convert-stream 2.4.4__tar.gz → 2.5__tar.gz

{convert_stream-2.4.4 → convert_stream-2.5}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.4.4
+Version: 2.5
 Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
 Author: Bruno Chaves
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
-Requires-Dist: soup_files>=1.4
+Requires-Dist: soup_files>=1.4.2
 Requires-Dist: PyMuPDF
 Requires-Dist: scipy
 Requires-Dist: reportlab
@@ -15,7 +15,7 @@ Requires-Dist: pandas
 Requires-Dist: Pillow>=11.3.0
 Requires-Dist: opencv-python
 Requires-Dist: requests>=2.32.4
-Requires-Dist: sheet_stream
+Requires-Dist: sheet_stream>=0.1.3
 
 # Configuração instalação:
 pip3 install -r requirements.txt

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/__init__.py

@@ -8,11 +8,17 @@ from ._version import (
     __module_name__, __author__, __license__, __modify_date__, __version__
 )
 from .mod_types import (
-    LibPDF, LibImage, LibPdfToImage,    LibImageToPdf, DictTextTable, RotationAngle,
+    LibPDF, LibImage, LibPdfToImage,  LibImageToPdf, RotationAngle,
 )
-from .image import ImageObject, CollectionImages
-from .pdf import DocumentPdf, PageDocumentPdf, CollectionPagePdf, ConvertPdfToImages, ConvertImageToPdf
-from .pdf.pdf_document import SearchableTextPdf
+from .image import ImageObject, CollectionImages, ProcessImageScanner
+from .pdf import (
+    DocumentPdf, PageDocumentPdf, CollectionPagePdf, SearchableTextPdf
+)
+from .convert import (
+    ConvertPdfToImages, ConvertImageToPdf, ABCConvertPdf, ABCConvertImageToPdf,
+    DEFAULT_LIB_PDF_TO_IMG, DEFAULT_LIB_IMAGE_TO_PDF, LibPdfToImage, LibImageToPdf,
+)
+
 from .doc_stream import PdfStream, SplitPdf
 from .table_files import PdfFinder
 from .text import print_title, print_line, FindStrings
@@ -71,14 +77,3 @@ def read_image(img: Union[str, File, bytes, BytesIO]) -> PdfStream:
         raise ValueError()
     return _pdf_stream
 
-
-__all__ = [
-    '__modify_date__', '__author__', '__license__', '__module_name__', '__version__',
-    'PdfStream', 'DocumentPdf', 'PageDocumentPdf', 'CollectionPagePdf', 'CollectionImages',
-    'ImageObject', 'File', 'Directory', 'LibraryDocs', 'InputFiles', 'SearchableTextPdf',
-    'PdfFinder', 'SplitPdf', 'LibImageToPdf',  'RotationAngle', 'ConvertImageToPdf',
-    'ConvertPdfToImages', 'LibPDF', 'LibImage', 'LibPdfToImage',
-    'read_pdf', 'read_files_pdf', 'read_image', 'DictTextTable',
-    'print_title', 'print_line', 'FindStrings',
-]
-

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/_version.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
-__version__ = '2.2.7'
+__version__ = '2.5'
 __author__ = 'Bruno Chaves'
 __license__ = 'MIT'
 __module_name__ = 'convert_stream'
-__modify_date__ = '2025-09-08'
+__modify_date__ = '2025-11-15'
 

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/doc_stream.py

@@ -4,21 +4,18 @@
     Módulo para trabalhar com pdfs e imagens
 """
 from __future__ import annotations
-from convert_stream.mod_types.modules import (
-    DEFAULT_LIB_PDF, DEFAULT_LIB_IMAGE, DEFAULT_LIB_PDF_TO_IMG, DEFAULT_LIB_IMAGE_TO_PDF,
-)
 from convert_stream.mod_types.enums import LibPDF, LibImage, LibPdfToImage
 from convert_stream.pdf.pdf_page import PageDocumentPdf
 from convert_stream.image.img_object import ImageObject, CollectionImages
 from convert_stream.pdf.pdf_document import DocumentPdf, CollectionPagePdf
-from convert_stream.pdf.image_to_pdf import LibImageToPdf, ConvertImageToPdf
-from convert_stream.pdf.pdf_to_image import ConvertPdfToImages
+from convert_stream.convert.image_to_pdf import LibImageToPdf, ConvertImageToPdf
+from convert_stream.convert.pdf_to_image import ConvertPdfToImages
 from soup_files import File, Directory, ProgressBarAdapter
 
 
 class ImageStream(CollectionImages):
 
-    def __init__(self, images: list[ImageObject]) -> None:
+    def __init__(self, images: list[ImageObject] = None) -> None:
         super().__init__(images)
 
     def add_image_bytes(self, bt: bytes) -> None:
@@ -39,7 +36,7 @@ class PdfStream(object):
             ) -> None:
         self.dpi = dpi
         self.progress: ProgressBarAdapter = pbar
-        self.collection_pages: CollectionPagePdf = CollectionPagePdf([])
+        self.collection_pages: CollectionPagePdf = CollectionPagePdf()
         self.collection_images: CollectionImages = CollectionImages([], lib_img=lib_img)
         self.collection_images.set_pbar(self.progress)
         self.collection_pages.set_pbar(self.progress)
@@ -132,25 +129,25 @@ class PdfStream(object):
         return _doc
 
     def thresold(self, *, land_scape: bool = False, a4: bool = False) -> DocumentPdf:
-        if self.collection_images.length == 0:
-            images: list[ImageObject] = []
-        else:
-            images: list[ImageObject] = self.collection_images.copy()
 
         if not self.collection_pages.is_empty:
             # Converter as páginas PDF em imagens.
             conv_pdf_to_img: ConvertPdfToImages = self.convert_pdf_to_images
-            images.extend(
-                conv_pdf_to_img.to_images(dpi=self.dpi, lib_image=self.lib_img),
-            )
-        if len(images) == 0:
+            _images: list[ImageObject] = conv_pdf_to_img.to_images(dpi=self.dpi, lib_image=self.lib_img)
+            _collection = CollectionImages(_images)
+        else:
+            _collection = CollectionImages()
+
+        if self.collection_images.length > 0:
+            _collection.add_images(self.collection_images)
+        if _collection.length == 0:
             raise ValueError('Adicione imagens para prosseguir!')
-        if land_scape:
-            for img in images:
-                img.set_landscape()
-        for i in images:
-            i.set_threshold_gray()
-        conv_img_to_pdf = ConvertImageToPdf(CollectionImages(images), lib_img_to_pdf=self.lib_img_to_pdf)
+
+        for num, i in enumerate(_collection):
+            if land_scape:
+                _collection[num].set_landscape()
+            _collection[num].set_threshold_black(max_value=255)
+        conv_img_to_pdf = ConvertImageToPdf(_collection, lib_img_to_pdf=self.lib_img_to_pdf)
         return conv_img_to_pdf.to_document(a4=a4)
 
     def to_files_images(
@@ -163,7 +160,7 @@ class PdfStream(object):
             raise ValueError('Adicione imagens e/ou documentos para prosseguir!')
         self.progress.start()
 
-        image_stream = ImageStream([])
+        image_stream = ImageStream()
         image_stream.set_pbar(self.progress)
         if not self.collection_images.is_empty:
             image_stream.add_images(self.collection_images)

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/image/img_object.py

@@ -4,17 +4,16 @@
     Módulo para trabalhar com imagens
 """
 from __future__ import annotations
-
 import os.path
 from typing import Union
 from abc import ABC, abstractmethod
-from soup_files import File, Directory, InputFiles, LibraryDocs, ProgressBarAdapter
+from soup_files import File, Directory, InputFiles, LibraryDocs, ProgressBarAdapter, TextProgress
 from io import BytesIO
 import numpy as np
 from scipy.ndimage import uniform_filter
 from sheet_stream.type_utils import get_hash_from_bytes, MetaDataFile, MetaDataItem
-from convert_stream.mod_types.enums import LibImage, RotationAngle
-from convert_stream.mod_types.table_types import ListItems
+from convert_stream.mod_types.enums import RotationAngle
+from sheet_stream import ListItems
 from convert_stream.mod_types.modules import (
     MOD_IMG_PIL, ModuleImage, DEFAULT_LIB_IMAGE,
     cv2, MatLike, Image, ImageFilter, LibImage
@@ -500,16 +499,28 @@ class ImageObject(object):
 
 class CollectionImages(ListItems):
     
-    def __init__(self, images: list[ImageObject], *, lib_img: LibImage = LibImage.OPENCV) -> None:
+    def __init__(self, images: list[ImageObject] = None, *, lib_img: LibImage = LibImage.OPENCV) -> None:
         """
             Gerir uma lista de Imagens
         :type images: list[ImageObject]
         """
         super().__init__(images)
         self.lib_img: LibImage = lib_img
-        self.pbar: ProgressBarAdapter = ProgressBarAdapter()
+        self.__pbar: TextProgress = TextProgress()
+        self.set_list_type(ImageObject)
         self.__count: int = 0
 
+    @property
+    def pbar(self) -> ProgressBarAdapter:
+        return self.__pbar.pbar
+
+    @pbar.setter
+    def pbar(self, pbar: ProgressBarAdapter) -> None:
+        self.__pbar.pbar = pbar
+
+    def set_list_type(self, cls_type=object):
+        super().set_list_type(ImageObject)
+
     def clear(self) -> None:
         super().clear()
         self.__count = 0
@@ -533,12 +544,12 @@ class CollectionImages(ListItems):
 
     def add_files_image(self, files: list[File]) -> None:
         self.pbar.start()
-        max_num: int = len(files)
+        self.__pbar.total = len(files)
+        self.__pbar.start = 0
+        self.__pbar.text = 'Adicionando imagem'
+
         for num, f in enumerate(files):
-            self.pbar.update(
-                ((num+1) / max_num) * 100,
-                f'Adicionando imagem: [{num+1} de {max_num}]'
-            )
+            self.__pbar.set_update()
             self.append(ImageObject.create_from_file(f, lib_image=self.lib_img))
         self.pbar.stop()
 
@@ -559,7 +570,7 @@ class CollectionImages(ListItems):
         max_num = self.length
         img: ImageObject
         for n, img in enumerate(self):
-            if img.metadata.file_path is not None:
+            if (img.metadata.file_path is not None) and (img.metadata.file_path != ''):
                 filename = f'{os.path.basename(img.metadata.file_path)}-{n}.png'
             else:
                 filename = f'{img.metadata.name}-{n}.png'
@@ -611,9 +622,9 @@ class ProcessImageScanner(object):
 
     def select_doc(self) -> ImageObject | None:
         """
-        Detecta e recorta automaticamente a área do documento principal
-        (texto ou folha digitalizada) em uma imagem.
-        Retorna um novo ImageObject contendo apenas o recorte detectado.
+        Deteta e recorta automaticamente a área do documento principal
+        (texto ou folha digitalizada) em imagem.
+        Retorna um novo ImageObject contendo apenas o recorte detetado.
         """
         # Converte para matriz OpenCV
         img_cv: np.ndarray = cv2.imdecode(self.image.to_numpy(), cv2.IMREAD_COLOR)

convert_stream-2.5/convert_stream/mod_types/__init__.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python3
+
+from __future__ import annotations
+from .enums import (
+    RotationAngle, LibImage, LibPdfToImage, LibPDF, LibImageToPdf
+)
+
+__all__ = [
+    'RotationAngle', 'LibPDF',
+    'LibImageToPdf', 'LibPdfToImage', 'LibImage',
+]

convert_stream-2.5/convert_stream/mod_types/enums.py

@@ -0,0 +1,37 @@
+#!/usr/bin/env python3
+from enum import Enum
+
+
+class LibPdfToImage(Enum):
+    """Enumerar as bibliotecas externas que convertem PDF em imagem"""
+    PDF_TO_IMG_FITZ = 'fitz'
+    NOT_IMPLEMENTED = 'null'
+
+
+class LibImageToPdf(Enum):
+
+    IMAGE_TO_PDF_FITZ = 'fitz'
+    IMAGE_TO_PDF_CANVAS = 'canvas'
+    IMAGE_TO_PDF_PIL = 'pil'
+    NOT_IMPLEMENTED = 'null'
+
+
+class LibPDF(Enum):
+
+    PYPDF = 'pypdf'
+    FITZ = 'fitz'
+    NOT_IMPLEMENTED = 'null'
+
+
+class LibImage(Enum):
+
+    PIL = 'pil'
+    OPENCV = 'opencv'
+    NOT_IMPLEMENTED = 'null'
+
+
+class RotationAngle(Enum):
+
+    ROTATION_90 = 90
+    ROTATION_180 = 180
+    ROTATION_270 = 270

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/mod_types/modules.py

@@ -29,15 +29,15 @@ try:
     from cv2.typing import MatLike
     MOD_IMG_OPENCV = True
 except ImportError:
-    MatLike = FakeType
+    MatLike = object
 
 try:
     from PIL import Image
     from PIL import ImageOps, ImageFilter
     MOD_IMG_PIL = True
 except ImportError:
-    Image = FakeType
-    Image.Image = FakeType
+    Image = object
+    Image.Image = object
 
 if MOD_IMG_OPENCV and MOD_IMG_PIL:
     ModuleImage: TypeAlias = Union[MatLike, Image.Image]
@@ -50,7 +50,7 @@ elif MOD_IMG_PIL:
     DEFAULT_LIB_IMAGE = LibImage.PIL
 else:
     DEFAULT_LIB_IMAGE = LibImage.NOT_IMPLEMENTED
-    ModuleImage = FakeType
+    ModuleImage: TypeAlias = Union[MatLike, Image]
 
 #=================================================================#
 # Módulos para PDF fitz e pypdf
@@ -90,8 +90,8 @@ elif MOD_PYPDF:
     ModDocPdf = Union[PdfWriter]
     DEFAULT_LIB_PDF = LibPDF.PYPDF
 else:
-    ModPagePdf = FakeType  # fallback para runtime
-    ModDocPdf = FakeType
+    ModPagePdf = Union[PageObject, fitz.Page]
+    ModDocPdf = Union[fitz.Document, PdfWriter]
     DEFAULT_LIB_PDF = LibPDF.NOT_IMPLEMENTED
 
 #=================================================================#

convert_stream-2.5/convert_stream/pdf/__init__.py

@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+from .pdf_page import PageDocumentPdf
+from .pdf_document import (
+    DocumentPdf, CollectionPagePdf, SearchableTextPdf, ABCDocument,
+    MOD_FITZ, MOD_PYPDF, ModDocPdf,
+)
+
+__all__ = [
+    'DocumentPdf', 'CollectionPagePdf', 'PageDocumentPdf',
+    'SearchableTextPdf', 'ModDocPdf', 'ABCDocument', 'MOD_PYPDF', 'MOD_FITZ',
+]
+

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/pdf/pdf_document.py

@@ -9,14 +9,10 @@ from io import BytesIO
 from typing import Union
 import pandas as pd
 from soup_files import File, Directory, LibraryDocs, InputFiles, ProgressBarAdapter, JsonConvert
-from sheet_stream.type_utils import (
-    get_hash_from_bytes, MetaDataFile, MetaDataItem
+from sheet_stream import (
+    ListItems, HeadCell, HeadValues, ColumnsTable, TableDocuments, ListColumnBody, ListString,
+    MetaDataItem, MetaDataFile, get_hash_from_bytes,
 )
-
-from sheet_stream.type_utils import (
-    ListItems, HeadCell, HeadValues, ColumnsTable, TableDocuments, ListColumnBody, ListString
-)
-from convert_stream.mod_types.table_types import DictTextTable, ColumnBody
 from convert_stream.mod_types.enums import LibPDF
 from convert_stream.mod_types.modules import (
     DEFAULT_LIB_PDF, ModDocPdf, PdfWriter, PdfReader, fitz, MOD_FITZ, MOD_PYPDF
@@ -70,7 +66,7 @@ class SearchableTextPdf(object):
     """
     def __init__(self, silent: bool = False):
         self.silent = silent
-        self.elements: dict[str, ColumnBody] = DictTextTable.create_void_dict()
+        self.elements: TableDocuments = TableDocuments.create_void_dict()
 
     def __repr__(self):
         return f'SearchableTextPdf: {self.elements}'
@@ -221,9 +217,9 @@ class ImplementDocumentFitz(ABCDocument):
     """
         Implementação usando a biblioteca fitz.
     """
-    def __init__(self, mod_doc_pdf: ModDocPdf):
+    def __init__(self, mod_doc_pdf: fitz.Document):
         super().__init__(mod_doc_pdf)
-        self.mod_doc_pdf: ModDocPdf = mod_doc_pdf
+        self.mod_doc_pdf: fitz.Document = mod_doc_pdf
         self.lib_pdf: LibPDF = LibPDF.FITZ
 
     def lenght(self) -> int:
@@ -592,11 +588,12 @@ class DocumentPdf(object):
         list_data: list[TableDocuments] = []
         pages: list[PageDocumentPdf] = self.to_pages()
 
+        _mp: TableDocuments
         for page_pdf in pages:
-            _mp: TableDocuments = self._create_map(page_pdf, separator=separator)
+            _mp = self._create_map(page_pdf, separator=separator)
             list_data.append(_mp)
         if len(list_data) == 0:
-            return DictTextTable.create_void_dict()
+            return TableDocuments.create_void_dict()
         return concat_table(list_data)
 
     def to_data(self, separator: str = '\n') -> pd.DataFrame:
@@ -712,9 +709,10 @@ class CollectionPagePdf(ListItems):
     """
         Gerir uma coleção de páginas PDF.
     """
-    def __init__(self, pages: list[PageDocumentPdf]) -> None:
+    def __init__(self, pages: list[PageDocumentPdf] = None) -> None:
         super().__init__(pages)
         self.pbar: ProgressBarAdapter = ProgressBarAdapter()
+        self.set_list_type(PageDocumentPdf)
 
     @property
     def name(self) -> str | None:
@@ -722,6 +720,9 @@ class CollectionPagePdf(ListItems):
             return None
         return self[0].__hash__()
 
+    def set_list_type(self, cls_type=PageDocumentPdf):
+        super().set_list_type(PageDocumentPdf)
+
     def set_pbar(self, p: ProgressBarAdapter):
         self.pbar = p
 

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/pdf/pdf_page.py

@@ -6,11 +6,8 @@
 from __future__ import annotations
 from abc import ABC, abstractmethod
 import pandas as pd
-
+from sheet_stream import ListString, TableDocuments
 from convert_stream.mod_types.enums import LibPDF
-from convert_stream.mod_types.table_types import (
-    DictTextTable, ListString
-)
 from convert_stream.mod_types.modules import (
     ModPagePdf, PageObject, fitz
 )
@@ -230,10 +227,16 @@ class PageDocumentPdf(object):
             return ListString([])
         return ListString(txt.split(separator))
 
-    def to_dict(self, separator: str = '\n') -> DictTextTable:
+    def to_dict(self, separator: str = '\n') -> TableDocuments:
+        """
+        Converte o texto da página em tabela/dicionário
+        """
         _values = self.to_list(separator)
-        return DictTextTable.create_from_values(
-            _values, page_num=f'{self.number_page}', file_type='.pdf'
+        return TableDocuments.create_from_values(
+            _values,
+            page_num=f'{self.number_page}',
+            file_type='.pdf',
+            file_path=self.metadata.file_path
         )
 
     def to_map(self, separator: str = '\n') -> pd.DataFrame:
@@ -246,9 +249,9 @@ class PageDocumentPdf(object):
         fd = FindText(self.to_string(), separator=separator)
         return fd.find(text, iqual=iqual, case=case)
 
-    def find_all(self, text: str, *, separator: str = '\n', iqual: bool = False, case: bool = True) -> list[str]:
+    def find_all(self, text: str, *, separator: str = '\n', iqual: bool = False, case: bool = True) -> ListString:
         fd = FindText(self.to_string(), separator=separator)
-        return fd.find_all(text, iqual=iqual, case=case)
+        return ListString(fd.find_all(text, iqual=iqual, case=case))
 
     def get_width(self) -> float:
         return self.implement_page_pdf.get_width()

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/table_files.py

@@ -3,12 +3,11 @@
 from __future__ import annotations
 from io import BytesIO
 from soup_files import File, Directory, InputFiles, LibraryDocs
-
 from convert_stream import PageDocumentPdf
 from convert_stream.text.find_text import FindText
 from convert_stream.pdf.pdf_document import SearchableTextPdf, DocumentPdf
-from convert_stream.mod_types.table_types import ColumnsTable
 from convert_stream.image import ImageObject
+from sheet_stream import ColumnsTable, TableDocuments
 
 
 class PdfFinder(object):

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream/text/__init__.py

@@ -8,4 +8,5 @@ from sheet_stream import ConvertStringDate, fmt_col_to_date
 __all__ = [
     'ConvertStringDate', 'print_title', 'print_line', 'fmt_col_to_date',
     'show_info', 'Colors', 'show_error', 'show_warning', 'FindText',
+    'FindStrings',
 ]

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream.egg-info/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.4.4
+Version: 2.5
 Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
 Author: Bruno Chaves
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
-Requires-Dist: soup_files>=1.4
+Requires-Dist: soup_files>=1.4.2
 Requires-Dist: PyMuPDF
 Requires-Dist: scipy
 Requires-Dist: reportlab
@@ -15,7 +15,7 @@ Requires-Dist: pandas
 Requires-Dist: Pillow>=11.3.0
 Requires-Dist: opencv-python
 Requires-Dist: requests>=2.32.4
-Requires-Dist: sheet_stream
+Requires-Dist: sheet_stream>=0.1.3
 
 # Configuração instalação:
 pip3 install -r requirements.txt

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream.egg-info/SOURCES.txt

@@ -15,12 +15,9 @@ convert_stream/image/img_object.py
 convert_stream/mod_types/__init__.py
 convert_stream/mod_types/enums.py
 convert_stream/mod_types/modules.py
-convert_stream/mod_types/table_types.py
 convert_stream/pdf/__init__.py
-convert_stream/pdf/image_to_pdf.py
 convert_stream/pdf/pdf_document.py
 convert_stream/pdf/pdf_page.py
-convert_stream/pdf/pdf_to_image.py
 convert_stream/text/__init__.py
 convert_stream/text/find_text.py
 convert_stream/text/terminal.py

{convert_stream-2.4.4 → convert_stream-2.5}/convert_stream.egg-info/requires.txt

@@ -1,4 +1,4 @@
-soup_files>=1.4
+soup_files>=1.4.2
 PyMuPDF
 scipy
 reportlab
@@ -8,4 +8,4 @@ pandas
 Pillow>=11.3.0
 opencv-python
 requests>=2.32.4
-sheet_stream
+sheet_stream>=0.1.3

{convert_stream-2.4.4 → convert_stream-2.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "convert_stream"
-version = "2.4.4"
+version = "2.5"
 authors = [
   { name="Bruno Chaves"},
 ]
@@ -14,7 +14,7 @@ readme = "README.md"
 requires-python = ">=3.11"
 
 dependencies = [
-    "soup_files>=1.4",
+    "soup_files>=1.4.2",
     "PyMuPDF",
     "scipy",
     "reportlab",
@@ -24,7 +24,7 @@ dependencies = [
     "Pillow>=11.3.0",
     "opencv-python",
     "requests>=2.32.4",
-    "sheet_stream",
+    "sheet_stream>=0.1.3",
 ]
 
 [tool.setuptools]

convert_stream-2.4.4/convert_stream/mod_types/__init__.py

@@ -1,13 +0,0 @@
-#!/usr/bin/env python3
-#
-from __future__ import annotations
-from .enums import (
-    RotationAngle, ColumnsTable, LibImage, LibPdfToImage, LibPDF, LibImageToPdf
-)
-from .table_types import DictTextTable
-
-
-__all__ = [
-    'DictTextTable', 'RotationAngle', 'LibPDF',
-    'LibImageToPdf', 'LibPdfToImage', 'LibImage',
-]

convert_stream-2.4.4/convert_stream/mod_types/enums.py

@@ -1,65 +0,0 @@
-#!/usr/bin/env python3
-from enum import Enum
-
-
-class ColumnsTable(Enum):
-    """
-        Classe enum para padronizar os nomes das tabelas geradas por este módulo.
-    """
-
-    NUM_LINE = 'LINHA'
-    NUM_PAGE = 'PÁGINA'
-    TEXT = 'TEXTO'
-    FILE_PATH = 'ARQUIVO'
-    FILE_NAME = 'NOME_ARQUIVO'
-    DIR = 'PASTA'
-    FILETYPE = 'TIPO_ARQUIVO'
-    KEY = 'KEY'
-
-    @classmethod
-    def to_list(cls) -> list[str]:
-        return [
-            cls.NUM_LINE.value,
-            cls.NUM_PAGE.value,
-            cls.TEXT.value,
-            cls.FILE_PATH.value,
-            cls.FILE_NAME.value,
-            cls.FILETYPE.value,
-            cls.DIR.value,
-            cls.KEY.value,
-        ]
-
-
-class LibPdfToImage(Enum):
-    """Enumerar as bibliotecas externas que convertem PDF em imagem"""
-    PDF_TO_IMG_FITZ = 'fitz'
-    NOT_IMPLEMENTED = 'null'
-
-
-class LibImageToPdf(Enum):
-
-    IMAGE_TO_PDF_FITZ = 'fitz'
-    IMAGE_TO_PDF_CANVAS = 'canvas'
-    IMAGE_TO_PDF_PIL = 'pil'
-    NOT_IMPLEMENTED = 'null'
-
-
-class LibPDF(Enum):
-
-    PYPDF = 'pypdf'
-    FITZ = 'fitz'
-    NOT_IMPLEMENTED = 'null'
-
-
-class LibImage(Enum):
-
-    PIL = 'pil'
-    OPENCV = 'opencv'
-    NOT_IMPLEMENTED = 'null'
-
-
-class RotationAngle(Enum):
-
-    ROTATION_90 = 90
-    ROTATION_180 = 180
-    ROTATION_270 = 270

convert_stream-2.4.4/convert_stream/mod_types/table_types.py

@@ -1,19 +0,0 @@
-#!/usr/bin/env python3
-
-from __future__ import annotations
-from sheet_stream import (
-    ColumnsTable, ListString, ListItems, ListColumnBody, ArrayString, TableDocuments, TableRow, TableTextKeyWord
-)
-from sheet_stream.type_utils import HeadCell
-
-
-class ColumnBody(ListColumnBody):
-
-    def __init__(self, col_name: HeadCell | str, col_body: list[str]):
-        super().__init__(col_name, col_body)
-
-
-class DictTextTable(TableDocuments):
-
-    def __init__(self, body_list: list[ListColumnBody]):
-        super().__init__(body_list)

convert_stream-2.4.4/convert_stream/pdf/__init__.py

@@ -1,14 +0,0 @@
-#!/usr/bin/env python3
-
-from .pdf_page import PageDocumentPdf
-from .pdf_document import (
-    DocumentPdf, CollectionPagePdf
-)
-from .pdf_to_image import ConvertPdfToImages
-from .image_to_pdf import ConvertImageToPdf
-
-__all__ = [
-    'ConvertPdfToImages', 'ConvertImageToPdf', 'DocumentPdf',
-    'CollectionPagePdf', 'PageDocumentPdf',
-]
-

convert_stream-2.4.4/convert_stream/pdf/image_to_pdf.py

@@ -1,349 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-    Módulo para trabalhar com imagens
-"""
-
-from __future__ import annotations
-from io import BytesIO
-from soup_files import File, Directory, ProgressBarAdapter
-from abc import ABC, abstractmethod
-from convert_stream.mod_types.enums import LibImageToPdf
-from convert_stream.mod_types.modules import (
-    MOD_CANVAS, DEFAULT_LIB_IMAGE_TO_PDF, canvas, letter, ImageReader
-)
-from convert_stream.pdf import DocumentPdf
-from convert_stream.pdf.pdf_page import fitz
-from convert_stream.image.img_object import MOD_IMG_PIL, Image, ImageObject, CollectionImages
-
-
-class ABCConvertImageToPdf(ABC):
-
-    def __init__(self, collection_images: CollectionImages):
-        self.collection_images: CollectionImages = collection_images
-        self.pbar: ProgressBarAdapter = ProgressBarAdapter()
-
-    @abstractmethod
-    def set_pbar(self, p: ProgressBarAdapter):
-        pass
-
-    @abstractmethod
-    def to_document(self, land_scape: bool = True, a4: bool = False) -> DocumentPdf:
-        pass
-
-    @abstractmethod
-    def to_file_pdf(self, output_file: File, *, land_scape: bool = True, a4: bool = False) -> None:
-        pass
-
-
-class ImplementImageToPdfCanvas(ABCConvertImageToPdf):
-
-    def __init__(self, collection_images: CollectionImages):
-        super().__init__(collection_images)
-
-    def set_pbar(self, p: ProgressBarAdapter):
-        self.pbar = p
-        self.collection_images.set_pbar(p)
-
-    def to_document(self, land_scape: bool = True, a4: bool = False) -> DocumentPdf:
-        if not MOD_CANVAS:
-            raise RuntimeError("A biblioteca 'reportlab' não está disponível.")
-
-        if self.collection_images.is_empty:
-            raise ValueError("A lista de imagens não pode estar vazia.")
-
-        buffer = BytesIO()
-        max_num: int = self.collection_images.length
-        self.pbar.start()
-        if land_scape:
-            self.collection_images.set_land_scape()
-
-        # Lógica para determinar o tamanho inicial da página
-        first_img_obj = self.collection_images[0]
-        first_img_width, first_img_height = first_img_obj.get_dimensions()
-
-        if a4:
-            # Se for A4, o tamanho da página é fixo desde o início
-            c = canvas.Canvas(buffer, pagesize=letter)
-        else:
-            # Se não for A4, o canvas é inicializado com as dimensões da primeira imagem
-            c = canvas.Canvas(buffer, pagesize=(first_img_width, first_img_height))
-
-        # Processa a primeira imagem
-        self.pbar.update(
-            (1 / max_num) * 100,
-            f'Adicionando imagem ao Documento [1 de {max_num}]'
-        )
-        img_bytes: BytesIO = first_img_obj.to_bytes()
-        img_bytes.seek(0)
-        img_reader = ImageReader(img_bytes)
-
-        if a4:
-            # Lógica de redimensionamento e centralização para A4
-            page_width, page_height = letter
-            scale_factor = min(page_width / first_img_width, page_height / first_img_height)
-            scaled_width = first_img_width * scale_factor
-            scaled_height = first_img_height * scale_factor
-            x_pos = (page_width - scaled_width) / 2
-            y_pos = (page_height - scaled_height) / 2
-            c.drawImage(img_reader, x_pos, y_pos, width=scaled_width, height=scaled_height)
-        else:
-            # Desenha a imagem preenchendo a página que já tem o tamanho correto
-            c.drawImage(img_reader, 0, 0, width=first_img_width, height=first_img_height)
-
-        # Processa as imagens restantes
-        for num, img_obj in enumerate(self.collection_images[1:], 1):
-
-            self.pbar.update(
-                ((num + 1) / max_num) * 100,
-                f'Adicionando imagem ao Documento [{num + 1} de {max_num}]'
-            )
-            img_bytes = img_obj.to_bytes()
-            img_bytes.seek(0)
-            img_reader = ImageReader(img_bytes)
-            img_width, img_height = img_obj.get_dimensions()
-            # Cria nova página
-            c.showPage()
-
-            if a4:
-                # O tamanho da página é fixo, apenas desenha a imagem centralizada e redimensionada
-                page_width, page_height = letter
-                scale_factor = min(page_width / img_width, page_height / img_height)
-                scaled_width = img_width * scale_factor
-                scaled_height = img_height * scale_factor
-                x_pos = (page_width - scaled_width) / 2
-                y_pos = (page_height - scaled_height) / 2
-                c.drawImage(img_reader, x_pos, y_pos, width=scaled_width, height=scaled_height)
-            else:
-                # Ajusta o tamanho da nova página para as dimensões da imagem atual
-                c.setPageSize((img_width, img_height))
-                c.drawImage(img_reader, 0, 0, width=img_width, height=img_height)
-
-        c.save()
-        buffer.seek(0)
-        self.pbar.stop()
-        return DocumentPdf.create_from_bytes(buffer)
-
-    def to_file_pdf(self, output_file: File, *, land_scape: bool = True, a4: bool = False) -> None:
-        self.to_document(land_scape=land_scape, a4=a4).to_file(output_file)
-
-
-class ImplementImageToPdfPil(ABCConvertImageToPdf):
-    """
-        Classe para converter uma lista de ImageObject em um DocumentPdf
-        usando a biblioteca Pillow (PIL).
-    """
-
-    def __init__(self, collection_images: CollectionImages):
-        super().__init__(collection_images)
-
-    def set_pbar(self, p: ProgressBarAdapter):
-        self.pbar = p
-        self.collection_images.set_pbar(p)
-
-    def to_document(self, land_scape: bool = True, a4: bool = False) -> DocumentPdf:
-        if not MOD_IMG_PIL:
-            raise RuntimeError("A biblioteca 'Pillow' não está disponível.")
-
-        if self.collection_images:
-            raise ValueError("A lista de imagens não pode estar vazia.")
-
-        if land_scape:
-            self.collection_images.set_land_scape()
-
-        pil_images_to_save = []
-        if a4:
-            # Obtém as dimensões da página A4 em píxels
-            # Usando uma resolução de 100 DPI para consistência
-            page_width, page_height = letter  # Padrão do reportlab
-            page_size = (int(page_width), int(page_height))
-
-            self.pbar.start()
-            max_num = self.collection_images.length
-            for num, img_obj in enumerate(self.collection_images):
-                self.pbar.update(
-                    ((num + 1) / max_num) * 100,
-                    f'Redimensionando e ajustando imagem para A4 [{num + 1} de {max_num}]'
-                )
-                original_pil_image = img_obj.to_pil()
-                img_width, img_height = original_pil_image.size
-
-                # Calcula o fator de escala para ajustar a imagem à página, mantendo a proporção
-                scale_factor = min(page_size[0] / img_width, page_size[1] / img_height)
-                scaled_width = int(img_width * scale_factor)
-                scaled_height = int(img_height * scale_factor)
-
-                # Redimensiona a imagem
-                resized_image = original_pil_image.resize(
-                    (scaled_width, scaled_height), Image.Resampling.LANCZOS
-                )
-
-                # Criar imagem de fundo branca com o tamanho A4
-                new_image = Image.new('RGB', page_size, 'white')
-
-                # Centraliza a imagem redimensionada na nova imagem
-                x_pos = (page_size[0] - scaled_width) // 2
-                y_pos = (page_size[1] - scaled_height) // 2
-                new_image.paste(resized_image, (x_pos, y_pos))
-
-                pil_images_to_save.append(new_image)
-            self.pbar.stop()
-        else:
-            # Para a4 = False, não precisa redimensionar. Pillow ajusta o tamanho da página.
-            pil_images_to_save = [img.to_pil() for img in self.collection_images]
-
-        buffer = BytesIO()
-        try:
-            first_image_pil = pil_images_to_save[0]
-            other_images_pil = pil_images_to_save[1:]
-
-            first_image_pil.save(
-                buffer,
-                'PDF',
-                resolution=140.0,
-                save_all=True,
-                append_images=other_images_pil
-            )
-        except Exception as e:
-            raise RuntimeError(f"Erro ao criar o PDF com Pillow: {e}") from e
-
-        buffer.seek(0)
-        return DocumentPdf.create_from_bytes(buffer)
-
-    def to_file_pdf(self, output_file: File, *, land_scape: bool = True, a4: bool = False) -> None:
-        self.to_document(land_scape=land_scape, a4=a4).to_file(output_file)
-
-
-class ImplementImageToPdfFitz(ABCConvertImageToPdf):
-    """
-        Classe para converter uma lista de ImageObject em um DocumentPdf
-        usando a biblioteca PyMuPDF (fitz).
-    """
-
-    def __init__(self, collection_images: CollectionImages):
-        super().__init__(collection_images)
-
-    def set_pbar(self, p: ProgressBarAdapter):
-        self.pbar = p
-        self.collection_images.set_pbar(p)
-
-    def to_document(self, land_scape: bool = True, a4: bool = False) -> DocumentPdf:
-        max_num: int = self.collection_images.length
-        if max_num == 0:
-            raise ValueError('Adicione imagens para prosseguir')
-        self.pbar.start()
-        self.pbar.update(0, f'Convertendo {max_num} imagens em Documento PDF')
-        buffer = BytesIO()
-        doc = fitz.open()  # Cria um novo documento PDF vazio
-
-        for num, img_obj in enumerate(self.collection_images):
-            self.pbar.update(
-                ((num + 1) / max_num) * 100,
-                f'Convertendo: [{num + 1} de {max_num}]'
-            )
-            if land_scape:
-                img_obj.set_landscape()
-
-            # Converte a imagem para bytes
-            img_bytes_obj = img_obj.to_bytes()
-            # Obtém as dimensões da imagem e da página
-            img_width, img_height = img_obj.get_dimensions()
-
-            # Adiciona uma nova página ao documento
-            if a4:
-                page = doc.new_page()
-            else:
-                page = doc.new_page(width=img_width, height=img_height)
-
-            # Cria um retângulo que preenche a página
-            rect = page.rect
-            page_width, page_height = rect.width, rect.height
-
-            # Calcula o fator de escala para ajustar a imagem à página
-            scale_factor_w = page_width / img_width
-            scale_factor_h = page_height / img_height
-            scale_factor = min(scale_factor_w, scale_factor_h)
-
-            # Ajusta o retângulo de inserção para centralizar a imagem
-            scaled_width = img_width * scale_factor
-            scaled_height = img_height * scale_factor
-            x0 = (page_width - scaled_width) / 2
-            y0 = (page_height - scaled_height) / 2
-
-            # Insere a imagem no retângulo calculado
-            page.insert_image(
-                fitz.Rect(x0, y0, x0 + scaled_width, y0 + scaled_height),
-                stream=img_bytes_obj
-            )
-
-        # Salva o documento no buffer de memória
-        doc.save(buffer)
-        doc.close()
-        buffer.seek(0)
-        self.pbar.update(100, 'Conversão concluída')
-        print()
-        self.pbar.stop()
-        return DocumentPdf.create_from_bytes(buffer)
-
-    def to_file_pdf(self, output_file: File, *, land_scape: bool = True, a4: bool = False) -> None:
-        self.to_document(land_scape=land_scape).to_file(output_file)
-
-
-class ConvertImageToPdf(object):
-    """
-        Classe com padrão ADAPTER para converter Imagens em documento(s) PDF.
-    """
-
-    def __init__(
-            self,
-            collection_images: CollectionImages, *,
-            lib_img_to_pdf: LibImageToPdf = LibImageToPdf.IMAGE_TO_PDF_FITZ
-    ):
-        if lib_img_to_pdf == LibImageToPdf.IMAGE_TO_PDF_CANVAS:
-            self.convert: ABCConvertImageToPdf = ImplementImageToPdfCanvas(collection_images)
-        elif lib_img_to_pdf == LibImageToPdf.IMAGE_TO_PDF_PIL:
-            self.convert: ABCConvertImageToPdf = ImplementImageToPdfPil(collection_images)
-        elif lib_img_to_pdf == LibImageToPdf.IMAGE_TO_PDF_FITZ:
-            self.convert: ABCConvertImageToPdf = ImplementImageToPdfFitz(collection_images)
-        else:
-            raise NotImplementedError()
-
-        self._count: int = 0
-
-    @property
-    def is_null(self) -> bool:
-        return self.convert.collection_images.is_empty
-
-    @property
-    def pbar(self) -> ProgressBarAdapter:
-        return self.convert.pbar
-
-    def set_pbar(self, p: ProgressBarAdapter):
-        self.convert.set_pbar(p)
-
-    def add_file(self, file: File) -> None:
-        self.convert.collection_images.add_file_image(file)
-
-    def add_files(self, files: list[File]) -> None:
-        self.convert.collection_images.add_files_image(files)
-
-    def add_image(self, image: ImageObject) -> None:
-        self.convert.collection_images.add_image(image)
-
-    def add_images(self, images: list[ImageObject]) -> None:
-        self.convert.collection_images.add_images(images)
-
-    def add_directory(self, src_dir: Directory, max_files: int = 4000) -> None:
-        self.convert.collection_images.add_directory_images(src_dir, max_files=max_files)
-
-    def to_document(self, land_scape: bool = True, *, a4: bool = False) -> DocumentPdf:
-        return self.convert.to_document(land_scape, a4=a4)
-
-    def to_file_pdf(self, output_file: File, *, land_scape: bool = True, a4: bool = False) -> None:
-        self.convert.to_file_pdf(output_file, land_scape=land_scape, a4=a4)
-
-    def set_gausian_blur(self, sigma: float = 0.8) -> None:
-        self.convert.collection_images.set_gausian_blur(sigma)
-
-    def set_land_scape(self):
-        self.convert.collection_images.set_land_scape()

convert_stream-2.4.4/convert_stream/pdf/pdf_to_image.py

@@ -1,223 +0,0 @@
-#!/usr/bin/env python3
-#
-"""
-    Módulo para trabalhar com imagens
-"""
-from __future__ import annotations
-from abc import ABC, abstractmethod
-
-from sheet_stream.type_utils import MetaDataFile
-
-from convert_stream import CollectionImages
-from soup_files import Directory, ProgressBarAdapter, CreatePbar
-from convert_stream.mod_types.enums import LibPdfToImage
-from convert_stream.mod_types.modules import DEFAULT_LIB_PDF_TO_IMG, DEFAULT_LIB_IMAGE, LibPDF
-from convert_stream.image.img_object import ImageObject, LibImage
-from convert_stream.pdf.pdf_document import DocumentPdf
-
-
-try:
-    import fitz
-    MOD_FITZ = True
-except ImportError:
-    try:
-        import pymupdf as fitz
-        from pymupdf import Page, Pixmap
-        MOD_FITZ = True
-    except ImportError:
-        fitz = object
-        fitz.Page = object
-        fitz.TextPage = object
-        Page = object
-        Pixmap = object
-
-
-class ABCConvertPdf(ABC):
-
-    def __init__(self, document: DocumentPdf):
-        self.document: DocumentPdf = document
-        self.lib_pdf_to_image: LibPdfToImage = DEFAULT_LIB_PDF_TO_IMG
-        self.pbar: ProgressBarAdapter = CreatePbar().get()
-
-    def set_pbar(self, pbar: ProgressBarAdapter):
-        self.pbar = pbar
-
-    @abstractmethod
-    def to_images(
-                self, *,
-                dpi: int = 150,
-                lib_image: LibImage = DEFAULT_LIB_IMAGE,
-            ) -> list[ImageObject]:
-        """
-            Converte as páginas PDF do documento em lista de objetos imagem ImageObject
-
-        :param dpi: DPI do documento, resolução da renderização.
-        :param lib_image: Biblioteca para manipular imagens PIL/OpenCv
-        """
-        pass
-
-    @abstractmethod
-    def to_files_image(
-            self,
-            output_dir: Directory, *,
-            replace: bool = False,
-            gaussian_filter: bool = False,
-            dpi: int = 300,
-            lib_image: LibImage = DEFAULT_LIB_IMAGE,
-            ) -> None:
-        """
-            Converte todas as páginas do documento em objeto de imagem e salva no disco
-        em formato de imagem PNG.
-        """
-        pass
-
-
-class ImplementConvertPdfFitz(ABCConvertPdf):
-
-    def __init__(self, document: DocumentPdf):
-        super().__init__(document)
-        self.lib_pdf_to_image: LibPdfToImage = LibPdfToImage.PDF_TO_IMG_FITZ
-
-    def __get_pages(self) -> list[Page]:
-        pages = self.document.to_pages()
-        fitz_pages = []
-        for p in pages:
-            fitz_pages.append(p.implement_page_pdf.mod_page)
-        return fitz_pages
-
-    def to_images(
-                self, *,
-                dpi: int = 200,
-                lib_image: LibImage = LibImage.PIL
-            ) -> list[ImageObject]:
-        """
-            Converte um Documento em lista de objetos ImageObject.
-        """
-        images: list[ImageObject] = []
-        _metadata: MetaDataFile = self.document.metadata
-
-        pages_fitz: list[Page] = self.__get_pages()
-        _count = len(pages_fitz)
-        for n, pg in enumerate(pages_fitz):
-            self.pbar.update(
-                ((n+1)/_count) * 100,
-                f'[Documento para Imagens]: página {n+1}/{_count}'
-            )
-            pix: Pixmap = pg.get_pixmap(dpi=dpi)
-            img = ImageObject.create_from_bytes(
-                pix.tobytes('png', jpg_quality=100),
-                lib_image=LibImage.PIL,
-            )
-            img.metadata.name = _metadata.name
-            img.metadata.file_path = _metadata.file_path
-            images.append(img)
-        return images
-
-    def to_files_image(
-                self,
-                output_dir: Directory, *,
-                replace: bool = False,
-                gaussian_filter: bool = False,
-                dpi: int = 300,
-                lib_image: LibImage = LibImage.PIL
-            ) -> None:
-        pages_fitz: list[Page] = self.__get_pages()
-        _count = len(pages_fitz)
-        for n, pg in enumerate(pages_fitz):
-            self.pbar.update(
-                ((n + 1) / _count) * 100,
-                f'[Documento para arquivos de imagens]: {n + 1}/{_count}'
-            )
-            out_file = output_dir.join_file(f'pag-{n+1}.png')
-            if not replace:
-                if out_file.exists():
-                    self.pbar.update_text(f'Pulando: {out_file.basename()}')
-                    continue
-            pix: Pixmap = pg.get_pixmap(dpi=dpi)
-            img = ImageObject.create_from_bytes(
-                pix.tobytes('png', jpg_quality=100),
-                lib_image=LibImage.PIL,
-            )
-            img.to_file(out_file)
-        print()
-
-
-class ConvertPdfToImages(object):
-
-    def __init__(self, mod_conv_to_img: ABCConvertPdf | DocumentPdf):
-        if isinstance(mod_conv_to_img, ABCConvertPdf):
-            self.mod_convert_to_image: ABCConvertPdf = mod_conv_to_img
-        elif isinstance(mod_conv_to_img, ImplementConvertPdfFitz):
-            self.mod_convert_to_image: ABCConvertPdf = mod_conv_to_img
-        elif isinstance(mod_conv_to_img, DocumentPdf):
-            self.mod_convert_to_image = ImplementConvertPdfFitz(mod_conv_to_img)
-        else:
-            raise NotImplementedError()
-
-    def set_pbar(self, pbar: ProgressBarAdapter):
-        self.mod_convert_to_image.set_pbar(pbar)
-
-    def to_images(
-                self, *,
-                dpi: int = 300,
-                lib_image: LibImage = LibImage.PIL,
-            ) -> list[ImageObject]:
-        return self.mod_convert_to_image.to_images(dpi=dpi, lib_image=lib_image)
-
-    def to_files_image(
-                self,
-                output_dir: Directory, *,
-                replace: bool = False,
-                gaussian_filter: bool = False,
-                dpi: int = 300,
-                lib_image: LibImage = LibImage.PIL,
-            ) -> None:
-        self.mod_convert_to_image.to_files_image(
-            dpi=dpi,
-            lib_image=lib_image,
-            replace=replace,
-            output_dir=output_dir,
-            gaussian_filter=gaussian_filter
-        )
-
-    def inner_images(self) -> CollectionImages:
-        """
-            Extrair imagens embutidas nas páginas PDF.
-        """
-        # doc = Document(stream=page_bytes, filetype="pdf")
-        collection_imgs: CollectionImages = CollectionImages([])
-        tmp_doc: fitz.Document
-        if self.mod_convert_to_image.document.lib_pdf == LibPDF.FITZ:
-            tmp_doc: fitz.Document = self.mod_convert_to_image.document.get_real_document()
-        elif self.mod_convert_to_image.document.lib_pdf == LibPDF.PYPDF:
-            tmp_doc = fitz.Document(
-                stream=self.mod_convert_to_image.document.to_bytes().getvalue(), filetype="pdf"
-            )
-        else:
-            raise NotImplementedError()
-
-        page: fitz.Page
-        for num, page in enumerate(tmp_doc):
-            # Extrair imagens embutidas na página
-            images_list: list = page.get_images(full=True)
-            for img in images_list:
-                try:
-                    # Referência do objeto da imagem
-                    xref = img[0]
-                    # Extrair imagem
-                    base_image = tmp_doc.extract_image(xref)
-                    # Bytes da imagem
-                    image_bytes = base_image["image"]
-                    # Extensão (jpg, png, etc.)
-                    #image_ext = base_image["ext"]
-                except Exception as e:
-                    print(e)
-                else:
-                    img = ImageObject(image_bytes)
-                    collection_imgs.append(img)
-        return collection_imgs
-
-    @classmethod
-    def create(cls, doc: DocumentPdf) -> ConvertPdfToImages:
-        _mod = ImplementConvertPdfFitz(doc)
-        return cls(_mod)