natural-pdf 0.1.0__tar.gz → 0.1.1__tar.gz

{natural_pdf-0.1.0 → natural_pdf-0.1.1}/.github/workflows/docs.yml

@@ -8,6 +8,8 @@ on:
       - 'docs/**'
       - 'mkdocs.yml'
       - '.github/workflows/docs.yml'
+    tags:
+      - 'v*'
 
 permissions:
   contents: write
@@ -27,7 +29,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install mkdocs-material mkdocs pymdown-extensions mkdocstrings mkdocstrings-python mkdocs-jupyter
+          pip install mkdocs-material mkdocs pymdown-extensions mkdocstrings mkdocstrings-python mkdocs-jupyter mkdocs-exclude
           pip install -e .
           
       - name: Build docs

{natural_pdf-0.1.0 → natural_pdf-0.1.1}/.gitignore

@@ -1,3 +1,12 @@
+.notebook_cache.json
+Untitled.ipynb
+conversation.md
+docs/tutorials/pdfs
+install.sh
+notebooks/Examples.md
+transcript.md
+
+
 # Created by https://www.toptal.com/developers/gitignore/api/python,macos,visualstudiocode,jupyternotebooks
 # Edit at https://www.toptal.com/developers/gitignore?templates=python,macos,visualstudiocode,jupyternotebooks
 

{natural_pdf-0.1.0 → natural_pdf-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: natural-pdf
-Version: 0.1.0
+Version: 0.1.1
 Summary: A more intuitive interface for working with PDFs
 Author-email: Jonathan Soma <jonathan.soma@gmail.com>
 License-Expression: MIT
@@ -48,7 +48,7 @@ A friendly library for working with PDFs, built on top of [pdfplumber](https://g
 Natural PDF lets you find and extract content from PDFs using simple code that makes sense.
 
 - [Complete documentation here](https://jsoma.github.io/natural-pdf)
-- [Live demo here](https://colab.research.google.com/github/jsoma/natural-pdf/blob/main/notebooks/Examples.ipynb)
+- [Live demos here](https://colab.research.google.com/github/jsoma/natural-pdf/)
 
 ## Features
 
@@ -74,18 +74,16 @@ pip install natural-pdf
 
 # Installs the core library along with required AI dependencies (PyTorch, Transformers)
 ```bash
-# Install with support for specific OCR engines
-pip install natural-pdf[easyocr]   # EasyOCR engine
-pip install natural-pdf[paddle]    # PaddleOCR engine (requires paddlepaddle)
-pip install natural-pdf[surya]     # Surya OCR engine
-
-# Install with support for YOLO layout detection model
+# Install with support for specific OCR and layout engines
+pip install natural-pdf[easyocr]
+pip install natural-pdf[paddle]
+pip install natural-pdf[surya]
 pip install natural-pdf[layout_yolo]
 
 # Install with support for the interactive Jupyter widget
 pip install natural-pdf[interactive]
 
-# Install everything
+# Just install everything
 pip install natural-pdf[all]
 ```
 
@@ -119,6 +117,8 @@ clean_text = page.extract_text()
 print(clean_text)
 ```
 
+- [Complete documentation here](https://jsoma.github.io/natural-pdf)
+
 ## Selectors
 
 The library supports CSS-like selectors for finding elements:
@@ -185,7 +185,7 @@ Exclusions work efficiently with different region types:
 
 ## OCR Integration
 
-Extract text from scanned documents using OCR, with support for multiple engines (EasyOCR, PaddleOCR, Surya):
+Extract text from scanned documents using OCR, with support for multiple engines ([EasyOCR](https://www.jaided.ai/easyocr/), [PaddleOCR](https://paddlepaddle.github.io/PaddleOCR/latest/en/index.html), [Surya](https://github.com/VikParuchuri/surya)):
 
 ```python
 # Apply OCR using a specific engine (e.g., PaddleOCR)

{natural_pdf-0.1.0 → natural_pdf-0.1.1}/README.md

@@ -5,7 +5,7 @@ A friendly library for working with PDFs, built on top of [pdfplumber](https://g
 Natural PDF lets you find and extract content from PDFs using simple code that makes sense.
 
 - [Complete documentation here](https://jsoma.github.io/natural-pdf)
-- [Live demo here](https://colab.research.google.com/github/jsoma/natural-pdf/blob/main/notebooks/Examples.ipynb)
+- [Live demos here](https://colab.research.google.com/github/jsoma/natural-pdf/)
 
 ## Features
 
@@ -31,18 +31,16 @@ pip install natural-pdf
 
 # Installs the core library along with required AI dependencies (PyTorch, Transformers)
 ```bash
-# Install with support for specific OCR engines
-pip install natural-pdf[easyocr]   # EasyOCR engine
-pip install natural-pdf[paddle]    # PaddleOCR engine (requires paddlepaddle)
-pip install natural-pdf[surya]     # Surya OCR engine
-
-# Install with support for YOLO layout detection model
+# Install with support for specific OCR and layout engines
+pip install natural-pdf[easyocr]
+pip install natural-pdf[paddle]
+pip install natural-pdf[surya]
 pip install natural-pdf[layout_yolo]
 
 # Install with support for the interactive Jupyter widget
 pip install natural-pdf[interactive]
 
-# Install everything
+# Just install everything
 pip install natural-pdf[all]
 ```
 
@@ -76,6 +74,8 @@ clean_text = page.extract_text()
 print(clean_text)
 ```
 
+- [Complete documentation here](https://jsoma.github.io/natural-pdf)
+
 ## Selectors
 
 The library supports CSS-like selectors for finding elements:
@@ -142,7 +142,7 @@ Exclusions work efficiently with different region types:
 
 ## OCR Integration
 
-Extract text from scanned documents using OCR, with support for multiple engines (EasyOCR, PaddleOCR, Surya):
+Extract text from scanned documents using OCR, with support for multiple engines ([EasyOCR](https://www.jaided.ai/easyocr/), [PaddleOCR](https://paddlepaddle.github.io/PaddleOCR/latest/en/index.html), [Surya](https://github.com/VikParuchuri/surya)):
 
 ```python
 # Apply OCR using a specific engine (e.g., PaddleOCR)

{natural_pdf-0.1.0 → natural_pdf-0.1.1}/check_run_md.sh

@@ -11,9 +11,10 @@ MARKDOWN_FILE=$1
 NOTEBOOK_FILE="${MARKDOWN_FILE%.md}.ipynb"
 
 echo "Converting $MARKDOWN_FILE to notebook..."
+# Jupytext will now automatically add tags based on markdown metadata
 jupytext --to ipynb "$MARKDOWN_FILE" || { echo "Conversion failed"; exit 1; }
 
 echo "Executing notebook $NOTEBOOK_FILE..."
 jupyter execute "$NOTEBOOK_FILE" --inplace || { echo "Execution failed"; exit 1; }
 
-echo "Success! Notebook executed and results saved to $NOTEBOOK_FILE" 
+echo "Success! Notebook executed and results saved to $NOTEBOOK_FILE"

{natural_pdf-0.1.0 → natural_pdf-0.1.1}/docs/assets/stylesheets/custom.css

@@ -1,5 +1,32 @@
 /* Natural PDF - Minimal Custom Styling */
 
+.jp-InputPrompt, .jp-OutputPrompt {
+  display: none !important;
+}
+
+.jupyter-wrapper .CodeMirror {
+  font-size: 0.85em !important;
+}
+
+.highlight-ipynb pre {
+  white-space: pre-wrap !important;
+  word-wrap: break-word !important;
+}
+
+.CodeMirror pre {
+  white-space: pre-wrap !important;
+  word-wrap: break-word !important;
+}
+
+.jp-CodeMirrorEditor {
+  max-width: 100%;
+  overflow-x: auto;
+}
+
+.jupyter-wrapper{ 
+  --jp-code-font-size: 0.85em !important;
+}
+
 /* Typography improvements */
 .md-typeset h1 {
   font-weight: 400;