fix ca mark

batchalign/formats/chat/utils.py

@@ -140,7 +140,7 @@ def annotation_clean(content, special=False):
     cleaned_word = cleaned_word.replace("‡","").replace("ạ","")
     cleaned_word = cleaned_word.replace("ʰ","").replace("ā","")
     cleaned_word = cleaned_word.replace("ʔ","").replace("ʕ","")
-    cleaned_word = cleaned_word.replace("š","").replace("ˈ","")
+    cleaned_word = cleaned_word.replace("ˈ","")
     cleaned_word = cleaned_word.replace("ˌ","").replace("‹","")
     cleaned_word = cleaned_word.replace("›","").replace("〔","")
     cleaned_word = cleaned_word.replace("~","").replace("&~","")

batchalign/version

@@ -1,3 +1,3 @@
-0.7.9.post.2
+0.7.9.post.3
 Janurary 14th, 2025
-more align fixes
+fix croatian

scratchpad.py

@@ -154,33 +154,33 @@
 # # forms
 # utterance = Utterance(content=forms, delim=delim, text=ut)
 
-sec = "une famille die@s:deu vacances"
+# sec = "vidiš (š)to sam lepo@d našalala [: našarala] ."
 
-forms, delim = chat_parse_utterance(sec, None, None, None, None)
-utterance = Utterance(content=forms, delim=delim, text=sec)
-# utterance.punct
+# forms, delim = chat_parse_utterance(sec, None, None, None, None)
+# utterance = Utterance(content=forms, delim=delim, text=sec)
+
+# utterance[3].time=(1500,1600)
+# ut = Document(content=[utterance], langs=["eng"])
+
+# print(str(CHATFile(doc=ut)))
 
-utterance[0]
 
 # # # # # =======
 # ut = Document(content=[utterance], langs=["jpn"])
 
 # pipeline = BatchalignPipeline.new("morphosyntax", lang="jpn")
 # res = pipeline(ut, retokenize=True)
 
-# print(str(CHATFile(doc=res)))
 
 # >>>>>>> theirs
 
-utterance[3].time=(1500,1600)
-ut = Document(content=[utterance], langs=["eng"])
 
 # pipeline = BatchalignPipeline.new("morphosyntax", lang="jpn")
 # res = pipeline(ut, retokenize=True)
 # >>>>>>> Stashed changes
 
 # # print(str(CHA
-print(str(CHATFile(doc=ut)))
+# print(str(CHATFile(doc=ut)))
 # ut = Document(content=[utterance], langs=[lang])
 
 # pipeline = BatchalignPipeline.new("morphosyntax", lang=lang)