ola5doc/content/patricia_morsheb/sources/pyt9c.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# this programme compare a text in french and its translation in englishe and liste the common words .import codecs
import codecs

f = codecs.open("JVFR.txt", encoding='utf-8') # on précise l’encodage à l’ouverture
textFr = f.read() # txt est une unicode

nm =0
#with open("JVFR.txt", encoding='utf-8', "r") as textFr:
for line in textFr:
		line=line.strip()
		mots=line.split()
		
		for mot in mots :
			#mot=mot.strip(" ;''?:,()!.\").”-")
			nm=nm+1
			
			print(mot)
print("nombres de mots en text francais = ", nm)
#
E = codecs.open("JVEN.txt", encoding='utf-8') # on précise l’encodage à l’ouverture
textEN = E.read() # txt est une unicode

nb =0
nbs=0
#with open("JVFR.txt", encoding='utf-8', "r") as textFr:
for line in textEN:
		line=line.strip()
		words=line.split()
		
		for word in words :
			word=word.strip(" ;''?:,()!.\").”-")
			nb=nb+1
			#print(word)
			for mot in mots:
				if word == mot :
					nbs=nbs+1
					print(word)
			#print(word)
print("nombres de mots en text anglais  = ", nb)
print("nombres des mots commun =" ,nbs)

S = codecs.open("JVES.txt", encoding='utf-8') # on précise l’encodage à l’ouverture
textES = S.read() # txt est une unicode

nmb =0
nmbs=0
#with open("JVFR.txt", encoding='utf-8', "r") as textFr:
for line in textES:
		line=line.strip()
		parabls=line.split()
		
		for parabl in parabls:
			#mot=mot.strip(" ;''?:,()!.\").”-")
			nmb=nmb+1
			if parabl== mot :
					nmbs=nmbs+1
					print(parabl)
			
			#print(mot)
print("nombres de mots en text espagnol = ", nmb)
print("nombres des mots commun =" ,nbs)