Merge pull request #1063 from PyThaiNLP/wannaphong/fix-newmm-safe

PyThaiNLP · Jan 11, 2025 · f56e7d9 · f56e7d9
2 parents 9a9d11f + aecdd66
commit f56e7d9
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/pythainlp/tokenize/newmm.py b/pythainlp/tokenize/newmm.py
@@ -182,7 +182,7 @@ def segment(
         # try to break by space first
         space_idx = sample.rfind(" ")
         if space_idx >= 0:
-            cut_pos = space_idx + 1
+            cut_pos = space_idx + 1 + _TEXT_SCAN_BEGIN
         else:
             tokens = list(_onecut(sample, custom_dict))
             token_max_idx = 0