295 lines
8.5 KiB
JSON
295 lines
8.5 KiB
JSON
|
{
|
||
|
|
"documents": [
|
||
|
|
{
|
||
|
|
"pdf_file": "sample_hierarchy_1.pdf",
|
||
|
|
"pages": [
|
||
|
|
{
|
||
|
|
"page_number": 1,
|
||
|
|
"blocks": [
|
||
|
|
{
|
||
|
|
"text": "Document Title",
|
||
|
|
"level": "H1",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 50.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 100.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Introduction Section",
|
||
|
|
"level": "H2",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 120.0,
|
||
|
|
"right": 450.0,
|
||
|
|
"bottom": 160.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "This is the introductory paragraph that provides background information about the document. It contains multiple sentences explaining the context and purpose of the content.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 170.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 250.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Main Content Section",
|
||
|
|
"level": "H2",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 270.0,
|
||
|
|
"right": 450.0,
|
||
|
|
"bottom": 310.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Subsection A",
|
||
|
|
"level": "H3",
|
||
|
|
"bbox": {
|
||
|
|
"left": 70.0,
|
||
|
|
"top": 330.0,
|
||
|
|
"right": 400.0,
|
||
|
|
"bottom": 360.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "This subsection contains detailed information about topic A. The content is organized hierarchically for better readability and structure.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 70.0,
|
||
|
|
"top": 370.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 450.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Subsection B",
|
||
|
|
"level": "H3",
|
||
|
|
"bbox": {
|
||
|
|
"left": 70.0,
|
||
|
|
"top": 470.0,
|
||
|
|
"right": 400.0,
|
||
|
|
"bottom": 500.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Further elaboration on topic B follows here. This demonstrates how hierarchical structure helps organize complex information.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 70.0,
|
||
|
|
"top": 510.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 570.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Conclusion",
|
||
|
|
"level": "H2",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 590.0,
|
||
|
|
"right": 350.0,
|
||
|
|
"bottom": 630.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "In conclusion, this document has demonstrated the importance of proper document hierarchy. Structured documents are easier to parse, understand, and process automatically.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 640.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 720.0
|
||
|
|
}
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"pdf_file": "sample_hierarchy_2.pdf",
|
||
|
|
"pages": [
|
||
|
|
{
|
||
|
|
"page_number": 1,
|
||
|
|
"blocks": [
|
||
|
|
{
|
||
|
|
"text": "Research Paper: Machine Learning",
|
||
|
|
"level": "H1",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 40.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 90.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Abstract",
|
||
|
|
"level": "H2",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 110.0,
|
||
|
|
"right": 350.0,
|
||
|
|
"bottom": 150.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Machine learning is a subset of artificial intelligence that focuses on enabling computer systems to learn from data. This paper provides a comprehensive overview of modern ML techniques.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 160.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 240.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "1. Introduction",
|
||
|
|
"level": "H2",
|
||
|
|
"bbox": {
|
||
|
|
"left": 50.0,
|
||
|
|
"top": 260.0,
|
||
|
|
"right": 400.0,
|
||
|
|
"bottom": 300.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "1.1 Background",
|
||
|
|
"level": "H3",
|
||
|
|
"bbox": {
|
||
|
|
"left": 70.0,
|
||
|
|
"top": 320.0,
|
||
|
|
"right": 400.0,
|
||
|
|
"bottom": 360.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "The field of machine learning has grown exponentially over the past decade. Novel algorithms and abundant data have enabled unprecedented advancements.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 70.0,
|
||
|
|
"top": 370.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 440.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "1.2 Problem Statement",
|
||
|
|
"level": "H3",
|
||
|
|
"bbox": {
|
||
|
|
"left": 70.0,
|
||
|
|
"top": 460.0,
|
||
|
|
"right": 400.0,
|
||
|
|
"bottom": 500.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Despite the progress made, several challenges remain in the field of machine learning. This work addresses key limitations in current approaches.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 70.0,
|
||
|
|
"top": 510.0,
|
||
|
|
"right": 550.0,
|
||
|
|
"bottom": 580.0
|
||
|
|
}
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"pdf_file": "sample_hierarchy_3.pdf",
|
||
|
|
"pages": [
|
||
|
|
{
|
||
|
|
"page_number": 1,
|
||
|
|
"blocks": [
|
||
|
|
{
|
||
|
|
"text": "Technical Documentation",
|
||
|
|
"level": "H1",
|
||
|
|
"bbox": {
|
||
|
|
"left": 40.0,
|
||
|
|
"top": 30.0,
|
||
|
|
"right": 560.0,
|
||
|
|
"bottom": 80.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Installation Guide",
|
||
|
|
"level": "H2",
|
||
|
|
"bbox": {
|
||
|
|
"left": 40.0,
|
||
|
|
"top": 100.0,
|
||
|
|
"right": 400.0,
|
||
|
|
"bottom": 140.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Prerequisites",
|
||
|
|
"level": "H3",
|
||
|
|
"bbox": {
|
||
|
|
"left": 60.0,
|
||
|
|
"top": 160.0,
|
||
|
|
"right": 350.0,
|
||
|
|
"bottom": 195.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Before beginning the installation process, ensure you have the following requirements met. Operating system compatibility and necessary dependencies must be verified.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 60.0,
|
||
|
|
"top": 205.0,
|
||
|
|
"right": 560.0,
|
||
|
|
"bottom": 280.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "System Requirements",
|
||
|
|
"level": "H4",
|
||
|
|
"bbox": {
|
||
|
|
"left": 80.0,
|
||
|
|
"top": 300.0,
|
||
|
|
"right": 400.0,
|
||
|
|
"bottom": 335.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Minimum: 4GB RAM, 2GHz processor. Recommended: 8GB RAM, modern multi-core processor with SSD.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 80.0,
|
||
|
|
"top": 345.0,
|
||
|
|
"right": 560.0,
|
||
|
|
"bottom": 400.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Installation Steps",
|
||
|
|
"level": "H3",
|
||
|
|
"bbox": {
|
||
|
|
"left": 60.0,
|
||
|
|
"top": 420.0,
|
||
|
|
"right": 350.0,
|
||
|
|
"bottom": 455.0
|
||
|
|
}
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"text": "Follow these numbered steps in order to complete the installation successfully. Each step builds on the previous one.",
|
||
|
|
"level": "Body",
|
||
|
|
"bbox": {
|
||
|
|
"left": 60.0,
|
||
|
|
"top": 465.0,
|
||
|
|
"right": 560.0,
|
||
|
|
"bottom": 520.0
|
||
|
|
}
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|