Commit485767a

authored

Merge pull request#78 from cessen/grapheme_bench

Add grapheme iteration benchmarks for various languages.

2 parentsb82ed4d +b1765ec commit485767aCopy full SHA for 485767a

File tree

12 files changed

+3619

-1

lines changed

Cargo.toml
benches
- graphemes.rs
- texts

12 files changed

+3619

-1

lines changed

`‎Cargo.toml`

Lines changed: 6 additions & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -16,10 +16,15 @@ This crate provides Grapheme Cluster, Word and Sentence boundaries`
`16`	`16`	`according to Unicode Standard Annex #29 rules.`
`17`	`17`	`"""`
`18`	`18`
`19`		`-exclude = ["target/","Cargo.lock","scripts/tmp",".txt" ]`
	`19`	`+exclude = ["target/","Cargo.lock","scripts/tmp","benches/texts/","*.txt", ]`
`20`	`20`
`21`	`21`	`[features]`
`22`	`22`	`no_std = []# This is a no-op, preserved for backward compatibility only.`
`23`	`23`
`24`	`24`	`[dev-dependencies]`
`25`	`25`	`quickcheck ="0.7"`
	`26`	`+bencher ="0.1"`
	`27`	`+`
	`28`	`+[[bench]]`
	`29`	`+name ="graphemes"`
	`30`	`+harness =false`

`‎benches/graphemes.rs`

Lines changed: 64 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,64 @@`
	`1`	`+#[macro_use]`
	`2`	`+externcrate bencher;`
	`3`	`+externcrate unicode_segmentation;`
	`4`	`+`
	`5`	`+use bencher::Bencher;`
	`6`	`+use unicode_segmentation::UnicodeSegmentation;`
	`7`	`+use std::fs;`
	`8`	`+`
	`9`	`+fngraphemes(bench:&mutBencher,path:&str){`
	`10`	`+let text = fs::read_to_string(path).unwrap();`
	`11`	`+ bench.iter(\|\|{`
	`12`	`+for ginUnicodeSegmentation::graphemes(&*text,true){`
	`13`	`+ bencher::black_box(g);`
	`14`	`+}`
	`15`	`+});`
	`16`	`+`
	`17`	`+ bench.bytes = text.len()asu64;`
	`18`	`+}`
	`19`	`+`
	`20`	`+fngraphemes_arabic(bench:&mutBencher){`
	`21`	`+graphemes(bench,"benches/texts/arabic.txt");`
	`22`	`+}`
	`23`	`+`
	`24`	`+fngraphemes_english(bench:&mutBencher){`
	`25`	`+graphemes(bench,"benches/texts/english.txt");`
	`26`	`+}`
	`27`	`+`
	`28`	`+fngraphemes_hindi(bench:&mutBencher){`
	`29`	`+graphemes(bench,"benches/texts/hindi.txt");`
	`30`	`+}`
	`31`	`+`
	`32`	`+fngraphemes_japanese(bench:&mutBencher){`
	`33`	`+graphemes(bench,"benches/texts/japanese.txt");`
	`34`	`+}`
	`35`	`+`
	`36`	`+fngraphemes_korean(bench:&mutBencher){`
	`37`	`+graphemes(bench,"benches/texts/korean.txt");`
	`38`	`+}`
	`39`	`+`
	`40`	`+fngraphemes_mandarin(bench:&mutBencher){`
	`41`	`+graphemes(bench,"benches/texts/mandarin.txt");`
	`42`	`+}`
	`43`	`+`
	`44`	`+fngraphemes_russian(bench:&mutBencher){`
	`45`	`+graphemes(bench,"benches/texts/russian.txt");`
	`46`	`+}`
	`47`	`+`
	`48`	`+fngraphemes_source_code(bench:&mutBencher){`
	`49`	`+graphemes(bench,"benches/texts/source_code.txt");`
	`50`	`+}`
	`51`	`+`
	`52`	`+benchmark_group!(`
	`53`	`+ benches,`
	`54`	`+ graphemes_arabic,`
	`55`	`+ graphemes_english,`
	`56`	`+ graphemes_hindi,`
	`57`	`+ graphemes_japanese,`
	`58`	`+ graphemes_korean,`
	`59`	`+ graphemes_mandarin,`
	`60`	`+ graphemes_russian,`
	`61`	`+ graphemes_source_code,`
	`62`	`+);`
	`63`	`+`
	`64`	`+benchmark_main!(benches);`