lda-ruby 0.4.0 → 0.5.0

data/ext/lda-ruby/cokus.h

@@ -12,9 +12,9 @@
 
 typedef unsigned long uint32;
 
-#define N              (624)                 // length of state vector
-#define M              (397)                 // a period parameter
-#define K              (0x9908B0DFU)         // a magic constant
+#define COKUS_N        (624)                 // length of state vector
+#define COKUS_M        (397)                 // a period parameter
+#define COKUS_K        (0x9908B0DFU)         // a magic constant
 #define hiBit(u)       ((u) & 0x80000000U)   // mask all but highest   bit of u
 #define loBit(u)       ((u) & 0x00000001U)   // mask all but lowest    bit of u
 #define loBits(u)      ((u) & 0x7FFFFFFFU)   // mask     the highest   bit of u

data/ext/lda-ruby/lda-inference.c

@@ -435,9 +435,9 @@ void infer(char* model_root, char* save, corpus* corpus) {
 int main(int argc, char* argv[]) {
 	corpus* corpus;
 
-	long t1;
+	time_t t1;
 	(void) time(&t1);
-	seedMT(t1);
+	seedMT((uint32) t1);
 		// seedMT(4357U);
 
 	if (argc > 1)

data/ext/lda-ruby/utils.c

@@ -1,5 +1,9 @@
 #include "utils.h"
 
+#ifdef _WIN32
+#include <direct.h>
+#endif
+
 /*
  * given log(a) and log(b), return log(a + b)
  *
@@ -85,7 +89,11 @@ double log_gamma(double x)
 
 void make_directory(char* name)
 {
+#ifdef _WIN32
+    _mkdir(name);
+#else
     mkdir(name, S_IRUSR|S_IWUSR|S_IXUSR);
+#endif
 }
 
 

data/ext/lda-ruby-rust/README.md

@@ -8,6 +8,8 @@ Current scope:
 - Exposes capability hooks:
   - `Lda::RustBackend.available?`
   - `Lda::RustBackend.abi_version`
+  - `Lda::RustBackend.corpus_session_count`
+  - `Lda::RustBackend.corpus_session_exists(session_id)`
   - `Lda::RustBackend.before_em(start, num_docs, num_terms)`
   - `Lda::RustBackend.topic_weights_for_word(beta, gamma, word_index, min_probability)`
   - `Lda::RustBackend.accumulate_topic_term_counts(topic_term_counts, phi_d, words, counts)`
@@ -17,6 +19,18 @@ Current scope:
   - `Lda::RustBackend.average_gamma_shift(previous_gamma, current_gamma)`
   - `Lda::RustBackend.topic_document_probability(phi_tensor, document_counts, num_topics, min_probability)`
   - `Lda::RustBackend.seeded_topic_term_probabilities(document_words, document_counts, topics, terms, min_probability)`
+  - `Lda::RustBackend.random_topic_term_probabilities(topics, terms, min_probability, random_seed)`
+  - `Lda::RustBackend.create_corpus_session(document_words, document_counts, terms)`
+  - `Lda::RustBackend.replace_corpus_session(session_id, document_words, document_counts, terms)`
+  - `Lda::RustBackend.drop_corpus_session(session_id)`
+  - `Lda::RustBackend.configure_corpus_session(session_id, topics, max_iter, convergence, em_max_iter, em_convergence, init_alpha, min_probability)`
+  - `Lda::RustBackend.run_em(initial_beta, document_words, document_counts, max_iter, convergence, em_max_iter, em_convergence, init_alpha, min_probability)`
+  - `Lda::RustBackend.run_em_with_start(start, document_words, document_counts, topics, terms, max_iter, convergence, em_max_iter, em_convergence, init_alpha, min_probability)`
+  - `Lda::RustBackend.run_em_with_start_seed(start, document_words, document_counts, topics, terms, max_iter, convergence, em_max_iter, em_convergence, init_alpha, min_probability, random_seed)`
+  - `Lda::RustBackend.run_em_on_session(session_id, start, topics, max_iter, convergence, em_max_iter, em_convergence, init_alpha, min_probability, random_seed)`
+  - `Lda::RustBackend.run_em_on_session_start(session_id, start, random_seed)`
+  - `Lda::RustBackend.run_em_on_session_with_start_seed(session_id, start, topics, max_iter, convergence, em_max_iter, em_convergence, init_alpha, min_probability, random_seed)`
+  - `Lda::RustBackend.run_em_on_session_with_corpus(session_id, document_words, document_counts, terms, start, topics, max_iter, convergence, em_max_iter, em_convergence, init_alpha, min_probability, random_seed)`
 
 Hot-path kernels currently executed in Rust when `backend: :rust` is active:
 - topic weights for a word across topics
@@ -27,6 +41,17 @@ Hot-path kernels currently executed in Rust when `backend: :rust` is active:
 - gamma convergence shift reduction between EM iterations
 - topic-document average log-probability computation
 - seeded topic-term initialization
+- random topic-term initialization with explicit seed control
+- EM outer-loop orchestration with convergence checks (`run_em`)
+- start-aware deterministic EM orchestration (`run_em_with_start` for `seeded`/`deterministic`)
+- start-aware seeded and random EM orchestration with explicit seed control (`run_em_with_start_seed`)
+- unified session-settings orchestration (`run_em_on_session`) that applies settings and executes EM in one call
+- session-based EM orchestration against Rust-managed corpus lifecycle (`create_corpus_session` + `run_em_on_session_with_start_seed`)
+- settings-aware session orchestration (`configure_corpus_session` + `run_em_on_session_start`)
+- managed corpus orchestration (`run_em_on_session_with_corpus`) that can recreate missing sessions and, if session-backed execution cannot be used, falls back internally to direct start-aware execution inside Rust
+- `Lda::Backends::Rust` prefers `run_em_on_session_with_corpus` whenever a cached Rust corpus snapshot is available, even if no session id is currently cached locally
+- direct and legacy beta-input compatibility fallbacks both reuse the backend's cached Rust corpus snapshot instead of rebuilding corpus arrays in Ruby
+- unknown EM start modes in seed-aware orchestration follow Ruby's non-seeded fallback behavior (seeded by explicit `random_seed`)
 
 Remaining numeric LDA kernels are still provided by the pure Ruby backend and will move incrementally.
 

data/ext/lda-ruby-rust/extconf.rb

@@ -61,27 +61,39 @@ module Lda
         success or raise "cargo build --release failed"
       end
 
-      source = File.join(__dir__, "target", "release", rust_cdylib_filename)
-      raise "Rust extension artifact not found at #{source}" unless File.exist?(source)
+      source = rust_cdylib_source
+      raise "Rust extension artifact not found at #{rust_cdylib_candidates.join(', ')}" unless source
 
       destination = File.expand_path("../../lib/lda_ruby_rust.#{RbConfig::CONFIG.fetch('DLEXT')}", __dir__)
       FileUtils.cp(source, destination)
       puts("Staged Rust extension to #{destination}")
     end
 
-    def rust_cdylib_filename
+    def rust_cdylib_source
+      rust_cdylib_candidates.find { |path| File.exist?(path) }
+    end
+
+    def rust_cdylib_candidates
+      rust_cdylib_filenames.map { |filename| File.join(__dir__, "target", "release", filename) }
+    end
+
+    def rust_cdylib_filenames
       host_os = RbConfig::CONFIG.fetch("host_os")
-      extension =
-        case host_os
-        when /darwin/
-          "dylib"
-        when /mswin|mingw|cygwin/
-          "dll"
-        else
-          "so"
-        end
+      case host_os
+      when /mswin|mingw|cygwin/
+        # On Windows cargo may emit either prefixed or unprefixed DLL names.
+        ["lda_ruby_rust.dll", "liblda_ruby_rust.dll"]
+      else
+        extension =
+          case host_os
+          when /darwin/
+            "dylib"
+          else
+            "so"
+          end
 
-      "liblda_ruby_rust.#{extension}"
+        ["liblda_ruby_rust.#{extension}"]
+      end
     end
 
     def rust_build_env

data/ext/lda-ruby-rust/include/strings.h

@@ -0,0 +1,35 @@
+#ifndef LDA_RUBY_BINDGEN_STRINGS_H
+#define LDA_RUBY_BINDGEN_STRINGS_H
+
+#include <string.h>
+
+/*
+ * RubyInstaller headers may include <strings.h> on Windows, but Clang-based
+ * bindgen runs can miss that header in this environment. Provide compatibility
+ * aliases for bindgen preprocessing.
+ */
+#if defined(_WIN32) && !defined(__MINGW32__)
+#ifndef bzero
+#define bzero(ptr, size) memset((ptr), 0, (size))
+#endif
+#ifndef bcmp
+#define bcmp(a, b, n) memcmp((a), (b), (n))
+#endif
+#ifndef bcopy
+#define bcopy(src, dst, n) memmove((dst), (src), (n))
+#endif
+#ifndef index
+#define index strchr
+#endif
+#ifndef rindex
+#define rindex strrchr
+#endif
+#ifndef strcasecmp
+#define strcasecmp _stricmp
+#endif
+#ifndef strncasecmp
+#define strncasecmp _strnicmp
+#endif
+#endif
+
+#endif