opendataloader-pdf 0.0.14__py3-none-any.whl → 0.0.16__py3-none-any.whl
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 opendataloader-pdf might be problematic. Click here for more details.
- opendataloader_pdf/jar/opendataloader-pdf-cli.jar +0 -0
- opendataloader_pdf/wrapper.py +11 -7
- {opendataloader_pdf-0.0.14.dist-info → opendataloader_pdf-0.0.16.dist-info}/METADATA +140 -81
- {opendataloader_pdf-0.0.14.dist-info → opendataloader_pdf-0.0.16.dist-info}/RECORD +6 -6
- {opendataloader_pdf-0.0.14.dist-info → opendataloader_pdf-0.0.16.dist-info}/WHEEL +0 -0
- {opendataloader_pdf-0.0.14.dist-info → opendataloader_pdf-0.0.16.dist-info}/top_level.txt +0 -0
|
Binary file
|
opendataloader_pdf/wrapper.py
CHANGED
|
@@ -12,11 +12,12 @@ def run(
|
|
|
12
12
|
input_path: str,
|
|
13
13
|
output_folder: str = None,
|
|
14
14
|
password: str = None,
|
|
15
|
+
replace_invalid_chars: str = None,
|
|
15
16
|
generate_markdown: bool = False,
|
|
16
17
|
generate_html: bool = False,
|
|
17
18
|
generate_annotated_pdf: bool = False,
|
|
18
19
|
keep_line_breaks: bool = False,
|
|
19
|
-
|
|
20
|
+
content_safety_off: str = None,
|
|
20
21
|
html_in_markdown: bool = False,
|
|
21
22
|
add_image_to_markdown: bool = False,
|
|
22
23
|
debug: bool = False,
|
|
@@ -28,6 +29,7 @@ def run(
|
|
|
28
29
|
input_path: Path to the input PDF file or folder.
|
|
29
30
|
output_folder: Path to the output folder. Defaults to the input folder.
|
|
30
31
|
password: Password for the PDF file.
|
|
32
|
+
replace_invalid_chars: Character to replace invalid or unrecognized characters (e.g., �, \u0000) with.
|
|
31
33
|
generate_markdown: If True, generates a Markdown output file.
|
|
32
34
|
generate_html: If True, generates an HTML output file.
|
|
33
35
|
generate_annotated_pdf: If True, generates an annotated PDF output file.
|
|
@@ -49,9 +51,11 @@ def run(
|
|
|
49
51
|
|
|
50
52
|
args = []
|
|
51
53
|
if output_folder:
|
|
52
|
-
args.extend(["--
|
|
54
|
+
args.extend(["--output-dir", output_folder])
|
|
53
55
|
if password:
|
|
54
56
|
args.extend(["--password", password])
|
|
57
|
+
if replace_invalid_chars:
|
|
58
|
+
args.extend(["--replace-invalid-chars", replace_invalid_chars])
|
|
55
59
|
if generate_markdown:
|
|
56
60
|
args.append("--markdown")
|
|
57
61
|
if generate_html:
|
|
@@ -59,13 +63,13 @@ def run(
|
|
|
59
63
|
if generate_annotated_pdf:
|
|
60
64
|
args.append("--pdf")
|
|
61
65
|
if keep_line_breaks:
|
|
62
|
-
args.append("--
|
|
63
|
-
if
|
|
64
|
-
args.append("--
|
|
66
|
+
args.append("--keep-line-breaks")
|
|
67
|
+
if content_safety_off:
|
|
68
|
+
args.append(["--content-safety-off", content_safety_off])
|
|
65
69
|
if html_in_markdown:
|
|
66
|
-
args.append("--
|
|
70
|
+
args.append("--markdown-with-html")
|
|
67
71
|
if add_image_to_markdown:
|
|
68
|
-
args.append("--
|
|
72
|
+
args.append("--markdown-with-images")
|
|
69
73
|
|
|
70
74
|
args.append(input_path)
|
|
71
75
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: opendataloader-pdf
|
|
3
|
-
Version: 0.0.
|
|
3
|
+
Version: 0.0.16
|
|
4
4
|
Summary: A Python wrapper for the opendataloader-pdf Java CLI.
|
|
5
5
|
Home-page: https://github.com/opendataloader-project/opendataloader-pdf
|
|
6
6
|
Author: opendataloader-project
|
|
@@ -10,6 +10,7 @@ Classifier: Programming Language :: Python :: 3
|
|
|
10
10
|
Classifier: Operating System :: OS Independent
|
|
11
11
|
Requires-Python: >=3.7
|
|
12
12
|
Description-Content-Type: text/markdown
|
|
13
|
+
Requires-Dist: importlib_resources; python_version < "3.9"
|
|
13
14
|
Dynamic: author
|
|
14
15
|
Dynamic: author-email
|
|
15
16
|
Dynamic: classifier
|
|
@@ -17,24 +18,26 @@ Dynamic: description
|
|
|
17
18
|
Dynamic: description-content-type
|
|
18
19
|
Dynamic: home-page
|
|
19
20
|
Dynamic: license
|
|
21
|
+
Dynamic: requires-dist
|
|
20
22
|
Dynamic: requires-python
|
|
21
23
|
Dynamic: summary
|
|
22
24
|
|
|
23
25
|
# OpenDataLoader PDF
|
|
24
26
|
|
|
25
27
|
|
|
26
|
-
[](https://
|
|
28
|
+
[](https://github.com/opendataloader-project/opendataloader-pdf/blob/main/LICENSE)
|
|
27
29
|
|
|
28
30
|
|
|
29
|
-
[](https://search.maven.org/artifact/org.opendataloader/opendataloader-pdf-core)
|
|
30
32
|
[](https://pypi.org/project/opendataloader-pdf/)
|
|
33
|
+
[](https://www.npmjs.com/package/@opendataloader/pdf)
|
|
31
34
|
[](https://github.com/opendataloader-project/opendataloader-pdf/pkgs/container/opendataloader-pdf-cli)
|
|
32
35
|
[](https://app.codecov.io/gh/opendataloader-project/opendataloader-pdf)
|
|
33
36
|
[](https://cla-assistant.io/opendataloader-project/opendataloader-pdf)
|
|
34
37
|
|
|
35
38
|
<br/>
|
|
36
39
|
|
|
37
|
-
**Safe, Open, High-Performance —
|
|
40
|
+
**Safe, Open, High-Performance — PDF for AI**
|
|
38
41
|
|
|
39
42
|
OpenDataLoader-PDF converts PDFs into JSON, Markdown or Html — ready to feed into modern AI stacks (LLMs, vector search, and RAG).
|
|
40
43
|
|
|
@@ -48,22 +51,23 @@ AI-safety is enabled by default and automatically filters likely prompt-injectio
|
|
|
48
51
|
|
|
49
52
|
- 🧾 **Rich, Structured Output** — JSON, Markdown or Html
|
|
50
53
|
- 🧩 **Layout Reconstruction** — Headings, Lists, Tables, Images, Reading Order
|
|
51
|
-
- 🔒 **Local-First Privacy** — Runs fully on your machine
|
|
52
54
|
- ⚡ **Fast & Lightweight** — Rule-Based Heuristic, High-Throughput, No GPU
|
|
53
|
-
-
|
|
54
|
-
-
|
|
55
|
+
- 🔒 **Local-First Privacy** — Runs fully on your machine
|
|
56
|
+
- 🛡️ **AI-Safety** — Auto-Filters likely prompt-injection content - [Learn more about AI-Safety](https://github.com/opendataloader-project/opendataloader-pdf/blob/main/docs/AI_SAFETY.md)
|
|
55
57
|
- 🖍️ **Annotated PDF Visualization** — See detected structures overlaid on the original
|
|
56
58
|
|
|
57
|
-
|
|
59
|
+
[Download Annotated PDF Sample](https://raw.githubusercontent.com/opendataloader-project/opendataloader-pdf/main/resources/1901.03003_annotated.pdf)
|
|
60
|
+
|
|
61
|
+
|
|
58
62
|
|
|
59
63
|
<br/>
|
|
60
64
|
|
|
61
65
|
## 🚀 Upcoming Features
|
|
62
66
|
|
|
63
|
-
- 🖨️ **OCR for scanned PDFs** — image-only pages
|
|
64
|
-
- 🧠 **Table AI option** —
|
|
65
|
-
-
|
|
66
|
-
- 🛡️ **AI
|
|
67
|
+
- 🖨️ **OCR for scanned PDFs** — Extract data from image-only pages
|
|
68
|
+
- 🧠 **Table AI option** — Higher accuracy for tables with borderless or merged cells
|
|
69
|
+
- ⚡ **Performance Benchmarks** — Transparent evaluations with open datasets and metrics, reported regularly
|
|
70
|
+
- 🛡️ **AI Red Teaming** — Transparent adversarial benchmarks with datasets and metrics, reported regularly
|
|
67
71
|
|
|
68
72
|
<br/>
|
|
69
73
|
|
|
@@ -79,7 +83,7 @@ AI-safety is enabled by default and automatically filters likely prompt-injectio
|
|
|
79
83
|
### Installation
|
|
80
84
|
|
|
81
85
|
```sh
|
|
82
|
-
pip install -U opendataloader-pdf
|
|
86
|
+
pip install -U opendataloader-pdf
|
|
83
87
|
```
|
|
84
88
|
|
|
85
89
|
### Usage
|
|
@@ -91,8 +95,8 @@ pip install -U opendataloader-pdf importlib_resources
|
|
|
91
95
|
import opendataloader_pdf
|
|
92
96
|
|
|
93
97
|
opendataloader_pdf.run(
|
|
94
|
-
input_path="path
|
|
95
|
-
output_folder="path
|
|
98
|
+
input_path="path-to-document.pdf",
|
|
99
|
+
output_folder="path-to-output",
|
|
96
100
|
generate_markdown=True,
|
|
97
101
|
generate_html=True,
|
|
98
102
|
generate_annotated_pdf=True,
|
|
@@ -103,36 +107,115 @@ opendataloader_pdf.run(
|
|
|
103
107
|
|
|
104
108
|
The main function to process PDFs.
|
|
105
109
|
|
|
106
|
-
| Parameter
|
|
107
|
-
|
|
108
|
-
| `input_path`
|
|
109
|
-
| `output_folder`
|
|
110
|
-
| `password`
|
|
111
|
-
| `
|
|
112
|
-
| `
|
|
113
|
-
| `
|
|
114
|
-
| `
|
|
115
|
-
| `
|
|
116
|
-
| `
|
|
117
|
-
| `
|
|
118
|
-
| `
|
|
110
|
+
| Parameter | Type | Required | Default | Description |
|
|
111
|
+
|--------------------------| ------ | -------- |--------------|-------------------------------------------------------------------------------------------------------------------------------------|
|
|
112
|
+
| `input_path` | `str` | ✅ Yes | — | Path to the input PDF file or folder. |
|
|
113
|
+
| `output_folder` | `str` | No | input folder | Path to the output folder. |
|
|
114
|
+
| `password` | `str` | No | `None` | Password for the PDF file. |
|
|
115
|
+
| `replace_invalid_chars` | `str` | No | `" "` | Character to replace invalid or unrecognized characters (e.g., �, \u0000) |
|
|
116
|
+
| `content_safety_off` | `str` | No | `None` | Disables one or more content safety filters. Accepts a comma-separated list of filter names. Arguments: all, hidden-text, off-page. |
|
|
117
|
+
| `generate_markdown` | `bool` | No | `False` | If `True`, generates a Markdown output file. |
|
|
118
|
+
| `generate_html` | `bool` | No | `False` | If `True`, generates an HTML output file. |
|
|
119
|
+
| `generate_annotated_pdf` | `bool` | No | `False` | If `True`, generates an annotated PDF output file. |
|
|
120
|
+
| `keep_line_breaks` | `bool` | No | `False` | If `True`, keeps line breaks in the output. |
|
|
121
|
+
| `html_in_markdown` | `bool` | No | `False` | If `True`, uses HTML in the Markdown output. |
|
|
122
|
+
| `add_image_to_markdown` | `bool` | No | `False` | If `True`, adds images to the Markdown output. |
|
|
123
|
+
| `debug` | `bool` | No | `False` | If `True`, prints CLI messages to the console during execution. |
|
|
124
|
+
|
|
125
|
+
<br/>
|
|
126
|
+
|
|
127
|
+
## Node.js / NPM
|
|
128
|
+
|
|
129
|
+
**Note:** This package is a wrapper around a Java CLI and is intended for use in a Node.js backend environment. It cannot be used in a browser-based frontend.
|
|
130
|
+
|
|
131
|
+
### Prerequisites
|
|
132
|
+
|
|
133
|
+
- Java 11 or higher must be installed and available in your system's PATH.
|
|
134
|
+
|
|
135
|
+
### Installation
|
|
136
|
+
|
|
137
|
+
```sh
|
|
138
|
+
npm install @opendataloader/pdf
|
|
139
|
+
```
|
|
140
|
+
|
|
141
|
+
### Usage
|
|
142
|
+
|
|
143
|
+
- `inputPath` can be either the path to a single document or the path to a folder.
|
|
144
|
+
- If you don’t specify an `outputFolder`, the output data will be saved in the same directory as the input document.
|
|
145
|
+
|
|
146
|
+
```typescript
|
|
147
|
+
import { run } from '@opendataloader/pdf';
|
|
148
|
+
|
|
149
|
+
async function main() {
|
|
150
|
+
try {
|
|
151
|
+
const output = await run('path-to-document.pdf', {
|
|
152
|
+
outputFolder: 'path-to-output',
|
|
153
|
+
generateMarkdown: true,
|
|
154
|
+
generateHtml: true,
|
|
155
|
+
generateAnnotatedPdf: true,
|
|
156
|
+
debug: true,
|
|
157
|
+
});
|
|
158
|
+
console.log('PDF processing complete.', output);
|
|
159
|
+
} catch (error) {
|
|
160
|
+
console.error('Error processing PDF:', error);
|
|
161
|
+
}
|
|
162
|
+
}
|
|
163
|
+
|
|
164
|
+
main();
|
|
165
|
+
```
|
|
166
|
+
|
|
167
|
+
### Function: run()
|
|
168
|
+
|
|
169
|
+
`run(inputPath: string, options?: RunOptions): Promise<string>`
|
|
170
|
+
|
|
171
|
+
The main function to process PDFs.
|
|
172
|
+
|
|
173
|
+
**Parameters**
|
|
174
|
+
|
|
175
|
+
| Parameter | Type | Required | Description |
|
|
176
|
+
| ----------- | -------- | -------- | ------------------------------------- |
|
|
177
|
+
| `inputPath` | `string` | ✅ Yes | Path to the input PDF file or folder. |
|
|
178
|
+
| `options` | `RunOptions` | No | Configuration options for the run. |
|
|
179
|
+
|
|
180
|
+
**RunOptions**
|
|
181
|
+
|
|
182
|
+
| Property | Type | Default | Description |
|
|
183
|
+
| ----------------------- | --------- | ------------- | --------------------------------------------------------------------------- |
|
|
184
|
+
| `outputFolder` | `string` | `undefined` | Path to the output folder. If not set, output is saved next to the input. |
|
|
185
|
+
| `password` | `string` | `undefined` | Password for the PDF file. |
|
|
186
|
+
| `replaceInvalidChars` | `string` | `" "` | Character to replace invalid or unrecognized characters (e.g., , \u0000). |
|
|
187
|
+
| `content_safety_off` | `string` | `undefined` | Disables one or more content safety filters. Accepts a comma-separated list of filter names. Arguments: all, hidden-text, off-page. |
|
|
188
|
+
| `generateMarkdown` | `boolean` | `false` | If `true`, generates a Markdown output file. |
|
|
189
|
+
| `generateHtml` | `boolean` | `false` | If `true`, generates an HTML output file. |
|
|
190
|
+
| `generateAnnotatedPdf` | `boolean` | `false` | If `true`, generates an annotated PDF output file. |
|
|
191
|
+
| `keepLineBreaks` | `boolean` | `false` | If `true`, keeps line breaks in the output. |
|
|
192
|
+
| `htmlInMarkdown` | `boolean` | `false` | If `true`, uses HTML in the Markdown output. |
|
|
193
|
+
| `addImageToMarkdown` | `boolean` | `false` | If `true`, adds images to the Markdown output. |
|
|
194
|
+
| `debug` | `boolean` | `false` | If `true`, prints CLI messages to the console during execution. |
|
|
119
195
|
|
|
120
196
|
<br/>
|
|
121
197
|
|
|
122
198
|
## Java
|
|
123
199
|
|
|
200
|
+
For various example templates, including Gradle and Maven, please refer to https://github.com/opendataloader-project/opendataloader-pdf/tree/main/examples/java.
|
|
201
|
+
|
|
124
202
|
### Dependency
|
|
125
203
|
|
|
126
204
|
To include OpenDataLoader PDF in your Maven project, add the dependency below to your `pom.xml` file.
|
|
127
205
|
|
|
128
|
-
Check for the latest version on [Maven Central](https://search.maven.org/artifact/
|
|
206
|
+
Check for the latest version on [Maven Central](https://search.maven.org/artifact/org.opendataloader/opendataloader-pdf-core).
|
|
129
207
|
|
|
130
208
|
```xml
|
|
131
|
-
|
|
132
|
-
|
|
133
|
-
|
|
134
|
-
|
|
135
|
-
|
|
209
|
+
<project>
|
|
210
|
+
<!-- other configurations... -->
|
|
211
|
+
|
|
212
|
+
<dependencies>
|
|
213
|
+
<dependency>
|
|
214
|
+
<groupId>org.opendataloader</groupId>
|
|
215
|
+
<artifactId>opendataloader-pdf-core</artifactId>
|
|
216
|
+
<version>0.0.15</version>
|
|
217
|
+
</dependency>
|
|
218
|
+
</dependencies>
|
|
136
219
|
|
|
137
220
|
<repositories>
|
|
138
221
|
<repository>
|
|
@@ -154,6 +237,9 @@ Check for the latest version on [Maven Central](https://search.maven.org/artifac
|
|
|
154
237
|
<url>https://artifactory.openpreservation.org/artifactory/vera-dev</url>
|
|
155
238
|
</pluginRepository>
|
|
156
239
|
</pluginRepositories>
|
|
240
|
+
|
|
241
|
+
<!-- other configurations... -->
|
|
242
|
+
</project>
|
|
157
243
|
```
|
|
158
244
|
|
|
159
245
|
|
|
@@ -162,51 +248,22 @@ Check for the latest version on [Maven Central](https://search.maven.org/artifac
|
|
|
162
248
|
To integrate Layout recognition API into Java code, one can follow the sample code below.
|
|
163
249
|
|
|
164
250
|
```java
|
|
165
|
-
import
|
|
166
|
-
import
|
|
251
|
+
import org.opendataloader.pdf.api.Config;
|
|
252
|
+
import org.opendataloader.pdf.api.OpenDataLoaderPDF;
|
|
167
253
|
|
|
168
254
|
import java.io.IOException;
|
|
169
255
|
|
|
170
256
|
public class Sample {
|
|
171
257
|
|
|
172
258
|
public static void main(String[] args) {
|
|
173
|
-
//create default config
|
|
174
259
|
Config config = new Config();
|
|
175
|
-
|
|
176
|
-
//set output folder relative to the input PDF
|
|
177
|
-
//if the output folder is not set, the current folder of the input PDF is used
|
|
178
|
-
config.setOutputFolder("output");
|
|
179
|
-
|
|
180
|
-
//generating pdf output file
|
|
260
|
+
config.setOutputFolder("path/to/output");
|
|
181
261
|
config.setGeneratePDF(true);
|
|
182
|
-
|
|
183
|
-
//set password of input pdf file
|
|
184
|
-
config.setPassword("password");
|
|
185
|
-
|
|
186
|
-
//generate markdown output file
|
|
187
262
|
config.setGenerateMarkdown(true);
|
|
188
|
-
|
|
189
|
-
//generate html output file
|
|
190
263
|
config.setGenerateHtml(true);
|
|
191
264
|
|
|
192
|
-
//enable html in markdown output file
|
|
193
|
-
config.setUseHTMLInMarkdown(true);
|
|
194
|
-
|
|
195
|
-
//add images to markdown output file
|
|
196
|
-
config.setAddImageToMarkdown(true);
|
|
197
|
-
|
|
198
|
-
//disable json output file
|
|
199
|
-
config.setGenerateJSON(false);
|
|
200
|
-
|
|
201
|
-
//keep line breaks
|
|
202
|
-
config.setKeepLineBreaks(true);
|
|
203
|
-
|
|
204
|
-
//find hidden text
|
|
205
|
-
config.setFindHiddenText(true);
|
|
206
|
-
|
|
207
265
|
try {
|
|
208
|
-
|
|
209
|
-
OpenDataLoaderPDF.processFile("input.pdf", config);
|
|
266
|
+
OpenDataLoaderPDF.processFile("path/to/document.pdf", config);
|
|
210
267
|
} catch (Exception exception) {
|
|
211
268
|
//exception during processing
|
|
212
269
|
}
|
|
@@ -216,7 +273,7 @@ public class Sample {
|
|
|
216
273
|
|
|
217
274
|
### API Documentation
|
|
218
275
|
|
|
219
|
-
The full API documentation is available at [javadoc](https://javadoc.io/doc/
|
|
276
|
+
The full API documentation is available at [javadoc](https://javadoc.io/doc/org.opendataloader/opendataloader-pdf-core/latest/)
|
|
220
277
|
|
|
221
278
|
<br/>
|
|
222
279
|
|
|
@@ -263,25 +320,27 @@ Additionally, annotated PDF with recognized structures, Markdown and Html are ge
|
|
|
263
320
|
|
|
264
321
|
By default all line breaks and hyphenation characters are removed, the Markdown does not include any images and does not use any HTML.
|
|
265
322
|
|
|
266
|
-
The option `--
|
|
267
|
-
|
|
268
|
-
The option `--
|
|
269
|
-
The option `--
|
|
323
|
+
The option `--keep-line-breaks` to preserve the original line breaks text content in JSON and Markdown output.
|
|
324
|
+
The option `--content-safety-off` disables one or more content safety filters. Accepts a comma-separated list of filter names.
|
|
325
|
+
The option `--markdown-with-html` enables use of HTML in Markdown, which may improve Markdown preview in processors that support HTML tags.
|
|
326
|
+
The option `--markdown-with-images` enables inclusion of image references into the output Markdown.
|
|
327
|
+
The option `--replace-invalid-chars` replaces invalid or unrecognized characters (e.g., �, \u0000) with the specified character.
|
|
270
328
|
The images are extracted from PDF as individual files and stored in a subfolder next to the Markdown output.
|
|
271
329
|
|
|
272
330
|
#### Available options:
|
|
273
331
|
|
|
274
332
|
```
|
|
275
333
|
Options:
|
|
276
|
-
-
|
|
277
|
-
-
|
|
278
|
-
-
|
|
279
|
-
-
|
|
280
|
-
-
|
|
281
|
-
|
|
282
|
-
|
|
283
|
-
-p,--password <arg>
|
|
284
|
-
|
|
334
|
+
-o,--output-dir <arg> Specifies the output directory for generated files
|
|
335
|
+
--keep-line-breaks Preserves original line breaks in the extracted text
|
|
336
|
+
--content-safety-off <arg> Disables one or more content safety filters. Accepts a comma-separated list of filter names. Arguments: all, hidden-text, off-page
|
|
337
|
+
--markdown-with-html Sets the data extraction output format to Markdown with rendering complex elements like tables as HTML for better structure
|
|
338
|
+
--markdown-with-images Sets the data extraction output format to Markdown with extracting images from the PDF and includes them as links
|
|
339
|
+
--markdown Sets the data extraction output format to Markdown
|
|
340
|
+
--html Sets the data extraction output format to HTML
|
|
341
|
+
-p,--password <arg> Specifies the password for an encrypted PDF
|
|
342
|
+
--pdf Generates a new PDF file where the extracted layout data is visualized as annotations
|
|
343
|
+
--replace-invalid-chars <arg> Replaces invalid or unrecognized characters (e.g., �, \u0000) with the specified character
|
|
285
344
|
```
|
|
286
345
|
|
|
287
346
|
### Schema of the JSON output
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
opendataloader_pdf/LICENSE,sha256=rxdbnZbuk8IaA2FS4bkFsLlTBNSujCySHHYJEAuo334,15921
|
|
2
2
|
opendataloader_pdf/NOTICE.md,sha256=Uxc6sEbVz2hfsDinzzSNMtmsjx9HsQUod0yy0cswUwg,562
|
|
3
3
|
opendataloader_pdf/__init__.py,sha256=T5RV-dcgjNCm8klNy_EH-IgOeodcPg6Yc34HHXtuAmQ,44
|
|
4
|
-
opendataloader_pdf/wrapper.py,sha256=
|
|
4
|
+
opendataloader_pdf/wrapper.py,sha256=bPy-wNmQfJpmCg9dVx9uNTrGfW446GdGNrlJnt0cosA,4960
|
|
5
5
|
opendataloader_pdf/THIRD_PARTY/THIRD_PARTY_LICENSES.md,sha256=QRYYiXFS2zBDGdmWRo_SrRfGhrdRBwhiRo1SdUKfrQo,11235
|
|
6
6
|
opendataloader_pdf/THIRD_PARTY/THIRD_PARTY_NOTICES.md,sha256=pB2ZitFM1u0x3rIDpMHsLxOe4OFNCZRqkzeR-bfpFzE,8911
|
|
7
7
|
opendataloader_pdf/THIRD_PARTY/licenses/Apache-2.0.txt,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
|
|
@@ -13,8 +13,8 @@ opendataloader_pdf/THIRD_PARTY/licenses/LICENSE-JJ2000.txt,sha256=itSesIy3XiNWgJ
|
|
|
13
13
|
opendataloader_pdf/THIRD_PARTY/licenses/MIT.txt,sha256=JPCdbR3BU0uO_KypOd3sGWnKwlVHGq4l0pmrjoGtop8,1078
|
|
14
14
|
opendataloader_pdf/THIRD_PARTY/licenses/MPL-2.0.txt,sha256=CGF6Fx5WV7DJmRZJ8_6w6JEt2N9bu4p6zDo18fTHHRw,15818
|
|
15
15
|
opendataloader_pdf/THIRD_PARTY/licenses/Plexus Classworlds License.txt,sha256=ZQuKXwVz4FeC34ApB20vYg8kPTwgIUKRzEk5ew74-hU,1937
|
|
16
|
-
opendataloader_pdf/jar/opendataloader-pdf-cli.jar,sha256=
|
|
17
|
-
opendataloader_pdf-0.0.
|
|
18
|
-
opendataloader_pdf-0.0.
|
|
19
|
-
opendataloader_pdf-0.0.
|
|
20
|
-
opendataloader_pdf-0.0.
|
|
16
|
+
opendataloader_pdf/jar/opendataloader-pdf-cli.jar,sha256=DI0_vONCuUqmvKnVwkzUcRoA4HSv4B8EWqs27vb8u2w,22126375
|
|
17
|
+
opendataloader_pdf-0.0.16.dist-info/METADATA,sha256=FjpkSNX7uz8YdehHMeZenaWi7ZVQKgJnJ-4RXAR_ITI,23689
|
|
18
|
+
opendataloader_pdf-0.0.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
19
|
+
opendataloader_pdf-0.0.16.dist-info/top_level.txt,sha256=xee0qFQd6HPfS50E2NLICGuR6cq9C9At5SJ81yv5HkY,19
|
|
20
|
+
opendataloader_pdf-0.0.16.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|