def _split_word_at_space(word):
prev_ = WordType(id=word.id + '_l')
next_ = WordType(id=word.id + '_r')
xywh = xywh_from_points(word.get_Coords().points)
textequiv = word.get_TextEquiv()[0]
pos = textequiv.Unicode.index(" ")
fract = pos / len(textequiv.Unicode)
xywh_prev = xywh.copy()
xywh_prev.update({'w': xywh['w'] * fract})
prev_.set_Coords(CoordsType(points=points_from_xywh(xywh_prev)))
xywh_next = xywh.copy()
xywh_next.update({
'x': xywh['x'] + xywh['w'] * fract,
'w': xywh['w'] * (1 - fract)
})
next_.set_Coords(CoordsType(points=points_from_xywh(xywh_next)))
if word.get_language():
prev_.set_language(word.get_language())
next_.set_language(word.get_language())
if word.get_TextStyle():
prev_.set_TextStyle(word.get_TextStyle())
next_.set_TextStyle(word.get_TextStyle())
# Glyphs: irrelevant at this processing level
textequiv_prev = TextEquivType(Unicode=textequiv.Unicode[0:pos],
conf=textequiv.conf)
textequiv_next = TextEquivType(Unicode=textequiv.Unicode[pos + 1:],
conf=textequiv.conf)
prev_.set_TextEquiv([textequiv_prev])
next_.set_TextEquiv([textequiv_next])
return prev_, next_
def _split_word_at_glyph(word, glyph):
prev_ = WordType(id=word.id + '_l')
next_ = WordType(id=word.id + '_r')
xywh_glyph = xywh_from_points(glyph.get_Coords().points)
xywh_word = xywh_from_points(word.get_Coords().points)
xywh_prev = xywh_word.copy()
xywh_prev.update({'w': xywh_glyph['x'] - xywh_word['x']})
prev_.set_Coords(CoordsType(points=points_from_xywh(xywh_prev)))
xywh_next = xywh_word.copy()
xywh_next.update({
'x': xywh_glyph['x'] - xywh_glyph['w'],
'w': xywh_word['w'] - xywh_prev['w']
})
next_.set_Coords(CoordsType(points=points_from_xywh(xywh_next)))
if word.get_language():
prev_.set_language(word.get_language())
next_.set_language(word.get_language())
if word.get_TextStyle():
prev_.set_TextStyle(word.get_TextStyle())
next_.set_TextStyle(word.get_TextStyle())
glyphs = word.get_Glyph()
pos = glyphs.index(glyph)
prev_.set_Glyph(glyphs[0:pos])
next_.set_Glyph(glyphs[pos + 1:])
# TextEquiv: will be overwritten by page_update_higher_textequiv_levels
return prev_, next_
def process(self):
"""
Performs the line segmentation.
"""
with PyTessBaseAPI(
psm=PSM.SINGLE_LINE,
path=TESSDATA_PREFIX,
) as tessapi:
for (n, input_file) in enumerate(self.input_files):
pcgts = page_from_file(self.workspace.download_file(input_file))
image_url = pcgts.get_Page().imageFilename
for region in pcgts.get_Page().get_TextRegion():
for line in region.get_TextLine():
log.debug("Detecting words in line '%s'", line.id)
image = self.workspace.resolve_image_as_pil(image_url, polygon_from_points(line.get_Coords().points))
tessapi.SetImage(image)
offset = xywh_from_points(line.get_Coords().points)
for (word_no, component) in enumerate(tessapi.GetComponentImages(RIL.WORD, True)):
word_id = '%s_word%04d' % (line.id, word_no)
word_xywh = component[1]
word_xywh['x'] += offset['x']
word_xywh['y'] += offset['y']
line.add_Word(WordType(id=word_id, Coords=CoordsType(points_from_xywh(word_xywh))))
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(
ID=ID,
file_grp=self.output_file_grp,
local_filename='%s/%s' % (self.output_file_grp, ID),
mimetype=MIMETYPE_PAGE,
content=to_xml(pcgts).encode('utf-8'),
)
def process(self):
"""
Performs the line segmentation.
"""
with PyTessBaseAPI(path=TESSDATA_PREFIX) as tessapi:
for (n, input_file) in enumerate(self.input_files):
pcgts = page_from_file(
self.workspace.download_file(input_file))
image_url = pcgts.get_Page().imageFilename
for region in pcgts.get_Page().get_TextRegion():
log.debug("Detecting lines in %s with tesseract",
region.id)
image = self.workspace.resolve_image_as_pil(
image_url,
polygon_from_points(region.get_Coords().points))
tessapi.SetImage(image)
offset = xywh_from_points(region.get_Coords().points)
for (line_no, component) in enumerate(
tessapi.GetComponentImages(RIL.TEXTLINE, True)):
line_id = '%s_line%04d' % (region.id, line_no)
line_xywh = component[1]
line_xywh['x'] += offset['x']
line_xywh['y'] += offset['y']
line_points = points_from_xywh(line_xywh)
region.add_TextLine(
TextLineType(id=line_id,
Coords=CoordsType(line_points)))
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(
ID=ID,
file_grp=self.output_file_grp,
mimetype=MIMETYPE_PAGE,
local_filename='%s/%s' % (self.output_file_grp, ID),
content=to_xml(pcgts).encode('utf-8'),
)
def test_points_from_xywh(self):
self.assertEqual(
points_from_xywh({
'x': 100,
'y': 100,
'w': 100,
'h': 100
}), '100,100 200,100 200,200 100,200')
def process(self):
"""
Performs the cropping.
"""
with tesserocr.PyTessBaseAPI(path=TESSDATA_PREFIX) as tessapi:
# print(self.input_file_grp)
for (n, input_file) in enumerate(self.input_files):
# print(input_file)
pcgts = page_from_file(self.workspace.download_file(input_file))
image = self.workspace.resolve_image_as_pil(pcgts.get_Page().imageFilename)
log.debug("Cropping with tesseract")
tessapi.SetImage(image)
#
# helper variables for saving the box coordinates
#
min_x = image.width
min_y = image.height
max_x = 0
max_y = 0
# iterate over all boxes and compare their extent
# to the min and max values
for component in tessapi.GetComponentImages(tesserocr.RIL.BLOCK, True):
points, index = points_from_xywh(component[1]), component[2]
#
# the region reference in the reading order element
#
ID = "region%04d" % index
log.debug("Detected region '%s': %s", ID, points)
for pair in points.split(' '):
x, y = (int(pair.split(',')[0]), int(pair.split(',')[1]))
if x < min_x:
min_x = x
if y < min_y:
min_y = y
elif x > max_x:
max_x = x
elif y > max_y:
max_y = y
log.debug("Updated page border: %i,%i %i,%i %i,%i %i,%i" % (min_x, min_y, max_x, min_y, max_x, max_y, min_x, max_y))
#
# set the identified page border
#
brd = BorderType(Coords=CoordsType("%i,%i %i,%i %i,%i %i,%i" % (min_x, min_y, max_x, min_y, max_x, max_y, min_x, max_y)))
pcgts.get_Page().set_Border(brd)
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(
ID=ID,
file_grp=self.output_file_grp,
mimetype=MIMETYPE_PAGE,
local_filename='%s/%s' % (self.output_file_grp, ID),
content=to_xml(pcgts).encode('utf-8'),
)
def process(self):
"""
Performs the region segmentation.
"""
with tesserocr.PyTessBaseAPI(path=TESSDATA_PREFIX) as tessapi:
# print(self.input_file_grp)
for (n, input_file) in enumerate(self.input_files):
# print(input_file)
pcgts = page_from_file(self.workspace.download_file(input_file))
image = self.workspace.resolve_image_as_pil(pcgts.get_Page().imageFilename)
log.debug("Detecting regions with tesseract")
tessapi.SetImage(image)
for component in tessapi.GetComponentImages(tesserocr.RIL.BLOCK, True):
points, index = points_from_xywh(component[1]), component[2]
#
# the region reference in the reading order element
#
ID = "region%04d" % index
log.debug("Detected region '%s': %s", ID, points)
# <pg:ReadingOrder>
ro = pcgts.get_Page().get_ReadingOrder()
if ro is None:
ro = ReadingOrderType()
pcgts.get_Page().set_ReadingOrder(ro)
# <pg:OrderedGroup>
og = ro.get_OrderedGroup()
if og is None:
og = OrderedGroupType(id="reading-order")
ro.set_OrderedGroup(og)
# <pg:RegionRefIndexed>
og.add_RegionRefIndexed(RegionRefIndexedType(regionRef=ID, index=index))
#
# text region
#
pcgts.get_Page().add_TextRegion(TextRegionType(id=ID, Coords=CoordsType(points=points)))
ID = concat_padded(self.output_file_grp, n)
self.workspace.add_file(
ID=ID,
file_grp=self.output_file_grp,
mimetype=MIMETYPE_PAGE,
local_filename='%s/%s' % (self.output_file_grp, ID),
content=to_xml(pcgts).encode('utf-8'),
)
def _merge_words(prev_, next_):
merged = WordType(id=prev_.id + '.' + next_.id)
merged.set_Coords(
CoordsType(points=points_from_xywh(
xywh_from_points(prev_.get_Coords().points + ' ' +
next_.get_Coords().points))))
if prev_.get_language():
merged.set_language(prev_.get_language())
if prev_.get_TextStyle():
merged.set_TextStyle(prev_.get_TextStyle())
if prev_.get_Glyph() or next_.get_Glyph():
merged.set_Glyph(prev_.get_Glyph() + next_.get_Glyph())
if prev_.get_TextEquiv():
merged.set_TextEquiv(prev_.get_TextEquiv())
else:
merged.set_TextEquiv([TextEquivType(Unicode='', conf=1.0)])
if next_.get_TextEquiv():
textequiv = merged.get_TextEquiv()[0]
textequiv2 = next_.get_TextEquiv()[0]
textequiv.Unicode += textequiv2.Unicode
if textequiv.conf and textequiv2.conf:
textequiv.conf *= textequiv2.conf
return merged
