opendataloader-pdf 0.0.9__py3-none-any.whl → 0.0.10__py3-none-any.whl

opendataloader_pdf/wrapper.py

@@ -12,8 +12,8 @@ def run(
     input_path: str,
     output_folder: str = None,
     password: str = None,
-    to_markdown: bool = False,
-    to_annotated_pdf: bool = False,
+    generate_markdown: bool = False,
+    generate_annotated_pdf: bool = False,
     keep_line_breaks: bool = False,
     find_hidden_text: bool = False,
     html_in_markdown: bool = False,
@@ -27,8 +27,8 @@ def run(
         input_path: Path to the input PDF file or folder.
         output_folder: Path to the output folder. Defaults to the input folder.
         password: Password for the PDF file.
-        to_markdown: If True, generates a Markdown output file.
-        to_annotated_pdf: If True, generates an annotated PDF output file.
+        generate_markdown: If True, generates a Markdown output file.
+        generate_annotated_pdf: If True, generates an annotated PDF output file.
         keep_line_breaks: If True, keeps line breaks in the output.
         find_hidden_text: If True, finds hidden text in the PDF.
         html_in_markdown: If True, uses HTML in the Markdown output.
@@ -50,9 +50,9 @@ def run(
         args.extend(["--folder", output_folder])
     if password:
         args.extend(["--password", password])
-    if to_markdown:
+    if generate_markdown:
         args.append("--markdown")
-    if to_annotated_pdf:
+    if generate_annotated_pdf:
         args.append("--pdf")
     if keep_line_breaks:
         args.append("--keeplinebreaks")

{opendataloader_pdf-0.0.9.dist-info → opendataloader_pdf-0.0.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opendataloader-pdf
-Version: 0.0.9
+Version: 0.0.10
 Summary: A Python wrapper for the opendataloader-pdf Java CLI.
 Home-page: https://github.com/opendataloader-project/opendataloader-pdf
 Author: opendataloader-project
@@ -32,7 +32,10 @@ Dynamic: summary
 
 <br/>
 
-OpenDataLoader PDF converts PDFs into JSON, Markdown or Html — ready to feed into modern AI stacks (LLMs, vector search, and RAG).
+**Safe, Open, High-Performance — OpenDataLoader PDF for AI**
+
+OpenDataLoader-PDF converts PDFs into JSON, Markdown or Html — ready to feed into modern AI stacks (LLMs, vector search, and RAG).
+
 It reconstructs document layout (headings, lists, tables, and reading order) so the content is easier to chunk, index, and query.
 Powered by fast, heuristic, rule-based inference, it runs entirely on your local machine and delivers high-throughput processing for large document sets.
 AI-safety is enabled by default and automatically filters likely prompt-injection content embedded in PDFs to reduce downstream risk.
@@ -41,13 +44,13 @@ AI-safety is enabled by default and automatically filters likely prompt-injectio
 
 ## 🌟 Key Features
 
-- 🧾 **Rich, structured output** — JSON, Markdown or Html
-- 🧩 **Layout reconstruction** — headings, lists, tables, images, reading order
-- 🔒 **Local-first privacy** — runs fully on your machine
-- ⚡ **Fast & lightweight** — rule-based heuristic, high-throughput, no GPU
-- 🛡️ **AI-safety by default** — auto-filters likely prompt-injection content
-- 🆓 **Open source for business** — free for commercial use; Java/Python/Docker
-- 🖍️ **Annotated PDF visualization** — see detected structures overlaid on the original
+- 🧾 **Rich, Structured Output** — JSON, Markdown or Html
+- 🧩 **Layout Reconstruction** — Headings, Lists, Tables, Images, Reading Order
+- 🔒 **Local-First Privacy** — Runs fully on your machine
+- ⚡ **Fast & Lightweight** — Rule-Based Heuristic, High-Throughput, No GPU
+- 🛡️ **AI-Safety** — Auto-Filters likely prompt-injection content
+- 🆓 **Open-Source** — Free for commercial use
+- 🖍️ **Annotated PDF Visualization** — See detected structures overlaid on the original
 
 ![Annotated PDF Example](https://raw.githubusercontent.com/opendataloader-project/opendataloader-pdf/main/resources/example_annotated_pdf.png)
 
@@ -88,7 +91,8 @@ import opendataloader_pdf
 opendataloader_pdf.run(
     input_path="path/to/document.pdf",
     output_folder="path/to/output",
-    to_markdown=True
+    generate_markdown=True,
+    generate_annotated_pdf=True
 )
 ```
 
@@ -101,8 +105,8 @@ The main function to process PDFs.
 | `input_path`            | `str`  | ✅ Yes    | —            | Path to the input PDF file or folder.                           |
 | `output_folder`         | `str`  | No       | input folder | Path to the output folder.                                      |
 | `password`              | `str`  | No       | `None`       | Password for the PDF file.                                      |
-| `to_markdown`           | `bool` | No       | `False`      | If `True`, generates a Markdown output file.                    |
-| `to_annotated_pdf`      | `bool` | No       | `False`      | If `True`, generates an annotated PDF output file.              |
+| `generate_markdown`     | `bool` | No       | `False`      | If `True`, generates a Markdown output file.                    |
+| `generate_annotated_pdf`| `bool` | No       | `False`      | If `True`, generates an annotated PDF output file.              |
 | `keep_line_breaks`      | `bool` | No       | `False`      | If `True`, keeps line breaks in the output.                     |
 | `find_hidden_text`      | `bool` | No       | `False`      | If `True`, finds hidden text in the PDF.                        |
 | `html_in_markdown`      | `bool` | No       | `False`      | If `True`, uses HTML in the Markdown output.                    |
@@ -205,11 +209,15 @@ public class Sample {
 
 ## Docker
 
+Download sample PDF
+
 ```sh
-# Download sample PDF
 curl -L -o 1901.03003.pdf https://arxiv.org/pdf/1901.03003
+```
+
+Run opendataloader-pdf in Docker container
 
-# Run OpenDataLoader PDF in Docker container
+```
 docker run --rm -v "$PWD":/work ghcr.io/opendataloader-project/opendataloader-pdf-cli:latest /work/1901.03003.pdf --markdown --pdf
 ```
 

{opendataloader_pdf-0.0.9.dist-info → opendataloader_pdf-0.0.10.dist-info}/RECORD

@@ -1,7 +1,7 @@
 opendataloader_pdf/LICENSE,sha256=rxdbnZbuk8IaA2FS4bkFsLlTBNSujCySHHYJEAuo334,15921
 opendataloader_pdf/NOTICE.md,sha256=Uxc6sEbVz2hfsDinzzSNMtmsjx9HsQUod0yy0cswUwg,562
 opendataloader_pdf/__init__.py,sha256=T5RV-dcgjNCm8klNy_EH-IgOeodcPg6Yc34HHXtuAmQ,44
-opendataloader_pdf/wrapper.py,sha256=faWntri6T_wHQSFpHcknfT15bX7aS6VJxUlMLcbfUUw,4482
+opendataloader_pdf/wrapper.py,sha256=DGwzBVy1DyNxUFPLxi8Mzwb68u3fo0k0B5YEBufy0vI,4518
 opendataloader_pdf/THIRD_PARTY/THIRD_PARTY_LICENSES.md,sha256=QRYYiXFS2zBDGdmWRo_SrRfGhrdRBwhiRo1SdUKfrQo,11235
 opendataloader_pdf/THIRD_PARTY/THIRD_PARTY_NOTICES.md,sha256=pB2ZitFM1u0x3rIDpMHsLxOe4OFNCZRqkzeR-bfpFzE,8911
 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
 opendataloader_pdf/THIRD_PARTY/licenses/MIT.txt,sha256=JPCdbR3BU0uO_KypOd3sGWnKwlVHGq4l0pmrjoGtop8,1078
 opendataloader_pdf/THIRD_PARTY/licenses/MPL-2.0.txt,sha256=CGF6Fx5WV7DJmRZJ8_6w6JEt2N9bu4p6zDo18fTHHRw,15818
 opendataloader_pdf/THIRD_PARTY/licenses/Plexus Classworlds License.txt,sha256=ZQuKXwVz4FeC34ApB20vYg8kPTwgIUKRzEk5ew74-hU,1937
-opendataloader_pdf/jar/opendataloader-pdf-cli.jar,sha256=ZtctQzzoQpnKCxEM4H6ktVTw4l5ZbP5gAetbPgp_bmA,22114701
-opendataloader_pdf-0.0.9.dist-info/METADATA,sha256=SVLovntCpxWdnlpsXwg0E1i3ct_uq-WchM4ximmY_m0,17559
-opendataloader_pdf-0.0.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-opendataloader_pdf-0.0.9.dist-info/top_level.txt,sha256=xee0qFQd6HPfS50E2NLICGuR6cq9C9At5SJ81yv5HkY,19
-opendataloader_pdf-0.0.9.dist-info/RECORD,,
+opendataloader_pdf/jar/opendataloader-pdf-cli.jar,sha256=Qp9qnNbptrsdrL2UJn8bw-WStRqfI9EGYd883EtDZfE,22114700
+opendataloader_pdf-0.0.10.dist-info/METADATA,sha256=ESHbbQmEr8L5VqKwpll0u7h4EiiG7YTnYiD10p7Z7h0,17626
+opendataloader_pdf-0.0.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+opendataloader_pdf-0.0.10.dist-info/top_level.txt,sha256=xee0qFQd6HPfS50E2NLICGuR6cq9C9At5SJ81yv5HkY,19
+opendataloader_pdf-0.0.10.dist-info/RECORD,,