add gherkin lexer (alecthomas#354)

mrsdizzie · May 1, 2020 · 3bd9228 · 3bd9228
1 parent de4a06f
commit 3bd9228
Show file tree

Hide file tree

Showing 3 changed files with 452 additions and 0 deletions.
diff --git a/lexers/g/gherkin.go b/lexers/g/gherkin.go
@@ -0,0 +1,118 @@
+package g
+
+import (
+	. "github.com/alecthomas/chroma" // nolint
+	"github.com/alecthomas/chroma/lexers/internal"
+)
+
+var stepKeywords = `^(\s*)(하지만|조건|먼저|만일|만약|단|그리고|그러면|那麼|那么|而且|當|当|前提|假設|假设|假如|假定|但是|但し|並且|并且|同時|同时|もし|ならば|ただし|しかし|かつ|و |متى |لكن |عندما |ثم |بفرض |اذاً |כאשר |וגם |בהינתן |אזי |אז |אבל |Якщо |Унда |То |Припустимо, що |Припустимо |Онда |Но |Нехай |Лекин |Когато |Када |Кад |К тому же |И |Задато |Задати |Задате |Если |Допустим |Дадено |Ва |Бирок |Аммо |Али |Але |Агар |А |І |Și |És |Zatati |Zakładając |Zadato |Zadate |Zadano |Zadani |Zadan |Youse know when youse got |Youse know like when |Yna |Ya know how |Ya gotta |Y |Wun |Wtedy |When y'all |When |Wenn |WEN |Và |Ve |Und |Un |Thì |Then y'all |Then |Tapi |Tak |Tada |Tad |Så |Stel |Soit |Siis |Si |Sed |Se |Quando |Quand |Quan |Pryd |Pokud |Pokiaľ |Però |Pero |Pak |Oraz |Onda |Ond |Oletetaan |Og |Och |O zaman |Når |När |Niin |Nhưng |N |Mutta |Men |Mas |Maka |Majd |Mais |Maar |Ma |Lorsque |Lorsqu'|Kun |Kuid |Kui |Khi |Keď |Ketika |Když |Kaj |Kai |Kada |Kad |Jeżeli |Ja |Ir |I CAN HAZ |I |Ha |Givun |Givet |Given y'all |Given |Gitt |Gegeven |Gegeben sei |Fakat |Eğer ki |Etant donné |Et |Então |Entonces |Entao |En |Eeldades |E |Duota |Dun |Donitaĵo |Donat |Donada |Do |Diyelim ki |Dengan |Den youse gotta |De |Dato |Dar |Dann |Dan |Dado |Dacă |Daca |DEN |Când |Cuando |Cho |Cept |Cand |Cal |But y'all |But |Buh |Biết |Bet |BUT |Atès |Atunci |Atesa |Anrhegedig a |Angenommen |And y'all |And |An |Ama |Als |Alors |Allora |Ali |Aleshores |Ale |Akkor |Aber |AN |A také |A |\* )`
+
+var featureKeywords = `^(기능|機能|功能|フィーチャ|خاصية|תכונה|Функціонал|Функционалност|Функционал|Фича|Особина|Могућност|Özellik|Właściwość|Tính năng|Trajto|Savybė|Požiadavka|Požadavek|Osobina|Ominaisuus|Omadus|OH HAI|Mogućnost|Mogucnost|Jellemző|Fīča|Funzionalità|Funktionalität|Funkcionalnost|Funkcionalitāte|Funcționalitate|Functionaliteit|Functionalitate|Funcionalitat|Funcionalidade|Fonctionnalité|Fitur|Feature|Egenskap|Egenskab|Crikey|Característica|Arwedd)(:)(.*)$`
+
+var featureElementKeywords = `^(\s*)(시나리오 개요|시나리오|배경|背景|場景大綱|場景|场景大纲|场景|劇本大綱|劇本|剧本大纲|剧本|テンプレ|シナリオテンプレート|シナリオテンプレ|シナリオアウトライン|シナリオ|سيناريو مخطط|سيناريو|الخلفية|תרחיש|תבנית תרחיש|רקע|Тарих|Сценарій|Сценарио|Сценарий структураси|Сценарий|Структура сценарію|Структура сценарија|Структура сценария|Скица|Рамка на сценарий|Пример|Предыстория|Предистория|Позадина|Передумова|Основа|Концепт|Контекст|Założenia|Wharrimean is|Tình huống|The thing of it is|Tausta|Taust|Tapausaihio|Tapaus|Szenariogrundriss|Szenario|Szablon scenariusza|Stsenaarium|Struktura scenarija|Skica|Skenario konsep|Skenario|Situācija|Senaryo taslağı|Senaryo|Scénář|Scénario|Schema dello scenario|Scenārijs pēc parauga|Scenārijs|Scenár|Scenaro|Scenariusz|Scenariul de şablon|Scenariul de sablon|Scenariu|Scenario Outline|Scenario Amlinellol|Scenario|Scenarijus|Scenarijaus šablonas|Scenarij|Scenarie|Rerefons|Raamstsenaarium|Primer|Pozadí|Pozadina|Pozadie|Plan du scénario|Plan du Scénario|Osnova scénáře|Osnova|Náčrt Scénáře|Náčrt Scenáru|Mate|MISHUN SRSLY|MISHUN|Kịch bản|Konturo de la scenaro|Kontext|Konteksts|Kontekstas|Kontekst|Koncept|Khung tình huống|Khung kịch bản|Háttér|Grundlage|Geçmiş|Forgatókönyv vázlat|Forgatókönyv|Fono|Esquema do Cenário|Esquema do Cenario|Esquema del escenario|Esquema de l'escenari|Escenario|Escenari|Dis is what went down|Dasar|Contexto|Contexte|Contesto|Condiţii|Conditii|Cenário|Cenario|Cefndir|Bối cảnh|Blokes|Bakgrunn|Bakgrund|Baggrund|Background|B4|Antecedents|Antecedentes|All y'all|Achtergrond|Abstrakt Scenario|Abstract Scenario)(:)(.*)$`
+
+var examplesKeywords = `^(\s*)(예|例子|例|サンプル|امثلة|דוגמאות|Сценарији|Примери|Приклади|Мисоллар|Значения|Örnekler|Voorbeelden|Variantai|Tapaukset|Scenarios|Scenariji|Scenarijai|Příklady|Példák|Príklady|Przykłady|Primjeri|Primeri|Piemēri|Pavyzdžiai|Paraugs|Juhtumid|Exemplos|Exemples|Exemplele|Exempel|Examples|Esempi|Enghreifftiau|Ekzemploj|Eksempler|Ejemplos|EXAMPLZ|Dữ liệu|Contoh|Cobber|Beispiele)(:)(.*)$`
+
+// Gherkin lexer.
+var Gherkin = internal.Register(MustNewLexer(
+	&Config{
+		Name:      "Gherkin",
+		Aliases:   []string{"cucumber", "Cucumber", "gherkin", "Gherkin"},
+		Filenames: []string{"*.feature", "*.FEATURE"},
+		MimeTypes: []string{"text/x-gherkin"},
+	},
+	Rules{
+		"comments": {
+			{`\s*#.*$`, Comment, nil},
+		},
+		"featureElements": {
+			{stepKeywords, Keyword, Push("stepContentStack")},
+			Include("comments"),
+			{`(\s|.)`, NameFunction, nil},
+		},
+		"featureElementsOnStack": {
+			{stepKeywords, Keyword, Pop(2)},
+			Include("comments"),
+			{`(\s|.)`, NameFunction, nil},
+		},
+		"examplesTable": {
+			{`\s+\|`, Keyword, Push("examplesTableHeader")},
+			Include("comments"),
+			{`(\s|.)`, NameFunction, nil},
+		},
+		"examplesTableHeader": {
+			{`\s+\|\s*$`, Keyword, Pop(2)},
+			Include("comments"),
+			{`\\\|`, NameVariable, nil},
+			{`\s*\|`, Keyword, nil},
+			{`[^|]`, NameVariable, nil},
+		},
+		"scenarioSectionsOnStack": {
+			{featureElementKeywords, ByGroups(NameFunction, Keyword, Keyword, NameFunction), Push("featureElementsOnStack")},
+		},
+		"narrative": {
+			Include("scenarioSectionsOnStack"),
+			{`(\s|.)`, NameFunction, nil},
+		},
+		"tableVars": {
+			{`(<[^>]+>)`, NameVariable, nil},
+		},
+		"numbers": {
+			{`(\d+\.?\d*|\d*\.\d+)([eE][+-]?[0-9]+)?`, LiteralString, nil},
+		},
+		"string": {
+			Include("tableVars"),
+			{`(\s|.)`, LiteralString, nil},
+		},
+		"pyString": {
+			{`"""`, Keyword, Pop(1)},
+			Include("string"),
+		},
+		"stepContentRoot": {
+			{`$`, Keyword, Pop(1)},
+			Include("stepContent"),
+		},
+		"stepContentStack": {
+			{`$`, Keyword, Pop(2)},
+			Include("stepContent"),
+		},
+		"stepContent": {
+			{`"`, NameFunction, Push("doubleString")},
+			Include("tableVars"),
+			Include("numbers"),
+			Include("comments"),
+			{`(\s|.)`, NameFunction, nil},
+		},
+		"tableContent": {
+			{`\s+\|\s*$`, Keyword, Pop(1)},
+			Include("comments"),
+			{`\\\|`, LiteralString, nil},
+			{`\s*\|`, Keyword, nil},
+			{`"`, LiteralString, Push("doubleStringTable")},
+			Include("string"),
+		},
+		"doubleString": {
+			{`"`, NameFunction, Pop(1)},
+			Include("string"),
+		},
+		"doubleStringTable": {
+			{`"`, LiteralString, Pop(1)},
+			Include("string"),
+		},
+		"root": {
+			{`\n`, NameFunction, nil},
+			Include("comments"),
+			{`"""`, Keyword, Push("pyString")},
+			{`\s+\|`, Keyword, Push("tableContent")},
+			{`"`, NameFunction, Push("doubleString")},
+			Include("tableVars"),
+			Include("numbers"),
+			{`(\s*)(@[^@\r\n\t ]+)`, ByGroups(NameFunction, NameTag), nil},
+			{stepKeywords, ByGroups(NameFunction, Keyword), Push("stepContentRoot")},
+			{featureKeywords, ByGroups(Keyword, Keyword, NameFunction), Push("narrative")},
+			{featureElementKeywords, ByGroups(NameFunction, Keyword, Keyword, NameFunction), Push("featureElements")},
+			{examplesKeywords, ByGroups(NameFunction, Keyword, Keyword, NameFunction), Push("examplesTable")},
+			{`(\s|.)`, NameFunction, nil},
+		},
+	},
+))
diff --git a/lexers/testdata/gherkin.actual b/lexers/testdata/gherkin.actual
@@ -0,0 +1,88 @@
+@foo34 @bar # some comment
+Feature: proof of concept
+
+  In order to read Cucumber features faster and eaiser on Github 
+  As a Cucumber user
+  I want to have syntax highlighting for Gherkin
+  This is part of the narrative, even if I have the # symbol, it is still the narrative- not a comment
+
+  Background: this is multi-line description
+    do you like it?
+    Given cheese is good
+
+  Scenario Outline: this is a test 
+                    this the second line of the desctiption
+    Given I have a <var1> and some "string"
+    And the following table and some 'string'
+      | header 1  | header 2  | # here is a comment after a step table header
+      | cell 1-1  | cell 1-2  | # here is a comment after a step table row
+      | cell 2-1  | "cell 2-2" |
+
+    When I do <var2>
+    And use apostrophes then the feature's syntax still looks good
+    And here is a string with single and double quotes- "i'll be back" 
+    And here is a string with the opposite 'the quote is "Foo"'
+    And what about a var in a quote like so: "<var2>"
+    And what about a multiline string with a var in it like so:
+    """
+    Hello!
+    I am a multiple line string, often called a pystring.
+    I can have regular "double quotes" without a problem...
+    I can also sub in vars as well like: <var1> and <var2>
+    """
+
+    Then I should see something...
+    But not something else...
+
+  Examples:
+    | var1  |  var2  | # i am a comment
+    | foo   |  bar   | # so am i
+    | dog   |  food  |
+
+  Scenarios: some other examples with a description
+             and guess waht?!? I can have multilines as well!  # look at me, I'm a comment
+             Who would have thunk?
+    | var1  |  var2  |
+    | foo   |  bar   |
+    | dog   |  food  |
+
+  @some_tag @another_tag
+  Scenario: more examples
+            will follow after this multi-line description
+    Given some context# this is an inline comment
+    # This is a comment
+# So is this with no space at front...
+
+Funktionalität: Addition
+  Um dumme Fehler zu vermeiden
+  möchte ich als Matheidiot
+  die Summe zweier Zahlen gesagt bekommen
+
+  Szenariogrundriss: Zwei Zahlen hinzufügen
+    Gegeben sei ich habe <Eingabe_1> in den Taschenrechner eingegeben
+    Und ich habe <Eingabe_2> in den Taschenrechner eingegeben
+    Wenn ich <Knopf> drücke
+    Dann sollte das Ergebniss auf dem Bildschirm <Ausgabe> sein
+
+  Beispiele:
+    | Eingabe_1 | Eingabe_2 | Knopf | Ausgabe |
+    | 20        | 30        | add   | 50      |
+    | 2         | 5         | add   | 7       |
+    | 0         | 40        | add   | 40      |
+
+Feature: Addition
+  In order to avoid silly mistakes
+  As a math idiot 
+  I want to be told the sum of two numbers
+
+  Scenario Outline: Add two numbers
+    Given I have entered <input_1> into the calculator
+    * I have entered <input_2> into the calculator
+    When I press <button>
+    Then the result should be <output> on the screen
+
+  Examples:
+    | input_1 | input_2 | button | output |
+    | 20      | 30      | add    | 50     |
+    | 2       | 5       | add    | 7      |
+    | 0       | 40      | add    | 40     |