diff --git a/report/datasets.non-failed.origin-redirects.coverage.sorted.tsv b/report/datasets.non-failed.origin-redirects.coverage.sorted.tsv new file mode 100644 index 0000000..ded97d0 --- /dev/null +++ b/report/datasets.non-failed.origin-redirects.coverage.sorted.tsv @@ -0,0 +1,73 @@ +Dataset Domains With R R/dwr I E Mix I+E Insec Sec Mix sec Final sec Mism +alexa.2014-09-01.random.10000-http 8216 4030 1.1369727047146403 0.9119106699751861 0.05707196029776675 0.008684863523573201 0.9176178660049628 0.04540942928039702 0.01488833746898263 0.05806451612903226 0.02258064516129032 +alexa.2014-09-01.random.10000-http-www 8493 2571 1.1338000777907429 0.8584208479190977 0.09607156748346947 0.010501750291715286 0.8716452742123687 0.08284714119019837 0.010890704006223259 0.09023726176584987 0.035783741734733567 +alexa.2014-09-01.random.10000-https 1135 717 1.2622036262203626 0.803347280334728 0.16178521617852162 0.0041841004184100415 0.6317991631799164 0.2649930264993027 0.07531380753138076 0.29428172942817293 0.030683403068340307 +alexa.2014-09-01.random.10000-https-www 1224 470 1.2319148936170212 0.9234042553191489 0.036170212765957444 0.00851063829787234 0.6148936170212767 0.30425531914893617 0.04680851063829787 0.32127659574468087 0.03404255319148936 +alexa.2014-09-01.top.10000-http 8545 6077 1.2033898305084745 0.9350008227743952 0.03570840875431956 0.010860622017442817 0.9047227250287971 0.05792331742636169 0.01908836597005101 0.0752015797268389 0.018430146453842357 +alexa.2014-09-01.top.10000-http-www 8682 2702 1.2427831236121392 0.8645447816432272 0.08697261287934863 0.01147298297557365 0.7890451517394522 0.14951887490747595 0.024056254626202814 0.17061435973353073 0.03774981495188749 +alexa.2014-09-01.top.10000-https 2507 1856 1.318426724137931 0.9515086206896551 0.022629310344827586 0.008620689655172414 0.6018318965517241 0.2920258620689655 0.08836206896551724 0.3141163793103448 0.017780172413793104 +alexa.2014-09-01.top.10000-https-www 2957 1536 1.2428385416666667 0.9231770833333334 0.03515625 0.011067708333333334 0.6875 0.2265625 0.055989583333333336 0.24479166666666666 0.030598958333333332 +alexa.2014-09-01.top.dk.10000-http 2263 1456 1.210164835164835 0.9354395604395604 0.036401098901098904 0.007554945054945055 0.9114010989010989 0.05425824175824176 0.013736263736263736 0.0673076923076923 0.020604395604395604 +alexa.2014-09-01.top.dk.10000-http-www 2310 833 1.1944777911164466 0.8715486194477791 0.07322929171668667 0.010804321728691477 0.8331332533013205 0.1056422569027611 0.01680672268907563 0.1212484993997599 0.04441776710684274 +alexa.2014-09-01.top.dk.10000-https 339 225 1.3422222222222222 0.9422222222222222 0.02666666666666667 0.008888888888888889 0.5288888888888889 0.3377777777777778 0.1111111111111111 0.38666666666666666 0.022222222222222223 +alexa.2014-09-01.top.dk.10000-https-www 441 232 1.2758620689655173 0.8922413793103449 0.03879310344827586 0.01293103448275862 0.6508620689655172 0.25 0.04310344827586207 0.27586206896551724 0.05603448275862069 +alexa.2014-09-01.top.se.10000-http 2797 1738 1.161680092059839 0.9476409666283084 0.03164556962025317 0.004027617951668585 0.9062140391254315 0.06501726121979287 0.012082853855005753 0.07652474108170311 0.01668584579976985 +alexa.2014-09-01.top.se.10000-http-www 2895 863 1.146002317497103 0.8980301274623407 0.07879490150637311 0.002317497103128621 0.8192352259559675 0.14947856315179606 0.010428736964078795 0.15990730011587487 0.02085747392815759 +alexa.2014-09-01.top.se.10000-https 438 282 1.2730496453900708 0.9680851063829787 0.014184397163120567 0 0.5638297872340425 0.3475177304964539 0.07092198581560284 0.37943262411347517 0.01773049645390071 +alexa.2014-09-01.top.se.10000-https-www 650 268 1.2164179104477613 0.9365671641791045 0.022388059701492536 0 0.6529850746268657 0.26865671641791045 0.03731343283582089 0.27611940298507465 0.041044776119402986 +com.2014-08-29.random.10000-http 7775 2419 1.204630012401819 0.5708970649028524 0.38735014468788753 0.014882182720132286 0.9313766019016122 0.014055394791236048 0.02687060768912774 0.03885903265812319 0.027697395618023975 +com.2014-08-29.random.10000-http-www 7811 1968 1.2266260162601625 0.46697154471544716 0.49339430894308944 0.007113821138211382 0.9176829268292683 0.01676829268292683 0.033028455284552845 0.046239837398373985 0.03353658536585366 +com.2014-08-29.random.10000-https 50 24 1.3333333333333333 0.9166666666666666 0 0 0.5833333333333334 0.25 0.08333333333333333 0.25 0.08333333333333333 +com.2014-08-29.random.10000-https-www 55 23 1.2173913043478262 0.9130434782608695 0.043478260869565216 0 0.5217391304347826 0.34782608695652173 0.08695652173913043 0.34782608695652173 0.043478260869565216 +dk.2014-07-23.random.10000-http 7180 2228 1.263016157989228 0.4403052064631957 0.48967684021543983 0.012567324955116697 0.9052962298025135 0.02154398563734291 0.01570915619389587 0.03590664272890485 0.05834829443447038 +dk.2014-07-23.random.10000-http-www 7378 2025 1.2982716049382717 0.36493827160493825 0.5575308641975308 0.01037037037037037 0.8933333333333333 0.02271604938271605 0.017777777777777778 0.03901234567901234 0.06765432098765432 +dk.2014-07-23.random.10000-https 23 10 1.1 0.9 0.1 0 0.4 0.5 0.1 0.6 0 +dk.2014-07-23.random.10000-https-www 32 15 1.2666666666666666 0.7333333333333333 0.06666666666666667 0 0.3333333333333333 0.4 0.06666666666666667 0.4666666666666667 0.2 +net.2014-08-29.random.10000-http 7270 2108 1.23719165085389 0.4672675521821632 0.49620493358633777 0.015180265654648957 0.9321631878557874 0.011859582542694497 0.03462998102466793 0.04601518026565465 0.021347248576850095 +net.2014-08-29.random.10000-http-www 7378 1874 1.25880469583778 0.3767342582710779 0.5944503735325507 0.0026680896478121665 0.9178228388473852 0.015474919957310566 0.04055496264674493 0.05549626467449306 0.026147278548559232 +net.2014-08-29.random.10000-https 26 7 1 0.8571428571428571 0 0 0.42857142857142855 0.42857142857142855 0 0.42857142857142855 0.14285714285714285 +net.2014-08-29.random.10000-https-www 28 8 1 0.75 0.125 0 0.625 0.25 0 0.25 0.125 +reach50.2014w35.se-http 43 37 1.1891891891891893 0.9459459459459459 0.02702702702702703 0 0.8648648648648649 0.08108108108108109 0.02702702702702703 0.10810810810810811 0.02702702702702703 +reach50.2014w35.se-http-www 42 12 1.25 0.8333333333333334 0.08333333333333333 0 0.5833333333333334 0.3333333333333333 0 0.3333333333333333 0.08333333333333333 +reach50.2014w35.se-https 18 13 1.4615384615384615 0.9230769230769231 0.07692307692307693 0 0.3076923076923077 0.6923076923076923 0 0.6923076923076923 0 +reach50.2014w35.se-https-www 26 17 1.0588235294117647 0.8823529411764706 0.058823529411764705 0 0.47058823529411764 0.47058823529411764 0 0.47058823529411764 0.058823529411764705 +se.2014-07-10.random.100000-http 73605 21181 1.2397903781691137 0.5017232425286814 0.43605117794249565 0.011803031018365516 0.9150181766677683 0.02011236485529484 0.014777394834993626 0.03389830508474576 0.05075303337897172 +se.2014-07-10.random.100000-http-www 77261 18765 1.2626165734079404 0.41007194244604317 0.5338129496402878 0.0035171862509992004 0.9086597388755662 0.023394617639221956 0.01630695443645084 0.03852917665867306 0.05259792166266986 +se.2014-07-10.random.100000-https 282 125 1.32 0.872 0.056 0.008 0.256 0.624 0.056 0.64 0.064 +se.2014-07-10.random.100000-https-www 328 115 1.2695652173913043 0.8782608695652174 0.06956521739130435 0.017391304347826087 0.41739130434782606 0.5130434782608696 0.034782608695652174 0.5217391304347826 0.034782608695652174 +se.healthstatus.2013.counties-http 18 4 1.25 1 0 0 1 0 0 0 0 +se.healthstatus.2013.counties-http-www 21 3 1 1 0 0 1 0 0 0 0 +se.healthstatus.2013.counties-https 3 2 1 1 0 0 1 0 0 0 0 +se.healthstatus.2013.counties-https-www 6 3 1 1 0 0 0.6666666666666666 0.3333333333333333 0 0.3333333333333333 0 +se.healthstatus.2013.domain-registrars-http 127 90 1.4777777777777779 0.7888888888888889 0.15555555555555556 0.03333333333333333 0.7777777777777778 0.14444444444444443 0.05555555555555555 0.2 0.022222222222222223 +se.healthstatus.2013.domain-registrars-http-www 134 55 1.6181818181818182 0.6545454545454545 0.32727272727272727 0 0.6545454545454545 0.2545454545454545 0.07272727272727272 0.32727272727272727 0.01818181818181818 +se.healthstatus.2013.domain-registrars-https 40 28 1.2142857142857142 0.8928571428571429 0.03571428571428571 0.07142857142857142 0.32142857142857145 0.6071428571428571 0.07142857142857142 0.6071428571428571 0 +se.healthstatus.2013.domain-registrars-https-www 42 14 1.2142857142857142 0.8571428571428571 0.14285714285714285 0 0.5 0.42857142857142855 0.07142857142857142 0.42857142857142855 0 +se.healthstatus.2013.financial-services-http 67 53 1.4528301886792452 0.8679245283018868 0.09433962264150944 0.03773584905660377 0.8301886792452831 0.05660377358490566 0.11320754716981132 0.16981132075471697 0 +se.healthstatus.2013.financial-services-http-www 72 36 1.1944444444444444 0.75 0.2222222222222222 0.027777777777777776 0.75 0.19444444444444445 0.05555555555555555 0.25 0 +se.healthstatus.2013.financial-services-https 16 9 1.2222222222222223 0.8888888888888888 0.1111111111111111 0 0.2222222222222222 0.7777777777777778 0 0.7777777777777778 0 +se.healthstatus.2013.financial-services-https-www 31 10 1.3 0.9 0.1 0 0.5 0.4 0.1 0.4 0 +se.healthstatus.2013.gocs-http 49 35 1.2857142857142858 0.8571428571428571 0.11428571428571428 0 0.9428571428571428 0.02857142857142857 0 0.02857142857142857 0.02857142857142857 +se.healthstatus.2013.gocs-http-www 57 14 1.5714285714285714 0.5 0.42857142857142855 0 0.8571428571428571 0.07142857142857142 0 0.07142857142857142 0.07142857142857142 +se.healthstatus.2013.gocs-https 4 3 1 1 0 0 0.3333333333333333 0.6666666666666666 0 0.6666666666666666 0 +se.healthstatus.2013.gocs-https-www 9 2 2 1 0 0 0 1 0 1 0 +se.healthstatus.2013.higher-education-http 40 26 1.2692307692307692 0.9615384615384616 0.038461538461538464 0 1 0 0 0 0 +se.healthstatus.2013.higher-education-http-www 47 10 1.2 0.9 0.1 0 1 0 0 0 0 +se.healthstatus.2013.higher-education-https 9 7 1.7142857142857142 1 0 0 0.42857142857142855 0.2857142857142857 0.2857142857142857 0.2857142857142857 0 +se.healthstatus.2013.higher-education-https-www 24 8 1.25 1 0 0 0.875 0.125 0 0.125 0 +se.healthstatus.2013.isps-http 18 14 1.2857142857142858 1 0 0 0.8571428571428571 0.14285714285714285 0 0.14285714285714285 0 +se.healthstatus.2013.isps-http-www 19 7 1.1428571428571428 1 0 0 0.7142857142857143 0.2857142857142857 0 0.2857142857142857 0 +se.healthstatus.2013.isps-https 6 4 1 1 0 0 0.5 0.5 0 0.5 0 +se.healthstatus.2013.isps-https-www 10 2 1 1 0 0 1 0 0 0 0 +se.healthstatus.2013.media-http 26 22 1.0454545454545454 0.8636363636363636 0.09090909090909091 0.045454545454545456 1 0 0 0 0 +se.healthstatus.2013.media-http-www 28 10 1.1 0.7 0.3 0 1 0 0 0 0 +se.healthstatus.2013.media-https 4 2 1.5 1 0 0 1 0 0 0 0 +se.healthstatus.2013.media-https-www 5 3 1 1 0 0 0.6666666666666666 0.3333333333333333 0 0.3333333333333333 0 +se.healthstatus.2013.municipalities-http 249 73 1.0547945205479452 0.9863013698630136 0 0.0136986301369863 0.9726027397260274 0.0273972602739726 0 0.0273972602739726 0 +se.healthstatus.2013.municipalities-http-www 271 26 1.0769230769230769 0.9230769230769231 0.038461538461538464 0 0.8461538461538461 0.11538461538461539 0 0.11538461538461539 0.038461538461538464 +se.healthstatus.2013.municipalities-https 44 23 1.3043478260869565 1 0 0 0.5217391304347826 0.34782608695652173 0.13043478260869565 0.34782608695652173 0 +se.healthstatus.2013.municipalities-https-www 54 20 1.05 1 0 0 0.7 0.3 0 0.3 0 +se.healthstatus.2013.public-authorities-http 170 84 1.1428571428571428 0.8095238095238095 0.17857142857142858 0.011904761904761904 0.9404761904761905 0.03571428571428571 0.023809523809523808 0.05952380952380952 0 +se.healthstatus.2013.public-authorities-http-www 203 54 1.2222222222222223 0.6296296296296297 0.37037037037037035 0 0.8888888888888888 0.09259259259259259 0.018518518518518517 0.1111111111111111 0 +se.healthstatus.2013.public-authorities-https 18 9 1.1111111111111112 1 0 0 0.7777777777777778 0.2222222222222222 0 0.2222222222222222 0 +se.healthstatus.2013.public-authorities-https-www 37 12 1.0833333333333333 1 0 0 0.6666666666666666 0.3333333333333333 0 0.3333333333333333 0 diff --git a/report/report.lyx b/report/report.lyx index 0aaf438..f00c743 100644 --- a/report/report.lyx +++ b/report/report.lyx @@ -5023,6 +5023,13 @@ During the development of code for this thesis, other projects have been \begin_layout Subsection The HAR specification +\begin_inset CommandInset label +LatexCommand label +name "sub:The-HAR-specification" + +\end_inset + + \end_layout \begin_layout Standard @@ -9499,11 +9506,80 @@ Write about HTTPS to HTTP redirects. \end_layout \begin_layout Standard -\begin_inset Note Greyedout +The table shows domains, domains with redirect responses to the origin request + and the average length of the redirect chain per domain with redirects. + The ratio of redirected domains making strictly internal or strictly external + redirects, and how many domains mix internal and external redirect URLs + are shown next. + The same goes for insecure, secure and mixed security redirects - plus + a column with the ratio of domains where the final redirect is to a secure + URL. + The last column shows the ratio of domains with mismatched redirect URLs + without a subsequently requested URL. +\end_layout + +\begin_layout Standard +\begin_inset ERT +status open + +\begin_layout Plain Layout + + +\backslash +tsvtable{datasets.non-failed.origin-redirects.coverage.sorted.tsv}{Origin domains + with redirects}{}{fixed, display columns/0/.style={string type, column type=l}, + display columns/1/.style={string type, column type=i}, display columns/2/.style={ +string type, column type=i}} +\end_layout + +\end_inset + + +\end_layout + +\begin_layout Standard +\begin_inset ERT status open \begin_layout Plain Layout -Insert table based on origin-redirects.sh. + + +\backslash +begin{futurework} +\end_layout + +\end_inset + + +\end_layout + +\begin_layout Standard +The mismatched redirect and request URLs are in part due to the HAR standard + not defining recorded redirect URLs as strictly absolute, and phantomjs + returning unparsed/unresolved URLs when a redirect is initially detected + in a HTTP response +\begin_inset CommandInset ref +LatexCommand eqref +reference "sub:The-HAR-specification" + +\end_inset + +. + Resolving redirect URLs outside of the browser means not all contexts and + rules are considered, thus leading to errors. + Both the thesis code, phantomjs software and HAR standard can be improved + upon. +\end_layout + +\begin_layout Standard +\begin_inset ERT +status open + +\begin_layout Plain Layout + + +\backslash +end{futurework} \end_layout \end_inset