I'm doing a python exercise that ask me to program a Lempel-Ziv algorithm to compress a text file. When I write the compressed file, the output file is higher than the first one. That's my code:
with open ("quijote.txt", "r") as myfile:
data=myfile.read()
datab = ''.join(format(ord(x), 'b') for x in data)
BitPos = {'':0}
PosAdded = {}
i = 0
for f in range(len(datab)):
if datab[i:f] not in BitPos:
BitPos[datab[i:f]] = format(i+1,'b')
PosAdded[BitPos[datab[i:f-1]]] = datab[f-1:f]
i = f
maxl = len(str(format(i,'b')))
compres = ''
for pos in PosAdded:
compres += str(pos).zfill(maxl)+PosAdded[pos]
compres = format(maxl+1,'b')+'\n'+compres
f = open('quijote3.txt','w')
f.write(compres)
f.close()
The input file is 2MB and the output is 9MB.
Related
I have a text file that has some values as follows:
matlab.file.here.we.go{1} = 50
matlab.file.here.sxd.go{1} = 50
matlab.file.here.asd.go{1} = 50
I want the code to look for "matlab.file.here.sxd.go{1}" and replace the value assigned to it from 50 to 1. But I want it to be dynamic (i.e., later I will have over 20 values to change and I don't want to search for that specific phrase). I'm new to python so I don't have much information in order to search for it online. Thanks
I tried the following
file_path = r'test\testfile.txt'
file_param = 'matlab.file.here.we.go{1}'
changing = 'matlab.file.here.we.go{1} = 1'
with open(file_path, 'r') as f:
content = f.readlines()
content = content.replace(file_param , changing)
with open(file_path, 'w') as f:
f.write(content)
but it didn't achieve what I wanted
You can split on the equal sign. You can read and write files at the same time.
import os
file_path = r'test\testfile.txt'
file_path_temp = r'test\testfile.txt.TEMP'
new_value = 50
changing = 'matlab.file.here.we.go{1} = 1'
with open(file_path, 'r') as rf, open(file_path_temp, 'w') as wf:
for line in rf:
if changing in line:
temp = line.split(' = ')
temp[1] = new_value
line = ' = '.join(temp)
wf.write(line)
os.remove(file_path)
os.rename(file_path_temp, file_path)
I have a code that is working for me in a Cinema 4d project. It is able to read 4 different data points and kick out outputs to the main project. Currently it is reading all of the lines of the csv file and I would like to pick one line and pull the data from that line only.
import c4d
import csv
def main():
path = Spreadsheet #Spreadsheet is an input filename path
with open(path, 'rb') as csv_file:
readed = csv.DictReader(csv_file,delimiter=',')
for i, row in enumerate(readed):
try:
Xcord = float(row["hc_x"])
Ycord = float(row["hc_y"])
Langle = float(row["launch_angle"])
Lspeed = float(row["launch_speed"])
except:
print "Error while reading - {}".format(row)
continue
global Output1
global Output2
global Output3
global Output4
Output1 = Xcord
Output2 = Ycord
Output3 = Langle
Output4 = Lspeed
This is about the first thing I have tried to code. So thanks.
csv.DictReader requires that you open the file with newline="" in order for it to parse the file correctly.
with open(path, 'rb', newline="") as csv_file:
readed = csv.DictReader(csv_file,delimiter=',')
You also don't have any condition to stop reading the file.
row_to_stop = 5
for i, row in enumerate(readed):
if i == row_to_stop:
Xcord = float(row["hc_x"])
Ycord = float(row["hc_y"])
Langle = float(row["launch_angle"])
Lspeed = float(row["launch_speed"])
break
If you only care about one line, don't look up and type cast values until you reach the line you care about.
I would like to pick one line and pull the data from that line only
The code below will return specific line (by index). You will have to split it and grab the data.
def get_interesting_line(file_name: str, idx: int):
cnt = 0
with open(file_name) as f:
while cnt != idx:
f.readline()
cnt += 1
return f.readline().strip()
# usage example below
print(get_interesting_line('data.txt',7))
I am using a script in fusion360 called importsplinecsv
I was wondering if it was possible to modify the script so that it would import one row every 10th row?
as the amount of rows that are being imported are very large and bloating.
if I could get some help that would be awesome.
here is the text
Author-Autodesk Inc.
Description-Import spline from csv file
import adsk.core, adsk.fusion, traceback
import io
def run(context):
ui = None
try:
app = adsk.core.Application.get()
ui = app.userInterface
# Get all components in the active design.
product = app.activeProduct
design = adsk.fusion.Design.cast(product)
title = 'Import Spline csv'
if not design:
ui.messageBox('No active Fusion design', title)
return
dlg = ui.createFileDialog()
dlg.title = 'Open CSV File'
dlg.filter = 'Comma Separated Values (*.csv);;All Files (*.*)'
if dlg.showOpen() != adsk.core.DialogResults.DialogOK :
return
filename = dlg.filename
with io.open(filename, 'r', encoding='utf-8-sig') as f:
points = adsk.core.ObjectCollection.create()
line = f.readline()
data = []
while line:
pntStrArr = line.split(',')
for pntStr in pntStrArr:
try:
data.append(float(pntStr))
except:
break
if len(data) >= 3 :
point = adsk.core.Point3D.create(data[0], data[1], data[2])
points.add(point)
line = f.readline()
data.clear()
if points.count:
root = design.rootComponent
sketch = root.sketches.add(root.xYConstructionPlane)
sketch.sketchCurves.sketchFittedSplines.add(points)
else:
ui.messageBox('No valid points', title)
except:
if ui:
ui.messageBox('Failed:\n{}'.format(traceback.format_exc()))
I have not used this library before but try:
for i, line in enumerate(f):
if i%10==0:
then your import command here
f is your filepointer
i will be the linenumber and line will be your line
dlg = ui.createFileDialog()
dlg.title = 'Open CSV File'
dlg.filter = 'Comma Separated Values (*.csv);;All Files (*.*)'
if dlg.showOpen() != adsk.core.DialogResults.DialogOK :
return
filename = dlg.filename
with io.open(filename, 'r', encoding='utf-8-sig') as f:
points = adsk.core.ObjectCollection.create()
for i, line in enumerate(f):
if i%10==0:
while line:
pntStrArr = line.split(',')
for pntStr in pntStrArr:
try:
data.append(float(pntStr))
except:
break
if len(data) >= 3 :
point = adsk.core.Point3D.create(data[0], data[1], data[2])
points.add(point)
line = f.readline()
data.clear()
if points.count:
root = design.rootComponent
sketch = root.sketches.add(root.xYConstructionPlane)
sketch.sketchCurves.sketchFittedSplines.add(points)
else:
ui.messageBox('No valid points', title)
except:
if ui:
ui.messageBox('Failed:\n{}'.format(traceback.format_exc()))
So, I'm trying to create a program that will automatically edit a specific set of characters in a file (it will read and replace them). No other data can be moved in the file otherwise it might become corrupted so I need to replace the text in the exact same place as before. I have looked around and found nothing useful but here is my code so far:
l = 3
w = 0
with open("InidCrd000.crd") as myfile:
hexWord = myfile.readlines()[l].split()[w]
codeA = hexWord[58]
codeB = hexWord[59]
print("Current value: ", codeA, codeB)
codeA = " "
codeB = "Ð"
print("New value: ", codeA, codeB)
EDIT - I now have this code (credit - Ilayaraja), which works but then it breaks the file up into lines and places random data in incorrect positions (although the inputted data is in the correct position):
def replace(filepath, lineno, position, newchar):
with open(filepath, "r") as reader:
lines = reader.readlines()
l = lines[lineno-1]
l = l[0:position] + newchar + l[position+1:]
lines[lineno-1] = l
with open(filepath, "w") as writer:
writer.writelines(lines)
replace("InidCrd000.crd", 4, 57, "")
replace("InidCrd000.crd", 4, 58, "Ð")
If you want the file for testing, here it is: 1drv.ms/u/s!AqRsP9xMA0g1iqMl-ZQbXUqX2WY8aA (It's a onedrive file)
first find the code you want to change using this :
l = 3
w = 0
with open("InidCrd000.crd") as myfile:
hexWord = myfile.readlines()[l].split()[w]
codeA = hexWord[58]
codeB = hexWord[59]
myfile.close()
then change like this :
import fileinput
with fileinput.FileInput(fileToSearch, inplace=True, backup='.bak') as file:
for line in file:
line.replace(codeA, textToReplace)
Define a function with the arguments the path of the file(filepath), line number(lineno 1 to N), position of the character in the line(position 0 to N) and the new character to be overwritten(newchar) as follows:
def replace(filepath, lineno, position, newchar):
with open(filepath, "r") as reader:
lines = reader.readlines()
l = lines[lineno-1]
l = l[0:position] + newchar + l[position+1:]
lines[lineno-1] = l
with open(filepath, "w") as writer:
writer.writelines(lines)
You can call the function as follows to replace the characters:
replace("InidCrd000.crd", 3, 58, " ")
replace("InidCrd000.crd", 3, 59, "Ð")
here is my code for readinng individual cell of one csv file. but want to read multiple csv file one by one from .txt file where csv file paths are located.
import csv
ifile = open ("C:\Users\BKA4ABT\Desktop\Test_Specification\RDBI.csv", "rb")
data = list(csv.reader(ifile, delimiter = ';'))
REQ = []
RES = []
n = len(data)
for i in range(n):
x = data[i][1]
y = data[i][2]
REQ.append (x)
RES.append (y)
i += 1
for j in range(2,n):
try:
if REQ[j] != '' and RES[j]!= '': # ignore blank cell
print REQ[j], ' ', RES[j]
except:
pass
j += 1
And csv file paths are stored in a .txt file like
C:\Desktop\Test_Specification\RDBI.csv
C:\Desktop\Test_Specification\ECUreset.csv
C:\Desktop\Test_Specification\RDTC.csv
and so on..
You can read stuff stored in files into variables. And you can use variables with strings in them anywhere you can use a literal string. So...
with open('mytxtfile.txt', 'r') as txt_file:
for line in txt_file:
file_name = line.strip() # or was it trim()? I keep mixing them up
ifile = open(file_name, 'rb')
# ... the rest of your code goes here
Maybe we can fix this up a little...
import csv
with open('mytxtfile.txt', 'r') as txt_file:
for line in txt_file:
file_name = line.strip()
csv_file = csv.reader(open(file_name, 'rb', delimiter=';'))
for record in csv_file[1:]: # skip header row
req = record[1]
res = record[2]
if len(req + res):
print req, ' ', res
you just need to add a while which will read your file containing your list of files & paths upon your first open statement, for example
from __future__ import with_statement
with open("myfile_which_contains_file_path.txt") as f:
for line in f:
ifile = open(line, 'rb')
# here the rest of your code
You need to use a raw string string your path contains \
import csv
file_list = r"C:\Users\BKA4ABT\Desktop\Test_Specification\RDBI.csv"
with open(file_list) as f:
for line in f:
with open(line.strip(), 'rb') as the_file:
reader = csv.reader(the_file, delimiter=';')
for row in reader:
req,res = row[1:3]
if req and res:
print('{0} {1}'.format(req, res))