DEFAULT);
}
else if (sc.state == SCE_MARKDOWN_EM2) {
if (sc.ch == '_' && sc.chPrev != ' ')
sc.ForwardSetState(SCE_MARKDOWN_DEFAULT);
}
else if (sc.state == SCE_MARKDOWN_CODEBK) {
if (sc.atLineStart && sc.Match("~~~")) {
Sci_Position i = 1;
while (!IsNewline(sc.GetRelative(i)) && sc.currentPos + i < endPos)
i++;
sc.Forward(i);
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
}
else if (sc.state == SCE_MARKDOWN_STRIKEOUT) {
if (sc.Match("~~") && sc.chPrev != ' ') {
sc.Forward(2);
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
}
else if (sc.state == SCE_MARKDOWN_LINE_BEGIN) {
// Header
if (sc.Match("######"))
SetStateAndZoom(SCE_MARKDOWN_HEADER6, 6, '#', sc);
else if (sc.Match("#####"))
SetStateAndZoom(SCE_MARKDOWN_HEADER5, 5, '#', sc);
else if (sc.Match("####"))
SetStateAndZoom(SCE_MARKDOWN_HEADER4, 4, '#', sc);
else if (sc.Match("###"))
SetStateAndZoom(SCE_MARKDOWN_HEADER3, 3, '#', sc);
else if (sc.Match("##"))
SetStateAndZoom(SCE_MARKDOWN_HEADER2, 2, '#', sc);
else if (sc.Match("#")) {
// Catch the special case of an unordered list
if (sc.chNext == '.' && IsASpaceOrTab(sc.GetRelative(2))) {
precharCount = 0;
sc.SetState(SCE_MARKDOWN_PRECHAR);
}
else
SetStateAndZoom(SCE_MARKDOWN_HEADER1, 1, '#', sc);
}
// Code block
else if (sc.Match("~~~")) {
if (!HasPrevLineContent(sc))
sc.SetState(SCE_MARKDOWN_CODEBK);
else
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
else if (sc.ch == '=') {
if (HasPrevLineContent(sc) && FollowToLineEnd('=', SCE_MARKDOWN_HEADER1, endPos, sc))
;
else
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
else if (sc.ch == '-') {
if (HasPrevLineContent(sc) && FollowToLineEnd('-', SCE_MARKDOWN_HEADER2, endPos, sc))
;
else {
precharCount = 0;
sc.SetState(SCE_MARKDOWN_PRECHAR);
}
}
else if (IsNewline(sc.ch))
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
else {
precharCount = 0;
sc.SetState(SCE_MARKDOWN_PRECHAR);
}
}
// The header lasts until the newline
else if (sc.state == SCE_MARKDOWN_HEADER1 || sc.state == SCE_MARKDOWN_HEADER2 ||
sc.state == SCE_MARKDOWN_HEADER3 || sc.state == SCE_MARKDOWN_HEADER4 ||
sc.state == SCE_MARKDOWN_HEADER5 || sc.state == SCE_MARKDOWN_HEADER6) {
if (IsNewline(sc.ch))
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
}
// New state only within the initial whitespace
if (sc.state == SCE_MARKDOWN_PRECHAR) {
// Blockquote
if (sc.ch == '>' && precharCount < 5)
sc.SetState(SCE_MARKDOWN_BLOCKQUOTE);
/*
// Begin of code block
else if (!HasPrevLineContent(sc) && (sc.chPrev == '\t' || precharCount >= 4))
sc.SetState(SCE_MARKDOWN_CODEBK);
*/
// HRule - Total of three or more hyphens, asterisks, or underscores
// on a line by themselves
else if ((sc.ch == '-' || sc.ch == '*' || sc.ch == '_') && IsValidHrule(endPos, sc))
;
// Unordered list
else if ((sc.ch == '-' || sc.ch == '*' || sc.ch == '+') && IsASpaceOrTab(sc.chNext)) {
sc.SetState(SCE_MARKDOWN_ULIST_ITEM);
sc.ForwardSetState(SCE_MARKDOWN_DEFAULT);
}
// Ordered list
else if (IsADigit(sc.ch)) {
int digitCount = 0;
while (IsADigit(sc.GetRelative(++digitCount)))
;
if (sc.GetRelative(digitCount) == '.' &&
IsASpaceOrTab(sc.GetRelative(digitCount + 1))) {
sc.SetState(SCE_MARKDOWN_OLIST_ITEM);
sc.Forward(digitCount + 1);
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
}
// Alternate Ordered list
else if (sc.ch == '#' && sc.chNext == '.' && IsASpaceOrTab(sc.GetRelative(2))) {
sc.SetState(SCE_MARKDOWN_OLIST_ITEM);
sc.Forward(2);
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
else if (sc.ch != ' ' || precharCount > 2)
sc.SetState(SCE_MARKDOWN_DEFAULT);
else
++precharCount;
}
// Any link
if (sc.state == SCE_MARKDOWN_LINK) {
if (sc.Match("](") && sc.GetRelative(-1) != '\\') {
sc.Forward(2);
isLinkNameDetecting = true;
}
else if (sc.Match("]:") && sc.GetRelative(-1) != '\\') {
sc.Forward(2);
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
else if (!isLinkNameDetecting && sc.ch == ']' && sc.GetRelative(-1) != '\\') {
sc.Forward();
sc.SetState(SCE_MARKDOWN_DEFAULT);
}
else if (isLinkNameDetecting && sc.ch == ')' && sc.GetRelative(-1) != '\\') {
sc.Forward();
sc.SetState(SCE_MARKDOWN_DEFAULT);
isLinkNameDetecting = false;
}
}
// New state anywhere in doc
if (sc.state == SCE_MARKDOWN_DEFAULT) {
if (sc.atLineStart && sc.ch == '#') {
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
freezeCursor = true;
}
// Links and Images
if (sc.Match("![")) {
sc.SetState(SCE_MARKDOWN_LINK);
sc.Forward(1);
}
else if (sc.ch == '[' && sc.GetRelative(-1) != '\\') {
sc.SetState(SCE_MARKDOWN_LINK);
}
// Code - also a special case for alternate inside spacing
else if (sc.Match("``") && sc.GetRelative(3) != ' ' && AtTermStart(sc)) {
sc.SetState(SCE_MARKDOWN_CODE2);
sc.Forward();
}
else if (sc.ch == '`' && sc.chNext != ' ' && AtTermStart(sc)) {
sc.SetState(SCE_MARKDOWN_CODE);
}
// Strong
else if (sc.Match("**") && sc.GetRelative(2) != ' ' && AtTermStart(sc)) {
sc.SetState(SCE_MARKDOWN_STRONG1);
sc.Forward();
}
else if (sc.Match("__") && sc.GetRelative(2) != ' ' && AtTermStart(sc)) {
sc.SetState(SCE_MARKDOWN_STRONG2);
sc.Forward();
}
// Emphasis
else if (sc.ch == '*' && sc.chNext != ' ' && AtTermStart(sc)) {
sc.SetState(SCE_MARKDOWN_EM1);
}
else if (sc.ch == '_' && sc.chNext != ' ' && AtTermStart(sc)) {
sc.SetState(SCE_MARKDOWN_EM2);
}
// Strikeout
else if (sc.Match("~~") && sc.GetRelative(2) != ' ' && AtTermStart(sc)) {
sc.SetState(SCE_MARKDOWN_STRIKEOUT);
sc.Forward();
}
// Beginning of line
else if (IsNewline(sc.ch)) {
sc.SetState(SCE_MARKDOWN_LINE_BEGIN);
}
}
// Advance if not holding back the cursor for this iteration.
if (!freezeCursor)
sc.Forward();
freezeCursor = false;
}
sc.Complete();
}
LexerModule lmMarkdown(SCLEX_MARKDOWN, ColorizeMarkdownDoc, "markdown");

View File

@ -30,8 +30,8 @@
#include "SubStyles.h"
#include "DefaultLexer.h"
using namespace Lexilla;
using namespace Scintilla;
using namespace Lexilla;
namespace {
// Use an unnamed namespace to protect the functions and classes from name conflicts

View File

@ -0,0 +1,503 @@
// Scintilla source code edit control
/**
* @file LexJSON.cxx
* @date February 19, 2016
* @brief Lexer for JSON and JSON-LD formats
* @author nkmathew
*
* The License.txt file describes the conditions under which this software may
* be distributed.
*
*/
#include <cstdlib>
#include <cassert>
#include <cctype>
#include <cstdio>
#include <string>
#include <vector>
#include <map>
#include "ILexer.h"
#include "Scintilla.h"
#include "SciLexer.h"
#include "WordList.h"
#include "LexAccessor.h"
#include "StyleContext.h"
#include "CharacterSet.h"
#include "LexerModule.h"
#include "OptionSet.h"
#include "DefaultLexer.h"
using namespace Scintilla;
using namespace Lexilla;
static const char *const JSONWordListDesc[] = {
"JSON Keywords",
"JSON-LD Keywords",
0
};
/**
* Used to detect compact IRI/URLs in JSON-LD without first looking ahead for the
* colon separating the prefix and suffix
*
* https://www.w3.org/TR/json-ld/#dfn-compact-iri
*/
struct CompactIRI {
int colonCount;
bool foundInvalidChar;
CharacterSet setCompactIRI;
CompactIRI() {
colonCount = 0;
foundInvalidChar = false;
setCompactIRI = CharacterSet(CharacterSet::setAlpha, "$_-");
}
void resetState() {
colonCount = 0;
foundInvalidChar = false;
}
void checkChar(int ch) {
if (ch == ':') {
colonCount++;
} else {
foundInvalidChar |= !setCompactIRI.Contains(ch);
}
}
bool shouldHighlight() const {
return !foundInvalidChar && colonCount == 1;
}
};
/**
* Keeps track of escaped characters in strings as per:
*
* https://tools.ietf.org/html/rfc7159#section-7
*/
struct EscapeSequence {
int digitsLeft;
CharacterSet setHexDigits;
CharacterSet setEscapeChars;
EscapeSequence() {
digitsLeft = 0;
setHexDigits = CharacterSet(CharacterSet::setDigits, "ABCDEFabcdef");
setEscapeChars = CharacterSet(CharacterSet::setNone, "\\\"tnbfru/");
}
// Returns true if the following character is a valid escaped character
bool newSequence(int nextChar) {
digitsLeft = 0;
if (nextChar == 'u') {
digitsLeft = 5;
} else if (!setEscapeChars.Contains(nextChar)) {
return false;
}
return true;
}
bool atEscapeEnd() const {
return digitsLeft <= 0;
}
bool isInvalidChar(int currChar) const {
return !setHexDigits.Contains(currChar);
}
};
struct OptionsJSON {
bool foldCompact;
bool fold;
bool allowComments;
bool escapeSequence;
OptionsJSON() {
foldCompact = false;
fold = false;
allowComments = false;
escapeSequence = false;
}
};
struct OptionSetJSON : public OptionSet<OptionsJSON> {
OptionSetJSON() {
DefineProperty("lexer.json.escape.sequence", &OptionsJSON::escapeSequence,
"Set to 1 to enable highlighting of escape sequences in strings");
DefineProperty("lexer.json.allow.comments", &OptionsJSON::allowComments,
"Set to 1 to enable highlighting of line/block comments in JSON");
DefineProperty("fold.compact", &OptionsJSON::foldCompact);
DefineProperty("fold", &OptionsJSON::fold);
DefineWordListSets(JSONWordListDesc);
}
};
class LexerJSON : public DefaultLexer {
OptionsJSON options;
OptionSetJSON optSetJSON;
EscapeSequence escapeSeq;
WordList keywordsJSON;
WordList keywordsJSONLD;
CharacterSet setOperators;
CharacterSet setURL;
CharacterSet setKeywordJSONLD;
CharacterSet setKeywordJSON;
CompactIRI compactIRI;
static bool IsNextNonWhitespace(LexAccessor &styler, Sci_Position start, char ch) {
Sci_Position i = 0;
while (i < 50) {
i++;
char curr = styler.SafeGetCharAt(start+i, '\0');
char next = styler.SafeGetCharAt(start+i+1, '\0');
bool atEOL = (curr == '\r' && next != '\n') || (curr == '\n');
if (curr == ch) {
return true;
} else if (!isspacechar(curr) || atEOL) {
return false;
}
}
return false;
}
/**
* Looks for the colon following the end quote
*
* Assumes property names of lengths no longer than a 100 characters.
* The colon is also expected to be less than 50 spaces after the end
* quote for the string to be considered a property name
*/
static bool AtPropertyName(LexAccessor &styler, Sci_Position start) {
Sci_Position i = 0;
bool escaped = false;
while (i < 100) {
i++;
char curr = styler.SafeGetCharAt(start+i, '\0');
if (escaped) {
escaped = false;
continue;
}
escaped = curr == '\\';
if (curr == '"') {
return IsNextNonWhitespace(styler, start+i, ':');
} else if (!curr) {
return false;
}
}
return false;
}
static bool IsNextWordInList(WordList &keywordList, CharacterSet wordSet,
StyleContext &context, LexAccessor &styler) {
char word[51];
Sci_Position currPos = (Sci_Position) context.currentPos;
int i = 0;
while (i < 50) {
char ch = styler.SafeGetCharAt(currPos + i);
if (!wordSet.Contains(ch)) {
break;
}
word[i] = ch;
i++;
}
word[i] = '\0';
return keywordList.InList(word);
}
public:
LexerJSON() :
DefaultLexer("json", SCLEX_JSON),
setOperators(CharacterSet::setNone, "[{}]:,"),
setURL(CharacterSet::setAlphaNum, "-._~:/?#[]@!$&'()*+,),="),
setKeywordJSONLD(CharacterSet::setAlpha, ":@"),
setKeywordJSON(CharacterSet::setAlpha, "$_") {
}
virtual ~LexerJSON() {}
int SCI_METHOD Version() const override {
return lvRelease5;
}
void SCI_METHOD Release() override {
delete this;
}
const char *SCI_METHOD PropertyNames() override {
return optSetJSON.PropertyNames();
}
int SCI_METHOD PropertyType(const char *name) override {
return optSetJSON.PropertyType(name);
}
const char *SCI_METHOD DescribeProperty(const char *name) override {
return optSetJSON.DescribeProperty(name);
}
Sci_Position SCI_METHOD PropertySet(const char *key, const char *val) override {
if (optSetJSON.PropertySet(&options, key, val)) {
return 0;
}
return -1;
}
const char * SCI_METHOD PropertyGet(const char *key) override {
return optSetJSON.PropertyGet(key);
}
Sci_Position SCI_METHOD WordListSet(int n, const char *wl) override {
WordList *wordListN = 0;
switch (n) {
case 0:
wordListN = &keywordsJSON;
break;
case 1:
wordListN = &keywordsJSONLD;
break;
}
Sci_Position firstModification = -1;
if (wordListN) {
WordList wlNew;
wlNew.Set(wl);
if (*wordListN != wlNew) {
wordListN->Set(wl);
firstModification = 0;
}
}
return firstModification;
}
void *SCI_METHOD PrivateCall(int, void *) override {
return 0;
}
static ILexer5 *LexerFactoryJSON() {
return new LexerJSON;
}
const char *SCI_METHOD DescribeWordListSets() override {
return optSetJSON.DescribeWordListSets();
}
void SCI_METHOD Lex(Sci_PositionU startPos,
Sci_Position length,
int initStyle,
IDocument *pAccess) override;
void SCI_METHOD Fold(Sci_PositionU startPos,
Sci_Position length,
int initStyle,
IDocument *pAccess) override;
};
void SCI_METHOD LexerJSON::Lex(Sci_PositionU startPos,
Sci_Position length,
int initStyle,
IDocument *pAccess) {
LexAccessor styler(pAccess);
StyleContext context(startPos, length, initStyle, styler);
int stringStyleBefore = SCE_JSON_STRING;
while (context.More()) {
switch (context.state) {
case SCE_JSON_BLOCKCOMMENT:
if (context.Match("*/")) {
context.Forward();
context.ForwardSetState(SCE_JSON_DEFAULT);
}
break;
case SCE_JSON_LINECOMMENT:
if (context.atLineEnd) {
context.SetState(SCE_JSON_DEFAULT);
}
break;
case SCE_JSON_STRINGEOL:
if (context.atLineStart) {
context.SetState(SCE_JSON_DEFAULT);
}
break;
case SCE_JSON_ESCAPESEQUENCE:
escapeSeq.digitsLeft--;
if (!escapeSeq.atEscapeEnd()) {
if (escapeSeq.isInvalidChar(context.ch)) {
context.SetState(SCE_JSON_ERROR);
}
break;
}
if (context.ch == '"') {
context.SetState(stringStyleBefore);
context.ForwardSetState(SCE_C_DEFAULT);
} else if (context.ch == '\\') {
if (!escapeSeq.newSequence(context.chNext)) {
context.SetState(SCE_JSON_ERROR);
}
context.Forward();
} else {
context.SetState(stringStyleBefore);
if (context.atLineEnd) {
context.ChangeState(SCE_JSON_STRINGEOL);
}
}
break;
case SCE_JSON_PROPERTYNAME:
case SCE_JSON_STRING:
if (context.ch == '"') {
if (compactIRI.shouldHighlight()) {
context.ChangeState(SCE_JSON_COMPACTIRI);
context.ForwardSetState(SCE_JSON_DEFAULT);
compactIRI.resetState();
} else {
context.ForwardSetState(SCE_JSON_DEFAULT);
}
} else if (context.atLineEnd) {
context.ChangeState(SCE_JSON_STRINGEOL);
} else if (context.ch == '\\') {
stringStyleBefore = context.state;
if (options.escapeSequence) {
context.SetState(SCE_JSON_ESCAPESEQUENCE);
if (!escapeSeq.newSequence(context.chNext)) {
context.SetState(SCE_JSON_ERROR);
}
}
context.Forward();
} else if (context.Match("https://") ||
context.Match("http://") ||
context.Match("ssh://") ||
context.Match("git://") ||
context.Match("svn://") ||
context.Match("ftp://") ||
context.Match("mailto:")) {
// Handle most common URI schemes only
stringStyleBefore = context.state;
context.SetState(SCE_JSON_URI);
} else if (context.ch == '@') {
// https://www.w3.org/TR/json-ld/#dfn-keyword
if (IsNextWordInList(keywordsJSONLD, setKeywordJSONLD, context, styler)) {
stringStyleBefore = context.state;
context.SetState(SCE_JSON_LDKEYWORD);
}
} else {
compactIRI.checkChar(context.ch);
}
break;
case SCE_JSON_LDKEYWORD:
case SCE_JSON_URI:
if ((!setKeywordJSONLD.Contains(context.ch) &&
(context.state == SCE_JSON_LDKEYWORD)) ||
(!setURL.Contains(context.ch))) {
context.SetState(stringStyleBefore);
}
if (context.ch == '"') {
context.ForwardSetState(SCE_JSON_DEFAULT);
} else if (context.atLineEnd) {
context.ChangeState(SCE_JSON_STRINGEOL);
}
break;
case SCE_JSON_OPERATOR:
case SCE_JSON_NUMBER:
context.SetState(SCE_JSON_DEFAULT);
break;
case SCE_JSON_ERROR:
if (context.atLineEnd) {
context.SetState(SCE_JSON_DEFAULT);
}
break;
case SCE_JSON_KEYWORD:
if (!setKeywordJSON.Contains(context.ch)) {
context.SetState(SCE_JSON_DEFAULT);
}
break;
}
if (context.state == SCE_JSON_DEFAULT) {
if (context.ch == '"') {
compactIRI.resetState();
context.SetState(SCE_JSON_STRING);
Sci_Position currPos = static_cast<Sci_Position>(context.currentPos);
if (AtPropertyName(styler, currPos)) {
context.SetState(SCE_JSON_PROPERTYNAME);
}
} else if (setOperators.Contains(context.ch)) {
context.SetState(SCE_JSON_OPERATOR);
} else if (options.allowComments && context.Match("/*")) {
context.SetState(SCE_JSON_BLOCKCOMMENT);
context.Forward();
} else if (options.allowComments && context.Match("//")) {
context.SetState(SCE_JSON_LINECOMMENT);
} else if (setKeywordJSON.Contains(context.ch)) {
if (IsNextWordInList(keywordsJSON, setKeywordJSON, context, styler)) {
context.SetState(SCE_JSON_KEYWORD);
}
}
bool numberStart =
IsADigit(context.ch) && (context.chPrev == '+'||
context.chPrev == '-' ||
context.atLineStart ||
IsASpace(context.chPrev) ||
setOperators.Contains(context.chPrev));
bool exponentPart =
tolower(context.ch) == 'e' &&
IsADigit(context.chPrev) &&
(IsADigit(context.chNext) ||
context.chNext == '+' ||
context.chNext == '-');
bool signPart =
(context.ch == '-' || context.ch == '+') &&
((tolower(context.chPrev) == 'e' && IsADigit(context.chNext)) ||
((IsASpace(context.chPrev) || setOperators.Contains(context.chPrev))
&& IsADigit(context.chNext)));
bool adjacentDigit =
IsADigit(context.ch) && IsADigit(context.chPrev);
bool afterExponent = IsADigit(context.ch) && tolower(context.chPrev) == 'e';
bool dotPart = context.ch == '.' &&
IsADigit(context.chPrev) &&
IsADigit(context.chNext);
bool afterDot = IsADigit(context.ch) && context.chPrev == '.';
if (numberStart ||
exponentPart ||
signPart ||
adjacentDigit ||
dotPart ||
afterExponent ||
afterDot) {
context.SetState(SCE_JSON_NUMBER);
} else if (context.state == SCE_JSON_DEFAULT && !IsASpace(context.ch)) {
context.SetState(SCE_JSON_ERROR);
}
}
context.Forward();
}
context.Complete();
}
void SCI_METHOD LexerJSON::Fold(Sci_PositionU startPos,
Sci_Position length,
int,
IDocument *pAccess) {
if (!options.fold) {
return;
}
LexAccessor styler(pAccess);
Sci_PositionU currLine = styler.GetLine(startPos);
Sci_PositionU endPos = startPos + length;
int currLevel = SC_FOLDLEVELBASE;
if (currLine > 0)
currLevel = styler.LevelAt(currLine - 1) >> 16;
int nextLevel = currLevel;
int visibleChars = 0;
for (Sci_PositionU i = startPos; i < endPos; i++) {
char curr = styler.SafeGetCharAt(i);
char next = styler.SafeGetCharAt(i+1);
bool atEOL = (curr == '\r' && next != '\n') || (curr == '\n');
if (styler.StyleAt(i) == SCE_JSON_OPERATOR) {
if (curr == '{' || curr == '[') {
nextLevel++;
} else if (curr == '}' || curr == ']') {
nextLevel--;
}
}
if (atEOL || i == (endPos-1)) {
int level = currLevel | nextLevel << 16;
if (!visibleChars && options.foldCompact) {
level |= SC_FOLDLEVELWHITEFLAG;
} else if (nextLevel > currLevel) {
level |= SC_FOLDLEVELHEADERFLAG;
}
if (level != styler.LevelAt(currLine)) {
styler.SetLevel(currLine, level);
}
currLine++;
currLevel = nextLevel;
visibleChars = 0;
}
if (!isspacechar(curr)) {
visibleChars++;
}
}
}
LexerModule lmJSON(SCLEX_JSON,
LexerJSON::LexerFactoryJSON,
"json",
JSONWordListDesc);

View File

@ -31,6 +31,7 @@
#include "DefaultLexer.h"
using namespace Scintilla;
using namespace Lexilla;
namespace {
// Use an unnamed namespace to protect the functions and classes from name conflicts

View File

@ -333,18 +333,6 @@ LexMake.o: \
../lexlib/StyleContext.h \
../lexlib/CharacterSet.h \
../lexlib/LexerModule.h
LexMarkdown.o: \
../lexers/LexMarkdown.cxx \
../../scintilla/include/ILexer.h \
../../scintilla/include/Sci_Position.h \
../../scintilla/include/Scintilla.h \
../include/SciLexer.h \
../lexlib/WordList.h \
../lexlib/LexAccessor.h \
../lexlib/Accessor.h \
../lexlib/StyleContext.h \
../lexlib/CharacterSet.h \
../lexlib/LexerModule.h
LexMatlab.o: \
../lexers/LexMatlab.cxx \
../../scintilla/include/ILexer.h \
@ -662,6 +650,18 @@ LexKotlin.o: \
../include/SciLexer.h \
../lexers_x/StringUtils.h \
../lexers_x/LexerUtils.h
LexMarkdown.o: \
../lexers_x/LexMarkdown.cxx \
../../scintilla/include/ILexer.h \
../../scintilla/include/Sci_Position.h \
../../scintilla/include/Scintilla.h \
../include/SciLexer.h \
../lexlib/WordList.h \
../lexlib/LexAccessor.h \
../lexlib/Accessor.h \
../lexlib/StyleContext.h \
../lexlib/CharacterSet.h \
../lexlib/LexerModule.h
LexPython.o: \
../lexers_x/LexPython.cxx \
../../scintilla/include/ILexer.h \

View File

@ -92,7 +92,6 @@ LEX_OBJS=\
$(DIR_O)\LexLaTeX.obj \
$(DIR_O)\LexLua.obj \
$(DIR_O)\LexMake.obj \
$(DIR_O)\LexMarkdown.obj \
$(DIR_O)\LexMatlab.obj \
$(DIR_O)\LexNim.obj \
$(DIR_O)\LexNsis.obj \
@ -116,6 +115,7 @@ LEX_OBJS=\
$(DIR_O)\LexerUtils.obj \
$(DIR_O)\LexJSON.obj \
$(DIR_O)\LexKotlin.obj \
$(DIR_O)\LexMarkdown.obj \
$(DIR_O)\LexPython.obj \
$(DIR_O)\LexTOML.obj \

View File

@ -333,18 +333,6 @@ $(DIR_O)/LexMake.obj: \
../lexlib/StyleContext.h \
../lexlib/CharacterSet.h \
../lexlib/LexerModule.h
$(DIR_O)/LexMarkdown.obj: \
../lexers/LexMarkdown.cxx \
../../scintilla/include/ILexer.h \
../../scintilla/include/Sci_Position.h \
../../scintilla/include/Scintilla.h \
../include/SciLexer.h \
../lexlib/WordList.h \
../lexlib/LexAccessor.h \
../lexlib/Accessor.h \
../lexlib/StyleContext.h \
../lexlib/CharacterSet.h \
../lexlib/LexerModule.h
$(DIR_O)/LexMatlab.obj: \
../lexers/LexMatlab.cxx \
../../scintilla/include/ILexer.h \
@ -662,6 +650,18 @@ $(DIR_O)/LexKotlin.obj: \
../include/SciLexer.h \
../lexers_x/StringUtils.h \
../lexers_x/LexerUtils.h
$(DIR_O)/LexMarkdown.obj: \
../lexers_x/LexMarkdown.cxx \
../../scintilla/include/ILexer.h \
../../scintilla/include/Sci_Position.h \
../../scintilla/include/Scintilla.h \
../include/SciLexer.h \
../lexlib/WordList.h \
../lexlib/LexAccessor.h \
../lexlib/Accessor.h \
../lexlib/StyleContext.h \
../lexlib/CharacterSet.h \
../lexlib/LexerModule.h
$(DIR_O)/LexPython.obj: \
../lexers_x/LexPython.cxx \
../../scintilla/include/ILexer.h \