feat: added YoloX types (#1284)

This PR adds extra element types so that additional output classes from Yolox may be mapped to those element types. E.g., a Yolox `List-item` class is now mapped to a ListItem element type, whereas before it would have been UncategorizedText.
Unstructured-IO · Sep 3, 2023 · f2af953 · f2af953
1 parent a475b44
commit f2af953
Show file tree

Hide file tree

Showing 2 changed files with 19 additions and 10 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,20 +2,13 @@
 
 ### Enhancements
 
-### Features
-
-* Add Salesforce Connector to be able to pull Account, Case, Campaign, EmailMessage, Lead
-
-### Fixes
-
-## 0.10.12-dev2
-
-### Enhancements
-
 * Removed PIL pin as issue has been resolved upstream
+* YoloX element types added
 
 ### Features
 
+* Add Salesforce Connector to be able to pull Account, Case, Campaign, EmailMessage, Lead
+
 ### Fixes
 
 * Update version-sync to prevent duplicate release versions

diff --git a/unstructured/documents/elements.py b/unstructured/documents/elements.py
@@ -381,6 +381,14 @@ def to_dict(self) -> dict:
         return out
 
 
+class Formula(Element):
+    "An element containing formulas in a document"
+
+    category = "Formula"
+
+    pass
+
+
 class Text(Element):
     """Base element for capturing free text from within document."""
 
@@ -553,4 +561,12 @@ class Footer(Text):
     "Table": Table,
     "Header": Header,
     "Footer": Footer,
+    "Caption": FigureCaption,
+    "Footnote": Footer,
+    "Formula": Formula,
+    "List-item": ListItem,
+    "Page-footer": Footer,
+    "Page-header": Header,  # Title?
+    "Picture": Image,
+    "Section-header": Header,
 }