qurator-spk/ocrd_repair_inconsistencies
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd_repair_inconsistencies.git synced 2025-06-09 19:59:59 +02:00
Code Issues Releases Wiki Activity

✨ Fix line order in regions

Browse source
This commit is contained in:
Gerber, Mike 2019-11-22 16:50:55 +01:00
parent c7033a5d4d
commit 25437176d4
1 changed files with 16 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

16
ocrd_repair_inconsistencies/ocrd_repair_inconsistencies.py
View file

@ -42,6 +42,21 @@ class RepairInconsistencies(Processor):
kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL]
super(RepairInconsistencies, self).__init__(*args, **kwargs)
def _fix_lines(self, region):
"""Fix line order in a region"""
lines = region.get_TextLine()
region_text = get_text(region)
lines_text = get_text(lines, '\n')
if region_text != lines_text:
# XXX Assumes top-to-bottom
sorted_lines = sorted(lines, key=lambda l: Polygon(polygon_from_points(l.get_Coords().points)).centroid.y)
sorted_lines_text = get_text(sorted_lines, '\n')
if sorted_lines_text == region_text:
LOG.info('Fixing line order of region "%s"', region.id)
region.set_TextLine(sorted_lines)
def _fix_words(self, line):
"""Fix word order in a line"""
@ -82,6 +97,7 @@ class RepairInconsistencies(Processor):
regions = page.get_TextRegion()
for region in regions:
self._fix_lines(region)
lines = region.get_TextLine()
for line in lines: