AoC 2020 Day 4. Solve by generating a huge regex

aoc-2020-day-4.clj

;; AoC 2020 Day 4. Solve by generating a huge regex.

(require '[clojure.string :as s])


(def sample-passports
"ecl:gry pid:860033327 eyr:2020 hcl:#fffffd
byr:1937 iyr:2017 cid:147 hgt:183cm

iyr:2013 ecl:amb cid:350 eyr:2023 pid:028048884
hcl:#cfa07d byr:1929

hcl:#ae17e1 iyr:2013
eyr:2024
ecl:brn pid:760753108 byr:1931
hgt:179cm

hcl:#cfa07d eyr:2025 pid:166559648
iyr:2011 ecl:brn hgt:59in")


(def mandatory-fields
  {"byr" "19[2-9]\\d|200[0-2]"
   "iyr" "20(?:1\\d|20)"
   "eyr" "20(?:2\\d|30)"
   "hgt" "(?:59|6\\d|7[0-6])in|(?:1(?:[5-8]\\d|9[0-3]))cm"
   "hcl" "#[\\da-f]{6}"
   "ecl" "amb|blu|brn|gry|grn|hzl|oth"
   "pid" "\\d{9}"})


(def re-valid-passport
  (letfn [(make-inner [xs start-idx]
            (s/join
             ["(?:" "\\b(?:"
              ;; trick: to make sure we don't catch the same key twice, add an
              ;; empty capturing group after each field, then re-match on them all.
              ;; if we didn't match on all the fields, we'd be lacking groups to
              ;; match on, and fail.
              ;; note that we may have previous fields, so we need an index to start with
              (s/join "()|" xs)
              "()):\\S+(?:\\s+|$)"   ;; assume field values are of length ≥ 1
              "){" (count xs) "}"
              (s/join
               (map (partial str "\\")
                    (range start-idx (+ start-idx (count xs)))))]))]
    (re-pattern
     (str (make-inner (keys mandatory-fields) 1)
          "|"
          (make-inner (conj (keys mandatory-fields) "cid") (inc (count mandatory-fields)))
          "(?:\\v|$)"))))
;; => #"(?:\b(?:byr()|iyr()|eyr()|hgt()|hcl()|ecl()|pid()):\S+(?:\s+|$)){7}\1\2\3\4\5\6\7|(?:\b(?:cid()|byr()|iyr()|eyr()|hgt()|hcl()|ecl()|pid()):\S+(?:\s+|$)){8}\8\9\10\11\12\13\14\15(?:\v|$)"

(defn count-passports [re passports]
  (count (re-seq re passports)))


(assert (= 2 (count-passports re-valid-fields sample-passports)))


(def re-valid-passport-with-vals
  (letfn [(make-inner [xs start-idx]
            (s/join
             ["(?:" "\\b(?:"
              (s/join
               "()|"
               (map (partial apply (partial format "%s:(?:%s)")) xs))
              "())(?:\\s+|$)"   ;; assume field values are of length ≥ 1
              "){" (count xs) "}"
              (s/join
               (map (partial str "\\")
                    (range start-idx (+ start-idx (count xs)))))]))]
        (re-pattern
         (str (make-inner mandatory-fields 1)
          "|"
          (make-inner (conj mandatory-fields ["cid" ".+"]) (inc (count mandatory-fields)))
          "(?:\\v|$)"))))
;; => #"(?:\b(?:byr:(?:19[2-9]\d|200[0-2])()|iyr:(?:20(?:1\d|20))()|eyr:(?:20(?:2\d|30))()|hgt:(?:(?:59|6\d|7[0-6])in|(?:1(?:[5-8]\d|9[0-3]))cm)()|hcl:(?:#[\da-f]{6})()|ecl:(?:amb|blu|brn|gry|grn|hzl|oth)()|pid:(?:\d{9})())(?:\s+|$)){7}\1\2\3\4\5\6\7|(?:\b(?:byr:(?:19[2-9]\d|200[0-2])()|iyr:(?:20(?:1\d|20))()|eyr:(?:20(?:2\d|30))()|hgt:(?:(?:59|6\d|7[0-6])in|(?:1(?:[5-8]\d|9[0-3]))cm)()|hcl:(?:#[\da-f]{6})()|ecl:(?:amb|blu|brn|gry|grn|hzl|oth)()|pid:(?:\d{9})()|cid:(?:.+)())(?:\s+|$)){8}\8\9\10\11\12\13\14\15(?:\v|$)"


(def sample-invalid-passports
"eyr:1972 cid:100
hcl:#18171d ecl:amb hgt:170 pid:186cm iyr:2018 byr:1926

iyr:2019
hcl:#602927 eyr:1967 hgt:170cm
ecl:grn pid:012533040 byr:1946

hcl:dab227 iyr:2012
ecl:brn hgt:182cm pid:021572410 eyr:2020 byr:1992 cid:277

hgt:59cm ecl:zzz
eyr:2038 hcl:74454a iyr:2023
pid:3556412378 byr:2007")


(assert (= 0 (count-passports re-valid-passport-with-vals sample-invalid-passports)))


(def sample-valid-passports
"pid:087499704 hgt:74in ecl:grn iyr:2012 eyr:2030 byr:1980
hcl:#623a2f

eyr:2029 ecl:blu cid:129 byr:1989
iyr:2014 pid:896056539 hcl:#a97842 hgt:165cm

hcl:#888785
hgt:164cm byr:2001 iyr:2015 cid:88
pid:545766238 ecl:hzl
eyr:2022

iyr:2010 hgt:158cm hcl:#b6652a ecl:blu byr:1944 eyr:2021 pid:093154719")


(assert (= 4 (count-passports re-valid-passport-with-vals sample-valid-passports)))