unicode-org · grhoten · Sep 3, 2025 · Sep 1, 2025
diff --git a/documents/how_to_add_new_language.md b/documents/how_to_add_new_language.md
@@ -10,6 +10,9 @@ The following steps with help you identify files that need to be added or change
 NOTE: Take a look at [PR #40](https://github.com/unicode-org/inflection/pull/40) and [PR #111](https://github.com/unicode-org/inflection/pull/111) for example on how to add initial language support based on dictionary lookup only.
 In general, to bootstrap your progress look for grammatically similar language that's already supported, e.g. if you are adding Serbian look for existing Russian implementation.
 This will help you find most of the files you need to add/change and will speed up implementation of the rules and lexicons.
+We recommend you spend around a week researching the language and all the different components of the language before even beginning to modify and add the files below. Look at all the files in the project such as tokenizers, configuration files, grammar files, and different lookup functions to see what you need. This will save you a lot of time in the end. We highly suggest you stray away from hardcoded logic and rely on the Dictionary Lookup. Look at all the grammemes, tokenizer logic, and multi-word phrase handling.
+
+Before you add new language support, go to the README.md in the inflection subfolder (inflection/inflection/README.md), build the project, and make sure all the tests run on your computer.
 
 ## Mark your language as supported
 * UPDATE: inflection/src/inflection/util/LocaleUtils.hpp
@@ -29,13 +32,13 @@ TODO: We need to expand what each of these do.
 * ADD: inflection/src/inflection/grammar/synthesis/*Xx*GrammarSynthesizer.hpp
 * ADD: inflection/src/inflection/grammar/synthesis/*Xx*GrammarSynthesizer.cpp
 * ADD: inflection/src/inflection/grammar/synthesis/*Xx*GrammarSynthesizer_*Xx*DisplayFunction.hpp
-* ADD: inflection/src/inflection/grammar/synthesis/*Xx*GrammarSynthesizer_*Xx*DisplayFunction.hpp
+* ADD: inflection/src/inflection/grammar/synthesis/*Xx*GrammarSynthesizer_*Xx*DisplayFunction.cpp
 * UPDATE: inflection/src/inflection/grammar/synthesis/GrammarSynthesizerFactory.cpp
 * UPDATE: inflection/src/inflection/grammar/synthesis/fwd.hpp
 
 ## Add language specific properties for lists, quantities and related topics
 * ADD: inflection/src/inflection/dialog/language/*Xx*CommonConceptFactory.hpp
-* ADD: inflection/src/inflection/dialog/language/*Xx*CommonConceptFactory.hpp
+* ADD: inflection/src/inflection/dialog/language/*Xx*CommonConceptFactory.cpp
 * UPDATE: inflection/src/inflection/dialog/language/fwd.hpp
 
 ## Define and create lexion

diff --git a/inflection/resources/org/unicode/inflection/dictionary/.gitattributes b/inflection/resources/org/unicode/inflection/dictionary/.gitattributes
@@ -8,6 +8,7 @@ dictionary_he.lst filter=lfs diff=lfs merge=lfs -text
 dictionary_hi.lst filter=lfs diff=lfs merge=lfs -text
 dictionary_it.lst filter=lfs diff=lfs merge=lfs -text
 dictionary_ko.lst filter=lfs diff=lfs merge=lfs -text
+dictionary_ml.lst filter=lfs diff=lfs merge=lfs -text
 dictionary_nb.lst filter=lfs diff=lfs merge=lfs -text
 dictionary_nl.lst filter=lfs diff=lfs merge=lfs -text
 dictionary_pt.lst filter=lfs diff=lfs merge=lfs -text
@@ -23,6 +24,7 @@ inflectional_fr.xml filter=lfs diff=lfs merge=lfs -text
 inflectional_he.xml filter=lfs diff=lfs merge=lfs -text
 inflectional_hi.xml filter=lfs diff=lfs merge=lfs -text
 inflectional_it.xml filter=lfs diff=lfs merge=lfs -text
+inflectional_ml.xml filter=lfs diff=lfs merge=lfs -text
 inflectional_nb.xml filter=lfs diff=lfs merge=lfs -text
 inflectional_nl.xml filter=lfs diff=lfs merge=lfs -text
 inflectional_pt.xml filter=lfs diff=lfs merge=lfs -text

diff --git a/inflection/resources/org/unicode/inflection/dictionary/dictionary_ml.lst b/inflection/resources/org/unicode/inflection/dictionary/dictionary_ml.lst
diff --git a/inflection/resources/org/unicode/inflection/dictionary/inflectional_ml.xml b/inflection/resources/org/unicode/inflection/dictionary/inflectional_ml.xml
diff --git a/inflection/resources/org/unicode/inflection/features/grammar.xml b/inflection/resources/org/unicode/inflection/features/grammar.xml
@@ -1624,6 +1624,97 @@
             </category>
         </grammar>
     </language>
+    <language id="ml">
+        <grammar>
+            <category name="case">
+                <grammeme name="nominative"/>      <!-- no explicit marker; subject form -->
+                <grammeme name="accusative"/>      <!-- -യെ, -ായെ, marks direct object -->
+                <grammeme name="genitive"/>        <!-- -ന്റെ, -യുടെ (possessive) -->
+                <grammeme name="dative"/>          <!-- -ക്ക്, -ന് (to/for) -->
+                <grammeme name="instrumental"/>    <!-- -ആല് (by means of) -->
+                <grammeme name="locative"/>        <!-- -യില് (in/at) -->
+                <grammeme name="sociative"/>       <!-- -ഓടു് (along with) -->
+            </category>
+            <category name="number">
+                <grammeme name="singular"/>
+                <grammeme name="plural"/>
+            </category>
+            <category name="animacy">
+                <grammeme name="animate"/>
+                <grammeme name="inanimate"/>
+                <grammeme name="human"/>
+            </category>
+            <category name="person">
+                <restrictions>
+                    <restriction name="pos" value="pronoun"/>
+                    <restriction name="pos" value="verb"/>
+                </restrictions>
+                <grammeme name="first"/>
+                <grammeme name="second"/>
+                <grammeme name="third"/>
+            </category>
+            <category name="gender">
+                <restrictions>
+                    <restriction name="pos" value="pronoun"/>
+                    <restriction name="pos" value="verb"/>
+                    <restriction name="pos" value="noun"/>
+                </restrictions>
+                <grammeme name="masculine"/>
+                <grammeme name="feminine"/>
+                <grammeme name="neuter"/> <!-- e.g. for objects or animals -->
+            </category>
+            <category name="tense">
+                <restrictions>
+                    <restriction name="pos" value="verb"/>
+                </restrictions>
+                <grammeme name="past"/>
+                <grammeme name="present"/>
+                <grammeme name="future"/>
+            </category>
+            <category name="form">
+                <grammeme name="infinitive"/>
+                <grammeme name="participle"/>
+            </category>
+            <category name="determination">
+                <restrictions>
+                    <restriction name="pos" value="pronoun"/>
+                    <restriction name="case" value="genitive"/>
+                </restrictions>
+                <grammeme name="independent"/> <!-- e.g. mine -->
+                <grammeme name="dependent"/> <!-- e.g. my {object} -->
+            </category>
+            <category name="mood">
+                <restrictions>
+                    <restriction name="pos" value="verb"/>
+                </restrictions>
+                <grammeme name="indicative"/>
+                <grammeme name="imperative"/>
+                <grammeme name="subjunctive"/>
+            </category>
+            <category name="pronounType">
+                <restrictions>
+                    <restriction name="pos" value="pronoun"/>
+                </restrictions>
+                <grammeme name="personal"/>    <!-- regular pronouns like ഞാൻ, നീ -->
+                <grammeme name="reflexive"/>   <!-- e.g. താൻ, തങ്ങൾ -->
+            </category>
+            <category name="formality">
+                <restrictions>
+                    <restriction name="pos" value="verb"/>
+                    <restriction name="pos" value="pronoun"/>
+                </restrictions>
+                <grammeme name="formal"/>
+                <grammeme name="informal"/>
+            </category>
+            <category name="clusivity">
+                <restrictions>
+                    <restriction name="pos" value="pronoun"/>
+                </restrictions>
+                <grammeme name="inclusive"/>
+                <grammeme name="exclusive"/>
+            </category>
+        </grammar>
+    </language>
     <language id="ms">
         <grammar>
             <category name="clusivity">

diff --git a/inflection/resources/org/unicode/inflection/inflection/pronoun_ml.csv b/inflection/resources/org/unicode/inflection/inflection/pronoun_ml.csv
@@ -0,0 +1,75 @@
+അവൻ,third,singular,nominative,masculine
+അവൾ,third,singular,nominative,feminine
+അത്,third,singular,nominative,neuter
+അവനെ,third,singular,accusative,masculine
+അവന്റെ,third,singular,genitive,masculine,determination=dependent
+അവന്റെത്,third,singular,genitive,masculine,determination=independent
+അവളെ,third,singular,accusative,feminine
+അവളുടെ,third,singular,genitive,feminine,determination=dependent
+അവളുടേതു്,third,singular,genitive,feminine,determination=independent
+അതിനെ,third,singular,accusative,neuter
+അതിന്റെ,third,singular,genitive,neuter,determination=dependent
+അതിന്റേതു്,third,singular,genitive,neuter,determination=independent
+അവനിൽ,third,singular,locative,masculine
+അവനാൽ,third,singular,instrumental,masculine
+അവനോടു്,third,singular,sociative,masculine
+അവളിൽ,third,singular,locative,feminine
+അവളാൽ,third,singular,instrumental,feminine
+അവളോടു്,third,singular,sociative,feminine
+അതിൽ,third,singular,locative,neuter
+അതാൽ,third,singular,instrumental,neuter
+അതോടു്,third,singular,sociative,neuter
+അവർ,third,plural,nominative
+അവരെ,third,plural,accusative
+അവരുടെ,third,plural,genitive,determination=dependent
+അവരുടേതു്,third,plural,genitive,determination=independent
+അവരിൽ,third,plural,locative
+അവരാൽ,third,plural,instrumental
+അവരോടു്,third,plural,sociative
+നീ,second,singular,nominative,informal
+താങ്കൾ,second,singular,nominative,formal
+നിനക്ക്,second,singular,dative,informal
+താങ്കൾക്ക്,second,singular,dative,formal
+നിനെ,second,singular,accusative,informal
+താങ്കളെ,second,singular,accusative,formal
+നിന്റെ,second,singular,genitive,informal,determination=dependent
+നിന്റേതു്,second,singular,genitive,informal,determination=independent
+താങ്കളുടെ,second,singular,genitive,formal,determination=dependent
+താങ്കളുടേതു്,second,singular,genitive,formal,determination=independent
+നിനിൽ,second,singular,locative,informal
+നിനാൽ,second,singular,instrumental,informal
+നിനോടു്,second,singular,sociative,informal
+താങ്കളിൽ,second,singular,locative,formal
+താങ്കളാൽ,second,singular,instrumental,formal
+താങ്കളോടു്,second,singular,sociative,formal
+നിങ്ങൾ,second,plural,nominative,formal
+നിങ്ങളെ,second,plural,accusative,formal
+നിങ്ങൾക്ക്,second,plural,dative,formal
+നിങ്ങളുടെ,second,plural,genitive,formal,determination=dependent
+നിങ്ങളുടേതു്,second,plural,genitive,formal,determination=independent
+നിങ്ങളിൽ,second,plural,locative,formal
+നിങ്ങളാൽ,second,plural,instrumental,formal
+നിങ്ങളോടു്,second,plural,sociative,formal
+ഞാൻ,first,singular,nominative,exclusive
+എനിക്ക്,first,singular,dative
+നമുക്ക്,first,plural,dative,inclusive
+എന്നെ,first,singular,accusative,exclusive
+നമ്മെ,first,plural,accusative,inclusive
+എന്റെ,first,singular,genitive,determination=dependent,exclusive
+എന്റേത്,first,singular,genitive,determination=independent,exclusive
+എന്നിൽ,first,singular,locative
+എന്നാൽ,first,singular,instrumental
+എന്നോടു്,first,singular,sociative
+ഞങ്ങൾ,first,plural,nominative,exclusive
+നാം,first,plural,nominative,inclusive
+ഞങ്ങളെ,first,plural,accusative,exclusive
+ഞങ്ങൾക്ക്,first,plural,dative,exclusive
+ഞങ്ങളുടെ,first,plural,genitive,exclusive,determination=dependent
+ഞങ്ങളുടേത്,first,plural,genitive,exclusive,determination=independent
+നമ്മുടെ,first,plural,genitive,inclusive,determination=dependent
+നമ്മുടേതു്,first,plural,genitive,inclusive,determination=independent
+ഞങ്ങളിലു്,first,plural,locative,exclusive
+ഞങ്ങളാൽ,first,plural,instrumental,exclusive
+ഞങ്ങളോടു്,first,plural,sociative,exclusive
+താൻ,third,singular,nominative,reflexive
+തങ്ങൾ,third,plural,nominative,formal,reflexive
diff --git a/inflection/resources/org/unicode/inflection/locale/supported-locales.properties b/inflection/resources/org/unicode/inflection/locale/supported-locales.properties
@@ -15,6 +15,7 @@ locale.group.it=it_IT,it_CH
 locale.group.ja=ja_JP
 locale.group.ko=ko_KR
 locale.group.ms=ms_MY
+locale.group.ml=ml_IN
 locale.group.nb=nb_NO
 locale.group.nl=nl_NL,nl_BE
 locale.group.pt=pt_BR,pt_PT

diff --git a/inflection/resources/org/unicode/inflection/tokenizer/config_ml.properties b/inflection/resources/org/unicode/inflection/tokenizer/config_ml.properties
@@ -0,0 +1,7 @@
+#
+# Copyright 2025 Unicode Incorporated and others. All rights reserved.
+#
+tokenizer.implementation.class=DefaultTokenizer
+tokenizer.nonDecompound.file=/org/unicode/inflection/tokenizer/ml/nondecompound.tok
+tokenizer.decompound=(ശ്രീ)(.+?)(ഗുരു|സര്‍ക്കാര്‍)|(.+?)(ഗുരു|സര്‍ക്കാര്‍|ഉണ്ട്|ആണ്|ഇല്ല|ഒടൊപ്പം|ഉടൻ|ഓടെ|ഓട്|ഒപ്പം|തന്നെ|പോലും|പോലെ|ഉം|യ്|കളുടെ|ങ്ങളുടെ|ത്തിന്റെ|ൻ്റെ|ന്റെ|യുടേ|യുടെ|യാൽ|യിൽ|ഇൽ|ല്|ൽ|ക്ക്|മാർ|ങ്ങൾ|കൾ|നെ|യെ)
+
diff --git a/inflection/resources/org/unicode/inflection/tokenizer/ml/nondecompound.tok b/inflection/resources/org/unicode/inflection/tokenizer/ml/nondecompound.tok
@@ -0,0 +1,35 @@
+അമ്മ
+അച്ഛൻ
+അച്ഛി
+അമ്മൻ
+മകൻ
+മകൾ
+കുട്ടി
+കുട്ടികൾ
+ആൺകുട്ടി
+ആൺകുട്ടികൾ
+പെൺകുട്ടി
+പെൺകുട്ടികൾ
+കഥ
+ചിത്രം
+ചിത്രങ്ങൾ
+ഗ്രന്ഥം
+ഗ്രന്ഥങ്ങൾ
+മക്കൾ
+ഞാൻ
+നീ
+നിങ്ങൾ
+അവൻ
+അവൾ
+അവ
+അവർ
+ഇത്
+അത്
+ഇവ
+അവ
+ശ്രീ
+നാരായണ
+ഗുരു
+കേരളം
+സര്‍ക്കാര്‍
+കേരളസര്‍ക്കാര്‍
diff --git a/inflection/src/inflection/dialog/PronounConcept.cpp b/inflection/src/inflection/dialog/PronounConcept.cpp
@@ -228,7 +228,7 @@ PronounConcept::PronounConcept(const SemanticFeatureModel& model, std::u16string
     for (int32_t idx = 0; idx < pronounData->numValues(); idx++) {
         const auto& pronounEntry = pronounData->getPronounEntry(idx);
         std::u16string_view displayString(pronounEntry.first);
-        if (displayString.back() == u' ') {
+        if (!displayString.empty() && displayString.back() == u' ') {
             displayString.remove_suffix(1);
         }
         auto status = U_ZERO_ERROR;

diff --git a/inflection/src/inflection/dialog/language/MlCommonConceptFactory.cpp b/inflection/src/inflection/dialog/language/MlCommonConceptFactory.cpp
@@ -0,0 +1,25 @@
+/*
+ * Copyright 2025 Unicode Incorporated and others. All rights reserved.
+ */
+
+#include <inflection/dialog/language/MlCommonConceptFactory.hpp>
+#include <inflection/dialog/SpeakableString.hpp>
+#include <inflection/dialog/Plurality.hpp>
+
+namespace inflection::dialog::language {
+
+// In Malayalam, numbers generally follow the noun
+::inflection::dialog::SpeakableString
+MlCommonConceptFactory::quantifiedJoin(const ::inflection::dialog::SpeakableString& formattedNumber,
+                                       const ::inflection::dialog::SpeakableString& nounPhrase,
+                                       const ::std::u16string& /*measureWord*/,
+                                       Plurality::Rule countType) const
+{
+    ::inflection::dialog::SpeakableString space(u" ");
+    if (countType == Plurality::Rule::ONE) {
+        return nounPhrase + space + formattedNumber;
+    }
+    return formattedNumber + space + nounPhrase;
+}
+
+} // namespace inflection::dialog::language
diff --git a/inflection/src/inflection/dialog/language/MlCommonConceptFactory.hpp b/inflection/src/inflection/dialog/language/MlCommonConceptFactory.hpp
@@ -0,0 +1,28 @@
+/*
+ * Copyright 2025 Unicode Incorporated and others. All rights reserved.
+ */
+#pragma once
+
+#include <inflection/dialog/language/fwd.hpp>
+#include <inflection/dialog/CommonConceptFactoryImpl.hpp>
+#include <inflection/grammar/synthesis/fwd.hpp>
+#include <inflection/dialog/Plurality.hpp>
+
+namespace inflection::dialog::language {
+
+class MlCommonConceptFactory : public CommonConceptFactoryImpl {
+    using super = CommonConceptFactoryImpl;
+
+public:
+    explicit MlCommonConceptFactory(const ::inflection::util::ULocale& language);
+    ~MlCommonConceptFactory() override;
+
+protected:
+    ::inflection::dialog::SpeakableString quantifiedJoin(
+        const ::inflection::dialog::SpeakableString& formattedNumber,
+        const ::inflection::dialog::SpeakableString& nounPhrase,
+        const ::std::u16string& measureWord,
+        ::inflection::dialog::Plurality::Rule countType) const override;
+};
+
+} // namespace inflection::dialog::language
diff --git a/inflection/src/inflection/dialog/language/fwd.hpp b/inflection/src/inflection/dialog/language/fwd.hpp
@@ -1,4 +1,5 @@
 /*
+ * Copyright 2025 Unicode Incorporated and others. All rights reserved.
  * Copyright 2017-2024 Apple Inc. All rights reserved.
  */
 // Forward declarations for inflection.dialog.language
@@ -28,6 +29,7 @@ namespace inflection
             class JaCommonConceptFactory;
             class KoCommonConceptFactory;
             class KoCommonConceptFactory_KoAndList;
+            class MlCommonConceptFactory;
             class MsCommonConceptFactory;
             class NbCommonConceptFactory;
             class NlCommonConceptFactory;

diff --git a/inflection/src/inflection/grammar/synthesis/GrammarSynthesizerFactory.cpp b/inflection/src/inflection/grammar/synthesis/GrammarSynthesizerFactory.cpp
@@ -1,4 +1,5 @@
 /*
+ * Copyright 2025 Unicode Incorporated and others. All rights reserved.
  * Copyright 2017-2024 Apple Inc. All rights reserved.
  */
 #include <inflection/grammar/synthesis/GrammarSynthesizerFactory.hpp>
@@ -13,6 +14,7 @@
 #include <inflection/grammar/synthesis/HiGrammarSynthesizer.hpp>
 #include <inflection/grammar/synthesis/ItGrammarSynthesizer.hpp>
 #include <inflection/grammar/synthesis/KoGrammarSynthesizer.hpp>
+#include <inflection/grammar/synthesis/MlGrammarSynthesizer.hpp>
 #include <inflection/grammar/synthesis/NbGrammarSynthesizer.hpp>
 #include <inflection/grammar/synthesis/NlGrammarSynthesizer.hpp>
 #include <inflection/grammar/synthesis/PtGrammarSynthesizer.hpp>
@@ -41,6 +43,7 @@ static const ::std::map<::inflection::util::ULocale, addSemanticFeatures>& GRAMM
         {::inflection::util::LocaleUtils::HINDI(), &HiGrammarSynthesizer::addSemanticFeatures},
         {::inflection::util::LocaleUtils::ITALIAN(), &ItGrammarSynthesizer::addSemanticFeatures},
         {::inflection::util::LocaleUtils::KOREAN(), &KoGrammarSynthesizer::addSemanticFeatures},
+        {::inflection::util::LocaleUtils::MALAYALAM(), &MlGrammarSynthesizer::addSemanticFeatures},
         {::inflection::util::LocaleUtils::NORWEGIAN(), &NbGrammarSynthesizer::addSemanticFeatures},
         {::inflection::util::LocaleUtils::DUTCH(), &NlGrammarSynthesizer::addSemanticFeatures},
         {::inflection::util::LocaleUtils::PORTUGUESE(), &PtGrammarSynthesizer::addSemanticFeatures},