[ocrfeeder] Port to Python 3
- From: Joaquim Rocha <jrocha src gnome org>
- To: commits-list gnome org
- Cc:
- Subject: [ocrfeeder] Port to Python 3
- Date: Tue, 7 Jan 2020 23:30:32 +0000 (UTC)
commit 8615aff3966dbfe24ed45eed6d34dc9b4e6b4e90
Author: Joaquim Rocha <me joaquimrocha com>
Date: Wed Jan 8 00:17:27 2020 +0100
Port to Python 3
Python 3 has been around for a while now, and Python 2 is going away
in Debian soon, so a port was due.
These changes represent the port and were done by using lib2to3, with
a few manual editions to add more needed changes (like dropping the
attempt to encode a string), or dropping some unnecessary ones, e.g.
iterating through an object as returned by the dict's keys() method
is fine, but lib2to3 still creates a list for it.
Special thanks to Reuben (@reubot on GNOME Gitlab) for having done an
initial MR for the port, which made me want to move this foward (but
I am pushing a different commit as it needed many changes).
bin/ocrfeeder-cli.in | 3 +--
bin/ocrfeeder.in | 2 +-
configure.ac | 2 +-
src/ocrfeeder/feeder/documentGeneration.py | 20 ++++++++---------
src/ocrfeeder/feeder/imageManipulation.py | 4 +---
src/ocrfeeder/feeder/layoutAnalysis.py | 12 +++++-----
src/ocrfeeder/feeder/ocrEngines.py | 24 ++++++--------------
src/ocrfeeder/studio/boxesarea.py | 2 --
src/ocrfeeder/studio/dataHolder.py | 8 +++----
src/ocrfeeder/studio/pagesiconview.py | 2 --
src/ocrfeeder/studio/project.py | 8 +++----
src/ocrfeeder/studio/studioBuilder.py | 18 +++++++--------
src/ocrfeeder/studio/widgetModeler.py | 36 ++++++++++++++----------------
src/ocrfeeder/studio/widgetPresenter.py | 30 ++++++++++++-------------
src/ocrfeeder/util/asyncworker.py | 12 +++++-----
src/ocrfeeder/util/configuration.py | 14 +++++-------
src/ocrfeeder/util/constants.py.in | 2 --
src/ocrfeeder/util/graphics.py | 14 +++++-------
src/ocrfeeder/util/lib.py | 20 +++++------------
src/ocrfeeder/util/log.py | 4 +---
20 files changed, 94 insertions(+), 143 deletions(-)
---
diff --git a/bin/ocrfeeder-cli.in b/bin/ocrfeeder-cli.in
index 809dcfa..80e7f3b 100644
--- a/bin/ocrfeeder-cli.in
+++ b/bin/ocrfeeder-cli.in
@@ -1,5 +1,4 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
+#!/usr/bin/env python3
###########################################################################
# OCRFeeder - The complete OCR suite
diff --git a/bin/ocrfeeder.in b/bin/ocrfeeder.in
index f2e5386..6d9b585 100644
--- a/bin/ocrfeeder.in
+++ b/bin/ocrfeeder.in
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
###########################################################################
# OCRFeeder - The complete OCR suite
diff --git a/configure.ac b/configure.ac
index 8301c2a..d2714b5 100644
--- a/configure.ac
+++ b/configure.ac
@@ -25,7 +25,7 @@ AS_IF([test "x$enable_sandbox" = "xyes"], [
])
dnl == check for python ==
-AM_PATH_PYTHON(2.5)
+AM_PATH_PYTHON(3.5)
dnl == Python dependencies ==
AX_PYTHON_MODULE([enchant],[needed])
diff --git a/src/ocrfeeder/feeder/documentGeneration.py b/src/ocrfeeder/feeder/documentGeneration.py
index c08a8ab..e47d6d7 100644
--- a/src/ocrfeeder/feeder/documentGeneration.py
+++ b/src/ocrfeeder/feeder/documentGeneration.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
@@ -51,7 +49,7 @@ class DocumentGeneratorManager(object):
return self.GENERATORS.get(id)
def getFormats(self):
- return self.GENERATORS.keys()
+ return list(self.GENERATORS.keys())
class DocumentGenerator(object):
@@ -174,7 +172,7 @@ class HtmlGenerator(DocumentGenerator):
def save(self):
pages = []
- for i in xrange(len(self.bodies)):
+ for i in range(len(self.bodies)):
previous_page = ''
next_page = ''
if i != 0:
@@ -213,12 +211,12 @@ class HtmlGenerator(DocumentGenerator):
os.mkdir(images_folder)
if pages:
file = open(os.path.join(self.name, 'index.html'), 'w')
- file.write(pages[0].encode('utf-8'))
+ file.write(pages[0])
file.close()
if len(pages) > 1:
- for i in xrange(1, len(pages)):
+ for i in range(1, len(pages)):
file = open(os.path.join(self.name, 'page%s.html' % (i + 1)), 'w')
- file.write(pages[i].encode('utf-8'))
+ file.write(pages[i])
file.close()
if self.styles:
file = open(os.path.join(self.name, 'style.css'), 'w')
@@ -250,7 +248,7 @@ class OdtGenerator(DocumentGenerator):
def addText(self, data_box):
text = data_box.getText()
frame_style = Style(name='FrameStyle', family = 'graphic')
- debug('Angle: %s' % data_box.text_data.angle)
+ debug('Angle: %s', data_box.text_data.angle)
angle = data_box.text_data.angle
if angle:
frame_style = Style(name='FrameStyleRotated', family = 'graphic')
@@ -301,7 +299,7 @@ class OdtGenerator(DocumentGenerator):
try:
os.unlink(image)
except:
- debug('Error removing image: %s' % image)
+ debug('Error removing image: %s', image)
def __handlePageMaster(self, page_data):
layout_name = 'Page%s%s' % (page_data.width, page_data.height)
@@ -355,7 +353,7 @@ class OdtGenerator(DocumentGenerator):
class PlaintextGenerator(DocumentGenerator):
def __init__(self, name):
self.name = name
- self.text = u''
+ self.text = ''
def addText(self, newText):
self.text += newText
@@ -368,7 +366,7 @@ class PlaintextGenerator(DocumentGenerator):
# This will create a new file or **overwrite an existing file
f = open(self.name, "w")
try:
- f.write(self.text.encode('utf-8'))
+ f.write(self.text)
finally:
f.close() # Close the file
except IOError:
diff --git a/src/ocrfeeder/feeder/imageManipulation.py b/src/ocrfeeder/feeder/imageManipulation.py
index 9b08e32..c940380 100644
--- a/src/ocrfeeder/feeder/imageManipulation.py
+++ b/src/ocrfeeder/feeder/imageManipulation.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
@@ -42,7 +40,7 @@ class ImageProcessor:
self.black_n_white_image = self.original_image.convert('L')
if not self.window_size:
self.window_size = self.original_image.size[1] / 60.
- debug('Window Size: %s' % self.window_size)
+ debug('Window Size: %s', self.window_size)
except:
debug(sys.exc_info())
raise ImageManipulationError(error_message)
diff --git a/src/ocrfeeder/feeder/layoutAnalysis.py b/src/ocrfeeder/feeder/layoutAnalysis.py
index a2fc873..f63a1d4 100644
--- a/src/ocrfeeder/feeder/layoutAnalysis.py
+++ b/src/ocrfeeder/feeder/layoutAnalysis.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
@@ -22,7 +20,7 @@ from ocrfeeder.util.log import debug
from ocrfeeder.util import graphics, lib
from ocrfeeder.util.constants import OCRFEEDER_DEBUG, DTP
from ocrfeeder.studio.dataHolder import DataBox
-from imageManipulation import ImageProcessor
+from .imageManipulation import ImageProcessor
from PIL import Image
import re
import math
@@ -93,10 +91,10 @@ class Block:
self.extra_charge = NONE
def __getVerticalRange(self):
- return xrange(self.start_line, self.finish_line + 1)
+ return range(self.start_line, self.finish_line + 1)
def __getHorizontalRange(self):
- return xrange(self.first_one, self.last_one + 1)
+ return range(self.first_one, self.last_one + 1)
def __inVerticalRange(self, verticalRange):
begin = self.start_line
@@ -430,7 +428,7 @@ class ImageDeskewer(object):
if not hough_accumulator:
return 0
- max_voted = hough_accumulator.keys()[0]
+ max_voted = list(hough_accumulator.keys())[0]
for r_angle in hough_accumulator:
max_voted_value = hough_accumulator.get(max_voted)
if hough_accumulator[r_angle] > max_voted_value:
@@ -547,7 +545,7 @@ class LayoutAnalysis(object):
text = self.ocr_engine.read()
if self.clean_text:
text = self.__cleanText(text)
- return lib.ensureUnicode(text)
+ return text
def __cleanText(self, text):
clean_text = re.sub(r'(?<!-)-\n(?!\n)', r'', text)
diff --git a/src/ocrfeeder/feeder/ocrEngines.py b/src/ocrfeeder/feeder/ocrEngines.py
index 0bbf118..e0cab8c 100644
--- a/src/ocrfeeder/feeder/ocrEngines.py
+++ b/src/ocrfeeder/feeder/ocrEngines.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
@@ -80,7 +78,7 @@ class Engine:
if self.languages:
favorite_language = self.languages.get(self._favorite_language, '')
if not favorite_language:
- values = self.languages.values()
+ values = list(self.languages.values())
if values:
favorite_language = values[0]
parsed_arguments = parsed_arguments.replace(LANGUAGE_ARGUMENT,
@@ -89,15 +87,7 @@ class Engine:
else:
parsed_arguments = parsed_arguments.replace(LANGUAGE_ARGUMENT, '')
- text = os.popen(self.engine_path + ' ' + parsed_arguments).read()
- try:
- try:
- text = unicode(text, 'utf-8', 'replace')
- except UnicodeDecodeError:
- text = unicode(text, 'ascii', 'replace').encode('utf-8', 'replace')
- finally:
- os.unlink(self.image_path)
- return text
+ return os.popen(self.engine_path + ' ' + parsed_arguments).read()
def classify(self, reading_output, rules = []):
stripped_output = reading_output.strip()
@@ -192,7 +182,7 @@ class OcrEnginesManager:
return None
def replaceEngine(self, engine, new_engine):
- for i in xrange(len(self.ocr_engines)):
+ for i in range(len(self.ocr_engines)):
eng, path = self.ocr_engines[i]
if eng == engine:
new_path = self.engineToXml(new_engine, path)
@@ -250,11 +240,11 @@ class OcrEnginesManager:
try:
engine = Engine(**arguments)
- except TypeError, exception:
- debug('Error when unserializing engine: %s' % exception.message)
+ except TypeError as exception:
+ debug('Error when unserializing engine: %s', exception.message)
engine = None
- except WrongSettingsForEngine, we:
- debug("Cannot load engine at %s: %s" %( xml_file_name, str(we)))
+ except WrongSettingsForEngine as we:
+ debug("Cannot load engine at %s: %s", xml_file_name, str(we))
engine = None
else:
engine.temporary_folder = self.configuration_manager.TEMPORARY_FOLDER
diff --git a/src/ocrfeeder/studio/boxesarea.py b/src/ocrfeeder/studio/boxesarea.py
index 34d89fb..e6a000d 100644
--- a/src/ocrfeeder/studio/boxesarea.py
+++ b/src/ocrfeeder/studio/boxesarea.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009-2013 Joaquim Rocha <me joaquimrocha com>
diff --git a/src/ocrfeeder/studio/dataHolder.py b/src/ocrfeeder/studio/dataHolder.py
index b4931e4..2e6f6d9 100644
--- a/src/ocrfeeder/studio/dataHolder.py
+++ b/src/ocrfeeder/studio/dataHolder.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
@@ -72,7 +70,7 @@ class DataBox(GObject.GObject):
(GObject.TYPE_INT,))
}
- def __init__(self, x = 0, y = 0, width = 0, height = 0, image = None, type = TEXT_TYPE, text = u''):
+ def __init__(self, x = 0, y = 0, width = 0, height = 0, image = None, type = TEXT_TYPE, text = ''):
super(DataBox, self).__init__()
self.x = int(x)
self.y = int(y)
@@ -132,7 +130,7 @@ class DataBox(GObject.GObject):
self.text_data.weight = font_weight
def setText(self, text):
- self.text = lib.ensureUnicode(text)
+ self.text = text
def getText(self):
return self.text
@@ -233,7 +231,7 @@ class PageData:
return {'PageData': dictionary}
def getTextFromBoxes(self, data_boxes=None):
- text = u''
+ text = ''
if data_boxes is None:
data_boxes = self.data_boxes
number_of_boxes = len(data_boxes)
diff --git a/src/ocrfeeder/studio/pagesiconview.py b/src/ocrfeeder/studio/pagesiconview.py
index 8f2c278..39966bf 100644
--- a/src/ocrfeeder/studio/pagesiconview.py
+++ b/src/ocrfeeder/studio/pagesiconview.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009-2013 Joaquim Rocha <me joaquimrocha com>
diff --git a/src/ocrfeeder/studio/project.py b/src/ocrfeeder/studio/project.py
index edff930..4e4f54c 100644
--- a/src/ocrfeeder/studio/project.py
+++ b/src/ocrfeeder/studio/project.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
@@ -18,7 +16,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
###########################################################################
-from dataHolder import PageData, DataBox, TextData
+from .dataHolder import PageData, DataBox, TextData
from ocrfeeder.util.log import debug
from ocrfeeder.util.configuration import ConfigurationManager
from xml.dom import minidom
@@ -75,7 +73,7 @@ class ProjectSaver:
for element in item:
self.convertToXml(element, root_node)
else:
- text = unicode(str(item), 'utf-8')
+ text = str(item)
text_node = self.document.createTextNode(text)
root_node.appendChild(text_node)
return root_node
@@ -103,7 +101,7 @@ class ProjectSaver:
embedded_name = os.path.join(images_dir, embbeded_name)
shutil.copy(original_name, embedded_name)
zip.write(embedded_name)
- f = open(os.path.join(os.curdir, 'project.xml'), 'w')
+ f = open(os.path.join(os.curdir, 'project.xml'), 'wb')
f.write(xml_content)
f.close()
zip.write(os.path.join(os.curdir, 'project.xml'))
diff --git a/src/ocrfeeder/studio/studioBuilder.py b/src/ocrfeeder/studio/studioBuilder.py
index 43cb432..cbf4490 100644
--- a/src/ocrfeeder/studio/studioBuilder.py
+++ b/src/ocrfeeder/studio/studioBuilder.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009-2013 Joaquim Rocha
@@ -27,11 +25,11 @@ from ocrfeeder.util import lib
from ocrfeeder.util.constants import *
import sys
import os.path
-import urllib
-import widgetPresenter
-from widgetModeler import ImageReviewer_Controler
-from dataHolder import DataBox, TextData
-from pagesiconview import PagesIconView
+import urllib.request, urllib.parse, urllib.error
+from . import widgetPresenter
+from .widgetModeler import ImageReviewer_Controler
+from .dataHolder import DataBox, TextData
+from .pagesiconview import PagesIconView
from ocrfeeder.feeder.ocrEngines import Engine, OcrEnginesManager
from ocrfeeder.feeder.documentGeneration import DocumentGeneratorManager
from ocrfeeder.util.configuration import ConfigurationManager
@@ -188,7 +186,7 @@ class Studio:
dialog = widgetPresenter.QueuedEventsProgressDialog(self.main_window)
item_obtain = AsyncItem(lib.obtainScanners,(),
self.__obtainScannersFinishedCb,(dialog,))
- info_obtain = (_('Obtaining scanners'), _(u'Please wait…'))
+ info_obtain = (_('Obtaining scanners'), _('Please wait…'))
dialog.setItemsList([(info_obtain, item_obtain)])
dialog.run()
@@ -214,7 +212,7 @@ class Studio:
self.main_window)
item_scan = AsyncItem(lib.scan,(device,),
self.__scanFinishedCb,(dialog_scan,))
- info_scan = (_('Scanning'), _(u'Please wait…'))
+ info_scan = (_('Scanning'), _('Please wait…'))
dialog_scan.setItemsList([(info_scan, item_scan)])
dialog_scan.run()
else:
@@ -258,7 +256,7 @@ class Studio:
self.configuration_manager.TEMPORARY_FOLDER),
self.__loadPdfFinishedCb,
(dialog,))
- info = (_('Loading PDF'), _(u'Please wait…'))
+ info = (_('Loading PDF'), _('Please wait…'))
dialog.setItemsList([(info, item)])
dialog.run()
diff --git a/src/ocrfeeder/studio/widgetModeler.py b/src/ocrfeeder/studio/widgetModeler.py
index ced5efd..34592b3 100644
--- a/src/ocrfeeder/studio/widgetModeler.py
+++ b/src/ocrfeeder/studio/widgetModeler.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009-2013 Joaquim Rocha
@@ -18,12 +16,12 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
###########################################################################
-from boxesarea import BoxesArea
-from dataHolder import DataBox, PageData, TEXT_TYPE, IMAGE_TYPE
+from .boxesarea import BoxesArea
+from .dataHolder import DataBox, PageData, TEXT_TYPE, IMAGE_TYPE
from ocrfeeder.feeder.documentGeneration import OdtGenerator, HtmlGenerator, PlaintextGenerator, PdfGenerator
from ocrfeeder.feeder.imageManipulation import *
from ocrfeeder.feeder.layoutAnalysis import *
-from project import ProjectSaver, ProjectLoader
+from .project import ProjectSaver, ProjectLoader
from ocrfeeder.util import graphics, ALIGN_LEFT, ALIGN_RIGHT, ALIGN_CENTER, \
ALIGN_FILL, PAPER_SIZES
from ocrfeeder.util.lib import getNonExistingFileName, unpaperImage
@@ -31,7 +29,7 @@ from ocrfeeder.util.log import debug, warning
from ocrfeeder.util.configuration import ConfigurationManager
from ocrfeeder.util import constants
from ocrfeeder.util.asyncworker import AsyncItem
-from widgetPresenter import BoxEditor, PagesToExportDialog, FileDialog, \
+from .widgetPresenter import BoxEditor, PagesToExportDialog, FileDialog, \
PageSizeDialog, UnpaperDialog, \
QueuedEventsProgressDialog, SpellCheckerDialog
import gettext
@@ -120,7 +118,7 @@ class ImageReviewer(Gtk.Paned):
def removedBox(self, widget, box):
self.updateMainWindow()
- if not self.boxes_dict.has_key(box):
+ if box not in self.boxes_dict:
return False
del self.boxes_dict[box]
if self.editor.box == box:
@@ -246,7 +244,7 @@ class ImageReviewer(Gtk.Paned):
return
try:
self.image_pixbuf = GdkPixbuf.Pixbuf.new_from_file(self.path_to_image)
- except Exception, exception:
+ except Exception as exception:
debug(exception.message)
return
self.selectable_boxes_area.setBackgroundImage(self.path_to_image)
@@ -340,7 +338,7 @@ class ImageReviewer_Controler:
not self.configuration_manager.unpaper_images_after_addition:
for index in range(0, len(image_path_list)):
if not self.__addImage(image_path_list[index], index == 0):
- debug('Failed to load image "%s"' % image_path_list[index])
+ debug('Failed to load image "%s"', image_path_list[index])
return
dialog = QueuedEventsProgressDialog(self.main_window)
for index in range(0, item_list_length):
@@ -352,12 +350,12 @@ class ImageReviewer_Controler:
index == item_list_length - 1,
index == 0))
if item_list_length == 1:
- item_info = (_('Preparing image'), _(u'Please wait…'))
+ item_info = (_('Preparing image'), _('Please wait…'))
else:
item_info = (_('Preparing image %(current_index)s/%(total)s') % \
{'current_index': index + 1,
'total': item_list_length},
- _(u'Please wait…'))
+ _('Please wait…'))
item_list.append((item_info,item))
dialog.setItemsList(item_list)
dialog.run()
@@ -411,7 +409,7 @@ class ImageReviewer_Controler:
(reviewer.path_to_image,),
self.__deskewCurrentImageFinishedCb,
(dialog, reviewer))
- item_info = (_('Deskewing image'), _(u'Please wait…'))
+ item_info = (_('Deskewing image'), _('Please wait…'))
dialog.setItemsList([(item_info, item)])
dialog.run()
@@ -508,7 +506,7 @@ class ImageReviewer_Controler:
(page,),
self.__performRecognitionForPageFinishedCb,
(dialog, page, [page]))
- info = (_('Recognizing Page'), _(u'Please wait…'))
+ info = (_('Recognizing Page'), _('Please wait…'))
dialog.setItemsList([(info, item)])
dialog.run()
@@ -526,7 +524,7 @@ class ImageReviewer_Controler:
self.__performRecognitionForPageFinishedCb,
(dialog, page, pages))
info = (_('Recognizing Document'),
- _(u'Recognizing page %(page_number)s/%(total_pages)s. Please wait…') % {'page_number': i,
+ _('Recognizing page %(page_number)s/%(total_pages)s. Please wait…') % {'page_number': i,
'total_pages':
total})
items.append((info, item))
i += 1
@@ -742,7 +740,7 @@ class ImageReviewer_Controler:
page.setSize(size)
else:
current_reviewer.page.setSize(size)
- debug('Page size: %s' % size)
+ debug('Page size: %s', size)
page_size_dialog.destroy()
self.__updateStatusBar(current_reviewer)
@@ -950,7 +948,7 @@ class Editor:
if index == -1:
return
engine = self.ocr_engines[index][0]
- self.box_editor.setAvailableLanguages(engine.getLanguages().keys())
+ self.box_editor.setAvailableLanguages(list(engine.getLanguages().keys()))
def _onOCREngineChanged(self, combobox):
self._resetLanguages()
@@ -982,7 +980,7 @@ class Editor:
def performOcr(self, engine_name = None):
selected_engine_index = self.box_editor.getSelectedOcrEngine()
if engine_name:
- for i in xrange(len(self.ocr_engines)):
+ for i in range(len(self.ocr_engines)):
if self.ocr_engines[i][0].name == engine_name:
selected_engine_index = i
break
@@ -1000,7 +998,7 @@ class Editor:
def performClassification(self, engine_name = None):
selected_engine_index = self.box_editor.getSelectedOcrEngine()
if engine_name:
- for i in xrange(len(self.ocr_engines)):
+ for i in range(len(self.ocr_engines)):
if self.ocr_engines[i][0].name == engine_name:
selected_engine_index = i
break
@@ -1012,7 +1010,7 @@ class Editor:
def __pressedAngleDetectionButton(self, widget):
image = graphics.convertPixbufToImage(self.box_editor.getImage())
angle = graphics.getHorizontalAngleForText(image)
- debug('ANGLE: %s' % angle)
+ debug('ANGLE: %s', angle)
self.box_editor.setAngle(angle)
def saveDataBox(self):
diff --git a/src/ocrfeeder/studio/widgetPresenter.py b/src/ocrfeeder/studio/widgetPresenter.py
index 359af9e..9b74dcb 100644
--- a/src/ocrfeeder/studio/widgetPresenter.py
+++ b/src/ocrfeeder/studio/widgetPresenter.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009-2013 Joaquim Rocha <me joaquimrocha com>
@@ -19,7 +17,7 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
###########################################################################
-from dataHolder import DataBox, TEXT_TYPE, IMAGE_TYPE
+from .dataHolder import DataBox, TEXT_TYPE, IMAGE_TYPE
from ocrfeeder.util import lib, PAPER_SIZES
from ocrfeeder.util.configuration import ConfigurationManager
from ocrfeeder.util.asyncworker import AsyncWorker
@@ -35,7 +33,7 @@ import signal
import subprocess
import sys
import threading
-import Queue
+import queue
import time
_ = gettext.gettext
@@ -84,12 +82,12 @@ class MainWindow(Gtk.Window):
('Quit', Gtk.STOCK_QUIT, _('_Quit'), None, _('Exit the program'),
menu_items['exit']),
('OpenProject', Gtk.STOCK_OPEN, _('_Open'), None, _('Open project'),
menu_items['open_project']),
('SaveProject', Gtk.STOCK_SAVE, _('_Save'), None, _('Save project'),
menu_items['save_project']),
- ('SaveProjectAs', Gtk.STOCK_SAVE_AS, _(u'_Save As…'), '<control><shift>s',
_('Save project with a chosen name'), menu_items['save_project_as']),
+ ('SaveProjectAs', Gtk.STOCK_SAVE_AS, _('_Save As…'), '<control><shift>s',
_('Save project with a chosen name'), menu_items['save_project_as']),
('AddImage', Gtk.STOCK_ADD, _('_Add Image'), None, _('Add another image'),
menu_items['add_image']),
('AddFolder', Gtk.STOCK_ADD, _('Add _Folder'), None, _('Add all images in
a folder'), menu_items['add_folder']),
('AppendProject', Gtk.STOCK_ADD, _('Append Project'), None, _('Load a
project and append it to the current one'), menu_items['append_project']),
('ImportPDF', Gtk.STOCK_ADD, _('_Import PDF'), None, _('Import PDF'),
menu_items['import_pdf']),
- ('Export', None, _(u'_Export…'), '<control><shift>e', _('Export to a
chosen format'), menu_items['export_dialog']),
+ ('Export', None, _('_Export…'), '<control><shift>e', _('Export to a chosen
format'), menu_items['export_dialog']),
('Edit', None, _('_Edit')),
('EditPage', Gtk.STOCK_EDIT, _('_Edit Page'), None, _('Edit page
settings'), menu_items['edit_page']),
('Preferences', Gtk.STOCK_PREFERENCES, _('_Preferences'), None,
_('Configure the application'), menu_items['preferences']),
@@ -279,7 +277,7 @@ class LanguagesComboBox(Gtk.ComboBox):
model = self.get_model()
if model.get_n_columns() != 3:
return
- cached_languages = self._cached_iters.keys()
+ cached_languages = list(self._cached_iters.keys())
languages_to_unset = [lang for lang in cached_languages
if lang not in languages]
for lang in languages:
@@ -841,9 +839,9 @@ class PageSizeDialog(Gtk.Dialog):
page_size_frame = PlainFrame(_('Page size'))
size_box = Gtk.VBox(spacing = 12)
self.paper_sizes = Gtk.ComboBoxText.new()
- papers = PAPER_SIZES.keys()
+ papers = list(PAPER_SIZES.keys())
papers.sort()
- self.paper_sizes.append_text(_(u'Custom…'))
+ self.paper_sizes.append_text(_('Custom…'))
for paper in papers:
self.paper_sizes.append_text(paper)
active_index = self.__checkIfSizeIsStandard(page_size)
@@ -900,7 +898,7 @@ class PageSizeDialog(Gtk.Dialog):
def __checkIfSizeIsStandard(self, page_size):
width, height = page_size
i = 1
- names = PAPER_SIZES.keys()
+ names = list(PAPER_SIZES.keys())
names.sort()
for name in names:
size = PAPER_SIZES[name]
@@ -975,7 +973,7 @@ class UnpaperDialog(Gtk.Dialog):
if os.path.exists(unpapered_image):
unpapered_image = lib.getNonExistingFileName(unpapered_image)
command += ' %s %s' % (name, unpapered_image)
- progress_bar = CommandProgressBarDialog(self, command, _('Performing Unpaper'), _(u'Performing
unpaper. Please wait…'))
+ progress_bar = CommandProgressBarDialog(self, command, _('Performing Unpaper'), _('Performing
unpaper. Please wait…'))
progress_bar.run()
self.unpapered_image = unpapered_image
@@ -985,7 +983,7 @@ class UnpaperDialog(Gtk.Dialog):
return
try:
thumbnail_image = Image.open(image_path)
- except Exception, exception:
+ except Exception as exception:
debug(exception.message)
return
thumbnail_image.thumbnail((150, 200), Image.ANTIALIAS)
@@ -1369,7 +1367,7 @@ class PreferencesDialog(Gtk.Dialog):
self.unpaper_images.get_active()
index = self.engines_combo.get_active()
if index != -1:
- debug('ACTIVE INDEX: %s %s' % (index, self.ocr_engines[index][0].name))
+ debug('ACTIVE INDEX: %s %s', index, self.ocr_engines[index][0].name)
self.configuration_manager.setFavoriteEngine(self.ocr_engines[index][0].name)
def __makeGeneralPreferences(self, *args):
@@ -1985,7 +1983,7 @@ class OcrSettingsDialog(Gtk.Dialog):
return True
except:
SimpleDialog(self, _('Error setting the new engine; please check your engine settings.'),
_('Warning'), 'warning').run()
- print sys.exc_info()
+ print(sys.exc_info())
return False
def __packSettingInFrame(self, box, size_group, entry_name, entry,
@@ -2094,7 +2092,7 @@ class SpellCheckerDialog():
self._numchars = 40
if self.text:
- self._checker.set_text(self.text.decode('utf-8'))
+ self._checker.set_text(self.text)
try:
self.__next()
except AttributeError:
@@ -2154,7 +2152,7 @@ class SpellCheckerDialog():
self.suggestions_list.clear()
try:
- self._checker.next()
+ next(self._checker)
except StopIteration:
self.__set_no_more()
return False
diff --git a/src/ocrfeeder/util/asyncworker.py b/src/ocrfeeder/util/asyncworker.py
index c42b1e2..9707ee6 100644
--- a/src/ocrfeeder/util/asyncworker.py
+++ b/src/ocrfeeder/util/asyncworker.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder
# Copyright (C) 2010 Igalia, S.L.
@@ -23,9 +21,9 @@
###########################################################################
from threading import Thread
-import Queue
+import queue
from gi.repository import GLib
-from log import debug
+from .log import debug
class AsyncItem(object):
@@ -42,7 +40,7 @@ class AsyncItem(object):
results = error = None
try:
results = self.target_method(*self.target_method_args)
- except Exception, exception:
+ except Exception as exception:
debug(str(exception))
error = exception
if self.canceled or not self.finish_callback:
@@ -58,7 +56,7 @@ class AsyncWorker(Thread):
def __init__(self):
Thread.__init__(self)
- self.queue = Queue.Queue(0)
+ self.queue = queue.Queue(0)
self.stopped = False
self.async_item = None
self.item_number = -1
@@ -74,7 +72,7 @@ class AsyncWorker(Thread):
self.async_item.run()
self.queue.task_done()
self.async_item = None
- except Exception, exception:
+ except Exception as exception:
debug(str(exception))
self.stop()
diff --git a/src/ocrfeeder/util/configuration.py b/src/ocrfeeder/util/configuration.py
index 26c33e5..1eec7f5 100644
--- a/src/ocrfeeder/util/configuration.py
+++ b/src/ocrfeeder/util/configuration.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
@@ -192,7 +190,7 @@ class ConfigurationManager(object):
color_list = [value.strip('()\ ') for value in color.split(',')]
try:
int_color_list = [int(value) for value in color_list]
- except ValueError, exception:
+ except ValueError as exception:
return None
return tuple(int_color_list)
@@ -381,13 +379,13 @@ class ConfigurationManager(object):
configuration_file = os.path.join(self.user_configuration_folder, 'preferences.xml')
doc = minidom.Document()
root_node = doc.createElement('ocrfeeder')
- for key, value in ConfigurationManager.conf.items():
+ for key, value in list(ConfigurationManager.conf.items()):
new_node = doc.createElement(key)
new_node.appendChild(doc.createTextNode(str(value)))
root_node.appendChild(new_node)
configuration = doc.toxml(encoding = 'utf-8')
- configuration += '\n' + root_node.toxml(encoding = 'utf-8')
- new_configuration_file = open(configuration_file, 'w')
+ configuration += b'\n' + root_node.toxml(encoding = 'utf-8')
+ new_configuration_file = open(configuration_file, 'wb')
new_configuration_file.write(configuration)
new_configuration_file.close()
@@ -404,8 +402,8 @@ class ConfigurationManager(object):
not os.path.exists(self.user_configuration_folder):
shutil.copytree(old_config_folder, self.user_configuration_folder)
debug('Migrated old configuration directory "%s" to the '
- 'new one: "%s"' %
- (old_config_folder, self.user_configuration_folder))
+ 'new one: "%s"',
+ old_config_folder, self.user_configuration_folder)
text_fill = property(getTextFill,
setTextFill)
diff --git a/src/ocrfeeder/util/constants.py.in b/src/ocrfeeder/util/constants.py.in
index 4219024..ae4ae65 100644
--- a/src/ocrfeeder/util/constants.py.in
+++ b/src/ocrfeeder/util/constants.py.in
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009 Joaquim Rocha
diff --git a/src/ocrfeeder/util/graphics.py b/src/ocrfeeder/util/graphics.py
index 1fc27f2..851cfe3 100644
--- a/src/ocrfeeder/util/graphics.py
+++ b/src/ocrfeeder/util/graphics.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2009-2013 Joaquim Rocha <me joaquimrocha com>
@@ -19,8 +17,8 @@
# along with this program. If not, see <http://www.gnu.org/licenses/>.
###########################################################################
-from lib import getNonExistingFileName
-from log import debug
+from .lib import getNonExistingFileName
+from .log import debug
from PIL import Image
from gi.repository import GdkPixbuf
import math
@@ -69,7 +67,7 @@ def convertPixbufToImage(pixbuf):
# creating the Image from bytes.
if pixbuf.get_byte_length() > num_channels * dimensions[0] * dimensions[1]:
i = 0
- p = ''
+ p = b''
for j in range(pixbuf.get_height()):
p += pixels[i:i + pixbuf.get_width() * num_channels]
i += pixbuf.get_rowstride()
@@ -112,7 +110,7 @@ def getTextSizeFromImage(image):
colors.sort()
background_color = colors[-1][1]
text_sizes = []
- for i in xrange(1, height):
+ for i in range(1, height):
blank_line = True
for j in range(0, width, 3):
color = image.getpixel((j, i - 1))
@@ -137,7 +135,7 @@ def getTextSizeFromImage(image):
text_size = math.floor(i)
break
text_size = max(text_sizes)
- debug('Text Size: %s' % text_size)
+ debug('Text Size: %s', text_size)
return text_size
def getTextBeginHeight(image):
@@ -200,7 +198,7 @@ def convertMultiImage(image_path, temp_dir):
extension)
image_name = getNonExistingFileName(file_name)
image.save(image_name, format='TIFF')
- debug('Saved %s' % image_name)
+ debug('Saved %s', image_name)
converted_paths.append(image_name)
i += 1
except EOFError:
diff --git a/src/ocrfeeder/util/lib.py b/src/ocrfeeder/util/lib.py
index c552d5a..f3f72b4 100644
--- a/src/ocrfeeder/util/lib.py
+++ b/src/ocrfeeder/util/lib.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2013 Joaquim Rocha <me joaquimrocha com>
@@ -25,12 +23,12 @@ from PIL import Image
import tempfile
from gi.repository import Gtk
import math
-from constants import *
+from .constants import *
import sane
import tempfile
import locale
import xml.etree.ElementTree as etree
-from log import debug
+from .log import debug
def getIconOrLabel(icon_name, label_text, icon_size = Gtk.IconSize.SMALL_TOOLBAR):
icon = Gtk.Image()
@@ -46,7 +44,7 @@ def getIconOrLabel(icon_name, label_text, icon_size = Gtk.IconSize.SMALL_TOOLBAR
def convertPdfToImages(pdf_file, temp_dir = '/tmp'):
dir_name = tempfile.mkdtemp(dir = temp_dir)
- debug('Converting PDF: %s to image' % pdf_file)
+ debug('Converting PDF: %s to image', pdf_file)
resolution = 300
file_name = os.path.splitext(os.path.basename(pdf_file))[0]
command = 'gs -SDEVICE=jpeg -r%(resolution)sx%(resolution)s -sPAPERSIZE=letter ' \
@@ -144,7 +142,7 @@ def unpaperImage(configuration_manager, image_path):
debug(command)
try:
os.system(command)
- except Exception, exception:
+ except Exception as exception:
debug(exception)
return None
finally:
@@ -156,7 +154,7 @@ def obtainScanners():
try:
devices = sane.get_devices()
return devices
- except (RuntimeError, sane._sane.error), msgerr:
+ except (RuntimeError, sane._sane.error) as msgerr:
return None
def scan(device):
@@ -169,7 +167,7 @@ def scan(device):
result.save(filename, 'PNG')
scandev.close()
return filename
- except (RuntimeError, sane._sane.error), msgerr:
+ except (RuntimeError, sane._sane.error) as msgerr:
return None
languages = {}
@@ -191,9 +189,3 @@ def makeRadioButton(label, from_widget=None):
button.set_use_underline(True)
return button
-
-def ensureUnicode(text):
- if isinstance(text, unicode):
- return text
-
- return unicode(text, 'utf-8')
diff --git a/src/ocrfeeder/util/log.py b/src/ocrfeeder/util/log.py
index f688a52..e07861c 100644
--- a/src/ocrfeeder/util/log.py
+++ b/src/ocrfeeder/util/log.py
@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
###########################################################################
# OCRFeeder - The complete OCR suite
# Copyright (C) 2013 Joaquim Rocha <me joaquimrocha com>
@@ -20,7 +18,7 @@
###########################################################################
import logging
-from constants import OCRFEEDER_COMPACT_NAME, OCRFEEDER_DEBUG
+from .constants import OCRFEEDER_COMPACT_NAME, OCRFEEDER_DEBUG
logger = logging.getLogger(OCRFEEDER_COMPACT_NAME)
LOG_FORMAT = "%(asctime)-15s %(levelname)s: %(message)s"
[
Date Prev][
Date Next] [
Thread Prev][
Thread Next]
[
Thread Index]
[
Date Index]
[
Author Index]
