raw.txt
No One
Actions

Authored By

	• Gilles
	Mar 14 2019, 4:17 PM

Size

696 B

Referenced Files

None

Subscribers

None

raw.txt
View Options

	import subprocess

	input_file = '/mnt/data/xmldatadumps/public/svwiki/20190301/svwiki-20190301-pages-meta-history.xml.bz2'

	output = subprocess.check_output(['getlastidinbz2xml', '-f', input_file, '--type', 'page'])

	revid = int(output.split(':')[1])

	file_id = 0
	step = 1000000
	fspec = []

	for range_start in range(0, revid, step):
	file_id += 1
	range_end = range_start + step

	if range_start == 0:
	range_start = 1

	if range_end > revid:
	range_end = revid

	fspec.append('svwiki-%02d.bz2:%d:%d' % (file_id, range_start, range_end))

	fspec = ','.join(fspec)

	command = ['writeuptopageid', '-fspec', fspec, '-i', input_file, '-odir', '.']

	print(' '.join(command))

	subprocess.call(command)