docling-core 2.18.1__tar.gz → 2.19.0__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.
- {docling_core-2.18.1 → docling_core-2.19.0}/PKG-INFO +1 -1
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/transforms/chunker/hierarchical_chunker.py +5 -2
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/doc/document.py +315 -293
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/doc/labels.py +1 -1
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/doc/tokens.py +20 -94
- {docling_core-2.18.1 → docling_core-2.19.0}/pyproject.toml +1 -1
- {docling_core-2.18.1 → docling_core-2.19.0}/LICENSE +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/README.md +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/cli/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/cli/view.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/py.typed +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/resources/schemas/doc/ANN.json +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/resources/schemas/doc/DOC.json +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/resources/schemas/doc/OCR-output.json +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/resources/schemas/doc/RAW.json +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/resources/schemas/generated/ccs_document_schema.json +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/resources/schemas/generated/minimal_document_schema_flat.json +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/resources/schemas/search/search_doc_mapping.json +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/resources/schemas/search/search_doc_mapping_v2.json +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/search/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/search/json_schema_to_search_mapper.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/search/mapping.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/search/meta.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/search/package.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/transforms/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/transforms/chunker/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/transforms/chunker/base.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/transforms/chunker/hybrid_chunker.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/base.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/doc/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/doc/base.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/doc/utils.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/gen/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/gen/generic.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/io/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/legacy_doc/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/legacy_doc/base.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/legacy_doc/doc_ann.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/legacy_doc/doc_ocr.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/legacy_doc/doc_raw.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/legacy_doc/document.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/legacy_doc/tokens.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/nlp/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/nlp/qa.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/nlp/qa_labels.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/rec/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/rec/attribute.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/rec/base.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/rec/predicate.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/rec/record.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/rec/statement.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/types/rec/subject.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/utils/__init__.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/utils/alias.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/utils/file.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/utils/generate_docs.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/utils/generate_jsonschema.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/utils/legacy.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/utils/validate.py +0 -0
- {docling_core-2.18.1 → docling_core-2.19.0}/docling_core/utils/validators.py +0 -0
{docling_core-2.18.1 → docling_core-2.19.0}/docling_core/transforms/chunker/hierarchical_chunker.py
RENAMED
|
@@ -19,6 +19,7 @@ from docling_core.search.package import VERSION_PATTERN
|
|
|
19
19
|
from docling_core.transforms.chunker import BaseChunk, BaseChunker, BaseMeta
|
|
20
20
|
from docling_core.types import DoclingDocument as DLDocument
|
|
21
21
|
from docling_core.types.doc.document import (
|
|
22
|
+
CodeItem,
|
|
22
23
|
DocItem,
|
|
23
24
|
DocumentOrigin,
|
|
24
25
|
LevelNumber,
|
|
@@ -199,8 +200,10 @@ class HierarchicalChunker(BaseChunker):
|
|
|
199
200
|
heading_by_level.pop(k, None)
|
|
200
201
|
continue
|
|
201
202
|
|
|
202
|
-
if
|
|
203
|
-
|
|
203
|
+
if (
|
|
204
|
+
isinstance(item, TextItem)
|
|
205
|
+
or ((not self.merge_list_items) and isinstance(item, ListItem))
|
|
206
|
+
or isinstance(item, CodeItem)
|
|
204
207
|
):
|
|
205
208
|
text = item.text
|
|
206
209
|
elif isinstance(item, TableItem):
|