tests/svnxml.py

run-tests: set a default largefiles usercache in the default hgrc file

This fixes a test failure introduced in 4be754832829 on Windows and OS X, where
the cached largefile wasn't being deleted because the named .cache directory
didn't exist.  It only existed on Linux because the test suite sets $HOME to the
directory of the test being run, and Linux uses $HOME/.cache by default.

Most of the other largefiles tests explicitly set this value at the top of their
scripts, but test-largefiles-update.t didn't pick that up when it was created.
Those scripts that do set a value will override this.

We could just set the parameter in the test-largefiles-update.t script, but
there are a few other non obvious tests that exercise largefiles too.  These
largefiles end up being cached in the user's real cache, so proper hygiene
dictates that this not be left to each individual test script.

# Read the output of a "svn log --xml" command on stdin, parse it and
# print a subset of attributes common to all svn versions tested by
# hg.
import xml.dom.minidom, sys

def xmltext(e):
    return ''.join(c.data for c
                   in e.childNodes
                   if c.nodeType == c.TEXT_NODE)

def parseentry(entry):
    e = {}
    e['revision'] = entry.getAttribute('revision')
    e['author'] = xmltext(entry.getElementsByTagName('author')[0])
    e['msg'] = xmltext(entry.getElementsByTagName('msg')[0])
    e['paths'] = []
    paths = entry.getElementsByTagName('paths')
    if paths:
        paths = paths[0]
        for p in paths.getElementsByTagName('path'):
            action = p.getAttribute('action')
            path = xmltext(p)
            frompath = p.getAttribute('copyfrom-path')
            fromrev = p.getAttribute('copyfrom-rev')
            e['paths'].append((path, action, frompath, fromrev))
    return e

def parselog(data):
    entries = []
    doc = xml.dom.minidom.parseString(data)
    for e in doc.getElementsByTagName('logentry'):
        entries.append(parseentry(e))
    return entries

def printentries(entries):
    fp = sys.stdout
    for e in entries:
        for k in ('revision', 'author', 'msg'):
            fp.write(('%s: %s\n' % (k, e[k])).encode('utf-8'))
        for path, action, fpath, frev in sorted(e['paths']):
            frominfo = ''
            if frev:
                frominfo = ' (from %s@%s)' % (fpath, frev)
            p = ' %s %s%s\n' % (action, path, frominfo)
            fp.write(p.encode('utf-8'))

if __name__ == '__main__':
    data = sys.stdin.read()
    entries = parselog(data)
    printentries(entries)