From ea300e9081cada562e714d1d2a218b88ce9d32a9 Mon Sep 17 00:00:00 2001
From: Yuri Astrakhan <YuriAstrakhan@gmail.com>
Date: Sat, 10 Feb 2024 12:44:20 -0500
Subject: [PATCH] Normalize unicode refs

Just to keep them a bit more consistent.

Note that there are a lot of code duplications here - but I do not know if they are worth consolidating, and/or any perf implications.
---
 lib/oxigraph/tests/store.rs |  2 +-
 lib/oxrdf/src/literal.rs    |  4 ++--
 lib/oxrdf/src/parser.rs     |  4 ++--
 lib/oxrdf/src/variable.rs   |  2 +-
 lib/oxrdfxml/src/utils.rs   | 10 +++++-----
 lib/spargebra/src/parser.rs |  6 +++---
 6 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/lib/oxigraph/tests/store.rs b/lib/oxigraph/tests/store.rs
index 48ff00f1..a3c5fe03 100644
--- a/lib/oxigraph/tests/store.rs
+++ b/lib/oxigraph/tests/store.rs
@@ -78,7 +78,7 @@ fn quads(graph_name: impl Into<GraphNameRef<'static>>) -> Vec<QuadRef<'static>>
         QuadRef::new(
             paris,
             name,
-            LiteralRef::new_language_tagged_literal_unchecked("la ville lumi\u{e8}re", "fr"),
+            LiteralRef::new_language_tagged_literal_unchecked("la ville lumi\u{E8}re", "fr"),
             graph_name,
         ),
         QuadRef::new(paris, country, france, graph_name),
diff --git a/lib/oxrdf/src/literal.rs b/lib/oxrdf/src/literal.rs
index 0872fab5..13ab07fe 100644
--- a/lib/oxrdf/src/literal.rs
+++ b/lib/oxrdf/src/literal.rs
@@ -622,11 +622,11 @@ pub fn print_quoted_str(string: &str, f: &mut impl Write) -> fmt::Result {
             '\u{08}' => f.write_str("\\b"),
             '\t' => f.write_str("\\t"),
             '\n' => f.write_str("\\n"),
-            '\u{0c}' => f.write_str("\\f"),
+            '\u{0C}' => f.write_str("\\f"),
             '\r' => f.write_str("\\r"),
             '"' => f.write_str("\\\""),
             '\\' => f.write_str("\\\\"),
-            '\0'..='\u{1f}' | '\u{7f}' => write!(f, "\\u{:04X}", u32::from(c)),
+            '\0'..='\u{1F}' | '\u{7F}' => write!(f, "\\u{:04X}", u32::from(c)),
             _ => f.write_char(c),
         }?;
     }
diff --git a/lib/oxrdf/src/parser.rs b/lib/oxrdf/src/parser.rs
index a531a86e..bcadd1ad 100644
--- a/lib/oxrdf/src/parser.rs
+++ b/lib/oxrdf/src/parser.rs
@@ -256,10 +256,10 @@ fn read_literal(s: &str) -> Result<(Literal, &str), TermParseError> {
                     if let Some(c) = chars.next() {
                         value.push(match c {
                             't' => '\t',
-                            'b' => '\u{8}',
+                            'b' => '\u{08}',
                             'n' => '\n',
                             'r' => '\r',
-                            'f' => '\u{C}',
+                            'f' => '\u{0C}',
                             '"' => '"',
                             '\'' => '\'',
                             '\\' => '\\',
diff --git a/lib/oxrdf/src/variable.rs b/lib/oxrdf/src/variable.rs
index 36dcb3e4..c2d89ca9 100644
--- a/lib/oxrdf/src/variable.rs
+++ b/lib/oxrdf/src/variable.rs
@@ -187,7 +187,7 @@ fn validate_variable_identifier(id: &str) -> Result<(), VariableNameParseError>
         match c {
             '0'..='9'
             | '\u{00B7}'
-            | '\u{00300}'..='\u{036F}'
+            | '\u{0300}'..='\u{036F}'
             | '\u{203F}'..='\u{2040}'
             | '_'
             | 'A'..='Z'
diff --git a/lib/oxrdfxml/src/utils.rs b/lib/oxrdfxml/src/utils.rs
index b8fb2447..0483488d 100644
--- a/lib/oxrdfxml/src/utils.rs
+++ b/lib/oxrdfxml/src/utils.rs
@@ -5,11 +5,11 @@ pub fn is_name_start_char(c: char) -> bool {
         | 'A'..='Z'
         | '_'
         | 'a'..='z'
-        | '\u{C0}'..='\u{D6}'
-        | '\u{D8}'..='\u{F6}'
-        | '\u{F8}'..='\u{2FF}'
-        | '\u{370}'..='\u{37D}'
-        | '\u{37F}'..='\u{1FFF}'
+        | '\u{00C0}'..='\u{00D6}'
+        | '\u{00D8}'..='\u{00F6}'
+        | '\u{00F8}'..='\u{02FF}'
+        | '\u{0370}'..='\u{037D}'
+        | '\u{037F}'..='\u{1FFF}'
         | '\u{200C}'..='\u{200D}'
         | '\u{2070}'..='\u{218F}'
         | '\u{2C00}'..='\u{2FEF}'
diff --git a/lib/spargebra/src/parser.rs b/lib/spargebra/src/parser.rs
index 8e5d7445..38496387 100644
--- a/lib/spargebra/src/parser.rs
+++ b/lib/spargebra/src/parser.rs
@@ -2019,13 +2019,13 @@ parser! {
         rule STRING_LITERAL1() -> String = "'" l:$((STRING_LITERAL1_simple_char() / ECHAR() / UCHAR())*) "'" {?
              unescape_string(l)
         }
-        rule STRING_LITERAL1_simple_char() = !['\u{27}' | '\u{5C}' | '\u{A}' | '\u{D}'] [_]
+        rule STRING_LITERAL1_simple_char() = !['\u{27}' | '\u{5C}' | '\u{0A}' | '\u{0D}'] [_]
 
 
         rule STRING_LITERAL2() -> String = "\"" l:$((STRING_LITERAL2_simple_char() / ECHAR() / UCHAR())*) "\"" {?
              unescape_string(l)
         }
-        rule STRING_LITERAL2_simple_char() = !['\u{22}' | '\u{5C}' | '\u{A}' | '\u{D}'] [_]
+        rule STRING_LITERAL2_simple_char() = !['\u{22}' | '\u{5C}' | '\u{0A}' | '\u{0D}'] [_]
 
         rule STRING_LITERAL_LONG1() -> String = "'''" l:$(STRING_LITERAL_LONG1_inner()*) "'''" {?
              unescape_string(l)
@@ -2045,7 +2045,7 @@ parser! {
 
         rule NIL() = "(" WS()* ")"
 
-        rule WS() = quiet! { ['\u{20}' | '\u{9}' | '\u{D}' | '\u{A}'] }
+        rule WS() = quiet! { ['\u{20}' | '\u{09}' | '\u{0D}' | '\u{0A}'] }
 
         rule ANON() = "[" WS()* "]"