From 360705a04c3ff34bf767cabc6640ff85ab3f8412 Mon Sep 17 00:00:00 2001
From: Zac Herd <mrdetonia@gmail.com>
Date: Sun, 3 Apr 2016 16:03:40 +0100
Subject: [PATCH] Added .markov command that generates markov chain sentences
 based on a user's chat history, v0.10.0

---
 bot.py             | 20 +++++++++++++++++++-
 markov.py          | 42 ++++++++++++++++++++++++++++++++++++++++++
 markovs/.gitignore |  2 ++
 3 files changed, 63 insertions(+), 1 deletion(-)
 create mode 100644 markov.py
 create mode 100644 markovs/.gitignore

diff --git a/bot.py b/bot.py
index ef05d3b..5d99baf 100644
--- a/bot.py
+++ b/bot.py
@@ -12,6 +12,7 @@ import os
 import time
 import datetime
 import json
+import markov
 
 # file in this directory called "secret.py" should contain these variables
 from secret import email,pwd
@@ -23,7 +24,7 @@ from secret import email,pwd
 name = "Maki"
 
 # bot version
-version = "v0.9.4"
+version = "v0.10.0"
 
 # text shown by .help command
 helptext = """I am a bot written in Python by MrDetonia
@@ -40,6 +41,7 @@ My commands are:
 .seen <user> - prints when user was last seen
 .tell <user> <message> - send message to user when they are next active
 .say <msg> - say something
+.markov <user> - generate sentence using markov chains over a user's chat history
 ```"""
 
 # IDs of admin users
@@ -145,6 +147,8 @@ def on_message(message):
     # print messages to terminal for info
     print(message.author.name + ': ' + message.content)
 
+
+
     # ensure we store this user's ID
     if message.author.name not in users:
         users[message.author.name] = message.author.id
@@ -252,12 +256,26 @@ def on_message(message):
             # echo message
             yield from client.send_message(message.channel, message.content[5:])
 
+        elif message.content.startswith('.markov'):
+            # generate a markov chain sentence based on the user's chat history
+            tmp = message.content[8:].split(' ',1)
+            if os.path.isfile('./markovs/' + users[tmp[0]]):
+                mc = markov.Markov(open('./markovs/' + users[tmp[0]]))
+                yield from client.send_message(message.channel, mc.generate_text())
+            else:
+                yield from client.send_message(message.channel, 'I haven\'t seen that user speak yet!')
+
+        # Stuff that happens when message is not a bot command:
         else:
             # log each message against users
             history[message.author.name] = (message.content, time.time())
             with open('hist.json', 'w') as fp:
                 json.dump(history, fp)
 
+            # log user messages for markov chains
+            with open('./markovs/' + message.author.id, 'a') as fp:
+                fp.write('\n' + message.content)
+
         # Ben meme trackers
         if '/ck/' in message.content and message.author.name == "Ben.H":
             bentrack['ck'] += 1
diff --git a/markov.py b/markov.py
new file mode 100644
index 0000000..554f2b5
--- /dev/null
+++ b/markov.py
@@ -0,0 +1,42 @@
+import random
+
+class Markov(object):
+
+    def __init__(self, open_file):
+        self.cache = {}
+        self.open_file = open_file
+        self.words = self.file_to_words()
+        self.word_size = len(self.words)
+        self.database()
+
+    def file_to_words(self):
+        self.open_file.seek(0)
+        data = self.open_file.read()
+        words = data.split()
+        return words
+
+    def triples(self):
+        if len(self.words) < 3:
+            return
+
+        for i in range(len(self.words) - 2):
+            yield (self.words[i], self.words[i+1], self.words[i+2])
+
+    def database(self):
+        for w1, w2, w3 in self.triples():
+            key = (w1, w2)
+            if key in self.cache:
+                self.cache[key].append(w3)
+            else:
+                self.cache[key] = [w3]
+
+    def generate_text(self, size=25):
+        seed = random.randint(0, self.word_size - 3)
+        seed_word, next_word = self.words[seed], self.words[seed+1]
+        w1, w2 = seed_word, next_word
+        gen_words = []
+        for i in range(size):
+            gen_words.append(w1)
+            w1, w2 = w2, random.choice(self.cache[(w1, w2)])
+        gen_words.append(w2)
+        return ' '.join(gen_words)
diff --git a/markovs/.gitignore b/markovs/.gitignore
new file mode 100644
index 0000000..d6b7ef3
--- /dev/null
+++ b/markovs/.gitignore
@@ -0,0 +1,2 @@
+*
+!.gitignore