From 9c7e84ecc18d63e7246e953ed5da53e7a199b28e Mon Sep 17 00:00:00 2001
From: Houjun Liu <houjun@jemoka.com>
Date: Wed, 17 Jan 2024 18:53:31 -0800
Subject: [PATCH] more patches

---
 batchalign/formats/chat/parser.py |  1 +
 batchalign/version                |  2 +-
 scratchpad.py                     | 15 ++++++++-------
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/batchalign/formats/chat/parser.py b/batchalign/formats/chat/parser.py
index acda930..104ba7c 100644
--- a/batchalign/formats/chat/parser.py
+++ b/batchalign/formats/chat/parser.py
@@ -131,6 +131,7 @@ def chat_parse_utterance(text, mor, gra, wor, additional):
     if (len(phonated_words) > 0 and
         phonated_words[-1][1][1] == TokenType.PUNCT and # because we don't track last ending PUNCT
         (len(phonated_words)-1 != len(wor))) and (len(phonated_words) != len(wor)):
+        breakpoint()
         raise CHATValidationException(f"Lengths of main and wor tiers are unaligned: lens main (filtered for phonation)={len(phonated_words)} wor={len(wor)}; line: '{text}'")
 
     # insert morphology into the parsed forms
diff --git a/batchalign/version b/batchalign/version
index 290543c..69889a4 100644
--- a/batchalign/version
+++ b/batchalign/version
@@ -1,3 +1,3 @@
-0.4.0-alpha.19.post2
+0.4.0-alpha.21
 Jan 17th, 2024
 Fix some multilingual tagging issues
\ No newline at end of file
diff --git a/scratchpad.py b/scratchpad.py
index 1d8caf4..c90cb5c 100644
--- a/scratchpad.py
+++ b/scratchpad.py
@@ -83,6 +83,7 @@
 #         raise e
 
 
+
 # pipeline = BatchalignPipeline.new("fa", lang="eng", num_speakers=len(doc.tiers))
 # doc = pipeline(doc)
 
@@ -125,16 +126,16 @@
 
 ########## The Batchalign CHAT Test Tarness ##########
 
-# from batchalign.formats.chat.parser import chat_parse_utterance
-# from batchalign.formats.chat.lexer import lex
+from batchalign.formats.chat.parser import chat_parse_utterance
+from batchalign.formats.chat.lexer import lex
 
-# from batchalign.formats.chat.utils import annotation_clean
+from batchalign.formats.chat.utils import annotation_clean
 
-# main = "+< <太 高 了> [/] 太 高 了 . •125000_126823•"
-# mor = None
-# gra = None
+main = "<and &+f> [//] <and the boy was &+kr> [//] and the boy heard a crying sound so he look back and said ."
+mor = None
+gra = None
 
-# chat_parse_utterance(main, mor, gra, None, None)
+chat_parse_utterance(main, mor, gra, None, None)