merge with stable

mercurial/archival.py

@@ -1,259 +1,266
 # archival.py - revision archival for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from i18n import _
 from node import hex
 import cmdutil
 import util
 import cStringIO, os, stat, tarfile, time, zipfile
 import zlib, gzip
 
 def tidyprefix(dest, kind, prefix):
     '''choose prefix to use for names in archive.  make sure prefix is
     safe for consumers.'''
 
     if prefix:
         prefix = util.normpath(prefix)
     else:
         if not isinstance(dest, str):
             raise ValueError('dest must be string if no prefix')
         prefix = os.path.basename(dest)
         lower = prefix.lower()
         for sfx in exts.get(kind, []):
             if lower.endswith(sfx):
                 prefix = prefix[:-len(sfx)]
                 break
     lpfx = os.path.normpath(util.localpath(prefix))
     prefix = util.pconvert(lpfx)
     if not prefix.endswith('/'):
         prefix += '/'
     if prefix.startswith('../') or os.path.isabs(lpfx) or '/../' in prefix:
         raise util.Abort(_('archive prefix contains illegal components'))
     return prefix
 
 exts = {
     'tar': ['.tar'],
     'tbz2': ['.tbz2', '.tar.bz2'],
     'tgz': ['.tgz', '.tar.gz'],
     'zip': ['.zip'],
     }
 
 def guesskind(dest):
     for kind, extensions in exts.iteritems():
         if util.any(dest.endswith(ext) for ext in extensions):
             return kind
     return None
 
 
 class tarit(object):
     '''write archive to tar file or stream.  can write uncompressed,
     or compress with gzip or bzip2.'''
 
     class GzipFileWithTime(gzip.GzipFile):
 
         def __init__(self, *args, **kw):
             timestamp = None
             if 'timestamp' in kw:
                 timestamp = kw.pop('timestamp')
             if timestamp is None:
                 self.timestamp = time.time()
             else:
                 self.timestamp = timestamp
             gzip.GzipFile.__init__(self, *args, **kw)
 
         def _write_gzip_header(self):
             self.fileobj.write('\037\213')             # magic header
             self.fileobj.write('\010')                 # compression method
             # Python 2.6 deprecates self.filename
             fname = getattr(self, 'name', None) or self.filename
             flags = 0
             if fname:
                 flags = gzip.FNAME
             self.fileobj.write(chr(flags))
             gzip.write32u(self.fileobj, long(self.timestamp))
             self.fileobj.write('\002')
             self.fileobj.write('\377')
             if fname:
                 self.fileobj.write(fname + '\000')
 
     def __init__(self, dest, mtime, kind=''):
         self.mtime = mtime
 
         def taropen(name, mode, fileobj=None):
             if kind == 'gz':
                 mode = mode[0]
                 if not fileobj:
                     fileobj = open(name, mode + 'b')
                 gzfileobj = self.GzipFileWithTime(name, mode + 'b',
                                                   zlib.Z_BEST_COMPRESSION,
                                                   fileobj, timestamp=mtime)
                 return tarfile.TarFile.taropen(name, mode, gzfileobj)
             else:
                 return tarfile.open(name, mode + kind, fileobj)
 
         if isinstance(dest, str):
             self.z = taropen(dest, mode='w:')
         else:
             # Python 2.5-2.5.1 have a regression that requires a name arg
             self.z = taropen(name='', mode='w|', fileobj=dest)
 
     def addfile(self, name, mode, islink, data):
         i = tarfile.TarInfo(name)
         i.mtime = self.mtime
         i.size = len(data)
         if islink:
             i.type = tarfile.SYMTYPE
             i.mode = 0777
             i.linkname = data
             data = None
             i.size = 0
         else:
             i.mode = mode
             data = cStringIO.StringIO(data)
         self.z.addfile(i, data)
 
     def done(self):
         self.z.close()
 
 class tellable(object):
     '''provide tell method for zipfile.ZipFile when writing to http
     response file object.'''
 
     def __init__(self, fp):
         self.fp = fp
         self.offset = 0
 
     def __getattr__(self, key):
         return getattr(self.fp, key)
 
     def write(self, s):
         self.fp.write(s)
         self.offset += len(s)
 
     def tell(self):
         return self.offset
 
 class zipit(object):
     '''write archive to zip file or stream.  can write uncompressed,
     or compressed with deflate.'''
 
     def __init__(self, dest, mtime, compress=True):
         if not isinstance(dest, str):
             try:
                 dest.tell()
             except (AttributeError, IOError):
                 dest = tellable(dest)
         self.z = zipfile.ZipFile(dest, 'w',
                                  compress and zipfile.ZIP_DEFLATED or
                                  zipfile.ZIP_STORED)
+
+        # Python's zipfile module emits deprecation warnings if we try
+        # to store files with a date before 1980.
+        epoch = 315532800 # calendar.timegm((1980, 1, 1, 0, 0, 0, 1, 1, 0))
+        if mtime < epoch:
+            mtime = epoch
+
         self.date_time = time.gmtime(mtime)[:6]
 
     def addfile(self, name, mode, islink, data):
         i = zipfile.ZipInfo(name, self.date_time)
         i.compress_type = self.z.compression
         # unzip will not honor unix file modes unless file creator is
         # set to unix (id 3).
         i.create_system = 3
         ftype = stat.S_IFREG
         if islink:
             mode = 0777
             ftype = stat.S_IFLNK
         i.external_attr = (mode | ftype) << 16L
         self.z.writestr(i, data)
 
     def done(self):
         self.z.close()
 
 class fileit(object):
     '''write archive as files in directory.'''
 
     def __init__(self, name, mtime):
         self.basedir = name
         self.opener = util.opener(self.basedir)
 
     def addfile(self, name, mode, islink, data):
         if islink:
             self.opener.symlink(data, name)
             return
         f = self.opener(name, "w", atomictemp=True)
         f.write(data)
         f.rename()
         destfile = os.path.join(self.basedir, name)
         os.chmod(destfile, mode)
 
     def done(self):
         pass
 
 archivers = {
     'files': fileit,
     'tar': tarit,
     'tbz2': lambda name, mtime: tarit(name, mtime, 'bz2'),
     'tgz': lambda name, mtime: tarit(name, mtime, 'gz'),
     'uzip': lambda name, mtime: zipit(name, mtime, False),
     'zip': zipit,
     }
 
 def archive(repo, dest, node, kind, decode=True, matchfn=None,
             prefix=None, mtime=None):
     '''create archive of repo as it was at node.
 
     dest can be name of directory, name of archive file, or file
     object to write archive to.
 
     kind is type of archive to create.
 
     decode tells whether to put files through decode filters from
     hgrc.
 
     matchfn is function to filter names of files to write to archive.
 
     prefix is name of path to put before every archive member.'''
 
     if kind == 'files':
         if prefix:
             raise util.Abort(_('cannot give prefix when archiving to files'))
     else:
         prefix = tidyprefix(dest, kind, prefix)
 
     def write(name, mode, islink, getdata):
         if matchfn and not matchfn(name):
             return
         data = getdata()
         if decode:
             data = repo.wwritedata(name, data)
         archiver.addfile(prefix + name, mode, islink, data)
 
     if kind not in archivers:
         raise util.Abort(_("unknown archive type '%s'") % kind)
 
     ctx = repo[node]
     archiver = archivers[kind](dest, mtime or ctx.date()[0])
 
     if repo.ui.configbool("ui", "archivemeta", True):
         def metadata():
             base = 'repo: %s\nnode: %s\nbranch: %s\n' % (
                 repo[0].hex(), hex(node), ctx.branch())
 
             tags = ''.join('tag: %s\n' % t for t in ctx.tags()
                            if repo.tagtype(t) == 'global')
             if not tags:
                 repo.ui.pushbuffer()
                 opts = {'template': '{latesttag}\n{latesttagdistance}',
                         'style': '', 'patch': None, 'git': None}
                 cmdutil.show_changeset(repo.ui, repo, opts).show(ctx)
                 ltags, dist = repo.ui.popbuffer().split('\n')
                 tags = ''.join('latesttag: %s\n' % t for t in ltags.split(':'))
                 tags += 'latesttagdistance: %s\n' % dist
 
             return base + tags
 
         write('.hg_archival.txt', 0644, False, metadata)
 
     for f in ctx:
         ff = ctx.flags(f)
         write(f, 'x' in ff and 0755 or 0644, 'l' in ff, ctx[f].data)
     archiver.done()

mercurial/revset.py

@@ -1,588 +1,591
 # revset.py - revision set queries for mercurial
 #
 # Copyright 2010 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import re
 import parser, util, error, discovery
 import match as matchmod
 from i18n import _
 
 elements = {
     "(": (20, ("group", 1, ")"), ("func", 1, ")")),
     "-": (19, ("negate", 19), ("minus", 19)),
     "::": (17, ("dagrangepre", 17), ("dagrange", 17),
            ("dagrangepost", 17)),
     "..": (17, ("dagrangepre", 17), ("dagrange", 17),
            ("dagrangepost", 17)),
     ":": (15, ("rangepre", 15), ("range", 15), ("rangepost", 15)),
     "not": (10, ("not", 10)),
     "!": (10, ("not", 10)),
     "and": (5, None, ("and", 5)),
     "&": (5, None, ("and", 5)),
     "or": (4, None, ("or", 4)),
     "|": (4, None, ("or", 4)),
     "+": (4, None, ("or", 4)),
     ",": (2, None, ("list", 2)),
     ")": (0, None, None),
     "symbol": (0, ("symbol",), None),
     "string": (0, ("string",), None),
     "end": (0, None, None),
 }
 
 keywords = set(['and', 'or', 'not'])
 
 def tokenize(program):
     pos, l = 0, len(program)
     while pos < l:
         c = program[pos]
         if c.isspace(): # skip inter-token whitespace
             pass
         elif c == ':' and program[pos:pos + 2] == '::': # look ahead carefully
             yield ('::', None, pos)
             pos += 1 # skip ahead
         elif c == '.' and program[pos:pos + 2] == '..': # look ahead carefully
             yield ('..', None, pos)
             pos += 1 # skip ahead
         elif c in "():,-|&+!": # handle simple operators
             yield (c, None, pos)
         elif c in '"\'': # handle quoted strings
             pos += 1
             s = pos
             while pos < l: # find closing quote
                 d = program[pos]
                 if d == '\\': # skip over escaped characters
                     pos += 2
                     continue
                 if d == c:
                     yield ('string', program[s:pos].decode('string-escape'), s)
                     break
                 pos += 1
             else:
                 raise error.ParseError(_("unterminated string"), s)
         elif c.isalnum() or c in '._' or ord(c) > 127: # gather up a symbol/keyword
             s = pos
             pos += 1
             while pos < l: # find end of symbol
                 d = program[pos]
                 if not (d.isalnum() or d in "._" or ord(d) > 127):
                     break
                 if d == '.' and program[pos - 1] == '.': # special case for ..
                     pos -= 1
                     break
                 pos += 1
             sym = program[s:pos]
             if sym in keywords: # operator keywords
                 yield (sym, None, s)
             else:
                 yield ('symbol', sym, s)
             pos -= 1
         else:
             raise error.ParseError(_("syntax error"), pos)
         pos += 1
     yield ('end', None, pos)
 
 # helpers
 
 def getstring(x, err):
     if x and (x[0] == 'string' or x[0] == 'symbol'):
         return x[1]
     raise error.ParseError(err)
 
 def getlist(x):
     if not x:
         return []
     if x[0] == 'list':
         return getlist(x[1]) + [x[2]]
     return [x]
 
 def getargs(x, min, max, err):
     l = getlist(x)
     if len(l) < min or len(l) > max:
         raise error.ParseError(err)
     return l
 
 def getset(repo, subset, x):
     if not x:
         raise error.ParseError(_("missing argument"))
     return methods[x[0]](repo, subset, *x[1:])
 
 # operator methods
 
 def stringset(repo, subset, x):
     x = repo[x].rev()
     if x == -1 and len(subset) == len(repo):
         return [-1]
     if x in subset:
         return [x]
     return []
 
 def symbolset(repo, subset, x):
     if x in symbols:
         raise error.ParseError(_("can't use %s here") % x)
     return stringset(repo, subset, x)
 
 def rangeset(repo, subset, x, y):
     m = getset(repo, subset, x)
     if not m:
         m = getset(repo, range(len(repo)), x)
 
     n = getset(repo, subset, y)
     if not n:
         n = getset(repo, range(len(repo)), y)
 
     if not m or not n:
         return []
     m, n = m[0], n[-1]
 
     if m < n:
         r = range(m, n + 1)
     else:
         r = range(m, n - 1, -1)
     s = set(subset)
     return [x for x in r if x in s]
 
 def andset(repo, subset, x, y):
     return getset(repo, getset(repo, subset, x), y)
 
 def orset(repo, subset, x, y):
     s = set(getset(repo, subset, x))
     s |= set(getset(repo, [r for r in subset if r not in s], y))
     return [r for r in subset if r in s]
 
 def notset(repo, subset, x):
     s = set(getset(repo, subset, x))
     return [r for r in subset if r not in s]
 
 def listset(repo, subset, a, b):
     raise error.ParseError(_("can't use a list in this context"))
 
 def func(repo, subset, a, b):
     if a[0] == 'symbol' and a[1] in symbols:
         return symbols[a[1]](repo, subset, b)
     raise error.ParseError(_("not a function: %s") % a[1])
 
 # functions
 
 def p1(repo, subset, x):
     ps = set()
     cl = repo.changelog
     for r in getset(repo, subset, x):
         ps.add(cl.parentrevs(r)[0])
     return [r for r in subset if r in ps]
 
 def p2(repo, subset, x):
     ps = set()
     cl = repo.changelog
     for r in getset(repo, subset, x):
         ps.add(cl.parentrevs(r)[1])
     return [r for r in subset if r in ps]
 
 def parents(repo, subset, x):
     ps = set()
     cl = repo.changelog
     for r in getset(repo, subset, x):
         ps.update(cl.parentrevs(r))
     return [r for r in subset if r in ps]
 
 def maxrev(repo, subset, x):
     s = getset(repo, subset, x)
     if s:
         m = max(s)
         if m in subset:
             return [m]
     return []
 
 def minrev(repo, subset, x):
     s = getset(repo, subset, x)
     if s:
         m = min(s)
         if m in subset:
             return [m]
     return []
 
 def limit(repo, subset, x):
     l = getargs(x, 2, 2, _("limit wants two arguments"))
     try:
         lim = int(getstring(l[1], _("limit wants a number")))
     except ValueError:
         raise error.ParseError(_("limit expects a number"))
     return getset(repo, subset, l[0])[:lim]
 
 def children(repo, subset, x):
     cs = set()
     cl = repo.changelog
     s = set(getset(repo, subset, x))
     for r in xrange(0, len(repo)):
         for p in cl.parentrevs(r):
             if p in s:
                 cs.add(r)
     return [r for r in subset if r in cs]
 
 def branch(repo, subset, x):
     s = getset(repo, range(len(repo)), x)
     b = set()
     for r in s:
         b.add(repo[r].branch())
     s = set(s)
     return [r for r in subset if r in s or repo[r].branch() in b]
 
 def ancestor(repo, subset, x):
     l = getargs(x, 2, 2, _("ancestor wants two arguments"))
     r = range(len(repo))
     a = getset(repo, r, l[0])
     b = getset(repo, r, l[1])
     if len(a) != 1 or len(b) != 1:
         raise error.ParseError(_("ancestor arguments must be single revisions"))
     an = [repo[a[0]].ancestor(repo[b[0]]).rev()]
 
     return [r for r in an if r in subset]
 
 def ancestors(repo, subset, x):
     args = getset(repo, range(len(repo)), x)
     if not args:
         return []
     s = set(repo.changelog.ancestors(*args)) | set(args)
     return [r for r in subset if r in s]
 
 def descendants(repo, subset, x):
     args = getset(repo, range(len(repo)), x)
     if not args:
         return []
     s = set(repo.changelog.descendants(*args)) | set(args)
     return [r for r in subset if r in s]
 
 def follow(repo, subset, x):
     getargs(x, 0, 0, _("follow takes no arguments"))
     p = repo['.'].rev()
     s = set(repo.changelog.ancestors(p)) | set([p])
     return [r for r in subset if r in s]
 
 def date(repo, subset, x):
     ds = getstring(x, _("date wants a string"))
     dm = util.matchdate(ds)
     return [r for r in subset if dm(repo[r].date()[0])]
 
 def keyword(repo, subset, x):
     kw = getstring(x, _("keyword wants a string")).lower()
     l = []
     for r in subset:
         c = repo[r]
         t = " ".join(c.files() + [c.user(), c.description()])
         if kw in t.lower():
             l.append(r)
     return l
 
 def grep(repo, subset, x):
-    gr = re.compile(getstring(x, _("grep wants a string")))
+    try:
+        gr = re.compile(getstring(x, _("grep wants a string")))
+    except re.error, e:
+        raise error.ParseError(_('invalid match pattern: %s') % e)
     l = []
     for r in subset:
         c = repo[r]
         for e in c.files() + [c.user(), c.description()]:
             if gr.search(e):
                 l.append(r)
                 continue
     return l
 
 def author(repo, subset, x):
     n = getstring(x, _("author wants a string")).lower()
     return [r for r in subset if n in repo[r].user().lower()]
 
 def hasfile(repo, subset, x):
     pat = getstring(x, _("file wants a pattern"))
     m = matchmod.match(repo.root, repo.getcwd(), [pat])
     s = []
     for r in subset:
         for f in repo[r].files():
             if m(f):
                 s.append(r)
                 continue
     return s
 
 def contains(repo, subset, x):
     pat = getstring(x, _("contains wants a pattern"))
     m = matchmod.match(repo.root, repo.getcwd(), [pat])
     s = []
     if m.files() == [pat]:
         for r in subset:
             if pat in repo[r]:
                 s.append(r)
                 continue
     else:
         for r in subset:
             for f in repo[r].manifest():
                 if m(f):
                     s.append(r)
                     continue
     return s
 
 def checkstatus(repo, subset, pat, field):
     m = matchmod.match(repo.root, repo.getcwd(), [pat])
     s = []
     fast = (m.files() == [pat])
     for r in subset:
         c = repo[r]
         if fast:
             if pat not in c.files():
                 continue
         else:
             for f in c.files():
                 if m(f):
                     break
             else:
                 continue
         files = repo.status(c.p1().node(), c.node())[field]
         if fast:
             if pat in files:
                 s.append(r)
                 continue
         else:
             for f in files:
                 if m(f):
                     s.append(r)
                     continue
     return s
 
 def modifies(repo, subset, x):
     pat = getstring(x, _("modifies wants a pattern"))
     return checkstatus(repo, subset, pat, 0)
 
 def adds(repo, subset, x):
     pat = getstring(x, _("adds wants a pattern"))
     return checkstatus(repo, subset, pat, 1)
 
 def removes(repo, subset, x):
     pat = getstring(x, _("removes wants a pattern"))
     return checkstatus(repo, subset, pat, 2)
 
 def merge(repo, subset, x):
     getargs(x, 0, 0, _("merge takes no arguments"))
     cl = repo.changelog
     return [r for r in subset if cl.parentrevs(r)[1] != -1]
 
 def closed(repo, subset, x):
     getargs(x, 0, 0, _("closed takes no arguments"))
     return [r for r in subset if repo[r].extra().get('close')]
 
 def head(repo, subset, x):
     getargs(x, 0, 0, _("head takes no arguments"))
     hs = set()
     for b, ls in repo.branchmap().iteritems():
         hs.update(repo[h].rev() for h in ls)
     return [r for r in subset if r in hs]
 
 def reverse(repo, subset, x):
     l = getset(repo, subset, x)
     l.reverse()
     return l
 
 def present(repo, subset, x):
     try:
         return getset(repo, subset, x)
     except error.RepoLookupError:
         return []
 
 def sort(repo, subset, x):
     l = getargs(x, 1, 2, _("sort wants one or two arguments"))
     keys = "rev"
     if len(l) == 2:
         keys = getstring(l[1], _("sort spec must be a string"))
 
     s = l[0]
     keys = keys.split()
     l = []
     def invert(s):
         return "".join(chr(255 - ord(c)) for c in s)
     for r in getset(repo, subset, s):
         c = repo[r]
         e = []
         for k in keys:
             if k == 'rev':
                 e.append(r)
             elif k == '-rev':
                 e.append(-r)
             elif k == 'branch':
                 e.append(c.branch())
             elif k == '-branch':
                 e.append(invert(c.branch()))
             elif k == 'desc':
                 e.append(c.description())
             elif k == '-desc':
                 e.append(invert(c.description()))
             elif k in 'user author':
                 e.append(c.user())
             elif k in '-user -author':
                 e.append(invert(c.user()))
             elif k == 'date':
                 e.append(c.date()[0])
             elif k == '-date':
                 e.append(-c.date()[0])
             else:
                 raise error.ParseError(_("unknown sort key %r") % k)
         e.append(r)
         l.append(e)
     l.sort()
     return [e[-1] for e in l]
 
 def getall(repo, subset, x):
     getargs(x, 0, 0, _("all takes no arguments"))
     return subset
 
 def heads(repo, subset, x):
     s = getset(repo, subset, x)
     ps = set(parents(repo, subset, x))
     return [r for r in s if r not in ps]
 
 def roots(repo, subset, x):
     s = getset(repo, subset, x)
     cs = set(children(repo, subset, x))
     return [r for r in s if r not in cs]
 
 def outgoing(repo, subset, x):
     import hg # avoid start-up nasties
     l = getargs(x, 0, 1, _("outgoing wants a repository path"))
     dest = l and getstring(l[0], _("outgoing wants a repository path")) or ''
     dest = repo.ui.expandpath(dest or 'default-push', dest or 'default')
     dest, branches = hg.parseurl(dest)
     other = hg.repository(hg.remoteui(repo, {}), dest)
     repo.ui.pushbuffer()
     o = discovery.findoutgoing(repo, other)
     repo.ui.popbuffer()
     cl = repo.changelog
     o = set([cl.rev(r) for r in repo.changelog.nodesbetween(o, None)[0]])
     return [r for r in subset if r in o]
 
 def tagged(repo, subset, x):
     getargs(x, 0, 0, _("tagged takes no arguments"))
     cl = repo.changelog
     s = set([cl.rev(n) for t, n in repo.tagslist() if t != 'tip'])
     return [r for r in subset if r in s]
 
 symbols = {
     "adds": adds,
     "all": getall,
     "ancestor": ancestor,
     "ancestors": ancestors,
     "author": author,
     "branch": branch,
     "children": children,
     "closed": closed,
     "contains": contains,
     "date": date,
     "descendants": descendants,
     "file": hasfile,
     "follow": follow,
     "grep": grep,
     "head": head,
     "heads": heads,
     "keyword": keyword,
     "limit": limit,
     "max": maxrev,
     "min": minrev,
     "merge": merge,
     "modifies": modifies,
     "outgoing": outgoing,
     "p1": p1,
     "p2": p2,
     "parents": parents,
     "present": present,
     "removes": removes,
     "reverse": reverse,
     "roots": roots,
     "sort": sort,
     "tagged": tagged,
     "user": author,
 }
 
 methods = {
     "range": rangeset,
     "string": stringset,
     "symbol": symbolset,
     "and": andset,
     "or": orset,
     "not": notset,
     "list": listset,
     "func": func,
 }
 
 def optimize(x, small):
     if x == None:
         return 0, x
 
     smallbonus = 1
     if small:
         smallbonus = .5
 
     op = x[0]
     if op == 'minus':
         return optimize(('and', x[1], ('not', x[2])), small)
     elif op == 'dagrange':
         return optimize(('and', ('func', ('symbol', 'descendants'), x[1]),
                          ('func', ('symbol', 'ancestors'), x[2])), small)
     elif op == 'dagrangepre':
         return optimize(('func', ('symbol', 'ancestors'), x[1]), small)
     elif op == 'dagrangepost':
         return optimize(('func', ('symbol', 'descendants'), x[1]), small)
     elif op == 'rangepre':
         return optimize(('range', ('string', '0'), x[1]), small)
     elif op == 'rangepost':
         return optimize(('range', x[1], ('string', 'tip')), small)
     elif op == 'negate':
         return optimize(('string',
                          '-' + getstring(x[1], _("can't negate that"))), small)
     elif op in 'string symbol negate':
         return smallbonus, x # single revisions are small
     elif op == 'and' or op == 'dagrange':
         wa, ta = optimize(x[1], True)
         wb, tb = optimize(x[2], True)
         w = min(wa, wb)
         if wa > wb:
             return w, (op, tb, ta)
         return w, (op, ta, tb)
     elif op == 'or':
         wa, ta = optimize(x[1], False)
         wb, tb = optimize(x[2], False)
         if wb < wa:
             wb, wa = wa, wb
         return max(wa, wb), (op, ta, tb)
     elif op == 'not':
         o = optimize(x[1], not small)
         return o[0], (op, o[1])
     elif op == 'group':
         return optimize(x[1], small)
     elif op in 'range list':
         wa, ta = optimize(x[1], small)
         wb, tb = optimize(x[2], small)
         return wa + wb, (op, ta, tb)
     elif op == 'func':
         f = getstring(x[1], _("not a symbol"))
         wa, ta = optimize(x[2], small)
         if f in "grep date user author keyword branch file":
             w = 10 # slow
         elif f in "modifies adds removes outgoing":
             w = 30 # slower
         elif f == "contains":
             w = 100 # very slow
         elif f == "ancestor":
             w = 1 * smallbonus
         elif f == "reverse limit":
             w = 0
         elif f in "sort":
             w = 10 # assume most sorts look at changelog
         else:
             w = 1
         return w + wa, (op, x[1], ta)
     return 1, x
 
 parse = parser.parser(tokenize, elements).parse
 
 def match(spec):
     if not spec:
         raise error.ParseError(_("empty query"))
     tree = parse(spec)
     weight, tree = optimize(tree, True)
     def mfunc(repo, subset):
         return getset(repo, subset, tree)
     return mfunc

tests/test-archive.t

@@ -1,223 +1,237
   $ mkdir test
   $ cd test
   $ hg init
   $ echo foo>foo
   $ hg commit -Am 1 -d '1 0'
   adding foo
   $ echo bar>bar
   $ hg commit -Am 2 -d '2 0'
   adding bar
   $ mkdir baz
   $ echo bletch>baz/bletch
   $ hg commit -Am 3 -d '1000000000 0'
   adding baz/bletch
   $ echo "[web]" >> .hg/hgrc
   $ echo "name = test-archive" >> .hg/hgrc
   $ cp .hg/hgrc .hg/hgrc-base
   > test_archtype() {
   >     echo "allow_archive = $1" >> .hg/hgrc
   >     hg serve -p $HGPORT -d --pid-file=hg.pid -E errors.log
   >     cat hg.pid >> $DAEMON_PIDS
   >     echo % $1 allowed should give 200
   >     "$TESTDIR/get-with-headers.py" localhost:$HGPORT "/archive/tip.$2" | head -n 1
   >     echo % $3 and $4 disallowed should both give 403
   >     "$TESTDIR/get-with-headers.py" localhost:$HGPORT "/archive/tip.$3" | head -n 1
   >     "$TESTDIR/get-with-headers.py" localhost:$HGPORT "/archive/tip.$4" | head -n 1
   >     "$TESTDIR/killdaemons.py"
   >     cat errors.log
   >     cp .hg/hgrc-base .hg/hgrc
   > }
 
 check http return codes
 
 
   $ test_archtype gz tar.gz tar.bz2 zip
   % gz allowed should give 200
   200 Script output follows
   % tar.bz2 and zip disallowed should both give 403
   403 Archive type not allowed: bz2
   403 Archive type not allowed: zip
   $ test_archtype bz2 tar.bz2 zip tar.gz
   % bz2 allowed should give 200
   200 Script output follows
   % zip and tar.gz disallowed should both give 403
   403 Archive type not allowed: zip
   403 Archive type not allowed: gz
   $ test_archtype zip zip tar.gz tar.bz2
   % zip allowed should give 200
   200 Script output follows
   % tar.gz and tar.bz2 disallowed should both give 403
   403 Archive type not allowed: gz
   403 Archive type not allowed: bz2
 
   $ echo "allow_archive = gz bz2 zip" >> .hg/hgrc
   $ hg serve -p $HGPORT -d --pid-file=hg.pid -E errors.log
   $ cat hg.pid >> $DAEMON_PIDS
 
 invalid arch type should give 404
 
   $ "$TESTDIR/get-with-headers.py" localhost:$HGPORT "/archive/tip.invalid" | head -n 1
   404 Unsupported archive type: None
 
   $ TIP=`hg id -v | cut -f1 -d' '`
   $ QTIP=`hg id -q`
   $ cat > getarchive.py <<EOF
   > import os, sys, urllib2
   > try:
   >     # Set stdout to binary mode for win32 platforms
   >     import msvcrt
   >     msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
   > except ImportError:
   >     pass
   > node, archive = sys.argv[1:]
   > f = urllib2.urlopen('http://127.0.0.1:%s/?cmd=archive;node=%s;type=%s'
   >                     % (os.environ['HGPORT'], node, archive))
   > sys.stdout.write(f.read())
   > EOF
   $ python getarchive.py "$TIP" gz | gunzip | tar tf - 2>/dev/null | sed "s/$QTIP/TIP/"
   test-archive-TIP/.hg_archival.txt
   test-archive-TIP/bar
   test-archive-TIP/baz/bletch
   test-archive-TIP/foo
   $ python getarchive.py "$TIP" bz2 | bunzip2 | tar tf - 2>/dev/null | sed "s/$QTIP/TIP/"
   test-archive-TIP/.hg_archival.txt
   test-archive-TIP/bar
   test-archive-TIP/baz/bletch
   test-archive-TIP/foo
   $ python getarchive.py "$TIP" zip > archive.zip
   $ unzip -t archive.zip | sed "s/$QTIP/TIP/"
   Archive:  archive.zip
       testing: test-archive-TIP/.hg_archival.txt   OK
       testing: test-archive-TIP/bar   OK
       testing: test-archive-TIP/baz/bletch   OK
       testing: test-archive-TIP/foo   OK
   No errors detected in compressed data of archive.zip.
 
   $ "$TESTDIR/killdaemons.py"
 
   $ hg archive -t tar test.tar
   $ tar tf test.tar
   test/.hg_archival.txt
   test/bar
   test/baz/bletch
   test/foo
 
   $ hg archive -t tbz2 -X baz test.tar.bz2
   $ bunzip2 -dc test.tar.bz2 | tar tf - 2>/dev/null
   test/.hg_archival.txt
   test/bar
   test/foo
 
   $ hg archive -t tgz -p %b-%h test-%h.tar.gz
   $ gzip -dc test-$QTIP.tar.gz | tar tf - 2>/dev/null | sed "s/$QTIP/TIP/"
   test-TIP/.hg_archival.txt
   test-TIP/bar
   test-TIP/baz/bletch
   test-TIP/foo
 
   $ hg archive autodetected_test.tar
   $ tar tf autodetected_test.tar
   autodetected_test/.hg_archival.txt
   autodetected_test/bar
   autodetected_test/baz/bletch
   autodetected_test/foo
 
 The '-t' should override autodetection
 
   $ hg archive -t tar autodetect_override_test.zip
   $ tar tf autodetect_override_test.zip
   autodetect_override_test.zip/.hg_archival.txt
   autodetect_override_test.zip/bar
   autodetect_override_test.zip/baz/bletch
   autodetect_override_test.zip/foo
 
   $ for ext in tar tar.gz tgz tar.bz2 tbz2 zip; do
   >     hg archive auto_test.$ext
   >     if [ -d auto_test.$ext ]; then
   >         echo "extension $ext was not autodetected."
   >     fi
   > done
 
   $ cat > md5comp.py <<EOF
   > try:
   >     from hashlib import md5
   > except ImportError:
   >     from md5 import md5
   > import sys
   > f1, f2 = sys.argv[1:3]
   > h1 = md5(file(f1, 'rb').read()).hexdigest()
   > h2 = md5(file(f2, 'rb').read()).hexdigest()
   > print h1 == h2 or "md5 differ: " + repr((h1, h2))
   > EOF
 
 archive name is stored in the archive, so create similar
 
 archives and rename them afterwards.
 
   $ hg archive -t tgz tip.tar.gz
   $ mv tip.tar.gz tip1.tar.gz
   $ sleep 1
   $ hg archive -t tgz tip.tar.gz
   $ mv tip.tar.gz tip2.tar.gz
   $ python md5comp.py tip1.tar.gz tip2.tar.gz
   True
 
   $ hg archive -t zip -p /illegal test.zip
   abort: archive prefix contains illegal components
   [255]
   $ hg archive -t zip -p very/../bad test.zip
 
   $ hg archive --config ui.archivemeta=false -t zip -r 2 test.zip
   $ unzip -t test.zip
   Archive:  test.zip
       testing: test/bar                 OK
       testing: test/baz/bletch          OK
       testing: test/foo                 OK
   No errors detected in compressed data of test.zip.
 
   $ hg archive -t tar - | tar tf - 2>/dev/null | sed "s/$QTIP/TIP/"
   test-TIP/.hg_archival.txt
   test-TIP/bar
   test-TIP/baz/bletch
   test-TIP/foo
 
   $ hg archive -r 0 -t tar rev-%r.tar
   $ if [ -f rev-0.tar ]; then
   $ fi
 
 test .hg_archival.txt
 
   $ hg archive ../test-tags
   $ cat ../test-tags/.hg_archival.txt
   repo: daa7f7c60e0a224faa4ff77ca41b2760562af264
   node: 2c0277f05ed49d1c8328fb9ba92fba7a5ebcb33e
   branch: default
   latesttag: null
   latesttagdistance: 3
   $ hg tag -r 2 mytag
   $ hg tag -r 2 anothertag
   $ hg archive -r 2 ../test-lasttag
   $ cat ../test-lasttag/.hg_archival.txt
   repo: daa7f7c60e0a224faa4ff77ca41b2760562af264
   node: 2c0277f05ed49d1c8328fb9ba92fba7a5ebcb33e
   branch: default
   tag: anothertag
   tag: mytag
 
   $ hg archive -t bogus test.bogus
   abort: unknown archive type 'bogus'
   [255]
 
 server errors
 
   $ cat errors.log
 
 empty repo
 
   $ hg init ../empty
   $ cd ../empty
   $ hg archive ../test-empty
   abort: no working directory: please specify a revision
   [255]
+old file -- date clamped to 1980
+
+  $ touch -d 1975-01-01 old
+  $ hg add old
+  $ hg commit -m old
+  $ hg archive ../old.zip
+  $ unzip -l ../old.zip
+  Archive:  ../old.zip
+    Length      Date    Time    Name
+  ---------  ---------- -----   ----
+        147  1980-01-01 00:00   old/.hg_archival.txt
+          0  1980-01-01 00:00   old/old
+  ---------                     -------
+        147                     2 files
 
   $ exit 0

tests/test-revset.t

@@ -1,317 +1,321
   $ HGENCODING=utf-8
   $ export HGENCODING
 
   $ try() {
   >   hg debugrevspec --debug $@
   > }
 
   $ log() {
   >   hg log --template '{rev}\n' -r "$1"
   > }
 
   $ hg init repo
   $ cd repo
 
   $ echo a > a
   $ hg branch a
   marked working directory as branch a
   $ hg ci -Aqm0
 
   $ echo b > b
   $ hg branch b
   marked working directory as branch b
   $ hg ci -Aqm1
 
   $ rm a
   $ hg branch a-b-c-
   marked working directory as branch a-b-c-
   $ hg ci -Aqm2 -u Bob
 
   $ hg co 1
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg branch +a+b+c+
   marked working directory as branch +a+b+c+
   $ hg ci -Aqm3
 
   $ hg co 2  # interleave
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ echo bb > b
   $ hg branch -- -a-b-c-
   marked working directory as branch -a-b-c-
   $ hg ci -Aqm4 -d "May 12 2005"
 
   $ hg co 3
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg branch /a/b/c/
   marked working directory as branch /a/b/c/
   $ hg ci -Aqm"5 bug"
 
   $ hg merge 4
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
   $ hg branch _a_b_c_
   marked working directory as branch _a_b_c_
   $ hg ci -Aqm"6 issue619"
 
   $ hg branch .a.b.c.
   marked working directory as branch .a.b.c.
   $ hg ci -Aqm7
 
   $ hg branch all
   marked working directory as branch all
   $ hg ci --close-branch -Aqm8
   abort: can only close branch heads
   [255]
 
   $ hg co 4
   0 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg branch é
   marked working directory as branch é
   $ hg ci -Aqm9
 
   $ hg tag -r6 1.0
 
   $ hg clone --quiet -U -r 7 . ../remote1
   $ hg clone --quiet -U -r 8 . ../remote2
   $ echo "[paths]" >> .hg/hgrc
   $ echo "default = ../remote1" >> .hg/hgrc
 
 names that should work without quoting
 
   $ try a
   ('symbol', 'a')
   0
   $ try b-a
   ('minus', ('symbol', 'b'), ('symbol', 'a'))
   1
   $ try _a_b_c_
   ('symbol', '_a_b_c_')
   6
   $ try _a_b_c_-a
   ('minus', ('symbol', '_a_b_c_'), ('symbol', 'a'))
   6
   $ try .a.b.c.
   ('symbol', '.a.b.c.')
   7
   $ try .a.b.c.-a
   ('minus', ('symbol', '.a.b.c.'), ('symbol', 'a'))
   7
   $ try -- '-a-b-c-' # complains
   hg: parse error at 7: not a prefix: end
   [255]
   $ log -a-b-c- # succeeds with fallback
   4
   $ try -- -a-b-c--a # complains
   ('minus', ('minus', ('minus', ('negate', ('symbol', 'a')), ('symbol', 'b')), ('symbol', 'c')), ('negate', ('symbol', 'a')))
   abort: unknown revision '-a'!
   [255]
   $ try é
   ('symbol', '\xc3\xa9')
   9
 
 quoting needed
 
   $ try '"-a-b-c-"-a'
   ('minus', ('string', '-a-b-c-'), ('symbol', 'a'))
   4
 
   $ log '1 or 2'
   1
   2
   $ log '1|2'
   1
   2
   $ log '1 and 2'
   $ log '1&2'
   $ try '1&2|3' # precedence - and is higher
   ('or', ('and', ('symbol', '1'), ('symbol', '2')), ('symbol', '3'))
   3
   $ try '1|2&3'
   ('or', ('symbol', '1'), ('and', ('symbol', '2'), ('symbol', '3')))
   1
   $ try '1&2&3' # associativity
   ('and', ('and', ('symbol', '1'), ('symbol', '2')), ('symbol', '3'))
   $ try '1|(2|3)'
   ('or', ('symbol', '1'), ('group', ('or', ('symbol', '2'), ('symbol', '3'))))
   1
   2
   3
   $ log '1.0' # tag
   6
   $ log 'a' # branch
   0
   $ log '2785f51ee'
   0
   $ log 'date(2005)'
   4
   $ log 'date(this is a test)'
   hg: parse error at 10: unexpected token: symbol
   [255]
   $ log 'date()'
   hg: parse error: date wants a string
   [255]
   $ log 'date'
   hg: parse error: can't use date here
   [255]
   $ log 'date('
   hg: parse error at 5: not a prefix: end
   [255]
   $ log 'date(tip)'
   abort: invalid date: 'tip'
   [255]
   $ log '"date"'
   abort: unknown revision 'date'!
   [255]
   $ log 'date(2005) and 1::'
   4
 
   $ log 'ancestor(1)'
   hg: parse error: ancestor wants two arguments
   [255]
   $ log 'ancestor(4,5)'
   1
   $ log 'ancestor(4,5) and 4'
   $ log 'ancestors(5)'
   0
   1
   3
   5
   $ log 'author(bob)'
   2
   $ log 'branch(é)'
   8
   9
   $ log 'children(ancestor(4,5))'
   2
   3
   $ log 'closed()'
   $ log 'contains(a)'
   0
   1
   3
   5
   $ log 'descendants(2 or 3)'
   2
   3
   4
   5
   6
   7
   8
   9
   $ log 'file(b)'
   1
   4
   $ log 'follow()'
   0
   1
   2
   4
   8
   9
   $ log 'grep("issue\d+")'
   6
+  $ try 'grep("(")' # invalid regular expression
+  ('func', ('symbol', 'grep'), ('string', '('))
+  hg: parse error: invalid match pattern: unbalanced parenthesis
+  [255]
   $ log 'head()'
   0
   1
   2
   3
   4
   5
   6
   7
   9
   $ log 'heads(6::)'
   7
   $ log 'keyword(issue)'
   6
   $ log 'limit(head(), 1)'
   0
   $ log 'max(contains(a))'
   5
   $ log 'min(contains(a))'
   0
   $ log 'merge()'
   6
   $ log 'modifies(b)'
   4
   $ log 'outgoing()'
   8
   9
   $ log 'outgoing("../remote1")'
   8
   9
   $ log 'outgoing("../remote2")'
   3
   5
   6
   7
   9
   $ log 'p1(merge())'
   5
   $ log 'p2(merge())'
   4
   $ log 'parents(merge())'
   4
   5
   $ log 'removes(a)'
   2
   6
   $ log 'roots(all())'
   0
   $ log 'reverse(2 or 3 or 4 or 5)'
   5
   4
   3
   2
   $ log 'sort(limit(reverse(all()), 3))'
   7
   8
   9
   $ log 'sort(2 or 3 or 4 or 5, date)'
   2
   3
   5
   4
   $ log 'tagged()'
   6
   $ log 'user(bob)'
   2
 
   $ log '4::8'
   4
   8
   $ log '4:8'
   4
   5
   6
   7
   8
 
   $ log 'sort(!merge() & (modifies(b) | user(bob) | keyword(bug) | keyword(issue) & 1::9), "-date")'
   4
   2
   5
 
   $ log 'not 0 and 0:2'
   1
   2
   $ log 'not 1 and 0:2'
   0
   2
   $ log 'not 2 and 0:2'
   0
   1
   $ log '(1 and 2)::'
   $ log '(1 and 2):'
   $ log '(1 and 2):3'
   $ log 'sort(head(), -rev)'
   9
   7
   6
   5
   4
   3
   2
   1
   0