mirror/OCRmyPDF
1
0
Fork 0
mirror of https://github.com/ocrmypdf/OCRmyPDF.git synced 2026-05-09 07:06:49 -04:00
Code Issues Packages Projects Releases Wiki Activity

Reversing character order for RTL helps output

Browse Source
This commit is contained in:
James R. Barlow
2023-12-24 01:24:44 -08:00
parent a0b98abb94
commit fd593eb5e9
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/ocrmypdf/hocrtransform/_hocr.py
View File

@@ -367,10 +367,15 @@ class HocrTransform:
self._debug_draw_word_bbox(canvas, box)
# If this word is 0 units wide, our best bet seems to be to suppress this text
if text_direction == TextDirection.RTL:
log.info("RTL: %s", elemtxt)
if font_width > 0:
text.text_transform(Matrix(1, 0, 0, -1, box.llx, 0))
text.horiz_scale(100 * box.width / font_width)
text.show(self._font.text_encode(elemtxt))
if text_direction == TextDirection.LTR:
text.show(self._font.text_encode(elemtxt))
elif text_direction == TextDirection.RTL:
text.show(self._font.text_encode(elemtxt[::-1]))
# Get coordinates of the next word (if there is one)
hocr_next_box = (