From 7d2134ade0cc36e32b763bf498c9ed17d190bdb6 Mon Sep 17 00:00:00 2001 From: Even Rouault Date: Wed, 8 May 2024 18:26:30 +0200 Subject: [PATCH 1/3] Add arrow_issue_41321.parquet --- bad_data/README.md | 2 ++ bad_data/arrow_issue_41321.parquet | Bin 0 -> 72995 bytes 2 files changed, 2 insertions(+) create mode 100644 bad_data/arrow_issue_41321.parquet diff --git a/bad_data/README.md b/bad_data/README.md index 472865b..372e66d 100644 --- a/bad_data/README.md +++ b/bad_data/README.md @@ -22,3 +22,5 @@ These are files used for reproducing various bugs that have been reported. * PARQUET-1481.parquet: tests a case where a schema Thrift value has been corrupted +* arrow_issue_41321.parquet: test case of https://github.com/apache/arrow/issues/41321 + where decoded rep / def levels is less than num_values in page_header. diff --git a/bad_data/arrow_issue_41321.parquet b/bad_data/arrow_issue_41321.parquet new file mode 100644 index 0000000000000000000000000000000000000000..b78c544151b40f9b5527cbea5348dd3ca4f46f53 GIT binary patch literal 72995 zcmeHwdz@59nP{KsW-`Gs4>r^3xTwfVnN2Xvn;AEIozva(f_XFVJaAqNGt2{-Cv$aw z7$ZS~hy)|Dh=>u9#I6n)%mK*tjS38q}`Hs%j~pd_>r8JJUw6-0mI`@x|@D`Jf0-@@AVp_ zaeA8Pu34Vsy8<`0_V@R6wDhHU{K@_*e-%l&-&X4`C=36vYMKv!mcfT_8k||!d=wjp zpX~9FjY-qflJ3g!AqHRHP*0Bq{$+z4HU54!K=J`dgd`x}mUdeiUIxep2L-pMrA3-WyM0JUz=tK^;QV-#$ThFTIAy4-Z!nLdTw(ZE7-WZ+TuYj6t9@4tBCfx|4m%M6 zA6^gm@IHuEIg21@OR^-$XVJ6K@NYE8-YI0|l<83b#i9+_zx{nw1r7n>b&Y@yrbv2{ zQ9v2Fii9rQL=N6WC8Si3Ma9`~yz$1R7v6ZoDIvTX@Zo)wkUWc!(7CCSqA8LfCZa1h zlVdl7h-6(GBrS0>(q^bO1n4}*u}%Mg-wq;E#GOD2wr>#37(!~t30_KM;z4q@M^$^_fatNEP~n{w?&GW z6U#*W^sQvwtsr7q*9J*ToKD2A442%g5pgbxli!n)h#>I7G@Cecv#B_@8vd;YSvidy zyB)1k2PPJEp7d$`KZ7>v34HQ9ufVrMgel@qAVrh~0cfsrivN7=`n4o-JWW!JR?7)y z`agUJS$PNOKW@lcCRF`<4t>z$nNi>%-iKE~cW|F-%{q$^?~cIqv=nZwH!bSvZyAiV zfIG>$JJABH+BR5P@)QdIWN=&s67ldk$xIPbp00DSfTHD$Yo?X(p(7Nzm0B=eXUwr5Ev{c~-1_qaP z^>r%lblp42i_@t)#2xv|@3~uZl}jnvFp@oF$4uE+ZX4|C?HCwr>0P?8cVJ;>?;w@ee#5`tAe-Mq zF3kXq#*IWPPnD0~mALW2?*KCXi}K;P8o|f@S(1-C?R+d;+A}n;kaYu$on7xGE8dIj zIH0=Vip9=`mdvSowTL@`6!8mDh~M&R1UskhmhAkkgPq>4KHw)kGb2aQ(6RTCE$;)C zoRD4c#bU|xted5YJJ76o8AKs|%c~JAUAtGZbh~6}U}0bX!oe|xkxTcGBln>5;IQQ{ z7c8+Dx!m-pKXm-l6kU_ycfb(%FGL}J%c~KLteqnnnI;(ljo3MPs-@NR%U=m7i5nI+vM?|VJu>|9CY&78|Bx!DVc7~yOb z^-Mlloe$>VgyRBT%Sd`!dKo@Bg1C=<{m$oGfkLDK4?(O$^eLibAVri#3v^xuAXp&T zpsKj?k4}#I7)PfK|7nA~azEL8KXBv(n3hj$!wLK_6~upB$H$TPgj zWJ}0K9UlU+7PvP^RtAAOS=k0kOI>POYFQc^=uq_etwUS4WX z*TCRH9^mugiLYz0qnDa)*dHdxD(?pX(c*j4)27Rg$%)KEE>v5sG;bDfhRXrW?>EdqS#FVgNOtdd7kZ5nFXfeX3!Mc6{xl)rTtVil3*0)*AX5?z{UauwR zY7>R`TMZH~6EcmKY0zG*CnxI@g?3w$)vM)6cC#`ycwcNJhZ+-wcl`qzcC~1qYbJY| z6NPrgLppYIvo-79eBv{|LuYT8sWe8N$R34M2juycKP8)m>T zBm1PcdyFIxdAi#g$Z%)Ef>k#1KH~ofIp0MNbxpT`Y5R+}LdwY=Ny_b1%WCvYL(sJ) z@+Av>4ZU_53ffIzrCDJuXoimNo3cDr87>m z6YK2jQ~i4k_#;P`l571q9#r9LHTfpU4k$qVktq06Q3MNn2PF%4*jaFl8&Y8&2d8rO z4Uh}VpovKN*ia>k8=H`H9PAsB9Qf@Vu(`YlvlUu6IZRd#|CMOr;F#pWVMxyLj8Mbj z<>bofxYh8Xv=5b`mBX{YIM8F^!Jcqr41hj|!gbU$9`-g8ND+4+QpgXm1kF{riNI~` z=bvQnu2r3FV3X?Km;`@h-ABoWk3hsAZsdtF$0!!B2Z zni=ovRR&r67${f6vrF62O5*OcyUWt1s?E5-<0*juE8zdu0%)r5O?$8G&afNXT0lFq z74%`>IrVh* zd`8yUL^Xp=(MfK9!XU@j(NCO@yUOa%@h>)5Lip#|hX#JwRyb6^O zSaK4LCa?dTY;||10_8((g9{gRb@a3wEi`t+V#<#`X^{P&MRhmOk&W1 z(M3FNVqYGvV9(9`d@BEj*))2j^6$6vZ;}r)r~Xsb>jKv z(k|#!cS&ETB5*;gRiT43>b13;Nq0I;;Y__6$=Pr7l5j20p>M?ItWDwUDF_2x{kr5# zMIbp-uj;1;-j(())r*g!g)YYrSk=K)mm0O;A0`*RZLp}11R5FjNsx42->*pL zW|R(%?YPQj8!Xy-1bqm=0}Pw zwX`YHWOjM&h(S&qnN+*nc~p@gZ9Fv8<|@FG&l+Uovk4Gj6pPUa^Xf50m^v~QSu)GK z{$qoj{P7L5%+o(ne+YLG{NO8fJ85l^IVIP-Hw1HxpY zC}8E!;X&wRECr}ja~pC-bUhZteBchVZxFb0rW5q8QyR-w$yDUbEPL-S;Kheupk=$_ znMk>={gonD%QAAaT`hax3kJFN%UFU{ExTYt&6h#4C|o@3mJPl)#ly=;+lGP;D?b14 zIxALbRiwMy@b5OrWmt{3|1?mmM>3I;J$y!ytgu*>SljsX!b=9(^U`<(d-mJ)_rYsv zZi1D<1n0raqRSBF|DAv90zhDUbN-Wu`ZUaOm-!)2c%9ux|QmmjPybpw} zoF3{`xZrRl*Ioq%L|9zPTxCF!IkWF`zca}8-_ah?fx`v!MC#y?ONtI|!O^l@z2a)( zJOA4tmoCOqgKFY(;ilch<-$!gaqCPc?$fUUt$bZ+o-3`2#F>?!{ewZi^#^L@7I{$f?E6iODsAalD&Kl?BE(u zY6m}&K4IqycoSbly>3IFpssatmFmei;4$!xNtf!%kH<%?L$+HVNg`)I2Cw)}rfkoB zLZS9nDqCD{9m8N(eBakh*r*(F-WV6<8rk2%t$p(oN#w=#z=a*P*4pn$yGP7YVB1^N z-;ZCdEz8&!&Q(Or4CcagGZYGVp$P9__-k3~J|~$7_}aVL*o)Haosol2CXuV31)|jI zT7ufs+C?ZS4G_@T2>4bH7(z$hDByQ-Y;DgglBPni3I-xB^XeYFO-I=DeZRe%6oyhd zJNkP&2KftAY`M^;&nJ;hkTM1)S|Y&3#G+xG=cK_zHP(a-zGkLo!0{QN+08(dGY5{3 z=D=CAIVt*DTThz$x(dy?1EULyk+TkFNuJsQIP7U~7=}w>I6laPgUN7?eJP1-`BDVQcN#CrH~}^;RrdcdJ0VB%S=uRgjjOA4RY_ysBjVz@Zr^f5AP#y@+^X=m0wke zvQpv*L2cR&oxxX7P_nuWn3g`}8QOUG#9owx!6Ud1eWr*zFn`a>0t(I52)eI)4d`}e z#qsf_)E9Onk=;9ha19(6=vqb;je9V`4uoMH4Dg^S-bdN65GpOLYX5~@HbK)@UxlDw z{g)(i=wDFKvbqhJmOfR```dq2h=Shw@9%jCzU_48qEPug5DPCIA=Is3w+ofN0qcXr zIG7vf>D|!D?xq&1gA|KE56{cvIq~~-_h|@(SRlUxzj#^HmGf!@(X00=L|f@`gdtqt zlSB^hK|^qYaRIL7Lp21?x&n`9Pk~*)7;)P}BW~+(X_|5tLGOic0lk_GIl>gKe=~`k z{3bO8H*i`C6;l9wa7-(pUmm}cQXZl5TX8E`mVuI{hk6w*NC$T2J3zT6Nsf^9$$ctmgKZBOZ4nf1I{*|qbL9B^qyABH`nySF=Xa_3 zvYH7-zWHedxjj7&BjNe)C6TAT7mEaHYx?9kqBn*V96W7~{DmTRUX}9kdC0kgK%(%P zy6iYUNR5NpaZY_7Wc7Vir4ynH9<4N0R(NI_yCMNayg6$uV+2;N{;R@Dlmt0~qgM}s zhdo3&iWglhjznS_Cr9FrOkRURb6$;5&gLH}9L30yBe+_3B#FHIL*&W{+y!MUu0)m^ zCs*PQ_|kZ?#ZKos=slLQUX4_8t~zL0Ii(KwgQhFmwyJti{~6QUykTSSN#k|(*VmmTXjxd~OUWDkyi{m$(l(ZD_HZ{@km<#`|=YPKAof2n^dIq)AKi2qsw6P^%bMg*jq}F@zgHy?d-vb?dm9~2hom>34KzrY-R;Wk9YVQ4Uk0Va;!i%Or7KPh(64sjlH+{{C@*|VnwuD)*TVXzIYKH z9xj5dMFQ5Ua-6gV6iWS(;B7KxbRT(5q1z>G&n^57%V+)o-M}AE(NY>V9Eo7TCKWB& zd;dovTPDJ><^2)ze(rJ-S#|lZLf%hZRS36I%Q)y}ue5IeV-h)cW&8qHUTLMh3fQg~ zgt)ynX1Do3ig=++85hCI9p_a59?@2rU0wb&@F^CvN(I^8Jii6rVa3;2PrVL~&pZNI`kjihy>EPr|C|AT zQqR3fkuXS743nRw_(dtLC$S=tb&0yy`;8d&wR5*3f-^IthN_*k5%xmRMrX$54u=ffteio<}E3B+nSs@*K#1fhm|7HXJ z$okKE$;l1i(jQxghyXCp5(8#QxCu? zO!B_$A#1(>M2fMsBjt%R;Z+K6K|42l$;E#Lfkk4_Dt8qQB(X^4EQ5^VH2iPUjaq=NQvAma_#^wj?j zO}@C-OIGYns7-o2hYCENv+&;oBk$X+9GRjA!Xfc(bmV=g0L)%F)2VOAcYrZ5?soK< zx*@o5EW7u4$!p(6t8~Q|ONT%Z9DxG*<(baEXYlWtIP|tT7FKemHS`W3i+l{MUWIbp zu>i0Xc-tR3-s=Z|RWb0^v+AP7m%r;JtG|#v@sFxlh z<^ojGm7CU+L;O=hOesFPl6KR-$`)lyK!Z7`#AMCdLol5E0g7JWS0Xt2nXOn1F?Rd~ z?E4*PWj2Py9ieZ(VrB2JY>z@fD`N~jeMFj@hDI(j4E!*UVSo&RwZ>M#qHpl;od!A_1c>QrD_>XaDHEr1RW zn180nZT$Oo{tZKZdVomjGn;rLB9J2P1X2VHRG;%IRHv@UkDpV0ETH)0Po(unO))jq zzbXm-$m{>+C2Ri;&Blqr1+SKMrD2Ofm!m-2 z{lGad*#dR+;vFyc*I!mR*JMVD(CogKy<`(qNDS&r=M}~^sBL`jI`1Xxph{wpUwB2~ z+sgK#$*{zPzWo(1Sq)VZgZ$+S3g=qnHr}^hfL;kIB?kSuR~6nxLJL>cx4a6GeyEWc z+@~)ptm|;wIDhh@m%RS_L}5R5N#WcQyqc9J!rs?kg4u!pP89MJuK{uqLDC|(@xJCY zFS+!GM4>-^S>ats-j(&$mm#eCe-nlKnJXHttGI2PKXS!O&i_xMuphpvaBc}+&2SN+ z_3MB1l5>Ad6!NEE*J)ivZsYyxpCADBr$nJYa82P|XkEn~!TOayd&%iPCkpr8>k8{S z+&0cH{skVE{*ox{yI1&Z!xp!!H_XLfc*9GMzYzobO*HZhJ$$S|)6Pc#y9i*(v?@_- z{`|*$LD2kakD6!z^a0lSE4N$yqbHr=25gpWM)iG<-_rEu?> zWhKJ&&pieNJeDW|cB}>h#7wj+0X7-D{7D}<`pHC*uzQV*3?lNNM9AR6<34iy@k9}@ zXRV72A_%a_;MGt0$caxSiiCaZ6d6#@@A3vea{;e?+DA@(I#I~?tdE7<&iiM8_s=8> z{q7A4`q&vzxD$K=EZ~Vmk?^f2<0HW)hfAOJk>@{~C?XDSRETg-{}Is;UjLkrocUa$ zC^)=HQZT**BupvSKkp;wKA$LR&TN*{#G6-y(XnZ>k6i!fMA30^i=^YtqzYj)?cCxc zYXMSXo=%?plB8)|89*2@C%5{@zO9KOX3v);F>gAl2P5p&ZQxn9xf2#g5|4#xzM-C;o~Hp3 zJ!PpbX8Fr@{S6Jmvoe^4d)B+~8crF|YdqP*tN>iS4a4=UI$fhNYX)AVMSXyR7R}0( zCGfX(BR6~2bSPdxVc=EvzPl$a1!?7@Y){%$>nu0hla`8LS?@c`Q#KvZ3A=A*0i!Uw@=54P!&tKy>9C$80{@qM`7p7p;%;^idgf`<*Ylf%xp=VQbxSW7*Pfl zX}vKx>z1;QSghe4`J!ILE#z9h2RG|Btfk--xB3Qp;Ku!o7zD@P-I|qJ)`P;cE`cKX zC8{0v)>4FC#3g)7BPrnA2OG1_q`)2J&6-(LVdds6vmeAy#1>fq#(uT}IcNmRe$B8? zd2$&NpW_SAsbUD}(pEtCaP~lP<;@RmVdRe%mW={x$@eZ|RI*wPRFaG8Gjd~8vznDf zA#GVPYFX_r0vTlG&`AOHZ<7Mxa4Bp_0YxVHfVbqLf|gBNe;R%CQoN&Sq%qSymF!RlHg*O5$#Hc*`=N( zJT!kTLKn-n5Jt2%9p+d75VONjco(cySVSAt*L1-d(HtGzvaVf=Qqw9TR&=CIWgR+f za7PCXMk{hvr@8TP->Q^|~?jA~B+A1DRg*gDxmF2bOpP|+mggn*{TAVf4&YuXGr8b2hp z$y#x7+Dyj}OYQzdtoKcVQk$_w7HxuYl7;%WiCgrOaYB&dMuk~K(3TM=2uValBNwuH zbD%5}lubNNa958Equ09>>#NmsQhjfCF(kDuqIaD}a6od8D4henl zntj)`F48C#m{?ENu*fEvX247luiU`iXRwu-M_pDzAXTSWsllGYt!ghrbi;5awIn$E zCKAM0IVqEQPD*$&;2OLy4X>MFyn&~WbcO}UmShP;B#}(!NhJ49AuFfg>uYcXe6R<` z8-9F!%{tR8!664zBs`e`Qc!i_CUWp5O4aS}i$>MCsS=8nvQdzA;D;3xaO)3!H$46CuzlLR0-Tk*4;@L z&d(^o<@2y*2TH&r&U7H3{99|HkAvhQU|L)K4s!f1q?#Ub%^mDeVQt;4Ue%#^@txK@ zu81H}qFG|sb?+oEPN(MD(%RM@fCkIn9>t&m1}y+FIs0x2AtKm3+P9GRja<7|qIE{!6l9m~AxG{(V|w$6*~r>C5}6XC8yZ;H*S~NOvQqu9`rW*Ve?{a-||cc^Xyy+Q${5z&~1hvHW+>_mmJImpodN%P;72MuyUpYdh!EO zEFx$*G(dqexA9CqS)C8kI5hgoOXxY21<~L(oL6;7uKc4D2~D__>}UIkzj8m>d_N#L z`t>`XZ-u4LffS@34-~ocst(Dy0x2GuAuAaKgR;5&L2~GWARAm)EptW7GabY&Asa;Q zPnin$2Fc1GK*YWeT{M%nJkvqkS17$-vXz-CnP#TC5GIGiICtTmmx}Bxmi6t)r5Kbm zMPy%53@E!wtpyR9I5O4!uz#4GDIxnxC@2_yp*}S3{PcVYN(nqGmVR*_IXn-tHf9{FCxkv@e)+BKkN^aW0m*kCP$1nFH~E$ zkf#K_ZFO7yt>md{vZ@+(OVBa)!U73J2EjEz)-NDeYFvOEsgpotFxmEIa}hs^ zvf?2fF}7Fs7%>MPBwHSI0dwhL3C5C)7Rt_t$=Ziqpq%-THNxZe#sdW!b#H{F`U_p) zoM^R%bt)V!J*!*E#TFMhD?6-4l@}3z&&bTPk;FE-TGLL>wvDrmUFmc|0?k*8qoFK5#j3BQqA*Yr^ z1^IlR|(93qw(q-cq&g8 zc>ZzN@cnVRX`N?l0c{N{*fYC0(+T$YI>0AZ=j!n}_+?qU_Iw(oyB7In#&d`D*0Bfi zYOd<=Uw;Ddix6aX3!tq3*XysAUH@v9Q8O#}E^uh78i?FKpc6+|Xb zNX17sRH1ksvKMwrWNvSwqLHQYcWe)S4W5s8yj3Gxvm3C+@&0QnfB*H;E@-5?q_xTT z8dzJhXr$^@9j}MJ5gRMMn<}tA1s(s@uS=}bnqgND3#)onhxOpM0IP5fQQtL9@vk@F zkDULeL3Vu;tP=wEV*z7S2lePafEwQ`r71MI?S*d}Y+Pi(YqdBJU_?BZy}nPawSheT80Y z%GjOU?*q9{M<@50LkhVXkP5YIVE^0?z$yIz>_edygsYtCG`IbS3gy-`tma)sA?o9Y z4YJ{IblT7SNTFQ|RH2^9`q~jl%XuUoS?@fmP%I{UqY!-ZS=e#(+2{mcJ*E(>gQ?KV zq<#Iz208iT@k;yjPZZiM!Km*n*$n%UpTJ1#x#+~7J^?_*Fis0pq5hQNKV^_ZKQ$l; z1N9|*zb?gFW8whERh{je`MJW4kXjUGR{k9Nxs%bE*>y^z2^FTo3)95jUl?TNFHjR~ zPc3YzX!r6=NBi1eDYRQcQ{SJmX=2|C2D$dj=)|A@cbz6wpbGW74gYS4V4j9y(rEyT zQZLw0^JO4k>Ox2P;WG;5Lh33G8{rpTg01FXica{U-zbFZU@CMo3)+6xAQyg(79{#} z7_y%IcKv-YLkiN@T-EaOvcij8GNJ0*&dqOuo8Ly~X3}=KClj(cJ-J~!#*>NK=$%aF zuIyx@Hd7~)x$`-hhz-lh>Axrqj=DYeG$@BEN=s+{bsW2klZo3DoJ__J-ekfy-X@9L zBRh^Ao5=)kZB1^#F4SZ)HjgGNZ_qx^BoTWvlgZo<+5hyThCi94;P)L6eTG$EZ(--- zH?^a2qIM)EiQh$-Bx)C6G66gHlF8UrmrTG;xFpd#*OE!tRhCT1POxNBc4>w12dv2C z;UZ;iSlm0UlEmzmI>|el-k4oS$qm~Xbh3BvB$K_vCYkJAFehl|N-{yaO_E9436f0G zE{$aG1njIhAv+?Hx4y3-N!0FyB%!+uPT0Bz)y z8AoowZf#`ZH&Y`Mytf&d{B6a^WbFDyZp4OLWRiBsB9pYG6`6odsK|tE8#OT-K~4P5 zO=L2+S0WR?9}=0=O^e8l-8qO%>h?Zl^7h>!H+1tGGRZsC+~{p$$VBe!LMC(96*8GS zqL2yL$AnD4?jz*J?EFC{b61WVvqi>@*}ei6Zor%8F%}Ibd~1osZWWP;oghd8cXl8N z-Kl{jZs!G($ek2OB6mh0iQVadByi^flF*$9NFsL@Ac@^6fFv;UKS^jNf0D?|{3NlN z_DKRW=aYnH!Y2vMY)=xLsh%V>^E^p#CV8?w!I|Mn;xoOIL}zX%iOwvejqd)MY=I&W^)I7(+^mi+nHgF6w0L1z zS!vaR%F?i^j@+!dc^O%AXJ_W;-Itj&H#0LUCpYUMOG{=bR99n$njXl!Fa4p1W``C$ z(9zS=wRE7rtG%UXcIHE~&BjtxFDRcWv8QFQYjCK&W5(TOEvSy!ef`S@7i-G(_jQVb z{e4)lqh(<5q1km6rL_RBy`ytk2Wmh4zVwW_**RI6`I$Kx`T5ydKwRAdv$*hq1)<6+ zw4##!WnE+aeS4L`_MyZ=dG>%qhQYuq|cs_IeSJnd_DwMJNnxC z+q?QY(b5~{2WNitqaXDIQq7v0%7zcHeDQ%@9dqc>*<+e!HT=h8zG-Hg!A`TtG&{{u zC%qO7M%*94i-p$x5;M%s;gdq4AN|=?bLNDwq)E$T8M8UFe%LImgWtiqrG3pkZG9C> zTQjq}D!a_C@=*3@S-06$7BaiqO6DzXZ75paQJ>%4nmL-$+Q7T+sp>M}yLh4rnCp?Qt1S@Q;(L&1{fhWsVXjWtV~mIrG)8Y|M98`3+=YnNnKgn~V- zeHA^e4N$Irq^qnjqo}rSUQu1oU|VTV`*2(D=#tXH_MX&x;ek*#};r+KcN4OT&dZmEr2n`GsxS6=UT~f!FpoL3>Gg zZDGb+z&%>g-S!svF3hUvE`9T~cNdOTE?{!2sT(a{P#>(VP46kR+eAfoc~)h(aI9ka z$a2uxPTP!>j67d0)YuRtC5DYiAx1UA-QQop2mf!SYMTtsD4R-7~3)>qRH zxPlFZJ=A8=wuMexi}Qz?!G78sYI?w)%ApN`OiBlu8;Zu-i_!<`>vHDR7lA$Y*7P)I z&Fi6d8a9W@!yvzK-B@||lI0b(U=Ov`W91o8zP=(@lV0CimtIj-$J#+Dw1cG`z4=4! zK!0g*#c*q5aJaR%eyBYZ9B%G1$7({sG2SkQm@O480C^}joI~xidda-1hN6MN%35=v zthO+_JT#I6|3@ps!FJ$pUJcT@q`tZ?y}hlpYb3pVtTeN+KApAi-g(0vA!yr010&!U zmc##a{BB$@(pd_$K>J_P(vZ_v+TGs?ZLh4lYhM1M#&qyBLF$C&he}Pea%8b-hO$fH z%AydstwKCEoA5jr9aLF0c)3s^lr-z`JlF~6;r=1Xr{1JU5tan)9kV zpio;0lq$vZ%IbEgKT-nlI)i|_uoKSBYCO*lLZ!0mHn?9}0vGG?JlF~6;ih8vxgydtN;AT4&Lp59sRTo0}(qK7w_>l#0E3XjBFAst|iaKksJp3{jfulDo zJ1gO{Fbwx=OyFmp36;W4A*esk1bT}{ppOV;hk!od0Objy3)LZO*(Q=YQVjHsAnF0u zApq!LDRu)bCKN3-0Sl`Qh~c1s`m>-ff|DS2HgJH9-~>O|f$E|C2lxNON zD&Phh%CQpgPJu$9V6cY%1Vzz8@F{L__{HGkv)DCIKg9ze#5a`h?wm6R>;Q_>izT&- z=FGWwK+s#r-~)GpUX-MXiZoHDW^u;iwxayrmd3?B%|-cREsaZi8Z$?iLZ7e*{x3)S z1$m?+yaiRzX;Mh(Ajk-Mfixi$N-LU^+1!wm-qzdG(>4-bg7r%(!>oRd2|71TT8QyW zMG10(18)U0n;J$lnh{jVGUSiKuNC#H>nIXdp2-GlG9W$J7viZ|h2`_ZV_ZH(lylbf z=ucV*&BqKbYi?X(HevZ3AT+*odoQGRO|v-*Yglpb10p@;E9Z?*Rp!FU5f zg|l&dQ(jrZ^lFpVOJm>IcJ29$1Lir=&3XB55Vfi(5vPOd7~tnO zWe+p|!P_Hke~dqhN+M3#bz%KHqzC;) zVI3`sK3mu~B^|3O?XQf|UzpG6H)HZ!QH$`)vq32ci1VxHlVYX*gO1-BzY3qV-N0m% zz~^EQlu~N+c6$h8{rmxepVLe6F?q|Xvb_Y`uzX%sEB9~AzcBdJo@pies8BrE(@`BV zvHVaa_lGrwRNnJwDO#SQV*U+XdvLI+F}MiEN8K$A8H-!Pr5P0bkQMeIK!{6h}bA01o5^;r^^K0~b^hVqOw3L2Y9Xds{IE4F^ah%Y}q2T&tpT))uK z!U=vb*F+5#`)J<3ENO0lXDJwHmDiSnK!PJ!KUf8-qBQ9H6C4Qep^~jX33X!q%*tBs z-`c3qi?O`gf8tf8z4uoxgYt|tEZJ<~kEQQ0<+rS|k>TU|rv0s>|3X*A_1!x<+|*c| zSpfr)9Pm#=7Ct?{)Ri#*W#czkhxNM!{_66$_-z`3N+{n>v+iEzA7krxer*q!LL1^k zMxwS~YL9IE0Av2e?cws}W(C&I?-%%7+AlR#ZTmHAd%-^Qa=5=VVf+L~jP`3T$mRBE zme=O+_7t=Ks;`9ho;`;60EOu9DLzUcRW0+6v}v>czGtXC+(ZW$i?RM_cP_{0(tfGy z)B58eY3$)=;>~qaRtUsqy;B)a$)U|8$X^IH)He0in3esq43KgMqcwdGoLn_=kh@2wN~T=;eO z$6>6W-!JgT$8R`<csweZa0okfbOXNiRwrCW7=HI0j!^1doRZ~ zZhxGO^+&tmgW`|RKg}2A&0q+qHs@RTWAa;32|~&o6ZrV^69Q46?*tlu<^C>QLj|skw`u$Wg~msslr-A( zS{fm)&nPX#`c;+is6qWR8$UXpZ?J4JWwCND5RD|6#kGUHJ%lMxHtL{15hpX%U>E+X z7~=NO87dd_a(}^8gN4{ZS*KbEc0(=d9~k7aZh^0Y8hu#uLkkp+VBJn+_QME^Js-(I zeMtq(ztnfPV@#`|exRA+3se5*Sp2j8SkFI-HdHznng*>(DL4E1xzHcgm!dyPBvk+n zs+mn#z7C}rtv^Hr#WG%%Ey`nr5ROi9Ud`;C8a2~0bv2b(h!Mf$iMUE?L7w*x2zp)Y zla_BrE1ZY&pHm%IdBj&XhUL>mc|JbZ>lfjdw~jFVmYOA%+&=jDKreqZtx!L=Kk?*S z%Fly^%u1-eEAsD0(lEws7B?^LD6U`9m{kGu1NDnwo&)9_lsHORD>^+Yzb=a&HohuG zAWXjW7lp6rrvuB+4P$+{Usz4)cf<#g2(uACntOY)n;RgGn%R>Jv7CVxn5S#ZY#wOM zEK0BFt~N`CF&>JpB|IYdb9vsewdZhg9`gqwGdRZO`_|~eac`GJPp~bI`>XiqF_-7D z_7XHpyW^pU#!vO~kz(GtQ<|PqRgUa={V`BsDgMP?M~S9Muw=*>DH(=F#@oNue&Vz5`FY@qC_TY3 zKEDyQ{Zs#}r6&{H8x=RSe?bqle}E4x1YO4aw)Pet;N`(w5LT#M)Q{TU-0hpTH`>2d zEkpjOzaA6wPj1hbD0IbN&l|@0AkqWvpYs!y9&8Kx_SV%3YdK*4dI;Kox}c}BO2i*s z#*;RB=41IxF&|V|&iW53dn!-b^-xaPQzGxXG;;yL&U{c+ufShZjgoZ67i{>uuza2! zKNfO4Z_uW1?>mRE{v4}5f4))Zr=V=@xssM|;`1e9{G^OuDeG-mHB9Bt#=o{$c^%fT zt!m`{)+OGHKotGg4@0M<#Cs{5rQr+^0u&VTr=pYcSLdtP*da1@U4rv3_ofSef}@Dk z5udcRk6<1=q|ITVaeN(KBI@(!0lhpBGJhUuma$~4---2$#e9WZJeby(ZX z4mFAS7uFw}*`j{b_=D2kn7zY=a5zVq&xsR%IE46US2j<~$3*qFH0Z$XUG}x8w0Ves zj>Ug4uJKWb@|#yB;?bs0x z74!!_6t0LT!Bu2EI3nPMS$|@ON2A8J@mm-8 z#Ko}I6zYc?XnoY*d@&zXSWBG>RRZtd;Wk_E8Wdv+1qN_h1)<1%t9~J^@0gFG<9}JN zoR!D^4S)wj%!yM$vY!-bF@C~Y!}R7_oI49sey#bO>Q3ewX;J!<{-UUhYZkW`!*7AU<#vV!o!jpVCj6W>nGp^r?>4uZK0Zu#mARf2b`Z zf2cJhKfMFwdGD|#k7_<25)85SWw*Zt2$0GXVi--ZAhj{8ehlO~+?Z993%8cfVeKIV z&;Kygrt+B2?2nQrD;0LLpOYKH* zY8dH;Nqc*SnyI;l+K|2sQQvL7 z7^24bDz7(+<>y%P4@&G}W(bPzuuzuM_#>s?s9jLpm9 zBTgsE0lw)GG>gWdDN%cK8IRETfHjA0R*Ld`Wl5o;pN5rV_}T? zRK9Esfa9+aeHVi^;u45is`7U9FUWKd|Y4u77v`(GOB zEus7atR}1vB+&LtO(j#vvzm?Xm{HKCMDfu6r#L606&EwZu^h{fiuoMA9v7|yP*Ew! z#~0Y>dHcd&tp8W$qi7YSfBQ#IV8+sxWgi~u7<_-*(xvZjS+=ZyWCnjLY(@sW5q4iX Yr0t&W@%;b4Hzxs4^?Hw|%B;!we;~s?DF6Tf literal 0 HcmV?d00001 From 13fba3a3ead071c555d743a02484558fb865677d Mon Sep 17 00:00:00 2001 From: Even Rouault Date: Wed, 8 May 2024 18:33:54 +0200 Subject: [PATCH 2/3] Add arrow_issue_41317.parquet --- bad_data/README.md | 2 ++ bad_data/arrow_issue_41317.parquet | Bin 0 -> 72995 bytes 2 files changed, 2 insertions(+) create mode 100644 bad_data/arrow_issue_41317.parquet diff --git a/bad_data/README.md b/bad_data/README.md index 372e66d..7e94b89 100644 --- a/bad_data/README.md +++ b/bad_data/README.md @@ -24,3 +24,5 @@ These are files used for reproducing various bugs that have been reported. corrupted * arrow_issue_41321.parquet: test case of https://github.com/apache/arrow/issues/41321 where decoded rep / def levels is less than num_values in page_header. +* arrow_issue_41317.parquet: test case of https://github.com/apache/arrow/issues/41317 + where all columns have not the same size. diff --git a/bad_data/arrow_issue_41317.parquet b/bad_data/arrow_issue_41317.parquet new file mode 100644 index 0000000000000000000000000000000000000000..a51eec71c65af1c91951866db341c79d115d4f84 GIT binary patch literal 72995 zcmeHwdz@59nP{KsW-`Gs4>r^3xTwfVnN2Xvn;AEIozva(f_XFVJaBqu7-s01LFUO^ z-5+c_1E}oNZS3jT6aNN_=i<9eE72hK77;Q%*5uS z*bMlo9uL`=GCd>Zt~?)N@bwKvqbB&5HF8w@``G}=2Otp=hkRScZ54PKAZrFFxIHan z8uG(1 z(36S+%F34{bm1m)@FprDsd_vr&VJ*KH!i*K#v4uv;njc-@1umonMFe9rV5It2!fc1 zuG~zH-3%fUb#0K8#LdWVB7SAK>`sM<^HH3}Js}ATffuIP#F?K<#kp1UZ`H`k zY2?`LXq753@u>4;PV4^}v{6sslizs-z8xY=<97mSyetSnan(Zc@eDyRTCG7a)BoW+ z$jUoF{|Q4@G9l~VbLfK}&x|4m@jko?x`X>vYv!4S*d2lC8EJ;K-n1y%-!^EqfIG>$ zJJABn+BR59@+1oYWN=&s67ldk$xP#SKqmCKisUM;!cEc0p8VVC8B;A}Tco`D9pw03 zC}n#1iuf;A*h)4683FDqKmeY$NP7puvr9T3S{L36;7vi|i|?GCklE zzaxJ6J$Eav8d6Htv{Vn-F;g^_+XlOPI|l~adY3Nj9az}aJ4ofVU-R$R$maKuOEW;D z2_sR;Q|9A$Wo~>JcL163i}K;PYT;x5EWyW}c0Lv^jSdYgWZeK`XV-hliuWQr4yZ1; z;<2-#Eqkh3E&NU(jsHRv{I|GjVdvD{f}Ov0u+!V!2mEAaXXQy6I`%%Y<$b`C6S51w zcr1CIb+a_M0~UC5U~w8RgDCiKXzWH!3rpAT6)fE@SQ=Q^*S~OZOk(8HJ>|8iAdQ#7-rac>D$}l$O84Xkgk4a=^K%yt zF~Zp>>X|~ax)9943C9Jxl99}e%nE#R1aTkz`kl{5fI_4J4^FH@^l7|gAdQzr3v^xu zAXp$(qpG;_k4}#I7)Pfy|7nf9azEL8KXBv(m|y?s&lXlKX5f$p)+g%TCR{$X;ajO;6;R2V>%Qjn~}Gwsx4 zZ~Xr6L5{Xw(}#B;Gy?a~sfsg0BM`m<4}E&RAZuzzXM1;VTQn=1#eA5BT%1P^&jSk) z0BqnUn8GbpP71U0Sj@$+;YzZya-0-;GTxE#4iVtXhhQ6XMAWBwZ}yP2H9WRgkRI(G z7+h!s_mKavrKTJ9hsm+(`vE|#_}=u4>7rwDBJ+?7wPq_Vm`c&n*qaSm#2+C~ z)sj`U(-EI4?gmaw3MlctKb;-hdq(NYPo5^fez5?&{dUCEl zS$MzIB=9mJ(`cCj?ZrlNvN2g`x3!qPT7h6UCtHE{#b$D-IazquKcHY&iT1fxvZpm! zXjeR>VmCim!R~L9@lyqNPL{2OkH{DY+rt;wvj*oQcyDh@b_uZ}O0Zq5| zNpJUPDIW54k2#ProCyn7*~t5d|0CplH#yWj-2|rWFWw3%C!>Ot+o_i2=$V3`YfH$f zB{2yyy5)3`h&1o!vCg~QgTtzH?_K2iKC_FyQyNlHQdGTly8l7{gXC&2pPA!utvxq= z-btr}Tfk$EU~&A8W9=#MAIO`TF>`hXl%jOPpwEZbEyHiGL8sTd>X{U>>%+nsXV{5# z_VwxhJsSLxqf5!PejE?V@Rgc;6J!S@pnfX~PQ)BoznyMg#|bI|pno&tkS*3nz!k%Hh8fEgT#ZJU9%=IiBHaIJ}%( z86CG8K9upH3bb-~(BlVsEIil~j)(!!=TNwgdd9=vMgnR44xeVAkFAQUP#J;S+Rs0U z-d(9W+rTE>zcB^=$hwb`4IhDsLBhzBWsWf{Ud7+5AJby%)xjTYUYB56{;3t(jnphO zJcW3bTHOB$;L@1(El{e_Hhf9gDPA~rTz67@AgkhY^xfrgKK8I zt5<1c?PH)^1<&9`6<5_yg?DG%U6CwWw7_YXTG~g>Zky{oFaDQ*OhL2!6EVM+bg%;>RMpD~3j-EedFDaL?&zuRj5N z88foZCaM^0@=kL56B;?bo;FbiT}iYQO-9=AKpOBs@!|pGT0&|fC@vO1p!M_e;wn@| zV5uoIn!NsVqSf7<4wMhI4=!BP-5KrB+Gy;C#grd?QX~66i|TL!bU_o3GvoqBi$(Oy zlWu%ZLmRYl#!5^xZO~VQD4kc~ip1G7n}qGzIEzS}?f<++Ufn1REdex2&cHeF831Zj zNJ(cFN~<$F$IcTNmlrMvv`$X5muh487bLr~YNK82pj5Bb{A)FGcC$vdZl-p`0VP6J z7gE(lsp?Ww1(yR_mzAp1UyMN&G#psW$EaHKMU6bSg;8YyQc|@}%UGvXKr9x=OnlIR z(M3FNVqYFZ!JeCq^Qp!+%%;&J-S~dH@eMM*FXO)12$ek-rSUtWXF$7gUIhTCrzxl5 z+0o;f=JQRtExUdg@skr@7R{r~s*uH&QSdbX3n}nNcEDWN)vahwPCPEyl_HW{0B>=M z!K1CAa8Zg@iYT2|fitP0Z2YR=(biD9rG~N^LJ$YPf}A-4x}b^28Fy}+LnI0hP$hlV z=Z}tpAK}IjC9fy0LS+PE42yj!-i|5cg`I-GG8S88eoiQm`nq)gc@6%^!LPw|=8m`S z>uBVKO#mTN=<9$n%QG?W-NdpY@NKEwx5-zbI%5p2z&rg}y5eQcZs5%5UfnoDU&o(s zF71L&b(ipUG6EO0N)emHl zG6KPwd{sRNd{@T1WG_C77P=fiU{wcGT^bK(z(VJ-fHum>PeEh!-s7Qu{NT5Md_F#S zTW{M^J~49hlFsD|hufkLQr-STNvc!1Rc7V8%Jn!rn{7Cp1i9KwMS5x~r*{*_p+(@!Re=VVq)= z5JNHOcobKmveXSRPjLDK(9Z)}O8O;p9X5xNG4LUhtEioJ&wjh{K6ow7 zO|U|k;5>}7=rVYDaaASkL%)%Pts-BNHS-wT&uZktuhC;TF}UEJQ2DTxLL$IkWF`zthO}-_ah?fx`v!MC#y?OOg(5!O^lkrh*P4Lvp z&9e!OAw2UxE)s@yHm(xBco}HEJn0hNa@9q`7Frz=e(H}9wYhS`B)t01l7#8#gU#Hy zN_X$;K<}U8Ntez9uyHj;N=Gr?gFnXbhuvA{`|h4XZv>{$f=c`SOFTLqlD&Kl?BE(u zY6m}&K4IqycoUyTy>3IFAg^_DmFmei;4$!xNtf!%k0(a0L$+HVNg-!H2Cw)}rfkoB zLZbFoDqCD{9mil-eBakh*r)nTwW;PO677k+s&-bUkS zhgJ!4o88G}vK4W72t`iy@6_OroO%pijd~17x8qZ?kfg}k?#Bh$1sTGE>1w$+vOWc~ z)|*$~09kKbD~N86M|2E{@BUN@xwvMMCBFVMg7|`Wpv3J<&fpmx#2>3d>+u4iK?46N=Po|Kop9P}i>Pmt- zGCFuDDFYDD*$DWS4;VsQZxk7KacphRE0Q5YFbf7OmyPNkyiG^g^nJg*nNjOte_Q#l@mv+{j6TiE7LV8GOx5&Vb|7K(m{HC}$2FAI*WY zW^+pHwYHuN`E?bVa|cEj6r;g9m?e2?3*fM)!C@FKeIbQB|AmxziEz-kah$^S!I6Oa zjfJUL0uGe6Ps28_cB_Qc%!K2EG&qbI< za0oHI_>@GF$cMw_wCX7^kuNhjNf6@6={Cr{Go#8$NWh0z13tWuyooalQ7gYH5oM;t z;ey(<9Xf-rprAx`8!#n((lfO7@QJ-B2hE7!I`o;w@4)=MQ5H}ru3G56@-?8_nH9%p zETz7%BZchV0fZ~yxIkAjB5B-%33eb1>tMhLn&N$w4GW>t(z5nn*kuzmef5hv3^zXFdwmxCde}N?U}w_3L(_(l=mzkQfJZ z<2=0^I@#USLRFCB5$G}U@_0`Ce%*Zv0wES?+<{+4S=5#Ds)gv)dnKaH^f=rQuJ1`9 zhxec%IKj98SMnhnf@fWk$Frx%E?|tf?V%C3b+|N5IVj3q${EkRogF6vY;$M-P2xqJ zDTg!j{4rPsdW@P|qL|_-hNr4=Du&;IZr#Y5gNot5#Z`-9UO%p8MoN~$nYs8A=tO^l z%s64XU~*>$bO7spx8CaUtoj@0C?(*-s{tS02hh@)ARZn$F8>UO=g&EEz8v0*uKF2_ zrcVIL5(FE(cqF<#3GvsJ@IHdXr=@@o&)^Wf<$>oV5-r(sIE}}Dob+ze*vG{OYaqB8?GIswfzTKHODpk^f7Q?TAD<+;EePft=OnfE;toXC{g9`3E6Y&cWZnkn}fnz{RudD9!NAB7gK{3AsI64kKaz zZ=qZJZF~}_a+q_3QLmXNNakMiNO^)-oMYvAARuP89G`!wexkNfm3J2{Qo~ec%;|GHb#dZpX*}6CB`wQd2Qu*dR_Yk&pgPK_ttW z!-?E@A%(p9U*jdxSfzanH~=Xq$X01%OTgyj9mYtl_uvPok`2EHI*e7??m2XB@#6yR zeXp9KLJrTmKwEl;k^3QhodzH8@HHABiO%Jifo_;O$Lp3p%%qLIxA^>j1ATl&v|H94 z9>%_S5gr~cf~{ErD^)p8S_2ZLek*vJOc~urUX$o{N!xRa@rLCye}Hb_52$D%4I7SR zuwavllI*?zBatl<;n?#2aCtv>Ifbmc{8u6Gr>;tbo2g|SbhB4lxBoGPoVzl9flIHn z(q08@mk&bRUK_L9d?1a#P$rFwVC9bUDgd{%Rc2S0{|tQc#jHX>wl~jjfp=K(HP%zF z!(i!8z^DQ~SeW9fx{I9P#h*Z;ybrAMk}Hn^R}x?w znt0j+I^YmdQ+EEYBKG|r0m@ealERm)`4n)<*8xhLy6ErX z<6iQ}}2YHIH-G}qFG zb-)8(To*HsmCwILgFmwA)1a`ms4xK;Gbo6&Ng(@?C)~)kr?KK>uUZct;xpqX8!U!T z)?-XtM>`0HaQqhv7lTF7*CzSeU6_^j!ex=y%9~0@ia%iQ6<+)-P|a6ZnXj@!I(W+x znl%4r4gSdb&w9zp4dBxRP-ROiB( z%B>Rd@l#!;`S)q?N7j7NOHORTW+cGdkiAttY+^B7uPpfM+a%hRDRyiFS1$R@+q~rL zmu|4+U;m0ky~Avr>8-fvSA4}wjyyGf(HCVDRlr-v+~&bLT$40_KeMy}dECnrJb<>P zK^(sdKppMlxvv4EdG$g8r=&cP(J$rtx}$%?&6wMmcXP?5)T7XEu+Qf!RxE zD)sI74lu^Y-Htv}H3a95W%oWWdF|V1m9F^W=@1BlBTz)YJkyQu8OHZa9D3Uv3oAL( z9C`3yo0g5s7*DIERiRHXa0K_@L0?CE4;>+xT#k=HH}|!{7Ik>rc~W$ABv-1+nur z8K7Qz@R$owNmp)~PY#Js2{EPk=t|m6|0-IPEddSYpyHD?YY)M2_6I0>j$ex4sAsm~ zF~r#M7qRbmpq1Ge;&-^d{gRcv!?ZmL0j-QN^z;#7UN(j>9Sdh@&kw!i@?l|1GCX0+ z@>TVN5j;W28tTl+%|i)w=H}(kwQ~f9G=<&>_^=!lqh!-O_dB1J49S}8h-IJh`8R0r zN1lHM2JFvJ!?6HUirYqAmqA^Z8+G(Xz=!25)Sdrv4C*io6{l|9kHJokGU{YtO6sH- z&Mklr514GUSBkf;wRdgzzHnbASIafYre%~*B&)G05y`U~O8WCS8KC0|v$G6!cOvy`1P zIhm6{Az!s}_S-bd+2zymIm66SoU<2xCO(*Ea8ob-gN6Aw+ z%sw@c|4Tq6@6*-En~WFuef|&mA!GiF@Lc*L_&lFVuAU6o%?AT~Y)aCBk8Jrhpi3-O zl+PdZ2Vt7udq3iWTJR5Pr_jg4;>zDhEYer})mfkzgNM&T(>d$LAaXVy+}F)rr_nQG!}bbe+gy>{ySO7PrL@mc?3y` z+{XKw*SzG?ACiUs_+^QAE_qkhS6_y(?*B~|?q{wjv@YYeasJ2^FFF4|$-;j4s>Hb| zcsav`MeEo9=q2a=m@MQ^zpm1{jNHci)jvT1>QBi+f8d(LJJ-65-NO2nKYPjPKPL{CFa8A{mj03~?7LU^Y{M3}tT)WXUwFeyj=zyC>^mO;>^y)a(yGL;`STz1 zkz*h8CCSh3d{oK3tLD#t9I$^pS=hI)1nfMfCAgQd+jM{K6F&0HCz6JLmBhVkmKBTX zpL+}lcq~~2>{ty1@R?{=0&FsP`IA0!^pnXVVfPvr8Cde5SY&YFaUVJUc(MrCv(`lh z76NQCc=c00a^h3TB4OV;Ne0yOyS%~AT)=Ce_K{PcP8RY#>*FD}^Zps&{WHlzzk7p( zK7Ixi!wEhC7Vt!}Nch&1iIHHF!==yq$n&2~77+(GN<_G)|FATK*FWbYXFiuK3Jz}) z6pSwc2~*1T&-=)^&nJtTGn)l9iRKkybZpw}BiH{qS#(_7BItNCsX`b{JGc1AT7ZuM+4E&V%$rW?!3cYG8+ev&?t~?f#KSTdfvb2TZDW|k zV~j_(Qs5vPw+ouh93DRZlN$VyqhIlnN4^47$hDOLD)$^7e4iLkQ3fEEQghr^1m}3b z4eP{7zQ>YXLlm^+@DP9j1`UAGtP%&lCNU)E@PLK+bib-?JA7o@SAnVVVo@-ja@Vz= zX?dPN>OlMA&fd0+tr~=qW~BsfG8PFzbPLXWeM8Y`^l2cIp0ZRIv-}mi{)PtOSsBd2 zJ?mX~4W|s~H6z)>tN>iS4a4=UI$fhNYX)AVMSXyR7R|{PCGfX-BR_Z6bSPd#Vc=Ev zzPl$Q4QVw-*`AE4=2?EOCnFufvfg)=r(!yy$4izsl=%&W>3A=A*0hQ>w@=54P!&tK zy>9C$80#%oM`7p7p;%;^j9Br`<*Ylf%xpoNREEFGXeon=G~XDUbxXxZOxEy@cu~)C z3%M5W!Ogl2Ye_iyt-gUM+_;|+gW!yJw`QeRL{WI=B~YYsiE4+vwPeu?zl3jTqy(J% zU}M&qG`J(ZSu<-YtlYe1_JjC|*sKL$>}M;Ghejan*9`lVr&b{GdA zXAcyY-uzG&M*e7F(I}vnc<&-kC9~B)C9$YJD?d&(vssxG(v}scmf7ws$RI0+N(!id zn-l0H^~Gcps6tkmWFChn*m4Tha@*yGcHb>>G)yE-5-zjzDZDW zGd9VhO)x>SQ2#b@^L{cx2twSbFp~({G7Grw?9d&dw6_M%9+65I8rUTx z4QeG zFw^)eH?a2^Y-Q$=mz5Am)yY?Cu%~dd+RG5#(40vv3C_Op1Tkh#%2XpKCA=7L4c?cA z*Ud2AV5E<9h6Tu$Q~`u1kxVs`Nba3NR!+g!*Wd{FU=NHp{P_Bsd8Sx`Lk^}1cp?KN zr|QB@h-|1r#%7BPZ+1&E(k4K-Q%fkgT)cU}T9i6Kbn<9AEX&g{0V0Yk4HqZl0Sqgysxa)h%}O%#DX4drj`QhT$+}x{*?4~E5%`QA zTZNJoXDWafrrAgauZ|E|roxre$g$f|l4+WeNKg>1f_5DC)HBux7$Fsj|HF5Xm3ILD zp1>!+^9rgr&67E;|7T3$imNIFI|AmMq#37?C2%KMcPCvqKcfhj&%>4-C;<;YQ-OT) zZ_SB51Ee7WrnS}YAjj`Qs_7xt+`$eN=GM*fRTYXC-)YX{@(2?*FmVlE4XT!V6*>}Z(vty=EkRv`tVX?e*o8Ln&%>b_7 zLe@I6f0n@I7U_~u?s_j-@m@sv=F`fNQ+ErLv0`Qt+GFn{Tiyp~-$LFua_wG$)){@1 zkX^cm9JvRL>CGo*BWvdfWKxW7XkcMq|H47YRt>F}De;l}$f@_EMBjYoG_oyQiH%1D zC2UV-kqeoC?JcA>BTwcD_h!ZxDGui0cIJ}nInchZ9xs62W>uzFZJQvp5s0U;J1v>Y0sK$+WkrjV>I1Zf-^edQ(e z9MXbla2w96DkN9_(TRj6+)DMceZ*h6pKQJ#kR1K`ozF*L>2n|rsmBA?KRd6gken+L z;t?6LQb8~%o68?0hdv0h!FAOlSF|`&LEI9uK{Wg+Q{mnqSs4U~*!Q7}X3`dCDv0}v zh4)J}GgGC~%v2Y`??@_WmmbmAVLvGrn(>Y50f)x zWM3Ht1;a1Yhr*qoo-aU2foI9mFU})}=Yg1{6j9idndzNWP`6Y$q2lw07$NMfBr7Y& z33Y7^A8Qs^qTH63pi=!|f0!JrzCSPtMi5fcaLF0Ar>IQ9`-cNKQ7oK-tz} zHthmIjO{g5M$C)N0trJ zl#CL}&WFj`hh3nY`H(rnGwjU>6e!fa5tiyNbb)gsVh-zMI7)g}N65uC7dR_B%|=yV ziN9xM7uZN*8(ppGAZOdh*~YGPxgde&t3+~b5jnAFoJgMTF}hj>$6=9_(aP0CP?d*l0$O*Orh|OJah2zRz?tj;O9G$3!~KF>$q*KkxG7 z71C=IWY>p9191eWX#mqgYPx@q27lz}QgW>yeYlZk61ypt6!s1Z@X8qn8+0}{*f&5f zECc1?Yf+*L6lW?-`$hyNN93B#P1tZTPEHP!mBR^ea&Sz*cL<8kT-d-fRt_&GS4PLl z%C3JBenQEL&4HyG>lD^~lx+A2jCRD^WK=EifukMgRh1ZD{TOWi#a~rX@#(9i{s(Y4AsmJPJ1WaoEHwVaB$9QbMI-%z=q5 z{#d1mNc{lsOcuaI4(0Y=1%{ z$JbNEYKsCeU8HcW>pv${X?xETUw`C-|3_gx(*DmPCpa9(L&RoKbIz+OWY268lC&Yi zHxfCr{h!y!s~d&b#Cv-_=@oAIstVceFGymuOrUA(mFQGI+iv|VCeLc8&+0SYr66N>!n@LNOuWq6Y({$wp89o<*O=Q4}Bv(R(v;=V|@xb z{;OXXScNsit{x^<`Kk)*!EXUp?iymgYntX?ufZQV|4ohT`X*Q>1nkEG+NcWZ(R~0l zu~$mdXmZ;N-`3c;NQ2jEaUMXkJeR$`U!qdX=88FBV=*zOaU1Mq@yd5%)41n*0F(Ev zDwxJ(555h|n)&eq;QS8&RLEn9R_i{2@cQ>9dd(?gcXGcE_>hABdzCR6My;y0Oi9tB~Xd_Q=0#jMh^W{gCq>pml*qXN!}V02RN>(Z0F3+C2qLX zVlcDv=g`lcjLpohQwmMUFeP4?Cieb9BP)M_nqYfsVM|537iTKk*ZxYP-4vSq{*+A< z`(DtJYUehb|EHa0htw#z-4kj?4I4cjrEOw>m2WHNVUClj@qI+@I!&&fn=SWZs=MQU)= z?XjmpF;tOSI`gmN*j=1V+@|1UGIsDL6Sna-nbbY9$pmk0O>V$0)MPR?k0vW`&_2&3 z8GAF6$=naw|Ma7pKb556_Z<*@hE-p0VdvvFwWBfLkvP}qNxdszuKx0kcSmB9{9S}e zvUUL`6R>kHnT%a^$pq|#OOm~FEt!N}Wyyr>1WP7mmsSXWz=}*GTqLaxOL(VMlAPUA zCwWKH8?);uxnVnll1bjZlep}#*(9wJs&J2#QZ z++K-H{C-GeQa3FkH+JVBVr=h|hf$~r-`9=o$wXu_CrQst4gn^StvKnK#>oU_4kwe437kx1W^XcCnYxpbUYks2N^Ad? z<$fPovpEHR+>runtOMSz&i=rUQvdhN;m&0P-Ti$tKQLov=6zZBWzL*EW9HIj-Mwwg zmM?7Yj}G$mIt!$%Y5je z*`WmwbVj4yO9%S9JKCbNvmctRHNiW;axo*8{wc&aP#hsQt|QGPCC9=H+A;X6I!U7Ut#vaSaRf(&7ge zgsN-Mipu(zb&vJ;4YoyRwD>dR<+0(+60-_`t5tIrQj?>bhPF|M8fw>$!TcOE1y& zE%|T5J2fo!edAt#?<3az`tA^zMp~-rZg{Z)v2dWO-*}VNWD`G%M1?%3%FSQ)6a(-x6A` zCA)B-qbX~seR+9)dD%d>e80LIaP(F!r}skh%IX>l%WAXc)i-60bT?*p)R%|5GMhu? z19c5~^>qzdq59&+NONdjb0lZpKx-&i*4k9Kq_w$jY0L6peP?r3W@}SsS7rT@+^SG8 z8tJQwMw*~p<4AW!aaKuv!@QD)=wN$!v}3rvcXUa4aYrrjrNq6ROPkj)I}o; z^wH}2uFUe#;)eF#lA-qOXy$yV-@IV73h~!9&Px!#-d{J?K2{lu0=~?F`i91;+9iz( zC|}uy%Oj<=U3DO**3!nzwx-IihMeeFM``0=dAK;QI$YZ|zqmcOYOHc8@Y?YvXfLa* zFV1=kxJRpc+TQ}-#W__yQy*1mh^4R?m1ZI=v;fL~Y+ z|1`b*%} zXs|)oOS&47esJJ=2NgptTnyC~L;3PxC3yIe1#qjN7|JgXf;>vP>aaZg(iefF*Q>j# z;j=gl_v>`vXPyp~!Yv`FKTijGOGluO2<3)=KHvc538D)%AZxigk~&ff^o=0u0oEY^ z=wLZ^18q7KE!P1Hs||?Zpn&>wpf7@xAa*uzfQ;Y-KiGllq5X&9|LN7TDyTFHBq3D5 z4K!3@CE%R`g+jq#9sLQ4qJ`j--!kBrf{)K(*FgOg4}jp`P`;;Y&K$4XjUtNDqDv9QTX+|er*Fq!pbw*U`+-jihUuT>NQxtFg#|+r-X9OnjZa0 z3!(Yw!DX$@OY{~jpU34{T!%Ia_JW_RJfdQz0X7Wnp{Zm9WVN`xw?iQ_UGGD9W8q8# ze-)*da$>-v@~7~rJkUn< zIKHW@E@SdeP+sL&er`RdH?F+uuzb!Kr_YcV)rXK5qqjzqm({k)da!z-K$&fiVu+X5*MXAM4NQ%4PL~VI~hOWYnjmF!>^BWvz=NWsNwd z)U&93#<~sp8vIh!l6_#M;8Gl;U>&^%`MtN6(;H+?g2AT+=m#B7wq-Zw>7g*dFKo#j zX8yxykF@XYw{J>1R+ZXc1*N~ZkkPNl<+rLH;aBE@QV@{AucS|kmHH1lerNnjeAf2>lPw&d zi#Ue`EfI!Ke02E73=V(!pqFZAi!R zL)C^qtShGSo<~d3@)Q;GZ|K^CgDuU$MKC_NLPrZH z_`zHgHCXJUjs9gxYZE+6!9c6Bz8nM+9Krg*8c-FbLEWF=K)@I(+4_@E7uL_Nt~dN! zI~95L4NwN9kvavn`pJ6E`{xszIrlVWWObeqju4jBj!pmqz-i z4eQldzhEp5ztl99{I+5Jd=r0S{MIZ3dJCx}=GTBxP=67xy@qnZ2<8+ZJ}e)zy`t-4 z?G?tl_Y$i$~^ukQXyZ$W!(s5bmtEk4bGE5wf&{wbH2hleyQnPcLQ$8T@| z@h#=`WAckb55{jt6WTJgSv}N_^($*&s7&Rn=GWCfb%iUjey|!;h4mBUw|NN419re) zIS1VqaeOZRiMn>Be=5WJ_hxeZ z`eJ|?*FOb|^O--xhgLX(`W!}oe15CKfUlt3s2`hO&k{+KoweE{oc*57O3 z8@E5s#rmT?@Imn>=AY*C@_H}?RO|Ci{BilMsso4N?Yg-cX#}O<)N}oF^zcBvBU;!$J*2mv*{nh+1 z$ZJju;>Y5~^C?xTG+xGr%0dmLBKFeJRF$b$Vf}*gxrV<82zhK%p5UQA!$Z zdTq@R*JqR#WBreOCgvukniZLvo$;%t#bG3dEer05Y>9<@jt2XSz7$2zRkERvsH|&o; z`IZ~!!D415)ZQie_akW-W7bPsmv)vmE@{rGg86~QMKI3+a}H7*r6Ph(kIJvxq=${K zN)ZT?Fa1T~OZw@=@^iyjAMO{|Qu-b7K_o(N#*fzCXl`p0#8I=O`4Gz)XoGpW=Iqvi zNOnnPRZp#6HjMF5bS>c#&Y#Qkj;%e1OADAk20s58AZGRp0z zx~6Pg?R&{El&4RQ!6gQLvF#bXirSuWJUdp2rdCy9(zA4&^ilFs;o4SzS5 zFRUlE$x;^>(Zprt)XwUt6ra z0qfV-G#mcbCEklbB>guIL#HIgdnudc;VcjW6y)-!q7(9$=d0M*!5X_R!}*tcGdVxO zQAFy9Puki?umB#?<}lDWz78+p^^NBNwLB2A@jTEfV#!#)3+tEi`3kpqFs(1fmve`q z63VzM$mern>x0%e^uh46J_pQt4XRHsXH0vAwM~Po<|16dS%oDL9l58e?Vbn~JmHLc_h_@9NF^F7Z^XFSY+1 zULMBkcxw?qkBOhg9~geKuMTD+{$*zU#PA1)A-+ldL%0R&0|~M14XKpuo%VlKRDb2h zd`g1-aj1pQzp(yT&*k-F#vi2i#_Sy~gu{8#d`^P+!y&{+yRvzFJ|?EWr9lV7-bG)F zN}GrH=a~El6B-|dD8B_YJRZ&Z3)-lp=Q}q4To-N0jt;gojlh~S>UMBlDQKb=f*%;~ zL3=cos-Qo>F_Erk-fKMX82(@K-?R)xCHk=9<)}*rkHY2gB)E#K2S+%(FzZk3@MzT7 zHh${{pST#-nnL|>6RnT>o6qNiitDLUp-M3Nceu^gy9W7~LV^LD)<7t-(5zof>pSM7 z==fjMt7PS|e*@sb5Od;GknAT#T8f{r)-bcR9_P-&lwWf`r?!i^Mp~5qq`xTY(z?YR zrLZOtc$+h9#1HjggNcty#<3oYhK^u;>mcH5&dwV{fQ2OaKet>w&;D#qZ^o%-{6OkUJTm_MgbP(MLf>zWm<9GkZ& z0_%DJ$OzJ(9}hp)XZXh|qlJ_Qy|Mzj62u3tg3s5~_EY*P(~K&5pFY*m`i-#078Wv= z6b`j#6%IwR3Nt%Fp7#!$@~AcDLxLgJzU=n500B~YLJXq?7Nj=kG>(B>hnsWi^5NF< zIjlW|;Q1eh+EgC%nf+1Hggod|6q5(6FIx=jHW$e>>E-oM|K0){JyN`fvKDdBlbr?h zbPPhQXAs&&R(n>#NM%oPmR<@r!{{+WWz;kWE5qgamG#&SjT!PRHt5AhB(;}dJDghS zjWky+YR%5dY|aS|binV*t`PKb#`6-BKehMyWBT&y9$YmNY%%6vxP0yWP$605%lScS z=u*28oEiqdLFt1_#Rfmre>650SL#c-eH+gMQvXVU&_zk5#(K3Jh?Dk4hgzw*hT4(7 zEMDJjy%?g#_^MHF6wA*s`J79VlCP!8}-kDy*M22F|Do6C5F#s|zfY`vP7H&&LE^Ydbt`qbZv_)m2N@D)oWeNkCsyWV~J6o z&p#H&sZZt0#sE0}3ek5lXd^Czn58UlNB@FM2T|U1jtcb!b_c3$$NtYa=yGP=oX;_y z=k5NNhI-2={{X86>jMe2{ZdoO=JKp%<2z;)v?)j0Ej3L4`JZ1hI^!e6Zam*%5r6{&ywM^9kJ(zazE9_k!?fBVvBE^|9@{z0-oCS9#4&4m-YVucPlx^ literal 0 HcmV?d00001 From 88974d3a3fc26b3b4b946f941b17cdeeca960beb Mon Sep 17 00:00:00 2001 From: mwish Date: Wed, 14 Aug 2024 22:07:20 +0800 Subject: [PATCH 3/3] resolve comment --- ...w_issue_41317.parquet => ARROW-GH-41317.parquet} | Bin ...w_issue_41321.parquet => ARROW-GH-41321.parquet} | Bin bad_data/README.md | 4 ++-- 3 files changed, 2 insertions(+), 2 deletions(-) rename bad_data/{arrow_issue_41317.parquet => ARROW-GH-41317.parquet} (100%) rename bad_data/{arrow_issue_41321.parquet => ARROW-GH-41321.parquet} (100%) diff --git a/bad_data/arrow_issue_41317.parquet b/bad_data/ARROW-GH-41317.parquet similarity index 100% rename from bad_data/arrow_issue_41317.parquet rename to bad_data/ARROW-GH-41317.parquet diff --git a/bad_data/arrow_issue_41321.parquet b/bad_data/ARROW-GH-41321.parquet similarity index 100% rename from bad_data/arrow_issue_41321.parquet rename to bad_data/ARROW-GH-41321.parquet diff --git a/bad_data/README.md b/bad_data/README.md index 7e94b89..885af61 100644 --- a/bad_data/README.md +++ b/bad_data/README.md @@ -22,7 +22,7 @@ These are files used for reproducing various bugs that have been reported. * PARQUET-1481.parquet: tests a case where a schema Thrift value has been corrupted -* arrow_issue_41321.parquet: test case of https://github.com/apache/arrow/issues/41321 +* ARROW-GH-41321.parquet: test case of https://github.com/apache/arrow/issues/41321 where decoded rep / def levels is less than num_values in page_header. -* arrow_issue_41317.parquet: test case of https://github.com/apache/arrow/issues/41317 +* ARROW-GH-41317.parquet: test case of https://github.com/apache/arrow/issues/41317 where all columns have not the same size.