batchalign 0.7.3b10__tar.gz → 0.7.3b12__tar.gz

{batchalign-0.7.3b10/batchalign.egg-info → batchalign-0.7.3b12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.3b10
+Version: 0.7.3b12
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu

{batchalign-0.7.3b10 → batchalign-0.7.3b12}/batchalign/document.py

@@ -203,9 +203,9 @@ class Utterance(BaseModel):
         t = re.sub(r"^\+\.\.\.", "", t.strip()).strip()
         # this is here thrice to prevent stuff from not
         # matching once because .sub seems to only match once
-        t = re.sub(r"^[^\w\d\s<]+", "", t.strip()).strip()
-        t = re.sub(r"^[^\w\d\s<]+", "", t.strip()).strip()
-        t = re.sub(r"^[^\w\d\s<]+", "", t.strip()).strip()
+        # t = re.sub(r"^[^\w\d\s<]+", "", t.strip()).strip()
+        # t = re.sub(r"^[^\w\d\s<]+", "", t.strip()).strip()
+        # t = re.sub(r"^[^\w\d\s<]+", "", t.strip()).strip()
         t = re.sub(r",", " , ", t.strip()).strip()
         t = re.sub(r" +", " ", t.strip()).strip()
         return t

batchalign-0.7.3b12/batchalign/pipelines/morphosyntax/ja/verbforms.py

@@ -0,0 +1,34 @@
+"""
+verbforms.py
+Fix Japanese verb forms.
+"""
+
+def verbform(upos, target, text):
+    if text == "な" and upos == "part":
+        return "aux", "うな"
+    if text == "呼ん":
+        return upos, "呼ん"
+    if text == "たり":
+        return "aux", "たり"
+    if text == "たら":
+        return "sconj", "たら"
+    if text == "たっ":
+        return "sconj", "たって"
+    if text == "て" and upos == "sconj":
+        return "aux", "て"
+    if text == "なさい" and target == "為さる":
+        return "aux", "為さい"
+    if text == "な" and upos == "part":
+        return "aux", "な"
+    if text == "脱" and upos == "noun":
+        return "verb", "脱"
+    if text == "よう" and upos == "aux":
+        return "aux", "よう"
+    if text == "ろ" and upos == "aux" and target == "為る":
+        return "aux", "ろ"
+    if upos == "verb" and "る" in target:
+        return "verb", target.replace("る","").strip()
+
+    return upos,target
+
+

{batchalign-0.7.3b10 → batchalign-0.7.3b12}/batchalign/pipelines/morphosyntax/ud.py

@@ -134,7 +134,13 @@ def handler(word, lang=None):
     if "“" in target:
         target = word.text
 
-    return f"{'' if not unknown else '0'}{word.upos.lower()}|{target}"
+    pos = word.upos.lower()
+
+    if lang == "ja":
+        from batchalign.pipelines.morphosyntax.ja.verbforms import verbform
+        pos,target = verbform(pos,target,word.text)
+
+    return f"{'' if not unknown else '0'}{pos}|{target}"
 
 # POS specific handler
 def handler__PRON(word, lang=None):

batchalign-0.7.3b12/batchalign/version

@@ -0,0 +1,3 @@
+0.7.3-beta.12
+June 19th, 2024
+UD Fixes

{batchalign-0.7.3b10 → batchalign-0.7.3b12/batchalign.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.3b10
+Version: 0.7.3b12
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu

{batchalign-0.7.3b10 → batchalign-0.7.3b12}/batchalign.egg-info/SOURCES.txt

@@ -72,6 +72,7 @@ batchalign/pipelines/fa/whisper_fa.py
 batchalign/pipelines/morphosyntax/__init__.py
 batchalign/pipelines/morphosyntax/ud.py
 batchalign/pipelines/morphosyntax/fr/case.py
+batchalign/pipelines/morphosyntax/ja/verbforms.py
 batchalign/pipelines/speaker/__init__.py
 batchalign/pipelines/speaker/nemo_speaker.py
 batchalign/pipelines/utr/__init__.py

batchalign-0.7.3b10/batchalign/version

@@ -1,3 +0,0 @@
-0.7.3-beta.10
-June 17, 2024
-more fixes for charmap encoding