This is an archive of the discontinued Mercurial Phabricator instance.

Differential D5665

tests: normalize XML values to bytes
ClosedPublic

Authored by indygreg on Jan 23 2019, 7:25 PM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHG7c54357be2ae: tests: normalize XML values to bytes
Summary

This fixes some type mismatches. The encoding shouldn't matter
for what this script is used for. UTF-8 seems reasonable, especially
since I'm pretty sure SVN will emit UTF-8 encoded XML.

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Event Timeline

indygreg created this revision.Jan 23 2019, 7:25 PM
durin42 added a subscriber: durin42.Jan 23 2019, 9:23 PM

Yes, svn is strongly UTF8.

Closed by commit rHG7c54357be2ae: tests: normalize XML values to bytes (authored by indygreg). · Explain WhyJan 23 2019, 9:26 PM
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mtests/svnxml.py (16 lines)

Diff 13383

tests/svnxml.py

e['revision'] = entry.getAttribute('revision') e['revision'] = entry.getAttribute('revision')
e['author'] = xmltext(entry.getElementsByTagName('author')[0]) e['author'] = xmltext(entry.getElementsByTagName('author')[0])
e['msg'] = xmltext(entry.getElementsByTagName('msg')[0]) e['msg'] = xmltext(entry.getElementsByTagName('msg')[0])
e['paths'] = [] e['paths'] = []
paths = entry.getElementsByTagName('paths') paths = entry.getElementsByTagName('paths')
if paths: if paths:
paths = paths[0] paths = paths[0]
for p in paths.getElementsByTagName('path'): for p in paths.getElementsByTagName('path'):
action = p.getAttribute('action') action = p.getAttribute('action').encode('utf-8')
path = xmltext(p) path = xmltext(p).encode('utf-8')
frompath = p.getAttribute('copyfrom-path') frompath = p.getAttribute('copyfrom-path').encode('utf-8')
fromrev = p.getAttribute('copyfrom-rev') fromrev = p.getAttribute('copyfrom-rev').encode('utf-8')
e['paths'].append((path, action, frompath, fromrev)) e['paths'].append((path, action, frompath, fromrev))
return e return e
def parselog(data): def parselog(data):
entries = [] entries = []
doc = xml.dom.minidom.parseString(data) doc = xml.dom.minidom.parseString(data)
for e in doc.getElementsByTagName('logentry'): for e in doc.getElementsByTagName('logentry'):
entries.append(parseentry(e)) entries.append(parseentry(e))
return entries return entries
def printentries(entries): def printentries(entries):
try: try:
fp = sys.stdout.buffer fp = sys.stdout.buffer
except AttributeError: except AttributeError:
fp = sys.stdout fp = sys.stdout
for e in entries: for e in entries:
for k in ('revision', 'author', 'msg'): for k in ('revision', 'author', 'msg'):
fp.write(('%s: %s\n' % (k, e[k])).encode('utf-8')) fp.write(('%s: %s\n' % (k, e[k])).encode('utf-8'))
for path, action, fpath, frev in sorted(e['paths']): for path, action, fpath, frev in sorted(e['paths']):
frominfo = '' frominfo = b''
if frev: if frev:
frominfo = ' (from %s@%s)' % (fpath, frev) frominfo = b' (from %s@%s)' % (fpath, frev)
p = ' %s %s%s\n' % (action, path, frominfo) p = b' %s %s%s\n' % (action, path, frominfo)
fp.write(p.encode('utf-8')) fp.write(p)
if __name__ == '__main__': if __name__ == '__main__':
data = sys.stdin.read() data = sys.stdin.read()
entries = parselog(data) entries = parselog(data)
printentries(entries) printentries(entries)