fix[display]: escape strings (#5551)

Signed-off-by: Joe Isaacs <[email protected]>

Author: joseph-isaacs

vortex-dtype/src/field_names.rs

@@ -7,6 +7,7 @@ use std::ops::Index;
 use std::sync::Arc;
 
 use itertools::Itertools;
+use vortex_utils::aliases::StringEscape;
 
 /// A name for a field in a struct.
 #[derive(Clone, Debug, PartialEq, Eq, PartialOrd, Ord, Hash)]
@@ -43,7 +44,7 @@ impl<'de> serde::de::Deserialize<'de> for FieldName {
 
 impl fmt::Display for FieldName {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(f, "{}", self.0)
+        write!(f, "{}", StringEscape(self.0.as_ref()))
     }
 }
 

vortex-scalar/src/utf8.rs

@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright the Vortex contributors
 
+use std::cmp;
+use std::fmt;
 use std::fmt::Display;
 use std::fmt::Formatter;
 use std::sync::Arc;
@@ -14,6 +16,7 @@ use vortex_error::VortexExpect as _;
 use vortex_error::VortexResult;
 use vortex_error::vortex_bail;
 use vortex_error::vortex_err;
+use vortex_utils::aliases::StringEscape;
 
 use crate::InnerScalarValue;
 use crate::Scalar;
@@ -30,10 +33,10 @@ pub struct Utf8Scalar<'a> {
 }
 
 impl Display for Utf8Scalar<'_> {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+    fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
         match &self.value {
             None => write!(f, "null"),
-            Some(v) => write!(f, "\"{}\"", v.as_str()),
+            Some(v) => write!(f, "\"{}\"", StringEscape(v.as_str())),
         }
     }
 }
@@ -45,13 +48,13 @@ impl PartialEq for Utf8Scalar<'_> {
 }
 
 impl PartialOrd for Utf8Scalar<'_> {
-    fn partial_cmp(&self, other: &Self) -> Option<std::cmp::Ordering> {
+    fn partial_cmp(&self, other: &Self) -> Option<cmp::Ordering> {
         Some(self.cmp(other))
     }
 }
 
 impl Ord for Utf8Scalar<'_> {
-    fn cmp(&self, other: &Self) -> std::cmp::Ordering {
+    fn cmp(&self, other: &Self) -> cmp::Ordering {
         self.value.cmp(&other.value)
     }
 }

vortex-utils/src/aliases/mod.rs

@@ -13,6 +13,8 @@ pub mod dash_map;
 pub mod hash_map;
 /// HashSet type aliases and re-exports.
 pub mod hash_set;
+mod string_escape;
 
 /// The default hash builder used by HashMap and HashSet.
 pub use hashbrown::DefaultHashBuilder;
+pub use string_escape::StringEscape;

vortex-utils/src/aliases/string_escape.rs

@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright the Vortex contributors
+
+use std::fmt::Debug;
+use std::fmt::Display;
+use std::fmt::Formatter;
+
+/// A wrapper around a string that implements `Display` for a string while removing all unicode
+/// escape sequences.
+#[derive(Debug)]
+pub struct StringEscape<'a>(pub &'a str);
+
+impl Display for StringEscape<'_> {
+    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+        write!(f, "{}", self.0.escape_debug())
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::aliases::string_escape::StringEscape;
+
+    #[test]
+    fn test_no_escape_string() {
+        let s = StringEscape("hello");
+        assert_eq!(s.to_string(), "hello");
+    }
+
+    #[test]
+    fn test_heart_string() {
+        let s = StringEscape("hello ♡");
+        assert_eq!(s.to_string(), "hello ♡");
+    }
+
+    #[test]
+    fn test_string_escape() {
+        let s = StringEscape("\"\n\t\r\\\0\x1f\x7f");
+        assert_eq!(s.to_string(), "\\\"\\n\\t\\r\\\\\\0\\u{1f}\\u{7f}");
+    }
+}