From 1b62994e5d37649c88356c7d4fb21f6fb6650486 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pawe=C5=82=20Skurzy=C5=84ski?= <pawelskurzynski@192.168.1.7>
Date: Wed, 27 Mar 2024 17:42:41 +0100
Subject: [PATCH] update

---
 .DS_Store            | Bin 6148 -> 6148 bytes
 lab/LAB_01.md        |   4 ++--
 mr/.DS_Store         | Bin 6148 -> 6148 bytes
 mr/python/.DS_Store  | Bin 0 -> 6148 bytes
 mr/python/mapper.py  |  14 +++++++++-----
 mr/python/reducer.py |   2 +-
 6 files changed, 12 insertions(+), 8 deletions(-)
 create mode 100644 mr/python/.DS_Store

diff --git a/.DS_Store b/.DS_Store
index 202195e8c630b9fe1b38dc4be4c04ab069deaf8e..0d6c775d6a2b70d17615bf9d3a141bd308afb685 100644
GIT binary patch
delta 17
YcmZoMXfc=&$H+J_-ky<h<NQ={05MesRsaA1

delta 17
YcmZoMXfc=&$H*`--ky<R<NQ={05L`dQ~&?~

diff --git a/lab/LAB_01.md b/lab/LAB_01.md
index a79f2f3..0ffde06 100644
--- a/lab/LAB_01.md
+++ b/lab/LAB_01.md
@@ -2,7 +2,7 @@
 
 Do wykonania ćwiczeń należy skopiować repozytorium:
 ```shell
-git clone https://git.wmi.amu.edu.pl/bigdata/apache_hadoop
+git clone https://git.wmi.amu.edu.pl/s1201683/hadoop_zaliczenie
 ```
 Celem ćwiczenia jest zaprezentowanie aplikacji w oparciu o algorytm MapReduce z wykorzystaniem:
 
@@ -18,7 +18,7 @@ WordCount jest „odpowiednikiem Hello World” w świecie Big Data. Ćwiczenie
 Aby wykonać ćwiczenia, należy skopiować folder _books_ do systemu HDFS:
 ```
 hdfs dfs -mkdir tmp
-hdfs dfs -copyFromLocal ~/apache_hadoop/mr/books tmp/books
+hdfs dfs -copyFromLocal ~/hadoop_zaliczenie/mr/books tmp/books
 ```
 ## 1.WordCount – Hadoop Streaming
 Hadoop streaming umożliwia użytkownikom wykorzystanie mappera i reducera napisanego w dowolnym języku programowania. Jedynym wymaganiem jest obecność interpretera na każdym z węzłów.
diff --git a/mr/.DS_Store b/mr/.DS_Store
index 0f95520c8457be0ea69fa299c1f93c06a59a0143..5117ba30fa365d4e4e0f636e8dc6a53c5a0c7254 100644
GIT binary patch
delta 20
ccmZoMXfc?ugpqOM#xVAY2Y5EKbNuB808nuUi2wiq

delta 18
acmZoMXfc?uWMYc?#sfC&o7p-3@&f=!F9$mS

diff --git a/mr/python/.DS_Store b/mr/python/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..5008ddfcf53c02e82d7eee2e57c38e5672ef89f6
GIT binary patch
literal 6148
zcmeH~Jr2S!425mzP>H1@V-^m;4Wg<&0T*E43hX&L&p$$qDprKhvt+--jT7}7np#A3
zem<@ulZcFPQ@L2!n>{z**<q8>++&mCkOWA81W14cNZ<zv;LbK1Poaz?KmsK2CSc!(
z0ynLxE!0092;Krf2c+FF_Fe*7ECH>lEfg7;MkzE(HCqgga^y>{tEnwC%0;vJ&^%eQ
zLs35+`xjp>T0<F0fCPF1$Cyrb|F7^5{eNG?83~ZUUlGt@xh*qZDeu<Z%US-OSsOPv
j)R!Z4KLME7ReXlK;d!wEw5GODWMKRea10D2@KpjYNUI8I

literal 0
HcmV?d00001

diff --git a/mr/python/mapper.py b/mr/python/mapper.py
index 77d44f4..8668ac8 100644
--- a/mr/python/mapper.py
+++ b/mr/python/mapper.py
@@ -2,13 +2,17 @@
 import sys
 import re
 
-
+# input comes from STDIN (standard input)
 for line in sys.stdin:
-
+    # remove leading and trailing whitespace
     line = line.strip()
-    words = re.findall(r'\b\w+\b', line)
-
+    # split the line into words
+    words = re.findall(r'\b\w+\b', line)  # using regex to find words
+    # increase counters
     for word in words:
-
+        # apply regex to remove non-alphanumeric characters and convert to lowercase
         word = re.sub(r'[^a-zA-Z0-9]', '', word).lower()
+        # write the results to STDOUT (standard output);
+        # what we output here will be the input for the
+        # Reduce step, i.e. the input for reducer.py
         print('%s\t%s' % (word, 1))
diff --git a/mr/python/reducer.py b/mr/python/reducer.py
index 6bf6ae3..e1ce1be 100644
--- a/mr/python/reducer.py
+++ b/mr/python/reducer.py
@@ -1,4 +1,4 @@
-
+#!/usr/bin/env python
 from operator import itemgetter
 import sys