batchalign 0.7.9.post3__tar.gz → 0.7.10__tar.gz

{batchalign-0.7.9.post3/batchalign.egg-info → batchalign-0.7.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.9.post3
+Version: 0.7.10
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu

{batchalign-0.7.9.post3 → batchalign-0.7.10}/batchalign/formats/chat/generator.py

@@ -1,5 +1,6 @@
 from batchalign.document import *
 from batchalign.constants import *
+import numbers
 
 import warnings
 
@@ -104,6 +105,32 @@ def generate_chat_utterance(utterance: Utterance, special_mor=False, write_wor=T
 
     return "\n".join(result)
 
+def check_utterances_ordered(doc):
+    """check if the utterances are ordered such that one is aligned after another
+
+    Parameters
+    ----------
+        doc : Document
+                The CHAT document to check.
+
+    Returns
+    -------
+        bool
+                Whether the utterances timings are ordered or not.
+    """
+
+    n = -1
+    for i in doc.content:
+        if isinstance(i, Utterance) and i.alignment:
+            (start, end) = i.alignment
+            if isinstance(start, numbers.Number) != None and isinstance(end, numbers.Number) != None:
+                if end < start:
+                    return False
+                if start < n:
+                    return False
+                n = end
+    return True
+
 def generate_chat_preamble(doc, birthdays=[]):
     """Generate header for a Batchalign document.
 
@@ -124,7 +151,8 @@ def generate_chat_preamble(doc, birthdays=[]):
     header = []
     header.append("@Languages:\t"+", ".join(doc.langs))
     header.append("@Participants:\t"+", ".join([f"{i.id} {i.name}" for i in doc.tiers]))
-    # header.append("@Options:\tmulti")
+    if not check_utterances_ordered(doc):
+        header.append("@Options:\tbullets")
     header.append("\n".join([f"@ID:\t{i.lang}|{i.corpus}|{i.id}|{i.birthday}|{i.additional[0]}|{i.additional[1]}|{i.additional[2]}|{i.name}|{i.additional[3]}|{i.additional[4]}|" for i in doc.tiers]))
     for i in birthdays:
         header.append(f"@{i.id}:\t{i.content}")

{batchalign-0.7.9.post3 → batchalign-0.7.10}/batchalign/pipelines/utterance/ud_utterance.py

@@ -294,6 +294,8 @@ class StanzaUtteranceEngine(BatchalignEngine):
                 contents.append(i)
                 continue
             
+            if len(i.content) == 0:
+                continue
             new_uts = process_ut(i, nlp)
             contents += new_uts
 

batchalign-0.7.10/batchalign/version

@@ -0,0 +1,3 @@
+0.7.10
+Janurary 20th, 2025
+insert options multi automatically

{batchalign-0.7.9.post3 → batchalign-0.7.10/batchalign.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.9.post3
+Version: 0.7.10
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu

batchalign-0.7.9.post3/batchalign/version

@@ -1,3 +0,0 @@
-0.7.9.post.3
-Janurary 14th, 2025
-fix croatian