Merge pull request tesseract-ocr#142 from stweil/fixes

Fix Chinese and Japanese langdata config
quasimzia · May 21, 2019 · 1f2cb09 · 1f2cb09
2 parents b82ffb4 + 9ff60ea
commit 1f2cb09
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git a/chi_tra/chi_tra.config b/chi_tra/chi_tra.config
@@ -1,4 +1,8 @@
 tessedit_load_sublangs chi_tra_vert
+
+# Fix https://github.com/tesseract-ocr/tesseract/issues/991
+preserve_interword_spaces 1
+
 # Important configurations for CJK mode
 
 # New Segmentation search params

diff --git a/jpn_vert/jpn_vert.config b/jpn_vert/jpn_vert.config
@@ -40,7 +40,7 @@ classify_integer_matcher_multiplier 10
 #classify_class_pruner_multiplier    15
 assume_fixed_pitch_char_segment     T
 chop_enable                         F
-tessedit_char_blacklist             �
+tessedit_char_blacklist             °
 segment_nonalphabetic_script        1
 allow_blob_division                 F