package ingestion

import (
	"fmt"
	"io"
	"os"
	"path/filepath"
	"strings"

	"github.com/pdfcpu/pdfcpu/pkg/api"
	"github.com/pdfcpu/pdfcpu/pkg/pdfcpu/model"
)

func ParsePDF(path string) (string, error) {
	ctx, err := api.ReadContextFile(path)
	if err != nil {
		return "", err
	}

	tmpDir, err := os.MkdirTemp("", "pdf-extract-*")
	if err != nil {
		return "", err
	}
	defer os.RemoveAll(tmpDir)

	conf := model.NewDefaultConfiguration()
	if err := api.ExtractContentFile(path, tmpDir, nil, conf); err != nil {
		return "", err
	}

	var buf strings.Builder
	entries, err := os.ReadDir(tmpDir)
	if err != nil {
		return "", err
	}

	for _, entry := range entries {
		if entry.IsDir() {
			continue
		}
		content, err := os.ReadFile(filepath.Join(tmpDir, entry.Name()))
		if err != nil {
			return "", fmt.Errorf("read extracted content %s: %w", entry.Name(), err)
		}
		buf.WriteString(string(content))
		buf.WriteString("\n")
	}

	if buf.Len() == 0 {
		content, err := extractPageText(ctx)
		if err == nil {
			buf.WriteString(content)
		}
	}

	return buf.String(), nil
}

func extractPageText(ctx *model.Context) (string, error) {
	var buf strings.Builder
	for i := 1; i <= ctx.PageCount; i++ {
		r, err := api.ExtractPage(ctx, i)
		if err != nil {
			continue
		}
		data, err := io.ReadAll(r)
		if err != nil {
			continue
		}
		buf.Write(data)
		buf.WriteString("\n")
	}
	return buf.String(), nil
}