Remove '-' as valid characters for 'names' (#545)

Removed `-` as a valid characters that can appear in "names" like variable or prefix names. This lead to confusion with the infix operator `-` for subtraction. Closes #543
knowsys · Oct 29, 2024 · 3a851d9 · 3a851d9
2 parents 1f4f886 + 99e9283
commit 3a851d9
Show file tree

Hide file tree

Showing 25 changed files with 50 additions and 39 deletions.
diff --git a/nemo-physical/src/columnar/column/rle.rs b/nemo-physical/src/columnar/column/rle.rs
@@ -216,7 +216,7 @@ where
     }
 }
 
-impl<'a, T> Iterator for ColumnScanRle<'a, T>
+impl<T> Iterator for ColumnScanRle<'_, T>
 where
     T: ColumnDataType,
 {
@@ -255,7 +255,7 @@ where
     }
 }
 
-impl<'a, T> ColumnScan for ColumnScanRle<'a, T>
+impl<T> ColumnScan for ColumnScanRle<'_, T>
 where
     T: ColumnDataType,
 {

diff --git a/nemo-physical/src/columnar/columnscan.rs b/nemo-physical/src/columnar/columnscan.rs
@@ -100,7 +100,7 @@ where
     }
 }
 
-impl<'a, T> From<ColumnScanConstant<T>> for ColumnScanEnum<'a, T>
+impl<T> From<ColumnScanConstant<T>> for ColumnScanEnum<'_, T>
 where
     T: ColumnDataType,
 {

diff --git a/nemo-physical/src/tabular/operations/prune.rs b/nemo-physical/src/tabular/operations/prune.rs
@@ -33,7 +33,7 @@ impl<'a> TrieScanPrune<'a> {
         let input_trie_scan_arity = input_trie_scan.arity();
 
         let mut output_column_scans =
-            Vec::<UnsafeCell<ColumnScanT<'a>>>::with_capacity(input_trie_scan.arity());
+            Vec::<UnsafeCell<ColumnScanT<'_>>>::with_capacity(input_trie_scan.arity());
 
         // TODO: One could check if some of the entries are empty here
         // and from that deduce that the result of this will be empty
@@ -563,7 +563,7 @@ impl<'a> TrieScanPruneState<'a> {
     }
 }
 
-impl<'a> TrieScanPrune<'a> {
+impl TrieScanPrune<'_> {
     /// Moves to the next value on a given layer while ensuring that only materialized tuples are returned (see guarantees provided by [TrieScanPrune]).
     ///
     /// It is assumed that the trie scan has been initialized by calling `down()` at least once.
@@ -639,7 +639,7 @@ impl<'a> PartialTrieScan<'a> for TrieScanPrune<'a> {
     }
 }
 
-impl<'a> TrieScan for TrieScanPrune<'a> {
+impl TrieScan for TrieScanPrune<'_> {
     fn advance_on_layer(&mut self, layer: usize) -> Option<usize> {
         if !unsafe { (*self.state.get()).initialized } {
             for current_layer in 0..=layer {

diff --git a/nemo-physical/src/tabular/operations/trim.rs b/nemo-physical/src/tabular/operations/trim.rs
@@ -121,7 +121,7 @@ impl<'a> TrieScanTrim<'a> {
     }
 }
 
-impl<'a> TrieScan for TrieScanTrim<'a> {
+impl TrieScan for TrieScanTrim<'_> {
     fn num_columns(&self) -> usize {
         self.trie_scan.arity()
     }

diff --git a/nemo/src/parser.rs b/nemo/src/parser.rs
@@ -99,7 +99,7 @@ impl<'a> ParserErrorReport<'a> {
     }
 }
 
-impl<'a> std::fmt::Debug for ParserErrorReport<'a> {
+impl std::fmt::Debug for ParserErrorReport<'_> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let reports = self.build_reports();
 
@@ -111,7 +111,7 @@ impl<'a> std::fmt::Debug for ParserErrorReport<'a> {
     }
 }
 
-impl<'a> std::fmt::Display for ParserErrorReport<'a> {
+impl std::fmt::Display for ParserErrorReport<'_> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let mut buffer = Vec::new();
         if self.write(&mut buffer).is_err() {

diff --git a/nemo/src/parser/ast/comment/closed.rs b/nemo/src/parser/ast/comment/closed.rs
@@ -25,7 +25,7 @@ pub struct ClosedComment<'a> {
 
 const CONTEXT: ParserContext = ParserContext::Comment;
 
-impl<'a> ClosedComment<'a> {
+impl ClosedComment<'_> {
     // NOTE: Should this return a &str, so that the consumer can decide whether to turn it into an
     //   owned value or not?
     /// Return the content of the comment

diff --git a/nemo/src/parser/ast/comment/doc.rs b/nemo/src/parser/ast/comment/doc.rs
@@ -26,7 +26,7 @@ pub struct DocComment<'a> {
     content: Vec<Span<'a>>,
 }
 
-impl<'a> DocComment<'a> {
+impl DocComment<'_> {
     /// Return the content of the comment
     pub fn content(&self) -> Vec<String> {
         self.content

diff --git a/nemo/src/parser/ast/comment/line.rs b/nemo/src/parser/ast/comment/line.rs
@@ -27,7 +27,7 @@ pub struct LineComment<'a> {
 
 const CONTEXT: ParserContext = ParserContext::Comment;
 
-impl<'a> LineComment<'a> {
+impl LineComment<'_> {
     /// Return the content of the comment
     pub fn content(&self) -> String {
         self.content.fragment().to_string()

diff --git a/nemo/src/parser/ast/comment/toplevel.rs b/nemo/src/parser/ast/comment/toplevel.rs
@@ -28,7 +28,7 @@ pub struct TopLevelComment<'a> {
 
 const CONTEXT: ParserContext = ParserContext::TopLevelComment;
 
-impl<'a> TopLevelComment<'a> {
+impl TopLevelComment<'_> {
     /// Return the content of the comment
     pub fn content(&self) -> Vec<String> {
         self.content

diff --git a/nemo/src/parser/ast/directive.rs b/nemo/src/parser/ast/directive.rs
@@ -82,7 +82,7 @@ pub enum Directive<'a> {
     Unknown(UnknownDirective<'a>),
 }
 
-impl<'a> Directive<'a> {
+impl Directive<'_> {
     /// Return the context of the underlying directive.
     pub fn context_type(&self) -> ParserContext {
         match self {

diff --git a/nemo/src/parser/ast/expression/basic/iri.rs b/nemo/src/parser/ast/expression/basic/iri.rs
@@ -21,7 +21,7 @@ pub struct Iri<'a> {
     content: Token<'a>,
 }
 
-impl<'a> Iri<'a> {
+impl Iri<'_> {
     /// Return the content of the iri.
     pub fn content(&self) -> String {
         self.content.to_string()

diff --git a/nemo/src/parser/ast/guard.rs b/nemo/src/parser/ast/guard.rs
@@ -18,7 +18,7 @@ pub enum Guard<'a> {
     Infix(InfixExpression<'a>),
 }
 
-impl<'a> Guard<'a> {
+impl Guard<'_> {
     /// Return the [ParserContext] of the underlying expression type.
     pub fn context_type(&self) -> ParserContext {
         match self {

diff --git a/nemo/src/parser/ast/sequence.rs b/nemo/src/parser/ast/sequence.rs
@@ -33,7 +33,7 @@ pub struct Sequence<'a, T> {
     elements: Vec<T>,
 }
 
-impl<'a, T> Sequence<'a, T> {
+impl<T> Sequence<'_, T> {
     /// Return an iterator over the elements.
     pub fn iter(&self) -> impl Iterator<Item = &T> {
         self.into_iter()
@@ -136,7 +136,7 @@ impl<'a, T: std::fmt::Debug + Sync + ProgramAST<'a>> ProgramAST<'a> for Sequence
     }
 }
 
-impl<'a, 'b, T> IntoIterator for &'b Sequence<'a, T> {
+impl<'b, T> IntoIterator for &'b Sequence<'_, T> {
     type Item = &'b T;
     type IntoIter = std::slice::Iter<'b, T>;
 
@@ -145,7 +145,7 @@ impl<'a, 'b, T> IntoIterator for &'b Sequence<'a, T> {
     }
 }
 
-impl<'a, T> IntoIterator for Sequence<'a, T> {
+impl<T> IntoIterator for Sequence<'_, T> {
     type Item = T;
     type IntoIter = IntoIter<T>;
 

diff --git a/nemo/src/parser/ast/tag/aggregation.rs b/nemo/src/parser/ast/tag/aggregation.rs
@@ -26,7 +26,7 @@ pub struct AggregationTag<'a> {
     kind: Option<AggregateKind>,
 }
 
-impl<'a> AggregationTag<'a> {
+impl AggregationTag<'_> {
     /// Return the [AggregateKind] that was parsed, if it is known.
     pub fn operation(&self) -> Option<AggregateKind> {
         self.kind

diff --git a/nemo/src/parser/ast/tag/datatype.rs b/nemo/src/parser/ast/tag/datatype.rs
@@ -26,7 +26,7 @@ pub struct DataTypeTag<'a> {
     data_type: DataType,
 }
 
-impl<'a> DataTypeTag<'a> {
+impl DataTypeTag<'_> {
     /// Return the [DataType] that was parsed.
     pub fn data_type(&self) -> DataType {
         self.data_type

diff --git a/nemo/src/parser/ast/tag/operation.rs b/nemo/src/parser/ast/tag/operation.rs
@@ -26,7 +26,7 @@ pub struct OperationTag<'a> {
     kind: OperationKind,
 }
 
-impl<'a> OperationTag<'a> {
+impl OperationTag<'_> {
     /// Return the [OperationKind] that was parsed.
     pub fn operation(&self) -> OperationKind {
         self.kind

diff --git a/nemo/src/parser/ast/tag/parameter.rs b/nemo/src/parser/ast/tag/parameter.rs
@@ -29,7 +29,7 @@ pub struct ParameterName<'a> {
     parameter: Parameter,
 }
 
-impl<'a> ParameterName<'a> {
+impl ParameterName<'_> {
     /// Return the [Parameter] that was parsed.
     pub fn parameter(&self) -> &Parameter {
         &self.parameter

diff --git a/nemo/src/parser/ast/tag/structure.rs b/nemo/src/parser/ast/tag/structure.rs
@@ -45,7 +45,7 @@ impl<'a> StructureTag<'a> {
     }
 }
 
-impl<'a> Display for StructureTag<'a> {
+impl Display for StructureTag<'_> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         match &self.kind {
             StructureTagKind::Plain(token) => token.fmt(f),

diff --git a/nemo/src/parser/ast/token.rs b/nemo/src/parser/ast/token.rs
@@ -264,7 +264,7 @@ pub struct Token<'a> {
     kind: TokenKind,
 }
 
-impl<'a> Display for Token<'a> {
+impl Display for Token<'_> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         self.span.fmt(f)
     }
@@ -316,7 +316,7 @@ impl<'a> Token<'a> {
             ParserContext::token(TokenKind::Name),
             recognize(pair(
                 alpha1,
-                many0(alt((alphanumeric1, tag("_"), tag("-"), tag("%")))),
+                many0(alt((alphanumeric1, tag("_"), tag("%")))),
             )),
         )(input)
         .map(|(rest_input, result)| {

diff --git a/nemo/src/parser/input.rs b/nemo/src/parser/input.rs
@@ -25,7 +25,7 @@ impl<'a> ParserInput<'a> {
     }
 }
 
-impl<'a> AsBytes for ParserInput<'a> {
+impl AsBytes for ParserInput<'_> {
     fn as_bytes(&self) -> &[u8] {
         self.span.fragment().as_bytes()
     }
@@ -41,7 +41,7 @@ impl<'a> nom::Compare<ParserInput<'a>> for ParserInput<'a> {
     }
 }
 
-impl<'a> nom::Compare<&str> for ParserInput<'a> {
+impl nom::Compare<&str> for ParserInput<'_> {
     fn compare(&self, t: &str) -> nom::CompareResult {
         self.span.compare(t)
     }
@@ -51,7 +51,7 @@ impl<'a> nom::Compare<&str> for ParserInput<'a> {
     }
 }
 
-impl<'a> nom::ExtendInto for ParserInput<'a> {
+impl nom::ExtendInto for ParserInput<'_> {
     type Item = char;
 
     type Extender = String;
@@ -65,13 +65,13 @@ impl<'a> nom::ExtendInto for ParserInput<'a> {
     }
 }
 
-impl<'a> nom::FindSubstring<&str> for ParserInput<'a> {
+impl nom::FindSubstring<&str> for ParserInput<'_> {
     fn find_substring(&self, substr: &str) -> Option<usize> {
         self.span.find_substring(substr)
     }
 }
 
-impl<'a> InputLength for ParserInput<'a> {
+impl InputLength for ParserInput<'_> {
     fn input_len(&self) -> usize {
         self.span.input_len()
     }

diff --git a/nemo/src/parser/span.rs b/nemo/src/parser/span.rs
@@ -243,7 +243,7 @@ impl<'a> Span<'a> {
     }
 }
 
-impl<'a> std::fmt::Display for Span<'a> {
+impl std::fmt::Display for Span<'_> {
     fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
         self.fragment.fmt(formatter)
     }
@@ -349,7 +349,7 @@ impl<'a> nom::Compare<Span<'a>> for Span<'a> {
     }
 }
 
-impl<'a> nom::Compare<&str> for Span<'a> {
+impl nom::Compare<&str> for Span<'_> {
     fn compare(&self, t: &str) -> nom::CompareResult {
         self.fragment.compare(t)
     }

diff --git a/nemo/src/rule_model/translation.rs b/nemo/src/rule_model/translation.rs
@@ -158,7 +158,7 @@ impl<'a> ProgramErrorReport<'a> {
     }
 }
 
-impl<'a> std::fmt::Debug for ProgramErrorReport<'a> {
+impl std::fmt::Debug for ProgramErrorReport<'_> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let reports = self.build_reports();
 
@@ -170,7 +170,7 @@ impl<'a> std::fmt::Debug for ProgramErrorReport<'a> {
     }
 }
 
-impl<'a> std::fmt::Display for ProgramErrorReport<'a> {
+impl std::fmt::Display for ProgramErrorReport<'_> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let mut buffer = Vec::new();
         if self.write(&mut buffer).is_err() {

diff --git a/nemo/src/rule_model/translation/directive/import_export.rs b/nemo/src/rule_model/translation/directive/import_export.rs
@@ -62,9 +62,7 @@ impl<'a> ASTProgramTranslation<'a> {
 
                 if let Some((extension, origin)) = extension {
                     for &rdf_format in FILE_FORMATS_RDF {
-                        if extension.to_ascii_lowercase()
-                            == rdf_format.extension().to_ascii_lowercase()
-                        {
+                        if extension.eq_ignore_ascii_case(rdf_format.extension()) {
                             return Ok(rdf_format);
                         }
                     }
@@ -81,7 +79,7 @@ impl<'a> ASTProgramTranslation<'a> {
                 }
             } else {
                 for format in FileFormat::iter() {
-                    if format_tag.to_ascii_lowercase() == format.name().to_ascii_lowercase() {
+                    if format_tag.eq_ignore_ascii_case(format.name()) {
                         return Ok(format);
                     }
                 }

diff --git a/resources/testcases/regression/parsing/variable-names/run.rls b/resources/testcases/regression/parsing/variable-names/run.rls
@@ -0,0 +1,11 @@
+%%% Test related to 
+%%% https://github.com/knowsys/nemo/issues/543
+%%% 
+%%% Varibale names were allowed to contain "-", which cannot be distinguished from an arithmetic operation
+
+fact(1) .
+
+result(?variable_name) :- fact(?variable_name) .
+result(?arithmetic-1) :- fact(?arithmetic) .
+
+@export result :- csv {} .
diff --git a/resources/testcases/regression/parsing/variable-names/run/result.csv b/resources/testcases/regression/parsing/variable-names/run/result.csv
@@ -0,0 +1,2 @@
+0
+1