annotate bin/wprog.sh @ 396:10813bab9072 plus tip

added test 9 for wat that pretty-prints json content
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Tue, 30 Jun 2026 16:50:56 +0100
parents 2502b81838da
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
318
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
1 #!/usr/bin/bash
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
2 # Usage wprog.sh seg start end=$(date) ty='warc'
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
3 seg="$1"
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
4 shift
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
5 start="$1"
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
6 shift
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
7 end=$(date)
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
8 ty='warc'
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
9 while [ "$1" ]
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
10 do
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
11 case "$1" in
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
12 [A-Z]*)
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
13 end="$1"
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
14 shift
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
15 ;;
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
16 warc|robotstxt|crawldiagnostics)
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
17 ty=$1
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
18 shift
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
19 ;;
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
20 *)
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
21 echo "Hunh?" "$@" 1>&2
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
22 echo "Usage: wprog.sh start end=$(date) ty='warc'" 1>&2
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
23 exit 1
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
24 ;;
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
25 esac
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
26 done
2502b81838da for tracking progress (of w2c?)
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
27 wprog.py $(fgrep -ch records x?/$seg/$ty/w* | btot -s | cut -f 2) "$start" "$end"