From b622bec794243a7c98508b1e1cb9d30d68b28b22 Mon Sep 17 00:00:00 2001
From: Jacob Quinn <quinn.jacobd@gmail.com>
Date: Mon, 22 May 2023 16:40:39 -0600
Subject: [PATCH] Handle len of -1 in "compresses" buffers from other languages

It's unclear why other language implementations will have a compression set
for arrow data, then indicate that the length is -1, as a sentinel value
that the data is actually _not_ compressed. But since they do, we can handle
that case pretty easily. I'm basically just adding a test here from @DrChainsaw's
original PR.
---
 src/table.jl                         |   5 +++--
 test/java_compress_len_neg_one.arrow | Bin 0 -> 6050 bytes
 test/runtests.jl                     |   8 ++++++++
 3 files changed, 11 insertions(+), 2 deletions(-)
 create mode 100644 test/java_compress_len_neg_one.arrow

diff --git a/src/table.jl b/src/table.jl
index ff44f058..49b61536 100644
--- a/src/table.jl
+++ b/src/table.jl
@@ -521,11 +521,12 @@ function uncompress(ptr::Ptr{UInt8}, buffer, compression)
     len = unsafe_load(convert(Ptr{Int64}, ptr))
     ptr += 8 # skip past uncompressed length as Int64
     encodedbytes = unsafe_wrap(Array, ptr, buffer.length - 8)
-    if len === -1
+    if len == -1
         # len = -1 means data is not compressed
+        # it's unclear why other language implementations allow this
+        # but we support to be able to read data produced as such
         return length(encodedbytes), copy(encodedbytes)
     end
-                                        
     decodedbytes = Vector{UInt8}(undef, len)
     if compression.codec === Meta.CompressionTypes.LZ4_FRAME
         transcode(LZ4FrameDecompressor, encodedbytes, decodedbytes)
diff --git a/test/java_compress_len_neg_one.arrow b/test/java_compress_len_neg_one.arrow
new file mode 100644
index 0000000000000000000000000000000000000000..1d0f864d6501cba873150bfa1a235df1dc4ba01a
GIT binary patch
literal 6050
zcmeI$dvKK18OQOn<iY|8A|QlTO#*7Pl(5_aR3J&YNE!&2Kp|2Hn`D6na$&O(D5mI8
zYSfX-bksUlMUfG#7F)HJTH2+V)-v`wRcqC@&}p@u-pAT1Vz=Ml`<}DeEMok-!<+f+
zdCz&zIq&Ux-gmQ=OP4NMF~OK5%gStHh8Qga&0v#j@=cI6E!lp1V4%sP7NoBBAod{(
zYY_rdn5URa+lE8svPgS;c}q0Ts<+*(zh?VsPR$W24SD?+w63p>hhtv<AbZsQG>@on
zKkVo<9HTLdW081#dv#=cO}IJIZp=lrEn~85B<Oe}Dv*stz?d#9Mgd-?@55-r4CvU;
zoJ}Tm+zzW*T6fFW-%BQS1i3WSZi&@)G#gV&o9l1;_8RlL9iwy9fHi&eAMsy*AL_p_
z+G6(f(SKfg|L`{Ropby5D{v=3`IvV+CQ!usAk@TK*VTrb+ct9n&zw6p$Bzj*viya8
z={|&Gv9K<?+Dd85IR9Q_inz}M=-1k?G13^{<PB=*W6Ux;rac~uwygKZ+;#4lUe~#X
zF}gQH*;iXE+8m8XZ-~@%G&e+I-UKi8F@BF7uVZcL8D<94?#|C%$6R}#>8ZHUpR&f7
zhSt{2k#LK5W#*-gyHp*CC0qJ6q9_Q(l8#&ZZEEdk*c|cC_X}y`?f!b*$GCUACQ!sU
z#eM3Wt6IFP{DVHmD^D2~DB?rM5cP+#Hq;b&889rB@4BY$8rXB_S45jz{5<XN<tS}|
zB0dzq(e_F{{pZUD8r*fuV-JJPNS-U%-ae)&5WOYa^~uUJm$Kc@f91XQD<N`uo!8g@
zaM!;$t?d%K?&7}G*5}*OZC`8a2Y4QM3v+96+Y4-cqTg&5XKdeK>(lM_!x`HX8TFSl
z>i@_XAJRo*ar>Wd>u&z8jO_<({b76j^K<<1<Nd;HvvoJ$K3jMFr}g(cF1G!<Y~A%g
zVC$~`d<7}XT)!~;Y~A%gZ0qiNoyyq$wyjUG<3s)nrssTZJ$1er+Yi|KwRZfejO}mR
z`X}sm70QkDcv0K`d!5uiXDR2rzhvVid-TGBrnY0lXeu-TliZ$Q&0Aa|oPDe~?&odh
zM4HF7skbh<(pNc}551Rl&Gp{67<zVSN6LN0$q0;ua&r_uf{#MEeHkuCA&O9p(HMg(
za3!un39iO9_!!3G;}{3!y5c_szS<bY;v`Il;;sx+F%60{#fsu-24-RwbdD9M#3wNu
zbD+4NhwGqcNfkbYYAnD))L;>mQ%kTEwOEGb_%v2vCF*cJR^c;PjWwvpT7=PnMl>M;
z#qN4+KolFX37f&!5$}Gu`;%VkoHFjeZbN-PK89zTWJf}G$YIr7zU_tkRrcKP%=z5&
z%Eps!-NnSy=wL<A6wV4NPI3}l(h4@P_~oAe3_0xAQ*o3zud4@aKUcW+^it<_zT+68
z<Cv2=jyV<nM1Hw@#;jaBar%62{e$Kmu6e6c^H$k;{c=gxmcHh7`_S%nj#<co9=Cc#
z4uWz?d88at{wQ~J!;~}17v)MJiZKSt4dsP$Vl0#k$^+$q;$N|^xL3?8-WBUQ$4bnG
zVq0;on68FmS#hiwR{Sb<6}O66#j9eq9$_>>v8lLJOm2c=u@zg;jt*?acI-eWcH(C2
z!fxDxTX8$?z+UXf7jY-<#yz+f_u&CNh=VwUM{opR!Q(iJui;5Njc0HS&*C_~ixcR^
z_wgJ~;(2IsrHyYTM|oKp-$0He%0fMV>iVmRxi9q@&+4e>-UR5mq3d=dbZ%dT_J0cR
zU}%8*h&fn|8?YCLaRRU4P2`clS7H`cpbfX;Av}v0@K@w!5igjACD@2v_%fcxPw)ox
zWp)%Mq8d%;#9cUwAL2C5U|0^%UChNAY=ypK9KrYSD*lCh65=Y9V<nUzx8WeZjTiAZ
z^zYAeAJefEoA7zuhi~Ag_#*;A-W!;N1&H8txEoL4Bz}i?F?;~IfO)9LHtffv=*DY!
z3tC)h@Anj%PS<+>gDmp?d)d*RZ|Y~3OfBgwFj<A6Q9U>OiG=^Z3L8Tu3T^Y*o#j7s
zd7fUDv(44jZxAj)A+EtB%*1tA0_9o+$|dE_E+{vY3lBoEuGm&ApTsZlYrKJf;$7qr
zCl_H9#$X(#q7v0uj(SAVj!xWy{kRv0a1_VTjUVHeIE_E!EhI63I2(q`P=X1#7IU!(
zb!bF0w&G^ojyv%Hj^Ifg$8-2OUd12qcf5lvVl*EkQH-&ef^t-$7OSxyTd)JWu^0E?
zARfmvIDzN!B7TcM;Z3{;Ev~fjpsyOq+*MT-lbf2#)-{E~tTr@EkCZhv4%9vUQKG4_
zr%4m6nEeW2ox0!dzN=ImobP=c@ZQH<Q19)aQp<>c|Nfi)TKYV0UGrtU2ldrT@8j`x
zyszk&m*5su(8%JK(WkB-N5##NUcS$KsrUO8djHj>-haL4JbQd+owth*J#P`+hj5$|
zZd%2}<IVYIF5Q2q(wjN`INkdD9B-kU_gmdM;4bfga}%bkyTY5smf^hLyzbS#>!3A#
zcg^FwP_F$CRNrm&U{rZECPQ~+1J6J$Z8lzd{*U$B^=(XJF8pS8;Wx7jznQt5xbT~q
SuEYoZW_A<Ll}hio`TqedLo_=8

literal 0
HcmV?d00001

diff --git a/test/runtests.jl b/test/runtests.jl
index 3cdac88b..47a137f0 100644
--- a/test/runtests.jl
+++ b/test/runtests.jl
@@ -666,6 +666,14 @@ t2 = Arrow.Table(buf2)
 
 end
 
+@testset "# 435" begin
+
+t = Arrow.Table(joinpath(dirname(pathof(Arrow)), "../test/java_compress_len_neg_one.arrow"))
+@test length(t) == 15
+@test length(t.isA) == 102
+
+end
+
 end # @testset "misc"
 
 end