def number_roots(m):
global TEIcount
TEIcount = TEIcount + 3
return """<TEI xml:id="ch%s" xmlns="http://www.tei-c.org/ns/1.0">""" % TEIcount
## Main
files = handle_args(sys.argv[1:])
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
for file in files:
# set counters to 0 (or a value) to make them reset to that value for each file
# comment counters out to increment across files
# (maybe add a command-line switch for this)
# bibcount = 70
# divcount = 110
# pcount = 480
s = read_file(file)
s = re.sub(r"""<bibl>""", number_bibs, s) ## <-- edit search regex! ## previous
s = re.sub(r"""<div>""", number_divs, s)
s = re.sub(r"""<p>""", number_paras, s)
s = re.sub(r"""<TEI>""", number_roots, s)
write_file(os.path.join(output_dir, file), s)
print "\n TEIcount ended at %s." % TEIcount
print "\n Bibcount ended at %s." % bibcount
print "\n Divcount ended at %s." % divcount
print "\n Pcount ended at %s." % pcount
from implib.io import read_file, write_file import re, sys f = read_file(sys.argv[1]) split = re.compile(r'^.*?$', re.MULTILINE) l = split.findall(f) for item in l: while l.count(item) > 1: l.remove(item) s = '' for item in l: s = s + item + '\n' write_file(sys.argv[2], s)
('\[hm(.+?)\]', r''),
('\[cf..?\]', r''),
('\[..', r''),
('<page.*?>', r''),
('<(/?)I>', r'<\1i>'),
('<(/?)B>', r'<\1b>'),
('<(/?)INF>', r'<\1sub>'),
('<(/?)SUB>', r'<\1sub>'),
('<(/?)SUP>', r'<\1sup>'),
('0\]-9\]', r'')
]
files = glob.glob('*toc')
for file in files:
f = read_file(file)
s_id = shortID(f)
l_id = longID(f)
toc = '<?xml version="1.0" encoding="iso-8859-1"?>\n' \
'<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" ' \
'"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">\n' \
'<html xmlns="http://www.w3.org/1999/xhtml">\n<head>\n<title>' \
'BSSA, Volume ' + s_id + '</title>\n</head>\n' \
'<body bgcolor="#FFFFFF" link="#0000FF" vlink="#FF0000" alink="#E6E6E6">' \
'\n<table cellpadding="20" cellspacing="0" width="500">\n<tr><td>\n' \
'<h2>Bulletin of the<br />Seismological Society of America</h2>\n' \
'<p><b><span style="font-size: larger">' + l_id + '</span></b></p>\n' \
'<h2>Contents</h2>\n'
regex = re.compile('<pag>.*?\]<1>', re.DOTALL)
f = regex.sub('<1>', f)
f = regexr(cleanupL, f)
from implib.io import read_file, write_file
import re, sys
f = read_file(sys.argv[1])
split = re.compile(r'^.*?$', re.MULTILINE)
l = split.findall(f)
for item in l:
while l.count(item) > 1:
l.remove(item)
s = ''
for item in l:
s = s + item + '\n'
write_file(sys.argv[2], s)