bug fix + remove unused code

papermerge/core/models/page.py

@@ -134,10 +134,6 @@ def update_text_field(self, stream: io.StringIO):
 
         Returns text read from IO stream
         """
-        logger.debug(
-            'update_text_field:'
-            f'len(page.stripped_text)=={len(self.stripped_text)}'
-        )
         self.text = stream.read()
         self.save()
 

papermerge/core/page_ops.py

@@ -185,7 +185,6 @@ def copy_text_field(
         # list of old_version page numbers
         page_numbers=page_numbers
     )
-
     # updates page.text fields and document_version.text field
     dst.update_text_field(streams)
 
@@ -251,7 +250,7 @@ def move_pages_mix(
         src_old_version,
         src_new_version,
         moved_pages_count
-    ] = copy_pages(source_page_ids)
+    ] = copy_without_pages(source_page_ids)
 
     moved_pages = Page.objects.filter(pk__in=source_page_ids)
     moved_page_ids = [page.id for page in moved_pages]
@@ -325,7 +324,7 @@ def move_pages_replace(
         src_old_version,
         src_new_version,
         moved_pages_count
-    ] = copy_pages(source_page_ids)
+    ] = copy_without_pages(source_page_ids)
 
     moved_pages = Page.objects.filter(pk__in=source_page_ids)
     moved_page_ids = [page.id for page in moved_pages]
@@ -384,7 +383,7 @@ def extract_pages(
         old_doc_ver,
         new_doc_ver,
         moved_pages_count
-    ] = copy_pages(source_page_ids)
+    ] = copy_without_pages(source_page_ids)
 
     if strategy == ExtractStrategy.ONE_PAGE_PER_DOC:
         new_docs = extract_to_single_paged_docs(
@@ -496,20 +495,18 @@ def extract_to_multi_paged_doc(
     return new_doc
 
 
-def copy_pages(
+def copy_without_pages(
     page_ids: List[uuid.UUID]
 ) -> [PyDocVer, PyDocVer, int]:
-    """Copy pages from src doc version to dst doc version
+    """Copy all pages  WHICH ARE NOT in `page_ids` list from src to dst
 
     All pages are assumed to be from same source document version.
-    Source document version is the doc ver of the first page
-    (again, all pages are assumed to be part of same doc ver).
-    The destination doc ver is created. All pages referenced
-    by IDs are copied into newly created destination doc version.
-
-    The OCR data/page folder is copied along (reused).
+    Source is the document version of the first page.
+    Destination will be created as new document version.
+    Destination will have all source pages WHICH ARE NOT in the `page_ids` list.
 
-    Also sends INDEX UPDATE notification
+    The OCR data/page folder reused.
+    Also sends INDEX UPDATE notification.
     """
     moved_pages = Page.objects.filter(pk__in=page_ids)
     moved_page_ids = [page.id for page in moved_pages]
@@ -532,7 +529,7 @@ def copy_pages(
     src_keys = [  # IDs of the pages which were not removed
         page.id
         for page in src_old_version.pages.order_by('number')
-        if not (page.id in moved_page_ids)
+        if not (page.id in moved_page_ids)  # Notice the negation
     ]
 
     dst_values = [
@@ -548,7 +545,11 @@ def copy_pages(
     copy_text_field(
         src=src_old_version,
         dst=src_new_version,
-        page_numbers=[p.number for p in moved_pages]
+        page_numbers=[
+            p.number
+            for p in src_old_version.pages.all()
+            if not (p.id in moved_page_ids)  # Notice the negation
+        ]
     )
 
     notify_index_update(

tests/core/test_page_ops.py

@@ -4,8 +4,8 @@
 import pytest
 
 from papermerge.core.models import Document
-from papermerge.core.page_ops import (apply_pages_op, copy_pages,
-                                      copy_text_field, extract_pages,
+from papermerge.core.page_ops import (apply_pages_op, copy_text_field,
+                                      copy_without_pages, extract_pages,
                                       move_pages)
 from papermerge.core.pathlib import abs_page_path
 from papermerge.core.schemas.pages import ExtractStrategy, MoveStrategy
@@ -636,12 +636,12 @@ def test_extract_two_pages_to_folder_each_page_in_separate_doc(_):
 
 
 @patch('papermerge.core.signals.ocr_document_task')
-def test_copy_pages(_):
+def test_copy_without_pages(_):
     """Scenario
 
-         copy page 1
+         copy without page 1
     ver X  ->  ver X + 1
-     S1         S1
+     S1         S2
      S2
     """
     user = user_recipe.make()
@@ -653,20 +653,22 @@ def test_copy_pages(_):
         user=user,
         include_ocr_data=True
     )
-    doc_ver = src.versions.last()
-    orig_first_page = src.versions.last().pages.all()[0]
-    orig_second_page = src.versions.last().pages.all()[1]
+    orig_doc_ver = src.versions.last()
+    orig_first_page = orig_doc_ver.pages.all()[0]
+    orig_second_page = orig_doc_ver.pages.all()[1]
     orig_first_page.text = "cat"
     orig_second_page.text = "dog"
     orig_first_page.save()
     orig_second_page.save()
-    pages_to_copy = [doc_ver.pages.first().id]
+    # page containing "cat" / first page is left behind
+    pages_to_leave_behind = [orig_doc_ver.pages.first().id]
 
-    [old_ver, new_ver, page_count] = copy_pages(pages_to_copy)
+    [_, new_ver, _] = copy_without_pages(pages_to_leave_behind)
 
     assert new_ver.pages.count() == 1
-    assert ['cat'] == [p.text for p in new_ver.pages.all()]
-    assert new_ver.text == 'cat'
+    # new version contains only 'dog'
+    assert ['dog'] == [p.text for p in new_ver.pages.all()]
+    assert new_ver.text == 'dog'
 
 
 class PageDir: