- fix bugs import data manipulates

evoflow/controller/data_manipulate/__init__.py

@@ -1,7 +0,0 @@
-#  Copyright (c) 2021. Copyright belongs to evoflow team
-
-from evoflow.Controller.DataManipulate.ExcelFileOperator import ExcelFileOperator
-from evoflow.Controller.DataManipulate.PdfFileOperator import PdfFileOperator
-from evoflow.Controller.DataManipulate.ImageFileOperator import ImageFileOperator
-from evoflow.Controller.DataManipulate.PptxFileOperator import PptxFileOperator
-from evoflow.Controller.DataManipulate.CatiaFileOperator import CatiaFileOperator

evoflow/controller/data_manipulate/excel_file_operator.py

@@ -2,9 +2,9 @@
 
 import pandas as pd
 
-from evoflow.controller.data_manipulate.FileOperator import FileOperator
-from evoflow.Entities.DataManipulate.FileOperator.DataFrameFile import DataFrameFile
-from evoflow.Entities.DataManipulate.FileOperator.File import File
+from evoflow.controller.data_manipulate.file_operator import FileOperator
+from evoflow.entities.data_manipulate.file_operator.dataframe_file import DataFrameFile
+from evoflow.entities.data_manipulate.file_operator.file import File
 
 
 class ExcelFileOperator(FileOperator):

evoflow/controller/data_manipulate/file_operator.py

@@ -1,11 +1,9 @@
-#  Copyright (c) 2021. Copyright belongs to evoflow team
-
 import abc
 
 from tqdm import tqdm
 
-from evoflow.Controller.DataManipulate.DataManipulate import DataManipulate
-from evoflow.Entities.DataManipulate.FileOperator.File import File
+from evoflow.controller.data_manipulate.data_manipulate import DataManipulate
+from evoflow.entities.data_manipulate.file_operator.file import File
 
 
 def get_reader(file_type):

evoflow/controller/data_manipulate/image_file_operator.py

@@ -8,7 +8,7 @@
 from evoflow import logger
 from evoflow.controller.data_manipulate.file_operator import FileOperator
 from evoflow.entities.data_manipulate.file_operator.file import File
-from evoflow.entities.data_manipulate.file_operator.ImageFile import ImageFile
+from evoflow.entities.data_manipulate.file_operator.image_file import ImageFile
 
 
 def imread(path, flags: int = -1):

evoflow/controller/data_manipulate/PdfFileOperator.py → evoflow/controller/data_manipulate/pdf_file_operator.py

@@ -1,8 +1,8 @@
 import pdfplumber
 
-from evoflow.Controller.DataManipulate.FileOperator import FileOperator
-from evoflow.Entities.DataManipulate.FileOperator.File import File
-from evoflow.Entities.DataManipulate.FileOperator.PdfFile import PdfFile
+from evoflow.controller.data_manipulate.file_operator import FileOperator
+from evoflow.entities.data_manipulate.file_operator.file import File
+from evoflow.entities.data_manipulate.file_operator.pdf_file import PdfFile
 
 
 class PdfFileOperator(FileOperator):

evoflow/controller/data_manipulate/PptxFileOperator.py → evoflow/controller/data_manipulate/pptx_file_operator.py

@@ -1,8 +1,8 @@
 from pptx import Presentation
 
-from evoflow.Controller.DataManipulate.FileOperator import FileOperator
-from evoflow.Entities.DataManipulate.FileOperator.File import File
-from evoflow.Entities.DataManipulate.FileOperator.PPTXFile import PPTXFile
+from evoflow.controller.data_manipulate.file_operator import FileOperator
+from evoflow.entities.data_manipulate.file_operator.file import File
+from evoflow.entities.data_manipulate.file_operator.pptx_file import PPTXFile
 
 
 class PptxFileOperator(FileOperator):

evoflow/entities/data_manipulate/file_operator/file.py

@@ -7,6 +7,7 @@
 class File(AbstractData):
     def __init__(self, file_path: str = None, **args):
         self.file_path = file_path
+        self.file_path = os.path.abspath(self.file_path)
 
         self.file_name = os.path.split(file_path)[1].replace(
             "." + self.get_file_type(), ""

evoflow/entities/data_manipulate/file_operator/image_file.py

@@ -5,9 +5,9 @@
 from PIL import Image, ImageDraw, ImageFont
 
 from evoflow.entities.data_manipulate.file_operator.file import File
-from evoflow.entities.Global import Global
-from evoflow.Services.OCR.EasyOCREngine import EasyOCREngine
-from evoflow.Services.OCR.Result import OCRResult
+from evoflow.entities.global_vars import Global
+from evoflow.services.ocr.easy_ocr_engine import EasyOCREngine
+from evoflow.services.ocr.result import OCRResult
 
 
 class ImageFile(File):
@@ -41,6 +41,11 @@ def __init__(self, **kwargs):
     def to_pil(self):
         return PIL.Image.fromarray(self.data)
 
+    def __array__(self):
+        """
+        Convert to numpy array: np.array(image_file)
+        """
+        return self.data
     def draw(self, ocr_results):
         user_path = f'{os.getenv("userprofile")}/.evoflow/fonts/Noto_Sans_JP/NotoSansJP-Regular.otf'
         data_path = "./data/.evoflow/fonts/Noto_Sans_JP/NotoSansJP-Regular.otf"

evoflow/entities/data_manipulate/file_operator/pdf_file.py

@@ -4,12 +4,14 @@
 import pathlib
 import urllib
 from typing import Iterator
+from urllib.request import URLopener
 
 import cv2
 import numpy as np
+import pdfplumber
 from tqdm import tqdm
 
-import evoflow.Params
+import evoflow.params
 from evoflow import logger
 from evoflow.controller.data_manipulate.image_file_operator import ImageFileOperator
 from evoflow.entities.data_manipulate.file_operator.file import File
@@ -26,11 +28,11 @@ def download_poppler():
 
     poppler_path = f"{os.getenv('userprofile')}/.evoflow/poppler"
     pathlib.Path(poppler_path).mkdir(parents=True, exist_ok=True)
-    poppler_file_name = evoflow.Params.POPPLER_URL.rsplit("/", maxsplit=-1)
-    opener = urllib.request.URLopener()
+    poppler_file_name = evoflow.params.POPPLER_URL.rsplit("/", maxsplit=-1)[-1]
+    opener = URLopener()
     opener.addheader("User-Agent", "evoflow")
     filename, _ = opener.retrieve(
-        evoflow.Params.POPPLER_URL, f"{poppler_path}/{poppler_file_name}"
+        evoflow.params.POPPLER_URL, f"{poppler_path}/{poppler_file_name}"
     )
     Archive(filename).extractall(poppler_path)
     os.remove(filename)
@@ -41,6 +43,11 @@ def download_poppler():
 class PdfFile(File):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
+        self.data = pdfplumber.open(self.file_path)
+
+    @property
+    def pages(self):
+        return self.data.pages
 
     def get_texts(self):
         page_count = len(self.data.pages)
@@ -76,7 +83,7 @@ def to_images(self, dpi=500) -> Iterator[ImageFile]:
                     ) from value_error
         else:
             poppler_path = poppler_paths[0]
-
+        poppler_path = os.path.abspath(poppler_path)
         pages = convert_from_path(self.file_path, dpi, poppler_path=poppler_path)
         images = []
         for i, page in tqdm(

evoflow/params.py

@@ -1,4 +1,4 @@
 POPPLER_URL = (
-    "http://blog.alivate.com.au/wp-content/uploads/2018/10/poppler-0.68.0_x86.7z"
+    "https://blog.alivate.com.au/wp-content/uploads/2018/10/poppler-0.68.0_x86.7z"
 )
 UPX_URL = "https://github.com/upx/upx/releases/download/v3.96/upx-3.96-win64.zip"

evoflow/services/ocr/easy_ocr_engine.py

@@ -8,7 +8,7 @@
 import numpy as np
 
 from evoflow import logger
-from evoflow.Services.ocr.result import OCRResult
+from evoflow.services.ocr.result import OCRResult
 
 try:
     import easyocr