view tests/svnxml.py @ 35922:0b79f99fd7b0

lfs: prefetch lfs blobs when applying merge updates

In addition to merge, this method ultimately gets called by many commands:

  - backout
  - bisect
  - clone
  - fetch
  - graft
  - import (without --bypass)
  - pull -u
  - rebase
  - strip
  - share
  - transplant
  - unbundle
  - update

Additionally, it's also called by histedit, shelve, unshelve, and split, but it
seems that the related blobs should always be available locally for these.

For `hg update`, it happens after the normal argument checking and pre-update
hook processing, and remote corruption is detected prior to manipulating the
working directory.  Other commands could use this treatment (archive, cat,
revert, etc), but this covers so many of the frequently used bulk commands, it
seems like a good starting point.

Losing the verbose message that prints the file name before a corrupt blob
aborts the command is a little sad, because there's no easy way to go from oid
to file name.  I'd like to change that message to list the file name so it looks
cleaner and less cryptic, but the pointer object is nowhere near where it needs
to be to do this.  So punt on that for now.

# 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.
from __future__ import absolute_import
import sys
import xml.dom.minidom

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)