CWL parameter reference parsing

antlr4/CwlEcmaStringLexer.g4

@@ -0,0 +1,41 @@
+lexer grammar CwlEcmaStringLexer;
+
+ANYCHAR: .;
+DOLLARPAREN: '$(' -> pushMode(ParenExpr);
+LPAREN: '(';
+RPAREN: ')';
+DOLLARBRACE: '${' -> pushMode(BraceExpr);
+LBRACE: '{';
+RBRACE: '}';
+DOLLARPARENESC: '\\$(';
+DOLLARBRACEESC: '\\${';
+BACKSLASH: '\\';
+BACKSLASHESC: '\\\\';
+
+mode ParenExpr;
+
+EscPart: BACKSLASH ANYCHAR;
+SubExprStart: LPAREN -> pushMode(SubExpr);
+ExprEnd: RPAREN -> popMode;
+ExprPart: ~[)];
+
+mode SubExpr;
+
+SubEscPart: BACKSLASH ANYCHAR -> type(SubExprPart);
+SubSubExprStart: LPAREN -> pushMode(SubExpr);
+SubExprEnd: RPAREN -> popMode;
+SubExprPart: ~[)];
+
+mode BraceExpr;
+
+BraceEscPart: BACKSLASH ANYCHAR -> type(EscPart);
+BraceSubExprStart: LBRACE -> pushMode(BraceSubExpr), type(SubExprStart);
+BraceExprEnd: RBRACE -> popMode, type(ExprEnd);
+BraceExprPart: ~[}] -> type(ExprPart);
+
+mode BraceSubExpr;
+
+BraceSubEscPart: BACKSLASH ANYCHAR -> type(SubExprPart);
+BraceSubSubExprStart: LBRACE -> pushMode(BraceSubExpr), type(SubSubExprStart);
+BraceSubExprEnd: RBRACE -> popMode, type(SubExprEnd);
+BraceSubExprPart: ~[}] -> type(SubExprPart);

antlr4/CwlEcmaStringParser.g4

@@ -0,0 +1,45 @@
+parser grammar CwlEcmaStringParser;
+
+options {
+  tokenVocab=CwlEcmaStringLexer;
+}
+
+sub_sub_expr
+  : SubSubExprStart sub_expr_part* SubExprEnd
+  ;
+
+sub_expr_part
+  : SubExprPart
+  | sub_sub_expr
+  ;
+
+sub_expr
+  : SubExprStart sub_expr_part* SubExprEnd
+  ;
+
+expr_part
+  : ExprPart
+  | EscPart
+  | sub_expr
+  ;
+
+paren_expr
+  : DOLLARPAREN expr_part+ ExprEnd
+  ;
+
+brace_expr
+  : DOLLARBRACE expr_part+ ExprEnd
+  ;
+
+interpolated_string_part
+  : BACKSLASHESC
+  | DOLLARPARENESC
+  | DOLLARBRACEESC
+  | paren_expr
+  | brace_expr
+  | ANYCHAR
+  ;
+
+interpolated_string
+  : interpolated_string_part+
+  ;

antlr4/CwlParameterReferenceLexer.g4

@@ -0,0 +1,67 @@
+lexer grammar CwlParameterReferenceLexer;
+
+DOT: '.';
+LBRACKET: '[';
+RBRACKET: ']';
+DOLLARPAREN: '$(' -> pushMode(ParenExpr);
+RPAREN: ')';
+DOLLARPARENESC: '\\$(';
+BACKSLASH: '\\';
+BACKSLASHESC: '\\\\';
+ANYCHAR: .;
+LBRACKETSINGLEQ: '[\'';
+LBRACKETDOUBLEQ: '["';
+SINGLEQRBRACKET: '\']';
+DOUBLEQRBRACKET: '"]';
+
+mode ParenExpr;
+
+ExprDot: DOT;
+ExprSymbol: CompleteSymbol;
+ExprSingleQ: LBRACKETSINGLEQ -> pushMode(SingleQString);
+ExprDoubleQ: LBRACKETDOUBLEQ -> pushMode(DoubleQString);
+ExprIntIndex: LBRACKET -> pushMode(IntIndex);
+EndParenExpr: RPAREN -> popMode;
+
+mode SingleQString;
+
+StringIndexEscPart: BACKSLASH ANYCHAR;
+EndSingleQ: SINGLEQRBRACKET -> popMode, type(ExprSingleQ);
+StringIndexPart: ~[\\']+;
+LiteralBackslash: BACKSLASH -> type(StringIndexPart);
+
+mode DoubleQString;
+
+DoubleQEscapedChar: BACKSLASH ANYCHAR -> type(StringIndexEscPart);
+EndDoubleQ: DOUBLEQRBRACKET ->  popMode, type(ExprDoubleQ);
+DoubleQStringIndexPart: ~[\\"]+ -> type(StringIndexPart);
+DoubleQLiteralBackslash: BACKSLASH -> type(StringIndexPart);
+
+mode IntIndex;
+
+EndIndex: RBRACKET -> popMode, type(ExprIntIndex);
+IntIndexPart: DecimalNumber;
+
+fragment CompleteSymbol
+	: SymbolStart SymbolFollow*
+	;
+
+fragment SymbolStart
+	: [a-zA-Z]
+	;
+
+fragment SymbolFollow
+	: [a-zA-Z0-9_]+
+	;
+
+fragment DecimalNumber
+  : DecimalDigit+
+  ;
+
+fragment DecimalDigit
+  : [0-9]
+  ;
+
+fragment HexDigit
+	: [0-9a-fA-F]
+	;

antlr4/CwlParameterReferenceParser.g4

@@ -0,0 +1,44 @@
+parser grammar CwlParameterReferenceParser;
+
+options {
+  tokenVocab=CwlParameterReferenceLexer;
+}
+
+expr_dot_symbol
+  : ExprDot ExprSymbol
+  ;
+
+int_index
+  : ExprIntIndex IntIndexPart ExprIntIndex
+  ;
+
+string_index_part
+  : StringIndexPart
+  | StringIndexEscPart
+  ;
+
+string_index
+  : ExprSingleQ string_index_part+ ExprSingleQ
+  | ExprDoubleQ string_index_part+ ExprDoubleQ
+  ;
+
+expr_segment
+  : expr_dot_symbol
+  | int_index
+  | string_index
+  ;
+
+paren_expr
+  : DOLLARPAREN ExprSymbol expr_segment* EndParenExpr
+  ;
+
+interpolated_string_part
+  : BACKSLASHESC
+  | DOLLARPARENESC
+  | paren_expr
+  | ANYCHAR
+  ;
+
+interpolated_string
+  : interpolated_string_part+
+  ;

cwl_utils/parser/v1_2EcmaStringLexer.py

@@ -0,0 +1,131 @@
+# Generated from antlr4/CwlEcmaStringLexer.g4 by ANTLR 4.7.2
+from antlr4 import *
+from io import StringIO
+from typing.io import TextIO
+import sys
+
+
+def serializedATN():
+    with StringIO() as buf:
+        buf.write("\3\u608b\ua72a\u8133\ub9ed\u417c\u3be7\u7786\u5964\2\24")
+        buf.write("\u00a0\b\1\b\1\b\1\b\1\b\1\4\2\t\2\4\3\t\3\4\4\t\4\4\5")
+        buf.write("\t\5\4\6\t\6\4\7\t\7\4\b\t\b\4\t\t\t\4\n\t\n\4\13\t\13")
+        buf.write("\4\f\t\f\4\r\t\r\4\16\t\16\4\17\t\17\4\20\t\20\4\21\t")
+        buf.write("\21\4\22\t\22\4\23\t\23\4\24\t\24\4\25\t\25\4\26\t\26")
+        buf.write("\4\27\t\27\4\30\t\30\4\31\t\31\4\32\t\32\4\33\t\33\4\34")
+        buf.write("\t\34\3\2\3\2\3\3\3\3\3\3\3\3\3\3\3\4\3\4\3\5\3\5\3\6")
+        buf.write("\3\6\3\6\3\6\3\6\3\7\3\7\3\b\3\b\3\t\3\t\3\t\3\t\3\n\3")
+        buf.write("\n\3\n\3\n\3\13\3\13\3\f\3\f\3\f\3\r\3\r\3\r\3\16\3\16")
+        buf.write("\3\16\3\16\3\17\3\17\3\17\3\17\3\20\3\20\3\21\3\21\3\21")
+        buf.write("\3\21\3\21\3\22\3\22\3\22\3\22\3\23\3\23\3\23\3\23\3\24")
+        buf.write("\3\24\3\25\3\25\3\25\3\25\3\25\3\26\3\26\3\26\3\26\3\26")
+        buf.write("\3\27\3\27\3\27\3\27\3\27\3\30\3\30\3\30\3\30\3\31\3\31")
+        buf.write("\3\31\3\31\3\31\3\32\3\32\3\32\3\32\3\32\3\33\3\33\3\33")
+        buf.write("\3\33\3\33\3\34\3\34\3\34\3\34\2\2\35\7\3\t\4\13\5\r\6")
+        buf.write("\17\7\21\b\23\t\25\n\27\13\31\f\33\r\35\16\37\17!\20#")
+        buf.write("\21%\2\'\22)\23+\24-\2/\2\61\2\63\2\65\2\67\29\2;\2\7")
+        buf.write("\2\3\4\5\6\4\3\2++\3\2\177\177\2\u009b\2\7\3\2\2\2\2\t")
+        buf.write("\3\2\2\2\2\13\3\2\2\2\2\r\3\2\2\2\2\17\3\2\2\2\2\21\3")
+        buf.write("\2\2\2\2\23\3\2\2\2\2\25\3\2\2\2\2\27\3\2\2\2\2\31\3\2")
+        buf.write("\2\2\2\33\3\2\2\2\3\35\3\2\2\2\3\37\3\2\2\2\3!\3\2\2\2")
+        buf.write("\3#\3\2\2\2\4%\3\2\2\2\4\'\3\2\2\2\4)\3\2\2\2\4+\3\2\2")
+        buf.write("\2\5-\3\2\2\2\5/\3\2\2\2\5\61\3\2\2\2\5\63\3\2\2\2\6\65")
+        buf.write("\3\2\2\2\6\67\3\2\2\2\69\3\2\2\2\6;\3\2\2\2\7=\3\2\2\2")
+        buf.write("\t?\3\2\2\2\13D\3\2\2\2\rF\3\2\2\2\17H\3\2\2\2\21M\3\2")
+        buf.write("\2\2\23O\3\2\2\2\25Q\3\2\2\2\27U\3\2\2\2\31Y\3\2\2\2\33")
+        buf.write("[\3\2\2\2\35^\3\2\2\2\37a\3\2\2\2!e\3\2\2\2#i\3\2\2\2")
+        buf.write("%k\3\2\2\2\'p\3\2\2\2)t\3\2\2\2+x\3\2\2\2-z\3\2\2\2/\177")
+        buf.write("\3\2\2\2\61\u0084\3\2\2\2\63\u0089\3\2\2\2\65\u008d\3")
+        buf.write("\2\2\2\67\u0092\3\2\2\29\u0097\3\2\2\2;\u009c\3\2\2\2")
+        buf.write("=>\13\2\2\2>\b\3\2\2\2?@\7&\2\2@A\7*\2\2AB\3\2\2\2BC\b")
+        buf.write("\3\2\2C\n\3\2\2\2DE\7*\2\2E\f\3\2\2\2FG\7+\2\2G\16\3\2")
+        buf.write("\2\2HI\7&\2\2IJ\7}\2\2JK\3\2\2\2KL\b\6\3\2L\20\3\2\2\2")
+        buf.write("MN\7}\2\2N\22\3\2\2\2OP\7\177\2\2P\24\3\2\2\2QR\7^\2\2")
+        buf.write("RS\7&\2\2ST\7*\2\2T\26\3\2\2\2UV\7^\2\2VW\7&\2\2WX\7}")
+        buf.write("\2\2X\30\3\2\2\2YZ\7^\2\2Z\32\3\2\2\2[\\\7^\2\2\\]\7^")
+        buf.write("\2\2]\34\3\2\2\2^_\5\31\13\2_`\5\7\2\2`\36\3\2\2\2ab\5")
+        buf.write("\13\4\2bc\3\2\2\2cd\b\16\4\2d \3\2\2\2ef\5\r\5\2fg\3\2")
+        buf.write("\2\2gh\b\17\5\2h\"\3\2\2\2ij\n\2\2\2j$\3\2\2\2kl\5\31")
+        buf.write("\13\2lm\5\7\2\2mn\3\2\2\2no\b\21\6\2o&\3\2\2\2pq\5\13")
+        buf.write("\4\2qr\3\2\2\2rs\b\22\4\2s(\3\2\2\2tu\5\r\5\2uv\3\2\2")
+        buf.write("\2vw\b\23\5\2w*\3\2\2\2xy\n\2\2\2y,\3\2\2\2z{\5\31\13")
+        buf.write("\2{|\5\7\2\2|}\3\2\2\2}~\b\25\7\2~.\3\2\2\2\177\u0080")
+        buf.write("\5\21\7\2\u0080\u0081\3\2\2\2\u0081\u0082\b\26\b\2\u0082")
+        buf.write("\u0083\b\26\t\2\u0083\60\3\2\2\2\u0084\u0085\5\23\b\2")
+        buf.write("\u0085\u0086\3\2\2\2\u0086\u0087\b\27\5\2\u0087\u0088")
+        buf.write("\b\27\n\2\u0088\62\3\2\2\2\u0089\u008a\n\3\2\2\u008a\u008b")
+        buf.write("\3\2\2\2\u008b\u008c\b\30\13\2\u008c\64\3\2\2\2\u008d")
+        buf.write("\u008e\5\31\13\2\u008e\u008f\5\7\2\2\u008f\u0090\3\2\2")
+        buf.write("\2\u0090\u0091\b\31\6\2\u0091\66\3\2\2\2\u0092\u0093\5")
+        buf.write("\21\7\2\u0093\u0094\3\2\2\2\u0094\u0095\b\32\b\2\u0095")
+        buf.write("\u0096\b\32\f\2\u00968\3\2\2\2\u0097\u0098\5\23\b\2\u0098")
+        buf.write("\u0099\3\2\2\2\u0099\u009a\b\33\5\2\u009a\u009b\b\33\r")
+        buf.write("\2\u009b:\3\2\2\2\u009c\u009d\n\3\2\2\u009d\u009e\3\2")
+        buf.write("\2\2\u009e\u009f\b\34\6\2\u009f<\3\2\2\2\7\2\3\4\5\6\16")
+        buf.write("\7\3\2\7\5\2\7\4\2\6\2\2\t\24\2\t\16\2\7\6\2\t\17\2\t")
+        buf.write("\20\2\t\21\2\t\22\2\t\23\2")
+        return buf.getvalue()
+
+
+class CwlEcmaStringLexer(Lexer):
+
+    atn = ATNDeserializer().deserialize(serializedATN())
+
+    decisionsToDFA = [ DFA(ds, i) for i, ds in enumerate(atn.decisionToState) ]
+
+    ParenExpr = 1
+    SubExpr = 2
+    BraceExpr = 3
+    BraceSubExpr = 4
+
+    ANYCHAR = 1
+    DOLLARPAREN = 2
+    LPAREN = 3
+    RPAREN = 4
+    DOLLARBRACE = 5
+    LBRACE = 6
+    RBRACE = 7
+    DOLLARPARENESC = 8
+    DOLLARBRACEESC = 9
+    BACKSLASH = 10
+    BACKSLASHESC = 11
+    EscPart = 12
+    SubExprStart = 13
+    ExprEnd = 14
+    ExprPart = 15
+    SubSubExprStart = 16
+    SubExprEnd = 17
+    SubExprPart = 18
+
+    channelNames = [ u"DEFAULT_TOKEN_CHANNEL", u"HIDDEN" ]
+
+    modeNames = [ "DEFAULT_MODE", "ParenExpr", "SubExpr", "BraceExpr", "BraceSubExpr" ]
+
+    literalNames = [ "<INVALID>",
+            "'$('", "'('", "')'", "'${'", "'{'", "'}'", "'\\$('", "'\\${'", 
+            "'\\'", "'\\\\'" ]
+
+    symbolicNames = [ "<INVALID>",
+            "ANYCHAR", "DOLLARPAREN", "LPAREN", "RPAREN", "DOLLARBRACE", 
+            "LBRACE", "RBRACE", "DOLLARPARENESC", "DOLLARBRACEESC", "BACKSLASH", 
+            "BACKSLASHESC", "EscPart", "SubExprStart", "ExprEnd", "ExprPart", 
+            "SubSubExprStart", "SubExprEnd", "SubExprPart" ]
+
+    ruleNames = [ "ANYCHAR", "DOLLARPAREN", "LPAREN", "RPAREN", "DOLLARBRACE", 
+                  "LBRACE", "RBRACE", "DOLLARPARENESC", "DOLLARBRACEESC", 
+                  "BACKSLASH", "BACKSLASHESC", "EscPart", "SubExprStart", 
+                  "ExprEnd", "ExprPart", "SubEscPart", "SubSubExprStart", 
+                  "SubExprEnd", "SubExprPart", "BraceEscPart", "BraceSubExprStart", 
+                  "BraceExprEnd", "BraceExprPart", "BraceSubEscPart", "BraceSubSubExprStart", 
+                  "BraceSubExprEnd", "BraceSubExprPart" ]
+
+    grammarFileName = "CwlEcmaStringLexer.g4"
+
+    def __init__(self, input=None, output:TextIO = sys.stdout):
+        super().__init__(input, output)
+        self.checkVersion("4.7.2")
+        self._interp = LexerATNSimulator(self, self.atn, self.decisionsToDFA, PredictionContextCache())
+        self._actions = None
+        self._predicates = None
+
+