ocr-stream 2.6__tar.gz → 2.6.1__tar.gz

{ocr_stream-2.6 → ocr_stream-2.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: ocr_stream
-Version: 2.6
+Version: 2.6.1
 Summary: Extrair textos de documentos digitalizados e imagens.
 Requires-Python: >=3.12
 Requires-Dist: convert-stream>=2.6

{ocr_stream-2.6 → ocr_stream-2.6.1}/ocr_stream/__init__.py

@@ -1,13 +1,14 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 """
-ocrlib depende de:
+ocr_stream depende de:
     table_stream
     pandas
-    convert_stream
     pytesseract
+    convert_stream
 """
 
+# stdlib/builtin.
 from __future__ import annotations
 import os
 from shutil import which
@@ -19,8 +20,8 @@ from enum import StrEnum
 import threading
 from contextlib import contextmanager
 
+# External libs.
 import pandas as pd
-
 from table_stream import (
     File,
     Directory,
@@ -60,15 +61,6 @@ from convert_stream import (
     MOD_CANVAS,
 )
 
-__version__ = "2.6"
-
-
-class FileTesseractNotFoundError(ValueError):
-
-    def __init__(self, *args: object) -> None:
-        super().__init__(*args)
-
-
 # ================================================================ #
 # Alias para variáveis e tipos de dados
 # ================================================================ #
@@ -99,6 +91,12 @@ if MOD_PYTESSERACT:
     from pytesseract import pytesseract, Output
 
 
+class FileTesseractNotFoundError(ValueError):
+
+    def __init__(self, *args: object) -> None:
+        super().__init__(*args)
+
+
 def _get_path_tesseract_unix() -> File | None:
     out = which("tesseract")
     if out is None:
@@ -340,10 +338,16 @@ class PyTesseractOcr(TesseractOcrAbstract):
 
     def __init__(self, bin_tess: BinTesseract):
         super().__init__(bin_tess)
-        self.modTess: pytesseract = pytesseract
+        if not MOD_PYTESSERACT:
+            pytesseract = "pytesseract"
+        self.mod_pytess: pytesseract = pytesseract
+
+        if self.bin_tess.exists() and MOD_PYTESSERACT:
+            self.mod_pytess.tesseract_cmd = self.bin_tess.get_tesseract().absolute()
 
-        if self.bin_tess.exists():
-            self.modTess.tesseract_cmd = self.bin_tess.get_tesseract().absolute()
+    def check_mod(self):
+        if not MOD_PYTESSERACT:
+            raise ModuleNotFoundError(f"Instale o pytesseract para prosseguir.")
 
     def _get_tess_dir_config(self) -> str:
         """
@@ -355,7 +359,7 @@ class PyTesseractOcr(TesseractOcrAbstract):
 
         It's important to add double quotes around the dir path.
         """
-
+        self.check_mod()
         # Caminho para os dados de idioma, por, eng etc...
         # os.environ["TESSDATA_PREFIX"] = self.tess_data_dir.absolute()
         if self.tess_data_dir is None:
@@ -365,34 +369,40 @@ class PyTesseractOcr(TesseractOcrAbstract):
         return r'--tessdata-dir "{}"'.format(self.tess_data_dir)
 
     def to_string(self, img: ImageElement) -> str:
+        self.check_mod()
+
         if not self.bin_tess.exists():
             raise FileTesseractNotFoundError("Instale o tesseract-ocr para prosseguir!")
 
         _im = img.to_opencv()
 
         if self.lang is None:
-            return self.modTess.image_to_string(_im, config=self._get_tess_dir_config())
+            return self.mod_pytess.image_to_string(
+                _im, config=self._get_tess_dir_config()
+            )
         else:
-            return self.modTess.image_to_string(
+            return self.mod_pytess.image_to_string(
                 _im, lang=self.lang, config=self._get_tess_dir_config()
             )
 
     def to_reconize(self, img: ImageElement) -> OcrBytesRecognized:
+        self.check_mod()
         if not self.bin_tess.exists():
             raise FileTesseractNotFoundError("Instale o tesseract-ocr para prosseguir!")
 
         _im = img.to_opencv()
 
-        bt = self.modTess.image_to_pdf_or_hocr(
+        bt = self.mod_pytess.image_to_pdf_or_hocr(
             _im, lang=self.lang, config=self._get_tess_dir_config()
         )
         return OcrBytesRecognized(bt)
 
     def recognize_file_image(self, f: File) -> textOcr:
+        self.check_mod()
         if not self.bin_tess.exists():
             raise FileTesseractNotFoundError("Instale o tesseract-ocr para prosseguir!")
 
-        txt = self.modTess.image_to_string(
+        txt = self.mod_pytess.image_to_string(
             f.absolute(), lang=self.lang, config=self._get_tess_dir_config()
         )
         return textOcr(txt)

{ocr_stream-2.6 → ocr_stream-2.6.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ocr_stream"
-version = "2.6"
+version = "2.6.1"
 
 description = "Extrair textos de documentos digitalizados e imagens."
 readme = "README.md"

{ocr_stream-2.6 → ocr_stream-2.6.1}/uv.lock

@@ -534,7 +534,7 @@ wheels = [
 
 [[package]]
 name = "ocr-stream"
-version = "2.6"
+version = "2.6.1"
 source = { editable = "." }
 dependencies = [
     { name = "convert-stream" },