| 0 | 1 <html> | 
|  | 2 <head> | 
|  | 3 <title>MayaChemTools:Code:SplitTextFiles.pl</title> | 
|  | 4 <meta http-equiv="content-type" content="text/html;charset=utf-8"> | 
|  | 5 <link rel="stylesheet" type="text/css" href="../../../css/MayaChemToolsCode.css"> | 
|  | 6 </head> | 
|  | 7 <body leftmargin="20" rightmargin="20" topmargin="10" bottommargin="10"> | 
|  | 8 <br/> | 
|  | 9 <center> | 
|  | 10 <a href="http://www.mayachemtools.org" title="MayaChemTools Home"><img src="../../../images/MayaChemToolsLogo.gif" border="0" alt="MayaChemTools"></a> | 
|  | 11 </center> | 
|  | 12 <br/> | 
|  | 13 <pre> | 
|  | 14    1 #!/usr/bin/perl -w | 
|  | 15    2 <span class="c">#</span> | 
|  | 16    3 <span class="c"># $RCSfile: SplitTextFiles.pl,v $</span> | 
|  | 17    4 <span class="c"># $Date: 2015/02/28 20:46:21 $</span> | 
|  | 18    5 <span class="c"># $Revision: 1.33 $</span> | 
|  | 19    6 <span class="c">#</span> | 
|  | 20    7 <span class="c"># Author: Manish Sud <msud@san.rr.com></span> | 
|  | 21    8 <span class="c">#</span> | 
|  | 22    9 <span class="c"># Copyright (C) 2015 Manish Sud. All rights reserved.</span> | 
|  | 23   10 <span class="c">#</span> | 
|  | 24   11 <span class="c"># This file is part of MayaChemTools.</span> | 
|  | 25   12 <span class="c">#</span> | 
|  | 26   13 <span class="c"># MayaChemTools is free software; you can redistribute it and/or modify it under</span> | 
|  | 27   14 <span class="c"># the terms of the GNU Lesser General Public License as published by the Free</span> | 
|  | 28   15 <span class="c"># Software Foundation; either version 3 of the License, or (at your option) any</span> | 
|  | 29   16 <span class="c"># later version.</span> | 
|  | 30   17 <span class="c">#</span> | 
|  | 31   18 <span class="c"># MayaChemTools is distributed in the hope that it will be useful, but without</span> | 
|  | 32   19 <span class="c"># any warranty; without even the implied warranty of merchantability of fitness</span> | 
|  | 33   20 <span class="c"># for a particular purpose.  See the GNU Lesser General Public License for more</span> | 
|  | 34   21 <span class="c"># details.</span> | 
|  | 35   22 <span class="c">#</span> | 
|  | 36   23 <span class="c"># You should have received a copy of the GNU Lesser General Public License</span> | 
|  | 37   24 <span class="c"># along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or</span> | 
|  | 38   25 <span class="c"># write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,</span> | 
|  | 39   26 <span class="c"># Boston, MA, 02111-1307, USA.</span> | 
|  | 40   27 <span class="c">#</span> | 
|  | 41   28 | 
|  | 42   29 <span class="k">use</span> <span class="w">strict</span><span class="sc">;</span> | 
|  | 43   30 <span class="k">use</span> <span class="w">FindBin</span><span class="sc">;</span> <span class="k">use</span> <span class="w">lib</span> <span class="q">"$FindBin::Bin/../lib"</span><span class="sc">;</span> | 
|  | 44   31 <span class="k">use</span> <span class="w">Getopt::Long</span><span class="sc">;</span> | 
|  | 45   32 <span class="k">use</span> <span class="w">File::Basename</span><span class="sc">;</span> | 
|  | 46   33 <span class="k">use</span> <span class="w">Text::ParseWords</span><span class="sc">;</span> | 
|  | 47   34 <span class="k">use</span> <span class="w">Benchmark</span><span class="sc">;</span> | 
|  | 48   35 <span class="k">use</span> <span class="w">FileUtil</span><span class="sc">;</span> | 
|  | 49   36 <span class="k">use</span> <span class="w">TextUtil</span><span class="sc">;</span> | 
|  | 50   37 | 
|  | 51   38 <span class="k">my</span><span class="s">(</span><span class="i">$ScriptName</span><span class="cm">,</span> <span class="i">%Options</span><span class="cm">,</span> <span class="i">$StartTime</span><span class="cm">,</span> <span class="i">$EndTime</span><span class="cm">,</span> <span class="i">$TotalTime</span><span class="s">)</span><span class="sc">;</span> | 
|  | 52   39 | 
|  | 53   40 <span class="c"># Autoflush STDOUT</span> | 
|  | 54   41 <span class="i">$|</span> = <span class="n">1</span><span class="sc">;</span> | 
|  | 55   42 | 
|  | 56   43 <span class="c"># Starting message...</span> | 
|  | 57   44 <span class="i">$ScriptName</span> = <span class="w">basename</span> <span class="i">$0</span><span class="sc">;</span> | 
|  | 58   45 <span class="k">print</span> <span class="q">"\n$ScriptName:Starting...\n\n"</span><span class="sc">;</span> | 
|  | 59   46 <span class="i">$StartTime</span> = <span class="w">new</span> <span class="w">Benchmark</span><span class="sc">;</span> | 
|  | 60   47 | 
|  | 61   48 <span class="c"># Get the options and setup script...</span> | 
|  | 62   49 <span class="i">SetupScriptUsage</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 63   50 <span class="k">if</span> <span class="s">(</span><span class="i">$Options</span>{<span class="w">help</span>} || <span class="i">@ARGV</span> < <span class="n">1</span><span class="s">)</span> <span class="s">{</span> | 
|  | 64   51   <span class="k">die</span> <span class="i">GetUsageFromPod</span><span class="s">(</span><span class="q">"$FindBin::Bin/$ScriptName"</span><span class="s">)</span><span class="sc">;</span> | 
|  | 65   52 <span class="s">}</span> | 
|  | 66   53 | 
|  | 67   54 <span class="k">my</span><span class="s">(</span><span class="i">@TextFilesList</span><span class="s">)</span><span class="sc">;</span> | 
|  | 68   55 <span class="i">@TextFilesList</span> = <span class="i">ExpandFileNames</span><span class="s">(</span>\<span class="i">@ARGV</span><span class="cm">,</span> <span class="q">"csv tsv"</span><span class="s">)</span><span class="sc">;</span> | 
|  | 69   56 | 
|  | 70   57 <span class="c"># Process options...</span> | 
|  | 71   58 <span class="k">print</span> <span class="q">"Processing options...\n"</span><span class="sc">;</span> | 
|  | 72   59 <span class="k">my</span><span class="s">(</span><span class="i">%OptionsInfo</span><span class="s">)</span><span class="sc">;</span> | 
|  | 73   60 <span class="i">ProcessOptions</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 74   61 | 
|  | 75   62 <span class="k">print</span> <span class="q">"Checking input text file(s)...\n"</span><span class="sc">;</span> | 
|  | 76   63 <span class="k">my</span><span class="s">(</span><span class="i">%TextFilesInfo</span><span class="s">)</span><span class="sc">;</span> | 
|  | 77   64 <span class="i">RetrieveTextFilesInfo</span><span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 78   65 | 
|  | 79   66 <span class="c"># Generate output files...</span> | 
|  | 80   67 <span class="k">my</span><span class="s">(</span><span class="i">$FileIndex</span><span class="s">)</span><span class="sc">;</span> | 
|  | 81   68 <span class="k">if</span> <span class="s">(</span><span class="i">@TextFilesList</span> > <span class="n">1</span><span class="s">)</span> <span class="s">{</span> | 
|  | 82   69   <span class="k">print</span> <span class="q">"\nProcessing text files...\n"</span><span class="sc">;</span> | 
|  | 83   70 <span class="s">}</span> | 
|  | 84   71 <span class="k">for</span> <span class="i">$FileIndex</span> <span class="s">(</span><span class="n">0</span> .. <span class="i">$#TextFilesList</span><span class="s">)</span> <span class="s">{</span> | 
|  | 85   72   <span class="k">if</span> <span class="s">(</span><span class="i">$TextFilesInfo</span>{<span class="w">FileOkay</span>}[<span class="i">$FileIndex</span>]<span class="s">)</span> <span class="s">{</span> | 
|  | 86   73     <span class="k">print</span> <span class="q">"\nProcessing file $TextFilesList[$FileIndex]...\n"</span><span class="sc">;</span> | 
|  | 87   74     <span class="i">SplitTextFile</span><span class="s">(</span><span class="i">$FileIndex</span><span class="s">)</span><span class="sc">;</span> | 
|  | 88   75   <span class="s">}</span> | 
|  | 89   76 <span class="s">}</span> | 
|  | 90   77 | 
|  | 91   78 <span class="k">print</span> <span class="q">"\n$ScriptName:Done...\n\n"</span><span class="sc">;</span> | 
|  | 92   79 | 
|  | 93   80 <span class="i">$EndTime</span> = <span class="w">new</span> <span class="w">Benchmark</span><span class="sc">;</span> | 
|  | 94   81 <span class="i">$TotalTime</span> = <span class="w">timediff</span> <span class="s">(</span><span class="i">$EndTime</span><span class="cm">,</span> <span class="i">$StartTime</span><span class="s">)</span><span class="sc">;</span> | 
|  | 95   82 <span class="k">print</span> <span class="q">"Total time: "</span><span class="cm">,</span> <span class="i">timestr</span><span class="s">(</span><span class="i">$TotalTime</span><span class="s">)</span><span class="cm">,</span> <span class="q">"\n"</span><span class="sc">;</span> | 
|  | 96   83 | 
|  | 97   84 <span class="c">###############################################################################</span> | 
|  | 98   85 | 
|  | 99   86 <span class="c"># Split a Text file...</span> | 
|  | 100   87 <span class="c">#</span> | 
|  | 101 <a name="SplitTextFile-"></a>  88 <span class="k">sub </span><span class="m">SplitTextFile</span> <span class="s">{</span> | 
|  | 102   89   <span class="k">my</span><span class="s">(</span><span class="i">$FileIndex</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> | 
|  | 103   90   <span class="k">my</span><span class="s">(</span><span class="i">$TextFile</span><span class="cm">,</span> <span class="i">$LineCount</span><span class="cm">,</span> <span class="i">$MaxLinesPerFile</span><span class="cm">,</span> <span class="i">$MaxNumOfFiles</span><span class="s">)</span><span class="sc">;</span> | 
|  | 104   91 | 
|  | 105   92   <span class="i">$TextFile</span> = <span class="i">$TextFilesList</span>[<span class="i">$FileIndex</span>]<span class="sc">;</span> | 
|  | 106   93 | 
|  | 107   94   <span class="k">if</span> <span class="s">(</span>!<span class="k">open</span> <span class="w">TEXTFILE</span><span class="cm">,</span> <span class="q">"$TextFile"</span><span class="s">)</span> <span class="s">{</span> | 
|  | 108   95     <span class="k">warn</span> <span class="q">"Warning: Ignoring file $TextFile: Couldn't open it: $! \n"</span><span class="sc">;</span> | 
|  | 109   96     <span class="k">return</span><span class="sc">;</span> | 
|  | 110   97   <span class="s">}</span> | 
|  | 111   98 | 
|  | 112   99   <span class="i">$MaxNumOfFiles</span> = <span class="i">$OptionsInfo</span>{<span class="w">NumOfFiles</span>}<span class="sc">;</span> | 
|  | 113  100 | 
|  | 114  101   <span class="c"># Count number of lines to figure out maximum number of lines per file...</span> | 
|  | 115  102   <span class="i">$LineCount</span> = <span class="n">0</span><span class="sc">;</span> | 
|  | 116  103   <span class="k">while</span> <span class="s">(</span><span class="q"><TEXTFILE></span><span class="s">)</span> <span class="s">{</span> | 
|  | 117  104       <span class="i">$LineCount</span>++<span class="sc">;</span> | 
|  | 118  105   <span class="s">}</span> | 
|  | 119  106   <span class="k">close</span> <span class="w">TEXTFILE</span><span class="sc">;</span> | 
|  | 120  107 | 
|  | 121  108   <span class="k">if</span> <span class="s">(</span><span class="i">$LineCount</span> < <span class="i">$MaxNumOfFiles</span><span class="s">)</span> <span class="s">{</span> | 
|  | 122  109     <span class="k">warn</span> <span class="q">"Warning: Ignoring file $TextFile: Total number of lines, $LineCount, is smaller than\nnumber of new files, $MaxNumOfFiles\n"</span><span class="sc">;</span> | 
|  | 123  110     <span class="k">return</span><span class="sc">;</span> | 
|  | 124  111   <span class="s">}</span> | 
|  | 125  112 | 
|  | 126  113   <span class="i">$MaxLinesPerFile</span> = <span class="k">int</span> <span class="i">$LineCount</span> / <span class="i">$MaxNumOfFiles</span><span class="sc">;</span> | 
|  | 127  114 | 
|  | 128  115   <span class="i">GenerateTextFiles</span><span class="s">(</span><span class="i">$FileIndex</span><span class="cm">,</span> <span class="i">$MaxNumOfFiles</span><span class="cm">,</span> <span class="i">$MaxLinesPerFile</span><span class="s">)</span><span class="sc">;</span> | 
|  | 129  116 <span class="s">}</span> | 
|  | 130  117 | 
|  | 131  118 <span class="c"># Generate new Text files...</span> | 
|  | 132  119 <span class="c">#</span> | 
|  | 133 <a name="GenerateTextFiles-"></a> 120 <span class="k">sub </span><span class="m">GenerateTextFiles</span> <span class="s">{</span> | 
|  | 134  121   <span class="k">my</span><span class="s">(</span><span class="i">$FileIndex</span><span class="cm">,</span> <span class="i">$NumOfFiles</span><span class="cm">,</span> <span class="i">$NumOfLinesPerFile</span><span class="s">)</span> = <span class="i">@_</span><span class="sc">;</span> | 
|  | 135  122   <span class="k">my</span><span class="s">(</span><span class="i">$TextFile</span><span class="cm">,</span> <span class="i">$LineCount</span><span class="cm">,</span> <span class="i">$NewFileIndex</span><span class="cm">,</span> <span class="i">$NewFileName</span><span class="cm">,</span> <span class="i">$MaxLinesCount</span><span class="cm">,</span> <span class="i">$InDelim</span><span class="cm">,</span> <span class="i">$OutDelim</span><span class="cm">,</span> <span class="i">$OutQuote</span><span class="cm">,</span> <span class="i">$ColLabelsLine</span><span class="cm">,</span> <span class="i">$Line</span><span class="cm">,</span> <span class="i">@ColLabels</span><span class="cm">,</span> <span class="i">@Words</span><span class="cm">,</span> <span class="i">@NewTextFilesList</span><span class="s">)</span><span class="sc">;</span> | 
|  | 136  123 | 
|  | 137  124   <span class="c"># Setup new file names list...</span> | 
|  | 138  125   <span class="i">@NewTextFilesList</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 139  126   <span class="k">for</span> <span class="i">$NewFileIndex</span> <span class="s">(</span><span class="n">1</span> .. <span class="i">$NumOfFiles</span><span class="s">)</span> <span class="s">{</span> | 
|  | 140  127     <span class="i">$NewFileName</span> = <span class="i">$TextFilesInfo</span>{<span class="w">OutFileRoot</span>}[<span class="i">$FileIndex</span>] . <span class="q">"Part${NewFileIndex}."</span> . <span class="i">$TextFilesInfo</span>{<span class="w">OutFileExt</span>}[<span class="i">$FileIndex</span>]<span class="sc">;</span> | 
|  | 141  128     <span class="k">if</span> <span class="s">(</span>!<span class="i">$OptionsInfo</span>{<span class="w">OverwriteFiles</span>}<span class="s">)</span> <span class="s">{</span> | 
|  | 142  129       <span class="k">if</span> <span class="s">(</span><span class="k">-e</span> <span class="i">$NewFileName</span><span class="s">)</span> <span class="s">{</span> | 
|  | 143  130         <span class="k">warn</span> <span class="q">"Warning: Ignoring file $TextFile: New Text file, $NewFileName, already exists\n"</span><span class="sc">;</span> | 
|  | 144  131         <span class="k">return</span><span class="sc">;</span> | 
|  | 145  132       <span class="s">}</span> | 
|  | 146  133     <span class="s">}</span> | 
|  | 147  134     <span class="k">push</span> <span class="i">@NewTextFilesList</span><span class="cm">,</span> <span class="i">$NewFileName</span><span class="sc">;</span> | 
|  | 148  135   <span class="s">}</span> | 
|  | 149  136 | 
|  | 150  137   <span class="i">$TextFile</span> = <span class="i">$TextFilesList</span>[<span class="i">$FileIndex</span>]<span class="sc">;</span> | 
|  | 151  138 | 
|  | 152  139   <span class="k">if</span> <span class="s">(</span>!<span class="k">open</span> <span class="w">TEXTFILE</span><span class="cm">,</span> <span class="q">"$TextFile"</span><span class="s">)</span> <span class="s">{</span> | 
|  | 153  140     <span class="k">warn</span> <span class="q">"Warning: Ignoring file $TextFile: Couldn't open it: $! \n"</span><span class="sc">;</span> | 
|  | 154  141     <span class="k">return</span><span class="sc">;</span> | 
|  | 155  142   <span class="s">}</span> | 
|  | 156  143 | 
|  | 157  144   <span class="i">$InDelim</span> = <span class="i">$TextFilesInfo</span>{<span class="w">InDelim</span>}[<span class="i">$FileIndex</span>]<span class="sc">;</span> | 
|  | 158  145 | 
|  | 159  146   <span class="i">$OutDelim</span> = <span class="i">$OptionsInfo</span>{<span class="w">OutDelim</span>}<span class="sc">;</span> | 
|  | 160  147   <span class="i">$OutQuote</span> = <span class="i">$OptionsInfo</span>{<span class="w">OutQuote</span>}<span class="sc">;</span> | 
|  | 161  148 | 
|  | 162  149   <span class="i">$MaxLinesCount</span> = <span class="i">$NumOfLinesPerFile</span><span class="sc">;</span> | 
|  | 163  150   <span class="i">$LineCount</span> = <span class="n">0</span><span class="sc">;</span> | 
|  | 164  151   <span class="i">$NewFileIndex</span> = <span class="n">1</span><span class="sc">;</span> | 
|  | 165  152 | 
|  | 166  153   <span class="k">open</span> <span class="w">NEWTEXTFILE</span><span class="cm">,</span> <span class="q">">$NewTextFilesList[$NewFileIndex - 1]"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Error: Can't open $NewTextFilesList[$NewFileIndex -1]: $! \n"</span><span class="sc">;</span> | 
|  | 167  154   <span class="k">print</span> <span class="q">"Generating $NewTextFilesList[$NewFileIndex - 1] file...\n"</span><span class="sc">;</span> | 
|  | 168  155 | 
|  | 169  156   <span class="k">if</span> <span class="s">(</span><span class="i">$OptionsInfo</span>{<span class="w">Label</span>}<span class="s">)</span> <span class="s">{</span> | 
|  | 170  157     <span class="k">if</span> <span class="s">(</span><span class="i">$OptionsInfo</span>{<span class="w">Fast</span>}<span class="s">)</span> <span class="s">{</span> | 
|  | 171  158       <span class="i">$ColLabelsLine</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*TEXTFILE</span><span class="s">)</span><span class="sc">;</span> | 
|  | 172  159     <span class="s">}</span> | 
|  | 173  160     <span class="k">else</span> <span class="s">{</span> | 
|  | 174  161       <span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*TEXTFILE</span><span class="s">)</span><span class="sc">;</span> | 
|  | 175  162       <span class="i">@ColLabels</span> = <span class="i">quotewords</span><span class="s">(</span><span class="i">$InDelim</span><span class="cm">,</span> <span class="n">0</span><span class="cm">,</span> <span class="i">$Line</span><span class="s">)</span><span class="sc">;</span> | 
|  | 176  163       <span class="i">$ColLabelsLine</span> = <span class="i">JoinWords</span><span class="s">(</span>\<span class="i">@ColLabels</span><span class="cm">,</span> <span class="i">$OutDelim</span><span class="cm">,</span> <span class="i">$OutQuote</span><span class="s">)</span><span class="sc">;</span> | 
|  | 177  164     <span class="s">}</span> | 
|  | 178  165     <span class="k">print</span> <span class="i">NEWTEXTFILE</span> <span class="q">"$ColLabelsLine\n"</span><span class="sc">;</span> | 
|  | 179  166   <span class="s">}</span> | 
|  | 180  167 | 
|  | 181  168   <span class="k">while</span> <span class="s">(</span><span class="i">$Line</span> = <span class="i">GetTextLine</span><span class="s">(</span>\<span class="i">*TEXTFILE</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> | 
|  | 182  169     <span class="i">$LineCount</span>++<span class="sc">;</span> | 
|  | 183  170 | 
|  | 184  171     <span class="k">if</span> <span class="s">(</span>!<span class="i">$Options</span>{<span class="w">fast</span>}<span class="s">)</span> <span class="s">{</span> | 
|  | 185  172       <span class="i">@Words</span> = <span class="i">quotewords</span><span class="s">(</span><span class="i">$InDelim</span><span class="cm">,</span> <span class="n">0</span><span class="cm">,</span> <span class="i">$Line</span><span class="s">)</span><span class="sc">;</span> | 
|  | 186  173       <span class="i">$Line</span> = <span class="i">JoinWords</span><span class="s">(</span>\<span class="i">@Words</span><span class="cm">,</span> <span class="i">$OutDelim</span><span class="cm">,</span> <span class="i">$OutQuote</span><span class="s">)</span><span class="sc">;</span> | 
|  | 187  174     <span class="s">}</span> | 
|  | 188  175     <span class="k">print</span> <span class="i">NEWTEXTFILE</span> <span class="q">"$Line\n"</span><span class="sc">;</span> | 
|  | 189  176 | 
|  | 190  177     <span class="k">if</span> <span class="s">(</span><span class="i">$NewFileIndex</span> <= <span class="i">$NumOfFiles</span><span class="s">)</span> <span class="s">{</span> | 
|  | 191  178       <span class="k">if</span> <span class="s">(</span><span class="i">$LineCount</span> >= <span class="i">$MaxLinesCount</span><span class="s">)</span> <span class="s">{</span> | 
|  | 192  179         <span class="k">if</span> <span class="s">(</span><span class="i">$NewFileIndex</span> < <span class="i">$NumOfFiles</span><span class="s">)</span> <span class="s">{</span> | 
|  | 193  180           <span class="k">close</span> <span class="w">NEWTEXTFILE</span><span class="sc">;</span> | 
|  | 194  181         <span class="s">}</span> | 
|  | 195  182         <span class="i">$NewFileIndex</span>++<span class="sc">;</span> | 
|  | 196  183         <span class="i">$MaxLinesCount</span> = <span class="i">$NumOfLinesPerFile</span> * <span class="i">$NewFileIndex</span><span class="sc">;</span> | 
|  | 197  184 | 
|  | 198  185         <span class="k">if</span> <span class="s">(</span><span class="i">$NewFileIndex</span> <= <span class="i">$NumOfFiles</span><span class="s">)</span> <span class="s">{</span> | 
|  | 199  186           <span class="k">open</span> <span class="w">NEWTEXTFILE</span><span class="cm">,</span> <span class="q">">$NewTextFilesList[$NewFileIndex - 1]"</span> <span class="k">or</span> <span class="k">die</span> <span class="q">"Error: Can't open $NewTextFilesList[$NewFileIndex -1]: $! \n"</span><span class="sc">;</span> | 
|  | 200  187           <span class="k">print</span> <span class="q">"Generating $NewTextFilesList[$NewFileIndex - 1] file...\n"</span><span class="sc">;</span> | 
|  | 201  188 | 
|  | 202  189           <span class="k">if</span> <span class="s">(</span><span class="i">$OptionsInfo</span>{<span class="w">Label</span>}<span class="s">)</span> <span class="s">{</span> | 
|  | 203  190             <span class="k">print</span> <span class="i">NEWTEXTFILE</span> <span class="q">"$ColLabelsLine\n"</span><span class="sc">;</span> | 
|  | 204  191           <span class="s">}</span> | 
|  | 205  192         <span class="s">}</span> | 
|  | 206  193       <span class="s">}</span> | 
|  | 207  194     <span class="s">}</span> | 
|  | 208  195   <span class="s">}</span> | 
|  | 209  196   <span class="k">close</span> <span class="w">NEWTEXTFILE</span><span class="sc">;</span> | 
|  | 210  197   <span class="k">close</span> <span class="w">TEXTFILE</span><span class="sc">;</span> | 
|  | 211  198 <span class="s">}</span> | 
|  | 212  199 | 
|  | 213  200 <span class="c"># Retrieve information about Text files...</span> | 
|  | 214 <a name="RetrieveTextFilesInfo-"></a> 201 <span class="k">sub </span><span class="m">RetrieveTextFilesInfo</span> <span class="s">{</span> | 
|  | 215  202   <span class="k">my</span><span class="s">(</span><span class="i">$Index</span><span class="cm">,</span> <span class="i">$TextFile</span><span class="cm">,</span> <span class="i">$InDelim</span><span class="cm">,</span> <span class="i">$FileDir</span><span class="cm">,</span> <span class="i">$FileName</span><span class="cm">,</span> <span class="i">$FileExt</span><span class="cm">,</span> <span class="i">$OutFileRoot</span><span class="cm">,</span> <span class="i">$OutFileExt</span><span class="s">)</span><span class="sc">;</span> | 
|  | 216  203 | 
|  | 217  204   <span class="i">%TextFilesInfo</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 218  205   <span class="i">@</span>{<span class="i">$TextFilesInfo</span>{<span class="w">FileOkay</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 219  206   <span class="i">@</span>{<span class="i">$TextFilesInfo</span>{<span class="w">InDelim</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 220  207   <span class="i">@</span>{<span class="i">$TextFilesInfo</span>{<span class="w">OutFileRoot</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 221  208   <span class="i">@</span>{<span class="i">$TextFilesInfo</span>{<span class="w">OutFileExt</span>}} = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 222  209 | 
|  | 223  210   <span class="j">FILELIST:</span> <span class="k">for</span> <span class="i">$Index</span> <span class="s">(</span><span class="n">0</span> .. <span class="i">$#TextFilesList</span><span class="s">)</span> <span class="s">{</span> | 
|  | 224  211     <span class="i">$TextFilesInfo</span>{<span class="w">FileOkay</span>}[<span class="i">$Index</span>] = <span class="n">0</span><span class="sc">;</span> | 
|  | 225  212     <span class="i">$TextFilesInfo</span>{<span class="w">InDelim</span>}[<span class="i">$Index</span>] = <span class="q">""</span><span class="sc">;</span> | 
|  | 226  213     <span class="i">$TextFilesInfo</span>{<span class="w">OutFileRoot</span>}[<span class="i">$Index</span>] = <span class="q">""</span><span class="sc">;</span> | 
|  | 227  214     <span class="i">$TextFilesInfo</span>{<span class="w">OutFileExt</span>}[<span class="i">$Index</span>] = <span class="q">""</span><span class="sc">;</span> | 
|  | 228  215 | 
|  | 229  216     <span class="i">$TextFile</span> = <span class="i">$TextFilesList</span>[<span class="i">$Index</span>]<span class="sc">;</span> | 
|  | 230  217     <span class="k">if</span> <span class="s">(</span>!<span class="s">(</span><span class="k">-e</span> <span class="i">$TextFile</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> | 
|  | 231  218       <span class="k">warn</span> <span class="q">"Warning: Ignoring file $TextFile: It doesn't exist\n"</span><span class="sc">;</span> | 
|  | 232  219       <span class="k">next</span> <span class="j">FILELIST</span><span class="sc">;</span> | 
|  | 233  220     <span class="s">}</span> | 
|  | 234  221     <span class="k">if</span> <span class="s">(</span>!<span class="i">CheckFileType</span><span class="s">(</span><span class="i">$TextFile</span><span class="cm">,</span> <span class="q">"csv tsv"</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> | 
|  | 235  222       <span class="k">warn</span> <span class="q">"Warning: Ignoring file $TextFile: It's not a Text file\n"</span><span class="sc">;</span> | 
|  | 236  223       <span class="k">next</span> <span class="j">FILELIST</span><span class="sc">;</span> | 
|  | 237  224     <span class="s">}</span> | 
|  | 238  225     <span class="k">if</span> <span class="s">(</span>! <span class="k">open</span> <span class="w">TEXTFILE</span><span class="cm">,</span> <span class="q">"$TextFile"</span><span class="s">)</span> <span class="s">{</span> | 
|  | 239  226       <span class="k">warn</span> <span class="q">"Warning: Ignoring file $TextFile: Couldn't open it: $! \n"</span><span class="sc">;</span> | 
|  | 240  227       <span class="k">next</span> <span class="j">FILELIST</span><span class="sc">;</span> | 
|  | 241  228     <span class="s">}</span> | 
|  | 242  229     <span class="k">close</span> <span class="w">TEXTFILE</span><span class="sc">;</span> | 
|  | 243  230 | 
|  | 244  231     <span class="s">(</span><span class="i">$FileDir</span><span class="cm">,</span> <span class="i">$FileName</span><span class="cm">,</span> <span class="i">$FileExt</span><span class="s">)</span> = <span class="i">ParseFileName</span><span class="s">(</span><span class="i">$TextFile</span><span class="s">)</span><span class="sc">;</span> | 
|  | 245  232 | 
|  | 246  233     <span class="c"># Setup input delimiter...</span> | 
|  | 247  234     <span class="i">$InDelim</span> = <span class="q">''</span><span class="sc">;</span> | 
|  | 248  235     <span class="k">if</span> <span class="s">(</span>!<span class="i">$OptionsInfo</span>{<span class="w">Fast</span>}<span class="s">)</span> <span class="s">{</span> | 
|  | 249  236       <span class="k">if</span> <span class="s">(</span><span class="i">$FileExt</span> =~ <span class="q">/^tsv$/i</span><span class="s">)</span> <span class="s">{</span> | 
|  | 250  237         <span class="i">$InDelim</span> = <span class="q">"\t"</span><span class="sc">;</span> | 
|  | 251  238       <span class="s">}</span> | 
|  | 252  239       <span class="k">else</span> <span class="s">{</span> | 
|  | 253  240         <span class="i">$InDelim</span> = <span class="q">"\,"</span><span class="sc">;</span> | 
|  | 254  241         <span class="k">if</span> <span class="s">(</span><span class="i">$OptionsInfo</span>{<span class="w">InDelim</span>} !~ <span class="q">/^(comma|semicolon)$/i</span><span class="s">)</span> <span class="s">{</span> | 
|  | 255  242           <span class="k">warn</span> <span class="q">"Warning: Ignoring file $TextFile: The value specified, $OptionsInfo{InDelim}, for option \"--indelim\" is not valid for csv files\n"</span><span class="sc">;</span> | 
|  | 256  243           <span class="k">next</span> <span class="j">FILELIST</span><span class="sc">;</span> | 
|  | 257  244         <span class="s">}</span> | 
|  | 258  245         <span class="k">if</span> <span class="s">(</span><span class="i">$OptionsInfo</span>{<span class="w">InDelim</span>} =~ <span class="q">/^semicolon$/i</span><span class="s">)</span> <span class="s">{</span> | 
|  | 259  246           <span class="i">$InDelim</span> = <span class="q">"\;"</span><span class="sc">;</span> | 
|  | 260  247         <span class="s">}</span> | 
|  | 261  248       <span class="s">}</span> | 
|  | 262  249     <span class="s">}</span> | 
|  | 263  250 | 
|  | 264  251     <span class="c"># Setup output file root...</span> | 
|  | 265  252     <span class="i">$OutFileExt</span> = <span class="i">$OptionsInfo</span>{<span class="w">Fast</span>} ? <span class="i">$FileExt</span> <span class="co">:</span> <span class="s">(</span><span class="s">(</span><span class="i">$Options</span>{<span class="w">outdelim</span>} =~ <span class="q">/^tab$/i</span> <span class="s">)</span> ? <span class="q">"tsv"</span> <span class="co">:</span> <span class="q">"csv"</span><span class="s">)</span><span class="sc">;</span> | 
|  | 266  253 | 
|  | 267  254     <span class="k">if</span> <span class="s">(</span><span class="i">$OptionsInfo</span>{<span class="w">OutFileRoot</span>} && <span class="s">(</span><span class="i">@TextFilesList</span> == <span class="n">1</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> | 
|  | 268  255       <span class="k">my</span> <span class="s">(</span><span class="i">$RootFileDir</span><span class="cm">,</span> <span class="i">$RootFileName</span><span class="cm">,</span> <span class="i">$RootFileExt</span><span class="s">)</span> = <span class="i">ParseFileName</span><span class="s">(</span><span class="i">$OptionsInfo</span>{<span class="w">OutFileRoot</span>}<span class="s">)</span><span class="sc">;</span> | 
|  | 269  256       <span class="k">if</span> <span class="s">(</span><span class="i">$RootFileName</span> && <span class="i">$RootFileExt</span><span class="s">)</span> <span class="s">{</span> | 
|  | 270  257         <span class="i">$FileName</span> = <span class="i">$RootFileName</span><span class="sc">;</span> | 
|  | 271  258       <span class="s">}</span> | 
|  | 272  259       <span class="k">else</span> <span class="s">{</span> | 
|  | 273  260         <span class="i">$FileName</span> = <span class="i">$OptionsInfo</span>{<span class="w">OutFileRoot</span>}<span class="sc">;</span> | 
|  | 274  261       <span class="s">}</span> | 
|  | 275  262       <span class="i">$OutFileRoot</span> = <span class="i">$FileName</span><span class="sc">;</span> | 
|  | 276  263     <span class="s">}</span> | 
|  | 277  264     <span class="k">else</span> <span class="s">{</span> | 
|  | 278  265       <span class="i">$OutFileRoot</span> = <span class="i">$FileName</span><span class="sc">;</span> | 
|  | 279  266     <span class="s">}</span> | 
|  | 280  267 | 
|  | 281  268     <span class="i">$TextFilesInfo</span>{<span class="w">FileOkay</span>}[<span class="i">$Index</span>] = <span class="n">1</span><span class="sc">;</span> | 
|  | 282  269     <span class="i">$TextFilesInfo</span>{<span class="w">InDelim</span>}[<span class="i">$Index</span>] = <span class="i">$InDelim</span><span class="sc">;</span> | 
|  | 283  270     <span class="i">$TextFilesInfo</span>{<span class="w">OutFileRoot</span>}[<span class="i">$Index</span>] = <span class="i">$OutFileRoot</span><span class="sc">;</span> | 
|  | 284  271     <span class="i">$TextFilesInfo</span>{<span class="w">OutFileExt</span>}[<span class="i">$Index</span>] = <span class="i">$OutFileExt</span><span class="sc">;</span> | 
|  | 285  272   <span class="s">}</span> | 
|  | 286  273 <span class="s">}</span> | 
|  | 287  274 | 
|  | 288  275 <span class="c"># Process option values...</span> | 
|  | 289 <a name="ProcessOptions-"></a> 276 <span class="k">sub </span><span class="m">ProcessOptions</span> <span class="s">{</span> | 
|  | 290  277 | 
|  | 291  278   <span class="i">%OptionsInfo</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 292  279 | 
|  | 293  280   <span class="i">$OptionsInfo</span>{<span class="w">Fast</span>} = <span class="k">defined</span> <span class="i">$Options</span>{<span class="w">fast</span>} ? <span class="i">$Options</span>{<span class="w">fast</span>} <span class="co">:</span> <span class="k">undef</span><span class="sc">;</span> | 
|  | 294  281 | 
|  | 295  282   <span class="i">$OptionsInfo</span>{<span class="w">InDelim</span>} = <span class="i">$Options</span>{<span class="w">indelim</span>}<span class="sc">;</span> | 
|  | 296  283   <span class="i">$OptionsInfo</span>{<span class="w">Label</span>} = <span class="s">(</span><span class="i">$Options</span>{<span class="w">label</span>} =~ <span class="q">/^yes$/i</span><span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span> | 
|  | 297  284 | 
|  | 298  285   <span class="i">$OptionsInfo</span>{<span class="w">NumOfFiles</span>} = <span class="i">$Options</span>{<span class="w">numfiles</span>}<span class="sc">;</span> | 
|  | 299  286 | 
|  | 300  287   <span class="i">$OptionsInfo</span>{<span class="w">OutFileRoot</span>} = <span class="i">$Options</span>{<span class="w">root</span>} ? <span class="i">$Options</span>{<span class="w">root</span>} <span class="co">:</span> <span class="k">undef</span><span class="sc">;</span> | 
|  | 301  288   <span class="i">$OptionsInfo</span>{<span class="w">OverwriteFiles</span>} = <span class="i">$Options</span>{<span class="w">overwrite</span>} ? <span class="i">$Options</span>{<span class="w">overwrite</span>} <span class="co">:</span> <span class="k">undef</span><span class="sc">;</span> | 
|  | 302  289 | 
|  | 303  290   <span class="i">$OptionsInfo</span>{<span class="w">OutDelim</span>} = <span class="s">(</span><span class="i">$Options</span>{<span class="w">outdelim</span>} =~ <span class="q">/^tab$/i</span> <span class="s">)</span> ? <span class="q">"\t"</span> <span class="co">:</span> <span class="s">(</span><span class="s">(</span><span class="i">$Options</span>{<span class="w">outdelim</span>} =~ <span class="q">/^semicolon$/i</span><span class="s">)</span> ? <span class="q">"\;"</span> <span class="co">:</span> <span class="q">"\,"</span><span class="s">)</span><span class="sc">;</span> | 
|  | 304  291   <span class="i">$OptionsInfo</span>{<span class="w">OutQuote</span>} = <span class="s">(</span><span class="i">$Options</span>{<span class="w">quote</span>} =~ <span class="q">/^yes$/i</span><span class="s">)</span> ? <span class="n">1</span> <span class="co">:</span> <span class="n">0</span><span class="sc">;</span> | 
|  | 305  292 <span class="s">}</span> | 
|  | 306  293 | 
|  | 307  294 <span class="c"># Setup script usage  and retrieve command line arguments specified using various options...</span> | 
|  | 308 <a name="SetupScriptUsage-"></a> 295 <span class="k">sub </span><span class="m">SetupScriptUsage</span> <span class="s">{</span> | 
|  | 309  296 | 
|  | 310  297   <span class="c"># Retrieve all the options...</span> | 
|  | 311  298   <span class="i">%Options</span> = <span class="s">(</span><span class="s">)</span><span class="sc">;</span> | 
|  | 312  299   <span class="i">$Options</span>{<span class="w">label</span>} = <span class="q">"yes"</span><span class="sc">;</span> | 
|  | 313  300   <span class="i">$Options</span>{<span class="w">numfiles</span>} = <span class="n">2</span><span class="sc">;</span> | 
|  | 314  301   <span class="i">$Options</span>{<span class="w">indelim</span>} = <span class="q">"comma"</span><span class="sc">;</span> | 
|  | 315  302   <span class="i">$Options</span>{<span class="w">outdelim</span>} = <span class="q">"comma"</span><span class="sc">;</span> | 
|  | 316  303   <span class="i">$Options</span>{<span class="w">quote</span>} = <span class="q">"yes"</span><span class="sc">;</span> | 
|  | 317  304   <span class="k">if</span> <span class="s">(</span>!<span class="i">GetOptions</span><span class="s">(</span>\<span class="i">%Options</span><span class="cm">,</span> <span class="q">"fast|f"</span><span class="cm">,</span> <span class="q">"help|h"</span><span class="cm">,</span> <span class="q">"indelim=s"</span><span class="cm">,</span> <span class="q">"label|l=s"</span><span class="cm">,</span> <span class="q">"numfiles|n=i"</span><span class="cm">,</span> <span class="q">"outdelim=s"</span><span class="cm">,</span> <span class="q">"overwrite|o"</span><span class="cm">,</span> <span class="q">"quote|q=s"</span><span class="cm">,</span> <span class="q">"root|r=s"</span><span class="cm">,</span> <span class="q">"workingdir|w=s"</span><span class="s">)</span><span class="s">)</span> <span class="s">{</span> | 
|  | 318  305     <span class="k">die</span> <span class="q">"\nTo get a list of valid options and their values, use \"$ScriptName -h\" or\n\"perl -S $ScriptName -h\" command and try again...\n"</span><span class="sc">;</span> | 
|  | 319  306   <span class="s">}</span> | 
|  | 320  307   <span class="k">if</span> <span class="s">(</span><span class="i">$Options</span>{<span class="w">workingdir</span>}<span class="s">)</span> <span class="s">{</span> | 
|  | 321  308     <span class="k">if</span> <span class="s">(</span>! <span class="k">-d</span> <span class="i">$Options</span>{<span class="w">workingdir</span>}<span class="s">)</span> <span class="s">{</span> | 
|  | 322  309       <span class="k">die</span> <span class="q">"Error: The value specified, $Options{workingdir},  for option \"-w --workingdir\" is not a directory name.\n"</span><span class="sc">;</span> | 
|  | 323  310     <span class="s">}</span> | 
|  | 324  311     <span class="k">chdir</span> <span class="i">$Options</span>{<span class="w">workingdir</span>} <span class="k">or</span> <span class="k">die</span> <span class="q">"Error: Couldn't chdir $Options{workingdir}: $! \n"</span><span class="sc">;</span> | 
|  | 325  312   <span class="s">}</span> | 
|  | 326  313   <span class="k">if</span> <span class="s">(</span><span class="i">$Options</span>{<span class="w">numfiles</span>} < <span class="n">2</span><span class="s">)</span> <span class="s">{</span> | 
|  | 327  314     <span class="k">die</span> <span class="q">"Error: The value specified, $Options{numfiles},  for option \"-n --numfiles\" is not valid. Allowed values: >= 2 \n"</span><span class="sc">;</span> | 
|  | 328  315   <span class="s">}</span> | 
|  | 329  316   <span class="k">if</span> <span class="s">(</span><span class="i">$Options</span>{<span class="w">indelim</span>} !~ <span class="q">/^(comma|semicolon)$/i</span><span class="s">)</span> <span class="s">{</span> | 
|  | 330  317     <span class="k">die</span> <span class="q">"Error: The value specified, $Options{indelim}, for option \"--indelim\" is not valid. Allowed values: comma or semicolon\n"</span><span class="sc">;</span> | 
|  | 331  318   <span class="s">}</span> | 
|  | 332  319   <span class="k">if</span> <span class="s">(</span><span class="i">$Options</span>{<span class="w">outdelim</span>} !~ <span class="q">/^(comma|semicolon|tab)$/i</span><span class="s">)</span> <span class="s">{</span> | 
|  | 333  320     <span class="k">die</span> <span class="q">"Error: The value specified, $Options{outdelim}, for option \"--outdelim\" is not valid. Allowed values: comma, tab, or semicolon\n"</span><span class="sc">;</span> | 
|  | 334  321   <span class="s">}</span> | 
|  | 335  322   <span class="k">if</span> <span class="s">(</span><span class="i">$Options</span>{<span class="w">quote</span>} !~ <span class="q">/^(yes|no)$/i</span><span class="s">)</span> <span class="s">{</span> | 
|  | 336  323     <span class="k">die</span> <span class="q">"Error: The value specified, $Options{quote}, for option \"-q --quote\" is not valid. Allowed values: yes or no\n"</span><span class="sc">;</span> | 
|  | 337  324   <span class="s">}</span> | 
|  | 338  325   <span class="k">if</span> <span class="s">(</span><span class="i">$Options</span>{<span class="w">label</span>} !~ <span class="q">/^(yes|no)$/i</span><span class="s">)</span> <span class="s">{</span> | 
|  | 339  326     <span class="k">die</span> <span class="q">"Error: The value specified, $Options{label}, for option \"-l --label\" is not valid. Allowed values: yes or no\n"</span><span class="sc">;</span> | 
|  | 340  327   <span class="s">}</span> | 
|  | 341  328 <span class="s">}</span> | 
|  | 342  329 | 
|  | 343 <a name="EOF-"></a></pre> | 
|  | 344 <p> </p> | 
|  | 345 <br /> | 
|  | 346 <center> | 
|  | 347 <img src="../../../images/h2o2.png"> | 
|  | 348 </center> | 
|  | 349 </body> | 
|  | 350 </html> |