Created
April 21, 2013 19:35
-
-
Save luisgabriel/5430769 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
(ns tsearch.lexer | |
(:require [clojure.string :as cjstr])) | |
(def a (Character/getNumericValue \a)) | |
(def z (Character/getNumericValue \z)) | |
(def A (Character/getNumericValue \A)) | |
(def Z (Character/getNumericValue \Z)) | |
(def zero (Character/getNumericValue \0)) | |
(def nine (Character/getNumericValue \9)) | |
(defn is-ascii-alpha-num [c] | |
(let [n (Character/getNumericValue c)] | |
(or (and (>= n a) (<= n z)) | |
(and (>= n A) (<= n Z)) | |
(and (>= n zero) (<= n nine))))) | |
(defn is-valid [c] | |
(or (is-ascii-alpha-num c) | |
(Character/isSpaceChar c) | |
(.equals (str \newline) (str c)))) | |
(defn lower-and-replace [c] | |
(if (.equals (str \newline) (str c)) \space (Character/toLowerCase c))) | |
(defn tokenize [content] | |
(let [filtered (filter is-valid content) | |
lowered (map lower-and-replace filtered)] | |
(cjstr/split (apply str lowered) #"\s+"))) | |
(defn process-content [content] | |
(let [words (tokenize content)] | |
(loop [ws words i 0 hmap (hash-map)] | |
(if (empty? ws) | |
hmap | |
(recur (rest ws) (+ i 1) (update-in hmap [(first ws)] #(conj % i))))))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment