Update new language doc #126
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,8 +1,10 @@ | ||
| dictionary_da.lst filter=lfs diff=lfs merge=lfs -text | ||
| dictionary_en.lst filter=lfs diff=lfs merge=lfs -text | ||
| dictionary_es.lst filter=lfs diff=lfs merge=lfs -text | ||
| dictionary_ml.lst filter=lfs diff=lfs merge=lfs -text | ||
| inflectional_da.xml filter=lfs diff=lfs merge=lfs -text | ||
| inflectional_en.xml filter=lfs diff=lfs merge=lfs -text | ||
| inflectional_es.xml filter=lfs diff=lfs merge=lfs -text | ||
| inflectional_ml.xml filter=lfs diff=lfs merge=lfs -text | ||
| inflectional_sv.xml filter=lfs diff=lfs merge=lfs -text | ||
| dictionary_sv.lst filter=lfs diff=lfs merge=lfs -text |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,39 @@ | ||
| എനിക്ക്,first,singular,dative | ||
| ഞാൻ,first,singular,nominative | ||
| എന്നെ,first,singular,accusative | ||
| എൻ്റെ,first,singular,genitive,dependency=dependent | ||
| എൻ്റെത്,first,singular,genitive,dependency=independent | ||
| നമുക്ക്,first,plural,dative | ||
| ഞങ്ങൾ,first,plural,nominative | ||
| ഞങ്ങളെ,first,plural,accusative | ||
| ഞങ്ങളുടെ,first,plural,genitive,dependency=dependent | ||
| ഞങ്ങളുടേതു്,first,plural,genitive,dependency=independent | ||
| നമ്മുടെ,first,plural,genitive,dependency=dependent | ||
| നമ്മുടേതു്,first,plural,genitive,dependency=independent | ||
| നിനക്ക്,second,singular,dative,dependency=nonhonorific | ||
| നീ,second,singular,nominative,dependency=nonhonorific | ||
| നിനെ,second,singular,accusative,dependency=nonhonorific | ||
| നിന്റെ,second,singular,genitive,dependency=dependent,dependency=nonhonorific | ||
| നിന്റേതു്,second,singular,genitive,dependency=independent,dependency=nonhonorific | ||
|
Comment on lines
+13
to
+17
There was a problem hiding this comment. This is confusing. Typically gender, number, or animacy would be used for dependency. The dependency is typically being used for the word being used in combination to the pronoun. For example, if I were to say "mio" or "mia" in a language, and the gender depended on the gender of the object being possessed instead of the gender of the person being referenced, then I'd use dependency. |
||
| നിങ്ങൾക്ക്,second,plural,dative,dependency=honorific | ||
| നിങ്ങൾ,second,plural,nominative,dependency=honorific | ||
| നിങ്ങളെ,second,plural,accusative,dependency=honorific | ||
| നിങ്ങളുടെ,second,plural,genitive,dependency=dependent,dependency=honorific | ||
| നിങ്ങളുടേതു്,second,plural,genitive,dependency=independent,dependency=honorific | ||
| അവൻ,third,singular,nominative,masculine | ||
| അവനെ,third,singular,accusative,masculine | ||
| അവൻ്റെ,third,singular,genitive,dependency=dependent,masculine | ||
| അവൻ്റെത്,third,singular,genitive,dependency=independent,masculine | ||
| അവൾ,third,singular,nominative,feminine | ||
| അവളെ,third,singular,accusative,feminine | ||
| അവളുടെ,third,singular,genitive,dependency=dependent,feminine | ||
| അവളുടേതു്,third,singular,genitive,dependency=independent,feminine | ||
| അത്,third,singular,nominative,neuter | ||
| അതിനെ,third,singular,accusative,neuter | ||
| അതിന്റെ,third,singular,genitive,dependency=dependent,neuter | ||
| അതിന്റേതു്,third,singular,genitive,dependency=independent,neuter | ||
| അവർ,third,plural,nominative | ||
| അവരെ,third,plural,accusative | ||
| അവരുടെ,third,plural,genitive,dependency=dependent | ||
| അവരുടേതു്,third,plural,genitive,dependency=independent | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| # | ||
| # Copyright 2025 Unicode Incorporated and others. All rights reserved. | ||
| # | ||
| tokenizer.implementation.class=DefaultTokenizer | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,17 @@ | ||
| /* | ||
| * Copyright 2025 Apple Inc. All rights reserved. | ||
| */ | ||
| #include <inflection/dialog/language/MlCommonConceptFactory.hpp> | ||
|
|
||
| namespace inflection::dialog::language { | ||
|
|
||
| MlCommonConceptFactory::MlCommonConceptFactory(const ::inflection::util::ULocale& language) | ||
| : super(language) | ||
| { | ||
| } | ||
|
|
||
| MlCommonConceptFactory::~MlCommonConceptFactory() | ||
| { | ||
| } | ||
|
Comment on lines
+2
to
+15
There was a problem hiding this comment. In all of the new files, please make sure that the copyright is not Apple, and it's not Unicode. I'm assuming that this class is trying to emulate the English behavior, where a quantity changes by only it being singular or plural for the noun in a quantity. For example, 1 man, 2 men, 1 woman, 2 women, and so forth. Are such quantities affected by grammatical case? If so, then this class likely needs a little more customization for the quantify method. For Slavic languages, the rules can get fairly complicated, and Malayalam seems to have more grammatical cases than Russian. So I'm wondering how this would work. I also see that the number pronunciation doesn't vary like many other European languages. So Malayalam language may be simpler to support. |
||
|
|
||
| } // namespace inflection::dialog::language | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,17 @@ | ||
| /* | ||
| * Copyright 2025 Apple Inc. All rights reserved. | ||
| */ | ||
| #pragma once | ||
|
|
||
| #include <inflection/dialog/language/fwd.hpp> | ||
| #include <inflection/dialog/CommonConceptFactoryImpl.hpp> | ||
|
|
||
| class inflection::dialog::language::MlCommonConceptFactory | ||
| : public CommonConceptFactoryImpl | ||
| { | ||
| public: | ||
| typedef CommonConceptFactoryImpl super; | ||
| public: | ||
| explicit MlCommonConceptFactory(const ::inflection::util::ULocale& language); | ||
| ~MlCommonConceptFactory() override; | ||
| }; |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
| /* | ||
| * Copyright 2025 Apple Inc. All rights reserved. | ||
| */ | ||
| #include <inflection/grammar/synthesis/MlGrammarSynthesizer.hpp> | ||
|
|
||
| #include <inflection/dialog/SemanticFeatureModel.hpp> | ||
| #include <inflection/grammar/synthesis/MlGrammarSynthesizer_CountLookupFunction.hpp> | ||
| #include <inflection/grammar/synthesis/MlGrammarSynthesizer_GenderLookupFunction.hpp> | ||
| #include <inflection/grammar/synthesis/MlGrammarSynthesizer_CaseLookupFunction.hpp> | ||
| #include <inflection/grammar/synthesis/MlGrammarSynthesizer_MlDisplayFunction.hpp> | ||
| #include <inflection/grammar/synthesis/GrammemeConstants.hpp> | ||
|
|
||
| namespace inflection::grammar::synthesis { | ||
|
|
||
| void MlGrammarSynthesizer::addSemanticFeatures(::inflection::dialog::SemanticFeatureModel& featureModel) | ||
| { | ||
| featureModel.putDefaultFeatureFunctionByName(GrammemeConstants::NUMBER, new MlGrammarSynthesizer_CountLookupFunction()); | ||
| featureModel.putDefaultFeatureFunctionByName(GrammemeConstants::GENDER, new MlGrammarSynthesizer_GenderLookupFunction()); | ||
| featureModel.putDefaultFeatureFunctionByName(GrammemeConstants::CASE, new MlGrammarSynthesizer_CaseLookupFunction()); | ||
|
|
||
| featureModel.setDefaultDisplayFunction(new MlGrammarSynthesizer_MlDisplayFunction(featureModel)); | ||
| } | ||
|
|
||
| } // namespace inflection::grammar::synthesis | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,17 @@ | ||
| /* | ||
| * Copyright 2025 Apple Inc. All rights reserved. | ||
| */ | ||
| #pragma once | ||
|
|
||
| #include <inflection/dialog/fwd.hpp> | ||
| #include <inflection/grammar/synthesis/fwd.hpp> | ||
| #include <string> | ||
|
|
||
| class inflection::grammar::synthesis::MlGrammarSynthesizer final | ||
| { | ||
| public: | ||
| static void addSemanticFeatures(::inflection::dialog::SemanticFeatureModel& featureModel); | ||
| private: | ||
| MlGrammarSynthesizer() = delete; | ||
| }; | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,40 @@ | ||
| /* | ||
| * Copyright 2025 Apple Inc. All rights reserved. | ||
| */ | ||
| #include <inflection/grammar/synthesis/MlGrammarSynthesizer_CaseLookupFunction.hpp> | ||
|
|
||
| #include <inflection/grammar/synthesis/GrammemeConstants.hpp> | ||
| #include <inflection/dialog/SemanticFeature.hpp> | ||
| #include <inflection/dialog/DisplayValue.hpp> | ||
| #include <inflection/dialog/SpeakableString.hpp> | ||
| #include <inflection/util/LocaleUtils.hpp> | ||
| #include <inflection/util/StringViewUtils.hpp> | ||
|
|
||
| namespace inflection::grammar::synthesis { | ||
|
|
||
| MlGrammarSynthesizer_CaseLookupFunction::MlGrammarSynthesizer_CaseLookupFunction() | ||
| : super() | ||
| { | ||
| // No file needed | ||
| } | ||
|
|
||
| inflection::dialog::SpeakableString* MlGrammarSynthesizer_CaseLookupFunction::getFeatureValue(const ::inflection::dialog::DisplayValue& displayValue, const ::std::map<::inflection::dialog::SemanticFeature, ::std::u16string>& /*constraints*/) const | ||
| { | ||
| std::u16string displayString; | ||
| ::inflection::util::StringViewUtils::lowercase(&displayString, displayValue.getDisplayString(), ::inflection::util::LocaleUtils::MALAYALAM()); | ||
|
|
||
| if (displayString.length() >= 3) { | ||
| // Genitive-indicative suffixes in Malayalam | ||
| if (displayString.ends_with(u"ഉടെ") || // uṭe | ||
| displayString.ends_with(u"യുടെ") || // yude (my, your, his, her...) | ||
| displayString.ends_with(u"ന്റെ") || // ente (mine), avante, etc. | ||
| displayString.ends_with(u"ആയുടെ")) // āyuṭe (fem. 3rd person possessive) | ||
|
There was a problem hiding this comment. Is this logic correct? Are these all suffixes? Should the |
||
| { | ||
| return new ::inflection::dialog::SpeakableString(GrammemeConstants::CASE_GENITIVE()); | ||
| } | ||
| } | ||
| return nullptr; | ||
| } | ||
|
|
||
| } // namespace inflection::grammar::synthesis | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
| /* | ||
| * Copyright 2025 Apple Inc. All rights reserved. | ||
| */ | ||
| #pragma once | ||
|
|
||
| #include <inflection/dialog/fwd.hpp> | ||
| #include <inflection/grammar/synthesis/fwd.hpp> | ||
| #include <inflection/dialog/DefaultFeatureFunction.hpp> | ||
| #include <set> | ||
| #include <string> | ||
|
|
||
| class inflection::grammar::synthesis::MlGrammarSynthesizer_CaseLookupFunction | ||
| : public ::inflection::dialog::DefaultFeatureFunction | ||
| { | ||
| public: | ||
| typedef ::inflection::dialog::DefaultFeatureFunction super; | ||
|
|
||
| public: | ||
| ::inflection::dialog::SpeakableString* getFeatureValue(const ::inflection::dialog::DisplayValue& displayValue, const ::std::map<::inflection::dialog::SemanticFeature, ::std::u16string>& constraints) const override; | ||
|
|
||
| MlGrammarSynthesizer_CaseLookupFunction(); | ||
| MlGrammarSynthesizer_CaseLookupFunction(const MlGrammarSynthesizer_CaseLookupFunction&) = delete; | ||
| MlGrammarSynthesizer_CaseLookupFunction& operator=(const MlGrammarSynthesizer_CaseLookupFunction&) = delete; | ||
| }; | ||
|
|
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good suggestion!