Add new app to handle all dependencies

Signed-off-by: Roberto Rosario <roberto.rosario.gonzalez@gmail.com>

mayan/apps/ocr/apps.py

@@ -19,6 +19,7 @@ from mayan.apps.documents.signals import post_version_upload
 from mayan.apps.navigation.classes import SourceColumn
 from mayan.celery import app
 
+from .dependencies import *  # NOQA
 from .handlers import (
     handler_index_document, handler_initialize_new_ocr_settings,
     handler_ocr_document_version,

mayan/apps/ocr/backends/tesseract.py

@@ -26,47 +26,11 @@ logger = logging.getLogger(__name__)
 
 class Tesseract(OCRBackendBase):
     def __init__(self, *args, **kwargs):
+        auto_initialize = kwargs.pop('auto_initialize', True)
         super(Tesseract, self).__init__(*args, **kwargs)
-        self.languages = ()
 
-        backend_arguments = yaml.load(
-            Loader=SafeLoader,
-            stream=setting_ocr_backend_arguments.value or '{}',
-        )
-
-        tesseract_binary_path = backend_arguments.get(
-            'tesseract_path', DEFAULT_TESSERACT_BINARY_PATH
-        )
-        self.command_timeout = backend_arguments.get(
-            'timeout', DEFAULT_TESSERACT_TIMEOUT
-        )
-
-        try:
-            self.command_tesseract = sh.Command(path=tesseract_binary_path)
-        except sh.CommandNotError:
-            self.command_tesseract = None
-            raise OCRError(
-                _('Tesseract not found.')
-            )
-        else:
-            # Get version
-            result = self.command_tesseract(v=True)
-            logger.debug('Tesseract version: %s', result.stdout)
-
-            # Get languages
-            result = self.command_tesseract(list_langs=True)
-            # Sample output format
-            # List of available languages (3):
-            # deu
-            # eng
-            # osd
-            # <- empty line
-
-            # Extaction: strip last line, split by newline, discard the first
-            # line
-            self.languages = force_text(result.stdout).strip().split('\n')[1:]
-
-            logger.debug('Available languages: %s', ', '.join(self.languages))
+        if auto_initialize:
+            self.initialize()
 
     def execute(self, *args, **kwargs):
         """
@@ -117,3 +81,49 @@ class Tesseract(OCRBackendBase):
                     return result
             finally:
                 temporary_image_file.close()
+
+    def initialize(self):
+        self.languages = ()
+
+        self.read_settings()
+
+        try:
+            self.command_tesseract = sh.Command(path=self.tesseract_binary_path)
+        except sh.CommandNotFound:
+            self.command_tesseract = None
+            raise OCRError(
+                _('Tesseract OCR not found.')
+            )
+        else:
+            # Get version
+            result = self.command_tesseract(v=True)
+            logger.debug('Tesseract version: %s', result.stdout)
+
+            # Get languages
+            result = self.command_tesseract(list_langs=True)
+            # Sample output format
+            # List of available languages (3):
+            # deu
+            # eng
+            # osd
+            # <- empty line
+
+            # Extaction: strip last line, split by newline, discard the first
+            # line
+            self.languages = force_text(result.stdout).strip().split('\n')[1:]
+
+            logger.debug('Available languages: %s', ', '.join(self.languages))
+
+    def read_settings(self):
+        backend_arguments = yaml.load(
+            Loader=SafeLoader,
+            stream=setting_ocr_backend_arguments.value or '{}',
+        )
+
+        self.tesseract_binary_path = backend_arguments.get(
+            'tesseract_path', DEFAULT_TESSERACT_BINARY_PATH
+        )
+
+        self.command_timeout = backend_arguments.get(
+            'timeout', DEFAULT_TESSERACT_TIMEOUT
+        )

mayan/apps/ocr/dependencies.py

@@ -0,0 +1,39 @@
+from __future__ import unicode_literals
+
+from django.utils.translation import ugettext_lazy as _
+
+from mayan.apps.dependencies.classes import BinaryDependency, PythonDependency
+
+from .backends.tesseract import Tesseract
+
+tesseract = Tesseract(auto_initialize=False)
+tesseract.read_settings()
+
+BinaryDependency(
+    copyright_text='''
+        The code in this repository is licensed under the Apache License, Version 2.0 (the "License");
+        you may not use this file except in compliance with the License.
+        You may obtain a copy of the License at
+
+           http://www.apache.org/licenses/LICENSE-2.0
+
+        Unless required by applicable law or agreed to in writing, software
+        distributed under the License is distributed on an "AS IS" BASIS,
+        WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+        See the License for the specific language governing permissions and
+        limitations under the License.
+    ''', help_text=_('Free Open Source OCR Engine'), label='Tesseract',
+    module=__name__, name='tesseract', path=tesseract.tesseract_binary_path
+)
+
+PythonDependency(
+    copyright_text='''
+        PyOCR is released under the GPL v3+.
+        Copyright belongs to the authors of each piece of code
+        (see the file AUTHORS for the contributors list, and
+        git blame to know which lines belong to which author).
+    ''', help_text=_(
+        'PyOCR is a Python library simplifying the use of OCR tools like '
+        'Tesseract or Cuneiform.'
+    ), module=__name__, name='pyocr', version_string='==0.6'
+)