ansible/roles/web-data-analysis/files/countme-update.sh

102 lines
3 KiB
Bash
Raw Normal View History

add 'countme' stuff to web-data-analysis role This should automate running the "countme" scripts every day to parse new log data and publish updated totals. Here's what I've added to the ansible role: * install package deps for `mirrors-countme` * make "countme" user with home /srv/countme * clone 'prod' branch of https://pagure.io/mirrors-countme to /srv/countme * if changed: pip install /srv/countme/mirrors-countme * make web subdir /var/www/html/csv-reports/countme * make local data dir /var/lib/countme * install `countme-update.sh` to /usr/local/bin * install `countme-update.cron` to /etc/cron.d * runs /usr/local/bin/countme-update.sh daily, as user `countme` That should make sure `countme-update.sh` runs every day. That script works like this: 1. Run `countme-update-rawdb.sh` * parse new mirrors.fp.o logs in /var/log/hosts/proxy* * write data to /var/lib/countme/raw.db 2. Run `countme-update-totals.sh` * parse raw data from /var/lib/countme/raw.db * write updated totals to /var/lib/countme/totals.{db,csv} 3. Track changes in updated totals * set up /var/lib/countme as git repo (if needed) * commit new `totals.csv` (if changed) 4. Make updated totals public * Copy totals.{db,csv} to /var/www/html/csv-reports/countme For safety's sake, I've tried to set up everything so it runs as the `countme` user rather than running everything as `root`. This might be an unnecessary complication but it seemed like the right thing to do. Similarly, keeping totals.csv in a git repo isn't _required_, but it seemed like a good idea to keep historical records in case we want/need to change the counting algorithm or something. I checked the YAML with ansible-lint and tested that all the scripts work as expected when run as `wwoods`, so unless I've missed something this should do the trick.
2020-08-10 17:53:26 -04:00
#!/bin/bash
# Where do we keep our local/internal data?
LOCAL_DATA_DIR=/var/lib/countme
RAW_DB=$LOCAL_DATA_DIR/raw.db
TOTALS_DB=$LOCAL_DATA_DIR/totals.db
TOTALS_CSV=$LOCAL_DATA_DIR/totals.csv
# Where do we put the public-facing data?
PUBLIC_DATA_DIR=/var/www/html/csv-reports/countme
PUBLIC_TOTALS_DB=$PUBLIC_DATA_DIR/totals.db
PUBLIC_TOTALS_CSV=$PUBLIC_DATA_DIR/totals.csv
# Names of the update commands (if not in $PATH..)
UPDATE_RAWDB=countme-update-rawdb.sh
UPDATE_TOTALS=countme-update-totals.sh
# Copy with atomic overwrite
atomic_copy() {
local src="$1" dst="$2"
cp -f ${src} ${dst}.part
mv -f ${dst}.part ${dst}
}
# die [MESSAGE]: prints "$PROG: error: $MESSAGE" on stderr and exits
die() { echo "${0##*/}: error: $*" >&2; exit 2; }
# _run [COMMAND...]: Run a command, honoring $VERBOSE and $DRYRUN
_run() {
if [ "$VERBOSE" -o "$DRYRUN" ]; then echo "$@"; fi
if [ "$DRYRUN" ]; then return 0; else "$@"; fi
}
# CLI help text
HELP_USAGE="usage: countme-updates.sh [OPTION]..."
HELP_OPTIONS="
Options:
-h, --help Show this message and exit
-v, --verbose Show more info about what's happening
-n, --dryrun Don't run anything, just show commands
-p, --progress Show progress meters while running
"
# Turn on progress by default if stderr is a tty
if [ -z "$PROGRESS" -a -t 2 ]; then PROGRESS=1; fi
# Parse CLI options with getopt(1)
_GETOPT_TMP=$(getopt \
--name countme-update \
--options hvnp \
--longoptions help,verbose,dryrun,progress,checkoutdir: \
-- "$@")
eval set -- "$_GETOPT_TMP"
unset _GETOPT_TMP
while [ $# -gt 0 ]; do
arg=$1; shift
case $arg in
'-h'|'--help') echo "$HELP_USAGE"; echo "$HELP_OPTIONS"; exit 0 ;;
'-v'|'--verbose') VERBOSE=1 ;;
'-n'|'--dryrun') DRYRUN=1 ;;
'-p'|'--progress') PROGRESS=1 ;;
# Hidden option for testing / manual use
'--checkoutdir') COUNTME_CHECKOUT=$1; shift ;;
'--') break ;;
esac
done
# Tweak path if needed
if [ -d "$COUNTME_CHECKOUT" ]; then
cd $COUNTME_CHECKOUT
PATH="$COUNTME_CHECKOUT:$COUNTME_CHECKOUT/scripts:$PATH"
fi
# Check for required commands
command -v $UPDATE_RAWDB >/dev/null || die "can't find '$UPDATE_RAWDB'"
command -v $UPDATE_TOTALS >/dev/null || die "can't find '$UPDATE_TOTALS'"
command -v git >/dev/null || die "can't find 'git'"
# Apply other CLI options
if [ "$PROGRESS" ]; then
UPDATE_RAWDB="$UPDATE_RAWDB --progress"
UPDATE_TOTALS="$UPDATE_TOTALS --progress"
fi
# Exit immediately on errors
set -e
# Run the updates
_run $UPDATE_RAWDB --rawdb $RAW_DB
_run $UPDATE_TOTALS --rawdb $RAW_DB --totals-db $TOTALS_DB --totals-csv $TOTALS_CSV
# Update local git repo
if [ ! -d $LOCAL_DATA_DIR/.git ]; then
_run git init $LOCAL_DATA_DIR
_run git -C $LOCAL_DATA_DIR add -N $(realpath $TOTALS_CSV --relative-to $LOCAL_DATA_DIR)
fi
_run git -C $LOCAL_DATA_DIR commit -a -m "$(date -u +%F) update"
# Copy new data into place
_run atomic_copy $TOTALS_DB $PUBLIC_TOTALS_DB
_run atomic_copy $TOTALS_CSV $PUBLIC_TOTALS_CSV