Use Field(default_factory=list) for CU response collections

Replace Optional[...] = None and mutable [] defaults on Page.spans,
Page.words, DocumentContent.paragraphs, and ResultData.warnings with
Field(default_factory=list). Removes a possible TypeError when the
confidence evaluator iterates page.words and aligns with the repo's
Pydantic convention. Tests updated to assert empty-list defaults.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: Harsh-Microsoft

src/ContentProcessor/src/libs/azure_helper/model/content_understanding.py

@@ -9,7 +9,7 @@
 
 from typing import List, Optional
 
-from pydantic import BaseModel, ValidationInfo, field_validator
+from pydantic import BaseModel, Field, ValidationInfo, field_validator
 
 
 class Span(BaseModel):
@@ -103,8 +103,8 @@ class Page(BaseModel):
     angle: Optional[float] = None
     width: float
     height: float
-    spans: Optional[List[Span]] = None
-    words: Optional[List[Word]] = None
+    spans: List[Span] = Field(default_factory=list)
+    words: List[Word] = Field(default_factory=list)
     lines: Optional[List[Line]] = []
     paragraphs: Optional[List[Paragraph]] = []
 
@@ -116,7 +116,7 @@ class DocumentContent(BaseModel):
     endPageNumber: int
     unit: str
     pages: List[Page]
-    paragraphs: Optional[List[Paragraph]] = None
+    paragraphs: List[Paragraph] = Field(default_factory=list)
 
 
 class Warning(BaseModel):
@@ -139,7 +139,7 @@ class ResultData(BaseModel):
     analyzerId: str
     apiVersion: str
     createdAt: str
-    warnings: List[Warning] = []
+    warnings: List[Warning] = Field(default_factory=list)
     contents: List[DocumentContent]
 
 

src/ContentProcessor/tests/unit/azure_helper/test_content_understanding_model.py

@@ -216,7 +216,7 @@ def test_page_can_be_constructed_without_angle_spans_words(self):
         )
         assert page.pageNumber == 1
         assert page.angle is None
-        assert page.spans is None
-        assert page.words is None
+        assert page.spans == []
+        assert page.words == []
         assert page.lines == []
         assert page.paragraphs == []

src/tests/ContentProcessor/azure_helper/test_content_understanding_model.py

@@ -216,7 +216,7 @@ def test_page_can_be_constructed_without_angle_spans_words(self):
         )
         assert page.pageNumber == 1
         assert page.angle is None
-        assert page.spans is None
-        assert page.words is None
+        assert page.spans == []
+        assert page.words == []
         assert page.lines == []
         assert page.paragraphs == []