changes in the API, ready to version 2

alias.go

@@ -2,7 +2,7 @@ package slinguist
 
 // CODE GENERATED AUTOMATICALLY WITH gopkg.in/src-d/simple-linguist.v1/internal/code-generator
 // THIS FILE SHOULD NOT BE EDITED BY HAND
-// Extracted from github/linguist commit: 60f864a138650dd17fafc94814be9ee2d3aaef8c
+// Extracted from github/linguist commit: b6460f8ed6b249281ada099ca28bd8f1230b8892
 
 // languagesByAlias keeps alias for different languages and use the name of the languages as an alias too.
 // All the keys (alias or not) are written in lower case and the whitespaces has been replaced by underscores.
@@ -608,9 +608,12 @@ var languagesByAlias = map[string]string{
 	"visual_basic":          "Visual Basic",
 	"volt":                  "Volt",
 	"vue":                   "Vue",
+	"wasm":                  "WebAssembly",
+	"wast":                  "WebAssembly",
 	"wavefront_material":    "Wavefront Material",
 	"wavefront_object":      "Wavefront Object",
 	"web_ontology_language": "Web Ontology Language",
+	"webassembly":           "WebAssembly",
 	"webidl":                "WebIDL",
 	"winbatch":              "Batchfile",
 	"wisp":                  "wisp",

classifier.go

@@ -6,36 +6,11 @@ import (
 	"gopkg.in/src-d/simple-linguist.v1/internal/tokenizer"
 )
 
-func getLanguageByClassifier(content []byte, candidates []string, classifier Classifier) string {
-	if classifier == nil {
-		classifier = DefaultClassifier
-	}
-
-	scores := classifier.Classify(content, candidates)
-	if len(scores) == 0 {
-		return OtherLanguage
-	}
-
-	return getLangugeHigherScore(scores)
-}
-
-func getLangugeHigherScore(scores map[string]float64) string {
-	var language string
-	higher := -math.MaxFloat64
-	for lang, score := range scores {
-		if higher < score {
-			language = lang
-			higher = score
-		}
-	}
-
-	return language
-}
-
 // Classifier is the interface that contains the method Classify which is in charge to assign scores to the possibles candidates.
-// The scores must order the candidates so as the highest score be the most probably language of the content.
+// The scores must order the candidates so as the highest score be the most probably language of the content. The candidates is
+// a map which can be used to assign weights to languages dynamically.
 type Classifier interface {
-	Classify(content []byte, candidates []string) map[string]float64
+	Classify(content []byte, candidates map[string]float64) map[string]float64
 }
 
 type classifier struct {
@@ -44,36 +19,36 @@ type classifier struct {
 	tokensTotal               float64
 }
 
-func (c *classifier) Classify(content []byte, candidates []string) map[string]float64 {
+func (c *classifier) Classify(content []byte, candidates map[string]float64) map[string]float64 {
 	if len(content) == 0 {
 		return nil
 	}
 
-	var languages []string
+	var languages map[string]float64
 	if len(candidates) == 0 {
 		languages = c.knownLangs()
 	} else {
-		languages = make([]string, 0, len(candidates))
-		for _, candidate := range candidates {
+		languages = make(map[string]float64, len(candidates))
+		for candidate, weight := range candidates {
 			if lang, ok := GetLanguageByAlias(candidate); ok {
-				languages = append(languages, lang)
+				languages[lang] = weight
 			}
 		}
 	}
 
 	tokens := tokenizer.Tokenize(content)
 	scores := make(map[string]float64, len(languages))
-	for _, language := range languages {
+	for language := range languages {
 		scores[language] = c.tokensLogProbability(tokens, language) + c.languagesLogProbabilities[language]
 	}
 
 	return scores
 }
 
-func (c *classifier) knownLangs() []string {
-	langs := make([]string, 0, len(c.languagesLogProbabilities))
+func (c *classifier) knownLangs() map[string]float64 {
+	langs := make(map[string]float64, len(c.languagesLogProbabilities))
 	for lang := range c.languagesLogProbabilities {
-		langs = append(langs, lang)
+		langs[lang]++
 	}
 
 	return langs

common.go

@@ -1,6 +1,7 @@
 package slinguist
 
 import (
+	"math"
 	"path/filepath"
 	"strings"
 )
@@ -8,100 +9,142 @@ import (
 // OtherLanguage is used as a zero value when a function can not return a specific language.
 const OtherLanguage = "Other"
 
+// Strategy type fix the signature for the functions that can be used as a strategy.
+type Strategy func(filename string, content []byte) (languages []string)
+
+var strategies = []Strategy{
+	GetLanguagesByModeline,
+	GetLanguagesByFilename,
+	GetLanguagesByShebang,
+	GetLanguagesByExtension,
+	GetLanguagesByContent,
+}
+
 // GetLanguage applies a sequence of strategies based on the given filename and content
 // to find out the most probably language to return.
 func GetLanguage(filename string, content []byte) string {
-	if lang, safe := GetLanguageByModeline(content); safe {
-		return lang
+	candidates := map[string]float64{}
+	for _, strategy := range strategies {
+		languages := strategy(filename, content)
+		if len(languages) == 1 {
+			return languages[0]
+		}
+
+		if len(languages) > 0 {
+			for _, language := range languages {
+				candidates[language]++
+			}
+		}
 	}
 
-	if lang, safe := GetLanguageByFilename(filename); safe {
-		return lang
+	if len(candidates) == 0 {
+		return OtherLanguage
 	}
 
-	if lang, safe := GetLanguageByShebang(content); safe {
-		return lang
-	}
-
-	if lang, safe := GetLanguageByExtension(filename); safe {
-		return lang
-	}
-
-	if lang, safe := GetLanguageByContent(filename, content); safe {
-		return lang
-	}
-
-	lang := GetLanguageByClassifier(content, nil, nil)
+	lang := GetLanguageByClassifier(content, candidates, nil)
 	return lang
 }
 
 // GetLanguageByModeline returns the language of the given content looking for the modeline,
 // and safe to indicate the sureness of returned language.
 func GetLanguageByModeline(content []byte) (lang string, safe bool) {
-	return getLanguageByModeline(content)
+	return getLangAndSafe("", content, GetLanguagesByModeline)
 }
 
 // GetLanguageByFilename returns a language based on the given filename, and safe to indicate
 // the sureness of returned language.
 func GetLanguageByFilename(filename string) (lang string, safe bool) {
-	return getLanguageByFilename(filename)
+	return getLangAndSafe(filename, nil, GetLanguagesByFilename)
 }
 
-func getLanguageByFilename(filename string) (lang string, safe bool) {
-	lang, safe = languagesByFilename[filename]
-	if lang == "" {
-		lang = OtherLanguage
-	}
-
-	return
+// GetLanguagesByFilename returns a slice of possible languages for the given filename, content will be ignored.
+// It accomplish the signature to be a Strategy type.
+func GetLanguagesByFilename(filename string, content []byte) []string {
+	return languagesByFilename[filename]
 }
 
 // GetLanguageByShebang returns the language of the given content looking for the shebang line,
 // and safe to indicate the sureness of returned language.
 func GetLanguageByShebang(content []byte) (lang string, safe bool) {
-	return getLanguageByShebang(content)
+	return getLangAndSafe("", content, GetLanguagesByShebang)
 }
 
 // GetLanguageByExtension returns a language based on the given filename, and safe to indicate
 // the sureness of returned language.
 func GetLanguageByExtension(filename string) (lang string, safe bool) {
-	return getLanguageByExtension(filename)
+	return getLangAndSafe(filename, nil, GetLanguagesByExtension)
 }
 
-func getLanguageByExtension(filename string) (lang string, safe bool) {
+// GetLanguagesByExtension returns a slice of possible languages for the given filename, content will be ignored.
+// It accomplish the signature to be a Strategy type.
+func GetLanguagesByExtension(filename string, content []byte) []string {
 	ext := strings.ToLower(filepath.Ext(filename))
-	lang = OtherLanguage
-	langs, ok := languagesByExtension[ext]
-	if !ok {
-		return
-	}
-
-	lang = langs[0]
-	safe = len(langs) == 1
-	return
+	return languagesByExtension[ext]
 }
 
 // GetLanguageByContent returns a language based on the filename and heuristics applies to the content,
 // and safe to indicate the sureness of returned language.
 func GetLanguageByContent(filename string, content []byte) (lang string, safe bool) {
-	return getLanguageByContent(filename, content)
+	return getLangAndSafe(filename, content, GetLanguagesByContent)
 }
 
-func getLanguageByContent(filename string, content []byte) (lang string, safe bool) {
+// GetLanguagesByContent returns a slice of possible languages for the given content, filename will be ignored.
+// It accomplish the signature to be a Strategy type.
+func GetLanguagesByContent(filename string, content []byte) []string {
 	ext := strings.ToLower(filepath.Ext(filename))
-	if fnMatcher, ok := contentMatchers[ext]; ok {
-		lang, safe = fnMatcher(content)
-	} else {
-		lang = OtherLanguage
+	fnMatcher, ok := contentMatchers[ext]
+	if !ok {
+		return nil
 	}
 
+	return fnMatcher(content)
+}
+
+func getLangAndSafe(filename string, content []byte, getLanguageByStrategy Strategy) (lang string, safe bool) {
+	languages := getLanguageByStrategy(filename, content)
+	if len(languages) == 0 {
+		lang = OtherLanguage
+		return
+	}
+
+	lang = languages[0]
+	safe = len(languages) == 1
 	return
 }
 
 // GetLanguageByClassifier takes in a content and a list of candidates, and apply the classifier's Classify method to
-// get the most probably language. If classifier is null then DefaultClassfier will be used.
-func GetLanguageByClassifier(content []byte, candidates []string, classifier Classifier) string {
-	return getLanguageByClassifier(content, candidates, classifier)
+// get the most probably language. If classifier is null then DefaultClassfier will be used. If there aren't candidates
+// OtherLanguage is returned.
+func GetLanguageByClassifier(content []byte, candidates map[string]float64, classifier Classifier) string {
+	scores := GetLanguagesByClassifier(content, candidates, classifier)
+	if len(scores) == 0 {
+		return OtherLanguage
+	}
+
+	return getLangugeHigherScore(scores)
+}
+
+func getLangugeHigherScore(scores map[string]float64) string {
+	var language string
+	higher := -math.MaxFloat64
+	for lang, score := range scores {
+		if higher < score {
+			language = lang
+			higher = score
+		}
+	}
+
+	return language
+}
+
+// GetLanguagesByClassifier returns a map of possible languages as keys and a score as value based on content and candidates. The values can be ordered
+// with the highest value as the most probably language. If classifier is null then DefaultClassfier will be used.
+func GetLanguagesByClassifier(content []byte, candidates map[string]float64, classifier Classifier) map[string]float64 {
+	if classifier == nil {
+		classifier = DefaultClassifier
+	}
+
+	return classifier.Classify(content, candidates)
 }
 
 // GetLanguageExtensions returns the different extensions being used by the language.

common_test.go

@@ -34,7 +34,7 @@ func (s *SimpleLinguistTestSuite) TestGetLanguage() {
 
 	for _, test := range tests {
 		language := GetLanguage(test.filename, test.content)
-		assert.Equal(s.T(), language, test.expected, fmt.Sprintf("%v: %v, expected: %v", test.name, language, test.expected))
+		assert.Equal(s.T(), test.expected, language, fmt.Sprintf("%v: %v, expected: %v", test.name, language, test.expected))
 	}
 }
 
@@ -91,8 +91,8 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageByModelineLinguist() {
 		assert.NoError(s.T(), err)
 
 		lang, safe := GetLanguageByModeline(content)
-		assert.Equal(s.T(), lang, test.expectedLang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
-		assert.Equal(s.T(), safe, test.expectedSafe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
+		assert.Equal(s.T(), test.expectedLang, lang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
+		assert.Equal(s.T(), test.expectedSafe, safe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
 	}
 }
 
@@ -116,8 +116,8 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageByModeline() {
 
 	for _, test := range tests {
 		lang, safe := GetLanguageByModeline(test.content)
-		assert.Equal(s.T(), lang, test.expectedLang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
-		assert.Equal(s.T(), safe, test.expectedSafe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
+		assert.Equal(s.T(), test.expectedLang, lang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
+		assert.Equal(s.T(), test.expectedSafe, safe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
 	}
 }
 
@@ -140,8 +140,8 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageByFilename() {
 
 	for _, test := range tests {
 		lang, safe := GetLanguageByFilename(test.filename)
-		assert.Equal(s.T(), lang, test.expectedLang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
-		assert.Equal(s.T(), safe, test.expectedSafe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
+		assert.Equal(s.T(), test.expectedLang, lang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
+		assert.Equal(s.T(), test.expectedSafe, safe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
 	}
 }
 
@@ -181,8 +181,8 @@ println("The shell script says ",vm.arglist.concat(" "));`
 
 	for _, test := range tests {
 		lang, safe := GetLanguageByShebang(test.content)
-		assert.Equal(s.T(), lang, test.expectedLang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
-		assert.Equal(s.T(), safe, test.expectedSafe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
+		assert.Equal(s.T(), test.expectedLang, lang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
+		assert.Equal(s.T(), test.expectedSafe, safe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
 	}
 }
 
@@ -200,8 +200,8 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageByExtension() {
 
 	for _, test := range tests {
 		lang, safe := GetLanguageByExtension(test.filename)
-		assert.Equal(s.T(), lang, test.expectedLang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
-		assert.Equal(s.T(), safe, test.expectedSafe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
+		assert.Equal(s.T(), test.expectedLang, lang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
+		assert.Equal(s.T(), test.expectedSafe, safe, fmt.Sprintf("%v: safe = %v, expected: %v", test.name, safe, test.expectedSafe))
 	}
 }
 
@@ -263,15 +263,15 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageByClassifier() {
 	test := []struct {
 		name       string
 		filename   string
-		candidates []string
+		candidates map[string]float64
 		expected   string
 	}{
-		{name: "TestGetLanguageByClassifier_1", filename: filepath.Join(samples, "C/blob.c"), candidates: []string{"python", "ruby", "c", "c++"}, expected: "C"},
+		{name: "TestGetLanguageByClassifier_1", filename: filepath.Join(samples, "C/blob.c"), candidates: map[string]float64{"python": 1.00, "ruby": 1.00, "c": 1.00, "c++": 1.00}, expected: "C"},
 		{name: "TestGetLanguageByClassifier_2", filename: filepath.Join(samples, "C/blob.c"), candidates: nil, expected: "C"},
 		{name: "TestGetLanguageByClassifier_3", filename: filepath.Join(samples, "C/main.c"), candidates: nil, expected: "C"},
-		{name: "TestGetLanguageByClassifier_4", filename: filepath.Join(samples, "C/blob.c"), candidates: []string{"python", "ruby", "c++"}, expected: "C++"},
-		{name: "TestGetLanguageByClassifier_5", filename: filepath.Join(samples, "C/blob.c"), candidates: []string{"ruby"}, expected: "Ruby"},
-		{name: "TestGetLanguageByClassifier_6", filename: filepath.Join(samples, "Python/django-models-base.py"), candidates: []string{"python", "ruby", "c", "c++"}, expected: "Python"},
+		{name: "TestGetLanguageByClassifier_4", filename: filepath.Join(samples, "C/blob.c"), candidates: map[string]float64{"python": 1.00, "ruby": 1.00, "c++": 1.00}, expected: "C++"},
+		{name: "TestGetLanguageByClassifier_5", filename: filepath.Join(samples, "C/blob.c"), candidates: map[string]float64{"ruby": 1.00}, expected: "Ruby"},
+		{name: "TestGetLanguageByClassifier_6", filename: filepath.Join(samples, "Python/django-models-base.py"), candidates: map[string]float64{"python": 1.00, "ruby": 1.00, "c": 1.00, "c++": 1.00}, expected: "Python"},
 		{name: "TestGetLanguageByClassifier_7", filename: filepath.Join(samples, "Python/django-models-base.py"), candidates: nil, expected: "Python"},
 	}
 
@@ -280,7 +280,7 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageByClassifier() {
 		assert.NoError(s.T(), err)
 
 		lang := GetLanguageByClassifier(content, test.candidates, nil)
-		assert.Equal(s.T(), lang, test.expected, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expected))
+		assert.Equal(s.T(), test.expected, lang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expected))
 	}
 }
 
@@ -297,7 +297,7 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageExtensions() {
 
 	for _, test := range tests {
 		extensions := GetLanguageExtensions(test.language)
-		assert.EqualValues(s.T(), extensions, test.expected, fmt.Sprintf("%v: extensions = %v, expected: %v", test.name, extensions, test.expected))
+		assert.EqualValues(s.T(), test.expected, extensions, fmt.Sprintf("%v: extensions = %v, expected: %v", test.name, extensions, test.expected))
 	}
 }
 
@@ -320,7 +320,7 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageType() {
 
 	for _, test := range tests {
 		langType := GetLanguageType(test.language)
-		assert.Equal(s.T(), langType, test.expected, fmt.Sprintf("%v: langType = %v, expected: %v", test.name, langType, test.expected))
+		assert.Equal(s.T(), test.expected, langType, fmt.Sprintf("%v: langType = %v, expected: %v", test.name, langType, test.expected))
 	}
 }
 
@@ -345,7 +345,7 @@ func (s *SimpleLinguistTestSuite) TestGetLanguageByAlias() {
 
 	for _, test := range tests {
 		lang, ok := GetLanguageByAlias(test.alias)
-		assert.Equal(s.T(), lang, test.expectedLang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
-		assert.Equal(s.T(), ok, test.expectedOk, fmt.Sprintf("%v: ok = %v, expected: %v", test.name, ok, test.expectedOk))
+		assert.Equal(s.T(), test.expectedLang, lang, fmt.Sprintf("%v: lang = %v, expected: %v", test.name, lang, test.expectedLang))
+		assert.Equal(s.T(), test.expectedOk, ok, fmt.Sprintf("%v: ok = %v, expected: %v", test.name, ok, test.expectedOk))
 	}
 }

content.go

@@ -2,447 +2,447 @@ package slinguist
 
 // CODE GENERATED AUTOMATICALLY WITH gopkg.in/src-d/simple-linguist.v1/internal/code-generator
 // THIS FILE SHOULD NOT BE EDITED BY HAND
-// Extracted from github/linguist commit: 60f864a138650dd17fafc94814be9ee2d3aaef8c
+// Extracted from github/linguist commit: b6460f8ed6b249281ada099ca28bd8f1230b8892
 
 import (
 	"regexp"
 )
 
-type languageMatcher func([]byte) (string, bool)
+type languageMatcher func([]byte) []string
 
 var contentMatchers = map[string]languageMatcher{
-	".asc": func(i []byte) (string, bool) {
+	".asc": func(i []byte) []string {
 		if asc_PublicKey_Matcher_0.Match(i) {
-			return "Public Key", true
+			return []string{"Public Key"}
 		} else if asc_AsciiDoc_Matcher_0.Match(i) {
-			return "AsciiDoc", true
+			return []string{"AsciiDoc"}
 		} else if asc_AGSScript_Matcher_0.Match(i) {
-			return "AGS Script", true
+			return []string{"AGS Script"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".bb": func(i []byte) (string, bool) {
+	".bb": func(i []byte) []string {
 		if bb_BlitzBasic_Matcher_0.Match(i) || bb_BlitzBasic_Matcher_1.Match(i) {
-			return "BlitzBasic", true
+			return []string{"BlitzBasic"}
 		} else if bb_BitBake_Matcher_0.Match(i) {
-			return "BitBake", true
+			return []string{"BitBake"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".builds": func(i []byte) (string, bool) {
+	".builds": func(i []byte) []string {
 		if builds_XML_Matcher_0.Match(i) {
-			return "XML", true
+			return []string{"XML"}
 		}
 
-		return "Text", true
+		return []string{"Text"}
 	},
-	".ch": func(i []byte) (string, bool) {
+	".ch": func(i []byte) []string {
 		if ch_xBase_Matcher_0.Match(i) {
-			return "xBase", true
+			return []string{"xBase"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".cl": func(i []byte) (string, bool) {
+	".cl": func(i []byte) []string {
 		if cl_CommonLisp_Matcher_0.Match(i) {
-			return "Common Lisp", true
+			return []string{"Common Lisp"}
 		} else if cl_Cool_Matcher_0.Match(i) {
-			return "Cool", true
+			return []string{"Cool"}
 		} else if cl_OpenCL_Matcher_0.Match(i) {
-			return "OpenCL", true
+			return []string{"OpenCL"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".cls": func(i []byte) (string, bool) {
+	".cls": func(i []byte) []string {
 		if cls_TeX_Matcher_0.Match(i) {
-			return "TeX", true
+			return []string{"TeX"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".cs": func(i []byte) (string, bool) {
+	".cs": func(i []byte) []string {
 		if cs_Smalltalk_Matcher_0.Match(i) {
-			return "Smalltalk", true
+			return []string{"Smalltalk"}
 		} else if cs_CSharp_Matcher_0.Match(i) || cs_CSharp_Matcher_1.Match(i) {
-			return "C#", true
+			return []string{"C#"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".d": func(i []byte) (string, bool) {
+	".d": func(i []byte) []string {
 		if d_D_Matcher_0.Match(i) {
-			return "D", true
+			return []string{"D"}
 		} else if d_DTrace_Matcher_0.Match(i) {
-			return "DTrace", true
+			return []string{"DTrace"}
 		} else if d_Makefile_Matcher_0.Match(i) {
-			return "Makefile", true
+			return []string{"Makefile"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".ecl": func(i []byte) (string, bool) {
+	".ecl": func(i []byte) []string {
 		if ecl_ECLiPSe_Matcher_0.Match(i) {
-			return "ECLiPSe", true
+			return []string{"ECLiPSe"}
 		} else if ecl_ECL_Matcher_0.Match(i) {
-			return "ECL", true
+			return []string{"ECL"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".es": func(i []byte) (string, bool) {
+	".es": func(i []byte) []string {
 		if es_Erlang_Matcher_0.Match(i) {
-			return "Erlang", true
+			return []string{"Erlang"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".f": func(i []byte) (string, bool) {
+	".f": func(i []byte) []string {
 		if f_Forth_Matcher_0.Match(i) {
-			return "Forth", true
+			return []string{"Forth"}
 		} else if f_FilebenchWML_Matcher_0.Match(i) {
-			return "Filebench WML", true
+			return []string{"Filebench WML"}
 		} else if f_Fortran_Matcher_0.Match(i) {
-			return "Fortran", true
+			return []string{"Fortran"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".for": func(i []byte) (string, bool) {
+	".for": func(i []byte) []string {
 		if for_Forth_Matcher_0.Match(i) {
-			return "Forth", true
+			return []string{"Forth"}
 		} else if for_Fortran_Matcher_0.Match(i) {
-			return "Fortran", true
+			return []string{"Fortran"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".fr": func(i []byte) (string, bool) {
+	".fr": func(i []byte) []string {
 		if fr_Forth_Matcher_0.Match(i) {
-			return "Forth", true
+			return []string{"Forth"}
 		} else if fr_Frege_Matcher_0.Match(i) {
-			return "Frege", true
+			return []string{"Frege"}
 		}
 
-		return "Text", true
+		return []string{"Text"}
 	},
-	".fs": func(i []byte) (string, bool) {
+	".fs": func(i []byte) []string {
 		if fs_Forth_Matcher_0.Match(i) {
-			return "Forth", true
+			return []string{"Forth"}
 		} else if fs_FSharp_Matcher_0.Match(i) {
-			return "F#", true
+			return []string{"F#"}
 		} else if fs_GLSL_Matcher_0.Match(i) {
-			return "GLSL", true
+			return []string{"GLSL"}
 		} else if fs_Filterscript_Matcher_0.Match(i) {
-			return "Filterscript", true
+			return []string{"Filterscript"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".gs": func(i []byte) (string, bool) {
+	".gs": func(i []byte) []string {
 		if gs_Gosu_Matcher_0.Match(i) {
-			return "Gosu", true
+			return []string{"Gosu"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".h": func(i []byte) (string, bool) {
+	".h": func(i []byte) []string {
 		if h_ObjectiveDashC_Matcher_0.Match(i) {
-			return "Objective-C", true
+			return []string{"Objective-C"}
 		} else if h_CPlusPlus_Matcher_0.Match(i) || h_CPlusPlus_Matcher_1.Match(i) || h_CPlusPlus_Matcher_2.Match(i) || h_CPlusPlus_Matcher_3.Match(i) || h_CPlusPlus_Matcher_4.Match(i) || h_CPlusPlus_Matcher_5.Match(i) || h_CPlusPlus_Matcher_6.Match(i) {
-			return "C++", true
+			return []string{"C++"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".inc": func(i []byte) (string, bool) {
+	".inc": func(i []byte) []string {
 		if inc_PHP_Matcher_0.Match(i) {
-			return "PHP", true
+			return []string{"PHP"}
 		} else if inc_POVDashRaySDL_Matcher_0.Match(i) {
-			return "POV-Ray SDL", true
+			return []string{"POV-Ray SDL"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".l": func(i []byte) (string, bool) {
+	".l": func(i []byte) []string {
 		if l_CommonLisp_Matcher_0.Match(i) {
-			return "Common Lisp", true
+			return []string{"Common Lisp"}
 		} else if l_Lex_Matcher_0.Match(i) {
-			return "Lex", true
+			return []string{"Lex"}
 		} else if l_Roff_Matcher_0.Match(i) {
-			return "Roff", true
+			return []string{"Roff"}
 		} else if l_PicoLisp_Matcher_0.Match(i) {
-			return "PicoLisp", true
+			return []string{"PicoLisp"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".ls": func(i []byte) (string, bool) {
+	".ls": func(i []byte) []string {
 		if ls_LoomScript_Matcher_0.Match(i) {
-			return "LoomScript", true
+			return []string{"LoomScript"}
 		}
 
-		return "LiveScript", true
+		return []string{"LiveScript"}
 	},
-	".lsp": func(i []byte) (string, bool) {
+	".lsp": func(i []byte) []string {
 		if lsp_CommonLisp_Matcher_0.Match(i) {
-			return "Common Lisp", true
+			return []string{"Common Lisp"}
 		} else if lsp_NewLisp_Matcher_0.Match(i) {
-			return "NewLisp", true
+			return []string{"NewLisp"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".lisp": func(i []byte) (string, bool) {
+	".lisp": func(i []byte) []string {
 		if lisp_CommonLisp_Matcher_0.Match(i) {
-			return "Common Lisp", true
+			return []string{"Common Lisp"}
 		} else if lisp_NewLisp_Matcher_0.Match(i) {
-			return "NewLisp", true
+			return []string{"NewLisp"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".m": func(i []byte) (string, bool) {
+	".m": func(i []byte) []string {
 		if m_ObjectiveDashC_Matcher_0.Match(i) {
-			return "Objective-C", true
+			return []string{"Objective-C"}
 		} else if m_Mercury_Matcher_0.Match(i) {
-			return "Mercury", true
+			return []string{"Mercury"}
 		} else if m_MUF_Matcher_0.Match(i) {
-			return "MUF", true
+			return []string{"MUF"}
 		} else if m_M_Matcher_0.Match(i) {
-			return "M", true
+			return []string{"M"}
 		} else if m_Mathematica_Matcher_0.Match(i) {
-			return "Mathematica", true
+			return []string{"Mathematica"}
 		} else if m_Matlab_Matcher_0.Match(i) {
-			return "Matlab", true
+			return []string{"Matlab"}
 		} else if m_Limbo_Matcher_0.Match(i) {
-			return "Limbo", true
+			return []string{"Limbo"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".md": func(i []byte) (string, bool) {
+	".md": func(i []byte) []string {
 		if md_Markdown_Matcher_0.Match(i) || md_Markdown_Matcher_1.Match(i) {
-			return "Markdown", true
+			return []string{"Markdown"}
 		} else if md_GCCMachineDescription_Matcher_0.Match(i) {
-			return "GCC Machine Description", true
+			return []string{"GCC Machine Description"}
 		}
 
-		return "Markdown", true
+		return []string{"Markdown"}
 	},
-	".ml": func(i []byte) (string, bool) {
+	".ml": func(i []byte) []string {
 		if ml_OCaml_Matcher_0.Match(i) {
-			return "OCaml", true
+			return []string{"OCaml"}
 		} else if ml_StandardML_Matcher_0.Match(i) {
-			return "Standard ML", true
+			return []string{"Standard ML"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".mod": func(i []byte) (string, bool) {
+	".mod": func(i []byte) []string {
 		if mod_XML_Matcher_0.Match(i) {
-			return "XML", true
+			return []string{"XML"}
 		} else if mod_ModulaDash2_Matcher_0.Match(i) || mod_ModulaDash2_Matcher_1.Match(i) {
-			return "Modula-2", true
+			return []string{"Modula-2"}
 		}
 
-		return "Linux Kernel Module", false
+		return []string{"Linux Kernel Module", "AMPL"}
 	},
-	".ms": func(i []byte) (string, bool) {
+	".ms": func(i []byte) []string {
 		if ms_Roff_Matcher_0.Match(i) {
-			return "Roff", true
+			return []string{"Roff"}
 		}
 
-		return "MAXScript", true
+		return []string{"MAXScript"}
 	},
-	".n": func(i []byte) (string, bool) {
+	".n": func(i []byte) []string {
 		if n_Roff_Matcher_0.Match(i) {
-			return "Roff", true
+			return []string{"Roff"}
 		} else if n_Nemerle_Matcher_0.Match(i) {
-			return "Nemerle", true
+			return []string{"Nemerle"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".ncl": func(i []byte) (string, bool) {
+	".ncl": func(i []byte) []string {
 		if ncl_Text_Matcher_0.Match(i) {
-			return "Text", true
+			return []string{"Text"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".nl": func(i []byte) (string, bool) {
+	".nl": func(i []byte) []string {
 		if nl_NL_Matcher_0.Match(i) {
-			return "NL", true
+			return []string{"NL"}
 		}
 
-		return "NewLisp", true
+		return []string{"NewLisp"}
 	},
-	".php": func(i []byte) (string, bool) {
+	".php": func(i []byte) []string {
 		if php_Hack_Matcher_0.Match(i) {
-			return "Hack", true
+			return []string{"Hack"}
 		} else if php_PHP_Matcher_0.Match(i) {
-			return "PHP", true
+			return []string{"PHP"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".pl": func(i []byte) (string, bool) {
+	".pl": func(i []byte) []string {
 		if pl_Prolog_Matcher_0.Match(i) {
-			return "Prolog", true
+			return []string{"Prolog"}
 		} else if pl_Perl_Matcher_0.Match(i) {
-			return "Perl", true
+			return []string{"Perl"}
 		} else if pl_Perl6_Matcher_0.Match(i) {
-			return "Perl6", true
+			return []string{"Perl6"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".pm": func(i []byte) (string, bool) {
+	".pm": func(i []byte) []string {
 		if pm_Perl6_Matcher_0.Match(i) {
-			return "Perl6", true
+			return []string{"Perl6"}
 		} else if pm_Perl_Matcher_0.Match(i) {
-			return "Perl", true
+			return []string{"Perl"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".pod": func(i []byte) (string, bool) {
+	".pod": func(i []byte) []string {
 		if pod_Pod_Matcher_0.Match(i) {
-			return "Pod", true
+			return []string{"Pod"}
 		}
 
-		return "Perl", true
+		return []string{"Perl"}
 	},
-	".pro": func(i []byte) (string, bool) {
+	".pro": func(i []byte) []string {
 		if pro_Prolog_Matcher_0.Match(i) {
-			return "Prolog", true
+			return []string{"Prolog"}
 		} else if pro_INI_Matcher_0.Match(i) {
-			return "INI", true
+			return []string{"INI"}
 		} else if pro_QMake_Matcher_0.Match(i) && pro_QMake_Matcher_1.Match(i) {
-			return "QMake", true
+			return []string{"QMake"}
 		} else if pro_IDL_Matcher_0.Match(i) {
-			return "IDL", true
+			return []string{"IDL"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".props": func(i []byte) (string, bool) {
+	".props": func(i []byte) []string {
 		if props_XML_Matcher_0.Match(i) {
-			return "XML", true
+			return []string{"XML"}
 		} else if props_INI_Matcher_0.Match(i) {
-			return "INI", true
+			return []string{"INI"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".r": func(i []byte) (string, bool) {
+	".r": func(i []byte) []string {
 		if r_Rebol_Matcher_0.Match(i) {
-			return "Rebol", true
+			return []string{"Rebol"}
 		} else if r_R_Matcher_0.Match(i) {
-			return "R", true
+			return []string{"R"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".rno": func(i []byte) (string, bool) {
+	".rno": func(i []byte) []string {
 		if rno_RUNOFF_Matcher_0.Match(i) {
-			return "RUNOFF", true
+			return []string{"RUNOFF"}
 		} else if rno_Roff_Matcher_0.Match(i) {
-			return "Roff", true
+			return []string{"Roff"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".rpy": func(i []byte) (string, bool) {
+	".rpy": func(i []byte) []string {
 		if rpy_Python_Matcher_0.Match(i) {
-			return "Python", true
+			return []string{"Python"}
 		}
 
-		return "Ren'Py", true
+		return []string{"Ren'Py"}
 	},
-	".rs": func(i []byte) (string, bool) {
+	".rs": func(i []byte) []string {
 		if rs_Rust_Matcher_0.Match(i) {
-			return "Rust", true
+			return []string{"Rust"}
 		} else if rs_RenderScript_Matcher_0.Match(i) {
-			return "RenderScript", true
+			return []string{"RenderScript"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".sc": func(i []byte) (string, bool) {
+	".sc": func(i []byte) []string {
 		if sc_SuperCollider_Matcher_0.Match(i) || sc_SuperCollider_Matcher_1.Match(i) || sc_SuperCollider_Matcher_2.Match(i) {
-			return "SuperCollider", true
+			return []string{"SuperCollider"}
 		} else if sc_Scala_Matcher_0.Match(i) || sc_Scala_Matcher_1.Match(i) || sc_Scala_Matcher_2.Match(i) {
-			return "Scala", true
+			return []string{"Scala"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".sql": func(i []byte) (string, bool) {
+	".sql": func(i []byte) []string {
 		if sql_PLpgSQL_Matcher_0.Match(i) || sql_PLpgSQL_Matcher_1.Match(i) || sql_PLpgSQL_Matcher_2.Match(i) {
-			return "PLpgSQL", true
+			return []string{"PLpgSQL"}
 		} else if sql_SQLPL_Matcher_0.Match(i) || sql_SQLPL_Matcher_1.Match(i) {
-			return "SQLPL", true
+			return []string{"SQLPL"}
 		} else if sql_PLSQL_Matcher_0.Match(i) || sql_PLSQL_Matcher_1.Match(i) {
-			return "PLSQL", true
+			return []string{"PLSQL"}
 		} else if sql_SQL_Matcher_0.Match(i) {
-			return "SQL", true
+			return []string{"SQL"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".srt": func(i []byte) (string, bool) {
+	".srt": func(i []byte) []string {
 		if srt_SubRipText_Matcher_0.Match(i) {
-			return "SubRip Text", true
+			return []string{"SubRip Text"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".t": func(i []byte) (string, bool) {
+	".t": func(i []byte) []string {
 		if t_Turing_Matcher_0.Match(i) {
-			return "Turing", true
+			return []string{"Turing"}
 		} else if t_Perl6_Matcher_0.Match(i) {
-			return "Perl6", true
+			return []string{"Perl6"}
 		} else if t_Perl_Matcher_0.Match(i) {
-			return "Perl", true
+			return []string{"Perl"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".toc": func(i []byte) (string, bool) {
+	".toc": func(i []byte) []string {
 		if toc_WorldofWarcraftAddonData_Matcher_0.Match(i) {
-			return "World of Warcraft Addon Data", true
+			return []string{"World of Warcraft Addon Data"}
 		} else if toc_TeX_Matcher_0.Match(i) {
-			return "TeX", true
+			return []string{"TeX"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".ts": func(i []byte) (string, bool) {
+	".ts": func(i []byte) []string {
 		if ts_XML_Matcher_0.Match(i) {
-			return "XML", true
+			return []string{"XML"}
 		}
 
-		return "TypeScript", true
+		return []string{"TypeScript"}
 	},
-	".tst": func(i []byte) (string, bool) {
+	".tst": func(i []byte) []string {
 		if tst_GAP_Matcher_0.Match(i) {
-			return "GAP", true
+			return []string{"GAP"}
 		}
 
-		return "Scilab", true
+		return []string{"Scilab"}
 	},
-	".tsx": func(i []byte) (string, bool) {
+	".tsx": func(i []byte) []string {
 		if tsx_TypeScript_Matcher_0.Match(i) {
-			return "TypeScript", true
+			return []string{"TypeScript"}
 		} else if tsx_XML_Matcher_0.Match(i) {
-			return "XML", true
+			return []string{"XML"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
 }
 

documentation.go

@@ -2,7 +2,7 @@ package slinguist
 
 // CODE GENERATED AUTOMATICALLY WITH gopkg.in/src-d/simple-linguist.v1/internal/code-generator
 // THIS FILE SHOULD NOT BE EDITED BY HAND
-// Extracted from github/linguist commit: 60f864a138650dd17fafc94814be9ee2d3aaef8c
+// Extracted from github/linguist commit: b6460f8ed6b249281ada099ca28bd8f1230b8892
 
 import "gopkg.in/toqueteos/substring.v1"
 

extension.go

@@ -2,7 +2,7 @@ package slinguist
 
 // CODE GENERATED AUTOMATICALLY WITH gopkg.in/src-d/simple-linguist.v1/internal/code-generator
 // THIS FILE SHOULD NOT BE EDITED BY HAND
-// Extracted from github/linguist commit: 60f864a138650dd17fafc94814be9ee2d3aaef8c
+// Extracted from github/linguist commit: b6460f8ed6b249281ada099ca28bd8f1230b8892
 
 var languagesByExtension = map[string][]string{
 	".1":                   {"Roff"},
@@ -926,6 +926,8 @@ var languagesByExtension = map[string][]string{
 	".vw":                  {"PLSQL"},
 	".vxml":                {"XML"},
 	".w":                   {"CWeb"},
+	".wast":                {"WebAssembly"},
+	".wat":                 {"WebAssembly"},
 	".watchr":              {"Ruby"},
 	".webidl":              {"WebIDL"},
 	".weechatlog":          {"IRC log"},
@@ -1419,6 +1421,7 @@ var extensionsByLanguage = map[string][]string{
 	"Wavefront Material":           {".mtl"},
 	"Wavefront Object":             {".obj"},
 	"Web Ontology Language":        {".owl"},
+	"WebAssembly":                  {".wast", ".wat"},
 	"WebIDL":                       {".webidl"},
 	"World of Warcraft Addon Data": {".toc"},
 	"X10":              {".x10"},

filename.go

@@ -2,141 +2,142 @@ package slinguist
 
 // CODE GENERATED AUTOMATICALLY WITH gopkg.in/src-d/simple-linguist.v1/internal/code-generator
 // THIS FILE SHOULD NOT BE EDITED BY HAND
-// Extracted from github/linguist commit: 60f864a138650dd17fafc94814be9ee2d3aaef8c
+// Extracted from github/linguist commit: b6460f8ed6b249281ada099ca28bd8f1230b8892
 
-var languagesByFilename = map[string]string{
-	".Rprofile":          "R",
-	".XCompose":          "XCompose",
-	".abbrev_defs":       "Emacs Lisp",
-	".arcconfig":         "JSON",
-	".babelrc":           "JSON5",
-	".bash_history":      "Shell",
-	".bash_logout":       "Shell",
-	".bash_profile":      "Shell",
-	".bashrc":            "Shell",
-	".clang-format":      "YAML",
-	".classpath":         "XML",
-	".emacs":             "Emacs Lisp",
-	".emacs.desktop":     "Emacs Lisp",
-	".factor-boot-rc":    "Factor",
-	".factor-rc":         "Factor",
-	".gclient":           "Python",
-	".gnus":              "Emacs Lisp",
-	".irbrc":             "Ruby",
-	".jshintrc":          "JSON",
-	".nvimrc":            "Vim script",
-	".php_cs":            "PHP",
-	".php_cs.dist":       "PHP",
-	".project":           "XML",
-	".pryrc":             "Ruby",
-	".spacemacs":         "Emacs Lisp",
-	".vimrc":             "Vim script",
-	".viper":             "Emacs Lisp",
-	"APKBUILD":           "Alpine Abuild",
-	"App.config":         "XML",
-	"Appraisals":         "Ruby",
-	"BSDmakefile":        "Makefile",
-	"BUCK":               "Python",
-	"BUILD":              "Python",
-	"Berksfile":          "Ruby",
-	"Brewfile":           "Ruby",
-	"Buildfile":          "Ruby",
-	"CMakeLists.txt":     "CMake",
-	"COPYING":            "Text",
-	"COPYRIGHT.regex":    "Text",
-	"Cakefile":           "CoffeeScript",
-	"Cask":               "Emacs Lisp",
-	"Dangerfile":         "Ruby",
-	"Deliverfile":        "Ruby",
-	"Dockerfile":         "Dockerfile",
-	"Emakefile":          "Erlang",
-	"FONTLOG":            "Text",
-	"Fakefile":           "Fancy",
-	"Fastfile":           "Ruby",
-	"GNUmakefile":        "Makefile",
-	"Gemfile":            "Ruby",
-	"Gemfile.lock":       "Ruby",
-	"Guardfile":          "Ruby",
-	"INSTALL":            "Text",
-	"INSTALL.mysql":      "Text",
-	"Jakefile":           "JavaScript",
-	"Jarfile":            "Ruby",
-	"Jenkinsfile":        "Groovy",
-	"Kbuild":             "Makefile",
-	"LICENSE":            "Text",
-	"LICENSE.mysql":      "Text",
-	"Makefile":           "Makefile",
-	"Makefile.am":        "Makefile",
-	"Makefile.boot":      "Makefile",
-	"Makefile.frag":      "Makefile",
-	"Makefile.in":        "Makefile",
-	"Makefile.inc":       "Makefile",
-	"Mavenfile":          "Ruby",
-	"Modulefile":         "Puppet",
-	"NEWS":               "Text",
-	"Notebook":           "Jupyter Notebook",
-	"NuGet.config":       "XML",
-	"Nukefile":           "Nu",
-	"PKGBUILD":           "Shell",
-	"Phakefile":          "PHP",
-	"Podfile":            "Ruby",
-	"Project.ede":        "Emacs Lisp",
-	"Puppetfile":         "Ruby",
-	"README.1ST":         "Text",
-	"README.me":          "Text",
-	"README.mysql":       "Text",
-	"ROOT":               "Isabelle ROOT",
-	"Rakefile":           "Ruby",
-	"Rexfile":            "Perl6",
-	"SConscript":         "Python",
-	"SConstruct":         "Python",
-	"Settings.StyleCop":  "XML",
-	"Slakefile":          "LiveScript",
-	"Snakefile":          "Python",
-	"Snapfile":           "Ruby",
-	"Thorfile":           "Ruby",
-	"Vagrantfile":        "Ruby",
-	"WORKSPACE":          "Python",
-	"Web.Debug.config":   "XML",
-	"Web.Release.config": "XML",
-	"Web.config":         "XML",
-	"XCompose":           "XCompose",
-	"_emacs":             "Emacs Lisp",
-	"_vimrc":             "Vim script",
-	"abbrev_defs":        "Emacs Lisp",
-	"ant.xml":            "Ant Build System",
-	"build.xml":          "Ant Build System",
-	"buildfile":          "Ruby",
-	"click.me":           "Text",
-	"composer.lock":      "JSON",
-	"configure.ac":       "M4Sugar",
-	"delete.me":          "Text",
-	"descrip.mmk":        "Module Management System",
-	"descrip.mms":        "Module Management System",
-	"gradlew":            "Shell",
-	"gvimrc":             "Vim script",
-	"keep.me":            "Text",
-	"ld.script":          "Linker Script",
-	"makefile":           "Makefile",
-	"makefile.sco":       "Makefile",
-	"mcmod.info":         "JSON",
-	"meson.build":        "Meson",
-	"meson_options.txt":  "Meson",
-	"mix.lock":           "Elixir",
-	"mkfile":             "Makefile",
-	"mmn":                "Roff",
-	"mmt":                "Roff",
-	"nginx.conf":         "Nginx",
-	"nvimrc":             "Vim script",
-	"packages.config":    "XML",
-	"pom.xml":            "Maven POM",
-	"read.me":            "Text",
-	"rebar.config":       "Erlang",
-	"rebar.config.lock":  "Erlang",
-	"rebar.lock":         "Erlang",
-	"riemann.config":     "Clojure",
-	"test.me":            "Text",
-	"vimrc":              "Vim script",
-	"wscript":            "Python",
-	"xcompose":           "XCompose",
+var languagesByFilename = map[string][]string{
+	".Rprofile":          {"R"},
+	".XCompose":          {"XCompose"},
+	".abbrev_defs":       {"Emacs Lisp"},
+	".arcconfig":         {"JSON"},
+	".babelrc":           {"JSON5"},
+	".bash_history":      {"Shell"},
+	".bash_logout":       {"Shell"},
+	".bash_profile":      {"Shell"},
+	".bashrc":            {"Shell"},
+	".clang-format":      {"YAML"},
+	".classpath":         {"XML"},
+	".emacs":             {"Emacs Lisp"},
+	".emacs.desktop":     {"Emacs Lisp"},
+	".factor-boot-rc":    {"Factor"},
+	".factor-rc":         {"Factor"},
+	".gclient":           {"Python"},
+	".gnus":              {"Emacs Lisp"},
+	".irbrc":             {"Ruby"},
+	".jshintrc":          {"JSON"},
+	".nvimrc":            {"Vim script"},
+	".php_cs":            {"PHP"},
+	".php_cs.dist":       {"PHP"},
+	".project":           {"XML"},
+	".pryrc":             {"Ruby"},
+	".spacemacs":         {"Emacs Lisp"},
+	".vimrc":             {"Vim script"},
+	".viper":             {"Emacs Lisp"},
+	"APKBUILD":           {"Alpine Abuild"},
+	"App.config":         {"XML"},
+	"Appraisals":         {"Ruby"},
+	"BSDmakefile":        {"Makefile"},
+	"BUCK":               {"Python"},
+	"BUILD":              {"Python"},
+	"Berksfile":          {"Ruby"},
+	"Brewfile":           {"Ruby"},
+	"Buildfile":          {"Ruby"},
+	"CMakeLists.txt":     {"CMake"},
+	"COPYING":            {"Text"},
+	"COPYRIGHT.regex":    {"Text"},
+	"Cakefile":           {"CoffeeScript"},
+	"Cask":               {"Emacs Lisp"},
+	"Dangerfile":         {"Ruby"},
+	"Deliverfile":        {"Ruby"},
+	"Dockerfile":         {"Dockerfile"},
+	"Emakefile":          {"Erlang"},
+	"FONTLOG":            {"Text"},
+	"Fakefile":           {"Fancy"},
+	"Fastfile":           {"Ruby"},
+	"GNUmakefile":        {"Makefile"},
+	"Gemfile":            {"Ruby"},
+	"Gemfile.lock":       {"Ruby"},
+	"Guardfile":          {"Ruby"},
+	"INSTALL":            {"Text"},
+	"INSTALL.mysql":      {"Text"},
+	"Jakefile":           {"JavaScript"},
+	"Jarfile":            {"Ruby"},
+	"Jenkinsfile":        {"Groovy"},
+	"Kbuild":             {"Makefile"},
+	"LICENSE":            {"Text"},
+	"LICENSE.mysql":      {"Text"},
+	"Makefile":           {"Makefile"},
+	"Makefile.am":        {"Makefile"},
+	"Makefile.boot":      {"Makefile"},
+	"Makefile.frag":      {"Makefile"},
+	"Makefile.in":        {"Makefile"},
+	"Makefile.inc":       {"Makefile"},
+	"Makefile.wat":       {"Makefile"},
+	"Mavenfile":          {"Ruby"},
+	"Modulefile":         {"Puppet"},
+	"NEWS":               {"Text"},
+	"Notebook":           {"Jupyter Notebook"},
+	"NuGet.config":       {"XML"},
+	"Nukefile":           {"Nu"},
+	"PKGBUILD":           {"Shell"},
+	"Phakefile":          {"PHP"},
+	"Podfile":            {"Ruby"},
+	"Project.ede":        {"Emacs Lisp"},
+	"Puppetfile":         {"Ruby"},
+	"README.1ST":         {"Text"},
+	"README.me":          {"Text"},
+	"README.mysql":       {"Text"},
+	"ROOT":               {"Isabelle ROOT"},
+	"Rakefile":           {"Ruby"},
+	"Rexfile":            {"Perl6"},
+	"SConscript":         {"Python"},
+	"SConstruct":         {"Python"},
+	"Settings.StyleCop":  {"XML"},
+	"Slakefile":          {"LiveScript"},
+	"Snakefile":          {"Python"},
+	"Snapfile":           {"Ruby"},
+	"Thorfile":           {"Ruby"},
+	"Vagrantfile":        {"Ruby"},
+	"WORKSPACE":          {"Python"},
+	"Web.Debug.config":   {"XML"},
+	"Web.Release.config": {"XML"},
+	"Web.config":         {"XML"},
+	"XCompose":           {"XCompose"},
+	"_emacs":             {"Emacs Lisp"},
+	"_vimrc":             {"Vim script"},
+	"abbrev_defs":        {"Emacs Lisp"},
+	"ant.xml":            {"Ant Build System"},
+	"build.xml":          {"Ant Build System"},
+	"buildfile":          {"Ruby"},
+	"click.me":           {"Text"},
+	"composer.lock":      {"JSON"},
+	"configure.ac":       {"M4Sugar"},
+	"delete.me":          {"Text"},
+	"descrip.mmk":        {"Module Management System"},
+	"descrip.mms":        {"Module Management System"},
+	"gradlew":            {"Shell"},
+	"gvimrc":             {"Vim script"},
+	"keep.me":            {"Text"},
+	"ld.script":          {"Linker Script"},
+	"makefile":           {"Makefile"},
+	"makefile.sco":       {"Makefile"},
+	"mcmod.info":         {"JSON"},
+	"meson.build":        {"Meson"},
+	"meson_options.txt":  {"Meson"},
+	"mix.lock":           {"Elixir"},
+	"mkfile":             {"Makefile"},
+	"mmn":                {"Roff"},
+	"mmt":                {"Roff"},
+	"nginx.conf":         {"Nginx"},
+	"nvimrc":             {"Vim script"},
+	"packages.config":    {"XML"},
+	"pom.xml":            {"Maven POM"},
+	"read.me":            {"Text"},
+	"rebar.config":       {"Erlang"},
+	"rebar.config.lock":  {"Erlang"},
+	"rebar.lock":         {"Erlang"},
+	"riemann.config":     {"Clojure"},
+	"test.me":            {"Text"},
+	"vimrc":              {"Vim script"},
+	"wscript":            {"Python"},
+	"xcompose":           {"XCompose"},
 }

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

@@ -8,11 +8,11 @@ import (
 	"regexp"
 )
 
-type languageMatcher func ([]byte) (string, bool)
+type languageMatcher func ([]byte) []string
 
 var contentMatchers = map[string]languageMatcher{
 	{{ range $index, $disambiguator := . -}}
-	{{ printf "%q" $disambiguator.Extension }}: func(i []byte) (string, bool) {
+	{{ printf "%q" $disambiguator.Extension }}: func(i []byte) []string {
 		{{ range $i, $language := $disambiguator.Languages -}}
 
 		{{- if not (avoidLanguage $language) }}
@@ -20,14 +20,14 @@ var contentMatchers = map[string]languageMatcher{
 		{{- if gt $i 0 }} else {{ end -}} 
 		if {{- range $j, $heuristic := $language.Heuristics }} {{ $heuristic.Name }}.Match(i) 
 		{{- if lt $j (len $language.LogicRelations) }} {{index $language.LogicRelations $j}} {{- end -}} {{ end }} {
-			return {{ printf "%q" $language.Language }}, true
+			return []string{ {{- printf "%q" $language.Language -}} }
 		}
 		
 		{{- end -}}
 		{{- end -}}
 		{{- end}}
 	
-		return {{ returnLanguage $disambiguator.Languages }}, {{ safeLanguage $disambiguator.Languages }}
+		return {{ returnLanguages $disambiguator.Languages | returnStringSlice }}
 	},
 	{{ end -}}
 }

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

@@ -4,8 +4,8 @@ package slinguist
 // THIS FILE SHOULD NOT BE EDITED BY HAND
 // Extracted from github/linguist commit: {{ getCommit }}
 
-var languagesByFilename = map[string]string{
-	{{range $filename, $language := . -}}
-	"{{ $filename }}":	{{- printf "%q" $language -}},
+var languagesByFilename = map[string][]string{
+	{{range $filename, $languages := . -}}
+	"{{ $filename }}":	{ {{- formatStringSlice $languages -}} },
 	{{end -}}
 }

internal/code-generator/generator/documentation.go

@@ -2,8 +2,8 @@ package generator
 
 import (
 	"bytes"
-	"html/template"
 	"io"
+	"text/template"
 
 	yaml "gopkg.in/yaml.v2"
 )

internal/code-generator/generator/filenames.go

@@ -3,6 +3,7 @@ package generator
 import (
 	"bytes"
 	"io"
+	"strings"
 	"text/template"
 
 	yaml "gopkg.in/yaml.v2"
@@ -25,20 +26,21 @@ func Filenames(data []byte, filenamesTmplPath, filenamesTmplName, commit string)
 	return buf.Bytes(), nil
 }
 
-func buildFilenameLanguageMap(languages map[string]*languageInfo) map[string]string {
-	filenameLangMap := make(map[string]string)
+func buildFilenameLanguageMap(languages map[string]*languageInfo) map[string][]string {
+	filenameLangMap := make(map[string][]string)
 	for lang, langInfo := range languages {
 		for _, filename := range langInfo.Filenames {
-			filenameLangMap[filename] = lang
+			filenameLangMap[filename] = append(filenameLangMap[filename], lang)
 		}
 	}
 
 	return filenameLangMap
 }
 
-func executeFilenamesTemplate(out io.Writer, languagesByFilename map[string]string, filenamesTmplPath, filenamesTmpl, commit string) error {
+func executeFilenamesTemplate(out io.Writer, languagesByFilename map[string][]string, filenamesTmplPath, filenamesTmpl, commit string) error {
 	fmap := template.FuncMap{
-		"getCommit": func() string { return commit },
+		"getCommit":         func() string { return commit },
+		"formatStringSlice": func(slice []string) string { return `"` + strings.Join(slice, `","`) + `"` },
 	}
 
 	t := template.Must(template.New(filenamesTmpl).Funcs(fmap).ParseFiles(filenamesTmplPath))

internal/code-generator/generator/heuristics.go

@@ -24,6 +24,8 @@ func Heuristics(heuristics []byte, contentTmplPath, contentTmplName, commit stri
 	}
 
 	return buf.Bytes(), nil
+	// fmt.Println(string(buf.Bytes()))
+	// return nil, nil
 }
 
 const unknownLanguage = "OtherLanguage"
@@ -417,9 +419,15 @@ func executeContentTemplate(out io.Writer, disambiguators []*disambiguator, cont
 	fmap := template.FuncMap{
 		"getCommit":        func() string { return commit },
 		"getAllHeuristics": getAllHeuristics,
-		"returnLanguage":   returnLanguage,
-		"safeLanguage":     safeLanguage,
-		"avoidLanguage":    avoidLanguage,
+		"returnStringSlice": func(slice []string) string {
+			if len(slice) == 0 {
+				return "nil"
+			}
+
+			return `[]string{` + strings.Join(slice, `, `) + `}`
+		},
+		"returnLanguages": returnLanguages,
+		"avoidLanguage":   avoidLanguage,
 	}
 
 	t := template.Must(template.New(contentTmpl).Funcs(fmap).ParseFiles(contentTmplPath))
@@ -458,18 +466,7 @@ func containsInvalidRegexp(reg string) bool {
 	return strings.Contains(reg, `(?<`) || strings.Contains(reg, `\1`)
 }
 
-func returnLanguage(langsHeuristics []*languageHeuristics) string {
-	lang, _ := returnLangAndSafe(langsHeuristics)
-	return lang
-}
-
-func safeLanguage(langsHeuristics []*languageHeuristics) bool {
-	_, safe := returnLangAndSafe(langsHeuristics)
-	return safe
-}
-
-func returnLangAndSafe(langsHeuristics []*languageHeuristics) (string, bool) {
-	// at the moment, only returns one string although might be exists several language to return as a []string.
+func returnLanguages(langsHeuristics []*languageHeuristics) []string {
 	langs := make([]string, 0)
 	for _, langHeu := range langsHeuristics {
 		if len(langHeu.Heuristics) == 0 {
@@ -477,12 +474,5 @@ func returnLangAndSafe(langsHeuristics []*languageHeuristics) (string, bool) {
 		}
 	}
 
-	lang := unknownLanguage
-	safe := false
-	if len(langs) != 0 {
-		lang = langs[0]
-		safe = len(langs) == 1
-	}
-
-	return lang, safe
+	return langs
 }

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

@@ -8,102 +8,102 @@ import (
 	"regexp"
 )
 
-type languageMatcher func([]byte) (string, bool)
+type languageMatcher func([]byte) []string
 
 var contentMatchers = map[string]languageMatcher{
-	".asc": func(i []byte) (string, bool) {
+	".asc": func(i []byte) []string {
 		if asc_PublicKey_Matcher_0.Match(i) {
-			return "Public Key", true
+			return []string{"Public Key"}
 		} else if asc_AsciiDoc_Matcher_0.Match(i) {
-			return "AsciiDoc", true
+			return []string{"AsciiDoc"}
 		} else if asc_AGSScript_Matcher_0.Match(i) {
-			return "AGS Script", true
+			return []string{"AGS Script"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".f": func(i []byte) (string, bool) {
+	".f": func(i []byte) []string {
 		if f_Forth_Matcher_0.Match(i) {
-			return "Forth", true
+			return []string{"Forth"}
 		} else if f_FilebenchWML_Matcher_0.Match(i) {
-			return "Filebench WML", true
+			return []string{"Filebench WML"}
 		} else if f_FORTRAN_Matcher_0.Match(i) {
-			return "FORTRAN", true
+			return []string{"FORTRAN"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".h": func(i []byte) (string, bool) {
+	".h": func(i []byte) []string {
 		if h_ObjectiveDashC_Matcher_0.Match(i) {
-			return "Objective-C", true
+			return []string{"Objective-C"}
 		} else if h_CPlusPlus_Matcher_0.Match(i) || h_CPlusPlus_Matcher_1.Match(i) || h_CPlusPlus_Matcher_2.Match(i) || h_CPlusPlus_Matcher_3.Match(i) || h_CPlusPlus_Matcher_4.Match(i) || h_CPlusPlus_Matcher_5.Match(i) || h_CPlusPlus_Matcher_6.Match(i) {
-			return "C++", true
+			return []string{"C++"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".lsp": func(i []byte) (string, bool) {
+	".lsp": func(i []byte) []string {
 		if lsp_CommonLisp_Matcher_0.Match(i) {
-			return "Common Lisp", true
+			return []string{"Common Lisp"}
 		} else if lsp_NewLisp_Matcher_0.Match(i) {
-			return "NewLisp", true
+			return []string{"NewLisp"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".lisp": func(i []byte) (string, bool) {
+	".lisp": func(i []byte) []string {
 		if lisp_CommonLisp_Matcher_0.Match(i) {
-			return "Common Lisp", true
+			return []string{"Common Lisp"}
 		} else if lisp_NewLisp_Matcher_0.Match(i) {
-			return "NewLisp", true
+			return []string{"NewLisp"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".md": func(i []byte) (string, bool) {
+	".md": func(i []byte) []string {
 		if md_Markdown_Matcher_0.Match(i) || md_Markdown_Matcher_1.Match(i) {
-			return "Markdown", true
+			return []string{"Markdown"}
 		} else if md_GCCmachinedescription_Matcher_0.Match(i) {
-			return "GCC machine description", true
+			return []string{"GCC machine description"}
 		}
 
-		return "Markdown", true
+		return []string{"Markdown"}
 	},
-	".ms": func(i []byte) (string, bool) {
+	".ms": func(i []byte) []string {
 		if ms_Groff_Matcher_0.Match(i) {
-			return "Groff", true
+			return []string{"Groff"}
 		}
 
-		return "MAXScript", true
+		return []string{"MAXScript"}
 	},
-	".mod": func(i []byte) (string, bool) {
+	".mod": func(i []byte) []string {
 		if mod_XML_Matcher_0.Match(i) {
-			return "XML", true
+			return []string{"XML"}
 		} else if mod_ModulaDash2_Matcher_0.Match(i) || mod_ModulaDash2_Matcher_1.Match(i) {
-			return "Modula-2", true
+			return []string{"Modula-2"}
 		}
 
-		return "Linux Kernel Module", false
+		return []string{"Linux Kernel Module", "AMPL"}
 	},
-	".pro": func(i []byte) (string, bool) {
+	".pro": func(i []byte) []string {
 		if pro_Prolog_Matcher_0.Match(i) {
-			return "Prolog", true
+			return []string{"Prolog"}
 		} else if pro_INI_Matcher_0.Match(i) {
-			return "INI", true
+			return []string{"INI"}
 		} else if pro_QMake_Matcher_0.Match(i) && pro_QMake_Matcher_1.Match(i) {
-			return "QMake", true
+			return []string{"QMake"}
 		} else if pro_IDL_Matcher_0.Match(i) {
-			return "IDL", true
+			return []string{"IDL"}
 		}
 
-		return OtherLanguage, false
+		return nil
 	},
-	".rpy": func(i []byte) (string, bool) {
+	".rpy": func(i []byte) []string {
 		if rpy_Python_Matcher_0.Match(i) {
-			return "Python", true
+			return []string{"Python"}
 		}
 
-		return "Ren'Py", true
+		return []string{"Ren'Py"}
 	},
 }
 

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

@@ -4,9 +4,9 @@ package slinguist
 // THIS FILE SHOULD NOT BE EDITED BY HAND
 // Extracted from github/linguist commit: 0123456789abcdef0123456789abcdef01234567
 
-var languagesByFilename = map[string]string{
-	"APKBUILD":       "Alpine Abuild",
-	"CMakeLists.txt": "CMake",
-	"Cakefile":       "CoffeeScript",
-	"mix.lock":       "Elixir",
+var languagesByFilename = map[string][]string{
+	"APKBUILD":       {"Alpine Abuild"},
+	"CMakeLists.txt": {"CMake"},
+	"Cakefile":       {"CoffeeScript"},
+	"mix.lock":       {"Elixir"},
 }

internal/code-generator/generator/vendor.go

@@ -2,8 +2,8 @@ package generator
 
 import (
 	"bytes"
-	"html/template"
 	"io"
+	"text/template"
 
 	yaml "gopkg.in/yaml.v2"
 )

interpreter.go

@@ -2,7 +2,7 @@ package slinguist
 
 // CODE GENERATED AUTOMATICALLY WITH gopkg.in/src-d/simple-linguist.v1/internal/code-generator
 // THIS FILE SHOULD NOT BE EDITED BY HAND
-// Extracted from github/linguist commit: 60f864a138650dd17fafc94814be9ee2d3aaef8c
+// Extracted from github/linguist commit: b6460f8ed6b249281ada099ca28bd8f1230b8892
 
 var languagesByInterpreter = map[string][]string{
 	"Rscript":     {"R"},

modeline.go

@@ -5,38 +5,60 @@ import (
 	"regexp"
 )
 
-func getLanguageByModeline(content []byte) (lang string, safe bool) {
+const (
+	searchScope = 5
+)
+
+// GetLanguagesByModeline returns a slice of possible languages for the given content, filename will be ignored.
+// It accomplish the signature to be a Strategy type.
+func GetLanguagesByModeline(filename string, content []byte) []string {
 	headFoot := getHeaderAndFooter(content)
+	var languages []string
 	for _, getLang := range modelinesFunc {
-		lang, safe = getLang(headFoot)
-		if safe {
+		languages = getLang("", headFoot)
+		if len(languages) > 0 {
 			break
 		}
 	}
 
-	return
+	return languages
 }
 
 func getHeaderAndFooter(content []byte) []byte {
-	const (
-		searchScope = 5
-		eol         = "\n"
-	)
-
-	if bytes.Count(content, []byte(eol)) < 2*searchScope {
+	if bytes.Count(content, []byte("\n")) < 2*searchScope {
 		return content
 	}
 
-	splitted := bytes.Split(content, []byte(eol))
-	header := splitted[:searchScope]
-	footer := splitted[len(splitted)-searchScope:]
-	headerAndFooter := append(header, footer...)
-	return bytes.Join(headerAndFooter, []byte(eol))
+	header := headScope(content, searchScope)
+	footer := footScope(content, searchScope)
+	headerAndFooter := make([]byte, 0, len(content[:header])+len(content[footer:]))
+	headerAndFooter = append(headerAndFooter, content[:header]...)
+	headerAndFooter = append(headerAndFooter, content[footer:]...)
+	return headerAndFooter
 }
 
-var modelinesFunc = []func(content []byte) (string, bool){
-	GetLanguageByEmacsModeline,
-	GetLanguageByVimModeline,
+func headScope(content []byte, scope int) (index int) {
+	for i := 0; i < scope; i++ {
+		eol := bytes.IndexAny(content, "\n")
+		content = content[eol+1:]
+		index += eol
+	}
+
+	return index + scope - 1
+}
+
+func footScope(content []byte, scope int) (index int) {
+	for i := 0; i < scope; i++ {
+		index = bytes.LastIndexAny(content, "\n")
+		content = content[:index]
+	}
+
+	return index + 1
+}
+
+var modelinesFunc = []func(filename string, content []byte) []string{
+	GetLanguagesByEmacsModeline,
+	GetLanguagesByVimModeline,
 }
 
 var (
@@ -49,9 +71,20 @@ var (
 // GetLanguageByEmacsModeline detecs if the content has a emacs modeline and try to get a
 // language basing on alias. If couldn't retrieve a valid language, it returns OtherLanguage and false.
 func GetLanguageByEmacsModeline(content []byte) (string, bool) {
+	languages := GetLanguagesByEmacsModeline("", content)
+	if len(languages) == 0 {
+		return OtherLanguage, false
+	}
+
+	return languages[0], true
+}
+
+// GetLanguagesByEmacsModeline returns a slice of possible languages for the given content, filename will be ignored.
+// It accomplish the signature to be a Strategy type.
+func GetLanguagesByEmacsModeline(filename string, content []byte) []string {
 	matched := reEmacsModeline.FindAllSubmatch(content, -1)
 	if matched == nil {
-		return OtherLanguage, false
+		return nil
 	}
 
 	// only take the last matched line, discard previous lines
@@ -64,22 +97,38 @@ func GetLanguageByEmacsModeline(content []byte) (string, bool) {
 		alias = string(lastLineMatched)
 	}
 
-	return GetLanguageByAlias(alias)
+	language, ok := GetLanguageByAlias(alias)
+	if !ok {
+		return nil
+	}
+
+	return []string{language}
 }
 
 // GetLanguageByVimModeline detecs if the content has a vim modeline and try to get a
 // language basing on alias. If couldn't retrieve a valid language, it returns OtherLanguage and false.
 func GetLanguageByVimModeline(content []byte) (string, bool) {
+	languages := GetLanguagesByVimModeline("", content)
+	if len(languages) == 0 {
+		return OtherLanguage, false
+	}
+
+	return languages[0], true
+}
+
+// GetLanguagesByVimModeline returns a slice of possible languages for the given content, filename will be ignored.
+// It accomplish the signature to be a Strategy type.
+func GetLanguagesByVimModeline(filename string, content []byte) []string {
 	matched := reVimModeline.FindAllSubmatch(content, -1)
 	if matched == nil {
-		return OtherLanguage, false
+		return nil
 	}
 
 	// only take the last matched line, discard previous lines
 	lastLineMatched := matched[len(matched)-1][1]
 	matchedAlias := reVimLang.FindAllSubmatch(lastLineMatched, -1)
 	if matchedAlias == nil {
-		return OtherLanguage, false
+		return nil
 	}
 
 	alias := string(matchedAlias[0][1])
@@ -90,11 +139,15 @@ func GetLanguageByVimModeline(content []byte) (string, bool) {
 		for _, match := range matchedAlias {
 			otherAlias := string(match[1])
 			if otherAlias != alias {
-				alias = OtherLanguage
-				break
+				return nil
 			}
 		}
 	}
 
-	return GetLanguageByAlias(alias)
+	language, ok := GetLanguageByAlias(alias)
+	if !ok {
+		return nil
+	}
+
+	return []string{language}
 }

shebang.go

@@ -14,15 +14,11 @@ var (
 	pythonVersion   = regexp.MustCompile(`python\d\.\d+`)
 )
 
-func getLanguageByShebang(content []byte) (lang string, safe bool) {
+// GetLanguagesByShebang returns a slice of possible languages for the given content, filename will be ignored.
+// It accomplish the signature to be a Strategy type.
+func GetLanguagesByShebang(filename string, content []byte) (languages []string) {
 	interpreter := getInterpreter(content)
-	lang = OtherLanguage
-	if langs, ok := languagesByInterpreter[interpreter]; ok {
-		lang = langs[0]
-		safe = len(langs) == 1
-	}
-
-	return
+	return languagesByInterpreter[interpreter]
 }
 
 func getInterpreter(data []byte) (interpreter string) {

type.go

@@ -2,7 +2,7 @@ package slinguist
 
 // CODE GENERATED AUTOMATICALLY WITH gopkg.in/src-d/simple-linguist.v1/internal/code-generator
 // THIS FILE SHOULD NOT BE EDITED BY HAND
-// Extracted from github/linguist commit: 60f864a138650dd17fafc94814be9ee2d3aaef8c
+// Extracted from github/linguist commit: b6460f8ed6b249281ada099ca28bd8f1230b8892
 
 var languagesType = map[string]Type{
 	"1C Enterprise":    Programming,
@@ -427,6 +427,7 @@ var languagesType = map[string]Type{
 	"Wavefront Material":           Data,
 	"Wavefront Object":             Data,
 	"Web Ontology Language":        Markup,
+	"WebAssembly":                  Programming,
 	"WebIDL":                       Programming,
 	"World of Warcraft Addon Data": Data,
 	"X10":              Programming,

utils.go

@@ -4,8 +4,6 @@ import (
 	"bytes"
 	"path/filepath"
 	"strings"
-
-	"gopkg.in/toqueteos/substring.v1"
 )
 
 var (
@@ -46,16 +44,12 @@ func IsDotFile(path string) bool {
 
 // IsVendor returns whether or not path is a vendor path.
 func IsVendor(path string) bool {
-	return findIndex(path, vendorMatchers) >= 0
+	return vendorMatchers.Match(path)
 }
 
 // IsDocumentation returns whether or not path is a documentation path.
 func IsDocumentation(path string) bool {
-	return findIndex(path, documentationMatchers) >= 0
-}
-
-func findIndex(path string, matchers substring.StringsMatcher) int {
-	return matchers.MatchIndex(path)
+	return documentationMatchers.Match(path)
 }
 
 const sniffLen = 8000

vendor.go

@@ -2,7 +2,7 @@ package slinguist
 
 // CODE GENERATED AUTOMATICALLY WITH gopkg.in/src-d/simple-linguist.v1/internal/code-generator
 // THIS FILE SHOULD NOT BE EDITED BY HAND
-// Extracted from github/linguist commit: 60f864a138650dd17fafc94814be9ee2d3aaef8c
+// Extracted from github/linguist commit: b6460f8ed6b249281ada099ca28bd8f1230b8892
 
 import "gopkg.in/toqueteos/substring.v1"
 
@@ -41,20 +41,20 @@ var vendorMatchers = substring.Or(
 	substring.Regexp(`3rd[-_]?party/`),
 	substring.Regexp(`vendors?/`),
 	substring.Regexp(`extern(al)?/`),
-	substring.Regexp(`(^|/)[Vv]+endor/`),
+	substring.Regexp(`(^|/)[Vv]+endor/`),
 	substring.Regexp(`^debian/`),
 	substring.Regexp(`run.n$`),
 	substring.Regexp(`bootstrap-datepicker/`),
 	substring.Regexp(`(^|/)jquery([^.]*)\.js$`),
-	substring.Regexp(`(^|/)jquery\-\d\.\d+(\.\d+)?\.js$`),
-	substring.Regexp(`(^|/)jquery\-ui(\-\d\.\d+(\.\d+)?)?(\.\w+)?\.(js|css)$`),
+	substring.Regexp(`(^|/)jquery\-\d\.\d+(\.\d+)?\.js$`),
+	substring.Regexp(`(^|/)jquery\-ui(\-\d\.\d+(\.\d+)?)?(\.\w+)?\.(js|css)$`),
 	substring.Regexp(`(^|/)jquery\.(ui|effects)\.([^.]*)\.(js|css)$`),
 	substring.Regexp(`jquery.fn.gantt.js`),
 	substring.Regexp(`jquery.fancybox.(js|css)`),
 	substring.Regexp(`fuelux.js`),
-	substring.Regexp(`(^|/)jquery\.fileupload(-\w+)?\.js$`),
-	substring.Regexp(`(^|/)slick\.\w+.js$`),
-	substring.Regexp(`(^|/)Leaflet\.Coordinates-\d+\.\d+\.\d+\.src\.js$`),
+	substring.Regexp(`(^|/)jquery\.fileupload(-\w+)?\.js$`),
+	substring.Regexp(`(^|/)slick\.\w+.js$`),
+	substring.Regexp(`(^|/)Leaflet\.Coordinates-\d+\.\d+\.\d+\.src\.js$`),
 	substring.Regexp(`leaflet.draw-src.js`),
 	substring.Regexp(`leaflet.draw.css`),
 	substring.Regexp(`Control.FullScreen.css`),
@@ -68,7 +68,7 @@ var vendorMatchers = substring.Or(
 	substring.Regexp(`(^|/)controls\.js$`),
 	substring.Regexp(`(^|/)dragdrop\.js$`),
 	substring.Regexp(`(.*?)\.d\.ts$`),
-	substring.Regexp(`(^|/)mootools([^.]*)\d+\.\d+.\d+([^.]*)\.js$`),
+	substring.Regexp(`(^|/)mootools([^.]*)\d+\.\d+.\d+([^.]*)\.js$`),
 	substring.Regexp(`(^|/)dojo\.js$`),
 	substring.Regexp(`(^|/)MochiKit\.js$`),
 	substring.Regexp(`(^|/)yahoo-([^.]*)\.js$`),
@@ -80,16 +80,16 @@ var vendorMatchers = substring.Or(
 	substring.Regexp(`(^|/)fontello(.*?)\.css$`),
 	substring.Regexp(`(^|/)MathJax/`),
 	substring.Regexp(`(^|/)Chart\.js$`),
-	substring.Regexp(`(^|/)[Cc]ode[Mm]irror/(\d+\.\d+/)?(lib|mode|theme|addon|keymap|demo)`),
+	substring.Regexp(`(^|/)[Cc]ode[Mm]irror/(\d+\.\d+/)?(lib|mode|theme|addon|keymap|demo)`),
 	substring.Regexp(`(^|/)shBrush([^.]*)\.js$`),
 	substring.Regexp(`(^|/)shCore\.js$`),
 	substring.Regexp(`(^|/)shLegacy\.js$`),
 	substring.Regexp(`(^|/)angular([^.]*)\.js$`),
-	substring.Regexp(`(^|\/)d3(\.v\d+)?([^.]*)\.js$`),
+	substring.Regexp(`(^|\/)d3(\.v\d+)?([^.]*)\.js$`),
 	substring.Regexp(`(^|/)react(-[^.]*)?\.js$`),
-	substring.Regexp(`(^|/)modernizr\-\d\.\d+(\.\d+)?\.js$`),
-	substring.Regexp(`(^|/)modernizr\.custom\.\d+\.js$`),
-	substring.Regexp(`(^|/)knockout-(\d+\.){3}(debug\.)?js$`),
+	substring.Regexp(`(^|/)modernizr\-\d\.\d+(\.\d+)?\.js$`),
+	substring.Regexp(`(^|/)modernizr\.custom\.\d+\.js$`),
+	substring.Regexp(`(^|/)knockout-(\d+\.){3}(debug\.)?js$`),
 	substring.Regexp(`(^|/)docs?/_?(build|themes?|templates?|static)/`),
 	substring.Regexp(`(^|/)admin_media/`),
 	substring.Regexp(`(^|/)env/`),
@@ -117,7 +117,7 @@ var vendorMatchers = substring.Or(
 	substring.Regexp(`(^|/)jquery([^.]*)\.validate(\.unobtrusive)?\.js$`),
 	substring.Regexp(`(^|/)jquery([^.]*)\.unobtrusive\-ajax\.js$`),
 	substring.Regexp(`(^|/)[Mm]icrosoft([Mm]vc)?([Aa]jax|[Vv]alidation)(\.debug)?\.js$`),
-	substring.Regexp(`^[Pp]ackages\/.+\.\d+\/`),
+	substring.Regexp(`^[Pp]ackages\/.+\.\d+\/`),
 	substring.Regexp(`(^|/)extjs/.*?\.js$`),
 	substring.Regexp(`(^|/)extjs/.*?\.xml$`),
 	substring.Regexp(`(^|/)extjs/.*?\.txt$`),