初始化

2026-08-25 17:59:42 +08:00
commit 4b7380dd9b
408 changed files with 327400 additions and 0 deletions
@@ -0,0 +1,95 @@
+package service
+
+import (
+	"archive/zip"
+	"bytes"
+	"strings"
+	"testing"
+)
+
+func TestParseDramaSourceRejectsDisguisedAndExecutableContent(t *testing.T) {
+	cases := []struct {
+		name     string
+		filename string
+		data     []byte
+		raw      string
+	}{
+		{name: "pdf renamed txt", filename: "novel.txt", data: []byte("%PDF-1.7\ncontent")},
+		{name: "zip renamed txt", filename: "novel.txt", data: []byte{'P', 'K', 3, 4, 1, 2, 3}},
+		{name: "html after long prefix", filename: "novel.txt", data: []byte(strings.Repeat("正文", 3000) + "<script>alert(1)</script>")},
+		{name: "script pasted", raw: "小说正文\njavascript:alert(1)"},
+		{name: "binary pasted", raw: "正文\x00内容"},
+	}
+	for _, test := range cases {
+		t.Run(test.name, func(t *testing.T) {
+			if _, _, err := parseDramaSource(test.filename, test.data, test.raw); err == nil {
+				t.Fatal("expected unsafe import to be rejected")
+			}
+		})
+	}
+}
+
+func TestExtractDOCXReadsParagraphsAndValidatesWordPackage(t *testing.T) {
+	valid := makeTestDOCX(t, `<?xml version="1.0"?><Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/></Types>`, nil)
+	text, err := extractDOCX(valid)
+	if err != nil {
+		t.Fatalf("extractDOCX returned error: %v", err)
+	}
+	if !strings.Contains(text, "第一章 开始") || !strings.Contains(text, "这是正文") {
+		t.Fatalf("unexpected extracted text: %q", text)
+	}
+
+	fake := makeTestDOCX(t, `<?xml version="1.0"?><Types/>`, nil)
+	if _, err := extractDOCX(fake); err == nil {
+		t.Fatal("expected ZIP with fake DOCX structure to be rejected")
+	}
+
+	macro := makeTestDOCX(t, `<?xml version="1.0"?><Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/></Types>`, map[string]string{"word/vbaProject.bin": "macro"})
+	if _, err := extractDOCX(macro); err == nil {
+		t.Fatal("expected macro-enabled package to be rejected")
+	}
+}
+
+func TestSplitDramaChaptersPreservesOriginalText(t *testing.T) {
+	source := "作品说明\n\n第一章 初见\n正文一\n\n第二章 重逢\n正文二"
+	chapters := splitDramaChapters(source)
+	if len(chapters) != 2 {
+		t.Fatalf("expected 2 chapters, got %d", len(chapters))
+	}
+	joined := strings.TrimSpace(chapters[0].Content + "\n\n" + chapters[1].Content)
+	if joined != source {
+		t.Fatalf("chapter splitting lost or duplicated text:\nwant: %q\n got: %q", source, joined)
+	}
+	if chapters[0].Title != "第一章 初见" || chapters[1].Title != "第二章 重逢" {
+		t.Fatalf("unexpected chapter titles: %#v", chapters)
+	}
+	if chapters := splitDramaChapters("没有章节标题的完整正文"); chapters != nil {
+		t.Fatalf("text without chapter titles must require single-episode confirmation: %#v", chapters)
+	}
+}
+
+func makeTestDOCX(t *testing.T, contentTypes string, extras map[string]string) []byte {
+	t.Helper()
+	var buffer bytes.Buffer
+	writer := zip.NewWriter(&buffer)
+	files := map[string]string{
+		"[Content_Types].xml": contentTypes,
+		"word/document.xml":   `<?xml version="1.0"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body><w:p><w:r><w:t>第一章 开始</w:t></w:r></w:p><w:p><w:r><w:t>这是正文</w:t></w:r></w:p></w:body></w:document>`,
+	}
+	for name, content := range extras {
+		files[name] = content
+	}
+	for name, content := range files {
+		entry, err := writer.Create(name)
+		if err != nil {
+			t.Fatal(err)
+		}
+		if _, err = entry.Write([]byte(content)); err != nil {
+			t.Fatal(err)
+		}
+	}
+	if err := writer.Close(); err != nil {
+		t.Fatal(err)
+	}
+	return buffer.Bytes()
+}