ocr-stream 1.3__tar.gz → 1.4__tar.gz

{ocr_stream-1.3 → ocr_stream-1.4}/PKG-INFO

@@ -1,19 +1,32 @@
 Metadata-Version: 2.4
 Name: ocr_stream
-Version: 1.3
+Version: 1.4
 Summary: Extrair textos de documentos digitalizados e imagens.
 Author: Bruno Chaves
+Requires: PyPDF2
+Requires: PyMuPDF
+Requires: reportlab
+Requires: openpyxl
+Requires: openpyxl
+Requires: pandas
+Requires: Pillow
+Requires: opencv_python
+Requires: requests
+Requires: pytesseract
+Requires: soup_files
+Requires: convert_stream
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
-Requires-Dist: PyPDF2
 Requires-Dist: PyMuPDF
 Requires-Dist: reportlab
 Requires-Dist: openpyxl
 Requires-Dist: pandas
 Requires-Dist: Pillow>=11.3.0
+Requires-Dist: requests>=2.32.4
 Requires-Dist: opencv-python
-Requires-Dist: convert_stream
+Requires-Dist: convert_stream>=1.4
 Requires-Dist: soup_files
+Dynamic: requires
 
 # ocrlib
 

{ocr_stream-1.3 → ocr_stream-1.4}/ocr_stream/__init__.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 
 from .models.m_modules_ocr import LibraryOCR
-from .modules_ocr import TextRecognized
+from .modules_ocr import TextRecognized, BinaryTesseract
 from .utils import File, Directory, InputFiles, UserFileSystem
 from .extractors import RecognizeImage, RecognizePdf
 from ._version import __version__, __modify_data__

ocr_stream-1.4/ocr_stream/_version.py

@@ -0,0 +1,5 @@
+#!/usr/bin/env python3
+#
+
+__version__ = '1.4'
+__modify_data__ = '2025-07-11'

{ocr_stream-1.3 → ocr_stream-1.4}/ocr_stream/extractors.py

@@ -2,13 +2,12 @@
 from __future__ import annotations
 from typing import List
 from ocr_stream.utils import (
-    File, Directory, ImageObject,
-    DataFrame, PageDocumentPdf,
-    DocumentPdf, PdfStream, LibraryPDF,
+    File, ImageObject,
+    DataFrame, PageDocumentPdf, DocumentPdf,
 )
 from ocr_stream.models import LibraryOCR
 from ocr_stream.modules_ocr import ModuleOcr, TextRecognized, BinaryTesseract
-from convert_stream import LibImageToPDF, ConvertPdfToImage, CreatePbar
+from convert_stream import ConvertPdfToImage, CreatePbar
 from soup_files import ProgressBarAdapter
 
 

{ocr_stream-1.3 → ocr_stream-1.4}/ocr_stream/modules_ocr.py

@@ -2,7 +2,6 @@
 from __future__ import annotations
 from types import ModuleType
 from typing import List, Dict
-from pathlib import Path
 from shutil import which
 import re
 import os
@@ -15,8 +14,8 @@ from ocr_stream.models import (
 
 from ocr_stream.utils import (
     PageDocumentPdf, DocumentPdf, LibraryImage, LibraryPDF,
-    ImageObject, ArrayString, DataString, File, Directory,
-    FileToTable, ColumnTable, KERNEL_TYPE,
+    ImageObject, DataString, File, Directory,
+    ColumnTable, KERNEL_TYPE, ArrayString,
 )
 
 try:
@@ -37,7 +36,7 @@ class TextRecognizedToi(object):
         self.separator: str = separator
         self.file: File = file
         self.column_text: str = column_text
-
+        self.listText = []
         self.pattern_line_uc_toi = r'UC:\s*\d+\s*TOI:\s*\d+'
         self.pattern_uc = r'\b(?:UC:?|UC):?\s*(\d+)'
         self.pattern_toi = r'\b(?:TOI?|TO):?\s*(\d+)'
@@ -80,7 +79,11 @@ class TextRecognizedToi(object):
         return self.text_document.split(self.separator)
 
     def to_array_string(self) -> ArrayString:
-        values: List[str] = self.to_list()
+        try:
+            return ArrayString(self.to_list())
+        except Exception as e:
+            print(e)
+            return ArrayString([])
 
     def to_upper(self) -> TextRecognizedToi:
         self.text_document = self.text_document.upper()
@@ -120,20 +123,21 @@ class TextRecognizedToi(object):
         self.listText = values
         return self
 
-    def uc(self) -> str:
+    def uc(self) -> str | None:
         """
             Extrair o número da UC em forma de string, se a operação falhar, será retornado (nan)
         """
         line_uc_toi = self.line_uc_and_toi()
+
         uc_value: str = None
         if line_uc_toi is not None:
-            uc_value = self.__get_match_group(self.pattern_uc, line_uc_toi)
+            uc_value: str = self.__get_match_group(self.pattern_uc, line_uc_toi.value)
         if uc_value is not None:
             return uc_value.replace('UC', '')
 
         arr = ArrayString(self.text_document.split(' '))
         for w in self.words_uc:
-            out = arr.get_next(w).value
+            out: str = arr.get_next(w).value
             try:
                 int(out)
             except:
@@ -142,11 +146,14 @@ class TextRecognizedToi(object):
                 return out
         return None
 
-    def toi(self) -> str:
+    def toi(self) -> str | None:
         line_uc_toi = self.line_uc_and_toi()
+        if line_uc_toi is None:
+            return None
+
         toi_value: str = None
         if line_uc_toi is not None:
-            toi_value = self.__get_match_group(self.pattern_toi, line_uc_toi)
+            toi_value = self.__get_match_group(self.pattern_toi, line_uc_toi.value)
         if toi_value is not None:
             return toi_value.replace('TOI', '')
         arr = ArrayString(self.text_document.split(' '))
@@ -194,9 +201,8 @@ class TextRecognizedToi(object):
     def line_roteiro(self) -> DataString:
         return DataString(None)
 
-    #======================================================================#
-
 
+#======================================================================#
 # Texto reconhecido de uma imagem.
 #======================================================================#
 
@@ -269,6 +275,13 @@ class BinaryTesseract(object):
     disponível. Você pode usar um binário alternativo, basta informar
     o caminho do binário desejado no construtor.
     """
+    _instance = None  # Atributo de classe para armazenar a instância singleton
+
+    def __new__(cls, *args, **kwargs):
+        if cls._instance is None:
+            cls._instance = super(BinaryTesseract, cls).__new__(cls)
+        return cls._instance
+
     def __init__(
                     self,
                     path: File = None, *,
@@ -276,6 +289,11 @@ class BinaryTesseract(object):
                     tess_data_dir: Directory = None
             ):
         #
+        # Garante que __init__ não será executado mais de uma vez
+        if hasattr(self, '_initialized') and self._initialized:
+            return
+        self._initialized = True
+
         self.tess_data_dir: Directory = tess_data_dir
         self.lang: str = lang
         self.path_tesseract: File = path
@@ -291,9 +309,10 @@ class BinaryTesseract(object):
                     self.path_tesseract = File(output)
 
     def exists(self) -> bool:
+        """Verifica se o binário tesseract existe"""
         if self.path_tesseract is None:
             return False
-        return True
+        return self.path_tesseract.exists()
 
 
 #======================================================================#

{ocr_stream-1.3 → ocr_stream-1.4}/ocr_stream.egg-info/PKG-INFO

@@ -1,19 +1,32 @@
 Metadata-Version: 2.4
 Name: ocr_stream
-Version: 1.3
+Version: 1.4
 Summary: Extrair textos de documentos digitalizados e imagens.
 Author: Bruno Chaves
+Requires: PyPDF2
+Requires: PyMuPDF
+Requires: reportlab
+Requires: openpyxl
+Requires: openpyxl
+Requires: pandas
+Requires: Pillow
+Requires: opencv_python
+Requires: requests
+Requires: pytesseract
+Requires: soup_files
+Requires: convert_stream
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
-Requires-Dist: PyPDF2
 Requires-Dist: PyMuPDF
 Requires-Dist: reportlab
 Requires-Dist: openpyxl
 Requires-Dist: pandas
 Requires-Dist: Pillow>=11.3.0
+Requires-Dist: requests>=2.32.4
 Requires-Dist: opencv-python
-Requires-Dist: convert_stream
+Requires-Dist: convert_stream>=1.4
 Requires-Dist: soup_files
+Dynamic: requires
 
 # ocrlib
 

{ocr_stream-1.3 → ocr_stream-1.4}/ocr_stream.egg-info/SOURCES.txt

@@ -1,5 +1,6 @@
 README.md
 pyproject.toml
+setup.py
 ocr_stream/__init__.py
 ocr_stream/__main__.py
 ocr_stream/_version.py
@@ -8,6 +9,7 @@ ocr_stream/modules_ocr.py
 ocr_stream.egg-info/PKG-INFO
 ocr_stream.egg-info/SOURCES.txt
 ocr_stream.egg-info/dependency_links.txt
+ocr_stream.egg-info/not-zip-safe
 ocr_stream.egg-info/requires.txt
 ocr_stream.egg-info/top_level.txt
 ocr_stream/models/__init__.py

ocr_stream-1.4/ocr_stream.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

{ocr_stream-1.3 → ocr_stream-1.4}/ocr_stream.egg-info/requires.txt

@@ -1,9 +1,9 @@
-PyPDF2
 PyMuPDF
 reportlab
 openpyxl
 pandas
 Pillow>=11.3.0
+requests>=2.32.4
 opencv-python
-convert_stream
+convert_stream>=1.4
 soup_files

{ocr_stream-1.3 → ocr_stream-1.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ocr_stream"
-version = "1.3"
+version = "1.4"
 authors = [
   { name="Bruno Chaves"},
 ]
@@ -14,14 +14,14 @@ readme = "README.md"
 requires-python = ">=3.11"
 
 dependencies = [
-    "PyPDF2",
     "PyMuPDF",
     "reportlab",
     "openpyxl",
     "pandas",
     "Pillow>=11.3.0",
+    "requests>=2.32.4",
     "opencv-python",
-    "convert_stream",
+    "convert_stream>=1.4",
     "soup_files",
 ]
 

ocr_stream-1.4/setup.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+
+import os
+import sys
+
+try:
+	from setuptools import setup
+except Exception as e:
+	print(e)
+	sys.exit(1)
+
+file_setup = os.path.abspath(os.path.realpath(__file__))
+dir_of_project = os.path.dirname(file_setup)
+sys.path.insert(0, dir_of_project)
+
+
+DESCRIPTION = ''
+LONG_DESCRIPTION = ''
+
+setup(
+	name='ocrlib',
+	version='1.2',
+	description=DESCRIPTION,
+	long_description=LONG_DESCRIPTION,
+	license='MIT',
+	requires=[
+			'PyPDF2',
+			'PyMuPDF',
+			'reportlab',
+			'openpyxl',
+			'openpyxl',
+			'pandas',
+			'Pillow',
+			'opencv_python',
+			'requests',
+			'pytesseract',
+			'soup_files',
+			'convert_stream',
+	],
+	packages=['ocrlib', 'ocrlib.models', 'ocrlib.utils'],
+	zip_safe=False,
+)
+
+

ocr_stream-1.3/ocr_stream/_version.py

@@ -1,5 +0,0 @@
-#!/usr/bin/env python3
-#
-
-__version__ = '1.3'
-__modify_data__ = '2025-07-06'