convert-stream 1.1.1__tar.gz → 1.2__tar.gz

{convert_stream-1.1.1 → convert_stream-1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 1.1.1
+Version: 1.2
 Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
 Author: Bruno Chaves
 Requires-Python: >=3.11

convert_stream-1.2/convert_stream/__init__.py

@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+#
+from ._version import (
+    __version__, __module_name__, 
+    __author__, __license__, __modify_date__
+)
+version = __version__
+
+from .text import (
+    ArrayString, ConvertDate, DataString, 
+    LibraryDates, print_title, print_line, save_data
+)
+
+from .models.progress_bar import (
+    ProgressBarAdapter, ProgressBarSimple, ProgressBarTqdm, ABCProgressBar
+)
+from .models.models_pdf import LibraryPDF
+from .imagelib import ImageObject, ImageInverColor, LibraryImage
+from .pdf_page import PageDocumentPdf, PagePdfFitz, PagePyPdf2
+from .pdf_document import DocumentPdf
+from .pdf_convert import ConvertPdfToImage, ImageConvertPdf
+from .convert import PdfStream, ImageStream, get_data_from_pdfs
+

{convert_stream-1.1.1 → convert_stream-1.2}/convert_stream/__main__.py

@@ -16,11 +16,16 @@ this_file = os.path.abspath(os.path.relpath(__file__))
 dir_of_project = os.path.dirname(this_file)
 sys.path.insert(0, dir_of_project)
 
-from convert_stream import version, __module_name__, __modify_date__, print_title
+from convert_stream import (
+    version, __module_name__, __modify_date__, print_title
+)
+
 
 def test():
-    pass
-    
+    from convert_stream import PageDocumentPdf, PdfStream, DocumentPdf
+    from soup_files import File, Directory, UserFileSystem
+
+
 def main():
     print_title(f'{__module_name__} versão {version} - {__modify_date__}', char='-')
     test()

{convert_stream-1.1.1 → convert_stream-1.2}/convert_stream/_version.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-__version__ = '1.1'
+__version__ = '1.2'
 __author__ = 'Bruno Chaves'
 __license__ = 'MIT'
 __module_name__ = 'pdflib'
-__modify_date__ = '2025-04-22'
+__modify_date__ = '2025-05-28'

{convert_stream-1.1.1 → convert_stream-1.2}/convert_stream/convert.py

@@ -6,6 +6,7 @@ import pandas
 
 from convert_stream.models import ABCDocumentStream, LibraryImage, LibraryPDF
 from convert_stream.imagelib import ImageObject
+from convert_stream.models.progress_bar import ProgressBarAdapter, ProgressBarSimple
 from convert_stream.pdf_page import PageDocumentPdf
 from convert_stream.pdf_document import DocumentPdf
 from convert_stream.pdf_convert import ConvertPdfToImage, ImageConvertPdf
@@ -14,17 +15,24 @@ from soup_files import File, Directory
 #==================================================================#
 # PDF
 #==================================================================#
+
 class PdfStream(ABCDocumentStream):
     """
         Objeto para manipular a exportação de dados PDF    
     """
-    def __init__(self, *, library_pdf=LibraryPDF.FITZ, library_image=LibraryImage.OPENCV):
-        
-        self.num_pages:int = 0 
-        self.library_pdf:LibraryPDF = library_pdf
-        self.library_image:LibraryImage = library_image
-        self.document:DocumentPdf = DocumentPdf(self.library_pdf)
-        self.converPdfToImages:ConvertPdfToImage = ConvertPdfToImage(library_image=library_image)
+
+    def __init__(
+                    self, *,
+                    library_pdf: LibraryPDF = LibraryPDF.FITZ,
+                    library_image: LibraryImage = LibraryImage.OPENCV,
+                    progress_bar: ProgressBarAdapter = ProgressBarAdapter(ProgressBarSimple())
+            ):
+        super().__init__(library_pdf=library_pdf, library_image=library_image, progress_bar=progress_bar)
+        self.num_pages: int = 0
+        self.library_pdf: LibraryPDF = library_pdf
+        self.library_image: LibraryImage = library_image
+        self.document: DocumentPdf = DocumentPdf(self.library_pdf, progress_bar=progress_bar)
+        self.convertPdfToImages: ConvertPdfToImage = ConvertPdfToImage(library_image=library_image)
         
         if self.library_pdf == LibraryPDF.CANVAS:
             self.imagesToPdf:ImageConvertPdf = ImageConvertPdf.create_from_canvas(self.library_image)
@@ -64,23 +72,28 @@ class PdfStream(ABCDocumentStream):
             return
         self.document.add_page(p)
             
-    def add_pages(self, pages:List[PageDocumentPdf]):
+    def add_pages(self, pages: List[PageDocumentPdf]):
         if not isinstance(pages, list):
             print(f'{__class__.__name__} Erro: Use lista de PageDocumentPdf, não {type(pages)}')
             return
-        for p in pages:
+        max_num: int = len(pages)
+        for num, p in enumerate(pages):
+            self.progress_bar.update(
+                ((num+1)/max_num) * 100,
+                f'Adicionando página: [{num+1} de {max_num}]'
+            )
             self.add_page(p)
-            
-    def add_page_pdf_bytes(self, bt:bytes):
+
+    def add_page_pdf_bytes(self, bt: bytes):
         _page = PageDocumentPdf.create_from_page_bytes(bt, library=self.library_pdf)
         self.add_page(_page)
             
-    def add_file_pdf(self, f:File):
-        doc:DocumentPdf = DocumentPdf(self.library_pdf)
+    def add_file_pdf(self, f: File):
+        doc: DocumentPdf = DocumentPdf(self.library_pdf)
         doc.add_file_pdf(f)
         self.add_pages(doc.pages)
         
-    def add_files_pdf(self, files:List[File]):
+    def add_files_pdf(self, files: List[File]):
         for f in files:
             self.add_file_pdf(f)
             
@@ -91,16 +104,16 @@ class PdfStream(ABCDocumentStream):
         pg: PageDocumentPdf = self.imagesToPdf.from_image(image)
         self.add_page(pg)
         
-    def to_file_pdf(self, f:File):
+    def to_file_pdf(self, f: File):
         if self.is_null():
             print(
                 f'{__class__.__name__} Nenhuma página foi adiconada, adicione páginas ao documento para prosseguir!'
             )
-        docpdf:DocumentPdf = DocumentPdf(self.library_pdf)
+        docpdf: DocumentPdf = DocumentPdf(self.library_pdf, progress_bar=self.progress_bar)
         docpdf.add_pages(self.pages)
         docpdf.to_file_pdf(f)
         
-    def to_files_pdf(self, outdir:Directory, *, prefix='pag'):
+    def to_files_pdf(self, outdir: Directory, *, prefix='pag'):
         if self.is_null():
             print(
                 f'{__class__.__name__} Nenhuma página foi adiconada, adicione páginas ao documento para prosseguir!'
@@ -122,14 +135,14 @@ class PdfStream(ABCDocumentStream):
         d.mkdir()
         for num, page in enumerate(self.pages):
             filename = f'{prefix}-{page.page_number}.png'
-            img = self.converPdfToImages.from_page_pdf(page)
+            img = self.convertPdfToImages.from_page_pdf(page)
             print(f'Exportando página PDF para imagem: [{num+1} de {self.num_pages}] {filename}')
             img.to_file(d.join_file(filename))
             
     def to_images(self) -> List[ImageObject]:
         images_obj:List[ImageObject] = []
         for page in self.pages:
-            images_obj.append(self.converPdfToImages.from_page_pdf(page))
+            images_obj.append(self.convertPdfToImages.from_page_pdf(page))
         return images_obj
     
     def to_document(self) -> DocumentPdf:
@@ -141,7 +154,7 @@ class PdfStream(ABCDocumentStream):
         inner_images:List[ImageObject] = []
         for p in self.pages:
             inner_images.extend(
-                self.converPdfToImages.inner_images(p.to_bytes())
+                self.convertPdfToImages.inner_images(p.to_bytes())
             )
         return inner_images
     
@@ -152,7 +165,7 @@ class PdfStream(ABCDocumentStream):
         outdir = d #.concat(f'{num+1}')
         outdir.mkdir()
         for num, page in enumerate(self.pages):
-            images = self.converPdfToImages.inner_images(page.to_bytes())
+            images = self.convertPdfToImages.inner_images(page.to_bytes())
             if len(images) < 1:
                 continue
             for n, img in enumerate(images):
@@ -166,6 +179,7 @@ class PdfStream(ABCDocumentStream):
 #==================================================================#
 # Imagens
 #==================================================================#
+
 class ImageStream(object):
     def __init__(self, *, library_image=LibraryImage.OPENCV, library_pdf=LibraryPDF.PILPDF):
         self.__images:List[ImageObject] = []

{convert_stream-1.1.1 → convert_stream-1.2}/convert_stream/imagelib.py

@@ -9,7 +9,7 @@ import cv2
 import numpy as np
 
 from soup_files import File
-from convert_stream.models.m_imgelib import LibraryImage, ABCImageObject, ABCInvertColor
+from convert_stream.models.models_image import LibraryImage, ABCImageObject, ABCInvertColor
 
 #=============================================================================#
 # Inverter cores em imagens

convert_stream-1.2/convert_stream/models/__init__.py

@@ -0,0 +1,13 @@
+#!/usr/bin/env python3
+from .m_text import (
+    DataString, ConvertDate, ConvertStringDate,
+    ArrayString, LibraryDates,
+    print_line, print_title, save_data
+)
+
+from .models_image import LibraryImage, ABCImageObject, ABCInvertColor
+from .models_pdf import (
+    LibraryPDF, ABCDocumentPdf, ABCPagePdf,
+    ABCConvertPdf, ABCImageConvertPdf, ABCDocumentStream,
+)
+

{convert_stream-1.1.1 → convert_stream-1.2}/convert_stream/models/m_text.py

@@ -34,7 +34,6 @@ def print_title(title:str, char:str='='):
     print(title.center(num_size, char))
     
 
-
 class LibraryDates(Enum):
     D_M_Y = '%d-%m-%Y'
     DMY = '%d/%m/%Y'
@@ -42,38 +41,8 @@ class LibraryDates(Enum):
     d_m_y = '%d-%m-%y'
     YMD = '%Y/%m/%d' 
     Y_M_D = '%Y-%m-%d'  
+     
         
-def is_valid_date(d) -> bool:
-    valid_formats = (
-            '%d-%m-%Y',  # Exemplo: 11-01-2025
-            '%d/%m/%y',
-            '%d-%m-%y',
-            '%Y/%m/%d',  # Exemplo: 2025/01/11
-            '%d/%m/%Y',  # Exemplo: 11/01/2025
-            '%Y-%m-%d',  # Exemplo: 2025-01-11
-            '%d %B %Y',  # Exemplo: 11 Janeiro 2025
-            '%b %d, %Y', # Exemplo: Jan 11, 2025
-            '%A, %d %B %Y', # Exemplo: Sábado, 11 Janeiro 2025
-            '%H:%M:%S',  # Exemplo: 08:35:00
-            '%H:%M',     # Exemplo: 08:35
-            '%I:%M %p',  # Exemplo: 08:35 AM
-            '%Y-%m-%d %H:%M:%S',  # Exemplo: 2025-01-11 08:35:00
-            '%Y-%m-%dT%H:%M:%S',  # Exemplo: 2025-01-11T08:35:00 (Formato ISO 8601)
-            '%Y%m%dT%H%M%S',      # Exemplo: 20250111T083500 (Formato compactado)
-        )
-        #
-        
-    _valid = False
-    for fmt in valid_formats:
-        try:
-            datetime.strptime(d, fmt)
-            _valid = True
-            break
-        except ValueError:
-            pass
-    #
-    return _valid
-
 def save_data(df:DataFrame, file:File):
     try:
         df.to_excel(file.absolute(), index=False)
@@ -82,10 +51,11 @@ def save_data(df:DataFrame, file:File):
     else:
         print('OK')
 
-class ConvertDate(object):
+
+class ConvertStringDate(object):
     def __init__(self):
         """
-         Converter vários formatos de datas.
+            Converter vários formatos de datas.
         """
         self.valid_formats = (
             '%d-%m-%Y',  # Exemplo: 11-01-2025
@@ -119,7 +89,7 @@ class ConvertDate(object):
         )
         #
         # Dicionário de mapeamento de nomes de meses em português para inglês
-        self.meses_para_ingles = {
+        self.meses_ptbr_para_ingles = {
             'Janeiro': 'January',
             'Fevereiro': 'February',
             'Março': 'March',
@@ -141,25 +111,43 @@ class ConvertDate(object):
             "setembro": "09", "outubro": "10", "novembro": "11", "dezembro": "12"
         }
 
-    def is_valid_date(self, d:str) -> bool:
+    def is_valid_date(self, date_str:str) -> bool:
+        """
+            Verificar se uma string é uma data válida
+        """
+        # Tentar conversão com formatos tradicionais.
+        date_str = date_str.strip()
         for fmt in self.valid_formats:
             try:
-                datetime.strptime(d, fmt)
+                datetime.strptime(date_str, fmt)
                 return True
             except:
                 pass
         
-        if ',' in d:
+        if ('de' in date_str) and (',' in date_str):
+            # Sexta-feira, 25 de abril de 2025
+            date_str = date_str.split(',')[1].strip()
+            date_str = date_str.replace(' ', '-').replace('de', '').replace('--', '-').strip()
+            
+        if '-' in date_str:
+            for _key in self.meses_ptbr_para_numeros.keys():
+                if _key in date_str:
+                    new = self._long_date_ptbr_format(date_str)
+                    if new is not None:
+                        return True
+        
+        if self._long_date_ptbr_format(date_str) is not None:
+            return True
+        if self.is_timestamp(date_str):
+            return True
+        if ',' in date_str:
             try:
-                d = self._long_date_ptbr_to_eng(d)
+                # Sábado, 11 Janeiro 2025
+                date_str = self._long_date_ptbr_to_eng(date_str)
             except:
                 pass
             else:
                 return True
-        if self.is_timestamp(d):
-            return True
-        if self.convert_string_date_ptbr(d) is not None:
-            return True
         return False
     
     def is_timestamp(self, d:object) -> bool:
@@ -177,9 +165,7 @@ class ConvertDate(object):
         return False
     
     def _long_date_ptbr_to_eng(self, data_string:str, fmt:str='%A, %d %B %Y') -> str:
-        
-        # Exemplo de data em string com o dia da semana em português
-        data_string = 'Sábado, 11 Janeiro 2025'
+        # Exemplo de data em string com o dia da semana em português => 'Sábado, 11 Janeiro 2025'
 
         # Remover o dia da semana da string
         new_string_date = data_string.split(", ")[1]
@@ -188,7 +174,7 @@ class ConvertDate(object):
         current_data_fmt = '%d %B %Y'
 
         # Substituir o nome do mês em português pelo nome em inglês
-        for pt_mes, en_mes in self.meses_para_ingles.items():
+        for pt_mes, en_mes in self.meses_ptbr_para_ingles.items():
             new_string_date = new_string_date.replace(pt_mes, en_mes)
 
         # Converter a string para um objeto datetime
@@ -197,7 +183,7 @@ class ConvertDate(object):
         # Formatando o objeto datetime para o formato desejado "dia/mês/ANO"
         return to_datetime.strftime(fmt)
     
-    def convert_string_date_ptbr(self, data_str_ptbr:str, *, fmt:LibraryDates=LibraryDates.DMY) -> str | None:
+    def _long_date_ptbr_format(self, data_str_ptbr:str, *, fmt:LibraryDates=LibraryDates.DMY) -> str | None:
             # Divide a string e substitui o mês pelo número correspondente
             try:
                 dia, mes, ano = data_str_ptbr.split("-")
@@ -209,23 +195,39 @@ class ConvertDate(object):
                 print(e)
                 return None
 
-    def convert_date(self, date:str, *, fmt:LibraryDates=LibraryDates.DMY) -> str | None:
+    def convert_date(self, date_str:str, *, fmt:LibraryDates=LibraryDates.DMY) -> str | None:
         """
             Converter uma data em string para um formato qualquer.
         """
-        if not self.is_valid_date(date):
+        if not self.is_valid_date(date_str):
             return None
-        if ',' in date:
-            date = self._long_date_ptbr_to_eng(date)
+        
+        if ('de' in date_str) and (',' in date_str):
+            # Sexta-feira, 25 de abril de 2025
+            date_str = date_str.split(',')[1].strip()
+            date_str = date_str.replace(' ', '-').replace('de', '').replace('--', '-').strip()
+            new = self._long_date_ptbr_format(date_str, fmt=fmt)
+            if new is not None:
+                return new
+            
+        if '-' in date_str:
+            for _key in self.meses_ptbr_para_numeros.keys():
+                if _key in date_str:
+                    new = self._long_date_ptbr_format(date_str)
+                    if new is not None:
+                        return new
+                    
+        if ',' in date_str:
+            date_str = self._long_date_ptbr_to_eng(date_str)
         
         for current_format in self.valid_formats:
             try:
-                date_obj = datetime.strptime(date, current_format)
+                date_obj = datetime.strptime(date_str, current_format)
             except:
                 pass
             else:
                 return date_obj.strftime('{}'.format(fmt.value))
-        return self.convert_string_date_ptbr(date, fmt=fmt)  
+        return None  
              
     def convert_timestamp(self, ts:str, *, fmt:LibraryDates=LibraryDates.DMY) -> str | None:
         """
@@ -244,6 +246,52 @@ class ConvertDate(object):
         return None
 
 
+
+class ConvertDate(object):
+    def __init__(self):
+        """
+         Converter vários formatos de datas.
+        """
+        print(
+            f'''
+            [!] INFO: Em versões futuras a classe {__class__.__name__} será excluída, para formatar data Use 
+            a classe ConvertStringDate()
+            '''
+        )
+        self.convert: ConvertStringDate = ConvertStringDate()
+        self.valid_formats = self.convert.valid_formats
+        self.valid_timestamp = self.convert.valid_timestamp
+        self.meses_para_ingles = self.convert.meses_ptbr_para_ingles
+        self.meses_ptbr_para_numeros = self.convert.meses_ptbr_para_numeros
+
+    def is_valid_date(self, d:str) -> bool:
+        return self.convert.is_valid_date(d)
+    
+    def is_timestamp(self, d:object) -> bool:
+        """
+            Verifica se o objeto atual é timestamp
+        """
+        return self.convert.is_timestamp(d)
+    
+    def _long_date_ptbr_to_eng(self, data_string:str, fmt:str='%A, %d %B %Y') -> str:
+        return self.convert._long_date_ptbr_to_eng(data_string, fmt)
+    
+    def convert_string_date_ptbr(self, data_str_ptbr:str, *, fmt:LibraryDates=LibraryDates.DMY) -> str | None:
+            return self.convert.convert_date(data_str_ptbr, fmt=fmt)
+
+    def convert_date(self, date:str, *, fmt:LibraryDates=LibraryDates.DMY) -> str | None:
+        """
+            Converter uma data em string para um formato qualquer.
+        """
+        return self.convert.convert_date(date, fmt=fmt)  
+             
+    def convert_timestamp(self, ts:str, *, fmt:LibraryDates=LibraryDates.DMY) -> str | None:
+        """
+            Converter uma data em string para um formato qualquer.
+        """
+        return self.convert.convert_timestamp(ts, fmt=fmt)
+
+
         
 class DataString(object):
     def __init__(self, value:str):
@@ -421,60 +469,4 @@ class ArrayString(object):
         except:
             return None
     
-            
-            
-# Tabela de arquivo/texto
-class TableText(object):
-    def __init__(self, values:str, *, separator:str='\n', column_text:str='TEXT', file:File=None):
-        self.values:str = values
-        self.separator:str = separator
-        self.column_text:str = column_text
-        self.file:File = file
-        
-    def get_len(self) -> int:
-        return len(self.to_list())
-        
-    def is_null(self) -> bool:
-        if (self.values == None) or (self.values == ''):
-            return True
-        return False
-        
-    def to_upper(self) -> None:
-        self.values = self.values.upper()
-        
-    def to_list(self) -> List[str]:
-        try:
-            return self.values.split(self.separator)
-        except Exception as e:
-            print(e)
-            return []
-        
-    def to_dict(self) -> Dict[str, List[str]]:
-        lines = self.to_list()
-        if len(lines) < 1:
-            return {}
-        tb:Dict[str, List[str]] = {}
-        tb[self.column_text] = []
-        tb['NUM_LINHA'] = []
-        for num, item in enumerate(lines):
-            tb['NUM_LINHA'].append(num+1)
-            tb[self.column_text].append(item)
-        
-        max_num:int = len(lines)
-        if self.file is not None:
-            tb['NOME_ARQUIVO'] = [self.file.basename()] * max_num
-            tb['MD5'] = [self.file.md5()] * max_num
-            tb['EXTENSÃO'] = [self.file.extension()] * max_num
-            tb['ARQUIVO'] = [self.file.absolute()] * max_num 
-            tb['PASTA'] = [self.file.dirname()] * max_num
-        return tb
-        
-    def to_data(self) -> DataFrame:
-        if self.is_null():
-            return DataFrame()
-        return DataFrame(self.to_dict())
-    
-    def to_excel(self, file:File):
-        if file.extension() != '.xlsx':
-            raise ValueError(f'{__class__.__name__} o arquivo precisa de do tipo .xlsx')
-        self.to_data().to_excel(file.absolute(), index=False)
+            

convert_stream-1.1.1/convert_stream/models/m_imgelib.py → convert_stream-1.2/convert_stream/models/models_image.py

@@ -1,15 +1,14 @@
 #!/usr/bin/env python3
 #
-
 from __future__ import annotations
 from abc import ABC, abstractmethod
 from enum import Enum
-from typing import List, Tuple
 from PIL import Image
 from cv2.typing import MatLike
 import cv2
 from soup_files import File
 
+
 class LibraryImage(Enum):
     PIL = 1
     OPENCV = 2