fasttext 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 374cacde6bb0c017d6d787dd41180d5de774929a34cad2e356546e02c89345b6
-  data.tar.gz: b4c767a2d263053148a2f02537fd2eff0883840cf8da5e4c5f437c5fcaca55da
+  metadata.gz: 9978bfe50053f76326bfd7f97b7acb6ff7af67ca4acba77f21de5000175428b1
+  data.tar.gz: 7488a7dc79f8d2e62636468f18e916b8bfbccec59897909a1f666a3ff02a1d86
 SHA512:
-  metadata.gz: 65dceed43c0cb7f84779b85b8387bdd67ab43b779fff5577e4bb13202ddee6a0d27fbdcab5f82af40fc070925c6e30ce73090c7db7d21da48a79810011235fd5
-  data.tar.gz: c565ef3d2c8132e84ec84a2d33b04caf6c8dead8928287966db1c34814673df3ca5a3d8372e3994478fd364f95c806a2515fa7f2106bef30deaf9e89f19a938a
+  metadata.gz: ffd2b8f15be1fdbbd0a0b10dfe94c482645c2961ca119af160c8a9952bb95380c5512fb2de85b9885c773f3393fbcc776efa2dcaf94dd390c459470974a07ef7
+  data.tar.gz: 831fa02b20d7b594dc3ceefe9b33499df37d75436ea724369b3dc976d950b72c533ae400a1d4c26838381746c94c227bccb50f9ca341d5575e87dd88e2908e41

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+## 0.5.0 (2026-04-09)
+
+- Dropped support for Ruby < 3.3
+
+## 0.4.1 (2025-10-26)
+
+- Fixed error with Rice 4.7
+
 ## 0.4.0 (2024-10-22)
 
 - Dropped support for Ruby < 3.1

data/LICENSE.txt

@@ -1,7 +1,7 @@
 MIT License
 
 Copyright (c) 2016-present, Facebook, Inc.
-Copyright (c) 2019-2024 Andrew Kane
+Copyright (c) 2019-2025 Andrew Kane
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/README.md

@@ -167,8 +167,8 @@ FastText::Classifier.new(
   dim: 100,                   # size of word vectors
   ws: 5,                      # size of the context window
   epoch: 5,                   # number of epochs
-  min_count: 1,               # minimal number of word occurences
-  min_count_label: 1,         # minimal number of label occurences
+  min_count: 1,               # minimal number of word occurrences
+  min_count_label: 1,         # minimal number of label occurrences
   minn: 0,                    # min length of char ngram
   maxn: 0,                    # max length of char ngram
   neg: 5,                     # number of negatives sampled
@@ -197,7 +197,7 @@ FastText::Vectorizer.new(
   dim: 100,                   # size of word vectors
   ws: 5,                      # size of the context window
   epoch: 5,                   # number of epochs
-  min_count: 5,               # minimal number of word occurences
+  min_count: 5,               # minimal number of word occurrences
   minn: 3,                    # min length of char ngram
   maxn: 6,                    # max length of char ngram
   neg: 5,                     # number of negatives sampled

data/ext/fasttext/ext.cpp

@@ -1,15 +1,21 @@
 // stdlib
 #include <cmath>
 #include <cstdint>
-#include <iterator>
+#include <fstream>
+#include <memory>
 #include <sstream>
 #include <stdexcept>
+#include <string>
+#include <utility>
+#include <vector>
 
 // fasttext
 #include <args.h>
 #include <autotune.h>
 #include <densematrix.h>
+#include <dictionary.h>
 #include <fasttext.h>
+#include <meter.h>
 #include <real.h>
 #include <vector.h>
 
@@ -20,41 +26,35 @@
 using fasttext::Args;
 using fasttext::FastText;
 
-using Rice::Array;
-using Rice::Constructor;
-using Rice::Module;
-using Rice::define_class_under;
-using Rice::define_module;
-using Rice::define_module_under;
-
-namespace Rice::detail
-{
+namespace Rice::detail {
   template<>
-  class To_Ruby<std::vector<std::pair<fasttext::real, std::string>>>
-  {
+  class To_Ruby<std::vector<std::pair<fasttext::real, std::string>>> {
   public:
-    VALUE convert(std::vector<std::pair<fasttext::real, std::string>> const & x)
-    {
-      Array ret;
+    explicit To_Ruby(Arg* arg) : arg_(arg) { }
+
+    VALUE convert(const std::vector<std::pair<fasttext::real, std::string>>& x) {
+      VALUE ret = detail::protect(rb_ary_new2, x.size());
       for (const auto& v : x) {
-        Array a;
-        a.push(v.first);
-        a.push(v.second);
-        ret.push(a);
+        VALUE p1 = To_Ruby<fasttext::real>().convert(v.first);
+        VALUE p2 = To_Ruby<std::string>().convert(v.second);
+        VALUE a = detail::protect(rb_ary_new3, 2, p1, p2);
+        detail::protect(rb_ary_push, ret, a);
       }
       return ret;
     }
+
+  private:
+    Arg* arg_ = nullptr;
   };
-}
+} // namespace Rice::detail
 
 extern "C"
-void Init_ext()
-{
-  Module rb_mFastText = define_module("FastText");
-  Module rb_mExt = define_module_under(rb_mFastText, "Ext");
+void Init_ext() {
+  Rice::Module rb_mFastText = Rice::define_module("FastText");
+  Rice::Module rb_mExt = Rice::define_module_under(rb_mFastText, "Ext");
 
-  define_class_under<Args>(rb_mExt, "Args")
-    .define_constructor(Constructor<Args>())
+  Rice::define_class_under<Args>(rb_mExt, "Args")
+    .define_constructor(Rice::Constructor<Args>())
     .define_attr("input", &Args::input)
     .define_attr("output", &Args::output)
     .define_attr("lr", &Args::lr)
@@ -110,24 +110,24 @@ void Init_ext()
     .define_attr("autotune_duration", &Args::autotuneDuration)
     .define_attr("autotune_model_size", &Args::autotuneModelSize);
 
-  define_class_under<FastText>(rb_mExt, "Model")
-    .define_constructor(Constructor<FastText>())
+  Rice::define_class_under<FastText>(rb_mExt, "Model")
+    .define_constructor(Rice::Constructor<FastText>())
     .define_method(
       "words",
       [](FastText& m) {
         std::shared_ptr<const fasttext::Dictionary> d = m.getDictionary();
         std::vector<int64_t> freq = d->getCounts(fasttext::entry_type::word);
 
-        Array vocab_list;
-        Array vocab_freq;
+        Rice::Array vocab_list;
+        Rice::Array vocab_freq;
         for (int32_t i = 0; i < d->nwords(); i++) {
-          vocab_list.push(d->getWord(i));
-          vocab_freq.push(freq[i]);
+          vocab_list.push(d->getWord(i), false);
+          vocab_freq.push(freq.at(i), false);
         }
 
-        Array ret;
-        ret.push(vocab_list);
-        ret.push(vocab_freq);
+        Rice::Array ret;
+        ret.push(vocab_list, false);
+        ret.push(vocab_freq, false);
         return ret;
       })
     .define_method(
@@ -136,22 +136,22 @@ void Init_ext()
         std::shared_ptr<const fasttext::Dictionary> d = m.getDictionary();
         std::vector<int64_t> freq = d->getCounts(fasttext::entry_type::label);
 
-        Array vocab_list;
-        Array vocab_freq;
+        Rice::Array vocab_list;
+        Rice::Array vocab_freq;
         for (int32_t i = 0; i < d->nlabels(); i++) {
-          vocab_list.push(d->getLabel(i));
-          vocab_freq.push(freq[i]);
+          vocab_list.push(d->getLabel(i), false);
+          vocab_freq.push(freq.at(i), false);
         }
 
-        Array ret;
-        ret.push(vocab_list);
-        ret.push(vocab_freq);
+        Rice::Array ret;
+        ret.push(vocab_list, false);
+        ret.push(vocab_freq, false);
         return ret;
       })
     .define_method(
       "test",
       [](FastText& m, const std::string& filename, int32_t k) {
-        std::ifstream ifs(filename);
+        std::ifstream ifs{filename};
         if (!ifs.is_open()) {
           throw std::invalid_argument("Test file cannot be opened!");
         }
@@ -159,21 +159,21 @@ void Init_ext()
         m.test(ifs, k, 0.0, meter);
         ifs.close();
 
-        Array ret;
-        ret.push(meter.nexamples());
-        ret.push(meter.precision());
-        ret.push(meter.recall());
+        Rice::Array ret;
+        ret.push(meter.nexamples(), false);
+        ret.push(meter.precision(), false);
+        ret.push(meter.recall(), false);
         return ret;
       })
     .define_method(
       "load_model",
-      [](FastText& m, const std::string& s) {
-        m.loadModel(s);
+      [](FastText& m, const std::string& filename) {
+        m.loadModel(filename);
       })
     .define_method(
       "save_model",
-      [](FastText& m, const std::string& s) {
-        m.saveModel(s);
+      [](FastText& m, const std::string& filename) {
+        m.saveModel(filename);
       })
     .define_method("dimension", &FastText::getDimension)
     .define_method("quantized?", &FastText::isQuant)
@@ -182,7 +182,7 @@ void Init_ext()
     .define_method(
       "predict",
       [](FastText& m, const std::string& text, int32_t k, float threshold) {
-        std::stringstream ioss(text);
+        std::stringstream ioss{text};
         std::vector<std::pair<fasttext::real, std::string>> predictions;
         m.predictLine(ioss, predictions, k, threshold);
         return predictions;
@@ -197,12 +197,13 @@ void Init_ext()
     .define_method(
       "word_vector",
       [](FastText& m, const std::string& word) {
-        auto dimension = m.getDimension();
-        fasttext::Vector vec = fasttext::Vector(dimension);
+        int dimension = m.getDimension();
+        fasttext::Vector vec{dimension};
         m.getWordVector(vec, word);
-        Array ret;
-        for (size_t i = 0; i < vec.size(); i++) {
-          ret.push(vec[i]);
+        Rice::Array ret;
+        // fasttext::Vector uses int64_t for size and indexing
+        for (int64_t i = 0; i < vec.size(); i++) {
+          ret.push(vec[i], false);
         }
         return ret;
       })
@@ -214,22 +215,23 @@ void Init_ext()
         std::shared_ptr<const fasttext::Dictionary> d = m.getDictionary();
         d->getSubwords(word, ngrams, subwords);
 
-        Array ret;
+        Rice::Array ret;
         for (const auto& subword : subwords) {
-          ret.push(subword);
+          ret.push(subword, false);
         }
         return ret;
       })
     .define_method(
       "sentence_vector",
       [](FastText& m, const std::string& text) {
-        std::istringstream in(text);
-        auto dimension = m.getDimension();
-        fasttext::Vector vec = fasttext::Vector(dimension);
+        std::istringstream in{text};
+        int dimension = m.getDimension();
+        fasttext::Vector vec{dimension};
         m.getSentenceVector(in, vec);
-        Array ret;
-        for (size_t i = 0; i < vec.size(); i++) {
-          ret.push(vec[i]);
+        Rice::Array ret;
+        // fasttext::Vector uses int64_t for size and indexing
+        for (int64_t i = 0; i < vec.size(); i++) {
+          ret.push(vec[i], false);
         }
         return ret;
       })
@@ -237,7 +239,7 @@ void Init_ext()
       "train",
       [](FastText& m, Args& a) {
         if (a.hasAutotune()) {
-          fasttext::Autotune autotune(std::shared_ptr<fasttext::FastText>(&m, [](fasttext::FastText*) {}));
+          fasttext::Autotune autotune{std::shared_ptr<fasttext::FastText>(&m, [](fasttext::FastText*) {})};
           autotune.train(a);
         } else {
           m.train(a);

data/lib/fasttext/version.rb

@@ -1,3 +1,3 @@
 module FastText
-  VERSION = "0.4.0"
+  VERSION = "0.5.0"
 end

data/lib/fasttext.rb

@@ -23,7 +23,7 @@ module FastText
         else
           FastText::Vectorizer.new
         end
-      model.instance_variable_set("@m", m)
+      model.instance_variable_set(:@m, m)
       model
     end
 

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: fasttext
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Andrew Kane
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-10-22 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rice
@@ -16,15 +15,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 4.3.3
+        version: '4.7'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 4.3.3
-description:
+        version: '4.7'
 email: andrew@ankane.org
 executables: []
 extensions:
@@ -75,7 +73,6 @@ homepage: https://github.com/ankane/fastText-ruby
 licenses:
 - MIT
 metadata: {}
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -83,15 +80,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '3.1'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.16
-signing_key:
+rubygems_version: 4.0.6
 specification_version: 4
 summary: Efficient text classification and representation learning for Ruby
 test_files: []