skrutable 2.0.0__tar.gz → 2.0.2__tar.gz

skrutable-2.0.2/PKG-INFO

@@ -0,0 +1,32 @@
+Metadata-Version: 2.1
+Name: skrutable
+Version: 2.0.2
+Summary: skrutable library for working with Sanskrit text
+Home-page: https://github.com/tylergneill/skrutable
+Author: Tyler Neill
+Author-email: tyler.g.neill@gmail.com
+License: CC BY-SA 4.0
+Keywords: Sanskrit text transliteration scansion meter identification sandhi compound splitting
+Description-Content-Type: text/markdown
+Provides-Extra: testing
+License-File: LICENSE.md
+
+# skrutable
+
+A toolkit and online workbench providing 
+transliteration, scansion, and meter identification for Sanskrit text,
+as well access to powerful sandhi and compound splitting.
+
+Web-app interface live online at [skrutable.info](https://www.skrutable.info).
+
+Install package from [PyPi](https://pypi.org/project/skrutable/) with `pip install skrutable`.
+
+See [manual.md](https://github.com/tylergneill/skrutable/blob/main/src/skrutable/manual.md) for instructions.
+
+Feedback welcome!
+My name is Tyler 
+([Academia](https://uni-leipzig1.academia.edu/TylerNeill),
+[LinkedIn](https://www.linkedin.com/in/tyler-g-neill/))
+and my Gmail is tyler.g.neill. 
+
+And please share and share-alike! Licensed under a [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-sa/4.0/).

skrutable-2.0.2/src/skrutable/__init__.py

@@ -0,0 +1 @@
+__version__ = "2.0.2"

{skrutable-2.0.0 → skrutable-2.0.2}/src/skrutable/splitting.py

@@ -102,7 +102,12 @@ class Splitter(object):
             sentence_results.append(new_sentence)
         return sentence_results
 
-    def _get_dharmamitra_split(self, text_input, preserve_compound_hyphens=True) -> List[str]:
+    def _get_dharmamitra_split(
+            self,
+            text_input: str,
+            preserve_compound_hyphens: bool=True,
+            batch_size: int=2000
+        ) -> List[str]:
         # TODO: change to "unsandhied-morphosyntax" when it works
         mode = "unsandhied-lemma-morphosyntax" if preserve_compound_hyphens else "unsandhied"
         """
@@ -117,31 +122,31 @@ class Splitter(object):
         headers = {
             'Content-Type': 'application/json',
         }
-        data = {
-            "input_sentence": text_input,
-            "mode": mode,
-            "input_encoding": "auto",
-            "human_readable_tags": False,
-        }
-
-        response = requests.post(url, headers=headers, json=data)
 
-        if response.status_code != 200:
-            response.raise_for_status()
-
-        return self._parse_dharmamitra_result(response.json(), mode)
+        sentences = text_input.split('\n')
+        results = []
+        for i in range(0, len(sentences), batch_size):
+            sentence_batch = sentences[i:i + batch_size]
+            batch_text_input = '\n'.join(sentence_batch)
+            data = {
+                "input_sentence": batch_text_input,
+                "mode": mode,
+                "input_encoding": "auto",
+                "human_readable_tags": False,
+            }
+            response = requests.post(url, headers=headers, json=data)
+            if response.status_code != 200:
+                response.raise_for_status()
+            batch_result = self._parse_dharmamitra_result(response.json(), mode)
+            results.extend(batch_result)
+
+        return results
 
     def _post_string_2018(self, input_text: str, url: str=SPLITTER_SERVER_URL):
         json_payload = {'input_text': input_text}
         result = requests.post(url, json=json_payload)
         return result.text
 
-    def _post_file_2018(self, input_file_path: str, url: str=SPLITTER_SERVER_URL):
-        input_file = open(input_file_path, 'rb')
-        file_payload = {"input_file": input_file}
-        result = requests.post(url, files=file_payload)
-        return result.text
-
     def _clean_up_2018(self, split_sentences_str: str, split_appearance: str=' ') -> List[str]:
         for (r_1, r_2) in [
             ('-\n', '\n'), # remove line-final hyphens
@@ -176,7 +181,6 @@ class Splitter(object):
             splitter_model: str='dharmamitra_2024_sept',
             preserve_compound_hyphens: bool = PRESERVE_COMPOUND_HYPHENS_DEFAULT,
             preserve_punctuation: bool=PRESERVE_PUNCTUATION_DEFAULT,
-            whole_file: bool=False,
     ) -> str:
         """
         Splits sandhi and compounds of multi-line Sanskrit string,
@@ -213,16 +217,7 @@ class Splitter(object):
 
         elif splitter_model == 'splitter_2018':
 
-            split_sentences_str: str
-
-            if whole_file:
-                # write prepared string to Splitter input buffer and send as binary
-                with open(SPLITTER_INPUT_BUFFER_FN, 'w') as f_out:
-                    f_out.write(sentences_str)
-                split_sentences_str = self._post_file_2018(SPLITTER_INPUT_BUFFER_FN)
-            else:
-                split_sentences_str = self._post_string_2018(sentences_str)
-
+            split_sentences_str = self._post_string_2018(sentences_str)
             split_sentences = self._clean_up_2018(split_sentences_str)
 
         else:

skrutable-2.0.2/src/skrutable.egg-info/PKG-INFO

@@ -0,0 +1,32 @@
+Metadata-Version: 2.1
+Name: skrutable
+Version: 2.0.2
+Summary: skrutable library for working with Sanskrit text
+Home-page: https://github.com/tylergneill/skrutable
+Author: Tyler Neill
+Author-email: tyler.g.neill@gmail.com
+License: CC BY-SA 4.0
+Keywords: Sanskrit text transliteration scansion meter identification sandhi compound splitting
+Description-Content-Type: text/markdown
+Provides-Extra: testing
+License-File: LICENSE.md
+
+# skrutable
+
+A toolkit and online workbench providing 
+transliteration, scansion, and meter identification for Sanskrit text,
+as well access to powerful sandhi and compound splitting.
+
+Web-app interface live online at [skrutable.info](https://www.skrutable.info).
+
+Install package from [PyPi](https://pypi.org/project/skrutable/) with `pip install skrutable`.
+
+See [manual.md](https://github.com/tylergneill/skrutable/blob/main/src/skrutable/manual.md) for instructions.
+
+Feedback welcome!
+My name is Tyler 
+([Academia](https://uni-leipzig1.academia.edu/TylerNeill),
+[LinkedIn](https://www.linkedin.com/in/tyler-g-neill/))
+and my Gmail is tyler.g.neill. 
+
+And please share and share-alike! Licensed under a [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-sa/4.0/).

skrutable-2.0.0/PKG-INFO

@@ -1,31 +0,0 @@
-Metadata-Version: 2.1
-Name: skrutable
-Version: 2.0.0
-Summary: skrutable library for working with Sanskrit text
-Home-page: https://github.com/tylergneill/skrutable
-Author: Tyler Neill
-Author-email: tyler.g.neill@gmail.com
-License: CC BY-SA 4.0
-Description: # skrutable
-        
-        A toolkit and online workbench providing 
-        transliteration, scansion, and meter identification for Sanskrit text,
-        as well access to powerful sandhi and compound splitting.
-        
-        Web-app interface live online at [skrutable.info](https://www.skrutable.info).
-        
-        Install package from [PyPi](https://pypi.org/project/skrutable/) with `pip install skrutable`.
-        
-        See [manual.md](https://github.com/tylergneill/skrutable/blob/main/src/skrutable/manual.md) for instructions.
-        
-        Feedback welcome!
-        My name is Tyler 
-        ([Academia](https://uni-leipzig1.academia.edu/TylerNeill),
-        [LinkedIn](https://www.linkedin.com/in/tyler-g-neill/))
-        and my Gmail is tyler.g.neill. 
-        
-        And please share and share-alike! Licensed under a [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-sa/4.0/).
-Keywords: Sanskrit text transliteration scansion meter identification sandhi compound splitting
-Platform: UNKNOWN
-Description-Content-Type: text/markdown
-Provides-Extra: testing

skrutable-2.0.0/src/skrutable/__init__.py

@@ -1 +0,0 @@
-__version__ = "2.0.0"

skrutable-2.0.0/src/skrutable.egg-info/PKG-INFO

@@ -1,31 +0,0 @@
-Metadata-Version: 2.1
-Name: skrutable
-Version: 2.0.0
-Summary: skrutable library for working with Sanskrit text
-Home-page: https://github.com/tylergneill/skrutable
-Author: Tyler Neill
-Author-email: tyler.g.neill@gmail.com
-License: CC BY-SA 4.0
-Description: # skrutable
-        
-        A toolkit and online workbench providing 
-        transliteration, scansion, and meter identification for Sanskrit text,
-        as well access to powerful sandhi and compound splitting.
-        
-        Web-app interface live online at [skrutable.info](https://www.skrutable.info).
-        
-        Install package from [PyPi](https://pypi.org/project/skrutable/) with `pip install skrutable`.
-        
-        See [manual.md](https://github.com/tylergneill/skrutable/blob/main/src/skrutable/manual.md) for instructions.
-        
-        Feedback welcome!
-        My name is Tyler 
-        ([Academia](https://uni-leipzig1.academia.edu/TylerNeill),
-        [LinkedIn](https://www.linkedin.com/in/tyler-g-neill/))
-        and my Gmail is tyler.g.neill. 
-        
-        And please share and share-alike! Licensed under a [Creative Commons Attribution-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-sa/4.0/).
-Keywords: Sanskrit text transliteration scansion meter identification sandhi compound splitting
-Platform: UNKNOWN
-Description-Content-Type: text/markdown
-Provides-Extra: testing