# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\\([a-zA-Z]+ *|.|\n)"
test_str = ("\\documentclass {book}\n"
"\\usepackage{a}\n"
"\\begin {document}\n"
"\\chapter*{This is the title of a index-absent chapter}\n"
"\\I'll try to do some actual \\LaTeX\\ text to se\\footnote {This is text in a footnote.} how it will be matched.\n\n"
"\\chapter{This is {\\bf another} chapter title}\n"
"You have to be carefull with accents, like ``Espa\\~nol'' \n"
"and active characters (characters like the quotes above \n"
"or the newline character, which act by themselves as a \n"
"command).\\\n\n"
"You have to be carefull also with comments (beginning with\n"
"the percentage char) % this is one comment.\n\n"
"And of course you'll loose al your math, as in \n"
"$e^{i\\pi} + 1 = 0$.\n\n"
"\\end{document}\n")
matches = re.finditer(regex, test_str)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html