docling-core 2.40.0__tar.gz → 2.42.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of docling-core might be problematic. Click here for more details.

Files changed (107) hide show
  1. {docling_core-2.40.0 → docling_core-2.42.0}/PKG-INFO +1 -1
  2. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/doc/base.py +29 -2
  3. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/doc/document.py +1329 -161
  4. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/doc/page.py +22 -2
  5. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core.egg-info/PKG-INFO +1 -1
  6. {docling_core-2.40.0 → docling_core-2.42.0}/pyproject.toml +1 -1
  7. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_docling_doc.py +277 -5
  8. {docling_core-2.40.0 → docling_core-2.42.0}/LICENSE +0 -0
  9. {docling_core-2.40.0 → docling_core-2.42.0}/README.md +0 -0
  10. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/__init__.py +0 -0
  11. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/cli/__init__.py +0 -0
  12. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/cli/view.py +0 -0
  13. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/experimental/__init__.py +0 -0
  14. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/py.typed +0 -0
  15. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/resources/schemas/doc/ANN.json +0 -0
  16. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/resources/schemas/doc/DOC.json +0 -0
  17. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/resources/schemas/doc/OCR-output.json +0 -0
  18. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/resources/schemas/doc/RAW.json +0 -0
  19. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/resources/schemas/generated/ccs_document_schema.json +0 -0
  20. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/resources/schemas/generated/minimal_document_schema_flat.json +0 -0
  21. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/resources/schemas/search/search_doc_mapping.json +0 -0
  22. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/resources/schemas/search/search_doc_mapping_v2.json +0 -0
  23. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/search/__init__.py +0 -0
  24. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/search/json_schema_to_search_mapper.py +0 -0
  25. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/search/mapping.py +0 -0
  26. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/search/meta.py +0 -0
  27. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/search/package.py +0 -0
  28. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/__init__.py +0 -0
  29. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/chunker/__init__.py +0 -0
  30. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/chunker/base.py +0 -0
  31. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/chunker/hierarchical_chunker.py +0 -0
  32. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/chunker/hybrid_chunker.py +0 -0
  33. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/chunker/tokenizer/__init__.py +0 -0
  34. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/chunker/tokenizer/base.py +0 -0
  35. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/chunker/tokenizer/huggingface.py +0 -0
  36. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/chunker/tokenizer/openai.py +0 -0
  37. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/serializer/__init__.py +0 -0
  38. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/serializer/base.py +0 -0
  39. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/serializer/common.py +0 -0
  40. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/serializer/doctags.py +0 -0
  41. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/serializer/html.py +0 -0
  42. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/serializer/html_styles.py +0 -0
  43. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/serializer/markdown.py +0 -0
  44. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/visualizer/__init__.py +0 -0
  45. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/visualizer/base.py +0 -0
  46. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/visualizer/layout_visualizer.py +0 -0
  47. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/visualizer/reading_order_visualizer.py +0 -0
  48. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/transforms/visualizer/table_visualizer.py +0 -0
  49. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/__init__.py +0 -0
  50. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/base.py +0 -0
  51. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/doc/__init__.py +0 -0
  52. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/doc/labels.py +0 -0
  53. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/doc/tokens.py +0 -0
  54. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/doc/utils.py +0 -0
  55. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/gen/__init__.py +0 -0
  56. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/gen/generic.py +0 -0
  57. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/io/__init__.py +0 -0
  58. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/legacy_doc/__init__.py +0 -0
  59. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/legacy_doc/base.py +0 -0
  60. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/legacy_doc/doc_ann.py +0 -0
  61. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/legacy_doc/doc_ocr.py +0 -0
  62. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/legacy_doc/doc_raw.py +0 -0
  63. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/legacy_doc/document.py +0 -0
  64. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/legacy_doc/tokens.py +0 -0
  65. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/nlp/__init__.py +0 -0
  66. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/nlp/qa.py +0 -0
  67. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/nlp/qa_labels.py +0 -0
  68. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/rec/__init__.py +0 -0
  69. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/rec/attribute.py +0 -0
  70. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/rec/base.py +0 -0
  71. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/rec/predicate.py +0 -0
  72. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/rec/record.py +0 -0
  73. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/rec/statement.py +0 -0
  74. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/types/rec/subject.py +0 -0
  75. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/utils/__init__.py +0 -0
  76. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/utils/alias.py +0 -0
  77. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/utils/file.py +0 -0
  78. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/utils/generate_docs.py +0 -0
  79. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/utils/generate_jsonschema.py +0 -0
  80. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/utils/legacy.py +0 -0
  81. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/utils/validate.py +0 -0
  82. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core/utils/validators.py +0 -0
  83. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core.egg-info/SOURCES.txt +0 -0
  84. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core.egg-info/dependency_links.txt +0 -0
  85. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core.egg-info/entry_points.txt +0 -0
  86. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core.egg-info/requires.txt +0 -0
  87. {docling_core-2.40.0 → docling_core-2.42.0}/docling_core.egg-info/top_level.txt +0 -0
  88. {docling_core-2.40.0 → docling_core-2.42.0}/setup.cfg +0 -0
  89. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_base.py +0 -0
  90. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_collection.py +0 -0
  91. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_data_gen_flag.py +0 -0
  92. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_doc_base.py +0 -0
  93. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_doc_legacy_convert.py +0 -0
  94. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_doc_schema.py +0 -0
  95. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_doc_schema_extractor.py +0 -0
  96. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_doctags_load.py +0 -0
  97. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_hierarchical_chunker.py +0 -0
  98. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_hybrid_chunker.py +0 -0
  99. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_json_schema_to_search_mapper.py +0 -0
  100. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_nlp_qa.py +0 -0
  101. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_otsl_table_export.py +0 -0
  102. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_page.py +0 -0
  103. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_rec_schema.py +0 -0
  104. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_search_meta.py +0 -0
  105. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_serialization.py +0 -0
  106. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_utils.py +0 -0
  107. {docling_core-2.40.0 → docling_core-2.42.0}/test/test_visualization.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: docling-core
3
- Version: 2.40.0
3
+ Version: 2.42.0
4
4
  Summary: A python library to define and validate data types in Docling.
5
5
  Author-email: Cesar Berrospi Ramis <ceb@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
6
6
  Maintainer-email: Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>, Cesar Berrospi Ramis <ceb@zurich.ibm.com>
@@ -1,9 +1,9 @@
1
1
  """Models for the base data types."""
2
2
 
3
3
  from enum import Enum
4
- from typing import List, Tuple
4
+ from typing import Any, List, Tuple
5
5
 
6
- from pydantic import BaseModel
6
+ from pydantic import BaseModel, FieldSerializationInfo, field_serializer
7
7
 
8
8
 
9
9
  class ImageRefMode(str, Enum):
@@ -21,12 +21,35 @@ class CoordOrigin(str, Enum):
21
21
  BOTTOMLEFT = "BOTTOMLEFT"
22
22
 
23
23
 
24
+ class PydanticSerCtxKey(str, Enum):
25
+ """Pydantic serialization context keys."""
26
+
27
+ COORD_PREC = "coord_prec" # key for coordinates precision
28
+ CONFID_PREC = "confid_prec" # key for confidence values precision
29
+
30
+
31
+ def round_pydantic_float(
32
+ val: float, ctx: Any, precision_ctx_key: PydanticSerCtxKey
33
+ ) -> float:
34
+ """Round float, provided the precision is available in the context."""
35
+ precision = (
36
+ ctx.get(precision_ctx_key.value)
37
+ if isinstance(ctx, dict)
38
+ else getattr(ctx, precision_ctx_key.value, None)
39
+ )
40
+ return round(val, precision) if isinstance(precision, int) else val
41
+
42
+
24
43
  class Size(BaseModel):
25
44
  """Size."""
26
45
 
27
46
  width: float = 0.0
28
47
  height: float = 0.0
29
48
 
49
+ @field_serializer("width", "height")
50
+ def _serialize(self, value: float, info: FieldSerializationInfo) -> float:
51
+ return round_pydantic_float(value, info.context, PydanticSerCtxKey.COORD_PREC)
52
+
30
53
  def as_tuple(self):
31
54
  """as_tuple."""
32
55
  return (self.width, self.height)
@@ -52,6 +75,10 @@ class BoundingBox(BaseModel):
52
75
  """height."""
53
76
  return abs(self.t - self.b)
54
77
 
78
+ @field_serializer("l", "t", "r", "b")
79
+ def _serialize(self, value: float, info: FieldSerializationInfo) -> float:
80
+ return round_pydantic_float(value, info.context, PydanticSerCtxKey.COORD_PREC)
81
+
55
82
  def resize_by_scale(self, x_scale: float, y_scale: float):
56
83
  """resize_by_scale."""
57
84
  return BoundingBox(