#!/usr/bin/env python
#  FINDING WORDS
#  How does it work?
#	\b	a word boundary (a space or beginning of a line, orpunctions)...
#	w	a w, followed by...
#	o	an o, followed by...
#	r	a r, then...
#	d	a d, and finally...
#	\b	a word boundary at the end of the word

import re

r = re.compile(r'\bword\b',re.M )
if r.search( open( 'sample.txt' ).read( ) ) : 
	print "I finally found what I'm looking for." ,
else: 
	print "\"word\"s not here, man." ,





#!/usr/bin/env python
#  FINDING MULTIPLE WORDS WITH ONE SEARCH
#  How does it work?
#  Starting outside working in, this expression searches for something 
#  that's surrounded by whitespace. For example:
#	\s	whitespace...
#	+	found one or more times...
#	(...)	followed by something...
#	\s	followed by whitespace...
#	+	that occurs one or more times.
#  The something here is another expression, (moo)|(oink).
#  This expression is as follows:
#	(	a group that contains...
#	m	an m, followed by...
#	o	an o, then..
#	o	an o...
#	)	the end of the group...
#	|	or...
#	(	a group that contains...
#	o	an o, followed by...
#	i	an i, then...
#	n	an n, followed by...
#	k	a k...
#	)	the end of a group

import re

r = re.compile(r'\s+((moo)|(oink))\s+')
if r.search( open( 'sample.txt' ).read( ) ) : 
	print "I spy a cow or pig.",
else: 
	print "Ah, there's no cow or pig here.",





#!/usr/bin/python
#  FINDING VARIATIONS ON WORDS (John, Jon, Jonathan)
#  How does it work?
#	J	followed by...
#	o	then...
#	h	that is...
#	?	optional, followed by...
#	n	followed by...
#	(...)	a goup of characters...
#	?	that may oppear once, but isn't required, followed by...
#	<space>	a space, followed by
#	D	then...
#	o	and finally...
#	e	at the end.

import re
import sys

nargs = len(sys.argv)

if nargs > 1:
	mystr = sys.argv[1]
	r = re.compile(r'Joh?n(athan)? Doe', re.M)
	if r.search(mystr):
		print 'Here\'s Johnny!',
	else: 
		print 'Who?',
else:
	print 'I came here for an argument!',





#!/usr/bin/python
#  FINDING SIMILAR WORDS (Bat, Cat, Mat)
#  How does it work?
#	\b	is a word boundary, followed by...
#	[bcm]	one of b, c, or m, followed by...
#	a	then...
#	t	and finally...
#	\b	a word boundary.

import re
import sys

nargs = len(sys.argv)

if nargs > 1:
	mystr = sys.argv[1]
	r = re.compile(r'\b[bcm]at\b', re.M)
	if r.search(mystr):
		print 'I spy a bat, a cat, or a mat',
	else: 
		print 'I don\'t spy nuttin\', honey',
else:
	print 'Come again?',





#!/usr/bin/python
#  REPLACING TAB CHARACTERS
#  How does it work?
#	\t	is a tab, replaced by...
#	|	a pipe character

import re
import sys

nargs = len(sys.argv)

if nargs > 1:
	mystr = sys.argv[1]
	r = re.compile(r'\t', re.M)
	returnstr = r.sub( ',', open( mystr ).read( ) )
	print returnstr,
else:
	print 'Come again?',





#!/usr/bin/python
#  SEARCHING FOR REPEATED WORDS ACROSS MULTIPLE LINES
#  How does it work?
#	\b	is a word boundary, followed by...
#	(...)	a group (explained next), then...
#	\s	a space
#	+	one or more times, then...
#	\1	whatever was found in the group, and lastly...
#	\b	a word boundary
#  The group is simply(\w+), which is as follows:
#	\w	is a word character...
#	+	found one or more times.

import re
import sys

nargs = len(sys.argv)

if nargs > 1:
	mystr = sys.argv[1]
	r = re.compile(r'\b(\w+)\s+\1\b', re.M )
	if r.match( open( mystr ).read( ) ) :
		print "Found double words",
	else:
		print "No match here.",
else:
	print "I came here for an argument.",





#!/usr/bin/python
#  SPLITTING LINES IN A FILE
#  How does it work?
#	,	is a comma followed by...
#	\s	a space...
#	*	none or many times.
#  The replacement expression is simply as follows:
#	,	is a comma followed by
#	\n	a newline character.

import re
import sys

nargs = len(sys.argv)

if nargs > 1:
	mystr = sys.argv[1]
	r = re.compile( r',\s*', re.M )
	newstr = r.sub( ',\n', open( mystr ).read( ) )
	print newstr,
else:
	print 'Filename?  Anyone?  Anyone?',





#!/usr/bin/python
#  JOINING LINES IN A FILE
#  How does it work?
#	\n	is a newline, replaced by...
#	,	is a comma followed by...
#	<space>	a space.

import re
import sys

nargs = len(sys.argv)

if nargs > 1:
	mystr = sys.argv[1]
	r = re.compile( r'\n', re.M )
	newstr = r.sub( ', ', open( mystr ).read( ) )
	print newstr,
else:
	print 'Filename?  Anyone?  Anyone?',





#!/usr/bin/python
#  FILTERING THE OUTPUT OF DU
#  How does it work?
#	^	the beginning of the line...
#	(?:	a noncapturing group that contains...
#	(?:	a noncapturing group that contains...
#	[2-9]	a digit two through nine...
#	[0-9]	a digit zero through nine...
#	{2}	found two times...
#	M	an M (printed by du -h for megabytes)...
#	)	the end of the inside group...
#	|	or...
#	(?:	another noncapturing group that contains...
#	[0-9.]	a character class that contains zero through nine or a literal...
#	+	found one of more times...
#	G	a G...
#	)	the end of the group...
#	)	the end of the outside group...
#	\s	whitespace...
#	+	one or more times...
#	(	a group that contains...
#	.	any character...
#	*	found zero, one, or many times...
#	$	the end of the line.

import re
from os import popen

output = popen( 'du -hs /Users/myusername/*' )
regex = re.compile( r'^(?:(?:[2-9][0-9]{2}M)|(?:[0-9.]+G))\s+(.*)$' )

lines = output.readlines()

for line in lines:
	if regex.match( line ):
		formatted = regex.sub( r'You have more than 200MB in directory: \1', line )
		print formatted,

output.close()





#!/usr/bin/python
#  CHANGING DOS TEXT TO UNIX TEXT
#  How does it work?
#	Windows text files have extra line characters at the end of the line, 
#	and this can sometimes cause problems on a Unix or Linux box. 
#	This can especially rear its ugly head when a text file is transferred 
#	as a binary over an FTP session. (ASCII mode on most FTP servers takes 
#	the extra line terminator out during transfer.) This can cause issues 
#	with shell scripts, and so on.
#	This simple recipe will remove the extra character, which is simply thid:\r.
#	It's removed here by replacing it with a zero-length string.

import re
import sys

nargs = len(sys.argv)

if nargs > 1:
	myfile = sys.argv[1]
	output = open( myfile )
	regex = re.compile( r'\r' )
	lines = output.readlines()
	for line in lines:
		formatted = regex.sub( r'', line )
		print formatted,
	output.close()
else:
	print 'I\'ve seen Tron eight times',





#!/usr/bin/python
#  SEARCHING FOR A SUBJECT IN MAIL FILES
#  How does it work?
#	^	the beginning of the line...
#	[	a character class that contains...
#	<space>	a space...
#	>	a >...
#	]	the end of the character class...
#	*	zero, one, or more times...
#	Subject:  the subject label.

import re
import sys
from os import popen

nargs = len(sys.argv)

if nargs > 1:
	myfile = sys.argv[1]
	output = open( myfile )
	regex = re.compile( r'^[ >]*Subject:' )
	lines = output.readlines()
	for line in lines:
		if regex.match( line ):
			print line,
	output.close()
else:
	print 'Please supply a parameter!',





#!/usr/bin/python
#  PARSING THE OUTPUT OF DF
#  How does it work?
#	\s	whitespace...
#	(	a group that contains...
#	(	another group with...
#	[5-9]	five through nine (in the tens place)...
#	[0-9]	zero through nine (in the ones place)...
#	)	the end of the group
#	|	or...
#	100	1, 0, and 0...
#	)	the end of the group...
#	\%	a percent sign...
#	\s	whitespace.

import re
from os import popen

output = popen( 'df' )
regex = re.compile( r'^.*\s(([5-9][0-9])|(100))%\s.*$' )

lines = output.readlines()

for line in lines:
	if regex.match( line ):
		print line,

output.close()