@lvce-editor/shared-process 0.0.15 → 0.0.16

package/extensions/builtin.language-basics-javascript/src/tokenizeJavaScript.js

@@ -0,0 +1,295 @@
+/**
+ * @enum number
+ */
+const State = {
+  None: 0,
+  TopLevelContent: 1,
+  AfterOpeningAngleBracket: 2,
+  InsideOpeningTag: 3,
+  InsideOpeningTagAndHasSeenWhitespace: 4,
+  AfterClosingTagAngleBrackets: 5,
+  AfterClosingTagName: 6,
+  AfterAttributeName: 7,
+  AfterAttributeEqualSign: 8,
+  InsideAttributeDoubleQuote: 9,
+  InsideBlockComment: 10,
+  InsideString: 11,
+  AfterKeyword: 12,
+  Keyword: 13,
+  InsideLineComment: 14,
+  InsideSingleQuoteString: 15,
+  InsideDoubleQuoteString: 16,
+  InsideBacktickString: 17,
+}
+
+/**
+ * @enum number
+ */
+export const TokenType = {
+  None: 99999999,
+  Numeric: 30,
+  String: 50,
+  Whitespace: 777,
+  Comment: 60,
+  Text: 117,
+  PunctuationTag: 228,
+  TagName: 118,
+  AttributeName: 119,
+  Punctuation: 10,
+  Error: 141,
+  PunctuationString: 11,
+  NewLine: 771,
+  Keyword: 951,
+  VariableName: 952,
+  LanguageConstant: 13,
+  Regex: 14,
+  KeywordImport: 215,
+  KeywordControl: 881,
+  KeywordModifier: 882,
+  KeywordReturn: 883,
+  KeywordNew: 884,
+}
+
+export const TokenMap = {
+  [TokenType.None]: 'None',
+  [TokenType.Numeric]: 'Numeric',
+  [TokenType.String]: 'String',
+  [TokenType.Whitespace]: 'Whitespace',
+  [TokenType.Comment]: 'Comment',
+  [TokenType.Text]: 'Text',
+  [TokenType.PunctuationTag]: 'PunctuationTag',
+  [TokenType.TagName]: 'TagName',
+  [TokenType.AttributeName]: 'AttributeName',
+  [TokenType.Punctuation]: 'Punctuation',
+  [TokenType.Error]: 'Error',
+  [TokenType.PunctuationString]: 'PunctuationString',
+  [TokenType.NewLine]: 'NewLine',
+  [TokenType.Keyword]: 'Keyword',
+  [TokenType.VariableName]: 'VariableName',
+  [TokenType.LanguageConstant]: 'LanguageConstant',
+  [TokenType.Regex]: 'Regex',
+  [TokenType.KeywordImport]: 'KeywordImport',
+  [TokenType.KeywordControl]: 'KeywordControl',
+  [TokenType.KeywordModifier]: 'KeywordModifier',
+  [TokenType.KeywordReturn]: 'KeywordReturn',
+  [TokenType.KeywordNew]: 'KeywordNew',
+}
+
+const RE_KEYWORD =
+  /^(?:as|async|await|break|case|catch|class|const|continue|debugger|default|delete|do|else|enum|export|extends|false|finally|for|from|function|if|implements|import|in|instanceof|interface|let|new|null|package|private|protected|public|return|super|switch|static|this|throw|try|true|typeof|var|void|while|with|yield)\b/
+const RE_CURLY_OPEN = /^\{/
+const RE_CURLY_CLOSE = /^\}/
+const RE_SQUARE_OPEN = /^\[/
+const RE_SQUARE_CLOSE = /^\]/
+const RE_COMMA = /^,/
+const RE_COLON = /^:/
+const RE_NUMERIC =
+  /^((0(x|X)[0-9a-fA-F]*)|(([0-9]+\.?[0-9]*)|(\.[0-9]+))((e|E)(\+|-)?[0-9]+)?)\b/
+const RE_LINE_COMMENT_START = /^\/\//
+const RE_LINE_COMMENT_CONTENT = /^[^\n]+/
+const RE_NEWLINE_WHITESPACE = /^\n\s*/
+const RE_BLOCK_COMMENT_START = /^\/\*/
+const RE_BLOCK_COMMENT_CONTENT = /^.+?(?=\*\/)/
+const RE_BLOCK_COMMENT_END = /^\*\//
+const RE_UNKNOWN_VALUE = /^[^\}\{\s,"]+/
+const RE_IMPORT = /^[a-zA-Z\.]+/
+const RE_SEMICOLON = /^;/
+const RE_VARIABLE_NAME = /^[a-zA-Z_][a-zA-Z\d\_]*/
+const RE_LINE_COMMENT = /^\/\/[^\n]*/
+const RE_ROUND_OPEN = /^\(/
+const RE_ROUND_CLOSE = /^\)/
+const RE_DOT = /^\./
+const RE_EQUAL_SIGN = /^=/
+const RE_SINGLE_QUOTE = /^'/
+const RE_PUNCTUATION = /^[\(\)=\+\-><\.:;\{\}\[\]!,&\|\^\?\*]/
+const RE_SLASH = /^\//
+const RE_ANYTHING_UNTIL_END = /^.+/s
+const RE_WHITESPACE = /^\s+/
+const RE_QUOTE_SINGLE = /^'/
+const RE_QUOTE_DOUBLE = /^"/
+const RE_QUOTE_BACKTICK = /^`/
+const RE_STRING_SINGLE_QUOTE_CONTENT = /^[^']+/
+const RE_STRING_DOUBLE_QUOTE_CONTENT = /^[^"]+/
+const RE_STRING_BACKTICK_QUOTE_CONTENT = /^[^`]+/
+
+// copied from https://github.com/PrismJS/prism/blob/master/components/prism-javascript.js#L57
+const RE_REGEX =
+  /((?:^|[^$\w\xA0-\uFFFF."'\])\s]|\b(?:return|yield))\s*)\/(?:\[(?:[^\]\\\r\n]|\\.)*\]|\\.|[^/\\\[\r\n])+\/[dgimyus]{0,7}(?=(?:\s|\/\*(?:[^*]|\*(?!\/))*\*\/)*(?:$|[\r\n,.;:})\]]|\/\/))/
+
+export const initialLineState = {
+  state: State.TopLevelContent,
+}
+
+export const tokenizeLine = (line, lineState) => {
+  let next = null
+  let index = 0
+  let tokens = []
+  let token = TokenType.None
+  let state = lineState.state
+  while (index < line.length) {
+    const part = line.slice(index)
+    switch (state) {
+      case State.TopLevelContent:
+        if ((next = part.match(RE_WHITESPACE))) {
+          token = TokenType.Whitespace
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_KEYWORD))) {
+          switch (next[0]) {
+            case 'true':
+            case 'false':
+            case 'null':
+              token = TokenType.LanguageConstant
+              break
+            case 'import':
+            case 'export':
+            case 'from':
+              token = TokenType.KeywordImport
+              break
+            case 'as':
+            case 'switch':
+            case 'default':
+            case 'case':
+            case 'else':
+            case 'if':
+            case 'break':
+            case 'throw':
+              token = TokenType.KeywordControl
+              break
+            case 'async':
+            case 'await':
+              token = TokenType.KeywordModifier
+              break
+            case 'return':
+              token = TokenType.KeywordReturn
+              break
+            case 'new':
+              token = TokenType.KeywordNew
+              break
+            default:
+              token = TokenType.Keyword
+              break
+          }
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_VARIABLE_NAME))) {
+          token = TokenType.VariableName
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_NUMERIC))) {
+          token = TokenType.Numeric
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_PUNCTUATION))) {
+          token = TokenType.Punctuation
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_SLASH))) {
+          if ((next = part.match(RE_BLOCK_COMMENT_START))) {
+            token = TokenType.Comment
+            state = State.InsideBlockComment
+          } else if ((next = part.match(RE_REGEX))) {
+            token = TokenType.Regex
+            state = State.TopLevelContent
+          } else if ((next = part.match(RE_LINE_COMMENT_START))) {
+            token = TokenType.Comment
+            state = State.InsideLineComment
+          } else {
+            next = part.match(RE_PUNCTUATION)
+            token = TokenType.Punctuation
+            state = State.TopLevelContent
+          }
+        } else if ((next = part.match(RE_QUOTE_SINGLE))) {
+          token = TokenType.Punctuation
+          state = State.InsideSingleQuoteString
+        } else if ((next = part.match(RE_QUOTE_DOUBLE))) {
+          token = TokenType.Punctuation
+          state = State.InsideDoubleQuoteString
+        } else if ((next = part.match(RE_QUOTE_BACKTICK))) {
+          token = TokenType.Punctuation
+          state = State.InsideBacktickString
+        } else {
+          line.slice(0, index) //?
+          part //?
+          throw new Error('no')
+        }
+        break
+      case State.Keyword:
+        const keyword = next[0]
+        switch (keyword) {
+          case 'true':
+          case 'false':
+            break
+          default:
+            token = TokenType.Keyword
+            state = State.TopLevelContent
+            break
+        }
+        break
+      case State.InsideLineComment:
+        if ((next = part.match(RE_ANYTHING_UNTIL_END))) {
+          token = TokenType.Comment
+          state = State.TopLevelContent
+        } else {
+          throw new Error('no')
+        }
+        break
+      case State.InsideBlockComment:
+        if ((next = part.match(RE_BLOCK_COMMENT_CONTENT))) {
+          token = TokenType.Comment
+          state = State.InsideBlockComment
+        } else if ((next = part.match(RE_BLOCK_COMMENT_END))) {
+          token = TokenType.Comment
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_ANYTHING_UNTIL_END))) {
+          token = TokenType.Comment
+          state = State.InsideBlockComment
+        } else {
+          throw new Error('no')
+        }
+        break
+      case State.InsideSingleQuoteString:
+        if ((next = part.match(RE_QUOTE_SINGLE))) {
+          token = TokenType.Punctuation
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_STRING_SINGLE_QUOTE_CONTENT))) {
+          token = TokenType.String
+          state = State.InsideSingleQuoteString
+        } else {
+          throw new Error('no')
+        }
+        break
+      case State.InsideDoubleQuoteString:
+        if ((next = part.match(RE_QUOTE_DOUBLE))) {
+          token = TokenType.Punctuation
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_STRING_DOUBLE_QUOTE_CONTENT))) {
+          token = TokenType.String
+          state = State.InsideDoubleQuoteString
+        } else {
+          throw new Error('no')
+        }
+        break
+      case State.InsideBacktickString:
+        if ((next = part.match(RE_QUOTE_BACKTICK))) {
+          token = TokenType.Punctuation
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_STRING_BACKTICK_QUOTE_CONTENT))) {
+          token = TokenType.String
+          state = State.InsideBacktickString
+        } else {
+          throw new Error('no')
+        }
+        break
+      default:
+        state
+        throw new Error('no')
+    }
+    index += next[0].length
+    tokens.push({
+      type: token,
+      length: next[0].length,
+    })
+  }
+  return {
+    state,
+    tokens,
+  }
+}
+
+tokenizeLine(`\`\``, initialLineState) //?

package/extensions/builtin.language-basics-julia/README.md

@@ -0,0 +1,18 @@
+# Language Basics Julia
+
+## Contributing
+
+```sh
+git clone git@github.com:lvce-editor/language-basics-julia.git &&
+cd language-basics-julia &&
+npm ci &&
+npm test
+```
+
+## Gitpod
+
+[![Open in Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/lvce-editor/language-basics-julia)
+
+## Credits
+
+Based on https://github.com/highlightjs/highlight.js/blob/main/src/languages/julia.js by @isagalaev and contributers.

package/extensions/builtin.language-basics-julia/extension.json

@@ -0,0 +1,12 @@
+{
+  "id": "builtin.language-basics-julia",
+  "name": "Language Basics Julia",
+  "description": "Provides syntax highlighting and bracket matching in Julia files.",
+  "languages": [
+    {
+      "id": "julia",
+      "extensions": [".jl"],
+      "tokenize": "src/tokenizeJulia.js"
+    }
+  ]
+}

package/extensions/builtin.language-basics-julia/src/tokenizeJulia.js

@@ -0,0 +1,135 @@
+/**
+ * @enum number
+ */
+const State = {
+  None: 0,
+  TopLevelContent: 1,
+  InsideSingleQuoteString: 2,
+  InsideDoubleQuoteString: 3,
+  InsideTripleQuoteString: 4,
+}
+
+/**
+ * @enum number
+ */
+export const TokenType = {
+  None: 99999999,
+  Keyword: 951,
+  Whitespace: 0,
+  NewLine: 771,
+  VariableName: 2,
+  Punctuation: 3,
+  String: 4,
+  Numeric: 5,
+  Attribute: 6,
+}
+
+export const TokenMap = {
+  [TokenType.None]: 'None',
+  [TokenType.Keyword]: 'Keyword',
+  [TokenType.Whitespace]: 'Whitespace',
+  [TokenType.NewLine]: 'NewLine',
+  [TokenType.VariableName]: 'VariableName',
+  [TokenType.Punctuation]: 'Punctuation',
+  [TokenType.String]: 'String',
+  [TokenType.Numeric]: 'Numeric',
+  [TokenType.Attribute]: 'Attribute',
+}
+
+export const initialLineState = {
+  state: State.TopLevelContent,
+}
+
+const RE_KEYWORD =
+  /^(?:baremodule|begin|break|catch|ccall|const|continue|do|else|elseif|end|export|false|finally|for|function|global|if|import|in|isa|let|local|macro|module|quote|return|true|try|using|where|while)\b/
+const RE_WHITESPACE = /^\s+/
+const RE_VARIABLE_NAME = /^[A-Za-z_\u00A1-\uFFFF][A-Za-z_0-9\u00A1-\uFFFF]*/
+const RE_PUNCTUATION = /^[:,;\{\}\[\]\.=\(\)>\^\+\-\<\?]/
+const RE_QUOTE_SINGLE = /^'/
+const RE_QUOTE_DOUBLE = /^"/
+const RE_STRING_SINGLE_QUOTE_CONTENT = /^[^']+/
+const RE_STRING_DOUBLE_QUOTE_CONTENT = /^[^"]+/
+const RE_NUMERIC = /^\d+/
+
+/**
+ * @param {string} line
+ * @param {any} lineState
+ */
+export const tokenizeLine = (line, lineState) => {
+  let next = null
+  let index = 0
+  let tokens = []
+  let token = TokenType.None
+  let state = lineState.state
+  while (index < line.length) {
+    const part = line.slice(index)
+    switch (state) {
+      case State.TopLevelContent:
+        if ((next = part.match(RE_WHITESPACE))) {
+          token = TokenType.Whitespace
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_KEYWORD))) {
+          token = TokenType.Keyword
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_VARIABLE_NAME))) {
+          token = TokenType.VariableName
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_PUNCTUATION))) {
+          token = TokenType.Punctuation
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_NUMERIC))) {
+          token = TokenType.Numeric
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_QUOTE_SINGLE))) {
+          token = TokenType.Punctuation
+          state = State.InsideSingleQuoteString
+        } else if ((next = part.match(RE_QUOTE_DOUBLE))) {
+          token = TokenType.Punctuation
+          state = State.InsideDoubleQuoteString
+        } else {
+          part //?
+          throw new Error('no')
+        }
+        break
+      case State.InsideSingleQuoteString:
+        if ((next = part.match(RE_QUOTE_SINGLE))) {
+          token = TokenType.Punctuation
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_STRING_SINGLE_QUOTE_CONTENT))) {
+          token = TokenType.String
+          state = State.InsideSingleQuoteString
+        } else {
+          throw new Error('no')
+        }
+        break
+      case State.InsideDoubleQuoteString:
+        if ((next = part.match(RE_QUOTE_DOUBLE))) {
+          token = TokenType.Punctuation
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_STRING_DOUBLE_QUOTE_CONTENT))) {
+          token = TokenType.String
+          state = State.InsideDoubleQuoteString
+        } else {
+          throw new Error('no')
+        }
+        break
+      default:
+        state
+        throw new Error('no')
+    }
+    index += next[0].length
+    tokens.push({
+      type: token,
+      length: next[0].length,
+    })
+  }
+  return {
+    state,
+    tokens,
+  }
+}
+
+tokenizeLine(
+  `abs(mandelbrot(complex(x, y))) < 2 ? print("*") : print(" ")`,
+  initialLineState
+)

package/extensions/builtin.language-basics-kotlin/README.md

@@ -0,0 +1,15 @@
+# Language Basics Kotlin
+
+
+## Contributing
+
+```sh
+git clone git@github.com:lvce-editor/language-basics-kotlin.git &&
+cd language-basics-kotlin &&
+npm ci &&
+npm test
+```
+
+## Gitpod
+
+[![Open in Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/lvce-editor/language-basics-kotlin)

package/extensions/builtin.language-basics-kotlin/extension.json

@@ -0,0 +1,12 @@
+{
+  "id": "builtin.language-basics-kotlin",
+  "name": "Language Basics Kotlin",
+  "description": "Provides syntax highlighting and bracket matching in Kotlin files.",
+  "languages": [
+    {
+      "id": "kotlin",
+      "extensions": [".kt"],
+      "tokenize": "src/tokenizeKotlin.js"
+    }
+  ]
+}

package/extensions/builtin.language-basics-kotlin/src/tokenizeKotlin.js

@@ -0,0 +1,127 @@
+/**
+ * @enum number
+ */
+export const State = {
+  TopLevelContent: 1,
+  InsideString: 2,
+}
+
+export const StateMap = {
+  [State.TopLevelContent]: 'TopLevelContent',
+}
+
+/**
+ * @enum number
+ */
+export const TokenType = {
+  None: 1,
+  Whitespace: 2,
+  PunctuationString: 3,
+  String: 4,
+  Keyword: 5,
+  Numeric: 6,
+  Punctuation: 7,
+  VariableName: 8,
+}
+
+export const TokenMap = {
+  [TokenType.None]: 'None',
+  [TokenType.Whitespace]: 'Whitespace',
+  [TokenType.PunctuationString]: 'PunctuationString',
+  [TokenType.String]: 'String',
+  [TokenType.Keyword]: 'Keyword',
+  [TokenType.Numeric]: 'Numeric',
+  [TokenType.Punctuation]: 'Punctuation',
+  [TokenType.VariableName]: 'VariableName',
+}
+
+const RE_SELECTOR = /^[\.a-zA-Z\d\-\:>]+/
+const RE_WHITESPACE = /^ +/
+const RE_CURLY_OPEN = /^\{/
+const RE_CURLY_CLOSE = /^\}/
+const RE_PROPERTY_NAME = /^[a-zA-Z\-]+\b/
+const RE_COLON = /^:/
+const RE_PROPERTY_VALUE = /^[^;\}]+/
+const RE_SEMICOLON = /^;/
+const RE_COMMA = /^,/
+const RE_ANYTHING = /^.*/
+const RE_ANYTHING_UNTIL_CLOSE_BRACE = /^[^\}]+/
+const RE_QUOTE_DOUBLE = /^"/
+const RE_STRING_DOUBLE_QUOTE_CONTENT = /^[^"]+/
+const RE_KEYWORD =
+  /^(?:while|when|var|val|typeof|typealias|try|true|throw|this|super|return|package|object|null|is|interface|in|if|fun|for|false|else|do|continue|class|break|as)\b/
+
+const RE_VARIABLE_NAME = /^[a-zA-Z]+/
+const RE_PUNCTUATION = /^[:,;\{\}\[\]\.=\(\)<>]/
+const RE_NUMERIC = /^\d+/
+
+export const initialLineState = {
+  state: State.TopLevelContent,
+  tokens: [],
+}
+
+export const isEqualLineState = (lineStateA, lineStateB) => {
+  return lineStateA.state === lineStateB.state
+}
+
+/**
+ * @param {string} line
+ */
+export const tokenizeLine = (line, lineState) => {
+  let next = null
+  let index = 0
+  let tokens = []
+  let token = TokenType.None
+  let state = lineState.state
+  while (index < line.length) {
+    const part = line.slice(index)
+    switch (state) {
+      case State.TopLevelContent:
+        if ((next = part.match(RE_WHITESPACE))) {
+          token = TokenType.Whitespace
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_KEYWORD))) {
+          token = TokenType.Keyword
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_PUNCTUATION))) {
+          token = TokenType.Punctuation
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_VARIABLE_NAME))) {
+          token = TokenType.VariableName
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_NUMERIC))) {
+          token = TokenType.Numeric
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_QUOTE_DOUBLE))) {
+          token = TokenType.PunctuationString
+          state = State.InsideString
+        } else {
+          part //?
+          throw new Error('no')
+        }
+        break
+      case State.InsideString:
+        if ((next = part.match(RE_QUOTE_DOUBLE))) {
+          token = TokenType.PunctuationString
+          state = State.TopLevelContent
+        } else if ((next = part.match(RE_STRING_DOUBLE_QUOTE_CONTENT))) {
+          token = TokenType.String
+          state = State.InsideString
+        } else {
+          throw new Error('no')
+        }
+        break
+      default:
+        throw new Error('no')
+    }
+    index += next[0].length
+    tokens.push({
+      type: token,
+      length: next[0].length,
+    })
+  }
+  return {
+    state,
+    tokens,
+  }
+}

package/extensions/builtin.language-basics-python/README.md

@@ -0,0 +1,14 @@
+# Language Basics Python
+
+## Contributing
+
+```sh
+git clone git@github.com:lvce-editor/language-basics-python.git &&
+cd language-basics-python &&
+npm ci &&
+npm test
+```
+
+## Gitpod
+
+[![Open in Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/lvce-editor/language-basics-python)

package/extensions/builtin.language-basics-python/extension.json

@@ -0,0 +1,13 @@
+{
+  "id": "builtin.language-basics-python",
+  "name": "Language Basics Python",
+  "description": "Provides syntax highlighting and bracket matching in Python files.",
+  "languages": [
+    {
+      "id": "python",
+      "extensions": [".py"],
+      "configuration": "./languageConfiguration.json",
+      "tokenize": "src/tokenizePython.js"
+    }
+  ]
+}