Merge pull request #10 from OpenVoiceOS/release-0.0.2a1

Release 0.0.2a1

Author: JarbasAl

CHANGELOG.md

@@ -1,18 +1,12 @@
 # Changelog
 
-## [0.0.1a2](https://github.com/OpenVoiceOS/ovos-number-parser/tree/0.0.1a2) (2024-11-07)
+## [0.0.2a1](https://github.com/OpenVoiceOS/ovos-number-parser/tree/0.0.2a1) (2024-11-13)
 
-[Full Changelog](https://github.com/OpenVoiceOS/ovos-number-parser/compare/bc086aef8c1f18b03f6481e222a6c460f5b94962...0.0.1a2)
-
-**Closed issues:**
-
-- Enhance text normalization in  [\#3](https://github.com/OpenVoiceOS/ovos-number-parser/issues/3)
-- Add  support for missing languages [\#2](https://github.com/OpenVoiceOS/ovos-number-parser/issues/2)
+[Full Changelog](https://github.com/OpenVoiceOS/ovos-number-parser/compare/0.0.1...0.0.2a1)
 
 **Merged pull requests:**
 
-- semver [\#6](https://github.com/OpenVoiceOS/ovos-number-parser/pull/6) ([JarbasAl](https://github.com/JarbasAl))
-- feat: numbers\_to\_digits [\#1](https://github.com/OpenVoiceOS/ovos-number-parser/pull/1) ([JarbasAl](https://github.com/JarbasAl))
+- fix: number\_to\_digits catalan placeholder [\#9](https://github.com/OpenVoiceOS/ovos-number-parser/pull/9) ([JarbasAl](https://github.com/JarbasAl))
 
 
 

README.md

@@ -14,23 +14,28 @@ fractional and ordinal numbers, and more.
 
 ## Supported Languages
 
+✅ - supported
+❌ - not supported
+🚧 - imperfect placeholder, needs rewriting
+
+
 | Language Code           | Pronounce Number | Pronounce Ordinal | Extract Number | numbers_to_digits |
 |-------------------------|------------------|-------------------|----------------|-------------------|
 | `en` (English)          | ✅               | ❌                | ✅             | ✅                |
 | `az` (Azerbaijani)      | ✅               | ❌                | ✅             | ✅                |
-| `ca` (Catalan)          | ✅                | ❌                 | ✅              | ❌                 |
+| `ca` (Catalan)          | ✅                | ❌                 | ✅              | 🚧                 |
 | `cs` (Czech)            | ✅                | ❌                 | ✅              | ✅                 |
 | `da` (Danish)           | ✅                | ✅                 | ✅              | ❌                 |
 | `de` (German)           | ✅                | ✅                 | ✅              | ✅                 |
-| `es` (Spanish)          | ✅                | ❌                 | ✅              | ✅                 |
+| `es` (Spanish)          | ✅                | ❌                 | ✅              | 🚧                 |
 | `eu` (Euskara / Basque) | ✅                | ❌                 | ✅              | ❌                 |
 | `fa` (Farsi / Persian)  | ✅                | ❌                 | ✅              | ❌                 |
 | `fr` (French)           | ✅                | ❌                 | ✅              | ❌                 |
 | `hu` (Hungarian)        | ✅                | ✅                 | ❌              | ❌                 |
 | `it` (Italian)          | ✅                | ❌                 | ✅              | ❌                 |
 | `nl` (Dutch)            | ✅                | ✅                 | ✅              | ✅                 |
 | `pl` (Polish)           | ✅                | ❌                 | ✅              | ✅                 |
-| `pt` (Portuguese)       | ✅                | ❌                 | ✅              | ✅                 |
+| `pt` (Portuguese)       | ✅                | ❌                 | ✅              | 🚧                 |
 | `ru` (Russian)          | ✅                | ❌                 | ✅              | ✅                 |
 | `sv` (Swedish)          | ✅                | ✅                 | ✅              | ❌                 |
 | `sl` (Slovenian)        | ✅                | ❌                 | ❌              | ❌                 |

ovos_number_parser/__init__.py

@@ -1,7 +1,7 @@
 from typing import Union
 
 from ovos_number_parser.numbers_az import numbers_to_digits_az, extract_number_az, is_fractional_az, pronounce_number_az
-from ovos_number_parser.numbers_ca import pronounce_number_ca, is_fractional_ca, extract_number_ca
+from ovos_number_parser.numbers_ca import numbers_to_digits_ca, pronounce_number_ca, is_fractional_ca, extract_number_ca
 from ovos_number_parser.numbers_cs import numbers_to_digits_cs, pronounce_number_cs, is_fractional_cs, extract_number_cs
 from ovos_number_parser.numbers_da import is_fractional_da, is_ordinal_da, pronounce_number_da, \
     pronounce_ordinal_da, extract_number_da
@@ -38,6 +38,8 @@ def numbers_to_digits(utterance: str, lang: str) -> str:
     """
     if lang.startswith("az"):
         return numbers_to_digits_az(utterance)
+    if lang.startswith("ca"):
+        return numbers_to_digits_ca(utterance)
     if lang.startswith("cs"):
         return numbers_to_digits_cs(utterance)
     if lang.startswith("de"):

ovos_number_parser/numbers_ca.py

@@ -1,5 +1,5 @@
 from ovos_number_parser.util import (convert_to_mixed_fraction, look_for_fractions,
-                                     is_numeric)
+                                     is_numeric, tokenize)
 
 _NUMBERS_CA = {
     "zero": 0,
@@ -466,3 +466,29 @@ def extract_number_ca(text, short_scale=True, ordinals=False):
             result = int(integer)
 
     return result or False
+
+
+def numbers_to_digits_ca(utterance: str) -> str:
+    """
+    Substitueix els números escrits en un text en català per les seves equivalents en xifres.
+
+    Args:
+        utterance (str): Cadena d'entrada que possiblement conté números escrits.
+
+    Returns:
+        str: Text amb els números escrits substituïts per xifres.
+    """
+    # TODO - this is a quick and dirty placeholder and needs rewriting
+    number_replacements = {
+        "un": "1", "dos": "2", "tres": "3", "quatre": "4",
+        "cinc": "5", "sis": "6", "set": "7", "vuit": "8", "nou": "9",
+        "deu": "10", "onze": "11", "dotze": "12", "tretze": "13", "catorze": "14",
+        "quinze": "15", "setze": "16", "disset": "17", "divuit": "18",
+        "dinou": "19", "vint": "20"
+        # Amplieu aquest diccionari per a números més alts si és necessari
+    }
+    words = tokenize(utterance)
+    for idx, word in enumerate(words):
+        if word in number_replacements:
+            words[idx] = number_replacements[word]
+    return " ".join(words)

ovos_number_parser/numbers_es.py

@@ -668,6 +668,7 @@ def pronounce_number_es(number, places=2):
             result += " " + _NUM_STRING_ES[int(char)]
     return result
 
+
 def numbers_to_digits_es(utterance: str) -> str:
     """
     Replace written numbers in a Spanish text with their digit equivalents.
@@ -678,6 +679,7 @@ def numbers_to_digits_es(utterance: str) -> str:
     Returns:
         str: Text with written numbers replaced by digits.
     """
+    # TODO - this is a quick and dirty placeholder and needs rewriting
     number_replacements = {
         "uno": "1", "dos": "2", "tres": "3", "cuatro": "4",
         "cinco": "5", "seis": "6", "siete": "7", "ocho": "8", "nueve": "9",
@@ -690,4 +692,4 @@ def numbers_to_digits_es(utterance: str) -> str:
     for idx, word in enumerate(words):
         if word in number_replacements:
             words[idx] = number_replacements[word]
-    return " ".join(words)
+    return " ".join(words)

ovos_number_parser/numbers_pt.py

@@ -389,6 +389,7 @@ def numbers_to_digits_pt(utterance: str) -> str:
     Returns:
         str: Text with written numbers replaced by digits.
     """
+    # TODO - this is a quick and dirty placeholder and needs rewriting
     number_replacements = {
         "catorze": "14",
         "cem": "100",

ovos_number_parser/version.py

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

setup.py

@@ -57,7 +57,6 @@ def get_version():
     version=get_version(),
     packages=['ovos_number_parser'],
     url='https://github.com/OpenVoiceOS/ovos-number-parser',
-    obsoletes=['ovos_number_parser'],
     license='Apache2.0',
     package_data={'': extra_files},
     include_package_data=True,