convert-stream 2.2.6__tar.gz → 2.3__tar.gz

{convert_stream-2.2.6 → convert_stream-2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.2.6
+Version: 2.3
 Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
 Author: Bruno Chaves
 Requires-Python: >=3.11
@@ -24,12 +24,12 @@ pip3 install -r requirements.txt
     >>> from file import File, Directory
     >>> from pdflib import PdfStream
     # instâncie o caminho do arquivo PDF e o diretório para exportar os dados.
-    f = File('path/to/file.pdf')
-    d = Directory('path/to/save')
+    file_pdf = File('path/to/file.pdf')
+    output_dir = Directory('path/to/save')
 
     pdf_stream = PdfStream()
-    pdf_stream.add_file_pdf(f)
-    pdf_stream.to_files_pdf(d) # isso irá converter cada página em um arquivo PDF
+    pdf_stream.add_file_pdf(file_pdf)
+    pdf_stream.to_files_pdf(output_dir) # isso irá converter cada página em um arquivo PDF
 
 # Uso para unir vários arquivos PDF.
     >>> from file import File, Directory

{convert_stream-2.2.6 → convert_stream-2.3}/README.md

@@ -6,12 +6,12 @@ pip3 install -r requirements.txt
     >>> from file import File, Directory
     >>> from pdflib import PdfStream
     # instâncie o caminho do arquivo PDF e o diretório para exportar os dados.
-    f = File('path/to/file.pdf')
-    d = Directory('path/to/save')
+    file_pdf = File('path/to/file.pdf')
+    output_dir = Directory('path/to/save')
 
     pdf_stream = PdfStream()
-    pdf_stream.add_file_pdf(f)
-    pdf_stream.to_files_pdf(d) # isso irá converter cada página em um arquivo PDF
+    pdf_stream.add_file_pdf(file_pdf)
+    pdf_stream.to_files_pdf(output_dir) # isso irá converter cada página em um arquivo PDF
 
 # Uso para unir vários arquivos PDF.
     >>> from file import File, Directory

convert_stream-2.3/convert_stream/__init__.py

@@ -0,0 +1,100 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+from io import BytesIO
+from typing import Union
+from soup_files import File, Directory, LibraryDocs, InputFiles
+
+from ._version import (
+    __module_name__, __author__, __license__, __modify_date__, __version__
+)
+from convert_stream.enum_libs.enums import *
+from convert_stream.enum_libs.modules import (
+    LibPDF, LibDate, LibImage, LibPdfToImage, LibImageToPdf,
+    DEFAULT_LIB_PDF, DEFAULT_LIB_IMAGE, DEFAULT_LIB_PDF_TO_IMG,
+    DEFAULT_LIB_IMAGE_TO_PDF, ModPdfToImage, ModPagePdf, ModuleImage,
+    ModImageToPdf, MOD_FITZ, MOD_PYPDF, MOD_CANVAS, MOD_IMG_PIL, MOD_IMG_OPENCV,
+)
+from .text.terminal import print_title, print_line
+from .text.string import (
+    FindText, ArrayString, MapText
+)
+from .text.date import ConvertStringDate
+from convert_stream.image.img_object import (
+    ImageObject, Image, MatLike, get_hash_from_bytes, CollectionImages,
+)
+from convert_stream.pdf import (
+    PageDocumentPdf, DocumentPdf, ConvertImageToPdf, ConvertPdfToImages,
+    ModImageToPdf, ModDocPdf, CollectionPagePdf, DEFAULT_LIB_PDF,
+    DEFAULT_LIB_IMAGE_TO_PDF, DEFAULT_LIB_PDF_TO_IMG
+)
+from .doc_stream import PdfStream, SplitPdf
+from .sheets import save_data, ReadFileSheet
+from .table_files import (
+    get_void_df, create_df_from_file_pdf, create_map_from_values,
+    FileToTable, ColumnsTable, PdfFinder, SearchableTextPdf
+)
+
+
+def __create_stream() -> PdfStream:
+    st = PdfStream()
+    st.clear()
+    return st
+
+
+def read_pdf(file: Union[str, File, bytes, BytesIO]) -> PdfStream:
+    _pdf_stream = __create_stream()
+
+    if isinstance(file, File):
+        _pdf_stream.add_file_pdf(file)
+    elif isinstance(file, str):
+        _pdf_stream.add_file_pdf(File(file))
+    elif isinstance(file, bytes):
+        _pdf_stream.add_document(DocumentPdf(BytesIO(file)))
+    elif isinstance(file, BytesIO):
+        _pdf_stream.add_document(DocumentPdf(file))
+    else:
+        raise ValueError()
+    return _pdf_stream
+
+
+def read_files_pdf(files: Union[list[str], list[File]]) -> PdfStream:
+    _pdf_stream = __create_stream()
+    if len(files) == 0:
+        return _pdf_stream
+
+    if isinstance(files[0], str):
+        for f in files:
+            _pdf_stream.add_file_pdf(File(f))
+    elif isinstance(files[0], File):
+        _pdf_stream.add_files_pdf(files)
+    else:
+        raise ValueError()
+    return _pdf_stream
+
+
+def read_image(image: Union[str, File, bytes, BytesIO]) -> PdfStream:
+    _pdf_stream = __create_stream()
+    if isinstance(image, str):
+        _pdf_stream.add_file_image(File(image))
+    elif isinstance(image, File):
+        _pdf_stream.add_image(ImageObject.create_from_file(image))
+    elif isinstance(image, bytes):
+        _pdf_stream.add_image(ImageObject.create_from_bytes(image))
+    elif isinstance(image, BytesIO):
+        image.seek(0)
+        _pdf_stream.add_image(ImageObject.create_from_bytes(image.getvalue()))
+    else:
+        raise ValueError()
+    return _pdf_stream
+
+
+def merge(stream: list[PdfStream]) -> PdfStream:
+    if len(stream) == 0:
+        raise ValueError()
+    if len(stream) == 1:
+        return stream[0]
+    else:
+        s = stream[0]
+        for pdf_stream in stream[1:]:
+            s.add_pages(pdf_stream.to_document().to_pages())
+        return s

{convert_stream-2.2.6 → convert_stream-2.3}/convert_stream/_version.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
-__version__ = '2.2'
+__version__ = '2.2.7'
 __author__ = 'Bruno Chaves'
 __license__ = 'MIT'
 __module_name__ = 'convert_stream'
-__modify_date__ = '2025-08-24'
+__modify_date__ = '2025-09-08'
 

convert_stream-2.2.6/convert_stream/stream.py → convert_stream-2.3/convert_stream/doc_stream.py

@@ -8,7 +8,6 @@ from convert_stream.enum_libs.modules import (
     DEFAULT_LIB_PDF, DEFAULT_LIB_IMAGE, DEFAULT_LIB_PDF_TO_IMG, DEFAULT_LIB_IMAGE_TO_PDF,
 )
 from convert_stream.enum_libs.enums import LibPDF, LibImage, LibImageToPdf, LibPdfToImage
-from convert_stream.text.string import FindText
 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
@@ -108,22 +107,43 @@ class PdfStream(object):
     def add_directory_image(self, src_dir: Directory, max_files: int = 4000) -> None:
         self.collection_images.add_directory_images(src_dir, max_files=max_files)
 
-    def to_document(self) -> DocumentPdf:
+    def to_document(self, *, land_scape: bool = False, a4: bool = False) -> DocumentPdf:
+        """
+
+            Converte os documentos adicionados em PdfStream (imagens/pdfs) em
+        objeto do tipo DocumentPdf().
+        """
         if self.collection_pages.is_null and self.collection_images.is_empty:
             raise ValueError('Adicione imagens e/ou documentos para prosseguir!')
+
         _doc = None
-        if not self.collection_pages.is_null:
-            _doc = DocumentPdf.create_from_pages(self.collection_pages.pages)
         if not self.collection_images.is_empty:
-            _convert_img_to_pdf = ConvertImageToPdf(self.collection_images)
-            _pages = _convert_img_to_pdf.to_document().to_pages()
-            self.collection_images.clear()
+            _convert = ConvertImageToPdf(self.collection_images, lib_img_to_pdf=self.lib_img_to_pdf)
+            _doc: DocumentPdf = _convert.to_document(land_scape, a4=a4)
+        if not self.collection_pages.is_null:
             if _doc is None:
-                _doc = DocumentPdf.create_from_pages(_pages)
+                _doc: DocumentPdf = self.collection_pages.to_document(self.lib_pdf)
             else:
-                _doc.add_pages(_pages)
+                _doc.add_pages(self.collection_pages.pages)
         return _doc
 
+    def thresold(self, *, land_scape: bool = False, a4: bool = False, dpi=300) -> DocumentPdf:
+        images: list[ImageObject] = self.collection_images.images
+        if not self.collection_pages.is_null:
+            tmp_doc = DocumentPdf.create_from_pages(self.collection_pages.pages)
+            conv_pdf_to_img = ConvertPdfToImages.create(tmp_doc)
+            images.extend(conv_pdf_to_img.to_images(dpi=dpi))
+            del tmp_doc
+        if len(images) == 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)
+        return conv_img_to_pdf.to_document(a4=a4)
+
     def to_files_images(
                 self,
                 output_dir: Directory, *,
@@ -134,16 +154,20 @@ class PdfStream(object):
         if self.collection_pages.is_null and self.collection_images.is_empty:
             raise ValueError('Adicione imagens e/ou documentos para prosseguir!')
         self.progress.start()
+
+        image_stream = ImageStream()
+        if not self.collection_images.is_empty:
+            image_stream.add_images(self.collection_images.images)
         if not self.collection_pages.is_null:
             self.progress.update_text('Processando Imagens')
             # Criar um documento a partir das páginas
             doc_pdf = DocumentPdf.create_from_pages(self.collection_pages.pages)
             convert_pdf_to_img = ConvertPdfToImages.create(doc_pdf)
             # Converter as páginas PDF em imagens e adicionar a coleção já existe de imagens.
-            self.collection_images.add_images(convert_pdf_to_img.to_images(dpi=dpi))
-            self.collection_pages.clear()
+            _pdf_to_images: list[ImageObject] = convert_pdf_to_img.to_images(dpi=dpi)
+            image_stream.add_images(_pdf_to_images)
         # Exportar para arquivos.
-        self.collection_images.to_files_image(output_dir, replace=replace, land_scape=land_scape)
+        image_stream.to_files_image(output_dir, replace=replace, land_scape=land_scape)
         self.progress.stop()
 
     def to_files_pdf(
@@ -151,21 +175,27 @@ class PdfStream(object):
                 output_dir: Directory, *,
                 replace: bool = False,
                 land_scape: bool = False,
+                a4: bool = False,
+                prefix: str = None,
             ) -> None:
         if self.collection_pages.is_null and self.collection_images.is_empty:
             raise ValueError('Adicione imagens e/ou documentos para prosseguir!')
+        pages_document = []
         if not self.collection_pages.is_null:
-            convert_img_to_pdf = ConvertImageToPdf(self.collection_images)
-            self.collection_pages.add_pages(convert_img_to_pdf.to_document().to_pages())
-            self.collection_images.clear()
+            pages_document.extend(self.collection_pages.pages)
+        if not self.collection_images.is_empty:
+            img_to_pdf = ConvertImageToPdf(self.collection_images, lib_img_to_pdf=self.lib_img_to_pdf)
+            tmp_document = img_to_pdf.to_document(land_scape, a4=a4)
+            pages_document.extend(tmp_document.to_pages())
+        final_collection = CollectionPagePdf(pages_document)
         if land_scape:
-            self.collection_pages.set_land_scape()
-        self.collection_pages.to_files_pdf(output_dir, replace=replace)
+            final_collection.set_land_scape()
+        final_collection.to_files_pdf(output_dir, replace=replace, prefix=prefix)
 
 
 class SplitPdf(object):
 
-    def __init__(self, pages: list[PageDocumentPdf], pbar: ProgressBarAdapter = ProgressBarAdapter()):
+    def __init__(self, pages: list[PageDocumentPdf] = [], pbar: ProgressBarAdapter = ProgressBarAdapter()):
         self.pbar: ProgressBarAdapter = pbar
         self.__collection_pages: CollectionPagePdf = CollectionPagePdf(pages)
         self.__collection_pages.set_pbar(self.pbar)
@@ -173,6 +203,9 @@ class SplitPdf(object):
     def is_empty(self) -> bool:
         return self.__collection_pages.is_null
 
+    def add_pages_pdf(self, pages: list[PageDocumentPdf]) -> None:
+        self.__collection_pages.add_pages(pages)
+
     def export(self, output_dir: Directory, *, replace: bool = False, prefix: str = 'pag') -> None:
         if self.is_empty():
             self.pbar.update_text(f'O Documento está vazio!')

{convert_stream-2.2.6 → convert_stream-2.3}/convert_stream/enum_libs/modules.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 from __future__ import annotations
-from typing import Union, TypeAlias
+from typing import Union, TypeAlias, Any
 from convert_stream.enum_libs.enums import *
 
 MOD_IMG_PIL: bool = False
@@ -18,16 +18,16 @@ try:
     from cv2.typing import MatLike
     MOD_IMG_OPENCV = True
 except ImportError:
-    cv2.typing.MatLike = object
-    MatLike = None
+    cv2.typing.MatLike = Any
+    MatLike = Any
 
 try:
     from PIL import Image
     from PIL import ImageOps, ImageFilter
     MOD_IMG_PIL = True
 except ImportError:
-    Image = None
-    Image.Image = None
+    Image = Any
+    Image.Image = Any
 
 if MOD_IMG_OPENCV and MOD_IMG_PIL:
     ModuleImage: TypeAlias = Union[MatLike, Image.Image]
@@ -40,7 +40,7 @@ elif MOD_IMG_PIL:
     DEFAULT_LIB_IMAGE = LibImage.PIL
 else:
     DEFAULT_LIB_IMAGE = LibImage.NOT_IMPLEMENTED
-    ModuleImage = None  # fallback para runtime
+    ModuleImage = Any  # fallback para runtime
 
 #=================================================================#
 # Módulos para PDF fitz e pypdf
@@ -54,34 +54,34 @@ except ImportError:
         import pymupdf as fitz
         MOD_FITZ = True
     except ImportError:
-        fitz = None
-        fitz.Page = None
-        fitz.TextPage = None
+        fitz = Any
+        fitz.Page = Any
+        fitz.TextPage = Any
 
 try:
     from pypdf import PdfWriter, PdfReader, PageObject
     MOD_PYPDF = True
 except ImportError:
-    PageObject = None
-    PdfReader = None
-    PdfWriter = None
+    PageObject = Any
+    PdfReader = Any
+    PdfWriter = Any
 
 
 if MOD_FITZ and MOD_PYPDF:
-    ModulePagePdf: TypeAlias = Union[PageObject, fitz.Page]
-    ModuleDocPdf: TypeAlias = Union[fitz.Document, PdfWriter]
+    ModPagePdf = Union[PageObject, fitz.Page]
+    ModDocPdf = Union[fitz.Document, PdfWriter]
     DEFAULT_LIB_PDF = LibPDF.FITZ
 elif MOD_FITZ:
-    ModulePagePdf: TypeAlias = Union[fitz.Page]
-    ModuleDocPdf: TypeAlias = Union[fitz.Document]
+    ModPagePdf = Union[fitz.Page]
+    ModDocPdf = Union[fitz.Document]
     DEFAULT_LIB_PDF = LibPDF.FITZ
 elif MOD_PYPDF:
-    ModulePagePdf: TypeAlias = Union[PageObject]
-    ModuleDocPdf: TypeAlias = Union[PdfWriter]
+    ModPagePdf = Union[PageObject]
+    ModDocPdf = Union[PdfWriter]
     DEFAULT_LIB_PDF = LibPDF.PYPDF
 else:
-    ModulePagePdf = None  # fallback para runtime
-    ModuleDocPdf: TypeAlias = None
+    ModPagePdf = Any  # fallback para runtime
+    ModDocPdf = Any
     DEFAULT_LIB_PDF = LibPDF.NOT_IMPLEMENTED
 
 #=================================================================#
@@ -95,10 +95,10 @@ try:
     from reportlab.lib.utils import ImageReader
     MOD_CANVAS = True
 except ImportError:
-    canvas = None
-    Canvas = None
+    canvas = Any
+    Canvas = Any
     letter = (612, 792)
-    ImageReader = None
+    ImageReader = Any
 
 if MOD_CANVAS and MOD_FITZ and MOD_IMG_PIL:
     ModImageToPdf: TypeAlias = Union[canvas, fitz.Page, Image]
@@ -113,7 +113,7 @@ elif MOD_IMG_PIL:
     ModImageToPdf: TypeAlias = Union[Image]
     DEFAULT_LIB_IMAGE_TO_PDF = LibImageToPdf.IMAGE_TO_PDF_PIL
 else:
-    ModImageToPdf = None
+    ModImageToPdf = Any
     DEFAULT_LIB_IMAGE_TO_PDF = LibImageToPdf.NOT_IMPLEMENTED
 
 #=================================================================#
@@ -125,4 +125,4 @@ if MOD_FITZ:
     ModPdfToImage: TypeAlias = Union[fitz]
 else:
     DEFAULT_LIB_PDF_TO_IMG = LibPdfToImage.NOT_IMPLEMENTED
-    ModPdfToImage = None
+    ModPdfToImage = Any