From 39d22fc4fbf321f1cc5f82b24f2c8f8304cdcae5 Mon Sep 17 00:00:00 2001
From: Omar Shrit <omar@shrit.me>
Date: Sun, 16 Jan 2022 16:21:27 +0000
Subject: [PATCH] Move constructor to implementation

Signed-off-by: Omar Shrit <omar@shrit.me>
---
 .../core/kernels/pspectrum_string_kernel.hpp  | 59 +------------------
 .../kernels/pspectrum_string_kernel_impl.hpp  | 59 +++++++++++++++++++
 2 files changed, 61 insertions(+), 57 deletions(-)

diff --git a/src/mlpack/core/kernels/pspectrum_string_kernel.hpp b/src/mlpack/core/kernels/pspectrum_string_kernel.hpp
index dc5ff24415..d76acb24a2 100644
--- a/src/mlpack/core/kernels/pspectrum_string_kernel.hpp
+++ b/src/mlpack/core/kernels/pspectrum_string_kernel.hpp
@@ -72,64 +72,9 @@ class PSpectrumStringKernel
    * @param datasets Sets of string data.
    * @param p The length of substrings to search.
    */
-  PSpectrumStringKernel(const std::vector<std::vector<std::string> >& datasets,
-                        const size_t p) : p(p)
-  {
-    // We have to assemble the counts of substrings.  This is not a particularly
-    // fast operation, unfortunately, but it only needs to be done once.
-    Log::Info << "Assembling counts of substrings of length " << p << "."
-        << std::endl;
+  inline PSpectrumStringKernel(const std::vector<std::vector<std::string> >& datasets,
+                               const size_t p);
 
-    // Resize for number of datasets.
-    counts.resize(datasets.size());
-
-    for (size_t dataset = 0; dataset < datasets.size(); ++dataset)
-    {
-      const std::vector<std::string>& set = datasets[dataset];
-
-      // Resize for number of strings in dataset.
-      counts[dataset].resize(set.size());
-
-      // Inspect each string in the dataset.
-      for (size_t index = 0; index < set.size(); ++index)
-      {
-        // Convenience references.
-        const std::string& str = set[index];
-        std::map<std::string, int>& mapping = counts[dataset][index];
-
-        size_t start = 0;
-        while ((start + p) <= str.length())
-        {
-          std::string sub = str.substr(start, p);
-
-          // Convert all characters to lowercase.
-          bool invalid = false;
-          for (size_t j = 0; j < p; ++j)
-          {
-            if (!isalnum(sub[j]))
-            {
-              invalid = true;
-              break; // Only consider substrings with alphanumerics.
-            }
-
-            sub[j] = tolower(sub[j]);
-          }
-
-          // Increment position in string.
-          ++start;
-
-          if (!invalid)
-          {
-            // Add to the map.
-            ++mapping[sub];
-          }
-        }
-      }
-    }
-
-    Log::Info << "Substring extraction complete." << std::endl;
-  }
-  
   /**
    * Evaluate the kernel for the string indices given.  As mentioned in the
    * class documentation, a and b should be 2-element vectors, where the first
diff --git a/src/mlpack/core/kernels/pspectrum_string_kernel_impl.hpp b/src/mlpack/core/kernels/pspectrum_string_kernel_impl.hpp
index cf04b8bdd6..616ae8c498 100644
--- a/src/mlpack/core/kernels/pspectrum_string_kernel_impl.hpp
+++ b/src/mlpack/core/kernels/pspectrum_string_kernel_impl.hpp
@@ -22,6 +22,65 @@
 namespace mlpack {
 namespace kernel {
 
+inline PSpectrumStringKernel::PSpectrumStringKernel(
+    const std::vector<std::vector<std::string> >& datasets,
+    const size_t p) : p(p)
+{
+  // We have to assemble the counts of substrings.  This is not a particularly
+  // fast operation, unfortunately, but it only needs to be done once.
+  Log::Info << "Assembling counts of substrings of length " << p << "."
+      << std::endl;
+
+  // Resize for number of datasets.
+  counts.resize(datasets.size());
+
+  for (size_t dataset = 0; dataset < datasets.size(); ++dataset)
+  {
+    const std::vector<std::string>& set = datasets[dataset];
+
+    // Resize for number of strings in dataset.
+    counts[dataset].resize(set.size());
+
+    // Inspect each string in the dataset.
+    for (size_t index = 0; index < set.size(); ++index)
+    {
+      // Convenience references.
+      const std::string& str = set[index];
+      std::map<std::string, int>& mapping = counts[dataset][index];
+
+      size_t start = 0;
+      while ((start + p) <= str.length())
+      {
+        std::string sub = str.substr(start, p);
+
+        // Convert all characters to lowercase.
+        bool invalid = false;
+        for (size_t j = 0; j < p; ++j)
+        {
+          if (!isalnum(sub[j]))
+          {
+            invalid = true;
+            break; // Only consider substrings with alphanumerics.
+          }
+
+          sub[j] = tolower(sub[j]);
+        }
+
+        // Increment position in string.
+        ++start;
+
+        if (!invalid)
+        {
+          // Add to the map.
+          ++mapping[sub];
+        }
+      }
+    }
+  }
+
+  Log::Info << "Substring extraction complete." << std::endl;
+}
+
 /**
  * Evaluate the kernel for the string indices given.  As mentioned in the class
  * documentation, a and b should be 2-element vectors, where the first element