Created
October 19, 2020 21:37
-
-
Save jwg4/a9ca3bba32f973be43048dabf39e7a7d to your computer and use it in GitHub Desktop.
Transforming plaintext to latex
This file contains 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 logging | |
import re | |
import sys | |
REPLACEMENTS = { | |
"’": "'", | |
"—": "--", | |
"“": "``", | |
"”": "''", | |
"…": "{\\ldots}", | |
"‘": "`", | |
"ä": "\\={a}", | |
"&": "\\&", | |
"$": "\\$", | |
} | |
TRANSFORMATIONS = { | |
r"^Chapter ([0-9]+)[ ]*$": r"\chapter*{\1}", | |
r"^PART ([A-Z]+)[ ]*$": r"\part*{\1}", | |
} | |
def prepare(line): | |
for s in REPLACEMENTS: | |
line.replace(s, REPLACEMENTS[s]) | |
line = line.strip() | |
for pattern in TRANSFORMATIONS: | |
line = re.sub(pattern, TRANSFORMATIONS[pattern], line) | |
return line + '\n' | |
def warn_on_ascii(line): | |
for c in line: | |
try: | |
x = c.encode('ascii') | |
except UnicodeEncodeError: | |
print('line = line.replace("%s", "???")' % (c, )) | |
if __name__ == '__main__': | |
logging.basicConfig(level=logging.INFO) | |
with open(sys.argv[1], 'r', encoding='utf-8') as f: | |
with open(sys.argv[2], 'w', encoding='utf-8') as ff: | |
for line in f.readlines(): | |
output = prepare(line) | |
logging.debug(repr(line), repr(output)) | |
ff.write(output) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment