Fix callouts with FileIcons (#504) [full CI check] (#506)

## NOTE: In order to fully test this user's contribution I had to merge
the changes to a non-main branch first. This PR is only for testing the
full CI flow + bumping version and changelog.

Fix: #503

User:
**I have tested this chang on my own fork of `unstructured-ingest` that
I use for processing our customer data. It includes this fix and many
other bug fixes that I would like to merge in!**

---------

Co-authored-by: Teddy Wahle <[email protected]>

Author: mpolomdeepsense

CHANGELOG.md

@@ -1,3 +1,7 @@
+## 1.0.26
+
+* **Fix Notion connector error with FileIcons**
+
 ## 1.0.25
 
 * **Fix Notion user text and html getters**

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "1.0.25"  # pragma: no cover
+__version__ = "1.0.26"  # pragma: no cover

unstructured_ingest/processes/connectors/notion/types/blocks/callout.py

@@ -51,22 +51,57 @@ def get_html(self) -> Optional[HtmlTag]:
             return None
 
 
+@dataclass
+class FileIconContent(FromJSONMixin):
+    url: str
+    expiry_time: Optional[str] = None  # Add expiry_time if needed
+
+    @classmethod
+    def from_dict(cls, data: dict):
+        # Only include expiry_time if it exists in the dictionary
+        # Notion API might not always include it
+        init_data = {"url": data.get("url")}
+        if "expiry_time" in data:
+            init_data["expiry_time"] = data.get("expiry_time")
+        return cls(**init_data)
+
+
+@dataclass
+class FileIcon(FromJSONMixin, GetHTMLMixin):
+    file: FileIconContent
+    type: str = "file"
+
+    @classmethod
+    def from_dict(cls, data: dict):
+        return cls(file=FileIconContent.from_dict(data=data.pop("file")), **data)
+
+    def get_html(self) -> Optional[HtmlTag]:
+        # Render the file URL, similar to how ExternalIcon is handled
+        if self.file:
+            # Could potentially render an <img> tag, but sticking to URL for consistency
+            return A([Href(self.file.url)], [f"[File Icon: {self.file.url}]"])
+        else:
+            return None
+
+
 class Icon(FromJSONMixin):
     @classmethod
-    def from_dict(cls, data: dict) -> Union[EmojiIcon, ExternalIcon]:
+    def from_dict(cls, data: dict) -> Union[EmojiIcon, ExternalIcon, FileIcon]:
         t = data.get("type")
         if t == "emoji":
             return EmojiIcon.from_dict(data)
         elif t == "external":
             return ExternalIcon.from_dict(data)
+        elif t == "file":
+            return FileIcon.from_dict(data)
         else:
             raise ValueError(f"Unexpected icon type: {t} ({data})")
 
 
 @dataclass
 class Callout(BlockBase):
     color: str
-    icon: Optional[Union[EmojiIcon, ExternalIcon]] = None
+    icon: Optional[Union[EmojiIcon, ExternalIcon, FileIcon]] = None
     rich_text: List[RichText] = field(default_factory=list)
 
     @staticmethod
@@ -76,9 +111,11 @@ def can_have_children() -> bool:
     @classmethod
     def from_dict(cls, data: dict):
         rich_text = data.pop("rich_text", [])
+        icon_data = data.pop("icon", None)
+        icon = Icon.from_dict(icon_data) if icon_data else None
         return cls(
             color=data["color"],
-            icon=Icon.from_dict(data.pop("icon")),
+            icon=icon,
             rich_text=[RichText.from_dict(rt) for rt in rich_text],
         )