All files / lib/env lexer.ts

93.1% Statements 189/203
91.75% Branches 89/97
89.47% Functions 17/19
92.12% Lines 152/165

Press n or j to go to the next uncovered block, b, p or k for the previous block.

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 3424x 4x   4x 4x 4x 4x 4x 4x 4x 4x 4x                       4x 4x 4x 4x 4x     4x 18x 18x 112x 112x 112x   18x     4x 112x   112x 112x 112x   112x 107x 107x     98x 88x 88x   79x 79x   69x 69x   63x 63x   45x 45x     37x 37x   20x 20x                 4x                                                     4x 112x 112x   95x 95x 95x 84x     4x 112x 112x   95x 95x 95x 84x     4x 14x             14x 14x 14x 4x 4x 4x 4x             10x             10x                 4x 9x 9x 9x 116x   116x 116x   113x   9x                   6x                 20x                 18x                 4x 112x   74x 74x 74x 74x   74x     4x 17x 17x   17x 17x 17x 17x 17x   17x   15x 246x 246x   246x 246x 246x   238x 238x   234x 234x   233x     15x 15x   15x 7x     15x                   4x 20x 20x 20x 160x 160x 160x 19x     141x     20x                   4x             4x 129x 129x   129x 217x 217x 217x 199x 199x 91x 91x   108x       129x     4x 37x 38x   38x 38x 17x     21x 21x 11x       9x     4x 88x  
import { QuoteType } from "lib/env/parser"
import { FileCoordinates, LexicalError } from "./error"
 
export enum TokenType {
    identifier = 'identifier',
    operator = 'operator',
    literal = 'literal',
    quote = 'quote',
    newline = 'newline',
    whitespace = 'whitespace',
    comment = 'comment',
    commentBody = 'commentBody'
}
 
export interface Token {
    type: TokenType
    position: number
    line: number
    column: number
    length: number
    value: string
}
 
const QUOTE_EXPRESSION = /^["']$/
const OPERATOR_EXPRESSION = /^=$/
const COMMENT_EXPRESSION = /^#$/
const IDENTIFIER_START_EXPRESSION = /^[a-zA-Z]$/
const IDENTIFIER_END_EXPRESSION = /^[^a-zA-Z0-9_-]$/
 
export type AnalyzeEnvSourceCode = typeof analyzeEnvSourceCode
export const analyzeEnvSourceCode = (path: string, src: string): Token[] => {
    const tokens: Token[] = []
    for (let i = 0; i < src.length;) {
        const token = getTokenAtPosition(path, src, i, tokens)
        tokens.push(token)
        i += token.length
    }
    return tokens
}
 
const getTokenAtPosition = (path: string, src: string, position: number, tokens: Token[]): Token => {
    const firstChar = src[position]
 
    const [previousToken, secondPreviousToken] = getPreviousTwoNonWhitespaceTokens(tokens)
    const isQuotedLiteral = isInsideQuotes(previousToken, secondPreviousToken)
    const isDoubleQuotedLiteral = isQuotedLiteral && previousToken.value === QuoteType.double
 
    if (!isDoubleQuotedLiteral) {
        const isNewline = firstChar === '\n' || firstChar === '\r'
        if (isNewline) return makeNewlineToken(position, src, tokens)
    }
 
    if (!isQuotedLiteral) {
        const isCommentBody = isLastTokenComment(tokens)
        if (isCommentBody) return makeCommentBodyToken(position, src, tokens)
 
        const isComment = COMMENT_EXPRESSION.test(firstChar)
        if (isComment) return makeCommentToken(position, src, tokens)
 
        const isWhiteSpace = /^\s$/.test(firstChar)
        if (isWhiteSpace) return makeWhiteSpaceToken(position, src, tokens)
 
        const isQuote = QUOTE_EXPRESSION.test(firstChar)
        if (isQuote) return makeQuoteToken(position, src, tokens)
 
        const isOperator = OPERATOR_EXPRESSION.test(firstChar)
        if (isOperator) return makeOperatorToken(position, src, tokens)
    }
 
    const isLiteral = hasAssignmentOperatorOnCurrentLine(tokens)
    if (isLiteral) return makeLiteralToken(position, src, tokens)
 
    const isIdentifier = IDENTIFIER_START_EXPRESSION.test(firstChar)
    Eif (isIdentifier) return makeIdentifierToken(position, src, tokens)
 
    {
        const previousToken = getPreviousToken(tokens)
        const coordinates = getCoordinates(previousToken)
        throw new LexicalError().setChar(firstChar).setCoordinates(coordinates).setFilePath(path)
    }
}
 
const getCoordinates = (previousToken?: Token): FileCoordinates => {
    if (!previousToken) {
        return {
            line: 1,
            column: 1,
            position: 1
        }
    }
 
    const position = previousToken.position + previousToken.length
 
    const isAfterNewline = previousToken.type === TokenType.newline
    if (isAfterNewline) {
        return {
            line: previousToken.line + 1,
            column: 1,
            position
        }
    }
 
    return {
        line: previousToken.line,
        column: previousToken.column + previousToken.length,
        position
    }
}
 
export const getLine = (tokens: Token[]): number => {
    const isFirstToken = tokens.length === 0
    if (isFirstToken) return 1
 
    const { type, line } = tokens[tokens.length - 1]
    const isNewLine = type === TokenType.newline
    if (isNewLine) return line + 1
    else return line
}
 
export const getColumn = (tokens: Token[]): number => {
    const isFirstToken = tokens.length === 0
    if (isFirstToken) return 1
 
    const { type, column, length } = tokens[tokens.length - 1]
    const isNewLine = type === TokenType.newline
    if (isNewLine) return 1
    else return column + length
}
 
const makeNewlineToken = (position: number, src: string, tokens: Token[]): Token => {
    const baseToken: Omit<Token, 'length' | 'value'> = {
        type: TokenType.newline,
        position,
        line: getLine(tokens),
        column: getColumn(tokens)
    }
 
    const char = src[position]
    const isCr = char === '\r'
    if (isCr) {
        const nextChar = src[position + 1]
        const isCrLf = nextChar === '\n'
        const value = isCrLf ? '\r\n' : '\r'
        return {
            ...baseToken,
            length: value.length,
            value
        }
    }
 
    return {
        ...baseToken,
        length: 1,
        value: '\n'
    }
}
 
const makeCommentToken = (position: number, src: string, tokens: Token[]): Token => ({
    type: TokenType.comment,
    position,
    line: getLine(tokens),
    column: getColumn(tokens),
    length: 1,
    value: src[position]
})
 
const makeCommentBodyToken = (position: number, src: string, tokens: Token[]): Token => {
    let i = position
    let value = src[i++]
    for (; i < src.length; i++) {
        const char = src[i]
        
        const isNewline = char === '\n' || char === '\r'
        if (isNewline) break
 
        value = `${value}${char}`
    }
    return {
        type: TokenType.commentBody,
        position,
        line: getLine(tokens),
        column: getColumn(tokens),
        length: value.length,
        value
    }
}
 
const makeWhiteSpaceToken = (position: number, src: string, tokens: Token[]): Token => ({
    type: TokenType.whitespace,
    position,
    line: getLine(tokens),
    column: getColumn(tokens),
    length: 1,
    value: src[position]
})
 
const makeQuoteToken = (position: number, src: string, tokens: Token[]): Token => ({
    type: TokenType.quote,
    position,
    line: getLine(tokens),
    column: getColumn(tokens),
    length: 1,
    value: src[position]
})
 
const makeOperatorToken = (position: number, src: string, tokens: Token[]): Token => ({
    type: TokenType.operator,
    position,
    line: getLine(tokens),
    column: getColumn(tokens),
    length: 1,
    value: src[position]
})
 
const isInsideQuotes = (previousToken?: Token, secondPreviousToken?: Token): boolean => {
    if (!previousToken || !secondPreviousToken) return false
 
    const hasOpeningQuote = previousToken.type === TokenType.quote
    const isSecondPreviousTokenQuote = secondPreviousToken.type === TokenType.quote
    const isSecondPreviousTokenLiteral = secondPreviousToken.type === TokenType.literal
    const hasTerminatingQuote = isSecondPreviousTokenQuote || isSecondPreviousTokenLiteral
 
    return hasOpeningQuote && !hasTerminatingQuote
}
 
const makeLiteralToken = (position: number, src: string, tokens: Token[]): Token => {
    let i = position
    let value = src[i++]
 
    const [previousToken] = getPreviousTwoNonWhitespaceTokens(tokens)
    const isQuotedValue = previousToken.type === TokenType.quote
    const firstChar = value
    const isClosingQuote = firstChar === previousToken?.value
    const isEmptyQuotedValue = isQuotedValue && isClosingQuote
 
    if (isEmptyQuotedValue) return makeQuoteToken(position, src, tokens)
 
    for (; i < src.length; i++) {
        const char = src[i]
        const previousChar = src[i - 1]
 
        const isClosingQuote = char === previousToken.value
        const isEscaped = previousChar === '\\'
        if (isQuotedValue && isClosingQuote && !isEscaped) break
 
        const isNewline = char === '\n' || char === '\r'
        if (isNewline && !isQuotedValue) break
 
        const isComment = char === '#'
        if (isComment && !isQuotedValue) break
 
        value = `${value}${char}`
    }
 
    const [ trailingWhitespace ] = /(\s*)$/.exec(value)
    const length = isQuotedValue ? value.length : value.length - trailingWhitespace.length
    
    if (!isQuotedValue) {
        value = value.substr(0, length)
    }
 
    return {
        type: TokenType.literal,
        position,
        line: getLine(tokens),
        column: getColumn(tokens),
        length,
        value
    }
}
 
const makeIdentifierToken = (position: number, src: string, tokens: Token[]): Token => {
    let i = position
    let value = src[i++]
    for (; i < src.length; i++) {
        const char = src[i]
        const isEndOfIdentifier = IDENTIFIER_END_EXPRESSION.test(char)
        if (isEndOfIdentifier) {
            break
        }
 
        value = `${value}${char}`
    }
 
    return {
        type: TokenType.identifier,
        position,
        line: getLine(tokens),
        column: getColumn(tokens),
        length: value.length,
        value
    }
}
 
const getPreviousToken = (tokens: Token[]): Token => {
    const hasTokens = tokens.length > 0
    if (!hasTokens) return null
 
    return tokens[tokens.length - 1]
}
 
const getPreviousTwoNonWhitespaceTokens = (tokens: Token[]): [Token?, Token?] => {
    let previousToken: Token = null
    let secondPreviousToken: Token = null
 
    for (let i = tokens.length - 1; i >= 0; i--) {
        const token = tokens[i]
        const isWhiteSpace = token.type === TokenType.whitespace
        if (!isWhiteSpace) {
            const hasPreviousToken = !!previousToken
            if (hasPreviousToken) {
                secondPreviousToken = token
                break
            }
            previousToken = token
        }
    }
 
    return [previousToken, secondPreviousToken]
}
 
const hasAssignmentOperatorOnCurrentLine = (previousTokens: Token[]): boolean => {
    for (let i = previousTokens.length - 1; i >= 0; i--) {
        const { type, value } = previousTokens[i]
 
        const isAssignmentOperator = type === TokenType.operator && value === '='
        if (isAssignmentOperator) {
            return true
        }
 
        const isNewline = type === TokenType.newline
        if (isNewline) {
            return false
        }
    }
 
    return false
}
 
const isLastTokenComment = (previousTokens: Token[]): boolean =>
    previousTokens.length > 0 && previousTokens[previousTokens.length - 1].type === TokenType.comment