feat: csv loader (#470)

Co-authored-by: Taranjeet Singh <reachtotj@gmail.com>
2023-09-05 10:18:03 +02:00
parent 344e7470f6
commit bd595f84e8
7 changed files with 172 additions and 0 deletions
@@ -147,6 +147,10 @@ def detect_datatype(source: Any) -> DataType:
            logging.debug(f"Source of `{formatted_source}` detected as `sitemap`.")
            return DataType.SITEMAP

+        if url.path.endswith(".csv"):
+            logging.debug(f"Source of `{formatted_source}` detected as `csv`.")
+            return DataType.CSV
+
        if url.path.endswith(".docx"):
            logging.debug(f"Source of `{formatted_source}` detected as `docx`.")
            return DataType.DOCX
@@ -182,6 +186,10 @@ def detect_datatype(source: Any) -> DataType:
            logging.debug(f"Source of `{formatted_source}` detected as `docx`.")
            return DataType.DOCX

+        if source.endswith(".csv"):
+            logging.debug(f"Source of `{formatted_source}` detected as `csv`.")
+            return DataType.CSV
+
        # If the source is a valid file, that's not detectable as a type, an error is raised.
        # It does not fallback to text.
        raise ValueError(