feat(cli): add option for html with split-page mode (#1355)
* updated the cli to output html in split-page mode Signed-off-by: Peter Staar <taa@zurich.ibm.com> * add pin for new docling-core with html split argument Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * relock with fixed html export in docling-core Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update test results Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update more tests Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update example Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update lock with docling-core fixes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update test results Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add again chunking extras Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Peter W. J. Staar
GitHub
parent
0de70e7991
commit
c0ba88edf1
@ -154,6 +154,7 @@ def export_documents(
|
||||
output_dir: Path,
|
||||
export_json: bool,
|
||||
export_html: bool,
|
||||
export_html_split_page: bool,
|
||||
export_md: bool,
|
||||
export_txt: bool,
|
||||
export_doctags: bool,
|
||||
@ -181,7 +182,15 @@ def export_documents(
|
||||
fname = output_dir / f"{doc_filename}.html"
|
||||
_log.info(f"writing HTML output to {fname}")
|
||||
conv_res.document.save_as_html(
|
||||
filename=fname, image_mode=image_export_mode
|
||||
filename=fname, image_mode=image_export_mode, split_page_view=False
|
||||
)
|
||||
|
||||
# Export HTML format:
|
||||
if export_html_split_page:
|
||||
fname = output_dir / f"{doc_filename}.html"
|
||||
_log.info(f"writing HTML output to {fname}")
|
||||
conv_res.document.save_as_html(
|
||||
filename=fname, image_mode=image_export_mode, split_page_view=True
|
||||
)
|
||||
|
||||
# Export Text format:
|
||||
@ -472,6 +481,7 @@ def convert(
|
||||
|
||||
export_json = OutputFormat.JSON in to_formats
|
||||
export_html = OutputFormat.HTML in to_formats
|
||||
export_html_split_page = OutputFormat.HTML_SPLIT_PAGE in to_formats
|
||||
export_md = OutputFormat.MARKDOWN in to_formats
|
||||
export_txt = OutputFormat.TEXT in to_formats
|
||||
export_doctags = OutputFormat.DOCTAGS in to_formats
|
||||
@ -585,6 +595,7 @@ def convert(
|
||||
output_dir=output,
|
||||
export_json=export_json,
|
||||
export_html=export_html,
|
||||
export_html_split_page=export_html_split_page,
|
||||
export_md=export_md,
|
||||
export_txt=export_txt,
|
||||
export_doctags=export_doctags,
|
||||
|
||||
@ -50,6 +50,7 @@ class OutputFormat(str, Enum):
|
||||
MARKDOWN = "md"
|
||||
JSON = "json"
|
||||
HTML = "html"
|
||||
HTML_SPLIT_PAGE = "html_split_page"
|
||||
TEXT = "text"
|
||||
DOCTAGS = "doctags"
|
||||
|
||||
|
||||
@ -40,7 +40,7 @@ def main():
|
||||
element_html_filename = output_dir / f"{doc_filename}-table-{table_ix+1}.html"
|
||||
_log.info(f"Saving HTML table to {element_html_filename}")
|
||||
with element_html_filename.open("w") as fp:
|
||||
fp.write(table.export_to_html())
|
||||
fp.write(table.export_to_html(doc=conv_res.document))
|
||||
|
||||
end_time = time.time() - start_time
|
||||
|
||||
|
||||
8
poetry.lock
generated
8
poetry.lock
generated
@ -870,13 +870,13 @@ files = [
|
||||
|
||||
[[package]]
|
||||
name = "docling-core"
|
||||
version = "2.25.0"
|
||||
version = "2.26.2"
|
||||
description = "A python library to define and validate data types in Docling."
|
||||
optional = false
|
||||
python-versions = "<4.0,>=3.9"
|
||||
files = [
|
||||
{file = "docling_core-2.25.0-py3-none-any.whl", hash = "sha256:24fe431005518df8e554b69c33178bca903bcf91c230cdcd31a905369f53a461"},
|
||||
{file = "docling_core-2.25.0.tar.gz", hash = "sha256:a2019392592840b2829082ef0c1d1a9096fb3512ae44c3a93dc04a5eaef81b2f"},
|
||||
{file = "docling_core-2.26.2-py3-none-any.whl", hash = "sha256:3f35627352e2311676af2e484646b9ccd1ecb3012f8a87a127692c1d862ea9f5"},
|
||||
{file = "docling_core-2.26.2.tar.gz", hash = "sha256:6d080acf5d37012ee6f4e47bc103049091480d9de708bd2cb899c2ac923f5616"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
@ -7859,4 +7859,4 @@ vlm = ["accelerate", "transformers", "transformers"]
|
||||
[metadata]
|
||||
lock-version = "2.0"
|
||||
python-versions = "^3.9"
|
||||
content-hash = "2c4da8d08fa1f95af87348179c20747e85749df670dea38f18f586c4397a358d"
|
||||
content-hash = "a9830e60f15bd80e7776c5dbba86dd477ae62408e55406c3f91a127bc553e173"
|
||||
|
||||
@ -46,7 +46,7 @@ packages = [{ include = "docling" }]
|
||||
######################
|
||||
python = "^3.9"
|
||||
pydantic = "^2.0.0"
|
||||
docling-core = {extras = ["chunking"], version = "^2.24.1"}
|
||||
docling-core = {version = "^2.26.0", extras = ["chunking"]}
|
||||
docling-ibm-models = "^3.4.0"
|
||||
docling-parse = "^4.0.0"
|
||||
filetype = "^1.2.0"
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@ -106,10 +106,10 @@
|
||||
<text><loc_252><loc_232><loc_445><loc_328>Cell Content. In this section, we evaluate the entire pipeline of recovering a table with content. Here we put our approach to test by capitalizing on extracting content from the PDF cells rather than decoding from images. Tab. 4 shows the TEDs score of HTML code representing the structure of the table along with the content inserted in the data cell and compared with the ground-truth. Our method achieved a 5.3% increase over the state-of-the-art, and commercial solutions. We believe our scores would be higher if the HTML ground-truth matched the extracted PDF cell content. Unfortunately, there are small discrepancies such as spacings around words or special characters with various unicode representations.</text>
|
||||
<otsl><loc_272><loc_341><loc_426><loc_406><fcel>Model<ched>Simple<ched>TEDS Complex<ched>All<nl><rhed>Tabula<fcel>78.0<fcel>57.8<fcel>67.9<nl><rhed>Traprange<fcel>60.8<fcel>49.9<fcel>55.4<nl><rhed>Camelot<fcel>80.0<fcel>66.0<fcel>73.0<nl><rhed>Acrobat Pro<fcel>68.9<fcel>61.8<fcel>65.3<nl><rhed>EDD<fcel>91.2<fcel>85.4<fcel>88.3<nl><rhed>TableFormer<fcel>95.4<fcel>90.1<fcel>93.6<nl><caption><loc_252><loc_415><loc_445><loc_435>Table 4: Results of structure with content retrieved using cell detection on PubTabNet. In all cases the input is PDF documents with cropped tables.</caption></otsl>
|
||||
<page_footer><loc_241><loc_463><loc_245><loc_469>7</page_footer>
|
||||
<page_break>
|
||||
<unordered_list><list_item><loc_44><loc_50><loc_50><loc_55>a.</list_item>
|
||||
<list_item><loc_54><loc_50><loc_408><loc_55>Red - PDF cells, Green - predicted bounding boxes, Blue - post-processed predictions matched to PDF cells</list_item>
|
||||
</unordered_list>
|
||||
<page_break>
|
||||
<section_header_level_1><loc_44><loc_60><loc_232><loc_64>Japanese language (previously unseen by TableFormer):</section_header_level_1>
|
||||
<section_header_level_1><loc_249><loc_60><loc_352><loc_64>Example table from FinTabNet:</section_header_level_1>
|
||||
<picture><loc_41><loc_65><loc_246><loc_118></picture>
|
||||
@ -127,7 +127,6 @@
|
||||
<unordered_list><list_item><loc_256><loc_438><loc_445><loc_450>[1] Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. End-to-</list_item>
|
||||
</unordered_list>
|
||||
<page_footer><loc_241><loc_463><loc_245><loc_469>8</page_footer>
|
||||
<page_break>
|
||||
<unordered_list><list_item><loc_57><loc_48><loc_234><loc_74>end object detection with transformers. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm, editors, Computer Vision - ECCV 2020 , pages 213-229, Cham, 2020. Springer International Publishing. 5</list_item>
|
||||
<list_item><loc_45><loc_76><loc_234><loc_95>[2] Zewen Chi, Heyan Huang, Heng-Da Xu, Houjin Yu, Wanxuan Yin, and Xian-Ling Mao. Complicated table structure recognition. arXiv preprint arXiv:1908.04729 , 2019. 3</list_item>
|
||||
<list_item><loc_45><loc_97><loc_234><loc_116>[3] Bertrand Couasnon and Aurelie Lemaitre. Recognition of Tables and Forms , pages 647-677. Springer London, London, 2014. 2</list_item>
|
||||
@ -154,6 +153,7 @@
|
||||
<list_item><loc_252><loc_396><loc_445><loc_422>[24] Shah Rukh Qasim, Hassan Mahmood, and Faisal Shafait. Rethinking table recognition using graph neural networks. In 2019 International Conference on Document Analysis and Recognition (ICDAR) , pages 142-147. IEEE, 2019. 3</list_item>
|
||||
<list_item><loc_252><loc_424><loc_445><loc_450>[25] Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, and Silvio Savarese. Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF Conference on</list_item>
|
||||
</unordered_list>
|
||||
<page_break>
|
||||
<page_footer><loc_241><loc_463><loc_245><loc_469>9</page_footer>
|
||||
<page_break>
|
||||
<text><loc_57><loc_48><loc_234><loc_60>Computer Vision and Pattern Recognition , pages 658-666, 2019. 6</text>
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@ -182,9 +182,9 @@
|
||||
<code><loc_112><loc_267><loc_430><loc_432><_unknown_>CREATE MASK HR_SCHEMA.MASK_TAX_ID_ON_EMPLOYEES ON HR_SCHEMA.EMPLOYEES AS EMPLOYEES FOR COLUMN TAX_ID RETURN CASE WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'HR' ) = 1 THEN EMPLOYEES . TAX_ID WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'MGR' ) = 1 AND SESSION_USER = EMPLOYEES . USER_ID THEN EMPLOYEES . TAX_ID WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'MGR' ) = 1 AND SESSION_USER <> EMPLOYEES . USER_ID THEN ( 'XXX-XX-' CONCAT QSYS2 . SUBSTR ( EMPLOYEES . TAX_ID , 8 , 4 ) ) WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'EMP' ) = 1 THEN EMPLOYEES . TAX_ID ELSE 'XXX-XX-XXXX' END ENABLE ;<caption><loc_112><loc_257><loc_288><loc_262>Example 3-9 Creating a mask on the TAX_ID column</caption></code>
|
||||
<page_footer><loc_282><loc_477><loc_428><loc_482>Chapter 3. Row and Column Access Control</page_footer>
|
||||
<page_footer><loc_438><loc_477><loc_447><loc_482>27</page_footer>
|
||||
<page_break>
|
||||
<unordered_list><list_item><loc_112><loc_45><loc_368><loc_51>3. Figure 3-10 shows the masks that are created in the HR_SCHEMA.</list_item>
|
||||
</unordered_list>
|
||||
<page_break>
|
||||
<picture><loc_52><loc_60><loc_447><loc_107><caption><loc_53><loc_110><loc_239><loc_115>Figure 3-10 Column masks shown in System i Navigator</caption></picture>
|
||||
<section_header_level_1><loc_53><loc_128><loc_167><loc_135>3.6.6 Activating RCAC</section_header_level_1>
|
||||
<text><loc_112><loc_144><loc_447><loc_165>Now that you have created the row permission and the two column masks, RCAC must be activated. The row permission and the two column masks are enabled (last clause in the scripts), but now you must activate RCAC on the table. To do so, complete the following steps:</text>
|
||||
@ -203,10 +203,10 @@
|
||||
<picture><loc_52><loc_270><loc_433><loc_408><caption><loc_53><loc_410><loc_284><loc_415>Figure 3-11 Selecting the EMPLOYEES table from System i Navigator</caption></picture>
|
||||
<page_footer><loc_53><loc_477><loc_64><loc_482>28</page_footer>
|
||||
<page_footer><loc_76><loc_477><loc_273><loc_482>Row and Column Access Control Support in IBM DB2 for i</page_footer>
|
||||
<page_break>
|
||||
<unordered_list><list_item><loc_112><loc_45><loc_420><loc_66>2. Figure 4-68 shows the Visual Explain of the same SQL statement, but with RCAC enabled. It is clear that the implementation of the SQL statement is more complex because the row permission rule becomes part of the WHERE clause.</list_item>
|
||||
<list_item><loc_112><loc_320><loc_447><loc_341>3. Compare the advised indexes that are provided by the Optimizer without RCAC and with RCAC enabled. Figure 4-69 shows the index advice for the SQL statement without RCAC enabled. The index being advised is for the ORDER BY clause.</list_item>
|
||||
</unordered_list>
|
||||
<page_break>
|
||||
<picture><loc_112><loc_75><loc_446><loc_301><caption><loc_112><loc_303><loc_267><loc_309>Figure 4-68 Visual Explain with RCAC enabled</caption></picture>
|
||||
<picture><loc_53><loc_349><loc_414><loc_419><caption><loc_53><loc_421><loc_186><loc_427>Figure 4-69 Index advice with no RCAC</caption></picture>
|
||||
<page_footer><loc_175><loc_477><loc_428><loc_482>Chapter 4. Implementing Row and Column Access Control: Banking example</page_footer>
|
||||
|
||||
@ -1,74 +1,129 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<html>
|
||||
<head>
|
||||
<link rel="icon" type="image/png"
|
||||
href="https://raw.githubusercontent.com/docling-project/docling/refs/heads/main/docs/assets/logo.svg"/>
|
||||
<meta charset="UTF-8">
|
||||
<title>
|
||||
Powered by Docling
|
||||
</title>
|
||||
<style>
|
||||
<meta charset="UTF-8">
|
||||
<title>word_tables</title>
|
||||
<meta name="generator" content="Docling HTML Serializer">
|
||||
<style>
|
||||
html {
|
||||
background-color: LightGray;
|
||||
background-color: #f5f5f5;
|
||||
font-family: Arial, sans-serif;
|
||||
line-height: 1.6;
|
||||
}
|
||||
body {
|
||||
margin: 0 auto;
|
||||
width:800px;
|
||||
padding: 30px;
|
||||
background-color: White;
|
||||
font-family: Arial, sans-serif;
|
||||
box-shadow: 10px 10px 10px grey;
|
||||
max-width: 800px;
|
||||
margin: 0 auto;
|
||||
padding: 2rem;
|
||||
background-color: white;
|
||||
box-shadow: 0 0 10px rgba(0,0,0,0.1);
|
||||
}
|
||||
figure{
|
||||
display: block;
|
||||
width: 100%;
|
||||
margin: 0px;
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
h1, h2, h3, h4, h5, h6 {
|
||||
color: #333;
|
||||
margin-top: 1.5em;
|
||||
margin-bottom: 0.5em;
|
||||
}
|
||||
img {
|
||||
display: block;
|
||||
margin: auto;
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
max-width: 640px;
|
||||
max-height: 640px;
|
||||
h1 {
|
||||
font-size: 2em;
|
||||
border-bottom: 1px solid #eee;
|
||||
padding-bottom: 0.3em;
|
||||
}
|
||||
table {
|
||||
min-width:500px;
|
||||
background-color: White;
|
||||
border-collapse: collapse;
|
||||
cell-padding: 5px;
|
||||
margin: auto;
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
border-collapse: collapse;
|
||||
margin: 1em 0;
|
||||
width: 100%;
|
||||
}
|
||||
th, td {
|
||||
border: 1px solid black;
|
||||
padding: 8px;
|
||||
border: 1px solid #ddd;
|
||||
padding: 8px;
|
||||
text-align: left;
|
||||
}
|
||||
th {
|
||||
font-weight: bold;
|
||||
background-color: #f2f2f2;
|
||||
font-weight: bold;
|
||||
}
|
||||
table tr:nth-child(even) td{
|
||||
background-color: LightGray;
|
||||
figure {
|
||||
margin: 1.5em 0;
|
||||
text-align: center;
|
||||
}
|
||||
math annotation {
|
||||
display: none;
|
||||
figcaption {
|
||||
color: #666;
|
||||
font-style: italic;
|
||||
margin-top: 0.5em;
|
||||
}
|
||||
img {
|
||||
max-width: 100%;
|
||||
height: auto;
|
||||
}
|
||||
pre {
|
||||
background-color: #f6f8fa;
|
||||
border-radius: 3px;
|
||||
padding: 1em;
|
||||
overflow: auto;
|
||||
}
|
||||
code {
|
||||
font-family: monospace;
|
||||
background-color: #f6f8fa;
|
||||
padding: 0.2em 0.4em;
|
||||
border-radius: 3px;
|
||||
}
|
||||
pre code {
|
||||
background-color: transparent;
|
||||
padding: 0;
|
||||
}
|
||||
.formula {
|
||||
text-align: center;
|
||||
padding: 0.5em;
|
||||
margin: 1em 0;
|
||||
background-color: #f9f9f9;
|
||||
}
|
||||
.formula-not-decoded {
|
||||
background: repeating-linear-gradient(
|
||||
45deg, /* Angle of the stripes */
|
||||
LightGray, /* First color */
|
||||
LightGray 10px, /* Length of the first color */
|
||||
White 10px, /* Second color */
|
||||
White 20px /* Length of the second color */
|
||||
);
|
||||
margin: 0;
|
||||
text-align: center;
|
||||
text-align: center;
|
||||
padding: 0.5em;
|
||||
margin: 1em 0;
|
||||
background: repeating-linear-gradient(
|
||||
45deg,
|
||||
#f0f0f0,
|
||||
#f0f0f0 10px,
|
||||
#f9f9f9 10px,
|
||||
#f9f9f9 20px
|
||||
);
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
.page-break {
|
||||
page-break-after: always;
|
||||
border-top: 1px dashed #ccc;
|
||||
margin: 2em 0;
|
||||
}
|
||||
.key-value-region {
|
||||
background-color: #f9f9f9;
|
||||
padding: 1em;
|
||||
border-radius: 4px;
|
||||
margin: 1em 0;
|
||||
}
|
||||
.key-value-region dt {
|
||||
font-weight: bold;
|
||||
}
|
||||
.key-value-region dd {
|
||||
margin-left: 1em;
|
||||
margin-bottom: 0.5em;
|
||||
}
|
||||
.form-container {
|
||||
border: 1px solid #ddd;
|
||||
padding: 1em;
|
||||
border-radius: 4px;
|
||||
margin: 1em 0;
|
||||
}
|
||||
.form-item {
|
||||
margin-bottom: 0.5em;
|
||||
}
|
||||
.image-classification {
|
||||
font-size: 0.9em;
|
||||
color: #666;
|
||||
margin-top: 0.5em;
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class='page'>
|
||||
<h2>Test with tables</h2>
|
||||
<p>A uniform table</p>
|
||||
<table><tbody><tr><th>Header 0.0</th><th>Header 0.1</th><th>Header 0.2</th></tr><tr><td>Cell 1.0</td><td>Cell 1.1</td><td>Cell 1.2</td></tr><tr><td>Cell 2.0</td><td>Cell 2.1</td><td>Cell 2.2</td></tr></tbody></table>
|
||||
@ -86,4 +141,6 @@
|
||||
<table><tbody><tr><th>Header 0.0</th><th>Header 0.1</th><th>Header 0.2</th><th></th><th></th></tr><tr><td>Cell 1.0</td><td rowspan="2">Merged Cell 1.1 2.1</td><td>Cell 1.2</td><td></td><td></td></tr><tr><td>Cell 2.0</td><td>Cell 2.2</td><td></td><td></td></tr><tr><td>Cell 3.0</td><td rowspan="2">Merged Cell 3.1 4.1</td><td>Cell 3.2</td><td rowspan="3"></td><td></td></tr><tr><td>Cell 4.0</td><td>Cell 4.2</td><td rowspan="2">Merged Cell 4.4 5.4</td></tr><tr><td></td><td></td><td></td></tr><tr><td></td><td></td><td></td><td></td><td></td></tr><tr><td colspan="5"></td></tr><tr><td></td><td></td><td></td><td></td><td>Cell 8.4</td></tr></tbody></table>
|
||||
<p></p>
|
||||
<p></p>
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
@ -1 +1 @@
|
||||
{"_name": "", "type": "pdf-document", "description": {"title": null, "abstract": null, "authors": null, "affiliations": null, "subjects": null, "keywords": null, "publication_date": null, "languages": null, "license": null, "publishers": null, "url_refs": null, "references": null, "publication": null, "reference_count": null, "citation_count": null, "citation_date": null, "advanced": null, "analytics": null, "logs": [], "collection": null, "acquisition": null}, "file-info": {"filename": "ocr_test.pdf", "filename-prov": null, "document-hash": "80f38f5b87a84870681556176a9622186fd200dd32c5557be9e0c0af05b8bc61", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "14d896dc8bcb7ee7c08c0347eb6be8dcb92a3782501992f1ea14d2e58077d4e3", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [69.0, 688.5883585611979, 506.6666666666667, 767.2550252278646], "page": 1, "span": [0, 94], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "type": "paragraph", "payload": null, "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 841.9216918945312, "page": 1, "width": 595.201171875}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}
|
||||
{"_name": "", "type": "pdf-document", "description": {"title": null, "abstract": null, "authors": null, "affiliations": null, "subjects": null, "keywords": null, "publication_date": null, "languages": null, "license": null, "publishers": null, "url_refs": null, "references": null, "publication": null, "reference_count": null, "citation_count": null, "citation_date": null, "advanced": null, "analytics": null, "logs": [], "collection": null, "acquisition": null}, "file-info": {"filename": "ocr_test.pdf", "filename-prov": null, "document-hash": "80f38f5b87a84870681556176a9622186fd200dd32c5557be9e0c0af05b8bc61", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "14d896dc8bcb7ee7c08c0347eb6be8dcb92a3782501992f1ea14d2e58077d4e3", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [69.6796630536824, 689.0124221922704, 504.8720051760782, 764.9216921155637], "page": 1, "span": [0, 94], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "type": "paragraph", "payload": null, "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 841.9216918945312, "page": 1, "width": 595.201171875}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}
|
||||
File diff suppressed because one or more lines are too long
@ -1,2 +1,2 @@
|
||||
<doctag><text><loc_58><loc_44><loc_426><loc_91>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
|
||||
<doctag><text><loc_59><loc_46><loc_424><loc_91>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
|
||||
</doctag>
|
||||
@ -1 +1 @@
|
||||
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.0, "t": 767.2550252278646, "r": 506.6666666666667, "b": 688.5883585611979, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}
|
||||
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.6796630536824, "t": 764.9216921155637, "r": 504.8720051760782, "b": 689.0124221922704, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}
|
||||
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue
Block a user