#LyX 2.3 created this file. For more info see http://www.lyx.org/ \lyxformat 544 \begin_document \begin_header \save_transient_properties true \origin unavailable \textclass scrbook \begin_preamble % in case somebody want to have the label "Equation" %\renewcommand{\eqref}[1]{Equation~(\negthinspace\autoref{#1})} % that links to image floats jumps to the beginning % of the float and not to its caption \usepackage[figure]{hypcap} % the pages of the TOC is numbered roman % and a pdf-bookmark for the TOC is added \let\myTOC\tableofcontents \renewcommand\tableofcontents{% \frontmatter \pdfbookmark[1]{\contentsname}{} \myTOC \mainmatter } % makes caption labels bold % for more info about these settings, see % https://ctan.org/tex-archive/macros/latex/contrib/koma-script/doc/scrguien.pdf \setkomafont{captionlabel}{\bfseries} \setcapindent{1em} % enables calculations \usepackage{calc} % fancy page header/footer settings % for more information see section 9 of % ftp://www.ctan.org/pub/tex-archive/macros/latex2e/contrib/fancyhdr/fancyhdr.pdf \renewcommand{\chaptermark}[1]{\markboth{#1}{#1}} \renewcommand{\sectionmark}[1]{\markright{\thesection\ #1}} % increases the bottom float placement fraction \renewcommand{\bottomfraction}{0.5} % avoids that floats are placed above its sections \let\mySection\section\renewcommand{\section}{\suppressfloats[t]\mySection} % increases link area for cross-references and autoname them % if you change the document language to e.g. French % you must change "extrasenglish" to "extrasfrench" % if you uncomment the following lines, you cannot use the reference version Ref+Text in LyX %\AtBeginDocument{% % \renewcommand{\ref}[1]{\autoref{#1}} %} %\def\refnamechanges{% % \renewcommand*{\equationautorefname}[1]{} % \renewcommand{\sectionautorefname}{sec.\negthinspace} % \renewcommand{\subsectionautorefname}{sec.\negthinspace} % \renewcommand{\subsubsectionautorefname}{sec.\negthinspace} % \renewcommand{\figureautorefname}{Fig.\negthinspace} % \renewcommand{\tableautorefname}{Tab.\negthinspace} %} %\@ifpackageloaded{babel}{\addto\extrasenglish{\refnamechanges}}{\refnamechanges} \end_preamble \options intoc,bibliography=totoc,index=totoc,BCOR10mm,captions=tableheading,titlepage \use_default_options true \master /usr/share/lyx/examples/thesis/thesis.lyx \begin_modules customHeadersFooters \end_modules \maintain_unincluded_children false \language slovene \language_package default \inputencoding utf8 \fontencoding global \font_roman "lmodern" "Noto Sans CJK HK" \font_sans "lmss" "default" \font_typewriter "lmtt" "default" \font_math "auto" "auto" \font_default_family default \use_non_tex_fonts false \font_sc false \font_osf false \font_sf_scale 100 100 \font_tt_scale 100 100 \use_microtype false \use_dash_ligatures false \graphics default \default_output_format default \output_sync 0 \bibtex_command bibtex \index_command default \float_placement H \paperfontsize 12 \spacing single \use_hyperref true \pdf_title "Your title" \pdf_author "Your name" \pdf_bookmarks true \pdf_bookmarksnumbered true \pdf_bookmarksopen true \pdf_bookmarksopenlevel 1 \pdf_breaklinks false \pdf_pdfborder true \pdf_colorlinks false \pdf_backref false \pdf_pdfusetitle false \pdf_quoted_options "pdfpagelayout=OneColumn, pdfnewwindow=true, pdfstartview=XYZ, plainpages=false" \papersize a4paper \use_geometry false \use_package amsmath 2 \use_package amssymb 2 \use_package cancel 1 \use_package esint 1 \use_package mathdots 1 \use_package mathtools 1 \use_package mhchem 1 \use_package stackrel 1 \use_package stmaryrd 1 \use_package undertilde 1 \cite_engine basic \cite_engine_type default \biblio_style plain \use_bibtopic false \use_indices false \paperorientation portrait \suppress_date false \justification true \use_refstyle 0 \use_minted 0 \branch Standalone \selected 1 \filename_suffix 0 \color #ff0000 \end_branch \index Index \shortcut idx \color #008000 \end_index \secnumdepth 3 \tocdepth 2 \paragraph_separation skip \defskip medskip \is_math_indent 1 \math_indentation default \math_numbering_side default \quotes_style german \dynamic_quotes 0 \papercolumns 1 \papersides 2 \paperpagestyle fancy \tracking_changes false \output_changes false \html_math_output 0 \html_css_as_file 0 \html_be_strict false \end_header \begin_body \begin_layout Left Header \begin_inset Argument 1 status open \begin_layout Plain Layout \begin_inset ERT status collapsed \begin_layout Plain Layout \backslash chaptername \end_layout \end_inset \begin_inset space ~ \end_inset \begin_inset ERT status collapsed \begin_layout Plain Layout \backslash thechapter \end_layout \end_inset \end_layout \end_inset \begin_inset ERT status collapsed \begin_layout Plain Layout \backslash rightmark \end_layout \end_inset \begin_inset Note Note status collapsed \begin_layout Plain Layout Enable page headers and add the chapter to the header line. \end_layout \end_inset \end_layout \begin_layout Right Header \begin_inset Argument 1 status open \begin_layout Plain Layout \begin_inset ERT status collapsed \begin_layout Plain Layout \backslash leftmark \end_layout \end_inset \end_layout \end_inset \end_layout \begin_layout Left Footer \begin_inset Argument 1 status open \begin_layout Plain Layout \begin_inset ERT status collapsed \begin_layout Plain Layout \backslash thepage \end_layout \end_inset \end_layout \end_inset \end_layout \begin_layout Center Footer \end_layout \begin_layout Right Footer \begin_inset Argument 1 status open \begin_layout Plain Layout \end_layout \end_inset \begin_inset ERT status collapsed \begin_layout Plain Layout \backslash thepage \end_layout \end_inset \end_layout \begin_layout Chapter Rezultati \end_layout \begin_layout Section Analiza podatkov \end_layout \begin_layout Standard Na računalniku z operacijskim sistemom Gentoo Linux s 16 GiB delovnega spomina, procesorjem Intel i5-4590 in vrtečim se diskom program za analizo, spisan v Pythonu, razčleni in v spomin shrani 47843 torrentov v 432 sekundah. Večino časa program za razčlenjevanje sicer porabi za branje z diska, saj se poraba procesorja giblje okoli 5 %, vsak torrent pa je shranjen kot samostojna datoteka. Celoten proces z vsemi torrenti porablja 702 MB delovnega spomina. \end_layout \begin_layout Standard Za primerjavo pa razčlenjevalnik v programskem jeziku C za razčlembo in shranjevanje istega korpusa potrebuje 337 MB spomina, proces pa traja: \end_layout \begin_layout Standard \noindent \align center \begin_inset ERT status open \begin_layout Plain Layout \backslash begin{lstlisting} \end_layout \begin_layout Plain Layout real 1m41,777s \end_layout \begin_layout Plain Layout user 0m44,879s \end_layout \begin_layout Plain Layout sys 0m1,179s \end_layout \begin_layout Plain Layout \backslash end{lstlisting} \end_layout \end_inset \end_layout \begin_layout Subsection Osnovne informacije o količini podatkov \end_layout \begin_layout Standard Program je korpus nabral januarja in februarja 2023 v skupno 16 dneh, torej je v povprečju prenesel en torrent na 29 sekund. Program ni tekel konstantno, saj med delovanjem preveč moti domačo internetno linijo. V 47843 torrentih so zapisani metapodatki 3084321 datotek v skupni velikosti 259 TiB. \end_layout \begin_layout Standard Da je program ves čas med dvema prejetima torrentoma tekel, štejem le, če je med torrentoma minilo manj kot deset minut časa. V nasprotnem primeru smatram, da je bil program vmes ugasnjen. Čas prejetja torrenta program travnik shrani v ključ \family typewriter creation date. \family default V pythonu lahko zgoraj navedene podatke izvemo z zanko čez vse torrente: \end_layout \begin_layout Standard \begin_inset ERT status open \begin_layout Plain Layout \backslash begin{lstlisting}[language=Python, breaklines=true, basicstyle= \backslash tiny] \end_layout \begin_layout Plain Layout s = monotonic() \end_layout \begin_layout Plain Layout prej = None \end_layout \begin_layout Plain Layout skup = 0 \end_layout \begin_layout Plain Layout dat = 0 \end_layout \begin_layout Plain Layout vel = 0 \end_layout \begin_layout Plain Layout for torrent in sorted([torrent for sha1, torrent in torrents.items()], key=lambda x:x.dict.get(b'creation date')): \end_layout \begin_layout Plain Layout č = torrent.dict.get(b'creation date') \end_layout \begin_layout Plain Layout dat += sum(1 for path, size in torrent.paths()) \end_layout \begin_layout Plain Layout vel += sum(size for path, size in torrent.paths()) \end_layout \begin_layout Plain Layout if not prej: \end_layout \begin_layout Plain Layout prej = č \end_layout \begin_layout Plain Layout continue \end_layout \begin_layout Plain Layout if prej + 60*10 > č: \end_layout \begin_layout Plain Layout skup += č-prej \end_layout \begin_layout Plain Layout prej = č \end_layout \begin_layout Plain Layout print(monotonic()-s, "torrenti so se zbirali", skup/86400, "dni. en torrent je bil najden v povprečju na", skup/len(torrents), "sekund, v", len(torrents), "torrentih so metapodatki", dat, "datotek", "v skupni velikosti", vel/(1024**4), "TiB") \end_layout \begin_layout Plain Layout \backslash end{lstlisting} \end_layout \end_inset \end_layout \begin_layout Standard \begin_inset Note Note status open \begin_layout Plain Layout XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX todo koliko torrentov na uro je program prejel za vse ure v času delovanja XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXX \end_layout \end_inset \end_layout \begin_layout Subsection Odjemalci, od katerih so bili prejeti torrenti \end_layout \begin_layout Standard travnik v vsak torrent poleg \family typewriter creation date \family default in \family typewriter info \family default ključev doda še slovar pod ključem \family typewriter source \family default , v katerem so IP naslov soležnika ter njegova vrata (ključ \family typewriter ip \family default ) in različica programske opreme (ključ \family typewriter v \family default ), če jo le-ta pošlje. Na logaritemski skali je predstavljeno, koliko so posamezni odjemalci reprezent irani \begin_inset Foot status open \begin_layout Plain Layout Na tem diagramu so predstavljeni le odjemalci, ki zavzemajo vsaj 1 odstotek celotne populacije. Celoten diagram je objavljen v prilogi na sliki \begin_inset CommandInset ref LatexCommand ref reference "fig:Reprezentacija-vseh-odjemalcev" plural "false" caps "false" noprefix "false" \end_inset . \end_layout \end_inset . Inačica posameznega programa je odstranjena, imena pa so so normalizirana \begin_inset CommandInset citation LatexCommand cite key "Hunter:2007" literal "false" \end_inset . \begin_inset Foot status open \begin_layout Plain Layout \begin_inset ERT status open \begin_layout Plain Layout \backslash textmu Torrent \end_layout \end_inset se drugače pojavi dvakrat, enkrat ima znak mikro, enkrat pa grško črko mu. Unicode namreč ta dva znaka, ki sicer izgledata identično, hrani pod dvema različnima kodama. \end_layout \end_inset \end_layout \begin_layout Standard \begin_inset Float figure wide false sideways false status open \begin_layout Plain Layout \begin_inset Graphics filename ../odjemalci_1_ods.png width 115text% \end_inset \end_layout \begin_layout Plain Layout \begin_inset Caption Standard \begin_layout Plain Layout Reprezentacija odjemalcev, ki predstavljajo vsaj en odstotek populacije, na logaritemski skali \end_layout \end_inset \end_layout \end_inset \end_layout \begin_layout Subsection Predstavnost ključev v prejetih slovarjih \family typewriter info \end_layout \begin_layout Standard V slovarju \family typewriter info \family default implementacije poleg standardnih pogosto shranjujejo tudi druge metapodatke. Z logaritemsko skalo so predstavljeni vsi ključi, ki so se pojavili v korpusu torrentov. \end_layout \begin_layout Standard \begin_inset Float figure wide false sideways false status open \begin_layout Plain Layout \begin_inset Graphics filename ../vsi_ključi.png width 115text% \end_inset \end_layout \begin_layout Plain Layout \begin_inset Caption Standard \begin_layout Plain Layout Reprezentacija ključev v slovarju \family typewriter info \family default na logaritemski skali \end_layout \end_inset \end_layout \end_inset \end_layout \begin_layout Subsection Viri torrentov \end_layout \begin_layout Standard Med prej omenjenimi ključi so tudi \family typewriter source \family default , \family typewriter publisher \family default , \family typewriter publisher-url \family default in \family typewriter comment \family default , v katerih so često shranjene informacije o distributorju torrenta, ko gre za večjo organizacijo. Kar 92 % torrentov takega ključa sploh nima. Sledi seznam največkrat omenjenih na tak način pridobljenih distributorjev. \end_layout \begin_layout Standard \begin_inset Float table wide false sideways false status open \begin_layout Plain Layout \noindent \align center \begin_inset Note Note status open \begin_layout Plain Layout \noindent \align center \begin_inset Tabular \begin_inset Text \begin_layout Plain Layout Besedilo v polju \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout Pojavitev \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout PMEDIA \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 163 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout http://tapochek.net/index.php \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 130 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 高清下载吧！ \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 122 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout https://FreeCourseWeb.com \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 122 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 灣搭拉咩拉 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 93 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 脫拉庫 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 88 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 第一會所新片@SIS001 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 82 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 大师兄福利网 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 79 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 2048 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 77 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 1024社區最新地址 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 75 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 74 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout LostFilm.TV \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 64 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout [https://tanhuazu.com] 探花族社区 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 47 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 2048核基地 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 46 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout https://hjd.tw \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 44 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 1024核工厂 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 43 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout RV原创 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 42 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 1024社區 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 41 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 小贾_KTXP \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 39 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 國產精品 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 37 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 麻豆之神 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 36 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 吃雞大神 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 34 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout b48t.com \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 34 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout https://crackshash.com/ \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 33 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 老含及 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 33 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 欧宝 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 31 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout https://rh2048.com \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 30 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 小隻馬 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 27 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 1024 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 27 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout AV大平台 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 27 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout @蜂鳥论坛@ \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 26 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout Weagogo \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 25 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 第一會所新片 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 25 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout JAV Torrent 掲示板 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 25 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 发发发 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 22 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 刷刷刷 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 21 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout https://1tors.ru/ \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 21 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 1024工厂 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 20 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout hjd.tw \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 20 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 不予 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 19 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 小樱 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 17 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout (美女裸聊直播 uur68.com) \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 17 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout xue0117 \end_layout \end_inset \begin_inset Text \begin_layout Plain Layout 17 \end_layout \end_inset \end_inset \end_layout \end_inset \begin_inset Graphics filename ../distributorji_5_ods.png scale 75 \end_inset \begin_inset Caption Standard \begin_layout Plain Layout Seznam največkrat omenjenih distributorskih organizacij, ki zavzemajo vsaj 5 % celotne populacije \end_layout \end_inset \end_layout \end_inset \end_layout \begin_layout Subsection Tipi datotek, ki se prenašajo v torrentih \end_layout \begin_layout Standard Za reprezentativen prikaz najpogostejše vrste vsebine, ki se po torrentih prenaša, glede na končnico datoteke, so podatki o končnicah (tipih datotek) prikazani po reprezentativni obliki datoteke v torrentih. Ponavadi je datoteka oz. tip datoteke, ki najbolje predstavlja torrent, tisti tip, ki v torrentu zajema največ prenesene velikosti. Za vsak torrent iz korpusa je bil poiskan reprezentativni tip datoteke ter predstavljen z diagramom, ki prikazuje reprezentativne tipe torrentov, ki predstavljajo vsaj en promil vseh reprezentativnih tipov. \end_layout \begin_layout Standard \begin_inset Float figure wide false sideways false status open \begin_layout Plain Layout \noindent \align center \begin_inset Graphics filename ../reprezentativni_.1_ods.png width 100text% \end_inset \end_layout \begin_layout Plain Layout \begin_inset Caption Standard \begin_layout Plain Layout Reprezentativni tipi torrentov, ki predstavljajo vsaj en promil populacije, na logaritemski skali \end_layout \end_inset \end_layout \end_inset \end_layout \begin_layout Standard Iz diagrama je razvidno, da je večina objavljenih vsebin v torrent omrežju videovsebin, zvočnih datotek ter stisnjenih arhivov. \end_layout \begin_layout Standard Če bi za določilo pojavnosti tipa uporabili število datotek, bi prevladovali tipi vsebin, ki so ponavadi preneseni kot kopica datotek, denimo slike (diagram v prilogi na sliki \begin_inset CommandInset ref LatexCommand ref reference "fig:Pojavnost-tipa-kot-število-datotek" plural "false" caps "false" noprefix "false" \end_inset ), če pa bi za določilo pojavnosti tipa uporabili velikost datotek tega tipa, pa bi prevladovali tisti tipi, ki zasedajo več prostora. V tem primeru bi npr. videovsebine zaradi svoje velikosti občutno presegale digitalne knjige (diagram v prilogi na sliki \begin_inset CommandInset ref LatexCommand ref reference "fig:Pojavnost-tipa-kot-velikost-datotek" plural "false" caps "false" noprefix "false" \end_inset ). \end_layout \begin_layout Standard \begin_inset Branch Standalone inverted 0 status open \begin_layout Standard \begin_inset Note Note status open \begin_layout Plain Layout The contents of this branch is only output if this chapter is processed on its own, i. \begin_inset space \thinspace{} \end_inset e., not from the master. This allows you to have a bibliography and a nomenclature if you only want to output this chapter. \end_layout \end_inset \end_layout \begin_layout Standard \begin_inset CommandInset include LatexCommand include filename "Bibliography.lyx" \end_inset \end_layout \end_inset \end_layout \end_body \end_document