feat: slim base views to 4, add ocr redo view

paperforge/worker/base_views.py

@@ -39,7 +39,7 @@ PAPERFORGE_VIEW_PREFIX = "# PAPERFORGE_VIEW: "
 
 
 def build_base_views(domain: str) -> list[dict]:
-    """Build the 8-view list for a domain Base file.
+    """Build the 4-view list for a domain Base file.
 
     Uses workflow gate columns (has_pdf, do_ocr, analyze, ocr_status)
     matching the master version's Base views.  See REQUIREMENTS.md
@@ -49,7 +49,7 @@ def build_base_views(domain: str) -> list[dict]:
         domain: The domain name (e.g., "骨科").
 
     Returns:
-        List of 8 view dicts, each with keys: name, order, filter, sort.
+        List of 4 view dicts, each with keys: name, order, filter, sort.
     """
     return [
         {
@@ -71,34 +71,11 @@ def build_base_views(domain: str) -> list[dict]:
             ],
             "filter": None,
         },
-        {
-            "name": "推荐分析",
-            "order": [
-                "year",
-                "title",
-                "first_author",
-                "journal",
-                "impact_factor",
-                "has_pdf",
-                "do_ocr",
-                "analyze",
-                "ocr_status",
-                "deep_reading_status",
-                "pdf_path",
-                "fulltext_md_path",
-            ],
-            "filter": "analyze = true AND has_pdf = true",
-        },
         {
             "name": "待 OCR",
             "order": ["year", "first_author", "title", "has_pdf", "do_ocr", "ocr_status", "pdf_path"],
             "filter": "do_ocr = true AND ocr_status = 'pending'",
         },
-        {
-            "name": "OCR 完成",
-            "order": ["year", "first_author", "title", "has_pdf", "do_ocr", "ocr_status", "pdf_path"],
-            "filter": "ocr_status = 'done'",
-        },
         {
             "name": "待深度阅读",
             "order": [
@@ -115,51 +92,9 @@ def build_base_views(domain: str) -> list[dict]:
             "filter": "analyze = true AND ocr_status = 'done' AND deep_reading_status = 'pending'",
         },
         {
-            "name": "深度阅读完成",
-            "order": [
-                "year",
-                "first_author",
-                "title",
-                "has_pdf",
-                "do_ocr",
-                "analyze",
-                "ocr_status",
-                "deep_reading_status",
-                "pdf_path",
-            ],
-            "filter": "deep_reading_status = 'done'",
-        },
-        {
-            "name": "正式卡片",
-            "order": [
-                "title",
-                "year",
-                "first_author",
-                "journal",
-                "impact_factor",
-                "has_pdf",
-                "deep_reading_status",
-                "pdf_path",
-            ],
-            "filter": "deep_reading_status = 'done'",
-        },
-        {
-            "name": "全记录",
-            "order": [
-                "title",
-                "year",
-                "first_author",
-                "journal",
-                "impact_factor",
-                "has_pdf",
-                "do_ocr",
-                "analyze",
-                "ocr_status",
-                "deep_reading_status",
-                "pdf_path",
-                "fulltext_md_path",
-            ],
-            "filter": None,
+            "name": "重做OCR",
+            "order": ["year", "first_author", "title", "ocr_redo", "ocr_status"],
+            "filter": "ocr_status = 'done'",
         },
     ]
 
@@ -267,7 +202,7 @@ def merge_base_views(existing_content: str | None, new_views: list[dict], folder
     """Incrementally merge standard PaperForge views into an existing .base file.
 
     Strategy:
-    - PaperForge generates exactly 8 views with known names (STANDARD_VIEW_NAMES).
+    - PaperForge generates exactly 4 views with known names.
     - Any OTHER views in the existing file are user-defined and MUST be preserved.
     - Each PaperForge view is preceded by a PAPERFORGE_VIEW_PREFIX comment marker.
     - On refresh: replace ALL PaperForge views (identified by prefix) with fresh ones.
@@ -276,7 +211,7 @@ def merge_base_views(existing_content: str | None, new_views: list[dict], folder
 
     Args:
         existing_content: Raw text of existing .base file (or None/empty for fresh generation).
-        new_views: List of 8 view dicts from build_base_views().
+        new_views: List of 4 view dicts from build_base_views().
         folder_filter: Vault-relative folder path for file.inFolder() (used for fresh generation).
 
     Returns:

tests/test_base_preservation.py

@@ -43,7 +43,7 @@ class TestIncrementalMerge:
 
         ensure_base_views(self.vault, self.paths, self.config, force=False)
         content = domain_base.read_text(encoding="utf-8")
-        assert content.count("type: table") == 8
+        assert content.count("type: table") == 4
 
         user_custom = (
             content
@@ -61,9 +61,9 @@ class TestIncrementalMerge:
         refreshed = domain_base.read_text(encoding="utf-8")
 
         assert "My Custom Dashboard" in refreshed, "User custom view was lost on incremental refresh"
-        assert refreshed.count("type: table") == 9
+        assert refreshed.count("type: table") == 5
         assert "控制面板" in refreshed
-        assert "OCR 完成" in refreshed
+        assert "重做OCR" in refreshed
 
     def test_standard_paperforge_views_are_updated_on_refresh(self):
         """Standard views are replaced with fresh content on each refresh."""
@@ -71,12 +71,12 @@ class TestIncrementalMerge:
         ensure_base_views(self.vault, self.paths, self.config, force=False)
 
         content1 = domain_base.read_text(encoding="utf-8")
-        assert content1.count(PAPERFORGE_VIEW_PREFIX) == 8
+        assert content1.count(PAPERFORGE_VIEW_PREFIX) == 4
 
         ensure_base_views(self.vault, self.paths, self.config, force=False)
         content2 = domain_base.read_text(encoding="utf-8")
 
-        assert content2.count("type: table") == 8
+        assert content2.count("type: table") == 4
         assert "${LIBRARY_RECORDS}" not in content2
 
     def test_force_flag_does_full_regeneration(self):
@@ -101,8 +101,8 @@ class TestIncrementalMerge:
         refreshed = domain_base.read_text(encoding="utf-8")
 
         assert "My Custom View" not in refreshed, "force=True should have replaced all views"
-        assert refreshed.count("type: table") == 8
-        assert refreshed.count(PAPERFORGE_VIEW_PREFIX) == 8
+        assert refreshed.count("type: table") == 4
+        assert refreshed.count(PAPERFORGE_VIEW_PREFIX) == 4
 
     def test_user_modified_filter_on_standard_view_is_preserved(self):
         """User changes filter on a standard PF view — on refresh it is PRESERVED.
@@ -140,7 +140,7 @@ class TestIncrementalMerge:
 
         assert domain_base.exists()
         content = domain_base.read_text(encoding="utf-8")
-        assert content.count("type: table") == 8
+        assert content.count("type: table") == 4
         assert PAPERFORGE_VIEW_PREFIX in content
 
 
@@ -174,7 +174,7 @@ class TestLiteratureHubBase:
         hub_base = bases / "Literature Hub.base"
         assert hub_base.exists(), "Literature Hub.base not created"
         content = hub_base.read_text(encoding="utf-8")
-        assert content.count("type: table") == 8, f"Expected 8 views, got {content.count('type: table')}"
+        assert content.count("type: table") == 4, f"Expected 4 views, got {content.count('type: table')}"
         assert PAPERFORGE_VIEW_PREFIX in content
         assert "${LIBRARY_RECORDS}" not in content, "Placeholder should be substituted"
 
@@ -237,8 +237,7 @@ views:
         result = merge_base_views(existing, views, folder_filter="Resources/Literature/骨科")
 
         assert "My Custom View" in result, "User view was lost"
-        assert "推荐分析" in result
-        assert result.count("type: table") >= 8
+        assert result.count("type: table") >= 6
 
     def test_merge_base_views_first_run_generates_fresh(self):
         """merge_base_views with no existing content generates fresh YAML."""
@@ -285,9 +284,9 @@ views:
       - file.name
       - title
       - year
-# PAPERFORGE_VIEW: OCR 完成
+# PAPERFORGE_VIEW: 重做OCR
   - type: table
-    name: "OCR 完成"
+    name: "重做OCR"
     widths:
       year: 55
       title: 380

tests/test_base_views.py

@@ -1,4 +1,4 @@
-"""Tests for the 8-view Base generation system (Phase 39: workflow-gate views)."""
+"""Tests for the 4-view Base generation system (Phase 44: slim base views)."""
 
 from paperforge.worker.base_views import (
     build_base_views,
@@ -7,15 +7,22 @@ from paperforge.worker.base_views import (
 
 
 class TestBuildBaseViews:
-    def test_returns_exactly_8_views(self):
+    def test_build_base_views_has_4_standard_views(self):
         views = build_base_views("骨科")
-        assert len(views) == 8
+        names = {v["name"] for v in views}
 
-    def test_all_view_names_present(self):
+        assert names == {"控制面板", "待 OCR", "待深度阅读", "重做OCR"}
+
+    def test_ocr_redo_view_has_correct_columns(self):
         views = build_base_views("骨科")
-        names = [v["name"] for v in views]
-        expected = ["控制面板", "推荐分析", "待 OCR", "OCR 完成", "待深度阅读", "深度阅读完成", "正式卡片", "全记录"]
-        assert names == expected
+        redo = next(v for v in views if v["name"] == "重做OCR")
+
+        assert redo["order"] == ["year", "first_author", "title", "ocr_redo", "ocr_status"]
+        assert redo["filter"] == "ocr_status = 'done'"
+
+    def test_returns_exactly_4_views(self):
+        views = build_base_views("骨科")
+        assert len(views) == 4
 
     def test_each_view_has_required_keys(self):
         views = build_base_views("骨科")
@@ -37,11 +44,6 @@ class TestBuildBaseViews:
         assert "do_ocr = true" in pending["filter"]
         assert "ocr_status = 'pending'" in pending["filter"]
 
-    def test_ocr_done_filter(self):
-        views = build_base_views("骨科")
-        done = next(v for v in views if v["name"] == "OCR 完成")
-        assert "ocr_status = 'done'" in done["filter"]
-
     def test_deep_reading_pending_filter(self):
         views = build_base_views("骨科")
         pending = next(v for v in views if v["name"] == "待深度阅读")
@@ -49,44 +51,16 @@ class TestBuildBaseViews:
         assert "ocr_status = 'done'" in pending["filter"]
         assert "deep_reading_status = 'pending'" in pending["filter"]
 
-    def test_build_base_views_includes_workflow_flags(self):
+    def test_removed_views_not_present(self):
+        removed = {"推荐分析", "OCR 完成", "深度阅读完成", "正式卡片", "全记录"}
         views = build_base_views("骨科")
-        for v in views:
-            order_set = set(v["order"])
-            assert "has_pdf" in order_set, f"View '{v['name']}' missing has_pdf"
-            if v["name"] not in ("正式卡片",):
-                assert "do_ocr" in order_set, f"View '{v['name']}' missing do_ocr"
-            if v["name"] not in ("正式卡片", "待 OCR", "OCR 完成"):
-                assert "analyze" in order_set, f"View '{v['name']}' missing analyze"
-
-    def test_build_base_views_removes_ghost_columns(self):
-        views = build_base_views("骨科")
-        ghost_fields = {"lifecycle", "maturity_level", "next_step"}
-        for v in views:
-            order_set = set(v["order"])
-            assert ghost_fields.isdisjoint(order_set), f"View '{v['name']}' still contains ghost lifecycle columns"
-
-    def test_build_base_views_filters_use_workflow_gates(self):
-        views = build_base_views("骨科")
-        for v in views:
-            if v["filter"] is not None:
-                assert "lifecycle" not in v["filter"], f"View '{v['name']}' filter uses lifecycle instead of workflow gates"
+        names = {v["name"] for v in views}
+        assert removed.isdisjoint(names), f"Removed views still present: {removed & names}"
 
     def test_build_base_views_has_no_sort(self):
         views = build_base_views("骨科")
         for v in views:
-            assert "sort" not in v, f"View '{v['name']}' should not have sort key (lifecycle removed from frontmatter)"
-
-    def test_properties_yaml_updated(self):
-        from paperforge.worker.base_views import merge_base_views
-        fresh = merge_base_views(None, build_base_views("骨科"), folder_filter="Resources/Literature/骨科")
-        assert "lifecycle:" not in fresh
-        assert "maturity_level:" not in fresh
-        assert "next_step:" not in fresh
-        assert "has_pdf:" in fresh
-        assert "do_ocr:" in fresh
-        assert "analyze:" in fresh
-        assert "ocr_status:" in fresh
+            assert "sort" not in v, f"View '{v['name']}' should not have sort key"
 
 
 class TestSubstituteConfigPlaceholders: