batchalign 0.7.19.post15__tar.gz → 0.7.20__tar.gz

{batchalign-0.7.19.post15/batchalign.egg-info → batchalign-0.7.20}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.2
 Name: batchalign
-Version: 0.7.19.post15
+Version: 0.7.20
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -47,7 +47,6 @@ Dynamic: author-email
 Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
-Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: summary

{batchalign-0.7.19.post15 → batchalign-0.7.20}/batchalign/pipelines/morphosyntax/ud.py

@@ -72,6 +72,8 @@ def handler(word, lang=None):
     # if the lemma is ", return the word
     # not sure what errors are coming along?
     target = word.lemma
+    if target.strip() == "」" or target.strip() == "「":
+        target = word.text
 
     if target == '"':
         target = word.text
@@ -885,7 +887,6 @@ def morphoanalyze(doc: Document, retokenize:bool, skipmultilang:bool, status_hoo
                 L.debug(f"Encountered an utterance that's likely devoid of morphological information; skipping... utterance='{doc.content[indx]}'")
                 continue
 
-
             if retokenize:
                 # rewrite the sentence with our desired tokenizations
                 ut, end = chat_parse_utterance(" ".join([i.text for i in sents[0].tokens])+" "+ending,
@@ -944,7 +945,7 @@ def morphoanalyze(doc: Document, retokenize:bool, skipmultilang:bool, status_hoo
                     # we want to replace the morphology of forms that are not actually
                     # supposed to be analyzed
                     elif isinstance(i, Extra) and i.extra_type == ExtraType.REFERENCE:
-                        if ut[i.payload].text != ",":
+                        if ut[i.payload].text not in MOR_PUNCT:
                             ut[i.payload].morphology = [Morphology(
                                 lemma = sents[0].tokens[i.payload].text if len(sents) > 0 and len(sents[0].tokens) > i.payload and sents[0].tokens[i.payload].text != "xbxxx" else ut[i.payload].text,
                                 pos = ut[i.payload].morphology[0].pos if (ut[i.payload].morphology and len(ut[i.payload].morphology) > 0) else "x",

batchalign-0.7.20/batchalign/version

@@ -0,0 +1,3 @@
+0.7.20
+July 17th, 2025
+UD Japanese Fixes

{batchalign-0.7.19.post15 → batchalign-0.7.20/batchalign.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.2
 Name: batchalign
-Version: 0.7.19.post15
+Version: 0.7.20
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -47,7 +47,6 @@ Dynamic: author-email
 Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
-Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: summary

batchalign-0.7.19.post15/batchalign/version

@@ -1,3 +0,0 @@
-0.7.19-post.15
-July 12nd, 2025
-compound word list bencmarking