fix: Discord connector when a channel is not found. (#1480)

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.10.17-dev16
+## 0.10.17-dev17
 
 ### Enhancements
 
@@ -29,6 +29,7 @@ should be generated, however the Formula class inherits from Element instead of
 allowing the document to be loaded. Fix: Change parent class for Formula to Text. Importance: Crucial to be able to load documents that contain formulas.
 * **Fixes Sphinx errors.** Fixes errors when running Sphinx `make html` and installs library to suppress warnings.
 * **Fixes a metadata backwards compatibility error** Problem: When calling `partition_via_api`, the hosted api may return an element schema that's newer than the current `unstructured`. In this case, metadata fields were added which did not exist in the local `ElementMetadata` dataclass, and `__init__()` threw an error. Fix: remove nonexistent fields before instantiating in `ElementMetadata.from_json()`. Importance: Crucial to avoid breaking changes when adding fields.
+* **Fixes issue with Discord connector when a channel returns `None`** Problem: Getting the `jump_url` from a nonexistent Discord `channel` fails. Fix: property `jump_url` is now retrieved within the same context as the messages from the channel. Importance: Avoids cascading issues when the connector fails to fetch information about a Discord channel.
 
 
 ## 0.10.16

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.10.17-dev16"  # pragma: no cover
+__version__ = "0.10.17-dev17"  # pragma: no cover

unstructured/ingest/connector/discord.py

@@ -77,6 +77,7 @@ def _get_messages(self):
         from discord.ext import commands
 
         messages: t.List[discord.Message] = []
+        jumpurl: t.List[str] = []
         intents = discord.Intents.default()
         intents.message_content = True
         bot = commands.Bot(command_prefix=">", intents=intents)
@@ -88,15 +89,17 @@ async def on_ready():
                 if self.days:
                     after_date = dt.datetime.utcnow() - dt.timedelta(days=self.days)
                 channel = bot.get_channel(int(self.channel))
+                jumpurl.append(channel.jump_url)  # type: ignore
                 async for msg in channel.history(after=after_date):  # type: ignore
                     messages.append(msg)
                 await bot.close()
             except Exception:
                 logger.error("Error fetching messages")
                 await bot.close()
+                raise
 
         bot.run(self.token)
-        jump_url = bot.get_channel(int(self.channel)).jump_url  # type: ignore
+        jump_url = None if len(jumpurl) < 1 else jumpurl[0]
         return messages, jump_url
 
     def update_source_metadata(self, **kwargs):