fix(utils): raise clear ValueError for multi-hyphen page range strings

haystack/utils/misc.py

@@ -39,6 +39,8 @@ def expand_page_range(page_range: list[str | int]) -> list[int]:
     :param page_range: List of page numbers and ranges
     :returns:
         An expanded list of page integers
+    :raises ValueError:
+        If any element is not a valid integer or a range string in the format ``'start-end'``.
 
     """
     expanded_page_range = []
@@ -55,7 +57,11 @@ def expand_page_range(page_range: list[str | int]) -> list[int]:
             expanded_page_range.append(int(page))
 
         elif isinstance(page, str) and "-" in page:
-            start, end = page.split("-")
+            parts = page.split("-", maxsplit=1)
+            if len(parts) != 2 or not parts[0].isdigit() or not parts[1].isdigit():
+                msg = "range must be a string in the format 'start-end'"
+                raise ValueError(f"Invalid page range: {page} - {msg}")
+            start, end = parts
             expanded_page_range.extend(range(int(start), int(end) + 1))
 
         else:

releasenotes/notes/fix-page-value-error-39ef3fa0300e2479.yaml

@@ -0,0 +1,6 @@
+---
+fixes:
+  - |
+    Fixed a ``ValueError: too many values to unpack`` raised when a page range string
+    contained more than one hyphen (e.g. ``"10-20-30"``). The parser now validates the
+    format and raises a clear ``ValueError`` with an explanatory message for invalid inputs.

test/utils/test_misc.py

@@ -13,6 +13,7 @@
     _normalize_metadata_field_name,
     _parse_dict_from_json,
     _reciprocal_rank_fusion,
+    expand_page_range,
 )
 
 
@@ -168,3 +169,9 @@ def test_parse_dict_from_json_missing_keys_raise_false(self, mock_logger):
         assert "Missing expected keys in JSON: {missing_keys}" in args[0]
         assert kwargs["missing_keys"] == ["key2"]
         assert kwargs["keys"] == ["key1"]
+
+
+class TestExpandPageRange:
+    def test_malformed_range_with_multiple_hyphens_raises_clear_valueerror(self):
+        with pytest.raises(ValueError, match="Invalid page range"):
+            expand_page_range(["1-3", "5-10-15"])