Import project files

docling/app/tests/test_word2markdown_inline_images.py

@@ -0,0 +1,51 @@
+import unittest
+from pathlib import Path
+import base64
+import tempfile
+import sys
+
+# ensure 'app' package is importable
+try:
+    root = Path(__file__).resolve().parents[2]
+    p = str(root)
+    if p not in sys.path:
+        sys.path.insert(0, p)
+except Exception:
+    pass
+
+from docx import Document
+
+from app.services.word2markdown import convert_any
+
+
+def _tiny_png_bytes() -> bytes:
+    return base64.b64decode(
+        b"iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR4nGNgYAAAAAMAASsJTYQAAAAASUVORK5CYII="
+    )
+
+
+class InlineImagesTest(unittest.TestCase):
+    def test_paragraph_image_order(self):
+        tmp = Path(tempfile.mkdtemp(prefix="w2m_inline_test_"))
+        img = tmp / "tiny.png"
+        img.write_bytes(_tiny_png_bytes())
+
+        docx = tmp / "sample.docx"
+        doc = Document()
+        doc.add_paragraph("前文A")
+        doc.add_picture(str(img))  # 图片单独段落
+        doc.add_paragraph("后文B")
+        doc.save(str(docx))
+
+        enc, md = convert_any(docx)
+        self.assertEqual(enc, "utf-8")
+        a_pos = md.find("前文A")
+        img_pos = md.find("![Image](data:")
+        b_pos = md.find("后文B")
+        # 顺序应为 A -> 图片 -> B
+        self.assertTrue(a_pos != -1 and img_pos != -1 and b_pos != -1)
+        self.assertTrue(a_pos < img_pos < b_pos)
+
+
+if __name__ == "__main__":
+    unittest.main()