refactor: split monolithic phase tests into per-module test files

- rename test_admin_phase4.py -> test_admin.py, test_search.py -> test_searcher.py
- split test_phase5.py into test_cleaner, test_embedder, test_image_extractor, test_pages
- move schema tests from test_summarizer.py into dedicated test_schemas.py
- add sample_papers_range and sample_papers_with_summary fixtures in conftest
- update .gitignore to exclude all of data/

tests/test_image_extractor.py

@@ -0,0 +1,88 @@
+"""LaTeX 图片提取测试 — 从 .tex 源码中提取图片文件。"""
+
+from __future__ import annotations
+
+import pytest
+
+
+# ═══════════════════════════════════════════════════════════════════════
+# Image Extraction
+# ═══════════════════════════════════════════════════════════════════════
+
+
+class TestImageExtraction:
+    """LaTeX 图片提取测试。"""
+
+    @pytest.mark.asyncio
+    async def test_extract_images_from_source_no_dir(self, monkeypatch, tmp_path):
+        """源码目录不存在时返回 0。"""
+        monkeypatch.setattr("app.services.pdf_downloader.tmp_dir", lambda x: tmp_path / "tmp" / x)
+        monkeypatch.setattr("app.services.pdf_downloader.paper_dir", lambda x: tmp_path / "papers" / x)
+        from app.services.image_extractor import extract_images_from_source
+        result = await extract_images_from_source("2401.99999")
+        assert result == 0
+
+    @pytest.mark.asyncio
+    async def test_extract_images_from_tex(self, monkeypatch, tmp_path):
+        """从 .tex 文件中提取图片。"""
+        from app.services.image_extractor import extract_images_from_source
+
+        tmp_source = tmp_path / "tmp" / "2401.00001" / "source"
+        tmp_source.mkdir(parents=True)
+
+        images_dir = tmp_source / "figs"
+        images_dir.mkdir()
+        (images_dir / "figure1.png").write_bytes(b"\x89PNG\r\n")
+        (images_dir / "figure2.jpg").write_bytes(b"\xff\xd8\xff\xe0")
+
+        # 创建 .tex 文件
+        tex_content = r"""
+\documentclass{article}
+\begin{document}
+\begin{figure}
+  \includegraphics[width=0.8\textwidth]{figs/figure1.png}
+  \includegraphics{figs/figure2.jpg}
+  \includegraphics[angle=90]{figs/nonexistent.pdf}
+\end{figure}
+\end{document}
+"""
+        (tmp_source / "main.tex").write_text(tex_content)
+
+        papers_dir = tmp_path / "papers" / "2401.00001"
+        monkeypatch.setattr("app.services.image_extractor.tmp_dir", lambda x: tmp_path / "tmp" / x)
+        monkeypatch.setattr("app.services.image_extractor.paper_dir", lambda x: tmp_path / "papers" / x)
+
+        # Mock download_source_zip to avoid real network call (source dir already exists)
+        async def _noop_download(*args, **kwargs):
+            pass
+
+        monkeypatch.setattr("app.services.image_extractor.download_source_zip", _noop_download)
+
+        result = await extract_images_from_source("2401.00001")
+
+        assert result == 2
+        dest_images = papers_dir / "images"
+        assert dest_images.exists()
+        assert (dest_images / "figure1.png").exists()
+        assert (dest_images / "figure2.jpg").exists()
+
+    @pytest.mark.asyncio
+    async def test_extract_images_empty_tex(self, monkeypatch, tmp_path):
+        """.tex 文件无图片时返回 0。"""
+        from app.services.image_extractor import extract_images_from_source
+
+        tmp_source = tmp_path / "tmp" / "2401.00002" / "source"
+        tmp_source.mkdir(parents=True)
+        (tmp_source / "main.tex").write_text(r"\documentclass{article}\begin{document}Hello\end{document}")
+
+        monkeypatch.setattr("app.services.image_extractor.tmp_dir", lambda x: tmp_path / "tmp" / x)
+        monkeypatch.setattr("app.services.image_extractor.paper_dir", lambda x: tmp_path / "papers" / x)
+
+        # Mock download_source_zip to avoid real network call
+        async def _noop_download(*args, **kwargs):
+            pass
+
+        monkeypatch.setattr("app.services.image_extractor.download_source_zip", _noop_download)
+
+        result = await extract_images_from_source("2401.00002")
+        assert result == 0