howto/recover-corrupted-object-harder.html

   1 <!DOCTYPE html>
   2 <html xmlns="http://www.w3.org/1999/xhtml" lang="en">
   3 <head>
   4 <meta charset="UTF-8"/>
   5 <meta http-equiv="X-UA-Compatible" content="IE=edge"/>
   6 <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
   7 <meta name="generator" content="Asciidoctor 2.0.20"/>
   8 <title>How to recover an object from scratch</title>
   9 <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Open+Sans:300,300italic,400,400italic,600,600italic%7CNoto+Serif:400,400italic,700,700italic%7CDroid+Sans+Mono:400,700"/>
  10 <style>
  11 /*! Asciidoctor default stylesheet | MIT License | https://asciidoctor.org */
  12 /* Uncomment the following line when using as a custom stylesheet */
  13 /* @import "https://fonts.googleapis.com/css?family=Open+Sans:300,300italic,400,400italic,600,600italic%7CNoto+Serif:400,400italic,700,700italic%7CDroid+Sans+Mono:400,700"; */
  14 html{font-family:sans-serif;-webkit-text-size-adjust:100%}
  15 a{background:none}
  16 a:focus{outline:thin dotted}
  17 a:active,a:hover{outline:0}
  18 h1{font-size:2em;margin:.67em 0}
  19 b,strong{font-weight:bold}
  20 abbr{font-size:.9em}
  21 abbr[title]{cursor:help;border-bottom:1px dotted #dddddf;text-decoration:none}
  22 dfn{font-style:italic}
  23 hr{height:0}
  24 mark{background:#ff0;color:#000}
  25 code,kbd,pre,samp{font-family:monospace;font-size:1em}
  26 pre{white-space:pre-wrap}
  27 q{quotes:"\201C" "\201D" "\2018" "\2019"}
  28 small{font-size:80%}
  29 sub,sup{font-size:75%;line-height:0;position:relative;vertical-align:baseline}
  30 sup{top:-.5em}
  31 sub{bottom:-.25em}
  32 img{border:0}
  33 svg:not(:root){overflow:hidden}
  34 figure{margin:0}
  35 audio,video{display:inline-block}
  36 audio:not([controls]){display:none;height:0}
  37 fieldset{border:1px solid silver;margin:0 2px;padding:.35em .625em .75em}
  38 legend{border:0;padding:0}
  39 button,input,select,textarea{font-family:inherit;font-size:100%;margin:0}
  40 button,input{line-height:normal}
  41 button,select{text-transform:none}
  42 button,html input[type=button],input[type=reset],input[type=submit]{-webkit-appearance:button;cursor:pointer}
  43 button[disabled],html input[disabled]{cursor:default}
  44 input[type=checkbox],input[type=radio]{padding:0}
  45 button::-moz-focus-inner,input::-moz-focus-inner{border:0;padding:0}
  46 textarea{overflow:auto;vertical-align:top}
  47 table{border-collapse:collapse;border-spacing:0}
  48 *,::before,::after{box-sizing:border-box}
  49 html,body{font-size:100%}
  50 body{background:#fff;color:rgba(0,0,0,.8);padding:0;margin:0;font-family:"Noto Serif","DejaVu Serif",serif;line-height:1;position:relative;cursor:auto;-moz-tab-size:4;-o-tab-size:4;tab-size:4;word-wrap:anywhere;-moz-osx-font-smoothing:grayscale;-webkit-font-smoothing:antialiased}
  51 a:hover{cursor:pointer}
  52 img,object,embed{max-width:100%;height:auto}
  53 object,embed{height:100%}
  54 img{-ms-interpolation-mode:bicubic}
  55 .left{float:left!important}
  56 .right{float:right!important}
  57 .text-left{text-align:left!important}
  58 .text-right{text-align:right!important}
  59 .text-center{text-align:center!important}
  60 .text-justify{text-align:justify!important}
  61 .hide{display:none}
  62 img,object,svg{display:inline-block;vertical-align:middle}
  63 textarea{height:auto;min-height:50px}
  64 select{width:100%}
  65 .subheader,.admonitionblock td.content>.title,.audioblock>.title,.exampleblock>.title,.imageblock>.title,.listingblock>.title,.literalblock>.title,.stemblock>.title,.openblock>.title,.paragraph>.title,.quoteblock>.title,table.tableblock>.title,.verseblock>.title,.videoblock>.title,.dlist>.title,.olist>.title,.ulist>.title,.qlist>.title,.hdlist>.title{line-height:1.45;color:#7a2518;font-weight:400;margin-top:0;margin-bottom:.25em}
  66 div,dl,dt,dd,ul,ol,li,h1,h2,h3,#toctitle,.sidebarblock>.content>.title,h4,h5,h6,pre,form,p,blockquote,th,td{margin:0;padding:0}
  67 a{color:#2156a5;text-decoration:underline;line-height:inherit}
  68 a:hover,a:focus{color:#1d4b8f}
  69 a img{border:0}
  70 p{line-height:1.6;margin-bottom:1.25em;text-rendering:optimizeLegibility}
  71 p aside{font-size:.875em;line-height:1.35;font-style:italic}
  72 h1,h2,h3,#toctitle,.sidebarblock>.content>.title,h4,h5,h6{font-family:"Open Sans","DejaVu Sans",sans-serif;font-weight:300;font-style:normal;color:#ba3925;text-rendering:optimizeLegibility;margin-top:1em;margin-bottom:.5em;line-height:1.0125em}
  73 h1 small,h2 small,h3 small,#toctitle small,.sidebarblock>.content>.title small,h4 small,h5 small,h6 small{font-size:60%;color:#e99b8f;line-height:0}
  74 h1{font-size:2.125em}
  75 h2{font-size:1.6875em}
  76 h3,#toctitle,.sidebarblock>.content>.title{font-size:1.375em}
  77 h4,h5{font-size:1.125em}
  78 h6{font-size:1em}
  79 hr{border:solid #dddddf;border-width:1px 0 0;clear:both;margin:1.25em 0 1.1875em}
  80 em,i{font-style:italic;line-height:inherit}
  81 strong,b{font-weight:bold;line-height:inherit}
  82 small{font-size:60%;line-height:inherit}
  83 code{font-family:"Droid Sans Mono","DejaVu Sans Mono",monospace;font-weight:400;color:rgba(0,0,0,.9)}
  84 ul,ol,dl{line-height:1.6;margin-bottom:1.25em;list-style-position:outside;font-family:inherit}
  85 ul,ol{margin-left:1.5em}
  86 ul li ul,ul li ol{margin-left:1.25em;margin-bottom:0}
  87 ul.circle{list-style-type:circle}
  88 ul.disc{list-style-type:disc}
  89 ul.square{list-style-type:square}
  90 ul.circle ul:not([class]),ul.disc ul:not([class]),ul.square ul:not([class]){list-style:inherit}
  91 ol li ul,ol li ol{margin-left:1.25em;margin-bottom:0}
  92 dl dt{margin-bottom:.3125em;font-weight:bold}
  93 dl dd{margin-bottom:1.25em}
  94 blockquote{margin:0 0 1.25em;padding:.5625em 1.25em 0 1.1875em;border-left:1px solid #ddd}
  95 blockquote,blockquote p{line-height:1.6;color:rgba(0,0,0,.85)}
  96 @media screen and (min-width:768px){h1,h2,h3,#toctitle,.sidebarblock>.content>.title,h4,h5,h6{line-height:1.2}
  97 h1{font-size:2.75em}
  98 h2{font-size:2.3125em}
  99 h3,#toctitle,.sidebarblock>.content>.title{font-size:1.6875em}
 100 h4{font-size:1.4375em}}
 101 table{background:#fff;margin-bottom:1.25em;border:1px solid #dedede;word-wrap:normal}
 102 table thead,table tfoot{background:#f7f8f7}
 103 table thead tr th,table thead tr td,table tfoot tr th,table tfoot tr td{padding:.5em .625em .625em;font-size:inherit;color:rgba(0,0,0,.8);text-align:left}
 104 table tr th,table tr td{padding:.5625em .625em;font-size:inherit;color:rgba(0,0,0,.8)}
 105 table tr.even,table tr.alt{background:#f8f8f7}
 106 table thead tr th,table tfoot tr th,table tbody tr td,table tr td,table tfoot tr td{line-height:1.6}
 107 h1,h2,h3,#toctitle,.sidebarblock>.content>.title,h4,h5,h6{line-height:1.2;word-spacing:-.05em}
 108 h1 strong,h2 strong,h3 strong,#toctitle strong,.sidebarblock>.content>.title strong,h4 strong,h5 strong,h6 strong{font-weight:400}
 109 .center{margin-left:auto;margin-right:auto}
 110 .stretch{width:100%}
 111 .clearfix::before,.clearfix::after,.float-group::before,.float-group::after{content:" ";display:table}
 112 .clearfix::after,.float-group::after{clear:both}
 113 :not(pre).nobreak{word-wrap:normal}
 114 :not(pre).nowrap{white-space:nowrap}
 115 :not(pre).pre-wrap{white-space:pre-wrap}
 116 :not(pre):not([class^=L])>code{font-size:.9375em;font-style:normal!important;letter-spacing:0;padding:.1em .5ex;word-spacing:-.15em;background:#f7f7f8;border-radius:4px;line-height:1.45;text-rendering:optimizeSpeed}
 117 pre{color:rgba(0,0,0,.9);font-family:"Droid Sans Mono","DejaVu Sans Mono",monospace;line-height:1.45;text-rendering:optimizeSpeed}
 118 pre code,pre pre{color:inherit;font-size:inherit;line-height:inherit}
 119 pre>code{display:block}
 120 pre.nowrap,pre.nowrap pre{white-space:pre;word-wrap:normal}
 121 em em{font-style:normal}
 122 strong strong{font-weight:400}
 123 .keyseq{color:rgba(51,51,51,.8)}
 124 kbd{font-family:"Droid Sans Mono","DejaVu Sans Mono",monospace;display:inline-block;color:rgba(0,0,0,.8);font-size:.65em;line-height:1.45;background:#f7f7f7;border:1px solid #ccc;border-radius:3px;box-shadow:0 1px 0 rgba(0,0,0,.2),inset 0 0 0 .1em #fff;margin:0 .15em;padding:.2em .5em;vertical-align:middle;position:relative;top:-.1em;white-space:nowrap}
 125 .keyseq kbd:first-child{margin-left:0}
 126 .keyseq kbd:last-child{margin-right:0}
 127 .menuseq,.menuref{color:#000}
 128 .menuseq b:not(.caret),.menuref{font-weight:inherit}
 129 .menuseq{word-spacing:-.02em}
 130 .menuseq b.caret{font-size:1.25em;line-height:.8}
 131 .menuseq i.caret{font-weight:bold;text-align:center;width:.45em}
 132 b.button::before,b.button::after{position:relative;top:-1px;font-weight:400}
 133 b.button::before{content:"[";padding:0 3px 0 2px}
 134 b.button::after{content:"]";padding:0 2px 0 3px}
 135 p a>code:hover{color:rgba(0,0,0,.9)}
 136 #header,#content,#footnotes,#footer{width:100%;margin:0 auto;max-width:62.5em;*zoom:1;position:relative;padding-left:.9375em;padding-right:.9375em}
 137 #header::before,#header::after,#content::before,#content::after,#footnotes::before,#footnotes::after,#footer::before,#footer::after{content:" ";display:table}
 138 #header::after,#content::after,#footnotes::after,#footer::after{clear:both}
 139 #content{margin-top:1.25em}
 140 #content::before{content:none}
 141 #header>h1:first-child{color:rgba(0,0,0,.85);margin-top:2.25rem;margin-bottom:0}
 142 #header>h1:first-child+#toc{margin-top:8px;border-top:1px solid #dddddf}
 143 #header>h1:only-child,body.toc2 #header>h1:nth-last-child(2){border-bottom:1px solid #dddddf;padding-bottom:8px}
 144 #header .details{border-bottom:1px solid #dddddf;line-height:1.45;padding-top:.25em;padding-bottom:.25em;padding-left:.25em;color:rgba(0,0,0,.6);display:flex;flex-flow:row wrap}
 145 #header .details span:first-child{margin-left:-.125em}
 146 #header .details span.email a{color:rgba(0,0,0,.85)}
 147 #header .details br{display:none}
 148 #header .details br+span::before{content:"\00a0\2013\00a0"}
 149 #header .details br+span.author::before{content:"\00a0\22c5\00a0";color:rgba(0,0,0,.85)}
 150 #header .details br+span#revremark::before{content:"\00a0|\00a0"}
 151 #header #revnumber{text-transform:capitalize}
 152 #header #revnumber::after{content:"\00a0"}
 153 #content>h1:first-child:not([class]){color:rgba(0,0,0,.85);border-bottom:1px solid #dddddf;padding-bottom:8px;margin-top:0;padding-top:1rem;margin-bottom:1.25rem}
 154 #toc{border-bottom:1px solid #e7e7e9;padding-bottom:.5em}
 155 #toc>ul{margin-left:.125em}
 156 #toc ul.sectlevel0>li>a{font-style:italic}
 157 #toc ul.sectlevel0 ul.sectlevel1{margin:.5em 0}
 158 #toc ul{font-family:"Open Sans","DejaVu Sans",sans-serif;list-style-type:none}
 159 #toc li{line-height:1.3334;margin-top:.3334em}
 160 #toc a{text-decoration:none}
 161 #toc a:active{text-decoration:underline}
 162 #toctitle{color:#7a2518;font-size:1.2em}
 163 @media screen and (min-width:768px){#toctitle{font-size:1.375em}
 164 body.toc2{padding-left:15em;padding-right:0}
 165 #toc.toc2{margin-top:0!important;background:#f8f8f7;position:fixed;width:15em;left:0;top:0;border-right:1px solid #e7e7e9;border-top-width:0!important;border-bottom-width:0!important;z-index:1000;padding:1.25em 1em;height:100%;overflow:auto}
 166 #toc.toc2 #toctitle{margin-top:0;margin-bottom:.8rem;font-size:1.2em}
 167 #toc.toc2>ul{font-size:.9em;margin-bottom:0}
 168 #toc.toc2 ul ul{margin-left:0;padding-left:1em}
 169 #toc.toc2 ul.sectlevel0 ul.sectlevel1{padding-left:0;margin-top:.5em;margin-bottom:.5em}
 170 body.toc2.toc-right{padding-left:0;padding-right:15em}
 171 body.toc2.toc-right #toc.toc2{border-right-width:0;border-left:1px solid #e7e7e9;left:auto;right:0}}
 172 @media screen and (min-width:1280px){body.toc2{padding-left:20em;padding-right:0}
 173 #toc.toc2{width:20em}
 174 #toc.toc2 #toctitle{font-size:1.375em}
 175 #toc.toc2>ul{font-size:.95em}
 176 #toc.toc2 ul ul{padding-left:1.25em}
 177 body.toc2.toc-right{padding-left:0;padding-right:20em}}
 178 #content #toc{border:1px solid #e0e0dc;margin-bottom:1.25em;padding:1.25em;background:#f8f8f7;border-radius:4px}
 179 #content #toc>:first-child{margin-top:0}
 180 #content #toc>:last-child{margin-bottom:0}
 181 #footer{max-width:none;background:rgba(0,0,0,.8);padding:1.25em}
 182 #footer-text{color:hsla(0,0%,100%,.8);line-height:1.44}
 183 #content{margin-bottom:.625em}
 184 .sect1{padding-bottom:.625em}
 185 @media screen and (min-width:768px){#content{margin-bottom:1.25em}
 186 .sect1{padding-bottom:1.25em}}
 187 .sect1:last-child{padding-bottom:0}
 188 .sect1+.sect1{border-top:1px solid #e7e7e9}
 189 #content h1>a.anchor,h2>a.anchor,h3>a.anchor,#toctitle>a.anchor,.sidebarblock>.content>.title>a.anchor,h4>a.anchor,h5>a.anchor,h6>a.anchor{position:absolute;z-index:1001;width:1.5ex;margin-left:-1.5ex;display:block;text-decoration:none!important;visibility:hidden;text-align:center;font-weight:400}
 190 #content h1>a.anchor::before,h2>a.anchor::before,h3>a.anchor::before,#toctitle>a.anchor::before,.sidebarblock>.content>.title>a.anchor::before,h4>a.anchor::before,h5>a.anchor::before,h6>a.anchor::before{content:"\00A7";font-size:.85em;display:block;padding-top:.1em}
 191 #content h1:hover>a.anchor,#content h1>a.anchor:hover,h2:hover>a.anchor,h2>a.anchor:hover,h3:hover>a.anchor,#toctitle:hover>a.anchor,.sidebarblock>.content>.title:hover>a.anchor,h3>a.anchor:hover,#toctitle>a.anchor:hover,.sidebarblock>.content>.title>a.anchor:hover,h4:hover>a.anchor,h4>a.anchor:hover,h5:hover>a.anchor,h5>a.anchor:hover,h6:hover>a.anchor,h6>a.anchor:hover{visibility:visible}
 192 #content h1>a.link,h2>a.link,h3>a.link,#toctitle>a.link,.sidebarblock>.content>.title>a.link,h4>a.link,h5>a.link,h6>a.link{color:#ba3925;text-decoration:none}
 193 #content h1>a.link:hover,h2>a.link:hover,h3>a.link:hover,#toctitle>a.link:hover,.sidebarblock>.content>.title>a.link:hover,h4>a.link:hover,h5>a.link:hover,h6>a.link:hover{color:#a53221}
 194 details,.audioblock,.imageblock,.literalblock,.listingblock,.stemblock,.videoblock{margin-bottom:1.25em}
 195 details{margin-left:1.25rem}
 196 details>summary{cursor:pointer;display:block;position:relative;line-height:1.6;margin-bottom:.625rem;outline:none;-webkit-tap-highlight-color:transparent}
 197 details>summary::-webkit-details-marker{display:none}
 198 details>summary::before{content:"";border:solid transparent;border-left:solid;border-width:.3em 0 .3em .5em;position:absolute;top:.5em;left:-1.25rem;transform:translateX(15%)}
 199 details[open]>summary::before{border:solid transparent;border-top:solid;border-width:.5em .3em 0;transform:translateY(15%)}
 200 details>summary::after{content:"";width:1.25rem;height:1em;position:absolute;top:.3em;left:-1.25rem}
 201 .admonitionblock td.content>.title,.audioblock>.title,.exampleblock>.title,.imageblock>.title,.listingblock>.title,.literalblock>.title,.stemblock>.title,.openblock>.title,.paragraph>.title,.quoteblock>.title,table.tableblock>.title,.verseblock>.title,.videoblock>.title,.dlist>.title,.olist>.title,.ulist>.title,.qlist>.title,.hdlist>.title{text-rendering:optimizeLegibility;text-align:left;font-family:"Noto Serif","DejaVu Serif",serif;font-size:1rem;font-style:italic}
 202 table.tableblock.fit-content>caption.title{white-space:nowrap;width:0}
 203 .paragraph.lead>p,#preamble>.sectionbody>[class=paragraph]:first-of-type p{font-size:1.21875em;line-height:1.6;color:rgba(0,0,0,.85)}
 204 .admonitionblock>table{border-collapse:separate;border:0;background:none;width:100%}
 205 .admonitionblock>table td.icon{text-align:center;width:80px}
 206 .admonitionblock>table td.icon img{max-width:none}
 207 .admonitionblock>table td.icon .title{font-weight:bold;font-family:"Open Sans","DejaVu Sans",sans-serif;text-transform:uppercase}
 208 .admonitionblock>table td.content{padding-left:1.125em;padding-right:1.25em;border-left:1px solid #dddddf;color:rgba(0,0,0,.6);word-wrap:anywhere}
 209 .admonitionblock>table td.content>:last-child>:last-child{margin-bottom:0}
 210 .exampleblock>.content{border:1px solid #e6e6e6;margin-bottom:1.25em;padding:1.25em;background:#fff;border-radius:4px}
 211 .sidebarblock{border:1px solid #dbdbd6;margin-bottom:1.25em;padding:1.25em;background:#f3f3f2;border-radius:4px}
 212 .sidebarblock>.content>.title{color:#7a2518;margin-top:0;text-align:center}
 213 .exampleblock>.content>:first-child,.sidebarblock>.content>:first-child{margin-top:0}
 214 .exampleblock>.content>:last-child,.exampleblock>.content>:last-child>:last-child,.exampleblock>.content .olist>ol>li:last-child>:last-child,.exampleblock>.content .ulist>ul>li:last-child>:last-child,.exampleblock>.content .qlist>ol>li:last-child>:last-child,.sidebarblock>.content>:last-child,.sidebarblock>.content>:last-child>:last-child,.sidebarblock>.content .olist>ol>li:last-child>:last-child,.sidebarblock>.content .ulist>ul>li:last-child>:last-child,.sidebarblock>.content .qlist>ol>li:last-child>:last-child{margin-bottom:0}
 215 .literalblock pre,.listingblock>.content>pre{border-radius:4px;overflow-x:auto;padding:1em;font-size:.8125em}
 216 @media screen and (min-width:768px){.literalblock pre,.listingblock>.content>pre{font-size:.90625em}}
 217 @media screen and (min-width:1280px){.literalblock pre,.listingblock>.content>pre{font-size:1em}}
 218 .literalblock pre,.listingblock>.content>pre:not(.highlight),.listingblock>.content>pre[class=highlight],.listingblock>.content>pre[class^="highlight "]{background:#f7f7f8}
 219 .literalblock.output pre{color:#f7f7f8;background:rgba(0,0,0,.9)}
 220 .listingblock>.content{position:relative}
 221 .listingblock code[data-lang]::before{display:none;content:attr(data-lang);position:absolute;font-size:.75em;top:.425rem;right:.5rem;line-height:1;text-transform:uppercase;color:inherit;opacity:.5}
 222 .listingblock:hover code[data-lang]::before{display:block}
 223 .listingblock.terminal pre .command::before{content:attr(data-prompt);padding-right:.5em;color:inherit;opacity:.5}
 224 .listingblock.terminal pre .command:not([data-prompt])::before{content:"$"}
 225 .listingblock pre.highlightjs{padding:0}
 226 .listingblock pre.highlightjs>code{padding:1em;border-radius:4px}
 227 .listingblock pre.prettyprint{border-width:0}
 228 .prettyprint{background:#f7f7f8}
 229 pre.prettyprint .linenums{line-height:1.45;margin-left:2em}
 230 pre.prettyprint li{background:none;list-style-type:inherit;padding-left:0}
 231 pre.prettyprint li code[data-lang]::before{opacity:1}
 232 pre.prettyprint li:not(:first-child) code[data-lang]::before{display:none}
 233 table.linenotable{border-collapse:separate;border:0;margin-bottom:0;background:none}
 234 table.linenotable td[class]{color:inherit;vertical-align:top;padding:0;line-height:inherit;white-space:normal}
 235 table.linenotable td.code{padding-left:.75em}
 236 table.linenotable td.linenos,pre.pygments .linenos{border-right:1px solid;opacity:.35;padding-right:.5em;-webkit-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none}
 237 pre.pygments span.linenos{display:inline-block;margin-right:.75em}
 238 .quoteblock{margin:0 1em 1.25em 1.5em;display:table}
 239 .quoteblock:not(.excerpt)>.title{margin-left:-1.5em;margin-bottom:.75em}
 240 .quoteblock blockquote,.quoteblock p{color:rgba(0,0,0,.85);font-size:1.15rem;line-height:1.75;word-spacing:.1em;letter-spacing:0;font-style:italic;text-align:justify}
 241 .quoteblock blockquote{margin:0;padding:0;border:0}
 242 .quoteblock blockquote::before{content:"\201c";float:left;font-size:2.75em;font-weight:bold;line-height:.6em;margin-left:-.6em;color:#7a2518;text-shadow:0 1px 2px rgba(0,0,0,.1)}
 243 .quoteblock blockquote>.paragraph:last-child p{margin-bottom:0}
 244 .quoteblock .attribution{margin-top:.75em;margin-right:.5ex;text-align:right}
 245 .verseblock{margin:0 1em 1.25em}
 246 .verseblock pre{font-family:"Open Sans","DejaVu Sans",sans-serif;font-size:1.15rem;color:rgba(0,0,0,.85);font-weight:300;text-rendering:optimizeLegibility}
 247 .verseblock pre strong{font-weight:400}
 248 .verseblock .attribution{margin-top:1.25rem;margin-left:.5ex}
 249 .quoteblock .attribution,.verseblock .attribution{font-size:.9375em;line-height:1.45;font-style:italic}
 250 .quoteblock .attribution br,.verseblock .attribution br{display:none}
 251 .quoteblock .attribution cite,.verseblock .attribution cite{display:block;letter-spacing:-.025em;color:rgba(0,0,0,.6)}
 252 .quoteblock.abstract blockquote::before,.quoteblock.excerpt blockquote::before,.quoteblock .quoteblock blockquote::before{display:none}
 253 .quoteblock.abstract blockquote,.quoteblock.abstract p,.quoteblock.excerpt blockquote,.quoteblock.excerpt p,.quoteblock .quoteblock blockquote,.quoteblock .quoteblock p{line-height:1.6;word-spacing:0}
 254 .quoteblock.abstract{margin:0 1em 1.25em;display:block}
 255 .quoteblock.abstract>.title{margin:0 0 .375em;font-size:1.15em;text-align:center}
 256 .quoteblock.excerpt>blockquote,.quoteblock .quoteblock{padding:0 0 .25em 1em;border-left:.25em solid #dddddf}
 257 .quoteblock.excerpt,.quoteblock .quoteblock{margin-left:0}
 258 .quoteblock.excerpt blockquote,.quoteblock.excerpt p,.quoteblock .quoteblock blockquote,.quoteblock .quoteblock p{color:inherit;font-size:1.0625rem}
 259 .quoteblock.excerpt .attribution,.quoteblock .quoteblock .attribution{color:inherit;font-size:.85rem;text-align:left;margin-right:0}
 260 p.tableblock:last-child{margin-bottom:0}
 261 td.tableblock>.content{margin-bottom:1.25em;word-wrap:anywhere}
 262 td.tableblock>.content>:last-child{margin-bottom:-1.25em}
 263 table.tableblock,th.tableblock,td.tableblock{border:0 solid #dedede}
 264 table.grid-all>*>tr>*{border-width:1px}
 265 table.grid-cols>*>tr>*{border-width:0 1px}
 266 table.grid-rows>*>tr>*{border-width:1px 0}
 267 table.frame-all{border-width:1px}
 268 table.frame-ends{border-width:1px 0}
 269 table.frame-sides{border-width:0 1px}
 270 table.frame-none>colgroup+*>:first-child>*,table.frame-sides>colgroup+*>:first-child>*{border-top-width:0}
 271 table.frame-none>:last-child>:last-child>*,table.frame-sides>:last-child>:last-child>*{border-bottom-width:0}
 272 table.frame-none>*>tr>:first-child,table.frame-ends>*>tr>:first-child{border-left-width:0}
 273 table.frame-none>*>tr>:last-child,table.frame-ends>*>tr>:last-child{border-right-width:0}
 274 table.stripes-all>*>tr,table.stripes-odd>*>tr:nth-of-type(odd),table.stripes-even>*>tr:nth-of-type(even),table.stripes-hover>*>tr:hover{background:#f8f8f7}
 275 th.halign-left,td.halign-left{text-align:left}
 276 th.halign-right,td.halign-right{text-align:right}
 277 th.halign-center,td.halign-center{text-align:center}
 278 th.valign-top,td.valign-top{vertical-align:top}
 279 th.valign-bottom,td.valign-bottom{vertical-align:bottom}
 280 th.valign-middle,td.valign-middle{vertical-align:middle}
 281 table thead th,table tfoot th{font-weight:bold}
 282 tbody tr th{background:#f7f8f7}
 283 tbody tr th,tbody tr th p,tfoot tr th,tfoot tr th p{color:rgba(0,0,0,.8);font-weight:bold}
 284 p.tableblock>code:only-child{background:none;padding:0}
 285 p.tableblock{font-size:1em}
 286 ol{margin-left:1.75em}
 287 ul li ol{margin-left:1.5em}
 288 dl dd{margin-left:1.125em}
 289 dl dd:last-child,dl dd:last-child>:last-child{margin-bottom:0}
 290 li p,ul dd,ol dd,.olist .olist,.ulist .ulist,.ulist .olist,.olist .ulist{margin-bottom:.625em}
 291 ul.checklist,ul.none,ol.none,ul.no-bullet,ol.no-bullet,ol.unnumbered,ul.unstyled,ol.unstyled{list-style-type:none}
 292 ul.no-bullet,ol.no-bullet,ol.unnumbered{margin-left:.625em}
 293 ul.unstyled,ol.unstyled{margin-left:0}
 294 li>p:empty:only-child::before{content:"";display:inline-block}
 295 ul.checklist>li>p:first-child{margin-left:-1em}
 296 ul.checklist>li>p:first-child>.fa-square-o:first-child,ul.checklist>li>p:first-child>.fa-check-square-o:first-child{width:1.25em;font-size:.8em;position:relative;bottom:.125em}
 297 ul.checklist>li>p:first-child>input[type=checkbox]:first-child{margin-right:.25em}
 298 ul.inline{display:flex;flex-flow:row wrap;list-style:none;margin:0 0 .625em -1.25em}
 299 ul.inline>li{margin-left:1.25em}
 300 .unstyled dl dt{font-weight:400;font-style:normal}
 301 ol.arabic{list-style-type:decimal}
 302 ol.decimal{list-style-type:decimal-leading-zero}
 303 ol.loweralpha{list-style-type:lower-alpha}
 304 ol.upperalpha{list-style-type:upper-alpha}
 305 ol.lowerroman{list-style-type:lower-roman}
 306 ol.upperroman{list-style-type:upper-roman}
 307 ol.lowergreek{list-style-type:lower-greek}
 308 .hdlist>table,.colist>table{border:0;background:none}
 309 .hdlist>table>tbody>tr,.colist>table>tbody>tr{background:none}
 310 td.hdlist1,td.hdlist2{vertical-align:top;padding:0 .625em}
 311 td.hdlist1{font-weight:bold;padding-bottom:1.25em}
 312 td.hdlist2{word-wrap:anywhere}
 313 .literalblock+.colist,.listingblock+.colist{margin-top:-.5em}
 314 .colist td:not([class]):first-child{padding:.4em .75em 0;line-height:1;vertical-align:top}
 315 .colist td:not([class]):first-child img{max-width:none}
 316 .colist td:not([class]):last-child{padding:.25em 0}
 317 .thumb,.th{line-height:0;display:inline-block;border:4px solid #fff;box-shadow:0 0 0 1px #ddd}
 318 .imageblock.left{margin:.25em .625em 1.25em 0}
 319 .imageblock.right{margin:.25em 0 1.25em .625em}
 320 .imageblock>.title{margin-bottom:0}
 321 .imageblock.thumb,.imageblock.th{border-width:6px}
 322 .imageblock.thumb>.title,.imageblock.th>.title{padding:0 .125em}
 323 .image.left,.image.right{margin-top:.25em;margin-bottom:.25em;display:inline-block;line-height:0}
 324 .image.left{margin-right:.625em}
 325 .image.right{margin-left:.625em}
 326 a.image{text-decoration:none;display:inline-block}
 327 a.image object{pointer-events:none}
 328 sup.footnote,sup.footnoteref{font-size:.875em;position:static;vertical-align:super}
 329 sup.footnote a,sup.footnoteref a{text-decoration:none}
 330 sup.footnote a:active,sup.footnoteref a:active{text-decoration:underline}
 331 #footnotes{padding-top:.75em;padding-bottom:.75em;margin-bottom:.625em}
 332 #footnotes hr{width:20%;min-width:6.25em;margin:-.25em 0 .75em;border-width:1px 0 0}
 333 #footnotes .footnote{padding:0 .375em 0 .225em;line-height:1.3334;font-size:.875em;margin-left:1.2em;margin-bottom:.2em}
 334 #footnotes .footnote a:first-of-type{font-weight:bold;text-decoration:none;margin-left:-1.05em}
 335 #footnotes .footnote:last-of-type{margin-bottom:0}
 336 #content #footnotes{margin-top:-.625em;margin-bottom:0;padding:.75em 0}
 337 div.unbreakable{page-break-inside:avoid}
 338 .big{font-size:larger}
 339 .small{font-size:smaller}
 340 .underline{text-decoration:underline}
 341 .overline{text-decoration:overline}
 342 .line-through{text-decoration:line-through}
 343 .aqua{color:#00bfbf}
 344 .aqua-background{background:#00fafa}
 345 .black{color:#000}
 346 .black-background{background:#000}
 347 .blue{color:#0000bf}
 348 .blue-background{background:#0000fa}
 349 .fuchsia{color:#bf00bf}
 350 .fuchsia-background{background:#fa00fa}
 351 .gray{color:#606060}
 352 .gray-background{background:#7d7d7d}
 353 .green{color:#006000}
 354 .green-background{background:#007d00}
 355 .lime{color:#00bf00}
 356 .lime-background{background:#00fa00}
 357 .maroon{color:#600000}
 358 .maroon-background{background:#7d0000}
 359 .navy{color:#000060}
 360 .navy-background{background:#00007d}
 361 .olive{color:#606000}
 362 .olive-background{background:#7d7d00}
 363 .purple{color:#600060}
 364 .purple-background{background:#7d007d}
 365 .red{color:#bf0000}
 366 .red-background{background:#fa0000}
 367 .silver{color:#909090}
 368 .silver-background{background:#bcbcbc}
 369 .teal{color:#006060}
 370 .teal-background{background:#007d7d}
 371 .white{color:#bfbfbf}
 372 .white-background{background:#fafafa}
 373 .yellow{color:#bfbf00}
 374 .yellow-background{background:#fafa00}
 375 span.icon>.fa{cursor:default}
 376 a span.icon>.fa{cursor:inherit}
 377 .admonitionblock td.icon [class^="fa icon-"]{font-size:2.5em;text-shadow:1px 1px 2px rgba(0,0,0,.5);cursor:default}
 378 .admonitionblock td.icon .icon-note::before{content:"\f05a";color:#19407c}
 379 .admonitionblock td.icon .icon-tip::before{content:"\f0eb";text-shadow:1px 1px 2px rgba(155,155,0,.8);color:#111}
 380 .admonitionblock td.icon .icon-warning::before{content:"\f071";color:#bf6900}
 381 .admonitionblock td.icon .icon-caution::before{content:"\f06d";color:#bf3400}
 382 .admonitionblock td.icon .icon-important::before{content:"\f06a";color:#bf0000}
 383 .conum[data-value]{display:inline-block;color:#fff!important;background:rgba(0,0,0,.8);border-radius:50%;text-align:center;font-size:.75em;width:1.67em;height:1.67em;line-height:1.67em;font-family:"Open Sans","DejaVu Sans",sans-serif;font-style:normal;font-weight:bold}
 384 .conum[data-value] *{color:#fff!important}
 385 .conum[data-value]+b{display:none}
 386 .conum[data-value]::after{content:attr(data-value)}
 387 pre .conum[data-value]{position:relative;top:-.125em}
 388 b.conum *{color:inherit!important}
 389 .conum:not([data-value]):empty{display:none}
 390 dt,th.tableblock,td.content,div.footnote{text-rendering:optimizeLegibility}
 391 h1,h2,p,td.content,span.alt,summary{letter-spacing:-.01em}
 392 p strong,td.content strong,div.footnote strong{letter-spacing:-.005em}
 393 p,blockquote,dt,td.content,td.hdlist1,span.alt,summary{font-size:1.0625rem}
 394 p{margin-bottom:1.25rem}
 395 .sidebarblock p,.sidebarblock dt,.sidebarblock td.content,p.tableblock{font-size:1em}
 396 .exampleblock>.content{background:#fffef7;border-color:#e0e0dc;box-shadow:0 1px 4px #e0e0dc}
 397 .print-only{display:none!important}
 398 @page{margin:1.25cm .75cm}
 399 @media print{*{box-shadow:none!important;text-shadow:none!important}
 400 html{font-size:80%}
 401 a{color:inherit!important;text-decoration:underline!important}
 402 a.bare,a[href^="#"],a[href^="mailto:"]{text-decoration:none!important}
 403 a[href^="http:"]:not(.bare)::after,a[href^="https:"]:not(.bare)::after{content:"(" attr(href) ")";display:inline-block;font-size:.875em;padding-left:.25em}
 404 abbr[title]{border-bottom:1px dotted}
 405 abbr[title]::after{content:" (" attr(title) ")"}
 406 pre,blockquote,tr,img,object,svg{page-break-inside:avoid}
 407 thead{display:table-header-group}
 408 svg{max-width:100%}
 409 p,blockquote,dt,td.content{font-size:1em;orphans:3;widows:3}
 410 h2,h3,#toctitle,.sidebarblock>.content>.title{page-break-after:avoid}
 411 #header,#content,#footnotes,#footer{max-width:none}
 412 #toc,.sidebarblock,.exampleblock>.content{background:none!important}
 413 #toc{border-bottom:1px solid #dddddf!important;padding-bottom:0!important}
 414 body.book #header{text-align:center}
 415 body.book #header>h1:first-child{border:0!important;margin:2.5em 0 1em}
 416 body.book #header .details{border:0!important;display:block;padding:0!important}
 417 body.book #header .details span:first-child{margin-left:0!important}
 418 body.book #header .details br{display:block}
 419 body.book #header .details br+span::before{content:none!important}
 420 body.book #toc{border:0!important;text-align:left!important;padding:0!important;margin:0!important}
 421 body.book #toc,body.book #preamble,body.book h1.sect0,body.book .sect1>h2{page-break-before:always}
 422 .listingblock code[data-lang]::before{display:block}
 423 #footer{padding:0 .9375em}
 424 .hide-on-print{display:none!important}
 425 .print-only{display:block!important}
 426 .hide-for-print{display:none!important}
 427 .show-for-print{display:inherit!important}}
 428 @media amzn-kf8,print{#header>h1:first-child{margin-top:1.25rem}
 429 .sect1{padding:0!important}
 430 .sect1+.sect1{border:0}
 431 #footer{background:none}
 432 #footer-text{color:rgba(0,0,0,.6);font-size:.9em}}
 433 @media amzn-kf8{#header,#content,#footnotes,#footer{padding:0}}
 434 </style>
 435 <style>
 436 pre>code {
 437    display: inline;
 438 }
 439 </style>
 440 </head>
 441 <body class="article">
 442 <div id="header">
 443 <h1>How to recover an object from scratch</h1>
 444 <div class="details">
 445 <span id="revdate">2024-08-23</span>
 446 </div>
 447 </div>
 448 <div id="content">
 449 <div id="preamble">
 450 <div class="sectionbody">
 451 <div class="paragraph">
 452 <p>I was recently presented with a repository with a corrupted packfile,
 453 and was asked if the data was recoverable. This post-mortem describes
 454 the steps I took to investigate and fix the problem. I thought others
 455 might find the process interesting, and it might help somebody in the
 456 same situation.</p>
 457 </div>
 458 <div class="sidebarblock">
 459 <div class="content">
 460 <div class="paragraph">
 461 <p>Note: In this case, no good copy of the repository was available. For
 462 the much easier case where you can get the corrupted object from
 463 elsewhere, see <a href="recover-corrupted-blob-object.html">this howto</a>.</p>
 464 </div>
 465 </div>
 466 </div>
 467 <div class="paragraph">
 468 <p>I started with an fsck, which found a problem with exactly one object
 469 (I&#8217;ve used $pack and $obj below to keep the output readable, and also
 470 because I&#8217;ll refer to them later):</p>
 471 </div>
 472 <div class="listingblock">
 473 <div class="content">
 474 <pre>    $ git fsck
 475     error: $pack SHA1 checksum mismatch
 476     error: index CRC mismatch for object $obj from $pack at offset 51653873
 477     error: inflate: data stream error (incorrect data check)
 478     error: cannot unpack $obj from $pack at offset 51653873</pre>
 479 </div>
 480 </div>
 481 <div class="paragraph">
 482 <p>The pack checksum failing means a byte is munged somewhere, and it is
 483 presumably in the object mentioned (since both the index checksum and
 484 zlib were failing).</p>
 485 </div>
 486 <div class="paragraph">
 487 <p>Reading the zlib source code, I found that "incorrect data check" means
 488 that the adler-32 checksum at the end of the zlib data did not match the
 489 inflated data. So stepping the data through zlib would not help, as it
 490 did not fail until the very end, when we realize the CRC does not match.
 491 The problematic bytes could be anywhere in the object data.</p>
 492 </div>
 493 <div class="paragraph">
 494 <p>The first thing I did was pull the broken data out of the packfile. I
 495 needed to know how big the object was, which I found out with:</p>
 496 </div>
 497 <div class="listingblock">
 498 <div class="content">
 499 <pre>    $ git show-index &lt;$idx | cut -d' ' -f1 | sort -n | grep -A1 51653873
 500     51653873
 501     51664736</pre>
 502 </div>
 503 </div>
 504 <div class="paragraph">
 505 <p>Show-index gives us the list of objects and their offsets. We throw away
 506 everything but the offsets, and then sort them so that our interesting
 507 offset (which we got from the fsck output above) is followed immediately
 508 by the offset of the next object. Now we know that the object data is
 509 10863 bytes long, and we can grab it with:</p>
 510 </div>
 511 <div class="listingblock">
 512 <div class="content">
 513 <pre>  dd if=$pack of=object bs=1 skip=51653873 count=10863</pre>
 514 </div>
 515 </div>
 516 <div class="paragraph">
 517 <p>I inspected a hexdump of the data, looking for any obvious bogosity
 518 (e.g., a 4K run of zeroes would be a good sign of filesystem
 519 corruption). But everything looked pretty reasonable.</p>
 520 </div>
 521 <div class="paragraph">
 522 <p>Note that the "object" file isn&#8217;t fit for feeding straight to zlib; it
 523 has the git packed object header, which is variable-length. We want to
 524 strip that off so we can start playing with the zlib data directly. You
 525 can either work your way through it manually (the format is described in
 526 <a href="../gitformat-pack.html">gitformat-pack(5)</a>),
 527 or you can walk through it in a debugger. I did the latter, creating a
 528 valid pack like:</p>
 529 </div>
 530 <div class="listingblock">
 531 <div class="content">
 532 <pre>    # pack magic and version
 533     printf 'PACK\0\0\0\2' &gt;tmp.pack
 534     # pack has one object
 535     printf '\0\0\0\1' &gt;&gt;tmp.pack
 536     # now add our object data
 537     cat object &gt;&gt;tmp.pack
 538     # and then append the pack trailer
 539     /path/to/git.git/t/helper/test-tool sha1 -b &lt;tmp.pack &gt;trailer
 540     cat trailer &gt;&gt;tmp.pack</pre>
 541 </div>
 542 </div>
 543 <div class="paragraph">
 544 <p>and then running "git index-pack tmp.pack" in the debugger (stop at
 545 unpack_raw_entry). Doing this, I found that there were 3 bytes of header
 546 (and the header itself had a sane type and size). So I stripped those
 547 off with:</p>
 548 </div>
 549 <div class="listingblock">
 550 <div class="content">
 551 <pre>    dd if=object of=zlib bs=1 skip=3</pre>
 552 </div>
 553 </div>
 554 <div class="paragraph">
 555 <p>I ran the result through zlib&#8217;s inflate using a custom C program. And
 556 while it did report the error, I did get the right number of output
 557 bytes (i.e., it matched git&#8217;s size header that we decoded above). But
 558 feeding the result back to "git hash-object" didn&#8217;t produce the same
 559 sha1. So there were some wrong bytes, but I didn&#8217;t know which. The file
 560 happened to be C source code, so I hoped I could notice something
 561 obviously wrong with it, but I didn&#8217;t. I even got it to compile!</p>
 562 </div>
 563 <div class="paragraph">
 564 <p>I also tried comparing it to other versions of the same path in the
 565 repository, hoping that there would be some part of the diff that didn&#8217;t
 566 make sense. Unfortunately, this happened to be the only revision of this
 567 particular file in the repository, so I had nothing to compare against.</p>
 568 </div>
 569 <div class="paragraph">
 570 <p>So I took a different approach. Working under the guess that the
 571 corruption was limited to a single byte, I wrote a program to munge each
 572 byte individually, and try inflating the result. Since the object was
 573 only 10K compressed, that worked out to about 2.5M attempts, which took
 574 a few minutes.</p>
 575 </div>
 576 <div class="paragraph">
 577 <p>The program I used is here:</p>
 578 </div>
 579 <div class="listingblock">
 580 <div class="content">
 581 <pre>#include &lt;stdio.h&gt;
 582 #include &lt;unistd.h&gt;
 583 #include &lt;string.h&gt;
 584 #include &lt;signal.h&gt;
 585 #include &lt;zlib.h&gt;
 586
 587 static int try_zlib(unsigned char *buf, int len)
 588 {
 589         /* make this absurdly large so we don't have to loop */
 590         static unsigned char out[1024*1024];
 591         z_stream z;
 592         int ret;
 593
 594         memset(&amp;z, 0, sizeof(z));
 595         inflateInit(&amp;z);
 596
 597         z.next_in = buf;
 598         z.avail_in = len;
 599         z.next_out = out;
 600         z.avail_out = sizeof(out);
 601
 602         ret = inflate(&amp;z, 0);
 603         inflateEnd(&amp;z);
 604         return ret &gt;= 0;
 605 }
 606
 607 /* eye candy */
 608 static int counter = 0;
 609 static void progress(int sig)
 610 {
 611         fprintf(stderr, "\r%d", counter);
 612         alarm(1);
 613 }
 614
 615 int main(void)
 616 {
 617         /* oversized so we can read the whole buffer in */
 618         unsigned char buf[1024*1024];
 619         int len;
 620         unsigned i, j;
 621
 622         signal(SIGALRM, progress);
 623         alarm(1);
 624
 625         len = read(0, buf, sizeof(buf));
 626         for (i = 0; i &lt; len; i++) {
 627                 unsigned char c = buf[i];
 628                 for (j = 0; j &lt;= 0xff; j++) {
 629                         buf[i] = j;
 630
 631                         counter++;
 632                         if (try_zlib(buf, len))
 633                                 printf("i=%d, j=%x\n", i, j);
 634                 }
 635                 buf[i] = c;
 636         }
 637
 638         alarm(0);
 639         fprintf(stderr, "\n");
 640         return 0;
 641 }</pre>
 642 </div>
 643 </div>
 644 <div class="paragraph">
 645 <p>I compiled and ran with:</p>
 646 </div>
 647 <div class="listingblock">
 648 <div class="content">
 649 <pre>  gcc -Wall -Werror -O3 munge.c -o munge -lz
 650   ./munge &lt;zlib</pre>
 651 </div>
 652 </div>
 653 <div class="paragraph">
 654 <p>There were a few false positives early on (if you write "no data" in the
 655 zlib header, zlib thinks it&#8217;s just fine :) ). But I got a hit about
 656 halfway through:</p>
 657 </div>
 658 <div class="listingblock">
 659 <div class="content">
 660 <pre>  i=5642, j=c7</pre>
 661 </div>
 662 </div>
 663 <div class="paragraph">
 664 <p>I let it run to completion, and got a few more hits at the end (where it
 665 was munging the CRC to match our broken data). So there was a good
 666 chance this middle hit was the source of the problem.</p>
 667 </div>
 668 <div class="paragraph">
 669 <p>I confirmed by tweaking the byte in a hex editor, zlib inflating the
 670 result (no errors!), and then piping the output into "git hash-object",
 671 which reported the sha1 of the broken object. Success!</p>
 672 </div>
 673 <div class="paragraph">
 674 <p>I fixed the packfile itself with:</p>
 675 </div>
 676 <div class="listingblock">
 677 <div class="content">
 678 <pre>  chmod +w $pack
 679   printf '\xc7' | dd of=$pack bs=1 seek=51659518 conv=notrunc
 680   chmod -w $pack</pre>
 681 </div>
 682 </div>
 683 <div class="paragraph">
 684 <p>The <code>\xc7</code> comes from the replacement byte our "munge" program found.
 685 The offset 51659518 is derived by taking the original object offset
 686 (51653873), adding the replacement offset found by "munge" (5642), and
 687 then adding back in the 3 bytes of git header we stripped.</p>
 688 </div>
 689 <div class="paragraph">
 690 <p>After that, "git fsck" ran clean.</p>
 691 </div>
 692 <div class="paragraph">
 693 <p>As for the corruption itself, I was lucky that it was indeed a single
 694 byte. In fact, it turned out to be a single bit. The byte 0xc7 was
 695 corrupted to 0xc5. So presumably it was caused by faulty hardware, or a
 696 cosmic ray.</p>
 697 </div>
 698 <div class="paragraph">
 699 <p>And the aborted attempt to look at the inflated output to see what was
 700 wrong? I could have looked forever and never found it. Here&#8217;s the diff
 701 between what the corrupted data inflates to, versus the real data:</p>
 702 </div>
 703 <div class="listingblock">
 704 <div class="content">
 705 <pre>  -       cp = strtok (arg, "+");
 706   +       cp = strtok (arg, ".");</pre>
 707 </div>
 708 </div>
 709 <div class="paragraph">
 710 <p>It tweaked one byte and still ended up as valid, readable C that just
 711 happened to do something totally different! One takeaway is that on a
 712 less unlucky day, looking at the zlib output might have actually been
 713 helpful, as most random changes would actually break the C code.</p>
 714 </div>
 715 <div class="paragraph">
 716 <p>But more importantly, git&#8217;s hashing and checksumming noticed a problem
 717 that easily could have gone undetected in another system. The result
 718 still compiled, but would have caused an interesting bug (that would
 719 have been blamed on some random commit).</p>
 720 </div>
 721 </div>
 722 </div>
 723 <div class="sect1">
 724 <h2 id="_the_adventure_continues">The adventure continues&#8230;&#8203;</h2>
 725 <div class="sectionbody">
 726 <div class="paragraph">
 727 <p>I ended up doing this again! Same entity, new hardware. The assumption
 728 at this point is that the old disk corrupted the packfile, and then the
 729 corruption was migrated to the new hardware (because it was done by
 730 rsync or similar, and no fsck was done at the time of migration).</p>
 731 </div>
 732 <div class="paragraph">
 733 <p>This time, the affected blob was over 20 megabytes, which was far too
 734 large to do a brute-force on. I followed the instructions above to
 735 create the <code>zlib</code> file. I then used the <code>inflate</code> program below to pull
 736 the corrupted data from that. Examining that output gave me a hint about
 737 where in the file the corruption was. But now I was working with the
 738 file itself, not the zlib contents. So knowing the sha1 of the object
 739 and the approximate area of the corruption, I used the <code>sha1-munge</code>
 740 program below to brute-force the correct byte.</p>
 741 </div>
 742 <div class="paragraph">
 743 <p>Here&#8217;s the inflate program (it&#8217;s essentially <code>gunzip</code> but without the
 744 <code>.gz</code> header processing):</p>
 745 </div>
 746 <div class="listingblock">
 747 <div class="content">
 748 <pre>#include &lt;stdio.h&gt;
 749 #include &lt;string.h&gt;
 750 #include &lt;zlib.h&gt;
 751 #include &lt;stdlib.h&gt;
 752
 753 int main(int argc, char **argv)
 754 {
 755         /*
 756          * oversized so we can read the whole buffer in;
 757          * this could actually be switched to streaming
 758          * to avoid any memory limitations
 759          */
 760         static unsigned char buf[25 * 1024 * 1024];
 761         static unsigned char out[25 * 1024 * 1024];
 762         int len;
 763         z_stream z;
 764         int ret;
 765
 766         len = read(0, buf, sizeof(buf));
 767         memset(&amp;z, 0, sizeof(z));
 768         inflateInit(&amp;z);
 769
 770         z.next_in = buf;
 771         z.avail_in = len;
 772         z.next_out = out;
 773         z.avail_out = sizeof(out);
 774
 775         ret = inflate(&amp;z, 0);
 776         if (ret != Z_OK &amp;&amp; ret != Z_STREAM_END)
 777                 fprintf(stderr, "initial inflate failed (%d)\n", ret);
 778
 779         fprintf(stderr, "outputting %lu bytes", z.total_out);
 780         fwrite(out, 1, z.total_out, stdout);
 781         return 0;
 782 }</pre>
 783 </div>
 784 </div>
 785 <div class="paragraph">
 786 <p>And here is the <code>sha1-munge</code> program:</p>
 787 </div>
 788 <div class="listingblock">
 789 <div class="content">
 790 <pre>#include &lt;stdio.h&gt;
 791 #include &lt;unistd.h&gt;
 792 #include &lt;string.h&gt;
 793 #include &lt;signal.h&gt;
 794 #include &lt;openssl/sha.h&gt;
 795 #include &lt;stdlib.h&gt;
 796
 797 /* eye candy */
 798 static int counter = 0;
 799 static void progress(int sig)
 800 {
 801         fprintf(stderr, "\r%d", counter);
 802         alarm(1);
 803 }
 804
 805 static const signed char hexval_table[256] = {
 806          -1, -1, -1, -1, -1, -1, -1, -1,                /* 00-07 */
 807          -1, -1, -1, -1, -1, -1, -1, -1,                /* 08-0f */
 808          -1, -1, -1, -1, -1, -1, -1, -1,                /* 10-17 */
 809          -1, -1, -1, -1, -1, -1, -1, -1,                /* 18-1f */
 810          -1, -1, -1, -1, -1, -1, -1, -1,                /* 20-27 */
 811          -1, -1, -1, -1, -1, -1, -1, -1,                /* 28-2f */
 812           0,  1,  2,  3,  4,  5,  6,  7,                /* 30-37 */
 813           8,  9, -1, -1, -1, -1, -1, -1,                /* 38-3f */
 814          -1, 10, 11, 12, 13, 14, 15, -1,                /* 40-47 */
 815          -1, -1, -1, -1, -1, -1, -1, -1,                /* 48-4f */
 816          -1, -1, -1, -1, -1, -1, -1, -1,                /* 50-57 */
 817          -1, -1, -1, -1, -1, -1, -1, -1,                /* 58-5f */
 818          -1, 10, 11, 12, 13, 14, 15, -1,                /* 60-67 */
 819          -1, -1, -1, -1, -1, -1, -1, -1,                /* 68-67 */
 820          -1, -1, -1, -1, -1, -1, -1, -1,                /* 70-77 */
 821          -1, -1, -1, -1, -1, -1, -1, -1,                /* 78-7f */
 822          -1, -1, -1, -1, -1, -1, -1, -1,                /* 80-87 */
 823          -1, -1, -1, -1, -1, -1, -1, -1,                /* 88-8f */
 824          -1, -1, -1, -1, -1, -1, -1, -1,                /* 90-97 */
 825          -1, -1, -1, -1, -1, -1, -1, -1,                /* 98-9f */
 826          -1, -1, -1, -1, -1, -1, -1, -1,                /* a0-a7 */
 827          -1, -1, -1, -1, -1, -1, -1, -1,                /* a8-af */
 828          -1, -1, -1, -1, -1, -1, -1, -1,                /* b0-b7 */
 829          -1, -1, -1, -1, -1, -1, -1, -1,                /* b8-bf */
 830          -1, -1, -1, -1, -1, -1, -1, -1,                /* c0-c7 */
 831          -1, -1, -1, -1, -1, -1, -1, -1,                /* c8-cf */
 832          -1, -1, -1, -1, -1, -1, -1, -1,                /* d0-d7 */
 833          -1, -1, -1, -1, -1, -1, -1, -1,                /* d8-df */
 834          -1, -1, -1, -1, -1, -1, -1, -1,                /* e0-e7 */
 835          -1, -1, -1, -1, -1, -1, -1, -1,                /* e8-ef */
 836          -1, -1, -1, -1, -1, -1, -1, -1,                /* f0-f7 */
 837          -1, -1, -1, -1, -1, -1, -1, -1,                /* f8-ff */
 838 };
 839
 840 static inline unsigned int hexval(unsigned char c)
 841 {
 842 return hexval_table[c];
 843 }
 844
 845 static int get_sha1_hex(const char *hex, unsigned char *sha1)
 846 {
 847         int i;
 848         for (i = 0; i &lt; 20; i++) {
 849                 unsigned int val;
 850                 /*
 851                  * hex[1]=='\0' is caught when val is checked below,
 852                  * but if hex[0] is NUL we have to avoid reading
 853                  * past the end of the string:
 854                  */
 855                 if (!hex[0])
 856                         return -1;
 857                 val = (hexval(hex[0]) &lt;&lt; 4) | hexval(hex[1]);
 858                 if (val &amp; ~0xff)
 859                         return -1;
 860                 *sha1++ = val;
 861                 hex += 2;
 862         }
 863         return 0;
 864 }
 865
 866 int main(int argc, char **argv)
 867 {
 868         /* oversized so we can read the whole buffer in */
 869         static unsigned char buf[25 * 1024 * 1024];
 870         char header[32];
 871         int header_len;
 872         unsigned char have[20], want[20];
 873         int start, len;
 874         SHA_CTX orig;
 875         unsigned i, j;
 876
 877         if (!argv[1] || get_sha1_hex(argv[1], want)) {
 878                 fprintf(stderr, "usage: sha1-munge &lt;sha1&gt; [start] &lt;file.in\n");
 879                 return 1;
 880         }
 881
 882         if (argv[2])
 883                 start = atoi(argv[2]);
 884         else
 885                 start = 0;
 886
 887         len = read(0, buf, sizeof(buf));
 888         header_len = sprintf(header, "blob %d", len) + 1;
 889         fprintf(stderr, "using header: %s\n", header);
 890
 891         /*
 892          * We keep a running sha1 so that if you are munging
 893          * near the end of the file, we do not have to re-sha1
 894          * the unchanged earlier bytes
 895          */
 896         SHA1_Init(&amp;orig);
 897         SHA1_Update(&amp;orig, header, header_len);
 898         if (start)
 899                 SHA1_Update(&amp;orig, buf, start);
 900
 901         signal(SIGALRM, progress);
 902         alarm(1);
 903
 904         for (i = start; i &lt; len; i++) {
 905                 unsigned char c;
 906                 SHA_CTX x;
 907
 908 #if 0
 909                 /*
 910                  * deletion -- this would not actually work in practice,
 911                  * I think, because we've already committed to a
 912                  * particular size in the header. Ditto for addition
 913                  * below. In those cases, you'd have to do the whole
 914                  * sha1 from scratch, or possibly keep three running
 915                  * "orig" sha1 computations going.
 916                  */
 917                 memcpy(&amp;x, &amp;orig, sizeof(x));
 918                 SHA1_Update(&amp;x, buf + i + 1, len - i - 1);
 919                 SHA1_Final(have, &amp;x);
 920                 if (!memcmp(have, want, 20))
 921                         printf("i=%d, deletion\n", i);
 922 #endif
 923
 924                 /*
 925                  * replacement -- note that this tries each of the 256
 926                  * possible bytes. If you suspect a single-bit flip,
 927                  * it would be much shorter to just try the 8
 928                  * bit-flipped variants.
 929                  */
 930                 c = buf[i];
 931                 for (j = 0; j &lt;= 0xff; j++) {
 932                         buf[i] = j;
 933
 934                         memcpy(&amp;x, &amp;orig, sizeof(x));
 935                         SHA1_Update(&amp;x, buf + i, len - i);
 936                         SHA1_Final(have, &amp;x);
 937                         if (!memcmp(have, want, 20))
 938                                 printf("i=%d, j=%02x\n", i, j);
 939                 }
 940                 buf[i] = c;
 941
 942 #if 0
 943                 /* addition */
 944                 for (j = 0; j &lt;= 0xff; j++) {
 945                         unsigned char extra = j;
 946                         memcpy(&amp;x, &amp;orig, sizeof(x));
 947                         SHA1_Update(&amp;x, &amp;extra, 1);
 948                         SHA1_Update(&amp;x, buf + i, len - i);
 949                         SHA1_Final(have, &amp;x);
 950                         if (!memcmp(have, want, 20))
 951                                 printf("i=%d, addition=%02x", i, j);
 952                 }
 953 #endif
 954
 955                 SHA1_Update(&amp;orig, buf + i, 1);
 956                 counter++;
 957         }
 958
 959         alarm(0);
 960         fprintf(stderr, "\r%d\n", counter);
 961         return 0;
 962 }</pre>
 963 </div>
 964 </div>
 965 </div>
 966 </div>
 967 </div>
 968 <div id="footer">
 969 <div id="footer-text">
 970 Last updated 2024-08-23 09:48:46 -0700
 971 </div>
 972 </div>
 973 </body>
 974 </html>