refactor: rename operator split to chunk

Author: ChenZiHong-Gavin

graphgen/bases/base_splitter.py

@@ -4,7 +4,7 @@
 from typing import Callable, Iterable, List, Literal, Optional, Union
 
 from graphgen.bases.datatypes import Chunk
-from graphgen.utils import logger
+from graphgen.utils.log import logger
 
 
 class BaseSplitter(ABC):
@@ -33,7 +33,7 @@ def split_text(self, text: str) -> List[str]:
         """
         Split the input text into smaller chunks.
 
-        :param text: The input text to be split.
+        :param text: The input text to be chunk.
         :return: A list of text chunks.
         """
 
@@ -111,7 +111,7 @@ def _merge_splits(self, splits: Iterable[str], separator: str) -> List[str]:
     def _split_text_with_regex(
         text: str, separator: str, keep_separator: Union[bool, Literal["start", "end"]]
     ) -> List[str]:
-        # Now that we have the separator, split the text
+        # Now that we have the separator, chunk the text
         if separator:
             if keep_separator:
                 # The parentheses in the pattern keep the delimiters in the result.

graphgen/models/splitter/character_splitter.py

@@ -17,7 +17,7 @@ def __init__(
 
     def split_text(self, text: str) -> List[str]:
         """Split incoming text and return chunks."""
-        # First we naively split the large input into a bunch of smaller ones.
+        # First we naively chunk the large input into a bunch of smaller ones.
         separator = (
             self._separator if self._is_separator_regex else re.escape(self._separator)
         )

graphgen/models/splitter/markdown_splitter.py

@@ -6,12 +6,12 @@
 
 
 class MarkdownTextRefSplitter(RecursiveCharacterSplitter):
-    """Attempts to split the text along Markdown-formatted headings."""
+    """Attempts to chunk the text along Markdown-formatted headings."""
 
     def __init__(self, **kwargs: Any) -> None:
         """Initialize a MarkdownTextRefSplitter."""
         separators = [
-            # First, try to split along Markdown headings (starting with level 2)
+            # First, try to chunk along Markdown headings (starting with level 2)
             "\n#{1,6} ",
             # Note the alternative syntax for headings (below) is not handled here
             # Heading level 2

graphgen/models/splitter/recursive_character_splitter.py

@@ -7,7 +7,7 @@
 class RecursiveCharacterSplitter(BaseSplitter):
     """Splitting text by recursively look at characters.
 
-    Recursively tries to split by different characters to find one that works.
+    Recursively tries to chunk by different characters to find one that works.
     """
 
     def __init__(
@@ -88,7 +88,7 @@ def __init__(
     def _split_text_with_regex_from_end(
         self, text: str, separator: str, keep_separator: bool
     ) -> List[str]:
-        # Now that we have the separator, split the text
+        # Now that we have the separator, chunk the text
         if separator:
             if keep_separator:
                 # The parentheses in the pattern keep the delimiters in the result.