-
-
Save ehatton/35724a66abdd53b66cc66dc4022d593d to your computer and use it in GitHub Desktop.
Python script to break large XML files
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
import os | |
import sys | |
from xml.sax import parse | |
from xml.sax.saxutils import XMLGenerator | |
class CycleFile: | |
def __init__(self, filename): | |
self.basename, self.ext = os.path.splitext(filename) | |
self.index = 0 | |
self.open_next_file() | |
def open_next_file(self): | |
self.index += 1 | |
self.file = open(self.name(), 'w') | |
def name(self): | |
return '%s%s%s' % (self.basename, self.index, self.ext) | |
def cycle(self): | |
self.file.close() | |
self.open_next_file() | |
def write(self, str_text): | |
self.file.write( | |
str_text.decode("utf-8") if isinstance(str_text, bytes) else str_text | |
) | |
def close(self): | |
self.file.close() | |
class XMLBreaker(XMLGenerator): | |
def __init__(self, break_into=None, break_after=1000, out=None, *args, **kwargs): | |
XMLGenerator.__init__(self, out, encoding='utf-8', *args, **kwargs) | |
self.out_file = out | |
self.break_into = break_into | |
self.break_after = break_after | |
self.context = [] | |
self.count = 0 | |
def startElement(self, name, attrs): | |
XMLGenerator.startElement(self, name, attrs) | |
self.context.append((name, attrs)) | |
def endElement(self, name): | |
XMLGenerator.endElement(self, name) | |
self.context.pop() | |
if name == self.break_into: | |
self.count += 1 | |
if self.count == self.break_after: | |
self.count = 0 | |
for element in reversed(self.context): | |
self.out_file.write("\n") | |
XMLGenerator.endElement(self, element[0]) | |
self.out_file.cycle() | |
XMLGenerator.startDocument(self) | |
for element in self.context: | |
XMLGenerator.startElement(self, *element) | |
filename, break_into, break_after = sys.argv[1:] | |
parse(filename, XMLBreaker(break_into, int(break_after), out=CycleFile(filename))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment