3
0
mirror of https://github.com/reality/dbot.git synced 2024-12-12 13:59:26 +01:00

underscorise spelling [#81]

This commit is contained in:
reality 2013-01-13 15:45:07 +00:00
parent 35e34874af
commit cd5649a1e8
2 changed files with 81 additions and 79 deletions

View File

@ -1,8 +1,83 @@
var _ = require('underscore')._;
var allGroupings = function(arr) {
if (arr.length == 0) {
return []; /* short-circuit the empty-array case */
}
var groupings = [];
for(var n=1;n<=arr.length;n++) {
for(var i=0;i<(arr.length-(n-1));i++) {
groupings.push(arr.slice(i, i+n));
}
}
return groupings;
}
var distance = function(s1, s2) {
// Calculate Levenshtein distance between two strings
//
// version: 1109.2015
// discuss at: http://phpjs.org/functions/levenshtein
// + original by: Carlos R. L. Rodrigues (http://www.jsfromhell.com)
// + bugfixed by: Onno Marsman
// + revised by: Andrea Giammarchi (http://webreflection.blogspot.com)
// + reimplemented by: Brett Zamir (http://brett-zamir.me)
// + reimplemented by: Alexander M Beedie
if (s1 == s2) {
return 0;
}
var s1_len = s1.length;
var s2_len = s2.length;
if (s1_len === 0) {
return s2_len; }
if (s2_len === 0) {
return s1_len;
}
// BEGIN STATIC
var split = false;
try {
split = !('0')[0];
} catch (e) {
split = true; // Earlier IE may not support access by string index
}
// END STATIC
if (split) {
s1 = s1.split(''); s2 = s2.split('');
}
var v0 = new Array(s1_len + 1);
var v1 = new Array(s1_len + 1);
var s1_idx = 0,
s2_idx = 0,
cost = 0;
for (s1_idx = 0; s1_idx < s1_len + 1; s1_idx++) { v0[s1_idx] = s1_idx;
}
var char_s1 = '',
char_s2 = '';
for (s2_idx = 1; s2_idx <= s2_len; s2_idx++) { v1[0] = s2_idx;
char_s2 = s2[s2_idx - 1];
for (s1_idx = 0; s1_idx < s1_len; s1_idx++) {
char_s1 = s1[s1_idx]; cost = (char_s1 == char_s2) ? 0 : 1;
var m_min = v0[s1_idx + 1] + 1;
var b = v1[s1_idx] + 1;
var c = v0[s1_idx] + cost;
if (b < m_min) { m_min = b;
}
if (c < m_min) {
m_min = c;
} v1[s1_idx + 1] = m_min;
}
var v_tmp = v0;
v0 = v1;
v1 = v_tmp; }
return v0[s1_len];
};
var spelling = function(dbot) { var spelling = function(dbot) {
var last = {}; var last = {};
var correct = function (event, correction, candidate, output_callback) { var correct = function (event, correction, candidate, output_callback) {
var rawCandidates = last[event.channel.name][candidate].split(' ').allGroupings(); var rawCandidates = allGroupings(last[event.channel.name][candidate].split(' '));
var candidates = []; var candidates = [];
for(var i=0;i<rawCandidates.length;i++) { for(var i=0;i<rawCandidates.length;i++) {
candidates.push(rawCandidates[i].join(' ')); candidates.push(rawCandidates[i].join(' '));
@ -11,10 +86,10 @@ var spelling = function(dbot) {
var winnerDistance = Infinity; var winnerDistance = Infinity;
for(var i=0;i<candidates.length;i++) { for(var i=0;i<candidates.length;i++) {
var distance = String.prototype.distance(correction.toLowerCase(), candidates[i].toLowerCase()); var d = distance(correction.toLowerCase(), candidates[i].toLowerCase());
if((distance < winnerDistance) && (distance > 0)) { if((d < winnerDistance) && (d > 0)) {
winner = candidates[i]; winner = candidates[i];
winnerDistance = distance; winnerDistance = d;
} }
} }
@ -51,7 +126,7 @@ var spelling = function(dbot) {
event.reply(dbot.t('spelling_other', e)); event.reply(dbot.t('spelling_other', e));
}); });
} else { } else {
if(last.hasOwnProperty(event.channel.name)) { if(_.has(last, event.channel.name)) {
last[event.channel.name][event.user] = event.message; last[event.channel.name][event.user] = event.message;
} else { } else {
last[event.channel.name] = { }; last[event.channel.name] = { };

View File

@ -35,19 +35,6 @@ Array.prototype.sum = function() {
return sum; return sum;
}; };
Array.prototype.allGroupings = function() {
if (this.length == 0) {
return []; /* short-circuit the empty-array case */
}
var groupings = [];
for(var n=1;n<=this.length;n++) {
for(var i=0;i<(this.length-(n-1));i++) {
groupings.push(this.slice(i, i+n));
}
}
return groupings;
}
Array.prototype.uniq = function() { Array.prototype.uniq = function() {
var hash = {} var hash = {}
var result = []; var result = [];
@ -79,66 +66,6 @@ String.prototype.startsWith = function(needle) {
return needle === this.slice(0, needle.length); return needle === this.slice(0, needle.length);
}; };
String.prototype.distance = function(s1, s2) {
// Calculate Levenshtein distance between two strings
//
// version: 1109.2015
// discuss at: http://phpjs.org/functions/levenshtein // + original by: Carlos R. L. Rodrigues (http://www.jsfromhell.com)
// + bugfixed by: Onno Marsman
// + revised by: Andrea Giammarchi (http://webreflection.blogspot.com)
// + reimplemented by: Brett Zamir (http://brett-zamir.me)
// + reimplemented by: Alexander M Beedie // * example 1: levenshtein('Kevin van Zonneveld', 'Kevin van Sommeveld');
// * returns 1: 3
if (s1 == s2) {
return 0;
}
var s1_len = s1.length;
var s2_len = s2.length;
if (s1_len === 0) {
return s2_len; }
if (s2_len === 0) {
return s1_len;
}
// BEGIN STATIC
var split = false;
try {
split = !('0')[0];
} catch (e) { split = true; // Earlier IE may not support access by string index
}
// END STATIC
if (split) {
s1 = s1.split(''); s2 = s2.split('');
}
var v0 = new Array(s1_len + 1);
var v1 = new Array(s1_len + 1);
var s1_idx = 0,
s2_idx = 0,
cost = 0;
for (s1_idx = 0; s1_idx < s1_len + 1; s1_idx++) { v0[s1_idx] = s1_idx;
}
var char_s1 = '',
char_s2 = '';
for (s2_idx = 1; s2_idx <= s2_len; s2_idx++) { v1[0] = s2_idx;
char_s2 = s2[s2_idx - 1];
for (s1_idx = 0; s1_idx < s1_len; s1_idx++) {
char_s1 = s1[s1_idx]; cost = (char_s1 == char_s2) ? 0 : 1;
var m_min = v0[s1_idx + 1] + 1;
var b = v1[s1_idx] + 1;
var c = v0[s1_idx] + cost;
if (b < m_min) { m_min = b;
}
if (c < m_min) {
m_min = c;
} v1[s1_idx + 1] = m_min;
}
var v_tmp = v0;
v0 = v1;
v1 = v_tmp; }
return v0[s1_len];
}
String.prototype.format = function() { // format takes either multiple indexed arguments, or a single object, whose keys/values will be used String.prototype.format = function() { // format takes either multiple indexed arguments, or a single object, whose keys/values will be used
var targetStr = this; var targetStr = this;
var replacements = [].splice.call(arguments, 0); var replacements = [].splice.call(arguments, 0);