Created
September 3, 2020 15:46
-
-
Save mcsf/b244662b89365961ddfd38aecf8b7526 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Invoke with | |
# | |
# awk -f script.awk -v term=li blocktypes.tsv | |
# | |
# With blocktypes.tsv: | |
# | |
# list List ul,ol | |
# revue Revue list | |
# paragraph Paragraph text | |
# image Image image,picture | |
# gallery Gallery image,images | |
# Different AWK implementations provide different regular expressions | |
# for word boundaries ("\<"), so do this manually. | |
function open_match(str, pat) { | |
return str ~ "(^|[^A-z])"pat | |
} | |
($1 == term || $2 == term) { | |
exact_name[NR] = $1 | |
} | |
($3 ~ term) { | |
split($3, words, ",") | |
for (i in words) { | |
if (words[i] == term) { | |
exact_keyw[NR] = $1 | |
break | |
} | |
} | |
} | |
(open_match($1, term) || open_match($2, term)) { | |
partial_name[NR] = $1 | |
} | |
open_match($3, term) { | |
partial_keyw[NR] = $1 | |
} | |
END { | |
for (i in exact_name) { | |
print "(exact-name-match) ", exact_name[i] | |
} | |
for (i in exact_keyw) { | |
if (i in exact_name) { | |
continue | |
} | |
print "(exact-keyword-match) ", exact_keyw[i] | |
} | |
for (i in partial_name) { | |
if (i in exact_name || i in exact_keyw) { | |
continue | |
} | |
print "(partial-name-match) ", partial_name[i] | |
} | |
for (i in partial_keyw) { | |
if (i in exact_name || i in exact_keyw || i in partial_name) { | |
continue | |
} | |
print "(partial-keyword-match) ", partial_keyw[i] | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment