phoonnx 0.0.0a2__py3-none-any.whl → 0.0.2a1__py3-none-any.whl

phoonnx/util.py

@@ -257,9 +257,9 @@ UNITS = {
     "en": {
         "€": "euros",
         "%": "per cent",
-        "ºC": "degrees celsius",
-        "ºF": "degrees fahrenheit",
-        "ºK": "degrees kelvin",
+        "°C": "degrees celsius",
+        "°F": "degrees fahrenheit",
+        "°K": "degrees kelvin",
         "°": "degrees",
         "$": "dollars",
         "£": "pounds",
@@ -287,9 +287,9 @@ UNITS = {
     "pt": {
         "€": "euros",
         "%": "por cento",
-        "ºC": "graus celsius",
-        "ºF": "graus fahrenheit",
-        "ºK": "graus kelvin",
+        "°C": "graus celsius",
+        "°F": "graus fahrenheit",
+        "°K": "graus kelvin",
         "°": "graus",
         "$": "dólares",
         "£": "libras",
@@ -308,9 +308,9 @@ UNITS = {
     "es": {
         "€": "euros",
         "%": "por ciento",
-        "ºC": "grados celsius",
-        "ºF": "grados fahrenheit",
-        "ºK": "grados kelvin",
+        "°C": "grados celsius",
+        "°F": "grados fahrenheit",
+        "°K": "grados kelvin",
         "°": "grados",
         "$": "dólares",
         "£": "libras",
@@ -325,9 +325,9 @@ UNITS = {
     "fr": {
         "€": "euros",
         "%": "pour cent",
-        "ºC": "degrés celsius",
-        "ºF": "degrés fahrenheit",
-        "ºK": "degrés kelvin",
+        "°C": "degrés celsius",
+        "°F": "degrés fahrenheit",
+        "°K": "degrés kelvin",
         "°": "degrés",
         "$": "dollars",
         "£": "livres",
@@ -342,9 +342,9 @@ UNITS = {
     "de": {
         "€": "Euro",
         "%": "Prozent",
-        "ºC": "Grad Celsius",
-        "ºF": "Grad Fahrenheit",
-        "ºK": "Grad Kelvin",
+        "°C": "Grad Celsius",
+        "°F": "Grad Fahrenheit",
+        "°K": "Grad Kelvin",
         "°": "Grad",
         "$": "Dollar",
         "£": "Pfund",
@@ -548,6 +548,7 @@ def _normalize_units(text: str, full_lang: str) -> str:
     This function handles symbolic and alphanumeric units separately
     to avoid issues with word boundaries.
     """
+    text = text.replace("º", "°") # these characters look the same... but...
     lang_code = full_lang.split("-")[0]
     if lang_code in UNITS:
         # Determine number separators for the language
@@ -566,15 +567,18 @@ def _normalize_units(text: str, full_lang: str) -> str:
             symbolic_pattern = re.compile(number_pattern_str + r"\s*(" + symbolic_pattern_str + r")", re.IGNORECASE)
 
             def replace_symbolic(match):
-                number_str = match.group(1)
+                number = match.group(1)
                 # Remove thousands separator and replace decimal separator for parsing
-                number = number_str.replace(thousands_separator, "").replace(decimal_separator, ".")
+                if thousands_separator in number and decimal_separator in number:
+                    number = number.replace(thousands_separator, "").replace(decimal_separator, ".")
+                elif decimal_separator != "." and decimal_separator in number:
+                    number = number.replace(decimal_separator, ".")
                 unit_symbol = match.group(2)
                 unit_word = symbolic_units[unit_symbol]
                 try:
-                    return f"{pronounce_number(float(number), full_lang)} {unit_word}"
+                    return f"{pronounce_number(float(number) if '.' in number else int(number), full_lang)} {unit_word}"
                 except Exception as e:
-                    LOG.error(f"Failed to pronounce number with unit: {number_str}{unit_symbol} - ({e})")
+                    LOG.error(f"Failed to pronounce number with unit: {number}{unit_symbol} - ({e})")
                     return match.group(0)
             text = symbolic_pattern.sub(replace_symbolic, text)
 
@@ -587,12 +591,15 @@ def _normalize_units(text: str, full_lang: str) -> str:
                                               re.IGNORECASE)
 
             def replace_alphanumeric(match):
-                number_str = match.group(1)
+                number = match.group(1)
                 # Remove thousands separator and replace decimal separator for parsing
-                number = number_str.replace(thousands_separator, "").replace(decimal_separator, ".")
+                if thousands_separator in number and decimal_separator in number:
+                    number = number.replace(thousands_separator, "").replace(decimal_separator, ".")
+                elif decimal_separator != "." and decimal_separator in number:
+                    number = number.replace(decimal_separator, ".")
                 unit_symbol = match.group(2)
                 unit_word = alphanumeric_units[unit_symbol]
-                return f"{pronounce_number(float(number), full_lang)} {unit_word}"
+                return f"{pronounce_number(float(number) if '.' in number else int(number), full_lang)} {unit_word}"
 
             text = alphanumeric_pattern.sub(replace_alphanumeric, text)
     return text
@@ -666,7 +673,8 @@ if __name__ == "__main__":
 
     # General normalization examples
     print("General English example: " + normalize('I\'m Dr. Prof. 3/3 0.5% of 12345€, 5ft, and 10kg', 'en'))
-    print(f"General Portuguese example: {normalize('Dr. Prof. 3/3 0.5% de 12345€, 5m, e 10kg', 'pt')}")
+    print(f"Word Salad Portuguese (Dr. Prof. 3/3 0,5% de 12345€, 5m, e 10kg): {normalize('Dr. Prof. 3/3 0,5% de 12345€, 5m, e 10kg', 'pt')}")
+    print(f"Word Salad Portuguese (Dr. Prof. 3/3 0.5% de 12345€, 5m, e 10kg): {normalize('Dr. Prof. 3/3 0.5% de 12345€, 5m, e 10kg', 'pt')}")
 
     # Portuguese examples with comma decimal separator
     print("\n--- Portuguese Decimal Separator Examples ---")
@@ -690,10 +698,10 @@ if __name__ == "__main__":
 
     # Portuguese dates and times
     print("\n--- Portuguese Date & Time Examples ---")
-    print(f"Portuguese date (DMY format): {normalize('A data é 03/08/2025', 'pt')}")
-    print(f"Portuguese ambiguous date (DMY assumed): {normalize('O relatório é para 15/05/2025', 'pt')}")
-    print(f"Portuguese date with dashes: {normalize('O evento é no dia 25-10-2024', 'pt')}")
-    print(f"Portuguese military time: {normalize('O encontro é às 14h30', 'pt')}")
+    print(f"Portuguese date (A data é 03/08/2025): {normalize('A data é 03/08/2025', 'pt')}")
+    print(f"Portuguese ambiguous date (O relatório é para 15/05/2025): {normalize('O relatório é para 15/05/2025', 'pt')}")
+    print(f"Portuguese date with dashes (O evento é no dia 25-10-2024): {normalize('O evento é no dia 25-10-2024', 'pt')}")
+    print(f"Portuguese military time (O encontro é às 14h30): {normalize('O encontro é às 14h30', 'pt')}")
 
     # Other examples
     print(f"\n--- Other Examples ---")

phoonnx/version.py

@@ -1,6 +1,6 @@
 # START_VERSION_BLOCK
 VERSION_MAJOR = 0
 VERSION_MINOR = 0
-VERSION_BUILD = 0
-VERSION_ALPHA = 2
+VERSION_BUILD = 2
+VERSION_ALPHA = 1
 # END_VERSION_BLOCK

{phoonnx-0.0.0a2.dist-info → phoonnx-0.0.2a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phoonnx
-Version: 0.0.0a2
+Version: 0.0.2a1
 Home-page: https://github.com/TigreGotico/phoonnx
 Author: JarbasAi
 Author-email: jarbasai@mailfence.com

{phoonnx-0.0.0a2.dist-info → phoonnx-0.0.2a1.dist-info}/RECORD

@@ -1,8 +1,8 @@
 phoonnx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoonnx/config.py,sha256=bO7dx2tfLotkohict3UKlCEVm-BRFB1feYYR1HarUkk,19382
 phoonnx/phoneme_ids.py,sha256=FiNgZwV6naEsBh6XwFLh3_FyOgPiCsK9qo7S0v-CmI4,13667
-phoonnx/util.py,sha256=3DqSRwsF498oP_uFVZnriP9PyjXhCfEy97Ey0ePTEqA,25042
-phoonnx/version.py,sha256=dR5gxHjK1GpeSbtoOSuQmJ4k9oUkkoIYYAwIJlvkQAk,114
+phoonnx/util.py,sha256=XSjFEoqSFcujFTHxednacgC9GrSYyF-Il5L6Utmxmu4,25909
+phoonnx/version.py,sha256=tnwL6H7F2rKiYfzZqG80Wt82MT0mHbzZ38RjwaJcsgs,114
 phoonnx/voice.py,sha256=FR_LafK1vSi_anPERJjZBuH3Bb9vUIof0MAW6TnALlA,20024
 phoonnx/locale/ca/phonetic_spellings.txt,sha256=igv3t7jxLSRE5GHsdn57HOpxiWNcEmECPql6m02wbO0,47
 phoonnx/locale/en/phonetic_spellings.txt,sha256=xGQlWOABLzbttpQvopl9CU-NnwEJRqKx8iuylsdUoQA,27
@@ -80,7 +80,7 @@ phoonnx_train/vits/utils.py,sha256=exiyrtPHbnnGvcHWSbaH9-gR6srH5ZPHlKiqV2IHUrQ,4
 phoonnx_train/vits/wavfile.py,sha256=oQZiTIrdw0oLTbcVwKfGXye1WtKte6qK_52qVwiMvfc,26396
 phoonnx_train/vits/monotonic_align/__init__.py,sha256=5IdAOD1Z7UloMb6d_9NRFsXoNIjEQ3h9mvOSh_AtO3k,636
 phoonnx_train/vits/monotonic_align/setup.py,sha256=0K5iJJ2mKIklx6ncEfCQS34skm5hHPiz9vRlQEvevvY,266
-phoonnx-0.0.0a2.dist-info/METADATA,sha256=6Vy9IlAd8I2pFPa-NyzdYCNTyUTDxfShyd1DVLrMzpQ,7868
-phoonnx-0.0.0a2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-phoonnx-0.0.0a2.dist-info/top_level.txt,sha256=ZrnHXe-4HqbOSX6fbdY-JiP7YEu2Bok9T0ji351MrmM,22
-phoonnx-0.0.0a2.dist-info/RECORD,,
+phoonnx-0.0.2a1.dist-info/METADATA,sha256=i-4sLAwReU6JT44xM2JVBcAfKP0Rv9mMpWpiEdNUX7U,7868
+phoonnx-0.0.2a1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+phoonnx-0.0.2a1.dist-info/top_level.txt,sha256=ZrnHXe-4HqbOSX6fbdY-JiP7YEu2Bok9T0ji351MrmM,22
+phoonnx-0.0.2a1.dist-info/RECORD,,