tinystr - cargo Package Compare versions

Comparing version 0.7.5 to 0.7.6

.cargo_vcs_info.json

 {
   "git": {
-    "sha1": "8b080b3753b91c58113c47c99108185d0614499c"
+    "sha1": "55cd12ebb25c6261492e1e3dfa2e6453c54dde31"
   },
   "path_in_vcs": "utils/tinystr"
 }

Cargo.toml

@@ -16,3 +16,3 @@ # THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
 name = "tinystr"
-version = "0.7.5"
+version = "0.7.6"
 authors = ["The ICU4X Project Developers"]
@@ -39,3 +39,3 @@ include = [
 categories = ["data-structures"]
-license-file = "LICENSE"
+license = "Unicode-3.0"
 repository = "https://github.com/unicode-org/icu4x"
@@ -82,3 +82,3 @@
 [dependencies.databake]
-version = "0.1.7"
+version = "0.1.8"
 optional = true
@@ -92,3 +92,3 @@ default-features = false
 [dependencies.serde]
-version = "1.0.123"
+version = "1.0.110"
 features = ["alloc"]
@@ -99,3 +99,3 @@ optional = true
 [dependencies.zerovec]
-version = "0.10.1"
+version = "0.10.2"
 optional = true
@@ -105,6 +105,6 @@ default-features = false
 [dev-dependencies.bincode]
-version = "1.3"
+version = "1.3.1"
 
 [dev-dependencies.postcard]
-version = "1.0.0"
+version = "1.0.1"
 features = ["use-std"]
@@ -114,9 +114,7 @@ default-features = false
 [dev-dependencies.rand]
-version = "0.8.5"
-features = ["small_rng"]
+version = "0.8"
 
 [dev-dependencies.serde_json]
-version = "1.0"
+version = "1.0.45"
 features = ["alloc"]
-default-features = false
 
@@ -130,2 +128,2 @@ [features]
 [target."cfg(not(target_arch = \"wasm32\"))".dev-dependencies.criterion]
-version = "0.4"
+version = "0.5.0"

LICENSE

@@ -5,3 +5,3 @@ UNICODE LICENSE V3
 
-Copyright © 2020-2023 Unicode, Inc.
+Copyright © 2020-2024 Unicode, Inc.
 
@@ -42,2 +42,4 @@ NOTICE TO USER: Carefully read the following legal agreement. BY
 
+SPDX-License-Identifier: Unicode-3.0
+
 —
@@ -44,0 +46,0 @@

src/ascii.rs

@@ -25,2 +25,33 @@ // This file is part of ICU4X. For terms of use, please see the file
 
+    /// Creates a `TinyAsciiStr<N>` from a byte slice, replacing invalid bytes.
+    ///
+    /// Null and non-ASCII bytes (i.e. those outside the range `0x01..=0x7F`)
+    /// will be replaced with the '?' character.
+    ///
+    /// The input slice will be truncated if its length exceeds `N`.
+    pub const fn from_bytes_lossy(bytes: &[u8]) -> Self {
+        const QUESTION: u8 = b'?';
+        let mut out = [0; N];
+        let mut i = 0;
+        // Ord is not available in const, so no `.min(N)`
+        let len = if bytes.len() > N { N } else { bytes.len() };
+
+        // Indexing is protected by the len check above
+        #[allow(clippy::indexing_slicing)]
+        while i < len {
+            let b = bytes[i];
+            if b > 0 && b < 0x80 {
+                out[i] = b;
+            } else {
+                out[i] = QUESTION;
+            }
+            i += 1;
+        }
+
+        Self {
+            // SAFETY: `out` only contains ASCII bytes and has same size as `self.bytes`
+            bytes: unsafe { AsciiByte::to_ascii_byte_array(&out) },
+        }
+    }
+
     /// Attempts to parse a fixed-length byte array to a `TinyAsciiStr`.
@@ -524,3 +555,3 @@ ///
                 unsafe {
-                    $self.bytes[i] = core::mem::transmute(
+                    $self.bytes[i] = core::mem::transmute::<u8, AsciiByte>(
                         ($self.bytes[i] as u8).$later_char_to()
@@ -534,3 +565,3 @@ );
                 $self.bytes[0] = unsafe {
-                    core::mem::transmute(($self.bytes[0] as u8).$first_char_to())
+                    core::mem::transmute::<u8, AsciiByte>(($self.bytes[0] as u8).$first_char_to())
                 };
@@ -631,3 +662,3 @@ )?
     #[inline]
-    fn from_str(s: &str) -> Result<Self, TinyStrError> {
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
         Self::from_str(s)
@@ -988,2 +1019,20 @@ }
     }
+
+    #[test]
+    fn lossy_constructor() {
+        assert_eq!(TinyAsciiStr::<4>::from_bytes_lossy(b"").as_str(), "");
+        assert_eq!(
+            TinyAsciiStr::<4>::from_bytes_lossy(b"oh\0o").as_str(),
+            "oh?o"
+        );
+        assert_eq!(TinyAsciiStr::<4>::from_bytes_lossy(b"\0").as_str(), "?");
+        assert_eq!(
+            TinyAsciiStr::<4>::from_bytes_lossy(b"toolong").as_str(),
+            "tool"
+        );
+        assert_eq!(
+            TinyAsciiStr::<4>::from_bytes_lossy(&[b'a', 0x80, 0xFF, b'1']).as_str(),
+            "a??1"
+        );
+    }
 }

src/int_ops.rs

@@ -30,3 +30,3 @@ // This file is part of ICU4X. For terms of use, please see the file
     pub const fn from_ascii_bytes<const N: usize>(src: &[AsciiByte; N]) -> Self {
-        Self::from_bytes::<N>(unsafe { core::mem::transmute(src) })
+        Self::from_bytes::<N>(unsafe { core::mem::transmute::<&[AsciiByte; N], &[u8; N]>(src) })
     }
@@ -188,3 +188,3 @@
     pub const fn from_ascii_bytes<const N: usize>(src: &[AsciiByte; N]) -> Self {
-        Self::from_bytes::<N>(unsafe { core::mem::transmute(src) })
+        Self::from_bytes::<N>(unsafe { core::mem::transmute::<&[AsciiByte; N], &[u8; N]>(src) })
     }
@@ -191,0 +191,0 @@

src/lib.rs

@@ -54,3 +54,3 @@ // This file is part of ICU4X. For terms of use, please see the file
 
-// https://github.com/unicode-org/icu4x/blob/main/docs/process/boilerplate.md#library-annotations
+// https://github.com/unicode-org/icu4x/blob/main/documents/process/boilerplate.md#library-annotations
 #![cfg_attr(not(any(test, feature = "std")), no_std)]
@@ -57,0 +57,0 @@ #![cfg_attr(

No alert changes

No metric changes