[Bio] / FigKernelPackages / Tracer.pm Repository:
ViewVC logotype

Diff of /FigKernelPackages/Tracer.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.6, Mon Mar 7 02:01:51 2005 UTC revision 1.104, Fri May 9 06:22:49 2008 UTC
# Line 1  Line 1 
1    # -*- perl -*-
2    ########################################################################
3    # Copyright (c) 2003-2006 University of Chicago and Fellowship
4    # for Interpretations of Genomes. All Rights Reserved.
5    #
6    # This file is part of the SEED Toolkit.
7    #
8    # The SEED Toolkit is free software. You can redistribute
9    # it and/or modify it under the terms of the SEED Toolkit
10    # Public License.
11    #
12    # You should have received a copy of the SEED Toolkit Public License
13    # along with this program; if not write to the University of Chicago
14    # at info@ci.uchicago.edu or the Fellowship for Interpretation of
15    # Genomes at veronika@thefig.info or download a copy from
16    # http://www.theseed.org/LICENSE.TXT.
17    ########################################################################
18    
19  package Tracer;  package Tracer;
20    
21          require Exporter;          require Exporter;
22          @ISA = ('Exporter');          @ISA = ('Exporter');
23          @EXPORT = qw(Trace T TSetup QTrace Confess Cluck Min Max Assert);      @EXPORT = qw(Trace T TSetup QTrace Confess Cluck Min Max Assert Open OpenDir TICK StandardSetup EmergencyKey ETracing Constrain Insure ChDir Emergency Warn);
24          @EXPORT_OK = qw(GetFile GetOptions Merge MergeOptions ParseCommand ParseRecord UnEscape);      @EXPORT_OK = qw(GetFile GetOptions Merge MergeOptions ParseCommand ParseRecord UnEscape Escape PrintLine PutLine);
25          use strict;          use strict;
26          use Carp qw(longmess croak);      use Carp qw(longmess croak carp);
27          use CGI;          use CGI;
28        use Cwd;
29        use FIG_Config;
30        use PageBuilder;
31        use Digest::MD5;
32        use File::Basename;
33        use File::Path;
34        use File::stat;
35        use LWP::UserAgent;
36        use Time::HiRes 'gettimeofday';
37        use URI::Escape;
38        use Time::Local;
39        use POSIX qw(strftime);
40        use Time::Zone;
41    
42    
43  =head1 Tracing and Debugging Helpers  =head1 Tracing and Debugging Helpers
44    
45  =head2 Introduction  =head2 Tracing
46    
47  This package provides simple tracing for debugging and reporting purposes. To use it simply call the  This package provides simple tracing for debugging and reporting purposes. To use it simply call the
48  L</TSetup> method to set the options and call L</Trace> to write out trace messages. Each trace  L</TSetup> or L</ETracing> method to set the options and call L</Trace> to write out trace messages.
49  message has a I<trace level> and I<category> associated with it. In addition, the tracing package itself  L</TSetup> and L</ETracing> both establish a I<trace level> and a list of I<categories>. Similarly,
50  has a list of categories and a single trace level set by the B<TSetup> method. Only messages whose trace  each trace message has a I<trace level> and I<category> associated with it. Only messages whose trace
51  level is less than or equal to this package's trace level and whose category is activated will  level is less than or equal to the setup trace level and whose category is activated will
52  be written. Thus, a higher trace level on a message indicates that the message  be written. Thus, a higher trace level on a message indicates that the message
53  is less likely to be seen. A higher trace level passed to B<Setup> means more trace messages will  is less likely to be seen, while a higher trace level passed to B<TSetup> means more trace messages will
54  appear. To generate a trace message, use the following syntax.  appear.
55    
56    =head3 Putting Trace Messages in Your Code
57    
58    To generate a trace message, use the following syntax.
59    
60  C<< Trace($message) if T(errors => 4); >>      Trace($message) if T(errors => 4);
61    
62  This statement will produce a trace message if the trace level is 4 or more and the C<errors>  This statement will produce a trace message if the trace level is 4 or more and the C<errors>
63  category is active. Note that the special category C<main> is always active, so  category is active. There is a special category C<main> that is always active, so
64    
65  C<< Trace($message) if T(main => 4); >>      Trace($message) if T(main => 4);
66    
67  will trace if the trace level is 4 or more.  will trace if the trace level is 4 or more.
68    
# Line 34  Line 70 
70  following call is made in the B<Sprout> package, it will appear if the C<Sprout> category is  following call is made in the B<Sprout> package, it will appear if the C<Sprout> category is
71  active and the trace level is 2 or more.  active and the trace level is 2 or more.
72    
73  C<< Trace($message) if T(2); >>      Trace($message) if T(2);
74    
75  To set up tracing, you call the C</Setup> method. The method takes as input a trace level, a list  In scripts, where no package name is available, the category defaults to C<main>.
76  of category names, and a set of options. The trace level and list of category names are  
77    =head3 Custom Tracing
78    
79    Many programs have customized tracing configured using the L</TSetup> method. This is no longer
80    the preferred method, but a knowledge of how custom tracing works can make the more modern
81    L</Emergency Tracing> easier to understand.
82    
83    To set up custom tracing, you call the L</TSetup> method. The method takes as input a trace level,
84    a list of category names, and a destination. The trace level and list of category names are
85  specified as a space-delimited string. Thus  specified as a space-delimited string. Thus
86    
87  C<< TSetup('3 errors Sprout ERDB', 'HTML'); >>      TSetup('3 errors Sprout ERDB', 'TEXT');
88    
89    sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and
90    specifies that messages should be sent to the standard output.
91    
92  sets the trace level to 3, activated the C<errors>, C<Sprout>, and C<ERDB> categories, and  To turn on tracing for ALL categories, use an asterisk. The call below sets every category to
93  specifies that messages should be output as HTML paragraphs. The idea is to make it easier to  level 3 and writes the output to the standard error output. This sort of thing might be
94  input tracing configuration on a web form.  useful in a CGI environment.
95    
96  In addition to HTML and file output for trace messages, you can specify that the trace messages      TSetup('3 *', 'WARN');
97    
98    In addition standard error and file output for trace messages, you can specify that the trace messages
99  be queued. The messages can then be retrieved by calling the L</QTrace> method. This approach  be queued. The messages can then be retrieved by calling the L</QTrace> method. This approach
100  is useful if you are building a web page. Instead of having the trace messages interspersed with  is useful if you are building a web page. Instead of having the trace messages interspersed with
101  the page output, they can be gathered together and displayed at the end of the page. This makes  the page output, they can be gathered together and displayed at the end of the page. This makes
102  it easier to debug page formatting problems.  it easier to debug page formatting problems.
103    
104  Finally, you can specify that all trace messages be emitted as warnings.  Finally, you can specify that all trace messages be emitted to a file, or the standard output and
105    a file at the same time. To trace to a file, specify the filename with an output character in front
106    of it.
107    
108        TSetup('4 SQL', ">$fileName");
109    
110    To trace to the standard output and a file at the same time, put a C<+> in front of the angle
111    bracket.
112    
113        TSetup('3 *', "+>$fileName");
114    
115  The flexibility of tracing makes it superior to simple use of directives like C<die> and C<warn>.  The flexibility of tracing makes it superior to simple use of directives like C<die> and C<warn>.
116  Tracer calls can be left in the code with minimal overhead and then turned on only when needed.  Tracer calls can be left in the code with minimal overhead and then turned on only when needed.
117  Thus, debugging information is available and easily retrieved even when the application is  Thus, debugging information is available and easily retrieved even when the application is
118  being used out in the field.  being used out in the field.
119    
120    =head3 Trace Levels
121    
122    There is no hard and fast rule on how to use trace levels. The following is therefore only
123    a suggestion.
124    
125    =over 4
126    
127    =item Error 0
128    
129    Message indicates an error that may lead to incorrect results or that has stopped the
130    application entirely.
131    
132    =item Warning 1
133    
134    Message indicates something that is unexpected but that probably did not interfere
135    with program execution.
136    
137    =item Notice 2
138    
139    Message indicates the beginning or end of a major task.
140    
141    =item Information 3
142    
143    Message indicates a subtask. In the FIG system, a subtask generally relates to a single
144    genome. This would be a big loop that is not expected to execute more than 500 times or so.
145    
146    =item Detail 4
147    
148    Message indicates a low-level loop iteration.
149    
150    =back
151    
152    The format of trace messages is important because some utilities analyze trace files.
153    There are three fields-- the time stamp, the category name, and the text.
154    The time stamp is between square brackets and the category name between angle brackets.
155    After the category name there is a colon (C<:>) followed by the message text.
156    If the square brackets or angle brackets are missing, then the trace management
157    utilities assume that they are encountering a set of pre-formatted lines.
158    
159    Note, however, that this formatting is done automatically by the tracing functions. You
160    only need to know about it if you want to parse a trace file.
161    
162    =head3 Emergency Tracing
163    
164    Sometimes, you need a way for tracing to happen automatically without putting parameters
165    in a form or on the command line. Emergency tracing does this. You invoke emergency tracing
166    from the debug form, which is accessed from the [[DebugConsole]]. Emergency tracing requires
167    that you specify a tracing key. For command-line tools, the key is
168    taken from the C<TRACING> environment variable. For web services, the key is taken from
169    a cookie. Either way, the key tells the tracing facility who you are, so that you control
170    the tracing in your environment without stepping on other users.
171    
172    The key can be anything you want. If you don't have a key, the C<SetPassword> page will
173    generate one for you.
174    
175    You can activate and de-activate emergency tracing from the debugging control panel, as
176    well as display the trace file itself.
177    
178    To enable emergency tracing in your code, call
179    
180        ETracing($cgi)
181    
182    from a web script and
183    
184        ETracing()
185    
186    from a command-line script.
187    
188    The web script will look for the tracing key in the cookies, and the command-line
189    script will look for it in the C<TRACING> environment variable. If you are
190    using the L</StandardSetup> method or a [[WebApplication]], emergency tracing
191    will be configured automatically.
192    
193  =cut  =cut
194    
195  # Declare the configuration variables.  # Declare the configuration variables.
196    
197  my $Destination = "NONE";       # Description of where to send the trace output.  my $Destination = "WARN";   # Description of where to send the trace output.
198    my $TeeFlag = 0;            # TRUE if output is going to a file and to the
199                                # standard output
200  my %Categories = ( main => 1 );  my %Categories = ( main => 1 );
201                                                          # hash of active category names                                                          # hash of active category names
202    my @LevelNames = qw(error warn notice info detail);
203  my $TraceLevel = 0;                     # trace level; a higher trace level produces more  my $TraceLevel = 0;                     # trace level; a higher trace level produces more
204                                                          # messages                                                          # messages
205  my @Queue = ();                         # queued list of trace messages.  my @Queue = ();                         # queued list of trace messages.
206    my $LastCategory = "main";  # name of the last category interrogated
207    my $LastLevel = 0;          # level of the last test call
208    my $SetupCount = 0;         # number of times TSetup called
209    my $AllTrace = 0;           # TRUE if we are tracing all categories.
210    my $SavedCGI;               # CGI object passed to ETracing
211    my $CommandLine;            # Command line passed to StandardSetup
212    umask 2;                    # Fix the damn umask so everything is group-writable.
213    
214  =head2 Public Methods  =head2 Tracing Methods
215    
216    =head3 Setups
217    
218        my $count = Tracer::Setups();
219    
220    Return the number of times L</TSetup> has been called.
221    
222    This method allows for the creation of conditional tracing setups where, for example, we
223    may want to set up tracing if nobody else has done it before us.
224    
225    =cut
226    
227    sub Setups {
228        return $SetupCount;
229    }
230    
231  =head3 TSetup  =head3 TSetup
232    
233  C<< TSetup($categoryList, $target); >>      TSetup($categoryList, $target);
234    
235  This method is used to specify the trace options. The options are stored as package data  This method is used to specify the trace options. The options are stored as package data
236  and interrogated by the L</Trace> and L</T> methods.  and interrogated by the L</Trace> and L</T> methods.
# Line 90  Line 246 
246    
247  The destination for the trace output. To send the trace output to a file, specify the file  The destination for the trace output. To send the trace output to a file, specify the file
248  name preceded by a ">" symbol. If a double symbol is used (">>"), then the data is appended  name preceded by a ">" symbol. If a double symbol is used (">>"), then the data is appended
249  to the file. Otherwise the file is cleared before tracing begins. In addition to sending  to the file. Otherwise the file is cleared before tracing begins. Precede the first ">"
250  the trace messages to a file, you can specify a special destination. C<HTML> will cause  symbol with a C<+> to echo output to a file AND to the standard output. In addition to
251  tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>  sending the trace messages to a file, you can specify a special destination. C<HTML> will
252    cause tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>
253  will cause tracing to the standard output as ordinary text. C<ERROR> will cause trace  will cause tracing to the standard output as ordinary text. C<ERROR> will cause trace
254  messages to be sent to the standard error output as ordinary text. C<QUEUE> will cause trace  messages to be sent to the standard error output as ordinary text. C<QUEUE> will cause trace
255  messages to be stored in a queue for later retrieval by the L</QTrace> method. C<WARN> will  messages to be stored in a queue for later retrieval by the L</QTrace> method. C<WARN> will
# Line 110  Line 267 
267          my @categoryData = split /\s+/, $categoryList;          my @categoryData = split /\s+/, $categoryList;
268          # Extract the trace level.          # Extract the trace level.
269          $TraceLevel = shift @categoryData;          $TraceLevel = shift @categoryData;
270          # Build the category hash.      # Presume category-based tracing until we learn otherwise.
271        $AllTrace = 0;
272        # Build the category hash. Note that if we find a "*", we turn on non-category
273        # tracing. We must also clear away any pre-existing data.
274        %Categories = ( main => 1 );
275          for my $category (@categoryData) {          for my $category (@categoryData) {
276                  $Categories{$category} = 1;          if ($category eq '*') {
277                $AllTrace = 1;
278            } else {
279                $Categories{lc $category} = 1;
280            }
281          }          }
282          # Now we need to process the destination information. The most important special          # Now we need to process the destination information. The most important special
283          # case is the single ">", which requires we clear the file first. After doing      # case is when we're writing to a file. This is indicated by ">" (overwrite) and
284          # so, we tack on another ">" sign so that future trace messages are appended.      # ">>" (append). A leading "+" for either indicates that we are also writing to
285        # the standard output (tee mode).
286        if ($target =~ m/^\+?>>?/) {
287            if ($target =~ m/^\+/) {
288                $TeeFlag = 1;
289                $target = substr($target, 1);
290            }
291          if ($target =~ m/^>[^>]/) {          if ($target =~ m/^>[^>]/) {
292                # We need to initialize the file (which clears it).
293                  open TRACEFILE, $target;                  open TRACEFILE, $target;
294                  print TRACEFILE Now() . " Tracing initialized.\n";              print TRACEFILE "[" . Now() . "] [notice] [Tracer] Tracing initialized.\n";
295                  close TRACEFILE;                  close TRACEFILE;
296                # Set to append mode now that the file has been cleared.
297                  $Destination = ">$target";                  $Destination = ">$target";
298          } else {          } else {
299                $Destination = $target;
300            }
301        } else {
302                  $Destination = uc($target);                  $Destination = uc($target);
303          }          }
304        # Increment the setup counter.
305        $SetupCount++;
306  }  }
307    
308  =head3 SetLevel  =head3 SetLevel
309    
310  C<< Tracer::SetLevel($newLevel); >>      Tracer::SetLevel($newLevel);
311    
312  Modify the trace level. A higher trace level will cause more messages to appear.  Modify the trace level. A higher trace level will cause more messages to appear.
313    
# Line 147  Line 325 
325      $TraceLevel = $_[0];      $TraceLevel = $_[0];
326  }  }
327    
328  =head3 Now  =head3 ParseDate
   
 C<< my $string = Tracer::Now(); >>  
   
 Return a displayable time stamp containing the local time.  
   
 =cut  
   
 sub Now {  
         my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime(time);  
         my $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .  
                                  _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);  
         return $retVal;  
 }  
   
 # Pad a number to 2 digits.  
 sub _p2 {  
         my ($value) = @_;  
         $value = "0$value" if ($value < 10);  
         return $value;  
 }  
   
 =head3 LogErrors  
   
 C<< Tracer::LogErrors($fileName); >>  
   
 Route the standard error output to a log file.  
   
 =over 4  
   
 =item fileName  
   
 Name of the file to receive the error output.  
   
 =back  
329    
330  =cut      my $time = Tracer::ParseDate($dateString);
331    
332  sub LogErrors {  Convert a date into a PERL time number. This method expects a date-like string
333          # Get the file name.  and parses it into a number. The string must be vaguely date-like or it will
334          my ($fileName) = @_;  return an undefined value. Our requirement is that a month and day be
335          # Open the file as the standard error output.  present and that three pieces of the date string (time of day, month and day,
336          open STDERR, '>', $fileName;  year) be separated by likely delimiters, such as spaces, commas, and such-like.
 }  
337    
338  =head3 ReadOptions  If a time of day is present, it must be in military time with two digits for
339    everything but the hour.
340    
341  C<< my %options = Tracer::ReadOptions($fileName); >>  The year must be exactly four digits.
342    
343  Read a set of options from a file. Each option is encoded in a line of text that has the  Additional stuff can be in the string. We presume it's time zones or weekdays or something
344  format  equally innocuous. This means, however, that a sufficiently long sentence with date-like
345    parts in it may be interpreted as a date. Hopefully this will not be a problem.
346    
347  I<optionName>C<=>I<optionValue>C<; >I<comment>  It should be guaranteed that this method will parse the output of the L</Now> function.
348    
349  The option name must consist entirely of letters, digits, and the punctuation characters  The parameters are as follows.
 C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank  
 character is a semi-colon will be ignored. The return hash will map each option name to  
 the corresponding option value.  
350    
351  =over 4  =over 4
352    
353  =item fileName  =item dateString
354    
355  Name of the file containing the option data.  The date string to convert.
356    
357  =item RETURN  =item RETURN
358    
359  Returns a hash mapping the option names specified in the file to their corresponding option  Returns a PERL time, that is, a number of seconds since the epoch, or C<undef> if
360  value.  the date string is invalid. A valid date string must contain a month and day.
361    
362  =back  =back
363    
364  =cut  =cut
365    
366  sub ReadOptions {  # Universal month conversion table.
367          # Get the parameters.  use constant MONTHS => {    Jan =>  0, January   =>  0, '01' =>  0,  '1' =>  0,
368          my ($fileName) = @_;                              Feb =>  1, February  =>  1, '02' =>  1,  '2' =>  1,
369          # Open the file.                              Mar =>  2, March     =>  2, '03' =>  2,  '3' =>  2,
370          (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");                              Apr =>  3, April     =>  3, '04' =>  3,  '4' =>  3,
371          # Count the number of records read.                              May =>  4, May       =>  4, '05' =>  4,  '5' =>  4,
372          my ($records, $comments) = 0;                              Jun =>  5, June      =>  5, '06' =>  5,  '6' =>  5,
373          # Create the return hash.                              Jul =>  6, July      =>  6, '07' =>  6,  '7' =>  6,
374          my %retVal = ();                              Aug =>  7, August    =>  7, '08' =>  7,  '8' =>  7,
375          # Loop through the file, accumulating key-value pairs.                              Sep =>  8, September =>  8, '09' =>  8,  '9' =>  8,
376          while (my $line = <CONFIGFILE>) {                              Oct =>  9, October  =>   9, '10' =>  9,
377                  # Denote we've read a line.                              Nov => 10, November =>  10, '11' => 10,
378                  $records++;                              Dec => 11, December =>  11, '12' => 11
379                  # Determine the line type.                          };
                 if ($line =~ /^\s*[\n\r]/) {  
                         # A blank line is a comment.  
                         $comments++;  
                 } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {  
                         # Here we have an option assignment.  
                         retVal{$1} = $2;  
                 } elsif ($line =~ /^\s*;/) {  
                         # Here we have a text comment.  
                         $comments++;  
                 } else {  
                         # Here we have an invalid line.  
                         Trace("Invalid option statement in record $records.") if T(0);  
                 }  
         }  
         # Return the hash created.  
         return %retVal;  
 }  
   
 =head3 GetOptions  
   
 C<< Tracer::GetOptions(\%defaults, \%options); >>  
   
 Merge a specified set of options into a table of defaults. This method takes two hash references  
 as input and uses the data from the second to update the first. If the second does not exist,  
 there will be no effect. An error will be thrown if one of the entries in the second hash does not  
 exist in the first.  
   
 Consider the following example.  
   
 C<< my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options); >>  
   
 In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and  
 B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of  
 B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and  
 the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level  
 will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as  
   
 C<< {databaseType => 'Oracle'} >>  
   
 an error will occur because the B<databaseType> option does not exist.  
   
 =over 4  
   
 =item defaults  
   
 Table of default option values.  
   
 =item options  
   
 Table of overrides, if any.  
   
 =item RETURN  
   
 Returns a reference to the default table passed in as the first parameter.  
   
 =back  
   
 =cut  
380    
381  sub GetOptions {  sub ParseDate {
382          # Get the parameters.          # Get the parameters.
383          my ($defaults, $options) = @_;      my ($dateString) = @_;
384          # Check for overrides.      # Declare the return variable.
385          if ($options) {      my $retVal;
386                  # Loop through the overrides.      # Find the month and day of month. There are two ways that can happen. We check for the
387                  while (my ($option, $setting) = each %{$options}) {      # numeric style first. That way, if the user's done something like "Sun 12/22", then we
388                          # Insure this override exists.      # won't be fooled into thinking the month is Sunday.
389                          if (!exists $defaults->{$option}) {      if ($dateString =~ m#\b(\d{1,2})/(\d{1,2})\b# || $dateString =~ m#\b(\w+)\s(\d{1,2})\b#) {
390                                  croak "Unrecognized option $option encountered.";          my ($mon, $mday) = (MONTHS->{$1}, $2);
391            # Insist that the month and day are valid.
392            if (defined($mon) && $2 >= 1 && $2 <= 31) {
393                # Find the time.
394                my ($hour, $min, $sec) = (0, 0, 0);
395                if ($dateString =~ /\b(\d{1,2}):(\d{2}):(\d{2})\b/) {
396                    ($hour, $min, $sec) = ($1, $2, $3);
397                }
398                # Find the year.
399                my $year;
400                if ($dateString =~ /\b(\d{4})\b/) {
401                    $year = $1;
402                          } else {                          } else {
403                                  # Apply the override.                  # Get the default year, which is this one. Note we must convert it to
404                                  $defaults->{$option} = $setting;                  # the four-digit value expected by "timelocal".
405                    (undef, undef, undef, undef, undef, $year) = localtime();
406                    $year += 1900;
407                          }                          }
408                $retVal = timelocal($sec, $min, $hour, $mday, $mon, $year);
409                  }                  }
410          }          }
411          # Return the merged table.      # Return the result.
412          return $defaults;      return $retVal;
413  }  }
414    
415  =head3 MergeOptions  =head3 LogErrors
416    
417  C<< Tracer::MergeOptions(\%table, \%defaults); >>      Tracer::LogErrors($fileName);
418    
419  Merge default values into a hash table. This method looks at the key-value pairs in the  Route the standard error output to a log file.
 second (default) hash, and if a matching key is not found in the first hash, the default  
 pair is copied in. The process is similar to L</GetOptions>, but there is no error-  
 checking and no return value.  
420    
421  =over 4  =over 4
422    
423  =item table  =item fileName
   
 Hash table to be updated with the default values.  
   
 =item defaults  
424    
425  Default values to be merged into the first hash table if they are not already present.  Name of the file to receive the error output.
426    
427  =back  =back
428    
429  =cut  =cut
430    
431  sub MergeOptions {  sub LogErrors {
432          # Get the parameters.      # Get the file name.
433          my ($table, $defaults) = @_;      my ($fileName) = @_;
434          # Loop through the defaults.      # Open the file as the standard error output.
435          while (my ($key, $value) = each %{$defaults}) {      open STDERR, '>', $fileName;
                 if (!exists $table->{$key}) {  
                         $table->{$key} = $value;  
                 }  
         }  
436  }  }
437    
438  =head3 Trace  =head3 Trace
439    
440  C<< Trace($message); >>      Trace($message);
441    
442  Write a trace message to the target location specified in L</TSetup>. If there has not been  Write a trace message to the target location specified in L</TSetup>. If there has not been
443  any prior call to B<TSetup>.  any prior call to B<TSetup>.
# Line 368  Line 455 
455  sub Trace {  sub Trace {
456          # Get the parameters.          # Get the parameters.
457          my ($message) = @_;          my ($message) = @_;
458        # Strip off any line terminators at the end of the message. We will add
459        # new-line stuff ourselves.
460        my $stripped = Strip($message);
461        # Compute the caller information.
462        my ($callPackage, $callFile, $callLine) = caller();
463        my $callFileTitle = basename($callFile);
464        # Check the caller.
465        my $callerInfo = ($callFileTitle ne "Tracer.pm" ? " [$callFileTitle $callLine]" : "");
466          # Get the timestamp.          # Get the timestamp.
467          my $timeStamp = Now();          my $timeStamp = Now();
468        # Build the prefix.
469        my $level = $LevelNames[$LastLevel] || "($LastLevel)";
470        my $prefix = "[$timeStamp] [$level] [$LastCategory]$callerInfo";
471          # Format the message.          # Format the message.
472          my $formatted = "$timeStamp $message";      my $formatted = "$prefix $stripped";
473          # Process according to the destination.          # Process according to the destination.
474          if ($Destination eq "TEXT") {          if ($Destination eq "TEXT") {
475                  # Write the message to the standard output.                  # Write the message to the standard output.
476                  print "$formatted\n";                  print "$formatted\n";
477          } elsif ($Destination eq "ERROR") {          } elsif ($Destination eq "ERROR") {
478                  # Write the message to the error output.          # Write the message to the error output. Here, we want our prefix fields.
479                  print STDERR "$formatted\n";                  print STDERR "$formatted\n";
480        } elsif ($Destination eq "WARN") {
481            # Emit the message to the standard error output. It is presumed that the
482            # error logger will add its own prefix fields, the notable exception being
483            # the caller info.
484            print STDERR "$callerInfo$stripped\n";
485          } elsif ($Destination eq "QUEUE") {          } elsif ($Destination eq "QUEUE") {
486                  # Push the message into the queue.                  # Push the message into the queue.
487                  push @Queue, "$formatted";                  push @Queue, "$formatted";
488          } elsif ($Destination eq "HTML") {          } elsif ($Destination eq "HTML") {
489                  # Convert the message to HTML and write it to the standard output.                  # Convert the message to HTML and write it to the standard output.
490                  my $escapedMessage = CGI::escapeHTML($message);          my $escapedMessage = CGI::escapeHTML($stripped);
491                  print "<p>$formatted</p>\n";          print "<p>$timeStamp $LastCategory $LastLevel: $escapedMessage</p>\n";
     } elsif ($Destination eq "WARN") {  
        # Emit the message as a warning.  
        warn $message;  
492          } elsif ($Destination =~ m/^>>/) {          } elsif ($Destination =~ m/^>>/) {
493                  # Write the trace message to an output file.                  # Write the trace message to an output file.
494                  open TRACING, $Destination;          open(TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";
495                  print TRACING "$formatted\n";                  print TRACING "$formatted\n";
496                  close TRACING;                  close TRACING;
497            # If the Tee flag is on, echo it to the standard output.
498            if ($TeeFlag) {
499                print "$formatted\n";
500            }
501          }          }
502  }  }
503    
504  =head3 T  =head3 T
505    
506  C<< my $switch = T($category, $traceLevel); >>      my $switch = T($category, $traceLevel);
507    
508          or          or
509    
510  C<< my $switch = T($traceLevel); >>      my $switch = T($traceLevel);
511    
512  Return TRUE if the trace level is at or above a specified value and the specified category  Return TRUE if the trace level is at or above a specified value and the specified category
513  is active, else FALSE. If no category is specified, the caller's package name is used.  is active, else FALSE. If no category is specified, the caller's package name is used.
# Line 436  Line 540 
540                  my ($category, $traceLevel) = @_;                  my ($category, $traceLevel) = @_;
541                  if (!defined $traceLevel) {                  if (!defined $traceLevel) {
542                          # Here we have no category, so we need to get the calling package.                          # Here we have no category, so we need to get the calling package.
543                # The calling package is normally the first parameter. If it is
544                # omitted, the first parameter will be the tracelevel. So, the
545                # first thing we do is shift the so-called category into the
546                # $traceLevel variable where it belongs.
547                          $traceLevel = $category;                          $traceLevel = $category;
548                          my ($package, $fileName, $line) = caller;                          my ($package, $fileName, $line) = caller;
549              # If there is no calling package, we default to "main".              # If there is no calling package, we default to "main".
550                          if (!$package) {                          if (!$package) {
551                  $category = "main";                  $category = "main";
552                          } else {                          } else {
553                                  $category = $package;                  my @cats = split /::/, $package;
554                    $category = $cats[$#cats];
555                          }                          }
556                  }                  }
557                  # Use the package and tracelevel to compute the result.          # Save the category name and level.
558                  $retVal = ($traceLevel <= $TraceLevel && exists $Categories{$category});          $LastCategory = $category;
559            $LastLevel = $traceLevel;
560            # Convert it to lower case before we hash it.
561            $category = lc $category;
562            # Validate the trace level.
563            if (ref $traceLevel) {
564                Confess("Bad trace level.");
565            } elsif (ref $TraceLevel) {
566                Confess("Bad trace config.");
567            }
568            # Make the check. Note that level 0 shows even if the category is turned off.
569            $retVal = ($traceLevel <= $TraceLevel && ($traceLevel == 0 || $AllTrace || exists $Categories{$category}));
570      }      }
571          # Return the computed result.          # Return the computed result.
572      return $retVal;      return $retVal;
573  }  }
574    
575  =head3 ParseCommand  =head3 QTrace
   
 C<< my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList); >>  
   
 Parse a command line consisting of a list of parameters. The initial parameters may be option  
 specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped  
 off and merged into a table of default options. The remainder of the command line is  
 returned as a list of positional arguments. For example, consider the following invocation.  
   
 C<< my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words); >>  
   
 In this case, the list @words will be treated as a command line. There are two options available,  
 B<errors> and B<logFile>. If @words has the following format  
   
 C<< -logFile=error.log apple orange rutabaga >>  
   
 then at the end of the invocation, C<$options> will be  
   
 C<< { errors => 0, logFile => 'error.log' } >>  
   
 and C<@arguments> will contain  
576    
577  C<< apple orange rutabaga >>      my $data = QTrace($format);
578    
579  The parser allows for some escape sequences. See L</UnEscape> for a description. There is no  Return the queued trace data in the specified format.
 support for quote characters.  
580    
581  =over 4  =over 4
582    
583  =item optionTable  =item format
   
 Table of default options.  
   
 =item inputList  
   
 List of words on the command line.  
   
 =item RETURN  
584    
585  Returns a reference to the option table and a list of the positional arguments.  C<html> to format the data as an HTML list, C<text> to format it as straight text.
586    
587  =back  =back
588    
589  =cut  =cut
590    
591  sub ParseCommand {  sub QTrace {
592          # Get the parameters.      # Get the parameter.
593          my ($optionTable, @inputList) = @_;      my ($format) = @_;
594          # Process any options in the input list.      # Create the return variable.
595        my $retVal = "";
596        # Only proceed if there is an actual queue.
597        if (@Queue) {
598            # Process according to the format.
599            if ($format =~ m/^HTML$/i) {
600                # Convert the queue into an HTML list.
601                $retVal = "<ul>\n";
602                for my $line (@Queue) {
603                    my $escapedLine = CGI::escapeHTML($line);
604                    $retVal .= "<li>$escapedLine</li>\n";
605                }
606                $retVal .= "</ul>\n";
607            } elsif ($format =~ m/^TEXT$/i) {
608                # Convert the queue into a list of text lines.
609                $retVal = join("\n", @Queue) . "\n";
610            }
611            # Clear the queue.
612            @Queue = ();
613        }
614        # Return the formatted list.
615        return $retVal;
616    }
617    
618    =head3 Confess
619    
620        Confess($message);
621    
622    Trace the call stack and abort the program with the specified message. When used with
623    the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.
624    So, for example
625    
626        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
627    
628    Will abort the program with a stack trace if the value of C<$recNum> is negative.
629    
630    =over 4
631    
632    =item message
633    
634    Message to include in the trace.
635    
636    =back
637    
638    =cut
639    
640    sub Confess {
641        # Get the parameters.
642        my ($message) = @_;
643        # Set up the category and level.
644        $LastCategory = "(confess)";
645        $LastLevel = 0;
646        if (! defined($FIG_Config::no_tool_hdr)) {
647            # Here we have a tool header. Display its length so that the user can adjust the line numbers.
648            my $toolHeaderFile = "$FIG_Config::fig_disk/dist/releases/current/$FIG_Config::arch/tool_hdr";
649            # Only proceed if the tool header file is actually present.
650            if (-f $toolHeaderFile) {
651                my $fh;
652                if (open $fh, "<$toolHeaderFile") {
653                    my @lines = <$fh>;
654                    Trace("Tool header has " . scalar(@lines) . " lines.");
655                }
656            }
657        }
658        # Trace the call stack.
659        Cluck($message);
660        # Abort the program.
661        croak(">>> $message");
662    }
663    
664    =head3 Warn
665    
666        Warn($message);
667    
668    This method traces an important message. If an RSS feed is configured
669    (via I<FIG_Config::error_feed>) and the tracing destination is C<WARN>,
670    then the message will be echoed to the feed. In general, a tracing
671    destination of C<WARN> indicates that the caller is running as a web
672    service in a production environment; however, this is not a requirement.
673    
674    To force warnings into the RSS feed even when the tracing destination
675    is not C<WARN>, simply specify the C<Feed> tracing module. This can be
676    configured automatically when L</StandardSetup> is used.
677    
678    The L</Cluck> method calls this one for its final message. Since
679    L</Confess> calls L</Cluck>, this means that any error which is caught
680    and confessed will put something in the feed. This insures that someone
681    will be alerted relatively quickly when a failure occurs.
682    
683    =over 4
684    
685    =item message
686    
687    Message to be traced.
688    
689    =back
690    
691    =cut
692    
693    sub Warn {
694        # Get the parameters.
695        my ($message) = @_;
696        # Trace the message.
697        Trace($message);
698        # Check for feed forcing.
699        my $forceFeed = exists $Categories{feed};
700        # An error here would be disastrous. Note, however, that we aren't too worried
701        # about losing events. The error log is always available for the occasions where
702        # we mess up. Note that if debug mode is specified, we do this stuff even in a
703        # test environment.
704        eval {
705            # Do we need to put this in the RSS feed?
706            if ($FIG_Config::error_feed && ($Destination eq 'WARN' || $forceFeed)) {
707                # Yes. We now need to compute the date, the link, and the title.
708                # First, the date, in a very specific format.
709                my $date = strftime("%a, %02e %b %H:%M:%S %Y ", localtime) .
710                    (tz_local_offset() / 30);
711                # Environment data goes in here. We start with the date.
712                my $environment = "$date.  ";
713                # If we need to recap the message (because it's too long to be a title), we'll
714                # put it in here.
715                my $recap;
716                # Copy the message and remove excess space.
717                my $title = $message;
718                $title =~ s/\s+/ /gs;
719                # If it's too long, we have to split it up.
720                if (length $title > 60) {
721                    # Put the full message in the environment string.
722                    $recap = $title;
723                    # Excerpt it as the title.
724                    $title = substr($title, 0, 50) . "...";
725                }
726                # If we have a CGI object, then this is a web error. Otherwise, it's
727                # command-line.
728                if (defined $SavedCGI) {
729                    # We're in a web service. The environment is the user's IP, and the link
730                    # is the URL that got us here.
731                    my $key = $ENV{HTTP_X_FORWARDED_FOR} || $ENV{REMOTE_ADDR};
732                    $environment .= "Event Reported at IP address $key.";
733                    my $url = $SavedCGI->url(-full => 1, -query => 1);
734                    # We need the user agent string and (if available) the referrer.
735                    # The referrer will be the link.
736                    $environment .= "User Agent $ENV{HTTP_USER_AGENT}";
737                    if ($ENV{HTTP_REFERER}) {
738                        my $link = $ENV{HTTP_REFERER};
739                        $environment .= " referred from <a href=\"$link\">$link</a>.";
740                    } else {
741                        $environment .= " referrer unknown.";
742                    }
743                    # Close off the sentence with the original link.
744                    $environment .= " URL of error is <a href=\"$url\">$url</a>.";
745                } else {
746                    # No CGI object, so we're a command-line tool. Use the tracing
747                    # key and the PID as the user identifier, and add the command.
748                    my $key = EmergencyKey();
749                    $environment .= "Event Reported by $key Process $$.";
750                    if ($CommandLine) {
751                        # We're in a StandardSetup script, so we have the real command line.
752                        $environment .= "\n<pre>" . CGI::escapeHTML($CommandLine) . "</pre>\n";
753                    } elsif ($ENV{_}) {
754                        # We're in a BASH script, so the command has been stored in the _ variable.
755                        $environment .= "  Command = " . CGI::escapeHTML($ENV{_}) . "\n";
756                    }
757                }
758                # Build a GUID. We use the current time, the title, and the process ID,
759                # then digest the result.
760                my $guid = Digest::MD5::md5_base64(gettimeofday(), $title, $$);
761                # Finally, the description. This is a stack trace plus various environmental stuff.
762                my $stackTrace = "";
763                my @trace = LongMess();
764                # Only proceed if we got something back.
765                if (scalar(@trace) > 0) {
766                    $trace[0] =~ s/Tracer::Warn.+?called/Event occurred/;
767                    $stackTrace = "Stack trace:<pre>" . join("\n", @trace, "</pre>");
768                }
769                # We got the stack trace. Now it's time to put it all together.
770                # We have a goofy thing here in that we need to HTML-escape some sections of the description
771                # twice. They will be escaped once here, and then once when written by XML::Simple. They are
772                # unescaped once when processed by the RSS reader, and stuff in the description is treated as
773                # HTML. So, anything escaped here is treated as a literal when viewed in the RSS reader, but
774                # our <br>s and <pre>s are used to format the description.
775                $recap = (defined $recap ? "<em>" . CGI::escapeHTML($recap) . "</em><br /><br />" : "");
776                my $description = "$recap$environment  $stackTrace";
777                # Okay, we have all the pieces. Create a hash of the new event.
778                my $newItem = { title => $title,
779                                description => $description,
780                                category => $LastCategory,
781                                pubDate => $date,
782                                guid => $guid,
783                               };
784                # We need XML capability for this.
785                require XML::Simple;
786                # The RSS document goes in here.
787                my $rss;
788                # Get the name of the RSS file. It's in the FIG temporary directory.
789                my $fileName = "$FIG_Config::temp/$FIG_Config::error_feed";
790                # Does it exist?
791                if (-s $fileName) {
792                    # Slurp it in.
793                    $rss = XML::Simple::XMLin($fileName, ForceArray => ['item']);
794                } else {
795                    my $size = -s $fileName;
796                    # Create an empty channel.
797                    $rss = {
798                        channel => {
799                            title => 'NMPDR Warning Feed',
800                            link => "$FIG_Config::temp_url/$FIG_Config::error_feed",
801                            description => "Important messages regarding the status of the NMPDR.",
802                            generator => "NMPDR Trace Facility",
803                            docs => "http://blogs.law.harvard.edu/tech/rss",
804                            item => []
805                        },
806                    };
807                }
808                # Get the channel object.
809                my $channel = $rss->{channel};
810                # Update the last-build date.
811                $channel->{lastBuildDate} = $date;
812                # Get the item array.
813                my $items = $channel->{item};
814                # Insure it has only 100 entries.
815                while (scalar @{$items} > 100) {
816                    pop @{$items};
817                }
818                # Add our new item at the front.
819                unshift @{$items}, $newItem;
820                # Create the XML. Note we do not include the root or the declaration. XML Simple can't handle
821                # the requirements for those.
822                my $xml = XML::Simple::XMLout($rss, NoAttr => 1, RootName => undef, XmlDecl => '');
823                # Here we put in the root and declaration. The problem is that the root has to have the version attribute
824                # in it. So, we suppress the root and do it by hand, and that requires suppressing the declaration, too.
825                $xml = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<rss version=\"2.0\">$xml\n</rss>";
826                # We don't use Open here because we can't afford an error.
827                if (open XMLOUT, ">$fileName") {
828                    print XMLOUT $xml;
829                    close XMLOUT;
830                }
831            }
832        };
833        if ($@) {
834            # If the feed failed, we need to know why. The error will be traced, but this method will not be involved
835            # (which is a good thing).
836            my $error = $@;
837            Trace("Feed Error: $error") if T(Feed => 0);
838        }
839    }
840    
841    =head3 Assert
842    
843        Assert($condition1, $condition2, ... $conditionN);
844    
845    Return TRUE if all the conditions are true. This method can be used in conjunction with
846    the OR operator and the L</Confess> method as a debugging assert.
847    So, for example
848    
849        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
850    
851    Will abort the program with a stack trace if the value of C<$recNum> is negative.
852    
853    =cut
854    sub Assert {
855        my $retVal = 1;
856        LOOP: for my $condition (@_) {
857            if (! $condition) {
858                $retVal = 0;
859                last LOOP;
860            }
861        }
862        return $retVal;
863    }
864    
865    =head3 Cluck
866    
867        Cluck($message);
868    
869    Trace the call stack. Note that for best results, you should qualify the call with a
870    trace condition. For example,
871    
872        Cluck("Starting record parse.") if T(3);
873    
874    will only trace the stack if the trace level for the package is 3 or more.
875    
876    =over 4
877    
878    =item message
879    
880    Message to include in the trace.
881    
882    =back
883    
884    =cut
885    
886    sub Cluck {
887        # Get the parameters.
888        my ($message) = @_;
889        # Trace what's happening.
890        Trace("Stack trace for event: $message");
891        # Get the stack trace.
892        my @trace = LongMess();
893        # Convert the trace to a series of messages.
894        for my $line (@trace) {
895            # Replace the tab at the beginning with spaces.
896            $line =~ s/^\t/    /;
897            # Trace the line.
898            Trace($line);
899        }
900        # Issue a warning. This displays the event message and inserts it into the RSS error feed.
901        Warn($message);
902    }
903    
904    =head3 LongMess
905    
906        my @lines = Tracer::LongMess();
907    
908    Return a stack trace with all tracing methods removed. The return will be in the form of a list
909    of message strings.
910    
911    =cut
912    
913    sub LongMess {
914        # Declare the return variable.
915        my @retVal = ();
916        my $confession = longmess("");
917        for my $line (split /\s*\n/, $confession) {
918            unless ($line =~ /Tracer\.pm/) {
919                # Here we have a line worth keeping. Push it onto the result list.
920                push @retVal, $line;
921            }
922        }
923        # Return the result.
924        return @retVal;
925    }
926    
927    =head3 ScriptSetup (deprecated)
928    
929        my ($cgi, $varHash) = ScriptSetup($noTrace);
930    
931    Perform standard tracing and debugging setup for scripts. The value returned is
932    the CGI object followed by a pre-built variable hash. At the end of the script,
933    the client should call L</ScriptFinish> to output the web page.
934    
935    This method calls L</ETracing> to configure tracing, which allows the tracing
936    to be configured via the emergency tracing form on the debugging control panel.
937    Tracing will then be turned on automatically for all programs that use the L</ETracing>
938    method, which includes every program that uses this method or L</StandardSetup>.
939    
940    =over 4
941    
942    =item noTrace (optional)
943    
944    If specified, tracing will be suppressed. This is useful if the script wants to set up
945    tracing manually.
946    
947    =item RETURN
948    
949    Returns a two-element list consisting of a CGI query object and a variable hash for
950    the output page.
951    
952    =back
953    
954    =cut
955    
956    sub ScriptSetup {
957        # Get the parameters.
958        my ($noTrace) = @_;
959        # Get the CGI query object.
960        my $cgi = CGI->new();
961        # Set up tracing if it's not suppressed.
962        ETracing($cgi) unless $noTrace;
963        # Create the variable hash.
964        my $varHash = { results => '' };
965        # Return the query object and variable hash.
966        return ($cgi, $varHash);
967    }
968    
969    =head3 ETracing
970    
971        ETracing($parameter);
972    
973    Set up emergency tracing. Emergency tracing is tracing that is turned
974    on automatically for any program that calls this method. The emergency
975    tracing parameters are stored in a a file identified by a tracing key.
976    If this method is called with a CGI object, then the tracing key is
977    taken from a cookie. If it is called with no parameters, then the tracing
978    key is taken from an environment variable. If it is called with a string,
979    the tracing key is that string.
980    
981    =over 4
982    
983    =item parameter
984    
985    A parameter from which the tracing key is computed. If it is a scalar,
986    that scalar is used as the tracing key. If it is a CGI object, the
987    tracing key is taken from the C<IP> cookie. If it is omitted, the
988    tracing key is taken from the C<TRACING> environment variable. If it
989    is a CGI object and emergency tracing is not on, the C<Trace> and
990    C<TF> parameters will be used to determine the type of tracing.
991    
992    =back
993    
994    =cut
995    
996    sub ETracing {
997        # Get the parameter.
998        my ($parameter) = @_;
999        # Check for CGI mode.
1000        if (defined $parameter && ref $parameter eq 'CGI') {
1001            $SavedCGI = $parameter;
1002        } else {
1003            $SavedCGI = undef;
1004        }
1005        # Default to no tracing except errors.
1006        my ($tracing, $dest) = ("0", "WARN");
1007        # Check for emergency tracing.
1008        my $tkey = EmergencyKey($parameter);
1009        my $emergencyFile = EmergencyFileName($tkey);
1010        if (-e $emergencyFile) {
1011            # We have the file. Read in the data.
1012            my @tracing = GetFile($emergencyFile);
1013            # Pull off the time limit.
1014            my $expire = shift @tracing;
1015            # Convert it to seconds.
1016            $expire *= 3600;
1017            # Check the file data.
1018            my $stat = stat($emergencyFile);
1019            my ($now) = gettimeofday;
1020            if ($now - $stat->mtime > $expire) {
1021                # Delete the expired file.
1022                unlink $emergencyFile;
1023            } else {
1024                # Emergency tracing is on. Pull off the destination and
1025                # the trace level;
1026                $dest = shift @tracing;
1027                my $level = shift @tracing;
1028                # Convert the destination to a real tracing destination.
1029                # temp directory.
1030                $dest = EmergencyTracingDest($tkey, $dest);
1031                # Insure Tracer is specified.
1032                my %moduleHash = map { $_ => 1 } @tracing;
1033                $moduleHash{Tracer} = 1;
1034                # Set the trace parameter.
1035                $tracing = join(" ", $level, sort keys %moduleHash);
1036            }
1037        } elsif (defined $SavedCGI) {
1038            # There's no emergency tracing, but we have a CGI object, so check
1039            # for tracing from the form parameters.
1040            if ($SavedCGI->param('Trace')) {
1041                # Here the user has requested tracing via a form.
1042                $dest = ($SavedCGI->param('TF') ? ">$FIG_Config::temp/Trace$$.log" : "QUEUE");
1043                $tracing = $SavedCGI->param('Trace') . " Tracer";
1044            }
1045        }
1046        # Setup the tracing we've determined from all the stuff above.
1047        TSetup($tracing, $dest);
1048        # Check to see if we're a web script.
1049        if (defined $SavedCGI) {
1050            # Yes we are. Trace the form and environment data.
1051            TraceParms($SavedCGI);
1052            # Check for RAW mode. In raw mode, we print a fake header so that we see everything
1053            # emitted by the script in its raw form.
1054            if (T(Raw => 3)) {
1055                print CGI::header(-type => 'text/plain', -tracing => 'Raw');
1056            }
1057        }
1058    }
1059    
1060    =head3 EmergencyFileName
1061    
1062        my $fileName = Tracer::EmergencyFileName($tkey);
1063    
1064    Return the emergency tracing file name. This is the file that specifies
1065    the tracing information.
1066    
1067    =over 4
1068    
1069    =item tkey
1070    
1071    Tracing key for the current program.
1072    
1073    =item RETURN
1074    
1075    Returns the name of the file to contain the emergency tracing information.
1076    
1077    =back
1078    
1079    =cut
1080    
1081    sub EmergencyFileName {
1082        # Get the parameters.
1083        my ($tkey) = @_;
1084        # Compute the emergency tracing file name.
1085        return "$FIG_Config::temp/Emergency$tkey.txt";
1086    }
1087    
1088    =head3 EmergencyFileTarget
1089    
1090        my $fileName = Tracer::EmergencyFileTarget($tkey);
1091    
1092    Return the emergency tracing target file name. This is the file that receives
1093    the tracing output for file-based tracing.
1094    
1095    =over 4
1096    
1097    =item tkey
1098    
1099    Tracing key for the current program.
1100    
1101    =item RETURN
1102    
1103    Returns the name of the file to contain the trace output.
1104    
1105    =back
1106    
1107    =cut
1108    
1109    sub EmergencyFileTarget {
1110        # Get the parameters.
1111        my ($tkey) = @_;
1112        # Compute the emergency tracing file name.
1113        return "$FIG_Config::temp/trace$tkey.log";
1114    }
1115    
1116    =head3 EmergencyTracingDest
1117    
1118        my $dest = Tracer::EmergencyTracingDest($tkey, $myDest);
1119    
1120    This method converts an emergency tracing destination to a real
1121    tracing destination. The main difference is that if the
1122    destination is C<FILE> or C<APPEND>, we convert it to file
1123    output. If the destination is C<DUAL>, we convert it to file
1124    and standard output.
1125    
1126    =over 4
1127    
1128    =item tkey
1129    
1130    Tracing key for this environment.
1131    
1132    =item myDest
1133    
1134    Destination from the emergency tracing file.
1135    
1136    =item RETURN
1137    
1138    Returns a destination that can be passed into L</TSetup>.
1139    
1140    =back
1141    
1142    =cut
1143    
1144    sub EmergencyTracingDest {
1145        # Get the parameters.
1146        my ($tkey, $myDest) = @_;
1147        # Declare the return variable.
1148        my $retVal = $myDest;
1149        # Process according to the destination value.
1150        if ($myDest eq 'FILE') {
1151            $retVal = ">" . EmergencyFileTarget($tkey);
1152        } elsif ($myDest eq 'APPEND') {
1153            $retVal = ">>" . EmergencyFileTarget($tkey);
1154        } elsif ($myDest eq 'DUAL') {
1155            $retVal = "+>" . EmergencyFileTarget($tkey);
1156        } elsif ($myDest eq 'WARN') {
1157            $retVal = "WARN";
1158        }
1159        # Return the result.
1160        return $retVal;
1161    }
1162    
1163    =head3 Emergency
1164    
1165        Emergency($key, $hours, $dest, $level, @modules);
1166    
1167    Turn on emergency tracing. This method is normally invoked over the web from
1168    a debugging console, but it can also be called by the C<trace.pl> script.
1169    The caller specifies the duration of the emergency in hours, the desired tracing
1170    destination, the trace level, and a list of the trace modules to activate.
1171    For the length of the duration, when a program in an environment with the
1172    specified tracing key active invokes a Sprout CGI script, tracing will be
1173    turned on automatically. See L</TSetup> for more about tracing setup and
1174    L</ETracing> for more about emergency tracing.
1175    
1176    =over 4
1177    
1178    =item tkey
1179    
1180    The tracing key. This is used to identify the control file and the trace file.
1181    
1182    =item hours
1183    
1184    Number of hours to keep emergency tracing alive.
1185    
1186    =item dest
1187    
1188    Tracing destination. If no path information is specified for a file
1189    destination, it is put in the FIG temporary directory.
1190    
1191    =item level
1192    
1193    Tracing level. A higher level means more trace messages.
1194    
1195    =item modules
1196    
1197    A list of the tracing modules to activate.
1198    
1199    =back
1200    
1201    =cut
1202    
1203    sub Emergency {
1204        # Get the parameters.
1205        my ($tkey, $hours, $dest, $level, @modules) = @_;
1206        # Create the emergency file.
1207        my $specFile = EmergencyFileName($tkey);
1208        my $outHandle = Open(undef, ">$specFile");
1209        print $outHandle join("\n", $hours, $dest, $level, @modules, "");
1210    }
1211    
1212    =head3 EmergencyKey
1213    
1214        my $tkey = EmergencyKey($parameter);
1215    
1216    Return the Key to be used for emergency tracing. This could be an IP address,
1217     a session ID, or a user name, depending on the environment.
1218    
1219    =over 4
1220    
1221    =item parameter
1222    
1223    Parameter defining the method for finding the tracing key. If it is a scalar,
1224    then it is presumed to be the tracing key itself. If it is a CGI object, then
1225    the tracing key is taken from the C<IP> cookie. Otherwise, the tracing key is
1226    taken from the C<TRACING> environment variable.
1227    
1228    =item RETURN
1229    
1230    Returns the key to be used for labels in emergency tracing.
1231    
1232    =back
1233    
1234    =cut
1235    
1236    sub EmergencyKey {
1237        # Get the parameters.
1238        my ($parameter) = @_;
1239        # Declare the return variable.
1240        my $retVal;
1241        # Determine the parameter type.
1242        if (! defined $parameter) {
1243            # Here we're supposed to check the environment. If that fails, we
1244            # get the effective login ID.
1245            $retVal = $ENV{TRACING} || scalar getpwuid($<);
1246        } else {
1247            my $ptype = ref $parameter;
1248            if ($ptype eq 'CGI') {
1249                # Here we were invoked from a web page. Look for a cookie.
1250                $retVal = $parameter->cookie('IP');
1251            } elsif (! $ptype) {
1252                # Here the key was passed in.
1253                $retVal = $parameter;
1254            }
1255        }
1256        # If no luck finding a key, use the PID.
1257        if (! defined $retVal) {
1258            $retVal = $$;
1259        }
1260        # Return the result.
1261        return $retVal;
1262    }
1263    
1264    
1265    =head3 TraceParms
1266    
1267        Tracer::TraceParms($cgi);
1268    
1269    Trace the CGI parameters at trace level CGI => 3 and the environment variables
1270    at level CGI => 4. A self-referencing URL is traced at level CGI => 2.
1271    
1272    =over 4
1273    
1274    =item cgi
1275    
1276    CGI query object containing the parameters to trace.
1277    
1278    =back
1279    
1280    =cut
1281    
1282    sub TraceParms {
1283        # Get the parameters.
1284        my ($cgi) = @_;
1285        if (T(CGI => 2)) {
1286            # Here we trace the GET-style URL for the script.
1287            Trace("[URL] " . $cgi->url(-relative => 1, -query => 1));
1288        }
1289        if (T(CGI => 3)) {
1290            # Here we want to trace the parameter data.
1291            my @names = $cgi->param;
1292            for my $parmName (sort @names) {
1293                # Note we skip the Trace parameters, which are for our use only.
1294                if ($parmName ne 'Trace' && $parmName ne 'TF') {
1295                    my @values = $cgi->param($parmName);
1296                    Trace("[CGI] $parmName = " . join(", ", @values));
1297                }
1298            }
1299            # Display the request method.
1300            my $method = $cgi->request_method();
1301            Trace("Method: $method");
1302        }
1303        if (T(CGI => 4)) {
1304            # Here we want the environment data too.
1305            for my $envName (sort keys %ENV) {
1306                Trace("[ENV] $envName = $ENV{$envName}");
1307            }
1308        }
1309    }
1310    
1311    =head3 TraceImages
1312    
1313        Tracer::TraceImages($htmlString);
1314    
1315    Trace information about all of an html document's images. The tracing
1316    will be for type "IMG" at level 3. The image's source string
1317    will be displayed. This is generally either the URL of the image or
1318    raw data for the image itself. If the source is too long, only the first 300
1319    characters will be shown at trace level 3. The entire source will be shown,
1320    however, at trace level 4. This method is not very smart, and might catch
1321    Javascript code, but it is still useful when debugging the arcane
1322    behavior of images in multiple browser environments.
1323    
1324    =over 4
1325    
1326    =item htmlString
1327    
1328    HTML text for an outgoing web page.
1329    
1330    =back
1331    
1332    =cut
1333    
1334    sub TraceImages {
1335        # Only proceed if we're at the proper trace level.
1336        if (T(IMG => 3)) {
1337            # For performance reasons we're manipulating $_[0] instead of retrieving the string
1338            # into a variable called "$htmlString". This is because we expect html strings to be
1339            # long, and don't want to copy them any more than we have to.
1340            Trace(length($_[0]) . " characters in web page.");
1341            # Loop through the HTML, culling image tags.
1342            while ($_[0] =~ /<img\s+[^>]+?src="([^"]+)"/sgi) {
1343                # Extract the source string and determine whether or not it's too long.
1344                my $srcString = $1;
1345                my $pos = pos($_[0]) - length($srcString);
1346                my $excess = length($srcString) - 300;
1347                # We'll put the display string in here.
1348                my $srcDisplay = $srcString;
1349                # If it's a data string, split it at the comma.
1350                $srcDisplay =~ s/^(data[^,]+,)/$1\n/;
1351                # If there's no excess or we're at trace level 4, we're done. At level 3 with
1352                # a long string, however, we only show the first 300 characters.
1353                if ($excess > 0 && ! T(IMG => 4)) {
1354                    $srcDisplay = substr($srcDisplay,0,300) . "\nplus $excess characters.";
1355                }
1356                # Output the trace message.
1357                Trace("Image tag at position $pos:\n$srcDisplay");
1358            }
1359        }
1360    }
1361    
1362    
1363    =head3 ScriptFinish (deprecated)
1364    
1365        ScriptFinish($webData, $varHash);
1366    
1367    Output a web page at the end of a script. Either the string to be output or the
1368    name of a template file can be specified. If the second parameter is omitted,
1369    it is assumed we have a string to be output; otherwise, it is assumed we have the
1370    name of a template file. The template should have the variable C<DebugData>
1371    specified in any form that invokes a standard script. If debugging mode is turned
1372    on, a form field will be put in that allows the user to enter tracing data.
1373    Trace messages will be placed immediately before the terminal C<BODY> tag in
1374    the output, formatted as a list.
1375    
1376    A typical standard script would loook like the following.
1377    
1378        BEGIN {
1379            # Print the HTML header.
1380            print "CONTENT-TYPE: text/html\n\n";
1381        }
1382        use Tracer;
1383        use CGI;
1384        use FIG;
1385        # ... more uses ...
1386    
1387        my ($cgi, $varHash) = ScriptSetup();
1388        eval {
1389            # ... get data from $cgi, put it in $varHash ...
1390        };
1391        if ($@) {
1392            Trace("Script Error: $@") if T(0);
1393        }
1394        ScriptFinish("Html/MyTemplate.html", $varHash);
1395    
1396    The idea here is that even if the script fails, you'll see trace messages and
1397    useful output.
1398    
1399    =over 4
1400    
1401    =item webData
1402    
1403    A string containing either the full web page to be written to the output or the
1404    name of a template file from which the page is to be constructed. If the name
1405    of a template file is specified, then the second parameter must be present;
1406    otherwise, it must be absent.
1407    
1408    =item varHash (optional)
1409    
1410    If specified, then a reference to a hash mapping variable names for a template
1411    to their values. The template file will be read into memory, and variable markers
1412    will be replaced by data in this hash reference.
1413    
1414    =back
1415    
1416    =cut
1417    
1418    sub ScriptFinish {
1419        # Get the parameters.
1420        my ($webData, $varHash) = @_;
1421        # Check for a template file situation.
1422        my $outputString;
1423        if (defined $varHash) {
1424            # Here we have a template file. We need to determine the template type.
1425            my $template;
1426            if ($FIG_Config::template_url && $webData =~ /\.php$/) {
1427                $template = "$FIG_Config::template_url/$webData";
1428            } else {
1429                $template = "<<$webData";
1430            }
1431            $outputString = PageBuilder::Build($template, $varHash, "Html");
1432        } else {
1433            # Here the user gave us a raw string.
1434            $outputString = $webData;
1435        }
1436        # Check for trace messages.
1437        if ($Destination ne "NONE" && $TraceLevel > 0) {
1438            # We have trace messages, so we want to put them at the end of the body. This
1439            # is either at the end of the whole string or at the beginning of the BODY
1440            # end-tag.
1441            my $pos = length $outputString;
1442            if ($outputString =~ m#</body>#gi) {
1443                $pos = (pos $outputString) - 7;
1444            }
1445            # If the trace messages were queued, we unroll them. Otherwise, we display the
1446            # destination.
1447            my $traceHtml;
1448            if ($Destination eq "QUEUE") {
1449                $traceHtml = QTrace('Html');
1450            } elsif ($Destination =~ /^>>(.+)$/) {
1451                # Here the tracing output it to a file. We code it as a hyperlink so the user
1452                # can copy the file name into the clipboard easily.
1453                my $actualDest = $1;
1454                $traceHtml = "<p>Tracing output to $actualDest.</p>\n";
1455            } else {
1456                # Here we have one of the special destinations.
1457                $traceHtml = "<P>Tracing output type is $Destination.</p>\n";
1458            }
1459            substr $outputString, $pos, 0, $traceHtml;
1460        }
1461        # Write the output string.
1462        print $outputString;
1463    }
1464    
1465    =head2 Command-Line Utility Methods
1466    
1467    =head3 SendSMS
1468    
1469        my $msgID = Tracer::SendSMS($phoneNumber, $msg);
1470    
1471    Send a text message to a phone number using Clickatell. The FIG_Config file must contain the
1472    user name, password, and API ID for the relevant account in the hash reference variable
1473    I<$FIG_Config::phone>, using the keys C<user>, C<password>, and C<api_id>. For
1474    example, if the user name is C<BruceTheHumanPet>, the password is C<silly>, and the API ID
1475    is C<2561022>, then the FIG_Config file must contain
1476    
1477        $phone =  { user => 'BruceTheHumanPet',
1478                    password => 'silly',
1479                    api_id => '2561022' };
1480    
1481    The original purpose of this method was to insure Bruce would be notified immediately when the
1482    Sprout Load terminates. Care should be taken if you do not wish Bruce to be notified immediately
1483    when you call this method.
1484    
1485    The message ID will be returned if successful, and C<undef> if an error occurs.
1486    
1487    =over 4
1488    
1489    =item phoneNumber
1490    
1491    Phone number to receive the message, in international format. A United States phone number
1492    would be prefixed by "1". A British phone number would be prefixed by "44".
1493    
1494    =item msg
1495    
1496    Message to send to the specified phone.
1497    
1498    =item RETURN
1499    
1500    Returns the message ID if successful, and C<undef> if the message could not be sent.
1501    
1502    =back
1503    
1504    =cut
1505    
1506    sub SendSMS {
1507        # Get the parameters.
1508        my ($phoneNumber, $msg) = @_;
1509        # Declare the return variable. If we do not change it, C<undef> will be returned.
1510        my $retVal;
1511        # Only proceed if we have phone support.
1512        if (! defined $FIG_Config::phone) {
1513            Trace("Phone support not present in FIG_Config.") if T(1);
1514        } else {
1515            # Get the phone data.
1516            my $parms = $FIG_Config::phone;
1517            # Get the Clickatell URL.
1518            my $url = "http://api.clickatell.com/http/";
1519            # Create the user agent.
1520            my $ua = LWP::UserAgent->new;
1521            # Request a Clickatell session.
1522            my $resp = $ua->post("$url/sendmsg", { user => $parms->{user},
1523                                         password => $parms->{password},
1524                                         api_id => $parms->{api_id},
1525                                         to => $phoneNumber,
1526                                         text => $msg});
1527            # Check for an error.
1528            if (! $resp->is_success) {
1529                Trace("Alert failed.") if T(1);
1530            } else {
1531                # Get the message ID.
1532                my $rstring = $resp->content;
1533                if ($rstring =~ /^ID:\s+(.*)$/) {
1534                    $retVal = $1;
1535                } else {
1536                    Trace("Phone attempt failed with $rstring") if T(1);
1537                }
1538            }
1539        }
1540        # Return the result.
1541        return $retVal;
1542    }
1543    
1544    =head3 StandardSetup
1545    
1546        my ($options, @parameters) = StandardSetup(\@categories, \%options, $parmHelp, @ARGV);
1547    
1548    This method performs standard command-line parsing and tracing setup. The return
1549    values are a hash of the command-line options and a list of the positional
1550    parameters. Tracing is automatically set up and the command-line options are
1551    validated.
1552    
1553    This is a complex method that does a lot of grunt work. The parameters can
1554    be more easily understood, however, once they are examined individually.
1555    
1556    The I<categories> parameter is the most obtuse. It is a reference to a list of
1557    special-purpose tracing categories. Most tracing categories are PERL package
1558    names. So, for example, if you wanted to turn on tracing inside the B<Sprout>,
1559    B<ERDB>, and B<SproutLoad> packages, you would specify the categories
1560    
1561        ["Sprout", "SproutLoad", "ERDB"]
1562    
1563    This would cause trace messages in the specified three packages to appear in
1564    the output. There are two special tracing categories that are automatically
1565    handled by this method. In other words, if you used L</TSetup> you would need
1566    to include these categories manually, but if you use this method they are turned
1567    on automatically.
1568    
1569    =over 4
1570    
1571    =item SQL
1572    
1573    Traces SQL commands and activity.
1574    
1575    =item Tracer
1576    
1577    Traces error messages and call stacks.
1578    
1579    =back
1580    
1581    C<SQL> is only turned on if the C<-sql> option is specified in the command line.
1582    The trace level is specified using the C<-trace> command-line option. For example,
1583    the following command line for C<TransactFeatures> turns on SQL tracing and runs
1584    all tracing at level 3.
1585    
1586        TransactFeatures -trace=3 -sql register ../xacts IDs.tbl
1587    
1588    Standard tracing is output to the standard output and echoed to the file
1589    C<trace>I<$$>C<.log> in the FIG temporary directory, where I<$$> is the
1590    process ID. You can also specify the C<user> parameter to put a user ID
1591    instead of a process ID in the trace file name. So, for example
1592    
1593    The default trace level is 2. To get all messages, specify a trace level of 4.
1594    For a genome-by-genome update, use 3.
1595    
1596        TransactFeatures -trace=3 -sql -user=Bruce register ../xacts IDs.tbl
1597    
1598    would send the trace output to C<traceBruce.log> in the temporary directory.
1599    
1600    The I<options> parameter is a reference to a hash containing the command-line
1601    options, their default values, and an explanation of what they mean. Command-line
1602    options may be in the form of switches or keywords. In the case of a switch, the
1603    option value is 1 if it is specified and 0 if it is not specified. In the case
1604    of a keyword, the value is separated from the option name by an equal sign. You
1605    can see this last in the command-line example above.
1606    
1607    You can specify a different default trace level by setting C<$options->{trace}>
1608    prior to calling this method.
1609    
1610    An example at this point would help. Consider, for example, the command-line utility
1611    C<TransactFeatures>. It accepts a list of positional parameters plus the options
1612    C<safe>, C<noAlias>, C<start>, and C<tblFiles>. To start up this command, we execute
1613    the following code.
1614    
1615        my ($options, @parameters) = Tracer::StandardSetup(["DocUtils"],
1616                            { safe => [0, "use database transactions"],
1617                              noAlias => [0, "do not expect aliases in CHANGE transactions"],
1618                              start => [' ', "start with this genome"],
1619                              tblFiles => [0, "output TBL files containing the corrected IDs"] },
1620                            "<command> <transactionDirectory> <IDfile>",
1621                          @ARGV);
1622    
1623    
1624    The call to C<ParseCommand> specifies the default values for the options and
1625    stores the actual options in a hash that is returned as C<$options>. The
1626    positional parameters are returned in C<@parameters>.
1627    
1628    The following is a sample command line for C<TransactFeatures>.
1629    
1630        TransactFeatures -trace=2 -noAlias register ../xacts IDs.tbl
1631    
1632    Single and double hyphens are equivalent. So, you could also code the
1633    above command as
1634    
1635        TransactFeatures --trace=2 --noAlias register ../xacts IDs.tbl
1636    
1637    In this case, C<register>, C<../xacts>, and C<IDs.tbl> are the positional
1638    parameters, and would find themselves in I<@parameters> after executing the
1639    above code fragment. The tracing would be set to level 2, and the categories
1640    would be C<Tracer>, and <DocUtils>. C<Tracer> is standard,
1641    and C<DocUtils> was included because it came in within the first parameter
1642    to this method. The I<$options> hash would be
1643    
1644        { trace => 2, sql => 0, safe => 0,
1645          noAlias => 1, start => ' ', tblFiles => 0 }
1646    
1647    Use of C<StandardSetup> in this way provides a simple way of performing
1648    standard tracing setup and command-line parsing. Note that the caller is
1649    not even aware of the command-line switches C<-trace> and C<-sql>, which
1650    are used by this method to control the tracing. If additional tracing features
1651    need to be added in the future, they can be processed by this method without
1652    upsetting the command-line utilities.
1653    
1654    If the C<background> option is specified on the command line, then the
1655    standard and error outputs will be directed to files in the temporary
1656    directory, using the same suffix as the trace file. So, if the command
1657    line specified
1658    
1659        -user=Bruce -background
1660    
1661    then the trace output would go to C<traceBruce.log>, the standard output to
1662    C<outBruce.log>, and the error output to C<errBruce.log>. This is designed to
1663    simplify starting a command in the background.
1664    
1665    The user name is also used as the tracing key for L</Emergency Tracing>.
1666    Specifying a value of C<E> for the trace level causes emergency tracing to
1667    be used instead of custom tracing. If the user name is not specified,
1668    the tracing key is taken from the C<Tracing> environment variable. If there
1669    is no value for that variable, the tracing key will be computed from the active
1670    login ID.
1671    
1672    Since the default situation in StandardSetup is to trace to the standard
1673    output, errors that occur in command-line scripts will not generate
1674    RSS events. To force the events, use the C<warn> option.
1675    
1676        TransactFeatures -background -warn register ../xacts IDs.tbl
1677    
1678    Finally, if the special option C<-help> is specified, the option
1679    names will be traced at level 0 and the program will exit without processing.
1680    This provides a limited help capability. For example, if the user enters
1681    
1682        TransactFeatures -help
1683    
1684    he would see the following output.
1685    
1686        TransactFeatures [options] <command> <transactionDirectory> <IDfile>
1687            -trace    tracing level (default E)
1688            -sql      trace SQL commands
1689            -safe     use database transactions
1690            -noAlias  do not expect aliases in CHANGE transactions
1691            -start    start with this genome
1692            -tblFiles output TBL files containing the corrected IDs
1693    
1694    The caller has the option of modifying the tracing scheme by placing a value
1695    for C<trace> in the incoming options hash. The default value can be overridden,
1696    or the tracing to the standard output can be turned off by suffixing a minus
1697    sign to the trace level. So, for example,
1698    
1699        { trace => [0, "tracing level (default 0)"],
1700           ...
1701    
1702    would set the default trace level to 0 instead of E, while
1703    
1704        { trace => ["2-", "tracing level (default 2)"],
1705           ...
1706    
1707    would set the default to 2, but trace only to the log file, not to the
1708    standard output.
1709    
1710    The parameters to this method are as follows.
1711    
1712    =over 4
1713    
1714    =item categories
1715    
1716    Reference to a list of tracing category names. These should be names of
1717    packages whose internal workings will need to be debugged to get the
1718    command working.
1719    
1720    =item options
1721    
1722    Reference to a hash containing the legal options for the current command mapped
1723    to their default values and descriptions. The user can override the defaults
1724    by specifying the options as command-line switches prefixed by a hyphen.
1725    Tracing-related options may be added to this hash. If the C<-h> option is
1726    specified on the command line, the option descriptions will be used to
1727    explain the options. To turn off tracing to the standard output, add a
1728    minus sign to the value for C<trace> (see above).
1729    
1730    =item parmHelp
1731    
1732    A string that vaguely describes the positional parameters. This is used
1733    if the user specifies the C<-h> option.
1734    
1735    =item argv
1736    
1737    List of command line parameters, including the option switches, which must
1738    precede the positional parameters and be prefixed by a hyphen.
1739    
1740    =item RETURN
1741    
1742    Returns a list. The first element of the list is the reference to a hash that
1743    maps the command-line option switches to their values. These will either be the
1744    default values or overrides specified on the command line. The remaining
1745    elements of the list are the position parameters, in order.
1746    
1747    =back
1748    
1749    =cut
1750    
1751    sub StandardSetup {
1752        # Get the parameters.
1753        my ($categories, $options, $parmHelp, @argv) = @_;
1754        # Get the default tracing key.
1755        my $tkey = EmergencyKey();
1756        # Save the command line.
1757        $CommandLine = join(" ", $0, map { $_ =~ /\s/ ? "\"$_\"" : $_ } @argv);
1758        # Add the tracing options.
1759        if (! exists $options->{trace}) {
1760            $options->{trace} = ['2', "tracing level (E for emergency tracing)"];
1761        }
1762        $options->{sql} = [0, "turn on SQL tracing"];
1763        $options->{help} = [0, "display command-line options"];
1764        $options->{user} = [$tkey, "tracing key"];
1765        $options->{background} = [0, "spool standard and error output"];
1766        $options->{warn} = [0, "send errors to RSS feed"];
1767        # Create a parsing hash from the options hash. The parsing hash
1768        # contains the default values rather than the default value
1769        # and the description. While we're at it, we'll memorize the
1770        # length of the longest option name.
1771        my $longestName = 0;
1772        my %parseOptions = ();
1773        for my $key (keys %{$options}) {
1774            if (length $key > $longestName) {
1775                $longestName = length $key;
1776            }
1777            $parseOptions{$key} = $options->{$key}->[0];
1778        }
1779        # Parse the command line.
1780        my ($retOptions, @retParameters) = ParseCommand(\%parseOptions, @argv);
1781        # Get the logfile suffix.
1782        my $suffix = $retOptions->{user};
1783        # Check for background mode.
1784        if ($retOptions->{background}) {
1785            my $outFileName = "$FIG_Config::temp/out$suffix.log";
1786            my $errFileName = "$FIG_Config::temp/err$suffix.log";
1787            open STDOUT, ">$outFileName";
1788            open STDERR, ">$errFileName";
1789            # Check for phone support. If we have phone support and a phone number,
1790            # we want to turn it on.
1791            if ($ENV{PHONE} && defined($FIG_Config::phone)) {
1792                $retOptions->{phone} = $ENV{PHONE};
1793            }
1794        }
1795        # Now we want to set up tracing. First, we need to know if the user
1796        # wants emergency tracing.
1797        if ($retOptions->{trace} eq 'E') {
1798            ETracing($retOptions->{user});
1799        } else {
1800            # Here the tracing is controlled from the command line.
1801            my @cats = @{$categories};
1802            if ($retOptions->{sql}) {
1803                push @cats, "SQL";
1804            }
1805            if ($retOptions->{warn}) {
1806                push @cats, "Feed";
1807            }
1808            # Add the default categories.
1809            push @cats, "Tracer";
1810            # Next, we create the category string by joining the categories.
1811            my $cats = join(" ", @cats);
1812            # Check to determine whether or not the caller wants to turn off tracing
1813            # to the standard output.
1814            my $traceLevel = $retOptions->{trace};
1815            my $textOKFlag = 1;
1816            if ($traceLevel =~ /^(.)-/) {
1817                $traceLevel = $1;
1818                $textOKFlag = 0;
1819            }
1820            # Now we set up the trace mode.
1821            my $traceMode;
1822            # Verify that we can open a file in the FIG temporary directory.
1823            my $traceFileName = "$FIG_Config::temp/trace$suffix.log";
1824            if (open TESTTRACE, ">$traceFileName") {
1825                # Here we can trace to a file.
1826                $traceMode = ">$traceFileName";
1827                if ($textOKFlag) {
1828                    # Echo to standard output if the text-OK flag is set.
1829                    $traceMode = "+$traceMode";
1830                }
1831                # Close the test file.
1832                close TESTTRACE;
1833            } else {
1834                # Here we can't trace to a file. Complain about this.
1835                warn "Could not open trace file $traceFileName: $!\n";
1836                # We trace to the standard output if it's
1837                # okay, and the error log otherwise.
1838                if ($textOKFlag) {
1839                    $traceMode = "TEXT";
1840                } else {
1841                    $traceMode = "WARN";
1842                }
1843            }
1844            # Now set up the tracing.
1845            TSetup("$traceLevel $cats", $traceMode);
1846        }
1847        # Check for the "help" option. If it is specified, dump the command-line
1848        # options and exit the program.
1849        if ($retOptions->{help}) {
1850            $0 =~ m#[/\\](\w+)(\.pl)?$#i;
1851            print "$1 [options] $parmHelp\n";
1852            for my $key (sort keys %{$options}) {
1853                my $name = Pad($key, $longestName, 0, ' ');
1854                my $desc = $options->{$key}->[1];
1855                if ($options->{$key}->[0]) {
1856                    $desc .= " (default " . $options->{$key}->[0] . ")";
1857                }
1858                print "  $name $desc\n";
1859            }
1860            exit(0);
1861        }
1862        # Trace the options, if applicable.
1863        if (T(3)) {
1864            my @parms = grep { $retOptions->{$_} } keys %{$retOptions};
1865            Trace("Selected options: " . join(", ", sort @parms) . ".");
1866        }
1867        # Return the parsed parameters.
1868        return ($retOptions, @retParameters);
1869    }
1870    
1871    =head3 ReadOptions
1872    
1873        my %options = Tracer::ReadOptions($fileName);
1874    
1875    Read a set of options from a file. Each option is encoded in a line of text that has the
1876    format
1877    
1878    I<optionName>C<=>I<optionValue>C<; >I<comment>
1879    
1880    The option name must consist entirely of letters, digits, and the punctuation characters
1881    C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank
1882    character is a semi-colon will be ignored. The return hash will map each option name to
1883    the corresponding option value.
1884    
1885    =over 4
1886    
1887    =item fileName
1888    
1889    Name of the file containing the option data.
1890    
1891    =item RETURN
1892    
1893    Returns a hash mapping the option names specified in the file to their corresponding option
1894    value.
1895    
1896    =back
1897    
1898    =cut
1899    
1900    sub ReadOptions {
1901        # Get the parameters.
1902        my ($fileName) = @_;
1903        # Open the file.
1904        (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");
1905        # Count the number of records read.
1906        my ($records, $comments) = 0;
1907        # Create the return hash.
1908        my %retVal = ();
1909        # Loop through the file, accumulating key-value pairs.
1910        while (my $line = <CONFIGFILE>) {
1911            # Denote we've read a line.
1912            $records++;
1913            # Determine the line type.
1914            if ($line =~ /^\s*[\n\r]/) {
1915                # A blank line is a comment.
1916                $comments++;
1917            } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {
1918                # Here we have an option assignment.
1919                retVal{$1} = $2;
1920            } elsif ($line =~ /^\s*;/) {
1921                # Here we have a text comment.
1922                $comments++;
1923            } else {
1924                # Here we have an invalid line.
1925                Trace("Invalid option statement in record $records.") if T(0);
1926            }
1927        }
1928        # Return the hash created.
1929        return %retVal;
1930    }
1931    
1932    =head3 GetOptions
1933    
1934        Tracer::GetOptions(\%defaults, \%options);
1935    
1936    Merge a specified set of options into a table of defaults. This method takes two hash references
1937    as input and uses the data from the second to update the first. If the second does not exist,
1938    there will be no effect. An error will be thrown if one of the entries in the second hash does not
1939    exist in the first.
1940    
1941    Consider the following example.
1942    
1943        my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options);
1944    
1945    In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and
1946    B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of
1947    B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and
1948    the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level
1949    will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as
1950    
1951        {databaseType => 'Oracle'}
1952    
1953    an error will occur because the B<databaseType> option does not exist.
1954    
1955    =over 4
1956    
1957    =item defaults
1958    
1959    Table of default option values.
1960    
1961    =item options
1962    
1963    Table of overrides, if any.
1964    
1965    =item RETURN
1966    
1967    Returns a reference to the default table passed in as the first parameter.
1968    
1969    =back
1970    
1971    =cut
1972    
1973    sub GetOptions {
1974        # Get the parameters.
1975        my ($defaults, $options) = @_;
1976        # Check for overrides.
1977        if ($options) {
1978            # Loop through the overrides.
1979            while (my ($option, $setting) = each %{$options}) {
1980                # Insure this override exists.
1981                if (!exists $defaults->{$option}) {
1982                    croak "Unrecognized option $option encountered.";
1983                } else {
1984                    # Apply the override.
1985                    $defaults->{$option} = $setting;
1986                }
1987            }
1988        }
1989        # Return the merged table.
1990        return $defaults;
1991    }
1992    
1993    =head3 MergeOptions
1994    
1995        Tracer::MergeOptions(\%table, \%defaults);
1996    
1997    Merge default values into a hash table. This method looks at the key-value pairs in the
1998    second (default) hash, and if a matching key is not found in the first hash, the default
1999    pair is copied in. The process is similar to L</GetOptions>, but there is no error-
2000    checking and no return value.
2001    
2002    =over 4
2003    
2004    =item table
2005    
2006    Hash table to be updated with the default values.
2007    
2008    =item defaults
2009    
2010    Default values to be merged into the first hash table if they are not already present.
2011    
2012    =back
2013    
2014    =cut
2015    
2016    sub MergeOptions {
2017        # Get the parameters.
2018        my ($table, $defaults) = @_;
2019        # Loop through the defaults.
2020        while (my ($key, $value) = each %{$defaults}) {
2021            if (!exists $table->{$key}) {
2022                $table->{$key} = $value;
2023            }
2024        }
2025    }
2026    
2027    =head3 ParseCommand
2028    
2029        my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList);
2030    
2031    Parse a command line consisting of a list of parameters. The initial parameters may be option
2032    specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped
2033    off and merged into a table of default options. The remainder of the command line is
2034    returned as a list of positional arguments. For example, consider the following invocation.
2035    
2036        my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words);
2037    
2038    In this case, the list @words will be treated as a command line and there are two options available,
2039    B<errors> and B<logFile>. If @words has the following format
2040    
2041        -logFile=error.log apple orange rutabaga
2042    
2043    then at the end of the invocation, C<$options> will be
2044    
2045        { errors => 0, logFile => 'error.log' }
2046    
2047    and C<@arguments> will contain
2048    
2049        apple orange rutabaga
2050    
2051    The parser allows for some escape sequences. See L</UnEscape> for a description. There is no
2052    support for quote characters. Options can be specified with single or double hyphens.
2053    
2054    =over 4
2055    
2056    =item optionTable
2057    
2058    Table of default options.
2059    
2060    =item inputList
2061    
2062    List of words on the command line.
2063    
2064    =item RETURN
2065    
2066    Returns a reference to the option table and a list of the positional arguments.
2067    
2068    =back
2069    
2070    =cut
2071    
2072    sub ParseCommand {
2073        # Get the parameters.
2074        my ($optionTable, @inputList) = @_;
2075        # Process any options in the input list.
2076          my %overrides = ();          my %overrides = ();
2077          while ((@inputList > 0) && ($inputList[0] =~ /^-/)) {      while ((@inputList > 0) && ($inputList[0] =~ /^--?/)) {
2078                  # Get the current option.                  # Get the current option.
2079                  my $arg = shift @inputList;                  my $arg = shift @inputList;
2080                  # Pull out the option name.                  # Pull out the option name.
2081                  $arg =~ /^-([^=]*)/g;          $arg =~ /^--?([^=]*)/g;
2082                  my $name = $1;                  my $name = $1;
2083                  # Check for an option value.                  # Check for an option value.
2084                  if ($arg =~ /\G=(.*)$/g) {                  if ($arg =~ /\G=(.*)$/g) {
2085                          # Here we have a value for the option.                          # Here we have a value for the option.
2086                          $overrides{$name} = UnEscape($1);                          $overrides{$name} = UnEscape($1);
2087                  } else {                  } else {
2088                          # Here there is no value, so we use 1.              # Here there is no value, so we use 1.
2089                          $overrides{$name} = 1;              $overrides{$name} = 1;
2090            }
2091        }
2092        # Merge the options into the defaults.
2093        GetOptions($optionTable, \%overrides);
2094        # Translate the remaining parameters.
2095        my @retVal = ();
2096        for my $inputParm (@inputList) {
2097            push @retVal, UnEscape($inputParm);
2098        }
2099        # Return the results.
2100        return ($optionTable, @retVal);
2101    }
2102    
2103    
2104    =head2 File Utility Methods
2105    
2106    =head3 GetFile
2107    
2108        my @fileContents = Tracer::GetFile($fileName);
2109    
2110        or
2111    
2112        my $fileContents = Tracer::GetFile($fileName);
2113    
2114    Return the entire contents of a file. In list context, line-ends are removed and
2115    each line is a list element. In scalar context, line-ends are replaced by C<\n>.
2116    
2117    =over 4
2118    
2119    =item fileName
2120    
2121    Name of the file to read.
2122    
2123    =item RETURN
2124    
2125    In a list context, returns the entire file as a list with the line terminators removed.
2126    In a scalar context, returns the entire file as a string. If an error occurs opening
2127    the file, an empty list will be returned.
2128    
2129    =back
2130    
2131    =cut
2132    
2133    sub GetFile {
2134        # Get the parameters.
2135        my ($fileName) = @_;
2136        # Declare the return variable.
2137        my @retVal = ();
2138        # Open the file for input.
2139        my $handle = Open(undef, "<$fileName");
2140        # Read the whole file into the return variable, stripping off any terminator
2141        # characters.
2142        my $lineCount = 0;
2143        while (my $line = <$handle>) {
2144            $lineCount++;
2145            $line = Strip($line);
2146            push @retVal, $line;
2147        }
2148        # Close it.
2149        close $handle;
2150        my $actualLines = @retVal;
2151        Trace("$actualLines lines read from file $fileName.") if T(File => 2);
2152        # Return the file's contents in the desired format.
2153        if (wantarray) {
2154            return @retVal;
2155        } else {
2156            return join "\n", @retVal;
2157        }
2158    }
2159    
2160    =head3 PutFile
2161    
2162        Tracer::PutFile($fileName, \@lines);
2163    
2164    Write out a file from a list of lines of text.
2165    
2166    =over 4
2167    
2168    =item fileName
2169    
2170    Name of the output file.
2171    
2172    =item lines
2173    
2174    Reference to a list of text lines. The lines will be written to the file in order, with trailing
2175    new-line characters. Alternatively, may be a string, in which case the string will be written without
2176    modification.
2177    
2178    =back
2179    
2180    =cut
2181    
2182    sub PutFile {
2183        # Get the parameters.
2184        my ($fileName, $lines) = @_;
2185        # Open the output file.
2186        my $handle = Open(undef, ">$fileName");
2187        # Count the lines written.
2188        if (ref $lines ne 'ARRAY') {
2189            # Here we have a scalar, so we write it raw.
2190            print $handle $lines;
2191            Trace("Scalar put to file $fileName.") if T(File => 3);
2192        } else {
2193            # Write the lines one at a time.
2194            my $count = 0;
2195            for my $line (@{$lines}) {
2196                print $handle "$line\n";
2197                $count++;
2198            }
2199            Trace("$count lines put to file $fileName.") if T(File => 3);
2200        }
2201        # Close the output file.
2202        close $handle;
2203    }
2204    
2205    =head3 ParseRecord
2206    
2207        my @fields = Tracer::ParseRecord($line);
2208    
2209    Parse a tab-delimited data line. The data line is split into field values. Embedded tab
2210    and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.
2211    These will automatically be converted.
2212    
2213    =over 4
2214    
2215    =item line
2216    
2217    Line of data containing the tab-delimited fields.
2218    
2219    =item RETURN
2220    
2221    Returns a list of the fields found in the data line.
2222    
2223    =back
2224    
2225    =cut
2226    
2227    sub ParseRecord {
2228        # Get the parameter.
2229        my ($line) = @_;
2230        # Remove the trailing new-line, if any.
2231        chomp $line;
2232        # Split the line read into pieces using the tab character.
2233        my @retVal = split /\t/, $line;
2234        # Trim and fix the escapes in each piece.
2235        for my $value (@retVal) {
2236            # Trim leading whitespace.
2237            $value =~ s/^\s+//;
2238            # Trim trailing whitespace.
2239            $value =~ s/\s+$//;
2240            # Delete the carriage returns.
2241            $value =~ s/\r//g;
2242            # Convert the escapes into their real values.
2243            $value =~ s/\\t/"\t"/ge;
2244            $value =~ s/\\n/"\n"/ge;
2245        }
2246        # Return the result.
2247        return @retVal;
2248    }
2249    
2250    =head3 Merge
2251    
2252        my @mergedList = Tracer::Merge(@inputList);
2253    
2254    Sort a list of strings and remove duplicates.
2255    
2256    =over 4
2257    
2258    =item inputList
2259    
2260    List of scalars to sort and merge.
2261    
2262    =item RETURN
2263    
2264    Returns a list containing the same elements sorted in ascending order with duplicates
2265    removed.
2266    
2267    =back
2268    
2269    =cut
2270    
2271    sub Merge {
2272        # Get the input list in sort order.
2273        my @inputList = sort @_;
2274        # Only proceed if the list has at least two elements.
2275        if (@inputList > 1) {
2276            # Now we want to move through the list splicing out duplicates.
2277            my $i = 0;
2278            while ($i < @inputList) {
2279                # Get the current entry.
2280                my $thisEntry = $inputList[$i];
2281                # Find out how many elements duplicate the current entry.
2282                my $j = $i + 1;
2283                my $dup1 = $i + 1;
2284                while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };
2285                # If the number is nonzero, splice out the duplicates found.
2286                if ($j > $dup1) {
2287                    splice @inputList, $dup1, $j - $dup1;
2288                }
2289                # Now the element at position $dup1 is different from the element before it
2290                # at position $i. We push $i forward one position and start again.
2291                $i++;
2292            }
2293        }
2294        # Return the merged list.
2295        return @inputList;
2296    }
2297    
2298    =head3 Open
2299    
2300        my $handle = Open($fileHandle, $fileSpec, $message);
2301    
2302    Open a file.
2303    
2304    The I<$fileSpec> is essentially the second argument of the PERL C<open>
2305    function. The mode is specified using Unix-like shell information. So, for
2306    example,
2307    
2308        Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2309    
2310    would open for output appended to the specified file, and
2311    
2312        Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");
2313    
2314    would open a pipe that sorts the records written and removes duplicates. Note
2315    the use of file handle syntax in the Open call. To use anonymous file handles,
2316    code as follows.
2317    
2318        my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2319    
2320    The I<$message> parameter is used if the open fails. If it is set to C<0>, then
2321    the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a
2322    failed open will throw an exception and the third parameter will be used to construct
2323    an error message. If the parameter is omitted, a standard message is constructed
2324    using the file spec.
2325    
2326        Could not open "/usr/spool/news/twitlog"
2327    
2328    Note that the mode characters are automatically cleaned from the file name.
2329    The actual error message from the file system will be captured and appended to the
2330    message in any case.
2331    
2332        Could not open "/usr/spool/news/twitlog": file not found.
2333    
2334    In some versions of PERL the only error message we get is a number, which
2335    corresponds to the C++ C<errno> value.
2336    
2337        Could not open "/usr/spool/news/twitlog": 6.
2338    
2339    =over 4
2340    
2341    =item fileHandle
2342    
2343    File handle. If this parameter is C<undef>, a file handle will be generated
2344    and returned as the value of this method.
2345    
2346    =item fileSpec
2347    
2348    File name and mode, as per the PERL C<open> function.
2349    
2350    =item message (optional)
2351    
2352    Error message to use if the open fails. If omitted, a standard error message
2353    will be generated. In either case, the error information from the file system
2354    is appended to the message. To specify a conditional open that does not throw
2355    an error if it fails, use C<0>.
2356    
2357    =item RETURN
2358    
2359    Returns the name of the file handle assigned to the file, or C<undef> if the
2360    open failed.
2361    
2362    =back
2363    
2364    =cut
2365    
2366    sub Open {
2367        # Get the parameters.
2368        my ($fileHandle, $fileSpec, $message) = @_;
2369        # Attempt to open the file.
2370        my $rv = open $fileHandle, $fileSpec;
2371        # If the open failed, generate an error message.
2372        if (! $rv) {
2373            # Save the system error message.
2374            my $sysMessage = $!;
2375            # See if we need a default message.
2376            if (!$message) {
2377                # Clean any obvious mode characters and leading spaces from the
2378                # filename.
2379                my ($fileName) = FindNamePart($fileSpec);
2380                $message = "Could not open \"$fileName\"";
2381            }
2382            # Terminate with an error using the supplied message and the
2383            # error message from the file system.
2384            Confess("$message: $!");
2385        }
2386        # Return the file handle.
2387        return $fileHandle;
2388    }
2389    
2390    =head3 FindNamePart
2391    
2392        my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec);
2393    
2394    Extract the portion of a file specification that contains the file name.
2395    
2396    A file specification is the string passed to an C<open> call. It specifies the file
2397    mode and name. In a truly complex situation, it can specify a pipe sequence. This
2398    method assumes that the file name is whatever follows the first angle bracket
2399    sequence.  So, for example, in the following strings the file name is
2400    C</usr/fig/myfile.txt>.
2401    
2402        >>/usr/fig/myfile.txt
2403        </usr/fig/myfile.txt
2404        | sort -u > /usr/fig/myfile.txt
2405    
2406    If the method cannot find a file name using its normal methods, it will return the
2407    whole incoming string.
2408    
2409    =over 4
2410    
2411    =item fileSpec
2412    
2413    File specification string from which the file name is to be extracted.
2414    
2415    =item RETURN
2416    
2417    Returns a three-element list. The first element contains the file name portion of
2418    the specified string, or the whole string if a file name cannot be found via normal
2419    methods. The second element contains the start position of the file name portion and
2420    the third element contains the length.
2421    
2422    =back
2423    
2424    =cut
2425    #: Return Type $;
2426    sub FindNamePart {
2427        # Get the parameters.
2428        my ($fileSpec) = @_;
2429        # Default to the whole input string.
2430        my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);
2431        # Parse out the file name if we can.
2432        if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {
2433            $retVal = $2;
2434            $len = length $retVal;
2435            $pos = (length $fileSpec) - (length $3) - $len;
2436        }
2437        # Return the result.
2438        return ($retVal, $pos, $len);
2439    }
2440    
2441    =head3 OpenDir
2442    
2443        my @files = OpenDir($dirName, $filtered, $flag);
2444    
2445    Open a directory and return all the file names. This function essentially performs
2446    the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is
2447    set to TRUE, all filenames beginning with a period (C<.>), dollar sign (C<$>),
2448    or pound sign (C<#>) and all filenames ending with a tilde C<~>) will be
2449    filtered out of the return list. If the directory does not open and I<$flag> is not
2450    set, an exception is thrown. So, for example,
2451    
2452        my @files = OpenDir("/Volumes/fig/contigs", 1);
2453    
2454    is effectively the same as
2455    
2456        opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");
2457        my @files = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir(TMP);
2458    
2459    Similarly, the following code
2460    
2461        my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs", 0, 1);
2462    
2463    Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and
2464    automatically returns an empty list if the directory fails to open.
2465    
2466    =over 4
2467    
2468    =item dirName
2469    
2470    Name of the directory to open.
2471    
2472    =item filtered
2473    
2474    TRUE if files whose names begin with a period (C<.>) should be automatically removed
2475    from the list, else FALSE.
2476    
2477    =item flag
2478    
2479    TRUE if a failure to open is okay, else FALSE
2480    
2481    =back
2482    
2483    =cut
2484    #: Return Type @;
2485    sub OpenDir {
2486        # Get the parameters.
2487        my ($dirName, $filtered, $flag) = @_;
2488        # Declare the return variable.
2489        my @retVal = ();
2490        # Open the directory.
2491        if (opendir(my $dirHandle, $dirName)) {
2492            # The directory opened successfully. Get the appropriate list according to the
2493            # strictures of the filter parameter.
2494            if ($filtered) {
2495                @retVal = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir $dirHandle;
2496            } else {
2497                @retVal = readdir $dirHandle;
2498            }
2499        } elsif (! $flag) {
2500            # Here the directory would not open and it's considered an error.
2501            Confess("Could not open directory $dirName.");
2502        }
2503        # Return the result.
2504        return @retVal;
2505    }
2506    
2507    
2508    =head3 Insure
2509    
2510        Insure($dirName, $chmod);
2511    
2512    Insure a directory is present.
2513    
2514    =over 4
2515    
2516    =item dirName
2517    
2518    Name of the directory to check. If it does not exist, it will be created.
2519    
2520    =item chmod (optional)
2521    
2522    Security privileges to be given to the directory if it is created.
2523    
2524    =back
2525    
2526    =cut
2527    
2528    sub Insure {
2529        my ($dirName, $chmod) = @_;
2530        if (! -d $dirName) {
2531            Trace("Creating $dirName directory.") if T(2);
2532            eval {
2533                mkpath $dirName;
2534                # If we have permissions specified, set them here.
2535                if (defined($chmod)) {
2536                    chmod $chmod, $dirName;
2537                }
2538            };
2539            if ($@) {
2540                Confess("Error creating $dirName: $@");
2541            }
2542        }
2543    }
2544    
2545    =head3 ChDir
2546    
2547        ChDir($dirName);
2548    
2549    Change to the specified directory.
2550    
2551    =over 4
2552    
2553    =item dirName
2554    
2555    Name of the directory to which we want to change.
2556    
2557    =back
2558    
2559    =cut
2560    
2561    sub ChDir {
2562        my ($dirName) = @_;
2563        if (! -d $dirName) {
2564            Confess("Cannot change to directory $dirName: no such directory.");
2565        } else {
2566            Trace("Changing to directory $dirName.") if T(File => 4);
2567            my $okFlag = chdir $dirName;
2568            if (! $okFlag) {
2569                Confess("Error switching to directory $dirName.");
2570            }
2571        }
2572    }
2573    
2574    =head3 SetPermissions
2575    
2576        Tracer::SetPermissions($dirName, $group, $mask, %otherMasks);
2577    
2578    Set the permissions for a directory and all the files and folders inside it.
2579    In addition, the group ownership will be changed to the specified value.
2580    
2581    This method is more vulnerable than most to permission and compatability
2582    problems, so it does internal error recovery.
2583    
2584    =over 4
2585    
2586    =item dirName
2587    
2588    Name of the directory to process.
2589    
2590    =item group
2591    
2592    Name of the group to be assigned.
2593    
2594    =item mask
2595    
2596    Permission mask. Bits that are C<1> in this mask will be ORed into the
2597    permission bits of any file or directory that does not already have them
2598    set to 1.
2599    
2600    =item otherMasks
2601    
2602    Map of search patterns to permission masks. If a directory name matches
2603    one of the patterns, that directory and all its members and subdirectories
2604    will be assigned the new pattern. For example, the following would
2605    assign 01664 to most files, but would use 01777 for directories named C<tmp>.
2606    
2607        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp$' => 01777);
2608    
2609    The list is ordered, so the following would use 0777 for C<tmp1> and
2610    0666 for C<tmp>, C<tmp2>, or C<tmp3>.
2611    
2612        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp1' => 0777,
2613                                                       '^tmp' => 0666);
2614    
2615    Note that the pattern matches are all case-insensitive, and only directory
2616    names are matched, not file names.
2617    
2618    =back
2619    
2620    =cut
2621    
2622    sub SetPermissions {
2623        # Get the parameters.
2624        my ($dirName, $group, $mask, @otherMasks) = @_;
2625        # Set up for error recovery.
2626        eval {
2627            # Switch to the specified directory.
2628            ChDir($dirName);
2629            # Get the group ID.
2630            my $gid = getgrnam($group);
2631            # Get the mask for tracing.
2632            my $traceMask = sprintf("%04o", $mask) . "($mask)";
2633            Trace("Fixing permissions for directory $dirName using group $group($gid) and mask $traceMask.") if T(File => 2);
2634            my $fixCount = 0;
2635            my $lookCount = 0;
2636            # @dirs will be a stack of directories to be processed.
2637            my @dirs = (getcwd());
2638            while (scalar(@dirs) > 0) {
2639                # Get the current directory.
2640                my $dir = pop @dirs;
2641                # Check for a match to one of the specified directory names. To do
2642                # that, we need to pull the individual part of the name off of the
2643                # whole path.
2644                my $simpleName = $dir;
2645                if ($dir =~ m!/([^/]+)$!) {
2646                    $simpleName = $1;
2647                }
2648                Trace("Simple directory name for $dir is $simpleName.") if T(File => 4);
2649                # Search for a match.
2650                my $match = 0;
2651                my $i;
2652                for ($i = 0; $i < $#otherMasks && ! $match; $i += 2) {
2653                    my $pattern = $otherMasks[$i];
2654                    if ($simpleName =~ /$pattern/i) {
2655                        $match = 1;
2656                    }
2657                }
2658                # Check for a match. Note we use $i-1 because the loop added 2
2659                # before terminating due to the match.
2660                if ($match && $otherMasks[$i-1] != $mask) {
2661                    # This directory matches one of the incoming patterns, and it's
2662                    # a different mask, so we process it recursively with that mask.
2663                    SetPermissions($dir, $group, $otherMasks[$i-1], @otherMasks);
2664                } else {
2665                    # Here we can process normally. Get all of the non-hidden members.
2666                    my @submems = OpenDir($dir, 1);
2667                    for my $submem (@submems) {
2668                        # Get the full name.
2669                        my $thisMem = "$dir/$submem";
2670                        Trace("Checking member $thisMem.") if T(4);
2671                        $lookCount++;
2672                        if ($lookCount % 1000 == 0) {
2673                            Trace("$lookCount members examined. Current is $thisMem. Mask is $traceMask") if T(File => 3);
2674                        }
2675                        # Fix the group.
2676                        chown -1, $gid, $thisMem;
2677                        # Insure this member is not a symlink.
2678                        if (! -l $thisMem) {
2679                            # Get its info.
2680                            my $fileInfo = stat $thisMem;
2681                            # Only proceed if we got the info. Otherwise, it's a hard link
2682                            # and we want to skip it anyway.
2683                            if ($fileInfo) {
2684                                my $fileMode = $fileInfo->mode;
2685                                if (($fileMode & $mask) != $mask) {
2686                                    # Fix this member.
2687                                    $fileMode |= $mask;
2688                                    chmod $fileMode, $thisMem;
2689                                    $fixCount++;
2690                                }
2691                                # If it's a subdirectory, stack it.
2692                                if (-d $thisMem) {
2693                                    push @dirs, $thisMem;
2694                                }
2695                            }
2696                        }
2697                    }
2698                }
2699            }
2700            Trace("$lookCount files and directories processed, $fixCount fixed.") if T(File => 2);
2701        };
2702        # Check for an error.
2703        if ($@) {
2704            Confess("SetPermissions error: $@");
2705                  }                  }
2706          }          }
2707          # Merge the options into the defaults.  
2708          GetOptions($optionTable, \%overrides);  =head3 GetLine
2709          # Translate the remaining parameters.  
2710        my @data = Tracer::GetLine($handle);
2711    
2712    Read a line of data from a tab-delimited file.
2713    
2714    =over 4
2715    
2716    =item handle
2717    
2718    Open file handle from which to read.
2719    
2720    =item RETURN
2721    
2722    Returns a list of the fields in the record read. The fields are presumed to be
2723    tab-delimited. If we are at the end of the file, then an empty list will be
2724    returned. If an empty line is read, a single list item consisting of a null
2725    string will be returned.
2726    
2727    =back
2728    
2729    =cut
2730    
2731    sub GetLine {
2732        # Get the parameters.
2733        my ($handle) = @_;
2734        # Declare the return variable.
2735          my @retVal = ();          my @retVal = ();
2736          for my $inputParm (@inputList) {      Trace("File position is " . tell($handle) . ". EOF flag is " . eof($handle) . ".") if T(File => 4);
2737                  push @retVal, UnEscape($inputParm);      # Read from the file.
2738        my $line = <$handle>;
2739        # Only proceed if we found something.
2740        if (defined $line) {
2741            # Remove the new-line. We are a bit over-cautious here because the file may be coming in via an
2742            # upload control and have a nonstandard EOL combination.
2743            $line =~ s/(\r|\n)+$//;
2744            # Here we do some fancy tracing to help in debugging complicated EOL marks.
2745            if (T(File => 4)) {
2746                my $escapedLine = $line;
2747                $escapedLine =~ s/\n/\\n/g;
2748                $escapedLine =~ s/\r/\\r/g;
2749                $escapedLine =~ s/\t/\\t/g;
2750                Trace("Line read: -->$escapedLine<--");
2751            }
2752            # If the line is empty, return a single empty string; otherwise, parse
2753            # it into fields.
2754            if ($line eq "") {
2755                push @retVal, "";
2756            } else {
2757                push @retVal, split /\t/,$line;
2758          }          }
2759          # Return the results.      } else {
2760          return ($optionTable, @retVal);          # Trace the reason the read failed.
2761            Trace("End of file: $!") if T(File => 3);
2762        }
2763        # Return the result.
2764        return @retVal;
2765    }
2766    
2767    =head3 PutLine
2768    
2769        Tracer::PutLine($handle, \@fields, $eol);
2770    
2771    Write a line of data to a tab-delimited file. The specified field values will be
2772    output in tab-separated form, with a trailing new-line.
2773    
2774    =over 4
2775    
2776    =item handle
2777    
2778    Output file handle.
2779    
2780    =item fields
2781    
2782    List of field values.
2783    
2784    =item eol (optional)
2785    
2786    End-of-line character (default is "\n").
2787    
2788    =back
2789    
2790    =cut
2791    
2792    sub PutLine {
2793        # Get the parameters.
2794        my ($handle, $fields, $eol) = @_;
2795        # Write the data.
2796        print $handle join("\t", @{$fields}) . ($eol || "\n");
2797    }
2798    
2799    
2800    =head3 PrintLine
2801    
2802        Tracer::PrintLine($line);
2803    
2804    Print a line of text with a trailing new-line.
2805    
2806    =over 4
2807    
2808    =item line
2809    
2810    Line of text to print.
2811    
2812    =back
2813    
2814    =cut
2815    
2816    sub PrintLine {
2817        # Get the parameters.
2818        my ($line) = @_;
2819        # Print the line.
2820        print "$line\n";
2821    }
2822    
2823    
2824    =head2 Other Useful Methods
2825    
2826    =head3 ParseParm
2827    
2828        my $listValue = Tracer::ParseParm($string);
2829    
2830    Convert a parameter into a list reference. If the parameter is undefined,
2831    an undefined value will be returned. Otherwise, it will be parsed as a
2832    comma-separated list of values.
2833    
2834    =over 4
2835    
2836    =item string
2837    
2838    Incoming string.
2839    
2840    =item RETURN
2841    
2842    Returns a reference to a list of values, or C<undef> if the incoming value
2843    was undefined.
2844    
2845    =back
2846    
2847    =cut
2848    
2849    sub ParseParm {
2850        # Get the parameters.
2851        my ($string) = @_;
2852        # Declare the return variable.
2853        my $retVal;
2854        # Check for data.
2855        if (defined $string) {
2856            # We have some, so split it into a list.
2857            $retVal = [ split /\s*,\s*/, $string];
2858        }
2859        # Return the result.
2860        return $retVal;
2861    }
2862    
2863    =head3 Now
2864    
2865        my $string = Tracer::Now();
2866    
2867    Return a displayable time stamp containing the local time. Whatever format this
2868    method produces must be parseable by L</ParseDate>.
2869    
2870    =cut
2871    
2872    sub Now {
2873        return DisplayTime(time);
2874    }
2875    
2876    =head3 DisplayTime
2877    
2878        my $string = Tracer::DisplayTime($time);
2879    
2880    Convert a time value to a displayable time stamp. Whatever format this
2881    method produces must be parseable by L</ParseDate>.
2882    
2883    =over 4
2884    
2885    =item time
2886    
2887    Time to display, in seconds since the epoch, or C<undef> if the time is unknown.
2888    
2889    =item RETURN
2890    
2891    Returns a displayable time, or C<(n/a)> if the incoming time is undefined.
2892    
2893    =back
2894    
2895    =cut
2896    
2897    sub DisplayTime {
2898        my ($time) = @_;
2899        my $retVal = "(n/a)";
2900        if (defined $time) {
2901            my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($time);
2902            $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .
2903                      _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);
2904        }
2905        return $retVal;
2906    }
2907    
2908    # Pad a number to 2 digits.
2909    sub _p2 {
2910        my ($value) = @_;
2911        $value = "0$value" if ($value < 10);
2912        return $value;
2913    }
2914    
2915    =head3 Escape
2916    
2917        my $codedString = Tracer::Escape($realString);
2918    
2919    Escape a string for use in a command. Tabs will be replaced by C<\t>, new-lines
2920    replaced by C<\n>, carriage returns will be deleted, and backslashes will be doubled. The
2921    result is to reverse the effect of L</UnEscape>.
2922    
2923    =over 4
2924    
2925    =item realString
2926    
2927    String to escape.
2928    
2929    =item RETURN
2930    
2931    Escaped equivalent of the real string.
2932    
2933    =back
2934    
2935    =cut
2936    
2937    sub Escape {
2938        # Get the parameter.
2939        my ($realString) = @_;
2940        # Initialize the return variable.
2941        my $retVal = "";
2942        # Loop through the parameter string, looking for sequences to escape.
2943        while (length $realString > 0) {
2944            # Look for the first sequence to escape.
2945            if ($realString =~ /^(.*?)([\n\t\r\\])/) {
2946                # Here we found it. The text preceding the sequence is in $1. The sequence
2947                # itself is in $2. First, move the clear text to the return variable.
2948                $retVal .= $1;
2949                # Strip the processed section off the real string.
2950                $realString = substr $realString, (length $2) + (length $1);
2951                # Get the matched character.
2952                my $char = $2;
2953                # If we have a CR, we are done.
2954                if ($char ne "\r") {
2955                    # It's not a CR, so encode the escape sequence.
2956                    $char =~ tr/\t\n/tn/;
2957                    $retVal .= "\\" . $char;
2958                }
2959            } else {
2960                # Here there are no more escape sequences. The rest of the string is
2961                # transferred unmodified.
2962                $retVal .= $realString;
2963                $realString = "";
2964            }
2965        }
2966        # Return the result.
2967        return $retVal;
2968  }  }
2969    
2970  =head3 UnEscape  =head3 UnEscape
2971    
2972  C<< my $realString = Tracer::UnEscape($codedString); >>      my $realString = Tracer::UnEscape($codedString);
2973    
2974  Replace escape sequences with their actual equivalents. C<\b> will be replaced by a space,  Replace escape sequences with their actual equivalents. C<\t> will be replaced by
2975  C<\t> by a tab, C<\n> by a new-line character, and C<\\> by a back-slash.  a tab, C<\n> by a new-line character, and C<\\> by a backslash. C<\r> codes will
2976    be deleted.
2977    
2978  =over 4  =over 4
2979    
# Line 555  Line 2995 
2995          my ($codedString) = @_;          my ($codedString) = @_;
2996          # Initialize the return variable.          # Initialize the return variable.
2997          my $retVal = "";          my $retVal = "";
2998        # Only proceed if the incoming string is nonempty.
2999        if (defined $codedString) {
3000          # Loop through the parameter string, looking for escape sequences. We can't do          # Loop through the parameter string, looking for escape sequences. We can't do
3001          # translating because it causes problems with the escaped slash. ("\\b" becomes          # translating because it causes problems with the escaped slash. ("\\t" becomes
3002          # "\ " no matter what we do.)          # "\<tab>" no matter what we do.)
3003          while (length $codedString > 0) {          while (length $codedString > 0) {
3004                  # Look for the first escape sequence.                  # Look for the first escape sequence.
3005                  if ($codedString =~ /^(.*?)\\(\\|b|n|t)/) {              if ($codedString =~ /^(.*?)\\(\\|n|t|r)/) {
3006                          # Here we found it. The text preceding the sequence is in $1. The sequence                          # Here we found it. The text preceding the sequence is in $1. The sequence
3007                          # itself is in $2. First, move the clear text to the return variable.                          # itself is in $2. First, move the clear text to the return variable.
3008                          $retVal .= $1;                          $retVal .= $1;
3009                          $codedString = substr $codedString, (2 + length $1);                          $codedString = substr $codedString, (2 + length $1);
3010                          # Decode the escape sequence.                  # Get the escape value.
3011                          my $char = $2;                          my $char = $2;
3012                          $char =~ tr/\\btn/\\ \t\n/;                  # If we have a "\r", we are done.
3013                    if ($char ne 'r') {
3014                        # Here it's not an 'r', so we convert it.
3015                        $char =~ tr/\\tn/\\\t\n/;
3016                          $retVal .= $char;                          $retVal .= $char;
3017                    }
3018                  } else {                  } else {
3019                          # Here there are no more escape sequences. The rest of the string is                          # Here there are no more escape sequences. The rest of the string is
3020                          # transferred unmodified.                          # transferred unmodified.
# Line 576  Line 3022 
3022                          $codedString = "";                          $codedString = "";
3023                  }                  }
3024          }          }
3025          # Return the result.      }
3026        # Return the result.
3027        return $retVal;
3028    }
3029    
3030    =head3 Percent
3031    
3032        my $percent = Tracer::Percent($number, $base);
3033    
3034    Returns the percent of the base represented by the given number. If the base
3035    is zero, returns zero.
3036    
3037    =over 4
3038    
3039    =item number
3040    
3041    Percent numerator.
3042    
3043    =item base
3044    
3045    Percent base.
3046    
3047    =item RETURN
3048    
3049    Returns the percentage of the base represented by the numerator.
3050    
3051    =back
3052    
3053    =cut
3054    
3055    sub Percent {
3056        # Get the parameters.
3057        my ($number, $base) = @_;
3058        # Declare the return variable.
3059        my $retVal = 0;
3060        # Compute the percent.
3061        if ($base != 0) {
3062            $retVal = $number * 100 / $base;
3063        }
3064        # Return the result.
3065        return $retVal;
3066    }
3067    
3068    =head3 Constrain
3069    
3070        my $constrained = Constrain($value, $min, $max);
3071    
3072    Modify a numeric value to bring it to a point in between a maximum and a minimum.
3073    
3074    =over 4
3075    
3076    =item value
3077    
3078    Value to constrain.
3079    
3080    =item min (optional)
3081    
3082    Minimum permissible value. If this parameter is undefined, no minimum constraint will be applied.
3083    
3084    =item max (optional)
3085    
3086    Maximum permissible value. If this parameter is undefined, no maximum constraint will be applied.
3087    
3088    =item RETURN
3089    
3090    Returns the incoming value, constrained according to the other parameters.
3091    
3092    =back
3093    
3094    =cut
3095    
3096    sub Constrain {
3097        # Get the parameters.
3098        my ($value, $min, $max) = @_;
3099        # Declare the return variable.
3100        my $retVal = $value;
3101        # Apply the minimum constraint.
3102        if (defined $min && $retVal < $min) {
3103            $retVal = $min;
3104        }
3105        # Apply the maximum constraint.
3106        if (defined $max && $retVal > $max) {
3107            $retVal = $max;
3108        }
3109        # Return the result.
3110        return $retVal;
3111    }
3112    
3113    =head3 Min
3114    
3115        my $min = Min($value1, $value2, ... $valueN);
3116    
3117    Return the minimum argument. The arguments are treated as numbers.
3118    
3119    =over 4
3120    
3121    =item $value1, $value2, ... $valueN
3122    
3123    List of numbers to compare.
3124    
3125    =item RETURN
3126    
3127    Returns the lowest number in the list.
3128    
3129    =back
3130    
3131    =cut
3132    
3133    sub Min {
3134        # Get the parameters. Note that we prime the return value with the first parameter.
3135        my ($retVal, @values) = @_;
3136        # Loop through the remaining parameters, looking for the lowest.
3137        for my $value (@values) {
3138            if ($value < $retVal) {
3139                $retVal = $value;
3140            }
3141        }
3142        # Return the minimum found.
3143        return $retVal;
3144    }
3145    
3146    =head3 Max
3147    
3148        my $max = Max($value1, $value2, ... $valueN);
3149    
3150    Return the maximum argument. The arguments are treated as numbers.
3151    
3152    =over 4
3153    
3154    =item $value1, $value2, ... $valueN
3155    
3156    List of numbers to compare.
3157    
3158    =item RETURN
3159    
3160    Returns the highest number in the list.
3161    
3162    =back
3163    
3164    =cut
3165    
3166    sub Max {
3167        # Get the parameters. Note that we prime the return value with the first parameter.
3168        my ($retVal, @values) = @_;
3169        # Loop through the remaining parameters, looking for the highest.
3170        for my $value (@values) {
3171            if ($value > $retVal) {
3172                $retVal = $value;
3173            }
3174        }
3175        # Return the maximum found.
3176          return $retVal;          return $retVal;
3177  }  }
3178    
 =head3 ParseRecord  
3179    
3180  C<< my @fields = Tracer::ParseRecord($line); >>  =head3 Strip
3181    
3182  Parse a tab-delimited data line. The data line is split into field values. Embedded tab      my $string = Tracer::Strip($line);
3183  and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.  
3184  These will automatically be converted.  Strip all line terminators off a string. This is necessary when dealing with files
3185    that may have been transferred back and forth several times among different
3186    operating environments.
3187    
3188  =over 4  =over 4
3189    
3190  =item line  =item line
3191    
3192  Line of data containing the tab-delimited fields.  Line of text to be stripped.
3193    
3194  =item RETURN  =item RETURN
3195    
3196  Returns a list of the fields found in the data line.  The same line of text with all the line-ending characters chopped from the end.
3197    
3198  =back  =back
3199    
3200  =cut  =cut
3201    
3202  sub ParseRecord {  sub Strip {
3203          # Get the parameter.      # Get a copy of the parameter string.
3204          my ($line) = @_;      my ($string) = @_;
3205          # Remove the trailing new-line, if any.      my $retVal = (defined $string ? $string : "");
3206          chomp $line;      # Strip the line terminator characters.
3207          # Split the line read into pieces using the tab character.      $retVal =~ s/(\r|\n)+$//g;
         my @retVal = split /\t/, $line;  
         # Trim and fix the escapes in each piece.  
         for my $value (@retVal) {  
                 # Trim leading whitespace.  
                 $value =~ s/^\s+//;  
                 # Trim trailing whitespace.  
                 $value =~ s/\s+$//;  
                 # Delete the carriage returns.  
                 $value =~ s/\r//g;  
                 # Convert the escapes into their real values.  
                 $value =~ s/\\t/"\t"/ge;  
                 $value =~ s/\\n/"\n"/ge;  
         }  
3208          # Return the result.          # Return the result.
3209          return @retVal;      return $retVal;
3210  }  }
3211    
3212  =head3 Merge  =head3 Pad
3213    
3214  C<< my @mergedList = Tracer::Merge(@inputList); >>      my $paddedString = Tracer::Pad($string, $len, $left, $padChar);
3215    
3216  Sort a list of strings and remove duplicates.  Pad a string to a specified length. The pad character will be a
3217    space, and the padding will be on the right side unless specified
3218    in the third parameter.
3219    
3220  =over 4  =over 4
3221    
3222  =item inputList  =item string
3223    
3224  List of scalars to sort and merge.  String to be padded.
3225    
3226    =item len
3227    
3228    Desired length of the padded string.
3229    
3230    =item left (optional)
3231    
3232    TRUE if the string is to be left-padded; otherwise it will be padded on the right.
3233    
3234    =item padChar (optional)
3235    
3236    Character to use for padding. The default is a space.
3237    
3238  =item RETURN  =item RETURN
3239    
3240  Returns a list containing the same elements sorted in ascending order with duplicates  Returns a copy of the original string with the pad character added to the
3241  removed.  specified end so that it achieves the desired length.
3242    
3243  =back  =back
3244    
3245  =cut  =cut
3246    
3247  sub Merge {  sub Pad {
3248          # Get the input list in sort order.      # Get the parameters.
3249          my @inputList = sort @_;      my ($string, $len, $left, $padChar) = @_;
3250          # Only proceed if the list has at least two elements.      # Compute the padding character.
3251          if (@inputList > 1) {      if (! defined $padChar) {
3252                  # Now we want to move through the list splicing out duplicates.          $padChar = " ";
3253                  my $i = 0;      }
3254                  while ($i < @inputList) {      # Compute the number of spaces needed.
3255                          # Get the current entry.      my $needed = $len - length $string;
3256                          my $thisEntry = $inputList[$i];      # Copy the string into the return variable.
3257                          # Find out how many elements duplicate the current entry.      my $retVal = $string;
3258                          my $j = $i + 1;      # Only proceed if padding is needed.
3259                          my $dup1 = $i + 1;      if ($needed > 0) {
3260                          while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };          # Create the pad string.
3261                          # If the number is nonzero, splice out the duplicates found.          my $pad = $padChar x $needed;
3262                          if ($j > $dup1) {          # Affix it to the return value.
3263                                  splice @inputList, $dup1, $j - $dup1;          if ($left) {
3264                $retVal = $pad . $retVal;
3265            } else {
3266                $retVal .= $pad;
3267                          }                          }
                         # Now the element at position $dup1 is different from the element before it  
                         # at position $i. We push $i forward one position and start again.  
                         $i++;  
3268                  }                  }
3269        # Return the result.
3270        return $retVal;
3271          }          }
3272          # Return the merged list.  
3273          return @inputList;  =head3 EOF
3274    
3275    This is a constant that is lexically greater than any useful string.
3276    
3277    =cut
3278    
3279    sub EOF {
3280        return "\xFF\xFF\xFF\xFF\xFF";
3281  }  }
3282    
3283  =head3 GetFile  =head3 TICK
3284    
3285        my @results = TICK($commandString);
3286    
3287  C<< my @fileContents = Tracer::GetFile($fileName); >>  Perform a back-tick operation on a command. If this is a Windows environment, any leading
3288    dot-slash (C<./> will be removed. So, for example, if you were doing
3289    
3290  Return the entire contents of a file.      `./protein.cgi`
3291    
3292    from inside a CGI script, it would work fine in Unix, but would issue an error message
3293    in Windows complaining that C<'.'> is not a valid command. If instead you code
3294    
3295        TICK("./protein.cgi")
3296    
3297    it will work correctly in both environments.
3298    
3299  =over 4  =over 4
3300    
3301  =item fileName  =item commandString
3302    
3303  Name of the file to read.  The command string to pass to the system.
3304    
3305  =item RETURN  =item RETURN
3306    
3307  In a list context, returns the entire file as a list with the line terminators removed.  Returns the standard output from the specified command, as a list.
 In a scalar context, returns the entire file as a string.  
3308    
3309  =back  =back
3310    
3311  =cut  =cut
3312    #: Return Type @;
3313  sub GetFile {  sub TICK {
3314          # Get the parameters.          # Get the parameters.
3315          my ($fileName) = @_;      my ($commandString) = @_;
3316          # Declare the return variable.      # Chop off the dot-slash if this is Windows.
3317          my @retVal = ();      if ($FIG_Config::win_mode) {
3318          # Open the file for input.          $commandString =~ s!^\./!!;
         my $ok = open INPUTFILE, "<$fileName";  
         if (!$ok) {  
                 # If we had an error, trace it. We will automatically return a null value.  
                 Trace("Could not open \"$fileName\" for input.") if T(0);  
         } else {  
                 # Read the whole file into the return variable, stripping off an terminator  
         # characters.  
         my $lineCount = 0;  
                 while (my $line = <INPUTFILE>) {  
             $lineCount++;  
             $line =~ s/(\r|\n)+$//g;  
                         push @retVal, $line;  
                 }  
                 # Close it.  
                 close INPUTFILE;  
         my $actualLines = @retVal;  
         Trace("$lineCount lines read from $fileName. $actualLines processed.") if T(0);  
         }  
         # Return the file's contents in the desired format.  
     if (wantarray) {  
             return @retVal;  
     } else {  
         return join "\n", @retVal;  
3319      }      }
3320        # Activate the command and return the result.
3321        return `$commandString`;
3322  }  }
3323    
 =head3 QTrace  
3324    
3325  C<< my $data = QTrace($format); >>  =head3 CommaFormat
3326    
3327  Return the queued trace data in the specified format.      my $formatted = Tracer::CommaFormat($number);
3328    
3329    Insert commas into a number.
3330    
3331  =over 4  =over 4
3332    
3333  =item format  =item number
3334    
3335  C<html> to format the data as an HTML list, C<text> to format it as straight text.  A sequence of digits.
3336    
3337    =item RETURN
3338    
3339    Returns the same digits with commas strategically inserted.
3340    
3341  =back  =back
3342    
3343  =cut  =cut
3344    
3345  sub QTrace {  sub CommaFormat {
3346          # Get the parameter.      # Get the parameters.
3347          my ($format) = @_;      my ($number) = @_;
3348          # Create the return variable.      # Pad the length up to a multiple of three.
3349          my $retVal = "";      my $padded = "$number";
3350          # Process according to the format.      $padded = " " . $padded while length($padded) % 3 != 0;
3351          if ($format =~ m/^HTML$/i) {      # This is a fancy PERL trick. The parentheses in the SPLIT pattern
3352                  # Convert the queue into an HTML list.      # cause the delimiters to be included in the output stream. The
3353                  $retVal = "<ul>\n";      # GREP removes the empty strings in between the delimiters.
3354                  for my $line (@Queue) {      my $retVal = join(",", grep { $_ ne '' } split(/(...)/, $padded));
3355                          my $escapedLine = CGI::escapeHTML($line);      # Clean out the spaces.
3356                          $retVal .= "<li>$escapedLine</li>\n";      $retVal =~ s/ //g;
3357                  }      # Return the result.
                 $retVal .= "</ul>\n";  
         } elsif ($format =~ m/^TEXT$/i) {  
                 # Convert the queue into a list of text lines.  
                 $retVal = join("\n", @Queue) . "\n";  
         }  
         # Clear the queue.  
         @Queue = ();  
         # Return the formatted list.  
3358          return $retVal;          return $retVal;
3359  }  }
3360    
 =head3 Confess  
   
 C<< Confess($message); >>  
3361    
3362  Trace the call stack and abort the program with the specified message. The stack  =head3 CompareLists
 trace will only appear if the trace level for this package is 1 or more. When used with  
 the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.  
 So, for example  
3363    
3364  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>      my ($inserted, $deleted) = Tracer::CompareLists(\@newList, \@oldList, $keyIndex);
3365    
3366  Will abort the program with a stack trace if the value of C<$recNum> is negative.  Compare two lists of tuples, and return a hash analyzing the differences. The lists
3367    are presumed to be sorted alphabetically by the value in the $keyIndex column.
3368    The return value contains a list of items that are only in the new list
3369    (inserted) and only in the old list (deleted).
3370    
3371  =over 4  =over 4
3372    
3373  =item message  =item newList
   
 Message to include in the trace.  
3374    
3375  =back  Reference to a list of new tuples.
3376    
3377  =cut  =item oldList
3378    
3379  sub Confess {  Reference to a list of old tuples.
         # Get the parameters.  
         my ($message) = @_;  
         # Trace the call stack.  
         Cluck($message) if T(1);  
         # Abort the program.  
         croak(">>> $message");  
 }  
3380    
3381  =head3 Assert  =item keyIndex (optional)
3382    
3383  C<< Assert($condition1, $condition2, ... $conditionN); >>  Index into each tuple of its key field. The default is 0.
3384    
3385  Return TRUE if all the conditions are true. This method can be used in conjunction with  =item RETURN
 the OR operator and the L</Confess> method, B<Assert> can function as a debugging assert.  
 So, for example  
3386    
3387  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>  Returns a 2-tuple consisting of a reference to the list of items that are only in the new
3388    list (inserted) followed by a reference to the list of items that are only in the old
3389    list (deleted).
3390    
3391  Will abort the program with a stack trace if the value of C<$recNum> is negative.  =back
3392    
3393  =cut  =cut
3394  sub Assert {  
3395      my $retVal = 1;  sub CompareLists {
3396      LOOP: for my $condition (@_) {      # Get the parameters.
3397          if (! $condition) {      my ($newList, $oldList, $keyIndex) = @_;
3398              $retVal = 0;      if (! defined $keyIndex) {
3399              last LOOP;          $keyIndex = 0;
3400        }
3401        # Declare the return variables.
3402        my ($inserted, $deleted) = ([], []);
3403        # Loop through the two lists simultaneously.
3404        my ($newI, $oldI) = (0, 0);
3405        my ($newN, $oldN) = (scalar @{$newList}, scalar @{$oldList});
3406        while ($newI < $newN || $oldI < $oldN) {
3407            # Get the current object in each list. Note that if one
3408            # of the lists is past the end, we'll get undef.
3409            my $newItem = $newList->[$newI];
3410            my $oldItem = $oldList->[$oldI];
3411            if (! defined($newItem) || defined($oldItem) && $newItem->[$keyIndex] gt $oldItem->[$keyIndex]) {
3412                # The old item is not in the new list, so mark it deleted.
3413                push @{$deleted}, $oldItem;
3414                $oldI++;
3415            } elsif (! defined($oldItem) || $oldItem->[$keyIndex] gt $newItem->[$keyIndex]) {
3416                # The new item is not in the old list, so mark it inserted.
3417                push @{$inserted}, $newItem;
3418                $newI++;
3419            } else {
3420                # The item is in both lists, so push forward.
3421                $oldI++;
3422                $newI++;
3423          }          }
3424      }      }
3425      return $retVal;      # Return the result.
3426        return ($inserted, $deleted);
3427  }  }
3428    
3429  =head3 Cluck  =head3 GenerateURL
3430    
3431  C<< Cluck($message); >>      my $queryUrl = Tracer::GenerateURL($page, %parameters);
3432    
3433  Trace the call stack. Note that for best results, you should qualify the call with a  Generate a GET-style URL for the specified page with the specified parameter
3434  trace condition. For example,  names and values. The values will be URL-escaped automatically. So, for
3435    example
3436    
3437  C<< Cluck("Starting record parse.") if T(3); >>      Tracer::GenerateURL("form.cgi", type => 1, string => "\"high pass\" or highway")
3438    
3439  will only trace the stack if the trace level for the package is 3 or more.  would return
3440    
3441        form.cgi?type=1;string=%22high%20pass%22%20or%20highway
3442    
3443  =over 4  =over 4
3444    
3445  =item message  =item page
3446    
3447  Message to include in the trace.  Page URL.
3448    
3449    =item parameters
3450    
3451    Hash mapping parameter names to parameter values.
3452    
3453    =item RETURN
3454    
3455    Returns a GET-style URL that goes to the specified page and passes in the
3456    specified parameters and values.
3457    
3458  =back  =back
3459    
3460  =cut  =cut
3461    
3462  sub Cluck {  sub GenerateURL {
3463          # Get the parameters.          # Get the parameters.
3464          my ($message) = @_;      my ($page, %parameters) = @_;
3465      # Trace what's happening.      # Prime the return variable with the page URL.
3466      Trace("Stack trace for event: $message");      my $retVal = $page;
3467          my $confession = longmess($message);      # Loop through the parameters, creating parameter elements in a list.
3468          # Convert the confession to a series of trace messages. Note we skip any      my @parmList = map { "$_=" . uri_escape($parameters{$_}) } keys %parameters;
3469      # messages relating to calls into Tracer.      # If the list is nonempty, tack it on.
3470          for my $line (split /\s*\n/, $confession) {      if (@parmList) {
3471                  Trace($line) if ($line !~ /Tracer\.pm/);          $retVal .= "?" . join(";", @parmList);
3472          }          }
3473        # Return the result.
3474        return $retVal;
3475  }  }
3476    
3477  =head3 Min  =head3 ApplyURL
3478    
3479  C<< my $min = Min($value1, $value2, ... $valueN); >>      Tracer::ApplyURL($table, $target, $url);
3480    
3481  Return the minimum argument. The arguments are treated as numbers.  Run through a two-dimensional table (or more accurately, a list of lists), converting the
3482    I<$target> column to HTML text having a hyperlink to a URL in the I<$url> column. The
3483    URL column will be deleted by this process and the target column will be HTML-escaped.
3484    
3485    This provides a simple way to process the results of a database query into something
3486    displayable by combining a URL with text.
3487    
3488  =over 4  =over 4
3489    
3490  =item $value1, $value2, ... $valueN  =item table
3491    
3492  List of numbers to compare.  Reference to a list of lists. The elements in the containing list will be updated by
3493    this method.
3494    
3495  =item RETURN  =item target
3496    
3497  Returns the lowest number in the list.  The index of the column to be converted into HTML.
3498    
3499    =item url
3500    
3501    The index of the column containing the URL. Note that the URL must have a recognizable
3502    C<http:> at the beginning.
3503    
3504  =back  =back
3505    
3506  =cut  =cut
3507    
3508  sub Min {  sub ApplyURL {
3509          # Get the parameters. Note that we prime the return value with the first parameter.      # Get the parameters.
3510          my ($retVal, @values) = @_;      my ($table, $target, $url) = @_;
3511          # Loop through the remaining parameters, looking for the lowest.      # Loop through the table.
3512          for my $value (@values) {      for my $row (@{$table}) {
3513                  if ($value < $retVal) {          # Apply the URL to the target cell.
3514                          $retVal = $value;          $row->[$target] = CombineURL($row->[$target], $row->[$url]);
3515                  }          # Delete the URL from the row.
3516            delete $row->[$url];
3517          }          }
         # Return the minimum found.  
         return $retVal;  
3518  }  }