Optimize unknown alpha paths

.github/workflows/rust.yml

@@ -1,7 +1,7 @@
 name: Lint & Test
 on:
   pull_request:
-    types: [opened, edited, reopened, synchronize]
+    types: [ opened, edited, reopened, synchronize ]
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
@@ -11,11 +11,11 @@ jobs:
   test:
     strategy:
       matrix:
-        platform: [ubuntu-latest, macos-latest, windows-latest]
+        platform: [ ubuntu-latest, macos-latest, windows-latest ]
     runs-on: ${{ matrix.platform }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Install Rust Stable
         uses: dtolnay/rust-toolchain@stable

CHANGELOG.md

@@ -1,33 +1,55 @@
 # Changelog
-All notable changes to this project will be documented in this file.
 
+All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
 
+## [0.5.0] - 2025-06-22
+
+### Changed
+
+- Updated deps.
+- Updated CI config.
+- Updated documentation.
+- Updated to Rust 2024 edition.
+- Optimized parsing performance for unknown alpha paths by pre-looking date part lookup prior to parsing.
+
 ## [0.4.0] - 2023-12-29
+
 ### Changed
+
 - Updated deps.
 - Updated CI config.
 - Update + Add documentation.
 - Add addition supported date format `%A %B %e %Y` (e.g. `Sunday, April 18th, 2021`).
 
 ## [0.3.0] - 2021-11-14
+
 ### Added
+
 - Serde deserialize_with helper functions.
 - Examples directory
 
 ## [0.2.0] - 2021-11-09
+
 ### Changed
+
 - Fixed Cargo.toml categories
 
 ## [0.1.0] - 2021-11-09
+
 ### Added
+
 - Initial Release
 
 [Unreleased]: https://github.com/rust-playground/anydate/compare/v0.4.0...HEAD
+
 [0.4.0]: https://github.com/rust-playground/anydate/compare/v0.3.0...v0.4.0
+
 [0.3.0]: https://github.com/rust-playground/anydate/compare/v0.2.0...v0.3.0
+
 [0.2.0]: https://github.com/rust-playground/anydate/compare/v0.1.0...v0.2.0
+
 [0.1.0]: https://github.com/rust-playground/anydate/commit/4ac9022aeeb9d2911a763651f70987cb8d98d47d

Cargo.toml

@@ -1,8 +1,8 @@
 [package]
 name = "anydate"
 description = "Date & DateTime string parser"
-version = "0.4.0"
-edition = "2021"
+version = "0.5.0"
+edition = "2024"
 authors = ["Dean Karn <dean.karn@gmail.com>"]
 license = "MIT OR Apache-2.0"
 readme = "README.md"
@@ -19,12 +19,12 @@ harness = false
 name = "bench"
 
 [dependencies]
-chrono = { version = "0.4.31", default-features = false, features = ["std"] }
-serde = {version = "1.0.192", features = ["derive"], optional = true }
-thiserror = "1.0.50"
+chrono = { version = "0.4.40", default-features = false, features = ["std"] }
+serde = { version = "1.0.218", features = ["derive"], optional = true }
+thiserror = "2.0.11"
 
 [dev-dependencies]
-criterion = { version = "0.5.1", features = ["html_reports"] }
+criterion = { version = "0.6.0", features = ["html_reports"] }
 serde_json = "1.0.108"
 
 [lib]

README.md

@@ -1,6 +1,7 @@
 # anydate   [![Latest Version]][crates.io]
 
 [Latest Version]: https://img.shields.io/crates/v/anydate.svg
+
 [crates.io]: https://crates.io/crates/anydate
 
 This crate is used to parse an unknown DateTime or Date format into a normalized version.
@@ -11,9 +12,10 @@ Any significant changes to anydate are documented in
 the [`CHANGELOG.md`](https://github.com/rust-playground/anydate/blob/main/CHANGELOG.md) file.
 
 ## Usage
+
 ```toml
 [dependencies]
-anydate = "0.4"
+anydate = "0.5"
 ```
 
 ### Features
@@ -25,6 +27,7 @@ Optional features:
 [`serde`]: https://github.com/serde-rs/serde
 
 ### Example usages
+
 ```rust
 fn main() -> Result<(), Box<dyn std::error::Error>> {
     // see parse_utc() for convenience conversion to UTC

src/date.rs

@@ -30,20 +30,33 @@ pub(crate) fn parse_with_alpha(s: &str) -> Result<NaiveDate, Error> {
 
 fn parse_naive_dates(s: &str) -> Result<NaiveDate, Error> {
     // Date parse formats
-    const PARSE_FORMATS: &[&str] = &[
-        "%Y-%m-%d",
-        "%Y/%m/%d",
-        "%Y.%m.%d",
-        "%m/%d/%y",
-        "%m/%d/%Y",
-        "%m.%d.%y",
-        "%m.%d.%Y",
-        "%Y-%b-%d",
-        "%d %B %y",
-        "%d %B %Y",
-        "%Y年%m月%d日",
-    ];
-    PARSE_FORMATS
+    const PARSE_FORMATS_DASHES: &[&str] = &["%Y-%m-%d", "%Y-%b-%d"];
+
+    const PARSE_FORMATS_SLASHES: &[&str] = &["%Y/%m/%d", "%m/%d/%y", "%m/%d/%Y"];
+
+    const PARSE_FORMATS_DOT: &[&str] = &["%Y.%m.%d", "%m.%d.%y", "%m.%d.%Y"];
+
+    const PARSE_FORMATS_SPACE: &[&str] = &["%d %B %y", "%d %B %Y"];
+
+    const PARSE_FORMATS_REMAINING: &[&str] = &["%Y年%m月%d日"];
+
+    for c in s.chars() {
+        if !c.is_alphanumeric() {
+            return match c {
+                '-' => PARSE_FORMATS_DASHES,
+                '/' => PARSE_FORMATS_SLASHES,
+                '.' => PARSE_FORMATS_DOT,
+                ' ' => PARSE_FORMATS_SPACE,
+                _ => break,
+            }
+            .iter()
+            .map(|fmt| NaiveDate::parse_from_str(s, fmt))
+            .find_map(Result::ok)
+            .map_or_else(|| Err(Error::InvalidDate), Ok);
+        }
+    }
+
+    PARSE_FORMATS_REMAINING
         .iter()
         .map(|fmt| NaiveDate::parse_from_str(s, fmt))
         .find_map(Result::ok)
@@ -114,6 +127,7 @@ mod tests {
                 *expected,
                 parse(input)?
                     .and_time(NaiveTime::from_num_seconds_from_midnight_opt(0, 0).unwrap())
+                    .and_utc()
                     .timestamp_nanos_opt()
                     .unwrap()
             );

src/datetime.rs

@@ -138,31 +138,48 @@ fn parse_naive_datetime(s: &str) -> Result<DateTime<FixedOffset>, Error> {
 
 fn parse_utc_naive_datetime_unknown_alpha(s: &str) -> Result<DateTime<FixedOffset>, Error> {
     // DateTimes without timezone info
-    const PARSE_FORMATS: &[&str] = &[
+    const PARSE_FORMATS_DASHES: &[&str] = &[
         "%Y-%m-%d %H:%M:%S%.f",
         "%Y-%m-%d %H:%M:%S",
         "%Y-%m-%d %H:%M",
+        "%Y-%m-%d %I:%M:%S %P",
+        "%Y-%m-%d %I:%M %P",
+    ];
+
+    const PARSE_FORMATS_SLASHES: &[&str] = &[
         "%m/%d/%y %H:%M:%S",
         "%m/%d/%y %H:%M",
         "%m/%d/%y %H:%M:%S%.f",
         "%m/%d/%Y %H:%M:%S",
         "%m/%d/%Y %H:%M",
         "%m/%d/%Y %H:%M:%S%.f",
-        "%y%m%d %H:%M:%S",
         "%Y/%m/%d %H:%M:%S",
         "%Y/%m/%d %H:%M",
         "%Y/%m/%d %H:%M:%S%.f",
-        "%Y-%m-%d %I:%M:%S %P",
-        "%Y-%m-%d %I:%M %P",
         "%m/%d/%y %I:%M:%S %P",
         "%m/%d/%y %I:%M %P",
         "%m/%d/%Y %I:%M:%S %P",
         "%m/%d/%Y %I:%M %P",
         "%Y/%m/%d %I:%M:%S %P",
         "%Y/%m/%d %I:%M %P",
-        "%Y年%m月%d日%H时%M分%S秒",
     ];
-    parse_utc_naive_datetime(s, PARSE_FORMATS)
+
+    const PARSE_FORMATS_REMAINING: &[&str] = &["%y%m%d %H:%M:%S", "%Y年%m月%d日%H时%M分%S秒"];
+
+    for c in s.chars() {
+        if !c.is_alphanumeric() {
+            return parse_utc_naive_datetime(
+                s,
+                match c {
+                    '-' => PARSE_FORMATS_DASHES,
+                    '/' => PARSE_FORMATS_SLASHES,
+                    _ => break,
+                },
+            );
+        }
+    }
+
+    parse_utc_naive_datetime(s, PARSE_FORMATS_REMAINING)
 }
 
 fn parse_utc_naive_datetime_alpha_prefix(s: &str) -> Result<DateTime<FixedOffset>, Error> {
@@ -211,9 +228,9 @@ fn parse_utc_naive_datetime(s: &str, formats: &[&str]) -> Result<DateTime<FixedO
         )
 }
 
-// last ditch effort, timezone abbreviation can't 100% relied upon.
+// last ditch effort, timezone abbreviation can't 100% be relied upon.
 //
-// It is not possible to reliably convert from an abbreviation to an offset, for example CDT can
+// It is not possible to reliably convert from an abbreviation to an offset; for example, CDT can
 // mean either Central Daylight Time (North America) or China Daylight Time.
 //
 // list sourced from https://www.utctime.net/time-zone-abbreviations
@@ -231,9 +248,9 @@ fn parse_timezone_abbreviation_unknown_alpha(s: &str) -> Result<DateTime<FixedOf
     )
 }
 
-// last ditch effort, timezone abbreviation can't 100% relied upon.
+// last ditch effort, timezone abbreviation can't 100% be relied upon.
 //
-// It is not possible to reliably convert from an abbreviation to an offset, for example CDT can
+// It is not possible to reliably convert from an abbreviation to an offset; for example, CDT can
 // mean either Central Daylight Time (North America) or China Daylight Time.
 //
 // list sourced from https://www.utctime.net/time-zone-abbreviations

src/serde.rs

@@ -5,7 +5,7 @@ use serde::de;
 
 struct AnydateVisitor;
 
-impl<'de> de::Visitor<'de> for AnydateVisitor {
+impl de::Visitor<'_> for AnydateVisitor {
     type Value = DateTime<FixedOffset>;
 
     fn expecting(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
@@ -40,7 +40,7 @@ pub mod deserialize {
     //! println!("{:?}", dt);
     //!
     //! ```
-    use super::{de, AnydateVisitor, DateTime, FixedOffset, Utc};
+    use super::{AnydateVisitor, DateTime, FixedOffset, Utc, de};
 
     /// deserializes to a [`DateTime<FixedOffset>`]
     ///
@@ -143,7 +143,7 @@ pub mod deserialize {
                     None => {
                         assert_eq!(s.dt, None);
                     }
-                };
+                }
             }
             Ok(())
         }
@@ -197,7 +197,7 @@ pub mod deserialize {
                     None => {
                         assert_eq!(s.dt, None);
                     }
-                };
+                }
             }
             Ok(())
         }