commit db5588f63378d85fb1c96c9027b2c5d370dbf1f2 Author: moparisthebest Date: Wed Apr 20 02:08:54 2016 -0400 Initial Commit diff --git a/english.txt b/english.txt new file mode 100644 index 0000000..942040e --- /dev/null +++ b/english.txt @@ -0,0 +1,2048 @@ +abandon +ability +able +about +above +absent +absorb +abstract +absurd +abuse +access +accident +account +accuse +achieve +acid +acoustic +acquire +across +act +action +actor +actress +actual +adapt +add +addict +address +adjust +admit +adult +advance +advice +aerobic +affair +afford +afraid +again +age +agent +agree +ahead +aim +air +airport +aisle +alarm +album +alcohol +alert +alien +all +alley +allow +almost +alone +alpha +already +also +alter +always +amateur +amazing +among +amount +amused +analyst +anchor +ancient +anger +angle +angry +animal +ankle +announce +annual +another +answer +antenna +antique +anxiety +any +apart +apology +appear +apple +approve +april +arch +arctic +area +arena +argue +arm +armed +armor +army +around +arrange +arrest +arrive +arrow +art +artefact +artist +artwork +ask +aspect +assault +asset +assist +assume +asthma +athlete +atom +attack +attend +attitude +attract +auction +audit +august +aunt +author +auto +autumn +average +avocado +avoid +awake +aware +away +awesome +awful +awkward +axis +baby +bachelor +bacon +badge +bag +balance +balcony +ball +bamboo +banana +banner +bar +barely +bargain +barrel +base +basic +basket +battle +beach +bean +beauty +because +become +beef +before +begin +behave +behind +believe +below +belt +bench +benefit +best +betray +better +between +beyond +bicycle +bid +bike +bind +biology +bird +birth +bitter +black +blade +blame +blanket +blast +bleak +bless +blind +blood +blossom +blouse +blue +blur +blush +board +boat +body +boil +bomb +bone +bonus +book +boost +border +boring +borrow +boss +bottom +bounce +box +boy +bracket +brain +brand +brass +brave +bread +breeze +brick +bridge +brief +bright +bring +brisk +broccoli +broken +bronze +broom +brother +brown +brush +bubble +buddy +budget +buffalo +build +bulb +bulk +bullet +bundle +bunker +burden +burger +burst +bus +business +busy +butter +buyer +buzz +cabbage +cabin +cable +cactus +cage +cake +call +calm +camera +camp +can +canal +cancel +candy +cannon +canoe +canvas +canyon +capable +capital +captain +car +carbon +card +cargo +carpet +carry +cart +case +cash +casino +castle +casual +cat +catalog +catch +category +cattle +caught +cause +caution +cave +ceiling +celery +cement +census +century +cereal +certain +chair +chalk +champion +change +chaos +chapter +charge +chase +chat +cheap +check +cheese +chef +cherry +chest +chicken +chief +child +chimney +choice +choose +chronic +chuckle +chunk +churn +cigar +cinnamon +circle +citizen +city +civil +claim +clap +clarify +claw +clay +clean +clerk +clever +click +client +cliff +climb +clinic +clip +clock +clog +close +cloth +cloud +clown +club +clump +cluster +clutch +coach +coast +coconut +code +coffee +coil +coin +collect +color +column +combine +come +comfort +comic +common +company +concert +conduct +confirm +congress +connect +consider +control +convince +cook +cool +copper +copy +coral +core +corn +correct +cost +cotton +couch +country +couple +course +cousin +cover +coyote +crack +cradle +craft +cram +crane +crash +crater +crawl +crazy +cream +credit +creek +crew +cricket +crime +crisp +critic +crop +cross +crouch +crowd +crucial +cruel +cruise +crumble +crunch +crush +cry +crystal +cube +culture +cup +cupboard +curious +current +curtain +curve +cushion +custom +cute +cycle +dad +damage +damp +dance +danger +daring +dash +daughter +dawn +day +deal +debate +debris +decade +december +decide +decline +decorate +decrease +deer +defense +define +defy +degree +delay +deliver +demand +demise +denial +dentist +deny +depart +depend +deposit +depth +deputy +derive +describe +desert +design +desk +despair +destroy +detail +detect +develop +device +devote +diagram +dial +diamond +diary +dice +diesel +diet +differ +digital +dignity +dilemma +dinner +dinosaur +direct +dirt +disagree +discover +disease +dish +dismiss +disorder +display +distance +divert +divide +divorce +dizzy +doctor +document +dog +doll +dolphin +domain +donate +donkey +donor +door +dose +double +dove +draft +dragon +drama +drastic +draw +dream +dress +drift +drill +drink +drip +drive +drop +drum +dry +duck +dumb +dune +during +dust +dutch +duty +dwarf +dynamic +eager +eagle +early +earn +earth +easily +east +easy +echo +ecology +economy +edge +edit +educate +effort +egg +eight +either +elbow +elder +electric +elegant +element +elephant +elevator +elite +else +embark +embody +embrace +emerge +emotion +employ +empower +empty +enable +enact +end +endless +endorse +enemy +energy +enforce +engage +engine +enhance +enjoy +enlist +enough +enrich +enroll +ensure +enter +entire +entry +envelope +episode +equal +equip +era +erase +erode +erosion +error +erupt +escape +essay +essence +estate +eternal +ethics +evidence +evil +evoke +evolve +exact +example +excess +exchange +excite +exclude +excuse +execute +exercise +exhaust +exhibit +exile +exist +exit +exotic +expand +expect +expire +explain +expose +express +extend +extra +eye +eyebrow +fabric +face +faculty +fade +faint +faith +fall +false +fame +family +famous +fan +fancy +fantasy +farm +fashion +fat +fatal +father +fatigue +fault +favorite +feature +february +federal +fee +feed +feel +female +fence +festival +fetch +fever +few +fiber +fiction +field +figure +file +film +filter +final +find +fine +finger +finish +fire +firm +first +fiscal +fish +fit +fitness +fix +flag +flame +flash +flat +flavor +flee +flight +flip +float +flock +floor +flower +fluid +flush +fly +foam +focus +fog +foil +fold +follow +food +foot +force +forest +forget +fork +fortune +forum +forward +fossil +foster +found +fox +fragile +frame +frequent +fresh +friend +fringe +frog +front +frost +frown +frozen +fruit +fuel +fun +funny +furnace +fury +future +gadget +gain +galaxy +gallery +game +gap +garage +garbage +garden +garlic +garment +gas +gasp +gate +gather +gauge +gaze +general +genius +genre +gentle +genuine +gesture +ghost +giant +gift +giggle +ginger +giraffe +girl +give +glad +glance +glare +glass +glide +glimpse +globe +gloom +glory +glove +glow +glue +goat +goddess +gold +good +goose +gorilla +gospel +gossip +govern +gown +grab +grace +grain +grant +grape +grass +gravity +great +green +grid +grief +grit +grocery +group +grow +grunt +guard +guess +guide +guilt +guitar +gun +gym +habit +hair +half +hammer +hamster +hand +happy +harbor +hard +harsh +harvest +hat +have +hawk +hazard +head +health +heart +heavy +hedgehog +height +hello +helmet +help +hen +hero +hidden +high +hill +hint +hip +hire +history +hobby +hockey +hold +hole +holiday +hollow +home +honey +hood +hope +horn +horror +horse +hospital +host +hotel +hour +hover +hub +huge +human +humble +humor +hundred +hungry +hunt +hurdle +hurry +hurt +husband +hybrid +ice +icon +idea +identify +idle +ignore +ill +illegal +illness +image +imitate +immense +immune +impact +impose +improve +impulse +inch +include +income +increase +index +indicate +indoor +industry +infant +inflict +inform +inhale +inherit +initial +inject +injury +inmate +inner +innocent +input +inquiry +insane +insect +inside +inspire +install +intact +interest +into +invest +invite +involve +iron +island +isolate +issue +item +ivory +jacket +jaguar +jar +jazz +jealous +jeans +jelly +jewel +job +join +joke +journey +joy +judge +juice +jump +jungle +junior +junk +just +kangaroo +keen +keep +ketchup +key +kick +kid +kidney +kind +kingdom +kiss +kit +kitchen +kite +kitten +kiwi +knee +knife +knock +know +lab +label +labor +ladder +lady +lake +lamp +language +laptop +large +later +latin +laugh +laundry +lava +law +lawn +lawsuit +layer +lazy +leader +leaf +learn +leave +lecture +left +leg +legal +legend +leisure +lemon +lend +length +lens +leopard +lesson +letter +level +liar +liberty +library +license +life +lift +light +like +limb +limit +link +lion +liquid +list +little +live +lizard +load +loan +lobster +local +lock +logic +lonely +long +loop +lottery +loud +lounge +love +loyal +lucky +luggage +lumber +lunar +lunch +luxury +lyrics +machine +mad +magic +magnet +maid +mail +main +major +make +mammal +man +manage +mandate +mango +mansion +manual +maple +marble +march +margin +marine +market +marriage +mask +mass +master +match +material +math +matrix +matter +maximum +maze +meadow +mean +measure +meat +mechanic +medal +media +melody +melt +member +memory +mention +menu +mercy +merge +merit +merry +mesh +message +metal +method +middle +midnight +milk +million +mimic +mind +minimum +minor +minute +miracle +mirror +misery +miss +mistake +mix +mixed +mixture +mobile +model +modify +mom +moment +monitor +monkey +monster +month +moon +moral +more +morning +mosquito +mother +motion +motor +mountain +mouse +move +movie +much +muffin +mule +multiply +muscle +museum +mushroom +music +must +mutual +myself +mystery +myth +naive +name +napkin +narrow +nasty +nation +nature +near +neck +need +negative +neglect +neither +nephew +nerve +nest +net +network +neutral +never +news +next +nice +night +noble +noise +nominee +noodle +normal +north +nose +notable +note +nothing +notice +novel +now +nuclear +number +nurse +nut +oak +obey +object +oblige +obscure +observe +obtain +obvious +occur +ocean +october +odor +off +offer +office +often +oil +okay +old +olive +olympic +omit +once +one +onion +online +only +open +opera +opinion +oppose +option +orange +orbit +orchard +order +ordinary +organ +orient +original +orphan +ostrich +other +outdoor +outer +output +outside +oval +oven +over +own +owner +oxygen +oyster +ozone +pact +paddle +page +pair +palace +palm +panda +panel +panic +panther +paper +parade +parent +park +parrot +party +pass +patch +path +patient +patrol +pattern +pause +pave +payment +peace +peanut +pear +peasant +pelican +pen +penalty +pencil +people +pepper +perfect +permit +person +pet +phone +photo +phrase +physical +piano +picnic +picture +piece +pig +pigeon +pill +pilot +pink +pioneer +pipe +pistol +pitch +pizza +place +planet +plastic +plate +play +please +pledge +pluck +plug +plunge +poem +poet +point +polar +pole +police +pond +pony +pool +popular +portion +position +possible +post +potato +pottery +poverty +powder +power +practice +praise +predict +prefer +prepare +present +pretty +prevent +price +pride +primary +print +priority +prison +private +prize +problem +process +produce +profit +program +project +promote +proof +property +prosper +protect +proud +provide +public +pudding +pull +pulp +pulse +pumpkin +punch +pupil +puppy +purchase +purity +purpose +purse +push +put +puzzle +pyramid +quality +quantum +quarter +question +quick +quit +quiz +quote +rabbit +raccoon +race +rack +radar +radio +rail +rain +raise +rally +ramp +ranch +random +range +rapid +rare +rate +rather +raven +raw +razor +ready +real +reason +rebel +rebuild +recall +receive +recipe +record +recycle +reduce +reflect +reform +refuse +region +regret +regular +reject +relax +release +relief +rely +remain +remember +remind +remove +render +renew +rent +reopen +repair +repeat +replace +report +require +rescue +resemble +resist +resource +response +result +retire +retreat +return +reunion +reveal +review +reward +rhythm +rib +ribbon +rice +rich +ride +ridge +rifle +right +rigid +ring +riot +ripple +risk +ritual +rival +river +road +roast +robot +robust +rocket +romance +roof +rookie +room +rose +rotate +rough +round +route +royal +rubber +rude +rug +rule +run +runway +rural +sad +saddle +sadness +safe +sail +salad +salmon +salon +salt +salute +same +sample +sand +satisfy +satoshi +sauce +sausage +save +say +scale +scan +scare +scatter +scene +scheme +school +science +scissors +scorpion +scout +scrap +screen +script +scrub +sea +search +season +seat +second +secret +section +security +seed +seek +segment +select +sell +seminar +senior +sense +sentence +series +service +session +settle +setup +seven +shadow +shaft +shallow +share +shed +shell +sheriff +shield +shift +shine +ship +shiver +shock +shoe +shoot +shop +short +shoulder +shove +shrimp +shrug +shuffle +shy +sibling +sick +side +siege +sight +sign +silent +silk +silly +silver +similar +simple +since +sing +siren +sister +situate +six +size +skate +sketch +ski +skill +skin +skirt +skull +slab +slam +sleep +slender +slice +slide +slight +slim +slogan +slot +slow +slush +small +smart +smile +smoke +smooth +snack +snake +snap +sniff +snow +soap +soccer +social +sock +soda +soft +solar +soldier +solid +solution +solve +someone +song +soon +sorry +sort +soul +sound +soup +source +south +space +spare +spatial +spawn +speak +special +speed +spell +spend +sphere +spice +spider +spike +spin +spirit +split +spoil +sponsor +spoon +sport +spot +spray +spread +spring +spy +square +squeeze +squirrel +stable +stadium +staff +stage +stairs +stamp +stand +start +state +stay +steak +steel +stem +step +stereo +stick +still +sting +stock +stomach +stone +stool +story +stove +strategy +street +strike +strong +struggle +student +stuff +stumble +style +subject +submit +subway +success +such +sudden +suffer +sugar +suggest +suit +summer +sun +sunny +sunset +super +supply +supreme +sure +surface +surge +surprise +surround +survey +suspect +sustain +swallow +swamp +swap +swarm +swear +sweet +swift +swim +swing +switch +sword +symbol +symptom +syrup +system +table +tackle +tag +tail +talent +talk +tank +tape +target +task +taste +tattoo +taxi +teach +team +tell +ten +tenant +tennis +tent +term +test +text +thank +that +theme +then +theory +there +they +thing +this +thought +three +thrive +throw +thumb +thunder +ticket +tide +tiger +tilt +timber +time +tiny +tip +tired +tissue +title +toast +tobacco +today +toddler +toe +together +toilet +token +tomato +tomorrow +tone +tongue +tonight +tool +tooth +top +topic +topple +torch +tornado +tortoise +toss +total +tourist +toward +tower +town +toy +track +trade +traffic +tragic +train +transfer +trap +trash +travel +tray +treat +tree +trend +trial +tribe +trick +trigger +trim +trip +trophy +trouble +truck +true +truly +trumpet +trust +truth +try +tube +tuition +tumble +tuna +tunnel +turkey +turn +turtle +twelve +twenty +twice +twin +twist +two +type +typical +ugly +umbrella +unable +unaware +uncle +uncover +under +undo +unfair +unfold +unhappy +uniform +unique +unit +universe +unknown +unlock +until +unusual +unveil +update +upgrade +uphold +upon +upper +upset +urban +urge +usage +use +used +useful +useless +usual +utility +vacant +vacuum +vague +valid +valley +valve +van +vanish +vapor +various +vast +vault +vehicle +velvet +vendor +venture +venue +verb +verify +version +very +vessel +veteran +viable +vibrant +vicious +victory +video +view +village +vintage +violin +virtual +virus +visa +visit +visual +vital +vivid +vocal +voice +void +volcano +volume +vote +voyage +wage +wagon +wait +walk +wall +walnut +want +warfare +warm +warrior +wash +wasp +waste +water +wave +way +wealth +weapon +wear +weasel +weather +web +wedding +weekend +weird +welcome +west +wet +whale +what +wheat +wheel +when +where +whip +whisper +wide +width +wife +wild +will +win +window +wine +wing +wink +winner +winter +wire +wisdom +wise +wish +witness +wolf +woman +wonder +wood +wool +word +work +world +worry +worth +wrap +wreck +wrestle +wrist +write +wrong +yard +year +yellow +you +young +youth +zebra +zero +zone +zoo diff --git a/freespeech.py b/freespeech.py new file mode 100755 index 0000000..ba492da --- /dev/null +++ b/freespeech.py @@ -0,0 +1,192 @@ +#!/usr/bin/env python + +""" + +get wordlists from: + +https://github.com/bitcoin/bips/blob/master/bip-0039/bip-0039-wordlists.md +http://wordnetcode.princeton.edu/3.0/WNdb-3.0.tar.gz + +extract useable nouns from wordnetcode: +$ cut -d' ' -f 5 data.noun | grep -v _ | grep -v '/' | tr '[A-Z]' '[a-z]' | sort | uniq | wc -l +40980 + +""" + +import sys, argparse +import math +from bitstring import ReadError, BitStream, pack +from collections import deque + +class FreeSpeech: + def __init__(self, dict_filename, max_words_per_line=10, byte_buffer=65536): + self.verbose = True + (self.word_list, self.word_dict) = self.read_dict(dict_filename) + #print 'word_list:', self.word_list + #print 'word_dict:', self.word_dict + self.num_bits = self.min_even_bits(len(self.word_dict)) + #print 'num_bits:', self.num_bits + self.int_type = 'uint:' + str(self.num_bits) + #print >> sys.stderr, 'int_type:', self.int_type + self.max_words_on_line = max_words_per_line + self.byte_buffer = byte_buffer + self.bit_buffer = self.byte_buffer * 8 + self.word_count = 0 + + def max_int(self, min_bits): + return math.pow(2, min_bits) + + def min_bits(self, max_int): + return math.log(max_int) / math.log(2) + + def min_even_bits(self, max_int): + exact = self.min_bits(max_int) + #print >> sys.stderr, 'exact:', exact + floor = int(math.floor(exact)) + if self.verbose and exact != floor: + print >> sys.stderr, 'There is no exact integer for min_bits, not all words will be used!' + return floor + + def bits_to_unsigned_int(self, bits): + num = 0 + index = 0 + for bit in bits: + if bit == '1': + num += math.pow(2, index) + index += 1 + return num + + def file_to_in_stream(self, in_filename): + return sys.stdin if in_filename == '-' else open(in_filename, 'rb') + + def file_to_out_stream(self, out_filename): + return sys.stdout if out_filename == '-' else open(out_filename, 'wb') + + def decodeFiles(self, in_filename, out_filename): + with self.file_to_in_stream(in_filename) as in_stream, self.file_to_out_stream(out_filename) as out_stream: + self.decode(in_stream, out_stream) + + def encodeFiles(self, in_filename, out_filename): + with self.file_to_in_stream(in_filename) as in_stream, self.file_to_out_stream(out_filename) as out_stream: + self.encode(in_stream, out_stream) + + def decode(self, in_stream, out_stream): + bs = BitStream() + dq = deque() + at_least_three = False + for word in self.words_from_file(in_stream): + if not word or word not in self.word_dict: + continue + #print >> sys.stderr, 'word:"', word, '"' + dq.append(self.word_dict[word]) + if at_least_three or len(dq) == 3: + bs.append(pack(self.int_type, dq.popleft())) + at_least_three = True + if bs.len > self.bit_buffer: + cut = 0 + for byte in bs.cut(self.bit_buffer): + cut += 1 + byte.tofile(out_stream) + del bs[:cut * self.bit_buffer] + + # dq has to have exactly 2 elements here, the last is the bit length of the first, unless it's 0 + #print >> sys.stderr, 'dq:', dq + extra_bits = dq.pop() + bs.append(pack('uint:' + str(extra_bits), dq.popleft())) + + bs.tofile(out_stream) + + def print_index(self, index, out_stream): + #print self.word_list[index], + out_stream.write(self.word_list[index]) + self.word_count += 1 + if self.word_count > self.max_words_on_line: + out_stream.write('\n') + self.word_count = 0 + else: + out_stream.write(' ') + + def encode(self, in_stream, out_stream): + extra_bits = self.num_bits + bs = BitStream() + try: + while True: + chunk = in_stream.read(self.byte_buffer) + #print >> sys.stderr, 'chunk:', chunk + if(chunk): + bs.append(BitStream(bytes=chunk)) + else: + while True: + self.print_index(bs.read(self.int_type), out_stream) + try: + while True: + self.print_index(bs.read(self.int_type), out_stream) + except ReadError, e: + #print >> sys.stderr, 'inner:', e + pass + except ReadError, e: + #print >> sys.stderr, 'outer:', e + extra_bits = bs.len - bs.bitpos + if extra_bits > 0: + #print >> sys.stderr, 'extra_bits:', extra_bits + self.print_index(bs.read('uint:' + str(extra_bits)), out_stream) + else: + extra_bits = self.num_bits + # write extra_bits + self.print_index(extra_bits, out_stream) + + def words_from_file(self, in_file): + for line in in_file: + #print 'line:', line + words = line.split(' ') + for word in words: + word = word.translate(None, '`~!@#$%^&*()-_=+[{]}\|\'";:/?.>,<\t\n\v\f\r').strip() + if word: + yield word + + def remove_duplicates(self, values): + output = [] + seen = set() + for value in values: + if value not in seen: + output.append(value) + seen.add(value) + return output + + def read_dict(self, filename): + ret = [] + with open(filename, 'r') as dict_file: + for word in self.words_from_file(dict_file): + ret.append(word.strip()) + ret = self.remove_duplicates(ret) + index = 0 + ret_dict = {} + for word in ret: + ret_dict[word] = index + index += 1 + return (ret, ret_dict) + +def main(argv=None): + parser = argparse.ArgumentParser(description='FreeSpeech encode or decode IN_FILE, or standard input, to OUT_FILE or standard output.') + parser.add_argument('-d', '--decode', dest='decode', action='store_true', help='decode data (default: encode data)') + parser.add_argument('-i', '--in', dest='in_file', default='-', help='input file (default: - (stdin))') + parser.add_argument('-o', '--out', dest='out_file', default='-', help='output file (default: - (stdout))') + parser.add_argument('-m', '--max-words-per-line', dest='max_words_per_line', type=int, default=10, help='maximum words to put on one line (default: 10)') + parser.add_argument('-b', '--byte-buffer', dest='byte_buffer', type=int, default=65536, help='size of byte buffer used when reading/writing files (default: 65536 (64MB))') + parser.add_argument('word_list', nargs=1, help='word list file to use, must use the same one for encoding/decoding') + + args = parser.parse_args() + #print args + + try: + fs = FreeSpeech(args.word_list[0], args.max_words_per_line, args.byte_buffer) + if args.decode: + fs.decodeFiles(args.in_file, args.out_file) + else: + fs.encodeFiles(args.in_file, args.out_file) + return 0 + except: + return 1 + +if __name__ == '__main__': + sys.exit(main(sys.argv)) diff --git a/readme.md b/readme.md new file mode 100644 index 0000000..ab65a99 --- /dev/null +++ b/readme.md @@ -0,0 +1,8 @@ +FreeSpeech +---------- + +The idea here is to encode arbitrary data as human words taken from an arbitrary wordlist of arbitrary length. +Then, using the same wordlist, be able to decode the words back to the same data as before. + +I will expand on the concept and techniques used later, for now, a working reference implementation can be found in +freespeech.py. A sample wordlist can be found in english.txt. \ No newline at end of file diff --git a/test.sh b/test.sh new file mode 100755 index 0000000..3202f9f --- /dev/null +++ b/test.sh @@ -0,0 +1,5 @@ +#!/bin/bash +count=$1 +bs=$2 +dd if=/dev/urandom count=$count bs=$bs 2>/dev/null | tee >(md5sum 1>&2) >(./freespeech.py english.txt | ./freespeech.py -d english.txt | md5sum 1>&2) 1>/dev/null 2>&1 | cat +#dd if=/dev/urandom count=$count bs=$bs 2>/dev/null | tee >(md5sum 1>&2) >(base64 | base64 -di | md5sum 1>&2) 1>/dev/null 2>&1 | cat