convert-stream 2.4.4__tar.gz → 2.5.1__tar.gz

{convert_stream-2.4.4 → convert_stream-2.5.1}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.4.4
+Version: 2.5.1
 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-2.5.1}/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-2.5.1}/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-2.5.1/convert_stream/convert/__init__.py

@@ -0,0 +1,6 @@
+from .image_to_pdf import (
+    ABCConvertImageToPdf, ConvertImageToPdf, DEFAULT_LIB_IMAGE_TO_PDF, LibImageToPdf,
+)
+from .pdf_to_image import (
+    ABCConvertPdf, ConvertPdfToImages, DEFAULT_LIB_PDF_TO_IMG, LibPdfToImage
+)

{convert_stream-2.4.4/convert_stream/pdf → convert_stream-2.5.1/convert_stream/convert}/image_to_pdf.py

@@ -145,7 +145,7 @@ class ImplementImageToPdfPil(ABCConvertImageToPdf):
         if not MOD_IMG_PIL:
             raise RuntimeError("A biblioteca 'Pillow' não está disponível.")
 
-        if self.collection_images:
+        if self.collection_images.length == 0:
             raise ValueError("A lista de imagens não pode estar vazia.")
 
         if land_scape:

{convert_stream-2.4.4 → convert_stream-2.5.1}/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-2.5.1}/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-2.5.1/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-2.5.1/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-2.5.1}/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-2.5.1/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-2.5.1}/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-2.5.1}/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-2.5.1}/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-2.5.1}/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-2.5.1}/convert_stream.egg-info/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.4.4
+Version: 2.5.1
 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-2.5.1}/convert_stream.egg-info/SOURCES.txt

@@ -10,17 +10,17 @@ convert_stream.egg-info/SOURCES.txt
 convert_stream.egg-info/dependency_links.txt
 convert_stream.egg-info/requires.txt
 convert_stream.egg-info/top_level.txt
+convert_stream/convert/__init__.py
+convert_stream/convert/image_to_pdf.py
+convert_stream/convert/pdf_to_image.py
 convert_stream/image/__init__.py
 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-2.5.1}/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-2.5.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "convert_stream"
-version = "2.4.4"
+version = "2.5.1"
 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",
@@ -24,12 +24,13 @@ dependencies = [
     "Pillow>=11.3.0",
     "opencv-python",
     "requests>=2.32.4",
-    "sheet_stream",
+    "sheet_stream>=0.1.3",
 ]
 
 [tool.setuptools]
 packages = [
     "convert_stream",
+    "convert_stream.convert",
     "convert_stream.mod_types",
     "convert_stream.pdf",
     "convert_stream.image",

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',
-]
-