PyPI - batchalign - Versions diffs - 0.7.1b9__tar.gz → 0.7.1b11__tar.gz - Mend

@@ -813,13 +813,13 @@ def morphoanalyze(doc: Document, retokenize:bool, status_hook:callable = None, *
                 chunks = list(enumerate(doc.content[indx].text.split(" ")))
                 # filter out everything that could not possibly align
                 chunks_align = [(i,j) for i,j in chunks
-                                if len(j) != 0 and (j[0] not in ["<", "[", "&", "\x15"])
-                                                   and (len(j) <= 2 or (j[-2] not in "@"))
+                                if len(j) != 0 and (j[0] not in ["<", "[", "&", "\x15"]) and (j[-1] not in ["]"])
+                                                   and ("@" not in j)
                                 and j.strip() not in ENDING_PUNCT + MOR_PUNCT + CHAT_IGNORE + ["++"]]
                 # hollow out anything we are trying to align, and leave everything else
                 chunks_backplate = [[j]
-                                    if not (len(j) != 0 and (j[0] not in ["<", "[", "&", "\x15"])
-                                    and (len(j) <= 2 or (j[-2] not in "@"))
+                                    if not (len(j) != 0 and (j[0] not in ["<", "[", "&", "\x15"]) and (j[-1] not in ["]"])
+                                    and ("@" not in j)
                                             and j.strip() not in ENDING_PUNCT + MOR_PUNCT + CHAT_IGNORE + ["++"])
                                     else
                                     []
@@ -848,7 +848,15 @@ def morphoanalyze(doc: Document, retokenize:bool, status_hook:callable = None, *
                                     for j in i]
                 retokenized_ut = " ".join(i for i in chunks_backplate if i.strip() not in ["(", ")"])
+                retokenized_ut = retokenized_ut.replace("^", "")
                 retokenized_ut = re.sub(r" +", " ", retokenized_ut)
+                retokenized_ut = retokenized_ut.replace("+ \"", "+\"")
+                retokenized_ut = retokenized_ut.replace(" >", ">")
+                retokenized_ut = retokenized_ut.replace("< ", "<")
+                retokenized_ut = retokenized_ut.replace(" :", ":")
+                retokenized_ut = retokenized_ut.replace(": <", ": <")
+                retokenized_ut = re.sub(r"@ ?w ?p", "@wp", retokenized_ut)
+                retokenized_ut = retokenized_ut.replace(" @", "@")
                 # pray to everyone that it works---this will simply crash and ignore
                 # the utterance if it didn't work, so we are doing this as a sanity
                 # check rather than needing the parsed result

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: batchalign
-Version: 0.7.1b9
+Version: 0.7.1b11
 Summary: Python Speech Language Sample Analysis
 Author: Brian MacWhinney, Houjun Liu
 Author-email: macw@cmu.edu, houjun@cmu.edu
@@ -82,7 +82,7 @@ The TalkBank Project, of which Batchalign is a part, is supported by NIH grant H
 ## Quick Start
-The following instructions is a quick start to install Batchalign.
+The following instructions is a quick start to install Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
 ### Get Python
 - We support Python versions 3.9, 3.10, and 3.11.

@@ -8,7 +8,7 @@ The TalkBank Project, of which Batchalign is a part, is supported by NIH grant H
 ## Quick Start
-The following instructions is a quick start to install Batchalign.
+The following instructions is a quick start to install Batchalign. For most users aiming to process CHAT and audio with Batchalign, we recommend more detailed usage instructions: for [usage](https://talkbank.org/info/BA2-usage.pdf) and [human transcript cleanup](https://talkbank.org/info/BA2-cleanup.pdf). The following provides a quick start guide for the program.
 ### Get Python
 - We support Python versions 3.9, 3.10, and 3.11.

@@ -193,9 +193,12 @@ class Utterance(BaseModel):
     def __str__(self):
         if self.text != None:
-            return self.text
+            t = self.text
         else:
-            return self._detokenize()
+            t = self._detokenize()
+        t = t.replace(". . .", "+...")
+        return t
     def __repr__(self):
         return str(self)

@@ -188,7 +188,7 @@ def process_generation(output, lang="eng", utterance_engine=None):
         final_utterances.append(Utterance(
             tier=participant,
-            content = words
+            content=words
         ))
     doc.content = final_utterances

@@ -0,0 +1,3 @@
+0.7.1-beta.11
+May 27th, 2024
+patch minor ud bugs

@@ -1,3 +0,0 @@
-0.7.1-beta.9
-May 21st, 2024
-minute %umor implementation changes

batchalign 0.7.1b9__tar.gz → 0.7.1b11__tar.gz

batchalign 0.7.1b9tar.gz → 0.7.1b11tar.gz