package parser

import (
	"archive/zip"
	"encoding/xml"
	"fmt"
	"io"
)

// WordParser extracts text from .docx files
type WordParser struct{}

// SupportedExtensions returns extensions this parser handles
func (p *WordParser) SupportedExtensions() []string {
	return []string{".docx"}
}

type wDocument struct {
	Body wBody `xml:"body"`
}

type wBody struct {
	P []wP `xml:"p"`
}

type wP struct {
	R []wR `xml:"r"`
}

type wR struct {
	T []string `xml:"t"`
}

// ParseToMarkdown extracts text from the word document and returns it as Markdown-like text
func (p *WordParser) ParseToMarkdown(path string) (string, error) {
	r, err := zip.OpenReader(path)
	if err != nil {
		return "", fmt.Errorf("failed to open docx as zip: %w", err)
	}
	defer r.Close()

	var docFile *zip.File
	for _, f := range r.File {
		if f.Name == "word/document.xml" {
			docFile = f
			break
		}
	}
	if docFile == nil {
		return "", fmt.Errorf("invalid docx file: word/document.xml not found")
	}

	rc, err := docFile.Open()
	if err != nil {
		return "", err
	}
	defer rc.Close()

	data, err := io.ReadAll(rc)
	if err != nil {
		return "", err
	}

	var doc wDocument
	if err := xml.Unmarshal(data, &doc); err != nil {
		return "", err
	}

	var md string
	for _, paragraph := range doc.Body.P {
		var pText string
		for _, run := range paragraph.R {
			for _, text := range run.T {
				pText += text
			}
		}
		if pText != "" {
			md += pText + "\n\n"
		}
	}

	return md, nil
}