package digest

import (
	"fmt"
	"regexp"
	"strconv"
	"strings"
)

// pageMarker matches a page header line like "--- page 7 ---"; the number is group 1.
var pageMarker = regexp.MustCompile(`^--- page (\d+) ---$`)

// SplitPages splits text into chunks of at most maxTok tokens (EstTokens) on line
// boundaries, like Split, but page-aware. The text is expected to carry "--- page N ---"
// markers (as pdfdoc.Full produces). A marker line sets the current page; a chunk that
// starts after the first marker but not on a marker line is prefixed with
// "--- page N (cont.) ---\n\n" for the page its first line belongs to, so every chunk
// names the page it cites. Text with no marker lines yields exactly Split's result.
func SplitPages(text string, maxTok int) []string {
	if maxTok <= 0 {
		maxTok = ChunkTokens
	}
	lines := strings.Split(text, "\n")
	var chunks []string
	var buf strings.Builder
	var firstLine string
	var chunkPage int
	hasLines, startedAfterMarker, markerSeen := false, false, false
	currentPage := 0

	flush := func() {
		s := strings.TrimSpace(buf.String())
		if s == "" {
			buf.Reset()
			hasLines = false
			return
		}
		if pageMarker.MatchString(firstLine) || !startedAfterMarker {
			chunks = append(chunks, s)
		} else {
			chunks = append(chunks, fmt.Sprintf("--- page %d (cont.) ---\n\n", chunkPage)+s)
		}
		buf.Reset()
		hasLines = false
	}

	for _, line := range lines {
		if m := pageMarker.FindStringSubmatch(line); m != nil {
			if n, err := strconv.Atoi(m[1]); err == nil {
				currentPage = n
				markerSeen = true
			}
		}
		next := line + "\n"
		if hasLines {
			est := EstTokens(buf.String() + next)
			if startedAfterMarker {
				est += EstTokens(fmt.Sprintf("--- page %d (cont.) ---\n\n", chunkPage))
			}
			if est > maxTok {
				flush()
			}
		}
		if !hasLines {
			firstLine = line
			chunkPage = currentPage
			startedAfterMarker = markerSeen
			hasLines = true
		}
		buf.WriteString(next)
	}
	flush()
	return chunks
}