Merge remote-tracking branch 'origin/main' into fix-numpy-pinning

docling/cli/main.py

@@ -2,6 +2,7 @@ import importlib
 import json
 import logging
 import re
+import tempfile
 import time
 import warnings
 from enum import Enum
@@ -9,7 +10,7 @@ from pathlib import Path
 from typing import Annotated, Dict, Iterable, List, Optional, Type
 
 import typer
-from docling_core.utils.file import resolve_file_source
+from docling_core.utils.file import resolve_source_to_path
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
@@ -256,9 +257,10 @@ def convert(
     if from_formats is None:
         from_formats = [e for e in InputFormat]
 
+    with tempfile.TemporaryDirectory() as tempdir:
         input_doc_paths: List[Path] = []
         for src in input_sources:
-        source = resolve_file_source(source=src)
+            source = resolve_source_to_path(source=src, workdir=Path(tempdir))
             if not source.exists():
                 err_console.print(
                     f"[red]Error: The input file {source} does not exist.[/red]"
@@ -302,7 +304,9 @@ def convert(
             ocr_options=ocr_options,
             do_table_structure=True,
         )
-    pipeline_options.table_structure_options.do_cell_matching = True  # do_cell_matching
+        pipeline_options.table_structure_options.do_cell_matching = (
+            True  # do_cell_matching
+        )
         pipeline_options.table_structure_options.mode = table_mode
 
         if artifacts_path is not None:

docling/datamodel/base_models.py

@@ -1,5 +1,4 @@
 from enum import Enum, auto
-from io import BytesIO
 from typing import TYPE_CHECKING, Dict, List, Optional, Union
 
 from docling_core.types.doc import (
@@ -9,6 +8,9 @@ from docling_core.types.doc import (
     Size,
     TableCell,
 )
+from docling_core.types.io import (  # DO ΝΟΤ REMOVE; explicitly exposed from this location
+    DocumentStream,
+)
 from PIL.Image import Image
 from pydantic import BaseModel, ConfigDict
 
@@ -207,10 +209,3 @@ class Page(BaseModel):
     @property
     def image(self) -> Optional[Image]:
         return self.get_image(scale=self._default_image_scale)
-
-
-class DocumentStream(BaseModel):
-    model_config = ConfigDict(arbitrary_types_allowed=True)
-
-    name: str
-    stream: BytesIO

docling/datamodel/document.py

@@ -32,7 +32,7 @@ from docling_core.types.legacy_doc.document import (
 )
 from docling_core.types.legacy_doc.document import CCSFileInfoObject as DsFileInfoObject
 from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument
-from docling_core.utils.file import resolve_file_source
+from docling_core.utils.file import resolve_source_to_stream
 from pydantic import BaseModel
 from typing_extensions import deprecated
 
@@ -459,7 +459,7 @@ class _DocumentConversionInput(BaseModel):
         self, format_options: Dict[InputFormat, "FormatOption"]
     ) -> Iterable[InputDocument]:
         for item in self.path_or_stream_iterator:
-            obj = resolve_file_source(item) if isinstance(item, str) else item
+            obj = resolve_source_to_stream(item) if isinstance(item, str) else item
             format = self._guess_format(obj)
             if format not in format_options.keys():
                 _log.info(

docling/models/tesseract_ocr_cli_model.py

@@ -1,5 +1,6 @@
 import io
 import logging
+import os
 import tempfile
 from subprocess import DEVNULL, PIPE, Popen
 from typing import Iterable, Optional, Tuple
@@ -130,14 +131,17 @@ class TesseractOcrCliModel(BaseOcrModel):
                         high_res_image = page._backend.get_page_image(
                             scale=self.scale, cropbox=ocr_rect
                         )
-
+                        try:
                             with tempfile.NamedTemporaryFile(
-                            suffix=".png", mode="w"
+                                suffix=".png", mode="w+b", delete=False
                             ) as image_file:
                                 fname = image_file.name
-                            high_res_image.save(fname)
+                                high_res_image.save(image_file)
 
                             df = self._run_tesseract(fname)
+                        finally:
+                            if os.path.exists(fname):
+                                os.remove(fname)
 
                         # _log.info(df)
 

poetry.lock

@@ -7647,4 +7647,4 @@ tesserocr = ["tesserocr"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "cbcb4f196d6d2631ce82af90af2d356c557c9dcd2c12bb7ee193043962ba729f"
+content-hash = "33ee730cf750e618ec005ad44ad09617bc8f95632b30ac02b5290a03a33bdf5b"

pyproject.toml

@@ -26,7 +26,7 @@ packages = [{include = "docling"}]
 ######################
 python = "^3.9"
 pydantic = ">=2.0.0,<2.10"
-docling-core = "^2.5.1"
+docling-core = "^2.6.1"
 docling-ibm-models = "^2.0.6"
 deepsearch-glm = "^0.26.1"
 filetype = "^1.2.0"