Last active
March 14, 2018 16:09
-
-
Save fitnr/5380778 to your computer and use it in GitHub Desktop.
The New York City Street Name Dictionary is in an insane fixed-width format. This python script parses it into a CSV.
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
from csv import writer | |
from collections import OrderedDict | |
''' | |
The New York City Street Name Dictionary is in an insane fixed-width format. | |
This python script parses it into a CSV. | |
http://www.nyc.gov/html/dcp/html/bytes/applbyte.shtml | |
''' | |
FIELDS_S = OrderedDict([ | |
('_', 1), | |
('borocode', 1), | |
('geo_feature', 32), | |
('__', 15), | |
('numeric_i', 1), | |
('geotype', 1), | |
('len_fullname', 2), | |
('progen_num', 1), | |
('progen1_firstword', 1), | |
('progen1_geotype', 1), | |
# progenitor 1 B10SC | |
('progen1_b10sc', 8), | |
# ('progen1_borough', 1), | |
# ('progen1_streetcode', 5), | |
# ('progen1_localgroup', 2), | |
('progen1_spellvar', 3), | |
('progen1_horiz_typology_flag', 1), | |
('___', 2), | |
('progen2_firstword', 1), | |
('progen2_geotype', 1), | |
# progenitor 2 B10SC | |
('progen2_b10sc', 8), | |
# ('progen2_borough', 1), | |
# ('progen2_streetcode', 5), | |
# ('progen2_localgroup', 2), | |
('progen2_spellvar', 3), | |
('progen2_horiz_typology_flag', 11), | |
('____', 2) | |
]) | |
FIELDS_NON_S = OrderedDict([ | |
('_', 1), | |
('borocode', 1), | |
('geo_feature', 32), | |
('primary_street_i', 1), | |
('local_group_i', 1), | |
('b10sc', 8), | |
# ('borough', 1), | |
# ('streetcode', 5), | |
# ('localgroup', 2), | |
('spellvar', 3), | |
('__', 2), | |
('numeric_i', 1), | |
('geotype', 1), | |
('______', 2), | |
('_____', 32), | |
('___', 2), | |
('____', 20), | |
('horiz_typology_code', 1) | |
]) | |
INDICATOR = 50 | |
OUTFILE_S = 'parsed_cow_s.csv' | |
OUTFILE_NON_S = 'parsed_cow_non_s.csv' | |
COWFILE = 'snd13Acow.txt' | |
def parse_line(line, fields): | |
out, i = [], 0 | |
for K, L in fields.items(): | |
if K[0] == '_': | |
i += L | |
continue | |
out.append(line[i:i+L].strip()) | |
i += L | |
return out | |
def write_file(filename, headers, writelist): | |
headers = [x for x in headers if x[0] != '_'] | |
with open(filename, 'wb') as g: | |
w = writer(g) | |
w.writerow(headers) | |
for x in writelist: | |
w.writerow(x) | |
print 'wrote to', filename | |
def readcow(filename): | |
with open(filename, 'rb') as f: | |
# Skip first line of file info junk | |
f.readline() | |
lines = f.readlines() | |
return lines | |
def readlines(inputlines, indicator, fields_s, fields_non_s): | |
outlines_s, outlines_non_s = [], [] | |
for line in inputlines: | |
if line[indicator] == 'S': | |
fields = fields_s | |
output = outlines_s | |
else: | |
fields = fields_non_s | |
output = outlines_non_s | |
output.append(parse_line(line, fields)) | |
return outlines_s, outlines_non_s | |
def main(): | |
lines = readcow(COWFILE) | |
lines_s, lines_non_s = readlines(lines, INDICATOR, FIELDS_S, FIELDS_NON_S) | |
write_file(OUTFILE_S, FIELDS_S.keys(), lines_s) | |
write_file(OUTFILE_NON_S, FIELDS_NON_S.keys(), lines_non_s) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment