Merge branch 'master' into spelling

.github/workflows/goTest.yml

@@ -4,12 +4,12 @@ jobs:
   test:
     strategy:
       matrix:
-        go-version: [1.16.x, 1.17.x]
+        go-version: [1.18.x, 1.19.x]
         platform: [ubuntu-latest, macos-latest, windows-latest]
     runs-on: ${{ matrix.platform }}
     steps:
     - name: Install Go
-      uses: actions/setup-go@v1
+      uses: actions/setup-go@v3
       with:
         go-version: ${{ matrix.go-version }}
     - name: Set git on win to use LF
@@ -26,7 +26,7 @@ jobs:
   test-oniguruma:
     strategy:
       matrix:
-        go-version: [1.16.x, 1.17.x]
+        go-version: [1.18.x, 1.19.x]
     runs-on: ubuntu-latest
     env:
       ONIGURUMA_VERSION: 6.9.4
@@ -39,7 +39,7 @@ jobs:
         sudo dpkg -i "libonig-dev_${ONIGURUMA_VERSION}-1_amd64.deb"
 
     - name: Install Go
-      uses: actions/setup-go@v1
+      uses: actions/setup-go@v3
       with:
         go-version: ${{ matrix.go-version }}
 

.github/workflows/pyTest.yml

@@ -4,7 +4,7 @@ jobs:
   test:
     strategy:
       matrix:
-        python-version: [3.6, 3.7, 3.8]
+        python-version: [3.7, 3.8, 3.9]
         platform: [ubuntu-latest, macos-latest]
     runs-on: ${{ matrix.platform }}
     steps:

README.md

@@ -61,7 +61,7 @@ To make a guess only based on the content of the file or a text snippet, use
 
 ### By file
 
-The most accurate guess would be one when both, the file name and the content are available:
+The most accurate guess would be when both, a file name and it's content are available:
 
 - `GetLanguagesByContent` only uses file extension and a set of regexp-based content heuristics.
 - `GetLanguages` uses the full set of matching strategies and is expected to be most accurate.
@@ -156,7 +156,7 @@ Generated Rust bindings using a C static library are available at https://github
 
 ## Divergences from Linguist
 
-The `enry` library is based on the data from `github/linguist` version **v7.20.0**.
+The `enry` library is based on the data from `github/linguist` version **v7.21.0**.
 
 Parsing [linguist/samples](https://github.com/github/linguist/tree/master/samples) the following `enry` results are different from the Linguist:
 
@@ -212,8 +212,8 @@ To run the tests use:
 
     go test ./...
 
-Setting `ENRY_TEST_REPO` to the path to existing checkout of Linguist will avoid cloning it and sepeed tests up.
+Setting `ENRY_TEST_REPO` to a path to the existing checkout of the Linguist will avoid cloning it and speeds tests up.
-Setting `ENRY_DEBUG=1` will provide insight in the Bayesian classifier building done by `make code-generate`.
+Setting `ENRY_DEBUG=1` will provide insight into the Bayesian classifier built during `make code-generate`.
 
 ### Sync with github/linguist upstream
 
@@ -237,12 +237,12 @@ To stay in sync, enry needs to be updated when a new release of the linguist inc
 - [vendor.yml](https://github.com/github/linguist/blob/master/lib/linguist/vendor.yml)
 - [documentation.yml](https://github.com/github/linguist/blob/master/lib/linguist/documentation.yml)
 
-There is no automation for detecting the changes in the linguist project, so this process above has to be done manually from time to time.
+There now is automation for detecting the changes in the upstream Linguist project: every day Github CI runs [a job](.github/workflows/sync-linguist.yml) that will create a PR to this repo for each new Linguist release. It will include all the steps from the above.
 
-When submitting a pull request syncing up to a new release, please make sure it only contains the changes in
+When submitting a pull request syncing up to a new release manually, please make sure it only contains the changes in
 the generated files (in [data](https://github.com/go-enry/go-enry/blob/master/data) subdirectory).
 
-Separating all the necessary "manual" code changes to a different PR that includes some background description and an update to the documentation on ["divergences from linguist"](#divergences-from-linguist) is very much appreciated as it simplifies the maintenance (review/release notes/etc).
+Separating all the necessary "manual" code changes to a different PR that includes some background description and an update to the documentation on ["divergences from linguist"](#divergences-from-linguist) is encouraged and very much appreciated, as it simplifies the maintenance (review/release notes/etc).
 
 ## Misc
 

benchmark_test.go

@@ -6,11 +6,8 @@ import (
 	"io/ioutil"
 	"log"
 	"os"
-	"os/exec"
 	"path/filepath"
 	"testing"
-
-	"github.com/go-enry/go-enry/v2/data"
 )
 
 type sample struct {
@@ -23,22 +20,21 @@ var (
 	overcomeLanguage  string
 	overcomeLanguages []string
 	samples           []*sample
-	samplesDir        string
-	cloned            bool
 )
 
 func TestMain(m *testing.M) {
 	flag.BoolVar(&slow, "slow", false, "run benchmarks per sample for strategies too")
 	flag.Parse()
 
-	if err := cloneLinguist(linguistURL); err != nil {
+	tmpLinguistDir, cleanupNeeded, err := maybeCloneLinguist()
+	if err != nil {
 		log.Fatal(err)
 	}
-	if cloned {
+	if cleanupNeeded {
-		defer os.RemoveAll(filepath.Dir(samplesDir))
+		defer os.RemoveAll(tmpLinguistDir)
 	}
 
-	var err error
+	samplesDir := filepath.Join(tmpLinguistDir, "samples")
 	samples, err = getSamples(samplesDir)
 	if err != nil {
 		log.Fatal(err)
@@ -47,47 +43,6 @@ func TestMain(m *testing.M) {
 	os.Exit(m.Run())
 }
 
-func cloneLinguist(linguistURL string) error {
-	repoLinguist := os.Getenv(linguistClonedEnvVar)
-	cloned = repoLinguist == ""
-	if cloned {
-		var err error
-		repoLinguist, err = ioutil.TempDir("", "linguist-")
-		if err != nil {
-			return err
-		}
-	}
-
-	samplesDir = filepath.Join(repoLinguist, "samples")
-
-	if cloned {
-		cmd := exec.Command("git", "clone", linguistURL, repoLinguist)
-		if err := cmd.Run(); err != nil {
-			return err
-		}
-	}
-
-	cwd, err := os.Getwd()
-	if err != nil {
-		return err
-	}
-
-	if err = os.Chdir(repoLinguist); err != nil {
-		return err
-	}
-
-	cmd := exec.Command("git", "checkout", data.LinguistCommit)
-	if err := cmd.Run(); err != nil {
-		return err
-	}
-
-	if err = os.Chdir(cwd); err != nil {
-		return err
-	}
-
-	return nil
-}
-
 func getSamples(dir string) ([]*sample, error) {
 	samples := make([]*sample, 0, 2000)
 	err := filepath.Walk(dir, func(path string, info os.FileInfo, err error) error {

common.go

@@ -38,7 +38,7 @@ var defaultClassifier classifier = &naiveBayes{
 }
 
 // GetLanguage applies a sequence of strategies based on the given filename and content
-// to find out the most probably language to return.
+// to find out the most probable language to return.
 func GetLanguage(filename string, content []byte) (language string) {
 	languages := GetLanguages(filename, content)
 	return firstLanguage(languages)
@@ -508,28 +508,6 @@ func GetLanguageExtensions(language string) []string {
 	return data.ExtensionsByLanguage[language]
 }
 
-// GetLanguageID returns the ID for the language. IDs are assigned by GitHub.
-// The input must be the canonical language name. Aliases are not supported.
-//
-// NOTE: The zero value (0) is a valid language ID, so this API mimics the Go
-// map API. Use the second return value to check if the language was found.
-func GetLanguageID(language string) (int, bool) {
-	id, ok := data.IDByLanguage[language]
-	return id, ok
-}
-
-// Type represent language's type. Either data, programming, markup, prose, or unknown.
-type Type int
-
-// Type's values.
-const (
-	Unknown     Type = Type(data.TypeUnknown)
-	Data             = Type(data.TypeData)
-	Programming      = Type(data.TypeProgramming)
-	Markup           = Type(data.TypeMarkup)
-	Prose            = Type(data.TypeProse)
-)
-
 // GetLanguageType returns the type of the given language.
 func GetLanguageType(language string) (langType Type) {
 	intType, ok := data.LanguagesType[language]
@@ -540,6 +518,15 @@ func GetLanguageType(language string) (langType Type) {
 	return langType
 }
 
+// GetLanguageGroup returns language group or empty string if language does not have group.
+func GetLanguageGroup(language string) string {
+	if group, ok := data.LanguagesGroup[language]; ok {
+		return group
+	}
+
+	return ""
+}
+
 // GetLanguageByAlias returns either the language related to the given alias and ok set to true
 // or Otherlanguage and ok set to false if the alias is not recognized.
 func GetLanguageByAlias(alias string) (lang string, ok bool) {
@@ -551,13 +538,14 @@ func GetLanguageByAlias(alias string) (lang string, ok bool) {
 	return
 }
 
-// GetLanguageGroup returns language group or empty string if language does not have group.
+// GetLanguageID returns the ID for the language. IDs are assigned by GitHub.
-func GetLanguageGroup(language string) string {
+// The input must be the canonical language name. Aliases are not supported.
-	if group, ok := data.LanguagesGroup[language]; ok {
+//
-		return group
+// NOTE: The zero value (0) is a valid language ID, so this API mimics the Go
-	}
+// map API. Use the second return value to check if the language was found.
-
+func GetLanguageID(language string) (int, bool) {
-	return ""
+	id, ok := data.IDByLanguage[language]
+	return id, ok
 }
 
 // GetLanguageInfo returns the LanguageInfo for a given language name, or an error if not found.

common_test.go

@@ -19,15 +19,78 @@ import (
 const linguistURL = "https://github.com/github/linguist.git"
 const linguistClonedEnvVar = "ENRY_TEST_REPO"
 
-type EnryTestSuite struct {
+// not a part of the test Suite as benchmark does not use testify
+func maybeCloneLinguist() (string, bool, error) {
+	var err error
+	linguistTmpDir := os.Getenv(linguistClonedEnvVar)
+	isCleanupNeeded := false
+	isLinguistCloned := linguistTmpDir != ""
+	if !isLinguistCloned {
+		linguistTmpDir, err = ioutil.TempDir("", "linguist-")
+		if err != nil {
+			return "", false, err
+		}
+
+		isCleanupNeeded = true
+		cmd := exec.Command("git", "clone", "--depth", "100", linguistURL, linguistTmpDir)
+		if err := cmd.Run(); err != nil {
+			return linguistTmpDir, isCleanupNeeded, err
+		}
+	}
+
+	cwd, err := os.Getwd()
+	if err != nil {
+		return linguistTmpDir, isCleanupNeeded, err
+	}
+
+	if err = os.Chdir(linguistTmpDir); err != nil {
+		return linguistTmpDir, isCleanupNeeded, err
+	}
+
+	cmd := exec.Command("git", "checkout", data.LinguistCommit)
+	if err := cmd.Run(); err != nil {
+		return linguistTmpDir, isCleanupNeeded, err
+	}
+
+	if err = os.Chdir(cwd); err != nil {
+		return linguistTmpDir, isCleanupNeeded, err
+	}
+	return linguistTmpDir, isCleanupNeeded, nil
+}
+
+type enryBaseTestSuite struct {
 	suite.Suite
-	tmpLinguist     string
+	tmpLinguistDir  string
-	needToClone     bool
+	isCleanupNeeded bool
 	samplesDir      string
 	testFixturesDir string
 }
 
-func (s *EnryTestSuite) TestRegexpEdgeCases() {
+func (s *enryBaseTestSuite) SetupSuite() {
+	var err error
+	s.tmpLinguistDir, s.isCleanupNeeded, err = maybeCloneLinguist()
+	require.NoError(s.T(), err)
+
+	s.samplesDir = filepath.Join(s.tmpLinguistDir, "samples")
+	s.testFixturesDir = filepath.Join(s.tmpLinguistDir, "test", "fixtures")
+}
+
+func (s *enryBaseTestSuite) TearDownSuite() {
+	if s.isCleanupNeeded {
+		err := os.RemoveAll(s.tmpLinguistDir)
+		require.NoError(s.T(), err)
+	}
+}
+
+type enryTestSuite struct {
+	enryBaseTestSuite
+}
+
+func Test_EnryTestSuite(t *testing.T) {
+	suite.Run(t, new(enryTestSuite))
+}
+
+func (s *enryTestSuite) TestRegexpEdgeCases() {
 	var regexpEdgeCases = []struct {
 		lang     string
 		filename string
@@ -41,7 +104,7 @@ func (s *EnryTestSuite) TestRegexpEdgeCases() {
 	}
 
 	for _, r := range regexpEdgeCases {
-		filename := filepath.Join(s.tmpLinguist, "samples", r.lang, r.filename)
+		filename := filepath.Join(s.tmpLinguistDir, "samples", r.lang, r.filename)
 
 		content, err := ioutil.ReadFile(filename)
 		require.NoError(s.T(), err)
@@ -54,51 +117,7 @@ func (s *EnryTestSuite) TestRegexpEdgeCases() {
 	}
 }
 
-func Test_EnryTestSuite(t *testing.T) {
+func (s *enryTestSuite) TestGetLanguage() {
-	suite.Run(t, new(EnryTestSuite))
-}
-
-func (s *EnryTestSuite) SetupSuite() {
-	var err error
-	s.tmpLinguist = os.Getenv(linguistClonedEnvVar)
-	s.needToClone = s.tmpLinguist == ""
-	if s.needToClone {
-		s.tmpLinguist, err = ioutil.TempDir("", "linguist-")
-		require.NoError(s.T(), err)
-		s.T().Logf("Cloning Linguist repo to '%s' as %s was not set\n",
-			s.tmpLinguist, linguistClonedEnvVar)
-		cmd := exec.Command("git", "clone", linguistURL, s.tmpLinguist)
-		err = cmd.Run()
-		require.NoError(s.T(), err)
-	}
-	s.samplesDir = filepath.Join(s.tmpLinguist, "samples")
-	s.T().Logf("using samples from %s", s.samplesDir)
-
-	s.testFixturesDir = filepath.Join(s.tmpLinguist, "test", "fixtures")
-	s.T().Logf("using test fixtures from %s", s.samplesDir)
-
-	cwd, err := os.Getwd()
-	assert.NoError(s.T(), err)
-
-	err = os.Chdir(s.tmpLinguist)
-	assert.NoError(s.T(), err)
-
-	cmd := exec.Command("git", "checkout", data.LinguistCommit)
-	err = cmd.Run()
-	assert.NoError(s.T(), err)
-
-	err = os.Chdir(cwd)
-	assert.NoError(s.T(), err)
-}
-
-func (s *EnryTestSuite) TearDownSuite() {
-	if s.needToClone {
-		err := os.RemoveAll(s.tmpLinguist)
-		assert.NoError(s.T(), err)
-	}
-}
-
-func (s *EnryTestSuite) TestGetLanguage() {
 	tests := []struct {
 		name     string
 		filename string
@@ -120,7 +139,7 @@ func (s *EnryTestSuite) TestGetLanguage() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguages() {
+func (s *enryTestSuite) TestGetLanguages() {
 	tests := []struct {
 		name     string
 		filename string
@@ -152,8 +171,8 @@ func (s *EnryTestSuite) TestGetLanguages() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesByModelineLinguist() {
+func (s *enryTestSuite) TestGetLanguagesByModelineLinguist() {
-	var modelinesDir = filepath.Join(s.tmpLinguist, "test", "fixtures", "Data", "Modelines")
+	var modelinesDir = filepath.Join(s.tmpLinguistDir, "test", "fixtures", "Data", "Modelines")
 
 	tests := []struct {
 		name       string
@@ -212,7 +231,7 @@ func (s *EnryTestSuite) TestGetLanguagesByModelineLinguist() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesByModeline() {
+func (s *enryTestSuite) TestGetLanguagesByModeline() {
 	const (
 		wrongVim  = `# vim: set syntax=ruby ft  =python filetype=perl :`
 		rightVim  = `/* vim: set syntax=python ft   =python filetype=python */`
@@ -239,7 +258,7 @@ func (s *EnryTestSuite) TestGetLanguagesByModeline() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesByFilename() {
+func (s *enryTestSuite) TestGetLanguagesByFilename() {
 	tests := []struct {
 		name       string
 		filename   string
@@ -267,7 +286,7 @@ func (s *EnryTestSuite) TestGetLanguagesByFilename() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesByShebang() {
+func (s *enryTestSuite) TestGetLanguagesByShebang() {
 	const (
 		multilineExecHack = `#!/bin/sh
 # Next line is comment in Tcl, but not in sh... \
@@ -352,7 +371,26 @@ println("The shell script says ",vm.arglist.concat(" "));`
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesByExtension() {
+func (s *enryTestSuite) TestGetLanguageByContent() {
+	tests := []struct {
+		name     string
+		filename string
+		content  []byte
+		expected string
+	}{
+		{name: "TestGetLanguageByContent_0", filename: "", expected: ""},
+		{name: "TestGetLanguageByContent_1", filename: "foo.cpp", content: []byte("int main() { return 0; }"), expected: ""},                      // as .cpp is unambiguous ¯\_(ツ)_/¯
+		{name: "TestGetLanguageByContent_2", filename: "foo.h", content: []byte("int main() { return 0; }"), expected: "C"},                       // C, as it does not match any of the heuristics for C++ or Objective-C
+		{name: "TestGetLanguageByContent_3", filename: "foo.h", content: []byte("#include <string>\n int main() { return 0; }"), expected: "C++"}, // '#include <string>' matches regex heuristic
+	}
+
+	for _, test := range tests {
+		languages, _ := GetLanguageByContent(test.filename, test.content)
+		assert.Equal(s.T(), test.expected, languages, fmt.Sprintf("%v: languages = %v, expected: %v", test.name, languages, test.expected))
+	}
+}
+
+func (s *enryTestSuite) TestGetLanguagesByExtension() {
 	tests := []struct {
 		name       string
 		filename   string
@@ -373,7 +411,7 @@ func (s *EnryTestSuite) TestGetLanguagesByExtension() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesByManpage() {
+func (s *enryTestSuite) TestGetLanguagesByManpage() {
 	tests := []struct {
 		name       string
 		filename   string
@@ -397,7 +435,7 @@ func (s *EnryTestSuite) TestGetLanguagesByManpage() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesByXML() {
+func (s *enryTestSuite) TestGetLanguagesByXML() {
 	tests := []struct {
 		name       string
 		filename   string
@@ -420,7 +458,7 @@ func (s *EnryTestSuite) TestGetLanguagesByXML() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesByClassifier() {
+func (s *enryTestSuite) TestGetLanguagesByClassifier() {
 	test := []struct {
 		name       string
 		filename   string
@@ -457,7 +495,7 @@ func (s *EnryTestSuite) TestGetLanguagesByClassifier() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguagesBySpecificClassifier() {
+func (s *enryTestSuite) TestGetLanguagesBySpecificClassifier() {
 	test := []struct {
 		name       string
 		filename   string
@@ -490,7 +528,7 @@ func (s *EnryTestSuite) TestGetLanguagesBySpecificClassifier() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguageExtensions() {
+func (s *enryTestSuite) TestGetLanguageExtensions() {
 	tests := []struct {
 		name     string
 		language string
@@ -507,7 +545,7 @@ func (s *EnryTestSuite) TestGetLanguageExtensions() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguageType() {
+func (s *enryTestSuite) TestGetLanguageType() {
 	tests := []struct {
 		name     string
 		language string
@@ -530,7 +568,7 @@ func (s *EnryTestSuite) TestGetLanguageType() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguageGroup() {
+func (s *enryTestSuite) TestGetLanguageGroup() {
 	tests := []struct {
 		name     string
 		language string
@@ -548,7 +586,7 @@ func (s *EnryTestSuite) TestGetLanguageGroup() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguageByAlias() {
+func (s *enryTestSuite) TestGetLanguageByAlias() {
 	tests := []struct {
 		name         string
 		alias        string
@@ -574,57 +612,7 @@ func (s *EnryTestSuite) TestGetLanguageByAlias() {
 	}
 }
 
-func (s *EnryTestSuite) TestLinguistCorpus() {
+func (s *enryTestSuite) TestGetLanguageID() {
-	const filenamesDir = "filenames"
-	var cornerCases = map[string]bool{
-		"drop_stuff.sql":        true, // https://github.com/src-d/enry/issues/194
-		"textobj-rubyblock.vba": true, // Because of unsupported negative lookahead RE syntax (https://github.com/github/linguist/blob/8083cb5a89cee2d99f5a988f165994d0243f0d1e/lib/linguist/heuristics.yml#L521)
-		// .es and .ice fail heuristics parsing, but do not fail any tests
-	}
-
-	var total, failed, ok, other int
-	var expected string
-	filepath.Walk(s.samplesDir, func(path string, f os.FileInfo, err error) error {
-		if f.IsDir() {
-			if f.Name() != filenamesDir {
-				expected, _ = data.LanguageByAlias(f.Name())
-			}
-
-			return nil
-		}
-
-		filename := filepath.Base(path)
-		content, _ := ioutil.ReadFile(path)
-
-		total++
-		obtained := GetLanguage(filename, content)
-		if obtained == OtherLanguage {
-			obtained = "Other"
-			other++
-		}
-
-		var status string
-		if expected == obtained {
-			status = "ok"
-			ok++
-		} else {
-			status = "failed"
-			failed++
-		}
-
-		if _, ok := cornerCases[filename]; ok {
-			s.T().Logf("\t\t[considered corner case] %s\texpected: %s\tobtained: %s\tstatus: %s\n", filename, expected, obtained, status)
-		} else {
-			assert.Equal(s.T(), expected, obtained, fmt.Sprintf("%s\texpected: %s\tobtained: %s\tstatus: %s\n", filename, expected, obtained, status))
-		}
-
-		return nil
-	})
-
-	s.T().Logf("\t\ttotal files: %d, ok: %d, failed: %d, other: %d\n", total, ok, failed, other)
-}
-
-func (s *EnryTestSuite) TestGetLanguageID() {
 	tests := []struct {
 		name       string
 		language   string
@@ -647,7 +635,7 @@ func (s *EnryTestSuite) TestGetLanguageID() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguageInfo() {
+func (s *enryTestSuite) TestGetLanguageInfo() {
 	tests := []struct {
 		name       string
 		language   string
@@ -674,7 +662,7 @@ func (s *EnryTestSuite) TestGetLanguageInfo() {
 	}
 }
 
-func (s *EnryTestSuite) TestGetLanguageInfoByID() {
+func (s *enryTestSuite) TestGetLanguageInfoByID() {
 	tests := []struct {
 		name         string
 		id           int

data/alias.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -44,6 +44,7 @@ var LanguageByAliasMap = map[string]string{
 	"amusewiki":                          "Muse",
 	"angelscript":                        "AngelScript",
 	"ant_build_system":                   "Ant Build System",
+	"antlers":                            "Antlers",
 	"antlr":                              "ANTLR",
 	"apache":                             "ApacheConf",
 	"apacheconf":                         "ApacheConf",
@@ -56,6 +57,7 @@ var LanguageByAliasMap = map[string]string{
 	"arc":                                "Arc",
 	"arexx":                              "REXX",
 	"as3":                                "ActionScript",
+	"ascii_stl":                          "STL",
 	"asciidoc":                           "AsciiDoc",
 	"asl":                                "ASL",
 	"asm":                                "Assembly",
@@ -94,6 +96,7 @@ var LanguageByAliasMap = map[string]string{
 	"berry":                              "Berry",
 	"bibtex":                             "BibTeX",
 	"bicep":                              "Bicep",
+	"bikeshed":                           "Bikeshed",
 	"bison":                              "Bison",
 	"bitbake":                            "BitBake",
 	"blade":                              "Blade",
@@ -107,6 +110,7 @@ var LanguageByAliasMap = map[string]string{
 	"boogie":                             "Boogie",
 	"bplus":                              "BlitzBasic",
 	"brainfuck":                          "Brainfuck",
+	"brighterscript":                     "BrighterScript",
 	"brightscript":                       "Brightscript",
 	"bro":                                "Zeek",
 	"browserslist":                       "Browserslist",
@@ -128,14 +132,18 @@ var LanguageByAliasMap = map[string]string{
 	"cakescript":                         "C#",
 	"cameligo":                           "CameLIGO",
 	"cap'n_proto":                        "Cap'n Proto",
+	"cap_cds":                            "CAP CDS",
 	"carto":                              "CartoCSS",
 	"cartocss":                           "CartoCSS",
+	"cds":                                "CAP CDS",
 	"ceylon":                             "Ceylon",
 	"cfc":                                "ColdFusion CFC",
 	"cfm":                                "ColdFusion",
 	"cfml":                               "ColdFusion",
 	"chapel":                             "Chapel",
 	"charity":                            "Charity",
+	"checksum":                           "Checksums",
+	"checksums":                          "Checksums",
 	"chpl":                               "Chapel",
 	"chuck":                              "ChucK",
 	"cil":                                "CIL",
@@ -293,6 +301,7 @@ var LanguageByAliasMap = map[string]string{
 	"gaml":                               "GAML",
 	"gams":                               "GAMS",
 	"gap":                                "GAP",
+	"gas":                                "Unix Assembly",
 	"gcc_machine_description":            "GCC Machine Description",
 	"gdb":                                "GDB",
 	"gdscript":                           "GDScript",
@@ -304,13 +313,16 @@ var LanguageByAliasMap = map[string]string{
 	"genshi":                             "Genshi",
 	"gentoo_ebuild":                      "Gentoo Ebuild",
 	"gentoo_eclass":                      "Gentoo Eclass",
+	"geojson":                            "JSON",
 	"gerber_image":                       "Gerber Image",
 	"gettext_catalog":                    "Gettext Catalog",
 	"gf":                                 "Grammatical Framework",
 	"gherkin":                            "Gherkin",
 	"git-ignore":                         "Ignore List",
 	"git_attributes":                     "Git Attributes",
+	"git_blame_ignore_revs":              "Git Revision List",
 	"git_config":                         "Git Config",
+	"git_revision_list":                  "Git Revision List",
 	"gitattributes":                      "Git Attributes",
 	"gitconfig":                          "Git Config",
 	"gitignore":                          "Ignore List",
@@ -320,6 +332,7 @@ var LanguageByAliasMap = map[string]string{
 	"glyph":                              "Glyph",
 	"glyph_bitmap_distribution_format":   "Glyph Bitmap Distribution Format",
 	"gn":                                 "GN",
+	"gnu_asm":                            "Unix Assembly",
 	"gnuplot":                            "Gnuplot",
 	"go":                                 "Go",
 	"go.mod":                             "Go Module",
@@ -347,6 +360,8 @@ var LanguageByAliasMap = map[string]string{
 	"handlebars":                         "Handlebars",
 	"haproxy":                            "HAProxy",
 	"harbour":                            "Harbour",
+	"hash":                               "Checksums",
+	"hashes":                             "Checksums",
 	"hashicorp_configuration_language":   "HCL",
 	"haskell":                            "Haskell",
 	"haxe":                               "Haxe",
@@ -410,6 +425,7 @@ var LanguageByAliasMap = map[string]string{
 	"javascript":                         "JavaScript",
 	"javascript+erb":                     "JavaScript+ERB",
 	"jest_snapshot":                      "Jest Snapshot",
+	"jetbrains_mps":                      "JetBrains MPS",
 	"jflex":                              "JFlex",
 	"jinja":                              "Jinja",
 	"jison":                              "Jison",
@@ -423,6 +439,7 @@ var LanguageByAliasMap = map[string]string{
 	"json_with_comments":                 "JSON with Comments",
 	"jsonc":                              "JSON with Comments",
 	"jsoniq":                             "JSONiq",
+	"jsonl":                              "JSON",
 	"jsonld":                             "JSONLD",
 	"jsonnet":                            "Jsonnet",
 	"jsp":                                "Java Server Pages",
@@ -532,6 +549,7 @@ var LanguageByAliasMap = map[string]string{
 	"moonscript":                         "MoonScript",
 	"motoko":                             "Motoko",
 	"motorola_68k_assembly":              "Motorola 68K Assembly",
+	"mps":                                "JetBrains MPS",
 	"mql4":                               "MQL4",
 	"mql5":                               "MQL5",
 	"mtml":                               "MTML",
@@ -649,6 +667,7 @@ var LanguageByAliasMap = map[string]string{
 	"pod_6":                              "Pod 6",
 	"pogoscript":                         "PogoScript",
 	"pony":                               "Pony",
+	"portugol":                           "Portugol",
 	"posh":                               "PowerShell",
 	"postcss":                            "PostCSS",
 	"postscr":                            "PostScript",
@@ -810,13 +829,18 @@ var LanguageByAliasMap = map[string]string{
 	"ssh_config":                         "SSH Config",
 	"stan":                               "Stan",
 	"standard_ml":                        "Standard ML",
+	"star":                               "STAR",
 	"starlark":                           "Starlark",
 	"stata":                              "Stata",
+	"stl":                                "STL",
+	"stla":                               "STL",
 	"ston":                               "STON",
 	"stringtemplate":                     "StringTemplate",
 	"stylus":                             "Stylus",
 	"subrip_text":                        "SubRip Text",
 	"sugarss":                            "SugarSS",
+	"sum":                                "Checksums",
+	"sums":                               "Checksums",
 	"supercollider":                      "SuperCollider",
 	"svelte":                             "Svelte",
 	"svg":                                "SVG",
@@ -841,6 +865,7 @@ var LanguageByAliasMap = map[string]string{
 	"tla":                                "TLA",
 	"tm-properties":                      "TextMate Properties",
 	"toml":                               "TOML",
+	"topojson":                           "JSON",
 	"troff":                              "Roff",
 	"ts":                                 "TypeScript",
 	"tsql":                               "TSQL",
@@ -857,6 +882,7 @@ var LanguageByAliasMap = map[string]string{
 	"ultisnips":                          "Vim Snippet",
 	"unified_parallel_c":                 "Unified Parallel C",
 	"unity3d_asset":                      "Unity3D Asset",
+	"unix_asm":                           "Unix Assembly",
 	"unix_assembly":                      "Unix Assembly",
 	"uno":                                "Uno",
 	"unrealscript":                       "UnrealScript",
@@ -888,6 +914,7 @@ var LanguageByAliasMap = map[string]string{
 	"visual_basic_for_applications":      "VBA",
 	"vlang":                              "V",
 	"volt":                               "Volt",
+	"vtt":                                "WebVTT",
 	"vue":                                "Vue",
 	"vyper":                              "Vyper",
 	"wasm":                               "WebAssembly",
@@ -901,6 +928,7 @@ var LanguageByAliasMap = map[string]string{
 	"webvtt":                             "WebVTT",
 	"wget_config":                        "Wget Config",
 	"wgetrc":                             "Wget Config",
+	"whiley":                             "Whiley",
 	"wiki":                               "Wikitext",
 	"wikitext":                           "Wikitext",
 	"win32_message_file":                 "Win32 Message File",
@@ -948,6 +976,7 @@ var LanguageByAliasMap = map[string]string{
 	"yas":                                "YASnippet",
 	"yasnippet":                          "YASnippet",
 	"yml":                                "YAML",
+	"yul":                                "Yul",
 	"zap":                                "ZAP",
 	"zeek":                               "Zeek",
 	"zenscript":                          "ZenScript",
@@ -969,8 +998,9 @@ func LanguageByAlias(langOrAlias string) (lang string, ok bool) {
 
 // convertToAliasKey converts language name to a key in LanguageByAliasMap.
 // Following
-//  - internal.code-generator.generator.convertToAliasKey()
+//   - internal.code-generator.generator.convertToAliasKey()
-//  - GetLanguageByAlias()
+//   - GetLanguageByAlias()
+//
 // conventions.
 // It is here to avoid dependency on "generate" and "enry" packages.
 func convertToAliasKey(langName string) string {

data/colors.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -27,6 +27,7 @@ var LanguagesColor = map[string]string{
 	"Altium Designer":                "#A89663",
 	"AngelScript":                    "#C7D7DC",
 	"Ant Build System":               "#A9157E",
+	"Antlers":                        "#ff269e",
 	"ApacheConf":                     "#d12127",
 	"Apex":                           "#1797c0",
 	"Apollo Guidance Computer":       "#0B3D91",
@@ -49,6 +50,7 @@ var LanguagesColor = map[string]string{
 	"Berry":                          "#15A13C",
 	"BibTeX":                         "#778899",
 	"Bicep":                          "#519aba",
+	"Bikeshed":                       "#5562ac",
 	"Bison":                          "#6A463F",
 	"BitBake":                        "#00bce4",
 	"Blade":                          "#f7523f",
@@ -58,11 +60,13 @@ var LanguagesColor = map[string]string{
 	"Boo":                            "#d4bec1",
 	"Boogie":                         "#c80fa0",
 	"Brainfuck":                      "#2F2530",
+	"BrighterScript":                 "#66AABB",
 	"Brightscript":                   "#662D91",
 	"Browserslist":                   "#ffd539",
 	"C":                              "#555555",
 	"C#":                             "#178600",
 	"C++":                            "#f34b7d",
+	"CAP CDS":                        "#0092d1",
 	"CLIPS":                          "#00A300",
 	"CMake":                          "#DA3434",
 	"COLLADA":                        "#F1A42B",
@@ -171,6 +175,7 @@ var LanguagesColor = map[string]string{
 	"Gherkin":                        "#5B2063",
 	"Git Attributes":                 "#F44D27",
 	"Git Config":                     "#F44D27",
+	"Git Revision List":              "#F44D27",
 	"Gleam":                          "#ffaff3",
 	"Glyph":                          "#c1ac7f",
 	"Gnuplot":                        "#f0a9f0",
@@ -232,6 +237,7 @@ var LanguagesColor = map[string]string{
 	"JavaScript":                     "#f1e05a",
 	"JavaScript+ERB":                 "#f1e05a",
 	"Jest Snapshot":                  "#15c213",
+	"JetBrains MPS":                  "#21D789",
 	"Jinja":                          "#a52a22",
 	"Jison":                          "#56b3cb",
 	"Jison Lex":                      "#56b3cb",
@@ -344,6 +350,7 @@ var LanguagesColor = map[string]string{
 	"PigLatin":                       "#fcd7de",
 	"Pike":                           "#005390",
 	"PogoScript":                     "#d80074",
+	"Portugol":                       "#f8bd00",
 	"PostCSS":                        "#dc3a0c",
 	"PostScript":                     "#da291c",
 	"PowerBuilder":                   "#8f0f8d",
@@ -399,6 +406,7 @@ var LanguagesColor = map[string]string{
 	"SQL":                            "#e38c00",
 	"SQLPL":                          "#e38c00",
 	"SRecode Template":               "#348a34",
+	"STL":                            "#373b5e",
 	"SVG":                            "#ff9900",
 	"SaltStack":                      "#646464",
 	"Sass":                           "#a53b70",
@@ -438,7 +446,7 @@ var LanguagesColor = map[string]string{
 	"TOML":                           "#9c4221",
 	"TSQL":                           "#e38c00",
 	"TSV":                            "#237346",
-	"TSX":                            "#2b7489",
+	"TSX":                            "#3178c6",
 	"TXL":                            "#0178b8",
 	"Talon":                          "#333333",
 	"Tcl":                            "#e4cc98",
@@ -449,7 +457,7 @@ var LanguagesColor = map[string]string{
 	"Thrift":                         "#D12127",
 	"Turing":                         "#cf142b",
 	"Twig":                           "#c1d026",
-	"TypeScript":                     "#2b7489",
+	"TypeScript":                     "#3178c6",
 	"Unified Parallel C":             "#4e3617",
 	"Unity3D Asset":                  "#222c37",
 	"Uno":                            "#9933cc",
@@ -472,6 +480,7 @@ var LanguagesColor = map[string]string{
 	"Vyper":                          "#2980b9",
 	"Web Ontology Language":          "#5b70bd",
 	"WebAssembly":                    "#04133b",
+	"Whiley":                         "#d5c397",
 	"Wikitext":                       "#fc5757",
 	"Windows Registry Entries":       "#52d5ff",
 	"Witcher Script":                 "#ff0000",
@@ -490,6 +499,7 @@ var LanguagesColor = map[string]string{
 	"YARA":                           "#220000",
 	"YASnippet":                      "#32AB90",
 	"Yacc":                           "#4B6C4B",
+	"Yul":                            "#794932",
 	"ZAP":                            "#0d665e",
 	"ZIL":                            "#dc75e5",
 	"ZenScript":                      "#00BCD1",

data/commit.go

@@ -1,7 +1,7 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
 // linguist's commit from which files were generated.
-var LinguistCommit = "4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26"
+var LinguistCommit = "d7799da826e01acdb8f84694d33116dccaabe9c2"

data/content.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -638,6 +638,10 @@ var ContentHeuristics = map[string]*Heuristics{
 			rule.MatchingLanguages("BitBake"),
 			regexp.MustCompile(`(?m)^\s*(# |include|require)\b`),
 		),
+		rule.Or(
+			rule.MatchingLanguages("Clojure"),
+			regexp.MustCompile(`(?m)\((def|defn|defmacro|let)\s`),
+		),
 	},
 	".bi": &Heuristics{
 		rule.Or(
@@ -645,6 +649,7 @@ var ContentHeuristics = map[string]*Heuristics{
 			regexp.MustCompile(`(?m)^[ \t]*#(?:define|endif|endmacro|ifn?def|if|include|lang|macro)\s`),
 		),
 	},
+	".bs": &Heuristics{},
 	".builds": &Heuristics{
 		rule.Or(
 			rule.MatchingLanguages("XML"),
@@ -1472,6 +1477,16 @@ var ContentHeuristics = map[string]*Heuristics{
 			regexp.MustCompile(`(?m)\A\s*[\[{(^"'\w#]|[a-zA-Z_]\w*\s*:=\s*[a-zA-Z_]\w*|class\s*>>\s*[a-zA-Z_]\w*|^[a-zA-Z_]\w*\s+[a-zA-Z_]\w*:|^Class\s*{|if(?:True|False):\s*\[`),
 		),
 	},
+	".star": &Heuristics{
+		rule.Or(
+			rule.MatchingLanguages("STAR"),
+			regexp.MustCompile(`(?m)^loop_\s*$`),
+		),
+		rule.Always(
+			rule.MatchingLanguages("Starlark"),
+		),
+	},
+	".stl": &Heuristics{},
 	".t": &Heuristics{
 		rule.Or(
 			rule.MatchingLanguages("Perl"),

data/documentation.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 

data/extension.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -18,7 +18,9 @@ var LanguagesByExtension = map[string][]string{
 	".3qt":                 {"Roff", "Roff Manpage"},
 	".3x":                  {"Roff", "Roff Manpage"},
 	".4":                   {"Roff", "Roff Manpage"},
+	".4dform":              {"JSON"},
 	".4dm":                 {"4D"},
+	".4dproject":           {"JSON"},
 	".4gl":                 {"Genero"},
 	".4th":                 {"Forth"},
 	".5":                   {"Roff", "Roff Manpage"},
@@ -59,6 +61,9 @@ var LanguagesByExtension = map[string][]string{
 	".angelscript":         {"AngelScript"},
 	".anim":                {"Unity3D Asset"},
 	".ant":                 {"XML"},
+	".antlers.html":        {"Antlers"},
+	".antlers.php":         {"Antlers"},
+	".antlers.xml":         {"Antlers"},
 	".apacheconf":          {"ApacheConf"},
 	".apib":                {"API Blueprint"},
 	".apl":                 {"APL"},
@@ -106,7 +111,7 @@ var LanguagesByExtension = map[string][]string{
 	".bash":                {"Shell"},
 	".bat":                 {"Batchfile"},
 	".bats":                {"Shell"},
-	".bb":                  {"BitBake", "BlitzBasic"},
+	".bb":                  {"BitBake", "BlitzBasic", "Clojure"},
 	".bbx":                 {"TeX"},
 	".bdf":                 {"Glyph Bitmap Distribution Format"},
 	".bdy":                 {"PLSQL"},
@@ -128,6 +133,7 @@ var LanguagesByExtension = map[string][]string{
 	".brd":                 {"Eagle", "KiCad Legacy Layout"},
 	".bro":                 {"Zeek"},
 	".brs":                 {"Brightscript"},
+	".bs":                  {"Bikeshed", "BrighterScript"},
 	".bsl":                 {"1C Enterprise"},
 	".bsv":                 {"Bluespec"},
 	".builder":             {"Ruby"},
@@ -151,6 +157,7 @@ var LanguagesByExtension = map[string][]string{
 	".ccxml":               {"XML"},
 	".cdc":                 {"Cadence"},
 	".cdf":                 {"Mathematica"},
+	".cds":                 {"CAP CDS"},
 	".ceylon":              {"Ceylon"},
 	".cfc":                 {"ColdFusion CFC"},
 	".cfg":                 {"HAProxy", "INI"},
@@ -206,6 +213,7 @@ var LanguagesByExtension = map[string][]string{
 	".cpy":                 {"COBOL"},
 	".cql":                 {"SQL"},
 	".cr":                  {"Crystal"},
+	".crc32":               {"Checksums"},
 	".creole":              {"Creole"},
 	".cs":                  {"C#", "Smalltalk"},
 	".csc":                 {"GSC"},
@@ -222,6 +230,7 @@ var LanguagesByExtension = map[string][]string{
 	".csx":                 {"C#"},
 	".ct":                  {"XML"},
 	".ctp":                 {"PHP"},
+	".cts":                 {"TypeScript"},
 	".cu":                  {"Cuda"},
 	".cue":                 {"CUE", "Cue Sheet"},
 	".cuh":                 {"Cuda"},
@@ -350,6 +359,7 @@ var LanguagesByExtension = map[string][]string{
 	".fsi":                 {"F#"},
 	".fsproj":              {"XML"},
 	".fst":                 {"F*"},
+	".fsti":                {"F*"},
 	".fsx":                 {"F#"},
 	".fth":                 {"Forth"},
 	".ftl":                 {"Fluent", "FreeMarker"},
@@ -540,6 +550,7 @@ var LanguagesByExtension = map[string][]string{
 	".kak":                 {"KakouneScript"},
 	".kicad_mod":           {"KiCad Layout"},
 	".kicad_pcb":           {"KiCad Layout"},
+	".kicad_sch":           {"KiCad Schematic"},
 	".kicad_wks":           {"KiCad Layout"},
 	".kid":                 {"Genshi"},
 	".kit":                 {"Kit"},
@@ -579,6 +590,7 @@ var LanguagesByExtension = map[string][]string{
 	".liquid":              {"Liquid"},
 	".lisp":                {"Common Lisp", "NewLisp"},
 	".litcoffee":           {"Literate CoffeeScript"},
+	".livemd":              {"Markdown"},
 	".ll":                  {"LLVM"},
 	".lmi":                 {"Python"},
 	".logtalk":             {"Logtalk"},
@@ -591,6 +603,7 @@ var LanguagesByExtension = map[string][]string{
 	".lsp":                 {"Common Lisp", "NewLisp"},
 	".ltx":                 {"TeX"},
 	".lua":                 {"Lua"},
+	".lvclass":             {"LabVIEW"},
 	".lvlib":               {"LabVIEW"},
 	".lvproj":              {"LabVIEW"},
 	".ly":                  {"LilyPond"},
@@ -623,6 +636,9 @@ var LanguagesByExtension = map[string][]string{
 	".mcmeta":              {"JSON"},
 	".mcr":                 {"MAXScript"},
 	".md":                  {"GCC Machine Description", "Markdown"},
+	".md2":                 {"Checksums"},
+	".md4":                 {"Checksums"},
+	".md5":                 {"Checksums"},
 	".mdoc":                {"Roff", "Roff Manpage"},
 	".mdown":               {"Markdown"},
 	".mdpolicy":            {"XML"},
@@ -664,16 +680,20 @@ var LanguagesByExtension = map[string][]string{
 	".monkey2":             {"Monkey"},
 	".moo":                 {"Mercury", "Moocode"},
 	".moon":                {"MoonScript"},
+	".mpl":                 {"JetBrains MPS"},
+	".mps":                 {"JetBrains MPS"},
 	".mq4":                 {"MQL4"},
 	".mq5":                 {"MQL5"},
 	".mqh":                 {"MQL4", "MQL5"},
 	".mrc":                 {"mIRC Script"},
 	".ms":                  {"MAXScript", "Roff", "Unix Assembly"},
+	".msd":                 {"JetBrains MPS"},
 	".mspec":               {"Ruby"},
 	".mss":                 {"CartoCSS"},
 	".mt":                  {"Mathematica"},
 	".mtl":                 {"Wavefront Material"},
 	".mtml":                {"MTML"},
+	".mts":                 {"TypeScript"},
 	".mu":                  {"mupad"},
 	".mud":                 {"ZIL"},
 	".muf":                 {"MUF"},
@@ -819,6 +839,7 @@ var LanguagesByExtension = map[string][]string{
 	".podspec":             {"Ruby"},
 	".pogo":                {"PogoScript"},
 	".pony":                {"Pony"},
+	".por":                 {"Portugol"},
 	".postcss":             {"PostCSS"},
 	".pot":                 {"Gettext Catalog"},
 	".pov":                 {"POV-Ray SDL"},
@@ -978,6 +999,14 @@ var LanguagesByExtension = map[string][]string{
 	".sh":                  {"Shell"},
 	".sh-session":          {"ShellSession"},
 	".sh.in":               {"Shell"},
+	".sha1":                {"Checksums"},
+	".sha2":                {"Checksums"},
+	".sha224":              {"Checksums"},
+	".sha256":              {"Checksums"},
+	".sha256sum":           {"Checksums"},
+	".sha3":                {"Checksums"},
+	".sha384":              {"Checksums"},
+	".sha512":              {"Checksums"},
 	".shader":              {"GLSL", "ShaderLab"},
 	".shen":                {"Shen"},
 	".shproj":              {"XML"},
@@ -1021,7 +1050,9 @@ var LanguagesByExtension = map[string][]string{
 	".sss":                 {"SugarSS"},
 	".st":                  {"Smalltalk", "StringTemplate"},
 	".stan":                {"Stan"},
+	".star":                {"STAR", "Starlark"},
 	".sthlp":               {"Stata"},
+	".stl":                 {"STL"},
 	".ston":                {"STON"},
 	".story":               {"Gherkin"},
 	".storyboard":          {"XML"},
@@ -1166,6 +1197,7 @@ var LanguagesByExtension = map[string][]string{
 	".webidl":              {"WebIDL"},
 	".webmanifest":         {"JSON"},
 	".weechatlog":          {"IRC log"},
+	".whiley":              {"Whiley"},
 	".wiki":                {"Wikitext"},
 	".wikitext":            {"Wikitext"},
 	".wisp":                {"wisp"},
@@ -1245,6 +1277,7 @@ var LanguagesByExtension = map[string][]string{
 	".yml":                 {"YAML"},
 	".yml.mysql":           {"YAML"},
 	".yrl":                 {"Erlang"},
+	".yul":                 {"Yul"},
 	".yy":                  {"JSON", "Yacc"},
 	".yyp":                 {"JSON"},
 	".zap":                 {"ZAP"},
@@ -1287,6 +1320,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Alloy":                              {".als"},
 	"Altium Designer":                    {".outjob", ".pcbdoc", ".prjpcb", ".schdoc"},
 	"AngelScript":                        {".as", ".angelscript"},
+	"Antlers":                            {".antlers.html", ".antlers.php", ".antlers.xml"},
 	"ApacheConf":                         {".apacheconf", ".vhost"},
 	"Apex":                               {".cls"},
 	"Apollo Guidance Computer":           {".agc"},
@@ -1310,6 +1344,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Berry":                              {".be"},
 	"BibTeX":                             {".bib", ".bibtex"},
 	"Bicep":                              {".bicep"},
+	"Bikeshed":                           {".bs"},
 	"Bison":                              {".bison"},
 	"BitBake":                            {".bb"},
 	"Blade":                              {".blade", ".blade.php"},
@@ -1319,12 +1354,14 @@ var ExtensionsByLanguage = map[string][]string{
 	"Boo":                                {".boo"},
 	"Boogie":                             {".bpl"},
 	"Brainfuck":                          {".b", ".bf"},
+	"BrighterScript":                     {".bs"},
 	"Brightscript":                       {".brs"},
 	"C":                                  {".c", ".cats", ".h", ".idc"},
 	"C#":                                 {".cs", ".cake", ".csx", ".linq"},
 	"C++":                                {".cpp", ".c++", ".cc", ".cp", ".cxx", ".h", ".h++", ".hh", ".hpp", ".hxx", ".inc", ".inl", ".ino", ".ipp", ".ixx", ".re", ".tcc", ".tpp"},
 	"C-ObjDump":                          {".c-objdump"},
 	"C2hs Haskell":                       {".chs"},
+	"CAP CDS":                            {".cds"},
 	"CIL":                                {".cil"},
 	"CLIPS":                              {".clp"},
 	"CMake":                              {".cmake", ".cmake.in"},
@@ -1344,6 +1381,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Ceylon":                             {".ceylon"},
 	"Chapel":                             {".chpl"},
 	"Charity":                            {".ch"},
+	"Checksums":                          {".crc32", ".md2", ".md4", ".md5", ".sha1", ".sha2", ".sha224", ".sha256", ".sha256sum", ".sha3", ".sha384", ".sha512"},
 	"ChucK":                              {".ck"},
 	"Cirru":                              {".cirru"},
 	"Clarion":                            {".clw"},
@@ -1351,7 +1389,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Classic ASP":                        {".asp"},
 	"Clean":                              {".icl", ".dcl"},
 	"Click":                              {".click"},
-	"Clojure":                            {".clj", ".boot", ".cl2", ".cljc", ".cljs", ".cljs.hl", ".cljscm", ".cljx", ".hic"},
+	"Clojure":                            {".clj", ".bb", ".boot", ".cl2", ".cljc", ".cljs", ".cljs.hl", ".cljscm", ".cljx", ".hic"},
 	"Closure Templates":                  {".soy"},
 	"CoNLL-U":                            {".conllu", ".conll"},
 	"CodeQL":                             {".ql", ".qll"},
@@ -1411,7 +1449,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Erlang":                             {".erl", ".app.src", ".es", ".escript", ".hrl", ".xrl", ".yrl"},
 	"Euphoria":                           {".e", ".ex"},
 	"F#":                                 {".fs", ".fsi", ".fsx"},
-	"F*":                                 {".fst"},
+	"F*":                                 {".fst", ".fsti"},
 	"FIGlet Font":                        {".flf"},
 	"FLUX":                               {".fx", ".flux"},
 	"Factor":                             {".factor"},
@@ -1502,7 +1540,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Isabelle":                           {".thy"},
 	"J":                                  {".ijs"},
 	"JFlex":                              {".flex", ".jflex"},
-	"JSON":                               {".json", ".avsc", ".geojson", ".gltf", ".har", ".ice", ".json-tmlanguage", ".jsonl", ".mcmeta", ".tfstate", ".tfstate.backup", ".topojson", ".webapp", ".webmanifest", ".yy", ".yyp"},
+	"JSON":                               {".json", ".4dform", ".4dproject", ".avsc", ".geojson", ".gltf", ".har", ".ice", ".json-tmlanguage", ".jsonl", ".mcmeta", ".tfstate", ".tfstate.backup", ".topojson", ".webapp", ".webmanifest", ".yy", ".yyp"},
 	"JSON with Comments":                 {".jsonc", ".code-snippets", ".sublime-build", ".sublime-commands", ".sublime-completions", ".sublime-keymap", ".sublime-macro", ".sublime-menu", ".sublime-mousemap", ".sublime-project", ".sublime-settings", ".sublime-theme", ".sublime-workspace", ".sublime_metrics", ".sublime_session"},
 	"JSON5":                              {".json5"},
 	"JSONLD":                             {".jsonld"},
@@ -1515,6 +1553,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"JavaScript":                         {".js", "._js", ".bones", ".cjs", ".es", ".es6", ".frag", ".gs", ".jake", ".javascript", ".jsb", ".jscad", ".jsfl", ".jslib", ".jsm", ".jspre", ".jss", ".jsx", ".mjs", ".njs", ".pac", ".sjs", ".ssjs", ".xsjs", ".xsjslib"},
 	"JavaScript+ERB":                     {".js.erb"},
 	"Jest Snapshot":                      {".snap"},
+	"JetBrains MPS":                      {".mps", ".mpl", ".msd"},
 	"Jinja":                              {".jinja", ".j2", ".jinja2"},
 	"Jison":                              {".jison"},
 	"Jison Lex":                          {".jisonlex"},
@@ -1527,7 +1566,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"KakouneScript":                      {".kak"},
 	"KiCad Layout":                       {".kicad_pcb", ".kicad_mod", ".kicad_wks"},
 	"KiCad Legacy Layout":                {".brd"},
-	"KiCad Schematic":                    {".sch"},
+	"KiCad Schematic":                    {".kicad_sch", ".sch"},
 	"Kit":                                {".kit"},
 	"Kotlin":                             {".kt", ".ktm", ".kts"},
 	"Kusto":                              {".csl"},
@@ -1536,7 +1575,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"LOLCODE":                            {".lol"},
 	"LSL":                                {".lsl", ".lslp"},
 	"LTspice Symbol":                     {".asy"},
-	"LabVIEW":                            {".lvproj", ".lvlib"},
+	"LabVIEW":                            {".lvproj", ".lvclass", ".lvlib"},
 	"Lark":                               {".lark"},
 	"Lasso":                              {".lasso", ".las", ".lasso8", ".lasso9"},
 	"Latte":                              {".latte"},
@@ -1571,7 +1610,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Macaulay2":                          {".m2"},
 	"Makefile":                           {".mak", ".d", ".make", ".makefile", ".mk", ".mkfile"},
 	"Mako":                               {".mako", ".mao"},
-	"Markdown":                           {".md", ".markdown", ".mdown", ".mdwn", ".mdx", ".mkd", ".mkdn", ".mkdown", ".ronn", ".scd", ".workbook"},
+	"Markdown":                           {".md", ".livemd", ".markdown", ".mdown", ".mdwn", ".mdx", ".mkd", ".mkdn", ".mkdown", ".ronn", ".scd", ".workbook"},
 	"Marko":                              {".marko"},
 	"Mask":                               {".mask"},
 	"Mathematica":                        {".mathematica", ".cdf", ".m", ".ma", ".mt", ".nb", ".nbp", ".wl", ".wlt"},
@@ -1665,6 +1704,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Pod 6":                              {".pod", ".pod6"},
 	"PogoScript":                         {".pogo"},
 	"Pony":                               {".pony"},
+	"Portugol":                           {".por"},
 	"PostCSS":                            {".pcss", ".postcss"},
 	"PostScript":                         {".ps", ".eps", ".epsi", ".pfa"},
 	"PowerBuilder":                       {".pbt", ".sra", ".sru", ".srw"},
@@ -1731,6 +1771,8 @@ var ExtensionsByLanguage = map[string][]string{
 	"SQL":                                {".sql", ".cql", ".ddl", ".inc", ".mysql", ".prc", ".tab", ".udf", ".viw"},
 	"SQLPL":                              {".sql", ".db2"},
 	"SRecode Template":                   {".srt"},
+	"STAR":                               {".star"},
+	"STL":                                {".stl"},
 	"STON":                               {".ston"},
 	"SVG":                                {".svg"},
 	"SWIG":                               {".i"},
@@ -1760,7 +1802,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Squirrel":                           {".nut"},
 	"Stan":                               {".stan"},
 	"Standard ML":                        {".ml", ".fun", ".sig", ".sml"},
-	"Starlark":                           {".bzl"},
+	"Starlark":                           {".bzl", ".star"},
 	"Stata":                              {".do", ".ado", ".doh", ".ihlp", ".mata", ".matah", ".sthlp"},
 	"StringTemplate":                     {".st"},
 	"Stylus":                             {".styl"},
@@ -1791,7 +1833,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Turtle":                             {".ttl"},
 	"Twig":                               {".twig"},
 	"Type Language":                      {".tl"},
-	"TypeScript":                         {".ts"},
+	"TypeScript":                         {".ts", ".cts", ".mts"},
 	"Unified Parallel C":                 {".upc"},
 	"Unity3D Asset":                      {".anim", ".asset", ".mask", ".mat", ".meta", ".prefab", ".unity"},
 	"Unix Assembly":                      {".s", ".ms"},
@@ -1819,6 +1861,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"WebAssembly":                        {".wast", ".wat"},
 	"WebIDL":                             {".webidl"},
 	"WebVTT":                             {".vtt"},
+	"Whiley":                             {".whiley"},
 	"Wikitext":                           {".mediawiki", ".wiki", ".wikitext"},
 	"Win32 Message File":                 {".mc"},
 	"Windows Registry Entries":           {".reg"},
@@ -1844,6 +1887,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"YARA":                               {".yar", ".yara"},
 	"YASnippet":                          {".yasnippet"},
 	"Yacc":                               {".y", ".yacc", ".yy"},
+	"Yul":                                {".yul"},
 	"ZAP":                                {".zap", ".xzap"},
 	"ZIL":                                {".zil", ".mud"},
 	"Zeek":                               {".zeek", ".bro"},

data/filename.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -24,10 +24,12 @@ var LanguagesByFilename = map[string][]string{
 	".clang-tidy":                  {"YAML"},
 	".classpath":                   {"XML"},
 	".coffeelintignore":            {"Ignore List"},
+	".coveragerc":                  {"INI"},
 	".cproject":                    {"XML"},
 	".cshrc":                       {"Shell"},
 	".curlrc":                      {"cURL Config"},
 	".cvsignore":                   {"Ignore List"},
+	".devcontainer.json":           {"JSON with Comments"},
 	".dir_colors":                  {"dircolors"},
 	".dircolors":                   {"dircolors"},
 	".dockerignore":                {"Ignore List"},
@@ -46,6 +48,7 @@ var LanguagesByFilename = map[string][]string{
 	".flaskenv":                    {"Shell"},
 	".gclient":                     {"Python"},
 	".gemrc":                       {"YAML"},
+	".git-blame-ignore-revs":       {"Git Revision List"},
 	".gitattributes":               {"Git Attributes"},
 	".gitconfig":                   {"Git Config"},
 	".gitignore":                   {"Ignore List"},
@@ -78,6 +81,7 @@ var LanguagesByFilename = map[string][]string{
 	".profile":                     {"Shell"},
 	".project":                     {"XML"},
 	".pryrc":                       {"Ruby"},
+	".pylintrc":                    {"INI"},
 	".shellcheckrc":                {"ShellCheck Config"},
 	".simplecov":                   {"Ruby"},
 	".spacemacs":                   {"Emacs Lisp"},
@@ -146,6 +150,7 @@ var LanguagesByFilename = map[string][]string{
 	"LICENSE.mysql":                {"Text"},
 	"Lexer.x":                      {"Lex"},
 	"MANIFEST.MF":                  {"JAR Manifest"},
+	"MD5SUMS":                      {"Checksums"},
 	"Makefile":                     {"Makefile"},
 	"Makefile.PL":                  {"Perl"},
 	"Makefile.am":                  {"Makefile"},
@@ -176,6 +181,10 @@ var LanguagesByFilename = map[string][]string{
 	"Rexfile":                      {"Perl"},
 	"SConscript":                   {"Python"},
 	"SConstruct":                   {"Python"},
+	"SHA1SUMS":                     {"Checksums"},
+	"SHA256SUMS":                   {"Checksums"},
+	"SHA256SUMS.txt":               {"Checksums"},
+	"SHA512SUMS":                   {"Checksums"},
 	"Settings.StyleCop":            {"XML"},
 	"Singularity":                  {"Singularity"},
 	"Slakefile":                    {"LiveScript"},
@@ -211,6 +220,8 @@ var LanguagesByFilename = map[string][]string{
 	"buildozer.spec":               {"INI"},
 	"cabal.config":                 {"Cabal Config"},
 	"cabal.project":                {"Cabal Config"},
+	"checksums.txt":                {"Checksums"},
+	"cksums":                       {"Checksums"},
 	"click.me":                     {"Text"},
 	"composer.lock":                {"JSON"},
 	"configure.ac":                 {"M4Sugar"},
@@ -259,6 +270,7 @@ var LanguagesByFilename = map[string][]string{
 	"makefile.sco":                 {"Makefile"},
 	"man":                          {"Shell"},
 	"mcmod.info":                   {"JSON"},
+	"md5sum.txt":                   {"Checksums"},
 	"meson.build":                  {"Meson"},
 	"meson_options.txt":            {"Meson"},
 	"mix.lock":                     {"Elixir"},
@@ -279,6 +291,7 @@ var LanguagesByFilename = map[string][]string{
 	"pom.xml":                      {"Maven POM"},
 	"port_contexts":                {"SELinux Policy"},
 	"profile":                      {"Shell"},
+	"pylintrc":                     {"INI"},
 	"read.me":                      {"Text"},
 	"readme.1st":                   {"Text"},
 	"rebar.config":                 {"Erlang"},

data/generated.go

@@ -74,7 +74,7 @@ var GeneratedCodeNameMatchers = []GeneratedCodeNameMatcher{
 	nameEndsWith("package-lock.json"),
 
 	// Yarn plugnplay
-	nameMatches(`(^|\/)\.pnp\.(c|m)?js$`),
+	nameMatches(`(^|\/)\.pnp\..*$`),
 
 	// Godeps
 	nameContains("Godeps/"),
@@ -113,6 +113,7 @@ var GeneratedCodeMatchers = []GeneratedCodeMatcher{
 	isGeneratedJavaScriptPEGParser,
 	isGeneratedPostScript,
 	isGeneratedGo,
+	isGeneratedProtobufFromGo,
 	isGeneratedProtobuf,
 	isGeneratedJavaScriptProtocolBuffer,
 	isGeneratedApacheThrift,
@@ -339,6 +340,24 @@ func isGeneratedGo(_, ext string, content []byte) bool {
 	return false
 }
 
+func isGeneratedProtobufFromGo(_, ext string, content []byte) bool {
+	if ext != ".proto" {
+		return false
+	}
+	lines := getLines(content, 20)
+	if len(lines) <= 1 {
+		return false
+	}
+
+	for _, line := range lines {
+		if bytes.Contains(line, []byte("This file was autogenerated by go-to-protobuf")) {
+			return true
+		}
+	}
+
+	return false
+}
+
 var protoExtensions = map[string]struct{}{
 	".py":   {},
 	".java": {},

data/groups.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 

data/id.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -30,6 +30,7 @@ var IDByLanguage = map[string]int{
 	"Altium Designer":                    187772328,
 	"AngelScript":                        389477596,
 	"Ant Build System":                   15,
+	"Antlers":                            1067292663,
 	"ApacheConf":                         16,
 	"Apex":                               17,
 	"Apollo Guidance Computer":           18,
@@ -53,6 +54,7 @@ var IDByLanguage = map[string]int{
 	"Berry":                              121855308,
 	"BibTeX":                             982188347,
 	"Bicep":                              321200902,
+	"Bikeshed":                           1055528081,
 	"Bison":                              31,
 	"BitBake":                            32,
 	"Blade":                              33,
@@ -62,6 +64,7 @@ var IDByLanguage = map[string]int{
 	"Boo":                                37,
 	"Boogie":                             955017407,
 	"Brainfuck":                          38,
+	"BrighterScript":                     943571030,
 	"Brightscript":                       39,
 	"Browserslist":                       153503348,
 	"C":                                  41,
@@ -69,6 +72,7 @@ var IDByLanguage = map[string]int{
 	"C++":                                43,
 	"C-ObjDump":                          44,
 	"C2hs Haskell":                       45,
+	"CAP CDS":                            390788699,
 	"CIL":                                29176339,
 	"CLIPS":                              46,
 	"CMake":                              47,
@@ -89,6 +93,7 @@ var IDByLanguage = map[string]int{
 	"Ceylon":                             54,
 	"Chapel":                             55,
 	"Charity":                            56,
+	"Checksums":                          372063053,
 	"ChucK":                              57,
 	"Cirru":                              58,
 	"Clarion":                            59,
@@ -202,6 +207,7 @@ var IDByLanguage = map[string]int{
 	"Gherkin":                            76,
 	"Git Attributes":                     956324166,
 	"Git Config":                         807968997,
+	"Git Revision List":                  461881235,
 	"Gleam":                              1054258749,
 	"Glyph":                              130,
 	"Glyph Bitmap Distribution Format":   997665271,
@@ -269,6 +275,7 @@ var IDByLanguage = map[string]int{
 	"JavaScript":                         183,
 	"JavaScript+ERB":                     914318960,
 	"Jest Snapshot":                      774635084,
+	"JetBrains MPS":                      465165328,
 	"Jinja":                              147,
 	"Jison":                              284531423,
 	"Jison Lex":                          406395330,
@@ -423,6 +430,7 @@ var IDByLanguage = map[string]int{
 	"Pod 6":                              155357471,
 	"PogoScript":                         289,
 	"Pony":                               290,
+	"Portugol":                           832391833,
 	"PostCSS":                            262764437,
 	"PostScript":                         291,
 	"PowerBuilder":                       292,
@@ -496,6 +504,8 @@ var IDByLanguage = map[string]int{
 	"SQLPL":                              334,
 	"SRecode Template":                   335,
 	"SSH Config":                         554920715,
+	"STAR":                               424510560,
+	"STL":                                455361735,
 	"STON":                               336,
 	"SVG":                                337,
 	"SWIG":                               1066250075,
@@ -589,6 +599,7 @@ var IDByLanguage = map[string]int{
 	"WebIDL":                             395,
 	"WebVTT":                             658679714,
 	"Wget Config":                        668457123,
+	"Whiley":                             888779559,
 	"Wikitext":                           228,
 	"Win32 Message File":                 950967261,
 	"Windows Registry Entries":           969674868,
@@ -616,6 +627,7 @@ var IDByLanguage = map[string]int{
 	"YARA":                               805122868,
 	"YASnippet":                          378760102,
 	"Yacc":                               409,
+	"Yul":                                237469033,
 	"ZAP":                                952972794,
 	"ZIL":                                973483626,
 	"Zeek":                               40,

data/interpreter.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -13,6 +13,7 @@ var LanguagesByInterpreter = map[string][]string{
 	"asy":         {"Asymptote"},
 	"awk":         {"Awk"},
 	"bash":        {"Shell"},
+	"bb":          {"Clojure"},
 	"bigloo":      {"Scheme"},
 	"boogie":      {"Boogie"},
 	"boolector":   {"SMT"},

data/languageInfo.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -584,6 +584,27 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     15,
 	},
+	1067292663: LanguageInfo{
+		Name:    "Antlers",
+		FSName:  "",
+		Type:    TypeForString("markup"),
+		Color:   "#ff269e",
+		Group:   "",
+		Aliases: []string{},
+		Extensions: []string{
+			".antlers.html",
+			".antlers.php",
+			".antlers.xml",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "",
+		TMScope:        "text.html.statamic",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     1067292663,
+	},
 	16: LanguageInfo{
 		Name:   "ApacheConf",
 		FSName: "",
@@ -1070,6 +1091,25 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     321200902,
 	},
+	1055528081: LanguageInfo{
+		Name:    "Bikeshed",
+		FSName:  "",
+		Type:    TypeForString("markup"),
+		Color:   "#5562ac",
+		Group:   "",
+		Aliases: []string{},
+		Extensions: []string{
+			".bs",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "text/html",
+		TMScope:        "source.csswg",
+		AceMode:        "html",
+		CodeMirrorMode: "htmlmixed",
+		Wrap:           false,
+		LanguageID:     1055528081,
+	},
 	31: LanguageInfo{
 		Name:    "Bison",
 		FSName:  "",
@@ -1253,6 +1293,25 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     38,
 	},
+	943571030: LanguageInfo{
+		Name:    "BrighterScript",
+		FSName:  "",
+		Type:    TypeForString("programming"),
+		Color:   "#66AABB",
+		Group:   "",
+		Aliases: []string{},
+		Extensions: []string{
+			".bs",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "",
+		TMScope:        "source.brs",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     943571030,
+	},
 	39: LanguageInfo{
 		Name:    "Brightscript",
 		FSName:  "",
@@ -1266,7 +1325,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Interpreters:   []string{},
 		Filenames:      []string{},
 		MimeType:       "",
-		TMScope:        "source.brightscript",
+		TMScope:        "source.brs",
 		AceMode:        "text",
 		CodeMirrorMode: "",
 		Wrap:           false,
@@ -1420,6 +1479,27 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     45,
 	},
+	390788699: LanguageInfo{
+		Name:   "CAP CDS",
+		FSName: "",
+		Type:   TypeForString("programming"),
+		Color:  "#0092d1",
+		Group:  "",
+		Aliases: []string{
+			"cds",
+		},
+		Extensions: []string{
+			".cds",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "",
+		TMScope:        "source.cds",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     390788699,
+	},
 	29176339: LanguageInfo{
 		Name:    "CIL",
 		FSName:  "",
@@ -1816,6 +1896,51 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     56,
 	},
+	372063053: LanguageInfo{
+		Name:   "Checksums",
+		FSName: "",
+		Type:   TypeForString("data"),
+		Color:  "",
+		Group:  "",
+		Aliases: []string{
+			"checksum",
+			"hash",
+			"hashes",
+			"sum",
+			"sums",
+		},
+		Extensions: []string{
+			".crc32",
+			".md2",
+			".md4",
+			".md5",
+			".sha1",
+			".sha2",
+			".sha224",
+			".sha256",
+			".sha256sum",
+			".sha3",
+			".sha384",
+			".sha512",
+		},
+		Interpreters: []string{},
+		Filenames: []string{
+			"MD5SUMS",
+			"SHA1SUMS",
+			"SHA256SUMS",
+			"SHA256SUMS.txt",
+			"SHA512SUMS",
+			"checksums.txt",
+			"cksums",
+			"md5sum.txt",
+		},
+		MimeType:       "",
+		TMScope:        "text.checksums",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     372063053,
+	},
 	57: LanguageInfo{
 		Name:    "ChucK",
 		FSName:  "",
@@ -1961,6 +2086,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Aliases: []string{},
 		Extensions: []string{
 			".clj",
+			".bb",
 			".boot",
 			".cl2",
 			".cljc",
@@ -1970,7 +2096,9 @@ var LanguageInfoByID = map[int]LanguageInfo{
 			".cljx",
 			".hic",
 		},
-		Interpreters: []string{},
+		Interpreters: []string{
+			"bb",
+		},
 		Filenames: []string{
 			"riemann.config",
 		},
@@ -3328,6 +3456,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		},
 		Extensions: []string{
 			".fst",
+			".fsti",
 		},
 		Interpreters:   []string{},
 		Filenames:      []string{},
@@ -4239,6 +4368,27 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     807968997,
 	},
+	461881235: LanguageInfo{
+		Name:   "Git Revision List",
+		FSName: "",
+		Type:   TypeForString("data"),
+		Color:  "#F44D27",
+		Group:  "",
+		Aliases: []string{
+			"Git Blame Ignore Revs",
+		},
+		Extensions:   []string{},
+		Interpreters: []string{},
+		Filenames: []string{
+			".git-blame-ignore-revs",
+		},
+		MimeType:       "",
+		TMScope:        "source.git-revlist",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     461881235,
+	},
 	1054258749: LanguageInfo{
 		Name:    "Gleam",
 		FSName:  "",
@@ -5115,8 +5265,11 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		},
 		Interpreters: []string{},
 		Filenames: []string{
+			".coveragerc",
 			".flake8",
+			".pylintrc",
 			"buildozer.spec",
+			"pylintrc",
 		},
 		MimeType:       "text/x-properties",
 		TMScope:        "source.ini",
@@ -5415,14 +5568,20 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		LanguageID:     173,
 	},
 	174: LanguageInfo{
-		Name:    "JSON",
+		Name:   "JSON",
-		FSName:  "",
+		FSName: "",
-		Type:    TypeForString("data"),
+		Type:   TypeForString("data"),
-		Color:   "#292929",
+		Color:  "#292929",
-		Group:   "",
+		Group:  "",
-		Aliases: []string{},
+		Aliases: []string{
+			"geojson",
+			"jsonl",
+			"topojson",
+		},
 		Extensions: []string{
 			".json",
+			".4DForm",
+			".4DProject",
 			".avsc",
 			".geojson",
 			".gltf",
@@ -5490,6 +5649,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Interpreters: []string{},
 		Filenames: []string{
 			".babelrc",
+			".devcontainer.json",
 			".eslintrc.json",
 			".jscsrc",
 			".jshintrc",
@@ -5762,6 +5922,29 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     774635084,
 	},
+	465165328: LanguageInfo{
+		Name:   "JetBrains MPS",
+		FSName: "",
+		Type:   TypeForString("programming"),
+		Color:  "#21D789",
+		Group:  "",
+		Aliases: []string{
+			"mps",
+		},
+		Extensions: []string{
+			".mps",
+			".mpl",
+			".msd",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "text/xml",
+		TMScope:        "none",
+		AceMode:        "xml",
+		CodeMirrorMode: "xml",
+		Wrap:           false,
+		LanguageID:     465165328,
+	},
 	147: LanguageInfo{
 		Name:   "Jinja",
 		FSName: "",
@@ -6030,6 +6213,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 			"eeschema schematic",
 		},
 		Extensions: []string{
+			".kicad_sch",
 			".sch",
 		},
 		Interpreters:   []string{},
@@ -6207,6 +6391,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Aliases: []string{},
 		Extensions: []string{
 			".lvproj",
+			".lvclass",
 			".lvlib",
 		},
 		Interpreters:   []string{},
@@ -6968,6 +7153,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		},
 		Extensions: []string{
 			".md",
+			".livemd",
 			".markdown",
 			".mdown",
 			".mdwn",
@@ -9056,6 +9242,25 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     290,
 	},
+	832391833: LanguageInfo{
+		Name:    "Portugol",
+		FSName:  "",
+		Type:    TypeForString("programming"),
+		Color:   "#f8bd00",
+		Group:   "",
+		Aliases: []string{},
+		Extensions: []string{
+			".por",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "",
+		TMScope:        "source.portugol",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     832391833,
+	},
 	262764437: LanguageInfo{
 		Name:    "PostCSS",
 		FSName:  "",
@@ -10764,6 +10969,47 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     554920715,
 	},
+	424510560: LanguageInfo{
+		Name:    "STAR",
+		FSName:  "",
+		Type:    TypeForString("data"),
+		Color:   "",
+		Group:   "",
+		Aliases: []string{},
+		Extensions: []string{
+			".star",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "",
+		TMScope:        "source.star",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     424510560,
+	},
+	455361735: LanguageInfo{
+		Name:   "STL",
+		FSName: "",
+		Type:   TypeForString("data"),
+		Color:  "#373b5e",
+		Group:  "",
+		Aliases: []string{
+			"ascii stl",
+			"stla",
+		},
+		Extensions: []string{
+			".stl",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "",
+		TMScope:        "source.stl",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     455361735,
+	},
 	336: LanguageInfo{
 		Name:    "STON",
 		FSName:  "",
@@ -11488,6 +11734,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		},
 		Extensions: []string{
 			".bzl",
+			".star",
 		},
 		Interpreters: []string{},
 		Filenames: []string{
@@ -11794,7 +12041,7 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Name:    "TSX",
 		FSName:  "",
 		Type:    TypeForString("programming"),
-		Color:   "#2b7489",
+		Color:   "#3178c6",
 		Group:   "TypeScript",
 		Aliases: []string{},
 		Extensions: []string{
@@ -12189,13 +12436,15 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Name:   "TypeScript",
 		FSName: "",
 		Type:   TypeForString("programming"),
-		Color:  "#2b7489",
+		Color:  "#3178c6",
 		Group:  "",
 		Aliases: []string{
 			"ts",
 		},
 		Extensions: []string{
 			".ts",
+			".cts",
+			".mts",
 		},
 		Interpreters: []string{
 			"deno",
@@ -12254,12 +12503,16 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		LanguageID:     380,
 	},
 	120: LanguageInfo{
-		Name:    "Unix Assembly",
+		Name:   "Unix Assembly",
-		FSName:  "",
+		FSName: "",
-		Type:    TypeForString("programming"),
+		Type:   TypeForString("programming"),
-		Color:   "",
+		Color:  "",
-		Group:   "Assembly",
+		Group:  "Assembly",
-		Aliases: []string{},
+		Aliases: []string{
+			"gas",
+			"gnu asm",
+			"unix asm",
+		},
 		Extensions: []string{
 			".s",
 			".ms",
@@ -12773,19 +13026,21 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		LanguageID:     395,
 	},
 	658679714: LanguageInfo{
-		Name:    "WebVTT",
+		Name:   "WebVTT",
-		FSName:  "",
+		FSName: "",
-		Type:    TypeForString("data"),
+		Type:   TypeForString("data"),
-		Color:   "",
+		Color:  "",
-		Group:   "",
+		Group:  "",
-		Aliases: []string{},
+		Aliases: []string{
+			"vtt",
+		},
 		Extensions: []string{
 			".vtt",
 		},
 		Interpreters:   []string{},
 		Filenames:      []string{},
 		MimeType:       "",
-		TMScope:        "source.vtt",
+		TMScope:        "text.vtt",
 		AceMode:        "text",
 		CodeMirrorMode: "",
 		Wrap:           true,
@@ -12812,6 +13067,25 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     668457123,
 	},
+	888779559: LanguageInfo{
+		Name:    "Whiley",
+		FSName:  "",
+		Type:    TypeForString("programming"),
+		Color:   "#d5c397",
+		Group:   "",
+		Aliases: []string{},
+		Extensions: []string{
+			".whiley",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "",
+		TMScope:        "source.whiley",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     888779559,
+	},
 	228: LanguageInfo{
 		Name:   "Wikitext",
 		FSName: "",
@@ -13502,6 +13776,25 @@ var LanguageInfoByID = map[int]LanguageInfo{
 		Wrap:           false,
 		LanguageID:     409,
 	},
+	237469033: LanguageInfo{
+		Name:    "Yul",
+		FSName:  "",
+		Type:    TypeForString("programming"),
+		Color:   "#794932",
+		Group:   "",
+		Aliases: []string{},
+		Extensions: []string{
+			".yul",
+		},
+		Interpreters:   []string{},
+		Filenames:      []string{},
+		MimeType:       "",
+		TMScope:        "source.yul",
+		AceMode:        "text",
+		CodeMirrorMode: "",
+		Wrap:           false,
+		LanguageID:     237469033,
+	},
 	952972794: LanguageInfo{
 		Name:    "ZAP",
 		FSName:  "",

data/mimeType.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -16,6 +16,7 @@ var LanguagesMime = map[string]string{
 	"Asymptote":                      "text/x-kotlin",
 	"Beef":                           "text/x-csharp",
 	"BibTeX":                         "text/x-stex",
+	"Bikeshed":                       "text/html",
 	"Brainfuck":                      "text/x-brainfuck",
 	"C":                              "text/x-csrc",
 	"C#":                             "text/x-csharp",
@@ -111,6 +112,7 @@ var LanguagesMime = map[string]string{
 	"JavaScript":                     "text/javascript",
 	"JavaScript+ERB":                 "application/javascript",
 	"Jest Snapshot":                  "application/javascript",
+	"JetBrains MPS":                  "text/xml",
 	"Jinja":                          "text/x-django",
 	"Julia":                          "text/x-julia",
 	"Jupyter Notebook":               "application/json",

data/type.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -72,6 +72,7 @@ var LanguagesType = map[string]int{
 	"Altium Designer":                    1,
 	"AngelScript":                        2,
 	"Ant Build System":                   1,
+	"Antlers":                            3,
 	"ApacheConf":                         1,
 	"Apex":                               2,
 	"Apollo Guidance Computer":           2,
@@ -95,6 +96,7 @@ var LanguagesType = map[string]int{
 	"Berry":                              2,
 	"BibTeX":                             3,
 	"Bicep":                              2,
+	"Bikeshed":                           3,
 	"Bison":                              2,
 	"BitBake":                            2,
 	"Blade":                              3,
@@ -104,6 +106,7 @@ var LanguagesType = map[string]int{
 	"Boo":                                2,
 	"Boogie":                             2,
 	"Brainfuck":                          2,
+	"BrighterScript":                     2,
 	"Brightscript":                       2,
 	"Browserslist":                       1,
 	"C":                                  2,
@@ -111,6 +114,7 @@ var LanguagesType = map[string]int{
 	"C++":                                2,
 	"C-ObjDump":                          1,
 	"C2hs Haskell":                       2,
+	"CAP CDS":                            2,
 	"CIL":                                1,
 	"CLIPS":                              2,
 	"CMake":                              2,
@@ -131,6 +135,7 @@ var LanguagesType = map[string]int{
 	"Ceylon":                             2,
 	"Chapel":                             2,
 	"Charity":                            2,
+	"Checksums":                          1,
 	"ChucK":                              2,
 	"Cirru":                              2,
 	"Clarion":                            2,
@@ -244,6 +249,7 @@ var LanguagesType = map[string]int{
 	"Gherkin":                            2,
 	"Git Attributes":                     1,
 	"Git Config":                         1,
+	"Git Revision List":                  1,
 	"Gleam":                              2,
 	"Glyph":                              2,
 	"Glyph Bitmap Distribution Format":   1,
@@ -311,6 +317,7 @@ var LanguagesType = map[string]int{
 	"JavaScript":                         2,
 	"JavaScript+ERB":                     2,
 	"Jest Snapshot":                      1,
+	"JetBrains MPS":                      2,
 	"Jinja":                              3,
 	"Jison":                              2,
 	"Jison Lex":                          2,
@@ -465,6 +472,7 @@ var LanguagesType = map[string]int{
 	"Pod 6":                              4,
 	"PogoScript":                         2,
 	"Pony":                               2,
+	"Portugol":                           2,
 	"PostCSS":                            3,
 	"PostScript":                         3,
 	"PowerBuilder":                       2,
@@ -538,6 +546,8 @@ var LanguagesType = map[string]int{
 	"SQLPL":                              2,
 	"SRecode Template":                   3,
 	"SSH Config":                         1,
+	"STAR":                               1,
+	"STL":                                1,
 	"STON":                               1,
 	"SVG":                                1,
 	"SWIG":                               2,
@@ -631,6 +641,7 @@ var LanguagesType = map[string]int{
 	"WebIDL":                             2,
 	"WebVTT":                             1,
 	"Wget Config":                        1,
+	"Whiley":                             2,
 	"Wikitext":                           4,
 	"Win32 Message File":                 1,
 	"Windows Registry Entries":           1,
@@ -658,6 +669,7 @@ var LanguagesType = map[string]int{
 	"YARA":                               2,
 	"YASnippet":                          3,
 	"Yacc":                               2,
+	"Yul":                                2,
 	"ZAP":                                2,
 	"ZIL":                                2,
 	"Zeek":                               2,

data/vendor.go

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -171,4 +171,8 @@ var VendorMatchers = []regex.EnryRegexp{
 	regex.MustCompile(`(^|/)\.google_apis/`),
 	regex.MustCompile(`(^|/)Jenkinsfile$`),
 	regex.MustCompile(`(^|/)\.gitpod\.Dockerfile$`),
+	regex.MustCompile(`(^|/)\.github/`),
 }
+
+// FastVendorMatcher is equivalent to matching any of the VendorMatchers.
+var FastVendorMatcher = regex.MustCompile(`(?:^(?:(?:[Dd]ependencies/)|(?:debian/)|(?:deps/)|(?:rebar$)))|(?:(?:^|/)(?:(?:BuddyBuildSDK\.framework/)|(?:Carthage/)|(?:Chart\.js$)|(?:Control\.FullScreen\.css)|(?:Control\.FullScreen\.js)|(?:Crashlytics\.framework/)|(?:Fabric\.framework/)|(?:Godeps/_workspace/)|(?:Jenkinsfile$)|(?:Leaflet\.Coordinates-\d+\.\d+\.\d+\.src\.js$)|(?:MathJax/)|(?:MochiKit\.js$)|(?:RealmSwift\.framework)|(?:Realm\.framework)|(?:Sparkle/)|(?:Vagrantfile$)|(?:[Bb]ourbon/.*\.(css|less|scss|styl)$)|(?:[Cc]ode[Mm]irror/(\d+\.\d+/)?(lib|mode|theme|addon|keymap|demo))|(?:[Ee]xtern(als?)?/)|(?:[Mm]icrosoft([Mm]vc)?([Aa]jax|[Vv]alidation)(\.debug)?\.js$)|(?:[Pp]ackages\/.+\.\d+\/)|(?:[Ss]pecs?/fixtures/)|(?:[Tt]ests?/fixtures/)|(?:[Vv]+endor/)|(?:\.[Dd][Ss]_[Ss]tore$)|(?:\.gitattributes$)|(?:\.github/)|(?:\.gitignore$)|(?:\.gitmodules$)|(?:\.gitpod\.Dockerfile$)|(?:\.google_apis/)|(?:\.indent\.pro)|(?:\.mvn/wrapper/)|(?:\.osx$)|(?:\.sublime-project)|(?:\.sublime-workspace)|(?:\.vscode/)|(?:\.yarn/plugins/)|(?:\.yarn/releases/)|(?:\.yarn/sdks/)|(?:\.yarn/unplugged/)|(?:\.yarn/versions/)|(?:_esy$)|(?:ace-builds/)|(?:aclocal\.m4)|(?:activator$)|(?:activator\.bat$)|(?:admin_media/)|(?:angular([^.]*)\.js$)|(?:animate\.(css|less|scss|styl)$)|(?:bootbox\.js)|(?:bootstrap([^/.]*)\.(js|css|less|scss|styl)$)|(?:bootstrap-datepicker/)|(?:bower_components/)|(?:bulma\.(css|sass|scss)$)|(?:cache/)|(?:ckeditor\.js$)|(?:config\.guess$)|(?:config\.sub$)|(?:configure$)|(?:controls\.js$)|(?:cordova([^.]*)\.js$)|(?:cordova\-\d\.\d(\.\d)?\.js$)|(?:cpplint\.py)|(?:custom\.bootstrap([^\s]*)(js|css|less|scss|styl)$)|(?:dist/)|(?:docs?/_?(build|themes?|templates?|static)/)|(?:dojo\.js$)|(?:dotnet-install\.(ps1|sh)$)|(?:dragdrop\.js$)|(?:effects\.js$)|(?:env/)|(?:erlang\.mk)|(?:extjs/.*?\.html$)|(?:extjs/.*?\.js$)|(?:extjs/.*?\.properties$)|(?:extjs/.*?\.txt$)|(?:extjs/.*?\.xml$)|(?:extjs/\.sencha/)|(?:extjs/builds/)|(?:extjs/cmd/)|(?:extjs/docs/)|(?:extjs/examples/)|(?:extjs/locale/)|(?:extjs/packages/)|(?:extjs/plugins/)|(?:extjs/resources/)|(?:extjs/src/)|(?:extjs/welcome/)|(?:fabfile\.py$)|(?:flow-typed/.*\.js$)|(?:font-?awesome/.*\.(css|less|scss|styl)$)|(?:font-?awesome\.(css|less|scss|styl)$)|(?:fontello(.*?)\.css$)|(?:foundation(\..*)?\.js$)|(?:foundation\.(css|less|scss|styl)$)|(?:fuelux\.js)|(?:gradle/wrapper/)|(?:gradlew$)|(?:gradlew\.bat$)|(?:html5shiv\.js$)|(?:inst/extdata/)|(?:jquery([^.]*)\.js$)|(?:jquery([^.]*)\.unobtrusive\-ajax\.js$)|(?:jquery([^.]*)\.validate(\.unobtrusive)?\.js$)|(?:jquery\-\d\.\d+(\.\d+)?\.js$)|(?:jquery\-ui(\-\d\.\d+(\.\d+)?)?(\.\w+)?\.(js|css)$)|(?:jquery\.(ui|effects)\.([^.]*)\.(js|css)$)|(?:jquery\.dataTables\.js)|(?:jquery\.fancybox\.(js|css))|(?:jquery\.fileupload(-\w+)?\.js$)|(?:jquery\.fn\.gantt\.js)|(?:knockout-(\d+\.){3}(debug\.)?js$)|(?:leaflet\.draw-src\.js)|(?:leaflet\.draw\.css)|(?:leaflet\.spin\.js)|(?:libtool\.m4)|(?:ltoptions\.m4)|(?:ltsugar\.m4)|(?:ltversion\.m4)|(?:lt~obsolete\.m4)|(?:materialize\.(css|less|scss|styl|js)$)|(?:modernizr\-\d\.\d+(\.\d+)?\.js$)|(?:modernizr\.custom\.\d+\.js$)|(?:mootools([^.]*)\d+\.\d+.\d+([^.]*)\.js$)|(?:mvnw$)|(?:mvnw\.cmd$)|(?:node_modules/)|(?:normalize\.(css|less|scss|styl)$)|(?:octicons\.css)|(?:pdf\.worker\.js)|(?:proguard-rules\.pro$)|(?:proguard\.pro$)|(?:prototype(.*)\.js$)|(?:puphpet/)|(?:react(-[^.]*)?\.js$)|(?:run\.n$)|(?:select2/.*\.(css|scss|js)$)|(?:shBrush([^.]*)\.js$)|(?:shCore\.js$)|(?:shLegacy\.js$)|(?:skeleton\.(css|less|scss|styl)$)|(?:slick\.\w+.js$)|(?:sprockets-octicons\.scss)|(?:testdata/)|(?:tiny_mce([^.]*)\.js$)|(?:tiny_mce/(langs|plugins|themes|utils))|(?:vendors?/)|(?:vignettes/)|(?:waf$)|(?:wicket-leaflet\.js)|(?:yahoo-([^.]*)\.js$)|(?:yui([^.]*)\.js$)))|(?:(.*?)\.d\.ts$)|(?:(3rd|[Tt]hird)[-_]?[Pp]arty/)|(?:([^\s]*)import\.(css|less|scss|styl)$)|(?:(\.|-)min\.(js|css)$)|(?:(^|\/)d3(\.v\d+)?([^.]*)\.js$)|(?:-vsdoc\.js$)|(?:\.imageset/)|(?:\.intellisense\.js$)|(?:\.xctemplate/)`)

enry.go

@@ -14,3 +14,17 @@
 package enry // import "github.com/go-enry/go-enry/v2"
 
 //go:generate make code-generate
+
+import "github.com/go-enry/go-enry/v2/data"
+
+// Type represent language's type. Either data, programming, markup, prose, or unknown.
+type Type int
+
+// Type's values.
+const (
+	Unknown     Type = Type(data.TypeUnknown)
+	Data             = Type(data.TypeData)
+	Programming      = Type(data.TypeProgramming)
+	Markup           = Type(data.TypeMarkup)
+	Prose            = Type(data.TypeProse)
+)

internal/code-generator/assets/alias.go.tmpl

@@ -22,8 +22,9 @@ func LanguageByAlias(langOrAlias string) (lang string, ok bool) {
 
 // convertToAliasKey converts language name to a key in LanguageByAliasMap.
 // Following
-//  - internal.code-generator.generator.convertToAliasKey()
+//   - internal.code-generator.generator.convertToAliasKey()
-//  - GetLanguageByAlias()
+//   - GetLanguageByAlias()
+//
 // conventions.
 // It is here to avoid dependency on "generate" and "enry" packages.
 func convertToAliasKey(langName string) string {

internal/code-generator/assets/vendor.go.tmpl

@@ -7,3 +7,6 @@ var VendorMatchers = []regex.EnryRegexp{
 	regex.MustCompile(`{{ $regexp }}`),
 	{{end -}}
 }
+
+// FastVendorMatcher is equivalent to matching any of the VendorMatchers.
+var FastVendorMatcher = regex.MustCompile(`{{ optimize . }}`)

internal/code-generator/generator/generator_test.go

@@ -19,7 +19,7 @@ import (
 var (
 	linguistURL          = "https://github.com/github/linguist.git"
 	linguistClonedEnvVar = "ENRY_TEST_REPO"
-	commit               = "4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26"
+	commit               = "d7799da826e01acdb8f84694d33116dccaabe9c2"
 	samplesDir           = "samples"
 	languagesFile        = filepath.Join("lib", "linguist", "languages.yml")
 
@@ -97,9 +97,9 @@ var (
 
 type GeneratorTestSuite struct {
 	suite.Suite
-	tmpLinguist string
+	tmpLinguistDir  string
-	cloned      bool
+	isCleanupNeeded bool
-	testCases   []testCase
+	testCases       []testCase
 }
 
 type testCase struct {
@@ -121,28 +121,32 @@ func Test_GeneratorTestSuite(t *testing.T) {
 
 func (s *GeneratorTestSuite) maybeCloneLinguist() {
 	var err error
-	s.tmpLinguist = os.Getenv(linguistClonedEnvVar)
+	s.tmpLinguistDir = os.Getenv(linguistClonedEnvVar)
-	s.cloned = s.tmpLinguist == ""
+	isLinguistCloned := s.tmpLinguistDir != ""
-	if s.cloned {
+	if !isLinguistCloned {
-		s.tmpLinguist, err = ioutil.TempDir("", "linguist-")
+		s.tmpLinguistDir, err = ioutil.TempDir("", "linguist-")
-		assert.NoError(s.T(), err)
+		require.NoError(s.T(), err)
-		cmd := exec.Command("git", "clone", linguistURL, s.tmpLinguist)
+
+		s.T().Logf("Cloning Linguist repo to '%s' as %s was not set\n",
+			s.tmpLinguistDir, linguistClonedEnvVar)
+		cmd := exec.Command("git", "clone", "--depth", "100", linguistURL, s.tmpLinguistDir)
 		err = cmd.Run()
-		assert.NoError(s.T(), err)
+		require.NoError(s.T(), err)
-
+		s.isCleanupNeeded = true
-		cwd, err := os.Getwd()
-		assert.NoError(s.T(), err)
-
-		err = os.Chdir(s.tmpLinguist)
-		assert.NoError(s.T(), err)
-
-		cmd = exec.Command("git", "checkout", commit)
-		err = cmd.Run()
-		assert.NoError(s.T(), err)
-
-		err = os.Chdir(cwd)
-		assert.NoError(s.T(), err)
 	}
+
+	cwd, err := os.Getwd()
+	require.NoError(s.T(), err)
+
+	err = os.Chdir(s.tmpLinguistDir)
+	require.NoError(s.T(), err)
+
+	cmd := exec.Command("git", "checkout", commit)
+	err = cmd.Run()
+	require.NoError(s.T(), err)
+
+	err = os.Chdir(cwd)
+	require.NoError(s.T(), err)
 }
 
 func (s *GeneratorTestSuite) SetupSuite() {
@@ -150,7 +154,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 	s.testCases = []testCase{
 		{
 			name:        "Extensions()",
-			fileToParse: filepath.Join(s.tmpLinguist, languagesFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, languagesFile),
 			samplesDir:  "",
 			tmplPath:    extensionTestTmplPath,
 			tmplName:    extensionTestTmplName,
@@ -160,7 +164,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Heuristics()",
-			fileToParse: filepath.Join(s.tmpLinguist, heuristicsTestFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, heuristicsTestFile),
 			samplesDir:  "",
 			tmplPath:    contentTestTmplPath,
 			tmplName:    contentTestTmplName,
@@ -170,7 +174,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Vendor()",
-			fileToParse: filepath.Join(s.tmpLinguist, vendorTestFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, vendorTestFile),
 			samplesDir:  "",
 			tmplPath:    vendorTestTmplPath,
 			tmplName:    vendorTestTmplName,
@@ -180,7 +184,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Documentation()",
-			fileToParse: filepath.Join(s.tmpLinguist, documentationTestFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, documentationTestFile),
 			samplesDir:  "",
 			tmplPath:    documentationTestTmplPath,
 			tmplName:    documentationTestTmplName,
@@ -190,7 +194,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Types()",
-			fileToParse: filepath.Join(s.tmpLinguist, languagesFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, languagesFile),
 			samplesDir:  "",
 			tmplPath:    typeTestTmplPath,
 			tmplName:    typeTestTmplName,
@@ -200,7 +204,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Interpreters()",
-			fileToParse: filepath.Join(s.tmpLinguist, languagesFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, languagesFile),
 			samplesDir:  "",
 			tmplPath:    interpreterTestTmplPath,
 			tmplName:    interpreterTestTmplName,
@@ -210,8 +214,8 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Filenames()",
-			fileToParse: filepath.Join(s.tmpLinguist, languagesFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, languagesFile),
-			samplesDir:  filepath.Join(s.tmpLinguist, samplesDir),
+			samplesDir:  filepath.Join(s.tmpLinguistDir, samplesDir),
 			tmplPath:    filenameTestTmplPath,
 			tmplName:    filenameTestTmplName,
 			commit:      commit,
@@ -220,7 +224,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Aliases()",
-			fileToParse: filepath.Join(s.tmpLinguist, languagesFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, languagesFile),
 			samplesDir:  "",
 			tmplPath:    aliasTestTmplPath,
 			tmplName:    aliasTestTmplName,
@@ -230,7 +234,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:       "Frequencies()",
-			samplesDir: filepath.Join(s.tmpLinguist, samplesDir),
+			samplesDir: filepath.Join(s.tmpLinguistDir, samplesDir),
 			tmplPath:   frequenciesTestTmplPath,
 			tmplName:   frequenciesTestTmplName,
 			commit:     commit,
@@ -248,7 +252,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "MimeType()",
-			fileToParse: filepath.Join(s.tmpLinguist, languagesFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, languagesFile),
 			samplesDir:  "",
 			tmplPath:    mimeTypeTestTmplPath,
 			tmplName:    mimeTypeTestTmplName,
@@ -258,7 +262,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Colors()",
-			fileToParse: filepath.Join(s.tmpLinguist, languagesFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, languagesFile),
 			samplesDir:  "",
 			tmplPath:    colorsTestTmplPath,
 			tmplName:    colorsTestTmplName,
@@ -268,7 +272,7 @@ func (s *GeneratorTestSuite) SetupSuite() {
 		},
 		{
 			name:        "Groups()",
-			fileToParse: filepath.Join(s.tmpLinguist, languagesFile),
+			fileToParse: filepath.Join(s.tmpLinguistDir, languagesFile),
 			samplesDir:  "",
 			tmplPath:    groupsTestTmplPath,
 			tmplName:    groupsTestTmplName,
@@ -280,11 +284,9 @@ func (s *GeneratorTestSuite) SetupSuite() {
 }
 
 func (s *GeneratorTestSuite) TearDownSuite() {
-	if s.cloned {
+	if s.isCleanupNeeded {
-		err := os.RemoveAll(s.tmpLinguist)
+		err := os.RemoveAll(s.tmpLinguistDir)
-		if err != nil {
+		assert.NoError(s.T(), err)
-			s.T().Logf("Failed to clean up %s after the test.\n", s.tmpLinguist)
-		}
 	}
 }
 
@@ -331,7 +333,7 @@ func (s *GeneratorTestSuite) TestGenerationFiles() {
 
 func (s *GeneratorTestSuite) TestTokenizerOnATS() {
 	const suspiciousSample = "samples/ATS/csv_parse.hats"
-	sFile := filepath.Join(s.tmpLinguist, suspiciousSample)
+	sFile := filepath.Join(s.tmpLinguistDir, suspiciousSample)
 	content, err := ioutil.ReadFile(sFile)
 	require.NoError(s.T(), err)
 

internal/code-generator/generator/test_files/alias.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -44,6 +44,7 @@ var LanguageByAliasMap = map[string]string{
 	"amusewiki":                          "Muse",
 	"angelscript":                        "AngelScript",
 	"ant_build_system":                   "Ant Build System",
+	"antlers":                            "Antlers",
 	"antlr":                              "ANTLR",
 	"apache":                             "ApacheConf",
 	"apacheconf":                         "ApacheConf",
@@ -56,6 +57,7 @@ var LanguageByAliasMap = map[string]string{
 	"arc":                                "Arc",
 	"arexx":                              "REXX",
 	"as3":                                "ActionScript",
+	"ascii_stl":                          "STL",
 	"asciidoc":                           "AsciiDoc",
 	"asl":                                "ASL",
 	"asm":                                "Assembly",
@@ -94,6 +96,7 @@ var LanguageByAliasMap = map[string]string{
 	"berry":                              "Berry",
 	"bibtex":                             "BibTeX",
 	"bicep":                              "Bicep",
+	"bikeshed":                           "Bikeshed",
 	"bison":                              "Bison",
 	"bitbake":                            "BitBake",
 	"blade":                              "Blade",
@@ -107,6 +110,7 @@ var LanguageByAliasMap = map[string]string{
 	"boogie":                             "Boogie",
 	"bplus":                              "BlitzBasic",
 	"brainfuck":                          "Brainfuck",
+	"brighterscript":                     "BrighterScript",
 	"brightscript":                       "Brightscript",
 	"bro":                                "Zeek",
 	"browserslist":                       "Browserslist",
@@ -128,14 +132,18 @@ var LanguageByAliasMap = map[string]string{
 	"cakescript":                         "C#",
 	"cameligo":                           "CameLIGO",
 	"cap'n_proto":                        "Cap'n Proto",
+	"cap_cds":                            "CAP CDS",
 	"carto":                              "CartoCSS",
 	"cartocss":                           "CartoCSS",
+	"cds":                                "CAP CDS",
 	"ceylon":                             "Ceylon",
 	"cfc":                                "ColdFusion CFC",
 	"cfm":                                "ColdFusion",
 	"cfml":                               "ColdFusion",
 	"chapel":                             "Chapel",
 	"charity":                            "Charity",
+	"checksum":                           "Checksums",
+	"checksums":                          "Checksums",
 	"chpl":                               "Chapel",
 	"chuck":                              "ChucK",
 	"cil":                                "CIL",
@@ -293,6 +301,7 @@ var LanguageByAliasMap = map[string]string{
 	"gaml":                               "GAML",
 	"gams":                               "GAMS",
 	"gap":                                "GAP",
+	"gas":                                "Unix Assembly",
 	"gcc_machine_description":            "GCC Machine Description",
 	"gdb":                                "GDB",
 	"gdscript":                           "GDScript",
@@ -304,13 +313,16 @@ var LanguageByAliasMap = map[string]string{
 	"genshi":                             "Genshi",
 	"gentoo_ebuild":                      "Gentoo Ebuild",
 	"gentoo_eclass":                      "Gentoo Eclass",
+	"geojson":                            "JSON",
 	"gerber_image":                       "Gerber Image",
 	"gettext_catalog":                    "Gettext Catalog",
 	"gf":                                 "Grammatical Framework",
 	"gherkin":                            "Gherkin",
 	"git-ignore":                         "Ignore List",
 	"git_attributes":                     "Git Attributes",
+	"git_blame_ignore_revs":              "Git Revision List",
 	"git_config":                         "Git Config",
+	"git_revision_list":                  "Git Revision List",
 	"gitattributes":                      "Git Attributes",
 	"gitconfig":                          "Git Config",
 	"gitignore":                          "Ignore List",
@@ -320,6 +332,7 @@ var LanguageByAliasMap = map[string]string{
 	"glyph":                              "Glyph",
 	"glyph_bitmap_distribution_format":   "Glyph Bitmap Distribution Format",
 	"gn":                                 "GN",
+	"gnu_asm":                            "Unix Assembly",
 	"gnuplot":                            "Gnuplot",
 	"go":                                 "Go",
 	"go.mod":                             "Go Module",
@@ -347,6 +360,8 @@ var LanguageByAliasMap = map[string]string{
 	"handlebars":                         "Handlebars",
 	"haproxy":                            "HAProxy",
 	"harbour":                            "Harbour",
+	"hash":                               "Checksums",
+	"hashes":                             "Checksums",
 	"hashicorp_configuration_language":   "HCL",
 	"haskell":                            "Haskell",
 	"haxe":                               "Haxe",
@@ -410,6 +425,7 @@ var LanguageByAliasMap = map[string]string{
 	"javascript":                         "JavaScript",
 	"javascript+erb":                     "JavaScript+ERB",
 	"jest_snapshot":                      "Jest Snapshot",
+	"jetbrains_mps":                      "JetBrains MPS",
 	"jflex":                              "JFlex",
 	"jinja":                              "Jinja",
 	"jison":                              "Jison",
@@ -423,6 +439,7 @@ var LanguageByAliasMap = map[string]string{
 	"json_with_comments":                 "JSON with Comments",
 	"jsonc":                              "JSON with Comments",
 	"jsoniq":                             "JSONiq",
+	"jsonl":                              "JSON",
 	"jsonld":                             "JSONLD",
 	"jsonnet":                            "Jsonnet",
 	"jsp":                                "Java Server Pages",
@@ -532,6 +549,7 @@ var LanguageByAliasMap = map[string]string{
 	"moonscript":                         "MoonScript",
 	"motoko":                             "Motoko",
 	"motorola_68k_assembly":              "Motorola 68K Assembly",
+	"mps":                                "JetBrains MPS",
 	"mql4":                               "MQL4",
 	"mql5":                               "MQL5",
 	"mtml":                               "MTML",
@@ -649,6 +667,7 @@ var LanguageByAliasMap = map[string]string{
 	"pod_6":                              "Pod 6",
 	"pogoscript":                         "PogoScript",
 	"pony":                               "Pony",
+	"portugol":                           "Portugol",
 	"posh":                               "PowerShell",
 	"postcss":                            "PostCSS",
 	"postscr":                            "PostScript",
@@ -810,13 +829,18 @@ var LanguageByAliasMap = map[string]string{
 	"ssh_config":                         "SSH Config",
 	"stan":                               "Stan",
 	"standard_ml":                        "Standard ML",
+	"star":                               "STAR",
 	"starlark":                           "Starlark",
 	"stata":                              "Stata",
+	"stl":                                "STL",
+	"stla":                               "STL",
 	"ston":                               "STON",
 	"stringtemplate":                     "StringTemplate",
 	"stylus":                             "Stylus",
 	"subrip_text":                        "SubRip Text",
 	"sugarss":                            "SugarSS",
+	"sum":                                "Checksums",
+	"sums":                               "Checksums",
 	"supercollider":                      "SuperCollider",
 	"svelte":                             "Svelte",
 	"svg":                                "SVG",
@@ -841,6 +865,7 @@ var LanguageByAliasMap = map[string]string{
 	"tla":                                "TLA",
 	"tm-properties":                      "TextMate Properties",
 	"toml":                               "TOML",
+	"topojson":                           "JSON",
 	"troff":                              "Roff",
 	"ts":                                 "TypeScript",
 	"tsql":                               "TSQL",
@@ -857,6 +882,7 @@ var LanguageByAliasMap = map[string]string{
 	"ultisnips":                          "Vim Snippet",
 	"unified_parallel_c":                 "Unified Parallel C",
 	"unity3d_asset":                      "Unity3D Asset",
+	"unix_asm":                           "Unix Assembly",
 	"unix_assembly":                      "Unix Assembly",
 	"uno":                                "Uno",
 	"unrealscript":                       "UnrealScript",
@@ -888,6 +914,7 @@ var LanguageByAliasMap = map[string]string{
 	"visual_basic_for_applications":      "VBA",
 	"vlang":                              "V",
 	"volt":                               "Volt",
+	"vtt":                                "WebVTT",
 	"vue":                                "Vue",
 	"vyper":                              "Vyper",
 	"wasm":                               "WebAssembly",
@@ -901,6 +928,7 @@ var LanguageByAliasMap = map[string]string{
 	"webvtt":                             "WebVTT",
 	"wget_config":                        "Wget Config",
 	"wgetrc":                             "Wget Config",
+	"whiley":                             "Whiley",
 	"wiki":                               "Wikitext",
 	"wikitext":                           "Wikitext",
 	"win32_message_file":                 "Win32 Message File",
@@ -948,6 +976,7 @@ var LanguageByAliasMap = map[string]string{
 	"yas":                                "YASnippet",
 	"yasnippet":                          "YASnippet",
 	"yml":                                "YAML",
+	"yul":                                "Yul",
 	"zap":                                "ZAP",
 	"zeek":                               "Zeek",
 	"zenscript":                          "ZenScript",
@@ -969,8 +998,9 @@ func LanguageByAlias(langOrAlias string) (lang string, ok bool) {
 
 // convertToAliasKey converts language name to a key in LanguageByAliasMap.
 // Following
-//  - internal.code-generator.generator.convertToAliasKey()
+//   - internal.code-generator.generator.convertToAliasKey()
-//  - GetLanguageByAlias()
+//   - GetLanguageByAlias()
+//
 // conventions.
 // It is here to avoid dependency on "generate" and "enry" packages.
 func convertToAliasKey(langName string) string {

internal/code-generator/generator/test_files/colors.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -27,6 +27,7 @@ var LanguagesColor = map[string]string{
 	"Altium Designer":                "#A89663",
 	"AngelScript":                    "#C7D7DC",
 	"Ant Build System":               "#A9157E",
+	"Antlers":                        "#ff269e",
 	"ApacheConf":                     "#d12127",
 	"Apex":                           "#1797c0",
 	"Apollo Guidance Computer":       "#0B3D91",
@@ -49,6 +50,7 @@ var LanguagesColor = map[string]string{
 	"Berry":                          "#15A13C",
 	"BibTeX":                         "#778899",
 	"Bicep":                          "#519aba",
+	"Bikeshed":                       "#5562ac",
 	"Bison":                          "#6A463F",
 	"BitBake":                        "#00bce4",
 	"Blade":                          "#f7523f",
@@ -58,11 +60,13 @@ var LanguagesColor = map[string]string{
 	"Boo":                            "#d4bec1",
 	"Boogie":                         "#c80fa0",
 	"Brainfuck":                      "#2F2530",
+	"BrighterScript":                 "#66AABB",
 	"Brightscript":                   "#662D91",
 	"Browserslist":                   "#ffd539",
 	"C":                              "#555555",
 	"C#":                             "#178600",
 	"C++":                            "#f34b7d",
+	"CAP CDS":                        "#0092d1",
 	"CLIPS":                          "#00A300",
 	"CMake":                          "#DA3434",
 	"COLLADA":                        "#F1A42B",
@@ -171,6 +175,7 @@ var LanguagesColor = map[string]string{
 	"Gherkin":                        "#5B2063",
 	"Git Attributes":                 "#F44D27",
 	"Git Config":                     "#F44D27",
+	"Git Revision List":              "#F44D27",
 	"Gleam":                          "#ffaff3",
 	"Glyph":                          "#c1ac7f",
 	"Gnuplot":                        "#f0a9f0",
@@ -232,6 +237,7 @@ var LanguagesColor = map[string]string{
 	"JavaScript":                     "#f1e05a",
 	"JavaScript+ERB":                 "#f1e05a",
 	"Jest Snapshot":                  "#15c213",
+	"JetBrains MPS":                  "#21D789",
 	"Jinja":                          "#a52a22",
 	"Jison":                          "#56b3cb",
 	"Jison Lex":                      "#56b3cb",
@@ -344,6 +350,7 @@ var LanguagesColor = map[string]string{
 	"PigLatin":                       "#fcd7de",
 	"Pike":                           "#005390",
 	"PogoScript":                     "#d80074",
+	"Portugol":                       "#f8bd00",
 	"PostCSS":                        "#dc3a0c",
 	"PostScript":                     "#da291c",
 	"PowerBuilder":                   "#8f0f8d",
@@ -399,6 +406,7 @@ var LanguagesColor = map[string]string{
 	"SQL":                            "#e38c00",
 	"SQLPL":                          "#e38c00",
 	"SRecode Template":               "#348a34",
+	"STL":                            "#373b5e",
 	"SVG":                            "#ff9900",
 	"SaltStack":                      "#646464",
 	"Sass":                           "#a53b70",
@@ -438,7 +446,7 @@ var LanguagesColor = map[string]string{
 	"TOML":                           "#9c4221",
 	"TSQL":                           "#e38c00",
 	"TSV":                            "#237346",
-	"TSX":                            "#2b7489",
+	"TSX":                            "#3178c6",
 	"TXL":                            "#0178b8",
 	"Talon":                          "#333333",
 	"Tcl":                            "#e4cc98",
@@ -449,7 +457,7 @@ var LanguagesColor = map[string]string{
 	"Thrift":                         "#D12127",
 	"Turing":                         "#cf142b",
 	"Twig":                           "#c1d026",
-	"TypeScript":                     "#2b7489",
+	"TypeScript":                     "#3178c6",
 	"Unified Parallel C":             "#4e3617",
 	"Unity3D Asset":                  "#222c37",
 	"Uno":                            "#9933cc",
@@ -472,6 +480,7 @@ var LanguagesColor = map[string]string{
 	"Vyper":                          "#2980b9",
 	"Web Ontology Language":          "#5b70bd",
 	"WebAssembly":                    "#04133b",
+	"Whiley":                         "#d5c397",
 	"Wikitext":                       "#fc5757",
 	"Windows Registry Entries":       "#52d5ff",
 	"Witcher Script":                 "#ff0000",
@@ -490,6 +499,7 @@ var LanguagesColor = map[string]string{
 	"YARA":                           "#220000",
 	"YASnippet":                      "#32AB90",
 	"Yacc":                           "#4B6C4B",
+	"Yul":                            "#794932",
 	"ZAP":                            "#0d665e",
 	"ZIL":                            "#dc75e5",
 	"ZenScript":                      "#00BCD1",

internal/code-generator/generator/test_files/commit.gold

@@ -1,7 +1,7 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
 // linguist's commit from which files were generated.
-var LinguistCommit = "4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26"
+var LinguistCommit = "d7799da826e01acdb8f84694d33116dccaabe9c2"

internal/code-generator/generator/test_files/content.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -638,6 +638,10 @@ var ContentHeuristics = map[string]*Heuristics{
 			rule.MatchingLanguages("BitBake"),
 			regexp.MustCompile(`(?m)^\s*(# |include|require)\b`),
 		),
+		rule.Or(
+			rule.MatchingLanguages("Clojure"),
+			regexp.MustCompile(`(?m)\((def|defn|defmacro|let)\s`),
+		),
 	},
 	".bi": &Heuristics{
 		rule.Or(
@@ -645,6 +649,7 @@ var ContentHeuristics = map[string]*Heuristics{
 			regexp.MustCompile(`(?m)^[ \t]*#(?:define|endif|endmacro|ifn?def|if|include|lang|macro)\s`),
 		),
 	},
+	".bs": &Heuristics{},
 	".builds": &Heuristics{
 		rule.Or(
 			rule.MatchingLanguages("XML"),
@@ -1472,6 +1477,16 @@ var ContentHeuristics = map[string]*Heuristics{
 			regexp.MustCompile(`(?m)\A\s*[\[{(^"'\w#]|[a-zA-Z_]\w*\s*:=\s*[a-zA-Z_]\w*|class\s*>>\s*[a-zA-Z_]\w*|^[a-zA-Z_]\w*\s+[a-zA-Z_]\w*:|^Class\s*{|if(?:True|False):\s*\[`),
 		),
 	},
+	".star": &Heuristics{
+		rule.Or(
+			rule.MatchingLanguages("STAR"),
+			regexp.MustCompile(`(?m)^loop_\s*$`),
+		),
+		rule.Always(
+			rule.MatchingLanguages("Starlark"),
+		),
+	},
+	".stl": &Heuristics{},
 	".t": &Heuristics{
 		rule.Or(
 			rule.MatchingLanguages("Perl"),

internal/code-generator/generator/test_files/documentation.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 

internal/code-generator/generator/test_files/extension.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -18,7 +18,9 @@ var LanguagesByExtension = map[string][]string{
 	".3qt":                 {"Roff", "Roff Manpage"},
 	".3x":                  {"Roff", "Roff Manpage"},
 	".4":                   {"Roff", "Roff Manpage"},
+	".4dform":              {"JSON"},
 	".4dm":                 {"4D"},
+	".4dproject":           {"JSON"},
 	".4gl":                 {"Genero"},
 	".4th":                 {"Forth"},
 	".5":                   {"Roff", "Roff Manpage"},
@@ -59,6 +61,9 @@ var LanguagesByExtension = map[string][]string{
 	".angelscript":         {"AngelScript"},
 	".anim":                {"Unity3D Asset"},
 	".ant":                 {"XML"},
+	".antlers.html":        {"Antlers"},
+	".antlers.php":         {"Antlers"},
+	".antlers.xml":         {"Antlers"},
 	".apacheconf":          {"ApacheConf"},
 	".apib":                {"API Blueprint"},
 	".apl":                 {"APL"},
@@ -106,7 +111,7 @@ var LanguagesByExtension = map[string][]string{
 	".bash":                {"Shell"},
 	".bat":                 {"Batchfile"},
 	".bats":                {"Shell"},
-	".bb":                  {"BitBake", "BlitzBasic"},
+	".bb":                  {"BitBake", "BlitzBasic", "Clojure"},
 	".bbx":                 {"TeX"},
 	".bdf":                 {"Glyph Bitmap Distribution Format"},
 	".bdy":                 {"PLSQL"},
@@ -128,6 +133,7 @@ var LanguagesByExtension = map[string][]string{
 	".brd":                 {"Eagle", "KiCad Legacy Layout"},
 	".bro":                 {"Zeek"},
 	".brs":                 {"Brightscript"},
+	".bs":                  {"Bikeshed", "BrighterScript"},
 	".bsl":                 {"1C Enterprise"},
 	".bsv":                 {"Bluespec"},
 	".builder":             {"Ruby"},
@@ -151,6 +157,7 @@ var LanguagesByExtension = map[string][]string{
 	".ccxml":               {"XML"},
 	".cdc":                 {"Cadence"},
 	".cdf":                 {"Mathematica"},
+	".cds":                 {"CAP CDS"},
 	".ceylon":              {"Ceylon"},
 	".cfc":                 {"ColdFusion CFC"},
 	".cfg":                 {"HAProxy", "INI"},
@@ -206,6 +213,7 @@ var LanguagesByExtension = map[string][]string{
 	".cpy":                 {"COBOL"},
 	".cql":                 {"SQL"},
 	".cr":                  {"Crystal"},
+	".crc32":               {"Checksums"},
 	".creole":              {"Creole"},
 	".cs":                  {"C#", "Smalltalk"},
 	".csc":                 {"GSC"},
@@ -222,6 +230,7 @@ var LanguagesByExtension = map[string][]string{
 	".csx":                 {"C#"},
 	".ct":                  {"XML"},
 	".ctp":                 {"PHP"},
+	".cts":                 {"TypeScript"},
 	".cu":                  {"Cuda"},
 	".cue":                 {"CUE", "Cue Sheet"},
 	".cuh":                 {"Cuda"},
@@ -350,6 +359,7 @@ var LanguagesByExtension = map[string][]string{
 	".fsi":                 {"F#"},
 	".fsproj":              {"XML"},
 	".fst":                 {"F*"},
+	".fsti":                {"F*"},
 	".fsx":                 {"F#"},
 	".fth":                 {"Forth"},
 	".ftl":                 {"Fluent", "FreeMarker"},
@@ -540,6 +550,7 @@ var LanguagesByExtension = map[string][]string{
 	".kak":                 {"KakouneScript"},
 	".kicad_mod":           {"KiCad Layout"},
 	".kicad_pcb":           {"KiCad Layout"},
+	".kicad_sch":           {"KiCad Schematic"},
 	".kicad_wks":           {"KiCad Layout"},
 	".kid":                 {"Genshi"},
 	".kit":                 {"Kit"},
@@ -579,6 +590,7 @@ var LanguagesByExtension = map[string][]string{
 	".liquid":              {"Liquid"},
 	".lisp":                {"Common Lisp", "NewLisp"},
 	".litcoffee":           {"Literate CoffeeScript"},
+	".livemd":              {"Markdown"},
 	".ll":                  {"LLVM"},
 	".lmi":                 {"Python"},
 	".logtalk":             {"Logtalk"},
@@ -591,6 +603,7 @@ var LanguagesByExtension = map[string][]string{
 	".lsp":                 {"Common Lisp", "NewLisp"},
 	".ltx":                 {"TeX"},
 	".lua":                 {"Lua"},
+	".lvclass":             {"LabVIEW"},
 	".lvlib":               {"LabVIEW"},
 	".lvproj":              {"LabVIEW"},
 	".ly":                  {"LilyPond"},
@@ -623,6 +636,9 @@ var LanguagesByExtension = map[string][]string{
 	".mcmeta":              {"JSON"},
 	".mcr":                 {"MAXScript"},
 	".md":                  {"GCC Machine Description", "Markdown"},
+	".md2":                 {"Checksums"},
+	".md4":                 {"Checksums"},
+	".md5":                 {"Checksums"},
 	".mdoc":                {"Roff", "Roff Manpage"},
 	".mdown":               {"Markdown"},
 	".mdpolicy":            {"XML"},
@@ -664,16 +680,20 @@ var LanguagesByExtension = map[string][]string{
 	".monkey2":             {"Monkey"},
 	".moo":                 {"Mercury", "Moocode"},
 	".moon":                {"MoonScript"},
+	".mpl":                 {"JetBrains MPS"},
+	".mps":                 {"JetBrains MPS"},
 	".mq4":                 {"MQL4"},
 	".mq5":                 {"MQL5"},
 	".mqh":                 {"MQL4", "MQL5"},
 	".mrc":                 {"mIRC Script"},
 	".ms":                  {"MAXScript", "Roff", "Unix Assembly"},
+	".msd":                 {"JetBrains MPS"},
 	".mspec":               {"Ruby"},
 	".mss":                 {"CartoCSS"},
 	".mt":                  {"Mathematica"},
 	".mtl":                 {"Wavefront Material"},
 	".mtml":                {"MTML"},
+	".mts":                 {"TypeScript"},
 	".mu":                  {"mupad"},
 	".mud":                 {"ZIL"},
 	".muf":                 {"MUF"},
@@ -819,6 +839,7 @@ var LanguagesByExtension = map[string][]string{
 	".podspec":             {"Ruby"},
 	".pogo":                {"PogoScript"},
 	".pony":                {"Pony"},
+	".por":                 {"Portugol"},
 	".postcss":             {"PostCSS"},
 	".pot":                 {"Gettext Catalog"},
 	".pov":                 {"POV-Ray SDL"},
@@ -978,6 +999,14 @@ var LanguagesByExtension = map[string][]string{
 	".sh":                  {"Shell"},
 	".sh-session":          {"ShellSession"},
 	".sh.in":               {"Shell"},
+	".sha1":                {"Checksums"},
+	".sha2":                {"Checksums"},
+	".sha224":              {"Checksums"},
+	".sha256":              {"Checksums"},
+	".sha256sum":           {"Checksums"},
+	".sha3":                {"Checksums"},
+	".sha384":              {"Checksums"},
+	".sha512":              {"Checksums"},
 	".shader":              {"GLSL", "ShaderLab"},
 	".shen":                {"Shen"},
 	".shproj":              {"XML"},
@@ -1021,7 +1050,9 @@ var LanguagesByExtension = map[string][]string{
 	".sss":                 {"SugarSS"},
 	".st":                  {"Smalltalk", "StringTemplate"},
 	".stan":                {"Stan"},
+	".star":                {"STAR", "Starlark"},
 	".sthlp":               {"Stata"},
+	".stl":                 {"STL"},
 	".ston":                {"STON"},
 	".story":               {"Gherkin"},
 	".storyboard":          {"XML"},
@@ -1166,6 +1197,7 @@ var LanguagesByExtension = map[string][]string{
 	".webidl":              {"WebIDL"},
 	".webmanifest":         {"JSON"},
 	".weechatlog":          {"IRC log"},
+	".whiley":              {"Whiley"},
 	".wiki":                {"Wikitext"},
 	".wikitext":            {"Wikitext"},
 	".wisp":                {"wisp"},
@@ -1245,6 +1277,7 @@ var LanguagesByExtension = map[string][]string{
 	".yml":                 {"YAML"},
 	".yml.mysql":           {"YAML"},
 	".yrl":                 {"Erlang"},
+	".yul":                 {"Yul"},
 	".yy":                  {"JSON", "Yacc"},
 	".yyp":                 {"JSON"},
 	".zap":                 {"ZAP"},
@@ -1287,6 +1320,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Alloy":                              {".als"},
 	"Altium Designer":                    {".outjob", ".pcbdoc", ".prjpcb", ".schdoc"},
 	"AngelScript":                        {".as", ".angelscript"},
+	"Antlers":                            {".antlers.html", ".antlers.php", ".antlers.xml"},
 	"ApacheConf":                         {".apacheconf", ".vhost"},
 	"Apex":                               {".cls"},
 	"Apollo Guidance Computer":           {".agc"},
@@ -1310,6 +1344,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Berry":                              {".be"},
 	"BibTeX":                             {".bib", ".bibtex"},
 	"Bicep":                              {".bicep"},
+	"Bikeshed":                           {".bs"},
 	"Bison":                              {".bison"},
 	"BitBake":                            {".bb"},
 	"Blade":                              {".blade", ".blade.php"},
@@ -1319,12 +1354,14 @@ var ExtensionsByLanguage = map[string][]string{
 	"Boo":                                {".boo"},
 	"Boogie":                             {".bpl"},
 	"Brainfuck":                          {".b", ".bf"},
+	"BrighterScript":                     {".bs"},
 	"Brightscript":                       {".brs"},
 	"C":                                  {".c", ".cats", ".h", ".idc"},
 	"C#":                                 {".cs", ".cake", ".csx", ".linq"},
 	"C++":                                {".cpp", ".c++", ".cc", ".cp", ".cxx", ".h", ".h++", ".hh", ".hpp", ".hxx", ".inc", ".inl", ".ino", ".ipp", ".ixx", ".re", ".tcc", ".tpp"},
 	"C-ObjDump":                          {".c-objdump"},
 	"C2hs Haskell":                       {".chs"},
+	"CAP CDS":                            {".cds"},
 	"CIL":                                {".cil"},
 	"CLIPS":                              {".clp"},
 	"CMake":                              {".cmake", ".cmake.in"},
@@ -1344,6 +1381,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Ceylon":                             {".ceylon"},
 	"Chapel":                             {".chpl"},
 	"Charity":                            {".ch"},
+	"Checksums":                          {".crc32", ".md2", ".md4", ".md5", ".sha1", ".sha2", ".sha224", ".sha256", ".sha256sum", ".sha3", ".sha384", ".sha512"},
 	"ChucK":                              {".ck"},
 	"Cirru":                              {".cirru"},
 	"Clarion":                            {".clw"},
@@ -1351,7 +1389,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Classic ASP":                        {".asp"},
 	"Clean":                              {".icl", ".dcl"},
 	"Click":                              {".click"},
-	"Clojure":                            {".clj", ".boot", ".cl2", ".cljc", ".cljs", ".cljs.hl", ".cljscm", ".cljx", ".hic"},
+	"Clojure":                            {".clj", ".bb", ".boot", ".cl2", ".cljc", ".cljs", ".cljs.hl", ".cljscm", ".cljx", ".hic"},
 	"Closure Templates":                  {".soy"},
 	"CoNLL-U":                            {".conllu", ".conll"},
 	"CodeQL":                             {".ql", ".qll"},
@@ -1411,7 +1449,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Erlang":                             {".erl", ".app.src", ".es", ".escript", ".hrl", ".xrl", ".yrl"},
 	"Euphoria":                           {".e", ".ex"},
 	"F#":                                 {".fs", ".fsi", ".fsx"},
-	"F*":                                 {".fst"},
+	"F*":                                 {".fst", ".fsti"},
 	"FIGlet Font":                        {".flf"},
 	"FLUX":                               {".fx", ".flux"},
 	"Factor":                             {".factor"},
@@ -1502,7 +1540,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Isabelle":                           {".thy"},
 	"J":                                  {".ijs"},
 	"JFlex":                              {".flex", ".jflex"},
-	"JSON":                               {".json", ".avsc", ".geojson", ".gltf", ".har", ".ice", ".json-tmlanguage", ".jsonl", ".mcmeta", ".tfstate", ".tfstate.backup", ".topojson", ".webapp", ".webmanifest", ".yy", ".yyp"},
+	"JSON":                               {".json", ".4dform", ".4dproject", ".avsc", ".geojson", ".gltf", ".har", ".ice", ".json-tmlanguage", ".jsonl", ".mcmeta", ".tfstate", ".tfstate.backup", ".topojson", ".webapp", ".webmanifest", ".yy", ".yyp"},
 	"JSON with Comments":                 {".jsonc", ".code-snippets", ".sublime-build", ".sublime-commands", ".sublime-completions", ".sublime-keymap", ".sublime-macro", ".sublime-menu", ".sublime-mousemap", ".sublime-project", ".sublime-settings", ".sublime-theme", ".sublime-workspace", ".sublime_metrics", ".sublime_session"},
 	"JSON5":                              {".json5"},
 	"JSONLD":                             {".jsonld"},
@@ -1515,6 +1553,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"JavaScript":                         {".js", "._js", ".bones", ".cjs", ".es", ".es6", ".frag", ".gs", ".jake", ".javascript", ".jsb", ".jscad", ".jsfl", ".jslib", ".jsm", ".jspre", ".jss", ".jsx", ".mjs", ".njs", ".pac", ".sjs", ".ssjs", ".xsjs", ".xsjslib"},
 	"JavaScript+ERB":                     {".js.erb"},
 	"Jest Snapshot":                      {".snap"},
+	"JetBrains MPS":                      {".mps", ".mpl", ".msd"},
 	"Jinja":                              {".jinja", ".j2", ".jinja2"},
 	"Jison":                              {".jison"},
 	"Jison Lex":                          {".jisonlex"},
@@ -1527,7 +1566,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"KakouneScript":                      {".kak"},
 	"KiCad Layout":                       {".kicad_pcb", ".kicad_mod", ".kicad_wks"},
 	"KiCad Legacy Layout":                {".brd"},
-	"KiCad Schematic":                    {".sch"},
+	"KiCad Schematic":                    {".kicad_sch", ".sch"},
 	"Kit":                                {".kit"},
 	"Kotlin":                             {".kt", ".ktm", ".kts"},
 	"Kusto":                              {".csl"},
@@ -1536,7 +1575,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"LOLCODE":                            {".lol"},
 	"LSL":                                {".lsl", ".lslp"},
 	"LTspice Symbol":                     {".asy"},
-	"LabVIEW":                            {".lvproj", ".lvlib"},
+	"LabVIEW":                            {".lvproj", ".lvclass", ".lvlib"},
 	"Lark":                               {".lark"},
 	"Lasso":                              {".lasso", ".las", ".lasso8", ".lasso9"},
 	"Latte":                              {".latte"},
@@ -1571,7 +1610,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Macaulay2":                          {".m2"},
 	"Makefile":                           {".mak", ".d", ".make", ".makefile", ".mk", ".mkfile"},
 	"Mako":                               {".mako", ".mao"},
-	"Markdown":                           {".md", ".markdown", ".mdown", ".mdwn", ".mdx", ".mkd", ".mkdn", ".mkdown", ".ronn", ".scd", ".workbook"},
+	"Markdown":                           {".md", ".livemd", ".markdown", ".mdown", ".mdwn", ".mdx", ".mkd", ".mkdn", ".mkdown", ".ronn", ".scd", ".workbook"},
 	"Marko":                              {".marko"},
 	"Mask":                               {".mask"},
 	"Mathematica":                        {".mathematica", ".cdf", ".m", ".ma", ".mt", ".nb", ".nbp", ".wl", ".wlt"},
@@ -1665,6 +1704,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Pod 6":                              {".pod", ".pod6"},
 	"PogoScript":                         {".pogo"},
 	"Pony":                               {".pony"},
+	"Portugol":                           {".por"},
 	"PostCSS":                            {".pcss", ".postcss"},
 	"PostScript":                         {".ps", ".eps", ".epsi", ".pfa"},
 	"PowerBuilder":                       {".pbt", ".sra", ".sru", ".srw"},
@@ -1731,6 +1771,8 @@ var ExtensionsByLanguage = map[string][]string{
 	"SQL":                                {".sql", ".cql", ".ddl", ".inc", ".mysql", ".prc", ".tab", ".udf", ".viw"},
 	"SQLPL":                              {".sql", ".db2"},
 	"SRecode Template":                   {".srt"},
+	"STAR":                               {".star"},
+	"STL":                                {".stl"},
 	"STON":                               {".ston"},
 	"SVG":                                {".svg"},
 	"SWIG":                               {".i"},
@@ -1760,7 +1802,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Squirrel":                           {".nut"},
 	"Stan":                               {".stan"},
 	"Standard ML":                        {".ml", ".fun", ".sig", ".sml"},
-	"Starlark":                           {".bzl"},
+	"Starlark":                           {".bzl", ".star"},
 	"Stata":                              {".do", ".ado", ".doh", ".ihlp", ".mata", ".matah", ".sthlp"},
 	"StringTemplate":                     {".st"},
 	"Stylus":                             {".styl"},
@@ -1791,7 +1833,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"Turtle":                             {".ttl"},
 	"Twig":                               {".twig"},
 	"Type Language":                      {".tl"},
-	"TypeScript":                         {".ts"},
+	"TypeScript":                         {".ts", ".cts", ".mts"},
 	"Unified Parallel C":                 {".upc"},
 	"Unity3D Asset":                      {".anim", ".asset", ".mask", ".mat", ".meta", ".prefab", ".unity"},
 	"Unix Assembly":                      {".s", ".ms"},
@@ -1819,6 +1861,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"WebAssembly":                        {".wast", ".wat"},
 	"WebIDL":                             {".webidl"},
 	"WebVTT":                             {".vtt"},
+	"Whiley":                             {".whiley"},
 	"Wikitext":                           {".mediawiki", ".wiki", ".wikitext"},
 	"Win32 Message File":                 {".mc"},
 	"Windows Registry Entries":           {".reg"},
@@ -1844,6 +1887,7 @@ var ExtensionsByLanguage = map[string][]string{
 	"YARA":                               {".yar", ".yara"},
 	"YASnippet":                          {".yasnippet"},
 	"Yacc":                               {".y", ".yacc", ".yy"},
+	"Yul":                                {".yul"},
 	"ZAP":                                {".zap", ".xzap"},
 	"ZIL":                                {".zil", ".mud"},
 	"Zeek":                               {".zeek", ".bro"},

internal/code-generator/generator/test_files/filename.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -24,10 +24,12 @@ var LanguagesByFilename = map[string][]string{
 	".clang-tidy":                  {"YAML"},
 	".classpath":                   {"XML"},
 	".coffeelintignore":            {"Ignore List"},
+	".coveragerc":                  {"INI"},
 	".cproject":                    {"XML"},
 	".cshrc":                       {"Shell"},
 	".curlrc":                      {"cURL Config"},
 	".cvsignore":                   {"Ignore List"},
+	".devcontainer.json":           {"JSON with Comments"},
 	".dir_colors":                  {"dircolors"},
 	".dircolors":                   {"dircolors"},
 	".dockerignore":                {"Ignore List"},
@@ -46,6 +48,7 @@ var LanguagesByFilename = map[string][]string{
 	".flaskenv":                    {"Shell"},
 	".gclient":                     {"Python"},
 	".gemrc":                       {"YAML"},
+	".git-blame-ignore-revs":       {"Git Revision List"},
 	".gitattributes":               {"Git Attributes"},
 	".gitconfig":                   {"Git Config"},
 	".gitignore":                   {"Ignore List"},
@@ -78,6 +81,7 @@ var LanguagesByFilename = map[string][]string{
 	".profile":                     {"Shell"},
 	".project":                     {"XML"},
 	".pryrc":                       {"Ruby"},
+	".pylintrc":                    {"INI"},
 	".shellcheckrc":                {"ShellCheck Config"},
 	".simplecov":                   {"Ruby"},
 	".spacemacs":                   {"Emacs Lisp"},
@@ -146,6 +150,7 @@ var LanguagesByFilename = map[string][]string{
 	"LICENSE.mysql":                {"Text"},
 	"Lexer.x":                      {"Lex"},
 	"MANIFEST.MF":                  {"JAR Manifest"},
+	"MD5SUMS":                      {"Checksums"},
 	"Makefile":                     {"Makefile"},
 	"Makefile.PL":                  {"Perl"},
 	"Makefile.am":                  {"Makefile"},
@@ -176,6 +181,10 @@ var LanguagesByFilename = map[string][]string{
 	"Rexfile":                      {"Perl"},
 	"SConscript":                   {"Python"},
 	"SConstruct":                   {"Python"},
+	"SHA1SUMS":                     {"Checksums"},
+	"SHA256SUMS":                   {"Checksums"},
+	"SHA256SUMS.txt":               {"Checksums"},
+	"SHA512SUMS":                   {"Checksums"},
 	"Settings.StyleCop":            {"XML"},
 	"Singularity":                  {"Singularity"},
 	"Slakefile":                    {"LiveScript"},
@@ -211,6 +220,8 @@ var LanguagesByFilename = map[string][]string{
 	"buildozer.spec":               {"INI"},
 	"cabal.config":                 {"Cabal Config"},
 	"cabal.project":                {"Cabal Config"},
+	"checksums.txt":                {"Checksums"},
+	"cksums":                       {"Checksums"},
 	"click.me":                     {"Text"},
 	"composer.lock":                {"JSON"},
 	"configure.ac":                 {"M4Sugar"},
@@ -259,6 +270,7 @@ var LanguagesByFilename = map[string][]string{
 	"makefile.sco":                 {"Makefile"},
 	"man":                          {"Shell"},
 	"mcmod.info":                   {"JSON"},
+	"md5sum.txt":                   {"Checksums"},
 	"meson.build":                  {"Meson"},
 	"meson_options.txt":            {"Meson"},
 	"mix.lock":                     {"Elixir"},
@@ -279,6 +291,7 @@ var LanguagesByFilename = map[string][]string{
 	"pom.xml":                      {"Maven POM"},
 	"port_contexts":                {"SELinux Policy"},
 	"profile":                      {"Shell"},
+	"pylintrc":                     {"INI"},
 	"read.me":                      {"Text"},
 	"readme.1st":                   {"Text"},
 	"rebar.config":                 {"Erlang"},

internal/code-generator/generator/test_files/groups.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 

internal/code-generator/generator/test_files/interpreter.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -13,6 +13,7 @@ var LanguagesByInterpreter = map[string][]string{
 	"asy":         {"Asymptote"},
 	"awk":         {"Awk"},
 	"bash":        {"Shell"},
+	"bb":          {"Clojure"},
 	"bigloo":      {"Scheme"},
 	"boogie":      {"Boogie"},
 	"boolector":   {"SMT"},

internal/code-generator/generator/test_files/mimeType.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -16,6 +16,7 @@ var LanguagesMime = map[string]string{
 	"Asymptote":                      "text/x-kotlin",
 	"Beef":                           "text/x-csharp",
 	"BibTeX":                         "text/x-stex",
+	"Bikeshed":                       "text/html",
 	"Brainfuck":                      "text/x-brainfuck",
 	"C":                              "text/x-csrc",
 	"C#":                             "text/x-csharp",
@@ -111,6 +112,7 @@ var LanguagesMime = map[string]string{
 	"JavaScript":                     "text/javascript",
 	"JavaScript+ERB":                 "application/javascript",
 	"Jest Snapshot":                  "application/javascript",
+	"JetBrains MPS":                  "text/xml",
 	"Jinja":                          "text/x-django",
 	"Julia":                          "text/x-julia",
 	"Jupyter Notebook":               "application/json",

internal/code-generator/generator/test_files/type.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -72,6 +72,7 @@ var LanguagesType = map[string]int{
 	"Altium Designer":                    1,
 	"AngelScript":                        2,
 	"Ant Build System":                   1,
+	"Antlers":                            3,
 	"ApacheConf":                         1,
 	"Apex":                               2,
 	"Apollo Guidance Computer":           2,
@@ -95,6 +96,7 @@ var LanguagesType = map[string]int{
 	"Berry":                              2,
 	"BibTeX":                             3,
 	"Bicep":                              2,
+	"Bikeshed":                           3,
 	"Bison":                              2,
 	"BitBake":                            2,
 	"Blade":                              3,
@@ -104,6 +106,7 @@ var LanguagesType = map[string]int{
 	"Boo":                                2,
 	"Boogie":                             2,
 	"Brainfuck":                          2,
+	"BrighterScript":                     2,
 	"Brightscript":                       2,
 	"Browserslist":                       1,
 	"C":                                  2,
@@ -111,6 +114,7 @@ var LanguagesType = map[string]int{
 	"C++":                                2,
 	"C-ObjDump":                          1,
 	"C2hs Haskell":                       2,
+	"CAP CDS":                            2,
 	"CIL":                                1,
 	"CLIPS":                              2,
 	"CMake":                              2,
@@ -131,6 +135,7 @@ var LanguagesType = map[string]int{
 	"Ceylon":                             2,
 	"Chapel":                             2,
 	"Charity":                            2,
+	"Checksums":                          1,
 	"ChucK":                              2,
 	"Cirru":                              2,
 	"Clarion":                            2,
@@ -244,6 +249,7 @@ var LanguagesType = map[string]int{
 	"Gherkin":                            2,
 	"Git Attributes":                     1,
 	"Git Config":                         1,
+	"Git Revision List":                  1,
 	"Gleam":                              2,
 	"Glyph":                              2,
 	"Glyph Bitmap Distribution Format":   1,
@@ -311,6 +317,7 @@ var LanguagesType = map[string]int{
 	"JavaScript":                         2,
 	"JavaScript+ERB":                     2,
 	"Jest Snapshot":                      1,
+	"JetBrains MPS":                      2,
 	"Jinja":                              3,
 	"Jison":                              2,
 	"Jison Lex":                          2,
@@ -465,6 +472,7 @@ var LanguagesType = map[string]int{
 	"Pod 6":                              4,
 	"PogoScript":                         2,
 	"Pony":                               2,
+	"Portugol":                           2,
 	"PostCSS":                            3,
 	"PostScript":                         3,
 	"PowerBuilder":                       2,
@@ -538,6 +546,8 @@ var LanguagesType = map[string]int{
 	"SQLPL":                              2,
 	"SRecode Template":                   3,
 	"SSH Config":                         1,
+	"STAR":                               1,
+	"STL":                                1,
 	"STON":                               1,
 	"SVG":                                1,
 	"SWIG":                               2,
@@ -631,6 +641,7 @@ var LanguagesType = map[string]int{
 	"WebIDL":                             2,
 	"WebVTT":                             1,
 	"Wget Config":                        1,
+	"Whiley":                             2,
 	"Wikitext":                           4,
 	"Win32 Message File":                 1,
 	"Windows Registry Entries":           1,
@@ -658,6 +669,7 @@ var LanguagesType = map[string]int{
 	"YARA":                               2,
 	"YASnippet":                          3,
 	"Yacc":                               2,
+	"Yul":                                2,
 	"ZAP":                                2,
 	"ZIL":                                2,
 	"Zeek":                               2,

internal/code-generator/generator/test_files/vendor.gold

@@ -1,5 +1,5 @@
 // Code generated by github.com/go-enry/go-enry/v2/internal/code-generator DO NOT EDIT.
-// Extracted from github/linguist commit: 4ffcdbcbb60a74cbfbd37656bcc3fcea4eca8e26
+// Extracted from github/linguist commit: d7799da826e01acdb8f84694d33116dccaabe9c2
 
 package data
 
@@ -171,4 +171,8 @@ var VendorMatchers = []regex.EnryRegexp{
 	regex.MustCompile(`(^|/)\.google_apis/`),
 	regex.MustCompile(`(^|/)Jenkinsfile$`),
 	regex.MustCompile(`(^|/)\.gitpod\.Dockerfile$`),
+	regex.MustCompile(`(^|/)\.github/`),
 }
+
+// FastVendorMatcher is equivalent to matching any of the VendorMatchers.
+var FastVendorMatcher = regex.MustCompile(`(?:^(?:(?:[Dd]ependencies/)|(?:debian/)|(?:deps/)|(?:rebar$)))|(?:(?:^|/)(?:(?:BuddyBuildSDK\.framework/)|(?:Carthage/)|(?:Chart\.js$)|(?:Control\.FullScreen\.css)|(?:Control\.FullScreen\.js)|(?:Crashlytics\.framework/)|(?:Fabric\.framework/)|(?:Godeps/_workspace/)|(?:Jenkinsfile$)|(?:Leaflet\.Coordinates-\d+\.\d+\.\d+\.src\.js$)|(?:MathJax/)|(?:MochiKit\.js$)|(?:RealmSwift\.framework)|(?:Realm\.framework)|(?:Sparkle/)|(?:Vagrantfile$)|(?:[Bb]ourbon/.*\.(css|less|scss|styl)$)|(?:[Cc]ode[Mm]irror/(\d+\.\d+/)?(lib|mode|theme|addon|keymap|demo))|(?:[Ee]xtern(als?)?/)|(?:[Mm]icrosoft([Mm]vc)?([Aa]jax|[Vv]alidation)(\.debug)?\.js$)|(?:[Pp]ackages\/.+\.\d+\/)|(?:[Ss]pecs?/fixtures/)|(?:[Tt]ests?/fixtures/)|(?:[Vv]+endor/)|(?:\.[Dd][Ss]_[Ss]tore$)|(?:\.gitattributes$)|(?:\.github/)|(?:\.gitignore$)|(?:\.gitmodules$)|(?:\.gitpod\.Dockerfile$)|(?:\.google_apis/)|(?:\.indent\.pro)|(?:\.mvn/wrapper/)|(?:\.osx$)|(?:\.sublime-project)|(?:\.sublime-workspace)|(?:\.vscode/)|(?:\.yarn/plugins/)|(?:\.yarn/releases/)|(?:\.yarn/sdks/)|(?:\.yarn/unplugged/)|(?:\.yarn/versions/)|(?:_esy$)|(?:ace-builds/)|(?:aclocal\.m4)|(?:activator$)|(?:activator\.bat$)|(?:admin_media/)|(?:angular([^.]*)\.js$)|(?:animate\.(css|less|scss|styl)$)|(?:bootbox\.js)|(?:bootstrap([^/.]*)\.(js|css|less|scss|styl)$)|(?:bootstrap-datepicker/)|(?:bower_components/)|(?:bulma\.(css|sass|scss)$)|(?:cache/)|(?:ckeditor\.js$)|(?:config\.guess$)|(?:config\.sub$)|(?:configure$)|(?:controls\.js$)|(?:cordova([^.]*)\.js$)|(?:cordova\-\d\.\d(\.\d)?\.js$)|(?:cpplint\.py)|(?:custom\.bootstrap([^\s]*)(js|css|less|scss|styl)$)|(?:dist/)|(?:docs?/_?(build|themes?|templates?|static)/)|(?:dojo\.js$)|(?:dotnet-install\.(ps1|sh)$)|(?:dragdrop\.js$)|(?:effects\.js$)|(?:env/)|(?:erlang\.mk)|(?:extjs/.*?\.html$)|(?:extjs/.*?\.js$)|(?:extjs/.*?\.properties$)|(?:extjs/.*?\.txt$)|(?:extjs/.*?\.xml$)|(?:extjs/\.sencha/)|(?:extjs/builds/)|(?:extjs/cmd/)|(?:extjs/docs/)|(?:extjs/examples/)|(?:extjs/locale/)|(?:extjs/packages/)|(?:extjs/plugins/)|(?:extjs/resources/)|(?:extjs/src/)|(?:extjs/welcome/)|(?:fabfile\.py$)|(?:flow-typed/.*\.js$)|(?:font-?awesome/.*\.(css|less|scss|styl)$)|(?:font-?awesome\.(css|less|scss|styl)$)|(?:fontello(.*?)\.css$)|(?:foundation(\..*)?\.js$)|(?:foundation\.(css|less|scss|styl)$)|(?:fuelux\.js)|(?:gradle/wrapper/)|(?:gradlew$)|(?:gradlew\.bat$)|(?:html5shiv\.js$)|(?:inst/extdata/)|(?:jquery([^.]*)\.js$)|(?:jquery([^.]*)\.unobtrusive\-ajax\.js$)|(?:jquery([^.]*)\.validate(\.unobtrusive)?\.js$)|(?:jquery\-\d\.\d+(\.\d+)?\.js$)|(?:jquery\-ui(\-\d\.\d+(\.\d+)?)?(\.\w+)?\.(js|css)$)|(?:jquery\.(ui|effects)\.([^.]*)\.(js|css)$)|(?:jquery\.dataTables\.js)|(?:jquery\.fancybox\.(js|css))|(?:jquery\.fileupload(-\w+)?\.js$)|(?:jquery\.fn\.gantt\.js)|(?:knockout-(\d+\.){3}(debug\.)?js$)|(?:leaflet\.draw-src\.js)|(?:leaflet\.draw\.css)|(?:leaflet\.spin\.js)|(?:libtool\.m4)|(?:ltoptions\.m4)|(?:ltsugar\.m4)|(?:ltversion\.m4)|(?:lt~obsolete\.m4)|(?:materialize\.(css|less|scss|styl|js)$)|(?:modernizr\-\d\.\d+(\.\d+)?\.js$)|(?:modernizr\.custom\.\d+\.js$)|(?:mootools([^.]*)\d+\.\d+.\d+([^.]*)\.js$)|(?:mvnw$)|(?:mvnw\.cmd$)|(?:node_modules/)|(?:normalize\.(css|less|scss|styl)$)|(?:octicons\.css)|(?:pdf\.worker\.js)|(?:proguard-rules\.pro$)|(?:proguard\.pro$)|(?:prototype(.*)\.js$)|(?:puphpet/)|(?:react(-[^.]*)?\.js$)|(?:run\.n$)|(?:select2/.*\.(css|scss|js)$)|(?:shBrush([^.]*)\.js$)|(?:shCore\.js$)|(?:shLegacy\.js$)|(?:skeleton\.(css|less|scss|styl)$)|(?:slick\.\w+.js$)|(?:sprockets-octicons\.scss)|(?:testdata/)|(?:tiny_mce([^.]*)\.js$)|(?:tiny_mce/(langs|plugins|themes|utils))|(?:vendors?/)|(?:vignettes/)|(?:waf$)|(?:wicket-leaflet\.js)|(?:yahoo-([^.]*)\.js$)|(?:yui([^.]*)\.js$)))|(?:(.*?)\.d\.ts$)|(?:(3rd|[Tt]hird)[-_]?[Pp]arty/)|(?:([^\s]*)import\.(css|less|scss|styl)$)|(?:(\.|-)min\.(js|css)$)|(?:(^|\/)d3(\.v\d+)?([^.]*)\.js$)|(?:-vsdoc\.js$)|(?:\.imageset/)|(?:\.intellisense\.js$)|(?:\.xctemplate/)`)

internal/code-generator/generator/vendor.go

@@ -2,8 +2,12 @@ package generator
 
 import (
 	"bytes"
+	"fmt"
 	"io"
 	"io/ioutil"
+	"sort"
+	"strings"
+	"text/template"
 
 	"gopkg.in/yaml.v2"
 )
@@ -16,19 +20,97 @@ func Vendor(fileToParse, samplesDir, outPath, tmplPath, tmplName, commit string)
 		return err
 	}
 
-	var regexpList []string
+	var regexps []string
-	if err := yaml.Unmarshal(data, &regexpList); err != nil {
+	if err := yaml.Unmarshal(data, &regexps); err != nil {
-		return nil
+		return fmt.Errorf("failed to parse YAML %s, %q", fileToParse, err)
 	}
 
 	buf := &bytes.Buffer{}
-	if err := executeVendorTemplate(buf, regexpList, tmplPath, tmplName, commit); err != nil {
+	if err := executeVendorTemplate(buf, regexps, tmplPath, tmplName, commit); err != nil {
-		return nil
+		return err
 	}
 
 	return formatedWrite(outPath, buf.Bytes())
 }
 
-func executeVendorTemplate(out io.Writer, regexpList []string, tmplPath, tmplName, commit string) error {
+func executeVendorTemplate(out io.Writer, regexps []string, tmplPath, tmplName, commit string) error {
-	return executeTemplate(out, tmplName, tmplPath, commit, nil, regexpList)
+	funcs := template.FuncMap{"optimize": collateAllMatchers}
+	return executeTemplate(out, tmplName, tmplPath, commit, funcs, regexps)
+}
+
+func collateAllMatchers(regexps []string) string {
+	// We now collate all regexps from VendorMatchers to a single large regexp
+	// which is at least twice as fast to test than simply iterating & matching.
+	//
+	// ---
+	//
+	// We could test each matcher from VendorMatchers in turn i.e.
+	//
+	//  	func IsVendor(filename string) bool {
+	// 			for _, matcher := range data.VendorMatchers {
+	// 				if matcher.MatchString(filename) {
+	//					return true
+	//				}
+	//			}
+	//			return false
+	//		}
+	//
+	// Or naïvely concatentate all these regexps using groups i.e.
+	//
+	//		`(regexp1)|(regexp2)|(regexp3)|...`
+	//
+	// However, both of these are relatively slow and don't take advantage
+	// of the inherent structure within our regexps.
+	//
+	// Imperical observation: by looking at the regexps, we only have 3 types.
+	//  1. Those that start with `^`
+	//  2. Those that start with `(^|/)`
+	//  3. All the rest
+	//
+	// If we collate our regexps into these 3 groups - that will significantly
+	// reduce the likelihood of backtracking within the regexp trie matcher.
+	//
+	// A further improvement is to use non-capturing groups (?:) as otherwise
+	// the regexp parser, whilst matching, will have to allocate slices for
+	// matching positions. (A future improvement left out could be to
+	// enforce non-capturing groups within the sub-regexps.)
+	const (
+		caret        = "^"
+		caretOrSlash = "(^|/)"
+	)
+
+	sort.Strings(regexps)
+
+	var caretPrefixed, caretOrSlashPrefixed, theRest []string
+	// Check prefix, add to the respective group slices
+	for _, re := range regexps {
+		if strings.HasPrefix(re, caret) {
+			caretPrefixed = append(caretPrefixed, re[len(caret):])
+		} else if strings.HasPrefix(re, caretOrSlash) {
+			caretOrSlashPrefixed = append(caretOrSlashPrefixed, re[len(caretOrSlash):])
+		} else {
+			theRest = append(theRest, re)
+		}
+	}
+	var sb strings.Builder
+	appendGroupWithCommonPrefix(&sb, "^", caretPrefixed)
+	sb.WriteString("|")
+
+	appendGroupWithCommonPrefix(&sb, "(?:^|/)", caretOrSlashPrefixed)
+	sb.WriteString("|")
+
+	appendGroupWithCommonPrefix(&sb, "", theRest)
+	return sb.String()
+}
+
+func appendGroupWithCommonPrefix(sb *strings.Builder, commonPrefix string, res []string) {
+	sb.WriteString("(?:")
+	if commonPrefix != "" {
+		sb.WriteString(fmt.Sprintf("%s(?:(?:", commonPrefix))
+	}
+	sb.WriteString(strings.Join(res, ")|(?:"))
+	if commonPrefix != "" {
+		sb.WriteString("))")
+	}
+	sb.WriteString(")")
 }

internal/code-generator/main.go

@@ -134,7 +134,7 @@ func main() {
 
 	for _, file := range fileList {
 		if err := file.generate(file.fileToParse, file.samplesDir, file.outPath, file.tmplPath, file.tmplName, file.commit); err != nil {
-			log.Printf("error generating template %q to %q: %+v", file.tmplPath, file.outPath, err)
+			log.Fatalf("error generating template %q to %q: %+v", file.tmplPath, file.outPath, err)
 		}
 	}
 }

linguist_corpus_test.go

@@ -0,0 +1,71 @@
+package enry
+
+import (
+	"fmt"
+	"io/ioutil"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/go-enry/go-enry/v2/data"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/suite"
+)
+
+type linguistCorpusSuite struct {
+	enryBaseTestSuite
+}
+
+func Test_EnryOnLinguistCorpus(t *testing.T) {
+	suite.Run(t, new(linguistCorpusSuite))
+}
+
+// First part of the test_blob.rb#test_language
+// https://github.com/github/linguist/blob/59b2d88b2242e6062384e5fb876668cc30ead951/test/test_blob.rb#L258
+func (s *linguistCorpusSuite) TestLinguistSamples() {
+	const filenamesDir = "filenames"
+	var cornerCases = map[string]bool{
+		"drop_stuff.sql":        true, // https://github.com/src-d/enry/issues/194
+		"textobj-rubyblock.vba": true, // Because of unsupported negative lookahead RE syntax (https://github.com/github/linguist/blob/8083cb5a89cee2d99f5a988f165994d0243f0d1e/lib/linguist/heuristics.yml#L521)
+		// .es and .ice fail heuristics parsing, but do not fail any tests
+	}
+
+	var total, failed, ok, other int
+	var expected string
+	filepath.Walk(s.samplesDir, func(path string, f os.FileInfo, err error) error {
+		if f.IsDir() {
+			if f.Name() != filenamesDir {
+				expected, _ = data.LanguageByAlias(f.Name())
+			}
+
+			return nil
+		}
+
+		filename := filepath.Base(path)
+		content, _ := ioutil.ReadFile(path)
+
+		total++
+		obtained := GetLanguage(filename, content)
+		if obtained == OtherLanguage {
+			obtained = "Other"
+			other++
+		}
+
+		var status string
+		if expected == obtained {
+			status = "ok"
+			ok++
+		} else {
+			status = "failed"
+			failed++
+		}
+
+		if _, ok := cornerCases[filename]; ok {
+			s.T().Logf("\t\t[considered corner case] %s\texpected: %s\tobtained: %s\tstatus: %s\n", filename, expected, obtained, status)
+		} else {
+			assert.Equal(s.T(), expected, obtained, fmt.Sprintf("%s\texpected: %s\tobtained: %s\tstatus: %s\n", filename, expected, obtained, status))
+		}
+		return nil
+	})
+	s.T().Logf("\t\ttotal files: %d, ok: %d, failed: %d, other: %d\n", total, ok, failed, other)
+}

utils.go

@@ -3,8 +3,6 @@ package enry
 import (
 	"bytes"
 	"path/filepath"
-	"regexp"
-	"sort"
 	"strings"
 
 	"github.com/go-enry/go-enry/v2/data"
@@ -63,11 +61,9 @@ func IsDotFile(path string) bool {
 	return strings.HasPrefix(base, ".") && base != "."
 }
 
-var isVendorRegExp *regexp.Regexp
-
 // IsVendor returns whether or not path is a vendor path.
 func IsVendor(path string) bool {
-	return isVendorRegExp.MatchString(path)
+	return data.FastVendorMatcher.MatchString(path)
 }
 
 // IsTest returns whether or not path is a test path.
@@ -75,6 +71,16 @@ func IsTest(path string) bool {
 	return matchRegexSlice(data.TestMatchers, path)
 }
 
+func matchRegexSlice(exprs []regex.EnryRegexp, str string) bool {
+	for _, expr := range exprs {
+		if expr.MatchString(str) {
+			return true
+		}
+	}
+
+	return false
+}
+
 // IsBinary detects if data is a binary value based on:
 // http://git.kernel.org/cgit/git/git.git/tree/xdiff-interface.c?id=HEAD#n198
 func IsBinary(data []byte) bool {
@@ -102,16 +108,6 @@ func GetColor(language string) string {
 	return "#cccccc"
 }
 
-func matchRegexSlice(exprs []regex.EnryRegexp, str string) bool {
-	for _, expr := range exprs {
-		if expr.MatchString(str) {
-			return true
-		}
-	}
-
-	return false
-}
-
 // IsGenerated returns whether the file with the given path and content is a
 // generated file.
 func IsGenerated(path string, content []byte) bool {
@@ -135,112 +131,3 @@ func IsGenerated(path string, content []byte) bool {
 
 	return false
 }
-
-func init() {
-	// We now collate the individual regexps that make up the VendorMatchers to
-	// produce a single large regexp which is around twice as fast to test than
-	// simply iterating through all the regexps or naïvely collating the
-	// regexps.
-	//
-	// ---
-	//
-	// data.VendorMatchers here is a slice containing individual regexps that
-	// match a vendor file therefore if we want to test if a filename is a
-	// Vendor we need to test whether that filename matches one or more of
-	// those regexps.
-	//
-	// Now we could test each matcher in turn using a shortcircuiting test i.e.
-	//
-	//  	func IsVendor(filename string) bool {
-	// 			for _, matcher := range data.VendorMatchers {
-	// 				if matcher.Match(filename) {
-	//					return true
-	//				}
-	//			}
-	//			return false
-	//		}
-	//
-	// Or concatenate all these regexps using groups i.e.
-	//
-	//		`(regexp1)|(regexp2)|(regexp3)|...`
-	//
-	// However both of these are relatively slow and they don't take advantage
-	// of the inherent structure within our regexps...
-	//
-	// If we look at our regexps there are essentially three types of regexp:
-	//
-	// 1. Those that start with `^`
-	// 2. Those that start with `(^|/)`
-	// 3. Others
-	//
-	// If we collate our regexps into these groups that will significantly
-	// reduce the likelihood of backtracking within the regexp trie matcher.
-	//
-	// A further improvement is to use non-capturing groups as otherwise the
-	// regexp parser, whilst matching, will have to allocate slices for
-	// matching positions. (A future improvement here could be in the use of
-	// enforcing non-capturing groups within the sub-regexps too.)
-	//
-	// Finally if we sort the segments we can help the matcher build a more
-	// efficient matcher and trie.
-
-	// alias the VendorMatchers to simplify things
-	matchers := data.VendorMatchers
-
-	// Create three temporary string slices for our three groups above - prefixes removed
-	caretStrings := make([]string, 0, 10)
-	caretSegmentStrings := make([]string, 0, 10)
-	matcherStrings := make([]string, 0, len(matchers))
-
-	// Walk the matchers and check their string representation for each group prefix, remove it and add to the respective group slices
-	for _, matcher := range matchers {
-		str := matcher.String()
-		if str[0] == '^' {
-			caretStrings = append(caretStrings, str[1:])
-		} else if str[0:5] == "(^|/)" {
-			caretSegmentStrings = append(caretSegmentStrings, str[5:])
-		} else {
-			matcherStrings = append(matcherStrings, str)
-		}
-	}
-
-	// Sort the strings within each group - a potential further improvement could be in simplifying within these groups
-	sort.Strings(caretSegmentStrings)
-	sort.Strings(caretStrings)
-	sort.Strings(matcherStrings)
-
-	// Now build the collated regexp
-	sb := &strings.Builder{}
-
-	// Start with group 1 - those that started with `^`
-	sb.WriteString("(?:^(?:")
-	sb.WriteString(caretStrings[0])
-	for _, matcher := range caretStrings[1:] {
-		sb.WriteString(")|(?:")
-		sb.WriteString(matcher)
-	}
-	sb.WriteString("))")
-	sb.WriteString("|")
-
-	// Now add group 2 - those that started with `(^|/)`
-	sb.WriteString("(?:(?:^|/)(?:")
-	sb.WriteString(caretSegmentStrings[0])
-	for _, matcher := range caretSegmentStrings[1:] {
-		sb.WriteString(")|(?:")
-		sb.WriteString(matcher)
-	}
-	sb.WriteString("))")
-	sb.WriteString("|")
-
-	// Finally add the rest
-	sb.WriteString("(?:")
-	sb.WriteString(matcherStrings[0])
-	for _, matcher := range matcherStrings[1:] {
-		sb.WriteString(")|(?:")
-		sb.WriteString(matcher)
-	}
-	sb.WriteString(")")
-
-	// Compile the whole thing as the isVendorRegExp
-	isVendorRegExp = regexp.MustCompile(sb.String())
-}

utils_test.go

@@ -11,45 +11,53 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
+//TODO(bzz): port all from test/test_file_blob.rb test_vendored()
+//https://github.com/github/linguist/blob/86adc140d3e8903980565a2984f5532edf4ae875/test/test_file_blob.rb#L270-L583
+var vendorTests = []struct {
+	path     string
+	expected bool
+}{
+	{"cache/", true},
+	{"something_cache/", false},
+	{"random/cache/", true},
+	{"cache", false},
+	{"dependencies/", true},
+	{"Dependencies/", true},
+	{"dependency/", false},
+	{"dist/", true},
+	{"dist", false},
+	{"random/dist/", true},
+	{"random/dist", false},
+	{"deps/", true},
+	{"foodeps/", false},
+	{"configure", true},
+	{"a/configure", true},
+	{"config.guess", true},
+	{"config.guess/", false},
+	{".vscode/", true},
+	{"doc/_build/", true},
+	{"a/docs/_build/", true},
+	{"a/dasdocs/_build-vsdoc.js", true},
+	{"a/dasdocs/_build-vsdoc.j", false},
+	{"foo/bar", false},
+	{".sublime-project", true},
+	{"foo/vendor/foo", true},
+	{"leaflet.draw-src.js", true},
+	{"foo/bar/MochiKit.js", true},
+	{"foo/bar/dojo.js", true},
+	{"foo/env/whatever", true},
+	{"some/python/venv/", false},
+	{"foo/.imageset/bar", true},
+	{"Vagrantfile", true},
+	{"src/bootstrap-custom.js", true},
+	// {"/css/bootstrap.rtl.css", true}, // from linguist v7.23
+}
+
 func TestIsVendor(t *testing.T) {
-	tests := []struct {
+	for _, tt := range vendorTests {
-		path     string
-		expected bool
-	}{
-		{"cache/", true},
-		{"random/cache/", true},
-		{"cache", false},
-		{"dependencies/", true},
-		{"Dependencies/", true},
-		{"dependency/", false},
-		{"dist/", true},
-		{"dist", false},
-		{"random/dist/", true},
-		{"random/dist", false},
-		{"deps/", true},
-		{"configure", true},
-		{"a/configure", true},
-		{"config.guess", true},
-		{"config.guess/", false},
-		{".vscode/", true},
-		{"doc/_build/", true},
-		{"a/docs/_build/", true},
-		{"a/dasdocs/_build-vsdoc.js", true},
-		{"a/dasdocs/_build-vsdoc.j", false},
-		{"foo/bar", false},
-		{".sublime-project", true},
-		{"foo/vendor/foo", true},
-		{"leaflet.draw-src.js", true},
-		{"foo/bar/MochiKit.js", true},
-		{"foo/bar/dojo.js", true},
-		{"foo/env/whatever", true},
-		{"foo/.imageset/bar", true},
-		{"Vagrantfile", true},
-	}
-	for _, tt := range tests {
 		t.Run(tt.path, func(t *testing.T) {
 			if got := IsVendor(tt.path); got != tt.expected {
-				t.Errorf("IsVendor() = %v, expected %v", got, tt.expected)
+				t.Errorf("IsVendor(%q) = %v, expected %v", tt.path, got, tt.expected)
 			}
 		})
 	}
@@ -57,10 +65,9 @@ func TestIsVendor(t *testing.T) {
 
 func BenchmarkIsVendor(b *testing.B) {
 	for i := 0; i < b.N; i++ {
-		IsVendor(".vscode/")
+		for _, t := range vendorTests {
-		IsVendor("cache/")
+			IsVendor(t.path)
-		IsVendor("foo/bar")
+		}
-		IsVendor("foo/bar/MochiKit.js")
 	}
 }