Initial data commit

This commit is contained in:
Ingy döt Net 2023-07-01 11:58:00 -04:00
parent 72d218235f
commit f23f22d71c
199087 changed files with 3378941 additions and 0 deletions

View file

@ -0,0 +1,27 @@
# Output: the input string with all its regex-special characters suitably escaped
def deregex:
reduce ("\\\\", "\\*", "\\^", "\\?", "\\+", "\\.", "\\!", "\\{", "\\}", "\\[", "\\]", "\\$", "\\|",
"\\(", "\\)" ) as $c
(.; gsub( $c; $c));
# line-break
def lb: "\n";
def split2($s):
index($s) as $ix
| if $ix then [ .[:$ix], .[$ix + ($s|length):]] else null end;
def trim: sub("^ *";"") | sub(" *$";"");
# rulesets are assumed to be separated by a blank line
# input: a string
def readRules:
trim | split("\(lb)\(lb)") | map(split(lb)) ;
# tests are assumed to be on consecutive lines via `inputs`
# Output: an array
def readTests: [inputs | trim | select(length>0) ];
def rules: $markov_rules | readRules;
def tests: readTests;

View file

@ -0,0 +1,39 @@
def parseRules($rules):
"^ *(?<period>[.]?) *(?<rule>.*)" as $pattern
| reduce $rules[] as $rule ([];
if $rule | (startswith("#") or (test(" -> ")|not)) then .
else ($rule|split2(" -> ")) as $splits
| ($splits[1] | capture($pattern)) as $re
| . + [[($splits[0]|trim|deregex), $re.period, ($re.rule | trim)]]
end );
# applyRules applies $rules to . recursively,
# where $rules is the set of applicable rules in the form of an array-of-triples.
# Input and output: a string
def applyRules($rules):
# The inner function has arity-0 for efficiency
# input and output: {stop, string}
def apply:
if .stop then .
else .string as $copy
| first( foreach $rules[] as $c (.;
.string |= sub($c[0]; $c[2])
| if $c[1] == "."
then .stop=true
elif .string != $copy
then (apply | .stop = true)
else .
end;
if .stop then . else empty end))
// .
end;
{stop: false, string: .} | apply | .string;
def proceed:
rules as $rules
| tests as $tests
| range(0; $tests|length) as $ix
| $tests[$ix]
| " \(.)\n=>\(applyRules( parseRules( $rules[$ix] ) ))\n" ;
proceed