convert-stream 2.4.1__tar.gz → 2.4.2__tar.gz

{convert_stream-2.4.1 → convert_stream-2.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.4.1
+Version: 2.4.2
 Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
 Author: Bruno Chaves
 Requires-Python: >=3.11
@@ -15,6 +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
 
 # Configuração instalação:
 pip3 install -r requirements.txt

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/__init__.py

@@ -8,20 +8,19 @@ from ._version import (
     __module_name__, __author__, __license__, __modify_date__, __version__
 )
 from .mod_types import (
-    MetaDataFile, MetaDataItem, create_metadata, ColumnsTable, ListString, ArrayString,
-    HeadCell, HeadValues, ColumnBody, TextTable, LibDate, LibPDF, LibImage, LibPdfToImage,
-    LibImageToPdf, DictTextTable, RotationAngle,
+    LibPDF, LibImage, LibPdfToImage,    LibImageToPdf, DictTextTable, RotationAngle,
 )
 from .image import ImageObject, CollectionImages
 from .pdf import DocumentPdf, PageDocumentPdf, CollectionPagePdf, ConvertPdfToImages, ConvertImageToPdf
 from .pdf.pdf_document import SearchableTextPdf
 from .doc_stream import PdfStream, SplitPdf
 from .table_files import PdfFinder
-from .text import ConvertStringDate, fmt_col_to_date
+from .text import print_title, print_line, FindStrings
+from sheet_stream import VoidAdapter
 
 
 def __create_stream() -> PdfStream:
-    st = PdfStream()
+    st = PdfStream(pbar=VoidAdapter())
     st.clear()
     return st
 
@@ -77,10 +76,9 @@ __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',
-    'MetaDataFile', 'MetaDataItem', 'ColumnsTable', 'ListString', 'ArrayString',
-    'HeadCell', 'HeadValues', 'ColumnBody', 'TextTable', 'LibDate', 'LibPDF', 'LibImage', 'LibPdfToImage',
+    'PdfFinder', 'SplitPdf', 'LibImageToPdf',  'RotationAngle', 'ConvertImageToPdf',
+    'ConvertPdfToImages', 'LibPDF', 'LibImage', 'LibPdfToImage',
     'read_pdf', 'read_files_pdf', 'read_image', 'DictTextTable',
-    'create_metadata', 'fmt_col_to_date',
+    'print_title', 'print_line', 'FindStrings',
 ]
 

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/doc_stream.py

@@ -31,22 +31,38 @@ class PdfStream(object):
     def __init__(
                 self, *,
                 pbar: ProgressBarAdapter = ProgressBarAdapter(),
-                lib_pdf: LibPDF = DEFAULT_LIB_PDF,
-                lib_img: LibImage = DEFAULT_LIB_IMAGE,
-                lib_img_to_pdf: LibImageToPdf = DEFAULT_LIB_IMAGE_TO_PDF,
-                lib_pdf_to_img: LibPdfToImage = DEFAULT_LIB_PDF_TO_IMG,
+                lib_pdf: LibPDF = LibPDF.FITZ,
+                lib_img: LibImage = LibImage.OPENCV,
+                lib_img_to_pdf: LibImageToPdf = LibImageToPdf.IMAGE_TO_PDF_FITZ,
+                lib_pdf_to_img: LibPdfToImage = LibPdfToImage.PDF_TO_IMG_FITZ,
+                dpi: int = 200,
             ) -> None:
+        self.dpi = dpi
         self.progress: ProgressBarAdapter = pbar
         self.collection_pages: CollectionPagePdf = CollectionPagePdf([])
-        self.collection_images: CollectionImages = CollectionImages([])
-        self.collection_images.set_pbar(pbar)
-        self.collection_pages.set_pbar(pbar)
+        self.collection_images: CollectionImages = CollectionImages([], lib_img=lib_img)
+        self.collection_images.set_pbar(self.progress)
+        self.collection_pages.set_pbar(self.progress)
         self.lib_pdf: LibPDF = lib_pdf
         self.lib_img: LibImage = lib_img
         self.lib_img_to_pdf: LibImageToPdf = lib_img_to_pdf
         self.lib_pdf_to_img: LibPdfToImage = lib_pdf_to_img
         self.clear()
 
+    @property
+    def convert_pdf_to_images(self) -> ConvertPdfToImages:
+        conv = ConvertPdfToImages.create(
+            DocumentPdf.create_from_pages(self.collection_pages, lib_pdf=self.lib_pdf),
+        )
+        conv.set_pbar(self.progress)
+        return conv
+
+    @property
+    def convert_images_to_pdf(self) -> ConvertImageToPdf:
+        _con = ConvertImageToPdf(self.collection_images, lib_img_to_pdf=self.lib_img_to_pdf)
+        _con.set_pbar(self.progress)
+        return _con
+
     @property
     def is_empty(self) -> bool:
         return self.collection_pages.is_empty
@@ -81,10 +97,10 @@ class PdfStream(object):
         self.collection_images.add_images(images)
 
     def add_file_pdf(self, f: File) -> None:
-        self.collection_pages.add_file_pdf(f)
+        self.collection_pages.add_file_pdf(f, lib_pdf=self.lib_pdf)
 
     def add_files_pdf(self, files: list[File]) -> None:
-        self.collection_pages.add_files_pdf(files)
+        self.collection_pages.add_files_pdf(files, lib_pdf=self.lib_pdf)
 
     def add_document(self, doc: DocumentPdf) -> None:
         self.collection_pages.add_document(doc)
@@ -105,23 +121,28 @@ class PdfStream(object):
 
         _doc: DocumentPdf = None
         if not self.collection_images.is_empty:
-            _convert = ConvertImageToPdf(self.collection_images, lib_img_to_pdf=self.lib_img_to_pdf)
-            _convert.set_pbar(self.progress)
-            _doc: DocumentPdf = _convert.to_document(land_scape, a4=a4)
+            # Converter as imagens em documento PDF.
+            _doc = self.convert_images_to_pdf.to_document(land_scape, a4=a4)
         if not self.collection_pages.is_empty:
+            # Converter/Adicionar as páginas PDF ao documento final.
             if _doc is None:
                 _doc: DocumentPdf = self.collection_pages.to_document(self.lib_pdf)
             else:
                 _doc.add_pages(self.collection_pages)
         return _doc
 
-    def thresold(self, *, land_scape: bool = False, a4: bool = False, dpi=300) -> DocumentPdf:
-        images: list[ImageObject] = self.collection_images
+    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:
-            tmp_doc = DocumentPdf.create_from_pages(self.collection_pages)
-            conv_pdf_to_img = ConvertPdfToImages.create(tmp_doc)
-            images.extend(conv_pdf_to_img.to_images(dpi=dpi))
-            del tmp_doc
+            # 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:
             raise ValueError('Adicione imagens para prosseguir!')
         if land_scape:
@@ -137,22 +158,21 @@ class PdfStream(object):
                 output_dir: Directory, *,
                 replace: bool = False,
                 land_scape: bool = False,
-                dpi: int = 300,
             ) -> None:
         if self.collection_pages.is_empty and self.collection_images.is_empty:
             raise ValueError('Adicione imagens e/ou documentos para prosseguir!')
         self.progress.start()
 
         image_stream = ImageStream([])
+        image_stream.set_pbar(self.progress)
         if not self.collection_images.is_empty:
             image_stream.add_images(self.collection_images)
         if not self.collection_pages.is_empty:
             self.progress.update_text('Processando Imagens')
             # Criar um documento a partir das páginas
-            doc_pdf = DocumentPdf.create_from_pages(self.collection_pages)
-            convert_pdf_to_img = ConvertPdfToImages.create(doc_pdf)
+            convert_pdf_to_img = self.convert_pdf_to_images
             # Converter as páginas PDF em imagens e adicionar a coleção já existe de imagens.
-            _pdf_to_images: list[ImageObject] = convert_pdf_to_img.to_images(dpi=dpi)
+            _pdf_to_images: list[ImageObject] = convert_pdf_to_img.to_images(dpi=self.dpi, lib_image=self.lib_img)
             image_stream.add_images(_pdf_to_images)
         # Exportar para arquivos.
         image_stream.to_files_image(output_dir, replace=replace, land_scape=land_scape)
@@ -172,7 +192,7 @@ class PdfStream(object):
         if not self.collection_pages.is_empty:
             pages_document.extend(self.collection_pages)
         if not self.collection_images.is_empty:
-            img_to_pdf = ConvertImageToPdf(self.collection_images, lib_img_to_pdf=self.lib_img_to_pdf)
+            img_to_pdf: ConvertImageToPdf = self.convert_images_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)

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/image/img_object.py

@@ -4,13 +4,15 @@
     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 io import BytesIO
 import numpy as np
 from scipy.ndimage import uniform_filter
-from convert_stream.mod_types import get_hash_from_bytes, MetaDataFile, MetaDataItem, create_metadata
+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.modules import (
@@ -205,7 +207,7 @@ class ImplementOpenCv(ABCImageObject):
         if img is None:
             raise ValueError(f"Não foi possível abrir a imagem: {f.absolute()}")
         im_obj = cls(img)
-        im_obj.metadata = create_metadata(f)
+        im_obj.metadata = MetaDataFile.create_metadata(f)
         return im_obj
 
     @classmethod
@@ -350,7 +352,7 @@ class ImplementPIL(ABCImageObject):
     def create_from_file(cls, f: File) -> ABCImageObject:
         img = Image.open(f.absolute())
         im_obj = cls(img)
-        im_obj.metadata = create_metadata(f)
+        im_obj.metadata = MetaDataFile.create_metadata(f)
         return im_obj
 
     @classmethod
@@ -498,12 +500,13 @@ class ImageObject(object):
 
 class CollectionImages(ListItems):
     
-    def __init__(self, images: list[ImageObject]) -> None:
+    def __init__(self, images: list[ImageObject], *, 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.__count: int = 0
 
@@ -520,7 +523,7 @@ class CollectionImages(ListItems):
         self.pbar.start()
         self.__count += 1
         self.pbar.update_text(f'Adicionando imagem {self.__count} {file.basename()}')
-        im = ImageObject.create_from_file(file)
+        im = ImageObject.create_from_file(file, lib_image=self.lib_img)
         self.append(im)
         self.pbar.stop()
 
@@ -536,7 +539,7 @@ class CollectionImages(ListItems):
                 ((num+1) / max_num) * 100,
                 f'Adicionando imagem: [{num+1} de {max_num}]'
             )
-            self.append(ImageObject.create_from_file(f))
+            self.append(ImageObject.create_from_file(f, lib_image=self.lib_img))
         self.pbar.stop()
 
     def add_directory_images(self, d: Directory, max_files: int = 4000) -> None:
@@ -554,8 +557,12 @@ class CollectionImages(ListItems):
         print()
         output_dir.mkdir()
         max_num = self.length
+        img: ImageObject
         for n, img in enumerate(self):
-            filename = f'{img.name}.png'
+            if img.metadata.file_path is not None:
+                filename = f'{os.path.basename(img.metadata.file_path)}-{n}.png'
+            else:
+                filename = f'{img.metadata.name}-{n}.png'
             file_path = output_dir.join_file(filename)
             if (not replace) and (file_path.exists()):
                 self.pbar.update_text(f'[PULANDO]: {file_path.basename()}')

convert_stream-2.4.2/convert_stream/mod_types/__init__.py

@@ -0,0 +1,13 @@
+#!/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-2.4.1 → convert_stream-2.4.2}/convert_stream/mod_types/enums.py

@@ -58,15 +58,6 @@ class LibImage(Enum):
     NOT_IMPLEMENTED = 'null'
 
 
-class LibDate(Enum):
-    D_M_Y = '%d-%m-%Y'
-    DMY = '%d/%m/%Y'
-    dmy = '%d/%m/%y'
-    d_m_y = '%d-%m-%y'
-    YMD = '%Y/%m/%d'
-    Y_M_D = '%Y-%m-%d'
-
-
 class RotationAngle(Enum):
 
     ROTATION_90 = 90

convert_stream-2.4.2/convert_stream/mod_types/table_types.py

@@ -0,0 +1,19 @@
+#!/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-2.4.1 → convert_stream-2.4.2}/convert_stream/pdf/image_to_pdf.py

@@ -297,7 +297,7 @@ class ConvertImageToPdf(object):
     def __init__(
             self,
             collection_images: CollectionImages, *,
-            lib_img_to_pdf: LibImageToPdf = DEFAULT_LIB_IMAGE_TO_PDF
+            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)

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/pdf/pdf_document.py

@@ -9,13 +9,14 @@ from io import BytesIO
 from typing import Union
 import pandas as pd
 from soup_files import File, Directory, LibraryDocs, InputFiles, ProgressBarAdapter, JsonConvert
-from convert_stream.mod_types import (
-    get_hash_from_bytes, create_metadata, MetaDataFile, MetaDataItem
+from sheet_stream.type_utils import (
+    get_hash_from_bytes, MetaDataFile, MetaDataItem
 )
-from convert_stream.mod_types.table_types import (
-    ListItems, concat_maps, DictTextTable, ColumnBody,
-    HeadCell, HeadValues, ColumnsTable
+
+from sheet_stream.type_utils import (
+    ListItems, HeadCell, HeadValues, ColumnsTable, concat_table_documents, TableDocuments
 )
+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
@@ -33,7 +34,7 @@ class SearchableTextPdf(object):
             ColumnsTable.KEY.value: ColumnBody(ColumnsTable.KEY.value, ListString([])),
             ColumnsTable.NUM_PAGE.value: ColumnBody(ColumnsTable.NUM_PAGE.value, ListString([])),
             ColumnsTable.NUM_LINE.value: ColumnBody(ColumnsTable.NUM_LINE.value, ListString([])),
-            ColumnsTable.TEXT.value: ColumnBody(ColumnsTable.TEXT.value, ListString([])),
+            ColumnsTable.TEXT: ColumnBody(ColumnsTable.TEXT, ListString([])),
             ColumnsTable.FILE_NAME.value: ColumnBody(ColumnsTable.FILE_NAME.value, ListString([])),
             ColumnsTable.FILETYPE.value: ColumnBody(ColumnsTable.FILETYPE.value, ListString([])),
             ColumnsTable.FILE_PATH.value: ColumnBody(ColumnsTable.FILE_PATH.value, ListString([])),
@@ -49,10 +50,10 @@ class SearchableTextPdf(object):
 
     @property
     def length(self) -> int:
-        return len(self.elements[ColumnsTable.TEXT.value])
+        return len(self.elements[ColumnsTable.TEXT])
 
     def is_empty(self) -> bool:
-        return len(self.elements[ColumnsTable.TEXT.value]) == 0
+        return len(self.elements[ColumnsTable.TEXT]) == 0
 
     @property
     def columns(self) -> HeadValues:
@@ -110,7 +111,7 @@ class SearchableTextPdf(object):
         ou 'nas' em caso de erro nas = Not a String
         """
         try:
-            return ' '.join(self.elements[ColumnsTable.TEXT.value])
+            return ' '.join(self.elements[ColumnsTable.TEXT])
         except Exception as e:
             print(e)
             return 'nas'
@@ -270,7 +271,7 @@ class ImplementDocumentFitz(ABCDocument):
             raise ImportError("Módulo fitz|pymupdf não instalado!\nUse pip install fitz.")
         doc = fitz.open(file.path)
         _obj_doc = cls(doc)
-        _obj_doc.metadata = create_metadata(file)
+        _obj_doc.metadata = MetaDataFile.create_metadata(file)
         return _obj_doc
 
     @classmethod
@@ -391,7 +392,7 @@ class ImplementDocumentPyPdf(ABCDocument):
             pdf_writer.add_page(p)
         del reader
         _obj_doc = cls(pdf_writer)
-        _obj_doc.metadata = create_metadata(file)
+        _obj_doc.metadata = MetaDataFile.create_metadata(file)
         return _obj_doc
 
     @classmethod
@@ -469,6 +470,7 @@ class DocumentPdf(object):
             raise ValueError(
                 f'Use: str, File, PdfWriter, fitz.Document ou BytesIO não => {type(document)}'
             )
+        print(self.metadata)
 
     @property
     def name(self) -> str | None:
@@ -560,7 +562,7 @@ class DocumentPdf(object):
                 dir_path=self.metadata.dir_path,
             )
 
-    def to_dict(self, separator: str = '\n') -> DictTextTable:
+    def to_dict(self, separator: str = '\n') -> TableDocuments:
         list_data: list[DictTextTable] = []
         pages: list[PageDocumentPdf] = self.to_pages()
 
@@ -569,7 +571,7 @@ class DocumentPdf(object):
             list_data.append(_mp)
         if len(list_data) == 0:
             return DictTextTable.create_void_dict()
-        return concat_maps(list_data)
+        return concat_table_documents(list_data)
 
     def to_data(self, separator: str = '\n') -> pd.DataFrame:
         return pd.DataFrame.from_dict(self.to_dict(separator=separator))
@@ -604,7 +606,7 @@ class DocumentPdf(object):
                             ColumnsTable.KEY.value: f'{idx}',
                             ColumnsTable.NUM_PAGE.value: f'{_page.number_page}',
                             ColumnsTable.NUM_LINE.value: f'{idx+1}',
-                            ColumnsTable.TEXT.value: math_text,
+                            ColumnsTable.TEXT: math_text,
                             ColumnsTable.FILE_NAME.value: self.metadata.name,
                             ColumnsTable.FILETYPE.value: self.metadata.extension,
                             ColumnsTable.FILE_PATH.value: self.metadata.file_path,
@@ -646,7 +648,7 @@ class DocumentPdf(object):
                     ColumnsTable.KEY.value: f'{idx}',
                     ColumnsTable.NUM_PAGE.value: f'{_page.number_page}',
                     ColumnsTable.NUM_LINE.value: f'{idx + 1}',
-                    ColumnsTable.TEXT.value: math_text,
+                    ColumnsTable.TEXT: math_text,
                     ColumnsTable.FILE_NAME.value: self.metadata.name,
                     ColumnsTable.FILETYPE.value: self.metadata.extension,
                     ColumnsTable.FILE_PATH.value: self.metadata.file_path,
@@ -671,6 +673,7 @@ class DocumentPdf(object):
             ) -> DocumentPdf:
         if lib_pdf == LibPDF.FITZ:
             mod_pdf = ImplementDocumentFitz.create_from_pages(pages)
+            mod_pdf.metadata.file_path = pages[0].metadata.file_path
             return cls(mod_pdf, lib_pdf=lib_pdf)
         elif lib_pdf == LibPDF.PYPDF:
             mod_pdf = ImplementDocumentPyPdf.create_from_pages(pages)
@@ -716,12 +719,12 @@ class CollectionPagePdf(ListItems):
             pg.number_page = _counter
             self.append(pg)
 
-    def add_file_pdf(self, file: File, *, lib_pdf: LibPDF = DEFAULT_LIB_PDF) -> None:
+    def add_file_pdf(self, file: File, *, lib_pdf: LibPDF = LibPDF.FITZ) -> None:
         self.pbar.update_text(f'Adicionando arquivo PDF {file.basename()}')
         doc_pdf = DocumentPdf(file, lib_pdf=lib_pdf)
         self.add_pages(doc_pdf.to_pages())
 
-    def add_files_pdf(self, files: list[File], lib_pdf: LibPDF = DEFAULT_LIB_PDF) -> None:
+    def add_files_pdf(self, files: list[File], lib_pdf: LibPDF = LibPDF.FITZ) -> None:
         max_num: int = len(files)
         for num, f in enumerate(files):
             self.pbar.update(

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/pdf/pdf_page.py

@@ -9,12 +9,12 @@ import pandas as pd
 
 from convert_stream.mod_types.enums import LibPDF
 from convert_stream.mod_types.table_types import (
-    DictTextTable, ListString, ColumnBody
+    DictTextTable, ListString
 )
 from convert_stream.mod_types.modules import (
     ModPagePdf, PageObject, fitz
 )
-from convert_stream.mod_types import MetaDataItem, MetaDataFile
+from sheet_stream.type_utils import MetaDataFile
 from convert_stream.text.find_text import FindText, ArrayString
 
 

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/pdf/pdf_to_image.py

@@ -6,6 +6,8 @@
 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
@@ -74,6 +76,7 @@ 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()
@@ -85,12 +88,14 @@ class ImplementConvertPdfFitz(ABCConvertPdf):
     def to_images(
                 self, *,
                 dpi: int = 200,
-                lib_image: LibImage = DEFAULT_LIB_IMAGE
+                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):
@@ -103,6 +108,8 @@ class ImplementConvertPdfFitz(ABCConvertPdf):
                 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
 
@@ -112,14 +119,14 @@ class ImplementConvertPdfFitz(ABCConvertPdf):
                 replace: bool = False,
                 gaussian_filter: bool = False,
                 dpi: int = 300,
-                lib_image: LibImage = DEFAULT_LIB_IMAGE
+                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 imagen]: {n + 1}/{_count}'
+                f'[Documento para arquivos de imagens]: {n + 1}/{_count}'
             )
             out_file = output_dir.join_file(f'pag-{n+1}.png')
             if not replace:
@@ -153,7 +160,7 @@ class ConvertPdfToImages(object):
     def to_images(
                 self, *,
                 dpi: int = 300,
-                lib_image: LibImage = DEFAULT_LIB_IMAGE,
+                lib_image: LibImage = LibImage.PIL,
             ) -> list[ImageObject]:
         return self.mod_convert_to_image.to_images(dpi=dpi, lib_image=lib_image)
 
@@ -163,7 +170,7 @@ class ConvertPdfToImages(object):
                 replace: bool = False,
                 gaussian_filter: bool = False,
                 dpi: int = 300,
-                lib_image: LibImage = DEFAULT_LIB_IMAGE,
+                lib_image: LibImage = LibImage.PIL,
             ) -> None:
         self.mod_convert_to_image.to_files_image(
             dpi=dpi,

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/table_files.py

@@ -88,14 +88,14 @@ class PdfFinder(object):
                     file_type = temp_doc.metadata.extension
 
                     new_line: dict[str, str] = {
-                        ColumnsTable.KEY.value: f'{idx}',
-                        ColumnsTable.NUM_PAGE.value: 'nan',
-                        ColumnsTable.NUM_LINE.value: f'{idx + 1}',
-                        ColumnsTable.TEXT.value: math_text,
-                        ColumnsTable.FILE_NAME.value: file_name,
-                        ColumnsTable.FILETYPE.value: file_type,
-                        ColumnsTable.FILE_PATH.value: file_path,
-                        ColumnsTable.DIR.value: dir_path,
+                        ColumnsTable.KEY: f'{idx}',
+                        ColumnsTable.NUM_PAGE: 'nan',
+                        ColumnsTable.NUM_LINE: f'{idx + 1}',
+                        ColumnsTable.TEXT: math_text,
+                        ColumnsTable.FILE_NAME: file_name,
+                        ColumnsTable.FILETYPE: file_type,
+                        ColumnsTable.FILE_PATH: file_path,
+                        ColumnsTable.DIR: dir_path,
                     }
                     _searchable.add_line(new_line)
                     return _searchable
@@ -140,14 +140,14 @@ class PdfFinder(object):
                     file_type = temp_doc.metadata.extension
 
                     new_line: dict[str, str] = {
-                        ColumnsTable.KEY.value: f'{idx}',
-                        ColumnsTable.NUM_PAGE.value: 'nan',
-                        ColumnsTable.NUM_LINE.value: f'{idx + 1}',
-                        ColumnsTable.TEXT.value: math_text,
-                        ColumnsTable.FILE_NAME.value: file_name,
-                        ColumnsTable.FILETYPE.value: file_type,
-                        ColumnsTable.FILE_PATH.value: file_path,
-                        ColumnsTable.DIR.value: dir_path,
+                        ColumnsTable.KEY: f'{idx}',
+                        ColumnsTable.NUM_PAGE: 'nan',
+                        ColumnsTable.NUM_LINE: f'{idx + 1}',
+                        ColumnsTable.TEXT: math_text,
+                        ColumnsTable.FILE_NAME: file_name,
+                        ColumnsTable.FILETYPE: file_type,
+                        ColumnsTable.FILE_PATH: file_path,
+                        ColumnsTable.DIR: dir_path,
                     }
                     _searchable.add_line(new_line)
         return _searchable

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/text/__init__.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python3
-from .date import ConvertStringDate, fmt_col_to_date
-from .find_text import FindText
+from .find_text import FindText, FindStrings
 from .terminal import (
     print_line, print_title, show_error, show_warning, show_info, Colors, msg
 )
+from sheet_stream import ConvertStringDate, fmt_col_to_date
 
 __all__ = [
     'ConvertStringDate', 'print_title', 'print_line', 'fmt_col_to_date',

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream/text/find_text.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 from __future__ import annotations
-from convert_stream.mod_types.table_types import ArrayString
+from sheet_stream import ArrayString, contains, find_index, find_all_index
 
 
 class FindText(object):
@@ -46,5 +46,20 @@ class FindText(object):
         return self.array.find_all(text, iqual=iqual, case=case)
 
 
+class FindStrings(object):
 
+    def __init__(self, key_words: list[str]):
+        self.key_words: list[str] = key_words
 
+    def find_all(self, values: list[str], *, iqual: bool = False, case: bool = True) -> ArrayString:
+        final_values = ArrayString([])
+        ignore_idx: list[int] = []
+
+        for txt in self.key_words:
+            all_idx: list[int] = find_all_index(txt, values, iqual=iqual, case=case)
+            if len(all_idx) > 0:
+                for i in all_idx:
+                    if not i in ignore_idx:
+                        final_values.append(values[i])
+                        ignore_idx.append(i)
+        return final_values

{convert_stream-2.4.1 → convert_stream-2.4.2}/convert_stream.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: convert_stream
-Version: 2.4.1
+Version: 2.4.2
 Summary: Manipulação de documentos PDF e Imagens. Converter, Ler, rotacionar exportar etc.
 Author: Bruno Chaves
 Requires-Python: >=3.11
@@ -15,6 +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
 
 # Configuração instalação:
 pip3 install -r requirements.txt