From d8fc61f610fbd7e3e0b3f173936617e8c844c926 Mon Sep 17 00:00:00 2001 From: Peter Kleiweg Date: Fri, 3 Apr 2026 17:47:53 +0200 Subject: [PATCH] website --- www/cats | 20 + www/cats.table | 25 + www/favicon.ico | Bin 0 -> 16494 bytes www/gettags.sh | 57 +++ www/index.html | 698 ++++++++++++++++++++++++++ www/locaties-2026-13-4.table | 25 + www/nieuw-namen-2026-13-4.t20.table | 25 + www/nieuw-woorden-2026-13-4.t20.table | 25 + www/organisaties-2026-13-4.table | 25 + www/overige-namen-2026-13-4.table | 25 + www/personen-2026-13-4.table | 25 + www/style.css | 106 ++++ www/tags | 1 + www/tags.table | 25 + www/top2html.py | 43 ++ 15 files changed, 1125 insertions(+) create mode 100644 www/cats create mode 100644 www/cats.table create mode 100644 www/favicon.ico create mode 100755 www/gettags.sh create mode 100644 www/index.html create mode 100644 www/locaties-2026-13-4.table create mode 100644 www/nieuw-namen-2026-13-4.t20.table create mode 100644 www/nieuw-woorden-2026-13-4.t20.table create mode 100644 www/organisaties-2026-13-4.table create mode 100644 www/overige-namen-2026-13-4.table create mode 100644 www/personen-2026-13-4.table create mode 100644 www/style.css create mode 100644 www/tags create mode 100644 www/tags.table create mode 100755 www/top2html.py diff --git a/www/cats b/www/cats new file mode 100644 index 0000000..4e5a759 --- /dev/null +++ b/www/cats @@ -0,0 +1,20 @@ + 433 Buitenland + 358 Binnenland + 280 system:vrtnieuws/brands/radio-2 + 170 Regionaal nieuws + 90 Economie + 88 Politiek + 45 Cultuur & Media + 42 system:vrtnieuws/brands/radio-1 + 17 Tech + 7 Koningshuis + 7 Opmerkelijk + 7 system:vrtnieuws/brands/sporza + 5 Voetbal + 1 Atletiek + 1 Handbal + 1 Nieuws + 1 Sport algemeen + 1 system:vrtnieuws/brands/stubru + 1 Tennis + 0 diff --git a/www/cats.table b/www/cats.table new file mode 100644 index 0000000..cea9fd7 --- /dev/null +++ b/www/cats.table @@ -0,0 +1,25 @@ +
+

cats

+ + + + + + + + + + + + + + + + + + + + + +
Buitenland
Binnenland
system:vrtnieuws/brands/radio-2
Regionaal nieuws
Economie
Politiek
Cultuur & Media
system:vrtnieuws/brands/radio-1
Tech
Koningshuis
Opmerkelijk
system:vrtnieuws/brands/sporza
Voetbal
Atletiek
Handbal
Nieuws
Sport algemeen
system:vrtnieuws/brands/stubru
Tennis
+
diff --git a/www/favicon.ico b/www/favicon.ico new file mode 100644 index 0000000000000000000000000000000000000000..4cd7daea8918b5b26d8439631fcdd07fba3e54cd GIT binary patch literal 16494 zcmeI32V7N0_Qyw~Nmh4F+w8{OWMg*I*50DA#1_T=eAbA7&xQpP8%7kAh*1QoBJdus zfFKa0BVfl~qp=VY%QYrzdNh{wnD+nPH*mc?g_wUJ$$mEP!|?8%nLBgl%sIbP<~||n zh+D*+cM8657gOsC(Lo5&q=~%GxLt@u>U#80@9z_jw-v&zkr0p5herh6oX_!f!%s^u zFVSk;IMHhSc+q;o1krZN6w!X#H1Wjr>EelJpA{Wu&J-PI%@R+}o-Ll7Ge>lK{&~?^ zE%WAyt_v23rvd^*kHw2ck0nb)&lg`5BPqR>EfZdpr&-HN1po9c5hx@@+ ztMKA_0^idpzIMBqk(em_l9EIKB``Tz1f-;h5VfSGiSV^+g|(nSWNh3hGAUV`H;eT< zc8CM7ydn-AJ0=cOj+B-P<&8JQnK$1QAAaQ(X0H{XcwzyDtR@WT%`O1zjNTffdfYQd8%FcMfuk~k5szv{?C7P&{zDy zX#BhGe()cS#s_*|t7zWfwnn%9L%YAl*z(_+xpB#(fR-jBOw5r{0U(`qwc&+R}JepT@VV_s09W^l#R(Rf|4d?{(f9jeq^q zgLQ6sqM>uPpSwpY&NiX+ps4s<)u*|;yHK&V<=C;JrO6~(sRi6^U5>l0Cr%V?CQTA; zy}d=-$&;Np+zu>mH+8CL2Og`K+}_7Wv{!LiEzdnCI;cg(=L(Eg@!8i`becQYiO*g9 z{6rTpx~spx6Q`eAxKMOkv`BOd3>4kf^1=(EyNcbEUX)SX_XrA-SYD3jZs2*(rAtL` zii+#Kf`gs7{&Yx)n80=K(9mlbufzGiVEt&YzHd~N=tt=r9WDB)1?(Tsw~GH0R679v z52g&Ij8JVsY^)ea8AKULQEkH@%5chP$^h)a7`_Mct=f!16fdq-yD^+HMy)HiA4Z+c z7=o=B&;10-M9MSVSJ;qoTzgX{t93S;7>_;irc5ojEzj~jgZep?nb;X$heIsD*7#FK zVrS-KZh!{!)wkR?)Q$$l%QXG`1tSk|$ zmYf`spqAWRk*JouJYmbv7s=SJtaa-|QemM;rK~9`63NBI;w4HZC4K#RkxR+hutBWV z*|==%+`5tyv2NQoQAjD;zFibk)~f~kw{h1lv1QL5QL=Zh*iPB8f4|s$@Sxa3+5Pg% zVh?36WuN+e=#bcV_^{YdIe6rVW;b6se%xt0kCl~)($`-XWt7)Xof0QcpB8UmOW%0w zEpe9e*12=yKX1P+-hJ;q@%{%Nhz~yeP<*HsZ0$$q&pYky$JpFUmoAA*moJOUlq=X@ zrwzvbR@mS#u)(Sw{_3l*G+X@bx8I8IzWeSsYm=4ApV9Lw-@Du$sdw)Nm#Rv)?xrr@ zl`1OV9I1bIyE`{luG8PSdp{T3-lVUobX|5^!`GEIe=Mm~sk@orJw{PNJ6B1;ef5vg zyGh+cx@UBkmTn&E-7N2Ex=P)p>B05t-O+mOb(PmHPd?^h8jzgZ*VLi@@oTl(Rdi#w zb_@EO?jIELuUl_>UaPLSSkf?gg2C{}B;Q7@yuCL+GPR<<{QL0jS&HIg>X}~9w!uG7 zD0^=!uH0cbTszp*WGXxA)vVDbMVVNM2}xb**Y9R+I{mcCm8^#4TDDJdcwkutmPFIx4BRZBc1%sa+Hj>r( zH)jg@G4vj*K-xnGm6z(>6{wsrcr(T9#t)p9%_V;;?Ksw}bJ>)~%=IFR8wMD>6_aUp z1vfVL4Io82Yswn+hEL4=NhV2yPw8?v$GT=Gcp3_cQcX!9J4Bq{*gC`6v8U`|W zmte)TRJJRBj~_6!wBzHDHsuipFK*bn@y@7`Tk9S!Z(mi{^x`XX>pZF`Cr5fCe0~1< z)V{S3{AG4|v!WDr_W0AtypCf}jP#z|;^6GY`QCT^p{HGIR+N|Pr7B8kM+R3WKX&g< zMcLl4P}i&|VRc8v%(=gtThIzqkGnkMjJM9J)T}7`2YYy=D9cPHzY|5nJO*y9Xs*gH z_@(MqKcxp{F-46NtNIYn)Y9jqqUH-FY9&Y^#+YickQwE+g{P;{ zY$iIXL5|hnP^2=Ee3A_0UJ2oeJmuhoZV*orfmomLJafZ_8l1EShgzDPOvZu)fy#WF zji^x$PN+A@Y(|8rB&9MmKAvE(2IsAjq27D{eMuf@Nsc8fElocx5j84|Udsh;+O;4=zF-&F3zXveKEGB?VMz&jG60jTAIvA0ay=!;JdzItq01c5%(dIE z@AIqFpq|JBXGu^_=5mU~f)%?VC4fIxxOYehoe?A#8N1;lzd+@QQ>UODgnw$$BC?Mq zd-hZ{DY+|{4+N3y#I;ycSXfohU$WkjpO5C2!=~BH;Z-%WFG@<{RF74l=A>1t+No+r zsPQKE*jSR|sAQM<^TX5As~?|~B-R;2MxLBqBdb__|JrVa+tAZ=)F|@oq}L}!Mn+_0 zB(GaXN|kJ#)=i;X=$X~3BhoofmS-;#eqV|8_~_Y$jCEi&sH-r;yKiqr8 z3W(v58vJAx(99pyVuCqM0c7z1>A>!w+OkP%3jGPnSP^}q($hKWttC>gAC}|f@YGa^ zByd$qK0F8f$ApBu`PN%ocIKK#yxY3LeMt<9rDYuopfS%hy-0 zy3AOEx60YG8Uv4(mTDt&h$HKv3OZRJ{{Jh-j>!(FxdDw{wTiPw*#VUgOHDuun3>?4%#1E{cGzBMHOhHy>tl5kT>t{!9agWIs zYD-AT%{_AL*qVX@0G4C6y$22$;^H`;m4bvW@cxN@1g`PGaVl^vayD&pY5MuM7^5hM z11%%G4Y%3!SRsiAfAEcaEnKKAVQodIjyuZ9D(Ix<5(5LJAh|378@H*Xgl9>-p#Epy zd=t0u=abC{B-4DIs1AUG_Rt`a+|S`4$@%fci*O#|Sr@Mdu}sKDLZl$&Zrn%~x}5m% z@C7#8l`B`4rKCtfVhKlIeU%u0)!Mbv#!1(d$59ZExVQ~FcDQWxPg)VrMmrIY1R!hy z>R}y!;2}ziCFP8KKzKNA1DuC=4gJ(5ICX(X&}ClH!sbFe=bsRuB5+EI6r`R(L0}hP zD{UMH`v8{;P-DjeurLZlVu3%2Y}uLZQ*oZuABbnMjE;$67U0ped^u?}liAE(-~dRm zfq1<{q3J9EVTO3bMiQ@&+2IUJKpG7W2UyBb!&UOgdrFt0Y1cL+p=pHaspdWUVmq7h@A9`h>)D;ErlSv-DRU+J9$!l+{t#ICIW1?J8i+nojZ9?f~~=_fJnT5fM?Duv#eHj?dF$o{``4Tf6`ErK;ywL zzW4%WVx+J&Qeh?WY!J>QGX|%mXj5nk3+LfyGk15yNmFM=<7EJqcw$MLja@(*r8>W~ zem%po-N(zy=qBv~W*ye;JaFLV=_kd6KM5=Bxw+a?W1N0IT=k5J(Zpuswrxy}cCdsM zsi`c16rx^X(+Udo>da`HckeDI-fFdFXG?DcyTCZ3f`erQt>unb2y3KrirK7D@}n1c zQ_|djr1Pm(Wo9CcFbBsHh2yP zlXC;B8L zXnkO{DK?h$luRA$*t=J2k{8)UMNBQ1&?hj^B}vN?7CFNlxrFJ#!5Z=MaWoDWj$M#~ zq_@sFn>T~Qu$0$cTqeEYE!;p=;r}zSvE_qbxZq_rqglAYEDcc^WwGcnO)4x)V+m4_ zP-i_NNrjc1mrFpXSd<(etR`{IwqgXOAW3zWtw{w1xTZJHf1Vm&kmytVbK~<;yj7)(}aLHdB`_WsTYrcpT!R)6!rsoHxeB1={T{OPFl2fZIHE z;ijVlGBa2oLXz0jROuc_3yYCLi9F0^gq)X`S;B$ChxKTK%*OC|A8E1^<*mL&|uw;`+VbPxQjRt;@rAC`c>p&2QAcD7z&;bcZp5w=w$p1hDY zI2SD8#iS$*5MqEwH1#@z#HhWM~GYb58e z$gaG=>gnfYNJzpWK&cc(7UUm}v8^C;}gM~-NS#4g}M zqp*6h(OYM(CGl_`;`#l-_T9T#Bfd26qUt5Ediu4LCT0k8#u9LG?k4DC{n$O9s#Nh%`7LK#C2-!yM?G z<@A481xi;v*|L?$8pXub^oomFD}hQ70e z{-L3I>r6Lfo>V71l)5l0CI*DjKmG}MV1Iu)@ZL9Dv!SF!YbBhQ{)6=7wfd?qmpFt)(~lRR+fuTEV+l{DW*8YxD|-?D|XRE9-afL7Q7^XDWa9DDWEpDH#tTn>Zq4wCf47eqvG zLZmmodPHJ&Hb@2|n!@TG3^)L+X=tNO$F6aZk&%~2hsTEv!}W6U*tMSjzYCBDVNf$# z4oBhEtuETCArgXw&Z3nX@p3wK3B20j6eK7#gojJtMo-L%)2BxRl{04o-TJ(fzR%CO zPF=T-on;AZ?sO7j`}YGf_z6&wzjZ6YKAtdohljvQmn0{H^9T=YB=3=!pWh$XE;?F; z0zW^4)yi*v$T5<3ASNXX&CiHz{?^DFp@UEIvN)xm*#PXQq%% ztcR6HPgx!EgCm3uRW*e_s}-R_+mrbj3h&4Bt)@7-wi3J6`NWib8v=MIpqN?8o{9gaR!GZq+A=5_2 literal 0 HcmV?d00001 diff --git a/www/gettags.sh b/www/gettags.sh new file mode 100755 index 0000000..e61c95b --- /dev/null +++ b/www/gettags.sh @@ -0,0 +1,57 @@ +#!/bin/bash + +unset CDPATH +PATH=/net/corpora/nlnieuws/bin:/net/aps/bin:$PATH +export TZ=Europe/Amsterdam + +item=tag +if [ "$1" = "cat" ] +then + item=cat + shift +fi + +if [ "$1" = "" ] +then + ds=`ISOWeek -7` +else + case "$1" in + 2[0-9][0-9][0-9]-[0-5][0-9]) + ds=$1 + ;; + *) + echo INVALID + exit 1 + ;; + esac +fi + +w=4 + +cd /net/corpora/nlnieuws + +collect() { + declare -gA counts + declare -i val + count="$1" + shift + word="$*" + val=${counts["$word"]} + counts["$word"]=$(( $val + $count )) +} + +for file in $( find . -name $ds-$w.$item.txt -or $( week2files $ds $w | sed -e "s/data.dz/$item.txt/g" ) ) +do + IFS=$'\n' + for line in $(cat $file) + do + IFS=' '$'\t'$'\n' + collect $line + done +done + +for i in "${!counts[@]}" +do + printf "%8d\t%s\n" ${counts[$i]} "$i" + #echo -e "${counts[$i]}\t$i" +done | sort -f -k 2 | sort -n -r -k 1,1 -s diff --git a/www/index.html b/www/index.html new file mode 100644 index 0000000..9884a02 --- /dev/null +++ b/www/index.html @@ -0,0 +1,698 @@ + + + + 2026 week 13 + + + + + + +
+

2026 week 13

+
+
+
+

nieuwe namen

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Antonelli
Jill Helena
Coldeweijer
Sef
Ten Damme
PFAS
Meloni
Bouchez
Tata Steel
Kampschreur
Kempi
Keuken
Larijani
Redzepi
Jansa
Sabalenka
Kharg
Mathieu van der Poel
Ronnie Flex
Theo Francken
+
+
+

nieuwe woorden

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Houthi's
energiecentrales
interlandperiode
energiefaciliteiten
energiecontract
pensioenhervorming
fatbike
gasinstallaties
maximumprijs
nepagenten
repatriëringsvluchten
schademeldingen
werkcultuur
ex-partner
Israëlisch-Amerikaanse
megawattuur
energiekosten
plofkraken
reboot
steunbewijs
+
+
+

personen

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Trump
Donald Trump
Verstappen
Ali B
Mette-Marit
Jetten
Orbán
Epstein
Høiby
Zelensky
Máxima
Khamenei
Ali Khamenei
Willem-Alexander
Van der Poel
Klaver
Koeman
Cruijff
Max Verstappen
Poetin
+
+
+

locaties

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Iran
Nederland
VS
Israël
Midden-Oosten
Amsterdam
Oekraïne
Verenigde Staten
Rusland
Europa
België
China
Straat van Hormuz
Brussel
Rotterdam
Libanon
Den Haag
Frankrijk
Teheran
Duitsland
+
+
+

organisaties

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ANP
Openbaar Ministerie
Ajax
EU
PSV
defensie
Hezbollah
Feyenoord
D66
VVD
Instagram
NU.nl
Tweede Kamer
CDA
Oranje
AI
AZ
kamer
justitie
NEC
+
+
+

andere namen

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Eredivisie
Oscar
X
Champions League
VRT NWS
Formule 1
Grand Prix
Premier League
Instagram
The New York Times
Facebook
X.
Spelen
WhatsApp
Paralympische Spelen
Olympische Spelen
Tweede Wereldoorlog
Parijs-Nice
NRC
De Telegraaf
+
+ +
+

cats

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Buitenland
Binnenland
system:vrtnieuws/brands/radio-2
Regionaal nieuws
Economie
Politiek
Cultuur & Media
system:vrtnieuws/brands/radio-1
Tech
Koningshuis
Opmerkelijk
system:vrtnieuws/brands/sporza
Voetbal
Atletiek
Handbal
Nieuws
Sport algemeen
system:vrtnieuws/brands/stubru
Tennis
 
+
+
+

tags

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Entertainment
Buitenland
Zakelijk
Landelijk
voetbal
Politiek
Sport
Voetbal
Koningshuis
economie
binnenland
Justitie
buitenland
Binnenland
achterklap
Iran
Artikelen
tweakers
muziek
Midden-Oosten
+
+
+ + diff --git a/www/locaties-2026-13-4.table b/www/locaties-2026-13-4.table new file mode 100644 index 0000000..cbe52f9 --- /dev/null +++ b/www/locaties-2026-13-4.table @@ -0,0 +1,25 @@ +
locaties + + + + + + + + + + + + + + + + + + + + + +
Iran
Nederland
VS
Israël
Midden-Oosten
Amsterdam
Oekraïne
Verenigde Staten
Rusland
Europa
België
China
Straat van Hormuz
Brussel
Rotterdam
Libanon
Den Haag
Frankrijk
Teheran
Duitsland
+
diff --git a/www/nieuw-namen-2026-13-4.t20.table b/www/nieuw-namen-2026-13-4.t20.table new file mode 100644 index 0000000..ab1c628 --- /dev/null +++ b/www/nieuw-namen-2026-13-4.t20.table @@ -0,0 +1,25 @@ +
nieuwe namen + + + + + + + + + + + + + + + + + + + + + +
Antonelli
Jill Helena
Coldeweijer
Sef
Ten Damme
PFAS
Meloni
Bouchez
Tata Steel
Kampschreur
Kempi
Keuken
Larijani
Redzepi
Jansa
Sabalenka
Kharg
Mathieu van der Poel
Ronnie Flex
Theo Francken
+
diff --git a/www/nieuw-woorden-2026-13-4.t20.table b/www/nieuw-woorden-2026-13-4.t20.table new file mode 100644 index 0000000..eb6952f --- /dev/null +++ b/www/nieuw-woorden-2026-13-4.t20.table @@ -0,0 +1,25 @@ +
nieuwe woorden + + + + + + + + + + + + + + + + + + + + + +
Houthi's
energiecentrales
interlandperiode
energiefaciliteiten
energiecontract
pensioenhervorming
fatbike
gasinstallaties
maximumprijs
nepagenten
repatriëringsvluchten
schademeldingen
werkcultuur
ex-partner
Israëlisch-Amerikaanse
megawattuur
energiekosten
plofkraken
reboot
steunbewijs
+
diff --git a/www/organisaties-2026-13-4.table b/www/organisaties-2026-13-4.table new file mode 100644 index 0000000..b01d98c --- /dev/null +++ b/www/organisaties-2026-13-4.table @@ -0,0 +1,25 @@ +
organisaties + + + + + + + + + + + + + + + + + + + + + +
ANP
Openbaar Ministerie
Ajax
EU
PSV
defensie
Hezbollah
Feyenoord
D66
VVD
Instagram
NU.nl
Tweede Kamer
CDA
Oranje
AI
AZ
kamer
justitie
NEC
+
diff --git a/www/overige-namen-2026-13-4.table b/www/overige-namen-2026-13-4.table new file mode 100644 index 0000000..eb10b87 --- /dev/null +++ b/www/overige-namen-2026-13-4.table @@ -0,0 +1,25 @@ +
andere namen + + + + + + + + + + + + + + + + + + + + + +
Eredivisie
Oscar
X
Champions League
VRT NWS
Formule 1
Grand Prix
Premier League
Instagram
The New York Times
Facebook
X.
Spelen
WhatsApp
Paralympische Spelen
Olympische Spelen
Tweede Wereldoorlog
Parijs-Nice
NRC
De Telegraaf
+
diff --git a/www/personen-2026-13-4.table b/www/personen-2026-13-4.table new file mode 100644 index 0000000..a5359e2 --- /dev/null +++ b/www/personen-2026-13-4.table @@ -0,0 +1,25 @@ +
personen + + + + + + + + + + + + + + + + + + + + + +
Trump
Donald Trump
Verstappen
Ali B
Mette-Marit
Jetten
Orbán
Epstein
Høiby
Zelensky
Máxima
Khamenei
Ali Khamenei
Willem-Alexander
Van der Poel
Klaver
Koeman
Cruijff
Max Verstappen
Poetin
+
diff --git a/www/style.css b/www/style.css new file mode 100644 index 0000000..6aa26e3 --- /dev/null +++ b/www/style.css @@ -0,0 +1,106 @@ +/* */ + +* { + box-sizing: border-box; + -webkit-box-sizing: border-box; + -moz-box-sizing: border-box; +} + +html { + font-family: 'IBM Plex Serif', serif; + font-size: 18px; +} + +body { + border: 0px; + margin: 0px; + padding: 0px; + color: black; + background-color: #fcfffc; +} + +.main { + margin: 4em 0px 8em 0px; + padding: 0.4em 0.2em; + + column-count: 4; + column-width: 22em; + + -webkit-column-gap: 0px; + -moz-column-gap: 0px; + column-gap: 0px; + + column-rule: 1px solid lightgrey; +} + +.main > div { + -webkit-column-break-inside: avoid; + -moz-column-break-inside: avoid; + -o-column-break-inside: avoid; + -ms-column-break-inside: avoid; + column-break-inside: avoid; + page-break-inside: avoid; + + /* zo moet het */ + break-inside: avoid; + + padding: 0px 1em; + margin: 0px 0.2em 4em 0.2em; + overflow-x: hidden; +} + +.footer { + text-align: center; + font-size: small; + margin-bottom: 2em; +} + +h1 { + margin-top: 4em; + text-align: center; +} + +h1, +h2 { + color: #62757f; + letter-spacing: 0.1em; + margin-top: 2em; +} +h1 { + font-size: xx-large; + font-weight: 200; +} +h2 { + margin-top: 0px; + font-size: large; + font-weight: 400; +} + +a { + text-decoration: none; + color: #0000ee; +} + +a:hover { + text-decoration: underline; +} + +table { + border-collapse: collapse; + border-spacing: 2em; +} + +td { + padding: 0.2em 0.5em 0.2em 0px; + vertical-align: center; + white-space: nowrap; +} + +tr > td:first-child { + width: 100px; +} +td > div { + height: 10px; + margin-top: auto; + background-color: #62757f; +} diff --git a/www/tags b/www/tags new file mode 100644 index 0000000..e420fe4 --- /dev/null +++ b/www/tags @@ -0,0 +1 @@ +INVALID diff --git a/www/tags.table b/www/tags.table new file mode 100644 index 0000000..36afe02 --- /dev/null +++ b/www/tags.table @@ -0,0 +1,25 @@ +
+

tags

+ + + + + + + + + + + + + + + + + + + + + +
Entertainment
Buitenland
Zakelijk
Landelijk
voetbal
Politiek
Sport
Voetbal
Koningshuis
economie
binnenland
Justitie
buitenland
Binnenland
achterklap
Iran
Artikelen
tweakers
muziek
Midden-Oosten
+
diff --git a/www/top2html.py b/www/top2html.py new file mode 100755 index 0000000..3b61044 --- /dev/null +++ b/www/top2html.py @@ -0,0 +1,43 @@ +#!/usr/bin/env python3 + +import html, sys + +titles = { + 'nieuw-namen': 'nieuwe namen', + 'nieuw-woorden': 'nieuwe woorden', + 'locaties':'locaties', + 'personen':'personen', + 'organisaties':'organisaties', + 'overige-namen':'andere namen', + 'nieuw-adjww':'nieuwe adjectieven, deelwoorden en werkwoorden' +} + +title = sys.argv[1] +for key, value in titles.items(): + if sys.argv[1].find(key) >= 0: + title = value + break + +sys.stdout.buffer.write('''
+

{}

+ +'''.format(html.escape(title)).encode('utf-8')) + +with open(sys.argv[1], 'rt', encoding='utf-8') as fp: + lineno = 0 + mx = 0 + for line in fp: + line = line.strip() + aa = line.split('\t') + for i in range(1, len(aa)): + aa[i] = html.escape(aa[i]) + v = int(aa[0]) + if lineno == 0: + mx = v + p = 100 / mx * v + sys.stdout.buffer.write('\n'.format(p, '
{}
'.join(aa[1:])).encode('utf-8')) + lineno += 1 + if lineno == 20: + break + +sys.stdout.buffer.write(b'
\n
\n')