|
|
@@ -1,69 +1,118 @@
|
|
|
-# Overview
|
|
|
+# MinerU Output Files Documentation
|
|
|
|
|
|
-After executing the `mineru` command, in addition to outputting files related to markdown, several other files unrelated to markdown will also be generated. These files will be introduced one by one.
|
|
|
+## Overview
|
|
|
|
|
|
-## some_pdf_layout.pdf
|
|
|
+After executing the `mineru` command, in addition to the main markdown file output, multiple auxiliary files are generated for debugging, quality inspection, and further processing. These files include:
|
|
|
|
|
|
-Each page's layout consists of one or more bounding boxes. The number in the top-right corner of each box indicates the reading order. Additionally, different content blocks are highlighted with distinct background colors within the layout.pdf.
|
|
|
-
|
|
|
+- **Visual debugging files**: Help users intuitively understand the document parsing process and results
|
|
|
+- **Structured data files**: Contain detailed parsing data for secondary development
|
|
|
|
|
|
-## some_pdf_spans.pdf(Applicable only to the pipeline backend)
|
|
|
+The following sections provide detailed descriptions of each file's purpose and format.
|
|
|
|
|
|
-All spans on the page are drawn with different colored line frames according to the span type. This file can be used for quality control, allowing for quick identification of issues such as missing text or unrecognized inline formulas.
|
|
|
+## Visual Debugging Files
|
|
|
|
|
|
-
|
|
|
+### Layout Analysis File (layout.pdf)
|
|
|
|
|
|
-## some_pdf_model.json(Applicable only to the pipeline backend)
|
|
|
+**File naming format**: `{original_filename}_layout.pdf`
|
|
|
|
|
|
-### Structure Definition
|
|
|
+**Functionality**:
|
|
|
+
|
|
|
+- Visualizes layout analysis results for each page
|
|
|
+- Numbers in the top-right corner of each detection box indicate reading order
|
|
|
+- Different background colors distinguish different types of content blocks
|
|
|
+
|
|
|
+**Use cases**:
|
|
|
+
|
|
|
+- Check if layout analysis is correct
|
|
|
+- Verify if reading order is reasonable
|
|
|
+- Debug layout-related issues
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+### Text Spans File (spans.pdf)
|
|
|
+
|
|
|
+> [!NOTE]
|
|
|
+> Only applicable to pipeline backend
|
|
|
+
|
|
|
+**File naming format**: `{original_filename}_spans.pdf`
|
|
|
+
|
|
|
+**Functionality**:
|
|
|
+
|
|
|
+- Uses different colored line boxes to annotate page content based on span type
|
|
|
+- Used for quality inspection and issue troubleshooting
|
|
|
+
|
|
|
+**Use cases**:
|
|
|
+
|
|
|
+- Quickly troubleshoot text loss issues
|
|
|
+- Check inline formula recognition
|
|
|
+- Verify text segmentation accuracy
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+## Structured Data Files
|
|
|
+
|
|
|
+### Model Inference Results (model.json)
|
|
|
+
|
|
|
+> [!NOTE]
|
|
|
+> Only applicable to pipeline backend
|
|
|
+
|
|
|
+**File naming format**: `{original_filename}_model.json`
|
|
|
+
|
|
|
+#### Data Structure Definition
|
|
|
|
|
|
```python
|
|
|
from pydantic import BaseModel, Field
|
|
|
from enum import IntEnum
|
|
|
|
|
|
class CategoryType(IntEnum):
|
|
|
- title = 0 # Title
|
|
|
- plain_text = 1 # Text
|
|
|
- abandon = 2 # Includes headers, footers, page numbers, and page annotations
|
|
|
- figure = 3 # Image
|
|
|
- figure_caption = 4 # Image description
|
|
|
- table = 5 # Table
|
|
|
- table_caption = 6 # Table description
|
|
|
- table_footnote = 7 # Table footnote
|
|
|
- isolate_formula = 8 # Block formula
|
|
|
- formula_caption = 9 # Formula label
|
|
|
-
|
|
|
- embedding = 13 # Inline formula
|
|
|
- isolated = 14 # Block formula
|
|
|
- text = 15 # OCR recognition result
|
|
|
-
|
|
|
+ """Content category enumeration"""
|
|
|
+ title = 0 # Title
|
|
|
+ plain_text = 1 # Text
|
|
|
+ abandon = 2 # Including headers, footers, page numbers, and page annotations
|
|
|
+ figure = 3 # Image
|
|
|
+ figure_caption = 4 # Image caption
|
|
|
+ table = 5 # Table
|
|
|
+ table_caption = 6 # Table caption
|
|
|
+ table_footnote = 7 # Table footnote
|
|
|
+ isolate_formula = 8 # Interline formula
|
|
|
+ formula_caption = 9 # Interline formula number
|
|
|
+ embedding = 13 # Inline formula
|
|
|
+ isolated = 14 # Interline formula
|
|
|
+ text = 15 # OCR recognition result
|
|
|
|
|
|
class PageInfo(BaseModel):
|
|
|
- page_no: int = Field(description="Page number, the first page is 0", ge=0)
|
|
|
+ """Page information"""
|
|
|
+ page_no: int = Field(description="Page number, first page is 0", ge=0)
|
|
|
height: int = Field(description="Page height", gt=0)
|
|
|
width: int = Field(description="Page width", ge=0)
|
|
|
|
|
|
class ObjectInferenceResult(BaseModel):
|
|
|
+ """Object recognition result"""
|
|
|
category_id: CategoryType = Field(description="Category", ge=0)
|
|
|
- poly: list[float] = Field(description="Quadrilateral coordinates, representing the coordinates of the top-left, top-right, bottom-right, and bottom-left points respectively")
|
|
|
- score: float = Field(description="Confidence of the inference result")
|
|
|
+ poly: list[float] = Field(description="Quadrilateral coordinates, format: [x0,y0,x1,y1,x2,y2,x3,y3]")
|
|
|
+ score: float = Field(description="Confidence score of inference result")
|
|
|
latex: str | None = Field(description="LaTeX parsing result", default=None)
|
|
|
html: str | None = Field(description="HTML parsing result", default=None)
|
|
|
|
|
|
class PageInferenceResults(BaseModel):
|
|
|
- layout_dets: list[ObjectInferenceResult] = Field(description="Page recognition results", ge=0)
|
|
|
- page_info: PageInfo = Field(description="Page metadata")
|
|
|
+ """Page inference results"""
|
|
|
+ layout_dets: list[ObjectInferenceResult] = Field(description="Page recognition results")
|
|
|
+ page_info: PageInfo = Field(description="Page metadata")
|
|
|
|
|
|
-
|
|
|
-# The inference results of all pages, ordered by page number, are stored in a list as the inference results of MinerU
|
|
|
+# Complete inference results
|
|
|
inference_result: list[PageInferenceResults] = []
|
|
|
-
|
|
|
```
|
|
|
|
|
|
-The format of the poly coordinates is \[x0, y0, x1, y1, x2, y2, x3, y3\], representing the coordinates of the top-left, top-right, bottom-right, and bottom-left points respectively.
|
|
|
-
|
|
|
+#### Coordinate System Description
|
|
|
|
|
|
-### example
|
|
|
+`poly` coordinate format: `[x0, y0, x1, y1, x2, y2, x3, y3]`
|
|
|
+
|
|
|
+- Represents coordinates of top-left, top-right, bottom-right, bottom-left points respectively
|
|
|
+- Coordinate origin is at the top-left corner of the page
|
|
|
+
|
|
|
+
|
|
|
+
|
|
|
+#### Sample Data
|
|
|
|
|
|
```json
|
|
|
[
|
|
|
@@ -116,142 +165,127 @@ The format of the poly coordinates is \[x0, y0, x1, y1, x2, y2, x3, y3\], repres
|
|
|
]
|
|
|
```
|
|
|
|
|
|
-## some_pdf_model_output.txt (Applicable only to the VLM backend)
|
|
|
-
|
|
|
-This file contains the output of the VLM model, with each page's output separated by `----`.
|
|
|
-Each page's output consists of text blocks starting with `<|box_start|>` and ending with `<|md_end|>`.
|
|
|
-The meaning of each field is as follows:
|
|
|
-- `<|box_start|>x0 y0 x1 y1<|box_end|>`
|
|
|
- x0 y0 x1 y1 represent the coordinates of a quadrilateral, indicating the top-left and bottom-right points. The values are based on a normalized page size of 1000x1000.
|
|
|
-- `<|ref_start|>type<|ref_end|>`
|
|
|
- `type` indicates the block type. Possible values are:
|
|
|
- ```json
|
|
|
- {
|
|
|
- "text": "Text",
|
|
|
- "title": "Title",
|
|
|
- "image": "Image",
|
|
|
- "image_caption": "Image Caption",
|
|
|
- "image_footnote": "Image Footnote",
|
|
|
- "table": "Table",
|
|
|
- "table_caption": "Table Caption",
|
|
|
- "table_footnote": "Table Footnote",
|
|
|
- "equation": "Interline Equation"
|
|
|
- }
|
|
|
- ```
|
|
|
-- `<|md_start|>Markdown content<|md_end|>`
|
|
|
- This field contains the Markdown content of the block. If `type` is `text`, the end of the text may contain the `<|txt_contd|>` tag, indicating that this block can be connected with the following `text` block(s).
|
|
|
- If `type` is `table`, the content is in `otsl` format and needs to be converted into HTML for rendering in Markdown.
|
|
|
-
|
|
|
-## some_pdf_middle.json
|
|
|
-
|
|
|
-| Field Name | Description |
|
|
|
-|:---------------| :------------------------------------------------------------------------------------------------------------- |
|
|
|
-| pdf_info | list, each element is a dict representing the parsing result of each PDF page, see the table below for details |
|
|
|
-| \_backend | pipeline \| vlm, used to indicate the mode used in this intermediate parsing state |
|
|
|
-| \_version_name | string, indicates the version of mineru used in this parsing |
|
|
|
-
|
|
|
-<br>
|
|
|
-
|
|
|
-**pdf_info**
|
|
|
+### VLM Output Results (model_output.txt)
|
|
|
|
|
|
-Field structure description
|
|
|
+> [!NOTE]
|
|
|
+> Only applicable to VLM backend
|
|
|
|
|
|
-| Field Name | Description |
|
|
|
-| :------------------ | :----------------------------------------------------------------------------------------------------------------- |
|
|
|
-| preproc_blocks | Intermediate result after PDF preprocessing, not yet segmented |
|
|
|
-| layout_bboxes | Layout segmentation results, containing layout direction (vertical, horizontal), and bbox, sorted by reading order |
|
|
|
-| page_idx | Page number, starting from 0 |
|
|
|
-| page_size | Page width and height |
|
|
|
-| \_layout_tree | Layout tree structure |
|
|
|
-| images | list, each element is a dict representing an img_block |
|
|
|
-| tables | list, each element is a dict representing a table_block |
|
|
|
-| interline_equations | list, each element is a dict representing an interline_equation_block |
|
|
|
-| discarded_blocks | List, block information returned by the model that needs to be dropped |
|
|
|
-| para_blocks | Result after segmenting preproc_blocks |
|
|
|
+**File naming format**: `{original_filename}_model_output.txt`
|
|
|
|
|
|
-In the above table, `para_blocks` is an array of dicts, each dict representing a block structure. A block can support up to one level of nesting.
|
|
|
+#### File Format Description
|
|
|
|
|
|
-<br>
|
|
|
+- Uses `----` to separate output results for each page
|
|
|
+- Each page contains multiple text blocks starting with `<|box_start|>` and ending with `<|md_end|>`
|
|
|
|
|
|
-**block**
|
|
|
+#### Field Meanings
|
|
|
|
|
|
-The outer block is referred to as a first-level block, and the fields in the first-level block include:
|
|
|
+| Tag | Format | Description |
|
|
|
+|-----|--------|-------------|
|
|
|
+| Bounding box | `<\|box_start\|>x0 y0 x1 y1<\|box_end\|>` | Quadrilateral coordinates (top-left, bottom-right points), coordinate values after scaling page to 1000×1000 |
|
|
|
+| Type tag | `<\|ref_start\|>type<\|ref_end\|>` | Content block type identifier |
|
|
|
+| Content | `<\|md_start\|>markdown content<\|md_end\|>` | Markdown content of the block |
|
|
|
|
|
|
-| Field Name | Description |
|
|
|
-| :--------- | :------------------------------------------------------------- |
|
|
|
-| type | Block type (table\|image) |
|
|
|
-| bbox | Block bounding box coordinates |
|
|
|
-| blocks | list, each element is a dict representing a second-level block |
|
|
|
+#### Supported Content Types
|
|
|
+
|
|
|
+```json
|
|
|
+{
|
|
|
+ "text": "Text",
|
|
|
+ "title": "Title",
|
|
|
+ "image": "Image",
|
|
|
+ "image_caption": "Image caption",
|
|
|
+ "image_footnote": "Image footnote",
|
|
|
+ "table": "Table",
|
|
|
+ "table_caption": "Table caption",
|
|
|
+ "table_footnote": "Table footnote",
|
|
|
+ "equation": "Interline formula"
|
|
|
+}
|
|
|
+```
|
|
|
|
|
|
-<br>
|
|
|
-There are only two types of first-level blocks: "table" and "image". All other blocks are second-level blocks.
|
|
|
+#### Special Tags
|
|
|
|
|
|
-The fields in a second-level block include:
|
|
|
+- `<|txt_contd|>`: Appears at the end of text, indicating that this text block can be connected with subsequent text blocks
|
|
|
+- Table content uses `otsl` format and needs to be converted to HTML for rendering in Markdown
|
|
|
|
|
|
-| Field Name | Description |
|
|
|
-| :--------- | :---------------------------------------------------------------------------------------------------------- |
|
|
|
-| type | Block type |
|
|
|
-| bbox | Block bounding box coordinates |
|
|
|
-| lines | list, each element is a dict representing a line, used to describe the composition of a line of information |
|
|
|
+### Intermediate Processing Results (middle.json)
|
|
|
|
|
|
-Detailed explanation of second-level block types
|
|
|
+**File naming format**: `{original_filename}_middle.json`
|
|
|
|
|
|
-| type | Description |
|
|
|
-| :----------------- | :--------------------- |
|
|
|
-| image_body | Main body of the image |
|
|
|
-| image_caption | Image description text |
|
|
|
-| image_footnote | Image footnote |
|
|
|
-| table_body | Main body of the table |
|
|
|
-| table_caption | Table description text |
|
|
|
-| table_footnote | Table footnote |
|
|
|
-| text | Text block |
|
|
|
-| title | Title block |
|
|
|
-| index | Index block |
|
|
|
-| list | List block |
|
|
|
-| interline_equation | Block formula |
|
|
|
+#### Top-level Structure
|
|
|
|
|
|
-<br>
|
|
|
+| Field Name | Type | Description |
|
|
|
+|------------|------|-------------|
|
|
|
+| `pdf_info` | `list[dict]` | Array of parsing results for each page |
|
|
|
+| `_backend` | `string` | Parsing mode: `pipeline` or `vlm` |
|
|
|
+| `_version_name` | `string` | MinerU version number |
|
|
|
|
|
|
-**line**
|
|
|
+#### Page Information Structure (pdf_info)
|
|
|
|
|
|
-The field format of a line is as follows:
|
|
|
+| Field Name | Description |
|
|
|
+|------------|-------------|
|
|
|
+| `preproc_blocks` | Unsegmented intermediate results after PDF preprocessing |
|
|
|
+| `layout_bboxes` | Layout segmentation results, including layout direction and bounding boxes, sorted by reading order |
|
|
|
+| `page_idx` | Page number, starting from 0 |
|
|
|
+| `page_size` | Page width and height `[width, height]` |
|
|
|
+| `_layout_tree` | Layout tree structure |
|
|
|
+| `images` | Image block information list |
|
|
|
+| `tables` | Table block information list |
|
|
|
+| `interline_equations` | Interline formula block information list |
|
|
|
+| `discarded_blocks` | Block information to be discarded |
|
|
|
+| `para_blocks` | Content block results after segmentation |
|
|
|
|
|
|
-| Field Name | Description |
|
|
|
-| :--------- | :------------------------------------------------------------------------------------------------------ |
|
|
|
-| bbox | Bounding box coordinates of the line |
|
|
|
-| spans | list, each element is a dict representing a span, used to describe the composition of the smallest unit |
|
|
|
-
|
|
|
-<br>
|
|
|
+#### Block Structure Hierarchy
|
|
|
|
|
|
-**span**
|
|
|
+```
|
|
|
+Level 1 blocks (table | image)
|
|
|
+└── Level 2 blocks
|
|
|
+ └── Lines
|
|
|
+ └── Spans
|
|
|
+```
|
|
|
|
|
|
-| Field Name | Description |
|
|
|
-| :------------------ | :------------------------------------------------------------------------------------------------------- |
|
|
|
-| bbox | Bounding box coordinates of the span |
|
|
|
-| type | Type of the span |
|
|
|
-| content \| img_path | Text spans use content, chart spans use img_path to store the actual text or screenshot path information |
|
|
|
+#### Level 1 Block Fields
|
|
|
|
|
|
-The types of spans are as follows:
|
|
|
+| Field Name | Description |
|
|
|
+|------------|-------------|
|
|
|
+| `type` | Block type: `table` or `image` |
|
|
|
+| `bbox` | Rectangular box coordinates of the block `[x0, y0, x1, y1]` |
|
|
|
+| `blocks` | List of contained level 2 blocks |
|
|
|
|
|
|
-| type | Description |
|
|
|
-| :----------------- | :------------- |
|
|
|
-| image | Image |
|
|
|
-| table | Table |
|
|
|
-| text | Text |
|
|
|
-| inline_equation | Inline formula |
|
|
|
-| interline_equation | Block formula |
|
|
|
+#### Level 2 Block Fields
|
|
|
|
|
|
-**Summary**
|
|
|
+| Field Name | Description |
|
|
|
+|------------|-------------|
|
|
|
+| `type` | Block type (see table below) |
|
|
|
+| `bbox` | Rectangular box coordinates of the block |
|
|
|
+| `lines` | List of contained line information |
|
|
|
|
|
|
-A span is the smallest storage unit for all elements.
|
|
|
+#### Level 2 Block Types
|
|
|
|
|
|
-The elements stored within para_blocks are block information.
|
|
|
+| Type | Description |
|
|
|
+|------|-------------|
|
|
|
+| `image_body` | Image body |
|
|
|
+| `image_caption` | Image caption text |
|
|
|
+| `image_footnote` | Image footnote |
|
|
|
+| `table_body` | Table body |
|
|
|
+| `table_caption` | Table caption text |
|
|
|
+| `table_footnote` | Table footnote |
|
|
|
+| `text` | Text block |
|
|
|
+| `title` | Title block |
|
|
|
+| `index` | Index block |
|
|
|
+| `list` | List block |
|
|
|
+| `interline_equation` | Interline formula block |
|
|
|
|
|
|
-The block structure is as follows:
|
|
|
+#### Line and Span Structure
|
|
|
|
|
|
-First-level block (if any) -> Second-level block -> Line -> Span
|
|
|
+**Line fields**:
|
|
|
+- `bbox`: Rectangular box coordinates of the line
|
|
|
+- `spans`: List of contained spans
|
|
|
|
|
|
-### example
|
|
|
+**Span fields**:
|
|
|
+- `bbox`: Rectangular box coordinates of the span
|
|
|
+- `type`: Span type (`image`, `table`, `text`, `inline_equation`, `interline_equation`)
|
|
|
+- `content` | `img_path`: Text content or image path
|
|
|
+
|
|
|
+#### Sample Data
|
|
|
|
|
|
```json
|
|
|
{
|
|
|
@@ -354,29 +388,37 @@ First-level block (if any) -> Second-level block -> Line -> Span
|
|
|
}
|
|
|
```
|
|
|
|
|
|
+### Content List (content_list.json)
|
|
|
+
|
|
|
+**File naming format**: `{original_filename}_content_list.json`
|
|
|
+
|
|
|
+#### Functionality
|
|
|
+
|
|
|
+This is a simplified version of `middle.json` that stores all readable content blocks in reading order as a flat structure, removing complex layout information for easier subsequent processing.
|
|
|
+
|
|
|
+#### Content Types
|
|
|
|
|
|
-## some_pdf_content_list.json
|
|
|
+| Type | Description |
|
|
|
+|------|-------------|
|
|
|
+| `image` | Image |
|
|
|
+| `table` | Table |
|
|
|
+| `text` | Text/Title |
|
|
|
+| `equation` | Interline formula |
|
|
|
|
|
|
-This file is a JSON array where each element is a dict storing all readable content blocks in the document in reading order.
|
|
|
-`content_list` can be viewed as a simplified version of `middle.json`. The content block types are mostly consistent with those in `middle.json`, but layout information is not included.
|
|
|
+#### Text Level Identification
|
|
|
|
|
|
-The content has the following types:
|
|
|
+Text levels are distinguished through the `text_level` field:
|
|
|
|
|
|
-| type | desc |
|
|
|
-|:---------|:--------------|
|
|
|
-| image | Image |
|
|
|
-| table | Table |
|
|
|
-| text | Text / Title |
|
|
|
-| equation | Block formula |
|
|
|
+- No `text_level` or `text_level: 0`: Body text
|
|
|
+- `text_level: 1`: Level 1 heading
|
|
|
+- `text_level: 2`: Level 2 heading
|
|
|
+- And so on...
|
|
|
|
|
|
-Please note that both `title` and text blocks in `content_list` are uniformly represented using the text type. The `text_level` field is used to distinguish the hierarchy of text blocks:
|
|
|
-- A block without the `text_level` field or with `text_level=0` represents body text.
|
|
|
-- A block with `text_level=1` represents a level-1 heading.
|
|
|
-- A block with `text_level=2` represents a level-2 heading, and so on.
|
|
|
+#### Common Fields
|
|
|
|
|
|
-Each content contains the `page_idx` field, indicating the page number (starting from 0) where the content block resides.
|
|
|
+All content blocks include a `page_idx` field indicating the page number (starting from 0).
|
|
|
|
|
|
-### example
|
|
|
+#### Sample Data
|
|
|
|
|
|
```json
|
|
|
[
|
|
|
@@ -437,4 +479,13 @@ Each content contains the `page_idx` field, indicating the page number (starting
|
|
|
"page_idx": 5
|
|
|
}
|
|
|
]
|
|
|
-```
|
|
|
+```
|
|
|
+
|
|
|
+## Summary
|
|
|
+
|
|
|
+The above files constitute MinerU's complete output results. Users can choose appropriate files for subsequent processing based on their needs:
|
|
|
+
|
|
|
+- **Model outputs**: Use raw outputs (model.json, model_output.txt)
|
|
|
+- **Debugging and verification**: Use visualization files (layout.pdf, spans.pdf)
|
|
|
+- **Content extraction**: Use simplified files (*.md, content_list.json)
|
|
|
+- **Secondary development**: Use structured files (middle.json)
|
myhloli