'''
File "heatindex.py" by KWR for CSE199, Fall 2022.  Activity support file.
Requires: "heatlib.py" in same directory or peer project file.

Usage: python3 heatindex.py [optional URL]   

Or within python3 environment, can call loadDict, heatScore, and
processUserInput at will.  Can skip "http://" in URL if next comes "www".

Computes a "heat index" for a given webpage from a given dictionary of
"intense" words and their intensity values in several categories.
Tailored to the Canadian National Research Council Affect Intensity Lexicon
http://saifmohammad.com/WebPages/AffectIntensity.htm
by Saif Mohammad, used with his permission (and request not to redistribute).
However, works with any file of lines of the form

word    #.###   category

where NRCAIL's categories 'anger', 'fear', 'sadness', 'joy' are not treated
specially, so that clients can define any categories they wish.
Dictionary file can be local or loaded from a URL.

2022 NOTE: Python 3 Trinket, in various pages of it, seems inconsistent in its
handling of urllib.request and the get method, versus using the urlopen method.
I have changed the default commented-in lines for heatlib.py lines 105-107 (or so)
which define "source", and lines 155-157 (or so) which define "page".
But in case of that not working, try reverting to commentin-in the lines after
them with "get"
'''

from __future__ import division
import sys
import re

from heatlib import loadDict, heatScore


def processUserInput(url,heatDict,mulDict):
   while url != "quit":
      if url == "mul":
         mulDict = {}
         angerMul = float(input("Anger multiplier: "))
         fearMul = float(input("Fear multiplier: "))
         sadnessMul = float(input("Sadness multiplier: "))
         joyMul = float(input("Joy multiplier: "))
         mulDict['anger'] = angerMul
         mulDict['fear'] = fearMul
         mulDict['sadness'] = sadnessMul
         mulDict['joy'] = joyMul
      else:
         if url.startswith("www"):
            url = 'http://' + url

         heatIndex, intenseCountUnique, intenseCount, wordCount, catDict \
               = heatScore(url, heatDict, mulDict)
   
         for category in sorted (catDict):  # parens needed here
            print("\nWords under '",category,"' and number of times occurring:", sep='')
            for word in sorted (catDict[category]):  
               print(word, catDict[category][word])
   
         print("\nHeat index with multipliers ",repr(mulDict),"\n" \
               "of ", url+" :\n", \
               round(heatIndex,3), " from ", intenseCountUnique, \
               " intense words (", intenseCount, " category hits) out of ", \
               wordCount, " words read.", sep='')
   
      url = input("\nPaste a URL, or enter 'mul' to change multipliers," \
                  + " 'quit' to quit: ")
   
   
# main [optional URL]

numArgs = len(sys.argv) - 1
mulDict = {'anger' : 1, 'fear' : 1, 'sadness' : 1, 'joy' : -1}
#location = "NRC-AffectIntensity-Lexicon.txt"
location = "https://www.cse.buffalo.edu/~regan/cse199/deepweb/NRC-AffectIntensity-Lexicon.txt"
(heatDict,mulDict) = loadDict(location, mulDict)

url = "quit"
if numArgs >= 1:
   url = sys.argv[1]
else:
   url = input("Paste a URL: ")

processUserInput(url,heatDict,mulDict)