KorAP
diff --git a/‎.github/workflows/ci_test.yml‎ ‎.github/workflows/linux_ci.yml‎.github/workflows/ci_test.yml renamed to .github/workflows/linux_ci.yml b/‎.github/workflows/ci_test.yml‎ ‎.github/workflows/linux_ci.yml‎.github/workflows/ci_test.yml renamed to .github/workflows/linux_ci.yml
diff --git a/‎.github/workflows/windows_ci.yml‎
Lines changed: 21 additions & 0 deletions b/‎.github/workflows/windows_ci.yml‎
Lines changed: 21 additions & 0 deletions
diff --git a/‎Changes‎
Lines changed: 6 additions & 0 deletions b/‎Changes‎
Lines changed: 6 additions & 0 deletions
diff --git a/‎README.md‎
Lines changed: 2 additions & 2 deletions b/‎README.md‎
Lines changed: 2 additions & 2 deletions
diff --git a/‎pom.xml‎
Lines changed: 10 additions & 9 deletions b/‎pom.xml‎
Lines changed: 10 additions & 9 deletions
diff --git a/‎src/main/antlr/cosmas/c2ps.g‎
Lines changed: 73 additions & 14 deletions b/‎src/main/antlr/cosmas/c2ps.g‎
Lines changed: 73 additions & 14 deletions
@@ -0,0 +1,21 @@
+name: CI Windows
+
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: windows-latest
+    steps:
+      - name: Set git to use LF
+        run: |
+          git config --global core.autocrlf false
+          git config --global core.eol lf
+      - name: Checkout Koral
+        uses: actions/checkout@v2
+      - name: Set up JDK 11
+        uses: actions/setup-java@v1
+        with:
+          java-version: 11
+
+      - name: Build and install Koral
+        run: mvn --file pom.xml install
@@ -1,5 +1,11 @@
+0.42 2024-01-11
+    - [feature] Support #REG in C2 (bodmer)
+    - [bugfix] Fix comma in #BED in C2 (bodmer)
+
 0.41 2023-09-13
+    - [feature] Finish support for CQP (irimia)
     - [bugfix] Disallow empty regex in PQ+ (diewald)
+    - [cleanup] Change of groupID.
 
 0.40 2023-07-26
     - [feature] Initial support for CQP
 
@@ -132,7 +132,7 @@ J. Bingel and N. Diewald, "KoralQuery – a General Corpus Query Protocol," in P
 ## Authorship
 
 Koral and KoralQuery were developed by Joachim Bingel,
-Nils Diewald, Michael Hanl and Eliza Margaretha at the
+Nils Diewald, Michael Hanl, Eliza Margaretha, and Franck Bodmer at the
 [Leibniz Institute for the German Language (IDS)](https://www.ids-mannheim.de/),
 member of the [Leibniz Association](https://www.leibniz-gemeinschaft.de).
 
@@ -142,7 +142,7 @@ The ANTLR grammars for parsing ANNIS QL and COSMAS II QL were developed by
 Thomas Krause (HU Berlin) and Franck Bodmer (IDS Mannheim), respectively.
 Minor adaptations of those grammars were implemented by the Koral authors.
 
-The authors wish to thank Piotr Bański, Franck Bodmer, Elena Frick and
+The authors wish to thank Piotr Bański, Elena Frick and
 Carsten Schnober for their valuable input.
 
 ## License
 
@@ -2,9 +2,9 @@
 	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 	<modelVersion>4.0.0</modelVersion>
 
-	<groupId>de.ids_mannheim.korap</groupId>
+	<groupId>de.ids-mannheim.korap.koral</groupId>
 	<artifactId>Koral</artifactId>
-	<version>0.41.0</version>
+	<version>0.42.0</version>
 	<packaging>jar</packaging>
 	<name>Koral</name>
 	<url>https://korap.ids-mannheim.de</url>
@@ -39,11 +39,11 @@
 
 	<properties>
 		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>		
-		<jackson.version>2.15.2</jackson.version>
+		<jackson.version>2.16.1</jackson.version>
 		<antlr4.version>4.9.3</antlr4.version>
 		<antlr3.version>3.5.3</antlr3.version>
 		<java.version>11</java.version>
-		<log4j.version>2.20.0</log4j.version>
+		<log4j.version>2.22.1</log4j.version>
 	</properties>
 
 	<repositories>
@@ -83,7 +83,7 @@
 		<dependency>
 			<groupId>com.google.guava</groupId>
 			<artifactId>guava</artifactId>
-			<version>32.1.2-jre</version>
+			<version>33.0.0-jre</version>
 		</dependency>
 		<dependency>
 			<groupId>com.fasterxml.jackson.core</groupId>
@@ -145,7 +145,7 @@
 		<dependency>
 			<groupId>org.slf4j</groupId>
 			<artifactId>slf4j-api</artifactId>
-			<version>2.0.9</version>
+			<version>2.0.11</version>
 		</dependency>
 		<dependency>
 			<groupId>eu.clarin.sru.fcs</groupId>
@@ -160,7 +160,7 @@
 		  <plugin>
 			  <groupId>org.apache.maven.plugins</groupId>
 			  <artifactId>maven-clean-plugin</artifactId>
-		    <version>3.3.1</version>
+		    <version>3.3.2</version>
 		    <configuration>
 		      <filesets>
 		        <fileset>
@@ -177,6 +177,7 @@
 		          	<exclude>**/c2ps_opIN.java</exclude>
 		          	<exclude>**/c2ps_opOV.java</exclude>
 		          	<exclude>**/c2ps_opPROX.java</exclude>
+		          	<exclude>**/c2ps_opREG.java</exclude>
 		          	<exclude>**/c2ps_opWF.java</exclude>
 		          	<exclude>**/c2ps_optCase.java</exclude>
 		          	<exclude>**/.gitignore</exclude>
@@ -190,7 +191,7 @@
 			<plugin>
 				<groupId>org.apache.maven.plugins</groupId>
 				<artifactId>maven-surefire-plugin</artifactId>
-				<version>3.1.2</version>
+				<version>3.2.5</version>
 				<configuration>
                     <useSystemClassLoader>false</useSystemClassLoader>
 					<excludes>
@@ -201,7 +202,7 @@
 			<plugin>
 				<groupId>org.apache.maven.plugins</groupId>
 				<artifactId>maven-compiler-plugin</artifactId>
-				<version>3.11.0</version>
+				<version>3.12.1</version>
 				<configuration>
 					<!-- <verbose>true</verbose>
 		          	<fork>true</fork> -->
 
@@ -1,16 +1,26 @@
- // * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
-//												//
-// 	COSMAS II zeilenorientierten Suchanfragesprache (C2 plain syntax)			//
-// 	globale Grammatik (ruft lokale c2ps_x.g Grammatiken auf).				//
-//	17.12.12/FB										//
-//      v-0.6											//
-// TODO:											//
-// - se1: Einsetzen des Default-Operators in den kumulierten AST.				//
+// * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
+//												
+// 	COSMAS II zeilenorientierten Suchanfragesprache (C2 plain syntax)	
+// 	globale Grammatik (ruft lokale c2ps_x.g Grammatiken auf).			
+//	17.12.12/FB										
+//      v-0.6										
+// TODO:											
+// - se1: Einsetzen des Default-Operators in den kumulierten AST.		
+//
+//  v0.7 - 25.07.23/FB
+//    - added: #REG(x)
+//  v0.8 - 06.11.23/FB
+//    - accepts #BED(searchword, sa) : comma attached to searchword.
+//    - more generally: comma at end of searchword, which is not enclosed by "..." is
+//      excluded from searchword now.
+//    - a comma inside a searchword is accepted if enclosed by "...".
+//
 // * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
 
 grammar c2ps;
 
 options { output=AST; backtrack=true; k=5;}
+// tokens that will appear as node names in the resulting AST:
 tokens  {C2PQ; OPBED; OPTS; OPBEG; OPEND; OPNHIT; OPALL; OPLEM; OPPROX;
 	 ARG1; ARG2; 
 	 OPWF; OPLEM; OPANNOT;
@@ -21,6 +31,7 @@ tokens  {C2PQ; OPBED; OPTS; OPBEG; OPEND; OPNHIT; OPALL; OPLEM; OPPROX;
 	 OPNOT;
 	 OPEXPR1;
 	 OPMORPH; OPELEM;
+	 OPREG;
 	}
 
 @header {package de.ids_mannheim.korap.query.parse.cosmas;}
@@ -63,19 +74,50 @@ WS	:	(' '|'\r'|'\n')+ {skip();};
 
 fragment DISTVALUE
 	:	 ('0' .. '9')+ (':' ('0'..'9')+)? ;
-		
+
+fragment DISTTYPE // 30.11.23/FB
+	: 	('w'|'s'|'p'|'t');
+
+fragment DISTDIR // 30.11.23/FB
+	: 	('+'|'-');
+	
+/* old version (before 30.11.23/FB)
 fragment DIST
 	:	('+'|'-')? (DISTVALUE ('w'|'s'|'p'|'t') | ('w'|'s'|'p'|'t') DISTVALUE);
-	
+*/
+
+// accept these 3 options in any order.
+// afterwards, we will have to check if any of them is missing.
+// 30.11.23/FB
+
+fragment DIST // 30.11.23/FB
+	:	(DISTDIR | DISTTYPE | DISTVALUE )+;
+
 fragment GROUP
 	:	('min' | 'max');
 
-OP_PROX	:	('/' | '%') DIST (',' DIST)* (',' GROUP)? ;
+// version (12.01.24/FB):
+// accept correct and incorrect chars till the next blank, that way the incorrect chars
+// are submitted to the sub-grammer c2ps_opPROX where they are detected and an appropriate 
+// error message is inserted:
+OP_PROX		:	('/' | '%') DIST (~' ')*; 
+
+// old version: accepts only correctly formulated options, so the incorrect
+// chars/options are hard to detect:
+// OP_PROX	:	('/' | '%') DIST (',' DIST)* (',' GROUP)?  ;
 
 OP_IN	:	'#IN' | '#IN(' OP_IN_OPTS? ')' ; 
 
 OP_OV	:	'#OV' | '#OV(' OP_OV_OPTS? ')' ;
 
+// #REG(abc['"]) or #REG('abc\'s') or #REG("abc\"s"):
+
+OP_REG	: '#REG(' ' '* '\'' ('\\\''|~'\'')+  '\'' (' ')* ')'	
+			| 
+		  '#REG(' ' '* '"' ('\\"'|~'"')+ '"' (' ')* ')'
+		  	|
+		  '#REG(' ' '* ~('\''|'"'|' ') (~(')'))* ')';
+
 // EAVEXP wird hier eingesetzt fÃ¼r eine beliebige Sequenz von Zeichen bis zu ')'.
 fragment OP_IN_OPTS
 	:	EAVEXPR ;
@@ -111,8 +153,23 @@ SEARCHLEMMA
 	:	'&' SEARCHWORD1 ; // rewrite rules funktionieren im lexer nicht: -> ^(OPLEM $SEARCHWORD1.text); 
 
 // SEARCHWORD2: schluckt Blanks. Diese mÃ¼ssen nachtrÃ¤glich als Wortdelimiter erkannt werden.
+
+// current syntax, drawback is:
+// e.g. aber, -> SEARCHWORD1 = "aber,"
+// but correct should be -> SEARCHWORD1 = "aber"  
+//SEARCHWORD1
+//	:	~('"' | ' ' | '#' | ')' | '(' )+ ;
+
+// new syntax (06.11.23/FB):
+// accept for searchword1 either a single ',' or exclude trailing ',' from searchword1:
+// E.g. Haus, -> searchword1=Haus.
+// For a ',' inside a search word, see searchword2. 
+// exclude trailing "," from searchword1.
 SEARCHWORD1
-	:	~('"' | ' ' | '#' | ')' | '(' )+ ;
+	:	(',' | ~('"' | ' ' | '#' | ')' | '(' | ',')+)  ;
+
+// searchword2 accepts a ',' inside a searchword enclosed by "...".
+// E.g. "Haus,tür": OK.
 
 SEARCHWORD2
 	:	'"' (~('"') | '\\"')+ '"' ;
@@ -226,7 +283,7 @@ searchLabel
 op2	:	(opPROX | opIN | opOV | opAND | opOR | opNOT) ;
 
 // AST with Options for opPROX is returned by c2ps_opPROX.check():
-opPROX	:	OP_PROX -> ^(OPPROX {c2ps_opPROX.check($OP_PROX.text, $OP_PROX.index)} );
+opPROX	:	OP_PROX -> ^(OPPROX {c2ps_opPROX.check($OP_PROX.text, $OP_PROX.pos)} );
 
 opIN	: 	OP_IN -> {c2ps_opIN.check($OP_IN.text, $OP_IN.index)};
 
@@ -241,7 +298,7 @@ opNOT	:	('nicht' | 'NICHT' | 'not' | 'NOT') -> ^(OPNOT);
 // OP1: Suchoperatoren mit 1 Argument:
 // -----------------------------------
 
-op1	:	opBEG | opEND | opNHIT | opALL | opBED; 
+op1	:	opBEG | opEND | opNHIT | opALL | opBED | opREG; 
 
 // #BED(serchExpr, B).
 // B muss nachtrÃ¤glich in einer lokalen Grammatik Ã¼berprÃ¼ft werden.
@@ -259,3 +316,5 @@ opEND	:	( '#END(' | '#RECHTS(' ) searchExpr ')'  -> ^(OPEND searchExpr) ;
 opNHIT	:	( '#NHIT(' | '#INKLUSIVE(' ) searchExpr ')' -> ^(OPNHIT searchExpr) ;
 
 opALL	:	( '#ALL(' | '#EXKLUSIVE(' ) searchExpr ')'  -> ^(OPALL searchExpr) ;
+
+opREG	:	OP_REG -> ^(OPREG {c2ps_opREG.encode($OP_REG.text, OPREG)}) ;