Vectorscan add to rebar

.vim/coc-settings.json

@@ -2,6 +2,7 @@
   "rust-analyzer.linkedProjects": [
     "byob/runner/Cargo.toml",
     "engines/hyperscan/Cargo.toml",
+    "engines/vectorscan/Cargo.toml",
     "engines/icu/Cargo.toml",
     "engines/pcre2/Cargo.toml",
     "engines/re2/Cargo.toml",

Cargo.toml

@@ -30,6 +30,7 @@ members = [
 exclude = [
   "byob/runner",
   "engines/hyperscan",
+  "engines/vectorscan",
   "engines/icu",
   "engines/pcre2",
   "engines/re2",

benchmarks/definitions/curated/01-literal.toml

@@ -42,6 +42,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -70,6 +71,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -98,6 +100,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -127,6 +130,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -158,6 +162,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',

benchmarks/definitions/curated/02-literal-alternate.toml

@@ -72,6 +72,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -100,6 +101,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -128,6 +130,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -157,6 +160,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -188,6 +192,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',

benchmarks/definitions/curated/03-date.toml

@@ -52,6 +52,7 @@ count = [
   { engine = 'dotnet.*', count = 111_825 },
   # Hyperscan reports all possible matches, so its total span count is higher.
   { engine = 'hyperscan', count = 547_662 },
+  { engine = 'vectorscan', count = 547_662 },
   # ICU doesn't provide a way to disable Unicode.
   { engine = 'icu', count = 111_825 },
   # I don't know why the count span differs here. Note that this matches
@@ -85,6 +86,7 @@ engines = [
   'dotnet/compiled',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -163,11 +165,13 @@ case-insensitive = true
 haystack = "2010-03-14"
 count = [
   { engine = 'hyperscan', count = 10 },
+  { engine = 'vectorscan', count = 10 },
   { engine = '.*', count = 5 },
 ]
 engines = [
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'pcre2',
   'pcre2/jit',

benchmarks/definitions/curated/06-cloud-flare-redos.toml

@@ -67,6 +67,7 @@ regex = '''(?:(?:"|'|\]|\}|\\|\d|(?:nan|infinity|true|false|null|undefined|symbo
 haystack = 'math x=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'
 count = [
   { engine = 'hyperscan', count = 5757 },
+  { engine = 'vectorscan', count = 5757 },
   { engine = '.*', count = 107 },
 ]
 engines = [
@@ -75,6 +76,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -97,6 +99,7 @@ regex = '.*.*=.*'
 haystack = 'x=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'
 count = [
   { engine = 'hyperscan', count = 5252 },
+  { engine = 'vectorscan', count = 5252 },
   { engine = '.*', count = 102 },
 ]
 engines = [
@@ -105,6 +108,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -127,6 +131,7 @@ regex = '.*.*=.*'
 haystack = { path = "cloud-flare-redos.txt" }
 count = [
   { engine = 'hyperscan', count = 50004999 },
+  { engine = 'vectorscan', count = 50004999 },
   { engine = '.*', count = 10000 },
 ]
 engines = [
@@ -135,6 +140,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',

benchmarks/definitions/curated/08-words.toml

@@ -46,6 +46,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -124,6 +125,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',

benchmarks/definitions/curated/09-aws-keys.toml

@@ -76,6 +76,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -123,6 +124,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'pcre2',
   'pcre2/jit',

benchmarks/definitions/curated/10-bounded-repeat.toml

@@ -42,6 +42,7 @@ regex = '[A-Za-z]{8,13}'
 haystack = { path = "opensubtitles/en-sampled.txt", line-end = 5_000 }
 count = [
   { engine = 'hyperscan', count = 3724 },
+  { engine = 'vectorscan', count = 3724 },
   { engine = '.*', count = 1833 },
 ]
 engines = [
@@ -50,6 +51,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -73,6 +75,7 @@ unicode = true
 haystack = { path = "opensubtitles/ru-sampled.txt", line-end = 5_000 }
 count = [
   { engine = 'hyperscan', count = 8570 },
+  { engine = 'vectorscan', count = 8570 },
   { engine = '.*', count = 3475 },
 ]
 engines = [
@@ -81,6 +84,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -101,6 +105,7 @@ regex = '[A-Za-z]{10}\s+[\s\S]{0,100}Result[\s\S]{0,100}\s+[A-Za-z]{10}'
 haystack = { path = "rust-src-tools-3b0d4813.txt" }
 count = [
   { engine = 'hyperscan', count = 109 },
+  { engine = 'vectorscan', count = 109 },
   { engine = '.*', count = 53 },
 ]
 engines = [
@@ -109,6 +114,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -131,6 +137,7 @@ regex = '(?:[A-Z][a-z]+\s*){10,100}'
 haystack = { path = "rust-src-tools-3b0d4813.txt" }
 count = [
   { engine = 'hyperscan', count = 237 },
+  { engine = 'vectorscan', count = 237 },  
   { engine = '.*', count = 11 },
 ]
 engines = [
@@ -139,6 +146,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -165,6 +173,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'pcre2',
   'pcre2/jit',
@@ -186,13 +195,15 @@ regex = '(?:[A-Z][a-z]+\s*){10,100}'
 haystack = 'Crazy Janey Mission Man Wild Billy Greasy Lake Hazy Davy Killer Joe'
 count = [
   { engine = 'hyperscan', count = 12 },
+  { engine = 'vectorscan', count = 12 },
   { engine = '.*', count = 1 },
 ]
 engines = [
   'dotnet/compiled',
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'pcre2',
   'pcre2/jit',

benchmarks/definitions/curated/12-dictionary.toml

@@ -128,6 +128,8 @@ analysis = '''
 
 `hyperscan` is omitted because the regex is too large.
 
+`vectorscan` is omitted because the regex is too large.
+
 `pcre2/*` are omitted because the regex is too large.
 '''
 
@@ -139,6 +141,7 @@ haystack = { path = "opensubtitles/en-medium.txt" }
 count = 1
 engines = [
   'hyperscan',
+  'vectorscan',
   'rust/regex',
 ]
 analysis = '''
@@ -173,6 +176,8 @@ analysis = '''
 
 `hyperscan` is omitted because the regex is too large.
 
+`vectorscan` is omitted because the regex is too large.
+
 `java/hotspot` is omitted because we currently don't benchmark Perl regex
 compilation.
 
@@ -192,6 +197,7 @@ haystack = "Zubeneschamali's"
 count = 1
 engines = [
   'hyperscan',
+  'vectorscan',
   'rust/regex',
 ]
 analysis = '''

benchmarks/definitions/curated/13-noseyparker.toml

@@ -56,10 +56,12 @@ regex = { path = "wild/noseyparker.txt", per-line = "alternate" }
 haystack = { path = 'wild/cpython-226484e4.py', utf8-lossy = true }
 count = [
   { engine = 'hyperscan', count = 241 },
+  { engine = 'vectorscan', count = 241 },
   { engine = '.*', count = 55 },
 ]
 engines = [
   'hyperscan',
+  'vectorscan',
   'pcre2/jit',
   'rust/regex',
   'rust/regexold',
@@ -88,10 +90,12 @@ regex = { path = "wild/noseyparker.txt", per-line = "pattern" }
 haystack = { path = 'wild/cpython-226484e4.py', utf8-lossy = true }
 count = [
   { engine = 'hyperscan', count = 241 },
+  { engine = 'vectorscan', count = 241 },
   { engine = '.*', count = 55 },
 ]
 engines = [
   'hyperscan',
+  'vectorscan',
   'rust/regex',
 ]
 analysis = '''
@@ -109,6 +113,7 @@ haystack = "TWITTER_API_KEY = 'UZYoBAfBzNace3mBwPOGYw'"
 count = 1
 engines = [
   'hyperscan',
+  'Vectorscan',
   'pcre2/jit',
   'rust/regex',
   'rust/regexold',
@@ -125,6 +130,7 @@ haystack = "TWITTER_API_KEY = 'UZYoBAfBzNace3mBwPOGYw'"
 count = 1
 engines = [
   'hyperscan',
+  'vectorscan',
   'rust/regex',
 ]
 analysis = '''

benchmarks/definitions/curated/14-quadratic.toml

@@ -91,6 +91,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -122,6 +123,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',
@@ -158,6 +160,7 @@ engines = [
   'dotnet/nobacktrack',
   'go/regexp',
   'hyperscan',
+  'vectorscan',
   'icu',
   'java/hotspot',
   'javascript/v8',