[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 1.103, Fri May 9 04:21:45 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    umask 2;                    # Fix the damn umask so everything is group-writable.
212    
213  =head2 Public Methods  =head2 Tracing Methods
214    
215    =head3 Setups
216    
217        my $count = Tracer::Setups();
218    
219    Return the number of times L</TSetup> has been called.
220    
221    This method allows for the creation of conditional tracing setups where, for example, we
222    may want to set up tracing if nobody else has done it before us.
223    
224    =cut
225    
226    sub Setups {
227        return $SetupCount;
228    }
229    
230  =head3 TSetup  =head3 TSetup
231    
232  C<< TSetup($categoryList, $target); >>      TSetup($categoryList, $target);
233    
234  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
235  and interrogated by the L</Trace> and L</T> methods.  and interrogated by the L</Trace> and L</T> methods.
# Line 90  Line 245 
245    
246  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
247  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
248  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 ">"
249  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
250  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
251    cause tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>
252  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
253  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
254  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 266 
266          my @categoryData = split /\s+/, $categoryList;          my @categoryData = split /\s+/, $categoryList;
267          # Extract the trace level.          # Extract the trace level.
268          $TraceLevel = shift @categoryData;          $TraceLevel = shift @categoryData;
269          # Build the category hash.      # Presume category-based tracing until we learn otherwise.
270        $AllTrace = 0;
271        # Build the category hash. Note that if we find a "*", we turn on non-category
272        # tracing. We must also clear away any pre-existing data.
273        %Categories = ( main => 1 );
274          for my $category (@categoryData) {          for my $category (@categoryData) {
275                  $Categories{$category} = 1;          if ($category eq '*') {
276                $AllTrace = 1;
277            } else {
278                $Categories{lc $category} = 1;
279            }
280          }          }
281          # Now we need to process the destination information. The most important special          # Now we need to process the destination information. The most important special
282          # case is the single ">", which requires we clear the file first. After doing      # case is when we're writing to a file. This is indicated by ">" (overwrite) and
283          # so, we tack on another ">" sign so that future trace messages are appended.      # ">>" (append). A leading "+" for either indicates that we are also writing to
284        # the standard output (tee mode).
285        if ($target =~ m/^\+?>>?/) {
286            if ($target =~ m/^\+/) {
287                $TeeFlag = 1;
288                $target = substr($target, 1);
289            }
290          if ($target =~ m/^>[^>]/) {          if ($target =~ m/^>[^>]/) {
291                # We need to initialize the file (which clears it).
292                  open TRACEFILE, $target;                  open TRACEFILE, $target;
293                  print TRACEFILE Now() . " Tracing initialized.\n";              print TRACEFILE "[" . Now() . "] [notice] [Tracer] Tracing initialized.\n";
294                  close TRACEFILE;                  close TRACEFILE;
295                # Set to append mode now that the file has been cleared.
296                  $Destination = ">$target";                  $Destination = ">$target";
297          } else {          } else {
298                $Destination = $target;
299            }
300        } else {
301                  $Destination = uc($target);                  $Destination = uc($target);
302          }          }
303        # Increment the setup counter.
304        $SetupCount++;
305  }  }
306    
307  =head3 SetLevel  =head3 SetLevel
308    
309  C<< Tracer::SetLevel($newLevel); >>      Tracer::SetLevel($newLevel);
310    
311  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.
312    
# Line 147  Line 324 
324      $TraceLevel = $_[0];      $TraceLevel = $_[0];
325  }  }
326    
327  =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  
328    
329  =cut      my $time = Tracer::ParseDate($dateString);
330    
331  sub LogErrors {  Convert a date into a PERL time number. This method expects a date-like string
332          # Get the file name.  and parses it into a number. The string must be vaguely date-like or it will
333          my ($fileName) = @_;  return an undefined value. Our requirement is that a month and day be
334          # Open the file as the standard error output.  present and that three pieces of the date string (time of day, month and day,
335          open STDERR, '>', $fileName;  year) be separated by likely delimiters, such as spaces, commas, and such-like.
 }  
336    
337  =head3 ReadOptions  If a time of day is present, it must be in military time with two digits for
338    everything but the hour.
339    
340  C<< my %options = Tracer::ReadOptions($fileName); >>  The year must be exactly four digits.
341    
342  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
343  format  equally innocuous. This means, however, that a sufficiently long sentence with date-like
344    parts in it may be interpreted as a date. Hopefully this will not be a problem.
345    
346  I<optionName>C<=>I<optionValue>C<; >I<comment>  It should be guaranteed that this method will parse the output of the L</Now> function.
347    
348  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.  
349    
350  =over 4  =over 4
351    
352  =item fileName  =item dateString
353    
354  Name of the file containing the option data.  The date string to convert.
355    
356  =item RETURN  =item RETURN
357    
358  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
359  value.  the date string is invalid. A valid date string must contain a month and day.
360    
361  =back  =back
362    
363  =cut  =cut
364    
365  sub ReadOptions {  # Universal month conversion table.
366          # Get the parameters.  use constant MONTHS => {    Jan =>  0, January   =>  0, '01' =>  0,  '1' =>  0,
367          my ($fileName) = @_;                              Feb =>  1, February  =>  1, '02' =>  1,  '2' =>  1,
368          # Open the file.                              Mar =>  2, March     =>  2, '03' =>  2,  '3' =>  2,
369          (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");                              Apr =>  3, April     =>  3, '04' =>  3,  '4' =>  3,
370          # Count the number of records read.                              May =>  4, May       =>  4, '05' =>  4,  '5' =>  4,
371          my ($records, $comments) = 0;                              Jun =>  5, June      =>  5, '06' =>  5,  '6' =>  5,
372          # Create the return hash.                              Jul =>  6, July      =>  6, '07' =>  6,  '7' =>  6,
373          my %retVal = ();                              Aug =>  7, August    =>  7, '08' =>  7,  '8' =>  7,
374          # Loop through the file, accumulating key-value pairs.                              Sep =>  8, September =>  8, '09' =>  8,  '9' =>  8,
375          while (my $line = <CONFIGFILE>) {                              Oct =>  9, October  =>   9, '10' =>  9,
376                  # Denote we've read a line.                              Nov => 10, November =>  10, '11' => 10,
377                  $records++;                              Dec => 11, December =>  11, '12' => 11
378                  # Determine the line type.                          };
                 if ($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  
379    
380  sub GetOptions {  sub ParseDate {
381          # Get the parameters.          # Get the parameters.
382          my ($defaults, $options) = @_;      my ($dateString) = @_;
383          # Check for overrides.      # Declare the return variable.
384          if ($options) {      my $retVal;
385                  # Loop through the overrides.      # Find the month and day of month. There are two ways that can happen. We check for the
386                  while (my ($option, $setting) = each %{$options}) {      # numeric style first. That way, if the user's done something like "Sun 12/22", then we
387                          # Insure this override exists.      # won't be fooled into thinking the month is Sunday.
388                          if (!exists $defaults->{$option}) {      if ($dateString =~ m#\b(\d{1,2})/(\d{1,2})\b# || $dateString =~ m#\b(\w+)\s(\d{1,2})\b#) {
389                                  croak "Unrecognized option $option encountered.";          my ($mon, $mday) = (MONTHS->{$1}, $2);
390            # Insist that the month and day are valid.
391            if (defined($mon) && $2 >= 1 && $2 <= 31) {
392                # Find the time.
393                my ($hour, $min, $sec) = (0, 0, 0);
394                if ($dateString =~ /\b(\d{1,2}):(\d{2}):(\d{2})\b/) {
395                    ($hour, $min, $sec) = ($1, $2, $3);
396                }
397                # Find the year.
398                my $year;
399                if ($dateString =~ /\b(\d{4})\b/) {
400                    $year = $1;
401                          } else {                          } else {
402                                  # Apply the override.                  # Get the default year, which is this one. Note we must convert it to
403                                  $defaults->{$option} = $setting;                  # the four-digit value expected by "timelocal".
404                    (undef, undef, undef, undef, undef, $year) = localtime();
405                    $year += 1900;
406                          }                          }
407                $retVal = timelocal($sec, $min, $hour, $mday, $mon, $year);
408                  }                  }
409          }          }
410          # Return the merged table.      # Return the result.
411          return $defaults;      return $retVal;
412  }  }
413    
414  =head3 MergeOptions  =head3 LogErrors
415    
416  C<< Tracer::MergeOptions(\%table, \%defaults); >>      Tracer::LogErrors($fileName);
417    
418  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.  
419    
420  =over 4  =over 4
421    
422  =item table  =item fileName
   
 Hash table to be updated with the default values.  
   
 =item defaults  
423    
424  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.
425    
426  =back  =back
427    
428  =cut  =cut
429    
430  sub MergeOptions {  sub LogErrors {
431          # Get the parameters.      # Get the file name.
432          my ($table, $defaults) = @_;      my ($fileName) = @_;
433          # Loop through the defaults.      # Open the file as the standard error output.
434          while (my ($key, $value) = each %{$defaults}) {      open STDERR, '>', $fileName;
                 if (!exists $table->{$key}) {  
                         $table->{$key} = $value;  
                 }  
         }  
435  }  }
436    
437  =head3 Trace  =head3 Trace
438    
439  C<< Trace($message); >>      Trace($message);
440    
441  Write a trace message to the target location specified in L</TSetup>. If there has not been  Write a trace message to the target location specified in L</TSetup>. If there has not been
442  any prior call to B<TSetup>.  any prior call to B<TSetup>.
# Line 368  Line 454 
454  sub Trace {  sub Trace {
455          # Get the parameters.          # Get the parameters.
456          my ($message) = @_;          my ($message) = @_;
457        # Strip off any line terminators at the end of the message. We will add
458        # new-line stuff ourselves.
459        my $stripped = Strip($message);
460        # Compute the caller information.
461        my ($callPackage, $callFile, $callLine) = caller();
462        my $callFileTitle = basename($callFile);
463        # Check the caller.
464        my $callerInfo = ($callFileTitle ne "Tracer.pm" ? " [$callFileTitle $callLine]" : "");
465          # Get the timestamp.          # Get the timestamp.
466          my $timeStamp = Now();          my $timeStamp = Now();
467        # Build the prefix.
468        my $level = $LevelNames[$LastLevel] || "($LastLevel)";
469        my $prefix = "[$timeStamp] [$level] [$LastCategory]$callerInfo";
470          # Format the message.          # Format the message.
471          my $formatted = "$timeStamp $message";      my $formatted = "$prefix $stripped";
472          # Process according to the destination.          # Process according to the destination.
473          if ($Destination eq "TEXT") {          if ($Destination eq "TEXT") {
474                  # Write the message to the standard output.                  # Write the message to the standard output.
475                  print "$formatted\n";                  print "$formatted\n";
476          } elsif ($Destination eq "ERROR") {          } elsif ($Destination eq "ERROR") {
477                  # Write the message to the error output.          # Write the message to the error output. Here, we want our prefix fields.
478                  print STDERR "$formatted\n";                  print STDERR "$formatted\n";
479        } elsif ($Destination eq "WARN") {
480            # Emit the message to the standard error output. It is presumed that the
481            # error logger will add its own prefix fields, the notable exception being
482            # the caller info.
483            print STDERR "$callerInfo$stripped\n";
484          } elsif ($Destination eq "QUEUE") {          } elsif ($Destination eq "QUEUE") {
485                  # Push the message into the queue.                  # Push the message into the queue.
486                  push @Queue, "$formatted";                  push @Queue, "$formatted";
487          } elsif ($Destination eq "HTML") {          } elsif ($Destination eq "HTML") {
488                  # Convert the message to HTML and write it to the standard output.                  # Convert the message to HTML and write it to the standard output.
489                  my $escapedMessage = CGI::escapeHTML($message);          my $escapedMessage = CGI::escapeHTML($stripped);
490                  print "<p>$formatted</p>\n";          print "<p>$timeStamp $LastCategory $LastLevel: $escapedMessage</p>\n";
     } elsif ($Destination eq "WARN") {  
        # Emit the message as a warning.  
        warn $message;  
491          } elsif ($Destination =~ m/^>>/) {          } elsif ($Destination =~ m/^>>/) {
492                  # Write the trace message to an output file.                  # Write the trace message to an output file.
493                  open TRACING, $Destination;          open(TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";
494                  print TRACING "$formatted\n";                  print TRACING "$formatted\n";
495                  close TRACING;                  close TRACING;
496            # If the Tee flag is on, echo it to the standard output.
497            if ($TeeFlag) {
498                print "$formatted\n";
499            }
500          }          }
501  }  }
502    
503  =head3 T  =head3 T
504    
505  C<< my $switch = T($category, $traceLevel); >>      my $switch = T($category, $traceLevel);
506    
507          or          or
508    
509  C<< my $switch = T($traceLevel); >>      my $switch = T($traceLevel);
510    
511  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
512  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 539 
539                  my ($category, $traceLevel) = @_;                  my ($category, $traceLevel) = @_;
540                  if (!defined $traceLevel) {                  if (!defined $traceLevel) {
541                          # 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.
542                # The calling package is normally the first parameter. If it is
543                # omitted, the first parameter will be the tracelevel. So, the
544                # first thing we do is shift the so-called category into the
545                # $traceLevel variable where it belongs.
546                          $traceLevel = $category;                          $traceLevel = $category;
547                          my ($package, $fileName, $line) = caller;                          my ($package, $fileName, $line) = caller;
548              # If there is no calling package, we default to "main".              # If there is no calling package, we default to "main".
549                          if (!$package) {                          if (!$package) {
550                  $category = "main";                  $category = "main";
551                          } else {                          } else {
552                                  $category = $package;                  my @cats = split /::/, $package;
553                    $category = $cats[$#cats];
554                          }                          }
555                  }                  }
556                  # Use the package and tracelevel to compute the result.          # Save the category name and level.
557                  $retVal = ($traceLevel <= $TraceLevel && exists $Categories{$category});          $LastCategory = $category;
558            $LastLevel = $traceLevel;
559            # Convert it to lower case before we hash it.
560            $category = lc $category;
561            # Validate the trace level.
562            if (ref $traceLevel) {
563                Confess("Bad trace level.");
564            } elsif (ref $TraceLevel) {
565                Confess("Bad trace config.");
566            }
567            # Make the check. Note that level 0 shows even if the category is turned off.
568            $retVal = ($traceLevel <= $TraceLevel && ($traceLevel == 0 || $AllTrace || exists $Categories{$category}));
569      }      }
570          # Return the computed result.          # Return the computed result.
571      return $retVal;      return $retVal;
572  }  }
573    
574  =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  
575    
576  C<< apple orange rutabaga >>      my $data = QTrace($format);
577    
578  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.  
579    
580  =over 4  =over 4
581    
582  =item optionTable  =item format
   
 Table of default options.  
   
 =item inputList  
   
 List of words on the command line.  
   
 =item RETURN  
583    
584  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.
585    
586  =back  =back
587    
588  =cut  =cut
589    
590  sub ParseCommand {  sub QTrace {
591          # Get the parameters.      # Get the parameter.
592          my ($optionTable, @inputList) = @_;      my ($format) = @_;
593          # Process any options in the input list.      # Create the return variable.
594        my $retVal = "";
595        # Only proceed if there is an actual queue.
596        if (@Queue) {
597            # Process according to the format.
598            if ($format =~ m/^HTML$/i) {
599                # Convert the queue into an HTML list.
600                $retVal = "<ul>\n";
601                for my $line (@Queue) {
602                    my $escapedLine = CGI::escapeHTML($line);
603                    $retVal .= "<li>$escapedLine</li>\n";
604                }
605                $retVal .= "</ul>\n";
606            } elsif ($format =~ m/^TEXT$/i) {
607                # Convert the queue into a list of text lines.
608                $retVal = join("\n", @Queue) . "\n";
609            }
610            # Clear the queue.
611            @Queue = ();
612        }
613        # Return the formatted list.
614        return $retVal;
615    }
616    
617    =head3 Confess
618    
619        Confess($message);
620    
621    Trace the call stack and abort the program with the specified message. When used with
622    the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.
623    So, for example
624    
625        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
626    
627    Will abort the program with a stack trace if the value of C<$recNum> is negative.
628    
629    =over 4
630    
631    =item message
632    
633    Message to include in the trace.
634    
635    =back
636    
637    =cut
638    
639    sub Confess {
640        # Get the parameters.
641        my ($message) = @_;
642        # Set up the category and level.
643        $LastCategory = "(confess)";
644        $LastLevel = 0;
645        if (! defined($FIG_Config::no_tool_hdr)) {
646            # Here we have a tool header. Display its length so that the user can adjust the line numbers.
647            my $toolHeaderFile = "$FIG_Config::fig_disk/dist/releases/current/$FIG_Config::arch/tool_hdr";
648            # Only proceed if the tool header file is actually present.
649            if (-f $toolHeaderFile) {
650                my $fh;
651                if (open $fh, "<$toolHeaderFile") {
652                    my @lines = <$fh>;
653                    Trace("Tool header has " . scalar(@lines) . " lines.");
654                }
655            }
656        }
657        # Trace the call stack.
658        Cluck($message);
659        # Abort the program.
660        croak(">>> $message");
661    }
662    
663    =head3 Warn
664    
665        Warn($message);
666    
667    This method traces an important message. If an RSS feed is configured
668    (via I<FIG_Config::error_feed>) and the tracing destination is C<WARN>,
669    then the message will be echoed to the feed. In general, a tracing
670    destination of C<WARN> indicates that the caller is running as a web
671    service in a production environment; however, this is not a requirement.
672    
673    To force warnings into the RSS feed even when the tracing destination
674    is not C<WARN>, simply specify the C<Feed> tracing module. This can be
675    configured automatically when L</StandardSetup> is used.
676    
677    The L</Cluck> method calls this one for its final message. Since
678    L</Confess> calls L</Cluck>, this means that any error which is caught
679    and confessed will put something in the feed. This insures that someone
680    will be alerted relatively quickly when a failure occurs.
681    
682    =over 4
683    
684    =item message
685    
686    Message to be traced.
687    
688    =back
689    
690    =cut
691    
692    sub Warn {
693        # Get the parameters.
694        my ($message) = @_;
695        # Trace the message.
696        Trace($message);
697        # Check for feed forcing.
698        my $forceFeed = exists $Categories{feed};
699        # An error here would be disastrous. Note, however, that we aren't too worried
700        # about losing events. The error log is always available for the occasions where
701        # we mess up. Note that if debug mode is specified, we do this stuff even in a
702        # test environment.
703        eval {
704            # Do we need to put this in the RSS feed?
705            if ($FIG_Config::error_feed && ($Destination eq 'WARN' || $forceFeed)) {
706                # Yes. We now need to compute the date, the link, and the title.
707                # First, the date, in a very specific format.
708                my $date = strftime("%a, %02e %b %H:%M:%S %Y ", localtime) .
709                    (tz_local_offset() / 30);
710                # Environment data goes in here. We start with the date.
711                my $environment = "$date.  ";
712                # If we need to recap the message (because it's too long to be a title), we'll
713                # put it in here.
714                my $recap;
715                # Copy the message and remove excess space.
716                my $title = $message;
717                $title =~ s/\s+/ /gs;
718                # If it's too long, we have to split it up.
719                if (length $title > 60) {
720                    # Put the full message in the environment string.
721                    $recap = $title;
722                    # Excerpt it as the title.
723                    $title = substr($title, 0, 50) . "...";
724                }
725                # If we have a CGI object, then this is a web error. Otherwise, it's
726                # command-line.
727                if (defined $SavedCGI) {
728                    # We're in a web service. The environment is the user's IP, and the link
729                    # is the URL that got us here.
730                    my $key = $ENV{HTTP_X_FORWARDED_FOR} || $ENV{REMOTE_ADDR};
731                    $environment .= "Event Reported at IP address $key.";
732                    my $url = $SavedCGI->url(-full => 1, -query => 1);
733                    # We need the user agent string and (if available) the referrer.
734                    # The referrer will be the link.
735                    $environment .= "User Agent $ENV{HTTP_USER_AGENT}";
736                    if ($ENV{HTTP_REFERER}) {
737                        my $link = $ENV{HTTP_REFERER};
738                        $environment .= " referred from <a href=\"$link\">$link</a>.";
739                    } else {
740                        $environment .= " referrer unknown.";
741                    }
742                    # Close off the sentence with the original link.
743                    $environment .= " URL of error is <a href=\"$url\">$url</a>.";
744                } else {
745                    # No CGI object, so we're a command-line tool. Use the tracing
746                    # key and the PID as the user identifier, and add the command.
747                    my $key = EmergencyKey();
748                    $environment .= "Event Reported by $key Process $$. Command $ENV{_}.";
749                }
750                # Build a GUID. We use the current time, the title, and the process ID,
751                # then digest the result.
752                my $guid = Digest::MD5::md5_base64(gettimeofday(), $title, $$);
753                # Finally, the description. This is a stack trace plus various environmental stuff.
754                my $stackTrace = "";
755                my @trace = LongMess();
756                # Only proceed if we got something back.
757                if (scalar(@trace) > 0) {
758                    $trace[0] =~ s/Tracer::Warn.+?called/Event occurred/;
759                    $stackTrace = "Stack trace:<pre>" . join("\n", @trace, "</pre>");
760                }
761                # We got the stack trace. Now it's time to put it all together.
762                # We have a goofy thing here in that we need to HTML-escape some sections of the description
763                # twice. They will be escaped once here, and then once when written by XML::Simple. They are
764                # unescaped once when processed by the RSS reader, and stuff in the description is treated as
765                # HTML. So, anything escaped here is treated as a literal when viewed in the RSS reader, but
766                # our <br>s and <pre>s are used to format the description.
767                $recap = (defined $recap ? "<em>" . CGI::escapeHTML($recap) . "</em><br /><br />" : "");
768                my $description = "$recap$environment  $stackTrace";
769                # Okay, we have all the pieces. Create a hash of the new event.
770                my $newItem = { title => $title,
771                                description => $description,
772                                category => $LastCategory,
773                                pubDate => $date,
774                                guid => $guid,
775                               };
776                # We need XML capability for this.
777                require XML::Simple;
778                # The RSS document goes in here.
779                my $rss;
780                # Get the name of the RSS file. It's in the FIG temporary directory.
781                my $fileName = "$FIG_Config::temp/$FIG_Config::error_feed";
782                # Does it exist?
783                if (-s $fileName) {
784                    # Slurp it in.
785                    $rss = XML::Simple::XMLin($fileName, ForceArray => ['item']);
786                } else {
787                    my $size = -s $fileName;
788                    # Create an empty channel.
789                    $rss = {
790                        channel => {
791                            title => 'NMPDR Warning Feed',
792                            link => "$FIG_Config::temp_url/$FIG_Config::error_feed",
793                            description => "Important messages regarding the status of the NMPDR.",
794                            generator => "NMPDR Trace Facility",
795                            docs => "http://blogs.law.harvard.edu/tech/rss",
796                            item => []
797                        },
798                    };
799                }
800                # Get the channel object.
801                my $channel = $rss->{channel};
802                # Update the last-build date.
803                $channel->{lastBuildDate} = $date;
804                # Get the item array.
805                my $items = $channel->{item};
806                # Insure it has only 100 entries.
807                while (scalar @{$items} > 100) {
808                    pop @{$items};
809                }
810                # Add our new item at the front.
811                unshift @{$items}, $newItem;
812                # Create the XML. Note we do not include the root or the declaration. XML Simple can't handle
813                # the requirements for those.
814                my $xml = XML::Simple::XMLout($rss, NoAttr => 1, RootName => undef, XmlDecl => '');
815                # Here we put in the root and declaration. The problem is that the root has to have the version attribute
816                # in it. So, we suppress the root and do it by hand, and that requires suppressing the declaration, too.
817                $xml = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<rss version=\"2.0\">$xml\n</rss>";
818                # We don't use Open here because we can't afford an error.
819                if (open XMLOUT, ">$fileName") {
820                    print XMLOUT $xml;
821                    close XMLOUT;
822                }
823            }
824        };
825        if ($@) {
826            # If the feed failed, we need to know why. The error will be traced, but this method will not be involved
827            # (which is a good thing).
828            my $error = $@;
829            Trace("Feed Error: $error") if T(Feed => 0);
830        }
831    }
832    
833    =head3 Assert
834    
835        Assert($condition1, $condition2, ... $conditionN);
836    
837    Return TRUE if all the conditions are true. This method can be used in conjunction with
838    the OR operator and the L</Confess> method as a debugging assert.
839    So, for example
840    
841        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
842    
843    Will abort the program with a stack trace if the value of C<$recNum> is negative.
844    
845    =cut
846    sub Assert {
847        my $retVal = 1;
848        LOOP: for my $condition (@_) {
849            if (! $condition) {
850                $retVal = 0;
851                last LOOP;
852            }
853        }
854        return $retVal;
855    }
856    
857    =head3 Cluck
858    
859        Cluck($message);
860    
861    Trace the call stack. Note that for best results, you should qualify the call with a
862    trace condition. For example,
863    
864        Cluck("Starting record parse.") if T(3);
865    
866    will only trace the stack if the trace level for the package is 3 or more.
867    
868    =over 4
869    
870    =item message
871    
872    Message to include in the trace.
873    
874    =back
875    
876    =cut
877    
878    sub Cluck {
879        # Get the parameters.
880        my ($message) = @_;
881        # Trace what's happening.
882        Trace("Stack trace for event: $message");
883        # Get the stack trace.
884        my @trace = LongMess();
885        # Convert the trace to a series of messages.
886        for my $line (@trace) {
887            # Replace the tab at the beginning with spaces.
888            $line =~ s/^\t/    /;
889            # Trace the line.
890            Trace($line);
891        }
892        # Issue a warning. This displays the event message and inserts it into the RSS error feed.
893        Warn($message);
894    }
895    
896    =head3 LongMess
897    
898        my @lines = Tracer::LongMess();
899    
900    Return a stack trace with all tracing methods removed. The return will be in the form of a list
901    of message strings.
902    
903    =cut
904    
905    sub LongMess {
906        # Declare the return variable.
907        my @retVal = ();
908        my $confession = longmess("");
909        for my $line (split /\s*\n/, $confession) {
910            unless ($line =~ /Tracer\.pm/) {
911                # Here we have a line worth keeping. Push it onto the result list.
912                push @retVal, $line;
913            }
914        }
915        # Return the result.
916        return @retVal;
917    }
918    
919    =head3 ScriptSetup (deprecated)
920    
921        my ($cgi, $varHash) = ScriptSetup($noTrace);
922    
923    Perform standard tracing and debugging setup for scripts. The value returned is
924    the CGI object followed by a pre-built variable hash. At the end of the script,
925    the client should call L</ScriptFinish> to output the web page.
926    
927    This method calls L</ETracing> to configure tracing, which allows the tracing
928    to be configured via the emergency tracing form on the debugging control panel.
929    Tracing will then be turned on automatically for all programs that use the L</ETracing>
930    method, which includes every program that uses this method or L</StandardSetup>.
931    
932    =over 4
933    
934    =item noTrace (optional)
935    
936    If specified, tracing will be suppressed. This is useful if the script wants to set up
937    tracing manually.
938    
939    =item RETURN
940    
941    Returns a two-element list consisting of a CGI query object and a variable hash for
942    the output page.
943    
944    =back
945    
946    =cut
947    
948    sub ScriptSetup {
949        # Get the parameters.
950        my ($noTrace) = @_;
951        # Get the CGI query object.
952        my $cgi = CGI->new();
953        # Set up tracing if it's not suppressed.
954        ETracing($cgi) unless $noTrace;
955        # Create the variable hash.
956        my $varHash = { results => '' };
957        # Return the query object and variable hash.
958        return ($cgi, $varHash);
959    }
960    
961    =head3 ETracing
962    
963        ETracing($parameter);
964    
965    Set up emergency tracing. Emergency tracing is tracing that is turned
966    on automatically for any program that calls this method. The emergency
967    tracing parameters are stored in a a file identified by a tracing key.
968    If this method is called with a CGI object, then the tracing key is
969    taken from a cookie. If it is called with no parameters, then the tracing
970    key is taken from an environment variable. If it is called with a string,
971    the tracing key is that string.
972    
973    =over 4
974    
975    =item parameter
976    
977    A parameter from which the tracing key is computed. If it is a scalar,
978    that scalar is used as the tracing key. If it is a CGI object, the
979    tracing key is taken from the C<IP> cookie. If it is omitted, the
980    tracing key is taken from the C<TRACING> environment variable. If it
981    is a CGI object and emergency tracing is not on, the C<Trace> and
982    C<TF> parameters will be used to determine the type of tracing.
983    
984    =back
985    
986    =cut
987    
988    sub ETracing {
989        # Get the parameter.
990        my ($parameter) = @_;
991        # Check for CGI mode.
992        if (defined $parameter && ref $parameter eq 'CGI') {
993            $SavedCGI = $parameter;
994        } else {
995            $SavedCGI = undef;
996        }
997        # Default to no tracing except errors.
998        my ($tracing, $dest) = ("0", "WARN");
999        # Check for emergency tracing.
1000        my $tkey = EmergencyKey($parameter);
1001        my $emergencyFile = EmergencyFileName($tkey);
1002        if (-e $emergencyFile) {
1003            # We have the file. Read in the data.
1004            my @tracing = GetFile($emergencyFile);
1005            # Pull off the time limit.
1006            my $expire = shift @tracing;
1007            # Convert it to seconds.
1008            $expire *= 3600;
1009            # Check the file data.
1010            my $stat = stat($emergencyFile);
1011            my ($now) = gettimeofday;
1012            if ($now - $stat->mtime > $expire) {
1013                # Delete the expired file.
1014                unlink $emergencyFile;
1015            } else {
1016                # Emergency tracing is on. Pull off the destination and
1017                # the trace level;
1018                $dest = shift @tracing;
1019                my $level = shift @tracing;
1020                # Convert the destination to a real tracing destination.
1021                # temp directory.
1022                $dest = EmergencyTracingDest($tkey, $dest);
1023                # Insure Tracer is specified.
1024                my %moduleHash = map { $_ => 1 } @tracing;
1025                $moduleHash{Tracer} = 1;
1026                # Set the trace parameter.
1027                $tracing = join(" ", $level, sort keys %moduleHash);
1028            }
1029        } elsif (defined $SavedCGI) {
1030            # There's no emergency tracing, but we have a CGI object, so check
1031            # for tracing from the form parameters.
1032            if ($SavedCGI->param('Trace')) {
1033                # Here the user has requested tracing via a form.
1034                $dest = ($SavedCGI->param('TF') ? ">$FIG_Config::temp/Trace$$.log" : "QUEUE");
1035                $tracing = $SavedCGI->param('Trace') . " Tracer";
1036            }
1037        }
1038        # Setup the tracing we've determined from all the stuff above.
1039        TSetup($tracing, $dest);
1040        # Check to see if we're a web script.
1041        if (defined $SavedCGI) {
1042            # Yes we are. Trace the form and environment data.
1043            TraceParms($SavedCGI);
1044            # Check for RAW mode. In raw mode, we print a fake header so that we see everything
1045            # emitted by the script in its raw form.
1046            if (T(Raw => 3)) {
1047                print CGI::header(-type => 'text/plain', -tracing => 'Raw');
1048            }
1049        }
1050    }
1051    
1052    =head3 EmergencyFileName
1053    
1054        my $fileName = Tracer::EmergencyFileName($tkey);
1055    
1056    Return the emergency tracing file name. This is the file that specifies
1057    the tracing information.
1058    
1059    =over 4
1060    
1061    =item tkey
1062    
1063    Tracing key for the current program.
1064    
1065    =item RETURN
1066    
1067    Returns the name of the file to contain the emergency tracing information.
1068    
1069    =back
1070    
1071    =cut
1072    
1073    sub EmergencyFileName {
1074        # Get the parameters.
1075        my ($tkey) = @_;
1076        # Compute the emergency tracing file name.
1077        return "$FIG_Config::temp/Emergency$tkey.txt";
1078    }
1079    
1080    =head3 EmergencyFileTarget
1081    
1082        my $fileName = Tracer::EmergencyFileTarget($tkey);
1083    
1084    Return the emergency tracing target file name. This is the file that receives
1085    the tracing output for file-based tracing.
1086    
1087    =over 4
1088    
1089    =item tkey
1090    
1091    Tracing key for the current program.
1092    
1093    =item RETURN
1094    
1095    Returns the name of the file to contain the trace output.
1096    
1097    =back
1098    
1099    =cut
1100    
1101    sub EmergencyFileTarget {
1102        # Get the parameters.
1103        my ($tkey) = @_;
1104        # Compute the emergency tracing file name.
1105        return "$FIG_Config::temp/trace$tkey.log";
1106    }
1107    
1108    =head3 EmergencyTracingDest
1109    
1110        my $dest = Tracer::EmergencyTracingDest($tkey, $myDest);
1111    
1112    This method converts an emergency tracing destination to a real
1113    tracing destination. The main difference is that if the
1114    destination is C<FILE> or C<APPEND>, we convert it to file
1115    output. If the destination is C<DUAL>, we convert it to file
1116    and standard output.
1117    
1118    =over 4
1119    
1120    =item tkey
1121    
1122    Tracing key for this environment.
1123    
1124    =item myDest
1125    
1126    Destination from the emergency tracing file.
1127    
1128    =item RETURN
1129    
1130    Returns a destination that can be passed into L</TSetup>.
1131    
1132    =back
1133    
1134    =cut
1135    
1136    sub EmergencyTracingDest {
1137        # Get the parameters.
1138        my ($tkey, $myDest) = @_;
1139        # Declare the return variable.
1140        my $retVal = $myDest;
1141        # Process according to the destination value.
1142        if ($myDest eq 'FILE') {
1143            $retVal = ">" . EmergencyFileTarget($tkey);
1144        } elsif ($myDest eq 'APPEND') {
1145            $retVal = ">>" . EmergencyFileTarget($tkey);
1146        } elsif ($myDest eq 'DUAL') {
1147            $retVal = "+>" . EmergencyFileTarget($tkey);
1148        } elsif ($myDest eq 'WARN') {
1149            $retVal = "WARN";
1150        }
1151        # Return the result.
1152        return $retVal;
1153    }
1154    
1155    =head3 Emergency
1156    
1157        Emergency($key, $hours, $dest, $level, @modules);
1158    
1159    Turn on emergency tracing. This method is normally invoked over the web from
1160    a debugging console, but it can also be called by the C<trace.pl> script.
1161    The caller specifies the duration of the emergency in hours, the desired tracing
1162    destination, the trace level, and a list of the trace modules to activate.
1163    For the length of the duration, when a program in an environment with the
1164    specified tracing key active invokes a Sprout CGI script, tracing will be
1165    turned on automatically. See L</TSetup> for more about tracing setup and
1166    L</ETracing> for more about emergency tracing.
1167    
1168    =over 4
1169    
1170    =item tkey
1171    
1172    The tracing key. This is used to identify the control file and the trace file.
1173    
1174    =item hours
1175    
1176    Number of hours to keep emergency tracing alive.
1177    
1178    =item dest
1179    
1180    Tracing destination. If no path information is specified for a file
1181    destination, it is put in the FIG temporary directory.
1182    
1183    =item level
1184    
1185    Tracing level. A higher level means more trace messages.
1186    
1187    =item modules
1188    
1189    A list of the tracing modules to activate.
1190    
1191    =back
1192    
1193    =cut
1194    
1195    sub Emergency {
1196        # Get the parameters.
1197        my ($tkey, $hours, $dest, $level, @modules) = @_;
1198        # Create the emergency file.
1199        my $specFile = EmergencyFileName($tkey);
1200        my $outHandle = Open(undef, ">$specFile");
1201        print $outHandle join("\n", $hours, $dest, $level, @modules, "");
1202    }
1203    
1204    =head3 EmergencyKey
1205    
1206        my $tkey = EmergencyKey($parameter);
1207    
1208    Return the Key to be used for emergency tracing. This could be an IP address,
1209     a session ID, or a user name, depending on the environment.
1210    
1211    =over 4
1212    
1213    =item parameter
1214    
1215    Parameter defining the method for finding the tracing key. If it is a scalar,
1216    then it is presumed to be the tracing key itself. If it is a CGI object, then
1217    the tracing key is taken from the C<IP> cookie. Otherwise, the tracing key is
1218    taken from the C<TRACING> environment variable.
1219    
1220    =item RETURN
1221    
1222    Returns the key to be used for labels in emergency tracing.
1223    
1224    =back
1225    
1226    =cut
1227    
1228    sub EmergencyKey {
1229        # Get the parameters.
1230        my ($parameter) = @_;
1231        # Declare the return variable.
1232        my $retVal;
1233        # Determine the parameter type.
1234        if (! defined $parameter) {
1235            # Here we're supposed to check the environment. If that fails, we
1236            # get the effective login ID.
1237            $retVal = $ENV{TRACING} || scalar getpwuid($<);
1238        } else {
1239            my $ptype = ref $parameter;
1240            if ($ptype eq 'CGI') {
1241                # Here we were invoked from a web page. Look for a cookie.
1242                $retVal = $parameter->cookie('IP');
1243            } elsif (! $ptype) {
1244                # Here the key was passed in.
1245                $retVal = $parameter;
1246            }
1247        }
1248        # If no luck finding a key, use the PID.
1249        if (! defined $retVal) {
1250            $retVal = $$;
1251        }
1252        # Return the result.
1253        return $retVal;
1254    }
1255    
1256    
1257    =head3 TraceParms
1258    
1259        Tracer::TraceParms($cgi);
1260    
1261    Trace the CGI parameters at trace level CGI => 3 and the environment variables
1262    at level CGI => 4. A self-referencing URL is traced at level CGI => 2.
1263    
1264    =over 4
1265    
1266    =item cgi
1267    
1268    CGI query object containing the parameters to trace.
1269    
1270    =back
1271    
1272    =cut
1273    
1274    sub TraceParms {
1275        # Get the parameters.
1276        my ($cgi) = @_;
1277        if (T(CGI => 2)) {
1278            # Here we trace the GET-style URL for the script.
1279            Trace("[URL] " . $cgi->url(-relative => 1, -query => 1));
1280        }
1281        if (T(CGI => 3)) {
1282            # Here we want to trace the parameter data.
1283            my @names = $cgi->param;
1284            for my $parmName (sort @names) {
1285                # Note we skip the Trace parameters, which are for our use only.
1286                if ($parmName ne 'Trace' && $parmName ne 'TF') {
1287                    my @values = $cgi->param($parmName);
1288                    Trace("[CGI] $parmName = " . join(", ", @values));
1289                }
1290            }
1291            # Display the request method.
1292            my $method = $cgi->request_method();
1293            Trace("Method: $method");
1294        }
1295        if (T(CGI => 4)) {
1296            # Here we want the environment data too.
1297            for my $envName (sort keys %ENV) {
1298                Trace("[ENV] $envName = $ENV{$envName}");
1299            }
1300        }
1301    }
1302    
1303    =head3 TraceImages
1304    
1305        Tracer::TraceImages($htmlString);
1306    
1307    Trace information about all of an html document's images. The tracing
1308    will be for type "IMG" at level 3. The image's source string
1309    will be displayed. This is generally either the URL of the image or
1310    raw data for the image itself. If the source is too long, only the first 300
1311    characters will be shown at trace level 3. The entire source will be shown,
1312    however, at trace level 4. This method is not very smart, and might catch
1313    Javascript code, but it is still useful when debugging the arcane
1314    behavior of images in multiple browser environments.
1315    
1316    =over 4
1317    
1318    =item htmlString
1319    
1320    HTML text for an outgoing web page.
1321    
1322    =back
1323    
1324    =cut
1325    
1326    sub TraceImages {
1327        # Only proceed if we're at the proper trace level.
1328        if (T(IMG => 3)) {
1329            # For performance reasons we're manipulating $_[0] instead of retrieving the string
1330            # into a variable called "$htmlString". This is because we expect html strings to be
1331            # long, and don't want to copy them any more than we have to.
1332            Trace(length($_[0]) . " characters in web page.");
1333            # Loop through the HTML, culling image tags.
1334            while ($_[0] =~ /<img\s+[^>]+?src="([^"]+)"/sgi) {
1335                # Extract the source string and determine whether or not it's too long.
1336                my $srcString = $1;
1337                my $pos = pos($_[0]) - length($srcString);
1338                my $excess = length($srcString) - 300;
1339                # We'll put the display string in here.
1340                my $srcDisplay = $srcString;
1341                # If it's a data string, split it at the comma.
1342                $srcDisplay =~ s/^(data[^,]+,)/$1\n/;
1343                # If there's no excess or we're at trace level 4, we're done. At level 3 with
1344                # a long string, however, we only show the first 300 characters.
1345                if ($excess > 0 && ! T(IMG => 4)) {
1346                    $srcDisplay = substr($srcDisplay,0,300) . "\nplus $excess characters.";
1347                }
1348                # Output the trace message.
1349                Trace("Image tag at position $pos:\n$srcDisplay");
1350            }
1351        }
1352    }
1353    
1354    
1355    =head3 ScriptFinish (deprecated)
1356    
1357        ScriptFinish($webData, $varHash);
1358    
1359    Output a web page at the end of a script. Either the string to be output or the
1360    name of a template file can be specified. If the second parameter is omitted,
1361    it is assumed we have a string to be output; otherwise, it is assumed we have the
1362    name of a template file. The template should have the variable C<DebugData>
1363    specified in any form that invokes a standard script. If debugging mode is turned
1364    on, a form field will be put in that allows the user to enter tracing data.
1365    Trace messages will be placed immediately before the terminal C<BODY> tag in
1366    the output, formatted as a list.
1367    
1368    A typical standard script would loook like the following.
1369    
1370        BEGIN {
1371            # Print the HTML header.
1372            print "CONTENT-TYPE: text/html\n\n";
1373        }
1374        use Tracer;
1375        use CGI;
1376        use FIG;
1377        # ... more uses ...
1378    
1379        my ($cgi, $varHash) = ScriptSetup();
1380        eval {
1381            # ... get data from $cgi, put it in $varHash ...
1382        };
1383        if ($@) {
1384            Trace("Script Error: $@") if T(0);
1385        }
1386        ScriptFinish("Html/MyTemplate.html", $varHash);
1387    
1388    The idea here is that even if the script fails, you'll see trace messages and
1389    useful output.
1390    
1391    =over 4
1392    
1393    =item webData
1394    
1395    A string containing either the full web page to be written to the output or the
1396    name of a template file from which the page is to be constructed. If the name
1397    of a template file is specified, then the second parameter must be present;
1398    otherwise, it must be absent.
1399    
1400    =item varHash (optional)
1401    
1402    If specified, then a reference to a hash mapping variable names for a template
1403    to their values. The template file will be read into memory, and variable markers
1404    will be replaced by data in this hash reference.
1405    
1406    =back
1407    
1408    =cut
1409    
1410    sub ScriptFinish {
1411        # Get the parameters.
1412        my ($webData, $varHash) = @_;
1413        # Check for a template file situation.
1414        my $outputString;
1415        if (defined $varHash) {
1416            # Here we have a template file. We need to determine the template type.
1417            my $template;
1418            if ($FIG_Config::template_url && $webData =~ /\.php$/) {
1419                $template = "$FIG_Config::template_url/$webData";
1420            } else {
1421                $template = "<<$webData";
1422            }
1423            $outputString = PageBuilder::Build($template, $varHash, "Html");
1424        } else {
1425            # Here the user gave us a raw string.
1426            $outputString = $webData;
1427        }
1428        # Check for trace messages.
1429        if ($Destination ne "NONE" && $TraceLevel > 0) {
1430            # We have trace messages, so we want to put them at the end of the body. This
1431            # is either at the end of the whole string or at the beginning of the BODY
1432            # end-tag.
1433            my $pos = length $outputString;
1434            if ($outputString =~ m#</body>#gi) {
1435                $pos = (pos $outputString) - 7;
1436            }
1437            # If the trace messages were queued, we unroll them. Otherwise, we display the
1438            # destination.
1439            my $traceHtml;
1440            if ($Destination eq "QUEUE") {
1441                $traceHtml = QTrace('Html');
1442            } elsif ($Destination =~ /^>>(.+)$/) {
1443                # Here the tracing output it to a file. We code it as a hyperlink so the user
1444                # can copy the file name into the clipboard easily.
1445                my $actualDest = $1;
1446                $traceHtml = "<p>Tracing output to $actualDest.</p>\n";
1447            } else {
1448                # Here we have one of the special destinations.
1449                $traceHtml = "<P>Tracing output type is $Destination.</p>\n";
1450            }
1451            substr $outputString, $pos, 0, $traceHtml;
1452        }
1453        # Write the output string.
1454        print $outputString;
1455    }
1456    
1457    =head2 Command-Line Utility Methods
1458    
1459    =head3 SendSMS
1460    
1461        my $msgID = Tracer::SendSMS($phoneNumber, $msg);
1462    
1463    Send a text message to a phone number using Clickatell. The FIG_Config file must contain the
1464    user name, password, and API ID for the relevant account in the hash reference variable
1465    I<$FIG_Config::phone>, using the keys C<user>, C<password>, and C<api_id>. For
1466    example, if the user name is C<BruceTheHumanPet>, the password is C<silly>, and the API ID
1467    is C<2561022>, then the FIG_Config file must contain
1468    
1469        $phone =  { user => 'BruceTheHumanPet',
1470                    password => 'silly',
1471                    api_id => '2561022' };
1472    
1473    The original purpose of this method was to insure Bruce would be notified immediately when the
1474    Sprout Load terminates. Care should be taken if you do not wish Bruce to be notified immediately
1475    when you call this method.
1476    
1477    The message ID will be returned if successful, and C<undef> if an error occurs.
1478    
1479    =over 4
1480    
1481    =item phoneNumber
1482    
1483    Phone number to receive the message, in international format. A United States phone number
1484    would be prefixed by "1". A British phone number would be prefixed by "44".
1485    
1486    =item msg
1487    
1488    Message to send to the specified phone.
1489    
1490    =item RETURN
1491    
1492    Returns the message ID if successful, and C<undef> if the message could not be sent.
1493    
1494    =back
1495    
1496    =cut
1497    
1498    sub SendSMS {
1499        # Get the parameters.
1500        my ($phoneNumber, $msg) = @_;
1501        # Declare the return variable. If we do not change it, C<undef> will be returned.
1502        my $retVal;
1503        # Only proceed if we have phone support.
1504        if (! defined $FIG_Config::phone) {
1505            Trace("Phone support not present in FIG_Config.") if T(1);
1506        } else {
1507            # Get the phone data.
1508            my $parms = $FIG_Config::phone;
1509            # Get the Clickatell URL.
1510            my $url = "http://api.clickatell.com/http/";
1511            # Create the user agent.
1512            my $ua = LWP::UserAgent->new;
1513            # Request a Clickatell session.
1514            my $resp = $ua->post("$url/sendmsg", { user => $parms->{user},
1515                                         password => $parms->{password},
1516                                         api_id => $parms->{api_id},
1517                                         to => $phoneNumber,
1518                                         text => $msg});
1519            # Check for an error.
1520            if (! $resp->is_success) {
1521                Trace("Alert failed.") if T(1);
1522            } else {
1523                # Get the message ID.
1524                my $rstring = $resp->content;
1525                if ($rstring =~ /^ID:\s+(.*)$/) {
1526                    $retVal = $1;
1527                } else {
1528                    Trace("Phone attempt failed with $rstring") if T(1);
1529                }
1530            }
1531        }
1532        # Return the result.
1533        return $retVal;
1534    }
1535    
1536    =head3 StandardSetup
1537    
1538        my ($options, @parameters) = StandardSetup(\@categories, \%options, $parmHelp, @ARGV);
1539    
1540    This method performs standard command-line parsing and tracing setup. The return
1541    values are a hash of the command-line options and a list of the positional
1542    parameters. Tracing is automatically set up and the command-line options are
1543    validated.
1544    
1545    This is a complex method that does a lot of grunt work. The parameters can
1546    be more easily understood, however, once they are examined individually.
1547    
1548    The I<categories> parameter is the most obtuse. It is a reference to a list of
1549    special-purpose tracing categories. Most tracing categories are PERL package
1550    names. So, for example, if you wanted to turn on tracing inside the B<Sprout>,
1551    B<ERDB>, and B<SproutLoad> packages, you would specify the categories
1552    
1553        ["Sprout", "SproutLoad", "ERDB"]
1554    
1555    This would cause trace messages in the specified three packages to appear in
1556    the output. There are two special tracing categories that are automatically
1557    handled by this method. In other words, if you used L</TSetup> you would need
1558    to include these categories manually, but if you use this method they are turned
1559    on automatically.
1560    
1561    =over 4
1562    
1563    =item SQL
1564    
1565    Traces SQL commands and activity.
1566    
1567    =item Tracer
1568    
1569    Traces error messages and call stacks.
1570    
1571    =back
1572    
1573    C<SQL> is only turned on if the C<-sql> option is specified in the command line.
1574    The trace level is specified using the C<-trace> command-line option. For example,
1575    the following command line for C<TransactFeatures> turns on SQL tracing and runs
1576    all tracing at level 3.
1577    
1578        TransactFeatures -trace=3 -sql register ../xacts IDs.tbl
1579    
1580    Standard tracing is output to the standard output and echoed to the file
1581    C<trace>I<$$>C<.log> in the FIG temporary directory, where I<$$> is the
1582    process ID. You can also specify the C<user> parameter to put a user ID
1583    instead of a process ID in the trace file name. So, for example
1584    
1585    The default trace level is 2. To get all messages, specify a trace level of 4.
1586    For a genome-by-genome update, use 3.
1587    
1588        TransactFeatures -trace=3 -sql -user=Bruce register ../xacts IDs.tbl
1589    
1590    would send the trace output to C<traceBruce.log> in the temporary directory.
1591    
1592    The I<options> parameter is a reference to a hash containing the command-line
1593    options, their default values, and an explanation of what they mean. Command-line
1594    options may be in the form of switches or keywords. In the case of a switch, the
1595    option value is 1 if it is specified and 0 if it is not specified. In the case
1596    of a keyword, the value is separated from the option name by an equal sign. You
1597    can see this last in the command-line example above.
1598    
1599    You can specify a different default trace level by setting C<$options->{trace}>
1600    prior to calling this method.
1601    
1602    An example at this point would help. Consider, for example, the command-line utility
1603    C<TransactFeatures>. It accepts a list of positional parameters plus the options
1604    C<safe>, C<noAlias>, C<start>, and C<tblFiles>. To start up this command, we execute
1605    the following code.
1606    
1607        my ($options, @parameters) = Tracer::StandardSetup(["DocUtils"],
1608                            { safe => [0, "use database transactions"],
1609                              noAlias => [0, "do not expect aliases in CHANGE transactions"],
1610                              start => [' ', "start with this genome"],
1611                              tblFiles => [0, "output TBL files containing the corrected IDs"] },
1612                            "<command> <transactionDirectory> <IDfile>",
1613                          @ARGV);
1614    
1615    
1616    The call to C<ParseCommand> specifies the default values for the options and
1617    stores the actual options in a hash that is returned as C<$options>. The
1618    positional parameters are returned in C<@parameters>.
1619    
1620    The following is a sample command line for C<TransactFeatures>.
1621    
1622        TransactFeatures -trace=2 -noAlias register ../xacts IDs.tbl
1623    
1624    Single and double hyphens are equivalent. So, you could also code the
1625    above command as
1626    
1627        TransactFeatures --trace=2 --noAlias register ../xacts IDs.tbl
1628    
1629    In this case, C<register>, C<../xacts>, and C<IDs.tbl> are the positional
1630    parameters, and would find themselves in I<@parameters> after executing the
1631    above code fragment. The tracing would be set to level 2, and the categories
1632    would be C<Tracer>, and <DocUtils>. C<Tracer> is standard,
1633    and C<DocUtils> was included because it came in within the first parameter
1634    to this method. The I<$options> hash would be
1635    
1636        { trace => 2, sql => 0, safe => 0,
1637          noAlias => 1, start => ' ', tblFiles => 0 }
1638    
1639    Use of C<StandardSetup> in this way provides a simple way of performing
1640    standard tracing setup and command-line parsing. Note that the caller is
1641    not even aware of the command-line switches C<-trace> and C<-sql>, which
1642    are used by this method to control the tracing. If additional tracing features
1643    need to be added in the future, they can be processed by this method without
1644    upsetting the command-line utilities.
1645    
1646    If the C<background> option is specified on the command line, then the
1647    standard and error outputs will be directed to files in the temporary
1648    directory, using the same suffix as the trace file. So, if the command
1649    line specified
1650    
1651        -user=Bruce -background
1652    
1653    then the trace output would go to C<traceBruce.log>, the standard output to
1654    C<outBruce.log>, and the error output to C<errBruce.log>. This is designed to
1655    simplify starting a command in the background.
1656    
1657    The user name is also used as the tracing key for L</Emergency Tracing>.
1658    Specifying a value of C<E> for the trace level causes emergency tracing to
1659    be used instead of custom tracing. If the user name is not specified,
1660    the tracing key is taken from the C<Tracing> environment variable. If there
1661    is no value for that variable, the tracing key will be computed from the active
1662    login ID.
1663    
1664    Since the default situation in StandardSetup is to trace to the standard
1665    output, errors that occur in command-line scripts will not generate
1666    RSS events. To force the events, use the C<warn> option.
1667    
1668        TransactFeatures -background -warn register ../xacts IDs.tbl
1669    
1670    Finally, if the special option C<-help> is specified, the option
1671    names will be traced at level 0 and the program will exit without processing.
1672    This provides a limited help capability. For example, if the user enters
1673    
1674        TransactFeatures -help
1675    
1676    he would see the following output.
1677    
1678        TransactFeatures [options] <command> <transactionDirectory> <IDfile>
1679            -trace    tracing level (default E)
1680            -sql      trace SQL commands
1681            -safe     use database transactions
1682            -noAlias  do not expect aliases in CHANGE transactions
1683            -start    start with this genome
1684            -tblFiles output TBL files containing the corrected IDs
1685    
1686    The caller has the option of modifying the tracing scheme by placing a value
1687    for C<trace> in the incoming options hash. The default value can be overridden,
1688    or the tracing to the standard output can be turned off by suffixing a minus
1689    sign to the trace level. So, for example,
1690    
1691        { trace => [0, "tracing level (default 0)"],
1692           ...
1693    
1694    would set the default trace level to 0 instead of E, while
1695    
1696        { trace => ["2-", "tracing level (default 2)"],
1697           ...
1698    
1699    would set the default to 2, but trace only to the log file, not to the
1700    standard output.
1701    
1702    The parameters to this method are as follows.
1703    
1704    =over 4
1705    
1706    =item categories
1707    
1708    Reference to a list of tracing category names. These should be names of
1709    packages whose internal workings will need to be debugged to get the
1710    command working.
1711    
1712    =item options
1713    
1714    Reference to a hash containing the legal options for the current command mapped
1715    to their default values and descriptions. The user can override the defaults
1716    by specifying the options as command-line switches prefixed by a hyphen.
1717    Tracing-related options may be added to this hash. If the C<-h> option is
1718    specified on the command line, the option descriptions will be used to
1719    explain the options. To turn off tracing to the standard output, add a
1720    minus sign to the value for C<trace> (see above).
1721    
1722    =item parmHelp
1723    
1724    A string that vaguely describes the positional parameters. This is used
1725    if the user specifies the C<-h> option.
1726    
1727    =item argv
1728    
1729    List of command line parameters, including the option switches, which must
1730    precede the positional parameters and be prefixed by a hyphen.
1731    
1732    =item RETURN
1733    
1734    Returns a list. The first element of the list is the reference to a hash that
1735    maps the command-line option switches to their values. These will either be the
1736    default values or overrides specified on the command line. The remaining
1737    elements of the list are the position parameters, in order.
1738    
1739    =back
1740    
1741    =cut
1742    
1743    sub StandardSetup {
1744        # Get the parameters.
1745        my ($categories, $options, $parmHelp, @argv) = @_;
1746        # Get the default tracing key.
1747        my $tkey = EmergencyKey();
1748        # Add the tracing options.
1749        if (! exists $options->{trace}) {
1750            $options->{trace} = ['2', "tracing level (E for emergency tracing)"];
1751        }
1752        $options->{sql} = [0, "turn on SQL tracing"];
1753        $options->{help} = [0, "display command-line options"];
1754        $options->{user} = [$tkey, "tracing key"];
1755        $options->{background} = [0, "spool standard and error output"];
1756        $options->{warn} = [0, "send errors to RSS feed"];
1757        # Create a parsing hash from the options hash. The parsing hash
1758        # contains the default values rather than the default value
1759        # and the description. While we're at it, we'll memorize the
1760        # length of the longest option name.
1761        my $longestName = 0;
1762        my %parseOptions = ();
1763        for my $key (keys %{$options}) {
1764            if (length $key > $longestName) {
1765                $longestName = length $key;
1766            }
1767            $parseOptions{$key} = $options->{$key}->[0];
1768        }
1769        # Parse the command line.
1770        my ($retOptions, @retParameters) = ParseCommand(\%parseOptions, @argv);
1771        # Get the logfile suffix.
1772        my $suffix = $retOptions->{user};
1773        # Check for background mode.
1774        if ($retOptions->{background}) {
1775            my $outFileName = "$FIG_Config::temp/out$suffix.log";
1776            my $errFileName = "$FIG_Config::temp/err$suffix.log";
1777            open STDOUT, ">$outFileName";
1778            open STDERR, ">$errFileName";
1779            # Check for phone support. If we have phone support and a phone number,
1780            # we want to turn it on.
1781            if ($ENV{PHONE} && defined($FIG_Config::phone)) {
1782                $retOptions->{phone} = $ENV{PHONE};
1783            }
1784        }
1785        # Now we want to set up tracing. First, we need to know if the user
1786        # wants emergency tracing.
1787        if ($retOptions->{trace} eq 'E') {
1788            ETracing($retOptions->{user});
1789        } else {
1790            # Here the tracing is controlled from the command line.
1791            my @cats = @{$categories};
1792            if ($retOptions->{sql}) {
1793                push @cats, "SQL";
1794            }
1795            if ($retOptions->{warn}) {
1796                push @cats, "Feed";
1797            }
1798            # Add the default categories.
1799            push @cats, "Tracer";
1800            # Next, we create the category string by joining the categories.
1801            my $cats = join(" ", @cats);
1802            # Check to determine whether or not the caller wants to turn off tracing
1803            # to the standard output.
1804            my $traceLevel = $retOptions->{trace};
1805            my $textOKFlag = 1;
1806            if ($traceLevel =~ /^(.)-/) {
1807                $traceLevel = $1;
1808                $textOKFlag = 0;
1809            }
1810            # Now we set up the trace mode.
1811            my $traceMode;
1812            # Verify that we can open a file in the FIG temporary directory.
1813            my $traceFileName = "$FIG_Config::temp/trace$suffix.log";
1814            if (open TESTTRACE, ">$traceFileName") {
1815                # Here we can trace to a file.
1816                $traceMode = ">$traceFileName";
1817                if ($textOKFlag) {
1818                    # Echo to standard output if the text-OK flag is set.
1819                    $traceMode = "+$traceMode";
1820                }
1821                # Close the test file.
1822                close TESTTRACE;
1823            } else {
1824                # Here we can't trace to a file. Complain about this.
1825                warn "Could not open trace file $traceFileName: $!\n";
1826                # We trace to the standard output if it's
1827                # okay, and the error log otherwise.
1828                if ($textOKFlag) {
1829                    $traceMode = "TEXT";
1830                } else {
1831                    $traceMode = "WARN";
1832                }
1833            }
1834            # Now set up the tracing.
1835            TSetup("$traceLevel $cats", $traceMode);
1836        }
1837        # Check for the "help" option. If it is specified, dump the command-line
1838        # options and exit the program.
1839        if ($retOptions->{help}) {
1840            $0 =~ m#[/\\](\w+)(\.pl)?$#i;
1841            print "$1 [options] $parmHelp\n";
1842            for my $key (sort keys %{$options}) {
1843                my $name = Pad($key, $longestName, 0, ' ');
1844                my $desc = $options->{$key}->[1];
1845                if ($options->{$key}->[0]) {
1846                    $desc .= " (default " . $options->{$key}->[0] . ")";
1847                }
1848                print "  $name $desc\n";
1849            }
1850            exit(0);
1851        }
1852        # Trace the options, if applicable.
1853        if (T(3)) {
1854            my @parms = grep { $retOptions->{$_} } keys %{$retOptions};
1855            Trace("Selected options: " . join(", ", sort @parms) . ".");
1856        }
1857        # Return the parsed parameters.
1858        return ($retOptions, @retParameters);
1859    }
1860    
1861    =head3 ReadOptions
1862    
1863        my %options = Tracer::ReadOptions($fileName);
1864    
1865    Read a set of options from a file. Each option is encoded in a line of text that has the
1866    format
1867    
1868    I<optionName>C<=>I<optionValue>C<; >I<comment>
1869    
1870    The option name must consist entirely of letters, digits, and the punctuation characters
1871    C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank
1872    character is a semi-colon will be ignored. The return hash will map each option name to
1873    the corresponding option value.
1874    
1875    =over 4
1876    
1877    =item fileName
1878    
1879    Name of the file containing the option data.
1880    
1881    =item RETURN
1882    
1883    Returns a hash mapping the option names specified in the file to their corresponding option
1884    value.
1885    
1886    =back
1887    
1888    =cut
1889    
1890    sub ReadOptions {
1891        # Get the parameters.
1892        my ($fileName) = @_;
1893        # Open the file.
1894        (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");
1895        # Count the number of records read.
1896        my ($records, $comments) = 0;
1897        # Create the return hash.
1898        my %retVal = ();
1899        # Loop through the file, accumulating key-value pairs.
1900        while (my $line = <CONFIGFILE>) {
1901            # Denote we've read a line.
1902            $records++;
1903            # Determine the line type.
1904            if ($line =~ /^\s*[\n\r]/) {
1905                # A blank line is a comment.
1906                $comments++;
1907            } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {
1908                # Here we have an option assignment.
1909                retVal{$1} = $2;
1910            } elsif ($line =~ /^\s*;/) {
1911                # Here we have a text comment.
1912                $comments++;
1913            } else {
1914                # Here we have an invalid line.
1915                Trace("Invalid option statement in record $records.") if T(0);
1916            }
1917        }
1918        # Return the hash created.
1919        return %retVal;
1920    }
1921    
1922    =head3 GetOptions
1923    
1924        Tracer::GetOptions(\%defaults, \%options);
1925    
1926    Merge a specified set of options into a table of defaults. This method takes two hash references
1927    as input and uses the data from the second to update the first. If the second does not exist,
1928    there will be no effect. An error will be thrown if one of the entries in the second hash does not
1929    exist in the first.
1930    
1931    Consider the following example.
1932    
1933        my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options);
1934    
1935    In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and
1936    B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of
1937    B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and
1938    the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level
1939    will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as
1940    
1941        {databaseType => 'Oracle'}
1942    
1943    an error will occur because the B<databaseType> option does not exist.
1944    
1945    =over 4
1946    
1947    =item defaults
1948    
1949    Table of default option values.
1950    
1951    =item options
1952    
1953    Table of overrides, if any.
1954    
1955    =item RETURN
1956    
1957    Returns a reference to the default table passed in as the first parameter.
1958    
1959    =back
1960    
1961    =cut
1962    
1963    sub GetOptions {
1964        # Get the parameters.
1965        my ($defaults, $options) = @_;
1966        # Check for overrides.
1967        if ($options) {
1968            # Loop through the overrides.
1969            while (my ($option, $setting) = each %{$options}) {
1970                # Insure this override exists.
1971                if (!exists $defaults->{$option}) {
1972                    croak "Unrecognized option $option encountered.";
1973                } else {
1974                    # Apply the override.
1975                    $defaults->{$option} = $setting;
1976                }
1977            }
1978        }
1979        # Return the merged table.
1980        return $defaults;
1981    }
1982    
1983    =head3 MergeOptions
1984    
1985        Tracer::MergeOptions(\%table, \%defaults);
1986    
1987    Merge default values into a hash table. This method looks at the key-value pairs in the
1988    second (default) hash, and if a matching key is not found in the first hash, the default
1989    pair is copied in. The process is similar to L</GetOptions>, but there is no error-
1990    checking and no return value.
1991    
1992    =over 4
1993    
1994    =item table
1995    
1996    Hash table to be updated with the default values.
1997    
1998    =item defaults
1999    
2000    Default values to be merged into the first hash table if they are not already present.
2001    
2002    =back
2003    
2004    =cut
2005    
2006    sub MergeOptions {
2007        # Get the parameters.
2008        my ($table, $defaults) = @_;
2009        # Loop through the defaults.
2010        while (my ($key, $value) = each %{$defaults}) {
2011            if (!exists $table->{$key}) {
2012                $table->{$key} = $value;
2013            }
2014        }
2015    }
2016    
2017    =head3 ParseCommand
2018    
2019        my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList);
2020    
2021    Parse a command line consisting of a list of parameters. The initial parameters may be option
2022    specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped
2023    off and merged into a table of default options. The remainder of the command line is
2024    returned as a list of positional arguments. For example, consider the following invocation.
2025    
2026        my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words);
2027    
2028    In this case, the list @words will be treated as a command line and there are two options available,
2029    B<errors> and B<logFile>. If @words has the following format
2030    
2031        -logFile=error.log apple orange rutabaga
2032    
2033    then at the end of the invocation, C<$options> will be
2034    
2035        { errors => 0, logFile => 'error.log' }
2036    
2037    and C<@arguments> will contain
2038    
2039        apple orange rutabaga
2040    
2041    The parser allows for some escape sequences. See L</UnEscape> for a description. There is no
2042    support for quote characters. Options can be specified with single or double hyphens.
2043    
2044    =over 4
2045    
2046    =item optionTable
2047    
2048    Table of default options.
2049    
2050    =item inputList
2051    
2052    List of words on the command line.
2053    
2054    =item RETURN
2055    
2056    Returns a reference to the option table and a list of the positional arguments.
2057    
2058    =back
2059    
2060    =cut
2061    
2062    sub ParseCommand {
2063        # Get the parameters.
2064        my ($optionTable, @inputList) = @_;
2065        # Process any options in the input list.
2066          my %overrides = ();          my %overrides = ();
2067          while ((@inputList > 0) && ($inputList[0] =~ /^-/)) {      while ((@inputList > 0) && ($inputList[0] =~ /^--?/)) {
2068                  # Get the current option.                  # Get the current option.
2069                  my $arg = shift @inputList;                  my $arg = shift @inputList;
2070                  # Pull out the option name.                  # Pull out the option name.
2071                  $arg =~ /^-([^=]*)/g;          $arg =~ /^--?([^=]*)/g;
2072                  my $name = $1;                  my $name = $1;
2073                  # Check for an option value.                  # Check for an option value.
2074                  if ($arg =~ /\G=(.*)$/g) {                  if ($arg =~ /\G=(.*)$/g) {
2075                          # Here we have a value for the option.                          # Here we have a value for the option.
2076                          $overrides{$name} = UnEscape($1);                          $overrides{$name} = UnEscape($1);
2077                  } else {                  } else {
2078                          # Here there is no value, so we use 1.              # Here there is no value, so we use 1.
2079                          $overrides{$name} = 1;              $overrides{$name} = 1;
2080            }
2081        }
2082        # Merge the options into the defaults.
2083        GetOptions($optionTable, \%overrides);
2084        # Translate the remaining parameters.
2085        my @retVal = ();
2086        for my $inputParm (@inputList) {
2087            push @retVal, UnEscape($inputParm);
2088        }
2089        # Return the results.
2090        return ($optionTable, @retVal);
2091    }
2092    
2093    
2094    =head2 File Utility Methods
2095    
2096    =head3 GetFile
2097    
2098        my @fileContents = Tracer::GetFile($fileName);
2099    
2100        or
2101    
2102        my $fileContents = Tracer::GetFile($fileName);
2103    
2104    Return the entire contents of a file. In list context, line-ends are removed and
2105    each line is a list element. In scalar context, line-ends are replaced by C<\n>.
2106    
2107    =over 4
2108    
2109    =item fileName
2110    
2111    Name of the file to read.
2112    
2113    =item RETURN
2114    
2115    In a list context, returns the entire file as a list with the line terminators removed.
2116    In a scalar context, returns the entire file as a string. If an error occurs opening
2117    the file, an empty list will be returned.
2118    
2119    =back
2120    
2121    =cut
2122    
2123    sub GetFile {
2124        # Get the parameters.
2125        my ($fileName) = @_;
2126        # Declare the return variable.
2127        my @retVal = ();
2128        # Open the file for input.
2129        my $handle = Open(undef, "<$fileName");
2130        # Read the whole file into the return variable, stripping off any terminator
2131        # characters.
2132        my $lineCount = 0;
2133        while (my $line = <$handle>) {
2134            $lineCount++;
2135            $line = Strip($line);
2136            push @retVal, $line;
2137        }
2138        # Close it.
2139        close $handle;
2140        my $actualLines = @retVal;
2141        Trace("$actualLines lines read from file $fileName.") if T(File => 2);
2142        # Return the file's contents in the desired format.
2143        if (wantarray) {
2144            return @retVal;
2145        } else {
2146            return join "\n", @retVal;
2147        }
2148    }
2149    
2150    =head3 PutFile
2151    
2152        Tracer::PutFile($fileName, \@lines);
2153    
2154    Write out a file from a list of lines of text.
2155    
2156    =over 4
2157    
2158    =item fileName
2159    
2160    Name of the output file.
2161    
2162    =item lines
2163    
2164    Reference to a list of text lines. The lines will be written to the file in order, with trailing
2165    new-line characters. Alternatively, may be a string, in which case the string will be written without
2166    modification.
2167    
2168    =back
2169    
2170    =cut
2171    
2172    sub PutFile {
2173        # Get the parameters.
2174        my ($fileName, $lines) = @_;
2175        # Open the output file.
2176        my $handle = Open(undef, ">$fileName");
2177        # Count the lines written.
2178        if (ref $lines ne 'ARRAY') {
2179            # Here we have a scalar, so we write it raw.
2180            print $handle $lines;
2181            Trace("Scalar put to file $fileName.") if T(File => 3);
2182        } else {
2183            # Write the lines one at a time.
2184            my $count = 0;
2185            for my $line (@{$lines}) {
2186                print $handle "$line\n";
2187                $count++;
2188            }
2189            Trace("$count lines put to file $fileName.") if T(File => 3);
2190        }
2191        # Close the output file.
2192        close $handle;
2193    }
2194    
2195    =head3 ParseRecord
2196    
2197        my @fields = Tracer::ParseRecord($line);
2198    
2199    Parse a tab-delimited data line. The data line is split into field values. Embedded tab
2200    and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.
2201    These will automatically be converted.
2202    
2203    =over 4
2204    
2205    =item line
2206    
2207    Line of data containing the tab-delimited fields.
2208    
2209    =item RETURN
2210    
2211    Returns a list of the fields found in the data line.
2212    
2213    =back
2214    
2215    =cut
2216    
2217    sub ParseRecord {
2218        # Get the parameter.
2219        my ($line) = @_;
2220        # Remove the trailing new-line, if any.
2221        chomp $line;
2222        # Split the line read into pieces using the tab character.
2223        my @retVal = split /\t/, $line;
2224        # Trim and fix the escapes in each piece.
2225        for my $value (@retVal) {
2226            # Trim leading whitespace.
2227            $value =~ s/^\s+//;
2228            # Trim trailing whitespace.
2229            $value =~ s/\s+$//;
2230            # Delete the carriage returns.
2231            $value =~ s/\r//g;
2232            # Convert the escapes into their real values.
2233            $value =~ s/\\t/"\t"/ge;
2234            $value =~ s/\\n/"\n"/ge;
2235        }
2236        # Return the result.
2237        return @retVal;
2238    }
2239    
2240    =head3 Merge
2241    
2242        my @mergedList = Tracer::Merge(@inputList);
2243    
2244    Sort a list of strings and remove duplicates.
2245    
2246    =over 4
2247    
2248    =item inputList
2249    
2250    List of scalars to sort and merge.
2251    
2252    =item RETURN
2253    
2254    Returns a list containing the same elements sorted in ascending order with duplicates
2255    removed.
2256    
2257    =back
2258    
2259    =cut
2260    
2261    sub Merge {
2262        # Get the input list in sort order.
2263        my @inputList = sort @_;
2264        # Only proceed if the list has at least two elements.
2265        if (@inputList > 1) {
2266            # Now we want to move through the list splicing out duplicates.
2267            my $i = 0;
2268            while ($i < @inputList) {
2269                # Get the current entry.
2270                my $thisEntry = $inputList[$i];
2271                # Find out how many elements duplicate the current entry.
2272                my $j = $i + 1;
2273                my $dup1 = $i + 1;
2274                while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };
2275                # If the number is nonzero, splice out the duplicates found.
2276                if ($j > $dup1) {
2277                    splice @inputList, $dup1, $j - $dup1;
2278                }
2279                # Now the element at position $dup1 is different from the element before it
2280                # at position $i. We push $i forward one position and start again.
2281                $i++;
2282            }
2283        }
2284        # Return the merged list.
2285        return @inputList;
2286    }
2287    
2288    =head3 Open
2289    
2290        my $handle = Open($fileHandle, $fileSpec, $message);
2291    
2292    Open a file.
2293    
2294    The I<$fileSpec> is essentially the second argument of the PERL C<open>
2295    function. The mode is specified using Unix-like shell information. So, for
2296    example,
2297    
2298        Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2299    
2300    would open for output appended to the specified file, and
2301    
2302        Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");
2303    
2304    would open a pipe that sorts the records written and removes duplicates. Note
2305    the use of file handle syntax in the Open call. To use anonymous file handles,
2306    code as follows.
2307    
2308        my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2309    
2310    The I<$message> parameter is used if the open fails. If it is set to C<0>, then
2311    the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a
2312    failed open will throw an exception and the third parameter will be used to construct
2313    an error message. If the parameter is omitted, a standard message is constructed
2314    using the file spec.
2315    
2316        Could not open "/usr/spool/news/twitlog"
2317    
2318    Note that the mode characters are automatically cleaned from the file name.
2319    The actual error message from the file system will be captured and appended to the
2320    message in any case.
2321    
2322        Could not open "/usr/spool/news/twitlog": file not found.
2323    
2324    In some versions of PERL the only error message we get is a number, which
2325    corresponds to the C++ C<errno> value.
2326    
2327        Could not open "/usr/spool/news/twitlog": 6.
2328    
2329    =over 4
2330    
2331    =item fileHandle
2332    
2333    File handle. If this parameter is C<undef>, a file handle will be generated
2334    and returned as the value of this method.
2335    
2336    =item fileSpec
2337    
2338    File name and mode, as per the PERL C<open> function.
2339    
2340    =item message (optional)
2341    
2342    Error message to use if the open fails. If omitted, a standard error message
2343    will be generated. In either case, the error information from the file system
2344    is appended to the message. To specify a conditional open that does not throw
2345    an error if it fails, use C<0>.
2346    
2347    =item RETURN
2348    
2349    Returns the name of the file handle assigned to the file, or C<undef> if the
2350    open failed.
2351    
2352    =back
2353    
2354    =cut
2355    
2356    sub Open {
2357        # Get the parameters.
2358        my ($fileHandle, $fileSpec, $message) = @_;
2359        # Attempt to open the file.
2360        my $rv = open $fileHandle, $fileSpec;
2361        # If the open failed, generate an error message.
2362        if (! $rv) {
2363            # Save the system error message.
2364            my $sysMessage = $!;
2365            # See if we need a default message.
2366            if (!$message) {
2367                # Clean any obvious mode characters and leading spaces from the
2368                # filename.
2369                my ($fileName) = FindNamePart($fileSpec);
2370                $message = "Could not open \"$fileName\"";
2371            }
2372            # Terminate with an error using the supplied message and the
2373            # error message from the file system.
2374            Confess("$message: $!");
2375        }
2376        # Return the file handle.
2377        return $fileHandle;
2378    }
2379    
2380    =head3 FindNamePart
2381    
2382        my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec);
2383    
2384    Extract the portion of a file specification that contains the file name.
2385    
2386    A file specification is the string passed to an C<open> call. It specifies the file
2387    mode and name. In a truly complex situation, it can specify a pipe sequence. This
2388    method assumes that the file name is whatever follows the first angle bracket
2389    sequence.  So, for example, in the following strings the file name is
2390    C</usr/fig/myfile.txt>.
2391    
2392        >>/usr/fig/myfile.txt
2393        </usr/fig/myfile.txt
2394        | sort -u > /usr/fig/myfile.txt
2395    
2396    If the method cannot find a file name using its normal methods, it will return the
2397    whole incoming string.
2398    
2399    =over 4
2400    
2401    =item fileSpec
2402    
2403    File specification string from which the file name is to be extracted.
2404    
2405    =item RETURN
2406    
2407    Returns a three-element list. The first element contains the file name portion of
2408    the specified string, or the whole string if a file name cannot be found via normal
2409    methods. The second element contains the start position of the file name portion and
2410    the third element contains the length.
2411    
2412    =back
2413    
2414    =cut
2415    #: Return Type $;
2416    sub FindNamePart {
2417        # Get the parameters.
2418        my ($fileSpec) = @_;
2419        # Default to the whole input string.
2420        my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);
2421        # Parse out the file name if we can.
2422        if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {
2423            $retVal = $2;
2424            $len = length $retVal;
2425            $pos = (length $fileSpec) - (length $3) - $len;
2426        }
2427        # Return the result.
2428        return ($retVal, $pos, $len);
2429    }
2430    
2431    =head3 OpenDir
2432    
2433        my @files = OpenDir($dirName, $filtered, $flag);
2434    
2435    Open a directory and return all the file names. This function essentially performs
2436    the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is
2437    set to TRUE, all filenames beginning with a period (C<.>), dollar sign (C<$>),
2438    or pound sign (C<#>) and all filenames ending with a tilde C<~>) will be
2439    filtered out of the return list. If the directory does not open and I<$flag> is not
2440    set, an exception is thrown. So, for example,
2441    
2442        my @files = OpenDir("/Volumes/fig/contigs", 1);
2443    
2444    is effectively the same as
2445    
2446        opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");
2447        my @files = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir(TMP);
2448    
2449    Similarly, the following code
2450    
2451        my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs", 0, 1);
2452    
2453    Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and
2454    automatically returns an empty list if the directory fails to open.
2455    
2456    =over 4
2457    
2458    =item dirName
2459    
2460    Name of the directory to open.
2461    
2462    =item filtered
2463    
2464    TRUE if files whose names begin with a period (C<.>) should be automatically removed
2465    from the list, else FALSE.
2466    
2467    =item flag
2468    
2469    TRUE if a failure to open is okay, else FALSE
2470    
2471    =back
2472    
2473    =cut
2474    #: Return Type @;
2475    sub OpenDir {
2476        # Get the parameters.
2477        my ($dirName, $filtered, $flag) = @_;
2478        # Declare the return variable.
2479        my @retVal = ();
2480        # Open the directory.
2481        if (opendir(my $dirHandle, $dirName)) {
2482            # The directory opened successfully. Get the appropriate list according to the
2483            # strictures of the filter parameter.
2484            if ($filtered) {
2485                @retVal = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir $dirHandle;
2486            } else {
2487                @retVal = readdir $dirHandle;
2488            }
2489        } elsif (! $flag) {
2490            # Here the directory would not open and it's considered an error.
2491            Confess("Could not open directory $dirName.");
2492        }
2493        # Return the result.
2494        return @retVal;
2495    }
2496    
2497    
2498    =head3 Insure
2499    
2500        Insure($dirName, $chmod);
2501    
2502    Insure a directory is present.
2503    
2504    =over 4
2505    
2506    =item dirName
2507    
2508    Name of the directory to check. If it does not exist, it will be created.
2509    
2510    =item chmod (optional)
2511    
2512    Security privileges to be given to the directory if it is created.
2513    
2514    =back
2515    
2516    =cut
2517    
2518    sub Insure {
2519        my ($dirName, $chmod) = @_;
2520        if (! -d $dirName) {
2521            Trace("Creating $dirName directory.") if T(2);
2522            eval {
2523                mkpath $dirName;
2524                # If we have permissions specified, set them here.
2525                if (defined($chmod)) {
2526                    chmod $chmod, $dirName;
2527                }
2528            };
2529            if ($@) {
2530                Confess("Error creating $dirName: $@");
2531            }
2532        }
2533    }
2534    
2535    =head3 ChDir
2536    
2537        ChDir($dirName);
2538    
2539    Change to the specified directory.
2540    
2541    =over 4
2542    
2543    =item dirName
2544    
2545    Name of the directory to which we want to change.
2546    
2547    =back
2548    
2549    =cut
2550    
2551    sub ChDir {
2552        my ($dirName) = @_;
2553        if (! -d $dirName) {
2554            Confess("Cannot change to directory $dirName: no such directory.");
2555        } else {
2556            Trace("Changing to directory $dirName.") if T(File => 4);
2557            my $okFlag = chdir $dirName;
2558            if (! $okFlag) {
2559                Confess("Error switching to directory $dirName.");
2560            }
2561        }
2562    }
2563    
2564    =head3 SetPermissions
2565    
2566        Tracer::SetPermissions($dirName, $group, $mask, %otherMasks);
2567    
2568    Set the permissions for a directory and all the files and folders inside it.
2569    In addition, the group ownership will be changed to the specified value.
2570    
2571    This method is more vulnerable than most to permission and compatability
2572    problems, so it does internal error recovery.
2573    
2574    =over 4
2575    
2576    =item dirName
2577    
2578    Name of the directory to process.
2579    
2580    =item group
2581    
2582    Name of the group to be assigned.
2583    
2584    =item mask
2585    
2586    Permission mask. Bits that are C<1> in this mask will be ORed into the
2587    permission bits of any file or directory that does not already have them
2588    set to 1.
2589    
2590    =item otherMasks
2591    
2592    Map of search patterns to permission masks. If a directory name matches
2593    one of the patterns, that directory and all its members and subdirectories
2594    will be assigned the new pattern. For example, the following would
2595    assign 01664 to most files, but would use 01777 for directories named C<tmp>.
2596    
2597        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp$' => 01777);
2598    
2599    The list is ordered, so the following would use 0777 for C<tmp1> and
2600    0666 for C<tmp>, C<tmp2>, or C<tmp3>.
2601    
2602        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp1' => 0777,
2603                                                       '^tmp' => 0666);
2604    
2605    Note that the pattern matches are all case-insensitive, and only directory
2606    names are matched, not file names.
2607    
2608    =back
2609    
2610    =cut
2611    
2612    sub SetPermissions {
2613        # Get the parameters.
2614        my ($dirName, $group, $mask, @otherMasks) = @_;
2615        # Set up for error recovery.
2616        eval {
2617            # Switch to the specified directory.
2618            ChDir($dirName);
2619            # Get the group ID.
2620            my $gid = getgrnam($group);
2621            # Get the mask for tracing.
2622            my $traceMask = sprintf("%04o", $mask) . "($mask)";
2623            Trace("Fixing permissions for directory $dirName using group $group($gid) and mask $traceMask.") if T(File => 2);
2624            my $fixCount = 0;
2625            my $lookCount = 0;
2626            # @dirs will be a stack of directories to be processed.
2627            my @dirs = (getcwd());
2628            while (scalar(@dirs) > 0) {
2629                # Get the current directory.
2630                my $dir = pop @dirs;
2631                # Check for a match to one of the specified directory names. To do
2632                # that, we need to pull the individual part of the name off of the
2633                # whole path.
2634                my $simpleName = $dir;
2635                if ($dir =~ m!/([^/]+)$!) {
2636                    $simpleName = $1;
2637                }
2638                Trace("Simple directory name for $dir is $simpleName.") if T(File => 4);
2639                # Search for a match.
2640                my $match = 0;
2641                my $i;
2642                for ($i = 0; $i < $#otherMasks && ! $match; $i += 2) {
2643                    my $pattern = $otherMasks[$i];
2644                    if ($simpleName =~ /$pattern/i) {
2645                        $match = 1;
2646                    }
2647                }
2648                # Check for a match. Note we use $i-1 because the loop added 2
2649                # before terminating due to the match.
2650                if ($match && $otherMasks[$i-1] != $mask) {
2651                    # This directory matches one of the incoming patterns, and it's
2652                    # a different mask, so we process it recursively with that mask.
2653                    SetPermissions($dir, $group, $otherMasks[$i-1], @otherMasks);
2654                } else {
2655                    # Here we can process normally. Get all of the non-hidden members.
2656                    my @submems = OpenDir($dir, 1);
2657                    for my $submem (@submems) {
2658                        # Get the full name.
2659                        my $thisMem = "$dir/$submem";
2660                        Trace("Checking member $thisMem.") if T(4);
2661                        $lookCount++;
2662                        if ($lookCount % 1000 == 0) {
2663                            Trace("$lookCount members examined. Current is $thisMem. Mask is $traceMask") if T(File => 3);
2664                        }
2665                        # Fix the group.
2666                        chown -1, $gid, $thisMem;
2667                        # Insure this member is not a symlink.
2668                        if (! -l $thisMem) {
2669                            # Get its info.
2670                            my $fileInfo = stat $thisMem;
2671                            # Only proceed if we got the info. Otherwise, it's a hard link
2672                            # and we want to skip it anyway.
2673                            if ($fileInfo) {
2674                                my $fileMode = $fileInfo->mode;
2675                                if (($fileMode & $mask) != $mask) {
2676                                    # Fix this member.
2677                                    $fileMode |= $mask;
2678                                    chmod $fileMode, $thisMem;
2679                                    $fixCount++;
2680                                }
2681                                # If it's a subdirectory, stack it.
2682                                if (-d $thisMem) {
2683                                    push @dirs, $thisMem;
2684                                }
2685                            }
2686                        }
2687                    }
2688                }
2689            }
2690            Trace("$lookCount files and directories processed, $fixCount fixed.") if T(File => 2);
2691        };
2692        # Check for an error.
2693        if ($@) {
2694            Confess("SetPermissions error: $@");
2695                  }                  }
2696          }          }
2697          # Merge the options into the defaults.  
2698          GetOptions($optionTable, \%overrides);  =head3 GetLine
2699          # Translate the remaining parameters.  
2700        my @data = Tracer::GetLine($handle);
2701    
2702    Read a line of data from a tab-delimited file.
2703    
2704    =over 4
2705    
2706    =item handle
2707    
2708    Open file handle from which to read.
2709    
2710    =item RETURN
2711    
2712    Returns a list of the fields in the record read. The fields are presumed to be
2713    tab-delimited. If we are at the end of the file, then an empty list will be
2714    returned. If an empty line is read, a single list item consisting of a null
2715    string will be returned.
2716    
2717    =back
2718    
2719    =cut
2720    
2721    sub GetLine {
2722        # Get the parameters.
2723        my ($handle) = @_;
2724        # Declare the return variable.
2725          my @retVal = ();          my @retVal = ();
2726          for my $inputParm (@inputList) {      Trace("File position is " . tell($handle) . ". EOF flag is " . eof($handle) . ".") if T(File => 4);
2727                  push @retVal, UnEscape($inputParm);      # Read from the file.
2728        my $line = <$handle>;
2729        # Only proceed if we found something.
2730        if (defined $line) {
2731            # Remove the new-line. We are a bit over-cautious here because the file may be coming in via an
2732            # upload control and have a nonstandard EOL combination.
2733            $line =~ s/(\r|\n)+$//;
2734            # Here we do some fancy tracing to help in debugging complicated EOL marks.
2735            if (T(File => 4)) {
2736                my $escapedLine = $line;
2737                $escapedLine =~ s/\n/\\n/g;
2738                $escapedLine =~ s/\r/\\r/g;
2739                $escapedLine =~ s/\t/\\t/g;
2740                Trace("Line read: -->$escapedLine<--");
2741            }
2742            # If the line is empty, return a single empty string; otherwise, parse
2743            # it into fields.
2744            if ($line eq "") {
2745                push @retVal, "";
2746            } else {
2747                push @retVal, split /\t/,$line;
2748          }          }
2749          # Return the results.      } else {
2750          return ($optionTable, @retVal);          # Trace the reason the read failed.
2751            Trace("End of file: $!") if T(File => 3);
2752        }
2753        # Return the result.
2754        return @retVal;
2755    }
2756    
2757    =head3 PutLine
2758    
2759        Tracer::PutLine($handle, \@fields, $eol);
2760    
2761    Write a line of data to a tab-delimited file. The specified field values will be
2762    output in tab-separated form, with a trailing new-line.
2763    
2764    =over 4
2765    
2766    =item handle
2767    
2768    Output file handle.
2769    
2770    =item fields
2771    
2772    List of field values.
2773    
2774    =item eol (optional)
2775    
2776    End-of-line character (default is "\n").
2777    
2778    =back
2779    
2780    =cut
2781    
2782    sub PutLine {
2783        # Get the parameters.
2784        my ($handle, $fields, $eol) = @_;
2785        # Write the data.
2786        print $handle join("\t", @{$fields}) . ($eol || "\n");
2787    }
2788    
2789    
2790    =head3 PrintLine
2791    
2792        Tracer::PrintLine($line);
2793    
2794    Print a line of text with a trailing new-line.
2795    
2796    =over 4
2797    
2798    =item line
2799    
2800    Line of text to print.
2801    
2802    =back
2803    
2804    =cut
2805    
2806    sub PrintLine {
2807        # Get the parameters.
2808        my ($line) = @_;
2809        # Print the line.
2810        print "$line\n";
2811    }
2812    
2813    
2814    =head2 Other Useful Methods
2815    
2816    =head3 ParseParm
2817    
2818        my $listValue = Tracer::ParseParm($string);
2819    
2820    Convert a parameter into a list reference. If the parameter is undefined,
2821    an undefined value will be returned. Otherwise, it will be parsed as a
2822    comma-separated list of values.
2823    
2824    =over 4
2825    
2826    =item string
2827    
2828    Incoming string.
2829    
2830    =item RETURN
2831    
2832    Returns a reference to a list of values, or C<undef> if the incoming value
2833    was undefined.
2834    
2835    =back
2836    
2837    =cut
2838    
2839    sub ParseParm {
2840        # Get the parameters.
2841        my ($string) = @_;
2842        # Declare the return variable.
2843        my $retVal;
2844        # Check for data.
2845        if (defined $string) {
2846            # We have some, so split it into a list.
2847            $retVal = [ split /\s*,\s*/, $string];
2848        }
2849        # Return the result.
2850        return $retVal;
2851    }
2852    
2853    =head3 Now
2854    
2855        my $string = Tracer::Now();
2856    
2857    Return a displayable time stamp containing the local time. Whatever format this
2858    method produces must be parseable by L</ParseDate>.
2859    
2860    =cut
2861    
2862    sub Now {
2863        return DisplayTime(time);
2864    }
2865    
2866    =head3 DisplayTime
2867    
2868        my $string = Tracer::DisplayTime($time);
2869    
2870    Convert a time value to a displayable time stamp. Whatever format this
2871    method produces must be parseable by L</ParseDate>.
2872    
2873    =over 4
2874    
2875    =item time
2876    
2877    Time to display, in seconds since the epoch, or C<undef> if the time is unknown.
2878    
2879    =item RETURN
2880    
2881    Returns a displayable time, or C<(n/a)> if the incoming time is undefined.
2882    
2883    =back
2884    
2885    =cut
2886    
2887    sub DisplayTime {
2888        my ($time) = @_;
2889        my $retVal = "(n/a)";
2890        if (defined $time) {
2891            my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($time);
2892            $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .
2893                      _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);
2894        }
2895        return $retVal;
2896    }
2897    
2898    # Pad a number to 2 digits.
2899    sub _p2 {
2900        my ($value) = @_;
2901        $value = "0$value" if ($value < 10);
2902        return $value;
2903    }
2904    
2905    =head3 Escape
2906    
2907        my $codedString = Tracer::Escape($realString);
2908    
2909    Escape a string for use in a command. Tabs will be replaced by C<\t>, new-lines
2910    replaced by C<\n>, carriage returns will be deleted, and backslashes will be doubled. The
2911    result is to reverse the effect of L</UnEscape>.
2912    
2913    =over 4
2914    
2915    =item realString
2916    
2917    String to escape.
2918    
2919    =item RETURN
2920    
2921    Escaped equivalent of the real string.
2922    
2923    =back
2924    
2925    =cut
2926    
2927    sub Escape {
2928        # Get the parameter.
2929        my ($realString) = @_;
2930        # Initialize the return variable.
2931        my $retVal = "";
2932        # Loop through the parameter string, looking for sequences to escape.
2933        while (length $realString > 0) {
2934            # Look for the first sequence to escape.
2935            if ($realString =~ /^(.*?)([\n\t\r\\])/) {
2936                # Here we found it. The text preceding the sequence is in $1. The sequence
2937                # itself is in $2. First, move the clear text to the return variable.
2938                $retVal .= $1;
2939                # Strip the processed section off the real string.
2940                $realString = substr $realString, (length $2) + (length $1);
2941                # Get the matched character.
2942                my $char = $2;
2943                # If we have a CR, we are done.
2944                if ($char ne "\r") {
2945                    # It's not a CR, so encode the escape sequence.
2946                    $char =~ tr/\t\n/tn/;
2947                    $retVal .= "\\" . $char;
2948                }
2949            } else {
2950                # Here there are no more escape sequences. The rest of the string is
2951                # transferred unmodified.
2952                $retVal .= $realString;
2953                $realString = "";
2954            }
2955        }
2956        # Return the result.
2957        return $retVal;
2958  }  }
2959    
2960  =head3 UnEscape  =head3 UnEscape
2961    
2962  C<< my $realString = Tracer::UnEscape($codedString); >>      my $realString = Tracer::UnEscape($codedString);
2963    
2964  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
2965  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
2966    be deleted.
2967    
2968  =over 4  =over 4
2969    
# Line 555  Line 2985 
2985          my ($codedString) = @_;          my ($codedString) = @_;
2986          # Initialize the return variable.          # Initialize the return variable.
2987          my $retVal = "";          my $retVal = "";
2988        # Only proceed if the incoming string is nonempty.
2989        if (defined $codedString) {
2990          # 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
2991          # translating because it causes problems with the escaped slash. ("\\b" becomes          # translating because it causes problems with the escaped slash. ("\\t" becomes
2992          # "\ " no matter what we do.)          # "\<tab>" no matter what we do.)
2993          while (length $codedString > 0) {          while (length $codedString > 0) {
2994                  # Look for the first escape sequence.                  # Look for the first escape sequence.
2995                  if ($codedString =~ /^(.*?)\\(\\|b|n|t)/) {              if ($codedString =~ /^(.*?)\\(\\|n|t|r)/) {
2996                          # 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
2997                          # 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.
2998                          $retVal .= $1;                          $retVal .= $1;
2999                          $codedString = substr $codedString, (2 + length $1);                          $codedString = substr $codedString, (2 + length $1);
3000                          # Decode the escape sequence.                  # Get the escape value.
3001                          my $char = $2;                          my $char = $2;
3002                          $char =~ tr/\\btn/\\ \t\n/;                  # If we have a "\r", we are done.
3003                    if ($char ne 'r') {
3004                        # Here it's not an 'r', so we convert it.
3005                        $char =~ tr/\\tn/\\\t\n/;
3006                          $retVal .= $char;                          $retVal .= $char;
3007                    }
3008                  } else {                  } else {
3009                          # 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
3010                          # transferred unmodified.                          # transferred unmodified.
# Line 576  Line 3012 
3012                          $codedString = "";                          $codedString = "";
3013                  }                  }
3014          }          }
3015          # Return the result.      }
3016        # Return the result.
3017        return $retVal;
3018    }
3019    
3020    =head3 Percent
3021    
3022        my $percent = Tracer::Percent($number, $base);
3023    
3024    Returns the percent of the base represented by the given number. If the base
3025    is zero, returns zero.
3026    
3027    =over 4
3028    
3029    =item number
3030    
3031    Percent numerator.
3032    
3033    =item base
3034    
3035    Percent base.
3036    
3037    =item RETURN
3038    
3039    Returns the percentage of the base represented by the numerator.
3040    
3041    =back
3042    
3043    =cut
3044    
3045    sub Percent {
3046        # Get the parameters.
3047        my ($number, $base) = @_;
3048        # Declare the return variable.
3049        my $retVal = 0;
3050        # Compute the percent.
3051        if ($base != 0) {
3052            $retVal = $number * 100 / $base;
3053        }
3054        # Return the result.
3055        return $retVal;
3056    }
3057    
3058    =head3 Constrain
3059    
3060        my $constrained = Constrain($value, $min, $max);
3061    
3062    Modify a numeric value to bring it to a point in between a maximum and a minimum.
3063    
3064    =over 4
3065    
3066    =item value
3067    
3068    Value to constrain.
3069    
3070    =item min (optional)
3071    
3072    Minimum permissible value. If this parameter is undefined, no minimum constraint will be applied.
3073    
3074    =item max (optional)
3075    
3076    Maximum permissible value. If this parameter is undefined, no maximum constraint will be applied.
3077    
3078    =item RETURN
3079    
3080    Returns the incoming value, constrained according to the other parameters.
3081    
3082    =back
3083    
3084    =cut
3085    
3086    sub Constrain {
3087        # Get the parameters.
3088        my ($value, $min, $max) = @_;
3089        # Declare the return variable.
3090        my $retVal = $value;
3091        # Apply the minimum constraint.
3092        if (defined $min && $retVal < $min) {
3093            $retVal = $min;
3094        }
3095        # Apply the maximum constraint.
3096        if (defined $max && $retVal > $max) {
3097            $retVal = $max;
3098        }
3099        # Return the result.
3100        return $retVal;
3101    }
3102    
3103    =head3 Min
3104    
3105        my $min = Min($value1, $value2, ... $valueN);
3106    
3107    Return the minimum argument. The arguments are treated as numbers.
3108    
3109    =over 4
3110    
3111    =item $value1, $value2, ... $valueN
3112    
3113    List of numbers to compare.
3114    
3115    =item RETURN
3116    
3117    Returns the lowest number in the list.
3118    
3119    =back
3120    
3121    =cut
3122    
3123    sub Min {
3124        # Get the parameters. Note that we prime the return value with the first parameter.
3125        my ($retVal, @values) = @_;
3126        # Loop through the remaining parameters, looking for the lowest.
3127        for my $value (@values) {
3128            if ($value < $retVal) {
3129                $retVal = $value;
3130            }
3131        }
3132        # Return the minimum found.
3133        return $retVal;
3134    }
3135    
3136    =head3 Max
3137    
3138        my $max = Max($value1, $value2, ... $valueN);
3139    
3140    Return the maximum argument. The arguments are treated as numbers.
3141    
3142    =over 4
3143    
3144    =item $value1, $value2, ... $valueN
3145    
3146    List of numbers to compare.
3147    
3148    =item RETURN
3149    
3150    Returns the highest number in the list.
3151    
3152    =back
3153    
3154    =cut
3155    
3156    sub Max {
3157        # Get the parameters. Note that we prime the return value with the first parameter.
3158        my ($retVal, @values) = @_;
3159        # Loop through the remaining parameters, looking for the highest.
3160        for my $value (@values) {
3161            if ($value > $retVal) {
3162                $retVal = $value;
3163            }
3164        }
3165        # Return the maximum found.
3166          return $retVal;          return $retVal;
3167  }  }
3168    
 =head3 ParseRecord  
3169    
3170  C<< my @fields = Tracer::ParseRecord($line); >>  =head3 Strip
3171    
3172  Parse a tab-delimited data line. The data line is split into field values. Embedded tab      my $string = Tracer::Strip($line);
3173  and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.  
3174  These will automatically be converted.  Strip all line terminators off a string. This is necessary when dealing with files
3175    that may have been transferred back and forth several times among different
3176    operating environments.
3177    
3178  =over 4  =over 4
3179    
3180  =item line  =item line
3181    
3182  Line of data containing the tab-delimited fields.  Line of text to be stripped.
3183    
3184  =item RETURN  =item RETURN
3185    
3186  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.
3187    
3188  =back  =back
3189    
3190  =cut  =cut
3191    
3192  sub ParseRecord {  sub Strip {
3193          # Get the parameter.      # Get a copy of the parameter string.
3194          my ($line) = @_;      my ($string) = @_;
3195          # Remove the trailing new-line, if any.      my $retVal = (defined $string ? $string : "");
3196          chomp $line;      # Strip the line terminator characters.
3197          # 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;  
         }  
3198          # Return the result.          # Return the result.
3199          return @retVal;      return $retVal;
3200  }  }
3201    
3202  =head3 Merge  =head3 Pad
3203    
3204  C<< my @mergedList = Tracer::Merge(@inputList); >>      my $paddedString = Tracer::Pad($string, $len, $left, $padChar);
3205    
3206  Sort a list of strings and remove duplicates.  Pad a string to a specified length. The pad character will be a
3207    space, and the padding will be on the right side unless specified
3208    in the third parameter.
3209    
3210  =over 4  =over 4
3211    
3212  =item inputList  =item string
3213    
3214  List of scalars to sort and merge.  String to be padded.
3215    
3216    =item len
3217    
3218    Desired length of the padded string.
3219    
3220    =item left (optional)
3221    
3222    TRUE if the string is to be left-padded; otherwise it will be padded on the right.
3223    
3224    =item padChar (optional)
3225    
3226    Character to use for padding. The default is a space.
3227    
3228  =item RETURN  =item RETURN
3229    
3230  Returns a list containing the same elements sorted in ascending order with duplicates  Returns a copy of the original string with the pad character added to the
3231  removed.  specified end so that it achieves the desired length.
3232    
3233  =back  =back
3234    
3235  =cut  =cut
3236    
3237  sub Merge {  sub Pad {
3238          # Get the input list in sort order.      # Get the parameters.
3239          my @inputList = sort @_;      my ($string, $len, $left, $padChar) = @_;
3240          # Only proceed if the list has at least two elements.      # Compute the padding character.
3241          if (@inputList > 1) {      if (! defined $padChar) {
3242                  # Now we want to move through the list splicing out duplicates.          $padChar = " ";
3243                  my $i = 0;      }
3244                  while ($i < @inputList) {      # Compute the number of spaces needed.
3245                          # Get the current entry.      my $needed = $len - length $string;
3246                          my $thisEntry = $inputList[$i];      # Copy the string into the return variable.
3247                          # Find out how many elements duplicate the current entry.      my $retVal = $string;
3248                          my $j = $i + 1;      # Only proceed if padding is needed.
3249                          my $dup1 = $i + 1;      if ($needed > 0) {
3250                          while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };          # Create the pad string.
3251                          # If the number is nonzero, splice out the duplicates found.          my $pad = $padChar x $needed;
3252                          if ($j > $dup1) {          # Affix it to the return value.
3253                                  splice @inputList, $dup1, $j - $dup1;          if ($left) {
3254                $retVal = $pad . $retVal;
3255            } else {
3256                $retVal .= $pad;
3257                          }                          }
                         # 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++;  
3258                  }                  }
3259        # Return the result.
3260        return $retVal;
3261          }          }
3262          # Return the merged list.  
3263          return @inputList;  =head3 EOF
3264    
3265    This is a constant that is lexically greater than any useful string.
3266    
3267    =cut
3268    
3269    sub EOF {
3270        return "\xFF\xFF\xFF\xFF\xFF";
3271  }  }
3272    
3273  =head3 GetFile  =head3 TICK
3274    
3275        my @results = TICK($commandString);
3276    
3277  C<< my @fileContents = Tracer::GetFile($fileName); >>  Perform a back-tick operation on a command. If this is a Windows environment, any leading
3278    dot-slash (C<./> will be removed. So, for example, if you were doing
3279    
3280  Return the entire contents of a file.      `./protein.cgi`
3281    
3282    from inside a CGI script, it would work fine in Unix, but would issue an error message
3283    in Windows complaining that C<'.'> is not a valid command. If instead you code
3284    
3285        TICK("./protein.cgi")
3286    
3287    it will work correctly in both environments.
3288    
3289  =over 4  =over 4
3290    
3291  =item fileName  =item commandString
3292    
3293  Name of the file to read.  The command string to pass to the system.
3294    
3295  =item RETURN  =item RETURN
3296    
3297  In a list context, returns the entire file as a list with the line terminators removed.  Returns the standard output from the specified command, as a list.
 In a scalar context, returns the entire file as a string.  
3298    
3299  =back  =back
3300    
3301  =cut  =cut
3302    #: Return Type @;
3303  sub GetFile {  sub TICK {
3304          # Get the parameters.          # Get the parameters.
3305          my ($fileName) = @_;      my ($commandString) = @_;
3306          # Declare the return variable.      # Chop off the dot-slash if this is Windows.
3307          my @retVal = ();      if ($FIG_Config::win_mode) {
3308          # 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. $actualLines processed.") if T(0);  
         }  
         # Return the file's contents in the desired format.  
     if (wantarray) {  
             return @retVal;  
     } else {  
         return join "\n", @retVal;  
3309      }      }
3310        # Activate the command and return the result.
3311        return `$commandString`;
3312  }  }
3313    
 =head3 QTrace  
3314    
3315  C<< my $data = QTrace($format); >>  =head3 CommaFormat
3316    
3317  Return the queued trace data in the specified format.      my $formatted = Tracer::CommaFormat($number);
3318    
3319    Insert commas into a number.
3320    
3321  =over 4  =over 4
3322    
3323  =item format  =item number
3324    
3325  C<html> to format the data as an HTML list, C<text> to format it as straight text.  A sequence of digits.
3326    
3327    =item RETURN
3328    
3329    Returns the same digits with commas strategically inserted.
3330    
3331  =back  =back
3332    
3333  =cut  =cut
3334    
3335  sub QTrace {  sub CommaFormat {
3336          # Get the parameter.      # Get the parameters.
3337          my ($format) = @_;      my ($number) = @_;
3338          # Create the return variable.      # Pad the length up to a multiple of three.
3339          my $retVal = "";      my $padded = "$number";
3340          # Process according to the format.      $padded = " " . $padded while length($padded) % 3 != 0;
3341          if ($format =~ m/^HTML$/i) {      # This is a fancy PERL trick. The parentheses in the SPLIT pattern
3342                  # Convert the queue into an HTML list.      # cause the delimiters to be included in the output stream. The
3343                  $retVal = "<ul>\n";      # GREP removes the empty strings in between the delimiters.
3344                  for my $line (@Queue) {      my $retVal = join(",", grep { $_ ne '' } split(/(...)/, $padded));
3345                          my $escapedLine = CGI::escapeHTML($line);      # Clean out the spaces.
3346                          $retVal .= "<li>$escapedLine</li>\n";      $retVal =~ s/ //g;
3347                  }      # 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.  
3348          return $retVal;          return $retVal;
3349  }  }
3350    
 =head3 Confess  
   
 C<< Confess($message); >>  
3351    
3352  Trace the call stack and abort the program with the specified message. The stack  =head3 CompareLists
 trace will only appear if the trace level for this package is 1 or more. When used with  
 the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.  
 So, for example  
3353    
3354  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>      my ($inserted, $deleted) = Tracer::CompareLists(\@newList, \@oldList, $keyIndex);
3355    
3356  Will abort the program with a stack trace if the value of C<$recNum> is negative.  Compare two lists of tuples, and return a hash analyzing the differences. The lists
3357    are presumed to be sorted alphabetically by the value in the $keyIndex column.
3358    The return value contains a list of items that are only in the new list
3359    (inserted) and only in the old list (deleted).
3360    
3361  =over 4  =over 4
3362    
3363  =item message  =item newList
   
 Message to include in the trace.  
3364    
3365  =back  Reference to a list of new tuples.
3366    
3367  =cut  =item oldList
3368    
3369  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(">>> $message");  
 }  
3370    
3371  =head3 Assert  =item keyIndex (optional)
3372    
3373  C<< Assert($condition1, $condition2, ... $conditionN); >>  Index into each tuple of its key field. The default is 0.
3374    
3375  Return TRUE if all the conditions are true. This method can be used in conjunction with  =item RETURN
 the OR operator and the L</Confess> method, B<Assert> can function as a debugging assert.  
 So, for example  
3376    
3377  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>  Returns a 2-tuple consisting of a reference to the list of items that are only in the new
3378    list (inserted) followed by a reference to the list of items that are only in the old
3379    list (deleted).
3380    
3381  Will abort the program with a stack trace if the value of C<$recNum> is negative.  =back
3382    
3383  =cut  =cut
3384  sub Assert {  
3385      my $retVal = 1;  sub CompareLists {
3386      LOOP: for my $condition (@_) {      # Get the parameters.
3387          if (! $condition) {      my ($newList, $oldList, $keyIndex) = @_;
3388              $retVal = 0;      if (! defined $keyIndex) {
3389              last LOOP;          $keyIndex = 0;
3390        }
3391        # Declare the return variables.
3392        my ($inserted, $deleted) = ([], []);
3393        # Loop through the two lists simultaneously.
3394        my ($newI, $oldI) = (0, 0);
3395        my ($newN, $oldN) = (scalar @{$newList}, scalar @{$oldList});
3396        while ($newI < $newN || $oldI < $oldN) {
3397            # Get the current object in each list. Note that if one
3398            # of the lists is past the end, we'll get undef.
3399            my $newItem = $newList->[$newI];
3400            my $oldItem = $oldList->[$oldI];
3401            if (! defined($newItem) || defined($oldItem) && $newItem->[$keyIndex] gt $oldItem->[$keyIndex]) {
3402                # The old item is not in the new list, so mark it deleted.
3403                push @{$deleted}, $oldItem;
3404                $oldI++;
3405            } elsif (! defined($oldItem) || $oldItem->[$keyIndex] gt $newItem->[$keyIndex]) {
3406                # The new item is not in the old list, so mark it inserted.
3407                push @{$inserted}, $newItem;
3408                $newI++;
3409            } else {
3410                # The item is in both lists, so push forward.
3411                $oldI++;
3412                $newI++;
3413          }          }
3414      }      }
3415      return $retVal;      # Return the result.
3416        return ($inserted, $deleted);
3417  }  }
3418    
3419  =head3 Cluck  =head3 GenerateURL
3420    
3421  C<< Cluck($message); >>      my $queryUrl = Tracer::GenerateURL($page, %parameters);
3422    
3423  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
3424  trace condition. For example,  names and values. The values will be URL-escaped automatically. So, for
3425    example
3426    
3427  C<< Cluck("Starting record parse.") if T(3); >>      Tracer::GenerateURL("form.cgi", type => 1, string => "\"high pass\" or highway")
3428    
3429  will only trace the stack if the trace level for the package is 3 or more.  would return
3430    
3431        form.cgi?type=1;string=%22high%20pass%22%20or%20highway
3432    
3433  =over 4  =over 4
3434    
3435  =item message  =item page
3436    
3437  Message to include in the trace.  Page URL.
3438    
3439    =item parameters
3440    
3441    Hash mapping parameter names to parameter values.
3442    
3443    =item RETURN
3444    
3445    Returns a GET-style URL that goes to the specified page and passes in the
3446    specified parameters and values.
3447    
3448  =back  =back
3449    
3450  =cut  =cut
3451    
3452  sub Cluck {  sub GenerateURL {
3453          # Get the parameters.          # Get the parameters.
3454          my ($message) = @_;      my ($page, %parameters) = @_;
3455      # Trace what's happening.      # Prime the return variable with the page URL.
3456      Trace("Stack trace for event: $message");      my $retVal = $page;
3457          my $confession = longmess($message);      # Loop through the parameters, creating parameter elements in a list.
3458          # Convert the confession to a series of trace messages. Note we skip any      my @parmList = map { "$_=" . uri_escape($parameters{$_}) } keys %parameters;
3459      # messages relating to calls into Tracer.      # If the list is nonempty, tack it on.
3460          for my $line (split /\s*\n/, $confession) {      if (@parmList) {
3461                  Trace($line) if ($line !~ /Tracer\.pm/);          $retVal .= "?" . join(";", @parmList);
3462          }          }
3463        # Return the result.
3464        return $retVal;
3465  }  }
3466    
3467  =head3 Min  =head3 ApplyURL
3468    
3469  C<< my $min = Min($value1, $value2, ... $valueN); >>      Tracer::ApplyURL($table, $target, $url);
3470    
3471  Return the minimum argument. The arguments are treated as numbers.  Run through a two-dimensional table (or more accurately, a list of lists), converting the
3472    I<$target> column to HTML text having a hyperlink to a URL in the I<$url> column. The
3473    URL column will be deleted by this process and the target column will be HTML-escaped.
3474    
3475    This provides a simple way to process the results of a database query into something
3476    displayable by combining a URL with text.
3477    
3478  =over 4  =over 4
3479    
3480  =item $value1, $value2, ... $valueN  =item table
3481    
3482  List of numbers to compare.  Reference to a list of lists. The elements in the containing list will be updated by
3483    this method.
3484    
3485  =item RETURN  =item target
3486    
3487  Returns the lowest number in the list.  The index of the column to be converted into HTML.
3488    
3489    =item url
3490    
3491    The index of the column containing the URL. Note that the URL must have a recognizable
3492    C<http:> at the beginning.
3493    
3494  =back  =back
3495    
3496  =cut  =cut
3497    
3498  sub Min {  sub ApplyURL {
3499          # Get the parameters. Note that we prime the return value with the first parameter.      # Get the parameters.
3500          my ($retVal, @values) = @_;      my ($table, $target, $url) = @_;
3501          # Loop through the remaining parameters, looking for the lowest.      # Loop through the table.
3502          for my $value (@values) {      for my $row (@{$table}) {
3503                  if ($value < $retVal) {          # Apply the URL to the target cell.
3504                          $retVal = $value;          $row->[$target] = CombineURL($row->[$target], $row->[$url]);
3505                  }          # Delete the URL from the row.
3506            delete $row->[$url];
3507          }          }
         # Return the minimum found.  
         return $retVal;  
3508  }  }
3509    
3510  =head3 Max  =head3 CombineURL
3511    
3512  C<< my $max = Max($value1, $value2, ... $valueN); >>      my $combinedHtml = Tracer::CombineURL($text, $url);
3513    
3514  Return the maximum argument. The arguments are treated as numbers.  This method will convert the specified text into HTML hyperlinked to the specified
3515    URL. The hyperlinking will only take place if the URL looks legitimate: that is, it
3516    is defined and begins with an C<http:> header.
3517    
3518  =over 4  =over 4
3519    
3520  =item $value1, $value2, ... $valueN  =item text