# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:^|\b)(?<number>(?:\d+|\d{1,3}(?:,\d{3})+)(?:\.\d+)?)(?<replace> ?|&[^;]{2,7};)(?<dimensions>(?<mathjax>\$[^\n\$]+\$)|(?<unit>(?<si>(?!as)(?:[QRYZEPTGMkhdcmµnpfazyrq]|da)?(?:mol|cd|Hz|Pa|Wb|lm|lx|Bq|Gy|Sv|kat|[mgsAKNJWCVFΩSTHL]))|(?<imperial>mil|P|in|ft|yd|mi|le|ftm|nmi|oz|lbs?|t|tsp|tbsp|c|fl oz|pt|qt|gal|(?:sq|cu) ?(?:in|ft|yd|mi)|ft-lbf?|lbf?-ft|deg|Btu|psi|Ly)|(?<common>mph|kph|rad|sr)|(?<binary>(?:(?:[KMGTPEZY])i?)?B)))(?=\b|$| |[.,:;()\[\]{}=/*+—–-])"
test_str = ("I have a 30 $m^2$ pumpernickle\n"
"More precisely it's 29.87$m^2$.\n"
"Traveling over 4,000 km, to where once there was\n"
"...in the year 2016 as a new method of...\n"
"He crashed at 50mph\n"
"They collided at speeds of over 200m/s\n"
"The reading is 2kHz.\n"
"The range is 20kHz–1MHz (1,000.3 kHz).\n"
"Just 4M words at 30MB.")
subst = "$<number> $<dimensions>"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE)
if result:
print (result)
# 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