From 5cad62bce41546ddae8908eeb5bb06476f4c5bd8 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Sat, 26 Aug 2023 15:55:23 +0300
Subject: [PATCH] tests : write a Python tokenizer test (wip)

---
 tests/test-tokenizer-0.cpp | 40 ++++++++++++++++++++------------------
 tests/test-tokenizer-0.py  | 18 +++++++++++++++++
 2 files changed, 39 insertions(+), 19 deletions(-)
 create mode 100644 tests/test-tokenizer-0.py

diff --git a/tests/test-tokenizer-0.cpp b/tests/test-tokenizer-0.cpp
index 7e9ac9188..4bed054d6 100644
--- a/tests/test-tokenizer-0.cpp
+++ b/tests/test-tokenizer-0.cpp
@@ -16,36 +16,38 @@ static std::string unescape_whitespace(llama_context* ctx, const std::vector<lla
 
 static const std::map<std::string, std::vector<llama_token>> & k_tests() {
     static std::map<std::string, std::vector<llama_token>> _k_tests = {
-        { " ",                      {1,    259, }, },
-        { "  ",                     { 1,    1678, }, },
-        { "   ",                    { 1,     268, }, },
-        { "\t",                     { 1,    29871,   12, }, },
-        { "\n",                     { 1,    29871,   13, }, },
-        { "\t\n",                   { 1,    29871,   12,     13, }, },
+        { " ",                      { 1,    259, }, },
+        { "  ",                     { 1,   1678, }, },
+        { "   ",                    { 1,    268, }, },
+        { "\t",                     { 1,  29871,     12, }, },
+        { "\n",                     { 1,  29871,     13, }, },
+        { "\t\n",                   { 1,  29871,     12,     13, }, },
         { "Hello world",            { 1,  15043,   3186, }, },
         { " Hello world",           { 1,  29871,  15043,   3186, }, },
         { "Hello World",            { 1,  15043,   2787, }, },
         { " Hello World",           { 1,  29871,  15043,   2787, }, },
         { " Hello World!",          { 1,  29871,  15043,   2787,  29991, }, },
+        { "Hello, world!",          { 1,  15043,  29892,   3186,  29991, }, },
+        { " Hello, world!",         { 1,  29871,  15043,  29892,   3186,  29991, }, },
         { " this is 🦙.cpp",        { 1,  29871,    445,    338,  29871,    243,    162,    169,    156,  29889,   8223, }, },
         { "w048 7tuijk dsdfhu",     { 1,    281,  29900,  29946,  29947,  29871,  29955,   9161,  13535,  18031,   2176,   6905, }, },
         { "нещо на Български",      { 1,   1538,   4851,    665,   1386,  29713,   1305, }, },
         { "កាន់តែពិសេសអាចខលចេញ",   { 1,  29871,  31849,  31324,  31934,    228,    162,    142,    228,    161,
-                                     146,    228,    162,    133,    228,    161,    153,    228,    161,    186,
-                                     31708,    228,    162,    132,  31708,    228,    161,    165,  31324,    228,
-                                     161,    136,    228,    161,    132,    228,    161,    158,    228,    161,
-                                     136,    228,    162,    132,    228,    161,    140, }, },
+                                    146,    228,    162,    133,    228,    161,    153,    228,    161,    186,
+                                  31708,    228,    162,    132,  31708,    228,    161,    165,  31324,    228,
+                                    161,    136,    228,    161,    132,    228,    161,    158,    228,    161,
+                                    136,    228,    162,    132,    228,    161,    140, }, },
         { "🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)",
             { 1,  29871,    243,    162,    157,    131,    313,   8945,  29897,  29871,
-                243,    162,    155,    185,  30722,    243,    162,    143,    174,  30598,
-                313,  20787,    953,   3848,    275,  16125,    630,  29897,  29871,  31681,
-                313,   6194,    953,  29877,   2397,    393,    756,    967,   1914,   5993,  29897, }, },
-        { "Hello",                  { 1,    15043 }, },
-        { " Hello",                 { 1,    29871,  15043 }, },
-        { "  Hello",                { 1,    259,    15043 }, },
-        { "   Hello",               { 1,    1678,   15043 }, },
-        { "    Hello",              { 1,    268,    15043 }, },
-        { "    Hello\n    Hello",   { 1,    268,    15043,  13,     1678,   15043 }, },
+                    243,    162,    155,    185,  30722,    243,    162,    143,    174,  30598,
+                    313,  20787,    953,   3848,    275,  16125,    630,  29897,  29871,  31681,
+                    313,   6194,    953,  29877,   2397,    393,    756,    967,   1914,   5993,  29897, }, },
+        { "Hello",                  { 1,  15043, }, },
+        { " Hello",                 { 1,  29871,  15043, }, },
+        { "  Hello",                { 1,    259,  15043, }, },
+        { "   Hello",               { 1,   1678,  15043, }, },
+        { "    Hello",              { 1,    268,  15043, }, },
+        { "    Hello\n    Hello",   { 1,    268,  15043,     13,   1678,  15043, }, },
     };
 
     return _k_tests;
diff --git a/tests/test-tokenizer-0.py b/tests/test-tokenizer-0.py
new file mode 100644
index 000000000..d21f8b5a1
--- /dev/null
+++ b/tests/test-tokenizer-0.py
@@ -0,0 +1,18 @@
+import os
+import sys
+import argparse
+
+from sentencepiece import SentencePieceProcessor
+
+parser = argparse.ArgumentParser()
+parser.add_argument("dir_tokenizer", help="directory containing 'tokenizer.model' file")
+args = parser.parse_args()
+
+dir_tokenizer = args.dir_tokenizer
+
+tokenizer = SentencePieceProcessor(dir_tokenizer + '/tokenizer.model')
+
+text = 'Hello, world!'
+print(text)
+print(tokenizer.encode(text, add_bos=True))
+print(tokenizer.decode(tokenizer.encode(text, add_bos=True)))