comparison mercurial/commands.py @ 30452:932b18c95e11

commands: print chunk type in debugrevlog

Each data entry ("chunk") in a revlog has a type based on the first
byte of the data. This type indicates how to interpret the data.

This seems like a useful thing to be able to query through a debug
command. So let's add that to `hg debugrevlog`.

This does make `hg debugrevlog` slightly slower, as it has to read
more than just the index. However, even on the mozilla-unified
manifest (which is ~200MB spread over ~350K revisions), this takes
<400ms.

30451:94ca0e13d1fc

import os
import random
import re
import shlex
import socket
import sys
import tempfile
import time

from .i18n import _

    chainlengths = []

    datasize = [None, 0, 0]
    fullsize = [None, 0, 0]
    deltasize = [None, 0, 0]

    def addsize(size, l):
        if l[0] is None or size < l[0]:
            l[0] = size
        if size > l[1]:

            elif delta == p2:
                nump2 += 1
            elif delta != nullrev:
                numother += 1

    # Adjust size min value for empty cases
    for size in (datasize, fullsize, deltasize):
        if size[0] is None:
            size[0] = 0

    ui.write(('    full      : ') + fmt % pcfmt(numfull, numrevs))
    ui.write(('    deltas    : ') + fmt % pcfmt(numdeltas, numrevs))
    ui.write(('revision size : ') + fmt2 % totalsize)
    ui.write(('    full      : ') + fmt % pcfmt(fulltotal, totalsize))
    ui.write(('    deltas    : ') + fmt % pcfmt(deltatotal, totalsize))

    ui.write('\n')
    fmt = dfmtstr(max(avgchainlen, compratio))
    ui.write(('avg chain length  : ') + fmt % avgchainlen)
    ui.write(('max chain length  : ') + fmt % maxchainlen)

30452:932b18c95e11

import os
import random
import re
import shlex
import socket
import string
import sys
import tempfile
import time

from .i18n import _

    chainlengths = []

    datasize = [None, 0, 0]
    fullsize = [None, 0, 0]
    deltasize = [None, 0, 0]
    chunktypecounts = {}
    chunktypesizes = {}

    def addsize(size, l):
        if l[0] is None or size < l[0]:
            l[0] = size
        if size > l[1]:

            elif delta == p2:
                nump2 += 1
            elif delta != nullrev:
                numother += 1

        # Obtain data on the raw chunks in the revlog.
        chunk = r._chunkraw(rev, rev)[1]
        if chunk:
            chunktype = chunk[0]
        else:
            chunktype = 'empty'

        if chunktype not in chunktypecounts:
            chunktypecounts[chunktype] = 0
            chunktypesizes[chunktype] = 0

        chunktypecounts[chunktype] += 1
        chunktypesizes[chunktype] += size

    # Adjust size min value for empty cases
    for size in (datasize, fullsize, deltasize):
        if size[0] is None:
            size[0] = 0

    ui.write(('    full      : ') + fmt % pcfmt(numfull, numrevs))
    ui.write(('    deltas    : ') + fmt % pcfmt(numdeltas, numrevs))
    ui.write(('revision size : ') + fmt2 % totalsize)
    ui.write(('    full      : ') + fmt % pcfmt(fulltotal, totalsize))
    ui.write(('    deltas    : ') + fmt % pcfmt(deltatotal, totalsize))

    def fmtchunktype(chunktype):
        if chunktype == 'empty':
            return '    %s     : ' % chunktype
        elif chunktype in string.ascii_letters:
            return '    0x%s (%s)  : ' % (hex(chunktype), chunktype)
        else:
            return '    0x%s      : ' % hex(chunktype)

    ui.write('\n')
    ui.write(('chunks        : ') + fmt2 % numrevs)
    for chunktype in sorted(chunktypecounts):
        ui.write(fmtchunktype(chunktype))
        ui.write(fmt % pcfmt(chunktypecounts[chunktype], numrevs))
    ui.write(('chunks size   : ') + fmt2 % totalsize)
    for chunktype in sorted(chunktypecounts):
        ui.write(fmtchunktype(chunktype))
        ui.write(fmt % pcfmt(chunktypesizes[chunktype], totalsize))

    ui.write('\n')
    fmt = dfmtstr(max(avgchainlen, compratio))
    ui.write(('avg chain length  : ') + fmt % avgchainlen)
    ui.write(('max chain length  : ') + fmt % maxchainlen)