import { omit } from 'lodash'
import { IDocument, INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
import { Document } from '@langchain/core/documents'
import { handleEscapeCharacters } from '../../../src'

class PlainText_DocumentLoaders implements INode {
    label: string
    name: string
    version: number
    description: string
    type: string
    icon: string
    category: string
    baseClasses: string[]
    inputs: INodeParams[]
    outputs: INodeOutputsValue[]

    constructor() {
        this.label = 'Plain Text'
        this.name = 'plainText'
        this.version = 2.0
        this.type = 'Document'
        this.icon = 'plaintext.svg'
        this.category = 'Document Loaders'
        this.description = `Load data from plain text`
        this.baseClasses = [this.type]
        this.inputs = [
            {
                label: 'Text',
                name: 'text',
                type: 'string',
                rows: 4,
                placeholder:
                    'Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua...'
            },
            {
                label: 'Text Splitter',
                name: 'textSplitter',
                type: 'TextSplitter',
                optional: true
            },
            {
                label: 'Additional Metadata',
                name: 'metadata',
                type: 'json',
                description: 'Additional metadata to be added to the extracted documents',
                optional: true,
                additionalParams: true
            },
            {
                label: 'Omit Metadata Keys',
                name: 'omitMetadataKeys',
                type: 'string',
                rows: 4,
                description:
                    'Each document loader comes with a default set of metadata keys that are extracted from the document. You can use this field to omit some of the default metadata keys. The value should be a list of keys, seperated by comma',
                placeholder: 'key1, key2, key3.nestedKey1',
                optional: true,
                additionalParams: true
            }
        ]
        this.outputs = [
            {
                label: 'Document',
                name: 'document',
                description: 'Array of document objects containing metadata and pageContent',
                baseClasses: [...this.baseClasses, 'json']
            },
            {
                label: 'Text',
                name: 'text',
                description: 'Concatenated string from pageContent of documents',
                baseClasses: ['string', 'json']
            }
        ]
    }

    async init(nodeData: INodeData): Promise<any> {
        const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
        const text = nodeData.inputs?.text as string
        const metadata = nodeData.inputs?.metadata
        const output = nodeData.outputs?.output as string
        const _omitMetadataKeys = nodeData.inputs?.omitMetadataKeys as string

        let omitMetadataKeys: string[] = []
        if (_omitMetadataKeys) {
            omitMetadataKeys = _omitMetadataKeys.split(',').map((key) => key.trim())
        }

        let docs: IDocument[] = []

        if (textSplitter) {
            docs.push(...(await textSplitter.createDocuments([text])))
        } else {
            docs.push(
                new Document({
                    pageContent: text
                })
            )
        }

        if (metadata) {
            const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata)
            docs = docs.map((doc) => ({
                ...doc,
                metadata: omit(
                    {
                        ...doc.metadata,
                        ...parsedMetadata
                    },
                    omitMetadataKeys
                )
            }))
        } else {
            docs = docs.map((doc) => ({
                ...doc,
                metadata: omit(
                    {
                        ...doc.metadata
                    },
                    omitMetadataKeys
                )
            }))
        }

        if (output === 'document') {
            return docs
        } else {
            let finaltext = ''
            for (const doc of docs) {
                finaltext += `${doc.pageContent}\n`
            }
            return handleEscapeCharacters(finaltext, false)
        }
    }
}

module.exports = { nodeClass: PlainText_DocumentLoaders }