{Rewriter, INVERSES, UNFINISHED} = require './rewriter'
CoffeeScript 詞法分析器。使用一系列代幣配對正規表示法嘗試與原始碼開頭進行配對。找到配對時,會產生一個代幣,我們使用配對,然後重新開始。代幣的格式為
[tag, value, locationData]
其中 locationData 為 {first_line, first_column, last_line, last_column, last_line_exclusive, last_column_exclusive},這是一種可以直接饋入 Jison 的格式。這些內容會由 coffeescript.coffee 中定義的 parser.lexer
函數在 jison 中讀取。
{Rewriter, INVERSES, UNFINISHED} = require './rewriter'
匯入我們需要的輔助程式。
{count, starts, compact, repeat, invertLiterate, merge,
attachCommentsToNode, locationDataToString, throwSyntaxError
replaceUnicodeCodePointEscapes, flatten, parseNumber} = require './helpers'
詞法分析器類別會讀取 CoffeeScript 串流,並將其分成標記代幣。詞法分析器已加入一些額外智慧,避免語法中潛在的歧義。
exports.Lexer = class Lexer
tokenize 是詞法分析器的主要方法。透過嘗試使用固定在剩餘程式碼開頭的正規表示法,或自訂遞迴代幣配對方法(用於內插),逐一配對代幣來進行掃描。記錄下一個代幣後,我們會在程式碼中向前移動,超過該代幣,然後重新開始。
每個代幣化方法負責傳回它已使用字元的數量。
在傳回 token 串流之前,透過 Rewriter 執行它。
tokenize: (code, opts = {}) ->
@literate = opts.literate # Are we lexing literate CoffeeScript?
@indent = 0 # The current indentation level.
@baseIndent = 0 # The overall minimum indentation level.
@continuationLineAdditionalIndent = 0 # The over-indentation at the current level.
@outdebt = 0 # The under-outdentation at the current level.
@indents = [] # The stack of all current indentation levels.
@indentLiteral = '' # The indentation.
@ends = [] # The stack for pairing up tokens.
@tokens = [] # Stream of parsed tokens in the form `['TYPE', value, location data]`.
@seenFor = no # Used to recognize `FORIN`, `FOROF` and `FORFROM` tokens.
@seenImport = no # Used to recognize `IMPORT FROM? AS?` tokens.
@seenExport = no # Used to recognize `EXPORT FROM? AS?` tokens.
@importSpecifierList = no # Used to identify when in an `IMPORT {...} FROM? ...`.
@exportSpecifierList = no # Used to identify when in an `EXPORT {...} FROM? ...`.
@jsxDepth = 0 # Used to optimize JSX checks, how deep in JSX we are.
@jsxObjAttribute = {} # Used to detect if JSX attributes is wrapped in {} (<div {props...} />).
@chunkLine =
opts.line or 0 # The start line for the current @chunk.
@chunkColumn =
opts.column or 0 # The start column of the current @chunk.
@chunkOffset =
opts.offset or 0 # The start offset for the current @chunk.
@locationDataCompensations =
opts.locationDataCompensations or {} # The location data compensations for the current @chunk.
code = @clean code # The stripped, cleaned original source code.
在每個位置,執行這個嘗試比對的清單,如果其中任何一個成功,則短路。它們的順序決定優先順序:@literalToken
是後備萬用字元。
i = 0
while @chunk = code[i..]
consumed = \
@identifierToken() or
@commentToken() or
@whitespaceToken() or
@lineToken() or
@stringToken() or
@numberToken() or
@jsxToken() or
@regexToken() or
@jsToken() or
@literalToken()
更新位置。
[@chunkLine, @chunkColumn, @chunkOffset] = @getLineAndColumnFromChunk consumed
i += consumed
return {@tokens, index: i} if opts.untilBalanced and @ends.length is 0
@closeIndentation()
@error "missing #{end.tag}", (end.origin ? end)[2] if end = @ends.pop()
return @tokens if opts.rewrite is off
(new Rewriter).rewrite @tokens
預處理程式碼以移除前導和尾隨空白、換行符號等。如果我們要分析識別 CoffeeScript,請移除所有縮排少於四個空格或一個 tab 的行,以移除外部 Markdown。
clean: (code) ->
thusFar = 0
if code.charCodeAt(0) is BOM
code = code.slice 1
@locationDataCompensations[0] = 1
thusFar += 1
if WHITESPACE.test code
code = "\n#{code}"
@chunkLine--
@locationDataCompensations[0] ?= 0
@locationDataCompensations[0] -= 1
code = code
.replace /\r/g, (match, offset) =>
@locationDataCompensations[thusFar + offset] = 1
''
.replace TRAILING_SPACES, ''
code = invertLiterate code if @literate
code
比對識別文字的項目:變數、關鍵字、方法名稱等。檢查以確保 JavaScript 保留字未用作識別碼。由於 CoffeeScript 保留了少數 JavaScript 中允許的關鍵字,因此我們小心不要在這裡將它們作為屬性名稱時標記為關鍵字,所以您仍然可以執行 jQuery.is()
,即使 is
否則表示 ===
。
identifierToken: ->
inJSXTag = @atJSXTag()
regex = if inJSXTag then JSX_ATTRIBUTE else IDENTIFIER
return 0 unless match = regex.exec @chunk
[input, id, colon] = match
保留 id 的長度以供位置資料使用
idLength = id.length
poppedToken = undefined
if id is 'own' and @tag() is 'FOR'
@token 'OWN', id
return id.length
if id is 'from' and @tag() is 'YIELD'
@token 'FROM', id
return id.length
if id is 'as' and @seenImport
if @value() is '*'
@tokens[@tokens.length - 1][0] = 'IMPORT_ALL'
else if @value(yes) in COFFEE_KEYWORDS
prev = @prev()
[prev[0], prev[1]] = ['IDENTIFIER', @value(yes)]
if @tag() in ['DEFAULT', 'IMPORT_ALL', 'IDENTIFIER']
@token 'AS', id
return id.length
if id is 'as' and @seenExport
if @tag() in ['IDENTIFIER', 'DEFAULT']
@token 'AS', id
return id.length
if @value(yes) in COFFEE_KEYWORDS
prev = @prev()
[prev[0], prev[1]] = ['IDENTIFIER', @value(yes)]
@token 'AS', id
return id.length
if id is 'default' and @seenExport and @tag() in ['EXPORT', 'AS']
@token 'DEFAULT', id
return id.length
if id is 'assert' and (@seenImport or @seenExport) and @tag() is 'STRING'
@token 'ASSERT', id
return id.length
if id is 'do' and regExSuper = /^(\s*super)(?!\(\))/.exec @chunk[3...]
@token 'SUPER', 'super'
@token 'CALL_START', '('
@token 'CALL_END', ')'
[input, sup] = regExSuper
return sup.length + 3
prev = @prev()
tag =
if colon or prev? and
(prev[0] in ['.', '?.', '::', '?::'] or
not prev.spaced and prev[0] is '@')
'PROPERTY'
else
'IDENTIFIER'
tokenData = {}
if tag is 'IDENTIFIER' and (id in JS_KEYWORDS or id in COFFEE_KEYWORDS) and
not (@exportSpecifierList and id in COFFEE_KEYWORDS)
tag = id.toUpperCase()
if tag is 'WHEN' and @tag() in LINE_BREAK
tag = 'LEADING_WHEN'
else if tag is 'FOR'
@seenFor = {endsLength: @ends.length}
else if tag is 'UNLESS'
tag = 'IF'
else if tag is 'IMPORT'
@seenImport = yes
else if tag is 'EXPORT'
@seenExport = yes
else if tag in UNARY
tag = 'UNARY'
else if tag in RELATION
if tag isnt 'INSTANCEOF' and @seenFor
tag = 'FOR' + tag
@seenFor = no
else
tag = 'RELATION'
if @value() is '!'
poppedToken = @tokens.pop()
tokenData.invert = poppedToken.data?.original ? poppedToken[1]
else if tag is 'IDENTIFIER' and @seenFor and id is 'from' and
isForFrom(prev)
tag = 'FORFROM'
@seenFor = no
對嘗試使用 get
或 set
作為關鍵字或 CoffeeScript 通常會解釋為對稱為 get
或 set
的函式的呼叫 (例如 get({foo: function () {}})
) 擲回錯誤。
else if tag is 'PROPERTY' and prev
if prev.spaced and prev[0] in CALLABLE and /^[gs]et$/.test(prev[1]) and
@tokens.length > 1 and @tokens[@tokens.length - 2][0] not in ['.', '?.', '@']
@error "'#{prev[1]}' cannot be used as a keyword, or as a function call
without parentheses", prev[2]
else if prev[0] is '.' and @tokens.length > 1 and (prevprev = @tokens[@tokens.length - 2])[0] is 'UNARY' and prevprev[1] is 'new'
prevprev[0] = 'NEW_TARGET'
else if prev[0] is '.' and @tokens.length > 1 and (prevprev = @tokens[@tokens.length - 2])[0] is 'IMPORT' and prevprev[1] is 'import'
@seenImport = no
prevprev[0] = 'IMPORT_META'
else if @tokens.length > 2
prevprev = @tokens[@tokens.length - 2]
if prev[0] in ['@', 'THIS'] and prevprev and prevprev.spaced and
/^[gs]et$/.test(prevprev[1]) and
@tokens[@tokens.length - 3][0] not in ['.', '?.', '@']
@error "'#{prevprev[1]}' cannot be used as a keyword, or as a
function call without parentheses", prevprev[2]
if tag is 'IDENTIFIER' and id in RESERVED and not inJSXTag
@error "reserved word '#{id}'", length: id.length
unless tag is 'PROPERTY' or @exportSpecifierList or @importSpecifierList
if id in COFFEE_ALIASES
alias = id
id = COFFEE_ALIAS_MAP[id]
tokenData.original = alias
tag = switch id
when '!' then 'UNARY'
when '==', '!=' then 'COMPARE'
when 'true', 'false' then 'BOOL'
when 'break', 'continue', \
'debugger' then 'STATEMENT'
when '&&', '||' then id
else tag
tagToken = @token tag, id, length: idLength, data: tokenData
tagToken.origin = [tag, alias, tagToken[2]] if alias
if poppedToken
[tagToken[2].first_line, tagToken[2].first_column, tagToken[2].range[0]] =
[poppedToken[2].first_line, poppedToken[2].first_column, poppedToken[2].range[0]]
if colon
colonOffset = input.lastIndexOf if inJSXTag then '=' else ':'
colonToken = @token ':', ':', offset: colonOffset
colonToken.jsxColon = yes if inJSXTag # used by rewriter
if inJSXTag and tag is 'IDENTIFIER' and prev[0] isnt ':'
@token ',', ',', length: 0, origin: tagToken, generated: yes
input.length
比對數字,包括小數、十六進位和指數表示法。小心不要干擾進行中的範圍。
numberToken: ->
return 0 unless match = NUMBER.exec @chunk
number = match[0]
lexedLength = number.length
switch
when /^0[BOX]/.test number
@error "radix prefix in '#{number}' must be lowercase", offset: 1
when /^0\d*[89]/.test number
@error "decimal literal '#{number}' must not be prefixed with '0'", length: lexedLength
when /^0\d+/.test number
@error "octal literal '#{number}' must be prefixed with '0o'", length: lexedLength
parsedValue = parseNumber number
tokenData = {parsedValue}
tag = if parsedValue is Infinity then 'INFINITY' else 'NUMBER'
if tag is 'INFINITY'
tokenData.original = number
@token tag, number,
length: lexedLength
data: tokenData
lexedLength
比對字串,包括多行字串以及帶或不帶內插的 heredocs。
stringToken: ->
[quote] = STRING_START.exec(@chunk) || []
return 0 unless quote
如果前一個 token 是 from
,而這是 import 或 export 陳述式,請正確標記 from
。
prev = @prev()
if prev and @value() is 'from' and (@seenImport or @seenExport)
prev[0] = 'FROM'
regex = switch quote
when "'" then STRING_SINGLE
when '"' then STRING_DOUBLE
when "'''" then HEREDOC_SINGLE
when '"""' then HEREDOC_DOUBLE
{tokens, index: end} = @matchWithInterpolations regex, quote
heredoc = quote.length is 3
if heredoc
找出最小的縮排。稍後會從所有行中移除它。
indent = null
doc = (token[1] for token, i in tokens when token[0] is 'NEOSTRING').join '#{}'
while match = HEREDOC_INDENT.exec doc
attempt = match[1]
indent = attempt if indent is null or 0 < attempt.length < indent.length
delimiter = quote.charAt(0)
@mergeInterpolationTokens tokens, {quote, indent, endOffset: end}, (value) =>
@validateUnicodeCodePointEscapes value, delimiter: quote
if @atJSXTag()
@token ',', ',', length: 0, origin: @prev, generated: yes
end
比對並使用註解。註解會從代碼串流中取出並儲存以供稍後使用,在解析完所有內容並產生 JavaScript 程式碼後,會將註解重新插入輸出中。
commentToken: (chunk = @chunk, {heregex, returnCommentTokens = no, offsetInChunk = 0} = {}) ->
return 0 unless match = chunk.match COMMENT
[commentWithSurroundingWhitespace, hereLeadingWhitespace, hereComment, hereTrailingWhitespace, lineComment] = match
contents = null
此註解是否與同一行中的程式碼相符?
leadingNewline = /^\s*\n+\s*#/.test commentWithSurroundingWhitespace
if hereComment
matchIllegal = HERECOMMENT_ILLEGAL.exec hereComment
if matchIllegal
@error "block comments cannot contain #{matchIllegal[0]}",
offset: '###'.length + matchIllegal.index, length: matchIllegal[0].length
解析縮排或取消縮排,就像此區塊註解不存在一樣。
chunk = chunk.replace "####{hereComment}###", ''
移除開頭的新行,例如 Rewriter::removeLeadingNewlines
,以避免產生不需要的 TERMINATOR
代碼。
chunk = chunk.replace /^\n+/, ''
@lineToken {chunk}
取出 ### 風格註解的內容,並格式化它。
content = hereComment
contents = [{
content
length: commentWithSurroundingWhitespace.length - hereLeadingWhitespace.length - hereTrailingWhitespace.length
leadingWhitespace: hereLeadingWhitespace
}]
else
COMMENT
正規表示法將連續的行註解擷取為一個代碼。移除第一個註解前的所有開頭新行,但保留行註解之間的空白行。
leadingNewlines = ''
content = lineComment.replace /^(\n*)/, (leading) ->
leadingNewlines = leading
''
precedingNonCommentLines = ''
hasSeenFirstCommentLine = no
contents =
content.split '\n'
.map (line, index) ->
unless line.indexOf('#') > -1
precedingNonCommentLines += "\n#{line}"
return
leadingWhitespace = ''
content = line.replace /^([ |\t]*)#/, (_, whitespace) ->
leadingWhitespace = whitespace
''
comment = {
content
length: '#'.length + content.length
leadingWhitespace: "#{unless hasSeenFirstCommentLine then leadingNewlines else ''}#{precedingNonCommentLines}#{leadingWhitespace}"
precededByBlankLine: !!precedingNonCommentLines
}
hasSeenFirstCommentLine = yes
precedingNonCommentLines = ''
comment
.filter (comment) -> comment
getIndentSize = ({leadingWhitespace, nonInitial}) ->
lastNewlineIndex = leadingWhitespace.lastIndexOf '\n'
if hereComment? or not nonInitial
return null unless lastNewlineIndex > -1
else
lastNewlineIndex ?= -1
leadingWhitespace.length - 1 - lastNewlineIndex
commentAttachments = for {content, length, leadingWhitespace, precededByBlankLine}, i in contents
nonInitial = i isnt 0
leadingNewlineOffset = if nonInitial then 1 else 0
offsetInChunk += leadingNewlineOffset + leadingWhitespace.length
indentSize = getIndentSize {leadingWhitespace, nonInitial}
noIndent = not indentSize? or indentSize is -1
commentAttachment = {
content
here: hereComment?
newLine: leadingNewline or nonInitial # Line comments after the first one start new lines, by definition.
locationData: @makeLocationData {offsetInChunk, length}
precededByBlankLine
indentSize
indented: not noIndent and indentSize > @indent
outdented: not noIndent and indentSize < @indent
}
commentAttachment.heregex = yes if heregex
offsetInChunk += length
commentAttachment
prev = @prev()
unless prev
如果沒有前一個代碼,請建立一個暫存代碼來附加此註解;並加上一個新行。
commentAttachments[0].newLine = yes
@lineToken chunk: @chunk[commentWithSurroundingWhitespace.length..], offset: commentWithSurroundingWhitespace.length # Set the indent.
placeholderToken = @makeToken 'JS', '', offset: commentWithSurroundingWhitespace.length, generated: yes
placeholderToken.comments = commentAttachments
@tokens.push placeholderToken
@newlineToken commentWithSurroundingWhitespace.length
else
attachCommentsToNode commentAttachments, prev
return commentAttachments if returnCommentTokens
commentWithSurroundingWhitespace.length
比對直接透過反引號插入來源的 JavaScript。
jsToken: ->
return 0 unless @chunk.charAt(0) is '`' and
(match = (matchedHere = HERE_JSTOKEN.exec(@chunk)) or JSTOKEN.exec(@chunk))
將跳脫的反引號轉換為反引號,以及跳脫反引號前方的跳脫反斜線轉換為反斜線
script = match[1]
{length} = match[0]
@token 'JS', script, {length, data: {here: !!matchedHere}}
length
比對正規表示法文字,以及多行延伸正規表示法文字。正規表示法的詞法分析難以與除法區分,因此我們借用了 JavaScript 和 Ruby 的一些基本啟發法。
regexToken: ->
switch
when match = REGEX_ILLEGAL.exec @chunk
@error "regular expressions cannot begin with #{match[2]}",
offset: match.index + match[1].length
when match = @matchWithInterpolations HEREGEX, '///'
{tokens, index} = match
comments = []
while matchedComment = HEREGEX_COMMENT.exec @chunk[0...index]
{index: commentIndex} = matchedComment
[fullMatch, leadingWhitespace, comment] = matchedComment
comments.push {comment, offsetInChunk: commentIndex + leadingWhitespace.length}
commentTokens = flatten(
for commentOpts in comments
@commentToken commentOpts.comment, Object.assign commentOpts, heregex: yes, returnCommentTokens: yes
)
when match = REGEX.exec @chunk
[regex, body, closed] = match
@validateEscapes body, isRegex: yes, offsetInChunk: 1
index = regex.length
prev = @prev()
if prev
if prev.spaced and prev[0] in CALLABLE
return 0 if not closed or POSSIBLY_DIVISION.test regex
else if prev[0] in NOT_REGEX
return 0
@error 'missing / (unclosed regex)' unless closed
else
return 0
[flags] = REGEX_FLAGS.exec @chunk[index..]
end = index + flags.length
origin = @makeToken 'REGEX', null, length: end
switch
when not VALID_FLAGS.test flags
@error "invalid regular expression flags #{flags}", offset: index, length: flags.length
when regex or tokens.length is 1
delimiter = if body then '/' else '///'
body ?= tokens[0][1]
@validateUnicodeCodePointEscapes body, {delimiter}
@token 'REGEX', "/#{body}/#{flags}", {length: end, origin, data: {delimiter}}
else
@token 'REGEX_START', '(', {length: 0, origin, generated: yes}
@token 'IDENTIFIER', 'RegExp', length: 0, generated: yes
@token 'CALL_START', '(', length: 0, generated: yes
@mergeInterpolationTokens tokens, {double: yes, heregex: {flags}, endOffset: end - flags.length, quote: '///'}, (str) =>
@validateUnicodeCodePointEscapes str, {delimiter}
if flags
@token ',', ',', offset: index - 1, length: 0, generated: yes
@token 'STRING', '"' + flags + '"', offset: index, length: flags.length
@token ')', ')', offset: end, length: 0, generated: yes
@token 'REGEX_END', ')', offset: end, length: 0, generated: yes
明確地將任何 heregex 註解附加到 REGEX/REGEX_END 代碼。
if commentTokens?.length
addTokenData @tokens[@tokens.length - 1],
heregexCommentTokens: commentTokens
end
比對新行、縮排和取消縮排,並判斷它們是什麼。如果我們可以偵測到目前行已繼續到下一行,則會抑制新行
elements
.each( ... )
.map( ... )
追蹤縮排層級,因為單一縮排取消代碼可以關閉多個縮排,所以我們需要知道我們目前在哪個層級。
lineToken: ({chunk = @chunk, offset = 0} = {}) ->
return 0 unless match = MULTI_DENT.exec chunk
indent = match[0]
prev = @prev()
backslash = prev?[0] is '\\'
@seenFor = no unless (backslash or @seenFor?.endsLength < @ends.length) and @seenFor
@seenImport = no unless (backslash and @seenImport) or @importSpecifierList
@seenExport = no unless (backslash and @seenExport) or @exportSpecifierList
size = indent.length - 1 - indent.lastIndexOf '\n'
noNewlines = @unfinished()
newIndentLiteral = if size > 0 then indent[-size..] else ''
unless /^(.?)\1*$/.exec newIndentLiteral
@error 'mixed indentation', offset: indent.length
return indent.length
minLiteralLength = Math.min newIndentLiteral.length, @indentLiteral.length
if newIndentLiteral[...minLiteralLength] isnt @indentLiteral[...minLiteralLength]
@error 'indentation mismatch', offset: indent.length
return indent.length
if size - @continuationLineAdditionalIndent is @indent
if noNewlines then @suppressNewlines() else @newlineToken offset
return indent.length
if size > @indent
if noNewlines
@continuationLineAdditionalIndent = size - @indent unless backslash
if @continuationLineAdditionalIndent
prev.continuationLineIndent = @indent + @continuationLineAdditionalIndent
@suppressNewlines()
return indent.length
unless @tokens.length
@baseIndent = @indent = size
@indentLiteral = newIndentLiteral
return indent.length
diff = size - @indent + @outdebt
@token 'INDENT', diff, offset: offset + indent.length - size, length: size
@indents.push diff
@ends.push {tag: 'OUTDENT'}
@outdebt = @continuationLineAdditionalIndent = 0
@indent = size
@indentLiteral = newIndentLiteral
else if size < @baseIndent
@error 'missing indentation', offset: offset + indent.length
else
endsContinuationLineIndentation = @continuationLineAdditionalIndent > 0
@continuationLineAdditionalIndent = 0
@outdentToken {moveOut: @indent - size, noNewlines, outdentLength: indent.length, offset, indentSize: size, endsContinuationLineIndentation}
indent.length
記錄縮排取消代碼或多個代碼,如果我們剛好往回移動超過幾個已記錄的縮排。設定新的 @indent 值。
outdentToken: ({moveOut, noNewlines, outdentLength = 0, offset = 0, indentSize, endsContinuationLineIndentation}) ->
decreasedIndent = @indent - moveOut
while moveOut > 0
lastIndent = @indents[@indents.length - 1]
if not lastIndent
@outdebt = moveOut = 0
else if @outdebt and moveOut <= @outdebt
@outdebt -= moveOut
moveOut = 0
else
dent = @indents.pop() + @outdebt
if outdentLength and @chunk[outdentLength] in INDENTABLE_CLOSERS
decreasedIndent -= dent - moveOut
moveOut = dent
@outdebt = 0
配對可能會呼叫縮排取消代碼,所以保留 decreasedIndent
@pair 'OUTDENT'
@token 'OUTDENT', moveOut, length: outdentLength, indentSize: indentSize + moveOut - dent
moveOut -= dent
@outdebt -= moveOut if dent
@suppressSemicolons()
unless @tag() is 'TERMINATOR' or noNewlines
terminatorToken = @token 'TERMINATOR', '\n', offset: offset + outdentLength, length: 0
terminatorToken.endsContinuationLineIndentation = {preContinuationLineIndent: @indent} if endsContinuationLineIndentation
@indent = decreasedIndent
@indentLiteral = @indentLiteral[...decreasedIndent]
this
比對並消耗沒有意義的空白。標記前一個代碼為「有空白」,因為在某些情況下會有差別。
whitespaceToken: ->
return 0 unless (match = WHITESPACE.exec @chunk) or
(nline = @chunk.charAt(0) is '\n')
prev = @prev()
prev[if match then 'spaced' else 'newLine'] = true if prev
if match then match[0].length else 0
產生換行代碼。連續換行會合併在一起。
newlineToken: (offset) ->
@suppressSemicolons()
@token 'TERMINATOR', '\n', {offset, length: 0} unless @tag() is 'TERMINATOR'
this
在行尾使用 \
來抑制換行。斜線在完成工作後會在此移除。
suppressNewlines: ->
prev = @prev()
if prev[1] is '\\'
if prev.comments and @tokens.length > 1
@tokens.length
應該至少為 2(一些程式碼,然後 \
)。如果某個東西在沒有任何東西後放置 \
,他們應該會失去任何緊接在後的註解。
attachCommentsToNode prev.comments, @tokens[@tokens.length - 2]
@tokens.pop()
this
jsxToken: ->
firstChar = @chunk[0]
檢查前一個代碼以偵測屬性是否已展開。
prevChar = if @tokens.length > 0 then @tokens[@tokens.length - 1][0] else ''
if firstChar is '<'
match = JSX_IDENTIFIER.exec(@chunk[1...]) or JSX_FRAGMENT_IDENTIFIER.exec(@chunk[1...])
return 0 unless match and (
@jsxDepth > 0 or
不是沒有空白的比較運算式右邊(例如 a<b
)。
not (prev = @prev()) or
prev.spaced or
prev[0] not in COMPARABLE_LEFT_SIDE
)
[input, id] = match
fullId = id
if '.' in id
[id, properties...] = id.split '.'
else
properties = []
tagToken = @token 'JSX_TAG', id,
length: id.length + 1
data:
openingBracketToken: @makeToken '<', '<'
tagNameToken: @makeToken 'IDENTIFIER', id, offset: 1
offset = id.length + 1
for property in properties
@token '.', '.', {offset}
offset += 1
@token 'PROPERTY', property, {offset}
offset += property.length
@token 'CALL_START', '(', generated: yes
@token '[', '[', generated: yes
@ends.push {tag: '/>', origin: tagToken, name: id, properties}
@jsxDepth++
return fullId.length + 1
else if jsxTag = @atJSXTag()
if @chunk[...2] is '/>' # Self-closing tag.
@pair '/>'
@token ']', ']',
length: 2
generated: yes
@token 'CALL_END', ')',
length: 2
generated: yes
data:
selfClosingSlashToken: @makeToken '/', '/'
closingBracketToken: @makeToken '>', '>', offset: 1
@jsxDepth--
return 2
else if firstChar is '{'
if prevChar is ':'
這個代碼代表 JSX 屬性值的開頭,是一個表達式(例如 <div a={b} />
中的 {b}
)。我們的語法將表達式的開頭表示為 (
代碼,所以將這變成一個顯示為 {
的 (
代碼。
token = @token '(', '{'
@jsxObjAttribute[@jsxDepth] = no
標記屬性名稱為 JSX
addTokenData @tokens[@tokens.length - 3],
jsx: yes
else
token = @token '{', '{'
@jsxObjAttribute[@jsxDepth] = yes
@ends.push {tag: '}', origin: token}
return 1
else if firstChar is '>' # end of opening tag
忽略標籤內的終止符。
{origin: openingTagToken} = @pair '/>' # As if the current tag was self-closing.
@token ']', ']',
generated: yes
data:
closingBracketToken: @makeToken '>', '>'
@token ',', 'JSX_COMMA', generated: yes
{tokens, index: end} =
@matchWithInterpolations INSIDE_JSX, '>', '</', JSX_INTERPOLATION
@mergeInterpolationTokens tokens, {endOffset: end, jsx: yes}, (value) =>
@validateUnicodeCodePointEscapes value, delimiter: '>'
match = JSX_IDENTIFIER.exec(@chunk[end...]) or JSX_FRAGMENT_IDENTIFIER.exec(@chunk[end...])
if not match or match[1] isnt "#{jsxTag.name}#{(".#{property}" for property in jsxTag.properties).join ''}"
@error "expected corresponding JSX closing tag for #{jsxTag.name}",
jsxTag.origin.data.tagNameToken[2]
[, fullTagName] = match
afterTag = end + fullTagName.length
if @chunk[afterTag] isnt '>'
@error "missing closing > after tag name", offset: afterTag, length: 1
開啟 </
為 -2/+2,關閉 >
為 +1。
endToken = @token 'CALL_END', ')',
offset: end - 2
length: fullTagName.length + 3
generated: yes
data:
closingTagOpeningBracketToken: @makeToken '<', '<', offset: end - 2
closingTagSlashToken: @makeToken '/', '/', offset: end - 1
待辦事項:複雜標籤名稱的個別標記?例如 < / A . B >
closingTagNameToken: @makeToken 'IDENTIFIER', fullTagName, offset: end
closingTagClosingBracketToken: @makeToken '>', '>', offset: end + fullTagName.length
讓語法更容易存取關閉標籤的位置資料
addTokenData openingTagToken, endToken.data
@jsxDepth--
return afterTag + 1
else
return 0
else if @atJSXTag 1
if firstChar is '}'
@pair firstChar
if @jsxObjAttribute[@jsxDepth]
@token '}', '}'
@jsxObjAttribute[@jsxDepth] = no
else
@token ')', '}'
@token ',', ',', generated: yes
return 1
else
return 0
else
return 0
atJSXTag: (depth = 0) ->
return no if @jsxDepth is 0
i = @ends.length - 1
i-- while @ends[i]?.tag is 'OUTDENT' or depth-- > 0 # Ignore indents.
last = @ends[i]
last?.tag is '/>' and last
我們將所有其他單一字元視為標記。例如:( ) , . !
多字元運算子也是文字標記,以便 Jison 可以指定適當的運算順序。我們在此特別標記了一些符號。;
和換行符號都視為 TERMINATOR
,我們區分表示方法呼叫的括號和一般括號,依此類推。
literalToken: ->
if match = OPERATOR.exec @chunk
[value] = match
@tagParameters() if CODE.test value
else
value = @chunk.charAt 0
tag = value
prev = @prev()
if prev and value in ['=', COMPOUND_ASSIGN...]
skipToken = false
if value is '=' and prev[1] in ['||', '&&'] and not prev.spaced
prev[0] = 'COMPOUND_ASSIGN'
prev[1] += '='
prev.data.original += '=' if prev.data?.original
prev[2].range = [
prev[2].range[0]
prev[2].range[1] + 1
]
prev[2].last_column += 1
prev[2].last_column_exclusive += 1
prev = @tokens[@tokens.length - 2]
skipToken = true
if prev and prev[0] isnt 'PROPERTY'
origin = prev.origin ? prev
message = isUnassignable prev[1], origin[1]
@error message, origin[2] if message
return value.length if skipToken
if value is '(' and prev?[0] is 'IMPORT'
prev[0] = 'DYNAMIC_IMPORT'
if value is '{' and @seenImport
@importSpecifierList = yes
else if @importSpecifierList and value is '}'
@importSpecifierList = no
else if value is '{' and prev?[0] is 'EXPORT'
@exportSpecifierList = yes
else if @exportSpecifierList and value is '}'
@exportSpecifierList = no
if value is ';'
@error 'unexpected ;' if prev?[0] in ['=', UNFINISHED...]
@seenFor = @seenImport = @seenExport = no
tag = 'TERMINATOR'
else if value is '*' and prev?[0] is 'EXPORT'
tag = 'EXPORT_ALL'
else if value in MATH then tag = 'MATH'
else if value in COMPARE then tag = 'COMPARE'
else if value in COMPOUND_ASSIGN then tag = 'COMPOUND_ASSIGN'
else if value in UNARY then tag = 'UNARY'
else if value in UNARY_MATH then tag = 'UNARY_MATH'
else if value in SHIFT then tag = 'SHIFT'
else if value is '?' and prev?.spaced then tag = 'BIN?'
else if prev
if value is '(' and not prev.spaced and prev[0] in CALLABLE
prev[0] = 'FUNC_EXIST' if prev[0] is '?'
tag = 'CALL_START'
else if value is '[' and ((prev[0] in INDEXABLE and not prev.spaced) or
(prev[0] is '::')) # `.prototype` can’t be a method you can call.
tag = 'INDEX_START'
switch prev[0]
when '?' then prev[0] = 'INDEX_SOAK'
token = @makeToken tag, value
switch value
when '(', '{', '[' then @ends.push {tag: INVERSES[value], origin: token}
when ')', '}', ']' then @pair value
@tokens.push @makeToken tag, value
value.length
我們的語法中,函式定義中的參數清單與函式呼叫中的引數清單之間的含糊性來源。向後移動,特別標記參數,以便讓剖析器更容易處理。
tagParameters: ->
return @tagDoIife() if @tag() isnt ')'
stack = []
{tokens} = this
i = tokens.length
paramEndToken = tokens[--i]
paramEndToken[0] = 'PARAM_END'
while tok = tokens[--i]
switch tok[0]
when ')'
stack.push tok
when '(', 'CALL_START'
if stack.length then stack.pop()
else if tok[0] is '('
tok[0] = 'PARAM_START'
return @tagDoIife i - 1
else
paramEndToken[0] = 'CALL_END'
return this
this
標記 do
後接函式與 do
後接例如識別碼不同,以允許不同的語法優先順序
tagDoIife: (tokenIndex) ->
tok = @tokens[tokenIndex ? @tokens.length - 1]
return this unless tok?[0] is 'DO'
tok[0] = 'DO_IIFE'
this
在檔案結尾關閉所有剩下的開啟區塊。
closeIndentation: ->
@outdentToken moveOut: @indent, indentSize: 0
比對分隔標記的內容,並使用類似 Ruby 的符號來擴充其中的變數和表達式,以取代任意表達式。
"Hello #{name.capitalize()}."
如果遇到內插,此方法將遞迴建立新的 Lexer 並進行標記化,直到 #{
的 {
與 }
平衡為止。
regex
比對標記的內容(但不比對 delimiter
,如果需要內插,也不比對 #{
)。delimiter
是標記的分隔符號。範例包括 '
、"
、'''
、"""
和 ///
。closingDelimiter
僅在 JSX 中與 delimiter
不同interpolators
符合內插的開頭,對於 JSX 來說,它同時為 {
和 <
(即巢狀 JSX 標籤)此方法允許我們在字串內有內插的字串,如此反覆下去。
matchWithInterpolations: (regex, delimiter, closingDelimiter = delimiter, interpolators = /^#\{/) ->
tokens = []
offsetInChunk = delimiter.length
return null unless @chunk[...offsetInChunk] is delimiter
str = @chunk[offsetInChunk..]
loop
[strPart] = regex.exec str
@validateEscapes strPart, {isRegex: delimiter.charAt(0) is '/', offsetInChunk}
推入一個假的 'NEOSTRING'
權杖,稍後它將會變成一個真正的字串。
tokens.push @makeToken 'NEOSTRING', strPart, offset: offsetInChunk
str = str[strPart.length..]
offsetInChunk += strPart.length
break unless match = interpolators.exec str
[interpolator] = match
移除 #{
中的 #
。
interpolationOffset = interpolator.length - 1
[line, column, offset] = @getLineAndColumnFromChunk offsetInChunk + interpolationOffset
rest = str[interpolationOffset..]
{tokens: nested, index} =
new Lexer().tokenize rest, {line, column, offset, untilBalanced: on, @locationDataCompensations}
考量 #{
中的 #
。
index += interpolationOffset
braceInterpolator = str[index - 1] is '}'
if braceInterpolator
將開頭和結尾的 {
和 }
變成括弧。不必要的括弧將會在稍後移除。
[open, ..., close] = nested
open[0] = 'INTERPOLATION_START'
open[1] = '('
open[2].first_column -= interpolationOffset
open[2].range = [
open[2].range[0] - interpolationOffset
open[2].range[1]
]
close[0] = 'INTERPOLATION_END'
close[1] = ')'
close.origin = ['', 'end of interpolation', close[2]]
移除開頭的 'TERMINATOR'
(如有)。
nested.splice 1, 1 if nested[1]?[0] is 'TERMINATOR'
移除結尾的 'INDENT'/'OUTDENT'
配對(如有)。
nested.splice -3, 2 if nested[nested.length - 3]?[0] is 'INDENT' and nested[nested.length - 2][0] is 'OUTDENT'
unless braceInterpolator
我們沒有使用 {
和 }
,所以改為包裝內插的權杖。
open = @makeToken 'INTERPOLATION_START', '(', offset: offsetInChunk, length: 0, generated: yes
close = @makeToken 'INTERPOLATION_END', ')', offset: offsetInChunk + index, length: 0, generated: yes
nested = [open, nested..., close]
推入一個假的 'TOKENS'
權杖,稍後它將會變成真正的權杖。
tokens.push ['TOKENS', nested]
str = str[index..]
offsetInChunk += index
unless str[...closingDelimiter.length] is closingDelimiter
@error "missing #{closingDelimiter}", length: delimiter.length
{tokens, index: offsetInChunk + closingDelimiter.length}
將假權杖類型 'TOKENS'
和 'NEOSTRING'
(由 matchWithInterpolations
傳回)的陣列 tokens
合併到權杖串流中。'NEOSTRING'
的值會使用 fn
轉換,並使用 options
先轉換成字串。
mergeInterpolationTokens: (tokens, options, fn) ->
{quote, indent, double, heregex, endOffset, jsx} = options
if tokens.length > 1
lparen = @token 'STRING_START', '(', length: quote?.length ? 0, data: {quote}, generated: not quote?.length
firstIndex = @tokens.length
$ = tokens.length - 1
for token, i in tokens
[tag, value] = token
switch tag
when 'TOKENS'
此內插中有註解(沒有其他東西)。
if value.length is 2 and (value[0].comments or value[1].comments)
placeholderToken = @makeToken 'JS', '', generated: yes
使用與第一個括弧相同的位址資料。
placeholderToken[2] = value[0][2]
for val in value when val.comments
placeholderToken.comments ?= []
placeholderToken.comments.push val.comments...
value.splice 1, 0, placeholderToken
推入假 'TOKENS'
權杖中的所有權杖。它們已經有健全的位址資料。
locationToken = value[0]
tokensToPush = value
when 'NEOSTRING'
將 'NEOSTRING'
轉換成 'STRING'
。
converted = fn.call this, token[1], i
addTokenData token, initialChunk: yes if i is 0
addTokenData token, finalChunk: yes if i is $
addTokenData token, {indent, quote, double}
addTokenData token, {heregex} if heregex
addTokenData token, {jsx} if jsx
token[0] = 'STRING'
token[1] = '"' + converted + '"'
if tokens.length is 1 and quote?
token[2].first_column -= quote.length
if token[1].substr(-2, 1) is '\n'
token[2].last_line += 1
token[2].last_column = quote.length - 1
else
token[2].last_column += quote.length
token[2].last_column -= 1 if token[1].length is 2
token[2].last_column_exclusive += quote.length
token[2].range = [
token[2].range[0] - quote.length
token[2].range[1] + quote.length
]
locationToken = token
tokensToPush = [token]
@tokens.push tokensToPush...
if lparen
[..., lastToken] = tokens
lparen.origin = ['STRING', null,
first_line: lparen[2].first_line
first_column: lparen[2].first_column
last_line: lastToken[2].last_line
last_column: lastToken[2].last_column
last_line_exclusive: lastToken[2].last_line_exclusive
last_column_exclusive: lastToken[2].last_column_exclusive
range: [
lparen[2].range[0]
lastToken[2].range[1]
]
]
lparen[2] = lparen.origin[2] unless quote?.length
rparen = @token 'STRING_END', ')', offset: endOffset - (quote ? '').length, length: quote?.length ? 0, generated: not quote?.length
配對一個關閉標記,確保標記串流的過程中,所有列出的標記配對都正確平衡。
pair: (tag) ->
[..., prev] = @ends
unless tag is wanted = prev?.tag
@error "unmatched #{tag}" unless 'OUTDENT' is wanted
[..., lastIndent] = @indents
@outdentToken moveOut: lastIndent, noNewlines: true
return @pair tag
@ends.pop()
補償我們最初移除的東西(例如換行符號),以便位置資料與原始來源檔案保持準確。
getLocationDataCompensation: (start, end) ->
totalCompensation = 0
initialEnd = end
current = start
while current <= end
break if current is end and start isnt initialEnd
compensation = @locationDataCompensations[current]
if compensation?
totalCompensation += compensation
end += compensation
current++
return totalCompensation
getLineAndColumnFromChunk: (offset) ->
compensation = @getLocationDataCompensation @chunkOffset, @chunkOffset + offset
if offset is 0
return [@chunkLine, @chunkColumn + compensation, @chunkOffset + compensation]
if offset >= @chunk.length
string = @chunk
else
string = @chunk[..offset-1]
lineCount = count string, '\n'
column = @chunkColumn
if lineCount > 0
[..., lastLine] = string.split '\n'
column = lastLine.length
previousLinesCompensation = @getLocationDataCompensation @chunkOffset, @chunkOffset + offset - column
不要補償最初插入的新行。
previousLinesCompensation = 0 if previousLinesCompensation < 0
columnCompensation = @getLocationDataCompensation(
@chunkOffset + offset + previousLinesCompensation - column
@chunkOffset + offset + previousLinesCompensation
)
else
column += string.length
columnCompensation = compensation
[@chunkLine + lineCount, column + columnCompensation, @chunkOffset + offset + compensation]
makeLocationData: ({ offsetInChunk, length }) ->
locationData = range: []
[locationData.first_line, locationData.first_column, locationData.range[0]] =
@getLineAndColumnFromChunk offsetInChunk
使用長度 - 1 作為最後的偏移量 - 我們提供 last_line 和 last_column,所以如果 last_column == first_column,那麼我們正在查看長度為 1 的字元。
lastCharacter = if length > 0 then (length - 1) else 0
[locationData.last_line, locationData.last_column, endOffset] =
@getLineAndColumnFromChunk offsetInChunk + lastCharacter
[locationData.last_line_exclusive, locationData.last_column_exclusive] =
@getLineAndColumnFromChunk offsetInChunk + lastCharacter + (if length > 0 then 1 else 0)
locationData.range[1] = if length > 0 then endOffset + 1 else endOffset
locationData
與 token
相同,只不過這個只傳回標記,而不會將其新增到結果中。
makeToken: (tag, value, {offset: offsetInChunk = 0, length = value.length, origin, generated, indentSize} = {}) ->
token = [tag, value, @makeLocationData {offsetInChunk, length}]
token.origin = origin if origin
token.generated = yes if generated
token.indentSize = indentSize if indentSize?
token
將標記新增到結果中。offset
是標記在當前 @chunk
中開始的偏移量。length
是標記在 @chunk
中的長度,在偏移量之後。如果未指定,將使用 value
的長度。
傳回新的標記。
token: (tag, value, {offset, length, origin, data, generated, indentSize} = {}) ->
token = @makeToken tag, value, {offset, length, origin, generated, indentSize}
addTokenData token, data if data
@tokens.push token
token
窺視標記串流中的最後一個標籤。
tag: ->
[..., token] = @tokens
token?[0]
窺視標記串流中的最後一個值。
value: (useOrigin = no) ->
[..., token] = @tokens
if useOrigin and token?.origin?
token.origin[1]
else
token?[1]
取得標記串流中的前一個標記。
prev: ->
@tokens[@tokens.length - 1]
我們是否處於未完成的表達式中?
unfinished: ->
LINE_CONTINUER.test(@chunk) or
@tag() in UNFINISHED
validateUnicodeCodePointEscapes: (str, options) ->
replaceUnicodeCodePointEscapes str, merge options, {@error}
驗證字串和正規表示式中的跳脫字元。
validateEscapes: (str, options = {}) ->
invalidEscapeRegex =
if options.isRegex
REGEX_INVALID_ESCAPE
else
STRING_INVALID_ESCAPE
match = invalidEscapeRegex.exec str
return unless match
[[], before, octal, hex, unicodeCodePoint, unicode] = match
message =
if octal
"octal escape sequences are not allowed"
else
"invalid escape sequence"
invalidEscape = "\\#{octal or hex or unicodeCodePoint or unicode}"
@error "#{message} #{invalidEscape}",
offset: (options.offsetInChunk ? 0) + match.index + before.length
length: invalidEscape.length
suppressSemicolons: ->
while @value() is ';'
@tokens.pop()
@error 'unexpected ;' if @prev()?[0] in ['=', UNFINISHED...]
在當前區塊的給定偏移量或記號位置 (token[2]
) 擲回錯誤。
error: (message, options = {}) =>
location =
if 'first_line' of options
options
else
[first_line, first_column] = @getLineAndColumnFromChunk options.offset ? 0
{first_line, first_column, last_column: first_column + (options.length ? 1) - 1}
throwSyntaxError message, location
isUnassignable = (name, displayName = name) -> switch
when name in [JS_KEYWORDS..., COFFEE_KEYWORDS...]
"keyword '#{displayName}' can't be assigned"
when name in STRICT_PROSCRIBED
"'#{displayName}' can't be assigned"
when name in RESERVED
"reserved word '#{displayName}' can't be assigned"
else
false
exports.isUnassignable = isUnassignable
from
並非 CoffeeScript 關鍵字,但它在 import
和 export
陳述式 (如上所述) 以及 for
迴圈的宣告列中,表現得像關鍵字一樣。請嘗試偵測 from
是變數識別碼還是這個「有時」關鍵字。
isForFrom = (prev) ->
for i from iterable
if prev[0] is 'IDENTIFIER'
yes
for from…
else if prev[0] is 'FOR'
no
for {from}…
, for [from]…
, for {a, from}…
, for {a: from}…
else if prev[1] in ['{', '[', ',', ':']
no
else
yes
addTokenData = (token, data) ->
Object.assign (token.data ?= {}), data
CoffeeScript 與 JavaScript 共用的關鍵字。
JS_KEYWORDS = [
'true', 'false', 'null', 'this'
'new', 'delete', 'typeof', 'in', 'instanceof'
'return', 'throw', 'break', 'continue', 'debugger', 'yield', 'await'
'if', 'else', 'switch', 'for', 'while', 'do', 'try', 'catch', 'finally'
'class', 'extends', 'super'
'import', 'export', 'default'
]
僅 CoffeeScript 的關鍵字。
COFFEE_KEYWORDS = [
'undefined', 'Infinity', 'NaN'
'then', 'unless', 'until', 'loop', 'of', 'by', 'when'
]
COFFEE_ALIAS_MAP =
and : '&&'
or : '||'
is : '=='
isnt : '!='
not : '!'
yes : 'true'
no : 'false'
on : 'true'
off : 'false'
COFFEE_ALIASES = (key for key of COFFEE_ALIAS_MAP)
COFFEE_KEYWORDS = COFFEE_KEYWORDS.concat COFFEE_ALIASES
JavaScript 保留但未使用的關鍵字清單,或 CoffeeScript 內部使用的關鍵字。當遇到這些關鍵字時,我們會擲回錯誤,以避免在執行階段發生 JavaScript 錯誤。
RESERVED = [
'case', 'function', 'var', 'void', 'with', 'const', 'let', 'enum'
'native', 'implements', 'interface', 'package', 'private'
'protected', 'public', 'static'
]
STRICT_PROSCRIBED = ['arguments', 'eval']
JavaScript 關鍵字和保留字的超集,其中任何一個都不可用作識別碼或屬性。
exports.JS_FORBIDDEN = JS_KEYWORDS.concat(RESERVED).concat(STRICT_PROSCRIBED)
令人討厭的 Microsoft 瘋狂行為的字元碼,也稱為 BOM。
BOM = 65279
記號比對正規表示式。
IDENTIFIER = /// ^
(?!\d)
( (?: (?!\s)[$\w\x7f-\uffff] )+ )
( [^\n\S]* : (?!:) )? # Is this a property name?
///
類似於 IDENTIFIER
,但包含 -
JSX_IDENTIFIER_PART = /// (?: (?!\s)[\-$\w\x7f-\uffff] )+ ///.source
在 https://facebook.github.io/jsx/ 規格中,JSXElementName 可以是 JSXIdentifier、JSXNamespacedName (JSXIdentifier : JSXIdentifier) 或 JSXMemberExpression (兩個或以上的 JSXIdentifier 以 .
連接)。
JSX_IDENTIFIER = /// ^
(?![\d<]) # Must not start with `<`.
( #{JSX_IDENTIFIER_PART}
(?: \s* : \s* #{JSX_IDENTIFIER_PART} # JSXNamespacedName
| (?: \s* \. \s* #{JSX_IDENTIFIER_PART} )+ # JSXMemberExpression
)? )
///
片段:<></>
JSX_FRAGMENT_IDENTIFIER = /// ^
()> # Ends immediately with `>`.
///
在 https://facebook.github.io/jsx/ 規格中,JSXAttributeName 可以是 JSXIdentifier 或 JSXNamespacedName,而 JSXNamespacedName 為 JSXIdentifier : JSXIdentifier
JSX_ATTRIBUTE = /// ^
(?!\d)
( #{JSX_IDENTIFIER_PART}
(?: \s* : \s* #{JSX_IDENTIFIER_PART} # JSXNamespacedName
)? )
( [^\S]* = (?!=) )? # Is this an attribute with a value?
///
NUMBER = ///
^ 0b[01](?:_?[01])*n? | # binary
^ 0o[0-7](?:_?[0-7])*n? | # octal
^ 0x[\da-f](?:_?[\da-f])*n? | # hex
^ \d+(?:_\d+)*n | # decimal bigint
^ (?:\d+(?:_\d+)*)? \.? \d+(?:_\d+)* # decimal
(?:e[+-]? \d+(?:_\d+)* )?
十進制,不支援數字文字分隔符號,供參考:\d*.?\d+ (?:e[+-]?\d+)?
///i
OPERATOR = /// ^ (
?: [-=]> # function
| [-+*/%<>&|^!?=]= # compound assign / compare
| >>>=? # zero-fill right shift
| ([-+:])\1 # doubles
| ([&|<>*/%])\2=? # logic / shift / power / floor division / modulo
| \?(\.|::) # soak access
| \.{2,3} # range or splat
) ///
WHITESPACE = /^[^\n\S]+/
COMMENT = /^(\s*)###([^#][\s\S]*?)(?:###([^\n\S]*)|###$)|^((?:\s*#(?!##[^#]).*)+)/
CODE = /^[-=]>/
MULTI_DENT = /^(?:\n[^\n\S]*)+/
JSTOKEN = ///^ `(?!``) ((?: [^`\\] | \\[\s\S] )*) ` ///
HERE_JSTOKEN = ///^ ``` ((?: [^`\\] | \\[\s\S] | `(?!``) )*) ``` ///
字串比對正規表示式。
STRING_START = /^(?:'''|"""|'|")/
STRING_SINGLE = /// ^(?: [^\\'] | \\[\s\S] )* ///
STRING_DOUBLE = /// ^(?: [^\\"#] | \\[\s\S] | \#(?!\{) )* ///
HEREDOC_SINGLE = /// ^(?: [^\\'] | \\[\s\S] | '(?!'') )* ///
HEREDOC_DOUBLE = /// ^(?: [^\\"#] | \\[\s\S] | "(?!"") | \#(?!\{) )* ///
INSIDE_JSX = /// ^(?:
[^
\{ # Start of CoffeeScript interpolation.
< # Maybe JSX tag (`<` not allowed even if bare).
]
)* /// # Similar to `HEREDOC_DOUBLE` but there is no escaping.
JSX_INTERPOLATION = /// ^(?:
\{ # CoffeeScript interpolation.
| <(?!/) # JSX opening tag.
)///
HEREDOC_INDENT = /\n+([^\n\S]*)(?=\S)/g
正規表示式比對正規表示式。
REGEX = /// ^
/ (?!/) ((
?: [^ [ / \n \\ ] # Every other thing.
| \\[^\n] # Anything but newlines escaped.
| \[ # Character class.
(?: \\[^\n] | [^ \] \n \\ ] )*
\]
)*) (/)?
///
REGEX_FLAGS = /^\w*/
VALID_FLAGS = /^(?!.*(.).*\1)[gimsuy]*$/
HEREGEX = /// ^
(?:
比對任何字元,但下列需要特殊處理的字元除外。
[^\\/#\s]
比對 \
後接任何字元。
| \\[\s\S]
比對任何 /
,但 ///
除外。
| /(?!//)
比對不屬於內插的一部分的 #
,例如 #{}
。
| \#(?!\{)
註解會使用到一行結尾的所有內容,包括 ///
。
| \s+(?:#(?!\{).*)?
)*
///
HEREGEX_COMMENT = /(\s+)(#(?!{).*)/gm
REGEX_ILLEGAL = /// ^ ( / | /{3}\s*) (\*) ///
POSSIBLY_DIVISION = /// ^ /=?\s ///
其他正則表示式。
HERECOMMENT_ILLEGAL = /\*\//
LINE_CONTINUER = /// ^ \s* (?: , | \??\.(?![.\d]) | \??:: ) ///
STRING_INVALID_ESCAPE = ///
( (?:^|[^\\]) (?:\\\\)* ) # Make sure the escape isn’t escaped.
\\ (
?: (0\d|[1-7]) # octal escape
| (x(?![\da-fA-F]{2}).{0,2}) # hex escape
| (u\{(?![\da-fA-F]{1,}\})[^}]*\}?) # unicode code point escape
| (u(?!\{|[\da-fA-F]{4}).{0,4}) # unicode escape
)
///
REGEX_INVALID_ESCAPE = ///
( (?:^|[^\\]) (?:\\\\)* ) # Make sure the escape isn’t escaped.
\\ (
?: (0\d) # octal escape
| (x(?![\da-fA-F]{2}).{0,2}) # hex escape
| (u\{(?![\da-fA-F]{1,}\})[^}]*\}?) # unicode code point escape
| (u(?!\{|[\da-fA-F]{4}).{0,4}) # unicode escape
)
///
TRAILING_SPACES = /\s+$/
複合指派令牌。
COMPOUND_ASSIGN = [
'-=', '+=', '/=', '*=', '%=', '||=', '&&=', '?=', '<<=', '>>=', '>>>='
'&=', '^=', '|=', '**=', '//=', '%%='
]
單元令牌。
UNARY = ['NEW', 'TYPEOF', 'DELETE']
UNARY_MATH = ['!', '~']
位元移位令牌。
SHIFT = ['<<', '>>', '>>>']
比較令牌。
COMPARE = ['==', '!=', '<', '>', '<=', '>=']
數學令牌。
MATH = ['*', '/', '%', '//', '%%']
可以使用 not
前綴否定的關係令牌。
RELATION = ['IN', 'OF', 'INSTANCEOF']
布林令牌。
BOOL = ['TRUE', 'FALSE']
可以合法地調用或索引的令牌。這些令牌後面的開括號或方括號將被記錄為函式調用或索引運算的開頭。
CALLABLE = ['IDENTIFIER', 'PROPERTY', ')', ']', '?', '@', 'THIS', 'SUPER', 'DYNAMIC_IMPORT']
INDEXABLE = CALLABLE.concat [
'NUMBER', 'INFINITY', 'NAN', 'STRING', 'STRING_END', 'REGEX', 'REGEX_END'
'BOOL', 'NULL', 'UNDEFINED', '}', '::'
]
可以作為小於比較運算的左邊的令牌,例如 a<b
。
COMPARABLE_LEFT_SIDE = ['IDENTIFIER', ')', ']', 'NUMBER']
正則表示式永遠不會立即遵循的令牌(在某些情況下,CALLABLE 除外),但除法運算子可以。
請參閱:http://www-archive.mozilla.org/js/language/js20-2002-04/rationale/syntax.html#regular-expressions
NOT_REGEX = INDEXABLE.concat ['++', '--']
在 WHEN
之前立即出現的令牌,表示 WHEN
出現在一行的開頭。我們將這些與尾隨的 WHEN 區分開來,以避免語法中的歧義。
LINE_BREAK = ['INDENT', 'OUTDENT', 'TERMINATOR']
忽略這些前面的額外縮排。
INDENTABLE_CLOSERS = [')', '}', ']']