fix: Runtime error when Pandas Series is not always of string type (#1024)

Signed-off-by: fan <fansluck@qq.com>
2025-02-20 22:41:41 +08:00 · 2025-02-20 22:41:41 +08:00 · 6796f0a132
commit 6796f0a132
parent dfcc30dddb
1 changed files with 3 additions and 1 deletions
--- a/docling/models/tesseract_ocr_cli_model.py
+++ b/docling/models/tesseract_ocr_cli_model.py
@ -114,7 +114,9 @@ class TesseractOcrCliModel(BaseOcrModel):
        # _log.info("df: ", df.head())

        # Filter rows that contain actual text (ignore header or empty rows)
-        df_filtered = df[df["text"].notnull() & (df["text"].str.strip() != "")]
+        df_filtered = df[
+            df["text"].notnull() & (df["text"].apply(str).str.strip() != "")
+        ]

        return df_filtered