Re-enable removal of facny quotes (#1256)

* comment out the rm of special characters * bump vers * re-enable text removal for fancy quotation marks
cltk · Apr 20, 2024 · 8ea1b26 · 8ea1b26
1 parent 1be4538
commit 8ea1b26
Show file tree

Hide file tree

Showing 4 changed files with 10 additions and 8 deletions.
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cltk"
-version = "1.2.2"
+version = "1.2.5"
 description = "The Classical Language Toolkit"
 license = "MIT"
 authors = ["Kyle P. Johnson <[email protected]>", "Patrick J. Burns <[email protected]>", "John Stewart <[email protected]>", "Todd Cook <[email protected]>", "Clément Besnier <[email protected]>", "William J. B. Mattingly <https://github.com/wjbmattingly>"]

diff --git a/src/cltk/alphabet/lat.py b/src/cltk/alphabet/lat.py
@@ -475,7 +475,7 @@ def normalize_lat(
     text_cltk_normalized: str = cltk_normalize(text=text)
     text_cltk_normalized = split_trailing_punct(text=text_cltk_normalized)
     text_cltk_normalized = split_leading_punct(text=text_cltk_normalized)
-    # text_cltk_normalized = remove_odd_punct(text=text_cltk_normalized)
+    text_cltk_normalized = remove_odd_punct(text=text_cltk_normalized)
     if drop_macrons:
         text_cltk_normalized = remove_macrons(text_cltk_normalized)
     if drop_accents:

diff --git a/src/cltk/alphabet/text_normalization.py b/src/cltk/alphabet/text_normalization.py
@@ -127,6 +127,6 @@ def remove_odd_punct(text: str, punctuation: list[str] = None) -> str:
     'κατηγόρων, οὐκ οἶδα ἐγὼ δ᾽ οὖν'
     """
     if not punctuation:
-        punctuation = ["‘", "“", ":", "’", "”"]
+        punctuation = ["‘", "“", "’", "”"]
     chars: list[str] = [char for char in text if char not in punctuation]
     return "".join(chars)
diff --git a/src/cltk/prosody/grc.py b/src/cltk/prosody/grc.py
@@ -263,7 +263,9 @@ def _long_by_nature(self, syllable: str) -> bool:
                 vowel_group += char
         return bool("".join(vowel_group) in self.diphthongs)
 
-    def _long_by_position(self, sentence_index, syllable: str, sentence: list[str]) -> bool:
+    def _long_by_position(
+        self, sentence_index, syllable: str, sentence: list[str]
+    ) -> bool:
         """Check if syllable is long by position. Returns ``True``
         if syllable is long by position Long by position
         includes contexts when:
@@ -321,10 +323,10 @@ def _scansion(self, sentence_syllables: list[list[str]]) -> list[str]:
         scanned_text = list()
         for sentence in sentence_syllables:
             scanned_sent = list()
-            for i, syllable in enumerate(sentence):   
-                if self._long_by_position(i, syllable, sentence) or self._long_by_nature(
-                    syllable
-                ):
+            for i, syllable in enumerate(sentence):
+                if self._long_by_position(
+                    i, syllable, sentence
+                ) or self._long_by_nature(syllable):
                     scanned_sent.append("¯")
                 else:
                     scanned_sent.append("˘")