Naturalize caption character expressions

caption_metadata_routes.py

@@ -94,6 +94,26 @@ def couple_subject_sentence(
     return f"{subject} are adults"
 
 
+def expression_detail(expression: Any, clean_text: Callable[[Any], str]) -> tuple[str, bool]:
+    text = clean_text(expression)
+    if not text:
+        return "", False
+    has_character_labels = bool(
+        re.search(
+            r"\b(?:Woman|Man) [A-Z] has\b|\bthe (?:woman|man) has\b",
+            text,
+            flags=re.IGNORECASE,
+        )
+    )
+    text = re.sub(
+        r"\b((?:Woman|Man) [A-Z]|the (?:woman|man)) has\b",
+        r"\1 with",
+        text,
+        flags=re.IGNORECASE,
+    )
+    return text, has_character_labels
+
+
 def single_from_row_result(
     request: CaptionMetadataRouteRequest,
     deps: CaptionMetadataRouteDependencies,
@@ -148,7 +168,11 @@ def single_from_row_result(
     if pose:
         parts.append(f"{pronoun(subject)} is {deps.pose_clause(pose)}")
     if expression:
-        parts.append(f"{possessive_pronoun(subject)} expression is {expression}")
+        expression, labeled_expression = expression_detail(expression, deps.clean_text)
+        if labeled_expression:
+            parts.append(f"The expression detail shows {expression}")
+        else:
+            parts.append(f"{possessive_pronoun(subject)} expression is {expression}")
     if scene:
         parts.append(f"The setting is {scene}")
     if deps.detail_allows(detail_level) and camera_scene:
@@ -204,7 +228,11 @@ def couple_from_row_result(
     if deps.detail_allows(detail_level) and camera_scene:
         parts.append(camera_scene)
     if expression:
-        parts.append(f"Their expressions are {expression}")
+        expression, labeled_expression = expression_detail(expression, deps.clean_text)
+        if labeled_expression:
+            parts.append(f"The expression details show {expression}")
+        else:
+            parts.append(f"Their expressions are {expression}")
     if deps.detail_allows(detail_level) and composition:
         parts.append(f"The composition is {composition}")
     if keep_style and style:
@@ -258,7 +286,11 @@ def configured_cast_from_row_result(
     if scene:
         scene_bits.append(f"set in {scene}")
     if expression:
-        scene_bits.append(f"with {expression}")
+        expression, labeled_expression = expression_detail(expression, deps.clean_text)
+        if labeled_expression:
+            scene_bits.append(f"with expression details showing {expression}")
+        else:
+            scene_bits.append(f"with {expression}")
     if composition:
         scene_bits.append(f"framed as {composition}")
     if scene_bits and deps.detail_allows(detail_level):
@@ -299,7 +331,11 @@ def group_or_layout_from_row_result(
     if primary == "layout scene":
         parts = [f"{deps.cap_first(subject)} is arranged as an adults-only designed illustration layout"]
         if expression:
-            parts.append(f"The featured expression is {expression}")
+            expression, labeled_expression = expression_detail(expression, deps.clean_text)
+            if labeled_expression:
+                parts.append(f"The featured expression details show {expression}")
+            else:
+                parts.append(f"The featured expression is {expression}")
     else:
         parts = [f"{deps.cap_first(subject)} includes adults"]
         if age:
@@ -307,7 +343,11 @@ def group_or_layout_from_row_result(
         if item:
             parts.append(f"They wear {item}")
         if expression:
-            parts.append(f"They show {expression}")
+            expression, labeled_expression = expression_detail(expression, deps.clean_text)
+            if labeled_expression:
+                parts.append(f"Their expressions show {expression}")
+            else:
+                parts.append(f"They show {expression}")
     if scene:
         parts.append(f"The setting is {scene}")
     if deps.detail_allows(detail_level) and camera_scene: