[Python][JP Number with Unit] Add Japanese number with unit support

Python/libraries/recognizers-number-with-unit/recognizers_number_with_unit/number_with_unit/japanese/__init__.py

@@ -0,0 +1,2 @@
+from .extractors import *
+from .parsers import *

Python/libraries/recognizers-number-with-unit/recognizers_number_with_unit/number_with_unit/japanese/extractors.py

@@ -0,0 +1,95 @@
+from typing import Dict, List, Pattern
+
+from recognizers_text.culture import Culture
+from recognizers_text.extractor import Extractor
+from recognizers_text.utilities import RegExpUtility
+from recognizers_number.culture import CultureInfo
+from recognizers_number.number.japanese.extractors import JapaneseNumberExtractor, JapaneseNumberExtractorMode
+from recognizers_number_with_unit.number_with_unit.constants import Constants
+from recognizers_number_with_unit.number_with_unit.extractors import NumberWithUnitExtractorConfiguration
+from recognizers_number_with_unit.resources.japanese_numeric_with_unit import JapaneseNumericWithUnit
+from recognizers_number_with_unit.resources.base_units import BaseUnits
+
+
+# pylint: disable=abstract-method
+class JapaneseNumberWithUnitExtractorConfiguration(NumberWithUnitExtractorConfiguration):
+
+    @property
+    def ambiguity_filters_dict(self) -> Dict[Pattern, Pattern]:
+        return JapaneseNumericWithUnit.AmbiguityFiltersDict
+
+    @property
+    def unit_num_extractor(self) -> Extractor:
+        return self._unit_num_extractor
+
+    @property
+    def build_prefix(self) -> str:
+        return self._build_prefix
+
+    @property
+    def build_suffix(self) -> str:
+        return self._build_suffix
+
+    @property
+    def connector_token(self) -> str:
+        return self._connector_token
+
+    @property
+    def compound_unit_connector_regex(self) -> Pattern:
+        return self._compound_unit_connector_regex
+
+    @property
+    def non_unit_regex(self) -> Pattern:
+        return self._pm_non_unit_regex
+
+    @property
+    def half_unit_regex(self) -> Pattern:
+        return self._half_unit_regex
+
+    @property
+    def ambiguous_unit_number_multiplier_regex(self) -> Pattern:
+        return None
+
+    def expand_half_suffix(self, source, result, numbers):
+        pass
+
+    def __init__(self, culture_info: CultureInfo):
+        if culture_info is None:
+            culture_info = CultureInfo(Culture.Japanese)
+        super().__init__(culture_info)
+        self._unit_num_extractor = JapaneseNumberExtractor(JapaneseNumberExtractorMode.EXTRACT_ALL)
+        self._build_prefix = JapaneseNumericWithUnit.BuildPrefix
+        self._build_suffix = JapaneseNumericWithUnit.BuildSuffix
+        self._connector_token = JapaneseNumericWithUnit.ConnectorToken
+        self._compound_unit_connector_regex = RegExpUtility.get_safe_reg_exp(
+            JapaneseNumericWithUnit.CompoundUnitConnectorRegex)
+        self._pm_non_unit_regex = RegExpUtility.get_safe_reg_exp(
+            BaseUnits.PmNonUnitRegex)
+        self._half_unit_regex = RegExpUtility.get_safe_reg_exp(JapaneseNumericWithUnit.HalfUnitRegex)
+
+
+# pylint: enable=abstract-method
+
+class JapaneseCurrencyExtractorConfiguration(JapaneseNumberWithUnitExtractorConfiguration):
+    @property
+    def extract_type(self) -> str:
+        return Constants.SYS_UNIT_CURRENCY
+
+    @property
+    def suffix_list(self) -> Dict[str, str]:
+        return self._suffix_list
+
+    @property
+    def prefix_list(self) -> Dict[str, str]:
+        return self._prefix_list
+
+    @property
+    def ambiguous_unit_list(self) -> List[str]:
+        return self._ambiguous_unit_list
+
+    def __init__(self, culture_info: CultureInfo = None):
+        super().__init__(culture_info)
+        self._suffix_list = JapaneseNumericWithUnit.CurrencySuffixList
+        self._prefix_list = JapaneseNumericWithUnit.CurrencyPrefixList
+        self._ambiguous_unit_list = JapaneseNumericWithUnit.CurrencyAmbiguousValues
+

Python/libraries/recognizers-number-with-unit/recognizers_number_with_unit/number_with_unit/japanese/parsers.py

@@ -0,0 +1,46 @@
+#  Copyright (c) Microsoft Corporation. All rights reserved.
+#  Licensed under the MIT License.
+
+from recognizers_text.culture import Culture
+from recognizers_text.extractor import Extractor
+from recognizers_text.parser import Parser
+from recognizers_number.culture import CultureInfo
+from recognizers_number.number.japanese.extractors import JapaneseNumberExtractor, JapaneseNumberExtractorMode
+from recognizers_number.number.parser_factory import AgnosticNumberParserFactory, ParserType
+from recognizers_number.number.japanese.parsers import JapaneseNumberParserConfiguration
+from recognizers_number_with_unit.number_with_unit.parsers import NumberWithUnitParserConfiguration
+from recognizers_number_with_unit.resources.japanese_numeric_with_unit import JapaneseNumericWithUnit
+
+
+class JapaneseNumberWithUnitParserConfiguration(NumberWithUnitParserConfiguration):
+    @property
+    def internal_number_parser(self) -> Parser:
+        return self._internal_number_parser
+
+    @property
+    def internal_number_extractor(self) -> Extractor:
+        return self._internal_number_extractor
+
+    @property
+    def connector_token(self) -> str:
+        return self._connector_token
+
+    def __init__(self, culture_info: CultureInfo):
+        if culture_info is None:
+            culture_info = CultureInfo(Culture.Japanese)
+        super().__init__(culture_info)
+        self._internal_number_extractor = JapaneseNumberExtractor(
+            JapaneseNumberExtractorMode.EXTRACT_ALL)
+        self._internal_number_parser = AgnosticNumberParserFactory.get_parser(
+            ParserType.NUMBER, JapaneseNumberParserConfiguration(culture_info))
+        self._connector_token = JapaneseNumericWithUnit.ConnectorToken
+
+
+class JapaneseCurrencyParserConfiguration(JapaneseNumberWithUnitParserConfiguration):
+    def __init__(self, culture_info: CultureInfo = None):
+        super().__init__(culture_info)
+        self.add_dict_to_unit_map(JapaneseNumericWithUnit.CurrencySuffixList)
+        self.add_dict_to_unit_map(JapaneseNumericWithUnit.CurrencyPrefixList)
+        self.currency_name_to_iso_code_map = JapaneseNumericWithUnit.CurrencyNameToIsoCodeMap
+        self.currency_fraction_code_list = JapaneseNumericWithUnit.FractionalUnitNameToCodeMap
+

Python/libraries/recognizers-number-with-unit/recognizers_number_with_unit/number_with_unit/models.py

@@ -43,7 +43,7 @@ def parse(self, query: str) -> List[ModelResult]:
                                 parse_results.append(j)
                         else:
                             parse_results.append(r)
-
+                model_result = None
                 for parse_result in parse_results:
                     model_result = ModelResult()
                     model_result.start = parse_result.start
@@ -57,6 +57,8 @@ def parse(self, query: str) -> List[ModelResult]:
 
                     if b_add:
                         extraction_results.append(model_result)
+                if model_result:
+                    break
         except Exception:
             pass
 

Python/libraries/recognizers-number-with-unit/recognizers_number_with_unit/number_with_unit/number_with_unit_recognizer.py

@@ -61,6 +61,8 @@
 from .german.parsers import GermanCurrencyParserConfiguration
 from .italian.extractors import ItalianCurrencyExtractorConfiguration
 from .italian.parsers import ItalianCurrencyParserConfiguration
+from .japanese.extractors import JapaneseCurrencyExtractorConfiguration
+from .japanese.parsers import JapaneseCurrencyParserConfiguration
 
 
 class NumberWithUnitOptions(IntFlag):
@@ -264,6 +266,19 @@ def initialize_configuration(self):
         ]))
         # endregion
 
+        # region Japanese
+        self.register_model('CurrencyModel', Culture.Japanese, lambda options: CurrencyModel([
+            ExtractorParserModel(
+                BaseMergedUnitExtractor(
+                    JapaneseCurrencyExtractorConfiguration()),
+                BaseMergedUnitParser(JapaneseCurrencyParserConfiguration())),
+            ExtractorParserModel(
+                NumberWithUnitExtractor(
+                    EnglishCurrencyExtractorConfiguration()),
+                NumberWithUnitParser(EnglishCurrencyParserConfiguration()))
+        ]))
+        # endregion
+
     def get_age_model(self, culture: str = None, fallback_to_default_culture: bool = True) -> Model:
         return self.get_model('AgeModel', culture, fallback_to_default_culture)
 

Python/libraries/recognizers-number-with-unit/recognizers_number_with_unit/resources/__init__.py

@@ -10,3 +10,4 @@
 from .dutch_numeric_with_unit import DutchNumericWithUnit
 from .portuguese_numeric_with_unit import PortugueseNumericWithUnit
 from .spanish_numeric_with_unit import SpanishNumericWithUnit
+from .japanese_numeric_with_unit import JapaneseNumericWithUnit