import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
import { CheerioWebBaseLoader } from 'langchain/document_loaders/web/cheerio'

class Cheerio_DocumentLoaders implements INode {
    label: string
    name: string
    description: string
    type: string
    icon: string
    category: string
    baseClasses: string[]
    inputs: INodeParams[]

    constructor() {
        this.label = 'Cheerio Web Scraper'
        this.name = 'cheerioWebScraper'
        this.type = 'Document'
        this.icon = 'cheerio.svg'
        this.category = 'Document Loaders'
        this.description = `Load data from webpages`
        this.baseClasses = [this.type]
        this.inputs = [
            {
                label: 'URL',
                name: 'url',
                type: 'string'
            },
            {
                label: 'Text Splitter',
                name: 'textSplitter',
                type: 'TextSplitter',
                optional: true
            },
            {
                label: 'Metadata',
                name: 'metadata',
                type: 'json',
                optional: true,
                additionalParams: true
            }
        ]
    }

    async init(nodeData: INodeData): Promise<any> {
        const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
        const metadata = nodeData.inputs?.metadata

        let url = nodeData.inputs?.url as string

        var urlPattern = new RegExp(
            '^(https?:\\/\\/)?' + // validate protocol
                '((([a-z\\d]([a-z\\d-]*[a-z\\d])*)\\.)+[a-z]{2,}|' + // validate domain name
                '((\\d{1,3}\\.){3}\\d{1,3}))' + // validate OR ip (v4) address
                '(\\:\\d+)?(\\/[-a-z\\d%_.~+]*)*' + // validate port and path
                '(\\?[;&a-z\\d%_.~+=-]*)?' + // validate query string
                '(\\#[-a-z\\d_]*)?$',
            'i'
        ) // validate fragment locator

        const loader = new CheerioWebBaseLoader(urlPattern.test(url.trim()) ? url.trim() : '')
        let docs = []

        if (textSplitter) {
            docs = await loader.loadAndSplit(textSplitter)
        } else {
            docs = await loader.load()
        }

        if (metadata) {
            const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata)
            let finaldocs = []
            for (const doc of docs) {
                const newdoc = {
                    ...doc,
                    metadata: {
                        ...doc.metadata,
                        ...parsedMetadata
                    }
                }
                finaldocs.push(newdoc)
            }
            return finaldocs
        }

        return docs
    }
}

module.exports = { nodeClass: Cheerio_DocumentLoaders }