ocr-stream 2.2__tar.gz → 2.2.6__tar.gz

{ocr_stream-2.2 → ocr_stream-2.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocr_stream
-Version: 2.2
+Version: 2.2.6
 Summary: Extrair textos de documentos digitalizados e imagens.
 Author: Bruno Chaves
 Requires-Python: >=3.11

{ocr_stream-2.2 → ocr_stream-2.2.6}/ocr_stream/recognize.py

@@ -84,7 +84,8 @@ class RecognizePdf(object):
         return text_recognized.to_document()
 
     def recognize_document(self, doc: DocumentPdf) -> DocumentPdf:
-        _stream = PdfStream()
+        _pages: list[PageDocumentPdf] = []
+        _pages.clear()
         _conv = ConvertPdfToImages.create(doc)
         images: list[ImageObject] = _conv.to_images()
         max_num: int = len(images)
@@ -94,12 +95,15 @@ class RecognizePdf(object):
                 f'Aplicando OCR [{num+1} de {max_num}]'
             )
             text_recognized = self.recognize_image.image_recognize(img)
-            _stream.add_page(text_recognized.to_page_pdf())
+            _pages.append(text_recognized.to_page_pdf())
         print()
         self.pbar.stop()
-        return _stream.to_document()
+        new_doc = DocumentPdf.create_from_pages(_pages)
+        return new_doc
 
     def recognize_file_pdf(self, file: File) -> DocumentPdf:
-        _doc = DocumentPdf.create_from_file(file)
-        return self.recognize_document(_doc)
+        file_doc = DocumentPdf.create_from_file(file)
+        recognized_doc = self.recognize_document(file_doc)
+        del file_doc
+        return recognized_doc
 

{ocr_stream-2.2 → ocr_stream-2.2.6}/ocr_stream.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocr_stream
-Version: 2.2
+Version: 2.2.6
 Summary: Extrair textos de documentos digitalizados e imagens.
 Author: Bruno Chaves
 Requires-Python: >=3.11

{ocr_stream-2.2 → ocr_stream-2.2.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ocr_stream"
-version = "2.2"
+version = "2.2.6"
 authors = [
   { name="Bruno Chaves"},
 ]