-
Notifications
You must be signed in to change notification settings - Fork 93
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
benchmarks: start work on a more curated set of benchmarks
This is a WIP for now.
- Loading branch information
1 parent
dd84b6d
commit 3ed2c38
Showing
4 changed files
with
154 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,45 @@ | ||
analysis = ''' | ||
This is a WIP for building our a curated set of Aho-Corasick benchmarks. | ||
The next step is not to actually add more benchmarks, but to hook up more | ||
Aho-Corasick libraries. There are a lot of them and it's a fair bit of work to | ||
do. | ||
''' | ||
|
||
[[bench]] | ||
model = "count" | ||
name = "sherlock" | ||
regex = [ | ||
'Sherlock Holmes', | ||
'John Watson', | ||
'Irene Adler', | ||
'Inspector Lestrade', | ||
'Professor Moriarty', | ||
] | ||
haystack = { path = "opensubtitles/en-sampled.txt" } | ||
count = 714 | ||
engines = [ | ||
"rust/aho-corasick/default/standard", | ||
"rust/aho-corasick/default/leftmost-first", | ||
"daachorse/bytewise/standard", | ||
"daachorse/bytewise/leftmost-first", | ||
"naive/rust/memchr/memmem", | ||
] | ||
|
||
[[bench]] | ||
model = "count" | ||
name = "dictionary-15" | ||
regex = { path = "dictionary/english/length-15.txt", per-line = "pattern" } | ||
haystack = { path = "opensubtitles/en-sampled.txt" } | ||
count = 15 | ||
engines = [ | ||
"rust/aho-corasick/default/standard", | ||
"rust/aho-corasick/default/overlapping", | ||
"rust/aho-corasick/default/leftmost-first", | ||
"daachorse/bytewise/standard", | ||
"daachorse/bytewise/overlapping", | ||
"daachorse/bytewise/leftmost-first", | ||
"naive/rust/memchr/memmem", | ||
] | ||
analysis = ''' | ||
Looks for occurrences of 2,663 words of length at least 15. | ||
''' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters