blob: 9a7d8869795bdfc72a0475efc4554f0aeaff5399 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
|
(ns pronouns.util
(:require [clojure.string :as s]))
(defn slurp-tabfile [path]
(let [lines (s/split (slurp path) #"\n")]
(map #(s/split % #"\t") lines)))
(defn table-lookup
[query-key table]
(let [arity (count query-key)
filtered-table (filter #(= query-key (take arity %)) table)]
(first filtered-table)))
(defn tabfile-lookup
[query-key tabfile]
(table-lookup query-key (slurp-tabfile tabfile)))
(defn disambiguate
"given a row and its lexically-closest neighbors,
determine the smallest abbreviation which is still
distinct."
[prev row next]
(loop [n 1]
(let [row-n (take n row)]
(cond
(>= n 5) row
(= row-n (take n prev)) (recur (+ n 1))
(= row-n (take n next)) (recur (+ n 1))
:else row-n))))
(defn abbreviate
"given a list of pronoun rows, return a list of
pairs, where the first item is the abbreviation
and the second is the original pronoun row."
[sorted-table]
(loop [acc nil
prev nil
row (first sorted-table)
todo (rest sorted-table)]
(let [next (first todo)
abbrev (disambiguate prev row next)
pair (list abbrev row)
acc2 (conj acc pair)]
(if (empty? todo) (reverse acc2)
(recur acc2 row next (rest todo))))))
(defn minimum-unambiguous-path
([pronouns-table sections] (minimum-unambiguous-path pronouns-table sections 1))
([pronouns-table sections number-of-sections]
(let [sections-subset (take number-of-sections sections)
results (filter #(= (take number-of-sections %) sections-subset) pronouns-table)]
(case (count results)
0 nil
1 (clojure.string/join "/" sections-subset)
(recur pronouns-table sections (+ number-of-sections 1))))))
|
