doctra 0.3.0__tar.gz → 0.3.2__tar.gz

{doctra-0.3.0/doctra.egg-info → doctra-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: doctra
-Version: 0.3.0
+Version: 0.3.2
 Summary: Parse, extract, and analyze documents with ease
 Home-page: https://github.com/AdemBoukhris457/Doctra
 Author: Adem Boukhris
@@ -234,6 +234,9 @@ Requires-Dist: opencv-python>=4.5.0
 Requires-Dist: pandas>=1.3.0
 Requires-Dist: openpyxl>=3.0.0
 Requires-Dist: tesseract>=0.1.3
+Requires-Dist: pytesseract>=0.3.10
+Requires-Dist: pdf2image>=1.16.0
+Requires-Dist: anthropic>=0.40.0
 Requires-Dist: outlines>=0.0.34
 Requires-Dist: tqdm>=4.62.0
 Requires-Dist: matplotlib>=3.5.0
@@ -241,8 +244,6 @@ Provides-Extra: openai
 Requires-Dist: openai>=1.0.0; extra == "openai"
 Provides-Extra: gemini
 Requires-Dist: google-generativeai>=0.3.0; extra == "gemini"
-Provides-Extra: anthropic
-Requires-Dist: anthropic>=0.40.0; extra == "anthropic"
 Provides-Extra: dev
 Requires-Dist: pytest>=6.0; extra == "dev"
 Requires-Dist: pytest-cov>=2.0; extra == "dev"
@@ -295,6 +296,31 @@ cd Doctra
 pip install .
 ```
 
+### System Dependencies
+
+Doctra requires **Poppler** for PDF processing. Install it based on your operating system:
+
+#### Ubuntu/Debian
+```bash
+sudo apt install poppler-utils
+```
+
+#### macOS
+```bash
+brew install poppler
+```
+
+#### Windows
+Download and install from [Poppler for Windows](http://blog.alivate.com.au/poppler-windows/) or use conda:
+```bash
+conda install -c conda-forge poppler
+```
+
+#### Google Colab
+```bash
+!sudo apt install poppler-utils
+```
+
 ## ⚡ Quick Start
 
 ```python

{doctra-0.3.0 → doctra-0.3.2}/README.md

@@ -37,6 +37,31 @@ cd Doctra
 pip install .
 ```
 
+### System Dependencies
+
+Doctra requires **Poppler** for PDF processing. Install it based on your operating system:
+
+#### Ubuntu/Debian
+```bash
+sudo apt install poppler-utils
+```
+
+#### macOS
+```bash
+brew install poppler
+```
+
+#### Windows
+Download and install from [Poppler for Windows](http://blog.alivate.com.au/poppler-windows/) or use conda:
+```bash
+conda install -c conda-forge poppler
+```
+
+#### Google Colab
+```bash
+!sudo apt install poppler-utils
+```
+
 ## ⚡ Quick Start
 
 ```python

{doctra-0.3.0 → doctra-0.3.2}/doctra/utils/progress.py

@@ -354,10 +354,11 @@ def create_notebook_friendly_bar(
     **kwargs
 ) -> tqdm:
     """
-    Create a notebook-friendly progress bar with minimal formatting.
+    Create a notebook-friendly progress bar with consistent sizing and static display.
     
     This function creates progress bars specifically optimized for Jupyter notebooks
-    to avoid display issues and ANSI code problems.
+    to avoid display issues and ANSI code problems while maintaining consistency
+    with the main progress bar styling.
     
     :param total: Total number of items to process
     :param desc: Description text for the progress bar
@@ -384,24 +385,52 @@ def create_notebook_friendly_bar(
         if prefix:
             desc = f"{prefix} {desc}"
     
-    # Simple format for notebooks
-    bar_format = "{desc}: {percentage:3.0f}%|{bar}| {n_fmt}/{total_fmt}"
+    # Use same format as main progress bar for consistency
+    bar_format = "{desc}: {percentage:3.0f}%|{bar}| {n_fmt}/{total_fmt} [{elapsed}<{remaining}]"
+    
+    # Color schemes based on operation type (same as main progress bar)
+    color_schemes = {
+        "loading": {"colour": "cyan", "ncols": 100},
+        "charts": {"colour": "green", "ncols": 100},
+        "tables": {"colour": "blue", "ncols": 100},
+        "figures": {"colour": "magenta", "ncols": 100},
+        "ocr": {"colour": "yellow", "ncols": 100},
+        "vlm": {"colour": "red", "ncols": 100},
+        "processing": {"colour": "white", "ncols": 100},
+    }
+    
+    # Determine color scheme based on description
+    if "loading" in desc_lower or "model" in desc_lower:
+        color_scheme = color_schemes["loading"]
+    elif "chart" in desc_lower:
+        color_scheme = color_schemes["charts"]
+    elif "table" in desc_lower:
+        color_scheme = color_schemes["tables"]
+    elif "figure" in desc_lower:
+        color_scheme = color_schemes["figures"]
+    elif "ocr" in desc_lower:
+        color_scheme = color_schemes["ocr"]
+    elif "vlm" in desc_lower:
+        color_scheme = color_schemes["vlm"]
+    else:
+        color_scheme = color_schemes["processing"]
     
     tqdm_config = {
         "total": total,
         "desc": desc,
         "leave": True,
         "bar_format": bar_format,
-        "ncols": _PROGRESS_CONFIG.ncols_env or 80,
+        "ncols": _PROGRESS_CONFIG.ncols_env or color_scheme["ncols"],  # Use same width as main progress bar
         "ascii": kwargs.get("ascii", False),
-        "dynamic_ncols": False,  # Fixed width for notebooks
-        "smoothing": 0.1,  # Faster updates
-        "mininterval": 0.05,
-        "maxinterval": 0.5,
+        "dynamic_ncols": True,  # Enable responsive width like main progress bar
+        "smoothing": 0.3,  # Use same smoothing as main progress bar
+        "mininterval": 0.1,  # Use same intervals as main progress bar
+        "maxinterval": 1.0,
         **kwargs
     }
     
-    return tqdm_auto(**tqdm_config)
+    # Use regular tqdm instead of tqdm_auto to avoid interactive widgets
+    return tqdm(**tqdm_config)
 
 
 def progress_for(iterable: Iterable[Any], desc: str, total: Optional[int] = None, leave: bool = True, **kwargs) -> Iterator[Any]:

{doctra-0.3.0 → doctra-0.3.2}/doctra/version.py

@@ -1,2 +1,2 @@
 """Version information for Doctra."""
-__version__ = '0.3.0'
+__version__ = '0.3.2'

{doctra-0.3.0 → doctra-0.3.2/doctra.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: doctra
-Version: 0.3.0
+Version: 0.3.2
 Summary: Parse, extract, and analyze documents with ease
 Home-page: https://github.com/AdemBoukhris457/Doctra
 Author: Adem Boukhris
@@ -234,6 +234,9 @@ Requires-Dist: opencv-python>=4.5.0
 Requires-Dist: pandas>=1.3.0
 Requires-Dist: openpyxl>=3.0.0
 Requires-Dist: tesseract>=0.1.3
+Requires-Dist: pytesseract>=0.3.10
+Requires-Dist: pdf2image>=1.16.0
+Requires-Dist: anthropic>=0.40.0
 Requires-Dist: outlines>=0.0.34
 Requires-Dist: tqdm>=4.62.0
 Requires-Dist: matplotlib>=3.5.0
@@ -241,8 +244,6 @@ Provides-Extra: openai
 Requires-Dist: openai>=1.0.0; extra == "openai"
 Provides-Extra: gemini
 Requires-Dist: google-generativeai>=0.3.0; extra == "gemini"
-Provides-Extra: anthropic
-Requires-Dist: anthropic>=0.40.0; extra == "anthropic"
 Provides-Extra: dev
 Requires-Dist: pytest>=6.0; extra == "dev"
 Requires-Dist: pytest-cov>=2.0; extra == "dev"
@@ -295,6 +296,31 @@ cd Doctra
 pip install .
 ```
 
+### System Dependencies
+
+Doctra requires **Poppler** for PDF processing. Install it based on your operating system:
+
+#### Ubuntu/Debian
+```bash
+sudo apt install poppler-utils
+```
+
+#### macOS
+```bash
+brew install poppler
+```
+
+#### Windows
+Download and install from [Poppler for Windows](http://blog.alivate.com.au/poppler-windows/) or use conda:
+```bash
+conda install -c conda-forge poppler
+```
+
+#### Google Colab
+```bash
+!sudo apt install poppler-utils
+```
+
 ## ⚡ Quick Start
 
 ```python

{doctra-0.3.0 → doctra-0.3.2}/doctra.egg-info/requires.txt

@@ -5,13 +5,13 @@ opencv-python>=4.5.0
 pandas>=1.3.0
 openpyxl>=3.0.0
 tesseract>=0.1.3
+pytesseract>=0.3.10
+pdf2image>=1.16.0
+anthropic>=0.40.0
 outlines>=0.0.34
 tqdm>=4.62.0
 matplotlib>=3.5.0
 
-[anthropic]
-anthropic>=0.40.0
-
 [dev]
 pytest>=6.0
 pytest-cov>=2.0

{doctra-0.3.0 → doctra-0.3.2}/pyproject.toml

@@ -36,6 +36,9 @@ dependencies = [
     "pandas>=1.3.0",
     "openpyxl>=3.0.0",
     "tesseract>=0.1.3",
+    "pytesseract>=0.3.10",
+    "pdf2image>=1.16.0",
+    "anthropic>=0.40.0",
     "outlines>=0.0.34",
     "tqdm>=4.62.0",
     "matplotlib>=3.5.0",
@@ -44,7 +47,6 @@ dependencies = [
 [project.optional-dependencies]
 openai = ["openai>=1.0.0"]
 gemini = ["google-generativeai>=0.3.0"]
-anthropic = ["anthropic>=0.40.0"]
 dev = [
     "pytest>=6.0",
     "pytest-cov>=2.0",

{doctra-0.3.0 → doctra-0.3.2}/setup.py

@@ -43,6 +43,9 @@ setup(
         "pandas>=1.3.0",
         "openpyxl>=3.0.0",
         "tesseract>=0.1.3",
+        "pytesseract>=0.3.10",
+        "pdf2image>=1.16.0",
+        "anthropic>=0.40.0",
         "outlines>=0.0.34",
         "tqdm>=4.62.0",
         "matplotlib>=3.5.0",
@@ -50,7 +53,6 @@ setup(
     extras_require={
         "openai": ["openai>=1.0.0"],
         "gemini": ["google-generativeai>=0.3.0"],
-        "anthropic": ["anthropic>=0.40.0"],
         "dev": [
             "pytest>=6.0",
             "pytest-cov>=2.0",