Skip to content
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.

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

add recursive option for folder-loader #1688

Merged
merged 3 commits into from
Feb 6, 2024
Merged
Changes from all commits
Commits
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
95 changes: 53 additions & 42 deletions packages/components/nodes/documentloaders/Folder/Folder.ts
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,12 @@ class Folder_DocumentLoaders implements INode {
type: 'string',
placeholder: ''
},
{
label: 'Recursive',
name: 'recursive',
type: 'boolean',
additionalParams: false
},
{
label: 'Text Splitter',
name: 'textSplitter',
Expand All @@ -54,49 +60,54 @@ class Folder_DocumentLoaders implements INode {
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
const folderPath = nodeData.inputs?.folderPath as string
const metadata = nodeData.inputs?.metadata
const recursive = nodeData.inputs?.recursive as boolean

const loader = new DirectoryLoader(folderPath, {
'.json': (path) => new JSONLoader(path),
'.txt': (path) => new TextLoader(path),
'.csv': (path) => new CSVLoader(path),
'.docx': (path) => new DocxLoader(path),
// @ts-ignore
'.pdf': (path) => new PDFLoader(path, { pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js') }),
'.aspx': (path) => new TextLoader(path),
'.asp': (path) => new TextLoader(path),
'.cpp': (path) => new TextLoader(path), // C++
'.c': (path) => new TextLoader(path),
'.cs': (path) => new TextLoader(path),
'.css': (path) => new TextLoader(path),
'.go': (path) => new TextLoader(path), // Go
'.h': (path) => new TextLoader(path), // C++ Header files
'.kt': (path) => new TextLoader(path), // Kotlin
'.java': (path) => new TextLoader(path), // Java
'.js': (path) => new TextLoader(path), // JavaScript
'.less': (path) => new TextLoader(path), // Less files
'.ts': (path) => new TextLoader(path), // TypeScript
'.php': (path) => new TextLoader(path), // PHP
'.proto': (path) => new TextLoader(path), // Protocol Buffers
'.python': (path) => new TextLoader(path), // Python
'.py': (path) => new TextLoader(path), // Python
'.rst': (path) => new TextLoader(path), // reStructuredText
'.ruby': (path) => new TextLoader(path), // Ruby
'.rb': (path) => new TextLoader(path), // Ruby
'.rs': (path) => new TextLoader(path), // Rust
'.scala': (path) => new TextLoader(path), // Scala
'.sc': (path) => new TextLoader(path), // Scala
'.scss': (path) => new TextLoader(path), // Sass
'.sol': (path) => new TextLoader(path), // Solidity
'.sql': (path) => new TextLoader(path), //SQL
'.swift': (path) => new TextLoader(path), // Swift
'.markdown': (path) => new TextLoader(path), // Markdown
'.md': (path) => new TextLoader(path), // Markdown
'.tex': (path) => new TextLoader(path), // LaTeX
'.ltx': (path) => new TextLoader(path), // LaTeX
'.html': (path) => new TextLoader(path), // HTML
'.vb': (path) => new TextLoader(path), // Visual Basic
'.xml': (path) => new TextLoader(path) // XML
})
const loader = new DirectoryLoader(
folderPath,
{
'.json': (path) => new JSONLoader(path),
'.txt': (path) => new TextLoader(path),
'.csv': (path) => new CSVLoader(path),
'.docx': (path) => new DocxLoader(path),
// @ts-ignore
'.pdf': (path) => new PDFLoader(path, { pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js') }),
'.aspx': (path) => new TextLoader(path),
'.asp': (path) => new TextLoader(path),
'.cpp': (path) => new TextLoader(path), // C++
'.c': (path) => new TextLoader(path),
'.cs': (path) => new TextLoader(path),
'.css': (path) => new TextLoader(path),
'.go': (path) => new TextLoader(path), // Go
'.h': (path) => new TextLoader(path), // C++ Header files
'.kt': (path) => new TextLoader(path), // Kotlin
'.java': (path) => new TextLoader(path), // Java
'.js': (path) => new TextLoader(path), // JavaScript
'.less': (path) => new TextLoader(path), // Less files
'.ts': (path) => new TextLoader(path), // TypeScript
'.php': (path) => new TextLoader(path), // PHP
'.proto': (path) => new TextLoader(path), // Protocol Buffers
'.python': (path) => new TextLoader(path), // Python
'.py': (path) => new TextLoader(path), // Python
'.rst': (path) => new TextLoader(path), // reStructuredText
'.ruby': (path) => new TextLoader(path), // Ruby
'.rb': (path) => new TextLoader(path), // Ruby
'.rs': (path) => new TextLoader(path), // Rust
'.scala': (path) => new TextLoader(path), // Scala
'.sc': (path) => new TextLoader(path), // Scala
'.scss': (path) => new TextLoader(path), // Sass
'.sol': (path) => new TextLoader(path), // Solidity
'.sql': (path) => new TextLoader(path), //SQL
'.swift': (path) => new TextLoader(path), // Swift
'.markdown': (path) => new TextLoader(path), // Markdown
'.md': (path) => new TextLoader(path), // Markdown
'.tex': (path) => new TextLoader(path), // LaTeX
'.ltx': (path) => new TextLoader(path), // LaTeX
'.html': (path) => new TextLoader(path), // HTML
'.vb': (path) => new TextLoader(path), // Visual Basic
'.xml': (path) => new TextLoader(path) // XML
},
recursive
)
let docs = []

if (textSplitter) {
Expand Down
Loading