Merge pull request #27 from hanabi1224/use_hashmap_instead_of_bin_search

Use hashmap instead of binary search

.gitignore

@@ -1,14 +1,111 @@
-# Compiled files
-*.o
-*.so
-*.rlib
-*.dll
 
-# Executables
-*.exe
+# Created by https://www.gitignore.io/api/rust,code,intellij+all
+# Edit at https://www.gitignore.io/?templates=rust,code,intellij+all
 
+### Code ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+
+### Intellij+all ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+# JetBrains templates
+**___jb_tmp___
+
+### Intellij+all Patch ###
+# Ignores the whole .idea folder and all .iml files
+# See https://github.com/joeblau/gitignore.io/issues/186 and https://github.com/joeblau/gitignore.io/issues/360
+
+.idea/
+
+# Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023
+
+*.iml
+modules.xml
+.idea/misc.xml
+*.ipr
+
+# Sonarlint plugin
+.idea/sonarlint
+
+### Rust ###
 # Generated by Cargo
+# will have compiled files and executables
 /target/
-*~
-*.bak
+
+# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
+# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
 Cargo.lock
+
+# These are backup files generated by rustfmt
+**/*.rs.bk
+
+# End of https://www.gitignore.io/api/rust,code,intellij+all

.travis.yml

@@ -22,8 +22,8 @@ rust:
 script:
   - |
       cargo clean &&
-      cargo build &&
-      cargo test &&
+      cargo build --release &&
+      cargo test --release &&
       cargo doc -p pinyin --no-deps &&
       cargo run --example main &&
       cargo bench

Cargo.toml

@@ -9,7 +9,7 @@ repository = "https://github.com/mozillazg/rust-pinyin"
 description = "Convert Chinese to pinyin"
 documentation = "https://docs.rs/pinyin/"
 keywords = ["pinyin", "hanzi", "Chinese"]
-exclude = ["pinyin-data"]
+exclude = ["pinyin-data/*/**"]
 
 [badges]
 travis-ci = { repository = "mozillazg/rust-pinyin" }
@@ -23,9 +23,8 @@ path = "./src/bin/mk_dict.rs"
 name = "main"
 path = "./examples/main.rs"
 
-
 [dependencies]
-
+lazy_static = "1"
 
 [features]
 unstable = []

Makefile

@@ -17,7 +17,7 @@ test: lint
 
 .PHONY: lint
 lint:
-	@cargo run --bin mk_dict > src/dict.rs.new
+	@cargo run --release --bin mk_dict > src/dict.rs.new
 	@mv src/dict.rs.new src/dict.rs
 	@cargo fmt
 	@cargo clippy -- -A clippy::unreadable_literal

src/bin/mk_dict.rs

@@ -92,10 +92,8 @@ fn main() {
 
     let template = format!(
         "
-
 pub static PINYIN_MAP: [(char, &str); {}] = {:?};
 pub static PHONETIC_SYMBOL_MAP: [(char, &str); {}] = {:?};
-
     ",
         pinyin_map.len(),
         pinyin_map,

src/integer_hasher.rs

@@ -0,0 +1,32 @@
+use std::collections::HashMap;
+use std::hash::{BuildHasherDefault, Hasher};
+
+pub struct IntegerHasher {
+    hash: u64,
+}
+
+impl Default for IntegerHasher {
+    #[inline]
+    fn default() -> IntegerHasher {
+        IntegerHasher { hash: 0 }
+    }
+}
+
+impl Hasher for IntegerHasher {
+    #[inline]
+    fn finish(&self) -> u64 {
+        self.hash
+    }
+
+    #[inline]
+    fn write(&mut self, bytes: &[u8]) {
+        let mut hash: u64 = 0;
+        for (i, byte) in bytes.iter().enumerate() {
+            hash += u64::from(*byte) << (8 * i);
+        }
+
+        self.hash = hash;
+    }
+}
+
+pub type IntegerHashMap<K, V> = HashMap<K, V, BuildHasherDefault<IntegerHasher>>;

src/lib.rs

@@ -55,9 +55,15 @@
 //! }
 //! ```
 
+#[macro_use]
+extern crate lazy_static;
+
 mod dict;
+pub mod integer_hasher;
+mod pinyin_map;
 
-pub use dict::{PHONETIC_SYMBOL_MAP, PINYIN_MAP};
+pub use dict::PHONETIC_SYMBOL_MAP;
+pub use pinyin_map::PINYIN_HASHMAP;
 
 // 声母表
 const _INITIALS: [&str; 21] = [
@@ -199,20 +205,21 @@ fn apply_style(pys: Vec<String>, a: &Args) -> Vec<String> {
 }
 
 fn single_pinyin(c: char, a: &Args) -> Vec<String> {
-    let ret: Vec<String> = PINYIN_MAP
-        .binary_search_by_key(&c, |&(k, _)| k)
-        .map(|index| {
-            let pinyin_list = PINYIN_MAP[index].1.split(',').collect::<Vec<&str>>();
-            if pinyin_list.is_empty() || a.heteronym {
-                pinyin_list
+    let ret: Vec<String> = match PINYIN_HASHMAP.get(&c) {
+        Some(candidates_str) => {
+            let candidates = candidates_str.split(',').collect::<Vec<&str>>();
+            if candidates.is_empty() || a.heteronym {
+                candidates
                     .iter()
-                    .map(|pinyin| pinyin.to_string())
+                    .map(std::string::ToString::to_string)
                     .collect::<Vec<String>>()
             } else {
-                vec![pinyin_list[0].to_string()]
+                vec![candidates[0].to_string()]
             }
-        })
-        .unwrap_or_default();
+        }
+        None => vec![],
+    };
+
     apply_style(ret, a)
 }
 

src/pinyin_map.rs

@@ -0,0 +1,7 @@
+use dict::PINYIN_MAP;
+use integer_hasher::IntegerHashMap;
+
+lazy_static! {
+    pub static ref PINYIN_HASHMAP: IntegerHashMap<char, &'static str> =
+        PINYIN_MAP.iter().cloned().collect();
+}

tests/integer_hasher.rs

@@ -0,0 +1,26 @@
+extern crate pinyin;
+use pinyin::integer_hasher::IntegerHasher;
+use std::hash::Hasher;
+
+#[test]
+fn test_integer_hasher_1() {
+    test_integer_hasher_inner(20464028);
+}
+
+#[test]
+fn test_integer_hasher_2() {
+    test_integer_hasher_inner(0);
+}
+
+#[test]
+fn test_integer_hasher_3() {
+    test_integer_hasher_inner(2046);
+}
+
+fn test_integer_hasher_inner(i: u64) {
+    let mut _hasher = IntegerHasher::default();
+    let expected: u64 = i;
+    _hasher.write_u64(expected);
+    let ret = _hasher.finish();
+    assert_eq!(expected, ret);
+}