rpa-suite 1.5.9__py3-none-any.whl → 1.6.0__py3-none-any.whl

rpa_suite/__init__.py

@@ -27,7 +27,10 @@ Available modules:
     ``printer``: Functions for formatted output
     ``regex``: Operations with regular expressions
     ``validate``: Data validation functions
+    ``ParallelRunner``: Object ParallelRunner functions to run in parallel
+    ``AsyncRunner``: Object AsyncRunner functions to run in Assyncronous
     ``Browser``: Object Browser automation functions (neeeds Selenium and Webdriver_Manager)
+    ``Iris``: Object Iris automation functions to convert documents with OCR + IA based on ``docling``
 
 pt-br
 -----
@@ -57,10 +60,13 @@ Módulos disponíveis:
     ``printer``: Funções para output formatado
     ``regex``: Operações com expressões regulares
     ``validate``: Funções de validação de dados
+    ``ParallelRunner``: Objeto ParallelRunner funções para rodar processos em paralelo
+    ``AsyncRunner``: Objeto AsyncRunner funções para rodar processos em assincronicidade
     ``Browser``: Objeto de Automação de Navegadores (necessario Selenium e Webdriver_Manager)
+    ``Iris``: Objeto Iris Automação de funções para converter documentos com OCR + IA baseado em ``docling``
 """
 
-__version__ = "1.5.5"
+__version__ = "1.5.9"
 
 # allows importing the rpa_suite module without the package name
 from .suite import rpa

rpa_suite/core/iris.py

@@ -0,0 +1,327 @@
+# rpa_suite/core/iris.py
+"""
+Iris (OCR-IA) module for document conversion using DocLing.
+
+This module provides a simplified interface for converting documents
+into various formats, optimized for RPA automation use.
+"""
+
+from enum import Enum
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Union
+
+# imports internal
+from rpa_suite.functions._printer import alert_print, error_print, success_print
+
+
+class ExportFormat(Enum):
+    """Supported export formats for document conversion."""
+    
+    MARKDOWN = "markdown"
+    DICT = "dict"
+    DOCTAGS = "doctags"
+    HTML = "html"
+    TEXT = "text"
+
+
+class IrisError(Exception):
+    """Custom exception for Iris class errors."""
+    
+    pass
+
+
+class Iris:
+    """
+    Iris (OCR-IA)
+    Document converter using the DocLing library.
+    
+    This class provides a simplified interface for converting documents
+    in various formats (PDF, images, text) to structured formats such as
+    Markdown, HTML, plain text, among others.
+    
+    Attributes:
+        engine: Instance of DocLing's DocumentConverter.
+        last_result: Last processed conversion result.
+        
+    Example:
+        >>> iris = Iris()
+        >>> content = iris.read_document("document.pdf", ExportFormat.MARKDOWN)
+        >>> print(content)
+    """
+    
+    # Supported file extensions
+    SUPPORTED_EXTENSIONS = {
+        '.pdf', '.txt', '.docx', '.doc', '.png', '.jpg', '.jpeg', 
+        '.tiff', '.bmp', '.webp', '.pptx', '.xlsx'
+    }
+    
+    def __init__(self, display_message: bool = False) -> None:
+        """
+        Initializes the Iris class with the document converter.
+        
+        Raises:
+            IrisError: If the DocLing library is not installed.
+        """
+        self._engine: Optional[Any] = None
+        self._last_result: Optional[Any] = None
+        self.display_message: bool = display_message
+        self._initialize_engine()
+    
+    def _initialize_engine(self) -> None:
+        """
+        Initializes the DocumentConverter engine.
+        
+        Raises:
+            IrisError: If the DocLing library is not available.
+        """
+        try:
+            from docling.document_converter import DocumentConverter
+            self._engine = DocumentConverter()
+            if self.display_message: success_print("Iris engine initialized successfully")
+        except ImportError as e:
+            error_msg = (
+                "The 'docling' library is not installed. "
+                "Run: python -m pip install docling"
+            )
+            error_print(f"Iris - {error_msg}")
+            error_print(f"Error importing DocLing: {e}")
+            raise IrisError(error_msg) from e
+    
+    @property
+    def engine(self) -> Any:
+        """Returns the DocumentConverter engine instance."""
+        return self._engine
+    
+    @property
+    def last_result(self) -> Optional[Any]:
+        """Returns the last processed conversion result."""
+        return self._last_result
+    
+    def _validate_file_path(self, file_path: Union[str, Path]) -> Path:
+        """
+        Validates the file path and returns a Path object.
+        
+        Args:
+            file_path: Path to the file.
+            
+        Returns:
+            Path: Validated Path object.
+            
+        Raises:
+            IrisError: If the file does not exist or is not supported.
+        """
+        path_obj = Path(file_path)
+        
+        if not path_obj.exists():
+            raise IrisError(f"File not found: {file_path}")
+        
+        if not path_obj.is_file():
+            raise IrisError(f"Path does not point to a file: {file_path}")
+        
+        if path_obj.suffix.lower() not in self.SUPPORTED_EXTENSIONS:
+            supported = ", ".join(sorted(self.SUPPORTED_EXTENSIONS))
+            raise IrisError(
+                f"Extension '{path_obj.suffix}' is not supported. "
+                f"Supported extensions: {supported}"
+            )
+        
+        return path_obj
+    
+    def _convert_document(self, file_path: Path) -> Any:
+        """
+        Converts the document using DocumentConverter.
+        
+        Args:
+            file_path: Path to the file.
+            
+        Returns:
+            Result of the DocLing conversion.
+            
+        Raises:
+            IrisError: If the conversion fails.
+        """
+        try:
+            if self.display_message: success_print(f"Starting conversion of file: {file_path}")
+            result = self._engine.convert(str(file_path))
+            self._last_result = result
+            if self.display_message: success_print("Conversion completed successfully")
+            return result
+        except Exception as e:
+            error_msg = f"Error converting document '{file_path}': {e}"
+            error_print(f"Iris - {error_msg}")
+            error_print(error_msg)
+            raise IrisError(error_msg) from e
+    
+    def _export_to_format(self, document: Any, export_format: ExportFormat) -> Any:
+        """
+        Exports the document to the specified format.
+        
+        Args:
+            document: Document converted by DocLing.
+            export_format: Desired export format.
+            
+        Returns:
+            Document in the specified format.
+            
+        Raises:
+            IrisError: If the export fails.
+        """
+        export_methods = {
+            ExportFormat.MARKDOWN: document.export_to_markdown,
+            ExportFormat.DICT: document.export_to_dict,
+            ExportFormat.DOCTAGS: document.export_to_doctags,
+            ExportFormat.HTML: document.export_to_html,
+            ExportFormat.TEXT: document.export_to_text,
+        }
+        
+        try:
+            export_method = export_methods[export_format]
+            return export_method()
+        except KeyError:
+            available_formats = ", ".join([fmt.value for fmt in ExportFormat])
+            raise IrisError(
+                f"Format '{export_format.value}' is not supported. "
+                f"Available formats: {available_formats}"
+            )
+        except Exception as e:
+            error_msg = f"Error exporting to format '{export_format.value}': {e}"
+            error_print(error_msg)
+            raise IrisError(error_msg) from e
+    
+    def read_document(
+        self,
+        file_path: Union[str, Path],
+        export_format: ExportFormat = ExportFormat.MARKDOWN,
+        verbose: bool = False,
+    ) -> Optional[Any]:
+        """
+        Reads and converts a document to the specified format.
+        
+        Args:
+            file_path: Path to the document file.
+            export_format: Desired export format.
+            verbose: If True, displays success messages.
+            
+        Returns:
+            Document converted to the specified format, or None if it fails.
+            
+        Raises:
+            IrisError: If an error occurs during validation, conversion, or export.
+            
+        Example:
+            >>> iris = Iris()
+            >>> content = iris.read_document("doc.pdf", ExportFormat.TEXT)
+            >>> print(content)
+        """
+        try:
+            # File validation
+            validated_path = self._validate_file_path(file_path)
+            
+            # Document conversion
+            conversion_result = self._convert_document(validated_path)
+            
+            # Conversion result check
+            if not conversion_result or not hasattr(conversion_result, 'document'):
+                raise IrisError("Invalid conversion result or document not found")
+            
+            # Export to desired format
+            formatted_result = self._export_to_format(
+                conversion_result.document, 
+                export_format
+            )
+            
+            if verbose:
+                success_print("Iris - Conversion completed successfully")
+            
+            success_print(
+                f"Document '{validated_path.name}' converted to '{export_format.value}'"
+            )
+            
+            return formatted_result
+            
+        except IrisError:
+            # Re-raise exceptions from the class itself
+            raise
+        except Exception as e:
+            error_msg = f"Unexpected error while processing document: {e}"
+            error_print(f"Iris - {error_msg}")
+            error_print(error_msg)
+            raise IrisError(error_msg) from e
+    
+    def read_multiple_documents(
+        self,
+        file_paths: List[Union[str, Path]],
+        export_format: ExportFormat = ExportFormat.MARKDOWN,
+        verbose: bool = False,
+    ) -> Dict[str, Optional[Any]]:
+        """
+        Reads and converts multiple documents.
+        
+        Args:
+            file_paths: List of file paths.
+            export_format: Desired export format.
+            verbose: If True, displays detailed messages.
+            
+        Returns:
+            Dictionary with the file name as key and converted content as value.
+            
+        Example:
+            >>> iris = Iris()
+            >>> files = ["doc1.pdf", "doc2.txt"]
+            >>> results = iris.read_multiple_documents(files, ExportFormat.TEXT)
+            >>> for filename, content in results.items():
+            ...     print(f"{filename}: {len(content) if content else 0} characters")
+        """
+        results = {}
+        successful_conversions = 0
+        
+        for file_path in file_paths:
+            try:
+                content = self.read_document(file_path, export_format, verbose=False)
+                filename = Path(file_path).name
+                results[filename] = content
+                successful_conversions += 1
+                
+                if verbose:
+                    if self.display_message: success_print(f"Iris - '{filename}' converted successfully")
+                    
+            except IrisError as e:
+                filename = Path(file_path).name
+                results[filename] = None
+                if verbose:
+                    error_print(f"Iris - Error converting '{filename}': {e}")
+                alert_print(f"Failed to convert '{filename}': {e}")
+        
+        if verbose:
+            total_files = len(file_paths)
+            if self.display_message: success_print(
+                f"Iris - Processing completed: {successful_conversions}/{total_files} "
+                f"files converted successfully"
+            )
+        
+        return results
+    
+    def get_supported_extensions(self) -> List[str]:
+        """
+        Returns the list of supported file extensions.
+        
+        Returns:
+            Sorted list of supported extensions.
+        """
+        return sorted(list(self.SUPPORTED_EXTENSIONS))
+    
+    def is_file_supported(self, file_path: Union[str, Path]) -> bool:
+        """
+        Checks if a file is supported by the class.
+        
+        Args:
+            file_path: Path to the file.
+            
+        Returns:
+            True if the file is supported, False otherwise.
+        """
+        try:
+            path_obj = Path(file_path)
+            return path_obj.suffix.lower() in self.SUPPORTED_EXTENSIONS
+        except Exception:
+            return False

rpa_suite/suite.py

@@ -13,7 +13,6 @@ from .core.validate import Validate
 from .core.parallel import ParallelRunner
 from .core.asyncrun import AsyncRunner
 
-
 # imports external
 from colorama import Fore
 from importlib.metadata import version
@@ -104,6 +103,10 @@ class Suite:
         ``printer``: Functions for formatted output
         ``regex``: Operations with regular expressions
         ``validate``: Data validation functions
+        ``ParallelRunner``: Object ParallelRunner functions to run in parallel
+        ``AsyncRunner``: Object AsyncRunner functions to run in Assyncronous
+        ``Browser``: Object Browser automation functions (neeeds Selenium and Webdriver_Manager)
+        ``Iris``: Object Iris automation functions to convert documents with OCR + IA based on ``docling``
 
     pt-br
     -----
@@ -133,6 +136,10 @@ class Suite:
         ``printer``: Funções para output formatado
         ``regex``: Operações com expressões regulares
         ``validate``: Funções de validação de dados
+        ``ParallelRunner``: Objeto ParallelRunner funções para rodar processos em paralelo
+        ``AsyncRunner``: Objeto AsyncRunner funções para rodar processos em assincronicidade
+        ``Browser``: Objeto de Automação de Navegadores (necessario Selenium e Webdriver_Manager)
+        ``Iris``: Objeto Iris Automação de funções para converter documentos com OCR + IA baseado em ``docling``
     """
 
     # SUBMODULES
@@ -148,8 +155,8 @@ class Suite:
     Parallel: ParallelRunner = ParallelRunner
     Asyn: AsyncRunner = AsyncRunner
 
-    # On this case, we are importing the Browser class only if the selenium and webdriver_manager modules are installed.
-    # This is useful to avoid unnecessary imports and dependencies if the user does not need the Browser functionality.
+    # On this case, we are importing the (Browser | Iris) class only if the selenium and webdriver_manager modules are installed.
+    # This is useful to avoid unnecessary imports and dependencies if the user does not need the (Browser | Iris) functionality.
     import importlib.util
 
     # from .browser import Browser
@@ -158,6 +165,12 @@ class Suite:
 
         browser: Browser = Browser
 
+    # from .iris import Iris
+    if importlib.util.find_spec("docling"):
+        from .core.iris import Iris
+
+        iris: Iris = Iris
+        
     # VARIABLES INTERNAL
     try:
         # old: __version__ = pkg_resources.get_distribution("rpa_suite").version
@@ -312,10 +325,16 @@ class Suite:
 
     def __install_all_libs(self):
         """
+        Method responsible for installing all libraries for advanced use of RPA-Suite, including all features such as OCR and AI agent.
+        ----------
         Metodo responsavel por instalar todas libs para uso avançado do RPA-Suite com todas funcionalidades incluindo OCR e agente de IA
         """
 
         libs = [
+            "setuptools",
+            "wheel",
+            "pyperclip",
+            "pywin32"
             "colorama",
             "colorlog",
             "email_validator",
@@ -326,15 +345,16 @@ class Suite:
             "selenium",
             "typing",
             "webdriver_manager",
+            "docling",
         ]
 
         for lib in libs:
             try:
                 subprocess.check_call([sys.executable, "-m", "pip", "install", lib])
-                self.success_print(f"Biblioteca {lib} instalada com sucesso!")
+                self.success_print(f"Suite RPA: Library {lib} installed successfully!")
 
             except subprocess.CalledProcessError:
-                self.error_print(f"Erro ao instalar biblioteca {lib}")
+                self.error_print(f"Suite RPA: Error installing library {lib}")
 
 
 rpa = Suite()

{rpa_suite-1.5.9.dist-info → rpa_suite-1.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rpa_suite
-Version: 1.5.9
+Version: 1.6.0
 Summary: Conjunto de ferramentas essenciais para Automação RPA com Python, que facilitam o dia a dia de desenvolvimento.
 Author: Camilo Costa de Carvalho
 Author-email: camilo.carvalho@vettracode.com
@@ -282,19 +282,33 @@ O módulo principal do rpa-suite é dividido em categorias. Cada categoria cont
   - **get_result** - Função para obter o resultado da execução assíncrona, incluindo tempo de execução e status, com suporte a timeout.
   - **cancel** - Função para cancelar a tarefa assíncrona em execução.
 
+  **Iris (OCR-IA)**
+
+  - **read_document** - Reads and converts a document to the specified format.
+  - **read_multiple_documents** - Reads and converts multiple documents.
+  - **get_supported_extensions** - Returns the list of supported file extensions
+  - **is_file_supported** - Checks if a file is supported by the class.
+
+
 ## Release Notes
 
-### Versão: **Beta 1.5.9**
+### Versão: **Beta 1.6.0**
 
 - **Data de Lançamento:** *20/02/2024*
-- **Última Atualização:** 06/06/2025
+- **Última Atualização:** 08/06/2025
 - **Status:** Em desenvolvimento
 
 Esta versão marca um grande avanço no desenvolvimento da RPA Suite, trazendo melhorias significativas na arquitetura, novas funcionalidades e maior simplicidade no uso. Confira as principais mudanças abaixo.
 
-### Notas da atualização:
+### Notas:
+- atualização 1.6.0 
+  - Adição Módulo: Iris (OCR-IA)
+  - Feat.: leitura de documento (aceita multiplos formatos)
+  - Feat.: leitura em lote (multiplos docmumentos em uma unica chamada)
+  - Melhoria de docstrings
 
-- Atualização de Linters e Formatters
+- atualização 1.5.9 
+  - Atualização de Linters e Formatters
   - black
   - pylint
   - bandit

{rpa_suite-1.5.9.dist-info → rpa_suite-1.6.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-rpa_suite/__init__.py,sha256=uk4XRRpZn734AlzjPgvbmW0mO384jmOdYOZ8a0c--Q8,2365
-rpa_suite/suite.py,sha256=E4UDl4SgLSu2c2yI-qmK48NbQH2WwjSfvq3MAjmGnJ4,10568
+rpa_suite/__init__.py,sha256=WqIndloIi1jP_YsEf0lGNOxgr7Htdgt6XuL5ti5znb8,2915
+rpa_suite/suite.py,sha256=j07ZkaJttJ9WhfIKcc7j6h11ZssRzWdpcvXQDBYZT_s,11804
 rpa_suite/core/__init__.py,sha256=2KWotqRNuCNwVhACACB4zhrXnTWR9H77_6U6j0WTJK0,1738
 rpa_suite/core/asyncrun.py,sha256=gRKsqvT4QAwg906BkLQXHi-oMbjM30D3yRWV1qAqj1Y,4192
 rpa_suite/core/browser.py,sha256=NeJk8lWDKZcGR9ULfWkDZ4WmFujU-DVr5-QH0qUSSgU,14725
@@ -8,6 +8,7 @@ rpa_suite/core/date.py,sha256=nnAktYMZNjcN4e6HEiYJgdMLD5VZluaOjfyfSPaz71c,6307
 rpa_suite/core/dir.py,sha256=ZfgFeCkl8iB8Tc5dST35olImpj4PoWThovNYvtpwnu8,10329
 rpa_suite/core/email.py,sha256=D69vPmoBJYwSTgDu5tvXhakvsYprXr0BAFRYeaVicx0,8473
 rpa_suite/core/file.py,sha256=hCXoWiEGtxRfp5Uq33p0f2eDwKUv3dEiUSajOhpNwbc,11317
+rpa_suite/core/iris.py,sha256=Z8aP96y78-DnzUxwtxJZiIXXOLXWTCsaWpdMoxROfQY,11467
 rpa_suite/core/log.py,sha256=9dPDnV8e4p9lwZoyd1ICb6CjJiiSXTXVJseQkdtdRuQ,6542
 rpa_suite/core/parallel.py,sha256=a_aEqvoJ9jxsFg1H42wsPT2pCS3WApqbGc2PETgBBEs,11460
 rpa_suite/core/print.py,sha256=i1icdpNreQf2DCO6uLQKuuUD0vsrsOnYSpiQGaGNJi4,5780
@@ -18,8 +19,8 @@ rpa_suite/functions/__init__.py,sha256=Y9Kp8tTmyCcQ4sErjb0c2cbDNTAAoTArEF2pYl7mt
 rpa_suite/functions/_printer.py,sha256=gj7dwOt4roSj2iwOGWeGgUD3JVr7h4UESyCg9CmrieA,3946
 rpa_suite/utils/__init__.py,sha256=bqxq5kckulcQzNCn1tHwHj0WMIQBTUYNDzMzBhLtbIY,729
 rpa_suite/utils/system.py,sha256=kkTsjwBQ-8_G_6l-0tuwkpmeI3KVssRZ7QAiYlR3vt0,5185
-rpa_suite-1.5.9.dist-info/licenses/LICENSE,sha256=5D8PIbs31iGd9i1_MDNg4SzaQnp9sEIULALh2y3WyMI,1102
-rpa_suite-1.5.9.dist-info/METADATA,sha256=Cb7VubI35_hoUBEU8Tkz1RQke7yFpqkAyUUBfo9ydbs,12978
-rpa_suite-1.5.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rpa_suite-1.5.9.dist-info/top_level.txt,sha256=HYkDtg-kJNAr3F2XAIPyJ-QBbNhk7q6jrqsFt10lz4Y,10
-rpa_suite-1.5.9.dist-info/RECORD,,
+rpa_suite-1.6.0.dist-info/licenses/LICENSE,sha256=5D8PIbs31iGd9i1_MDNg4SzaQnp9sEIULALh2y3WyMI,1102
+rpa_suite-1.6.0.dist-info/METADATA,sha256=sIX1G91PeiHFKxPIrckrZFQ32BgGfv5Mf4YwKFsM4sQ,13546
+rpa_suite-1.6.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rpa_suite-1.6.0.dist-info/top_level.txt,sha256=HYkDtg-kJNAr3F2XAIPyJ-QBbNhk7q6jrqsFt10lz4Y,10
+rpa_suite-1.6.0.dist-info/RECORD,,