From c862af0c296e9269c7f59a19e21d787c6cc4139b Mon Sep 17 00:00:00 2001 From: Dirk Date: Mon, 7 Oct 2019 22:29:14 +0100 Subject: [PATCH] Initial commit --- Generate-ScriptMarkdownHelp.ps1 | 61 + OutConsoleDiff.PNG | Bin 0 -> 11414 bytes PSDiff/PSDiff.psm1 | 367 ++++ PSDiff/README.md | 21 + PSDiff/docs/ConvertFrom-DiffToHtml.md | 76 + PSDiff/docs/ConvertFrom-DiffToText.md | 50 + PSDiff/docs/Get-CharDiff.md | 61 + PSDiff/docs/Get-CommonOverlapLength.md | 64 + PSDiff/docs/Get-CommonPrefixLength.md | 64 + PSDiff/docs/Get-CommonSuffixLength.md | 64 + PSDiff/docs/Get-LineDiff.md | 77 + PSDiff/docs/Get-WordDiff.md | 77 + PSDiff/docs/Out-ConsoleDiff.md | 104 ++ README.md | 10 +- Source/DiffMatchPatch.cs | 2307 ++++++++++++++++++++++++ Tests/DiffMatchPatch.Tests.ps1 | 88 + build.ps1 | 17 + 17 files changed, 3506 insertions(+), 2 deletions(-) create mode 100644 Generate-ScriptMarkdownHelp.ps1 create mode 100644 OutConsoleDiff.PNG create mode 100644 PSDiff/PSDiff.psm1 create mode 100644 PSDiff/README.md create mode 100644 PSDiff/docs/ConvertFrom-DiffToHtml.md create mode 100644 PSDiff/docs/ConvertFrom-DiffToText.md create mode 100644 PSDiff/docs/Get-CharDiff.md create mode 100644 PSDiff/docs/Get-CommonOverlapLength.md create mode 100644 PSDiff/docs/Get-CommonPrefixLength.md create mode 100644 PSDiff/docs/Get-CommonSuffixLength.md create mode 100644 PSDiff/docs/Get-LineDiff.md create mode 100644 PSDiff/docs/Get-WordDiff.md create mode 100644 PSDiff/docs/Out-ConsoleDiff.md create mode 100644 Source/DiffMatchPatch.cs create mode 100644 Tests/DiffMatchPatch.Tests.ps1 create mode 100644 build.ps1 diff --git a/Generate-ScriptMarkdownHelp.ps1 b/Generate-ScriptMarkdownHelp.ps1 new file mode 100644 index 0000000..5ff4d9c --- /dev/null +++ b/Generate-ScriptMarkdownHelp.ps1 @@ -0,0 +1,61 @@ +function Generate-ScriptMarkdownHelp { + <# + .SYNOPSIS + The function that generated the Markdown help in this repository. (see Example for usage). + Generates markdown help for each function containing comment based help in the module (Description not empty) within a folder recursively and a summary table for the main README.md + .DESCRIPTION + platyPS is used to generate the function level help + the README.md is generated "manually". + .PARAMETER Module + Name of the Module to generate help for. + .PARAMETER RepoUrl + Url for the Git repository homepage + .EXAMPLE + Generate-ScriptMarkdownHelp -Module SearchLucene -RepoUrl https://github.com/DBremen/SearchLucene +#> + [CmdletBinding()] + Param($Module, $RepoUrl) + $summaryTable = @' +# PSDiff +PowerShell wrapper + additional functionality around the diff part of https://github.com/google/diff-match-patch + +This is using a slightly customized version of the c# version provided in the diff-match-patch repository (mainly replacing protected by public and implementing the suggested line and word modes). + +![OutConsoleDiff]($($RepoUrl)/blob/master/OutConsoleDiff.PNG) +For usage check the documentation and the tests. +The PSDiff module exports the following functions: + + +| Function | Synopsis | Documentation | +| --- | --- | --- | +'@ + Import-Module platyps + $htCheck = @{ } + Import-Module C:\Scripts\ps1\PSDiff\PSDiff\PSDiff.psm1 + $functions = Get-Command -Module $Module + foreach ($function in $functions) { + try { + $help = Get-Help $function.Name | Where-Object { $_.Name -eq $function.Name } -ErrorAction Stop + } + catch { + continue + } + if ($help.description -ne $null) { + $htCheck[$function.Name] += 1 + $link = $help.relatedLinks + if ($link) { + $link = $link.navigationLink.uri | Where-Object { $_ -like '*powershellone*' } + } + $mdFile = $function.Name + '.md' + $summaryTable += "`n| $($function.Name) | $($help.Synopsis) | $("[Link]($($RepoUrl)/blob/master/$Module/docs/$mdFile)") |" + } + } + $docFolder = "$(Split-Path (Get-Module $Module)[0].Path)\docs" + $summaryTable | Set-Content "$(Split-Path $docFolder -Parent)/README.md" -Force + $documenation = New-MarkdownHelp -Module $Module -OutputFolder $docFolder -Force + foreach ($file in (dir $docFolder)) { + $text = (Get-Content -Path $file.FullName | Select-Object -Skip 6) | Set-Content $file.FullName -Force + } + #sanity check if help file were generated for each script + [PSCustomObject]$htCheck +} +Generate-ScriptMarkdownHelp PSDiff -RepoUrl https://github.com/DBremen/PSDiff \ No newline at end of file diff --git a/OutConsoleDiff.PNG b/OutConsoleDiff.PNG new file mode 100644 index 0000000000000000000000000000000000000000..08e41774cf5059f6bfdedb1207c6902570087f27 GIT binary patch literal 11414 zcmeHtXH=8j7G^|L5R~2o<&zeb5&?xE2vQX3DvI=&Pz3@6q?cGQ(vc#OCV~`^UPF%% ziV%u`^b#QgLg)}mLc+xFyZ5e{`)k&kHEYd}`IGaWtn;3;`+4@>Z^S)g-7}}pody5^ zXY}ssJOBWgaExaR%Sp!X-bd3$#&FF0fvy&yq)%jtF=2MnG|~hB%H!A$p(hw~R?oW@ z-T=T^##?7`$2vVe+XDbH(t0|Y5B+UdGc;mnz74!tY`}f^`u&7R^ve^w02H^bv2MJn zknqYGncGZe+qqahvo_rph*z0-neaix)DTebZ}*Zib3kHTu}GXfwvG18qp`znjfl?&{i3PsM@8srvDWoW!V<})Zhu?3B&1-2^5tNWHIjwvE#zoC z;_jUvqDHETrIYo1|&# zrK8xiyCD?fcC94r98!QlyIAFMo0k6_q9STtyRGTu?q*Xs0B1n#-qxf@5vjm+DRww zM2#K9gKn$M(2T1?Be~}IcN=p(?Q^X$)nL;r$U}dwtauIQ4iMLp4v)Ca-Y9Ap}Ui;8uD|4rd+}!J)^Oi5oCG=GU%9AEC zl8d(%(W;s5*!?3A?`z-?eh80>Ak$+cCs~9$hrpfgz zM0&2sWdTXW&*t!N!)|}Rn}Myuoc>mWIH{76b(XgO<)EE44qL;d7(N88`wim5ihV?O zIrbEj^Lip?pCWOA*X3oLn;m@n*N+3k^GNR$Rv#S`Sa-*=vUOX$Z4QXf4cCrgQ!Z(I z?oG`}tM0+uzZ?Q>zpN2Ro%VW#O(Mg_4m7gpcj|q`QO5vJ-n@5De9zs{v~dpj>#r|? z$M|(}jM(?IDj+psmquh2V=0D9=7x*3)AJqVZ-x^|o`&TkX$nA8F+H!%(-{*QWl&&} z>#JKdFXONIdxCT#^$_U@v1)gIf5NBPntkvnuKQ8sWHrnjoJ+s65X=MsOesIwV~42i z*VF}Wmed`PeY_>HHeTu6#R&kD+wA=jmDbl>v>uXlizW%#e^pkc)_(r1?4Zv+y00oA zFJpbE-DY+TSbr$XN(`|TU$`-FSxG+BrG55+e2VuK8sAIK54)@YfF~h+r^l1i$@rmU z&g5A8#`(v$lfuzQ)reOWCv1c=VVn(%}e2 zjkTdBX?$U9yBl@|<*^Fq4p2c`SEtO^1~Z;pb3Bu7SZ~E~v^<@=#{)NL_iP(Y+^=NF ze;BB_ou4(Tded}ubls5MAZYMZ)5*E3eb3}L-%Lm62@88qn$vE(;1|=ikPd`E&6|oi zb^xFZ_+?FKc!}ILF2Y(8l*ykpH=que1iAk zSM5FHX`Sfy(4?8xCw#baYu?FFi@oG%dn>ypFB9kJ+vXrGb-A=%Ab!sE=iu&bdF#Ob zvMS)nWRsB?y>C}H8kZ3Y9Bq)<`;n93{8Y2d-ycmX=zYR;pjwd-K3dmZ2-o z@rUf|@pxTAjhe>?{p?_}nuTve#Natx)G0!}{ZUEX(?l>#aJOS7PMoXN>u^e9HNh^D z$cQldMf^CiU%_6_9F9}q+;sj(j7F`*yS|x5*AhrH&yqiCk-VIeUy>nb;X*oL(4?R} zPmPxu3O4D>b07yH-49}VK4Vxjew_(&810O25d{El^+_q>1Q4iiz!DYt!;(5g#O4>H z=-CTI==o{({-{Ouay_kvt@#m~NLk4{u1)fC$`RolFMX#x>fjRLlc6VNjYd?;&xAwA zr1L#RZtKGtcQvOH!wq}pdcvWuT8*!TJ|x7Y25M_)Lk5rX9fIrh5mADuChyao_wDtF!YwQV#v;c^ymuaE-h8= zdDe86%b3)hSti%C;k1uT^pwMNnWy^(x+IyxR=>c1NH~J)8{$6%7 zw%)h5=PF|_XTdhlEoML6xv!F0?g6|weU(DN*a(n%%o@fAZ@=K&8;!UeVMQ9|_D=ml zRDdYiGWq)KmM1cJp7ZMbU2u@4@to>d+Ib%fx6V}9IRyZ`eZY%bZbEjgc+|?M+=ldB zLD9U>zYiUT`r;bnYE4QEE=eM?9M%Tg%2lSVyld$QK-*Jz{td)D^3pUw6S_D0CTL9 z3jjzLZ%>(JSoYbwqq$R$Riw?3L7-EfndY5KGkAtu>eL!BF5~|NpZ+&q{okFN&u+Ch zEMOoI<;UGOW|tpPx<<+KfIhBRhEl;Nd}UFf4~@I58Ocui@!0|zO zR5e!k*6BYCP5~QuaGMFgV|p&#q_nWj<#v6e29m99fH|bw&ox4XmuqZen@AF&vvY`> z&O}v#G>{!cIy0Ia$j zlGdg#zmm9UMN@zqPAG#Y68@W)tYe#Yx?CZ8jd8aLGaH?);P~$OCG(Lz-Mb@Hg=V7) z_=ex+?*LADy~Z2RPb?Qf&!u2&izhm{7zBS+@g9MJd%ped@?PWqJ>`4ZFSRWO&Yj$0 zl-4r1JioPB{u4YnYSMyW26$SgV+4&IgJE+Kl~+huk|~T_vMA zc+;yC>}kzo`5c|`&7r3mvVJ}^*VtZWatqEa0FgUpi-jZmC9-cyAzC0WjV{O}g#~3u zj5b@VxYKPrUzE-`$+-nnKkeU_i^2uq5ZA0fwEj7ll3pixmQ}X~ts@Zur1>q|HZ@6Y z@@9rjp7PrYbBRd9KE6MZB(d^+9l^~(=a#QRK%NjhMb2RKX8*`6q|cI_EuqNW_M5h> z9=BK5B)0O|9P5GU-8rtz=xyK>8)8Uq{B%|ZQ9`aQFgPWmw&kD|aSg@L`A@a648i1- z)U~eFfuSjilJ|ZNk-Ju6jlPw0ctNTh+63p0!zKnc0O!w7>jKP@D!D1MZMqe3(M;(0 z`<#%$)#a7-xM;d^25HM7P}dkBGeO{9t21X}w!l zSAH^rJ?v$L`e1UDj}>R;ryw31Eh7lm^-JrN z475>VX-^<|-O?u%q9$4uB*Tu1(6BkR$kBNplKh8@#xXLSyG#_u-Jhrm82clWG0|}7 zB{B3DTC`}T1t9A0zkuP;_qh!#vYGE6jU2xv^oK6mOTj-W?{nP$G(OkRBU*#OL9ThOiI@Q-Oh83Wl8^tS5l;n>$U zSs`8t!ofYaE}NS6waz4V#3xK}8y|oN!#=(SJ?>A9)97REf76S`zv*3k>0E=B_AZ3& zGYFt)+c2q14s~=`a^kjq$t@Ym>iGs&%O6k}<@Zx@gZ!O!4J z!M#177Zj)FJX+W>ab1RlA@cRrsQqR_wV+&^g&^djf73EgjX+%bd;DG}+n(;@2YHSn z)=l5A#tX2->e4*y*1=p~=6a!=Z80L=4)qPbys!Y)!?DvLn;n&pefYZ4@xsZ(066-q)9(H2-W*OF5XgxWCr zRat0_+&D+@4P+)SGN5T4qGXa7=#adM;fQM>)U}f*#@@f$?)VNlHgJ}!1bU7}C=gsDPRVYUFXP+yyB6WO z1aB%%Yq38j3-5c>fryVSYz#3aqm=L!N}9D{OP$U&nSscVR#WO^WUt(;KQe2|lQ1#I zO>5s2=;#`QoM9-xw?FUXCRLp;5j|Uj0zFQs-Mxe&TwAw6s$*J}_GwKA{_m1}wDy~< zcIoSJlcAlH*Jhr*tW`v>$eqai3~Vbico>S5fN641#cV6<@1JDT+cNSdp14!dGsvd`n6D2bA?HVcUT`U16I1U4A3Xy0L6l_SX6u~YKi}^?y8$NSK1(WV&MXf#L zb8`a0@St?I{EH~sG0V(Du@J4{Q8t?17YILy%_QQ@_mT(+^~#du@jyp88>>l9O0!L! z$__a0Xl$Hv`o)5YT^BgqnfPPbWYq)x_4Itvrs?6Z=W^$LMQImNWlbHdHZ47g2F3Vvo407&KVl|VK@sHG9j~JoOf`XYM+AH{BedwVX8OJF=+LSL#X)e7nb0e$%9{c(} zSil#A!WG>|{w3G)q3w;H-y?1h3>lsMt90{Mj+uco5-h(Pier_wQJ(0#BvIAuYL4%f zpBKN$+8<%->ZM=6HDJ)8X@8?&o~{*C|4U(@xzX0ux`^(gLMC47Nw{-NsLcb&dy1ss zD~;+@N6q=k#8!KWD@q6>mmWBJoa`!|(Msqco$e|%Nf^p@wtU~_8$0^cPMhHzVOUG) zNOdB;SOE{VQ7D=4L8P_RcZc#46?}rDZ~yul3G-jtH2dt=u^XJO%K$JqR_HkG#pMNw z4-rMz^`=VE24qt9iXFBVL0217k*HME;RiPNi5&OqBUj6hTcUc}o? zY4`9Ztu9_#?c^na-?m-k@ZF^FGas zruCZ=LRDQ#R8qPI_AuNptj_*jxkk{Jjy1JwI=*=wh_ZqzwLg$oyP=*pxmqlNit3z9 zy3~sw?=>sE9{Rw&fv8qtATM(&^C;@Ns;10*bAo^5x+(QZYZCVIT-V(R&}!1^5OUks zZ*uh!yR>?hP~-&Ih>P}AQC!7Rts24Ekx$Z9P}gq67`osBixK6N!ucO@pBRNbj8?dF z67|&(@;YKkWiw^ACFJ{Qap{QJ7hN|)W;N3$4H8VdR5B54^E%eyka2aIa`I3Is^bSD z2a&UVM>OOU-|bAFqY`;|`Z?0|sM+8t{*_;Co>?vj!GTOPbtb_y`b1<Nb{OrsILDPe;XBP=uy2AusmY#bv|OrE`6QoZz z@$vCoTJ_+;w%x~=pB0}xzLRgkr z-#LLo>^TPN*_tcki!RuRX;t8h5504}*!x!cFx&|?tPs26d!jn}-ut>?mh2h$B1Igg zydOxUe4OG&9Qf~lfL=z2+sSACY#^&F$t3cyy`o+{FUOi&TJ}ZWJAv0V5e8Y`pnaN| zkWkl8cemix{P!gv?fR~cmJpXR&|J9!seBYY^q|T1qfmPpM5{#eX2e9m_DbY#C!S_;%f5Oi9^t&ASHWe_na6{gGAk?og-ve*s`Yz}Xj4%omMBJFmjso@ZQ37OZ(Z)UhTK z4h6iw&2taH`St3`nj!wa)pJ4j0b2*tR*y>JsdW8S;pQ2a5EV9qxnL{9rZ3;RlM!`n z$-9qv0H)7M4b6#C%t-rfw2!J~NoJf*hV3J^2dX_><%8vt z9N&tMczLIz1<$&1p>GAGm)Lp0z+*POJ;j&?KAZzvDVH`osRo0{o&PM$$k=w#9}@em zPs>Lv;$?LZH^sJxBdS)|G)GfBe@_e^r1EPnqoeqHJYD7W^hQUkKwcnNEvFNd7yGW1 z{amm`!L&dsxTqMzD-fkY0+StLRx5WgVFG|v^yHnxeJ~em#9dd71L5v2fqt(nUgq2D zu6LNv1heu$ETw;fI-ORHgi1=CA^4{7Sy=k{fWy$x@nFjh*5BXI*f?xpe&lR-U=*T! zUoqA+t~?}{e$qhw?%NPeR|yI`#FErD`mrcD!qxItUlc#1OoH`Y=yoaXt_aoa{mxO| zg6?S>U37r?Z_F#Vqe$B4Lqw(K21C2tbjz+jn@Gz z5I$nQv)*;c;1@QaJ}43!wRDeF>zh^(Eo`=qChR+GkvDm=$D*m?ZL&X9qisT(yb%SP zPD1%+$Pv2bZ=IH5MbK#-_HPbwlZFy$;_ZpFg(e=C%%-w%G?ozk`p(YmiJmYPua}Y| zLg)xUaOr{c--q33c={Cb^3g9#2HJ}C-bw2Xuh|SDgoFk-BF&xK9kCh`?pZU?m1R;! zjKOOSJoq|QaYxyb^E~L)CHh7WYww%h`NdA{mL={cjZj@t#qa7kYF-_JNz5HNei~CC z)T1)MJ)(EMc;EBoXp|t=C3s3%BRrGG1l?@Aq;0Om`LH8Yr+gfF(xNRfDG^Qzvj=`o zaA>;BWHqN;U!%@` zhN)8v|JY%Z;BMCpL29x*12T|Z62&!Te}=ubQBC{R%7{ZK);_3pM!I+wO!}E zG+RM-Ubw0NREp91(NR@Rn;4L*`9^t&PVjvmQKHu^^h z&g$_EyCzYnr}Al0&o3X#j(YvXaex~xfm&?$^%w~?d}nn@tjRfM^^AIbJ!88`L-s{= z{#{(k8mO&s&nbF)uvV~Ft%L!((-_#^h0XV-qKF)yhQ|j=3bbzVKIn0)49Xi(p~X%m z!zWemgF-&@ifK9PN~3Z?#!n!B>RhZ_O_9*s5A*P#44^|DU~(hjp}@qo}|4I*Z1< zM4on_2D}7|tak<S zE4Wt?sp_iXRn7x<3Fyk1sc911n!&o25HQ$9=5;feKd+x_V@DnpPlUy6x7G^6L#-vv zxN*Yde@78E14m}@JxP?QPPlb7$FOqI)`16v-RM| zo$by;#4DAY7f4a_5Dg-*?K9529CPtuZUAWUlXoKw;01&tsL8RCyAbvvZ&GqJyHZGB;dLHb8t z{-UKe?47IU@4NY`Q{kVm`yI^Kq9ChV*dF~2ftgm$iAzimLP4&Oy$)7gf8myHuRAY2 zpTUh`JQFGHxjgQh#jGXiR#K(BX@^An*pjoO?t50d*eMr<$joX+KK+Gq|3bba5=FnG z$ci>*>ByhYxaY~h@(&6wu`spC@@Ni4K4MfgH~-`s%QF%2?iMn`k-tme3U>Pyb@abV z)$q)IZkasyd^{4rQ@NNEs>TmC9nzogc<_De7LpCWGTyu%#qzZrD|q}Vwn{U~pz1G| zT;#M;NybwZo1W=r!IE>JyjsEHDBM&nHwoX{9)SNR2n3{sg^TM=cyXRco_0+WoBJyI zJ>C~}y#x~p)gUHQgnlyL$H4vB?$|m74?mK zAugkL|9$(5(=Mia@GWK6l9xVXQLaYjXK`p&2}SCC$&MSznFus4Yqm3Qyw{Zgd*MDw=U=nz^=< z@3Pc8JQY1`4)=+@=LkB5@C9E?p~ruWs#E2}!IHtkM3^GAwxZ)-k~CiU00q>FK7axM z+U~e#o6n)|lRwn}Z);l!PAQBMVU#@=O8 z>kJYM$*dZcfu@aZR2vK-YLZn`hdbs=Ix7EO$|w*KsXpl7YPjs|@l(XTMkWzfz2{Ds zQ5qVqB^v3znL1a8vAWMDYRCe%&4i{Z4GYCK@)La)?o|`(2!fL5vqc7KqAJ?`AXs%WvZWj8 zbH!p^_8`!7w>@i9AVP*-l#H}_ddJ=wGDj)e8MRlyp^@|5!%bD9s{;9Vax!~j^4dY` zZ^j`Z8jP=}2sJB}Ed$nsJDI#nW68vELf^;srs_dTLT_ik(g(~+=|6&zMm2@|Fx66b zRsbSm%33 zzmsv2H@{9R{;x=laKb-`4f<%d-|azMse#T&*f(dAQF|#%gk-CM49mIk8uB6?up#Ey z?$%(<9|zx|aV3yvq=?ENj@9g24aNn?k4`?TGuycQaxgCIg#1cpWnt-bW)@vW4z(!| zY*Y=MORVHGi-t@+RwVwhy1(^;W;DCHZ){#UB51KYDK>8IvKg(MhNj)a)~GwV@C*GE zdCM%w?Ig#XI6gh{43Qlr1W}q)$DBhBD*;i9BX9?A#Si=>=Aa6h$}jsuhXrQ8b?^67 zD_I#&i{d>C~!Njmx9E5ZG_}^ZHN%-S*z!yS8~2A(w4oEm)|QV``%BRYms2=p4P9DGRVddFIQN#-q+{$k#-~5;CVt5B&YH0^8uq{h0NMV= zhX5J2sTmmuR|fZts@cNir*M3LaHpP3c={wS&UBM4+v!JKHr9bw7O7%TCy0d91ZwOo zU^2t;37azWzp^Ux5qHdCOEudZnZ?fe@2`iF{-BKs6{ep*#^;YeyX@za7B+ue*v85d zxkcS-CoNFkHM*SnTLHIjrd*l(%=eHs^xNGEV`w{^6m==_`{xa(%H1yN&JuNBmCL&v zyTtB%RP#DCrPp$EoIE^CUUKlJX*#Ap4xd$`+lu&xd|UIl(C%^Q`+P>9euXjs7bOi5 z-Q)y{GhR1GWP4{>v@?Ws0y$Wst|S)iksNF4ZB6k?-fX;$toCO9TJTEHIMiyHb0EFB z)O_aE6ns6ocN%ugGjc!dvy^E_-c_UrBT*ws)ZMAhI$n7 zC`S<#r%p%yG?2@}yFsPprYizpOsDeP3J}&6L)^n8r39FGcV!lc(mdY1c=B*W_ec4F zyPc4-q9gwsSn}rL>))PMkT+H}`*Hat&Cxm2Bb$v5|Ik$##EAWS25DmQZm0N}r{**+ zlnv+o(dzj>p*=xLi@iaaDppCxmVV&t7)kk8NC#XsNM(^vZf2;XpvP|dNOw~VJ zGA@ll9mba@ip!t7yNf?^Z$kUt1a}x(Xq_gNE+AmP#S|GfZlCm Kof54lFaHN_Ge+0| literal 0 HcmV?d00001 diff --git a/PSDiff/PSDiff.psm1 b/PSDiff/PSDiff.psm1 new file mode 100644 index 0000000..ad0104b --- /dev/null +++ b/PSDiff/PSDiff.psm1 @@ -0,0 +1,367 @@ +# Import the functions +$srcPath = "$(Split-Path $PSScriptRoot -Parent)\Source\DiffMatchPatch.cs" +if (!(Test-Path $srcPath)) { + Write-Warning "$srcPath not found. `nPlease download DiffMatchPatch.cs from https://github.com/google/diff-match-patch`nand put it into the folder $(Split-Path $PSScriptRoot -Parent)\Source" + exit +} +$assemblies = @' +System +System.Core +System.Linq +System.Web +'@ -split "`r`n" +if ("DiffMatchPatch.diff_match_patch" -as [type]) { } else { + $code = (Get-Content -Raw -Path $srcPath) -replace 'protected', 'public' + Add-Type -ReferencedAssemblies $assemblies -TypeDefinition $code -Language CSharp +} +$dmp = New-Object DiffMatchPatch.diff_match_patch + +function Get-CommonPrefixLength { + <# + .SYNOPSIS + Get the length of a common prefix for two strings + .DESCRIPTION + Function from https://github.com/google/diff-match-patch + .PARAMETER Text1 + The first string + .PARAMETER Text2 + The second string + .EXAMPLE + # returns 4 + Get-CommonPrefixLength "1234abcdef" "1234xyz" + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0)] + $Text1, + [Parameter(Mandatory, Position = 1)] + $Text2 + ) + $dmp.diff_commonPrefix($Text1, $Text2) +} + +function Get-CommonSuffixLength { + <# + .SYNOPSIS + Get the length of a common suffix for two strings + .DESCRIPTION + Function from https://github.com/google/diff-match-patch + .PARAMETER Text1 + The first string + .PARAMETER Text2 + The second string + .EXAMPLE + # returns 4 + Get-CommonSuffixLength "abcdef1234" "xyz1234" + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0)] + $Text1, + [Parameter(Mandatory, Position = 1)] + $Text2 + ) + $dmp.diff_commonSuffix($Text1, $Text2) +} + +function Get-CommonOverlapLength { + <# + .SYNOPSIS + Get the length of a common suffix or prefix overlap for two strings + .DESCRIPTION + Function from https://github.com/google/diff-match-patch + .PARAMETER Text1 + The first string + .PARAMETER Text2 + The second string + .EXAMPLE + # returns 3 + Get-CommonOverlapLength "123456xxx" "xxxabcd") + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0)] + $Text1, + [Parameter(Mandatory, Position = 1)] + $Text2 + ) + $dmp.diff_commonOverlap($Text1, $Text2) +} + +function Get-LineDiff { + <# + .SYNOPSIS + Get a diff of two texts based on lines rather than chars or words + .DESCRIPTION + Function from https://github.com/google/diff-match-patch + .PARAMETER Text1 + The first text + .PARAMETER Text2 + The second text + .PARAMETER Delimiter + The line delimiter for the text elements. Defaults to "`r`n" + .EXAMPLE + Get-lineDiff (get-content .\txt1.txt -raw) (get-content .\txt2.txt -raw) + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0)] + $Text1, + [Parameter(Mandatory, Position = 1)] + $Text2, + [Parameter(Position = 2)] + $Delimiter = '`r`n' + ) + $dmp.diff_lineWordDiff($Text1, $Text2, $Delimiter.Replace('`','\')) +} + +function Get-WordDiff { + <# + .SYNOPSIS + Get a diff of two texts based on words rather than chars + .DESCRIPTION + Function from https://github.com/google/diff-match-patch + .PARAMETER Text1 + The first text + .PARAMETER Text2 + The second text + .PARAMETER Delimiter + The delimter that separate the words in the text. Defaults to " " + .EXAMPLE + Get-WordDiff "this is a test" "this is not a test" + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0)] + $Text1, + [Parameter(Mandatory, Position = 1)] + $Text2, + [Parameter(Position = 2)] + $Delimiter = ' ' + ) + $dmp.diff_lineWordDiff($Text1, $Text2, $Delimiter.Replace('`', '\')) +} + +function Get-CharDiff { + <# + .SYNOPSIS + Get a diff of two strings character by character + .DESCRIPTION + Function from https://github.com/google/diff-match-patch + .PARAMETER Text1 + The first string + .PARAMETER Text2 + The second string + .EXAMPLE + Get-CharDiff 'this and that' 'tit and tat' + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0)] + $Text1, + [Parameter(Mandatory, Position = 1)] + $Text2 + ) + $diff = $dmp.diff_main($Text1, $Text2) + $dmp.diff_cleanupSemantic($diff) + $diff +} + +function ConvertFrom-DiffToHtml { + <# + .SYNOPSIS + Convert a diff to hmtl, output to file and open in browser (unless specified) + .DESCRIPTION + Function from https://github.com/google/diff-match-patch + .PARAMETER Diff + The diffs (output from Get-*Diff command) to be converted to html + .PARAMETER NoFile + Switch parameter if specified, the command will only return the html output + .PARAMETER NoOpen + Switch parameter if specified, the command will put the html into a file and only return the path to the file. + .EXAMPLE + Get-CharDiff 'this and that' 'tit and tat' | ConvertFrom-DiffToHtml + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0, ValueFromPipeline)] + $Diff, + [Switch]$NoFile, + [Switch]$NoOpen + ) + BEGIN { + $diffs = New-Object System.Collections.Generic.List[DiffMatchPatch.Diff] + } + PROCESS { + $Null = $diffs.Add($Diff) + } + END { + $html = $dmp.diff_prettyHtml($diffs) + if ($NoFile) { + return $html + } + $path = [IO.Path]::ChangeExtension([IO.Path]::GetTempFileName(), 'html') + ConvertTo-Html -Body $html -Title 'Diff by https://github.com/google/diff-match-patch' | + Set-Content -Path $path + if ($NoOpen) { + return $path + } + ii $path + } +} + +function ConvertFrom-DiffToText { + <# + .SYNOPSIS + Converts a diff (output of one of the Get-*Diff commands) to a source (text1) and destination (text2) + .DESCRIPTION + Function from https://github.com/google/diff-match-patch + .PARAMETER Diff + The diffs (output from Get-*Diff command) to be converted to text1 and text2 + .EXAMPLE + $srcText = "jumps over the lazy" + $destText = "jumped over a lazy" + $res = Get-CharDiff $srcText $destText | ConvertFrom-DiffToText + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0, ValueFromPipeline)] + $Diff + ) + + BEGIN { + $diffs = New-Object System.Collections.Generic.List[DiffMatchPatch.Diff] + } + PROCESS { + $Null = $diffs.Add($Diff) + } + END { + $dmp.diff_text1($diffs) + $dmp.diff_text2($diffs) + } +} + +function Out-ConsoleDiff { + <# + .SYNOPSIS + Diffs two strings and outputs the results side by side in the console color coded and with line numbers. + .DESCRIPTION + Uses Get-CharDiff but adds handing of array input (strings with multiple lines need to be split by new line) + by inserting a replacementchar to mark new lines. The color coding is done using ansi escape sequences. White on + red for deletions and white on green for insertions. + .PARAMETER Text + The base string + .PARAMETER Text 1 + The difference string + .PARAMETER ReplacementDelimiter + The string used to replace newline characters internally, Defaults to 'ÜÜÜ' + .EXAMPLE + # Using file content as input + $txt1 = (get-content "c:\txt1.txt") + $txt2 = (get-content "c:\txt2.txt") + Out-ConsoleDiff $txt1 $txt2 + .EXAMPLE + # Using string input split by newline + $txt1 = @' +will stay +this will be changed +this will be deleted +'@ -split '\r?\n' + $txt2 = @' +will stay +this is now changed to something new +replaced with new line +here is a totally new line +'@ -split '\r?\n' + Out-ConsoleDiff $txt1 $txt2 + + + #> + [CmdletBinding()] + param( + [Parameter(Mandatory, Position = 0)] + $Text1, + [Parameter(Mandatory, Position = 1)] + $Text2, + [Parameter(Position = 2)] + $ReplacementDelimiter = 'ÜÜÜ' + ) + #put the replacementdelimiter at the end of every line of the texts (lines remain array items) + $regex = '(?<=' + $ReplacementDelimiter + ')' + $txt1 = $Text1 -join $ReplacementDelimiter -split $regex + $txt2 = $Text2 -join $ReplacementDelimiter -split $regex + #handle txts of different lengths substituting the empty line/array item with '' + $len1 = $txt1.Length + $len2 = $txt2.Length + $maxLength = [Math]::Max($len1, $len2) + $diffs = for ($i = 0; $i -lt $maxLength; $i++) { + $t1 = $t2 = '' + if ($i -lt $len1) { $t1 = $txt1[$i] } + if ($i -lt $len2) { $t2 = $txt2[$i] } + #get the character based diff based on a line by line comparison + Get-CharDiff $t1 $t2 + } + + $diffText1 = [System.Text.StringBuilder]::new() + $diffText2 = [System.Text.StringBuilder]::new() + #ansi escape + $esc=$([char]27) + #run through the diffs and rebuild text1 and text2 color coding the diff text with white on green for insertions and with on red for deletions + #esnure end ansi escape sequence '[0m' are preceding the replacementchars to remain on the same line + foreach ($currDiff in $diffs) { + switch ($currDiff.Operation) { + 'Equal' { + [void]$diffText1.Append($currDiff.text) + [void]$diffText2.Append($currDiff.text) + break + } + 'Delete' { + [void]$diffText1.Append($currDiff.text) + if ($currDiff.text.EndsWith($ReplacementDelimiter)) { + [void]$diffText2.Append("$esc[48;5;9m$($currDiff.text.Replace($ReplacementDelimiter,"$esc[0m$ReplacementDelimiter"))") + } + else{ + [void]$diffText2.Append("$esc[48;5;9m$($currDiff.text)$esc[0m") + } + break + } + 'Insert' { + if ($currDiff.text.EndsWith($ReplacementDelimiter)) { + [void]$diffText2.Append("$esc[48;5;10m$($currDiff.text.Replace($ReplacementDelimiter,"$esc[0m$ReplacementDelimiter"))") + } + else{ + [void]$diffText2.Append("$esc[48;5;10m$($currDiff.text)$esc[0m") + } + } + } + } + #split the now color coded diffs again at the original new lines (marked by the replacement char) + $diffText1 = $diffText1 -Split $ReplacementDelimiter + $diffText2 = $diffText2 -Split $ReplacementDelimiter + #handle texts of different lengths and substitute missing lines by 'n/a' + #also add the linenumbers + $max = $diffText1 + $minCount, $maxName, $minName = $diffText2.Count, 't1', 't2' + if ($diffText1.Count -ne $diffText2.Count -and $diffText1.Count -lt $diffText2.Count){ + $max = $diffText2 + $minCount, $maxName, $minName = $diffText1.Count, 't2', 't1' + } + $t1 = $t2 = '' + for ($i = 0; $i -lt $max.Count;$i++){ + if ($i+1 -gt $minCount){ + Set-Variable $minName 'n/a' + Set-Variable $maxName ($max[$i]) + } + else{ + $t1 = $diffText1[$i] + $t2 = $diffText2[$i] + + } + [PSCustomObject][ordered]@{ + Line = $i+1 + Text1 = $t1 + Text2 = $t2 + } + } + +} \ No newline at end of file diff --git a/PSDiff/README.md b/PSDiff/README.md new file mode 100644 index 0000000..24acd3e --- /dev/null +++ b/PSDiff/README.md @@ -0,0 +1,21 @@ +# PSDiff +PowerShell wrapper + additional functionality around the diff part of https://github.com/google/diff-match-patch + +This is using a slightly customized version of the c# version provided in the diff-match-patch repository (mainly replacing protected by public and implementing the suggested line and word modes). + +![OutConsoleDiff]($($RepoUrl)/blob/master/OutConsoleDiff.PNG) +For usage check the documentation and the tests. +The PSDiff module exports the following functions: + + +| Function | Synopsis | Documentation | +| --- | --- | --- | +| ConvertFrom-DiffToHtml | Convert a diff to hmtl, output to file and open in browser (unless specified) | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/ConvertFrom-DiffToHtml.md) | +| ConvertFrom-DiffToText | Converts a diff (output of one of the Get-*Diff commands) to a source (text1) and destination (text2) | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/ConvertFrom-DiffToText.md) | +| Get-CharDiff | Get a diff of two strings character by character | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/Get-CharDiff.md) | +| Get-CommonOverlapLength | Get the length of a common suffix or prefix overlap for two strings | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/Get-CommonOverlapLength.md) | +| Get-CommonPrefixLength | Get the length of a common prefix for two strings | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/Get-CommonPrefixLength.md) | +| Get-CommonSuffixLength | Get the length of a common suffix for two strings | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/Get-CommonSuffixLength.md) | +| Get-LineDiff | Get a diff of two texts based on lines rather than chars or words | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/Get-LineDiff.md) | +| Get-WordDiff | Get a diff of two texts based on words rather than chars | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/Get-WordDiff.md) | +| Out-ConsoleDiff | Diffs two strings and outputs the results side by side in the console color coded and with line numbers. | [Link](https://github.com/DBremen/PSDiff/blob/master/PSDiff/docs/Out-ConsoleDiff.md) | diff --git a/PSDiff/docs/ConvertFrom-DiffToHtml.md b/PSDiff/docs/ConvertFrom-DiffToHtml.md new file mode 100644 index 0000000..26ed4e1 --- /dev/null +++ b/PSDiff/docs/ConvertFrom-DiffToHtml.md @@ -0,0 +1,76 @@ +# ConvertFrom-DiffToHtml + +## SYNOPSIS +Convert a diff to hmtl, output to file and open in browser (unless specified) + +## SYNTAX + +``` +ConvertFrom-DiffToHtml [-Diff] [-NoFile] [-NoOpen] +``` + +## DESCRIPTION +Function from https://github.com/google/diff-match-patch + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +Get-CharDiff 'this and that' 'tit and tat' | ConvertFrom-DiffToHtml +``` +## PARAMETERS + +### -Diff +The diffs (output from Get-*Diff command) to be converted to html + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: True (ByValue) +Accept wildcard characters: False +``` + +### -NoFile +Switch parameter if specified, the command will only return the html output + +```yaml +Type: SwitchParameter +Parameter Sets: (All) +Aliases: + +Required: False +Position: Named +Default value: False +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -NoOpen +Switch parameter if specified, the command will put the html into a file and only return the path to the file. + +```yaml +Type: SwitchParameter +Parameter Sets: (All) +Aliases: + +Required: False +Position: Named +Default value: False +Accept pipeline input: False +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + diff --git a/PSDiff/docs/ConvertFrom-DiffToText.md b/PSDiff/docs/ConvertFrom-DiffToText.md new file mode 100644 index 0000000..63094d1 --- /dev/null +++ b/PSDiff/docs/ConvertFrom-DiffToText.md @@ -0,0 +1,50 @@ +# ConvertFrom-DiffToText + +## SYNOPSIS +Converts a diff (output of one of the Get-*Diff commands) to a source (text1) and destination (text2) + +## SYNTAX + +``` +ConvertFrom-DiffToText [-Diff] +``` + +## DESCRIPTION +Function from https://github.com/google/diff-match-patch + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +$srcText = "jumps over the lazy" + + +$destText = "jumped over a lazy" +$res = Get-CharDiff $srcText $destText | ConvertFrom-DiffToText +``` +## PARAMETERS + +### -Diff +The diffs (output from Get-*Diff command) to be converted to text1 and text2 + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: True (ByValue) +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + diff --git a/PSDiff/docs/Get-CharDiff.md b/PSDiff/docs/Get-CharDiff.md new file mode 100644 index 0000000..5551fcb --- /dev/null +++ b/PSDiff/docs/Get-CharDiff.md @@ -0,0 +1,61 @@ +# Get-CharDiff + +## SYNOPSIS +Get a diff of two strings character by character + +## SYNTAX + +``` +Get-CharDiff [-Text1] [-Text2] +``` + +## DESCRIPTION +Function from https://github.com/google/diff-match-patch + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +Get-CharDiff 'this and that' 'tit and tat' +``` +## PARAMETERS + +### -Text1 +The first string + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Text2 +The second string + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 2 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + diff --git a/PSDiff/docs/Get-CommonOverlapLength.md b/PSDiff/docs/Get-CommonOverlapLength.md new file mode 100644 index 0000000..7c37ec1 --- /dev/null +++ b/PSDiff/docs/Get-CommonOverlapLength.md @@ -0,0 +1,64 @@ +# Get-CommonOverlapLength + +## SYNOPSIS +Get the length of a common suffix or prefix overlap for two strings + +## SYNTAX + +``` +Get-CommonOverlapLength [-Text1] [-Text2] +``` + +## DESCRIPTION +Function from https://github.com/google/diff-match-patch + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +# returns 3 + + +Get-CommonOverlapLength "123456xxx" "xxxabcd") +``` +## PARAMETERS + +### -Text1 +The first string + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Text2 +The second string + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 2 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + diff --git a/PSDiff/docs/Get-CommonPrefixLength.md b/PSDiff/docs/Get-CommonPrefixLength.md new file mode 100644 index 0000000..725e422 --- /dev/null +++ b/PSDiff/docs/Get-CommonPrefixLength.md @@ -0,0 +1,64 @@ +# Get-CommonPrefixLength + +## SYNOPSIS +Get the length of a common prefix for two strings + +## SYNTAX + +``` +Get-CommonPrefixLength [-Text1] [-Text2] +``` + +## DESCRIPTION +Function from https://github.com/google/diff-match-patch + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +# returns 4 + + +Get-CommonPrefixLength "1234abcdef" "1234xyz" +``` +## PARAMETERS + +### -Text1 +The first string + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Text2 +The second string + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 2 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + diff --git a/PSDiff/docs/Get-CommonSuffixLength.md b/PSDiff/docs/Get-CommonSuffixLength.md new file mode 100644 index 0000000..78bf40a --- /dev/null +++ b/PSDiff/docs/Get-CommonSuffixLength.md @@ -0,0 +1,64 @@ +# Get-CommonSuffixLength + +## SYNOPSIS +Get the length of a common suffix for two strings + +## SYNTAX + +``` +Get-CommonSuffixLength [-Text1] [-Text2] +``` + +## DESCRIPTION +Function from https://github.com/google/diff-match-patch + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +# returns 4 + + +Get-CommonSuffixLength "abcdef1234" "xyz1234" +``` +## PARAMETERS + +### -Text1 +The first string + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Text2 +The second string + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 2 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + diff --git a/PSDiff/docs/Get-LineDiff.md b/PSDiff/docs/Get-LineDiff.md new file mode 100644 index 0000000..ba7b5e2 --- /dev/null +++ b/PSDiff/docs/Get-LineDiff.md @@ -0,0 +1,77 @@ +# Get-LineDiff + +## SYNOPSIS +Get a diff of two texts based on lines rather than chars or words + +## SYNTAX + +``` +Get-LineDiff [-Text1] [-Text2] [[-Delimiter] ] +``` + +## DESCRIPTION +Function from https://github.com/google/diff-match-patch + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +Get-lineDiff (get-content .\txt1.txt -raw) (get-content .\txt2.txt -raw) +``` +## PARAMETERS + +### -Text1 +The first text + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Text2 +The second text + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 2 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Delimiter +The line delimiter for the text elements. +Defaults to "\`r\`n" + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: False +Position: 3 +Default value: `r`n +Accept pipeline input: False +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + diff --git a/PSDiff/docs/Get-WordDiff.md b/PSDiff/docs/Get-WordDiff.md new file mode 100644 index 0000000..bde43dc --- /dev/null +++ b/PSDiff/docs/Get-WordDiff.md @@ -0,0 +1,77 @@ +# Get-WordDiff + +## SYNOPSIS +Get a diff of two texts based on words rather than chars + +## SYNTAX + +``` +Get-WordDiff [-Text1] [-Text2] [[-Delimiter] ] +``` + +## DESCRIPTION +Function from https://github.com/google/diff-match-patch + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +Get-WordDiff "this is a test" "this is not a test" +``` +## PARAMETERS + +### -Text1 +The first text + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Text2 +The second text + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 2 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Delimiter +The delimter that separate the words in the text. +Defaults to " " + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: False +Position: 3 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + diff --git a/PSDiff/docs/Out-ConsoleDiff.md b/PSDiff/docs/Out-ConsoleDiff.md new file mode 100644 index 0000000..8f5769c --- /dev/null +++ b/PSDiff/docs/Out-ConsoleDiff.md @@ -0,0 +1,104 @@ +# Out-ConsoleDiff + +## SYNOPSIS +Diffs two strings and outputs the results side by side in the console color coded and with line numbers. + +## SYNTAX + +``` +Out-ConsoleDiff [-Text1] [-Text2] [[-ReplacementDelimiter] ] +``` + +## DESCRIPTION +Uses Get-CharDiff but adds handing of array input (strings with multiple lines need to be split by new line) +by inserting a replacementchar to mark new lines. +The color coding is done using ansi escape sequences. +White on +red for deletions and white on green for insertions. + +## EXAMPLES + +### -------------------------- EXAMPLE 1 -------------------------- +``` +# Using file content as input + + +$txt1 = (get-content "c:\txt1.txt") +$txt2 = (get-content "c:\txt2.txt") +Out-ConsoleDiff $txt1 $txt2 +``` +### -------------------------- EXAMPLE 2 -------------------------- +``` +# Using string input split by newline + + +$txt1 = @' +will stay +this will be changed +this will be deleted +'@ -split '\r?\n' +$txt2 = @' +will stay +this is now changed to something new +replaced with new line +here is a totally new line +'@ -split '\r?\n' +Out-ConsoleDiff $txt1 $txt2 +``` +## PARAMETERS + +### -Text1 +{{Fill Text1 Description}} + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 1 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -Text2 +{{Fill Text2 Description}} + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: True +Position: 2 +Default value: None +Accept pipeline input: False +Accept wildcard characters: False +``` + +### -ReplacementDelimiter +The string used to replace newline characters internally, Defaults to 'ÜÜÜ' + +```yaml +Type: Object +Parameter Sets: (All) +Aliases: + +Required: False +Position: 3 +Default value: ÜÜÜ +Accept pipeline input: False +Accept wildcard characters: False +``` + +## INPUTS + +## OUTPUTS + +## NOTES + +## RELATED LINKS + + + diff --git a/README.md b/README.md index 638de3e..77c7ac7 100644 --- a/README.md +++ b/README.md @@ -1,2 +1,8 @@ -# PSDiffMatchPatch -PowerShell wrapper + additional functionality around https://github.com/google/diff-match-patch +# PSDiff +PowerShell wrapper + additional functionality around the diff part of https://github.com/google/diff-match-patch + +This is using a slightly customized version of the c# version provided in the diff-match-patch repository (mainly replacing protected by public and implementing the suggested line and word modes). + +The PSDiff module exports the following functions: + +![OutConsoleDiff](C:\Scripts\ps1\PSDiff\OutConsoleDiff.PNG) \ No newline at end of file diff --git a/Source/DiffMatchPatch.cs b/Source/DiffMatchPatch.cs new file mode 100644 index 0000000..82fc4db --- /dev/null +++ b/Source/DiffMatchPatch.cs @@ -0,0 +1,2307 @@ +/* + * Diff Match and Patch + * Copyright 2018 The diff-match-patch Authors. + * https://github.com/google/diff-match-patch + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +using System; +using System.Collections.Generic; +using System.Linq; +using System.Text; +using System.Text.RegularExpressions; +using System.Web; + +namespace DiffMatchPatch { + internal static class CompatibilityExtensions { + // JScript splice function + public static List Splice(this List input, int start, int count, + params T[] objects) { + List deletedRange = input.GetRange(start, count); + input.RemoveRange(start, count); + input.InsertRange(start, objects); + + return deletedRange; + } + + // Java substring function + public static string JavaSubstring(this string s, int begin, int end) { + return s.Substring(begin, end - begin); + } + } + + /**- + * The data structure representing a diff is a List of Diff objects: + * {Diff(Operation.DELETE, "Hello"), Diff(Operation.INSERT, "Goodbye"), + * Diff(Operation.EQUAL, " world.")} + * which means: delete "Hello", add "Goodbye" and keep " world." + */ + public enum Operation { + DELETE, INSERT, EQUAL + } + + + /** + * Class representing one diff operation. + */ + public class Diff { + public Operation operation; + // One of: INSERT, DELETE or EQUAL. + public string text; + // The text associated with this diff operation. + + /** + * Constructor. Initializes the diff with the provided values. + * @param operation One of INSERT, DELETE or EQUAL. + * @param text The text being applied. + */ + public Diff(Operation operation, string text) { + // Construct a diff with the specified operation and text. + this.operation = operation; + this.text = text; + } + + /** + * Display a human-readable version of this Diff. + * @return text version. + */ + public override string ToString() { + string prettyText = this.text.Replace('\n', '\u00b6'); + return "Diff(" + this.operation + ",\"" + prettyText + "\")"; + } + + /** + * Is this Diff equivalent to another Diff? + * @param d Another Diff to compare against. + * @return true or false. + */ + public override bool Equals(Object obj) { + // If parameter is null return false. + if (obj == null) { + return false; + } + + // If parameter cannot be cast to Diff return false. + Diff p = obj as Diff; + if ((System.Object)p == null) { + return false; + } + + // Return true if the fields match. + return p.operation == this.operation && p.text == this.text; + } + + public bool Equals(Diff obj) { + // If parameter is null return false. + if (obj == null) { + return false; + } + + // Return true if the fields match. + return obj.operation == this.operation && obj.text == this.text; + } + + public override int GetHashCode() { + return text.GetHashCode() ^ operation.GetHashCode(); + } + } + + + /** + * Class representing one patch operation. + */ + public class Patch { + public List diffs = new List(); + public int start1; + public int start2; + public int length1; + public int length2; + + /** + * Emulate GNU diff's format. + * Header: @@ -382,8 +481,9 @@ + * Indices are printed as 1-based, not 0-based. + * @return The GNU diff string. + */ + public override string ToString() { + string coords1, coords2; + if (this.length1 == 0) { + coords1 = this.start1 + ",0"; + } else if (this.length1 == 1) { + coords1 = Convert.ToString(this.start1 + 1); + } else { + coords1 = (this.start1 + 1) + "," + this.length1; + } + if (this.length2 == 0) { + coords2 = this.start2 + ",0"; + } else if (this.length2 == 1) { + coords2 = Convert.ToString(this.start2 + 1); + } else { + coords2 = (this.start2 + 1) + "," + this.length2; + } + StringBuilder text = new StringBuilder(); + text.Append("@@ -").Append(coords1).Append(" +").Append(coords2) + .Append(" @@\n"); + // Escape the body of the patch with %xx notation. + foreach (Diff aDiff in this.diffs) { + switch (aDiff.operation) { + case Operation.INSERT: + text.Append('+'); + break; + case Operation.DELETE: + text.Append('-'); + break; + case Operation.EQUAL: + text.Append(' '); + break; + } + + text.Append(diff_match_patch.encodeURI(aDiff.text)).Append("\n"); + } + return text.ToString(); + } + } + + + /** + * Class containing the diff, match and patch methods. + * Also Contains the behaviour settings. + */ + public class diff_match_patch { + // Defaults. + // Set these on your diff_match_patch instance to override the defaults. + + // Number of seconds to map a diff before giving up (0 for infinity). + public float Diff_Timeout = 1.0f; + // Cost of an empty edit operation in terms of edit characters. + public short Diff_EditCost = 4; + // At what point is no match declared (0.0 = perfection, 1.0 = very loose). + public float Match_Threshold = 0.5f; + // How far to search for a match (0 = exact location, 1000+ = broad match). + // A match this many characters away from the expected location will add + // 1.0 to the score (0.0 is a perfect match). + public int Match_Distance = 1000; + // When deleting a large block of text (over ~64 characters), how close + // do the contents have to be to match the expected contents. (0.0 = + // perfection, 1.0 = very loose). Note that Match_Threshold controls + // how closely the end points of a delete need to match. + public float Patch_DeleteThreshold = 0.5f; + // Chunk size for context length. + public short Patch_Margin = 4; + + // The number of bits in an int. + private short Match_MaxBits = 32; + + + // DIFF FUNCTIONS + + + /** + * Find the differences between two texts. + * Run a faster, slightly less optimal diff. + * This method allows the 'checklines' of diff_main() to be optional. + * Most of the time checklines is wanted, so default to true. + * @param text1 Old string to be diffed. + * @param text2 New string to be diffed. + * @return List of Diff objects. + */ + public List diff_main(string text1, string text2) { + return diff_main(text1, text2, true); + } + + /** + * Find the differences between two texts. + * @param text1 Old string to be diffed. + * @param text2 New string to be diffed. + * @param checklines Speedup flag. If false, then don't run a + * line-level diff first to identify the changed areas. + * If true, then run a faster slightly less optimal diff. + * @return List of Diff objects. + */ + public List diff_main(string text1, string text2, bool checklines) { + // Set a deadline by which time the diff must be complete. + DateTime deadline; + if (this.Diff_Timeout <= 0) { + deadline = DateTime.MaxValue; + } else { + deadline = DateTime.Now + + new TimeSpan(((long)(Diff_Timeout * 1000)) * 10000); + } + return diff_main(text1, text2, checklines, deadline); + } + + /** + * Find the differences between two texts. Simplifies the problem by + * stripping any common prefix or suffix off the texts before diffing. + * @param text1 Old string to be diffed. + * @param text2 New string to be diffed. + * @param checklines Speedup flag. If false, then don't run a + * line-level diff first to identify the changed areas. + * If true, then run a faster slightly less optimal diff. + * @param deadline Time when the diff should be complete by. Used + * internally for recursive calls. Users should set DiffTimeout + * instead. + * @return List of Diff objects. + */ + private List diff_main(string text1, string text2, bool checklines, + DateTime deadline) { + // Check for null inputs not needed since null can't be passed in C#. + + // Check for equality (speedup). + List diffs; + if (text1 == text2) { + diffs = new List(); + if (text1.Length != 0) { + diffs.Add(new Diff(Operation.EQUAL, text1)); + } + return diffs; + } + + // Trim off common prefix (speedup). + int commonlength = diff_commonPrefix(text1, text2); + string commonprefix = text1.Substring(0, commonlength); + text1 = text1.Substring(commonlength); + text2 = text2.Substring(commonlength); + + // Trim off common suffix (speedup). + commonlength = diff_commonSuffix(text1, text2); + string commonsuffix = text1.Substring(text1.Length - commonlength); + text1 = text1.Substring(0, text1.Length - commonlength); + text2 = text2.Substring(0, text2.Length - commonlength); + + // Compute the diff on the middle block. + diffs = diff_compute(text1, text2, checklines, deadline); + + // Restore the prefix and suffix. + if (commonprefix.Length != 0) { + diffs.Insert(0, (new Diff(Operation.EQUAL, commonprefix))); + } + if (commonsuffix.Length != 0) { + diffs.Add(new Diff(Operation.EQUAL, commonsuffix)); + } + + diff_cleanupMerge(diffs); + return diffs; + } + + /** + * Find the differences between two texts. Assumes that the texts do not + * have any common prefix or suffix. + * @param text1 Old string to be diffed. + * @param text2 New string to be diffed. + * @param checklines Speedup flag. If false, then don't run a + * line-level diff first to identify the changed areas. + * If true, then run a faster slightly less optimal diff. + * @param deadline Time when the diff should be complete by. + * @return List of Diff objects. + */ + private List diff_compute(string text1, string text2, + bool checklines, DateTime deadline) { + List diffs = new List(); + + if (text1.Length == 0) { + // Just add some text (speedup). + diffs.Add(new Diff(Operation.INSERT, text2)); + return diffs; + } + + if (text2.Length == 0) { + // Just delete some text (speedup). + diffs.Add(new Diff(Operation.DELETE, text1)); + return diffs; + } + + string longtext = text1.Length > text2.Length ? text1 : text2; + string shorttext = text1.Length > text2.Length ? text2 : text1; + int i = longtext.IndexOf(shorttext, StringComparison.Ordinal); + if (i != -1) { + // Shorter text is inside the longer text (speedup). + Operation op = (text1.Length > text2.Length) ? + Operation.DELETE : Operation.INSERT; + diffs.Add(new Diff(op, longtext.Substring(0, i))); + diffs.Add(new Diff(Operation.EQUAL, shorttext)); + diffs.Add(new Diff(op, longtext.Substring(i + shorttext.Length))); + return diffs; + } + + if (shorttext.Length == 1) { + // Single character string. + // After the previous speedup, the character can't be an equality. + diffs.Add(new Diff(Operation.DELETE, text1)); + diffs.Add(new Diff(Operation.INSERT, text2)); + return diffs; + } + + // Check to see if the problem can be split in two. + string[] hm = diff_halfMatch(text1, text2); + if (hm != null) { + // A half-match was found, sort out the return data. + string text1_a = hm[0]; + string text1_b = hm[1]; + string text2_a = hm[2]; + string text2_b = hm[3]; + string mid_common = hm[4]; + // Send both pairs off for separate processing. + List diffs_a = diff_main(text1_a, text2_a, checklines, deadline); + List diffs_b = diff_main(text1_b, text2_b, checklines, deadline); + // Merge the results. + diffs = diffs_a; + diffs.Add(new Diff(Operation.EQUAL, mid_common)); + diffs.AddRange(diffs_b); + return diffs; + } + + if (checklines && text1.Length > 100 && text2.Length > 100) { + return diff_lineMode(text1, text2, deadline); + } + + return diff_bisect(text1, text2, deadline); + } + + public List diff_lineWordDiff(string text1, string text2, string delim) { + Object[] a = diff_linesToChars(text1, text2, delim); + text1 = (string)a[0]; + text2 = (string)a[1]; + List lineArray = (List)a[2]; + List diffs = diff_main(text1, text2, false); + diff_charsToLines(diffs, lineArray); + diff_cleanupSemantic(diffs); + return diffs; +} + + /** + * Do a quick line-level diff on both strings, then rediff the parts for + * greater accuracy. + * This speedup can produce non-minimal diffs. + * @param text1 Old string to be diffed. + * @param text2 New string to be diffed. + * @param deadline Time when the diff should be complete by. + * @return List of Diff objects. + */ + private List diff_lineMode(string text1, string text2, + DateTime deadline) { + // Scan the text on a line-by-line basis first. + Object[] a = diff_linesToChars(text1, text2,"\n"); + text1 = (string)a[0]; + text2 = (string)a[1]; + List linearray = (List)a[2]; + + List diffs = diff_main(text1, text2, false, deadline); + + // Convert the diff back to original text. + diff_charsToLines(diffs, linearray); + // Eliminate freak matches (e.g. blank lines) + diff_cleanupSemantic(diffs); + + // Rediff any replacement blocks, this time character-by-character. + // Add a dummy entry at the end. + diffs.Add(new Diff(Operation.EQUAL, string.Empty)); + int pointer = 0; + int count_delete = 0; + int count_insert = 0; + string text_delete = string.Empty; + string text_insert = string.Empty; + while (pointer < diffs.Count) { + switch (diffs[pointer].operation) { + case Operation.INSERT: + count_insert++; + text_insert += diffs[pointer].text; + break; + case Operation.DELETE: + count_delete++; + text_delete += diffs[pointer].text; + break; + case Operation.EQUAL: + // Upon reaching an equality, check for prior redundancies. + if (count_delete >= 1 && count_insert >= 1) { + // Delete the offending records and add the merged ones. + diffs.RemoveRange(pointer - count_delete - count_insert, + count_delete + count_insert); + pointer = pointer - count_delete - count_insert; + List subDiff = + this.diff_main(text_delete, text_insert, false, deadline); + diffs.InsertRange(pointer, subDiff); + pointer = pointer + subDiff.Count; + } + count_insert = 0; + count_delete = 0; + text_delete = string.Empty; + text_insert = string.Empty; + break; + } + pointer++; + } + diffs.RemoveAt(diffs.Count - 1); // Remove the dummy entry at the end. + + return diffs; + } + + /** + * Find the 'middle snake' of a diff, split the problem in two + * and return the recursively constructed diff. + * See Myers 1986 paper: An O(ND) Difference Algorithm and Its Variations. + * @param text1 Old string to be diffed. + * @param text2 New string to be diffed. + * @param deadline Time at which to bail if not yet complete. + * @return List of Diff objects. + */ + protected List diff_bisect(string text1, string text2, + DateTime deadline) { + // Cache the text lengths to prevent multiple calls. + int text1_length = text1.Length; + int text2_length = text2.Length; + int max_d = (text1_length + text2_length + 1) / 2; + int v_offset = max_d; + int v_length = 2 * max_d; + int[] v1 = new int[v_length]; + int[] v2 = new int[v_length]; + for (int x = 0; x < v_length; x++) { + v1[x] = -1; + v2[x] = -1; + } + v1[v_offset + 1] = 0; + v2[v_offset + 1] = 0; + int delta = text1_length - text2_length; + // If the total number of characters is odd, then the front path will + // collide with the reverse path. + bool front = (delta % 2 != 0); + // Offsets for start and end of k loop. + // Prevents mapping of space beyond the grid. + int k1start = 0; + int k1end = 0; + int k2start = 0; + int k2end = 0; + for (int d = 0; d < max_d; d++) { + // Bail out if deadline is reached. + if (DateTime.Now > deadline) { + break; + } + + // Walk the front path one step. + for (int k1 = -d + k1start; k1 <= d - k1end; k1 += 2) { + int k1_offset = v_offset + k1; + int x1; + if (k1 == -d || k1 != d && v1[k1_offset - 1] < v1[k1_offset + 1]) { + x1 = v1[k1_offset + 1]; + } else { + x1 = v1[k1_offset - 1] + 1; + } + int y1 = x1 - k1; + while (x1 < text1_length && y1 < text2_length + && text1[x1] == text2[y1]) { + x1++; + y1++; + } + v1[k1_offset] = x1; + if (x1 > text1_length) { + // Ran off the right of the graph. + k1end += 2; + } else if (y1 > text2_length) { + // Ran off the bottom of the graph. + k1start += 2; + } else if (front) { + int k2_offset = v_offset + delta - k1; + if (k2_offset >= 0 && k2_offset < v_length && v2[k2_offset] != -1) { + // Mirror x2 onto top-left coordinate system. + int x2 = text1_length - v2[k2_offset]; + if (x1 >= x2) { + // Overlap detected. + return diff_bisectSplit(text1, text2, x1, y1, deadline); + } + } + } + } + + // Walk the reverse path one step. + for (int k2 = -d + k2start; k2 <= d - k2end; k2 += 2) { + int k2_offset = v_offset + k2; + int x2; + if (k2 == -d || k2 != d && v2[k2_offset - 1] < v2[k2_offset + 1]) { + x2 = v2[k2_offset + 1]; + } else { + x2 = v2[k2_offset - 1] + 1; + } + int y2 = x2 - k2; + while (x2 < text1_length && y2 < text2_length + && text1[text1_length - x2 - 1] + == text2[text2_length - y2 - 1]) { + x2++; + y2++; + } + v2[k2_offset] = x2; + if (x2 > text1_length) { + // Ran off the left of the graph. + k2end += 2; + } else if (y2 > text2_length) { + // Ran off the top of the graph. + k2start += 2; + } else if (!front) { + int k1_offset = v_offset + delta - k2; + if (k1_offset >= 0 && k1_offset < v_length && v1[k1_offset] != -1) { + int x1 = v1[k1_offset]; + int y1 = v_offset + x1 - k1_offset; + // Mirror x2 onto top-left coordinate system. + x2 = text1_length - v2[k2_offset]; + if (x1 >= x2) { + // Overlap detected. + return diff_bisectSplit(text1, text2, x1, y1, deadline); + } + } + } + } + } + // Diff took too long and hit the deadline or + // number of diffs equals number of characters, no commonality at all. + List diffs = new List(); + diffs.Add(new Diff(Operation.DELETE, text1)); + diffs.Add(new Diff(Operation.INSERT, text2)); + return diffs; + } + + /** + * Given the location of the 'middle snake', split the diff in two parts + * and recurse. + * @param text1 Old string to be diffed. + * @param text2 New string to be diffed. + * @param x Index of split point in text1. + * @param y Index of split point in text2. + * @param deadline Time at which to bail if not yet complete. + * @return LinkedList of Diff objects. + */ + private List diff_bisectSplit(string text1, string text2, + int x, int y, DateTime deadline) { + string text1a = text1.Substring(0, x); + string text2a = text2.Substring(0, y); + string text1b = text1.Substring(x); + string text2b = text2.Substring(y); + + // Compute both diffs serially. + List diffs = diff_main(text1a, text2a, false, deadline); + List diffsb = diff_main(text1b, text2b, false, deadline); + + diffs.AddRange(diffsb); + return diffs; + } + + /** + * Split two texts into a list of strings. Reduce the texts to a string of + * hashes where each Unicode character represents one line. + * @param text1 First string. + * @param text2 Second string. + * @return Three element Object array, containing the encoded text1, the + * encoded text2 and the List of unique strings. The zeroth element + * of the List of unique strings is intentionally blank. + */ + protected Object[] diff_linesToChars(string text1, string text2,string delim) { + List lineArray = new List(); + Dictionary lineHash = new Dictionary(); + // e.g. linearray[4] == "Hello\n" + // e.g. linehash.get("Hello\n") == 4 + + // "\x00" is a valid character, but various debuggers don't like it. + // So we'll insert a junk entry to avoid generating a null character. + lineArray.Add(string.Empty); + + // Allocate 2/3rds of the space for text1, the rest for text2. + string chars1 = diff_linesToCharsMunge(delim, text1, lineArray, lineHash, 40000); + string chars2 = diff_linesToCharsMunge(delim, text2, lineArray, lineHash, 65535); + return new Object[] { chars1, chars2, lineArray }; + } + + /** + * Split a text into a list of strings. Reduce the texts to a string of + * hashes where each Unicode character represents one line. + * @param text String to encode. + * @param lineArray List of unique strings. + * @param lineHash Map of strings to indices. + * @param maxLines Maximum length of lineArray. + * @return Encoded string. + */ + private string diff_linesToCharsMunge(string delim,string text, List lineArray, + Dictionary lineHash, int maxLines) { + int lineStart = 0; + int lineEnd = -1; + string line; + StringBuilder chars = new StringBuilder(); + // Walk the text, pulling out a Substring for each line. + // text.split('\n') would would temporarily double our memory footprint. + // Modifying text would create many large strings to garbage collect. + while (lineEnd < text.Length - 1) { + lineEnd = text.IndexOf(delim, lineStart); + if (lineEnd == -1) { + lineEnd = text.Length - 1; + } + line = text.JavaSubstring(lineStart, lineEnd + 1); + + if (lineHash.ContainsKey(line)) { + chars.Append(((char)(int)lineHash[line])); + } else { + if (lineArray.Count == maxLines) { + // Bail out at 65535 because char 65536 == char 0. + line = text.Substring(lineStart); + lineEnd = text.Length; + } + lineArray.Add(line); + lineHash.Add(line, lineArray.Count - 1); + chars.Append(((char)(lineArray.Count - 1))); + } + lineStart = lineEnd + 1; + } + return chars.ToString(); + } + + /** + * Rehydrate the text in a diff from a string of line hashes to real lines + * of text. + * @param diffs List of Diff objects. + * @param lineArray List of unique strings. + */ + protected void diff_charsToLines(ICollection diffs, + IList lineArray) { + StringBuilder text; + foreach (Diff diff in diffs) { + text = new StringBuilder(); + for (int j = 0; j < diff.text.Length; j++) { + text.Append(lineArray[diff.text[j]]); + } + diff.text = text.ToString(); + } + } + + /** + * Determine the common prefix of two strings. + * @param text1 First string. + * @param text2 Second string. + * @return The number of characters common to the start of each string. + */ + public int diff_commonPrefix(string text1, string text2) { + // Performance analysis: https://neil.fraser.name/news/2007/10/09/ + int n = Math.Min(text1.Length, text2.Length); + for (int i = 0; i < n; i++) { + if (text1[i] != text2[i]) { + return i; + } + } + return n; + } + + /** + * Determine the common suffix of two strings. + * @param text1 First string. + * @param text2 Second string. + * @return The number of characters common to the end of each string. + */ + public int diff_commonSuffix(string text1, string text2) { + // Performance analysis: https://neil.fraser.name/news/2007/10/09/ + int text1_length = text1.Length; + int text2_length = text2.Length; + int n = Math.Min(text1.Length, text2.Length); + for (int i = 1; i <= n; i++) { + if (text1[text1_length - i] != text2[text2_length - i]) { + return i - 1; + } + } + return n; + } + + /** + * Determine if the suffix of one string is the prefix of another. + * @param text1 First string. + * @param text2 Second string. + * @return The number of characters common to the end of the first + * string and the start of the second string. + */ + protected int diff_commonOverlap(string text1, string text2) { + // Cache the text lengths to prevent multiple calls. + int text1_length = text1.Length; + int text2_length = text2.Length; + // Eliminate the null case. + if (text1_length == 0 || text2_length == 0) { + return 0; + } + // Truncate the longer string. + if (text1_length > text2_length) { + text1 = text1.Substring(text1_length - text2_length); + } else if (text1_length < text2_length) { + text2 = text2.Substring(0, text1_length); + } + int text_length = Math.Min(text1_length, text2_length); + // Quick check for the worst case. + if (text1 == text2) { + return text_length; + } + + // Start by looking for a single character match + // and increase length until no match is found. + // Performance analysis: https://neil.fraser.name/news/2010/11/04/ + int best = 0; + int length = 1; + while (true) { + string pattern = text1.Substring(text_length - length); + int found = text2.IndexOf(pattern, StringComparison.Ordinal); + if (found == -1) { + return best; + } + length += found; + if (found == 0 || text1.Substring(text_length - length) == + text2.Substring(0, length)) { + best = length; + length++; + } + } + } + + /** + * Do the two texts share a Substring which is at least half the length of + * the longer text? + * This speedup can produce non-minimal diffs. + * @param text1 First string. + * @param text2 Second string. + * @return Five element String array, containing the prefix of text1, the + * suffix of text1, the prefix of text2, the suffix of text2 and the + * common middle. Or null if there was no match. + */ + + protected string[] diff_halfMatch(string text1, string text2) { + if (this.Diff_Timeout <= 0) { + // Don't risk returning a non-optimal diff if we have unlimited time. + return null; + } + string longtext = text1.Length > text2.Length ? text1 : text2; + string shorttext = text1.Length > text2.Length ? text2 : text1; + if (longtext.Length < 4 || shorttext.Length * 2 < longtext.Length) { + return null; // Pointless. + } + + // First check if the second quarter is the seed for a half-match. + string[] hm1 = diff_halfMatchI(longtext, shorttext, + (longtext.Length + 3) / 4); + // Check again based on the third quarter. + string[] hm2 = diff_halfMatchI(longtext, shorttext, + (longtext.Length + 1) / 2); + string[] hm; + if (hm1 == null && hm2 == null) { + return null; + } else if (hm2 == null) { + hm = hm1; + } else if (hm1 == null) { + hm = hm2; + } else { + // Both matched. Select the longest. + hm = hm1[4].Length > hm2[4].Length ? hm1 : hm2; + } + + // A half-match was found, sort out the return data. + if (text1.Length > text2.Length) { + return hm; + //return new string[]{hm[0], hm[1], hm[2], hm[3], hm[4]}; + } else { + return new string[] { hm[2], hm[3], hm[0], hm[1], hm[4] }; + } + } + + /** + * Does a Substring of shorttext exist within longtext such that the + * Substring is at least half the length of longtext? + * @param longtext Longer string. + * @param shorttext Shorter string. + * @param i Start index of quarter length Substring within longtext. + * @return Five element string array, containing the prefix of longtext, the + * suffix of longtext, the prefix of shorttext, the suffix of shorttext + * and the common middle. Or null if there was no match. + */ + private string[] diff_halfMatchI(string longtext, string shorttext, int i) { + // Start with a 1/4 length Substring at position i as a seed. + string seed = longtext.Substring(i, longtext.Length / 4); + int j = -1; + string best_common = string.Empty; + string best_longtext_a = string.Empty, best_longtext_b = string.Empty; + string best_shorttext_a = string.Empty, best_shorttext_b = string.Empty; + while (j < shorttext.Length && (j = shorttext.IndexOf(seed, j + 1, + StringComparison.Ordinal)) != -1) { + int prefixLength = diff_commonPrefix(longtext.Substring(i), + shorttext.Substring(j)); + int suffixLength = diff_commonSuffix(longtext.Substring(0, i), + shorttext.Substring(0, j)); + if (best_common.Length < suffixLength + prefixLength) { + best_common = shorttext.Substring(j - suffixLength, suffixLength) + + shorttext.Substring(j, prefixLength); + best_longtext_a = longtext.Substring(0, i - suffixLength); + best_longtext_b = longtext.Substring(i + prefixLength); + best_shorttext_a = shorttext.Substring(0, j - suffixLength); + best_shorttext_b = shorttext.Substring(j + prefixLength); + } + } + if (best_common.Length * 2 >= longtext.Length) { + return new string[]{best_longtext_a, best_longtext_b, + best_shorttext_a, best_shorttext_b, best_common}; + } else { + return null; + } + } + + /** + * Reduce the number of edits by eliminating semantically trivial + * equalities. + * @param diffs List of Diff objects. + */ + public void diff_cleanupSemantic(List diffs) { + bool changes = false; + // Stack of indices where equalities are found. + Stack equalities = new Stack(); + // Always equal to equalities[equalitiesLength-1][1] + string lastEquality = null; + int pointer = 0; // Index of current position. + // Number of characters that changed prior to the equality. + int length_insertions1 = 0; + int length_deletions1 = 0; + // Number of characters that changed after the equality. + int length_insertions2 = 0; + int length_deletions2 = 0; + while (pointer < diffs.Count) { + if (diffs[pointer].operation == Operation.EQUAL) { // Equality found. + equalities.Push(pointer); + length_insertions1 = length_insertions2; + length_deletions1 = length_deletions2; + length_insertions2 = 0; + length_deletions2 = 0; + lastEquality = diffs[pointer].text; + } else { // an insertion or deletion + if (diffs[pointer].operation == Operation.INSERT) { + length_insertions2 += diffs[pointer].text.Length; + } else { + length_deletions2 += diffs[pointer].text.Length; + } + // Eliminate an equality that is smaller or equal to the edits on both + // sides of it. + if (lastEquality != null && (lastEquality.Length + <= Math.Max(length_insertions1, length_deletions1)) + && (lastEquality.Length + <= Math.Max(length_insertions2, length_deletions2))) { + // Duplicate record. + diffs.Insert(equalities.Peek(), + new Diff(Operation.DELETE, lastEquality)); + // Change second copy to insert. + diffs[equalities.Peek() + 1].operation = Operation.INSERT; + // Throw away the equality we just deleted. + equalities.Pop(); + if (equalities.Count > 0) { + equalities.Pop(); + } + pointer = equalities.Count > 0 ? equalities.Peek() : -1; + length_insertions1 = 0; // Reset the counters. + length_deletions1 = 0; + length_insertions2 = 0; + length_deletions2 = 0; + lastEquality = null; + changes = true; + } + } + pointer++; + } + + // Normalize the diff. + if (changes) { + diff_cleanupMerge(diffs); + } + diff_cleanupSemanticLossless(diffs); + + // Find any overlaps between deletions and insertions. + // e.g: abcxxxxxxdef + // -> abcxxxdef + // e.g: xxxabcdefxxx + // -> defxxxabc + // Only extract an overlap if it is as big as the edit ahead or behind it. + pointer = 1; + while (pointer < diffs.Count) { + if (diffs[pointer - 1].operation == Operation.DELETE && + diffs[pointer].operation == Operation.INSERT) { + string deletion = diffs[pointer - 1].text; + string insertion = diffs[pointer].text; + int overlap_length1 = diff_commonOverlap(deletion, insertion); + int overlap_length2 = diff_commonOverlap(insertion, deletion); + if (overlap_length1 >= overlap_length2) { + if (overlap_length1 >= deletion.Length / 2.0 || + overlap_length1 >= insertion.Length / 2.0) { + // Overlap found. + // Insert an equality and trim the surrounding edits. + diffs.Insert(pointer, new Diff(Operation.EQUAL, + insertion.Substring(0, overlap_length1))); + diffs[pointer - 1].text = + deletion.Substring(0, deletion.Length - overlap_length1); + diffs[pointer + 1].text = insertion.Substring(overlap_length1); + pointer++; + } + } else { + if (overlap_length2 >= deletion.Length / 2.0 || + overlap_length2 >= insertion.Length / 2.0) { + // Reverse overlap found. + // Insert an equality and swap and trim the surrounding edits. + diffs.Insert(pointer, new Diff(Operation.EQUAL, + deletion.Substring(0, overlap_length2))); + diffs[pointer - 1].operation = Operation.INSERT; + diffs[pointer - 1].text = + insertion.Substring(0, insertion.Length - overlap_length2); + diffs[pointer + 1].operation = Operation.DELETE; + diffs[pointer + 1].text = deletion.Substring(overlap_length2); + pointer++; + } + } + pointer++; + } + pointer++; + } + } + + /** + * Look for single edits surrounded on both sides by equalities + * which can be shifted sideways to align the edit to a word boundary. + * e.g: The cat came. -> The cat came. + * @param diffs List of Diff objects. + */ + public void diff_cleanupSemanticLossless(List diffs) { + int pointer = 1; + // Intentionally ignore the first and last element (don't need checking). + while (pointer < diffs.Count - 1) { + if (diffs[pointer - 1].operation == Operation.EQUAL && + diffs[pointer + 1].operation == Operation.EQUAL) { + // This is a single edit surrounded by equalities. + string equality1 = diffs[pointer - 1].text; + string edit = diffs[pointer].text; + string equality2 = diffs[pointer + 1].text; + + // First, shift the edit as far left as possible. + int commonOffset = this.diff_commonSuffix(equality1, edit); + if (commonOffset > 0) { + string commonString = edit.Substring(edit.Length - commonOffset); + equality1 = equality1.Substring(0, equality1.Length - commonOffset); + edit = commonString + edit.Substring(0, edit.Length - commonOffset); + equality2 = commonString + equality2; + } + + // Second, step character by character right, + // looking for the best fit. + string bestEquality1 = equality1; + string bestEdit = edit; + string bestEquality2 = equality2; + int bestScore = diff_cleanupSemanticScore(equality1, edit) + + diff_cleanupSemanticScore(edit, equality2); + while (edit.Length != 0 && equality2.Length != 0 + && edit[0] == equality2[0]) { + equality1 += edit[0]; + edit = edit.Substring(1) + equality2[0]; + equality2 = equality2.Substring(1); + int score = diff_cleanupSemanticScore(equality1, edit) + + diff_cleanupSemanticScore(edit, equality2); + // The >= encourages trailing rather than leading whitespace on + // edits. + if (score >= bestScore) { + bestScore = score; + bestEquality1 = equality1; + bestEdit = edit; + bestEquality2 = equality2; + } + } + + if (diffs[pointer - 1].text != bestEquality1) { + // We have an improvement, save it back to the diff. + if (bestEquality1.Length != 0) { + diffs[pointer - 1].text = bestEquality1; + } else { + diffs.RemoveAt(pointer - 1); + pointer--; + } + diffs[pointer].text = bestEdit; + if (bestEquality2.Length != 0) { + diffs[pointer + 1].text = bestEquality2; + } else { + diffs.RemoveAt(pointer + 1); + pointer--; + } + } + } + pointer++; + } + } + + /** + * Given two strings, compute a score representing whether the internal + * boundary falls on logical boundaries. + * Scores range from 6 (best) to 0 (worst). + * @param one First string. + * @param two Second string. + * @return The score. + */ + private int diff_cleanupSemanticScore(string one, string two) { + if (one.Length == 0 || two.Length == 0) { + // Edges are the best. + return 6; + } + + // Each port of this function behaves slightly differently due to + // subtle differences in each language's definition of things like + // 'whitespace'. Since this function's purpose is largely cosmetic, + // the choice has been made to use each language's native features + // rather than force total conformity. + char char1 = one[one.Length - 1]; + char char2 = two[0]; + bool nonAlphaNumeric1 = !Char.IsLetterOrDigit(char1); + bool nonAlphaNumeric2 = !Char.IsLetterOrDigit(char2); + bool whitespace1 = nonAlphaNumeric1 && Char.IsWhiteSpace(char1); + bool whitespace2 = nonAlphaNumeric2 && Char.IsWhiteSpace(char2); + bool lineBreak1 = whitespace1 && Char.IsControl(char1); + bool lineBreak2 = whitespace2 && Char.IsControl(char2); + bool blankLine1 = lineBreak1 && BLANKLINEEND.IsMatch(one); + bool blankLine2 = lineBreak2 && BLANKLINESTART.IsMatch(two); + + if (blankLine1 || blankLine2) { + // Five points for blank lines. + return 5; + } else if (lineBreak1 || lineBreak2) { + // Four points for line breaks. + return 4; + } else if (nonAlphaNumeric1 && !whitespace1 && whitespace2) { + // Three points for end of sentences. + return 3; + } else if (whitespace1 || whitespace2) { + // Two points for whitespace. + return 2; + } else if (nonAlphaNumeric1 || nonAlphaNumeric2) { + // One point for non-alphanumeric. + return 1; + } + return 0; + } + + // Define some regex patterns for matching boundaries. + private Regex BLANKLINEEND = new Regex("\\n\\r?\\n\\Z"); + private Regex BLANKLINESTART = new Regex("\\A\\r?\\n\\r?\\n"); + + /** + * Reduce the number of edits by eliminating operationally trivial + * equalities. + * @param diffs List of Diff objects. + */ + public void diff_cleanupEfficiency(List diffs) { + bool changes = false; + // Stack of indices where equalities are found. + Stack equalities = new Stack(); + // Always equal to equalities[equalitiesLength-1][1] + string lastEquality = string.Empty; + int pointer = 0; // Index of current position. + // Is there an insertion operation before the last equality. + bool pre_ins = false; + // Is there a deletion operation before the last equality. + bool pre_del = false; + // Is there an insertion operation after the last equality. + bool post_ins = false; + // Is there a deletion operation after the last equality. + bool post_del = false; + while (pointer < diffs.Count) { + if (diffs[pointer].operation == Operation.EQUAL) { // Equality found. + if (diffs[pointer].text.Length < this.Diff_EditCost + && (post_ins || post_del)) { + // Candidate found. + equalities.Push(pointer); + pre_ins = post_ins; + pre_del = post_del; + lastEquality = diffs[pointer].text; + } else { + // Not a candidate, and can never become one. + equalities.Clear(); + lastEquality = string.Empty; + } + post_ins = post_del = false; + } else { // An insertion or deletion. + if (diffs[pointer].operation == Operation.DELETE) { + post_del = true; + } else { + post_ins = true; + } + /* + * Five types to be split: + * ABXYCD + * AXCD + * ABXC + * AXCD + * ABXC + */ + if ((lastEquality.Length != 0) + && ((pre_ins && pre_del && post_ins && post_del) + || ((lastEquality.Length < this.Diff_EditCost / 2) + && ((pre_ins ? 1 : 0) + (pre_del ? 1 : 0) + (post_ins ? 1 : 0) + + (post_del ? 1 : 0)) == 3))) { + // Duplicate record. + diffs.Insert(equalities.Peek(), + new Diff(Operation.DELETE, lastEquality)); + // Change second copy to insert. + diffs[equalities.Peek() + 1].operation = Operation.INSERT; + equalities.Pop(); // Throw away the equality we just deleted. + lastEquality = string.Empty; + if (pre_ins && pre_del) { + // No changes made which could affect previous entry, keep going. + post_ins = post_del = true; + equalities.Clear(); + } else { + if (equalities.Count > 0) { + equalities.Pop(); + } + + pointer = equalities.Count > 0 ? equalities.Peek() : -1; + post_ins = post_del = false; + } + changes = true; + } + } + pointer++; + } + + if (changes) { + diff_cleanupMerge(diffs); + } + } + + /** + * Reorder and merge like edit sections. Merge equalities. + * Any edit section can move as long as it doesn't cross an equality. + * @param diffs List of Diff objects. + */ + public void diff_cleanupMerge(List diffs) { + // Add a dummy entry at the end. + diffs.Add(new Diff(Operation.EQUAL, string.Empty)); + int pointer = 0; + int count_delete = 0; + int count_insert = 0; + string text_delete = string.Empty; + string text_insert = string.Empty; + int commonlength; + while (pointer < diffs.Count) { + switch (diffs[pointer].operation) { + case Operation.INSERT: + count_insert++; + text_insert += diffs[pointer].text; + pointer++; + break; + case Operation.DELETE: + count_delete++; + text_delete += diffs[pointer].text; + pointer++; + break; + case Operation.EQUAL: + // Upon reaching an equality, check for prior redundancies. + if (count_delete + count_insert > 1) { + if (count_delete != 0 && count_insert != 0) { + // Factor out any common prefixies. + commonlength = this.diff_commonPrefix(text_insert, text_delete); + if (commonlength != 0) { + if ((pointer - count_delete - count_insert) > 0 && + diffs[pointer - count_delete - count_insert - 1].operation + == Operation.EQUAL) { + diffs[pointer - count_delete - count_insert - 1].text + += text_insert.Substring(0, commonlength); + } else { + diffs.Insert(0, new Diff(Operation.EQUAL, + text_insert.Substring(0, commonlength))); + pointer++; + } + text_insert = text_insert.Substring(commonlength); + text_delete = text_delete.Substring(commonlength); + } + // Factor out any common suffixies. + commonlength = this.diff_commonSuffix(text_insert, text_delete); + if (commonlength != 0) { + diffs[pointer].text = text_insert.Substring(text_insert.Length + - commonlength) + diffs[pointer].text; + text_insert = text_insert.Substring(0, text_insert.Length + - commonlength); + text_delete = text_delete.Substring(0, text_delete.Length + - commonlength); + } + } + // Delete the offending records and add the merged ones. + pointer -= count_delete + count_insert; + diffs.Splice(pointer, count_delete + count_insert); + if (text_delete.Length != 0) { + diffs.Splice(pointer, 0, + new Diff(Operation.DELETE, text_delete)); + pointer++; + } + if (text_insert.Length != 0) { + diffs.Splice(pointer, 0, + new Diff(Operation.INSERT, text_insert)); + pointer++; + } + pointer++; + } else if (pointer != 0 + && diffs[pointer - 1].operation == Operation.EQUAL) { + // Merge this equality with the previous one. + diffs[pointer - 1].text += diffs[pointer].text; + diffs.RemoveAt(pointer); + } else { + pointer++; + } + count_insert = 0; + count_delete = 0; + text_delete = string.Empty; + text_insert = string.Empty; + break; + } + } + if (diffs[diffs.Count - 1].text.Length == 0) { + diffs.RemoveAt(diffs.Count - 1); // Remove the dummy entry at the end. + } + + // Second pass: look for single edits surrounded on both sides by + // equalities which can be shifted sideways to eliminate an equality. + // e.g: ABAC -> ABAC + bool changes = false; + pointer = 1; + // Intentionally ignore the first and last element (don't need checking). + while (pointer < (diffs.Count - 1)) { + if (diffs[pointer - 1].operation == Operation.EQUAL && + diffs[pointer + 1].operation == Operation.EQUAL) { + // This is a single edit surrounded by equalities. + if (diffs[pointer].text.EndsWith(diffs[pointer - 1].text, + StringComparison.Ordinal)) { + // Shift the edit over the previous equality. + diffs[pointer].text = diffs[pointer - 1].text + + diffs[pointer].text.Substring(0, diffs[pointer].text.Length - + diffs[pointer - 1].text.Length); + diffs[pointer + 1].text = diffs[pointer - 1].text + + diffs[pointer + 1].text; + diffs.Splice(pointer - 1, 1); + changes = true; + } else if (diffs[pointer].text.StartsWith(diffs[pointer + 1].text, + StringComparison.Ordinal)) { + // Shift the edit over the next equality. + diffs[pointer - 1].text += diffs[pointer + 1].text; + diffs[pointer].text = + diffs[pointer].text.Substring(diffs[pointer + 1].text.Length) + + diffs[pointer + 1].text; + diffs.Splice(pointer + 1, 1); + changes = true; + } + } + pointer++; + } + // If shifts were made, the diff needs reordering and another shift sweep. + if (changes) { + this.diff_cleanupMerge(diffs); + } + } + + /** + * loc is a location in text1, compute and return the equivalent location in + * text2. + * e.g. "The cat" vs "The big cat", 1->1, 5->8 + * @param diffs List of Diff objects. + * @param loc Location within text1. + * @return Location within text2. + */ + public int diff_xIndex(List diffs, int loc) { + int chars1 = 0; + int chars2 = 0; + int last_chars1 = 0; + int last_chars2 = 0; + Diff lastDiff = null; + foreach (Diff aDiff in diffs) { + if (aDiff.operation != Operation.INSERT) { + // Equality or deletion. + chars1 += aDiff.text.Length; + } + if (aDiff.operation != Operation.DELETE) { + // Equality or insertion. + chars2 += aDiff.text.Length; + } + if (chars1 > loc) { + // Overshot the location. + lastDiff = aDiff; + break; + } + last_chars1 = chars1; + last_chars2 = chars2; + } + if (lastDiff != null && lastDiff.operation == Operation.DELETE) { + // The location was deleted. + return last_chars2; + } + // Add the remaining character length. + return last_chars2 + (loc - last_chars1); + } + + /** + * Convert a Diff list into a pretty HTML report. + * @param diffs List of Diff objects. + * @return HTML representation. + */ + public string diff_prettyHtml(List diffs) { + StringBuilder html = new StringBuilder(); + foreach (Diff aDiff in diffs) { + string text = aDiff.text.Replace("&", "&").Replace("<", "<") + .Replace(">", ">").Replace("\n", "¶
"); + switch (aDiff.operation) { + case Operation.INSERT: + html.Append("").Append(text) + .Append(""); + break; + case Operation.DELETE: + html.Append("").Append(text) + .Append(""); + break; + case Operation.EQUAL: + html.Append("").Append(text).Append(""); + break; + } + } + return html.ToString(); + } + + /** + * Compute and return the source text (all equalities and deletions). + * @param diffs List of Diff objects. + * @return Source text. + */ + public string diff_text1(List diffs) { + StringBuilder text = new StringBuilder(); + foreach (Diff aDiff in diffs) { + if (aDiff.operation != Operation.INSERT) { + text.Append(aDiff.text); + } + } + return text.ToString(); + } + + /** + * Compute and return the destination text (all equalities and insertions). + * @param diffs List of Diff objects. + * @return Destination text. + */ + public string diff_text2(List diffs) { + StringBuilder text = new StringBuilder(); + foreach (Diff aDiff in diffs) { + if (aDiff.operation != Operation.DELETE) { + text.Append(aDiff.text); + } + } + return text.ToString(); + } + + /** + * Compute the Levenshtein distance; the number of inserted, deleted or + * substituted characters. + * @param diffs List of Diff objects. + * @return Number of changes. + */ + public int diff_levenshtein(List diffs) { + int levenshtein = 0; + int insertions = 0; + int deletions = 0; + foreach (Diff aDiff in diffs) { + switch (aDiff.operation) { + case Operation.INSERT: + insertions += aDiff.text.Length; + break; + case Operation.DELETE: + deletions += aDiff.text.Length; + break; + case Operation.EQUAL: + // A deletion and an insertion is one substitution. + levenshtein += Math.Max(insertions, deletions); + insertions = 0; + deletions = 0; + break; + } + } + levenshtein += Math.Max(insertions, deletions); + return levenshtein; + } + + /** + * Crush the diff into an encoded string which describes the operations + * required to transform text1 into text2. + * E.g. =3\t-2\t+ing -> Keep 3 chars, delete 2 chars, insert 'ing'. + * Operations are tab-separated. Inserted text is escaped using %xx + * notation. + * @param diffs Array of Diff objects. + * @return Delta text. + */ + public string diff_toDelta(List diffs) { + StringBuilder text = new StringBuilder(); + foreach (Diff aDiff in diffs) { + switch (aDiff.operation) { + case Operation.INSERT: + text.Append("+").Append(encodeURI(aDiff.text)).Append("\t"); + break; + case Operation.DELETE: + text.Append("-").Append(aDiff.text.Length).Append("\t"); + break; + case Operation.EQUAL: + text.Append("=").Append(aDiff.text.Length).Append("\t"); + break; + } + } + string delta = text.ToString(); + if (delta.Length != 0) { + // Strip off trailing tab character. + delta = delta.Substring(0, delta.Length - 1); + } + return delta; + } + + /** + * Given the original text1, and an encoded string which describes the + * operations required to transform text1 into text2, compute the full diff. + * @param text1 Source string for the diff. + * @param delta Delta text. + * @return Array of Diff objects or null if invalid. + * @throws ArgumentException If invalid input. + */ + public List diff_fromDelta(string text1, string delta) { + List diffs = new List(); + int pointer = 0; // Cursor in text1 + string[] tokens = delta.Split(new string[] { "\t" }, + StringSplitOptions.None); + foreach (string token in tokens) { + if (token.Length == 0) { + // Blank tokens are ok (from a trailing \t). + continue; + } + // Each token begins with a one character parameter which specifies the + // operation of this token (delete, insert, equality). + string param = token.Substring(1); + switch (token[0]) { + case '+': + // decode would change all "+" to " " + param = param.Replace("+", "%2b"); + + param = HttpUtility.UrlDecode(param); + //} catch (UnsupportedEncodingException e) { + // // Not likely on modern system. + // throw new Error("This system does not support UTF-8.", e); + //} catch (IllegalArgumentException e) { + // // Malformed URI sequence. + // throw new IllegalArgumentException( + // "Illegal escape in diff_fromDelta: " + param, e); + //} + diffs.Add(new Diff(Operation.INSERT, param)); + break; + case '-': + // Fall through. + case '=': + int n; + try { + n = Convert.ToInt32(param); + } catch (FormatException e) { + throw new ArgumentException( + "Invalid number in diff_fromDelta: " + param, e); + } + if (n < 0) { + throw new ArgumentException( + "Negative number in diff_fromDelta: " + param); + } + string text; + try { + text = text1.Substring(pointer, n); + pointer += n; + } catch (ArgumentOutOfRangeException e) { + throw new ArgumentException("Delta length (" + pointer + + ") larger than source text length (" + text1.Length + + ").", e); + } + if (token[0] == '=') { + diffs.Add(new Diff(Operation.EQUAL, text)); + } else { + diffs.Add(new Diff(Operation.DELETE, text)); + } + break; + default: + // Anything else is an error. + throw new ArgumentException( + "Invalid diff operation in diff_fromDelta: " + token[0]); + } + } + if (pointer != text1.Length) { + throw new ArgumentException("Delta length (" + pointer + + ") smaller than source text length (" + text1.Length + ")."); + } + return diffs; + } + + + // MATCH FUNCTIONS + + + /** + * Locate the best instance of 'pattern' in 'text' near 'loc'. + * Returns -1 if no match found. + * @param text The text to search. + * @param pattern The pattern to search for. + * @param loc The location to search around. + * @return Best match index or -1. + */ + public int match_main(string text, string pattern, int loc) { + // Check for null inputs not needed since null can't be passed in C#. + + loc = Math.Max(0, Math.Min(loc, text.Length)); + if (text == pattern) { + // Shortcut (potentially not guaranteed by the algorithm) + return 0; + } else if (text.Length == 0) { + // Nothing to match. + return -1; + } else if (loc + pattern.Length <= text.Length + && text.Substring(loc, pattern.Length) == pattern) { + // Perfect match at the perfect spot! (Includes case of null pattern) + return loc; + } else { + // Do a fuzzy compare. + return match_bitap(text, pattern, loc); + } + } + + /** + * Locate the best instance of 'pattern' in 'text' near 'loc' using the + * Bitap algorithm. Returns -1 if no match found. + * @param text The text to search. + * @param pattern The pattern to search for. + * @param loc The location to search around. + * @return Best match index or -1. + */ + protected int match_bitap(string text, string pattern, int loc) { + // assert (Match_MaxBits == 0 || pattern.Length <= Match_MaxBits) + // : "Pattern too long for this application."; + + // Initialise the alphabet. + Dictionary s = match_alphabet(pattern); + + // Highest score beyond which we give up. + double score_threshold = Match_Threshold; + // Is there a nearby exact match? (speedup) + int best_loc = text.IndexOf(pattern, loc, StringComparison.Ordinal); + if (best_loc != -1) { + score_threshold = Math.Min(match_bitapScore(0, best_loc, loc, + pattern), score_threshold); + // What about in the other direction? (speedup) + best_loc = text.LastIndexOf(pattern, + Math.Min(loc + pattern.Length, text.Length), + StringComparison.Ordinal); + if (best_loc != -1) { + score_threshold = Math.Min(match_bitapScore(0, best_loc, loc, + pattern), score_threshold); + } + } + + // Initialise the bit arrays. + int matchmask = 1 << (pattern.Length - 1); + best_loc = -1; + + int bin_min, bin_mid; + int bin_max = pattern.Length + text.Length; + // Empty initialization added to appease C# compiler. + int[] last_rd = new int[0]; + for (int d = 0; d < pattern.Length; d++) { + // Scan for the best match; each iteration allows for one more error. + // Run a binary search to determine how far from 'loc' we can stray at + // this error level. + bin_min = 0; + bin_mid = bin_max; + while (bin_min < bin_mid) { + if (match_bitapScore(d, loc + bin_mid, loc, pattern) + <= score_threshold) { + bin_min = bin_mid; + } else { + bin_max = bin_mid; + } + bin_mid = (bin_max - bin_min) / 2 + bin_min; + } + // Use the result from this iteration as the maximum for the next. + bin_max = bin_mid; + int start = Math.Max(1, loc - bin_mid + 1); + int finish = Math.Min(loc + bin_mid, text.Length) + pattern.Length; + + int[] rd = new int[finish + 2]; + rd[finish + 1] = (1 << d) - 1; + for (int j = finish; j >= start; j--) { + int charMatch; + if (text.Length <= j - 1 || !s.ContainsKey(text[j - 1])) { + // Out of range. + charMatch = 0; + } else { + charMatch = s[text[j - 1]]; + } + if (d == 0) { + // First pass: exact match. + rd[j] = ((rd[j + 1] << 1) | 1) & charMatch; + } else { + // Subsequent passes: fuzzy match. + rd[j] = ((rd[j + 1] << 1) | 1) & charMatch + | (((last_rd[j + 1] | last_rd[j]) << 1) | 1) | last_rd[j + 1]; + } + if ((rd[j] & matchmask) != 0) { + double score = match_bitapScore(d, j - 1, loc, pattern); + // This match will almost certainly be better than any existing + // match. But check anyway. + if (score <= score_threshold) { + // Told you so. + score_threshold = score; + best_loc = j - 1; + if (best_loc > loc) { + // When passing loc, don't exceed our current distance from loc. + start = Math.Max(1, 2 * loc - best_loc); + } else { + // Already passed loc, downhill from here on in. + break; + } + } + } + } + if (match_bitapScore(d + 1, loc, loc, pattern) > score_threshold) { + // No hope for a (better) match at greater error levels. + break; + } + last_rd = rd; + } + return best_loc; + } + + /** + * Compute and return the score for a match with e errors and x location. + * @param e Number of errors in match. + * @param x Location of match. + * @param loc Expected location of match. + * @param pattern Pattern being sought. + * @return Overall score for match (0.0 = good, 1.0 = bad). + */ + private double match_bitapScore(int e, int x, int loc, string pattern) { + float accuracy = (float)e / pattern.Length; + int proximity = Math.Abs(loc - x); + if (Match_Distance == 0) { + // Dodge divide by zero error. + return proximity == 0 ? accuracy : 1.0; + } + return accuracy + (proximity / (float) Match_Distance); + } + + /** + * Initialise the alphabet for the Bitap algorithm. + * @param pattern The text to encode. + * @return Hash of character locations. + */ + protected Dictionary match_alphabet(string pattern) { + Dictionary s = new Dictionary(); + char[] char_pattern = pattern.ToCharArray(); + foreach (char c in char_pattern) { + if (!s.ContainsKey(c)) { + s.Add(c, 0); + } + } + int i = 0; + foreach (char c in char_pattern) { + int value = s[c] | (1 << (pattern.Length - i - 1)); + s[c] = value; + i++; + } + return s; + } + + + // PATCH FUNCTIONS + + + /** + * Increase the context until it is unique, + * but don't let the pattern expand beyond Match_MaxBits. + * @param patch The patch to grow. + * @param text Source text. + */ + protected void patch_addContext(Patch patch, string text) { + if (text.Length == 0) { + return; + } + string pattern = text.Substring(patch.start2, patch.length1); + int padding = 0; + + // Look for the first and last matches of pattern in text. If two + // different matches are found, increase the pattern length. + while (text.IndexOf(pattern, StringComparison.Ordinal) + != text.LastIndexOf(pattern, StringComparison.Ordinal) + && pattern.Length < Match_MaxBits - Patch_Margin - Patch_Margin) { + padding += Patch_Margin; + pattern = text.JavaSubstring(Math.Max(0, patch.start2 - padding), + Math.Min(text.Length, patch.start2 + patch.length1 + padding)); + } + // Add one chunk for good luck. + padding += Patch_Margin; + + // Add the prefix. + string prefix = text.JavaSubstring(Math.Max(0, patch.start2 - padding), + patch.start2); + if (prefix.Length != 0) { + patch.diffs.Insert(0, new Diff(Operation.EQUAL, prefix)); + } + // Add the suffix. + string suffix = text.JavaSubstring(patch.start2 + patch.length1, + Math.Min(text.Length, patch.start2 + patch.length1 + padding)); + if (suffix.Length != 0) { + patch.diffs.Add(new Diff(Operation.EQUAL, suffix)); + } + + // Roll back the start points. + patch.start1 -= prefix.Length; + patch.start2 -= prefix.Length; + // Extend the lengths. + patch.length1 += prefix.Length + suffix.Length; + patch.length2 += prefix.Length + suffix.Length; + } + + /** + * Compute a list of patches to turn text1 into text2. + * A set of diffs will be computed. + * @param text1 Old text. + * @param text2 New text. + * @return List of Patch objects. + */ + public List patch_make(string text1, string text2) { + // Check for null inputs not needed since null can't be passed in C#. + // No diffs provided, compute our own. + List diffs = diff_main(text1, text2, true); + if (diffs.Count > 2) { + diff_cleanupSemantic(diffs); + diff_cleanupEfficiency(diffs); + } + return patch_make(text1, diffs); + } + + /** + * Compute a list of patches to turn text1 into text2. + * text1 will be derived from the provided diffs. + * @param diffs Array of Diff objects for text1 to text2. + * @return List of Patch objects. + */ + public List patch_make(List diffs) { + // Check for null inputs not needed since null can't be passed in C#. + // No origin string provided, compute our own. + string text1 = diff_text1(diffs); + return patch_make(text1, diffs); + } + + /** + * Compute a list of patches to turn text1 into text2. + * text2 is ignored, diffs are the delta between text1 and text2. + * @param text1 Old text + * @param text2 Ignored. + * @param diffs Array of Diff objects for text1 to text2. + * @return List of Patch objects. + * @deprecated Prefer patch_make(string text1, List diffs). + */ + public List patch_make(string text1, string text2, + List diffs) { + return patch_make(text1, diffs); + } + + /** + * Compute a list of patches to turn text1 into text2. + * text2 is not provided, diffs are the delta between text1 and text2. + * @param text1 Old text. + * @param diffs Array of Diff objects for text1 to text2. + * @return List of Patch objects. + */ + public List patch_make(string text1, List diffs) { + // Check for null inputs not needed since null can't be passed in C#. + List patches = new List(); + if (diffs.Count == 0) { + return patches; // Get rid of the null case. + } + Patch patch = new Patch(); + int char_count1 = 0; // Number of characters into the text1 string. + int char_count2 = 0; // Number of characters into the text2 string. + // Start with text1 (prepatch_text) and apply the diffs until we arrive at + // text2 (postpatch_text). We recreate the patches one by one to determine + // context info. + string prepatch_text = text1; + string postpatch_text = text1; + foreach (Diff aDiff in diffs) { + if (patch.diffs.Count == 0 && aDiff.operation != Operation.EQUAL) { + // A new patch starts here. + patch.start1 = char_count1; + patch.start2 = char_count2; + } + + switch (aDiff.operation) { + case Operation.INSERT: + patch.diffs.Add(aDiff); + patch.length2 += aDiff.text.Length; + postpatch_text = postpatch_text.Insert(char_count2, aDiff.text); + break; + case Operation.DELETE: + patch.length1 += aDiff.text.Length; + patch.diffs.Add(aDiff); + postpatch_text = postpatch_text.Remove(char_count2, + aDiff.text.Length); + break; + case Operation.EQUAL: + if (aDiff.text.Length <= 2 * Patch_Margin + && patch.diffs.Count() != 0 && aDiff != diffs.Last()) { + // Small equality inside a patch. + patch.diffs.Add(aDiff); + patch.length1 += aDiff.text.Length; + patch.length2 += aDiff.text.Length; + } + + if (aDiff.text.Length >= 2 * Patch_Margin) { + // Time for a new patch. + if (patch.diffs.Count != 0) { + patch_addContext(patch, prepatch_text); + patches.Add(patch); + patch = new Patch(); + // Unlike Unidiff, our patch lists have a rolling context. + // https://github.com/google/diff-match-patch/wiki/Unidiff + // Update prepatch text & pos to reflect the application of the + // just completed patch. + prepatch_text = postpatch_text; + char_count1 = char_count2; + } + } + break; + } + + // Update the current character count. + if (aDiff.operation != Operation.INSERT) { + char_count1 += aDiff.text.Length; + } + if (aDiff.operation != Operation.DELETE) { + char_count2 += aDiff.text.Length; + } + } + // Pick up the leftover patch if not empty. + if (patch.diffs.Count != 0) { + patch_addContext(patch, prepatch_text); + patches.Add(patch); + } + + return patches; + } + + /** + * Given an array of patches, return another array that is identical. + * @param patches Array of Patch objects. + * @return Array of Patch objects. + */ + public List patch_deepCopy(List patches) { + List patchesCopy = new List(); + foreach (Patch aPatch in patches) { + Patch patchCopy = new Patch(); + foreach (Diff aDiff in aPatch.diffs) { + Diff diffCopy = new Diff(aDiff.operation, aDiff.text); + patchCopy.diffs.Add(diffCopy); + } + patchCopy.start1 = aPatch.start1; + patchCopy.start2 = aPatch.start2; + patchCopy.length1 = aPatch.length1; + patchCopy.length2 = aPatch.length2; + patchesCopy.Add(patchCopy); + } + return patchesCopy; + } + + /** + * Merge a set of patches onto the text. Return a patched text, as well + * as an array of true/false values indicating which patches were applied. + * @param patches Array of Patch objects + * @param text Old text. + * @return Two element Object array, containing the new text and an array of + * bool values. + */ + public Object[] patch_apply(List patches, string text) { + if (patches.Count == 0) { + return new Object[] { text, new bool[0] }; + } + + // Deep copy the patches so that no changes are made to originals. + patches = patch_deepCopy(patches); + + string nullPadding = this.patch_addPadding(patches); + text = nullPadding + text + nullPadding; + patch_splitMax(patches); + + int x = 0; + // delta keeps track of the offset between the expected and actual + // location of the previous patch. If there are patches expected at + // positions 10 and 20, but the first patch was found at 12, delta is 2 + // and the second patch has an effective expected position of 22. + int delta = 0; + bool[] results = new bool[patches.Count]; + foreach (Patch aPatch in patches) { + int expected_loc = aPatch.start2 + delta; + string text1 = diff_text1(aPatch.diffs); + int start_loc; + int end_loc = -1; + if (text1.Length > this.Match_MaxBits) { + // patch_splitMax will only provide an oversized pattern + // in the case of a monster delete. + start_loc = match_main(text, + text1.Substring(0, this.Match_MaxBits), expected_loc); + if (start_loc != -1) { + end_loc = match_main(text, + text1.Substring(text1.Length - this.Match_MaxBits), + expected_loc + text1.Length - this.Match_MaxBits); + if (end_loc == -1 || start_loc >= end_loc) { + // Can't find valid trailing context. Drop this patch. + start_loc = -1; + } + } + } else { + start_loc = this.match_main(text, text1, expected_loc); + } + if (start_loc == -1) { + // No match found. :( + results[x] = false; + // Subtract the delta for this failed patch from subsequent patches. + delta -= aPatch.length2 - aPatch.length1; + } else { + // Found a match. :) + results[x] = true; + delta = start_loc - expected_loc; + string text2; + if (end_loc == -1) { + text2 = text.JavaSubstring(start_loc, + Math.Min(start_loc + text1.Length, text.Length)); + } else { + text2 = text.JavaSubstring(start_loc, + Math.Min(end_loc + this.Match_MaxBits, text.Length)); + } + if (text1 == text2) { + // Perfect match, just shove the Replacement text in. + text = text.Substring(0, start_loc) + diff_text2(aPatch.diffs) + + text.Substring(start_loc + text1.Length); + } else { + // Imperfect match. Run a diff to get a framework of equivalent + // indices. + List diffs = diff_main(text1, text2, false); + if (text1.Length > this.Match_MaxBits + && this.diff_levenshtein(diffs) / (float) text1.Length + > this.Patch_DeleteThreshold) { + // The end points match, but the content is unacceptably bad. + results[x] = false; + } else { + diff_cleanupSemanticLossless(diffs); + int index1 = 0; + foreach (Diff aDiff in aPatch.diffs) { + if (aDiff.operation != Operation.EQUAL) { + int index2 = diff_xIndex(diffs, index1); + if (aDiff.operation == Operation.INSERT) { + // Insertion + text = text.Insert(start_loc + index2, aDiff.text); + } else if (aDiff.operation == Operation.DELETE) { + // Deletion + text = text.Remove(start_loc + index2, diff_xIndex(diffs, + index1 + aDiff.text.Length) - index2); + } + } + if (aDiff.operation != Operation.DELETE) { + index1 += aDiff.text.Length; + } + } + } + } + } + x++; + } + // Strip the padding off. + text = text.Substring(nullPadding.Length, text.Length + - 2 * nullPadding.Length); + return new Object[] { text, results }; + } + + /** + * Add some padding on text start and end so that edges can match something. + * Intended to be called only from within patch_apply. + * @param patches Array of Patch objects. + * @return The padding string added to each side. + */ + public string patch_addPadding(List patches) { + short paddingLength = this.Patch_Margin; + string nullPadding = string.Empty; + for (short x = 1; x <= paddingLength; x++) { + nullPadding += (char)x; + } + + // Bump all the patches forward. + foreach (Patch aPatch in patches) { + aPatch.start1 += paddingLength; + aPatch.start2 += paddingLength; + } + + // Add some padding on start of first diff. + Patch patch = patches.First(); + List diffs = patch.diffs; + if (diffs.Count == 0 || diffs.First().operation != Operation.EQUAL) { + // Add nullPadding equality. + diffs.Insert(0, new Diff(Operation.EQUAL, nullPadding)); + patch.start1 -= paddingLength; // Should be 0. + patch.start2 -= paddingLength; // Should be 0. + patch.length1 += paddingLength; + patch.length2 += paddingLength; + } else if (paddingLength > diffs.First().text.Length) { + // Grow first equality. + Diff firstDiff = diffs.First(); + int extraLength = paddingLength - firstDiff.text.Length; + firstDiff.text = nullPadding.Substring(firstDiff.text.Length) + + firstDiff.text; + patch.start1 -= extraLength; + patch.start2 -= extraLength; + patch.length1 += extraLength; + patch.length2 += extraLength; + } + + // Add some padding on end of last diff. + patch = patches.Last(); + diffs = patch.diffs; + if (diffs.Count == 0 || diffs.Last().operation != Operation.EQUAL) { + // Add nullPadding equality. + diffs.Add(new Diff(Operation.EQUAL, nullPadding)); + patch.length1 += paddingLength; + patch.length2 += paddingLength; + } else if (paddingLength > diffs.Last().text.Length) { + // Grow last equality. + Diff lastDiff = diffs.Last(); + int extraLength = paddingLength - lastDiff.text.Length; + lastDiff.text += nullPadding.Substring(0, extraLength); + patch.length1 += extraLength; + patch.length2 += extraLength; + } + + return nullPadding; + } + + /** + * Look through the patches and break up any which are longer than the + * maximum limit of the match algorithm. + * Intended to be called only from within patch_apply. + * @param patches List of Patch objects. + */ + public void patch_splitMax(List patches) { + short patch_size = this.Match_MaxBits; + for (int x = 0; x < patches.Count; x++) { + if (patches[x].length1 <= patch_size) { + continue; + } + Patch bigpatch = patches[x]; + // Remove the big old patch. + patches.Splice(x--, 1); + int start1 = bigpatch.start1; + int start2 = bigpatch.start2; + string precontext = string.Empty; + while (bigpatch.diffs.Count != 0) { + // Create one of several smaller patches. + Patch patch = new Patch(); + bool empty = true; + patch.start1 = start1 - precontext.Length; + patch.start2 = start2 - precontext.Length; + if (precontext.Length != 0) { + patch.length1 = patch.length2 = precontext.Length; + patch.diffs.Add(new Diff(Operation.EQUAL, precontext)); + } + while (bigpatch.diffs.Count != 0 + && patch.length1 < patch_size - this.Patch_Margin) { + Operation diff_type = bigpatch.diffs[0].operation; + string diff_text = bigpatch.diffs[0].text; + if (diff_type == Operation.INSERT) { + // Insertions are harmless. + patch.length2 += diff_text.Length; + start2 += diff_text.Length; + patch.diffs.Add(bigpatch.diffs.First()); + bigpatch.diffs.RemoveAt(0); + empty = false; + } else if (diff_type == Operation.DELETE && patch.diffs.Count == 1 + && patch.diffs.First().operation == Operation.EQUAL + && diff_text.Length > 2 * patch_size) { + // This is a large deletion. Let it pass in one chunk. + patch.length1 += diff_text.Length; + start1 += diff_text.Length; + empty = false; + patch.diffs.Add(new Diff(diff_type, diff_text)); + bigpatch.diffs.RemoveAt(0); + } else { + // Deletion or equality. Only take as much as we can stomach. + diff_text = diff_text.Substring(0, Math.Min(diff_text.Length, + patch_size - patch.length1 - Patch_Margin)); + patch.length1 += diff_text.Length; + start1 += diff_text.Length; + if (diff_type == Operation.EQUAL) { + patch.length2 += diff_text.Length; + start2 += diff_text.Length; + } else { + empty = false; + } + patch.diffs.Add(new Diff(diff_type, diff_text)); + if (diff_text == bigpatch.diffs[0].text) { + bigpatch.diffs.RemoveAt(0); + } else { + bigpatch.diffs[0].text = + bigpatch.diffs[0].text.Substring(diff_text.Length); + } + } + } + // Compute the head context for the next patch. + precontext = this.diff_text2(patch.diffs); + precontext = precontext.Substring(Math.Max(0, + precontext.Length - this.Patch_Margin)); + + string postcontext = null; + // Append the end context for this patch. + if (diff_text1(bigpatch.diffs).Length > Patch_Margin) { + postcontext = diff_text1(bigpatch.diffs) + .Substring(0, Patch_Margin); + } else { + postcontext = diff_text1(bigpatch.diffs); + } + + if (postcontext.Length != 0) { + patch.length1 += postcontext.Length; + patch.length2 += postcontext.Length; + if (patch.diffs.Count != 0 + && patch.diffs[patch.diffs.Count - 1].operation + == Operation.EQUAL) { + patch.diffs[patch.diffs.Count - 1].text += postcontext; + } else { + patch.diffs.Add(new Diff(Operation.EQUAL, postcontext)); + } + } + if (!empty) { + patches.Splice(++x, 0, patch); + } + } + } + } + + /** + * Take a list of patches and return a textual representation. + * @param patches List of Patch objects. + * @return Text representation of patches. + */ + public string patch_toText(List patches) { + StringBuilder text = new StringBuilder(); + foreach (Patch aPatch in patches) { + text.Append(aPatch); + } + return text.ToString(); + } + + /** + * Parse a textual representation of patches and return a List of Patch + * objects. + * @param textline Text representation of patches. + * @return List of Patch objects. + * @throws ArgumentException If invalid input. + */ + public List patch_fromText(string textline) { + List patches = new List(); + if (textline.Length == 0) { + return patches; + } + string[] text = textline.Split('\n'); + int textPointer = 0; + Patch patch; + Regex patchHeader + = new Regex("^@@ -(\\d+),?(\\d*) \\+(\\d+),?(\\d*) @@$"); + Match m; + char sign; + string line; + while (textPointer < text.Length) { + m = patchHeader.Match(text[textPointer]); + if (!m.Success) { + throw new ArgumentException("Invalid patch string: " + + text[textPointer]); + } + patch = new Patch(); + patches.Add(patch); + patch.start1 = Convert.ToInt32(m.Groups[1].Value); + if (m.Groups[2].Length == 0) { + patch.start1--; + patch.length1 = 1; + } else if (m.Groups[2].Value == "0") { + patch.length1 = 0; + } else { + patch.start1--; + patch.length1 = Convert.ToInt32(m.Groups[2].Value); + } + + patch.start2 = Convert.ToInt32(m.Groups[3].Value); + if (m.Groups[4].Length == 0) { + patch.start2--; + patch.length2 = 1; + } else if (m.Groups[4].Value == "0") { + patch.length2 = 0; + } else { + patch.start2--; + patch.length2 = Convert.ToInt32(m.Groups[4].Value); + } + textPointer++; + + while (textPointer < text.Length) { + try { + sign = text[textPointer][0]; + } catch (IndexOutOfRangeException) { + // Blank line? Whatever. + textPointer++; + continue; + } + line = text[textPointer].Substring(1); + line = line.Replace("+", "%2b"); + line = HttpUtility.UrlDecode(line); + if (sign == '-') { + // Deletion. + patch.diffs.Add(new Diff(Operation.DELETE, line)); + } else if (sign == '+') { + // Insertion. + patch.diffs.Add(new Diff(Operation.INSERT, line)); + } else if (sign == ' ') { + // Minor equality. + patch.diffs.Add(new Diff(Operation.EQUAL, line)); + } else if (sign == '@') { + // Start of next patch. + break; + } else { + // WTF? + throw new ArgumentException( + "Invalid patch mode '" + sign + "' in: " + line); + } + textPointer++; + } + } + return patches; + } + + /** + * Encodes a string with URI-style % escaping. + * Compatible with JavaScript's encodeURI function. + * + * @param str The string to encode. + * @return The encoded string. + */ + public static string encodeURI(string str) { + // C# is overzealous in the replacements. Walk back on a few. + return new StringBuilder(HttpUtility.UrlEncode(str)) + .Replace('+', ' ').Replace("%20", " ").Replace("%21", "!") + .Replace("%2a", "*").Replace("%27", "'").Replace("%28", "(") + .Replace("%29", ")").Replace("%3b", ";").Replace("%2f", "/") + .Replace("%3f", "?").Replace("%3a", ":").Replace("%40", "@") + .Replace("%26", "&").Replace("%3d", "=").Replace("%2b", "+") + .Replace("%24", "$").Replace("%2c", ",").Replace("%23", "#") + .Replace("%7e", "~") + .ToString(); + } + } +} diff --git a/Tests/DiffMatchPatch.Tests.ps1 b/Tests/DiffMatchPatch.Tests.ps1 new file mode 100644 index 0000000..1db1ef5 --- /dev/null +++ b/Tests/DiffMatchPatch.Tests.ps1 @@ -0,0 +1,88 @@ +$here = Split-Path (Split-Path -Parent $MyInvocation.MyCommand.Path) -Parent +$sut = (Split-Path -Leaf $MyInvocation.MyCommand.Path).Replace('.Tests', '').Replace('ps1', 'psm1') +Import-Module "$here\DiffMatchPatch\$sut" -force + +Describe "Get-CommonPrefixLength" { + It "Returns 0 if there is no common prefix" { + Get-CommonPrefixLength "abc" "xyz" | Should -Be 0 + } + It "It returns the number of common prefix chars" { + Get-CommonPrefixLength "1234abcdef" "1234xyz" | Should -Be 4 + } + It "It also works if one string begins with the other" { + Get-CommonPrefixLength "1234" "1234xyz" | Should -Be 4 + } +} + +Describe "Get-CommonSuffixLength" { + It "Returns 0 if there is no common suffix" { + Get-CommonSuffixLength "abc" "xyz" | Should -Be 0 + } + It "It returns the number of common suffix chars" { + Get-CommonSuffixLength "abcdef1234" "xyz1234" | Should -Be 4 + } + It "It also works if one string ends with the other" { + Get-CommonSuffixLength "1234" "xyz1234" | Should -Be 4 + } +} + +Describe "Get-CommonOverlapLength" { + It "Returns 0 if there is no common overlap" { + Get-CommonOverlapLength "" "abcd" | Should -Be 0 + } + It "It returns the number of common overlap chars if one string contains the other" { + Get-CommonOverlapLength "abc" "abcd" | Should -Be 3 + } + It "It returns 0 if there is no overlap" { + Get-CommonOverlapLength "123456" "abcd" | Should -Be 0 + } + It "It returns the number of common overlap chars" { + Get-CommonOverlapLength "123456xxx" "xxxabcd" | Should -Be 3 + } +} + +Describe "ConvertFrom-DiffToHtml" { + It "Outputs diff converted to hmlt if -NoFile switch is used" { + $res = Get-CharDiff 'this and that' 'tit and tat' | ConvertFrom-DiffToHtml -NoFile + $res.Trim() | Should -Be 'thisit and that' + } + It "It returns a file path if -NoOpen switch is used" { + Get-CharDiff 'this and that' 'tit and tat' | ConvertFrom-DiffToHtml -NoOpen | + Test-Path | Should -Be $true +} +} + +Describe "ConvertFrom-DiffToText" { + $srcText = "jumps over the lazy" + $destText = "jumped over a lazy" + $res = Get-CharDiff $srcText $destText | ConvertFrom-DiffToText + It "It converts a list of diffs back to the source (text1)" { + $res[0] | Should -Be $srcText + } + It "It converts a list of diffs back to the destination (text2)" { + $res[1] | Should -Be $destText + } +} + + +Describe "Get-CharDiff" { + It "It recognizes equality of two strings" { + $diffs = New-Object System.Collections.Generic.List[DiffMatchPatch.Diff] + $diffs.Add((New-Object DiffMatchPatch.Diff('Equal', 'abc'))) + Get-CharDiff 'abc' 'abc' | Should -Be $diffs + } + It "It recognizes a simple insertion in one of the strings" { + $diffs = New-Object System.Collections.Generic.List[DiffMatchPatch.Diff] + $diffs.Add((New-Object DiffMatchPatch.Diff('Equal', 'ab'))) + $diffs.Add((New-Object DiffMatchPatch.Diff('Insert', '123'))) + $diffs.Add((New-Object DiffMatchPatch.Diff('Equal', 'c'))) + Get-CharDiff 'abc' 'ab123c' | Should -Be $diffs + } + It "It recognizes a simple deletion in one of the strings" { + $diffs = New-Object System.Collections.Generic.List[DiffMatchPatch.Diff] + $diffs.Add((New-Object DiffMatchPatch.Diff('Equal', 'a'))) + $diffs.Add((New-Object DiffMatchPatch.Diff('Delete', '123'))) + $diffs.Add((New-Object DiffMatchPatch.Diff('Equal', 'bc'))) + Get-CharDiff 'a123bc' 'abc' | Should -Be $diffs + } +} diff --git a/build.ps1 b/build.ps1 new file mode 100644 index 0000000..a71fcc9 --- /dev/null +++ b/build.ps1 @@ -0,0 +1,17 @@ +# Fix Example section markup from PlatyPS +$files = dir "$PSSCriptRoot\PSDiff\docs" +$replacements = foreach ($file in $files) { + $exampleText = [RegEx]::Match(($file | Get-Content -Raw), '(?ms)## EXAMPLES(.*)?## PARAMETERS').Groups[1].Value + $examples = ($exampleText -split '###.*EXAMPLE \d\s*[-]*') | select -Skip 1 + foreach ($example in $examples) { + [PSCustomObject][ordered]@{ + Old = $example + New = "`r`n" + '```' + "`r`n$($example.Replace('```','').Trim())`r`n" + '```' + "`r`n" + Path = $file.FullName + } + } +} + +foreach ($replacement in $replacements) { + (Get-Content $replacement.Path -Raw).Replace($replacement.Old, $replacement.New) | Set-Content $replacement.Path +}