Add parser and serializer for the OWL2 Functional-style syntax

Cargo.toml

@@ -22,6 +22,8 @@ log = {version="0.4.8"}
 oxiri="0.2.2"
 quick-xml={version="0.26.0"}
 indexmap={workspace=true}
+pest = "2.7.8"
+pest_derive = "2.7.8"
 pretty_rdf={workspace=true}
 rio_api={workspace=true}
 rio_xml={workspace=true}

src/error.rs

@@ -1,11 +1,14 @@
 //! Errors for the Horned-OWL library
 use std::fmt::{Display, Formatter};
+use std::ops::Range;
 
+use pest::RuleType;
 use thiserror::Error;
 
 #[derive(Debug)]
 pub enum Location {
     BytePosition(usize),
+    ByteSpan(Range<usize>),
     Unknown
 }
 
@@ -15,10 +18,32 @@ impl From<usize> for Location{
     }
 }
 
+impl From<Range<usize>> for Location {
+    fn from(r: Range<usize>) -> Self {
+        Location::ByteSpan(r)
+    }
+}
+
+impl From<pest::error::InputLocation> for Location {
+    fn from(l: pest::error::InputLocation) -> Self {
+        match l {
+            pest::error::InputLocation::Pos(x) => Location::BytePosition(x),
+            pest::error::InputLocation::Span((x, y)) => Location::ByteSpan(x..y),
+        }
+    }
+}
+
+impl<'i> From<pest::Span<'i>> for Location {
+    fn from(span: pest::Span<'i>) -> Self {
+        Location::ByteSpan(span.start()..span.end())
+    }
+}
+
 impl Display for Location {
     fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
         match self {
             Self::BytePosition(u) => write!(f, "Byte Position: {}", u),
+            Self::ByteSpan(r) => write!(f, "Byte Span: {} to {}", r.start, r.end),
             Self::Unknown => write!(f, "Unknown")
         }
     }
@@ -75,3 +100,10 @@ impl From<rio_xml::RdfXmlError> for HornedError {
         Self::ParserError(e.into(), Location::Unknown)
     }
 }
+
+impl<R: RuleType + 'static> From<pest::error::Error<R>> for HornedError {
+    fn from(e: pest::error::Error<R>) -> Self {
+        let location = e.location.clone().into();
+        Self::ParserError(e.into(), location)
+    }
+}

src/grammars/bcp47.pest

@@ -0,0 +1,54 @@
+// Annex III: Language Tag Grammar from BCP 47
+// (source: https://www.rfc-editor.org/bcp/bcp47.txt)
+
+BCP47_LanguageTag = ${ BCP47_LangTag | BCP47_PrivateUse | BCP47_GrandFathered }
+BCP47_LangTag     = ${
+    BCP47_Language ~ ("-" ~ BCP47_Script)? ~ ("-" ~ BCP47_Region)? ~ ("-" ~ BCP47_Variant)* ~ ("-" ~ BCP47_Extension)* ~ ("-" ~ BCP47_PrivateUse)?
+}
+
+BCP47_Language = ${
+    ASCII_ALPHA{2, 3} ~ ("-" ~ BCP47_ExtLang)?
+  | ASCII_ALPHA{4}
+  | ASCII_ALPHA{5}
+}
+
+BCP47_ExtLang       = ${ ASCII_ALPHA{3} ~ ("-" ~ ASCII_ALPHA{3}){,2} }
+BCP47_Script        = ${ ASCII_ALPHA{4} }
+BCP47_Region        = ${ ASCII_ALPHA{2} | ASCII_DIGIT{3} }
+BCP47_Variant       = ${ ASCII_ALPHANUMERIC{5, 8} | ASCII_DIGIT ~ ASCII_ALPHANUMERIC{3} }
+BCP47_Extension     = ${ BCP47_Singleton ~ ("-" ~ ASCII_ALPHANUMERIC{2, 8})+ }
+BCP47_Singleton     = @{ ASCII_DIGIT | '\u{41}'..'\u{57}' | '\u{59}'..'\u{5A}' | '\u{61}'..'\u{77}' | '\u{79}'..'\u{7A}' }
+BCP47_PrivateUse    = ${ "x" ~ ("-" ~ ASCII_ALPHANUMERIC{1, 8})+ }
+BCP47_GrandFathered = ${ BCP47_Irregular | BCP47_Regular }
+
+BCP47_Irregular = ${
+    "en-GB-oed"
+  | "i-ami"
+  | "i-bnn"
+  | "i-default"
+  | "i-enochian"
+  | "i-hak"
+  | "i-klingon"
+  | "i-lux"
+  | "i-mingo"
+  | "i-navajo"
+  | "i-pwn"
+  | "i-tao"
+  | "i-tay"
+  | "i-tsu"
+  | "sgn-BE-FR"
+  | "sgn-BE-NL"
+  | "sgn-CH-DE"
+}
+
+BCP47_Regular = ${
+    "art-lojban"
+  | "cel-gaulish"
+  | "no-bok"
+  | "no-nyn"
+  | "zh-guoyu"
+  | "zh-hakka"
+  | "zh-min"
+  | "zh-min-nan"
+  | "zh-xiang"
+}