"""Convert SQL backups of my WordPress blog into charts"""

import datetime, pylab, numpy

class blogChrono():
    baseUrl="https://swharden.com/blog"
    posts=[]
    dates=[]
    def __init__(self,fname):
        self.fname=fname
        self.load()
    def load(self):
        print "loading [%s]..."%self.fname,
        f=open(self.fname)
        raw=f.readlines()
        f.close()
        for line in raw:
            if "INSERT INTO" in line
            and';' in line[-2:-1]
            and " 'post'," in line[-20:-1]:
                post={}
                line=line.split("VALUES(",1)[1][:-3]
                line=line.replace(', NULL',', None')
                line=line.replace(", '',",", None,")
                line=line.replace("''","")
                c= line.split(',',4)[4][::-1]
                c= c.split(" ,",21)
                text=c[-1]
                text=text[::-1]
                text=text[2:-1]
                text=text.replace('"""','###')
                line=line.replace(text,'blogtext')
                line=line.replace(', ,',', None,')
                line=eval("["+line+"]")
                if len(line[4])>len('blogtext'):
                    x=str(line[4].split(', '))[2:-2]
                    raw=str(line)
                    raw=raw.replace(line[4],x)
                    line=eval(raw)
                post["id"]=int(line[0])
                post["date"]=datetime.datetime.strptime(line[2],
                                                        "%Y-%m-%d %H:%M:%S")
                post["text"]=eval('"""'+text+' """')
                post["title"]=line[5]
                post["url"]=line[21]
                post["comm"]=int(line[25])
                post["words"]=post["text"].count(" ")
                self.dates.append(post["date"])
                self.posts.append(post)
        self.dates.sort()
        d=self.dates[:]
        i,newposts=0,[]
        while len(self.posts)>0:
            die=min(self.dates)
            for post in self.posts:
                if post["date"]==die:
                    self.dates.remove(die)
                    newposts.append(post)
                    self.posts.remove(post)
        self.posts,self.dates=newposts,d
        print "read %d posts!n"%len(self.posts)

#d=blogChrono('sml.sql')
d=blogChrono('test.sql')

fig=pylab.figure(figsize=(7,5))
dates,lengths,words,ltot,wtot=[],[],[],[0],[0]
for post in d.posts:
    dates.append(post["date"])
    lengths.append(len(post["text"]))
    ltot.append(ltot[-1]+lengths[-1])
    words.append(post["words"])
    wtot.append(wtot[-1]+words[-1])
ltot,wtot=ltot[1:],wtot[1:]

pylab.subplot(211)
#pylab.plot(dates,numpy.array(ltot)/(10.0**6),label="letters")
pylab.plot(dates,numpy.array(wtot)/(10.0**3),label="words")
pylab.ylabel("Thousand")
pylab.title("Total Blogged Words")
pylab.grid(alpha=.2)
#pylab.legend()
fig.autofmt_xdate()
pylab.subplot(212,sharex=pylab.subplot(211))
pylab.bar(dates,numpy.array(words)/(10.0**3))
pylab.title("Words Per Entry")
pylab.ylabel("Thousand")
pylab.xlabel("Date")
pylab.grid(alpha=.2)
#pylab.axis([min(d.dates),max(d.dates),None,20])
fig.autofmt_xdate()
pylab.subplots_adjust(left=.1,bottom=.13,right=.98,top=.92,hspace=.25)
width=675
pylab.savefig('out.png',dpi=675/7)
pylab.show()

print "DONE"

import datetime, pylab, numpy
f=open('dump.txt')
body=f.read()
f.close()
body=body.lower()
body=body.split(" ")
tot=float(len(body))
words={}
for word in body:
    for i in word:
        if 65< =ord(i)<=90 or 97<=ord(i)<=122: pass
        else: word=None
    if word:
        if not word in words:words[word]=0
        words[word]=words[word]+1
data=[]
for word in words: data.append([words[word],word])
data.sort()
data.reverse()
out= "<b>Out of %d words...n"%tot
xs=[]
for i in range(1000):
    d=data[i]
    out += '<b>"%s"</b> ranks #%d used <b>%d</b> times (%.05f%%)
n'%
                (d[1],i+1,d[0],d[0]/tot)
f=open("dump.html",'w')
f.write(out)
f.close()
print "DONE"</b>