Merge pull request #1917

6e679478 mnemonics: sanity checks for word lists (moneromooo-monero)
e98f1114 mnemonics: misc cleanup (moneromooo-monero)

11 files changed, 72 insertions, 103 deletions

diff --git a/src/mnemonics/dutch.h b/src/mnemonics/dutch.h
index d0a972e59..0d7a637e6 100644
--- a/src/mnemonics/dutch.h
+++ b/src/mnemonics/dutch.h
@@ -49,9 +49,7 @@ namespace Language
   class Dutch: public Base

   {

   public:

-    Dutch()

-    {

-      word_list = new std::vector<std::string>({

+    Dutch(): Base("Dutch", std::vector<std::string>({

         "aalglad",

         "aalscholver",

         "aambeeld",

@@ -1678,11 +1676,8 @@ namespace Language
         "zwiep",

         "zwijmel",

         "zworen"

-      });

-      unique_prefix_length = 4;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "Dutch";

+      }), 4)

+    {

       populate_maps();

     }

   };

diff --git a/src/mnemonics/english.h b/src/mnemonics/english.h
index 703c7780c..e6cfa8951 100644
--- a/src/mnemonics/english.h
+++ b/src/mnemonics/english.h
@@ -49,9 +49,7 @@ namespace Language
   class English: public Base

   {

   public:

-    English()

-    {

-      word_list = new std::vector<std::string>({

+    English(): Base("English", std::vector<std::string>({

         "abbey",

         "abducts",

         "ability",

@@ -1678,11 +1676,8 @@ namespace Language
         "zombie",

         "zones",

         "zoom"

-      });

-      unique_prefix_length = 3;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "English";

+      }), 3)

+    {

       populate_maps();

     }

   };

diff --git a/src/mnemonics/french.h b/src/mnemonics/french.h
index 2f6eb7e8a..6cf44a197 100644
--- a/src/mnemonics/french.h
+++ b/src/mnemonics/french.h
@@ -49,9 +49,7 @@ namespace Language
   class French: public Base
   {
   public:
-    French()
-    {
-      word_list = new std::vector<std::string>({
+    French(): Base("French", std::vector<std::string>({
         "abandon",
         "abattre",
         "aboi",
@@ -1678,11 +1676,8 @@ namespace Language
         "zinc",
         "zone",
         "zoom"
-      });
-      unique_prefix_length = 4;
-      word_map = new std::unordered_map<std::string, uint32_t>;
-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;
-      language_name = "French";
+      }), 4)
+    {
       populate_maps();
     }
   };
diff --git a/src/mnemonics/german.h b/src/mnemonics/german.h
index a9614e4a9..1a1e6b467 100644
--- a/src/mnemonics/german.h
+++ b/src/mnemonics/german.h
@@ -51,9 +51,7 @@ namespace Language
   class German: public Base

   {

   public:

-    German()

-    {

-      word_list = new std::vector<std::string>({

+    German(): Base("German", std::vector<std::string>({

         "Abakus",

         "Abart",

         "abbilden",

@@ -1680,11 +1678,8 @@ namespace Language
         "Zündung",

         "Zweck",

         "Zyklop"

-      });

-      unique_prefix_length = 4;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "German";

+      }), 4)
+    {
       populate_maps();

     }

   };

diff --git a/src/mnemonics/italian.h b/src/mnemonics/italian.h
index 24ed67442..28cee9d9a 100644
--- a/src/mnemonics/italian.h
+++ b/src/mnemonics/italian.h
@@ -51,9 +51,7 @@ namespace Language
   class Italian: public Base

   {

   public:

-    Italian()

-    {

-      word_list = new std::vector<std::string>({

+    Italian(): Base("Italian", std::vector<std::string>({

         "abbinare",

         "abbonato",

         "abisso",

@@ -1680,11 +1678,8 @@ namespace Language
         "zolfo",

         "zombie",

         "zucchero"

-      });

-      unique_prefix_length = 4;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "Italian";

+      }), 4)
+    {
       populate_maps();

     }

   };

diff --git a/src/mnemonics/japanese.h b/src/mnemonics/japanese.h
index b437ae2af..09d05d132 100644
--- a/src/mnemonics/japanese.h
+++ b/src/mnemonics/japanese.h
@@ -51,9 +51,7 @@ namespace Language
   class Japanese: public Base

   {

   public:

-    Japanese()

-    {

-      word_list = new std::vector<std::string>({

+    Japanese(): Base("Japanese", std::vector<std::string>({

         "あいこくしん",

         "あいさつ",

         "あいだ",

@@ -1680,11 +1678,8 @@ namespace Language
         "ひさん",

         "びじゅつかん",

         "ひしょ"

-      });

-      unique_prefix_length = 3;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "Japanese";

+      }), 3)

+    {

       populate_maps();

     }

   };

diff --git a/src/mnemonics/language_base.h b/src/mnemonics/language_base.h
index 5ad4211d4..8f0a7a9d3 100644
--- a/src/mnemonics/language_base.h
+++ b/src/mnemonics/language_base.h
@@ -38,6 +38,7 @@
 #include <vector>

 #include <unordered_map>

 #include <string>

+#include "misc_log_ex.h"

 

 /*!

  * \namespace Language

@@ -73,44 +74,62 @@ namespace Language
   class Base

   {

   protected:

-    std::vector<std::string> *word_list; /*!< A pointer to the array of words */

-    std::unordered_map<std::string, uint32_t> *word_map; /*!< hash table to find word's index */

-    std::unordered_map<std::string, uint32_t> *trimmed_word_map; /*!< hash table to find word's trimmed index */

+    enum {

+      ALLOW_SHORT_WORDS = 1<<0,

+      ALLOW_DUPLICATE_PREFIXES = 1<<1,

+    };

+    const std::vector<std::string> word_list; /*!< A pointer to the array of words */

+    std::unordered_map<std::string, uint32_t> word_map; /*!< hash table to find word's index */

+    std::unordered_map<std::string, uint32_t> trimmed_word_map; /*!< hash table to find word's trimmed index */

     std::string language_name; /*!< Name of language */

     uint32_t unique_prefix_length; /*!< Number of unique starting characters to trim the wordlist to when matching */

     /*!

      * \brief Populates the word maps after the list is ready.

      */

-    void populate_maps()

+    void populate_maps(uint32_t flags = 0)

     {

       int ii;

-      std::vector<std::string>::iterator it;

-      for (it = word_list->begin(), ii = 0; it != word_list->end(); it++, ii++)

+      std::vector<std::string>::const_iterator it;

+      if (word_list.size () != 1626)

+        throw std::runtime_error("Wrong word list length for " + language_name);

+      for (it = word_list.begin(), ii = 0; it != word_list.end(); it++, ii++)

       {

-        (*word_map)[*it] = ii;

+        word_map[*it] = ii;

+        if ((*it).size() < unique_prefix_length)

+        {

+          if (flags & ALLOW_SHORT_WORDS)

+            MWARNING(language_name << " word '" << *it << "' is shorter than its prefix length, " << unique_prefix_length);

+          else

+            throw std::runtime_error("Too short word in " + language_name + " word list: " + *it);

+        }

+        std::string trimmed;

         if (it->length() > unique_prefix_length)

         {

-          (*trimmed_word_map)[utf8prefix(*it, unique_prefix_length)] = ii;

+          trimmed = utf8prefix(*it, unique_prefix_length);

         }

         else

         {

-          (*trimmed_word_map)[*it] = ii;

+          trimmed = *it;

+        }

+        if (trimmed_word_map.find(trimmed) != trimmed_word_map.end())

+        {

+          if (flags & ALLOW_DUPLICATE_PREFIXES)

+            MWARNING("Duplicate prefix in " << language_name << " word list: " << trimmed);

+          else

+            throw std::runtime_error("Duplicate prefix in " + language_name + " word list: " + trimmed);

         }

+        trimmed_word_map[trimmed] = ii;

       }

     }

   public:

-    Base()

+    Base(const char *language_name, const std::vector<std::string> &words, uint32_t prefix_length):

+      word_list(words),

+      unique_prefix_length(prefix_length),

+      language_name(language_name)

     {

-      word_list = new std::vector<std::string>;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      unique_prefix_length = 4;

     }

     virtual ~Base()

     {

-      delete word_list;

-      delete word_map;

-      delete trimmed_word_map;

     }

     /*!

      * \brief Returns a pointer to the word list.

@@ -118,7 +137,7 @@ namespace Language
      */

     const std::vector<std::string>& get_word_list() const

     {

-      return *word_list;

+      return word_list;

     }

     /*!

      * \brief Returns a pointer to the word map.

@@ -126,7 +145,7 @@ namespace Language
      */

     const std::unordered_map<std::string, uint32_t>& get_word_map() const

     {

-      return *word_map;

+      return word_map;

     }

     /*!

      * \brief Returns a pointer to the trimmed word map.

@@ -134,13 +153,13 @@ namespace Language
      */

     const std::unordered_map<std::string, uint32_t>& get_trimmed_word_map() const

     {

-      return *trimmed_word_map;

+      return trimmed_word_map;

     }

     /*!

      * \brief Returns the name of the language.

      * \return Name of the language.

      */

-    std::string get_language_name() const

+    const std::string &get_language_name() const

     {

       return language_name;

     }

diff --git a/src/mnemonics/old_english.h b/src/mnemonics/old_english.h
index 690e46616..21ac95de3 100644
--- a/src/mnemonics/old_english.h
+++ b/src/mnemonics/old_english.h
@@ -51,9 +51,7 @@ namespace Language
   class OldEnglish: public Base

   {

   public:

-    OldEnglish()

-    {

-      word_list = new std::vector<std::string>({

+    OldEnglish(): Base("OldEnglish", std::vector<std::string>({

         "like",

         "just",

         "love",

@@ -1680,12 +1678,9 @@ namespace Language
         "unseen",

         "weapon",

         "weary"

-      });

-      unique_prefix_length = 4;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "OldEnglish";

-      populate_maps();

+      }), 4)

+    {

+      populate_maps(ALLOW_DUPLICATE_PREFIXES | ALLOW_SHORT_WORDS);

     }

   };

 }

diff --git a/src/mnemonics/portuguese.h b/src/mnemonics/portuguese.h
index 91e2145b8..09d7132f5 100644
--- a/src/mnemonics/portuguese.h
+++ b/src/mnemonics/portuguese.h
@@ -49,9 +49,7 @@ namespace Language
   class Portuguese: public Base

   {

   public:

-    Portuguese()

-    {

-      word_list = new std::vector<std::string>({

+    Portuguese(): Base("Portuguese", std::vector<std::string>({

         "abaular",

         "abdominal",

         "abeto",

@@ -1678,11 +1676,8 @@ namespace Language
         "zeloso",

         "zenite",

         "zumbi"

-      });

-      unique_prefix_length = 4;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "Portuguese";

+      }), 4)

+    {

       populate_maps();

     }

   };

diff --git a/src/mnemonics/russian.h b/src/mnemonics/russian.h
index 981f40d98..b3db4aa4c 100644
--- a/src/mnemonics/russian.h
+++ b/src/mnemonics/russian.h
@@ -51,9 +51,7 @@ namespace Language
   class Russian: public Base

   {

   public:

-    Russian()

-    {

-      word_list = new std::vector<std::string>({

+    Russian(): Base("Russian", std::vector<std::string>({

         "абажур",

         "абзац",

         "абонент",

@@ -1680,11 +1678,8 @@ namespace Language
         "яхта",

         "ячейка",

         "ящик"

-      });

-      unique_prefix_length = 4;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "Russian";

+      }), 4)
+    {
       populate_maps();

     }

   };

diff --git a/src/mnemonics/spanish.h b/src/mnemonics/spanish.h
index ec3a8991d..4b386a968 100644
--- a/src/mnemonics/spanish.h
+++ b/src/mnemonics/spanish.h
@@ -51,9 +51,7 @@ namespace Language
   class Spanish: public Base

   {

   public:

-    Spanish()

-    {

-      word_list = new std::vector<std::string>({

+    Spanish(): Base("Spanish", std::vector<std::string>({

         "ábaco",

         "abdomen",

         "abeja",

@@ -1680,12 +1678,9 @@ namespace Language
         "risa",

         "ritmo",

         "rito"

-      });

-      unique_prefix_length = 4;

-      word_map = new std::unordered_map<std::string, uint32_t>;

-      trimmed_word_map = new std::unordered_map<std::string, uint32_t>;

-      language_name = "Spanish";

-      populate_maps();

+      }), 4)
+    {
+      populate_maps(ALLOW_SHORT_WORDS);

     }

   };

 }