Data commit

This commit is contained in:
Ingy döt Net 2023-07-01 11:58:00 -04:00
parent 7387c8f97b
commit cb5bb5e222
199093 changed files with 3378972 additions and 0 deletions

View file

@ -0,0 +1,18 @@
# Given an array of [ doc, array_of_distinct_words ]
# construct a lookup table: { word: array_of_docs }
def inverted_index:
reduce .[] as $pair
({};
$pair[0] as $doc
| reduce $pair[1][] as $word
(.; .[$word] += [$doc]));
def search(words):
def overlap(that): . as $this
| reduce that[] as $item ([]; if $this|index($item) then . + [$item] else . end);
. as $dict
| if (words|length) == 0 then []
else reduce words[1:][] as $word
( $dict[words[0]]; overlap( $dict[$word] ) )
end ;

View file

@ -0,0 +1,8 @@
def prompt_search:
"Enter a string or an array of strings to search for, quoting each string, or 0 to exit:",
( (input | if type == "array" then . elif type == "string" then [.]
else empty
end) as $in
| search($in), prompt_search ) ;
$in | inverted_index | prompt_search

View file

@ -0,0 +1,10 @@
$ jq -r -c -n --argfile in <(jq -R 'split(" ") | select(length>0) | [input_filename, unique]' T?.txt) -f Inverted_index.jq
Enter a string or an array of strings to search for, quoting each string, or 0 to exit:
"is"
["T0.txt","T1.txt","T2.txt"]
Enter a string or an array of strings to search for, quoting each string, or 0 to exit:
["is", "banana"]
["T2.txt"]
Enter a string or an array of strings to search for, quoting each string, or 0 to exit:
0
$