diff --git a/modules/lang-painless/src/main/antlr/PainlessLexer.g4 b/modules/lang-painless/src/main/antlr/PainlessLexer.g4 index 9504a3d911a..18fdae751af 100644 --- a/modules/lang-painless/src/main/antlr/PainlessLexer.g4 +++ b/modules/lang-painless/src/main/antlr/PainlessLexer.g4 @@ -107,7 +107,7 @@ HEX: '0' [xX] [0-9a-fA-F]+ [lL]?; INTEGER: ( '0' | [1-9] [0-9]* ) [lLfFdD]?; DECIMAL: ( '0' | [1-9] [0-9]* ) (DOT [0-9]+)? ( [eE] [+\-]? [0-9]+ )? [fFdD]?; -STRING: ( '"' ( '\\"' | '\\\\' | ~[\\"] )*? '"' ) | ( '\'' ( '\\\'' | '\\\\' | ~[\\"] )*? '\'' ); +STRING: ( '"' ( '\\"' | '\\\\' | ~[\\"] )*? '"' ) | ( '\'' ( '\\\'' | '\\\\' | ~[\\'] )*? '\'' ); REGEX: '/' ( ~('/' | '\n') | '\\' ~'\n' )+ '/' [cilmsUux]* { SlashStrategy.slashIsRegex(this) }?; TRUE: 'true'; diff --git a/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/EnhancedPainlessLexer.java b/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/EnhancedPainlessLexer.java index 94a2c258974..244c2f38e62 100644 --- a/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/EnhancedPainlessLexer.java +++ b/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/EnhancedPainlessLexer.java @@ -29,12 +29,13 @@ import org.antlr.v4.runtime.misc.Pair; import org.elasticsearch.painless.Location; /** - * A lexer that is customized for painless. It will: + * A lexer that is customized for painless. It: * */ final class EnhancedPainlessLexer extends PainlessLexer { @@ -77,7 +78,15 @@ final class EnhancedPainlessLexer extends PainlessLexer { final String text = charStream.getText(Interval.of(startIndex, charStream.index())); Location location = new Location(sourceName, _tokenStartCharIndex); - throw location.createError(new IllegalArgumentException("unexpected character [" + getErrorDisplay(text) + "].", lnvae)); + String message = "unexpected character [" + getErrorDisplay(text) + "]."; + char firstChar = text.charAt(0); + if ((firstChar == '\'' || firstChar == '"') && text.length() - 2 > 0 && text.charAt(text.length() - 2) == '\\') { + /* Use a simple heuristic to guess if the unrecognized characters were trying to be a string but has a broken escape sequence. + * If it was add an extra message about valid string escape sequences. */ + message += " The only valid escape sequences in strings starting with [" + firstChar + "] are [\\\\] and [\\" + + firstChar + "]."; + } + throw location.createError(new IllegalArgumentException(message, lnvae)); } private static boolean insertSemicolon(Token previous, Token next) { diff --git a/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/PainlessLexer.java b/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/PainlessLexer.java index 529ae6f89ea..900180ec106 100644 --- a/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/PainlessLexer.java +++ b/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/PainlessLexer.java @@ -203,51 +203,51 @@ class PainlessLexer extends Lexer { "\348\35:\36<\37> @!B\"D#F$H%J&L\'N(P)R*T+V,X-Z.\\/^\60`\61b\62d\63f\64"+ "h\65j\66l\67n8p9r:t;v|?~@\u0080A\u0082B\u0084C\u0086D\u0088E\u008a"+ "F\u008cG\u008eH\u0090I\u0092J\u0094K\u0096L\u0098M\u009aN\u009cO\u009e"+ - "P\u00a0Q\u00a2R\u00a4S\u00a6T\u00a8U\u00aaV\4\2\3\24\5\2\13\f\17\17\""+ + "P\u00a0Q\u00a2R\u00a4S\u00a6T\u00a8U\u00aaV\4\2\3\25\5\2\13\f\17\17\""+ "\"\4\2\f\f\17\17\3\2\629\4\2NNnn\4\2ZZzz\5\2\62;CHch\3\2\63;\3\2\62;\b"+ - "\2FFHHNNffhhnn\4\2GGgg\4\2--//\6\2FFHHffhh\4\2$$^^\4\2\f\f\61\61\3\2\f"+ - "\f\t\2WWeekknouuwwzz\5\2C\\aac|\6\2\62;C\\aac|\u0277\2\4\3\2\2\2\2\6\3"+ - "\2\2\2\2\b\3\2\2\2\2\n\3\2\2\2\2\f\3\2\2\2\2\16\3\2\2\2\2\20\3\2\2\2\2"+ - "\22\3\2\2\2\2\24\3\2\2\2\2\26\3\2\2\2\2\30\3\2\2\2\2\32\3\2\2\2\2\34\3"+ - "\2\2\2\2\36\3\2\2\2\2 \3\2\2\2\2\"\3\2\2\2\2$\3\2\2\2\2&\3\2\2\2\2(\3"+ - "\2\2\2\2*\3\2\2\2\2,\3\2\2\2\2.\3\2\2\2\2\60\3\2\2\2\2\62\3\2\2\2\2\64"+ - "\3\2\2\2\2\66\3\2\2\2\28\3\2\2\2\2:\3\2\2\2\2<\3\2\2\2\2>\3\2\2\2\2@\3"+ - "\2\2\2\2B\3\2\2\2\2D\3\2\2\2\2F\3\2\2\2\2H\3\2\2\2\2J\3\2\2\2\2L\3\2\2"+ - "\2\2N\3\2\2\2\2P\3\2\2\2\2R\3\2\2\2\2T\3\2\2\2\2V\3\2\2\2\2X\3\2\2\2\2"+ - "Z\3\2\2\2\2\\\3\2\2\2\2^\3\2\2\2\2`\3\2\2\2\2b\3\2\2\2\2d\3\2\2\2\2f\3"+ - "\2\2\2\2h\3\2\2\2\2j\3\2\2\2\2l\3\2\2\2\2n\3\2\2\2\2p\3\2\2\2\2r\3\2\2"+ - "\2\2t\3\2\2\2\2v\3\2\2\2\2x\3\2\2\2\2z\3\2\2\2\2|\3\2\2\2\2~\3\2\2\2\2"+ - "\u0080\3\2\2\2\2\u0082\3\2\2\2\2\u0084\3\2\2\2\2\u0086\3\2\2\2\2\u0088"+ - "\3\2\2\2\2\u008a\3\2\2\2\2\u008c\3\2\2\2\2\u008e\3\2\2\2\2\u0090\3\2\2"+ - "\2\2\u0092\3\2\2\2\2\u0094\3\2\2\2\2\u0096\3\2\2\2\2\u0098\3\2\2\2\2\u009a"+ - "\3\2\2\2\2\u009c\3\2\2\2\2\u009e\3\2\2\2\2\u00a0\3\2\2\2\2\u00a2\3\2\2"+ - "\2\2\u00a4\3\2\2\2\2\u00a6\3\2\2\2\3\u00a8\3\2\2\2\3\u00aa\3\2\2\2\4\u00ad"+ - "\3\2\2\2\6\u00c8\3\2\2\2\b\u00cc\3\2\2\2\n\u00ce\3\2\2\2\f\u00d0\3\2\2"+ - "\2\16\u00d2\3\2\2\2\20\u00d4\3\2\2\2\22\u00d6\3\2\2\2\24\u00d8\3\2\2\2"+ - "\26\u00dc\3\2\2\2\30\u00e1\3\2\2\2\32\u00e3\3\2\2\2\34\u00e5\3\2\2\2\36"+ - "\u00e8\3\2\2\2 \u00eb\3\2\2\2\"\u00f0\3\2\2\2$\u00f6\3\2\2\2&\u00f9\3"+ - "\2\2\2(\u00fd\3\2\2\2*\u0106\3\2\2\2,\u010c\3\2\2\2.\u0113\3\2\2\2\60"+ - "\u0117\3\2\2\2\62\u011b\3\2\2\2\64\u0121\3\2\2\2\66\u0127\3\2\2\28\u012c"+ - "\3\2\2\2:\u0137\3\2\2\2<\u0139\3\2\2\2>\u013b\3\2\2\2@\u013d\3\2\2\2B"+ - "\u0140\3\2\2\2D\u0142\3\2\2\2F\u0144\3\2\2\2H\u0146\3\2\2\2J\u0149\3\2"+ - "\2\2L\u014c\3\2\2\2N\u0150\3\2\2\2P\u0152\3\2\2\2R\u0155\3\2\2\2T\u0157"+ - "\3\2\2\2V\u015a\3\2\2\2X\u015d\3\2\2\2Z\u0161\3\2\2\2\\\u0164\3\2\2\2"+ - "^\u0168\3\2\2\2`\u016a\3\2\2\2b\u016c\3\2\2\2d\u016e\3\2\2\2f\u0171\3"+ - "\2\2\2h\u0174\3\2\2\2j\u0176\3\2\2\2l\u0178\3\2\2\2n\u017b\3\2\2\2p\u017e"+ - "\3\2\2\2r\u0181\3\2\2\2t\u0184\3\2\2\2v\u0188\3\2\2\2x\u018b\3\2\2\2z"+ - "\u018e\3\2\2\2|\u0190\3\2\2\2~\u0193\3\2\2\2\u0080\u0196\3\2\2\2\u0082"+ - "\u0199\3\2\2\2\u0084\u019c\3\2\2\2\u0086\u019f\3\2\2\2\u0088\u01a2\3\2"+ - "\2\2\u008a\u01a5\3\2\2\2\u008c\u01a8\3\2\2\2\u008e\u01ac\3\2\2\2\u0090"+ - "\u01b0\3\2\2\2\u0092\u01b5\3\2\2\2\u0094\u01be\3\2\2\2\u0096\u01d0\3\2"+ - "\2\2\u0098\u01dd\3\2\2\2\u009a\u020d\3\2\2\2\u009c\u020f\3\2\2\2\u009e"+ - "\u0220\3\2\2\2\u00a0\u0225\3\2\2\2\u00a2\u022b\3\2\2\2\u00a4\u0230\3\2"+ - "\2\2\u00a6\u023b\3\2\2\2\u00a8\u024a\3\2\2\2\u00aa\u024e\3\2\2\2\u00ac"+ - "\u00ae\t\2\2\2\u00ad\u00ac\3\2\2\2\u00ae\u00af\3\2\2\2\u00af\u00ad\3\2"+ - "\2\2\u00af\u00b0\3\2\2\2\u00b0\u00b1\3\2\2\2\u00b1\u00b2\b\2\2\2\u00b2"+ - "\5\3\2\2\2\u00b3\u00b4\7\61\2\2\u00b4\u00b5\7\61\2\2\u00b5\u00b9\3\2\2"+ - "\2\u00b6\u00b8\13\2\2\2\u00b7\u00b6\3\2\2\2\u00b8\u00bb\3\2\2\2\u00b9"+ - "\u00ba\3\2\2\2\u00b9\u00b7\3\2\2\2\u00ba\u00bc\3\2\2\2\u00bb\u00b9\3\2"+ - "\2\2\u00bc\u00c9\t\3\2\2\u00bd\u00be\7\61\2\2\u00be\u00bf\7,\2\2\u00bf"+ + "\2FFHHNNffhhnn\4\2GGgg\4\2--//\6\2FFHHffhh\4\2$$^^\4\2))^^\4\2\f\f\61"+ + "\61\3\2\f\f\t\2WWeekknouuwwzz\5\2C\\aac|\6\2\62;C\\aac|\u0277\2\4\3\2"+ + "\2\2\2\6\3\2\2\2\2\b\3\2\2\2\2\n\3\2\2\2\2\f\3\2\2\2\2\16\3\2\2\2\2\20"+ + "\3\2\2\2\2\22\3\2\2\2\2\24\3\2\2\2\2\26\3\2\2\2\2\30\3\2\2\2\2\32\3\2"+ + "\2\2\2\34\3\2\2\2\2\36\3\2\2\2\2 \3\2\2\2\2\"\3\2\2\2\2$\3\2\2\2\2&\3"+ + "\2\2\2\2(\3\2\2\2\2*\3\2\2\2\2,\3\2\2\2\2.\3\2\2\2\2\60\3\2\2\2\2\62\3"+ + "\2\2\2\2\64\3\2\2\2\2\66\3\2\2\2\28\3\2\2\2\2:\3\2\2\2\2<\3\2\2\2\2>\3"+ + "\2\2\2\2@\3\2\2\2\2B\3\2\2\2\2D\3\2\2\2\2F\3\2\2\2\2H\3\2\2\2\2J\3\2\2"+ + "\2\2L\3\2\2\2\2N\3\2\2\2\2P\3\2\2\2\2R\3\2\2\2\2T\3\2\2\2\2V\3\2\2\2\2"+ + "X\3\2\2\2\2Z\3\2\2\2\2\\\3\2\2\2\2^\3\2\2\2\2`\3\2\2\2\2b\3\2\2\2\2d\3"+ + "\2\2\2\2f\3\2\2\2\2h\3\2\2\2\2j\3\2\2\2\2l\3\2\2\2\2n\3\2\2\2\2p\3\2\2"+ + "\2\2r\3\2\2\2\2t\3\2\2\2\2v\3\2\2\2\2x\3\2\2\2\2z\3\2\2\2\2|\3\2\2\2\2"+ + "~\3\2\2\2\2\u0080\3\2\2\2\2\u0082\3\2\2\2\2\u0084\3\2\2\2\2\u0086\3\2"+ + "\2\2\2\u0088\3\2\2\2\2\u008a\3\2\2\2\2\u008c\3\2\2\2\2\u008e\3\2\2\2\2"+ + "\u0090\3\2\2\2\2\u0092\3\2\2\2\2\u0094\3\2\2\2\2\u0096\3\2\2\2\2\u0098"+ + "\3\2\2\2\2\u009a\3\2\2\2\2\u009c\3\2\2\2\2\u009e\3\2\2\2\2\u00a0\3\2\2"+ + "\2\2\u00a2\3\2\2\2\2\u00a4\3\2\2\2\2\u00a6\3\2\2\2\3\u00a8\3\2\2\2\3\u00aa"+ + "\3\2\2\2\4\u00ad\3\2\2\2\6\u00c8\3\2\2\2\b\u00cc\3\2\2\2\n\u00ce\3\2\2"+ + "\2\f\u00d0\3\2\2\2\16\u00d2\3\2\2\2\20\u00d4\3\2\2\2\22\u00d6\3\2\2\2"+ + "\24\u00d8\3\2\2\2\26\u00dc\3\2\2\2\30\u00e1\3\2\2\2\32\u00e3\3\2\2\2\34"+ + "\u00e5\3\2\2\2\36\u00e8\3\2\2\2 \u00eb\3\2\2\2\"\u00f0\3\2\2\2$\u00f6"+ + "\3\2\2\2&\u00f9\3\2\2\2(\u00fd\3\2\2\2*\u0106\3\2\2\2,\u010c\3\2\2\2."+ + "\u0113\3\2\2\2\60\u0117\3\2\2\2\62\u011b\3\2\2\2\64\u0121\3\2\2\2\66\u0127"+ + "\3\2\2\28\u012c\3\2\2\2:\u0137\3\2\2\2<\u0139\3\2\2\2>\u013b\3\2\2\2@"+ + "\u013d\3\2\2\2B\u0140\3\2\2\2D\u0142\3\2\2\2F\u0144\3\2\2\2H\u0146\3\2"+ + "\2\2J\u0149\3\2\2\2L\u014c\3\2\2\2N\u0150\3\2\2\2P\u0152\3\2\2\2R\u0155"+ + "\3\2\2\2T\u0157\3\2\2\2V\u015a\3\2\2\2X\u015d\3\2\2\2Z\u0161\3\2\2\2\\"+ + "\u0164\3\2\2\2^\u0168\3\2\2\2`\u016a\3\2\2\2b\u016c\3\2\2\2d\u016e\3\2"+ + "\2\2f\u0171\3\2\2\2h\u0174\3\2\2\2j\u0176\3\2\2\2l\u0178\3\2\2\2n\u017b"+ + "\3\2\2\2p\u017e\3\2\2\2r\u0181\3\2\2\2t\u0184\3\2\2\2v\u0188\3\2\2\2x"+ + "\u018b\3\2\2\2z\u018e\3\2\2\2|\u0190\3\2\2\2~\u0193\3\2\2\2\u0080\u0196"+ + "\3\2\2\2\u0082\u0199\3\2\2\2\u0084\u019c\3\2\2\2\u0086\u019f\3\2\2\2\u0088"+ + "\u01a2\3\2\2\2\u008a\u01a5\3\2\2\2\u008c\u01a8\3\2\2\2\u008e\u01ac\3\2"+ + "\2\2\u0090\u01b0\3\2\2\2\u0092\u01b5\3\2\2\2\u0094\u01be\3\2\2\2\u0096"+ + "\u01d0\3\2\2\2\u0098\u01dd\3\2\2\2\u009a\u020d\3\2\2\2\u009c\u020f\3\2"+ + "\2\2\u009e\u0220\3\2\2\2\u00a0\u0225\3\2\2\2\u00a2\u022b\3\2\2\2\u00a4"+ + "\u0230\3\2\2\2\u00a6\u023b\3\2\2\2\u00a8\u024a\3\2\2\2\u00aa\u024e\3\2"+ + "\2\2\u00ac\u00ae\t\2\2\2\u00ad\u00ac\3\2\2\2\u00ae\u00af\3\2\2\2\u00af"+ + "\u00ad\3\2\2\2\u00af\u00b0\3\2\2\2\u00b0\u00b1\3\2\2\2\u00b1\u00b2\b\2"+ + "\2\2\u00b2\5\3\2\2\2\u00b3\u00b4\7\61\2\2\u00b4\u00b5\7\61\2\2\u00b5\u00b9"+ + "\3\2\2\2\u00b6\u00b8\13\2\2\2\u00b7\u00b6\3\2\2\2\u00b8\u00bb\3\2\2\2"+ + "\u00b9\u00ba\3\2\2\2\u00b9\u00b7\3\2\2\2\u00ba\u00bc\3\2\2\2\u00bb\u00b9"+ + "\3\2\2\2\u00bc\u00c9\t\3\2\2\u00bd\u00be\7\61\2\2\u00be\u00bf\7,\2\2\u00bf"+ "\u00c3\3\2\2\2\u00c0\u00c2\13\2\2\2\u00c1\u00c0\3\2\2\2\u00c2\u00c5\3"+ "\2\2\2\u00c3\u00c4\3\2\2\2\u00c3\u00c1\3\2\2\2\u00c4\u00c6\3\2\2\2\u00c5"+ "\u00c3\3\2\2\2\u00c6\u00c7\7,\2\2\u00c7\u00c9\7\61\2\2\u00c8\u00b3\3\2"+ @@ -340,14 +340,14 @@ class PainlessLexer extends Lexer { "\u01fa\3\2\2\2\u01fc\u01ff\3\2\2\2\u01fd\u01fe\3\2\2\2\u01fd\u01fb\3\2"+ "\2\2\u01fe\u0200\3\2\2\2\u01ff\u01fd\3\2\2\2\u0200\u020e\7$\2\2\u0201"+ "\u0209\7)\2\2\u0202\u0203\7^\2\2\u0203\u0208\7)\2\2\u0204\u0205\7^\2\2"+ - "\u0205\u0208\7^\2\2\u0206\u0208\n\16\2\2\u0207\u0202\3\2\2\2\u0207\u0204"+ + "\u0205\u0208\7^\2\2\u0206\u0208\n\17\2\2\u0207\u0202\3\2\2\2\u0207\u0204"+ "\3\2\2\2\u0207\u0206\3\2\2\2\u0208\u020b\3\2\2\2\u0209\u020a\3\2\2\2\u0209"+ "\u0207\3\2\2\2\u020a\u020c\3\2\2\2\u020b\u0209\3\2\2\2\u020c\u020e\7)"+ "\2\2\u020d\u01f5\3\2\2\2\u020d\u0201\3\2\2\2\u020e\u009b\3\2\2\2\u020f"+ - "\u0213\7\61\2\2\u0210\u0214\n\17\2\2\u0211\u0212\7^\2\2\u0212\u0214\n"+ - "\20\2\2\u0213\u0210\3\2\2\2\u0213\u0211\3\2\2\2\u0214\u0215\3\2\2\2\u0215"+ + "\u0213\7\61\2\2\u0210\u0214\n\20\2\2\u0211\u0212\7^\2\2\u0212\u0214\n"+ + "\21\2\2\u0213\u0210\3\2\2\2\u0213\u0211\3\2\2\2\u0214\u0215\3\2\2\2\u0215"+ "\u0213\3\2\2\2\u0215\u0216\3\2\2\2\u0216\u0217\3\2\2\2\u0217\u021b\7\61"+ - "\2\2\u0218\u021a\t\21\2\2\u0219\u0218\3\2\2\2\u021a\u021d\3\2\2\2\u021b"+ + "\2\2\u0218\u021a\t\22\2\2\u0219\u0218\3\2\2\2\u021a\u021d\3\2\2\2\u021b"+ "\u0219\3\2\2\2\u021b\u021c\3\2\2\2\u021c\u021e\3\2\2\2\u021d\u021b\3\2"+ "\2\2\u021e\u021f\6N\3\2\u021f\u009d\3\2\2\2\u0220\u0221\7v\2\2\u0221\u0222"+ "\7t\2\2\u0222\u0223\7w\2\2\u0223\u0224\7g\2\2\u0224\u009f\3\2\2\2\u0225"+ @@ -357,14 +357,14 @@ class PainlessLexer extends Lexer { "\u0236\5\u00a6S\2\u0231\u0232\5\24\n\2\u0232\u0233\5\u00a6S\2\u0233\u0235"+ "\3\2\2\2\u0234\u0231\3\2\2\2\u0235\u0238\3\2\2\2\u0236\u0234\3\2\2\2\u0236"+ "\u0237\3\2\2\2\u0237\u0239\3\2\2\2\u0238\u0236\3\2\2\2\u0239\u023a\6R"+ - "\4\2\u023a\u00a5\3\2\2\2\u023b\u023f\t\22\2\2\u023c\u023e\t\23\2\2\u023d"+ + "\4\2\u023a\u00a5\3\2\2\2\u023b\u023f\t\23\2\2\u023c\u023e\t\24\2\2\u023d"+ "\u023c\3\2\2\2\u023e\u0241\3\2\2\2\u023f\u023d\3\2\2\2\u023f\u0240\3\2"+ "\2\2\u0240\u00a7\3\2\2\2\u0241\u023f\3\2\2\2\u0242\u024b\7\62\2\2\u0243"+ "\u0247\t\b\2\2\u0244\u0246\t\t\2\2\u0245\u0244\3\2\2\2\u0246\u0249\3\2"+ "\2\2\u0247\u0245\3\2\2\2\u0247\u0248\3\2\2\2\u0248\u024b\3\2\2\2\u0249"+ "\u0247\3\2\2\2\u024a\u0242\3\2\2\2\u024a\u0243\3\2\2\2\u024b\u024c\3\2"+ - "\2\2\u024c\u024d\bT\4\2\u024d\u00a9\3\2\2\2\u024e\u0252\t\22\2\2\u024f"+ - "\u0251\t\23\2\2\u0250\u024f\3\2\2\2\u0251\u0254\3\2\2\2\u0252\u0250\3"+ + "\2\2\u024c\u024d\bT\4\2\u024d\u00a9\3\2\2\2\u024e\u0252\t\23\2\2\u024f"+ + "\u0251\t\24\2\2\u0250\u024f\3\2\2\2\u0251\u0254\3\2\2\2\u0252\u0250\3"+ "\2\2\2\u0252\u0253\3\2\2\2\u0253\u0255\3\2\2\2\u0254\u0252\3\2\2\2\u0255"+ "\u0256\bU\4\2\u0256\u00ab\3\2\2\2$\2\3\u00af\u00b9\u00c3\u00c8\u01b9\u01bc"+ "\u01c3\u01c6\u01cd\u01d0\u01d3\u01da\u01dd\u01e3\u01e5\u01e9\u01ee\u01f0"+ diff --git a/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/Walker.java b/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/Walker.java index 84d58afa62d..9de833e5419 100644 --- a/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/Walker.java +++ b/modules/lang-painless/src/main/java/org/elasticsearch/painless/antlr/Walker.java @@ -799,9 +799,27 @@ public final class Walker extends PainlessParserBaseVisitor { @Override public ANode visitString(StringContext ctx) { - String string = ctx.STRING().getText().substring(1, ctx.STRING().getText().length() - 1); + StringBuilder string = new StringBuilder(ctx.STRING().getText()); - return new EString(location(ctx), string); + // Strip the leading and trailing quotes and replace the escape sequences with their literal equivalents + int src = 1; + int dest = 0; + int end = string.length() - 1; + assert string.charAt(0) == '"' || string.charAt(0) == '\'' : "expected string to start with a quote but was [" + string + "]"; + assert string.charAt(end) == '"' || string.charAt(end) == '\'' : "expected string to end with a quote was [" + string + "]"; + while (src < end) { + char current = string.charAt(src); + if (current == '\\') { + src++; + current = string.charAt(src); + } + string.setCharAt(dest, current); + src++; + dest++; + } + string.setLength(dest); + + return new EString(location(ctx), string.toString()); } @Override diff --git a/modules/lang-painless/src/test/java/org/elasticsearch/painless/BasicExpressionTests.java b/modules/lang-painless/src/test/java/org/elasticsearch/painless/BasicExpressionTests.java index 7c0694d67ba..ef2ddad5452 100644 --- a/modules/lang-painless/src/test/java/org/elasticsearch/painless/BasicExpressionTests.java +++ b/modules/lang-painless/src/test/java/org/elasticsearch/painless/BasicExpressionTests.java @@ -42,6 +42,7 @@ public class BasicExpressionTests extends ScriptTestCase { assertEquals((byte)255, exec("return (byte)255")); assertEquals((short)5, exec("return (short)5")); assertEquals("string", exec("return \"string\"")); + assertEquals("string", exec("return 'string'")); assertEquals(true, exec("return true")); assertEquals(false, exec("return false")); assertNull(exec("return null")); @@ -55,6 +56,37 @@ public class BasicExpressionTests extends ScriptTestCase { assertEquals('čš ', exec("return (char)100000;")); } + public void testStringEscapes() { + // The readability of this test suffers from having to escape `\` and `"` in java strings. Please be careful. Sorry! + // `\\` is a `\` + assertEquals("\\string", exec("\"\\\\string\"")); + assertEquals("\\string", exec("'\\\\string'")); + // `\"` is a `"` if surrounded by `"`s + assertEquals("\"string", exec("\"\\\"string\"")); + Exception e = expectScriptThrows(IllegalArgumentException.class, () -> exec("'\\\"string'", false)); + assertEquals("unexpected character ['\\\"]. The only valid escape sequences in strings starting with ['] are [\\\\] and [\\'].", + e.getMessage()); + // `\'` is a `'` if surrounded by `'`s + e = expectScriptThrows(IllegalArgumentException.class, () -> exec("\"\\'string\"", false)); + assertEquals("unexpected character [\"\\']. The only valid escape sequences in strings starting with [\"] are [\\\\] and [\\\"].", + e.getMessage()); + assertEquals("'string", exec("'\\'string'")); + // We don't break native escapes like new line + assertEquals("\nstring", exec("\"\nstring\"")); + assertEquals("\nstring", exec("'\nstring'")); + + // And we're ok with strings with multiple escape sequences + assertEquals("\\str\"in\\g", exec("\"\\\\str\\\"in\\\\g\"")); + assertEquals("st\\r'i\\ng", exec("'st\\\\r\\'i\\\\ng'")); + } + + public void testStringTermination() { + // `'` inside of a string delimited with `"` should be ok + assertEquals("test'", exec("\"test'\"")); + // `"` inside of a string delimited with `'` should be ok + assertEquals("test\"", exec("'test\"'")); + } + /** declaring variables for primitive types */ public void testDeclareVariable() { assertEquals(5, exec("int i = 5; return i;")); diff --git a/modules/lang-painless/src/test/java/org/elasticsearch/painless/WhenThingsGoWrongTests.java b/modules/lang-painless/src/test/java/org/elasticsearch/painless/WhenThingsGoWrongTests.java index f23b13341cc..4051d8457fa 100644 --- a/modules/lang-painless/src/test/java/org/elasticsearch/painless/WhenThingsGoWrongTests.java +++ b/modules/lang-painless/src/test/java/org/elasticsearch/painless/WhenThingsGoWrongTests.java @@ -267,4 +267,20 @@ public class WhenThingsGoWrongTests extends ScriptTestCase { assertEquals("invalid sequence of tokens near ['.'].", e.getMessage()); } + public void testBadStringEscape() { + Exception e = expectScriptThrows(IllegalArgumentException.class, () -> exec("'\\a'", false)); + assertEquals("unexpected character ['\\a]. The only valid escape sequences in strings starting with ['] are [\\\\] and [\\'].", + e.getMessage()); + e = expectScriptThrows(IllegalArgumentException.class, () -> exec("\"\\a\"", false)); + assertEquals("unexpected character [\"\\a]. The only valid escape sequences in strings starting with [\"] are [\\\\] and [\\\"].", + e.getMessage()); + } + + public void testRegularUnexpectedCharacter() { + Exception e = expectScriptThrows(IllegalArgumentException.class, () -> exec("'", false)); + assertEquals("unexpected character ['].", e.getMessage()); + e = expectScriptThrows(IllegalArgumentException.class, () -> exec("'cat", false)); + assertEquals("unexpected character ['cat].", e.getMessage()); + } + }