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>
 445 <div id="content">
 446 <div id="preamble">
 447 <div class="sectionbody">
 448 <div class="paragraph">
 449 <p>I was recently presented with a repository with a corrupted packfile,
 450 and was asked if the data was recoverable. This post-mortem describes
 451 the steps I took to investigate and fix the problem. I thought others
 452 might find the process interesting, and it might help somebody in the
 453 same situation.</p>
 454 </div>
 455 <div class="sidebarblock">
 456 <div class="content">
 457 <div class="paragraph">
 458 <p>Note: In this case, no good copy of the repository was available. For
 459 the much easier case where you can get the corrupted object from
 460 elsewhere, see <a href="recover-corrupted-blob-object.html">this howto</a>.</p>
 461 </div>
 462 </div>
 463 </div>
 464 <div class="paragraph">
 465 <p>I started with an fsck, which found a problem with exactly one object
 466 (I&#8217;ve used $pack and $obj below to keep the output readable, and also
 467 because I&#8217;ll refer to them later):</p>
 468 </div>
 469 <div class="listingblock">
 470 <div class="content">
 471 <pre>    $ git fsck
 472     error: $pack SHA1 checksum mismatch
 473     error: index CRC mismatch for object $obj from $pack at offset 51653873
 474     error: inflate: data stream error (incorrect data check)
 475     error: cannot unpack $obj from $pack at offset 51653873</pre>
 476 </div>
 477 </div>
 478 <div class="paragraph">
 479 <p>The pack checksum failing means a byte is munged somewhere, and it is
 480 presumably in the object mentioned (since both the index checksum and
 481 zlib were failing).</p>
 482 </div>
 483 <div class="paragraph">
 484 <p>Reading the zlib source code, I found that "incorrect data check" means
 485 that the adler-32 checksum at the end of the zlib data did not match the
 486 inflated data. So stepping the data through zlib would not help, as it
 487 did not fail until the very end, when we realize the CRC does not match.
 488 The problematic bytes could be anywhere in the object data.</p>
 489 </div>
 490 <div class="paragraph">
 491 <p>The first thing I did was pull the broken data out of the packfile. I
 492 needed to know how big the object was, which I found out with:</p>
 493 </div>
 494 <div class="listingblock">
 495 <div class="content">
 496 <pre>    $ git show-index &lt;$idx | cut -d' ' -f1 | sort -n | grep -A1 51653873
 497     51653873
 498     51664736</pre>
 499 </div>
 500 </div>
 501 <div class="paragraph">
 502 <p>Show-index gives us the list of objects and their offsets. We throw away
 503 everything but the offsets, and then sort them so that our interesting
 504 offset (which we got from the fsck output above) is followed immediately
 505 by the offset of the next object. Now we know that the object data is
 506 10863 bytes long, and we can grab it with:</p>
 507 </div>
 508 <div class="listingblock">
 509 <div class="content">
 510 <pre>  dd if=$pack of=object bs=1 skip=51653873 count=10863</pre>
 511 </div>
 512 </div>
 513 <div class="paragraph">
 514 <p>I inspected a hexdump of the data, looking for any obvious bogosity
 515 (e.g., a 4K run of zeroes would be a good sign of filesystem
 516 corruption). But everything looked pretty reasonable.</p>
 517 </div>
 518 <div class="paragraph">
 519 <p>Note that the "object" file isn&#8217;t fit for feeding straight to zlib; it
 520 has the git packed object header, which is variable-length. We want to
 521 strip that off so we can start playing with the zlib data directly. You
 522 can either work your way through it manually (the format is described in
 523 <a href="../gitformat-pack.html">gitformat-pack(5)</a>),
 524 or you can walk through it in a debugger. I did the latter, creating a
 525 valid pack like:</p>
 526 </div>
 527 <div class="listingblock">
 528 <div class="content">
 529 <pre>    # pack magic and version
 530     printf 'PACK\0\0\0\2' &gt;tmp.pack
 531     # pack has one object
 532     printf '\0\0\0\1' &gt;&gt;tmp.pack
 533     # now add our object data
 534     cat object &gt;&gt;tmp.pack
 535     # and then append the pack trailer
 536     /path/to/git.git/t/helper/test-tool sha1 -b &lt;tmp.pack &gt;trailer
 537     cat trailer &gt;&gt;tmp.pack</pre>
 538 </div>
 539 </div>
 540 <div class="paragraph">
 541 <p>and then running "git index-pack tmp.pack" in the debugger (stop at
 542 unpack_raw_entry). Doing this, I found that there were 3 bytes of header
 543 (and the header itself had a sane type and size). So I stripped those
 544 off with:</p>
 545 </div>
 546 <div class="listingblock">
 547 <div class="content">
 548 <pre>    dd if=object of=zlib bs=1 skip=3</pre>
 549 </div>
 550 </div>
 551 <div class="paragraph">
 552 <p>I ran the result through zlib&#8217;s inflate using a custom C program. And
 553 while it did report the error, I did get the right number of output
 554 bytes (i.e., it matched git&#8217;s size header that we decoded above). But
 555 feeding the result back to "git hash-object" didn&#8217;t produce the same
 556 sha1. So there were some wrong bytes, but I didn&#8217;t know which. The file
 557 happened to be C source code, so I hoped I could notice something
 558 obviously wrong with it, but I didn&#8217;t. I even got it to compile!</p>
 559 </div>
 560 <div class="paragraph">
 561 <p>I also tried comparing it to other versions of the same path in the
 562 repository, hoping that there would be some part of the diff that didn&#8217;t
 563 make sense. Unfortunately, this happened to be the only revision of this
 564 particular file in the repository, so I had nothing to compare against.</p>
 565 </div>
 566 <div class="paragraph">
 567 <p>So I took a different approach. Working under the guess that the
 568 corruption was limited to a single byte, I wrote a program to munge each
 569 byte individually, and try inflating the result. Since the object was
 570 only 10K compressed, that worked out to about 2.5M attempts, which took
 571 a few minutes.</p>
 572 </div>
 573 <div class="paragraph">
 574 <p>The program I used is here:</p>
 575 </div>
 576 <div class="listingblock">
 577 <div class="content">
 578 <pre>#include &lt;stdio.h&gt;
 579 #include &lt;unistd.h&gt;
 580 #include &lt;string.h&gt;
 581 #include &lt;signal.h&gt;
 582 #include &lt;zlib.h&gt;
 583
 584 static int try_zlib(unsigned char *buf, int len)
 585 {
 586         /* make this absurdly large so we don't have to loop */
 587         static unsigned char out[1024*1024];
 588         z_stream z;
 589         int ret;
 590
 591         memset(&amp;z, 0, sizeof(z));
 592         inflateInit(&amp;z);
 593
 594         z.next_in = buf;
 595         z.avail_in = len;
 596         z.next_out = out;
 597         z.avail_out = sizeof(out);
 598
 599         ret = inflate(&amp;z, 0);
 600         inflateEnd(&amp;z);
 601         return ret &gt;= 0;
 602 }
 603
 604 /* eye candy */
 605 static int counter = 0;
 606 static void progress(int sig)
 607 {
 608         fprintf(stderr, "\r%d", counter);
 609         alarm(1);
 610 }
 611
 612 int main(void)
 613 {
 614         /* oversized so we can read the whole buffer in */
 615         unsigned char buf[1024*1024];
 616         int len;
 617         unsigned i, j;
 618
 619         signal(SIGALRM, progress);
 620         alarm(1);
 621
 622         len = read(0, buf, sizeof(buf));
 623         for (i = 0; i &lt; len; i++) {
 624                 unsigned char c = buf[i];
 625                 for (j = 0; j &lt;= 0xff; j++) {
 626                         buf[i] = j;
 627
 628                         counter++;
 629                         if (try_zlib(buf, len))
 630                                 printf("i=%d, j=%x\n", i, j);
 631                 }
 632                 buf[i] = c;
 633         }
 634
 635         alarm(0);
 636         fprintf(stderr, "\n");
 637         return 0;
 638 }</pre>
 639 </div>
 640 </div>
 641 <div class="paragraph">
 642 <p>I compiled and ran with:</p>
 643 </div>
 644 <div class="listingblock">
 645 <div class="content">
 646 <pre>  gcc -Wall -Werror -O3 munge.c -o munge -lz
 647   ./munge &lt;zlib</pre>
 648 </div>
 649 </div>
 650 <div class="paragraph">
 651 <p>There were a few false positives early on (if you write "no data" in the
 652 zlib header, zlib thinks it&#8217;s just fine :) ). But I got a hit about
 653 halfway through:</p>
 654 </div>
 655 <div class="listingblock">
 656 <div class="content">
 657 <pre>  i=5642, j=c7</pre>
 658 </div>
 659 </div>
 660 <div class="paragraph">
 661 <p>I let it run to completion, and got a few more hits at the end (where it
 662 was munging the CRC to match our broken data). So there was a good
 663 chance this middle hit was the source of the problem.</p>
 664 </div>
 665 <div class="paragraph">
 666 <p>I confirmed by tweaking the byte in a hex editor, zlib inflating the
 667 result (no errors!), and then piping the output into "git hash-object",
 668 which reported the sha1 of the broken object. Success!</p>
 669 </div>
 670 <div class="paragraph">
 671 <p>I fixed the packfile itself with:</p>
 672 </div>
 673 <div class="listingblock">
 674 <div class="content">
 675 <pre>  chmod +w $pack
 676   printf '\xc7' | dd of=$pack bs=1 seek=51659518 conv=notrunc
 677   chmod -w $pack</pre>
 678 </div>
 679 </div>
 680 <div class="paragraph">
 681 <p>The \xc7 comes from the replacement byte our "munge" program found.
 682 The offset 51659518 is derived by taking the original object offset
 683 (51653873), adding the replacement offset found by "munge" (5642), and
 684 then adding back in the 3 bytes of git header we stripped.</p>
 685 </div>
 686 <div class="paragraph">
 687 <p>After that, "git fsck" ran clean.</p>
 688 </div>
 689 <div class="paragraph">
 690 <p>As for the corruption itself, I was lucky that it was indeed a single
 691 byte. In fact, it turned out to be a single bit. The byte 0xc7 was
 692 corrupted to 0xc5. So presumably it was caused by faulty hardware, or a
 693 cosmic ray.</p>
 694 </div>
 695 <div class="paragraph">
 696 <p>And the aborted attempt to look at the inflated output to see what was
 697 wrong? I could have looked forever and never found it. Here&#8217;s the diff
 698 between what the corrupted data inflates to, versus the real data:</p>
 699 </div>
 700 <div class="listingblock">
 701 <div class="content">
 702 <pre>  -       cp = strtok (arg, "+");
 703   +       cp = strtok (arg, ".");</pre>
 704 </div>
 705 </div>
 706 <div class="paragraph">
 707 <p>It tweaked one byte and still ended up as valid, readable C that just
 708 happened to do something totally different! One takeaway is that on a
 709 less unlucky day, looking at the zlib output might have actually been
 710 helpful, as most random changes would actually break the C code.</p>
 711 </div>
 712 <div class="paragraph">
 713 <p>But more importantly, git&#8217;s hashing and checksumming noticed a problem
 714 that easily could have gone undetected in another system. The result
 715 still compiled, but would have caused an interesting bug (that would
 716 have been blamed on some random commit).</p>
 717 </div>
 718 </div>
 719 </div>
 720 <div class="sect1">
 721 <h2 id="_the_adventure_continues">The adventure continues&#8230;&#8203;</h2>
 722 <div class="sectionbody">
 723 <div class="paragraph">
 724 <p>I ended up doing this again! Same entity, new hardware. The assumption
 725 at this point is that the old disk corrupted the packfile, and then the
 726 corruption was migrated to the new hardware (because it was done by
 727 rsync or similar, and no fsck was done at the time of migration).</p>
 728 </div>
 729 <div class="paragraph">
 730 <p>This time, the affected blob was over 20 megabytes, which was far too
 731 large to do a brute-force on. I followed the instructions above to
 732 create the <code>zlib</code> file. I then used the <code>inflate</code> program below to pull
 733 the corrupted data from that. Examining that output gave me a hint about
 734 where in the file the corruption was. But now I was working with the
 735 file itself, not the zlib contents. So knowing the sha1 of the object
 736 and the approximate area of the corruption, I used the <code>sha1-munge</code>
 737 program below to brute-force the correct byte.</p>
 738 </div>
 739 <div class="paragraph">
 740 <p>Here&#8217;s the inflate program (it&#8217;s essentially <code>gunzip</code> but without the
 741 .<code>gz</code> header processing):</p>
 742 </div>
 743 <div class="listingblock">
 744 <div class="content">
 745 <pre>#include &lt;stdio.h&gt;
 746 #include &lt;string.h&gt;
 747 #include &lt;zlib.h&gt;
 748 #include &lt;stdlib.h&gt;
 749
 750 int main(int argc, char **argv)
 751 {
 752         /*
 753          * oversized so we can read the whole buffer in;
 754          * this could actually be switched to streaming
 755          * to avoid any memory limitations
 756          */
 757         static unsigned char buf[25 * 1024 * 1024];
 758         static unsigned char out[25 * 1024 * 1024];
 759         int len;
 760         z_stream z;
 761         int ret;
 762
 763         len = read(0, buf, sizeof(buf));
 764         memset(&amp;z, 0, sizeof(z));
 765         inflateInit(&amp;z);
 766
 767         z.next_in = buf;
 768         z.avail_in = len;
 769         z.next_out = out;
 770         z.avail_out = sizeof(out);
 771
 772         ret = inflate(&amp;z, 0);
 773         if (ret != Z_OK &amp;&amp; ret != Z_STREAM_END)
 774                 fprintf(stderr, "initial inflate failed (%d)\n", ret);
 775
 776         fprintf(stderr, "outputting %lu bytes", z.total_out);
 777         fwrite(out, 1, z.total_out, stdout);
 778         return 0;
 779 }</pre>
 780 </div>
 781 </div>
 782 <div class="paragraph">
 783 <p>And here is the <code>sha1-munge</code> program:</p>
 784 </div>
 785 <div class="listingblock">
 786 <div class="content">
 787 <pre>#include &lt;stdio.h&gt;
 788 #include &lt;unistd.h&gt;
 789 #include &lt;string.h&gt;
 790 #include &lt;signal.h&gt;
 791 #include &lt;openssl/sha.h&gt;
 792 #include &lt;stdlib.h&gt;
 793
 794 /* eye candy */
 795 static int counter = 0;
 796 static void progress(int sig)
 797 {
 798         fprintf(stderr, "\r%d", counter);
 799         alarm(1);
 800 }
 801
 802 static const signed char hexval_table[256] = {
 803          -1, -1, -1, -1, -1, -1, -1, -1,                /* 00-07 */
 804          -1, -1, -1, -1, -1, -1, -1, -1,                /* 08-0f */
 805          -1, -1, -1, -1, -1, -1, -1, -1,                /* 10-17 */
 806          -1, -1, -1, -1, -1, -1, -1, -1,                /* 18-1f */
 807          -1, -1, -1, -1, -1, -1, -1, -1,                /* 20-27 */
 808          -1, -1, -1, -1, -1, -1, -1, -1,                /* 28-2f */
 809           0,  1,  2,  3,  4,  5,  6,  7,                /* 30-37 */
 810           8,  9, -1, -1, -1, -1, -1, -1,                /* 38-3f */
 811          -1, 10, 11, 12, 13, 14, 15, -1,                /* 40-47 */
 812          -1, -1, -1, -1, -1, -1, -1, -1,                /* 48-4f */
 813          -1, -1, -1, -1, -1, -1, -1, -1,                /* 50-57 */
 814          -1, -1, -1, -1, -1, -1, -1, -1,                /* 58-5f */
 815          -1, 10, 11, 12, 13, 14, 15, -1,                /* 60-67 */
 816          -1, -1, -1, -1, -1, -1, -1, -1,                /* 68-67 */
 817          -1, -1, -1, -1, -1, -1, -1, -1,                /* 70-77 */
 818          -1, -1, -1, -1, -1, -1, -1, -1,                /* 78-7f */
 819          -1, -1, -1, -1, -1, -1, -1, -1,                /* 80-87 */
 820          -1, -1, -1, -1, -1, -1, -1, -1,                /* 88-8f */
 821          -1, -1, -1, -1, -1, -1, -1, -1,                /* 90-97 */
 822          -1, -1, -1, -1, -1, -1, -1, -1,                /* 98-9f */
 823          -1, -1, -1, -1, -1, -1, -1, -1,                /* a0-a7 */
 824          -1, -1, -1, -1, -1, -1, -1, -1,                /* a8-af */
 825          -1, -1, -1, -1, -1, -1, -1, -1,                /* b0-b7 */
 826          -1, -1, -1, -1, -1, -1, -1, -1,                /* b8-bf */
 827          -1, -1, -1, -1, -1, -1, -1, -1,                /* c0-c7 */
 828          -1, -1, -1, -1, -1, -1, -1, -1,                /* c8-cf */
 829          -1, -1, -1, -1, -1, -1, -1, -1,                /* d0-d7 */
 830          -1, -1, -1, -1, -1, -1, -1, -1,                /* d8-df */
 831          -1, -1, -1, -1, -1, -1, -1, -1,                /* e0-e7 */
 832          -1, -1, -1, -1, -1, -1, -1, -1,                /* e8-ef */
 833          -1, -1, -1, -1, -1, -1, -1, -1,                /* f0-f7 */
 834          -1, -1, -1, -1, -1, -1, -1, -1,                /* f8-ff */
 835 };
 836
 837 static inline unsigned int hexval(unsigned char c)
 838 {
 839 return hexval_table[c];
 840 }
 841
 842 static int get_sha1_hex(const char *hex, unsigned char *sha1)
 843 {
 844         int i;
 845         for (i = 0; i &lt; 20; i++) {
 846                 unsigned int val;
 847                 /*
 848                  * hex[1]=='\0' is caught when val is checked below,
 849                  * but if hex[0] is NUL we have to avoid reading
 850                  * past the end of the string:
 851                  */
 852                 if (!hex[0])
 853                         return -1;
 854                 val = (hexval(hex[0]) &lt;&lt; 4) | hexval(hex[1]);
 855                 if (val &amp; ~0xff)
 856                         return -1;
 857                 *sha1++ = val;
 858                 hex += 2;
 859         }
 860         return 0;
 861 }
 862
 863 int main(int argc, char **argv)
 864 {
 865         /* oversized so we can read the whole buffer in */
 866         static unsigned char buf[25 * 1024 * 1024];
 867         char header[32];
 868         int header_len;
 869         unsigned char have[20], want[20];
 870         int start, len;
 871         SHA_CTX orig;
 872         unsigned i, j;
 873
 874         if (!argv[1] || get_sha1_hex(argv[1], want)) {
 875                 fprintf(stderr, "usage: sha1-munge &lt;sha1&gt; [start] &lt;file.in\n");
 876                 return 1;
 877         }
 878
 879         if (argv[2])
 880                 start = atoi(argv[2]);
 881         else
 882                 start = 0;
 883
 884         len = read(0, buf, sizeof(buf));
 885         header_len = sprintf(header, "blob %d", len) + 1;
 886         fprintf(stderr, "using header: %s\n", header);
 887
 888         /*
 889          * We keep a running sha1 so that if you are munging
 890          * near the end of the file, we do not have to re-sha1
 891          * the unchanged earlier bytes
 892          */
 893         SHA1_Init(&amp;orig);
 894         SHA1_Update(&amp;orig, header, header_len);
 895         if (start)
 896                 SHA1_Update(&amp;orig, buf, start);
 897
 898         signal(SIGALRM, progress);
 899         alarm(1);
 900
 901         for (i = start; i &lt; len; i++) {
 902                 unsigned char c;
 903                 SHA_CTX x;
 904
 905 #if 0
 906                 /*
 907                  * deletion -- this would not actually work in practice,
 908                  * I think, because we've already committed to a
 909                  * particular size in the header. Ditto for addition
 910                  * below. In those cases, you'd have to do the whole
 911                  * sha1 from scratch, or possibly keep three running
 912                  * "orig" sha1 computations going.
 913                  */
 914                 memcpy(&amp;x, &amp;orig, sizeof(x));
 915                 SHA1_Update(&amp;x, buf + i + 1, len - i - 1);
 916                 SHA1_Final(have, &amp;x);
 917                 if (!memcmp(have, want, 20))
 918                         printf("i=%d, deletion\n", i);
 919 #endif
 920
 921                 /*
 922                  * replacement -- note that this tries each of the 256
 923                  * possible bytes. If you suspect a single-bit flip,
 924                  * it would be much shorter to just try the 8
 925                  * bit-flipped variants.
 926                  */
 927                 c = buf[i];
 928                 for (j = 0; j &lt;= 0xff; j++) {
 929                         buf[i] = j;
 930
 931                         memcpy(&amp;x, &amp;orig, sizeof(x));
 932                         SHA1_Update(&amp;x, buf + i, len - i);
 933                         SHA1_Final(have, &amp;x);
 934                         if (!memcmp(have, want, 20))
 935                                 printf("i=%d, j=%02x\n", i, j);
 936                 }
 937                 buf[i] = c;
 938
 939 #if 0
 940                 /* addition */
 941                 for (j = 0; j &lt;= 0xff; j++) {
 942                         unsigned char extra = j;
 943                         memcpy(&amp;x, &amp;orig, sizeof(x));
 944                         SHA1_Update(&amp;x, &amp;extra, 1);
 945                         SHA1_Update(&amp;x, buf + i, len - i);
 946                         SHA1_Final(have, &amp;x);
 947                         if (!memcmp(have, want, 20))
 948                                 printf("i=%d, addition=%02x", i, j);
 949                 }
 950 #endif
 951
 952                 SHA1_Update(&amp;orig, buf + i, 1);
 953                 counter++;
 954         }
 955
 956         alarm(0);
 957         fprintf(stderr, "\r%d\n", counter);
 958         return 0;
 959 }</pre>
 960 </div>
 961 </div>
 962 </div>
 963 </div>
 964 </div>
 965 <div id="footer">
 966 <div id="footer-text">
 967 Last updated 2025-01-10 09:40:20 -0800
 968 </div>
 969 </div>
 970 </body>
 971 </html>