scriptconv 0.0.3a18__tar.gz → 0.0.3a19__tar.gz

{scriptconv-0.0.3a18 → scriptconv-0.0.3a19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scriptconv
-Version: 0.0.3a18
+Version: 0.0.3a19
 Summary: Zero-dependency script & phoneme-notation core — ISO-15924 detection & metadata, IPA↔ARPABET/X-SAMPA/Lexique/Kirshenbaum/Cotovía/RFE, Buckwalter↔Arabic, Hangul→jamo, kana
 License: Apache-2.0
 Project-URL: Homepage, https://github.com/TigreGotico/scriptconv

{scriptconv-0.0.3a18 → scriptconv-0.0.3a19}/scriptconv/notation.py

@@ -1034,7 +1034,8 @@ _MANTOQ_VOWELS: dict[str, str] = {
     "u": "u", "uu": "uː",
 }
 
-_MANTOQ_MULTI = ("_dbl_", "_+_", "aaaa", "aa", "ii", "uu")
+_MANTOQ_MULTI = ("_dbl_", "_+_", "_sil_", "_eos_", "_pad_",
+                 "aaaa", "aa", "ii", "uu")
 
 
 def _tokenize_mantoq(text: str) -> list[str]:
@@ -1065,16 +1066,29 @@ def mantoq_to_ipa(mantoq: str, errors: str = "pass") -> str:
     's a l aː m'
     >>> mantoq_to_ipa("b_dbl_a")
     'bːa'
+
+    The inventory's special tokens are honoured: ``_sil_`` becomes a space,
+    ``_eos_``/``_pad_`` are dropped.
     """
     out: list[str] = []
     last_tok = None
     for pos, tok in enumerate(_tokenize_mantoq(mantoq)):
         if tok == "_dbl_":
-            # vowels lengthen cumulatively (aa + _dbl_ -> aːː); consonants
-            # geminate once
-            if out and last_tok is not None:
-                if last_tok in _MANTOQ_VOWELS or not out[-1].endswith("ː"):
-                    out[-1] += "ː"
+            # upstream emits _dbl_ only by splitting a doubled CONSONANT
+            # (mantoq buck/tokenization.py: `phon not in vowels and
+            # phon[0] == phon[1]`); geminate it with a length mark.  A
+            # vowel+_dbl_ sequence does not occur in genuine mantoq output
+            # and is left unchanged.
+            if out and last_tok in _MANTOQ_CONSONANTS \
+                    and not out[-1].endswith("ː"):
+                out[-1] += "ː"
+            continue
+        if tok == "_sil_":
+            out.append(" ")
+            last_tok = None
+            continue
+        if tok in ("_eos_", "_pad_"):
+            last_tok = None
             continue
         if tok == "_+_":
             out.append(" ")

{scriptconv-0.0.3a18 → scriptconv-0.0.3a19}/scriptconv/version.py

@@ -2,7 +2,7 @@
 VERSION_MAJOR = 0
 VERSION_MINOR = 0
 VERSION_BUILD = 3
-VERSION_ALPHA = 18
+VERSION_ALPHA = 19
 # END_VERSION_BLOCK
 
 VERSION_STR = f"{VERSION_MAJOR}.{VERSION_MINOR}.{VERSION_BUILD}"

{scriptconv-0.0.3a18 → scriptconv-0.0.3a19}/scriptconv.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scriptconv
-Version: 0.0.3a18
+Version: 0.0.3a19
 Summary: Zero-dependency script & phoneme-notation core — ISO-15924 detection & metadata, IPA↔ARPABET/X-SAMPA/Lexique/Kirshenbaum/Cotovía/RFE, Buckwalter↔Arabic, Hangul→jamo, kana
 License: Apache-2.0
 Project-URL: Homepage, https://github.com/TigreGotico/scriptconv

{scriptconv-0.0.3a18 → scriptconv-0.0.3a19}/tests/test_notation.py

@@ -1168,7 +1168,20 @@ def test_mantoq_theta_is_caret_not_shadda():
 
 def test_mantoq_gemination_marker():
     assert mantoq_to_ipa("b_dbl_a") == "bːa"
-    assert mantoq_to_ipa("aa_dbl_") == "aːː"
+
+
+def test_mantoq_dbl_after_vowel_is_inert():
+    # upstream only emits _dbl_ after consonants (tokenization.py splits
+    # doubled consonant phonemes); a vowel+_dbl_ input is left unchanged
+    assert mantoq_to_ipa("aa_dbl_") == "aː"
+
+
+def test_mantoq_special_tokens():
+    # inventory special tokens: _sil_ -> pause (space), _eos_/_pad_ dropped —
+    # and never shredded into letter phonemes
+    assert mantoq_to_ipa("m_sil_n") == "m n"
+    assert mantoq_to_ipa("m a_eos_") == "m a"
+    assert mantoq_to_ipa("_pad_b") == "b"
 
 
 def test_mantoq_word_separator_and_glottal():