BatchalignHK 0.7.19.post24__tar.gz → 0.7.20.post1__tar.gz

{batchalignhk-0.7.19.post24 → batchalignhk-0.7.20.post1}/BatchalignHK.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.2
 Name: BatchalignHK
-Version: 0.7.19.post24
+Version: 0.7.20.post1
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -52,7 +52,6 @@ Dynamic: author-email
 Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
-Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: summary

{batchalignhk-0.7.19.post24 → batchalignhk-0.7.20.post1}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.2
 Name: BatchalignHK
-Version: 0.7.19.post24
+Version: 0.7.20.post1
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -52,7 +52,6 @@ Dynamic: author-email
 Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type
-Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: summary

{batchalignhk-0.7.19.post24 → batchalignhk-0.7.20.post1}/batchalign/pipelines/analysis/eval.py

@@ -60,6 +60,14 @@ def conform(x):
         elif "wanna" == i.strip():
             result.append("want")
             result.append("to")
+        elif "mba" == i.strip():
+            result.append("m")
+            result.append("b")
+            result.append("a")
+        elif "tli" == i.strip():
+            result.append("t")
+            result.append("l")
+            result.append("i")
         elif "bbc" == i.strip():
             result.append("b")
             result.append("b")

{batchalignhk-0.7.19.post24 → batchalignhk-0.7.20.post1}/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",

batchalignhk-0.7.20.post1/batchalign/version

@@ -0,0 +1,3 @@
+0.7.20-post.1
+July 21th, 2025
+Some benchmarking anonyms

batchalignhk-0.7.19.post24/batchalign/version

@@ -1,3 +0,0 @@
-0.7.19-post.24
-July 12nd, 2025
-compound word list bencmarking