comparison mercurial/manifest.py @ 42380:12bd4e2d4d06

merge with stable

42379:e2e507573c7c

)

parsers = policy.importmod(r'parsers')
propertycache = util.propertycache

def _parse(data):
    # This method does a little bit of excessive-looking
    # precondition checking. This is so that the behavior of this
    # class exactly matches its C counterpart to try and help
    # prevent surprise breakage for anyone that develops against

def _cmp(a, b):
    return (a > b) - (a < b)

class _lazymanifest(object):
    def __init__(self, data, positions=None, extrainfo=None, extradata=None):
        if positions is None:
            self.positions = self.findlines(data)
            self.extrainfo = [0] * len(self.positions)
            self.data = data
            self.extradata = []
        else:
            self.positions = positions[:]
            self.extrainfo = extrainfo[:]
            self.extradata = extradata[:]
            self.data = data

    def findlines(self, data):
        if not data:
            return []
        pos = data.find("\n")

            raise KeyError
        cur = self.positions[needle]
        self.positions = self.positions[:needle] + self.positions[needle + 1:]
        self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1:]
        if cur >= 0:
            self.data = self.data[:cur] + '\x00' + self.data[cur + 1:]

    def __setitem__(self, key, value):
        if not isinstance(key, bytes):
            raise TypeError("setitem: manifest keys must be a byte string.")
        if not isinstance(value, tuple) or len(value) != 2:

                              self.extrainfo[needle:])

    def copy(self):
        # XXX call _compact like in C?
        return _lazymanifest(self.data, self.positions, self.extrainfo,
            self.extradata)

    def _compact(self):
        # hopefully not called TOO often
        if len(self.extradata) == 0:
            return
        l = []
        i = 0
        offset = 0
        self.extrainfo = [0] * len(self.positions)
        while i < len(self.positions):
            if self.positions[i] >= 0:
                cur = self.positions[i]
                last_cut = cur
                while True:
                    self.positions[i] = offset
                    i += 1
                    if i == len(self.positions) or self.positions[i] < 0:
                        break
                    offset += self.positions[i] - cur
                    cur = self.positions[i]
                end_cut = self.data.find('\n', cur)
                if end_cut != -1:
                    end_cut += 1

                    if len(t[1]) > 20:
                        self.extrainfo[i] = ord(t[1][21])
                    offset += len(l[-1])
                    i += 1
        self.data = ''.join(l)
        self.extradata = []

    def _pack(self, d):
        return d[0] + '\x00' + hex(d[1][:20]) + d[2] + '\n'

        start = 0
        # zero copy representation of base as a buffer
        addbuf = util.buffer(base)

        changes = list(changes)
        if len(changes) < 1000:
            # start with a readonly loop that finds the offset of
            # each line and creates the deltas
            for f, todelete in changes:
                # bs will either be the index of the item or the insert point
                start, end = _msearch(addbuf, f, start)

42380:12bd4e2d4d06

)

parsers = policy.importmod(r'parsers')
propertycache = util.propertycache

# Allow tests to more easily test the alternate path in manifestdict.fastdelta()
FASTDELTA_TEXTDIFF_THRESHOLD = 1000

def _parse(data):
    # This method does a little bit of excessive-looking
    # precondition checking. This is so that the behavior of this
    # class exactly matches its C counterpart to try and help
    # prevent surprise breakage for anyone that develops against

def _cmp(a, b):
    return (a > b) - (a < b)

class _lazymanifest(object):
    """A pure python manifest backed by a byte string.  It is supplimented with
    internal lists as it is modified, until it is compacted back to a pure byte
    string.

    ``data`` is the initial manifest data.

    ``positions`` is a list of offsets, one per manifest entry.  Positive
    values are offsets into ``data``, negative values are offsets into the
    ``extradata`` list.  When an entry is removed, its entry is dropped from
    ``positions``.  The values are encoded such that when walking the list and
    indexing into ``data`` or ``extradata`` as appropriate, the entries are
    sorted by filename.

    ``extradata`` is a list of (key, hash, flags) for entries that were added or
    modified since the manifest was created or compacted.
    """
    def __init__(self, data, positions=None, extrainfo=None, extradata=None,
                 hasremovals=False):
        if positions is None:
            self.positions = self.findlines(data)
            self.extrainfo = [0] * len(self.positions)
            self.data = data
            self.extradata = []
            self.hasremovals = False
        else:
            self.positions = positions[:]
            self.extrainfo = extrainfo[:]
            self.extradata = extradata[:]
            self.data = data
            self.hasremovals = hasremovals

    def findlines(self, data):
        if not data:
            return []
        pos = data.find("\n")

            raise KeyError
        cur = self.positions[needle]
        self.positions = self.positions[:needle] + self.positions[needle + 1:]
        self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1:]
        if cur >= 0:
            # This does NOT unsort the list as far as the search functions are
            # concerned, as they only examine lines mapped by self.positions.
            self.data = self.data[:cur] + '\x00' + self.data[cur + 1:]
            self.hasremovals = True

    def __setitem__(self, key, value):
        if not isinstance(key, bytes):
            raise TypeError("setitem: manifest keys must be a byte string.")
        if not isinstance(value, tuple) or len(value) != 2:

                              self.extrainfo[needle:])

    def copy(self):
        # XXX call _compact like in C?
        return _lazymanifest(self.data, self.positions, self.extrainfo,
            self.extradata, self.hasremovals)

    def _compact(self):
        # hopefully not called TOO often
        if len(self.extradata) == 0 and not self.hasremovals:
            return
        l = []
        i = 0
        offset = 0
        self.extrainfo = [0] * len(self.positions)
        while i < len(self.positions):
            if self.positions[i] >= 0:
                cur = self.positions[i]
                last_cut = cur

                # Collect all contiguous entries in the buffer at the current
                # offset, breaking out only for added/modified items held in
                # extradata, or a deleted line prior to the next position.
                while True:
                    self.positions[i] = offset
                    i += 1
                    if i == len(self.positions) or self.positions[i] < 0:
                        break

                    # A removed file has no positions[] entry, but does have an
                    # overwritten first byte.  Break out and find the end of the
                    # current good entry/entries if there is a removed file
                    # before the next position.
                    if (self.hasremovals
                        and self.data.find('\n\x00', cur,
                                           self.positions[i]) != -1):
                        break

                    offset += self.positions[i] - cur
                    cur = self.positions[i]
                end_cut = self.data.find('\n', cur)
                if end_cut != -1:
                    end_cut += 1

                    if len(t[1]) > 20:
                        self.extrainfo[i] = ord(t[1][21])
                    offset += len(l[-1])
                    i += 1
        self.data = ''.join(l)
        self.hasremovals = False
        self.extradata = []

    def _pack(self, d):
        return d[0] + '\x00' + hex(d[1][:20]) + d[2] + '\n'

        start = 0
        # zero copy representation of base as a buffer
        addbuf = util.buffer(base)

        changes = list(changes)
        if len(changes) < FASTDELTA_TEXTDIFF_THRESHOLD:
            # start with a readonly loop that finds the offset of
            # each line and creates the deltas
            for f, todelete in changes:
                # bs will either be the index of the item or the insert point
                start, end = _msearch(addbuf, f, start)