From a16cd1ae80c04193c029a686d3006c95edb81594 Mon Sep 17 00:00:00 2001 From: Yikun Jiang Date: Fri, 16 Sep 2022 23:10:36 +0800 Subject: [PATCH 1/3] Add spark doc --- spark/README-short.txt | 1 + spark/content.md | 49 +++++++++++++++++++++++++++++++++++++++++ spark/get-help.md | 1 + spark/github-repo | 1 + spark/issues.md | 1 + spark/license.md | 3 +++ spark/logo.png | Bin 0 -> 11306 bytes spark/maintainer.md | 1 + 8 files changed, 57 insertions(+) create mode 100644 spark/README-short.txt create mode 100644 spark/content.md create mode 100644 spark/get-help.md create mode 100644 spark/github-repo create mode 100644 spark/issues.md create mode 100644 spark/license.md create mode 100644 spark/logo.png create mode 100644 spark/maintainer.md diff --git a/spark/README-short.txt b/spark/README-short.txt new file mode 100644 index 000000000..109840a85 --- /dev/null +++ b/spark/README-short.txt @@ -0,0 +1 @@ +Apache Spark™ is a multi-language engine for executing data engineering, data science, and machine learning on single-node machines or clusters. \ No newline at end of file diff --git a/spark/content.md b/spark/content.md new file mode 100644 index 000000000..c905ba1ee --- /dev/null +++ b/spark/content.md @@ -0,0 +1,49 @@ +# What is Apache Spark™? + +Apache Spark™ is a multi-language engine for executing data engineering, data science, and machine learning on single-node machines or clusters. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, pandas API on Spark for pandas workloads, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for stream processing. + +%%LOGO%% + +## Online Documentation +You can find the latest Spark documentation, including a programming guide, on the [project web page](https://spark.apache.org/documentation.html). This README file only contains basic setup instructions. + +## Interactive Scala Shell + +The easiest way to start using Spark is through the Scala shell: + +``` +docker run -it spark /opt/spark/bin/spark-shell +``` + +Try the following command, which should return 1,000,000,000: + +``` +scala> spark.range(1000 * 1000 * 1000).count() +``` + +## Interactive Python Shell + +The easiest way to start using PySpark is through the Python shell: + +``` +docker run -it spark:python3 /opt/spark/bin/pyspark +``` + +And run the following command, which should also return 1,000,000,000: + +``` +>>> spark.range(1000 * 1000 * 1000).count() +``` + +## Interactive R Shell + +The easiest way to start using R on Spark is through the R shell: + +``` +docker run -it apache/spark-r /opt/spark/bin/sparkR +``` + +## Running Spark on Kubernetes + +https://spark.apache.org/docs/latest/running-on-kubernetes.html + diff --git a/spark/get-help.md b/spark/get-help.md new file mode 100644 index 000000000..f4569f262 --- /dev/null +++ b/spark/get-help.md @@ -0,0 +1 @@ +[Apache Spark™ community](https://spark.apache.org/community.html) diff --git a/spark/github-repo b/spark/github-repo new file mode 100644 index 000000000..56646b9d2 --- /dev/null +++ b/spark/github-repo @@ -0,0 +1 @@ +https://github.com/apache/spark-docker diff --git a/spark/issues.md b/spark/issues.md new file mode 100644 index 000000000..09392138d --- /dev/null +++ b/spark/issues.md @@ -0,0 +1 @@ +https://issues.apache.org/jira/browse/SPARK \ No newline at end of file diff --git a/spark/license.md b/spark/license.md new file mode 100644 index 000000000..4170f2532 --- /dev/null +++ b/spark/license.md @@ -0,0 +1,3 @@ +Apache Spark, Spark, Apache, the Apache feather logo, and the Apache Spark project logo are trademarks of The Apache Software Foundation. + +Licensed under the [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0). diff --git a/spark/logo.png b/spark/logo.png new file mode 100644 index 0000000000000000000000000000000000000000..464eda547ba913899655c14d8d5f4d5093aea01d GIT binary patch literal 11306 zcmcI~Wl$VG&^Ikkaf)+DacJRi=L)n~4=?UsytqrzQrwDjxEFW#!;hi|w9w*k*x_=( z+yBRR=6OCo$s{}3%_f;-C$qcri&j@vAi$%+LqkI&P*QxS`Hw#SYehI%|N6?vBA zO}?9niu~nu8zb-o3|NhY@$RL*6-i{~Q(&hm-+L|NKviu|*ub?E%ooe1vPvyieEs(7 znwyLCe=G+d1iK$YYDJdFA-_IS29~z-oEcO~`vu7zg)oec0NSz-#>OD4T9*~mn0G4h4;@h1dFAKUeIw>w8Hj!6?!1%i*T8H!B`&Yo^~Fu50yN3ygM(= z2(y9WW?t1$Ns6ZV;p1Fw5#TEqBgL<=AaOqho&@QI0IMCq_nsc%yBj(cg?#NHvU_8= zyR+1J{*$7)v}njk*qEtvO3V#~QVd2NYtdtg$4eWv;@Mxz$n4yV>^ z55i^f&-!W0Ex$w{vH{e?TL@P3J(rbutx^>q@S}jOWoE*zOxeRwbF=f{*!;w_lKaw0 z!L;m4Q3B@>fzYr*y(r7xpGies~`Q>V-&M9ffNwN~h8FUD8w?yjUBZRB0>mv)qhJoAV=KPNU3q?A}T&YlN# z8{QRI0QhdR@IGN`yF@p>8^I4+6%_YlkzQRZ9&_}#5Q^n^1R0iyOPzSub17cXx+b&& z7f%_LR`(Y#3xFMl)UI+W7i_-wvJy3crj(tp(=B*W z=6MCViW#&dr1t)J3(w=Xt&BcoL04$y0RiQ!yM|EuCeVO217hV@%R843 z0)EwuvB!lwt>QvNOa*{%;!w(?c|Eeg+J!+?UHk`&6LyT1Y#Cc?C+L_;>)Li^(Ub4JvDN-^tRg>>xCg zcd?z}9@+WVh@7?|;-wMFOTYQ6*u-Vm+7i_b z7XCdeW^2jD9>O+W@}}40BpQ}ud$8xAskyAW*njegzlo9cT6$|CAtU0TWBTAA7mzjn zrX!zeKMeh^obRfv?ECQ|Q`+3$$=uqlY~sP34Hq6K64zairmQ1DJa&`nCfRsL6&6`U zjKdH|8Lp$rj?q66`oKGC8TEr69?}_8aS2Sax1X@txfi_5#HdczKGIML=oZE9y%@>D zaI~YN$536n1Rmi>365UPU&EwT=$>ZezS?CuM=_Hf>=u8uo+sFjby#-EH1H8@o4Hj0a>|- zZn0@J_FX@O61J;CfJOoe|BQ>U+E;wK>w6P6s3SHlu;E3x7mj^p!s85=Wt`+hA|-Xi zBw}eIFLLwwYh96SHd83w+Wb%Tn;bKgr_U8+)S398@m-mArL#JQ@MUe5gQZr5Dr`9m zn?X`35-n%$+0e2vtZXJ2GBZY?UjIlq5H>bVeBh3Odt;qC_=q$4*!gkACf+$CCF(#} zTS>&yzKhDzsw{X7@6@x4JIOdMUZ$X!1!C(Wy)egj+6W3wqGpF z(dY2k{4Q%$^mkSOIcY%tTv6Uz#quR}ygWz8y=S~pm0OIjqhTk$ zjh*(3{TI*z>~;C0IzXSWh7a@UvTS$W--J++M_->I5f}lr7uOuMe3||#+~dZ9d~*%R zFs&9BjemGpDo=G%^ce@-E6eU!HknN!542jsxwN={_|u&~4ocS4ck(s&N~5W2SeG8S zq2=F^=d)Tof(6@b-J5NR-I;g7&!~%-!>o33E^Rp18ED(1;V0(&UB;&t4umtWC|-F# z1cjqig;fg2*z5P@-JQ0C0JijVf#%<;qm(|U9?}(Ccx$Tkt= z@&zv#JL943oP_ek4h9>2))cRxGT_x{&wSb79_}Z^Bymite3zehvuymHH~aMIy8m#A zpQi4n@TNxU_EuwFpr5$tNqkvIw)UMe{`3;{-y>V; zYo{o)jYh-C0WTtzYMvE+uXy#^Qek2L>bRP-lz@~5s>nEYd6+y;0Pnm<{IfZi8DFo( zg|K~7bM80)7GG6wMz1btotaDuyM~UKAYzb+*&oF##CM(HzIWXR?awCSCMAE=8FL+_ z#!kx>zkokeSG6d~5p-5oR(W2^r6)@1Yud>t$c@+wcR$MWw$`q$VmQJ*V|SRG+&bqz zc$410O>!MrgIn9*9JQ?%192nhTpXZ5NlM@Qt3ekBZ*$& zqv?|PE!INtr{vGnE4`xKa6`FQj*Bj#8q($E94A|SHpW;x%f=^-$hk?<$ed_+Bj?Srcy6yd8B9mNCtXPYV z4&koR?&XQ;rFOcn@mQ}ROv@k*L4A{(>0tgFlqYc1%!iRU?y-|Qei)X!9_gx58Fd{R z7405X!_JV^@Ar;15^pK;)zODw^yrZ(2z~TBRLr+;vtgH1AlDxjZt>ex3>J<%PYX=R zjb_i2`6Cfa%j;?*{eir5=6;ix(m_O2pa-#lN9I_z*bm@8u$(}e{iPom3iy21qwZx;zsgyxRo~4jvYe3{tyc@*Px8pq zdoe!tD*g6uSdtnIFf+JcN$(GdTfBy@U%Sm}+=V)T8Z)HpE32!EC!cW!Z*ZT*u#%UtQSa8A_o$KUw!e|KJBTA@`UiGR6=WkDsC z?Ug^H?me5ofCjs+kv2IuRIO7rI}+L0axE|&-8t~rUZ)TKbk1c0;Zf_xKQAYdj%W!F zec%)Ld2y-v9jdO~d(d{bO3o$5jmIW_>cH5s0PA}glELGKQ@9*Pk!weOAHjG8ahG`3;hNrcO<}2iw*m_y_KCsq%(QXFrp0Yu2$N$i(;<^2#%wde!*3M1M%ZWK zA6ly84SY0QKpK;*Wmlwh{IVCiQ@qTezxGh(Yl*Gr;TW_f97efw)T09*%u^ejxoWgR zH#_d=D$hRHHwN!*BfZW;HrL*?s2q|$wK`pM(nn1j8^^cb1UknS4JnvL|s5Jq_gnJgIuut34_pPvv((`*!8&^0$UY z8QO9t4c($uW|~6Mr|LttobHi3y=LdBP`s1exg)TtzSs?|*$unLg74EL#OND=*!+6I zOURCBBK^pR9?afO?T3KE7-X`yb@238<^b~GqR~EKEAZ-HL!YQ5%pedpz&W+fKIlc` zt?);|{NI1oI~fjc{(2C9PiLRTnv*`Ue*Q5|%NANDM5)8?@#~?vSqNrOWY(h(*~UdX3Qdx3UdYK&G?RoP&K!`}xE}2n z?>v!c*-u*hNZaw2u8&*~{v#=RTsaRlmJZ0<=pxAGE6<|NVqg~oC$t&~BOjYI(pUmn z6>jW{{1!p9@I|Ad_utI_T5`~Cl`561v?aAaYwtQEw6(C+-B7nkN~ahIlQnM5J7}9Y ze}FIIWOVNy@kT?O8H!bVV>_O@Dl1Xq`5Bqm41GUNr+MAa(e=Cn90dX}gR@M6|Fi8@UWAW?QM<*m zNBtg4Id^-*qG$$(Y&7HFA$$Tw?cryj?&H$T%D_v+u@wsWcKkhZ`utzKYcCEA{N9hh z()cIE>To6V%Anjlu*_rtNBF$;R5th-uC|J{V9f88gab|%SD_k-`ZoA)*XJX*1)eJU zo;)YL=WCUTtPkyHXJ_3FK+Pf7lSdj@glvJ;o4KfZirx~1ELhecw!7eo+F0Ip9^WJ2 zTAVe#XqIcMzQ&XAva>(JhGyqk$g*10))RK!eGOYq+WDz&)b^d@BRjc9#j$f^rixTW z#h%v?>!FVf`zT&*U9L|geX!rK!b@CS-z=6Ag+KY(1@*cT&EzTDpZK`3%Uc&%ge za-iQD$(p}1Q84cjRBu_GL-P6SnFOk;%gxb7fR;>d$T*>sD>pYesbheK1Ofp2P9Dl@Io*$0PY3iaFXTD5ZaUT0jl~NKE5lX-8i6-dK>@8sP^IoG& z`TJ@G{x7@pS8vrqw~;UMNMy0rv1v*BD(mBGTx$~b)pu@^*JZkb@8#~h9+S{ zl@}R8_;%mC?R3PXjK8~wuZ}XcC3U0Q#ENf8Z^sQ#t| zDt$AqPDimLkva=@u-?NC&K^aV5vfYxl9n@5pkJ0Fr3&|B;maA#!N?69rg@=5c}MaJ zK1c~)FF1RvTK|M)1DP)!aJLKp#kbmoFo|4Ok@Yz%{C>9~M`_x0BAlO3P=t+-rd9j% zs2siG$t9=c{ns&1W5P^uuEodeuDfObhoqO%A zo<++m`>3#kqf4k+8Uc)2`bzAE28t=j7=S0XxJDr;3n^F3ex@lM#VxOB+*Ny z|8ig$T0tvDlv9Sju4_^#ib>6YFEwP-E+r|-ZGW%9&pye^AZIh1LixfoJS+d~@nlfF z+w;vCQ@(llO)+Yn6D^9~jc4J9$2XS{t)RD5G>Q+lV(O@orS}`flVfE&b&2)Oe)Vu= z6wUBd^o7h%ASK=H{Owo|JiUVM`uD&Vn+e1@VK|cMvOW~pqipD$No&(Bt;Y9yhrQ!~ zOgnI^k6}0E8PU)NdGRI5`9}XFC8-KFxDGxt)tKbWANAnBGr#FR^?G6$c2<}OM3>cc z_b#i9aV^8_blNs*lS*)hV+%X*0(tmYPFpun$$)@7n|&uiQ&!Za zDvdYMdSN{GmrCeI9`AXWtZ|En4BL+@CL@1DTZ2dJXbp{sM|87>E7kdKaB<&X{tiJ_ zT!BxbafMUo%WWhu&;8?@Pubow>7S8hTwYeq93yZ=2>aSH<#UyIh97RDJ3T zfaQAeAvmbktTU^ni0GS^6*}aLbKmPww<4f;ipC>QffhKmw|-OUZ$0b+chGc9TDqas zeO5>o6aV9GfiRVZ=*0)Ha59%C%0UCB)WF0)W9JjOPuNxqoQM=NxzG})Q+L=;i1QVZ zkvbgjPMj?~`Z~^KfwHbL$1!)&o(;D0)2l%2*iKK(`j9>e<7}%Sfv&x&Uj$PHie6rK zt}r3h9{%LW*nvYzB?W>ic>qi|<(D~O1A{-BvP6ey!6Io~L2X^w<-MQ*A3n!Om>U}K z;k+TBwYgAisF`(Am{p~xj+hP`&7J?%-{Xp{g|;WkAOX?L_gS2Jd$bm6Xy^%#f%HA0 zs~)>H%&!|)<{l**E_yH%?p407itwAL?bkB)%Gm~R>vISTdEm=D*SYbP!T(tw)G0xg zm;GVEwD!$MjifLQdUxm0#O}qg#Z>7T7`jf#M~PZsU;H*Mtb;fY1$54whns@#5}Bfk>6S zzpu7%#+rx!ybTD;7wm9AyU0QROdR`s4)jIN%+BFKc)zPh*7rs%PUyLB18WKd8xCZk z9Di)?x{TJ3z`#W|Fb#&{*)l83gF7}ECq94uaVGn6xjAR@zg_CE1a(*aW&3(#}^D;?!8m4e!1W} z5Sq<08xunP2^Q^WsrWI+JLJ>%Gru1%DDE##f2OIi?{(Q4Xas#gxAo|5#o1E&i@A&j`M%B?$Q%QO!YG%6sbv-`%ip1+fGzFjY zYP9LG>;bboAVf*&7p2D+p#;e@#g)q`CVTGe48`qNIVQlbe}fh4^qRd1r?g*xXWBn+ zNl>a@$KGU!bz2jUy=VHnKJaO~@5xl|+p$xlyu$c5y!RMc_|MzZ5>hl-gARvl>K{?W zxV8!maTzV(Vgy%>>alni^(k*|$xw9^;LDm!PZos8${g#J`5B5{CYZ~u^ zrN+5&o<2q?5I38EA6&-$1xv4aOEUMi;?m$Plh!9&A*Y)zIPy-laVUq8SK|%+#{Q!d zGkb;2_Y{@gEyV%-INPkDprG)omec36oL%cpkH(rIk>$Y6~Mk1uy?_4EniZ@#L0>DM^F0! zQ5N+bgE7gW0*otaKOe^>m(op6MCNICRKU98*PH^JYxdnM8Wz{>B`0VGo3p?t;z$}% zy*g_mE0f2`9|#S8F~N>4 z_tQXm_aJ+YSYeuc(2t>qC`w#?y+fH?A+Hg#Tu|xydT;PktwlET-okqNF;^aZHpiro}@HFuJutqY|%{H5^Qm2gmx-sLTQjMu;AqP$#d&T9EGFO1VRUE z%-LUKP=N}In1#KLa-Zez^XtQF$>TgD$8}O%5$Bau=))+)YX-Wf2hSM3W+?I>Sc>b zV=Rs$ErCpD--Mg1|2_WI!i2aoeKCMK7@oRx`$)p2q%ctFA83T5$my8s+7X)o;k9Xp zreH-u(=b1;5jLW!H8+w4Z@4kad#@QjziPL{pENvACqy~qY>*SVN8Chr&P`vxyYLMcPO%J^% zsILeJF??X?Dq-!|Zj(NH=}bPon1aH_7(3RQZi6*k3J8os*Ah<(86jLpvEY0{{y3g6 znIApfpEa^?UP`?QKdC+xrF>Jm_BKWgb|Oh#c$pNOf5eQJ%up{!;=gL%|NTb0`=jL~ zw=oOO7ozl?j@lIrmx5mfjG{i@y+I<%NpZc>L8z8<{rFKG{ zzp7;7L9s>idHBpwUVtMmOXrw7JUmw>mf%dxm5d7qgc=N=gvt0uT`EodjSSn%1AX$o zcU5a&QX^yezgHWRTOTX(`X=A3U?&^Khs%8ZA@!9xt}P5JwwK~d24v3HHiH)l?qOQE z!>=F|qYYGkJlg08FvqIgtcdVaHKsM5a?p&VXygWDWf@FXVFm>++4Ik1rE|!Ea*xNo zL}%143kOlzj_UFENe6bpJ$43yAZDWx_w2;Tn=Kg`uKh$W^ue%G?=;J$qv^mp-VMju;j%txfPN zH+BAZZ3d>~olrGQV;fTe)T8;-y`v3B#b=s9 z@6b%%9(+%xxawwo)NKr#ta3I;)W)qK#|vOY z+jIcr#CL>t3P=Y>w~w2)jVhbgUrS6<^;Rve7VC#%Hjse2h+&x8?xp~3sciRn)i>x^ zx3yPJh%zBi+!9%xDfQVJ=bFtUgGh&~#5#!Ot?v7cVo1Ecc z@Oif=mzHaE(Am`0u&j|T@R3VJ#YR9d(>%fl`I@0c*3>|=X=E7HuEjp6DdtM_;`6DA zQwaKU62bc@Kq6Q>=(t{*a$|F%udt_&QXs(R{bCJsxEIjhU8&boZ^Z1 z8dAGo`kCFc`pYQz`t*47aV~oz9Be{8Qe0n^g<3_lJH`rti$e)V*_g_}B%VkxWyId7 z+>ZH~wQT``lZVQP%XD~0>A|$4w2BQ%0qw^-?%T16_JbDPHyC^TgIqmB5Wkr4sB^YQ ziBjN!uudIfESkd7iwm)8ZciVRW8cG*90T3)!={J7y^@~z$eFqC55#Ba&gJHg8x?4K zM3>uHr;7}%Nc@&vP5f!>E%xS8asE0r70y73 zop=L9ydvdJ>sku|1tE&&uLossOhZ>Z?)NH{^ou!8|B^EE0|Zj1C*|k(7#fuB!P)hN zp@GO`+6UmnRcvxV{1~MI-QT#AkzI?)bhb##l^@8 z@Q0f=C4jNFPc7T(qRuDftZmq;m98^67Zx8X1^pBEZuX~SHsJDj@M%0z)YCE#FWhfS0f4fNdzR=k|cb4|IK-c${*=w9^SvFb!KUF=LTO-vT!2XNx4=shZ@;+ zr2B!lbm5yj=ePO{%>_?JR&Z8bk*lKx!dS+f)GZ?g9S)0Fv)C0s(7u=cQRay}U<-EN z_;a%i8?I|eC5)fnyk=8pk_|?PytaaDiO-F2dc0I|@VBPMJyqS-y= zw~Y^7%QI7SU-hWnP{F z_x4xC;PFj&-hZAASmurRIsT2YAR@rT+TvlLeofaQ@{GdT+1YqKX_kNOqEkLL99S{Q zNOLKR7OXc=tYAq+67w%WV%R4f(F7-~+|DM6?TGwf7wECbiGD^SYvp{vd!AeVeI|km zp!$bYXLTPaEq$)4fkh#WydGabVaE_DT9m&Rre+HcD|MdrWjxxE6sV{GVXGN1~gFCc~2vbCQP9fDkn$|)P5Jyfv z)_6*0qp@KCe5|h=^8cZ1Uuf9|S>TtfU*SF%*pn|3Z)_mOx5@3Zj!79yF7l)^!7_*P z;<@^`^621;i%F2tzXod-{LBV0wRTCqNQpWeA+ezf8Ot^jzVOBJys<>t=8ULa8}3sN zQLExBF_7d1Tan@4tXdWO;kOJdlHZfehcn60y=|9#qxb5ZLPVPuNCu)&2owW3y zMV_CuTTI7CP*)d;S5gJOp;a<= zH;-k;p4^%$xb_?RLRxKZ5LMysTF$o0_{z(`UbocX7$0=+w{U-C?3gp**_;|cdcL1_ z*V`wimV27Hnd@QD{4Cl(f15QIn{TofavD-J598Bm^Wd^rTB*1}*}wQS7g+wT2vg=z zM_daj=}_%&%^=CK93eV6lcjl^&RN|{Kx0`{2@d2v&-7JiOBtNC?v4U@!KEc}=DorB zCyL9ry!1gnW7l|`);$WvhG4&MPPT^Gw)b1a&Kyvz;>yt!1Pu_ZM4U=m`e@G|8iOOg1S1Tm@>`e|09s}|A5K$@*#MMx;inL!+rE0n3mP!y`G1a zxrep5rJMCXg2oTz6Mh2}e!~a+$j>j%Cm_xz%njrd2Lfw)L+}4T1t%9PI~(8sU15Dg ST;ZPrn$mmKcQvwRq5ltl>JQ8S literal 0 HcmV?d00001 diff --git a/spark/maintainer.md b/spark/maintainer.md new file mode 100644 index 000000000..e4ef7ed7a --- /dev/null +++ b/spark/maintainer.md @@ -0,0 +1 @@ +[Apache Spark](https://spark.apache.org/committers.html) From 1777da678f336a868f83434fe8d673d063e1748c Mon Sep 17 00:00:00 2001 From: Yikun Jiang Date: Mon, 26 Jun 2023 20:15:49 +0800 Subject: [PATCH 2/3] Fix ci Signed-off-by: Yikun Jiang --- spark/README-short.txt | 2 +- spark/content.md | 15 ++++++++++----- spark/issues.md | 2 +- 3 files changed, 12 insertions(+), 7 deletions(-) diff --git a/spark/README-short.txt b/spark/README-short.txt index 109840a85..1b5f8f525 100644 --- a/spark/README-short.txt +++ b/spark/README-short.txt @@ -1 +1 @@ -Apache Spark™ is a multi-language engine for executing data engineering, data science, and machine learning on single-node machines or clusters. \ No newline at end of file +Apache Spark - A unified analytics engine for large-scale data processing diff --git a/spark/content.md b/spark/content.md index c905ba1ee..b13a962e1 100644 --- a/spark/content.md +++ b/spark/content.md @@ -5,19 +5,20 @@ Apache Spark™ is a multi-language engine for executing data engineering, data %%LOGO%% ## Online Documentation + You can find the latest Spark documentation, including a programming guide, on the [project web page](https://spark.apache.org/documentation.html). This README file only contains basic setup instructions. ## Interactive Scala Shell The easiest way to start using Spark is through the Scala shell: -``` +```console docker run -it spark /opt/spark/bin/spark-shell ``` Try the following command, which should return 1,000,000,000: -``` +```scala scala> spark.range(1000 * 1000 * 1000).count() ``` @@ -25,13 +26,13 @@ scala> spark.range(1000 * 1000 * 1000).count() The easiest way to start using PySpark is through the Python shell: -``` +```console docker run -it spark:python3 /opt/spark/bin/pyspark ``` And run the following command, which should also return 1,000,000,000: -``` +```python >>> spark.range(1000 * 1000 * 1000).count() ``` @@ -39,7 +40,7 @@ And run the following command, which should also return 1,000,000,000: The easiest way to start using R on Spark is through the R shell: -``` +```console docker run -it apache/spark-r /opt/spark/bin/sparkR ``` @@ -47,3 +48,7 @@ docker run -it apache/spark-r /opt/spark/bin/sparkR https://spark.apache.org/docs/latest/running-on-kubernetes.html +## Configuration and environment variables + +See more in https://github.com/apache/spark-docker/blob/master/OVERVIEW.md#environment-variable + diff --git a/spark/issues.md b/spark/issues.md index 09392138d..3222af653 100644 --- a/spark/issues.md +++ b/spark/issues.md @@ -1 +1 @@ -https://issues.apache.org/jira/browse/SPARK \ No newline at end of file +https://issues.apache.org/jira/browse/SPARK From cbce68ea834d859aed904f968bd49b2acc6108e5 Mon Sep 17 00:00:00 2001 From: Yikun Jiang Date: Fri, 30 Jun 2023 12:04:11 +0800 Subject: [PATCH 3/3] Addresss comments --- spark/content.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/spark/content.md b/spark/content.md index b13a962e1..380ac1aa6 100644 --- a/spark/content.md +++ b/spark/content.md @@ -13,7 +13,7 @@ You can find the latest Spark documentation, including a programming guide, on t The easiest way to start using Spark is through the Scala shell: ```console -docker run -it spark /opt/spark/bin/spark-shell +docker run -it %%IMAGE%% /opt/spark/bin/spark-shell ``` Try the following command, which should return 1,000,000,000: @@ -27,7 +27,7 @@ scala> spark.range(1000 * 1000 * 1000).count() The easiest way to start using PySpark is through the Python shell: ```console -docker run -it spark:python3 /opt/spark/bin/pyspark +docker run -it %%IMAGE%%:python3 /opt/spark/bin/pyspark ``` And run the following command, which should also return 1,000,000,000: @@ -41,7 +41,7 @@ And run the following command, which should also return 1,000,000,000: The easiest way to start using R on Spark is through the R shell: ```console -docker run -it apache/spark-r /opt/spark/bin/sparkR +docker run -it %%IMAGE%%:r /opt/spark/bin/sparkR ``` ## Running Spark on Kubernetes @@ -51,4 +51,3 @@ https://spark.apache.org/docs/latest/running-on-kubernetes.html ## Configuration and environment variables See more in https://github.com/apache/spark-docker/blob/master/OVERVIEW.md#environment-variable -