amake

/**************************************************************************
 Public Domain
 To the extent possible under law, Aaron Madlon-Kay has waived all
 copyright and related or neighboring rights to this work.
 This work is published from: Japan
 **************************************************************************/

package org.amk;

import java.util.ArrayList;

amake

'''
A simple phrase extractor

Usage: cat file.txt | python phraseextractor.py [max_ngram] [min_count]

Options:
  max_ngram: Maximum phrase length in words (default: 5)
  min_count: Minimum number of phrase occurrences (default: 3)
'''

amake

# -*- coding: utf-8 -*-

'''Like Miyagawa's cute "生 & 死 = 愛" trick?
https://gist.github.com/miyagawa/2212589

This script generates every (jōyō) kanji & kanji = ? combination (no
args) or the result for supplied strings.

Note: A "wide" build of Python is required to handle surrogate chars
correctly.

amake

#!/usr/bin/env python

# Convert the parallel corpora available at
# http://www2.nict.go.jp/univ-com/multi_trans/member/mutiyama/manual/index.html
# to TMX format

import os
import re
import tarfile
import urllib

amake

# -*- coding: utf-8 -*-

'''
Generate randomize rings of kanji with a shared component a la the classic
吾、唯、足るを知る:

　五
矢口隹
　止

amake

//
//  main.swift
//  doservice
//
//  Created by Aaron Madlon-Kay on 6/2/16.
//  Copyright © 2016 Aaron Madlon-Kay. All rights reserved.
//

import Foundation
import AppKit

amake

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple Computer//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
  <dict>
    <key>Label</key>
    <string>io.jenkins.slave</string>
    <key>ProgramArguments</key>
    <array>
        <!-- If authentication is not required, you can launch via Java Web Start directly in the plist.
             Otherwise you need a script like below.

amake

import urllib2
import re

dict_url = 'http://openlab.jp/skk/skk/dic/SKK-JISYO.L'

data = urllib2.urlopen(dict_url).read().decode('euc-jp')

words = set([l.split('/')[1].split(';')[0]
             for l in data.split('\n')
             if '/' in l and not l.startswith(';;')])

amake

// Making strings of "normal" Unicode is pretty easy:

// Unicode Scalar literal
"\u{2603}" // "☃"

// From int
String(UnicodeScalar(0x2603)) // "☃"

// Maybe you want to test how your app handles weird Unicode input, like naked surrogates.
// But Swift makes it pretty hard to create such strings.

amake

import urllib2

# Data from Quandl: https://www.quandl.com/resources/useful-lists
data = ['https://s3.amazonaws.com/quandl-static-content/Ticker+CSV%27s/Indicies/SP500.csv',
        'https://s3.amazonaws.com/quandl-static-content/Ticker+CSV%27s/Indicies/dowjonesIA.csv',
        'https://s3.amazonaws.com/quandl-static-content/Ticker+CSV%27s/Indicies/NASDAQComposite.csv',
        'https://s3.amazonaws.com/quandl-static-content/Ticker+CSV%27s/Indicies/nasdaq100.csv',
        'https://s3.amazonaws.com/quandl-static-content/Ticker+CSV%27s/Indicies/NYSEComposite.csv',
        'https://s3.amazonaws.com/quandl-static-content/Ticker+CSV%27s/Indicies/nyse100.csv',
        'https://s3.amazonaws.com/quandl-static-content/Ticker+CSV%27s/Indicies/FTSE100.csv']