initial shaclc-grammars

shacl-compact-syntax/grammar/Makefile

@@ -0,0 +1,34 @@
+# delete targets that caused an error
+.DELETE_ON_ERROR:
+
+# make as many targets as you can
+# .IGNORE:
+
+ebnf-convert = java -jar c:/prog/bin/ebnf-convert.war
+rr           = java -jar c:/prog/bin/rr.war
+
+HTML = shaclc-ANTLR.html shaclc-JavaCC.html shaclc-Jison.html shaclc-XText.html 
+
+# MD = shaclc-ANTLR.md shaclc-JavaCC.md shaclc-Jison.md shaclc-XText.md
+# Neither embedded PNG nor SVG is rendered by Github markdown
+
+all: $(HTML) # $(MD)
+
+%.html: %.ebnf
+	$(rr) $^ > $@
+
+%.md: %.ebnf
+	$(rr) -md -png $^ > $@
+
+shaclc-ANTLR.ebnf : shaclc-ANTLR.g4
+	$(ebnf-convert) $^ > $@
+
+shaclc-JavaCC.ebnf: shaclc-JavaCC.jj
+	$(ebnf-convert) $^ > $@
+
+shaclc-Jison.ebnf : shaclc-Jison.jison
+	$(ebnf-convert) $^ > $@
+
+shaclc-XText.ebnf : shaclc-XText.xtext
+	$(ebnf-convert) $^ > $@
+

shacl-compact-syntax/grammar/README.md

@@ -0,0 +1,31 @@
+# Unifying SHACL-C Grammars
+(Task: https://github.com/w3c/shacl/issues/37#issuecomment-1997655429 )
+
+As a first task of the SHACL Compact Syntax sub-WG, we look at proposed SHACL-C grammars:
+
+- [ANTLR](shaclc-ANTLR.g4) (was part of TopQuadrant SHACL, also in the [grammar-section](https://w3c.github.io/shacl/shacl-compact-syntax/#grammar-section) of the candidate spec) by @HolgerKnublauch
+- [JavaCC](https://github.com/apache/jena/blob/main/jena-shacl/shaclc/shaclc.jj) (part of Jena) by @afs
+- [XText](https://gitlab.com/allotrope-open-source/shape-editor/-/blob/master/src/com.osthus.shapes.shaclc.parent/com.osthus.shapes.shaclc/src/com/osthus/shapes/shaclc/SHACLC.xtext) (part of Allotrope-open-source) by @tw-osthus
+- [Jison](https://github.com/jeswr/shaclcjs/blob/main/lib/shaclc.jison) (part of shacl.js) by @jeswr 
+
+We use two tools to understand them and try to unify them:
+- https://github.com/GuntherRademacher/ebnf-convert to convert them to W3C-style EBNF, which is also needed for official publication.
+- https://github.com/GuntherRademacher/rr to produce "rail-road" diagrams, which make it easier to understand the grammars.
+
+Problems:
+- DONE: Unicode escapes in XText: https://github.com/GuntherRademacher/ebnf-convert/issues/8 .
+  This was fixed 22-Mar-2024: build from source and use `build/distributions/ebnf-convert-0.68-SNAPSHOT-java11.zip/ebnf-convert.war`
+- DONE: fixed problems in Jison: https://github.com/w3c/shacl/issues/48 .
+
+`rr` can make railroad diagrams in HTML or Markdown.
+- The Markdown uses embedded images (eg `data:image/png;base64`), which are not rendered by Github (neither PNG nor SVG)
+- We could ask `rr` to put the images outside, but I think that's too much trouble
+- So instead, we use HTML where the images are embedded as SVG and render properly
+
+# Candidate SHACL-C Grammars
+
+- [shacl-ANTLR.g4](shacl-ANTLR.g4) -> [shacl-ANTLR.ebnf](shacl-ANTLR.ebnf) -> [shaclc-ANTLR.html](https://rawgit2.com/shacl/master/shacl-compact-syntax/grammar/shaclc-ANTLR.html) (or [in branch](https://rawgit2.com/VladimirAlexiev/shacl/shaclc-grammars/shacl-compact-syntax/grammar/shaclc-ANTLR.html))
+- [shacl-JavaCC.jj](shacl-JavaCC.jj) -> [shacl-JavaCC.ebnf](shacl-JavaCC.ebnf) -> [shaclc-JavaCC.html](https://rawgit2.com/shacl/master/shacl-compact-syntax/grammar/shaclc-JavaCC.html) (or [in branch](https://rawgit2.com/VladimirAlexiev/shacl/shaclc-grammars/shacl-compact-syntax/grammar/shaclc-JavaCC.html))
+- [shacl-XText.xtext](shacl-XText.xtext) -> [shacl-XText.ebnf](shacl-XText.ebnf) -> [shaclc-XText.html](https://rawgit2.com/shacl/master/shacl-compact-syntax/grammar/shaclc-XText.html) (or [in branch](https://rawgit2.com/VladimirAlexiev/shacl/shaclc-grammars/shacl-compact-syntax/grammar/shaclc-XText.html))
+- [shacl-Jison.jison](shacl-Jison.jison) -> [shacl-Jison.ebnf](shacl-Jison.ebnf) -> [shaclc-Jison.html](https://rawgit2.com/shacl/master/shacl-compact-syntax/grammar/shaclc-Jison.html) (or [in branch](https://rawgit2.com/VladimirAlexiev/shacl/shaclc-grammars/shacl-compact-syntax/grammar/shaclc-Jison.html))
+

shacl-compact-syntax/grammar/shaclc-ANTLR.ebnf

@@ -0,0 +1,203 @@
+/* converted on Mon Mar 18, 2024, 18:17 (UTC+02) by antlr_4-to-w3c v0.67 which is Copyright (c) 2011-2024 by Gunther Rademacher <grd@gmx.net> */
+
+shaclDoc ::= directive* ( nodeShape | shapeClass )* EOF
+directive
+         ::= baseDecl
+           | importsDecl
+           | prefixDecl
+baseDecl ::= 'BASE' IRIREF
+importsDecl
+         ::= 'IMPORTS' IRIREF
+prefixDecl
+         ::= 'PREFIX' PNAME_NS IRIREF
+shapeClass
+         ::= 'shapeClass' iri nodeShapeBody
+nodeShape
+         ::= 'shape' iri targetClass? nodeShapeBody
+nodeShapeBody
+         ::= '{' constraint* '}'
+targetClass
+         ::= '->' iri+
+constraint
+         ::= ( nodeOr+ | propertyShape ) '.'
+nodeOr   ::= nodeNot ( '|' nodeNot )*
+nodeNot  ::= '!'? nodeValue
+nodeValue
+         ::= nodeParam '=' iriOrLiteralOrArray
+propertyShape
+         ::= path ( propertyCount | propertyOr )*
+propertyOr
+         ::= propertyNot ( '|' propertyNot )*
+propertyNot
+         ::= '!'? propertyAtom
+propertyAtom
+         ::= propertyType
+           | nodeKind
+           | shapeRef
+           | propertyValue
+           | nodeShapeBody
+propertyCount
+         ::= '[' propertyMinCount '..' propertyMaxCount ']'
+propertyMinCount
+         ::= INTEGER
+propertyMaxCount
+         ::= INTEGER
+           | '*'
+propertyType
+         ::= iri
+nodeKind ::= 'BlankNode'
+           | 'IRI'
+           | 'Literal'
+           | 'BlankNodeOrIRI'
+           | 'BlankNodeOrLiteral'
+           | 'IRIOrLiteral'
+shapeRef ::= ATPNAME_LN
+           | ATPNAME_NS
+           | '@' IRIREF
+propertyValue
+         ::= propertyParam '=' iriOrLiteralOrArray
+path     ::= pathAlternative
+pathAlternative
+         ::= pathSequence ( '|' pathSequence )*
+pathSequence
+         ::= pathEltOrInverse ( '/' pathEltOrInverse )*
+pathElt  ::= pathPrimary pathMod?
+pathEltOrInverse
+         ::= '^'? pathElt
+pathMod  ::= '?'
+           | '*'
+           | '+'
+pathPrimary
+         ::= iri
+           | '(' path ')'
+iriOrLiteralOrArray
+         ::= iriOrLiteral
+           | array
+iriOrLiteral
+         ::= iri
+           | literal
+iri      ::= IRIREF
+           | prefixedName
+prefixedName
+         ::= PNAME_LN
+           | PNAME_NS
+literal  ::= rdfLiteral
+           | numericLiteral
+           | booleanLiteral
+booleanLiteral
+         ::= 'true'
+           | 'false'
+numericLiteral
+         ::= INTEGER
+           | DECIMAL
+           | DOUBLE
+rdfLiteral
+         ::= string ( LANGTAG | '^^' datatype )?
+datatype ::= iri
+string   ::= STRING_LITERAL_LONG1
+           | STRING_LITERAL_LONG2
+           | STRING_LITERAL1
+           | STRING_LITERAL2
+array    ::= '[' iriOrLiteral* ']'
+nodeParam
+         ::= 'targetNode'
+           | 'targetObjectsOf'
+           | 'targetSubjectsOf'
+           | 'deactivated'
+           | 'severity'
+           | 'message'
+           | 'class'
+           | 'datatype'
+           | 'nodeKind'
+           | 'minExclusive'
+           | 'minInclusive'
+           | 'maxExclusive'
+           | 'maxInclusive'
+           | 'minLength'
+           | 'maxLength'
+           | 'pattern'
+           | 'flags'
+           | 'languageIn'
+           | 'equals'
+           | 'disjoint'
+           | 'closed'
+           | 'ignoredProperties'
+           | 'hasValue'
+           | 'in'
+propertyParam
+         ::= 'deactivated'
+           | 'severity'
+           | 'message'
+           | 'class'
+           | 'datatype'
+           | 'nodeKind'
+           | 'minExclusive'
+           | 'minInclusive'
+           | 'maxExclusive'
+           | 'maxInclusive'
+           | 'minLength'
+           | 'maxLength'
+           | 'pattern'
+           | 'flags'
+           | 'languageIn'
+           | 'uniqueLang'
+           | 'equals'
+           | 'disjoint'
+           | 'lessThan'
+           | 'lessThanOrEquals'
+           | 'qualifiedValueShape'
+           | 'qualifiedMinCount'
+           | 'qualifiedMaxCount'
+           | 'qualifiedValueShapesDisjoint'
+           | 'closed'
+           | 'ignoredProperties'
+           | 'hasValue'
+           | 'in'
+_        ::= PASS
+           | COMMENT
+          /* ws: definition */
+
+<?TOKENS?>
+
+PASS     ::= [ #x9#xd#xa]+
+COMMENT  ::= '#' [^#xd#xa]*
+IRIREF   ::= '<' ( [^=<>"{}|^`\#x0000-#x0020] | UCHAR )* '>'
+PNAME_NS ::= PN_PREFIX? ':'
+PNAME_LN ::= PNAME_NS PN_LOCAL
+ATPNAME_NS
+         ::= '@' PN_PREFIX? ':'
+ATPNAME_LN
+         ::= '@' PNAME_NS PN_LOCAL
+LANGTAG  ::= '@' [a-zA-Z]+ ( '-' [a-zA-Z0-9]+ )*
+INTEGER  ::= [+#x2D]? [0-9]+
+DECIMAL  ::= [+#x2D]? [0-9]* '.' [0-9]+
+DOUBLE   ::= [+#x2D]? ( [0-9]+ '.' | '.'? [0-9] ) [0-9]* EXPONENT
+EXPONENT ::= [eE] [+#x2D]? [0-9]+
+STRING_LITERAL1
+         ::= "'" ( [^#x0027#x005C#x000A#x000D] | ECHAR | UCHAR )* "'"
+STRING_LITERAL2
+         ::= '"' ( [^#x0022#x005C#x000A#x000D] | ECHAR | UCHAR )* '"'
+STRING_LITERAL_LONG1
+         ::= "'''" ( ( "'" | "''" )? ( [^'\] | ECHAR | UCHAR ) )* "'''"
+STRING_LITERAL_LONG2
+         ::= '"""' ( ( '"' | '""' )? ( [^"\] | ECHAR | UCHAR ) )* '"""'
+UCHAR    ::= ( '\u' | '\U' HEX HEX HEX HEX ) HEX HEX HEX HEX
+ECHAR    ::= '\' [tbnrf\"']
+WS       ::= [#x0020#x0009#x000D#x000A]
+PN_CHARS_BASE
+         ::= [A-Za-z#x00C0-#x00D6#x00D8-#x00F6#x00F8-#x02FF#x0370-#x037D#x037F-#x1FFF#x200C-#x200D#x2070-#x218F#x2C00-#x2FEF#x3001-#xD7FF#xF900-#xFDCF#xFDF0-#xFFFD]
+PN_CHARS_U
+         ::= PN_CHARS_BASE
+           | '_'
+PN_CHARS ::= PN_CHARS_U
+           | [-0-9#x00B7#x0300-#x036F#x203F-#x2040]
+PN_PREFIX
+         ::= PN_CHARS_BASE ( ( PN_CHARS | '.' )* PN_CHARS )?
+PN_LOCAL ::= ( PN_CHARS_U | [:0-9] | PLX ) ( ( PN_CHARS | '.' | ':' | PLX )* ( PN_CHARS | ':' | PLX ) )?
+PLX      ::= PERCENT
+           | PN_LOCAL_ESC
+PERCENT  ::= '%' HEX HEX
+HEX      ::= [0-9A-Fa-f]
+PN_LOCAL_ESC
+         ::= '\' ( '_' | '~' | '.' | '-' | '!' | '$' | '&' | "'" | '(' | ')' | '*' | '+' | ',' | ';' | '=' | '/' | '?' | '#' | '@' | '%' )
+EOF      ::= $