Search This Blog

Loading...

2012-05-06

how-to convert csv to confluence wiki with perl

package CsvToWiki; 
my $VERSION='1.0.0' ; 
use strict ; use warnings ; use Exporter; 
my @ISA = qw(AutoLoader Exporter);
my @EXPORT = qw( RunCsvToWiki );
 
BEGIN {     
    #add the scripts dir to the INC
    $0 =~ m/^(.*)(\\|\/)(.*)\.([a-z]*)/; 
    push ( @INC , $1) ;     
    
} #eof sub
 
use Configurator ; use Logger ; use FileHandler ; 
 
 
#    anonymous hash !!!
our ( $confHolder , $confHolderOfObj , $objLogger , $MyBareName , $objConfigurator)= () ; 
our ( $objFileHandler , $RunDir ) = () ; 
our ( $FileCsvInput , $FolderOutput , $HtmlPageSize ) = () ; 
 
our ( $CsvFileSeparator  , $TokenStart , $TokenStop  , $LineStart  , $LineStop )  = () ; 
our ( $BareFileCsvInput , $FileOutput , $StrToWriteStart , $StrToWriteStop , $Pager ) = () ; 
our ( $DirCsvInput  , $DirCsvOutput , $RegexFilterForCsvToWikiSourceFiles) = () ; 
 
 
our (  $EnvironmentName  , $ProductBaseDir , $ProductVersionDir , $HostName ) = () ; 
our (  $ConfDir  ) = () ; 
our ( $FileConfig ) = () ; 
 
 
# -----------------------------------------------------------------------------
# Initialize the object with the minimum data it will need to operate 
# -----------------------------------------------------------------------------
sub Initialize {
 
    my $self = shift ; 
    
    $objLogger = new Logger (\$confHolder) ; 
    $objFileHandler = new FileHandler ( \$confHolder ) ; 
 
    my $ActionName = ref ( $self ) ; 
    my $msg = "\$ActionName is $ActionName" ; 
    $objLogger->LogDebugMsg     ( "$msg" ) ; 
    $objLogger->LogDebugMsg ( "The \$ActionName is $ActionName " ) ; 
    $EnvironmentName = $confHolder->{'EnvironmentName'} ; 
    $ProductBaseDir = $confHolder->{'ProductBaseDir'} ; 
    $ProductVersionDir = $confHolder->{'ProductVersionDir'} ; 
    $HostName= $confHolder->{'HostName'} ; 
    $ConfDir = "$ProductVersionDir/conf/$HostName/ini" ; 
    $FileConfig = "$ConfDir/$EnvironmentName" . '.' . "$ActionName" . '.' . "$HostName" . '.ini' ; 
    $objLogger->LogDebugMsg ( "\$FileConfig is $FileConfig " ) ; 
    my $objConfigurator = clone Configurator($FileConfig , $confHolder); 
    # get the hash having the vars 
    $confHolderOfObj = $objConfigurator->getConfHolder () ; 
 
 
        #get it from the conf 
        $DirCsvInput = $confHolderOfObj->{'DirCsvInput'} || "$ProductVersionDir/docs/excel" ; 
        
        #get it from the conf 
        $DirCsvOutput = $confHolderOfObj->{'DirCsvOutput'} || "$ProductVersionDir/docs/csv" ;  ; 
        $objFileHandler->MkDir ( $DirCsvOutput ) unless ( -d $DirCsvOutput ); 
        
        
        #v1.3.0 ysg --- Add
        my ($RefFilesAndDirs , $RefDirsToProcess , $RefFilesToProcess ) = 
        $objFileHandler->ReadDirRecursivelyReturnArrays ( $DirCsvOutput , '(.*?)\.html') ; 
        my @FilesAndDirs = @$RefFilesAndDirs ; 
        my @DirsToProcess = @$RefDirsToProcess ; 
        my @FilesToProcess = @$RefFilesToProcess ; 
 
        foreach my $FileHtmlOldOutput ( @FilesToProcess ) { 
            $objLogger->LogDebugMsg ( 
                                    "CsvToWiki->Initialize: unlink \$FileHtmlOldOutput $FileHtmlOldOutput" ); 
            unlink ( $FileHtmlOldOutput ) ; 
            }
            
        $RegexFilterForCsvToWikiSourceFiles = 
                                    $confHolderOfObj->{'RegexFilterForCsvToWikiSourceFiles'} || '^.*\.csv' ; 
        # set a default page size if not defined
        $HtmlPageSize = $confHolderOfObj->{'HtmlPageSize'} || 20; 
 
        $CsvFileSeparator = chr(    $confHolderOfObj->{'CsvFileSeparator'}) || chr(44) ; 
        
        $TokenStart = ''  ; 
        $TokenStop = '|' ; 
        $LineStart = '||' ; 
        $LineStop = ' ' . "\n" ; 
        $StrToWriteStart = '{table-plus:autoTotal=true|autoNumber=true|sortColumn=2|sortIcon=true|columnTypes=S,I,I}' . "\n" ; 
        $StrToWriteStop = '{table-plus}' . "\n" ; 
        $Pager = '' ; 
 
} #eof sub
# =============================================================================
# START OO
 
 
#sourcF:\\\\\\http://www.netalive.org/tinkering/serious-perl/#oop_constructors
sub new {
    
    my $class = shift ;        # Class name is in the first parameter
    $confHolder = ${ shift @_ } if ( @_ )  ; 
    
    my $self = { };  # Anonymous hash reference holds instance attributes
    
    bless($self, $class);          # Say: $self is a $class
        $self->Initialize() ;    
    return $self;
} #eof const 
 
 
sub AUTOLOAD {
 
    my $self = shift ; 
    no strict 'refs'; 
    my $name = our $AUTOLOAD;
    *$AUTOLOAD = sub { 
    my $msg = () ; 
    $msg .= "BOOM! BOOM! BOOM! \n RunTime Error !!!\n" ; 
    $msg .= "Undefined Function $name(@_)\n" ;
    cluck(  "$self , $msg" ) ; 
    };
    goto &$AUTOLOAD;    # Restart the new routine.
}    
 
 
    sub get    {
    
        my $self = shift;
        my $name = shift;
        return $self->{$name};
    } #eof sub get 
 
 
    sub set    {
    
        my $self = shift;
        my $name = shift;
        my $value = shift;
        $self->{$name}=$value;
    } #eof sub set 
 
 
    sub dumpFields        {
        my $self = shift ; 
        my $strFields = () ; 
        foreach my $key (keys %$self)        {
            $strFields .= "$key = $self->{$key}\n";
        }
        
        return $strFields ; 
    } #eof sub dumpFields 
 
 
sub DESTROY {
 
    my $self = shift;
    #debug print "the DESTRUCTOR is called  \n" ; 
    return ; 
} 
 
 
# STOP OO
# =============================================================================
 
sub RunCsvToWiki {
    
    my $self = shift ; 
    my $msg = () ; 
    $msg = "CFPoint24    OK    Convert the csv files from the $DirCsvInput dir to html files in the $DirCsvOutput dir"  ;
    $objLogger->LogInfoMsg ( $msg ) ; 
    
    my ($RefFilesAndDirs , $RefDirsToProcess , $RefFilesToProcess ) = 
    $objFileHandler->ReadDirRecursivelyReturnArrays ( $DirCsvInput , $RegexFilterForCsvToWikiSourceFiles) ; 
    my @FilesAndDirs = @$RefFilesAndDirs ; 
    my @DirsToProcess = @$RefDirsToProcess ; 
    my @FilesToProcess = @$RefFilesToProcess ; 
 
 
    foreach my $FileToProcess ( @FilesToProcess ) {
    
        $objLogger->LogDebugMsg ( "csv \$FileToProcess is $FileToProcess " ) ; 
        #read the input metadata file 
        my $RefRowsFileInput = $objFileHandler->ReadFileReturnArray ( $FileToProcess ) ; 
        my @RowsFileInput = @$RefRowsFileInput; 
        $objLogger->LogDebugMsg ( "\@RowsFileInput is @RowsFileInput " ) ; 
        #FOREACH LINE OF THE FILE DO SOMETHING
        my $OldTableName = '' ; 
        my $ColList = '' ; 
        my $StrOutput = '' ; 
        my $rowCounter= 0 ; 
        my $PageStartLine = 0 ; 
        
        $Pager = '<table><tr>' ; 
        
        # start with 1 
        for ( my $rowCounter = 1 ; $rowCounter <= $#RowsFileInput ; 
                                            $rowCounter=$rowCounter + 1)                                     {
                
                if ( $rowCounter % $HtmlPageSize == 0 
                                || $rowCounter == $#RowsFileInput )     {
 
                    # $1 should produce the full path till the last \ or /
                    # $2 should produce the BareName without the .extension
                    # $3 should produce the file extension after the last dot
                    $FileToProcess =~m/^(.*)(\\|\/)(.*)(\..*)/; # strip the remote path and keep the filename
                    my $LinkName = $3 ; 
                    # use human readable 
                    my $StartItemNumberInPage = $rowCounter  ; 
                    $StartItemNumberInPage = $rowCounter - $HtmlPageSize +1 unless ( $rowCounter == $#RowsFileInput) ; 
                    $StartItemNumberInPage = $rowCounter - ($rowCounter % $HtmlPageSize ) if ( $rowCounter == $#RowsFileInput) ; 
                    my $EndItemNumberInPage = $rowCounter ;  
                    $LinkName = $LinkName . '.' . "$StartItemNumberInPage"   . '-' . "$EndItemNumberInPage"  . '.html' ; 
 
                    $Pager .= '<td>' . '<a href="' . $LinkName   . "\">" . 
                    "$StartItemNumberInPage" . '-' . "$EndItemNumberInPage"  . "</a></td>" ;   
                    
                    #            print "\$Pager is $Pager " ; 
                    $objLogger->LogDebugMsg (  "\$LinkName is $LinkName " ) ; 
                    $objLogger->LogDebugMsg (  "\$rowCounter is $rowCounter " ) ; 
                    $objLogger->LogDebugMsg (  "\$#RowsFileInput is $#RowsFileInput " ) ; 
                }
        } #eof for
        $Pager .= '</tr></table>' ; 
        $Pager = "" ; 
        
        $rowCounter = 0 ; 
        
        foreach my $line ( @RowsFileInput  ) {
        
            $objLogger->LogDebugMsg ( "\$line is $line " ) ; 
            chop($line ) ; 
            my @tokens= split( "$CsvFileSeparator" , $line ) ; 
            $line = '' ; 
            
            if ( $rowCounter == 0 ) {
                $TokenStop = '||' ;  
            } else {
                $TokenStop = '|' ;   
                }
                
            foreach my $token ( @tokens)     {
            
                $token = GenerateToken ( $token )  ;
                $line = $line . $token ; 
            }
            
            $line = GenerateLine ( $line , $rowCounter ) ;         
            $rowCounter++ ;
            $StrOutput = $StrOutput . $line ; 
    
            if ( $rowCounter % $HtmlPageSize == 0 || $rowCounter == $#RowsFileInput)     {
 
                    $FileToProcess =~m/^(.*)(\\|\/)(.*)(\..*)/; # strip the remote path and keep the filename
                    my $LinkName = $3 ; 
                    # use human readable numbers start with 1 not 0
                    
                    my $StartItemNumberInPage = 0 ; 
                    $StartItemNumberInPage    = $rowCounter - $HtmlPageSize +1 unless $rowCounter == $#RowsFileInput ; 
                    $StartItemNumberInPage    = $rowCounter - ( $rowCounter % $HtmlPageSize ) if ( $rowCounter == $#RowsFileInput ) ; 
                    my $EndItemNumberInPage = $rowCounter ;  
                                        
                    $LinkName = $LinkName . '.' . "$StartItemNumberInPage"  . '-' . $rowCounter   . '.html' ; 
                    $FileOutput = "$DirCsvOutput" . '/' . "$LinkName" ;
                    WriteFile ( $FileOutput , $StrOutput , $PageStartLine ) ; 
                    $objLogger->LogDebugMsg ( "\$StrOutput is $StrOutput" ) ; 
                    $StrOutput = '' ; 
                    $PageStartLine = $PageStartLine + $HtmlPageSize ; 
                }
                #debug $objLogger->LogDebugMsg ( "\$StrOutput is $StrOutput" ) ; 
        } #eof foreach line
        # END FOREACH LINE 
    
    } #eof foreach $FileToProcess 
    
    $Pager = ""; 
} #eof sub ExecuteRunCommand 
 
 
sub GenerateToken    {
 
    my $token = shift ; 
    $token = $TokenStart . $token . $TokenStop ;     
}    # eof sub GenerateToken
 
 
sub GenerateLine    {
 
    my $line = shift ; 
    my $rowCounter = shift ; 
    
    if ( $rowCounter % 2 != 0 ) 
        { $line = $LineStart . $line . $LineStop ; }
    else 
        {        $line = $LineStart . $line . $LineStop ; }
    
    return $line ; 
} # eof sub GenerateLine
 
 
sub trim        {
 
    $_[0]=~s/^\s+//;
    $_[0]=~s/\s+$//;
    return $_[0];
}
 
#eof sub trim 
 
 
sub WriteFile    {
    
    my $FileToWrite = shift ; 
    my $StrToWrite = shift ; 
        my $PageStartSize = shift ; 
        
        my $head .= 
'<html>
<head>
<title>tables</title>
  <style type="text/css">
    table tbody tr td {
      background-color: #eee;
    }
    table tr.odd  td {
      background-color: #fff;
    }
  </style>
</head><body>
' ; 
 
$StrToWrite = $head . $Pager . $StrToWriteStart . $StrToWrite .  $StrToWriteStop;   
$StrToWrite .= $Pager . '</body></html>' ; 
 
 
#$LinkName = $LinkName . '.' . $rowCounter . '-' . ( $rowCounter + $HtmlPageSize ) . '.html' ; 
$objFileHandler->PrintToFile ( $FileToWrite , $StrToWrite ) ; 
 
    
} #eof sub WriteToFile 
 
 
1 ; 
 
__END__
 
 
# VersionHistory:
# 1.0.0 --- 2011.12.25 - 20:13:19 --- Changed default conf dir
# 1.4.0 --- 2011.08.13 16:54:07 --- Added Control Flow documentation 
# 1.3.0 --- 2011.07.14 20:34:44 --- Added clean of html files 
# 1.2.1 --- 2011.07.06 11:05:05 --- Removed FilF:\\\\\\:Find 
# 1.0.0 --- 2011.07.06 10:26:59 --- ysg --- Added RegexFilterForCsvToWikiSourceFiles , full proof Initialize 
# 1.0.001.0.01_222618 --- Yordan Georgiev --- Generates Select All with full [] column list from Table
# 1.0.601.0.04_1.0.65 --- Yordan Georgiev --- REnamed to NiceHtmlTableGenerator.1.0.pl -- added css and a nice ttable
#hint: add to some rows : color:#FF0000; red or style="color:#009900" green to underline some colors
 
# [r1c1link alias|r1c1 pagetitle|r1c1 tip]
# RowNum    WorkFlowName    SubObjectType    SubObjectName    LogPageId    FolderId    ImaticaFolderName    WorkFlowId    WorkFlowLastUpdateTime    SubObjectInstanceId    PageId
# PageId = =G2&"-"&B2&"-"&C2&"-"&D2
# LogId = = "[etl-log-"&K2&"]"
# 
pre

Labels

perl (41) Cheat Sheet (25) how-to (24) windows (13) oracle (12) sql server 2008 (12) Unix (11) linux (11) sql (11) cmd windows batch (10) mssql (10) cmd (9) script (9) textpad (9) netezza (8) sql server 2005 (8) code generation (7) cygwin (7) meta data mssql (7) metadata (7) Informatica (5) cheatsheet (5) energy (5) excel (5) tsql (5) utilities (5) bash (4) future (4) generic (4) html (4) perl modules (4) programs (4) settings (4) sh (4) поуки (4) принципи (4) Focus Fusion (3) Solaris (3) cool programs (3) development (3) economy (3) example (3) freeware (3) fusion (3) morphus (3) mssql 2005 (3) nuclear (3) nz (3) parse (3) sftp (3) shortcuts (3) sofware development (3) source (3) sqlplus (3) table (3) vim (3) .Net (2) C# (2) China (2) GUI (2) Google (2) GoogleCL (2) Solaris Unix (2) ascii (2) awk (2) batch (2) cas (2) code2html (2) columns (2) configuration (2) conversion (2) duplicates (2) export (2) file (2) free programs (2) google code (2) logging (2) mssql 2008 (2) mysql (2) next big future (2) nsis (2) nzsql (2) ora (2) prediction (2) publish (2) python (2) release management (2) report (2) security (2) single-click (2) sqlserver 2005 (2) sqlserver 2008 (2) src (2) ssh (2) template (2) tools (2) vba (2) video (2) xlt (2) xml (2) youtube videos (2) *nix (1) .vimrc (1) BSD license (1) Bulgaria (1) Dallas (1) Database role (1) Dense plasma focus (1) Deployment (1) ERP (1) ExcelToHtml (1) GD (1) GDP (1) HP-UX (1) Hosting (1) INC (1) IT general (1) ITIL management bullshit-management (1) IZarc (1) Java Web Start (1) Khan Academy (1) Linux Unix rpm cpio build install configure (1) Linux git source build .configure make (1) ListBox (1) MIT HYDROGEN VIRUS (1) OO (1) Obama (1) PowerShell (1) Run-time (1) SDL (1) SIWA (1) SOX (1) Services (1) Stacks (1) SubSonic (1) TED (1) abstractions (1) ansible hosts linux bash (1) ansible linux deployment how-to (1) ansible yum pip python (1) apache (1) apache 2.2 (1) application life cycle (1) architecture (1) archive (1) arguments (1) avatar (1) backup (1) bash Linux open-ssh ssh ssh_server ssh_client public-private key authentication (1) bash stub (1) bin (1) biofuels (1) biology (1) books (1) browser (1) bubblesort (1) bugs (1) build (1) byte (1) cas_sql_dev (1) chennai (1) class (1) claut (1) cmdow (1) code generation sqlserver (1) command (1) command line (1) conf (1) confluence (1) console (1) convert (1) cool programs windows free freeware (1) copy-paste (1) csv (1) ctags (1) current local time (1) cygwin X11 port-forwarding mintty xclock Linux Unix X (1) cygwin bash how-to tips_n_tricks (1) cygwin conf how-to (1) data (1) data types (1) debt (1) diagram (1) digital (1) disk (1) disk space (1) documentation (1) dos (1) dubai (1) e-cars (1) electric cars (1) electricity (1) emulate (1) errors (1) excel shortcuts (1) exponents (1) export workflow (1) extract (1) fast export (1) fexp (1) file extension (1) file permissions (1) findtag (1) firewall (1) for loop (1) functions (1) fusion research (1) german (1) google cli (1) google command line interface (1) gpg (1) head (1) helsinki (1) history (1) hop or flop (1) host-independant (1) how-to Windows cmd time date datetime (1) ideas (1) image (1) informatica repo sql workflows sessions file source dir (1) informatica sql repository (1) install (1) java (1) jump to (1) keyboard shortcuts (1) ksh (1) level (1) linkedin (1) linux bash ansible hosts (1) linux bash commands (1) linux bash how-to shell expansion (1) linux bash user accounts password (1) linux cheat-sheet (1) linux cheatsheet cheat-sheet revised how-to (1) linux how-to non-root vim (1) linux ssh hosts parallel subshell bash oneliner (1) london (1) make (1) me (1) metacolumn (1) metadata functions (1) metaphonre (1) method (1) model (1) movie (1) multithreaded (1) mysql how-to table datatypes (1) n900 (1) nano (1) neteza (1) netezza bash linux nps (1) netezza nps (1) netezza nps nzsql (1) netezza nz Linux bash (1) netezza nz bash linux (1) netezza nz nzsql sql (1) netezza nzsql database db sizes (1) non-password (1) nord pol (1) nps backup nzsql schema (1) number formatting (1) nz db size (1) nz netezza cheat sheet (1) nzsql date timestamp compare bigint to_date to_char now (1) on-lier (1) one-liners (1) one-to-many (1) oneliners (1) open (1) open source (1) openrowset (1) outlook (1) parser (1) password (1) paths (1) perl disk usage administration Linux Unix (1) permissions (1) php (1) picasa (1) platform (1) ppm (1) predictions (1) prices (1) principles (1) productivity (1) project (1) prompt (1) proxy account (1) public private key (1) publishing (1) putty (1) qt (1) read file (1) registry (1) relationship (1) repository (1) rm (1) scp (1) scripts (1) scsi (1) sed (1) sendEmail (1) sh stub (1) silicon (1) smtp (1) software procurement (1) sofware (1) sort (1) sql script (1) sql_dev (1) sqlcmd (1) sqlite (1) sqlite3 (1) sshd (1) stackoverflow (1) stored procedure (1) stub (1) stupidity (1) subroutines (1) svn (1) sysinternals (1) tail (1) tar (1) temp table (1) templates (1) teradata (1) terminal (1) test (1) testing (1) theory (1) thorium (1) time (1) tip (1) title (1) tool (1) url (1) urls (1) user (1) utility (1) utils (1) vb (1) vim perl regex bash search for string (1) vimeo (1) warsaw (1) wiki (1) wikipedia (1) window (1) windows 7 (1) windows programs (1) windows reinstall (1) wisdoms (1) workflow (1) worth-reading (1) wrapper (1) xp_cmdshell (1) xslt (1) youtube (1)

Blog Archive

Translate with Google Translate

My Blog List

Loading...