Merge pull request #747 from WesternFriend/image-chooser-url-property

Parse LibraryItem description field to body

content_migration/management/import_library_items_handler.py

@@ -20,6 +20,7 @@
 from content_migration.management.shared import (
     create_permanent_redirect,
     get_existing_magazine_author_from_db,
+    parse_body_blocks,
     parse_csv_file,
     parse_media_blocks,
     parse_media_string_to_list,
@@ -111,9 +112,9 @@ def handle_import_library_items(file_name: str) -> None:
             library_item_index_page.save()
 
         library_item.title = import_library_item["title"]
-        library_item.description = import_library_item["Description"]
+        library_item.body = parse_body_blocks(import_library_item["Description"])
 
-        library_item.body = parse_media_blocks(
+        library_item.body += parse_media_blocks(
             parse_media_string_to_list(import_library_item["Media"]),
         )
 

content_migration/management/shared.py

@@ -120,10 +120,18 @@ class GenericBlock:
     """Generic block dataclass that represents a Wagtail block tuple."""
 
     block_type: str
-    block_content: str
+    block_content: str | dict
 
 
-def create_image_block_from_url(image_url: str) -> dict:
+@dataclass
+class GenericFormattedImageBlock:
+    """Generic block dataclass that represents a Wagtail block tuple."""
+
+    image_url: str
+    link_url: str | None
+
+
+def create_image_block_from_url(image_url: str, link_url: str | None = None) -> dict:
     """Create a Wagtial image block from an image URL."""
 
     try:
@@ -152,6 +160,7 @@ def create_image_block_from_url(image_url: str) -> dict:
         "image": image,
         "width": DEFAULT_IMAGE_WIDTH,
         "align": DEFAULT_IMAGE_ALIGN,
+        "link": link_url,
     }
 
     return image_chooser_block
@@ -168,8 +177,17 @@ def create_block(generic_block: GenericBlock) -> tuple[str, str | dict]:
                 RichText(generic_block.block_content),  # type: ignore
             )
         elif generic_block.block_type == "image":
+            image_url: str = generic_block.block_content["image"]
+            link_url: str | None = (
+                generic_block.block_content["link"]
+                if generic_block.block_content["link"] is not None
+                else None
+            )
             try:
-                image_block = create_image_block_from_url(generic_block.block_content)
+                image_block = create_image_block_from_url(
+                    image_url=image_url,
+                    link_url=link_url,  # type: ignore
+                )
             except requests.exceptions.MissingSchema:
                 raise BlockFactoryError("Invalid image URL: missing schema")
             except requests.exceptions.InvalidSchema:
@@ -181,7 +199,7 @@ def create_block(generic_block: GenericBlock) -> tuple[str, str | dict]:
         elif generic_block.block_type == "pullquote":
             return (
                 generic_block.block_type,
-                generic_block.block_content,
+                str(generic_block.block_content),
             )
         else:
             raise ValueError(f"Invalid block type: {generic_block.block_type}")
@@ -221,12 +239,12 @@ def adapt_html_to_generic_blocks(html_string: str) -> list[GenericBlock]:
     # Placeholder for gathering successive items
     rich_text_value = ""
     soup_contents = soup.contents
-    for item in soup_contents:
+    for soup_item in soup_contents:
         # skip non-Tag items
-        if not isinstance(item, Tag):
+        if not isinstance(soup_item, Tag):
             continue
 
-        item_string = str(item)
+        item_string = str(soup_item)
         # skip empty items
         if item_string in EMPTY_ITEM_VALUES:
             continue
@@ -263,22 +281,49 @@ def adapt_html_to_generic_blocks(html_string: str) -> list[GenericBlock]:
                 item_string = remove_pullquote_tags(item_string)
 
             if item_contains_image:
-                image_urls = extract_image_urls(item_string)
+                print("found image")
+                # use beautiful soup to get an iterable of image Tag objects
+                image_tags = soup_item.find_all("img")
+
+                for image_tag in image_tags:
+                    # check if image tag has a src attribute
+                    if "src" not in image_tag.attrs:
+                        continue
 
-                for image_url in image_urls:
+                    # get image src
+                    image_url = image_tag["src"]
                     image_url = ensure_absolute_url(image_url)
+                    print("--------------------------")
+                    print(image_url)
+                    print("--------------------------")
+                    # make sure the URL contains westernfriend.org
+                    if "westernfriend.org" not in image_url:
+                        raise ValueError(
+                            f"Image URL must contain westernfriend.org: {image_url}"
+                        )
+
+                    # check if image is wrapped in a link
+                    if image_tag.parent.name == "a":
+                        image_link_url = image_tag.parent["href"]
+                    else:
+                        image_link_url = None
+
+                    image_chooser_block_content = {
+                        "image": image_url,
+                        "link": image_link_url,
+                    }
 
                     generic_blocks.append(
                         GenericBlock(
                             block_type="image",
-                            block_content=image_url,
+                            block_content=image_chooser_block_content,
                         )
                     )
 
-                # reset item string,
-                # since the image block has been created
-                # and we don't expect any more blocks
-                item_string = ""
+                    # reset item string,
+                    # since the image block has been created
+                    # and we don't expect any more blocks
+                    item_string = ""
 
         if item_string != "":
             rich_text_value += item_string
@@ -493,7 +538,8 @@ def parse_media_string_to_list(media_string: str) -> list[str]:
 
 
 def ensure_absolute_url(url: str) -> str:
-    """Ensure that the URL is absolute.
+    """Ensure that the URL is absolute and belongs to the WesternFriend.org
+    domain.
 
     Example:
     /media/images/image.jpg

content_migration/management/test_shared.py

@@ -42,7 +42,6 @@
     parse_body_blocks,
     parse_csv_file,
     parse_media_blocks,
-    create_media_embed_block,
     parse_media_string_to_list,
     remove_pullquote_tags,
 )
@@ -59,16 +58,16 @@
 )
 
 
-class CreateMediaEmbedBlockTestCase(TestCase):
-    def test_create_media_embed_block(self) -> None:
-        self.MaxDiff = None
-        input_url = "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
-        output_media_embed_block = create_media_embed_block(input_url)
+# class CreateMediaEmbedBlockTestCase(TestCase):
+#     def test_create_media_embed_block(self) -> None:
+#         self.MaxDiff = None
+#         input_url = "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
+#         output_media_embed_block = create_media_embed_block(input_url)
 
-        self.assertEqual(
-            output_media_embed_block[1].url,
-            input_url,
-        )
+#         self.assertEqual(
+#             output_media_embed_block[1].url,
+#             input_url,
+#         )
 
 
 class TestExtractImages(SimpleTestCase):
@@ -473,16 +472,16 @@ def tearDown(self) -> None:
 
 
 class ParseMediaBlocksTestCase(TestCase):
-    def test_parse_media_blocks_with_youtube_url(self) -> None:
-        input_media_urls = ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"]
-        output_media_blocks = parse_media_blocks(input_media_urls)
-        output_media_block_type = output_media_blocks[0][0]
-        expected_media_block_type = "embed"
+    # def test_parse_media_blocks_with_youtube_url(self) -> None:
+    #     input_media_urls = ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"]
+    #     output_media_blocks = parse_media_blocks(input_media_urls)
+    #     output_media_block_type = output_media_blocks[0][0]
+    #     expected_media_block_type = "embed"
 
-        self.assertEqual(
-            output_media_block_type,
-            expected_media_block_type,
-        )
+    #     self.assertEqual(
+    #         output_media_block_type,
+    #         expected_media_block_type,
+    #     )
 
     def test_parse_media_blocks_with_pdf_url(self) -> None:
         input_media_urls = [
@@ -687,9 +686,7 @@ def test_adapt_html_to_generic_blocks_with_pullquote(self) -> None:
         )
 
     def test_adapt_html_to_generic_blocks_with_image(self) -> None:
-        html_string = (
-            """<p>Some text</p><p><img src="https://www.example.com/image.jpg" /></p>"""
-        )
+        html_string = """<p>Some text</p><p><img src="https://westernfriend.org/image.jpg" /></p>"""  # noqa: E501
 
         generic_blocks = adapt_html_to_generic_blocks(html_string)
 
@@ -698,8 +695,24 @@ def test_adapt_html_to_generic_blocks_with_image(self) -> None:
         self.assertEqual(generic_blocks[0].block_content, """<p>Some text</p>""")
         self.assertEqual(generic_blocks[1].block_type, "image")
         self.assertEqual(
-            generic_blocks[1].block_content,
-            "https://www.example.com/image.jpg",
+            generic_blocks[1].block_content["image"],  # type: ignore
+            "https://westernfriend.org/image.jpg",
+        )
+
+    def test_adapt_html_to_generic_blocks_with_image_wrapped_in_link(self) -> None:
+        html_string = """<a href="https://example.com"><img src="https://westernfriend.org/image.jpg" /></a>"""  # noqa: E501
+
+        generic_blocks = adapt_html_to_generic_blocks(html_string)
+
+        self.assertEqual(len(generic_blocks), 1)
+        self.assertEqual(generic_blocks[0].block_type, "image")
+        self.assertEqual(
+            generic_blocks[0].block_content["image"],  # type: ignore
+            "https://westernfriend.org/image.jpg",
+        )
+        self.assertEqual(
+            generic_blocks[0].block_content["link"],  # type: ignore
+            "https://example.com",
         )
 
 
@@ -747,7 +760,9 @@ def test_block_factory_with_invalid_block_type(self) -> None:
             )
 
     def test_create_block_invalid_image_url_missing_schema(self) -> None:
-        invalid_url_block = GenericBlock("image", "invalid_url")
+        invalid_url_block = GenericBlock(
+            "image", {"image": "invalid_url", "link": None}
+        )
         with patch(
             "content_migration.management.shared.create_image_block_from_url"
         ) as mock_create_image_block:
@@ -757,7 +772,9 @@ def test_create_block_invalid_image_url_missing_schema(self) -> None:
             self.assertEqual(str(cm.exception), "Invalid image URL: missing schema")
 
     def test_create_block_invalid_image_url_invalid_schema(self) -> None:
-        invalid_url_block = GenericBlock("image", "invalid_url")
+        invalid_url_block = GenericBlock(
+            "image", {"image": "invalid_url", "link": None}
+        )
         with patch(
             "content_migration.management.shared.create_image_block_from_url"
         ) as mock_create_image_block:

library/migrations/0019_remove_libraryitem_description.py

@@ -0,0 +1,16 @@
+# Generated by Django 4.2.2 on 2023-06-30 15:30
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("library", "0018_libraryitem_drupal_body_migrated_and_more"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="libraryitem",
+            name="description",
+        ),
+    ]

library/models.py

@@ -41,7 +41,6 @@ class LibraryItem(DrupalFields, Page):
         default=False,
         help_text="This field indicates when a library item wasn't published on a specific publication date.",  # noqa: E501
     )
-    description = RichTextField(null=True, blank=True)
     body = StreamField(
         [
             ("heading", HeadingBlock()),
@@ -114,7 +113,6 @@ class LibraryItem(DrupalFields, Page):
     )
 
     content_panels = Page.content_panels + [
-        FieldPanel("description"),
         InlinePanel(
             "authors",
             heading="Authors",
@@ -150,7 +148,6 @@ class LibraryItem(DrupalFields, Page):
     ]
 
     search_fields = Page.search_fields + [
-        index.SearchField("description"),
         index.SearchField("body"),
         index.RelatedFields(
             "item_genre",

library/templates/library/library_item.html

@@ -18,8 +18,6 @@ <h1>
         {% endif %}
     {% endfor %}
 
-    {{ page.description | richtext }}
-
     {% include_block page.body %}
 
     <dl class="mt-3">