From 19dc6a36410a1c9d42fd961b34a1d6ad5b0406e2 Mon Sep 17 00:00:00 2001 From: Hew Li Yang Date: Mon, 16 Dec 2024 15:44:30 +0800 Subject: [PATCH] chore: update test excel with a nan --- tests/test_files/test.xlsx | Bin 11770 -> 11739 bytes tests/test_markitdown.py | 1 + 2 files changed, 1 insertion(+) diff --git a/tests/test_files/test.xlsx b/tests/test_files/test.xlsx index 56ec4978178a08dbf5c627d2e2792c61486a7b25..0dcbeb9b15bc026e88c46f179e8df38705cc70b1 100755 GIT binary patch delta 2611 zcmV-33e5HTTiaW(F9!up$a!RjlQah-f1v*$=v^VHt1Uz+Y)irhNQ%I5lkHPLOLRn7 z5?zvx9Tffd4&`g=Md79uY*Hjghi7IEhnFAMO>Mm}skmqpn_OVqVr?Nx-aaSx=SlAL zY)fg{mb4ZvOYB#s?2lI;{<&NUIiCtKw*a73iCt;Eh!Ijn#Tu$E#DcZ3G83|)e;S7J z8L5S2v{V&ix~Y+iaflkqTYG~L%X2WqY{mjW&sdWUUU80f!bD6#MjTQkaSvu+iMb7YYD#){scqg?skHuldT$FNTI|`UjQ`P zkUsIBU_{895UfvQa2}G6Bzxf|e}{WkGJGeiaE}!pzzF_hGy>A&JIWj+<}%BF`cSAsw-gYL_?t?RnpTV@Ef|Mg$WCSP;BUK-hU1Yu$J*o zdv{t|@P3`%K>Y9N3uFUwUTzQTwF$TP)D|)(Pv1x{9F4pzcRZ4hoSyFwoME01oWRY= zsD~r3mwDg885zcfpi5nCe-mw>6WfQZo-Ezc^=^gWc*)BHjc<7SIHv!p*{yvy4x5tp zz}ZS2Bw>cu`jNK~ad07W!Kv5%u;;^Y)h#~qQdf!Xfu#0x|1$nu0b|nl&37Pu!z{7i zFiJO!a(EomykUfnD0RgXsCB*7c7ne*1(iURHhmXl5O{3%kk=(Ke?A>s<30{CaeZeR zu*mTv5;^@6M~+uuKV;J*7$|Ui7`M~HZuf%L#htWF*X`FQ*zFq&w$?XFcRlErgO|j| zg9!J12WMX3_`SXhx%OOVHL|K{*1CwTRhs1xQl6J=^-d#?HWksc)NLtL{N*lA; zkSfq+7Z(J4kI4>$f8G##K+(@h?)apSo#8O_ogmG;<{ z=Nb=ghw0#a`@wiT_%g}<+iijVH=vt@o3@iF+R5bV2LJ#7v(XAo0uA3Bi3kM%06!D} z02lz1Tq_!XoRdv&+b|4gwjdi?M znD-%@b3qOc?;M}vEHlnuDQPL3^|lQOlG!Qd>-6v0J>y~`UFUxjCYv({?=lwfg33P@ zQnr|XSosB3d=Pdw!Qytga*$0$f2aSh8ID;r>BXFVf9QJENUU(oia2O1`k0lQd`{VV zH8#)>348zFI|;mg1qC7iie!}hvR1ze9&48^u!&>8*4FOg!WaA{jVN}-+Km1B)sdQe zc(UrJY(j?!JQoeLd{E&sxlEQto)%fYn4I5#?EVYLZ5N^{CLOz`Y>v<11-2`yCVA8q zR$=gHiI#ZmaC#x(tb@=P8+HU?xIGx|V|BaXH`SNjl-xgoo_INlyLccy@$1etc9q9cS z4!isDusb8-+Z3?_XzeFu`bo4ART|ORi2XBSH!S117MHP>$Exnfx=H71fgOodEJZ=m zz$v^3_OE6744HnExu=x0idlVB?B{uZ$9?M*2UZEZqB3Nt45P}5vePQAsYs$?q11P; zaj&>sQCViFEH#(3<4P-16BP?@IPhG6V}^SSvLbRgSO0y+Dy>VJpao`?zkn1uGS7?P($d=(22-8Lu9QR&Sk0Cl%?W|PD!VKxTMVY ziv7IQL}inqve6yqR4VpV2vKq1Bd*vyvq^X@p+%(`M^&+tXPrcc+n92$Y8~X9$YAcapIKm z4m?nN4_@!*f25hsaU^-|CM~#ssR9k>>gW)@SaT{V$9@DJLF;Y@zIk3%xOL(q$LAfK z&pWUWbFWPW=Qxq5Uj)8=fH!oyBe=O3=`h~xH@K`7XO1BWJcjbrf;&^38c$uKL%272 zg(-!#Q=j8XqTbO^5w_r^DNc>&1J)tFHZ2PAejX?-f*f}eIE!gf$`^%yHr_EJ;v3UX z;b&AGJ>q3mY>r6@oWwML_z_JW5x;1UdKCq?nZ@|knxncLs~UpG*9oTtyKh}H33Gw($D9L@1ChsP4%0lPT6J@}%;RqJm4N#Gx|4HCf;1k#R=aI?}RH3119D?u&$pzNZBlMp5wf5gj!EWIz# zrl?ecNDv|q6t6^~@&vtPD}RAJW0?}HtP~{Z2nH?F>#La8lvf&_bX9}41sKnfl%c#% z(9YVLVr=*hBr}0?C?{?!Etz#ko#UGEPnH9Y!f=iySSFZdxCQ$4Ktv~`-~+PW>#_p~ zj-dnz${I`pf`7agv^0MXe{{;oDGPh7U8hsrF2lQah-e_;PX&^tp?res-&Q&^US4UiOp<0iXL0WHxH z5na3_9Xlxc?;Xn5)Qg3iRN<5ET|YOi;9$g7s+(&O>5Ye~DLVbGT=vf)BC^_E^CIjFMkQqadwLD-i_mgJ}Mq zo9A9#&SfPYHqv$YV)2>RHdB@BR9u_1kVX_kw-3X1B@Pqdm0B+1rL16;!b4nqwU_gq zf&t`yR2iWfZp6543`lKD{a0nxVUNoeMC?q&ze}kEoE?x5xC1TEBRP4EOT{YN%W4ddfY&0}JQYAk<0zaWkp4+fs2*rl(=KaU8 z0BaTPw0CEe1Mk<#4aEPRzd|-3=f(E0UfXc@o|;@m^yzDujhIiFk9z(fMnR8J6#7Yu zLXV~Kn2h{*9DW05R1oDYe_xt%n`jF?bQxszWa*Z#cPo@cOIaLfd?nil+5U%SxAx6C zY)jgM6f1p@gdIBTN7+Ec!G*pDPQC4iA%o$nTYQv-DTi(kB(-+}Zk zv!VNrQLtv_Fa%c;E~-!e_a>U`gCkf1|%TV zV`%1!K4N{^M}va&Q7XJr9jp;-!8+P14x6X|{Jr^gAkPcZ{OlY>!NB*Je{AfBG3fzCmeC9`Iv^;H1BU!0>-l|}j8i{5khSj5KUl{?+)FM>v`!HtyT6|IhFqysyNW#@WM}hU3q-)7vv`Z_?@0 zV|K3b=r&G9=i84alhHrZ^zYpk_&)=>Nw{r0nc|&HuD$~Rv(E}n0u4$7()o`j+cm+*F$x$Da6UHezwcnz zPNm#LwQRtAJnuR1vU)gaMGjz{G)+O1D5eA&VM^KT3i|qEGh0&PJa0;_OalcygQE}Y z&!1LDWB0BG@B|5sD`@R~n=|G_4Vt^iw9w#4Wvu3Z9)InQxz++N`$bx@G>-3>=CYv! zA-A_MOjSt%Peyba8b3fRDDE+SSIgFoG%aqyX>RvjI}=8?h}cRc{kexyqDB6^YmDVv zg?XQnITz$)@lEl|Mw!0Y_CeU)1Pj|`^G=op{TshMGpv(P#Ft_m`$yNSQsN1RtcZoGpkI=Flg=qy zuX+RhlyG$K+Qjqi3n&mCP$Z$`k1_g1@Njm?0!UnR-|H24n$PF$oG!+S(&q<*?qmnd!DzQ7KD z0nf%#{jK_SVwUxI$6R~+alPKd`F=jNpFe-^KHv9dzq|c9f854@y;b|&ALGxLx9@+$ z^>(>_+~4=b7rQ^Tmr43{($2pa`E8_+lWz}?Q+v2T@oiBY06P7XGX6=>iYiw0T5)_T z4&!S)-^FIU%k)-{Q{BYR>VPd3DcBT$1(gO)@&VYrF4JX{>E<$z)RImxS04ns^||xD z^@2TD37n|XXH@CuDl6(vC%7h)1i^+{-@nF#;4)EVnNejay`&u%T2VDYu;C2{UJW>R zc)%iwBFA&}-)F26U(y3QV6GCFPmJJ_8b1hjW;H@|e2y7q9_KPGIjs}S8!nW8-P&Uf z8VG}0Ix4cxD6*CfXIlzZwiH~^Dd`25)cHZMTVFM*vdO5jksaq&3U*|KAlUN}7i>*z z?g5KzcvPk-a;ASF?WAXP<08{2HEOU6uWKIX!X1wztmEDKfVkMKs4`+u-g_gQcR7Gt zKJSa35B$P?B8p5-7LDSmgB2ftdT>J>3=5}@_u!uN19*L0|0C{fP9mAtY0`l!7l@qQ z(L>JfJbx-(bM$kA$O{;2rHkO203YEBvTrHGG_-~D$|Od z4_*&_twtC0Ze1ugK~8EJB#s(g!Z${n?;ZjAM$K8|9JynF-Xx372`__$QK5jGqK60Q zH)B(-sNlM@SiedQ1e+6Kqj>&m;nspz>;rIhRR!N9m0SZCUZy@!aw5!1R4LPf>tYdk ze6L>g>LW$;$;M`VO(DTic+y(on|_FA!8gwq8!URhxq>%EVj9?-1RKSZ3mX2Y0^$od2L#^O@zVf|CVKeO%;!4d?T znmP@$vm`YE39BnXE&HJCqJxw1B^!Sv%e}0;FVLo}Rfw$W#W{j zJv6Stne51iwA5pZltQsk&WpKv^O<x*0B6Lfvn6Zy;- None: assert test_string in text_content # Check negations assert "Unnamed:" not in text_content + assert "NaN" not in text_content # Test DOCX processing result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.docx"))