Skip to content

Instantly share code, notes, and snippets.

@kiyoto
kiyoto / fluent.conf
Created January 27, 2015 04:44
EFK for Apache
<source>
type tail
tag apache.access
format apache2
path /path/to/your/log
read_from_head true #過去ログ用。ファイルの先頭から読む
</source>
<match apache.access>
type elasticsearch
@kiyoto
kiyoto / failed_plugin_tests.log
Created February 1, 2015 16:50
Failed plugin test for Fluentd Windows in the test suite @v0.10.46
-------------------------------------------------------------------
test_in_exec.rb
-------------------------------------------------------------------
Run options:
# Running tests:
......
Finished tests in 8.276824s, 0.7249 tests/s, 1.8123 assertions/s.
@kiyoto
kiyoto / strata_hadoop_2015.R
Created March 10, 2015 05:31
Script for Strata Hadoop 2015 Reviews Data Collection + Analysis
library(ggplot2)
library(dplyr)
library(scrapeR)
strata_speakers <- "http://strataconf.com/big-data-conference-ca-2015/public/schedule/speakers"
speaker_page <-
scrape(url=strata_speakers,
parse=T, headers=T)
href <- xpathSApply(speaker_page[[strata_speakers]], "//a/@href")
href <- unique(href)
@kiyoto
kiyoto / strata_hadoop_2015.csv
Created March 11, 2015 16:56
Strata_hadoop_2015 CSV Data
We can make this file beautiful and searchable if this error is corrected: Unclosed quoted field in line 10.
"","avg_points","num_reviews","time","date","title","location","category"
"1",4,1,"10:40a","02/20/2015","The IoT P2P Backbone","LL21 E/F","Machine Data / IoT"
"2",4.4,10,"11:30a","02/19/2015","Unboxing Data Startups","LL20 BC","Business & Industry"
"3",3.57,7,"11:30a","02/20/2015","The Sushi Principle: Raw Data Is Better","LL21 E/F","Machine Data / IoT"
"4",4,1,"2:20p","02/20/2015","Streaming Analytics: It'™s Not The Same Game","LL21 E/F","Machine Data / IoT"
"5",3.25,16,"1:30p","02/18/2015","Building A Data Platform","210 C/G","Hadoop Platform"
"6",NA,0,"11:30a","02/20/2015","Silicon Valley Data Science: Ask Us Anything","211 B","Ask Us Anything"
"7",4,1,"10:40a","02/20/2015","Credit Suisse Puts Vendors in the Hot Seat on Data Quality and Governance","230 B","Sponsored"
"8",4.86,7,"9:00a","02/18/2015","Hardcore Data Science","LL20 BC","Hardcore Data Science"
"9",4,6,"1:30p","02/18/2015","Tensor Methods for Large-scale Unsupervised Learning: Applications to Topic and Community Modeling","LL20 BC.","Hardcore D
@kiyoto
kiyoto / php-bug-60668.diff
Created January 25, 2012 10:47
php bug 60668 fix
diff --git a/Zend/zend_ini.c b/Zend/zend_ini.c
index a7ec5d7..89b1287 100644
--- a/Zend/zend_ini.c
+++ b/Zend/zend_ini.c
@@ -83,6 +83,23 @@ static int zend_restore_ini_entry_wrapper(zend_ini_entry **ini_entry TSRMLS_DC)
}
/* }}} */
+static uint zend_trim_after_carriage_return(char *value, uint value_length) /* {{{ */
+{
@kiyoto
kiyoto / gist:1857431
Created February 18, 2012 04:36
openssl_decrypt bug patch
Index: ext/openssl/openssl.c
===================================================================
--- ext/openssl/openssl.c (revision 323312)
+++ ext/openssl/openssl.c (working copy)
@@ -4801,6 +4801,11 @@
base64_str = (char*)php_base64_decode((unsigned char*)data, data_len, &base64_str_len);
data_len = base64_str_len;
data = base64_str;
+
+ if (data == NULL) {
@kiyoto
kiyoto / github-scraper.php
Created March 28, 2012 06:17
github scraper. get user info for the users watching a particular repo
#!/usr/bin/env php
<?php
function get_watchers($login, $repo) {
$per_page = 100; // this is the max set by github http://developer.github.com/v3/#pagination
$page_number = 1;
$watchers = array();
while (1) {
$ch = curl_init(sprintf('https://api.github.com/repos/%s/%s/watchers?page=%d&per_page=%d',
@kiyoto
kiyoto / hn-stats
Created June 2, 2012 22:21
Just a random script to scrape info from HN's top page.
#!/bin/sh
HN_FILE='hn.html'
HN="http://news.ycombinator.com"
rm -f $HN_FILE
wget "$HN" -O $HN_FILE
if [ -f $HN_FILE ]
then
perl -ne 'while (m!<td class="title"><a href="(http[^"]+)">(?:.*?)</a><span class="comhead"> \(([^)]+)\) </span></td></tr><tr><td colspan=2></td>(?:<td class="subtext"><span id=score_\d+>(\d+) points</span> by <a href="user\?id=[^"]+">(?:.*?)</a> (\d+) (minute|hour|day)s? ago \| <a href="item\?id=\d+">(\d+) comments?</a>)?!g) { print "$1 $2"; if (defined $3) { print " $3 $4 $5 $6"; } print "\n"; }' < $HN_FILE
else
@kiyoto
kiyoto / random_array.php
Created June 15, 2012 00:38
creating random associative arrays
<?php
function random_array(&$current) {
foreach ($current as $k => &$v) {
if ((rand() % 10) / 10 >= 0.68) {
$v = array(0, 'aoiyu', 1337);
random_array($v);
}
}
unset($v);
@kiyoto
kiyoto / basic_information.sql
Created July 10, 2012 19:33 — forked from doryokujin/basic_information.sql
Book-Crossing Dataset
-- 1.1.1 all users v. active users --
td query -w -d book_crossing_dataset "
SELECT t1.cnt AS all_users, t2.cnt AS active_users, ROUND(t2.cnt/t1.cnt*100) AS active_rate
FROM
(
SELECT COUNT(distinct user_id) as cnt, 1 AS one
FROM users
) t1
JOIN
(