Updates
Browse files
app.py
CHANGED
|
@@ -59,14 +59,28 @@ def deduplicate_embeddings(
|
|
| 59 |
|
| 60 |
def display_word_differences(x: str, y: str) -> str:
|
| 61 |
"""
|
| 62 |
-
Display the word-level differences between two texts
|
|
|
|
| 63 |
|
| 64 |
:param x: First text.
|
| 65 |
:param y: Second text.
|
| 66 |
-
:return: A string showing word-level differences.
|
| 67 |
"""
|
| 68 |
diff = ndiff(x.split(), y.split())
|
| 69 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
def load_dataset_texts(dataset_name: str, dataset_split: str, text_column: str) -> list[str]:
|
| 72 |
"""
|
|
|
|
| 59 |
|
| 60 |
def display_word_differences(x: str, y: str) -> str:
|
| 61 |
"""
|
| 62 |
+
Display the word-level differences between two texts, formatted to avoid
|
| 63 |
+
misinterpretation of Markdown syntax.
|
| 64 |
|
| 65 |
:param x: First text.
|
| 66 |
:param y: Second text.
|
| 67 |
+
:return: A string showing word-level differences, wrapped in a code block.
|
| 68 |
"""
|
| 69 |
diff = ndiff(x.split(), y.split())
|
| 70 |
+
# Wrap differences in a code block to prevent interpretation as Markdown
|
| 71 |
+
formatted_diff = "\n".join(word for word in diff if word.startswith(("+", "-")))
|
| 72 |
+
return f"```\n{formatted_diff}\n```"
|
| 73 |
+
|
| 74 |
+
# def display_word_differences(x: str, y: str) -> str:
|
| 75 |
+
# """
|
| 76 |
+
# Display the word-level differences between two texts.
|
| 77 |
+
|
| 78 |
+
# :param x: First text.
|
| 79 |
+
# :param y: Second text.
|
| 80 |
+
# :return: A string showing word-level differences.
|
| 81 |
+
# """
|
| 82 |
+
# diff = ndiff(x.split(), y.split())
|
| 83 |
+
# return " ".join(word for word in diff if word.startswith(("+", "-")))
|
| 84 |
|
| 85 |
def load_dataset_texts(dataset_name: str, dataset_split: str, text_column: str) -> list[str]:
|
| 86 |
"""
|