Merge pull request #108 from Shreeshrii/patch-2

Fixes extra intra-word-spaces problem with 4.0
tesseract-ocr · Feb 21, 2018 · f1cb043 · f1cb043
2 parents e793460 + 342c09f
commit f1cb043
Showing 1 changed file with 4 additions and 1 deletion.
diff --git a/jpn/jpn.config b/jpn/jpn.config
@@ -1,3 +1,6 @@
+#Fixes https://github.com/tesseract-ocr/tesseract/issues/988
+preserve_interword_spaces 1
+
 tessedit_load_sublangs jpn_vert
 # Important configurations for CJK mode
 
@@ -42,7 +45,7 @@ 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