feat: Add option to define page range (#852)

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

docling/datamodel/document.py

@@ -157,6 +157,8 @@ class InputDocument(BaseModel):
                     self.page_count = self._backend.page_count()
                     if not self.page_count <= self.limits.max_num_pages:
                         self.valid = False
+                    elif self.page_count < self.limits.page_range[0]:
+                        self.valid = False
 
         except (FileNotFoundError, OSError) as e:
             self.valid = False

docling/datamodel/settings.py

@@ -1,13 +1,28 @@
 import sys
 from pathlib import Path
+from typing import Annotated, Tuple
 
-from pydantic import BaseModel
+from pydantic import BaseModel, PlainValidator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
+def _validate_page_range(v: Tuple[int, int]) -> Tuple[int, int]:
+    if v[0] < 1 or v[1] < v[0]:
+        raise ValueError(
+            "Invalid page range: start must be ≥ 1 and end must be ≥ start."
+        )
+    return v
+
+
+PageRange = Annotated[Tuple[int, int], PlainValidator(_validate_page_range)]
+
+DEFAULT_PAGE_RANGE: PageRange = (1, sys.maxsize)
+
+
 class DocumentLimits(BaseModel):
     max_num_pages: int = sys.maxsize
     max_file_size: int = sys.maxsize
+    page_range: PageRange = DEFAULT_PAGE_RANGE
 
 
 class BatchConcurrencySettings(BaseModel):