contrib/buildrpm

match: making visitdir() deal with non-recursive entries

Primarily as an optimization to avoid recursing into directories that will
never have a match inside, this classifies each matcher pattern's root as
recursive or non-recursive (erring on the side of keeping it recursive,
which may lead to wasteful directory or manifest walks that yield no matches).

I measured the performance of "rootfilesin" in two repos:
- The Firefox repo with tree manifests, with
  "hg files -r . -I rootfilesin:browser".
  The browser directory contains about 3K files across 249 subdirectories.
- A specific Google-internal directory which contains 75K files across 19K
  subdirectories, with "hg files -r . -I rootfilesin:REDACTED".

I tested with both cold and warm disk caches. Cold cache was produced by
running "sync; echo 3 > /proc/sys/vm/drop_caches". Warm cache was produced
by re-running the same command a few times.

These were the results:

               Cold cache           Warm cache
             Before   After      Before   After
firefox      0m5.1s   0m2.18s   0m0.22s  0m0.14s
google3 dir  2m3.9s   0m1.57s   0m8.12s  0m0.16s

Certain extensions, notably narrowhg, can depend on this for correctness
(not trying to recurse into directories for which it has no information).

#!/bin/bash -e
#
# Build a Mercurial RPM from the current repo
#
# Tested on
# - Fedora 20
# - CentOS 5
# - centOS 6

. $(dirname $0)/packagelib.sh

BUILD=1
RPMBUILDDIR="$PWD/rpmbuild"
while [ "$1" ]; do
    case "$1" in
    --prepare )
        shift
        BUILD=
        ;;
    --withpython | --with-python)
        shift
        PYTHONVER=2.7.10
        PYTHONMD5=d7547558fd673bd9d38e2108c6b42521
        ;;
    --rpmbuilddir )
        shift
        RPMBUILDDIR="$1"
        shift
        ;;
    * )
        echo "Invalid parameter $1!" 1>&2
        exit 1
        ;;
    esac
done

cd "`dirname $0`/.."

specfile=$PWD/contrib/mercurial.spec
if [ ! -f $specfile ]; then
    echo "Cannot find $specfile!" 1>&2
    exit 1
fi

if [ ! -d .hg ]; then
    echo 'You are not inside a Mercurial repository!' 1>&2
    exit 1
fi

gethgversion

# TODO: handle distance/node set, and type set

if [ -z "$type" ] ; then
   release=1
else
    release=0.9_$type
fi

if [ -n "$distance" ] ; then
    release=$release+$distance_$node
fi

if [ "$PYTHONVER" ]; then
    release=$release+$PYTHONVER
    RPMPYTHONVER=$PYTHONVER
else
    RPMPYTHONVER=%{nil}
fi

mkdir -p $RPMBUILDDIR/{SOURCES,BUILD,SRPMS,RPMS}
$HG archive -t tgz $RPMBUILDDIR/SOURCES/mercurial-$version-$release.tar.gz
if [ "$PYTHONVER" ]; then
(
    mkdir -p build
    cd build
    PYTHON_SRCFILE=Python-$PYTHONVER.tgz
    [ -f $PYTHON_SRCFILE ] || curl -Lo $PYTHON_SRCFILE http://www.python.org/ftp/python/$PYTHONVER/$PYTHON_SRCFILE
    if [ "$PYTHONMD5" ]; then
        echo "$PYTHONMD5 $PYTHON_SRCFILE" | md5sum -w -c
    fi
    ln -f $PYTHON_SRCFILE $RPMBUILDDIR/SOURCES/$PYTHON_SRCFILE

    DOCUTILSVER=`sed -ne "s/^%global docutilsname docutils-//p" $specfile`
    DOCUTILS_SRCFILE=docutils-$DOCUTILSVER.tar.gz
    [ -f $DOCUTILS_SRCFILE ] || curl -Lo $DOCUTILS_SRCFILE http://downloads.sourceforge.net/project/docutils/docutils/$DOCUTILSVER/$DOCUTILS_SRCFILE
    DOCUTILSMD5=`sed -ne "s/^%global docutilsmd5 //p" $specfile`
    if [ "$DOCUTILSMD5" ]; then
        echo "$DOCUTILSMD5 $DOCUTILS_SRCFILE" | md5sum -w -c
    fi
    ln -f $DOCUTILS_SRCFILE $RPMBUILDDIR/SOURCES/$DOCUTILS_SRCFILE
)
fi

mkdir -p $RPMBUILDDIR/SPECS
rpmspec=$RPMBUILDDIR/SPECS/mercurial.spec

sed -e "s,^Version:.*,Version: $version," \
    -e "s,^Release:.*,Release: $release," \
    $specfile > $rpmspec

echo >> $rpmspec
echo "%changelog" >> $rpmspec

if echo $version | grep '+' > /dev/null 2>&1; then
    latesttag="`echo $version | sed -e 's/+.*//'`"
    $HG log -r .:"$latesttag" -fM \
        --template '{date|hgdate}\t{author}\t{desc|firstline}\n' | python -c '
import sys, time

def datestr(date, format):
    return time.strftime(format, time.gmtime(float(date[0]) - date[1]))

changelog = []
for l in sys.stdin.readlines():
    tok = l.split("\t")
    hgdate = tuple(int(v) for v in tok[0].split())
    changelog.append((datestr(hgdate, "%F"), tok[1], hgdate, tok[2]))
prevtitle = ""
for l in sorted(changelog, reverse=True):
    title = "* %s %s" % (datestr(l[2], "%a %b %d %Y"), l[1])
    if prevtitle != title:
        prevtitle = title
        print
        print title
    print "- %s" % l[3].strip()
' >> $rpmspec

else

    $HG log \
         --template '{date|hgdate}\t{author}\t{desc|firstline}\n' \
         .hgtags | python -c '
import sys, time

def datestr(date, format):
    return time.strftime(format, time.gmtime(float(date[0]) - date[1]))

for l in sys.stdin.readlines():
    tok = l.split("\t")
    hgdate = tuple(int(v) for v in tok[0].split())
    print "* %s %s\n- %s" % (datestr(hgdate, "%a %b %d %Y"), tok[1], tok[2])
' >> $rpmspec

fi

sed -i \
    -e "s/^%define withpython.*$/%define withpython $RPMPYTHONVER/" \
    $rpmspec

if [ "$BUILD" ]; then
    rpmbuild --define "_topdir $RPMBUILDDIR" -ba $rpmspec --clean
    if [ $? = 0 ]; then
        echo
        echo "Built packages for $version-$release:"
        find $RPMBUILDDIR/*RPMS/ -type f -newer $rpmspec
    fi
else
    echo "Prepared sources for $version-$release $rpmspec are in $RPMBUILDDIR/SOURCES/ - use like:"
    echo "rpmbuild --define '_topdir $RPMBUILDDIR' -ba $rpmspec --clean"
fi