# Function: OpenRead(file)
# A text file can be encoded using:
# (1) The default operating system code page, Or
# (2) utf8 with a BOM header
#
# If a text file is encoded with utf8, and does not have a BOM header,
# the user can manually add a BOM header to the text file
# using a text editor such as notepad++, and rerun the python script,
# otherwise the file is read as a codepage file with the
# invalid codepage characters removed
import sys
if int(sys.version[0]) != 3:
print('Aborted: Python 3.x required')
sys.exit(1)
def bomType(file):
"""
returns file encoding string for open() function
EXAMPLE:
bom = bomtype(file)
open(file, encoding=bom, errors='ignore')
"""
f = open(file, 'rb')
b = f.read(4)
f.close()
if (b[0:3] == b'\xef\xbb\xbf'):
return "utf8"
# Python automatically detects endianess if utf-16 bom is present
# write endianess generally determined by endianess of CPU
if ((b[0:2] == b'\xfe\xff') or (b[0:2] == b'\xff\xfe')):
return "utf16"
if ((b[0:5] == b'\xfe\xff\x00\x00')
or (b[0:5] == b'\x00\x00\xff\xfe')):
return "utf32"
# If BOM is not provided, then assume its the codepage
# used by your operating system
return "cp1252"
# For the United States its: cp1252
def OpenRead(file):
bom = bomType(file)
return open(file, 'r', encoding=bom, errors='ignore')
#######################
# Testing it
#######################
fout = open("myfile1.txt", "w", encoding="cp1252")
fout.write("* hi there (cp1252)")
fout.close()
fout = open("myfile2.txt", "w", encoding="utf8")
fout.write("\u2022 hi there (utf8)")
fout.close()
# this case is still treated like codepage cp1252
# (User responsible for making sure that all utf8 files
# have a BOM header)
fout = open("badboy.txt", "wb")
fout.write(b"hi there. barf(\x81\x8D\x90\x9D)")
fout.close()
# Read Example file with Bom Detection
fin = OpenRead("myfile1.txt")
L = fin.readline()
print(L)
fin.close()
# Read Example file with Bom Detection
fin = OpenRead("myfile2.txt")
L =fin.readline()
print(L) #requires QtConsole to view, Cmd.exe is cp1252
fin.close()
# Read CP1252 with a few undefined chars without barfing
fin = OpenRead("badboy.txt")
L =fin.readline()
print(L)
fin.close()
# Check that bad characters are still in badboy codepage file
fin = open("badboy.txt", "rb")
fin.read(20)
fin.close()
import subprocess
file_cmd = ['file', 'test.txt']
p = subprocess.Popen(file_cmd, stdout=subprocess.PIPE)
cmd_output = p.stdout.readlines()
# x will begin with the file type output as is observed using 'file' command
x = cmd_output[0].split(": ")[1]
return x.startswith('UTF-8')
import chardet
from pathlib import Path
def predict_encoding(file_path: Path, n_lines: int=20) -> str:
'''Predict a file's encoding using chardet'''
# Open the file as binary data
with Path(file_path).open('rb') as f:
# Join binary lines for specified number of lines
rawdata = b''.join([f.readline() for _ in range(n_lines)])
return chardet.detect(rawdata)['encoding']
def guess_encoding(data: bytes, fallback: str = "iso8859_15") -> str:
"""
A basic encoding detector.
"""
for bom, encoding in [
(codecs.BOM_UTF32_BE, "utf_32_be"),
(codecs.BOM_UTF32_LE, "utf_32_le"),
(codecs.BOM_UTF16_BE, "utf_16_be"),
(codecs.BOM_UTF16_LE, "utf_16_le"),
(codecs.BOM_UTF8, "utf_8_sig"),
]:
if data.startswith(bom):
return encoding
if all(b < 128 for b in data):
return "ascii" # you may want to use the fallback here if data is only a sample.
decoder = codecs.getincrementaldecoder("utf_8")()
try:
decoder.decode(data, final=False)
except UnicodeDecodeError:
return fallback
else:
return "utf_8" # not certain if data is only a sample
