Created
October 20, 2022 03:17
-
-
Save xtornasol512/0e9b791919d90f83605cd257f0f757e6 to your computer and use it in GitHub Desktop.
Scape functions for latex, compatible only with python 3+
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
import unicodedata | |
def escape_text(s): | |
# Convert from python escape text to latex format. | |
"""^*¨ÑLIOPL:_:(/&%&()=(/&WQ·W$ERTY +´^*Ñ´plqj""" | |
# This block is omited | |
s = s.replace("·", "") | |
s = s.replace("¨", "") | |
s = s.replace("$", "") | |
s = s.replace("\"", "``") | |
s = s.replace("<", "\\textless ") | |
s = s.replace(">", "\\textgreater ") | |
s = s.replace("&", "\\& ") | |
s = s.replace("%", "\\% ") | |
s = s.replace("#", "\\# ") | |
s = s.replace("\n", "\\" + "\\ ") | |
s = s.replace("_", "\\textunderscore ") | |
s = s.replace("{", "\\{ ") | |
s = s.replace("}", "\\} ") | |
s = s.replace("^", "\\^{} ") | |
s = s.replace("\'", "\\textsc{\\char13} ") | |
s = s.replace("´", "\\textsc{\\char13} ") | |
s = s.replace("°", " (grados)") | |
s = s.replace("º", " (grados)") | |
s = s.strip() | |
# If no length, return something useful | |
if len(s) == 0: | |
s = "NA" | |
return s | |
def clean_text(text): | |
""" Method to clean characters """ | |
text = text.replace("\r", "") | |
text = text.replace("\t", "") | |
text = unicodedata.normalize('NFKD', text).encode('ascii', 'ignore') | |
# Allowed characters for RegEx function: | |
# Lower/Mayus characters (a-z) (A-Z) [ascii encoding] | |
# Numbers (0-9) | |
# Special (.) (/) (() ()) (-) (=) (@) | |
# Blank space | |
decoded_text = text.decode() | |
regex = re.compile(r'[A-Za-z0-9. ^/\-\(\)\=@#&%\+\n]', re.IGNORECASE) | |
text = ''.join(char for char in decoded_text if regex.match(char)) # noqa: W605 | |
text = text.strip() | |
# Add a post space in order to avoid latex errors ie '\\ string' | |
text = text.replace("#", "\\# ") | |
text = text.replace("&", "\\& ") | |
text = text.replace("%", "\\% ") | |
text = text.replace("^", "\\^{} ") | |
text = text.replace("\n", "\\" + "\\ ") | |
return text if len(text) != 0 else "N/A" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment