refactor: Rename SplitContentComponent to SplitTextComponent and update related variables and descriptions

src/backend/base/langflow/components/experimental/SplitText.py

@@ -7,18 +7,18 @@ from langflow.template import Output
 from langflow.utils.util import unescape_string
 
 
-class SplitContentComponent(Component):
+class SplitTextComponent(Component):
-    display_name: str = "Split Content"
+    display_name: str = "Split Text"
-    description: str = "Split textual content into chunks based on specified criteria."
+    description: str = "Split text into chunks based on specified criteria."
     icon = "split"
 
     inputs = [
         HandleInput(name="data", display_name="Data", info="Data with text to split.", input_types=["Data"]),
         TextInput(
-            name="content_key",
+            name="text_key",
-            display_name="Content Key",
+            display_name="Text Key",
             info="The key to access the text content in the Data object.",
-            value="content",
+            value="text",
         ),
         TextInput(
             name="separator",
@@ -27,25 +27,18 @@ class SplitContentComponent(Component):
             value="\n",
             advanced=True,
         ),
-        IntInput(
-            name="chunk_size",
-            display_name="Chunk Size",
-            info="The target length (in number of characters) of each chunk.",
-            value=0,
-            advanced=True,
-        ),
         IntInput(
             name="min_chunk_size",
             display_name="Minimum Chunk Size",
             info="The minimum size of chunks. Smaller chunks will be merged.",
-            value=0,
+            value=10,
             advanced=True,
         ),
         IntInput(
             name="max_chunk_size",
             display_name="Maximum Chunk Size",
             info="The maximum size of chunks. Larger chunks will be split.",
-            value=0,
+            value=200,
             advanced=True,
         ),
     ]
@@ -56,33 +49,39 @@ class SplitContentComponent(Component):
 
     def split_text(self) -> List[Data]:
         data = self.data if isinstance(self.data, list) else [self.data]
-        content_key = self.content_key
+        text_key = self.text_key
         separator = unescape_string(self.separator)
-        chunk_size = self.chunk_size
         min_chunk_size = self.min_chunk_size
         max_chunk_size = self.max_chunk_size
         results = []
+
+        if not separator:
+            raise ValueError("Separator cannot be empty.")
+        if max_chunk_size < 10:
+            raise ValueError("Maximum chunk size cannot be less than 10 characters.")
+        if min_chunk_size < 10:
+            raise ValueError("Minimum chunk size cannot be less than 10 characters.")
+        if max_chunk_size < min_chunk_size:
+            raise ValueError("Maximum chunk size cannot be less than minimum chunk size.")
+
         buffer = ""
 
         for row in data:
-            content = row.data.get(content_key, "")
+            text = row.data.get(text_key, "")
-            if chunk_size > 0:
+            chunks = text.split(separator)
-                chunks = [content[i : i + chunk_size] for i in range(0, len(content), chunk_size)]
-            else:
-                chunks = content.split(separator)
 
             for chunk in chunks:
                 buffer += chunk
                 while len(buffer) >= max_chunk_size:
-                    results.append(Data(data={"parent": content, "chunk": buffer[:max_chunk_size]}))
+                    results.append(Data(data={"parent": text, "chunk": buffer[:max_chunk_size]}))
                     buffer = buffer[max_chunk_size:]
                 if len(buffer) >= min_chunk_size:
-                    results.append(Data(data={"parent": content, "chunk": buffer}))
+                    results.append(Data(data={"parent": text, "chunk": buffer}))
                     buffer = ""
 
-        # Handle any remaining content that may not meet the min_chunk_size requirement
+        # Handle any remaining text that may not meet the min_chunk_size requirement
         if buffer:
-            results.append(Data(data={"parent": content, "chunk": buffer}))
+            results.append(Data(data={"parent": text, "chunk": buffer}))
 
         self.status = results
         return results