commit 09691a0fe7b3809f2cdacd7713c2b37668c6c93b Author: Matt Traudt sirmatt@ksu.edu Date: Thu Jun 14 22:23:22 2018 -0400

Replace v3bw-into-xy bash script with python script

GH: ref #182 --- CHANGELOG.md | 2 ++ scripts/tools/v3bw-into-xy.py | 53 +++++++++++++++++++++++++++++++++++++++++++ scripts/tools/v3bw-into-xy.sh | 26 --------------------- 3 files changed, 55 insertions(+), 26 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md index 3a79c02..6e40965 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -13,6 +13,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0. stored in `v3bw` directory, named `YYmmdd_HHMMSS.v3bw`, and previously generated ones are kept. A `latest.v3bw` symlink is updated. (GH#179 GHPR#190) - Code refactoring in the v3bw classes and generation area +- Replace v3bw-into-xy bash script with python script to handle a more complex + v3bw file format (GH#182)

## [0.4.1]

diff --git a/scripts/tools/v3bw-into-xy.py b/scripts/tools/v3bw-into-xy.py new file mode 100755 index 0000000..fda5d74 --- /dev/null +++ b/scripts/tools/v3bw-into-xy.py @@ -0,0 +1,53 @@ +#!/usr/bin/env python3 +import sys +import re +# File: v3bw-into-xy.py +# Author: Matt Traudt +# License: CC0 +# +# Takes one or more v3bw files as arguments. +# +# Looks for lines that contain actual data. That means most of them, since most +# of them contain "node_id=" and those are the ones that are interesting. +# +# Extract the fingerprint and bandwidth values for each of those lines and put +# them on stdout, one per line. Effectively, after ignoring other lines, this: +# node_id=$AAAA...AAAA bw=12345 +# becomes this: +# AAAA...AAAA 12345 +# +# NOTE: If you specify more than v3bw file, this will do NOTHING to tell you +# when the output from one file stops and the next begins +# +# With v1.1.0 of the v3bw file format, we no longer know if node_id or bw is +# first in the line. Hence two regular expresions and searching for the matched +# item that has 40 chars (the fingerprint) + + +def main(): + re1 = re.compile('.*node_id=$?([\w]+).* bw=([\d]+).*') # noqa + re2 = re.compile('.*bw=([\d]+).* node_id=$?([\w]+)') # noqa + for fname in sys.argv[1:]: + with open(fname, 'rt') as fd: + for line in fd: + if 'node_id' not in line: + continue + match = re1.match(line) or re2.match(line) + if not match: + continue + items = match.groups() + assert len(items) == 2 + s = '{} {}\n' + if len(items[0]) == 40: + s = s.format(*items) + else: + s = s.format(*items[::-1]) + sys.stdout.write(s) + return 0 + + +if __name__ == '__main__': + try: + exit(main()) + except (KeyboardInterrupt, BrokenPipeError): + pass diff --git a/scripts/tools/v3bw-into-xy.sh b/scripts/tools/v3bw-into-xy.sh deleted file mode 100755 index 059739d..0000000 --- a/scripts/tools/v3bw-into-xy.sh +++ /dev/null @@ -1,26 +0,0 @@ -#!/usr/bin/env bash -# File: v3bw-into-xy.sh -# Author: Matt Traudt -# License: CC0 -# -# Takes one or more v3bw files as arguments. -# -# Looks for lines that contain actual data. That means most of them, since most -# of them start with "node_id=" and those are the ones that are interesting. -# -# Extract the fingerprint and bandwidth values for each of those lines and put -# them on stdout, one per line. Effectively, after ignoring other lines, this: -# node_id=$AAAA...AAAA bw=12345 -# becomes this: -# AAAA...AAAA 12345 -# -# NOTE: If you specify more than v3bw file, this will do NOTHING to tell you -# when the output from one file stops and the next begins -set -e -while [ "$1" != "" ] -do - grep '^node_id=' "$1" | - sed -r 's|^node_id=([$A-Z0-9]+) bw=([0-9]+).*$|\1 \2|' | - sed 's|$||g' - shift -done