source("multiplot.R")
source("password_strength.R")
library("ggplot2")
print("loading yandex data")
yandex <- read.csv("yandex.txt", header = FALSE, sep = ":", quote = "", stringsAsFactors = FALSE)
print("loading mailru data")
mailru <- read.csv("mail.txt",   header = FALSE, sep = ":", quote = "", stringsAsFactors = FALSE)
print("loading gmail data")
gmail  <- read.csv("gmail.txt",  header = FALSE, sep = ":", quote = "", stringsAsFactors = FALSE)
##testing if data loaded correctly
print("testing, if loaded correctly")
print(head(yandex))
print(head(mailru))
print(head(gmail))
##changing names
names(yandex) <- c("email", "password")
names(mailru) <- c("email", "password")
names(gmail)  <- c("email", "password")
print("computing lengths of passwords and adding to the datasets")
yandex$pass_length   <- sapply(yandex$password, nchar)
mailru$pass_length   <- sapply(mailru$password, nchar)
gmail$pass_length    <- sapply(gmail$password,  nchar)
print("number of invalid passwords by length")
print(nrow(yandex[yandex$pass_length <  6,]))
print(nrow(yandex[yandex$pass_length >  60,]))
print(nrow(mailru[mailru$pass_length <  6,]))
print(nrow(mailru[mailru$pass_length >  60,]))
print(nrow(gmail[gmail$pass_length <  6,]))
print(nrow(gmail[gmail$pass_length >  60,]))
print("removing invalid passwords by length")
yandex <- subset(yandex, pass_length >= 6 & pass_length <= 60)
mailru <- subset(mailru, pass_length >= 6 & pass_length <= 60)
gmail  <- subset(gmail , pass_length >= 6 & pass_length <= 60)
#print("checking that they are removed")
print(nrow(yandex[yandex$pass_length <  6,]))
print(nrow(yandex[yandex$pass_length >  60,]))
print(nrow(mailru[mailru$pass_length <  6,]))
print(nrow(mailru[mailru$pass_length >  60,]))
print(nrow(gmail[gmail$pass_length <  6,]))
print(nrow(gmail[gmail$pass_length >  60,]))
print("visualizing distribution of password lenghts by provider")
gmailcolor  <- "deepskyblue"
yandexcolor <- "orangered1"
mailrucolor <- "limegreen"
 pgmail <- ggplot(data=gmail, aes(x=pass_length)) + scale_x_discrete(limits=seq(6, 20, 1), breaks=seq(6, 20, 1), drop=TRUE) + geom_histogram(colour="black", fill=gmailcolor, aes(y=..density..)) + coord_cartesian(xlim=c(5,21.5)) + xlab(expression("Длина пароля"))+ ylab(expression("Доля"))+ggtitle("Gmail")
 pyandex <- ggplot(data=yandex, aes(x=pass_length)) + scale_x_discrete(limits=seq(6, 21, 1), breaks=seq(6, 21, 1), drop=TRUE) + geom_histogram(colour="black", fill=yandexcolor, aes(y=..density..)) + coord_cartesian(xlim=c(5,21.5)) + xlab(expression("Длина пароля"))+ ylab(expression("Доля"))+ggtitle("Yandex")     
 pmailru <- ggplot(data=mailru, aes(x=pass_length)) + scale_x_discrete(limits=seq(6, 20, 1), breaks=seq(6, 20, 1), drop=TRUE) + geom_histogram(colour="black", fill=mailrucolor, aes(y=..density..)) + coord_cartesian(xlim=c(5,20.5)) + xlab(expression("Длина пароля"))+ ylab(expression("Доля"))+ggtitle("Mail.ru")     
 multiplot(pgmail, pyandex, pmailru, cols=3)

print("computing strength of the passwords")
yandex$strength <- sapply(yandex$password, strength)
mailru$strength <- sapply(mailru$password, strength)
gmail$strength  <- sapply(gmail$password,  strength)
 print(head(yandex))
 print(head(mailru))
 print(head(gmail))
scale <- scale_x_discrete(limits=c(1,2,3,4,5), breaks=c(1,2,3,4,5), drop=TRUE, labels=c("Очень\nслабый", "Слабый", "Средний", "Надежный", "Очень\nнадежный"))
pgmail <- ggplot(data=gmail  , aes(factor(strength))) + geom_bar(colour="black", fill=gmailcolor) + xlab(expression("Надежность"))+ coord + ylab(expression("Доля"))+ggtitle("Gmail") + scale
pyandex <- ggplot(data=yandex, aes(factor(strength))) + geom_bar(colour="black", fill=yandexcolor, binwidth=0.5) + xlab(expression("Надежность"))+ coord + ylab(expression("Доля"))+ggtitle("Yandex") + scale
pmailru <- ggplot(data=mailru, aes(factor(strength))) + geom_bar(colour="black", fill=mailrucolor, binwidth=0.5) + xlab(expression("Надежность"))+ coord + ylab(expression("Доля"))+ggtitle("Mail.ru") + scale    
multiplot(pgmail, pyandex, pmailru, cols=3)
 print("Zero strength passwords")
 print("GMAIL")
 print(head(gmail[gmail$strength == 0,]))
 print("YANDEX")
 print(head(yandex[yandex$strength == 0,]))
 print("MAILRU")
 print(head(mailru[mailru$strength == 0,]))

table_gmail  <- sort(table(gmail$password) , TRUE)
table_yandex <- sort(table(yandex$password), TRUE)
table_mailru <- sort(table(mailru$password), TRUE)

print("gmail most frequent")
print(head(table_gmail, 100))
print("yandex most frequent")
print(head(table_yandex,100))
print("mailru most frequent")
print(head(table_mailru,100))

only_pass_gmail  <- gmail[ ,2] 
write.csv(only_pass_gmail,  "only_pass_gmail",  row.names = FALSE)
only_pass_yandex <- yandex[,2] 
write.csv(only_pass_yandex, "only_pass_yandex", row.names = FALSE)
only_pass_mailru <- mailru[,2] 
write.csv(only_pass_mailru, "only_pass_mailru", row.names = FALSE)

#!/bin/bash
data=sample_mailru
dict=saved_dict_mailru
> $dict
j=0
while read p; do
  ((j++))
  echo -n $j
  if grep -q "^$p$" dictionary/*; then
    echo " in "
    echo $p >> $dict
  else
    echo " out " 
  fi
  if (("$j" > 10000)); then
    break
  fi
done <$data