From cb7a9674142c137367bf75a01b79c6e214a73199 Mon Sep 17 00:00:00 2001
From: Jinpeng <zjpzlz@163.com>
Date: Thu, 15 Aug 2024 03:00:42 -0700
Subject: [PATCH] adding some bad parquet files (#58)

* adding some bad parquet files

* move to bad-data

* fmt?

---------

Co-authored-by: jp0317 <zjpzlz@gmail.com>
Co-authored-by: mwish <maplewish117@gmail.com>
---
 bad_data/ARROW-RS-GH-6229-DICTHEADER.parquet | Bin 0 -> 533 bytes
 bad_data/ARROW-RS-GH-6229-LEVELS.parquet     | Bin 0 -> 609 bytes
 bad_data/README.md                           |   6 +++++-
 3 files changed, 5 insertions(+), 1 deletion(-)
 create mode 100755 bad_data/ARROW-RS-GH-6229-DICTHEADER.parquet
 create mode 100644 bad_data/ARROW-RS-GH-6229-LEVELS.parquet

diff --git a/bad_data/ARROW-RS-GH-6229-DICTHEADER.parquet b/bad_data/ARROW-RS-GH-6229-DICTHEADER.parquet
new file mode 100755
index 0000000000000000000000000000000000000000..7d14d5ec7995c3b3826f767723824c0e1f04a47b
GIT binary patch
literal 533
zcmY+Cze>YU6vj`kN&lo#tM=R`5a?uZsDlyRGnBRvN-1s%rIeteNo}cvtMm=roq~h2
zkKyPb_y*2SBItKR#R&IzPj0@G@0^^Z9}M=G_(j8N)_hzRxI`p~$k(uu+SF+U=)j=w
zuL5EbAd$+z1QlQ*bro?9tb;1p0GnV7)Bpns>cCcKogdW-d7t60Y=f}f8gv8Y91Pm6
z-ch#~prq>J?CI^`7}2(Mt!k0^e5d-#E95j`sk1<(EMz5!MX1h5MzFZrWRblqd<!-8
zyddwP&O!>=kv;E2dau$w6v~Z-bJEdbjD^Lvu+3yNKc6JSi|7VUxS=PbI9h76==7gf
z8BgLkO6J4y<dUTCxK8MmTsRs|-iV>ePYuh%Oubv-vZYco>r7l2a$!J#nihWz{;K5+
pQjE~MFE1VP4P;4aL#7Sr>MKZ}cFe2MY<eBdcjFnoV-9`%5I?)(Q<MMz

literal 0
HcmV?d00001

diff --git a/bad_data/ARROW-RS-GH-6229-LEVELS.parquet b/bad_data/ARROW-RS-GH-6229-LEVELS.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..110b78397af76610e3a6b0310c009f0bd07d83db
GIT binary patch
literal 609
zcmbu7+fKqj5QdkvHeTorahujO#+cZs;ZQCb6C)Q>P%)sCB0&r{P#Xk`oC+A9#E0>L
zd<<u{@&rzkIq$cBll8za2t_c#Yv`0TV+`YgILwH1?5jdGv9)J&^c+9*Tg)1nf*X#)
zRHL#zS;pa9iH3_<8OGr_6$q|zt*iAd%i1~1AVd+IpcIhKjjqFVbrHOV;~usgt|tt^
zg<8A96-Ut}FBwWI5%>w$Q$h5N8yYuE!~Bm7t*>!wr1ke1GfaIK(tf>tnP}3#c%JNH
z0B8+zXjOnUxC6KW7(hvmz;yxcX;=cdqlon;Vs%X|>1H1C)>t*xEoxTCC1^YX1Vy8f
zyLx%@qk#C;GO1|g^LCyFWnW4OFsFOaB>IgqS>HzXbK9m8KIy&>$wfUKaMy`WJhAy7
z7ks(eA)oMMEz=HZ#nr#Qya=FJWcu;6H=ixTI2%l-N2_qY7*5_#bGd?3$TlCqYgX!y
OhDlH6C&ieDkLwo|hlFAP

literal 0
HcmV?d00001

diff --git a/bad_data/README.md b/bad_data/README.md
index 885af61..30802a5 100644
--- a/bad_data/README.md
+++ b/bad_data/README.md
@@ -21,7 +21,11 @@
 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
+  corrupted.
+* ARROW-RS-GH-6229-DICTHEADER.parquet: tests a case where the number of values
+  stored in dictionary page header is negative.
+* ARROW-RS-GH-6229-LEVELS.parquet: tests a case where a page has insufficient 
+  repetition levels.
 * 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-GH-41317.parquet: test case of https://github.com/apache/arrow/issues/41317