Merge pull request #143 from stweil/fixes

Fix extra intra-word spacing in Chinese and Japanese (GitHub issue #991)
tesseract-ocr · May 21, 2019 · fe3769c · fe3769c
2 parents 1f2cb09 + 0309ca8
commit fe3769c
Show file tree

Hide file tree

Showing 6 changed files with 10 additions and 9 deletions.
diff --git a/chi_sim/chi_sim.config b/chi_sim/chi_sim.config
@@ -1,7 +1,5 @@
-#Fixes https://github.com/tesseract-ocr/tesseract/issues/991
-preserve_interword_spaces 1
-
 tessedit_load_sublangs chi_sim_vert
+
 # Important configurations for CJK mode
 
 # New Segmentation search params

diff --git a/chi_sim_vert/chi_sim_vert.config b/chi_sim_vert/chi_sim_vert.config
@@ -1,5 +1,8 @@
 # Important configurations for CJK mode
 
+# Fix https://github.com/tesseract-ocr/tesseract/issues/991
+preserve_interword_spaces 1
+
 # New Segmentation search params
 language_model_ngram_on             1
 segsearch_max_char_wh_ratio         1.3

diff --git a/chi_tra/chi_tra.config b/chi_tra/chi_tra.config
@@ -1,8 +1,5 @@
 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/chi_tra_vert/chi_tra_vert.config b/chi_tra_vert/chi_tra_vert.config
@@ -1,5 +1,8 @@
 # Important configurations for CJK mode
 
+# Fix https://github.com/tesseract-ocr/tesseract/issues/991
+preserve_interword_spaces 1
+
 # New Segmentation search params
 language_model_ngram_on             1
 segsearch_max_char_wh_ratio         1.3

diff --git a/jpn/jpn.config b/jpn/jpn.config
@@ -1,6 +1,3 @@
-#Fixes https://github.com/tesseract-ocr/tesseract/issues/988
-preserve_interword_spaces 1
-
 tessedit_load_sublangs jpn_vert
 # Important configurations for CJK mode
 

diff --git a/jpn_vert/jpn_vert.config b/jpn_vert/jpn_vert.config
@@ -1,5 +1,8 @@
 # Important configurations for CJK mode
 
+# Fix https://github.com/tesseract-ocr/tesseract/issues/991
+preserve_interword_spaces 1
+
 # New Segmentation search params
 language_model_ngram_on         1
 segsearch_max_char_wh_ratio     1.3