yujunjun/docling
1
0
Fork 0
mirror of https://github.com/docling-project/docling.git synced 2025-06-27 05:20:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: typo fix (#1465)

Browse Source 
* typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

* chore: typo fix

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>

---------

Signed-off-by: nkh0472 <67589323+nkh0472@users.noreply.github.com>
This commit is contained in:
nkh0472 2025-04-28 14:52:09 +08:00 committed by GitHub
parent 3afbe6c969
commit a097ccd8d5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
14 changed files with 19 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docling/backend/md_backend.py
View File

@ -409,7 +409,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
) )
return _txt return _txt
# restore original HTML by removing previouly added markers # restore original HTML by removing previously added markers
for regex in [ for regex in [
rf"<pre>\s*<code>\s*{_START_MARKER}", rf"<pre>\s*<code>\s*{_START_MARKER}",
rf"{_STOP_MARKER}\s*</code>\s*</pre>", rf"{_STOP_MARKER}\s*</code>\s*</pre>",

2
docling/backend/msword_backend.py
View File

@ -436,7 +436,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
# Common styles for bullet and numbered lists. # Common styles for bullet and numbered lists.
# "List Bullet", "List Number", "List Paragraph" # "List Bullet", "List Number", "List Paragraph"
# Identify wether list is a numbered list or not # Identify whether list is a numbered list or not
# is_numbered = "List Bullet" not in paragraph.style.name # is_numbered = "List Bullet" not in paragraph.style.name
is_numbered = False is_numbered = False
p_style_id, p_level = self._get_label_and_level(paragraph) p_style_id, p_level = self._get_label_and_level(paragraph)

2
docling/backend/xml/jats_backend.py
View File

@ -91,7 +91,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
super().__init__(in_doc, path_or_stream) super().__init__(in_doc, path_or_stream)
self.path_or_stream = path_or_stream self.path_or_stream = path_or_stream
# Initialize the root of the document hiearchy # Initialize the root of the document hierarchy
self.root: Optional[NodeItem] = None self.root: Optional[NodeItem] = None
self.valid = False self.valid = False

8
docling/backend/xml/uspto_backend.py
View File

@ -1,6 +1,6 @@
"""Backend to parse patents from the United States Patent Office (USPTO). """Backend to parse patents from the United States Patent Office (USPTO).
The parsers included in this module can handle patent grants pubished since 1976 and The parsers included in this module can handle patent grants published since 1976 and
patent applications since 2001. patent applications since 2001.
The original files can be found in https://bulkdata.uspto.gov. The original files can be found in https://bulkdata.uspto.gov.
""" """
@ -440,7 +440,7 @@ class PatentUsptoIce(PatentUspto):
) )
elif name == self.Element.PARAGRAPH.value and text: elif name == self.Element.PARAGRAPH.value and text:
# remmove blank spaces added in paragraphs # remove blank spaces added in paragraphs
text = re.sub("\\s+", " ", text) text = re.sub("\\s+", " ", text)
if self.Element.ABSTRACT.value in self.property: if self.Element.ABSTRACT.value in self.property:
self.abstract = ( self.abstract = (
@ -1697,7 +1697,7 @@ class XmlTable:
class HtmlEntity: class HtmlEntity:
"""Provide utility functions to get the HTML entities of styled characters. """Provide utility functions to get the HTML entities of styled characters.
This class has been developped from: This class has been developed from:
https://unicode-table.com/en/html-entities/ https://unicode-table.com/en/html-entities/
https://www.w3.org/TR/WD-math-970515/table03.html https://www.w3.org/TR/WD-math-970515/table03.html
""" """
@ -1896,7 +1896,7 @@ class HtmlEntity:
"""Get an HTML entity of a greek letter in ISO 8879. """Get an HTML entity of a greek letter in ISO 8879.
Args: Args:
The text to transform, as an ISO 8879 entitiy. The text to transform, as an ISO 8879 entity.
Returns: Returns:
The HTML entity representing a greek letter. If the input text is not The HTML entity representing a greek letter. If the input text is not

2
docling/cli/main.py
View File

@ -521,7 +521,7 @@ def convert( # noqa: C901
if image_export_mode != ImageRefMode.PLACEHOLDER: if image_export_mode != ImageRefMode.PLACEHOLDER:
pipeline_options.generate_page_images = True pipeline_options.generate_page_images = True
pipeline_options.generate_picture_images = ( pipeline_options.generate_picture_images = (
True # FIXME: to be deprecated in verson 3 True # FIXME: to be deprecated in version 3
) )
pipeline_options.images_scale = 2 pipeline_options.images_scale = 2

2
docling/models/table_structure_model.py
View File

@ -234,7 +234,7 @@ class TableStructureModel(BasePageModel):
tcells = table_cluster.cells tcells = table_cluster.cells
tokens = [] tokens = []
for c in tcells: for c in tcells:
# Only allow non empty stings (spaces) into the cells of a table # Only allow non empty strings (spaces) into the cells of a table
if len(c.text.strip()) > 0: if len(c.text.strip()) > 0:
new_cell = copy.deepcopy(c) new_cell = copy.deepcopy(c)
new_cell.rect = BoundingRectangle.from_bounding_box( new_cell.rect = BoundingRectangle.from_bounding_box(

2
docling/models/tesseract_ocr_model.py
View File

@ -151,7 +151,7 @@ class TesseractOcrModel(BaseOcrModel):
script = map_tesseract_script(script) script = map_tesseract_script(script)
lang = f"{self.script_prefix}{script}" lang = f"{self.script_prefix}{script}"
# Check if the detected languge is present in the system # Check if the detected language is present in the system
if lang not in self._tesserocr_languages: if lang not in self._tesserocr_languages:
msg = f"Tesseract detected the script '{script}' and language '{lang}'." msg = f"Tesseract detected the script '{script}' and language '{lang}'."
msg += " However this language is not installed in your system and will be ignored." msg += " However this language is not installed in your system and will be ignored."

2
docs/examples/backend_xml_rag.ipynb
View File

@ -569,7 +569,7 @@
"The `DoclingDocument` format of the converted patents has a rich hierarchical structure, inherited from the original XML document and preserved by the Docling custom backend.\n", "The `DoclingDocument` format of the converted patents has a rich hierarchical structure, inherited from the original XML document and preserved by the Docling custom backend.\n",
"In this notebook, we will leverage:\n", "In this notebook, we will leverage:\n",
"- The `SimpleDirectoryReader` pattern to iterate over the exported XML files created in section [Fetch the data](#fetch-the-data).\n", "- The `SimpleDirectoryReader` pattern to iterate over the exported XML files created in section [Fetch the data](#fetch-the-data).\n",
"- The LlamaIndex extensions, `DoclingReader` and `DoclingNodeParser`, to ingest the patent chunks into a Milvus vectore store.\n", "- The LlamaIndex extensions, `DoclingReader` and `DoclingNodeParser`, to ingest the patent chunks into a Milvus vector store.\n",
"- The `HierarchicalChunker` implementation, which applies a document-based hierarchical chunking, to leverage the patent structures like sections and paragraphs within sections.\n", "- The `HierarchicalChunker` implementation, which applies a document-based hierarchical chunking, to leverage the patent structures like sections and paragraphs within sections.\n",
"\n", "\n",
"Refer to other possible implementations and usage patterns in the [Chunking](../../concepts/chunking/) documentation and the [RAG with LlamaIndex](../rag_llamaindex/) notebook." "Refer to other possible implementations and usage patterns in the [Chunking](../../concepts/chunking/) documentation and the [RAG with LlamaIndex](../rag_llamaindex/) notebook."

2
docs/examples/hybrid_chunking.ipynb
View File

@ -206,7 +206,7 @@
"source": [ "source": [
"Points to notice looking at the output chunks below:\n", "Points to notice looking at the output chunks below:\n",
"- Where possible, we fit the limit of 64 tokens for the metadata-enriched serialization form (see chunk 2)\n", "- Where possible, we fit the limit of 64 tokens for the metadata-enriched serialization form (see chunk 2)\n",
"- Where neeeded, we stop before the limit, e.g. see cases of 63 as it would otherwise run into a comma (see chunk 6)\n", "- Where needed, we stop before the limit, e.g. see cases of 63 as it would otherwise run into a comma (see chunk 6)\n",
"- Where possible, we merge undersized peer chunks (see chunk 0)\n", "- Where possible, we merge undersized peer chunks (see chunk 0)\n",
"- \"Tail\" chunks trailing right after merges may still be undersized (see chunk 8)" "- \"Tail\" chunks trailing right after merges may still be undersized (see chunk 8)"
] ]

2
docs/examples/pictures_description.ipynb
View File

@ -279,7 +279,7 @@
"## Use other vision models\n", "## Use other vision models\n",
"\n", "\n",
"The examples above can also be reproduced using other vision model.\n", "The examples above can also be reproduced using other vision model.\n",
"The Docling options `PictureDescriptionVlmOptions` allows to speficy your favorite vision model from the Hugging Face Hub." "The Docling options `PictureDescriptionVlmOptions` allows to specify your favorite vision model from the Hugging Face Hub."
] ]
}, },
{ {

2
docs/examples/rag_milvus.ipynb
View File

@ -32,7 +32,7 @@
"\n", "\n",
"Note: For best results, please use **GPU acceleration** to run this notebook. Here are two options for running this notebook:\n", "Note: For best results, please use **GPU acceleration** to run this notebook. Here are two options for running this notebook:\n",
"1. **Locally on a MacBook with an Apple Silicon chip.** Converting all documents in the notebook takes ~2 minutes on a MacBook M2 due to Docling's usage of MPS accelerators.\n", "1. **Locally on a MacBook with an Apple Silicon chip.** Converting all documents in the notebook takes ~2 minutes on a MacBook M2 due to Docling's usage of MPS accelerators.\n",
"2. **Run this notebook on Google Colab.** Converting all documents in the notebook takes ~8 mintutes on a Google Colab T4 GPU.\n" "2. **Run this notebook on Google Colab.** Converting all documents in the notebook takes ~8 minutes on a Google Colab T4 GPU.\n"
] ]
}, },
{ {

4
docs/examples/rag_weaviate.ipynb
View File

@ -43,7 +43,7 @@
"\n", "\n",
"Note: For best results, please use **GPU acceleration** to run this notebook. Here are two options for running this notebook:\n", "Note: For best results, please use **GPU acceleration** to run this notebook. Here are two options for running this notebook:\n",
"1. **Locally on a MacBook with an Apple Silicon chip.** Converting all documents in the notebook takes ~2 minutes on a MacBook M2 due to Docling's usage of MPS accelerators.\n", "1. **Locally on a MacBook with an Apple Silicon chip.** Converting all documents in the notebook takes ~2 minutes on a MacBook M2 due to Docling's usage of MPS accelerators.\n",
"2. **Run this notebook on Google Colab.** Converting all documents in the notebook takes ~8 mintutes on a Google Colab T4 GPU." "2. **Run this notebook on Google Colab.** Converting all documents in the notebook takes ~8 minutes on a Google Colab T4 GPU."
] ]
}, },
{ {
@ -716,7 +716,7 @@
"id": "7tGz49nfUegG" "id": "7tGz49nfUegG"
}, },
"source": [ "source": [
"We can see that our RAG pipeline performs relatively well for simple queries, especially given the small size of the dataset. Scaling this method for converting a larger sample of PDFs would require more compute (GPUs) and a more advanced deployment of Weaviate (like Docker, Kubernetes, or Weaviate Cloud). For more information on available Weaviate configurations, check out the [documetation](https://weaviate.io/developers/weaviate/starter-guides/which-weaviate)." "We can see that our RAG pipeline performs relatively well for simple queries, especially given the small size of the dataset. Scaling this method for converting a larger sample of PDFs would require more compute (GPUs) and a more advanced deployment of Weaviate (like Docker, Kubernetes, or Weaviate Cloud). For more information on available Weaviate configurations, check out the [documentation](https://weaviate.io/developers/weaviate/starter-guides/which-weaviate)."
] ]
} }
], ],

2
docs/faq/index.md
View File

@ -137,7 +137,7 @@ This is a collection of FAQ collected from the user questions on <https://github
### Some images are missing from MS Word and Powerpoint ### Some images are missing from MS Word and Powerpoint
The image processing library used by Docling is able to handle embedded WMF images only on Windows platform. The image processing library used by Docling is able to handle embedded WMF images only on Windows platform.
If you are on other operaring systems, these images will be ignored. If you are on other operating systems, these images will be ignored.
??? question "`HybridChunker` triggers warning: 'Token indices sequence length is longer than the specified maximum sequence length for this model'" ??? question "`HybridChunker` triggers warning: 'Token indices sequence length is longer than the specified maximum sequence length for this model'"

4
docs/v2.md
View File

@ -37,7 +37,7 @@ docling ./input/dir --output ./scratch --abort-on-error
### Setting up a `DocumentConverter` ### Setting up a `DocumentConverter`
To accomodate many input formats, we changed the way you need to set up your `DocumentConverter` object. To accommodate many input formats, we changed the way you need to set up your `DocumentConverter` object.
You can now define a list of allowed formats on the `DocumentConverter` initialization, and specify custom options You can now define a list of allowed formats on the `DocumentConverter` initialization, and specify custom options
per-format if desired. By default, all supported formats are allowed. If you don't provide `format_options`, defaults per-format if desired. By default, all supported formats are allowed. If you don't provide `format_options`, defaults
will be used for all `allowed_formats`. will be used for all `allowed_formats`.
@ -151,7 +151,7 @@ conv_result: ConversionResult = doc_converter.convert("https://arxiv.org/pdf/240
## Inspect the converted document: ## Inspect the converted document:
conv_result.document.print_element_tree() conv_result.document.print_element_tree()
## Iterate the elements in reading order, including hierachy level: ## Iterate the elements in reading order, including hierarchy level:
for item, level in conv_result.document.iterate_items(): for item, level in conv_result.document.iterate_items():
if isinstance(item, TextItem): if isinstance(item, TextItem):
print(item.text) print(item.text)