Skip to content

refactor #61

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nirgit merged 2 commits into from
Aug 1, 2025
Merged

refactor #61

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
adc92de
refactor
nirgit Jul 18, 2025
e6c36f5
refactor
nirgit Aug 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
127 changes: 70 additions & 57 deletions src/transpiler.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,15 @@ const AttribNode = (name, value) => {
})
}

// Frame factory for stack items in parseXML
function Frame(node, scopingElement) {
return {
node,
scopingElement,
children: node.value.children
}
}

const parseXML = (lexer) => {
/*
How does the grammar look?
Expand All @@ -48,89 +57,93 @@ const parseXML = (lexer) => {
| AttributeName: String
| AttributeValue: String
*/
const rootNode = Node(ROOT, {
children: parseExpr(lexer, Token(ROOT, 'ROOT'))
})
return rootNode
}

const parseExpr = (lexer, scopingElement) => {
const children = []
const rootNode = Node(ROOT, { children: [] })
const stack = [
Frame(rootNode, Token(ROOT, 'ROOT'))
]
let currentFrame = stack[stack.length - 1]
while (lexer.hasNext()) {
const lexem = lexer.next()
switch (lexem.type) {
case TOKEN_TYPE.OPEN_BRACKET: {
const elementLexem = lexer.next()
const [elementAttributes, currentToken] =
parseElementAttributes(lexer)
let elementChildren = []
if (currentToken.type !== TOKEN_TYPE.CLOSE_ELEMENT) {
elementChildren = parseExpr(lexer, elementLexem)
}
if (
elementChildren &&
elementChildren.length > 0 &&
elementChildren[0].type === TOKEN_TYPE.CONTENT
) {
elementChildren = reduceChildrenElements(elementChildren)
}
children.push(
ElementNode(
elementLexem.value,
elementAttributes,
elementChildren
)
)
case TOKEN_TYPE.OPEN_BRACKET:
handleOpenBracket(lexer, stack)
currentFrame = stack[stack.length - 1]
break
}
case TOKEN_TYPE.CLOSE_ELEMENT: {
if (lexem.value === scopingElement.value) return children
case TOKEN_TYPE.CLOSE_ELEMENT:
handleCloseElement(lexem, stack)
currentFrame = stack[stack.length - 1]
break
}
case TOKEN_TYPE.CONTENT: {
children.push(ContentNode(lexem.value))
case TOKEN_TYPE.CONTENT:
handleContent(lexem, currentFrame)
break
}
case TOKEN_TYPE.EOF: {
return children
}
default: {
case TOKEN_TYPE.EOF:
break
default:
throw new Error(
`Unknown Lexem type: ${lexem.type} "${lexem.value}, scoping element: ${scopingElement.value}"`
`Unknown Lexem type: ${lexem.type} "${lexem.value}, scoping element: ${currentFrame.scopingElement.value}"`
)
}
}
}
return children
return rootNode
}

const parseElementAttributes = (lexer) => {
const attribs = []
function handleOpenBracket(lexer, stack) {
const currentFrame = stack[stack.length - 1]
const elementLexem = lexer.next()
let attribs = []
let currentToken = lexer.peek()
if (
!lexer.hasNext() ||
(currentToken && currentToken.type === TOKEN_TYPE.CLOSE_BRACKET) ||
(currentToken && currentToken.type === TOKEN_TYPE.CLOSE_ELEMENT)
) {
return [attribs, currentToken]
const areAttributesExpected = lexer.hasNext() &&
(currentToken && currentToken.type !== TOKEN_TYPE.CLOSE_BRACKET) &&
(currentToken && currentToken.type !== TOKEN_TYPE.CLOSE_ELEMENT)
if (areAttributesExpected) {
[attribs, currentToken] = collectAttributes(lexer)
}
currentToken = lexer.next()
const elementNode = ElementNode(elementLexem.value, attribs, [])
currentFrame.children.push(elementNode)
if (currentToken && currentToken.type === TOKEN_TYPE.CLOSE_ELEMENT) {
return
}
stack.push(Frame(elementNode, elementLexem))
}

function collectAttributes(lexer) {
const attribs = []
let currentToken = lexer.next()
while (
lexer.hasNext() &&
currentToken &&
currentToken.type !== TOKEN_TYPE.CLOSE_BRACKET &&
currentToken.type !== TOKEN_TYPE.CLOSE_ELEMENT
) {
const attribName = currentToken
lexer.next() //assignment token
lexer.next() // assignment token
const attribValue = lexer.next()
const attributeNode = AttribNode(attribName.value, attribValue.value)
attribs.push(attributeNode)
attribs.push(AttribNode(attribName.value, attribValue.value))
currentToken = lexer.next()
}
return [attribs, currentToken]
}

function handleCloseElement(lexem, stack) {
const currentFrame = stack[stack.length - 1]
if (lexem.value === currentFrame.scopingElement.value) {
let children = currentFrame.children
if (
children &&
children.length > 0 &&
children[0].type === TOKEN_TYPE.CONTENT
) {
children = reduceChildrenElements(children)
currentFrame.node.value.children = children
}
stack.pop()
}
}

function handleContent(lexem, currentFrame) {
currentFrame.children.push(ContentNode(lexem.value))
}

function reduceChildrenElements(elementChildren) {
let reduced = [],
buffer = ''
Expand All @@ -154,7 +167,7 @@ function reduceChildrenElements(elementChildren) {

function transpile(xmlAsString, astConverter) {
const lexer = createLexer(xmlAsString)
const ast = parseXML(lexer, xmlAsString)
const ast = parseXML(lexer)
if (astConverter) {
return astConverter.convert(ast)
}
Expand Down