Initial commit

backend/internal/services/modlist_parser.go

@@ -0,0 +1,116 @@
+package services
+
+import (
+	"fmt"
+	"io"
+	"net/url"
+	"path"
+	"strings"
+
+	"arma3-web-server/internal/models"
+	"golang.org/x/net/html"
+)
+
+func ParseModlistHTML(r io.Reader) (string, []models.ModEntry, error) {
+	doc, err := html.Parse(r)
+	if err != nil {
+		return "", nil, fmt.Errorf("parse html: %w", err)
+	}
+
+	var mods []models.ModEntry
+	seen := map[string]bool{}
+
+	var walk func(*html.Node)
+	walk = func(n *html.Node) {
+		if n.Type == html.ElementNode && n.Data == "tr" {
+			if name, id, ok := extractModRow(n); ok && id != "" {
+				if !seen[id] {
+					seen[id] = true
+					mods = append(mods, models.ModEntry{
+						ID:      id,
+						Name:    cleanModName(name),
+						Enabled: true,
+					})
+				}
+			}
+		}
+		for c := n.FirstChild; c != nil; c = c.NextSibling {
+			walk(c)
+		}
+	}
+	walk(doc)
+
+	if mods == nil {
+		mods = []models.ModEntry{}
+	}
+	return "", mods, nil
+}
+
+func extractModRow(tr *html.Node) (name, id string, ok bool) {
+	var cells []*html.Node
+	for c := tr.FirstChild; c != nil; c = c.NextSibling {
+		if c.Type == html.ElementNode && c.Data == "td" {
+			cells = append(cells, c)
+		}
+	}
+	if len(cells) < 3 {
+		return "", "", false
+	}
+
+	name = extractText(cells[0])
+
+	for c := cells[2].FirstChild; c != nil; c = c.NextSibling {
+		if c.Type == html.ElementNode && c.Data == "a" {
+			id = extractWorkshopID(c)
+			break
+		}
+	}
+
+	if name == "" {
+		return "", "", false
+	}
+	return name, id, true
+}
+
+func extractText(n *html.Node) string {
+	var b strings.Builder
+	var walk func(*html.Node)
+	walk = func(n *html.Node) {
+		if n.Type == html.TextNode {
+			b.WriteString(n.Data)
+		}
+		for c := n.FirstChild; c != nil; c = c.NextSibling {
+			walk(c)
+		}
+	}
+	walk(n)
+	return strings.TrimSpace(b.String())
+}
+
+func extractWorkshopID(a *html.Node) string {
+	for _, attr := range a.Attr {
+		if attr.Key == "href" {
+			u, err := url.Parse(attr.Val)
+			if err != nil {
+				continue
+			}
+			return u.Query().Get("id")
+		}
+	}
+	return ""
+}
+
+func cleanModName(name string) string {
+	name = strings.TrimSpace(name)
+	name = strings.ReplaceAll(name, "/", "_")
+	name = strings.ReplaceAll(name, "\\", "_")
+	return name
+}
+
+func FileNameToModlistName(filename string) string {
+	ext := path.Ext(filename)
+	name := strings.TrimSuffix(filename, ext)
+	name = strings.ReplaceAll(name, "_", " ")
+	name = strings.ReplaceAll(name, "-", " ")
+	return name
+}