interface ChunkInput {
  text: string
  pageNumber: number
}

export interface DocumentChunkData {
  content: string
  chunkIndex: number
  pageNumber: number
  startChar: number
  endChar: number
  metadata?: string
}

export class DocumentChunkingService {
  private readonly CHUNK_SIZE = 800
  private readonly OVERLAP = 200

  chunk(pages: ChunkInput[]): DocumentChunkData[] {
    const chunks: DocumentChunkData[] = []
    let globalIndex = 0
    let previousTail = ''

    for (const page of pages) {
      const text = page.text.trim()
      if (!text) continue

      const sections = this.splitSections(text)
      let buffer = previousTail
      let bufferStart = 0

      for (const section of sections) {
        if (buffer.length + section.length > this.CHUNK_SIZE && buffer.length > 0) {
          chunks.push({
            content: buffer.trim(),
            chunkIndex: globalIndex++,
            pageNumber: page.pageNumber,
            startChar: bufferStart,
            endChar: bufferStart + buffer.length,
          })
          previousTail = buffer.slice(-this.OVERLAP)
          buffer = previousTail + '\n' + section
          bufferStart += buffer.length - section.length - previousTail.length
        } else {
          buffer += (buffer ? '\n\n' : '') + section
        }
      }

      if (buffer.trim()) {
        chunks.push({
          content: buffer.trim(),
          chunkIndex: globalIndex++,
          pageNumber: page.pageNumber,
          startChar: bufferStart,
          endChar: bufferStart + buffer.length,
        })
        previousTail = buffer.slice(-this.OVERLAP)
      }
    }

    return chunks
  }

  private splitSections(text: string): string[] {
    const lines = text.split('\n')
    const sections: string[] = []
    let current = ''

    for (const line of lines) {
      const isHeading = /^(#{1,6}\s|[A-Z][A-Z\s]{5,}$)/.test(line.trim())
      if (isHeading && current.trim()) {
        sections.push(current.trim())
        current = line
      } else {
        current += (current ? '\n' : '') + line
      }
    }
    if (current.trim()) sections.push(current.trim())
    return sections
  }
}

export const documentChunkingService = new DocumentChunkingService()