def ocr_search(request, pk):
obj = get_screenshot(request, pk)
if not HAS_OCR:
return search_results(500, obj)
translation = obj.component.source_translation
# Load image
original_image = Image.open(obj.image.path)
# Convert to greyscale
original_image = original_image.convert("L")
# Resize image (tesseract works best around 300dpi)
scaled_image = original_image.copy().resize(
[size * 4 for size in original_image.size], Image.BICUBIC)
# Find all our strings
sources = dict(translation.unit_set.values_list("source", "pk"))
strings = tuple(sources.keys())
results = set()
# Extract and match strings
with c_locale(), PyTessBaseAPI() as api:
for image in (original_image, scaled_image):
for match in ocr_extract(api, image, strings):
results.add(sources[match])
# Close images
original_image.close()
scaled_image.close()
return search_results(200, obj,
translation.unit_set.filter(pk__in=results))
def ocr_search(request, pk):
obj = get_screenshot(request, pk)
if not HAS_OCR:
return search_results(500, obj)
try:
translation = obj.component.translation_set.all()[0]
except IndexError:
return search_results(500, obj)
# Load image
original_image = Image.open(obj.image.path)
# Convert to greyscale
original_image = original_image.convert("L")
# Resize image (tesseract works best around 300dpi)
scaled_image = original_image.copy().resize(
[size * 4 for size in original_image.size],
Image.BICUBIC
)
# Find all our strings
sources = dict(translation.unit_set.values_list('source', 'pk'))
strings = tuple(sources.keys())
results = set()
# Extract and match strings
with c_locale(), PyTessBaseAPI() as api:
for image in (original_image, scaled_image):
for match in ocr_extract(api, image, strings):
results.add(sources[match])
return search_results(
200,
obj,
translation.unit_set.filter(pk__in=results)
)
import difflib
from django.contrib.auth.decorators import login_required
from django.core.exceptions import PermissionDenied
from django.http import JsonResponse
from django.utils.translation import ugettext as _
from django.views.decorators.http import require_POST
from django.views.generic import ListView, DetailView
from django.shortcuts import get_object_or_404, redirect, render
from PIL import Image
from weblate.utils.locale import c_locale
try:
with c_locale():
from tesserocr import PyTessBaseAPI, RIL
HAS_OCR = True
except ImportError:
HAS_OCR = False
from weblate.screenshots.forms import ScreenshotForm
from weblate.screenshots.models import Screenshot
from weblate.trans.models import Source
from weblate.utils import messages
from weblate.utils.views import ComponentViewMixin
def try_add_source(request, obj):
if 'source' not in request.POST or not request.POST['source'].isdigit():
return False
from django.http import JsonResponse
from django.shortcuts import get_object_or_404, redirect, render
from django.utils.translation import ugettext as _
from django.views.decorators.http import require_POST
from django.views.generic import DetailView, ListView
from PIL import Image
from weblate.screenshots.forms import ScreenshotForm
from weblate.screenshots.models import Screenshot
from weblate.trans.models import Source
from weblate.utils import messages
from weblate.utils.locale import c_locale
from weblate.utils.views import ComponentViewMixin
try:
with c_locale():
from tesserocr import PyTessBaseAPI, RIL
HAS_OCR = True
except ImportError:
HAS_OCR = False
def try_add_source(request, obj):
if 'source' not in request.POST:
return False
try:
source = Source.objects.get(
pk=int(request.POST['source']),
component=obj.component
)
