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

Diff of /FigKernelPackages/Tracer.pm

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

revision 1.9, Wed May 4 03:05:12 2005 UTC revision 1.112, Wed Oct 1 03:23:40 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 Escape);      @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;          use FIG_Config;
30      use PageBuilder;      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        use Fcntl qw(:DEFAULT :flock);
42    
43    
44  =head1 Tracing and Debugging Helpers  =head1 Tracing and Debugging Helpers
45    
46  =head2 Introduction  =head2 Tracing
47    
48  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
49  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.
50  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,
51  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
52  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
53  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
54  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
55  appear. To generate a trace message, use the following syntax.  appear.
56    
57    =head3 Putting Trace Messages in Your Code
58    
59    To generate a trace message, use the following syntax.
60    
61  C<< Trace($message) if T(errors => 4); >>      Trace($message) if T(errors => 4);
62    
63  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>
64  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
65    
66  C<< Trace($message) if T(main => 4); >>      Trace($message) if T(main => 4);
67    
68  will trace if the trace level is 4 or more.  will trace if the trace level is 4 or more.
69    
# Line 36  Line 71 
71  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
72  active and the trace level is 2 or more.  active and the trace level is 2 or more.
73    
74  C<< Trace($message) if T(2); >>      Trace($message) if T(2);
75    
76  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>.
77  of category names, and a set of options. The trace level and list of category names are  
78    =head3 Custom Tracing
79    
80    Many programs have customized tracing configured using the L</TSetup> method. This is no longer
81    the preferred method, but a knowledge of how custom tracing works can make the more modern
82    L</Emergency Tracing> easier to understand.
83    
84    To set up custom tracing, you call the L</TSetup> method. The method takes as input a trace level,
85    a list of category names, and a destination. The trace level and list of category names are
86  specified as a space-delimited string. Thus  specified as a space-delimited string. Thus
87    
88  C<< TSetup('3 errors Sprout ERDB', 'HTML'); >>      TSetup('3 errors Sprout ERDB', 'TEXT');
89    
90  sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and  sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and
91  specifies that messages should be output as HTML paragraphs. The parameters are formatted  specifies that messages should be sent to the standard output.
92  to make it easier to input tracing configuration on a web form.  
93    To turn on tracing for ALL categories, use an asterisk. The call below sets every category to
94    level 3 and writes the output to the standard error output. This sort of thing might be
95    useful in a CGI environment.
96    
97  In addition to HTML and file output for trace messages, you can specify that the trace messages      TSetup('3 *', 'WARN');
98    
99    In addition standard error and file output for trace messages, you can specify that the trace messages
100  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
101  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
102  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
103  it easier to debug page formatting problems.  it easier to debug page formatting problems.
104    
105  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
106    a file at the same time. To trace to a file, specify the filename with an output character in front
107    of it.
108    
109        TSetup('4 SQL', ">$fileName");
110    
111    To trace to the standard output and a file at the same time, put a C<+> in front of the angle
112    bracket.
113    
114        TSetup('3 *', "+>$fileName");
115    
116  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>.
117  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.
118  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
119  being used out in the field.  being used out in the field.
120    
121    =head3 Trace Levels
122    
123    There is no hard and fast rule on how to use trace levels. The following is therefore only
124    a suggestion.
125    
126    =over 4
127    
128    =item Error 0
129    
130    Message indicates an error that may lead to incorrect results or that has stopped the
131    application entirely.
132    
133    =item Warning 1
134    
135    Message indicates something that is unexpected but that probably did not interfere
136    with program execution.
137    
138    =item Notice 2
139    
140    Message indicates the beginning or end of a major task.
141    
142    =item Information 3
143    
144    Message indicates a subtask. In the FIG system, a subtask generally relates to a single
145    genome. This would be a big loop that is not expected to execute more than 500 times or so.
146    
147    =item Detail 4
148    
149    Message indicates a low-level loop iteration.
150    
151    =back
152    
153    The format of trace messages is important because some utilities analyze trace files.
154    There are three fields-- the time stamp, the category name, and the text.
155    The time stamp is between square brackets and the category name between angle brackets.
156    After the category name there is a colon (C<:>) followed by the message text.
157    If the square brackets or angle brackets are missing, then the trace management
158    utilities assume that they are encountering a set of pre-formatted lines.
159    
160    Note, however, that this formatting is done automatically by the tracing functions. You
161    only need to know about it if you want to parse a trace file.
162    
163    =head3 Emergency Tracing
164    
165    Sometimes, you need a way for tracing to happen automatically without putting parameters
166    in a form or on the command line. Emergency tracing does this. You invoke emergency tracing
167    from the debug form, which is accessed from the [[DebugConsole]]. Emergency tracing requires
168    that you specify a tracing key. For command-line tools, the key is
169    taken from the C<TRACING> environment variable. For web services, the key is taken from
170    a cookie. Either way, the key tells the tracing facility who you are, so that you control
171    the tracing in your environment without stepping on other users.
172    
173    The key can be anything you want. If you don't have a key, the C<SetPassword> page will
174    generate one for you.
175    
176    You can activate and de-activate emergency tracing from the debugging control panel, as
177    well as display the trace file itself.
178    
179    To enable emergency tracing in your code, call
180    
181        ETracing($cgi)
182    
183    from a web script and
184    
185        ETracing()
186    
187    from a command-line script.
188    
189    The web script will look for the tracing key in the cookies, and the command-line
190    script will look for it in the C<TRACING> environment variable. If you are
191    using the L</StandardSetup> method or a [[WebApplication]], emergency tracing
192    will be configured automatically.
193    
194  =cut  =cut
195    
196  # Declare the configuration variables.  # Declare the configuration variables.
197    
198  my $Destination = "NONE";       # Description of where to send the trace output.  my $Destination = "WARN";   # Description of where to send the trace output.
199    my $TeeFlag = 0;            # TRUE if output is going to a file and to the
200                                # standard output
201  my %Categories = ( main => 1 );  my %Categories = ( main => 1 );
202                                                          # hash of active category names                                                          # hash of active category names
203    my @LevelNames = qw(error warn notice info detail);
204  my $TraceLevel = 0;                     # trace level; a higher trace level produces more  my $TraceLevel = 0;                     # trace level; a higher trace level produces more
205                                                          # messages                                                          # messages
206  my @Queue = ();                         # queued list of trace messages.  my @Queue = ();                         # queued list of trace messages.
207  my $LastCategory = "main";  # name of the last category interrogated  my $LastCategory = "main";  # name of the last category interrogated
208    my $LastLevel = 0;          # level of the last test call
209    my $SetupCount = 0;         # number of times TSetup called
210    my $AllTrace = 0;           # TRUE if we are tracing all categories.
211    my $SavedCGI;               # CGI object passed to ETracing
212    my $CommandLine;            # Command line passed to StandardSetup
213    umask 2;                    # Fix the damn umask so everything is group-writable.
214    
215  =head2 Public Methods  =head2 Tracing Methods
216    
217    =head3 Setups
218    
219        my $count = Tracer::Setups();
220    
221    Return the number of times L</TSetup> has been called.
222    
223    This method allows for the creation of conditional tracing setups where, for example, we
224    may want to set up tracing if nobody else has done it before us.
225    
226    =cut
227    
228    sub Setups {
229        return $SetupCount;
230    }
231    
232  =head3 TSetup  =head3 TSetup
233    
234  C<< TSetup($categoryList, $target); >>      TSetup($categoryList, $target);
235    
236  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
237  and interrogated by the L</Trace> and L</T> methods.  and interrogated by the L</Trace> and L</T> methods.
# Line 93  Line 247 
247    
248  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
249  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
250  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 ">"
251  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
252  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
253    cause tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>
254  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
255  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
256  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 113  Line 268 
268          my @categoryData = split /\s+/, $categoryList;          my @categoryData = split /\s+/, $categoryList;
269          # Extract the trace level.          # Extract the trace level.
270          $TraceLevel = shift @categoryData;          $TraceLevel = shift @categoryData;
271          # Build the category hash.      # Presume category-based tracing until we learn otherwise.
272        $AllTrace = 0;
273        # Build the category hash. Note that if we find a "*", we turn on non-category
274        # tracing. We must also clear away any pre-existing data.
275        %Categories = ( main => 1 );
276          for my $category (@categoryData) {          for my $category (@categoryData) {
277                  $Categories{$category} = 1;          if ($category eq '*') {
278                $AllTrace = 1;
279            } else {
280                $Categories{lc $category} = 1;
281            }
282          }          }
283          # Now we need to process the destination information. The most important special          # Now we need to process the destination information. The most important special
284          # case is the single ">", which requires we clear the file first. After doing      # case is when we're writing to a file. This is indicated by ">" (overwrite) and
285          # so, we tack on another ">" sign so that future trace messages are appended.      # ">>" (append). A leading "+" for either indicates that we are also writing to
286        # the standard output (tee mode).
287        if ($target =~ m/^\+?>>?/) {
288            if ($target =~ m/^\+/) {
289                $TeeFlag = 1;
290                $target = substr($target, 1);
291            }
292          if ($target =~ m/^>[^>]/) {          if ($target =~ m/^>[^>]/) {
293                # We need to initialize the file (which clears it).
294                  open TRACEFILE, $target;                  open TRACEFILE, $target;
295                  print TRACEFILE Now() . " Tracing initialized.\n";              print TRACEFILE "[" . Now() . "] [notice] [Tracer] Tracing initialized.\n";
296                  close TRACEFILE;                  close TRACEFILE;
297                # Set to append mode now that the file has been cleared.
298                  $Destination = ">$target";                  $Destination = ">$target";
299          } else {          } else {
300                $Destination = $target;
301            }
302        } else {
303                  $Destination = uc($target);                  $Destination = uc($target);
304          }          }
305        # Increment the setup counter.
306        $SetupCount++;
307  }  }
308    
309  =head3 SetLevel  =head3 SetLevel
310    
311  C<< Tracer::SetLevel($newLevel); >>      Tracer::SetLevel($newLevel);
312    
313  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.
314    
# Line 150  Line 326 
326      $TraceLevel = $_[0];      $TraceLevel = $_[0];
327  }  }
328    
329  =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  
330    
331  =cut      my $time = Tracer::ParseDate($dateString);
332    
333  sub LogErrors {  Convert a date into a PERL time number. This method expects a date-like string
334          # Get the file name.  and parses it into a number. The string must be vaguely date-like or it will
335          my ($fileName) = @_;  return an undefined value. Our requirement is that a month and day be
336          # Open the file as the standard error output.  present and that three pieces of the date string (time of day, month and day,
337          open STDERR, '>', $fileName;  year) be separated by likely delimiters, such as spaces, commas, and such-like.
 }  
338    
339  =head3 ReadOptions  If a time of day is present, it must be in military time with two digits for
340    everything but the hour.
341    
342  C<< my %options = Tracer::ReadOptions($fileName); >>  The year must be exactly four digits.
343    
344  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
345  format  equally innocuous. This means, however, that a sufficiently long sentence with date-like
346    parts in it may be interpreted as a date. Hopefully this will not be a problem.
347    
348  I<optionName>C<=>I<optionValue>C<; >I<comment>  It should be guaranteed that this method will parse the output of the L</Now> function.
349    
350  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.  
351    
352  =over 4  =over 4
353    
354  =item fileName  =item dateString
355    
356  Name of the file containing the option data.  The date string to convert.
357    
358  =item RETURN  =item RETURN
359    
360  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
361  value.  the date string is invalid. A valid date string must contain a month and day.
362    
363  =back  =back
364    
365  =cut  =cut
366    
367  sub ReadOptions {  # Universal month conversion table.
368          # Get the parameters.  use constant MONTHS => {    Jan =>  0, January   =>  0, '01' =>  0,  '1' =>  0,
369          my ($fileName) = @_;                              Feb =>  1, February  =>  1, '02' =>  1,  '2' =>  1,
370          # Open the file.                              Mar =>  2, March     =>  2, '03' =>  2,  '3' =>  2,
371          (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");                              Apr =>  3, April     =>  3, '04' =>  3,  '4' =>  3,
372          # Count the number of records read.                              May =>  4, May       =>  4, '05' =>  4,  '5' =>  4,
373          my ($records, $comments) = 0;                              Jun =>  5, June      =>  5, '06' =>  5,  '6' =>  5,
374          # Create the return hash.                              Jul =>  6, July      =>  6, '07' =>  6,  '7' =>  6,
375          my %retVal = ();                              Aug =>  7, August    =>  7, '08' =>  7,  '8' =>  7,
376          # Loop through the file, accumulating key-value pairs.                              Sep =>  8, September =>  8, '09' =>  8,  '9' =>  8,
377          while (my $line = <CONFIGFILE>) {                              Oct =>  9, October  =>   9, '10' =>  9,
378                  # Denote we've read a line.                              Nov => 10, November =>  10, '11' => 10,
379                  $records++;                              Dec => 11, December =>  11, '12' => 11
380                  # Determine the line type.                          };
                 if ($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  
381    
382  sub GetOptions {  sub ParseDate {
383          # Get the parameters.          # Get the parameters.
384          my ($defaults, $options) = @_;      my ($dateString) = @_;
385          # Check for overrides.      # Declare the return variable.
386          if ($options) {      my $retVal;
387                  # Loop through the overrides.      # Find the month and day of month. There are two ways that can happen. We check for the
388                  while (my ($option, $setting) = each %{$options}) {      # numeric style first. That way, if the user's done something like "Sun 12/22", then we
389                          # Insure this override exists.      # won't be fooled into thinking the month is Sunday.
390                          if (!exists $defaults->{$option}) {      if ($dateString =~ m#\b(\d{1,2})/(\d{1,2})\b# || $dateString =~ m#\b(\w+)\s(\d{1,2})\b#) {
391                                  croak "Unrecognized option $option encountered.";          my ($mon, $mday) = (MONTHS->{$1}, $2);
392            # Insist that the month and day are valid.
393            if (defined($mon) && $2 >= 1 && $2 <= 31) {
394                # Find the time.
395                my ($hour, $min, $sec) = (0, 0, 0);
396                if ($dateString =~ /\b(\d{1,2}):(\d{2}):(\d{2})\b/) {
397                    ($hour, $min, $sec) = ($1, $2, $3);
398                }
399                # Find the year.
400                my $year;
401                if ($dateString =~ /\b(\d{4})\b/) {
402                    $year = $1;
403                          } else {                          } else {
404                                  # Apply the override.                  # Get the default year, which is this one. Note we must convert it to
405                                  $defaults->{$option} = $setting;                  # the four-digit value expected by "timelocal".
406                    (undef, undef, undef, undef, undef, $year) = localtime();
407                    $year += 1900;
408                          }                          }
409                $retVal = timelocal($sec, $min, $hour, $mday, $mon, $year);
410                  }                  }
411          }          }
412          # Return the merged table.      # Return the result.
413          return $defaults;      return $retVal;
414  }  }
415    
416  =head3 MergeOptions  =head3 LogErrors
417    
418  C<< Tracer::MergeOptions(\%table, \%defaults); >>      Tracer::LogErrors($fileName);
419    
420  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.  
421    
422  =over 4  =over 4
423    
424  =item table  =item fileName
   
 Hash table to be updated with the default values.  
   
 =item defaults  
425    
426  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.
427    
428  =back  =back
429    
430  =cut  =cut
431    
432  sub MergeOptions {  sub LogErrors {
433          # Get the parameters.      # Get the file name.
434          my ($table, $defaults) = @_;      my ($fileName) = @_;
435          # Loop through the defaults.      # Open the file as the standard error output.
436          while (my ($key, $value) = each %{$defaults}) {      open STDERR, '>', $fileName;
                 if (!exists $table->{$key}) {  
                         $table->{$key} = $value;  
                 }  
         }  
437  }  }
438    
439  =head3 Trace  =head3 Trace
440    
441  C<< Trace($message); >>      Trace($message);
442    
443  Write a trace message to the target location specified in L</TSetup>. If there has not been  Write a trace message to the target location specified in L</TSetup>. If there has not been
444  any prior call to B<TSetup>.  any prior call to B<TSetup>.
# Line 371  Line 456 
456  sub Trace {  sub Trace {
457          # Get the parameters.          # Get the parameters.
458          my ($message) = @_;          my ($message) = @_;
459        # Strip off any line terminators at the end of the message. We will add
460        # new-line stuff ourselves.
461        my $stripped = Strip($message);
462        # Compute the caller information.
463        my ($callPackage, $callFile, $callLine) = caller();
464        my $callFileTitle = basename($callFile);
465        # Check the caller.
466        my $callerInfo = ($callFileTitle ne "Tracer.pm" ? " [$callFileTitle $callLine]" : "");
467          # Get the timestamp.          # Get the timestamp.
468          my $timeStamp = Now();          my $timeStamp = Now();
469          # Format the message. Note we strip off any line terminators at the end.      # Build the prefix.
470          my $formatted = "$timeStamp <$LastCategory>: " . Strip($message);      my $level = $LevelNames[$LastLevel] || "($LastLevel)";
471        my $prefix = "[$timeStamp] [$level] [$LastCategory]$callerInfo";
472        # Format the message.
473        my $formatted = "$prefix $stripped";
474          # Process according to the destination.          # Process according to the destination.
475          if ($Destination eq "TEXT") {          if ($Destination eq "TEXT") {
476                  # Write the message to the standard output.                  # Write the message to the standard output.
477                  print "$formatted\n";                  print "$formatted\n";
478          } elsif ($Destination eq "ERROR") {          } elsif ($Destination eq "ERROR") {
479                  # Write the message to the error output.          # Write the message to the error output. Here, we want our prefix fields.
480                  print STDERR "$formatted\n";                  print STDERR "$formatted\n";
481        } elsif ($Destination eq "WARN") {
482            # Emit the message to the standard error output. It is presumed that the
483            # error logger will add its own prefix fields, the notable exception being
484            # the caller info.
485            print STDERR "$callerInfo$stripped\n";
486          } elsif ($Destination eq "QUEUE") {          } elsif ($Destination eq "QUEUE") {
487                  # Push the message into the queue.                  # Push the message into the queue.
488                  push @Queue, "$formatted";                  push @Queue, "$formatted";
489          } elsif ($Destination eq "HTML") {          } elsif ($Destination eq "HTML") {
490                  # Convert the message to HTML and write it to the standard output.                  # Convert the message to HTML and write it to the standard output.
491                  my $escapedMessage = CGI::escapeHTML($message);          my $escapedMessage = CGI::escapeHTML($stripped);
492                  print "<p>$formatted</p>\n";          print "<p>$timeStamp $LastCategory $LastLevel: $escapedMessage</p>\n";
     } elsif ($Destination eq "WARN") {  
        # Emit the message as a warning.  
        warn $message;  
493          } elsif ($Destination =~ m/^>>/) {          } elsif ($Destination =~ m/^>>/) {
494                  # Write the trace message to an output file.                  # Write the trace message to an output file.
495                  open TRACING, $Destination;          open(TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";
496            # Lock the file.
497            flock TRACING, LOCK_EX;
498                  print TRACING "$formatted\n";                  print TRACING "$formatted\n";
499                  close TRACING;                  close TRACING;
500            # If the Tee flag is on, echo it to the standard output.
501            if ($TeeFlag) {
502                print "$formatted\n";
503            }
504          }          }
505  }  }
506    
507  =head3 T  =head3 T
508    
509  C<< my $switch = T($category, $traceLevel); >>      my $switch = T($category, $traceLevel);
510    
511          or          or
512    
513  C<< my $switch = T($traceLevel); >>      my $switch = T($traceLevel);
514    
515  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
516  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 439  Line 543 
543                  my ($category, $traceLevel) = @_;                  my ($category, $traceLevel) = @_;
544                  if (!defined $traceLevel) {                  if (!defined $traceLevel) {
545                          # 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.
546                # The calling package is normally the first parameter. If it is
547                # omitted, the first parameter will be the tracelevel. So, the
548                # first thing we do is shift the so-called category into the
549                # $traceLevel variable where it belongs.
550                          $traceLevel = $category;                          $traceLevel = $category;
551                          my ($package, $fileName, $line) = caller;                          my ($package, $fileName, $line) = caller;
552              # If there is no calling package, we default to "main".              # If there is no calling package, we default to "main".
553                          if (!$package) {                          if (!$package) {
554                  $category = "main";                  $category = "main";
555                          } else {                          } else {
556                                  $category = $package;                  my @cats = split /::/, $package;
557                    $category = $cats[$#cats];
558                          }                          }
559                  }                  }
560          # Save the category name.          # Save the category name and level.
561          $LastCategory = $category;          $LastCategory = $category;
562                  # Use the category and tracelevel to compute the result.          $LastLevel = $traceLevel;
563                  $retVal = ($traceLevel <= $TraceLevel && exists $Categories{$category});          # Convert it to lower case before we hash it.
564            $category = lc $category;
565            # Validate the trace level.
566            if (ref $traceLevel) {
567                Confess("Bad trace level.");
568            } elsif (ref $TraceLevel) {
569                Confess("Bad trace config.");
570            }
571            # Make the check. Note that level 0 shows even if the category is turned off.
572            $retVal = ($traceLevel <= $TraceLevel && ($traceLevel == 0 || $AllTrace || exists $Categories{$category}));
573      }      }
574          # Return the computed result.          # Return the computed result.
575      return $retVal;      return $retVal;
576  }  }
577    
578  =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  
579    
580  C<< apple orange rutabaga >>      my $data = QTrace($format);
581    
582  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.  
583    
584  =over 4  =over 4
585    
586  =item optionTable  =item format
   
 Table of default options.  
   
 =item inputList  
   
 List of words on the command line.  
   
 =item RETURN  
587    
588  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.
589    
590  =back  =back
591    
592  =cut  =cut
593    
594  sub ParseCommand {  sub QTrace {
595          # Get the parameters.      # Get the parameter.
596          my ($optionTable, @inputList) = @_;      my ($format) = @_;
597        # Create the return variable.
598        my $retVal = "";
599        # Only proceed if there is an actual queue.
600        if (@Queue) {
601            # Process according to the format.
602            if ($format =~ m/^HTML$/i) {
603                # Convert the queue into an HTML list.
604                $retVal = "<ul>\n";
605                for my $line (@Queue) {
606                    my $escapedLine = CGI::escapeHTML($line);
607                    $retVal .= "<li>$escapedLine</li>\n";
608                }
609                $retVal .= "</ul>\n";
610            } elsif ($format =~ m/^TEXT$/i) {
611                # Convert the queue into a list of text lines.
612                $retVal = join("\n", @Queue) . "\n";
613            }
614            # Clear the queue.
615            @Queue = ();
616        }
617        # Return the formatted list.
618        return $retVal;
619    }
620    
621    =head3 Confess
622    
623        Confess($message);
624    
625    Trace the call stack and abort the program with the specified message. When used with
626    the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.
627    So, for example
628    
629        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
630    
631    Will abort the program with a stack trace if the value of C<$recNum> is negative.
632    
633    =over 4
634    
635    =item message
636    
637    Message to include in the trace.
638    
639    =back
640    
641    =cut
642    
643    sub Confess {
644        # Get the parameters.
645        my ($message) = @_;
646        # Set up the category and level.
647        $LastCategory = "(confess)";
648        $LastLevel = 0;
649        if (! defined($FIG_Config::no_tool_hdr)) {
650            # Here we have a tool header. Display its length so that the user can adjust the line numbers.
651            my $toolHeaderFile = "$FIG_Config::fig_disk/dist/releases/current/$FIG_Config::arch/tool_hdr";
652            # Only proceed if the tool header file is actually present.
653            if (-f $toolHeaderFile) {
654                my $fh;
655                if (open $fh, "<$toolHeaderFile") {
656                    my @lines = <$fh>;
657                    Trace("Tool header has " . scalar(@lines) . " lines.");
658                }
659            }
660        }
661        # Trace the call stack.
662        Cluck($message);
663        # Abort the program.
664        croak(">>> $message");
665    }
666    
667    =head3 SaveCGI
668    
669        Tracer::SaveCGI($cgi);
670    
671    This method saves the CGI object but does not activate emergency tracing.
672    It is used to allow L</Warn> to work in situations where emergency
673    tracing is contra-indicated (e.g. the wiki).
674    
675    =over 4
676    
677    =item cgi
678    
679    Active CGI query object.
680    
681    =back
682    
683    =cut
684    
685    sub SaveCGI {
686        $SavedCGI = $_[0];
687    }
688    
689    =head3 Warn
690    
691        Warn($message, @options);
692    
693    This method traces an important message. If an RSS feed is configured
694    (via I<FIG_Config::error_feed>) and the tracing destination is C<WARN>,
695    then the message will be echoed to the feed. In general, a tracing
696    destination of C<WARN> indicates that the caller is running as a web
697    service in a production environment; however, this is not a requirement.
698    
699    To force warnings into the RSS feed even when the tracing destination
700    is not C<WARN>, simply specify the C<Feed> tracing module. This can be
701    configured automatically when L</StandardSetup> is used.
702    
703    The L</Cluck> method calls this one for its final message. Since
704    L</Confess> calls L</Cluck>, this means that any error which is caught
705    and confessed will put something in the feed. This insures that someone
706    will be alerted relatively quickly when a failure occurs.
707    
708    =over 4
709    
710    =item message
711    
712    Message to be traced.
713    
714    =item options
715    
716    A list containing zero or more options.
717    
718    =back
719    
720    The permissible options are as follows.
721    
722    =over 4
723    
724    =item noStack
725    
726    If specified, then the stack trace is not included in the output.
727    
728    =back
729    
730    =cut
731    
732    sub Warn {
733        # Get the parameters.
734        my $message = shift @_;
735        my %options = map { $_ => 1 } @_;
736        # Save $@;
737        my $savedError = $@;
738        # Trace the message.
739        Trace($message);
740        # This will contain the lock handle. If it's defined, it means we need to unlock.
741        my $lock;
742        # Check for feed forcing.
743        my $forceFeed = exists $Categories{feed};
744        # An error here would be disastrous. Note that if debug mode is specified,
745        # we do this stuff even in a test environment.
746        eval {
747            # Do we need to put this in the RSS feed?
748            if ($FIG_Config::error_feed && ($Destination eq 'WARN' || $forceFeed)) {
749                # Probably. We need to check first, however, to see if it's from an
750                # ignored IP. For non-CGI situations, we default the IP to the self-referent.
751                my $key = "127.0.0.1";
752                if (defined $SavedCGI) {
753                    # Get the IP address.
754                    $key = $ENV{HTTP_X_FORWARDED_FOR} || $ENV{REMOTE_ADDR};
755                }
756                # Is the IP address in the ignore list?
757                my $found = scalar(grep { $_ eq $key } @FIG_Config::error_ignore_ips);
758                if (! $found) {
759                    # No. We're good. We now need to compute the date, the link, and the title.
760                    # First, the date, in a very specific format.
761                    my $date = strftime("%a, %02e %b %H:%M:%S %Y ", localtime) .
762                        (tz_local_offset() / 30);
763                    # Environment data goes in here. We start with the date.
764                    my $environment = "$date.  ";
765                    # If we need to recap the message (because it's too long to be a title), we'll
766                    # put it in here.
767                    my $recap;
768                    # Copy the message and remove excess space.
769                    my $title = $message;
770                    $title =~ s/\s+/ /gs;
771                    # If it's too long, we have to split it up.
772                    if (length $title > 60) {
773                        # Put the full message in the environment string.
774                        $recap = $title;
775                        # Excerpt it as the title.
776                        $title = substr($title, 0, 50) . "...";
777                    }
778                    # If we have a CGI object, then this is a web error. Otherwise, it's
779                    # command-line.
780                    if (defined $SavedCGI) {
781                        # We're in a web service. The environment is the user's IP, and the link
782                        # is the URL that got us here.
783                        $environment .= "Event Reported at IP address $key process $$.";
784                        my $url = $SavedCGI->self_url();
785                        # We need the user agent string and (if available) the referrer.
786                        # The referrer will be the link.
787                        $environment .= " User Agent $ENV{HTTP_USER_AGENT}";
788                        if ($ENV{HTTP_REFERER}) {
789                            my $link = $ENV{HTTP_REFERER};
790                            $environment .= " referred from <a href=\"$link\">$link</a>.";
791                        } else {
792                            $environment .= " referrer unknown.";
793                        }
794                        # Close off the sentence with the original link.
795                        $environment .= " URL of event is <a href=\"$url\">$url</a>.";
796                    } else {
797                        # No CGI object, so we're a command-line tool. Use the tracing
798                        # key and the PID as the user identifier, and add the command.
799                        my $key = EmergencyKey();
800                        $environment .= "Event Reported by $key process $$.";
801                        if ($CommandLine) {
802                            # We're in a StandardSetup script, so we have the real command line.
803                            $environment .= "\n<pre>" . CGI::escapeHTML($CommandLine) . "</pre>\n";
804                        } elsif ($ENV{_}) {
805                            # We're in a BASH script, so the command has been stored in the _ variable.
806                            $environment .= "  Command = " . CGI::escapeHTML($ENV{_}) . "\n";
807                        }
808                    }
809                    # Build a GUID. We use the current time, the title, and the process ID,
810                    # then digest the result.
811                    my $guid = Digest::MD5::md5_base64(gettimeofday(), $title, $$);
812                    # Finally, the description. This is a stack trace plus various environmental stuff.
813                    # The trace is optional.
814                    my $stackTrace;
815                    if ($options{noStack}) {
816                        $stackTrace = "";
817                    } else {
818                        my @trace = LongMess();
819                        # Only proceed if we got something back.
820                        if (scalar(@trace) > 0) {
821                            $trace[0] =~ s/Tracer::Warn.+?called/Event occurred/;
822                            $stackTrace = "Stack trace:<pre>" . join("\n", @trace, "</pre>");
823                        }
824                    }
825                    # We got the stack trace. Now it's time to put it all together.
826                    # We have a goofy thing here in that we need to HTML-escape some sections of the description
827                    # twice. They will be escaped once here, and then once when written by XML::Simple. They are
828                    # unescaped once when processed by the RSS reader, and stuff in the description is treated as
829                    # HTML. So, anything escaped here is treated as a literal when viewed in the RSS reader, but
830                    # our <br>s and <pre>s are used to format the description.
831                    $recap = (defined $recap ? "<em>" . CGI::escapeHTML($recap) . "</em><br /><br />" : "");
832                    my $description = "$recap$environment  $stackTrace";
833                    # Okay, we have all the pieces. Create a hash of the new event.
834                    my $newItem = { title => $title,
835                                    description => $description,
836                                    category => $LastCategory,
837                                    pubDate => $date,
838                                    guid => $guid,
839                                  };
840                    # We need XML capability for this.
841                    require XML::Simple;
842                    # The RSS document goes in here.
843                    my $rss;
844                    # Get the name of the RSS file. It's in the FIG temporary directory.
845                    my $fileName = "$FIG_Config::temp/$FIG_Config::error_feed";
846                    # Open the config file and lock it.
847                    $lock = Open(undef, "<$FIG_Config::fig_disk/config/FIG_Config.pm");
848                    flock $lock, LOCK_EX;
849                    # Does it exist?
850                    if (-s $fileName) {
851                        # Slurp it in.
852                        $rss = XML::Simple::XMLin($fileName, ForceArray => ['item']);
853                    } else {
854                        my $size = -s $fileName;
855                        # Create an empty channel.
856                        $rss = {
857                            channel => {
858                                title => 'NMPDR Warning Feed',
859                                link => "$FIG_Config::temp_url/$FIG_Config::error_feed",
860                                description => "Important messages regarding the status of the NMPDR.",
861                                generator => "NMPDR Trace Facility",
862                                docs => "http://blogs.law.harvard.edu/tech/rss",
863                                item => []
864                            },
865                        };
866                    }
867                    # Get the channel object.
868                    my $channel = $rss->{channel};
869                    # Update the last-build date.
870                    $channel->{lastBuildDate} = $date;
871                    # Get the item array.
872                    my $items = $channel->{item};
873                    # Insure it has only 100 entries.
874                    while (scalar @{$items} > 100) {
875                        pop @{$items};
876                    }
877                    # Add our new item at the front.
878                    unshift @{$items}, $newItem;
879                    # Create the XML. Note we do not include the root or the declaration. XML Simple can't handle
880                    # the requirements for those.
881                    my $xml = XML::Simple::XMLout($channel, NoAttr => 1, RootName => 'channel', XmlDecl => '');
882                    # Here we put in the root and declaration. The problem is that the root has to have the version attribute
883                    # in it. So, we suppress the root and do it by hand, and that requires suppressing the declaration, too.
884                    $xml = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<rss version=\"2.0\">$xml\n</rss>";
885                    # We don't use Open here because we can't afford an error.
886                    if (open XMLOUT, ">$fileName") {
887                        print XMLOUT $xml;
888                        close XMLOUT;
889                    }
890                }
891            }
892        };
893        if ($@) {
894            # If the feed failed, we need to know why. The error will be traced, but this method will not be involved
895            # (which is a good thing).
896            my $error = $@;
897            Trace("Feed Error: $error") if T(Feed => 0);
898        }
899        # Be sure to unlock.
900        if ($lock) {
901            flock $lock, LOCK_UN;
902            undef $lock;
903        }
904        # Restore the error message.
905        $@ = $savedError;
906    }
907    
908    
909    
910    
911    =head3 Assert
912    
913        Assert($condition1, $condition2, ... $conditionN);
914    
915    Return TRUE if all the conditions are true. This method can be used in conjunction with
916    the OR operator and the L</Confess> method as a debugging assert.
917    So, for example
918    
919        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
920    
921    Will abort the program with a stack trace if the value of C<$recNum> is negative.
922    
923    =cut
924    sub Assert {
925        my $retVal = 1;
926        LOOP: for my $condition (@_) {
927            if (! $condition) {
928                $retVal = 0;
929                last LOOP;
930            }
931        }
932        return $retVal;
933    }
934    
935    =head3 Cluck
936    
937        Cluck($message);
938    
939    Trace the call stack. Note that for best results, you should qualify the call with a
940    trace condition. For example,
941    
942        Cluck("Starting record parse.") if T(3);
943    
944    will only trace the stack if the trace level for the package is 3 or more.
945    
946    =over 4
947    
948    =item message
949    
950    Message to include in the trace.
951    
952    =back
953    
954    =cut
955    
956    sub Cluck {
957        # Get the parameters.
958        my ($message) = @_;
959        # Trace what's happening.
960        Trace("Stack trace for event: $message");
961        # Get the stack trace.
962        my @trace = LongMess();
963        # Convert the trace to a series of messages.
964        for my $line (@trace) {
965            # Replace the tab at the beginning with spaces.
966            $line =~ s/^\t/    /;
967            # Trace the line.
968            Trace($line);
969        }
970        # Issue a warning. This displays the event message and inserts it into the RSS error feed.
971        Warn($message);
972    }
973    
974    =head3 LongMess
975    
976        my @lines = Tracer::LongMess();
977    
978    Return a stack trace with all tracing methods removed. The return will be in the form of a list
979    of message strings.
980    
981    =cut
982    
983    sub LongMess {
984        # Declare the return variable.
985        my @retVal = ();
986        my $confession = longmess("");
987        for my $line (split /\s*\n/, $confession) {
988            unless ($line =~ /Tracer\.pm/) {
989                # Here we have a line worth keeping. Push it onto the result list.
990                push @retVal, $line;
991            }
992        }
993        # Return the result.
994        return @retVal;
995    }
996    
997    =head3 ETracing
998    
999        ETracing($parameter);
1000    
1001    Set up emergency tracing. Emergency tracing is tracing that is turned
1002    on automatically for any program that calls this method. The emergency
1003    tracing parameters are stored in a a file identified by a tracing key.
1004    If this method is called with a CGI object, then the tracing key is
1005    taken from a cookie. If it is called with no parameters, then the tracing
1006    key is taken from an environment variable. If it is called with a string,
1007    the tracing key is that string.
1008    
1009    =over 4
1010    
1011    =item parameter
1012    
1013    A parameter from which the tracing key is computed. If it is a scalar,
1014    that scalar is used as the tracing key. If it is a CGI object, the
1015    tracing key is taken from the C<IP> cookie. If it is omitted, the
1016    tracing key is taken from the C<TRACING> environment variable. If it
1017    is a CGI object and emergency tracing is not on, the C<Trace> and
1018    C<TF> parameters will be used to determine the type of tracing.
1019    
1020    =back
1021    
1022    =cut
1023    
1024    sub ETracing {
1025        # Get the parameter.
1026        my ($parameter) = @_;
1027        # Check for CGI mode.
1028        if (defined $parameter && ref $parameter eq 'CGI') {
1029            $SavedCGI = $parameter;
1030        } else {
1031            $SavedCGI = undef;
1032        }
1033        # Default to no tracing except errors.
1034        my ($tracing, $dest) = ("0", "WARN");
1035        # Check for emergency tracing.
1036        my $tkey = EmergencyKey($parameter);
1037        my $emergencyFile = EmergencyFileName($tkey);
1038        if (-e $emergencyFile) {
1039            # We have the file. Read in the data.
1040            my @tracing = GetFile($emergencyFile);
1041            # Pull off the time limit.
1042            my $expire = shift @tracing;
1043            # Convert it to seconds.
1044            $expire *= 3600;
1045            # Check the file data.
1046            my $stat = stat($emergencyFile);
1047            my ($now) = gettimeofday;
1048            if ($now - $stat->mtime > $expire) {
1049                # Delete the expired file.
1050                unlink $emergencyFile;
1051            } else {
1052                # Emergency tracing is on. Pull off the destination and
1053                # the trace level;
1054                $dest = shift @tracing;
1055                my $level = shift @tracing;
1056                # Convert the destination to a real tracing destination.
1057                # temp directory.
1058                $dest = EmergencyTracingDest($tkey, $dest);
1059                # Insure Tracer is specified.
1060                my %moduleHash = map { $_ => 1 } @tracing;
1061                $moduleHash{Tracer} = 1;
1062                # Set the trace parameter.
1063                $tracing = join(" ", $level, sort keys %moduleHash);
1064            }
1065        } elsif (defined $SavedCGI) {
1066            # There's no emergency tracing, but we have a CGI object, so check
1067            # for tracing from the form parameters.
1068            if ($SavedCGI->param('Trace')) {
1069                # Here the user has requested tracing via a form.
1070                $dest = ($SavedCGI->param('TF') ? ">$FIG_Config::temp/Trace$$.log" : "QUEUE");
1071                $tracing = $SavedCGI->param('Trace') . " Tracer";
1072            }
1073        }
1074        # Setup the tracing we've determined from all the stuff above.
1075        TSetup($tracing, $dest);
1076        # Check to see if we're a web script.
1077        if (defined $SavedCGI) {
1078            # Yes we are. Trace the form and environment data.
1079            TraceParms($SavedCGI);
1080            # Check for RAW mode. In raw mode, we print a fake header so that we see everything
1081            # emitted by the script in its raw form.
1082            if (T(Raw => 3)) {
1083                print CGI::header(-type => 'text/plain', -tracing => 'Raw');
1084            }
1085        }
1086    }
1087    
1088    =head3 EmergencyFileName
1089    
1090        my $fileName = Tracer::EmergencyFileName($tkey);
1091    
1092    Return the emergency tracing file name. This is the file that specifies
1093    the tracing information.
1094    
1095    =over 4
1096    
1097    =item tkey
1098    
1099    Tracing key for the current program.
1100    
1101    =item RETURN
1102    
1103    Returns the name of the file to contain the emergency tracing information.
1104    
1105    =back
1106    
1107    =cut
1108    
1109    sub EmergencyFileName {
1110        # Get the parameters.
1111        my ($tkey) = @_;
1112        # Compute the emergency tracing file name.
1113        return "$FIG_Config::temp/Emergency$tkey.txt";
1114    }
1115    
1116    =head3 EmergencyFileTarget
1117    
1118        my $fileName = Tracer::EmergencyFileTarget($tkey);
1119    
1120    Return the emergency tracing target file name. This is the file that receives
1121    the tracing output for file-based tracing.
1122    
1123    =over 4
1124    
1125    =item tkey
1126    
1127    Tracing key for the current program.
1128    
1129    =item RETURN
1130    
1131    Returns the name of the file to contain the trace output.
1132    
1133    =back
1134    
1135    =cut
1136    
1137    sub EmergencyFileTarget {
1138        # Get the parameters.
1139        my ($tkey) = @_;
1140        # Compute the emergency tracing file name.
1141        return "$FIG_Config::temp/trace$tkey.log";
1142    }
1143    
1144    =head3 EmergencyTracingDest
1145    
1146        my $dest = Tracer::EmergencyTracingDest($tkey, $myDest);
1147    
1148    This method converts an emergency tracing destination to a real
1149    tracing destination. The main difference is that if the
1150    destination is C<FILE> or C<APPEND>, we convert it to file
1151    output. If the destination is C<DUAL>, we convert it to file
1152    and standard output.
1153    
1154    =over 4
1155    
1156    =item tkey
1157    
1158    Tracing key for this environment.
1159    
1160    =item myDest
1161    
1162    Destination from the emergency tracing file.
1163    
1164    =item RETURN
1165    
1166    Returns a destination that can be passed into L</TSetup>.
1167    
1168    =back
1169    
1170    =cut
1171    
1172    sub EmergencyTracingDest {
1173        # Get the parameters.
1174        my ($tkey, $myDest) = @_;
1175        # Declare the return variable.
1176        my $retVal = $myDest;
1177        # Process according to the destination value.
1178        if ($myDest eq 'FILE') {
1179            $retVal = ">" . EmergencyFileTarget($tkey);
1180        } elsif ($myDest eq 'APPEND') {
1181            $retVal = ">>" . EmergencyFileTarget($tkey);
1182        } elsif ($myDest eq 'DUAL') {
1183            $retVal = "+>" . EmergencyFileTarget($tkey);
1184        } elsif ($myDest eq 'WARN') {
1185            $retVal = "WARN";
1186        }
1187        # Return the result.
1188        return $retVal;
1189    }
1190    
1191    =head3 Emergency
1192    
1193        Emergency($key, $hours, $dest, $level, @modules);
1194    
1195    Turn on emergency tracing. This method is normally invoked over the web from
1196    a debugging console, but it can also be called by the C<trace.pl> script.
1197    The caller specifies the duration of the emergency in hours, the desired tracing
1198    destination, the trace level, and a list of the trace modules to activate.
1199    For the length of the duration, when a program in an environment with the
1200    specified tracing key active invokes a Sprout CGI script, tracing will be
1201    turned on automatically. See L</TSetup> for more about tracing setup and
1202    L</ETracing> for more about emergency tracing.
1203    
1204    =over 4
1205    
1206    =item tkey
1207    
1208    The tracing key. This is used to identify the control file and the trace file.
1209    
1210    =item hours
1211    
1212    Number of hours to keep emergency tracing alive.
1213    
1214    =item dest
1215    
1216    Tracing destination. If no path information is specified for a file
1217    destination, it is put in the FIG temporary directory.
1218    
1219    =item level
1220    
1221    Tracing level. A higher level means more trace messages.
1222    
1223    =item modules
1224    
1225    A list of the tracing modules to activate.
1226    
1227    =back
1228    
1229    =cut
1230    
1231    sub Emergency {
1232        # Get the parameters.
1233        my ($tkey, $hours, $dest, $level, @modules) = @_;
1234        # Create the emergency file.
1235        my $specFile = EmergencyFileName($tkey);
1236        my $outHandle = Open(undef, ">$specFile");
1237        print $outHandle join("\n", $hours, $dest, $level, @modules, "");
1238    }
1239    
1240    =head3 EmergencyKey
1241    
1242        my $tkey = EmergencyKey($parameter);
1243    
1244    Return the Key to be used for emergency tracing. This could be an IP address,
1245     a session ID, or a user name, depending on the environment.
1246    
1247    =over 4
1248    
1249    =item parameter
1250    
1251    Parameter defining the method for finding the tracing key. If it is a scalar,
1252    then it is presumed to be the tracing key itself. If it is a CGI object, then
1253    the tracing key is taken from the C<IP> cookie. Otherwise, the tracing key is
1254    taken from the C<TRACING> environment variable.
1255    
1256    =item RETURN
1257    
1258    Returns the key to be used for labels in emergency tracing.
1259    
1260    =back
1261    
1262    =cut
1263    
1264    sub EmergencyKey {
1265        # Get the parameters.
1266        my ($parameter) = @_;
1267        # Declare the return variable.
1268        my $retVal;
1269        # Determine the parameter type.
1270        if (! defined $parameter) {
1271            # Here we're supposed to check the environment. If that fails, we
1272            # get the effective login ID.
1273            $retVal = $ENV{TRACING} || scalar getpwuid($<);
1274        } else {
1275            my $ptype = ref $parameter;
1276            if ($ptype eq 'CGI') {
1277                # Here we were invoked from a web page. Look for a cookie.
1278                $retVal = $parameter->cookie('IP');
1279            } elsif (! $ptype) {
1280                # Here the key was passed in.
1281                $retVal = $parameter;
1282            }
1283        }
1284        # If no luck finding a key, use the PID.
1285        if (! defined $retVal) {
1286            $retVal = $$;
1287        }
1288        # Return the result.
1289        return $retVal;
1290    }
1291    
1292    
1293    =head3 TraceParms
1294    
1295        Tracer::TraceParms($cgi);
1296    
1297    Trace the CGI parameters at trace level CGI => 3 and the environment variables
1298    at level CGI => 4. A self-referencing URL is traced at level CGI => 2.
1299    
1300    =over 4
1301    
1302    =item cgi
1303    
1304    CGI query object containing the parameters to trace.
1305    
1306    =back
1307    
1308    =cut
1309    
1310    sub TraceParms {
1311        # Get the parameters.
1312        my ($cgi) = @_;
1313        if (T(CGI => 2)) {
1314            # Here we trace the GET-style URL for the script.
1315            Trace("[URL] " . $cgi->url(-relative => 1, -query => 1));
1316        }
1317        if (T(CGI => 3)) {
1318            # Here we want to trace the parameter data.
1319            my @names = $cgi->param;
1320            for my $parmName (sort @names) {
1321                # Note we skip the Trace parameters, which are for our use only.
1322                if ($parmName ne 'Trace' && $parmName ne 'TF') {
1323                    my @values = $cgi->param($parmName);
1324                    Trace("[CGI] $parmName = " . join(", ", @values));
1325                }
1326            }
1327            # Display the request method.
1328            my $method = $cgi->request_method();
1329            Trace("Method: $method");
1330        }
1331        if (T(CGI => 4)) {
1332            # Here we want the environment data too.
1333            for my $envName (sort keys %ENV) {
1334                Trace("[ENV] $envName = $ENV{$envName}");
1335            }
1336        }
1337    }
1338    
1339    =head3 TraceImages
1340    
1341        Tracer::TraceImages($htmlString);
1342    
1343    Trace information about all of an html document's images. The tracing
1344    will be for type "IMG" at level 3. The image's source string
1345    will be displayed. This is generally either the URL of the image or
1346    raw data for the image itself. If the source is too long, only the first 300
1347    characters will be shown at trace level 3. The entire source will be shown,
1348    however, at trace level 4. This method is not very smart, and might catch
1349    Javascript code, but it is still useful when debugging the arcane
1350    behavior of images in multiple browser environments.
1351    
1352    =over 4
1353    
1354    =item htmlString
1355    
1356    HTML text for an outgoing web page.
1357    
1358    =back
1359    
1360    =cut
1361    
1362    sub TraceImages {
1363        # Only proceed if we're at the proper trace level.
1364        if (T(IMG => 3)) {
1365            # For performance reasons we're manipulating $_[0] instead of retrieving the string
1366            # into a variable called "$htmlString". This is because we expect html strings to be
1367            # long, and don't want to copy them any more than we have to.
1368            Trace(length($_[0]) . " characters in web page.");
1369            # Loop through the HTML, culling image tags.
1370            while ($_[0] =~ /<img\s+[^>]+?src="([^"]+)"/sgi) {
1371                # Extract the source string and determine whether or not it's too long.
1372                my $srcString = $1;
1373                my $pos = pos($_[0]) - length($srcString);
1374                my $excess = length($srcString) - 300;
1375                # We'll put the display string in here.
1376                my $srcDisplay = $srcString;
1377                # If it's a data string, split it at the comma.
1378                $srcDisplay =~ s/^(data[^,]+,)/$1\n/;
1379                # If there's no excess or we're at trace level 4, we're done. At level 3 with
1380                # a long string, however, we only show the first 300 characters.
1381                if ($excess > 0 && ! T(IMG => 4)) {
1382                    $srcDisplay = substr($srcDisplay,0,300) . "\nplus $excess characters.";
1383                }
1384                # Output the trace message.
1385                Trace("Image tag at position $pos:\n$srcDisplay");
1386            }
1387        }
1388    }
1389    
1390    =head2 Command-Line Utility Methods
1391    
1392    =head3 SendSMS
1393    
1394        my $msgID = Tracer::SendSMS($phoneNumber, $msg);
1395    
1396    Send a text message to a phone number using Clickatell. The FIG_Config file must contain the
1397    user name, password, and API ID for the relevant account in the hash reference variable
1398    I<$FIG_Config::phone>, using the keys C<user>, C<password>, and C<api_id>. For
1399    example, if the user name is C<BruceTheHumanPet>, the password is C<silly>, and the API ID
1400    is C<2561022>, then the FIG_Config file must contain
1401    
1402        $phone =  { user => 'BruceTheHumanPet',
1403                    password => 'silly',
1404                    api_id => '2561022' };
1405    
1406    The original purpose of this method was to insure Bruce would be notified immediately when the
1407    Sprout Load terminates. Care should be taken if you do not wish Bruce to be notified immediately
1408    when you call this method.
1409    
1410    The message ID will be returned if successful, and C<undef> if an error occurs.
1411    
1412    =over 4
1413    
1414    =item phoneNumber
1415    
1416    Phone number to receive the message, in international format. A United States phone number
1417    would be prefixed by "1". A British phone number would be prefixed by "44".
1418    
1419    =item msg
1420    
1421    Message to send to the specified phone.
1422    
1423    =item RETURN
1424    
1425    Returns the message ID if successful, and C<undef> if the message could not be sent.
1426    
1427    =back
1428    
1429    =cut
1430    
1431    sub SendSMS {
1432        # Get the parameters.
1433        my ($phoneNumber, $msg) = @_;
1434        # Declare the return variable. If we do not change it, C<undef> will be returned.
1435        my $retVal;
1436        # Only proceed if we have phone support.
1437        if (! defined $FIG_Config::phone) {
1438            Trace("Phone support not present in FIG_Config.") if T(1);
1439        } else {
1440            # Get the phone data.
1441            my $parms = $FIG_Config::phone;
1442            # Get the Clickatell URL.
1443            my $url = "http://api.clickatell.com/http/";
1444            # Create the user agent.
1445            my $ua = LWP::UserAgent->new;
1446            # Request a Clickatell session.
1447            my $resp = $ua->post("$url/sendmsg", { user => $parms->{user},
1448                                         password => $parms->{password},
1449                                         api_id => $parms->{api_id},
1450                                         to => $phoneNumber,
1451                                         text => $msg});
1452            # Check for an error.
1453            if (! $resp->is_success) {
1454                Trace("Alert failed.") if T(1);
1455            } else {
1456                # Get the message ID.
1457                my $rstring = $resp->content;
1458                if ($rstring =~ /^ID:\s+(.*)$/) {
1459                    $retVal = $1;
1460                } else {
1461                    Trace("Phone attempt failed with $rstring") if T(1);
1462                }
1463            }
1464        }
1465        # Return the result.
1466        return $retVal;
1467    }
1468    
1469    =head3 StandardSetup
1470    
1471        my ($options, @parameters) = StandardSetup(\@categories, \%options, $parmHelp, @ARGV);
1472    
1473    This method performs standard command-line parsing and tracing setup. The return
1474    values are a hash of the command-line options and a list of the positional
1475    parameters. Tracing is automatically set up and the command-line options are
1476    validated.
1477    
1478    This is a complex method that does a lot of grunt work. The parameters can
1479    be more easily understood, however, once they are examined individually.
1480    
1481    The I<categories> parameter is the most obtuse. It is a reference to a list of
1482    special-purpose tracing categories. Most tracing categories are PERL package
1483    names. So, for example, if you wanted to turn on tracing inside the B<Sprout>,
1484    B<ERDB>, and B<SproutLoad> packages, you would specify the categories
1485    
1486        ["Sprout", "SproutLoad", "ERDB"]
1487    
1488    This would cause trace messages in the specified three packages to appear in
1489    the output. There are two special tracing categories that are automatically
1490    handled by this method. In other words, if you used L</TSetup> you would need
1491    to include these categories manually, but if you use this method they are turned
1492    on automatically.
1493    
1494    =over 4
1495    
1496    =item SQL
1497    
1498    Traces SQL commands and activity.
1499    
1500    =item Tracer
1501    
1502    Traces error messages and call stacks.
1503    
1504    =back
1505    
1506    C<SQL> is only turned on if the C<-sql> option is specified in the command line.
1507    The trace level is specified using the C<-trace> command-line option. For example,
1508    the following command line for C<TransactFeatures> turns on SQL tracing and runs
1509    all tracing at level 3.
1510    
1511        TransactFeatures -trace=3 -sql register ../xacts IDs.tbl
1512    
1513    Standard tracing is output to the standard output and echoed to the file
1514    C<trace>I<$$>C<.log> in the FIG temporary directory, where I<$$> is the
1515    process ID. You can also specify the C<user> parameter to put a user ID
1516    instead of a process ID in the trace file name. So, for example
1517    
1518    The default trace level is 2. To get all messages, specify a trace level of 4.
1519    For a genome-by-genome update, use 3.
1520    
1521        TransactFeatures -trace=3 -sql -user=Bruce register ../xacts IDs.tbl
1522    
1523    would send the trace output to C<traceBruce.log> in the temporary directory.
1524    
1525    The I<options> parameter is a reference to a hash containing the command-line
1526    options, their default values, and an explanation of what they mean. Command-line
1527    options may be in the form of switches or keywords. In the case of a switch, the
1528    option value is 1 if it is specified and 0 if it is not specified. In the case
1529    of a keyword, the value is separated from the option name by an equal sign. You
1530    can see this last in the command-line example above.
1531    
1532    You can specify a different default trace level by setting C<$options->{trace}>
1533    prior to calling this method.
1534    
1535    An example at this point would help. Consider, for example, the command-line utility
1536    C<TransactFeatures>. It accepts a list of positional parameters plus the options
1537    C<safe>, C<noAlias>, C<start>, and C<tblFiles>. To start up this command, we execute
1538    the following code.
1539    
1540        my ($options, @parameters) = Tracer::StandardSetup(["DocUtils"],
1541                            { safe => [0, "use database transactions"],
1542                              noAlias => [0, "do not expect aliases in CHANGE transactions"],
1543                              start => [' ', "start with this genome"],
1544                              tblFiles => [0, "output TBL files containing the corrected IDs"] },
1545                            "<command> <transactionDirectory> <IDfile>",
1546                          @ARGV);
1547    
1548    
1549    The call to C<ParseCommand> specifies the default values for the options and
1550    stores the actual options in a hash that is returned as C<$options>. The
1551    positional parameters are returned in C<@parameters>.
1552    
1553    The following is a sample command line for C<TransactFeatures>.
1554    
1555        TransactFeatures -trace=2 -noAlias register ../xacts IDs.tbl
1556    
1557    Single and double hyphens are equivalent. So, you could also code the
1558    above command as
1559    
1560        TransactFeatures --trace=2 --noAlias register ../xacts IDs.tbl
1561    
1562    In this case, C<register>, C<../xacts>, and C<IDs.tbl> are the positional
1563    parameters, and would find themselves in I<@parameters> after executing the
1564    above code fragment. The tracing would be set to level 2, and the categories
1565    would be C<Tracer>, and <DocUtils>. C<Tracer> is standard,
1566    and C<DocUtils> was included because it came in within the first parameter
1567    to this method. The I<$options> hash would be
1568    
1569        { trace => 2, sql => 0, safe => 0,
1570          noAlias => 1, start => ' ', tblFiles => 0 }
1571    
1572    Use of C<StandardSetup> in this way provides a simple way of performing
1573    standard tracing setup and command-line parsing. Note that the caller is
1574    not even aware of the command-line switches C<-trace> and C<-sql>, which
1575    are used by this method to control the tracing. If additional tracing features
1576    need to be added in the future, they can be processed by this method without
1577    upsetting the command-line utilities.
1578    
1579    If the C<background> option is specified on the command line, then the
1580    standard and error outputs will be directed to files in the temporary
1581    directory, using the same suffix as the trace file. So, if the command
1582    line specified
1583    
1584        -user=Bruce -background
1585    
1586    then the trace output would go to C<traceBruce.log>, the standard output to
1587    C<outBruce.log>, and the error output to C<errBruce.log>. This is designed to
1588    simplify starting a command in the background.
1589    
1590    The user name is also used as the tracing key for L</Emergency Tracing>.
1591    Specifying a value of C<E> for the trace level causes emergency tracing to
1592    be used instead of custom tracing. If the user name is not specified,
1593    the tracing key is taken from the C<Tracing> environment variable. If there
1594    is no value for that variable, the tracing key will be computed from the active
1595    login ID.
1596    
1597    Since the default situation in StandardSetup is to trace to the standard
1598    output, errors that occur in command-line scripts will not generate
1599    RSS events. To force the events, use the C<warn> option.
1600    
1601        TransactFeatures -background -warn register ../xacts IDs.tbl
1602    
1603    Finally, if the special option C<-help> is specified, the option
1604    names will be traced at level 0 and the program will exit without processing.
1605    This provides a limited help capability. For example, if the user enters
1606    
1607        TransactFeatures -help
1608    
1609    he would see the following output.
1610    
1611        TransactFeatures [options] <command> <transactionDirectory> <IDfile>
1612            -trace    tracing level (default E)
1613            -sql      trace SQL commands
1614            -safe     use database transactions
1615            -noAlias  do not expect aliases in CHANGE transactions
1616            -start    start with this genome
1617            -tblFiles output TBL files containing the corrected IDs
1618            -forked   do not erase the trace file before tracing
1619    
1620    The caller has the option of modifying the tracing scheme by placing a value
1621    for C<trace> in the incoming options hash. The default value can be overridden,
1622    or the tracing to the standard output can be turned off by suffixing a minus
1623    sign to the trace level. So, for example,
1624    
1625        { trace => [0, "tracing level (default 0)"],
1626           ...
1627    
1628    would set the default trace level to 0 instead of E, while
1629    
1630        { trace => ["2-", "tracing level (default 2)"],
1631           ...
1632    
1633    would set the default to 2, but trace only to the log file, not to the
1634    standard output.
1635    
1636    The parameters to this method are as follows.
1637    
1638    =over 4
1639    
1640    =item categories
1641    
1642    Reference to a list of tracing category names. These should be names of
1643    packages whose internal workings will need to be debugged to get the
1644    command working.
1645    
1646    =item options
1647    
1648    Reference to a hash containing the legal options for the current command mapped
1649    to their default values and descriptions. The user can override the defaults
1650    by specifying the options as command-line switches prefixed by a hyphen.
1651    Tracing-related options may be added to this hash. If the C<-h> option is
1652    specified on the command line, the option descriptions will be used to
1653    explain the options. To turn off tracing to the standard output, add a
1654    minus sign to the value for C<trace> (see above).
1655    
1656    =item parmHelp
1657    
1658    A string that vaguely describes the positional parameters. This is used
1659    if the user specifies the C<-h> option.
1660    
1661    =item argv
1662    
1663    List of command line parameters, including the option switches, which must
1664    precede the positional parameters and be prefixed by a hyphen.
1665    
1666    =item RETURN
1667    
1668    Returns a list. The first element of the list is the reference to a hash that
1669    maps the command-line option switches to their values. These will either be the
1670    default values or overrides specified on the command line. The remaining
1671    elements of the list are the position parameters, in order.
1672    
1673    =back
1674    
1675    =cut
1676    
1677    sub StandardSetup {
1678        # Get the parameters.
1679        my ($categories, $options, $parmHelp, @argv) = @_;
1680        # Get the default tracing key.
1681        my $tkey = EmergencyKey();
1682        # Save the command line.
1683        $CommandLine = join(" ", $0, map { $_ =~ /\s/ ? "\"$_\"" : $_ } @argv);
1684        # Add the tracing options.
1685        if (! exists $options->{trace}) {
1686            $options->{trace} = ['2', "tracing level (E for emergency tracing)"];
1687        }
1688        if (! exists $options->{forked}) {
1689            $options->{forked} = [0, "keep old trace file"];
1690        }
1691        $options->{sql} = [0, "turn on SQL tracing"];
1692        $options->{help} = [0, "display command-line options"];
1693        $options->{user} = [$tkey, "tracing key"];
1694        $options->{background} = [0, "spool standard and error output"];
1695        $options->{warn} = [0, "send errors to RSS feed"];
1696        # Create a parsing hash from the options hash. The parsing hash
1697        # contains the default values rather than the default value
1698        # and the description. While we're at it, we'll memorize the
1699        # length of the longest option name.
1700        my $longestName = 0;
1701        my %parseOptions = ();
1702        for my $key (keys %{$options}) {
1703            if (length $key > $longestName) {
1704                $longestName = length $key;
1705            }
1706            $parseOptions{$key} = $options->{$key}->[0];
1707        }
1708        # Parse the command line.
1709        my ($retOptions, @retParameters) = ParseCommand(\%parseOptions, @argv);
1710        # Get the logfile suffix.
1711        my $suffix = $retOptions->{user};
1712        # Check for background mode.
1713        if ($retOptions->{background}) {
1714            my $outFileName = "$FIG_Config::temp/out$suffix$$.log";
1715            my $errFileName = "$FIG_Config::temp/err$suffix$$.log";
1716            open STDOUT, ">$outFileName";
1717            open STDERR, ">$errFileName";
1718            # Check for phone support. If we have phone support and a phone number,
1719            # we want to turn it on.
1720            if ($ENV{PHONE} && defined($FIG_Config::phone)) {
1721                $retOptions->{phone} = $ENV{PHONE};
1722            }
1723        }
1724        # Now we want to set up tracing. First, we need to know if the user
1725        # wants emergency tracing.
1726        if ($retOptions->{trace} eq 'E') {
1727            ETracing($retOptions->{user});
1728        } else {
1729            # Here the tracing is controlled from the command line.
1730            my @cats = @{$categories};
1731            if ($retOptions->{sql}) {
1732                push @cats, "SQL";
1733            }
1734            if ($retOptions->{warn}) {
1735                push @cats, "Feed";
1736            }
1737            # Add the default categories.
1738            push @cats, "Tracer";
1739            # Next, we create the category string by joining the categories.
1740            my $cats = join(" ", @cats);
1741            # Check to determine whether or not the caller wants to turn off tracing
1742            # to the standard output.
1743            my $traceLevel = $retOptions->{trace};
1744            my $textOKFlag = 1;
1745            if ($traceLevel =~ /^(.)-/) {
1746                $traceLevel = $1;
1747                $textOKFlag = 0;
1748            }
1749            # Now we set up the trace mode.
1750            my $traceMode;
1751            # Verify that we can open a file in the FIG temporary directory.
1752            my $traceFileName = "$FIG_Config::temp/trace$suffix.log";
1753            my $traceFileSpec = ($retOptions->{forked} ? ">>$traceFileName" : ">$traceFileName");
1754            if (open TESTTRACE, "$traceFileSpec") {
1755                # Here we can trace to a file.
1756                $traceMode = ">>$traceFileName";
1757                if ($textOKFlag) {
1758                    # Echo to standard output if the text-OK flag is set.
1759                    $traceMode = "+$traceMode";
1760                }
1761                # Close the test file.
1762                close TESTTRACE;
1763            } else {
1764                # Here we can't trace to a file. Complain about this.
1765                warn "Could not open trace file $traceFileName: $!\n";
1766                # We trace to the standard output if it's
1767                # okay, and the error log otherwise.
1768                if ($textOKFlag) {
1769                    $traceMode = "TEXT";
1770                } else {
1771                    $traceMode = "WARN";
1772                }
1773            }
1774            # Now set up the tracing.
1775            TSetup("$traceLevel $cats", $traceMode);
1776        }
1777        # Check for the "help" option. If it is specified, dump the command-line
1778        # options and exit the program.
1779        if ($retOptions->{help}) {
1780            $0 =~ m#[/\\](\w+)(\.pl)?$#i;
1781            print "$1 [options] $parmHelp\n";
1782            for my $key (sort keys %{$options}) {
1783                my $name = Pad($key, $longestName, 0, ' ');
1784                my $desc = $options->{$key}->[1];
1785                if ($options->{$key}->[0]) {
1786                    $desc .= " (default " . $options->{$key}->[0] . ")";
1787                }
1788                print "  $name $desc\n";
1789            }
1790            exit(0);
1791        }
1792        # Trace the options, if applicable.
1793        if (T(3)) {
1794            my @parms = grep { $retOptions->{$_} } keys %{$retOptions};
1795            Trace("Selected options: " . join(", ", sort @parms) . ".");
1796        }
1797        # Return the parsed parameters.
1798        return ($retOptions, @retParameters);
1799    }
1800    
1801    =head3 ReadOptions
1802    
1803        my %options = Tracer::ReadOptions($fileName);
1804    
1805    Read a set of options from a file. Each option is encoded in a line of text that has the
1806    format
1807    
1808    I<optionName>C<=>I<optionValue>C<; >I<comment>
1809    
1810    The option name must consist entirely of letters, digits, and the punctuation characters
1811    C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank
1812    character is a semi-colon will be ignored. The return hash will map each option name to
1813    the corresponding option value.
1814    
1815    =over 4
1816    
1817    =item fileName
1818    
1819    Name of the file containing the option data.
1820    
1821    =item RETURN
1822    
1823    Returns a hash mapping the option names specified in the file to their corresponding option
1824    value.
1825    
1826    =back
1827    
1828    =cut
1829    
1830    sub ReadOptions {
1831        # Get the parameters.
1832        my ($fileName) = @_;
1833        # Open the file.
1834        (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");
1835        # Count the number of records read.
1836        my ($records, $comments) = 0;
1837        # Create the return hash.
1838        my %retVal = ();
1839        # Loop through the file, accumulating key-value pairs.
1840        while (my $line = <CONFIGFILE>) {
1841            # Denote we've read a line.
1842            $records++;
1843            # Determine the line type.
1844            if ($line =~ /^\s*[\n\r]/) {
1845                # A blank line is a comment.
1846                $comments++;
1847            } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {
1848                # Here we have an option assignment.
1849                retVal{$1} = $2;
1850            } elsif ($line =~ /^\s*;/) {
1851                # Here we have a text comment.
1852                $comments++;
1853            } else {
1854                # Here we have an invalid line.
1855                Trace("Invalid option statement in record $records.") if T(0);
1856            }
1857        }
1858        # Return the hash created.
1859        return %retVal;
1860    }
1861    
1862    =head3 GetOptions
1863    
1864        Tracer::GetOptions(\%defaults, \%options);
1865    
1866    Merge a specified set of options into a table of defaults. This method takes two hash references
1867    as input and uses the data from the second to update the first. If the second does not exist,
1868    there will be no effect. An error will be thrown if one of the entries in the second hash does not
1869    exist in the first.
1870    
1871    Consider the following example.
1872    
1873        my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options);
1874    
1875    In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and
1876    B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of
1877    B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and
1878    the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level
1879    will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as
1880    
1881        {databaseType => 'Oracle'}
1882    
1883    an error will occur because the B<databaseType> option does not exist.
1884    
1885    =over 4
1886    
1887    =item defaults
1888    
1889    Table of default option values.
1890    
1891    =item options
1892    
1893    Table of overrides, if any.
1894    
1895    =item RETURN
1896    
1897    Returns a reference to the default table passed in as the first parameter.
1898    
1899    =back
1900    
1901    =cut
1902    
1903    sub GetOptions {
1904        # Get the parameters.
1905        my ($defaults, $options) = @_;
1906        # Check for overrides.
1907        if ($options) {
1908            # Loop through the overrides.
1909            while (my ($option, $setting) = each %{$options}) {
1910                # Insure this override exists.
1911                if (!exists $defaults->{$option}) {
1912                    croak "Unrecognized option $option encountered.";
1913                } else {
1914                    # Apply the override.
1915                    $defaults->{$option} = $setting;
1916                }
1917            }
1918        }
1919        # Return the merged table.
1920        return $defaults;
1921    }
1922    
1923    =head3 MergeOptions
1924    
1925        Tracer::MergeOptions(\%table, \%defaults);
1926    
1927    Merge default values into a hash table. This method looks at the key-value pairs in the
1928    second (default) hash, and if a matching key is not found in the first hash, the default
1929    pair is copied in. The process is similar to L</GetOptions>, but there is no error-
1930    checking and no return value.
1931    
1932    =over 4
1933    
1934    =item table
1935    
1936    Hash table to be updated with the default values.
1937    
1938    =item defaults
1939    
1940    Default values to be merged into the first hash table if they are not already present.
1941    
1942    =back
1943    
1944    =cut
1945    
1946    sub MergeOptions {
1947        # Get the parameters.
1948        my ($table, $defaults) = @_;
1949        # Loop through the defaults.
1950        while (my ($key, $value) = each %{$defaults}) {
1951            if (!exists $table->{$key}) {
1952                $table->{$key} = $value;
1953            }
1954        }
1955    }
1956    
1957    =head3 UnparseOptions
1958    
1959        my $optionString = Tracer::UnparseOptions(\%options);
1960    
1961    Convert an option hash into a command-line string. This will not
1962    necessarily be the same text that came in, but it will nonetheless
1963    produce the same ultimate result when parsed by L</StandardSetup>.
1964    
1965    =over 4
1966    
1967    =item options
1968    
1969    Reference to a hash of options to convert into an option string.
1970    
1971    =item RETURN
1972    
1973    Returns a string that will parse to the same set of options when
1974    parsed by L</StandardSetup>.
1975    
1976    =back
1977    
1978    =cut
1979    
1980    sub UnparseOptions {
1981        # Get the parameters.
1982        my ($options) = @_;
1983        # The option segments will be put in here.
1984        my @retVal = ();
1985        # Loop through the options.
1986        for my $key (keys %$options) {
1987            # Get the option value.
1988            my $value = $options->{$key};
1989            # Only use it if it's nonempty.
1990            if (defined $value && $value ne "") {
1991                my $segment = "--$key=$value";
1992                # Quote it if necessary.
1993                if ($segment =~ /[ |<>*]/) {
1994                    $segment = '"' . $segment . '"';
1995                }
1996                # Add it to the return list.
1997                push @retVal, $segment;
1998            }
1999        }
2000        # Return the result.
2001        return join(" ", @retVal);
2002    }
2003    
2004    =head3 ParseCommand
2005    
2006        my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList);
2007    
2008    Parse a command line consisting of a list of parameters. The initial parameters may be option
2009    specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped
2010    off and merged into a table of default options. The remainder of the command line is
2011    returned as a list of positional arguments. For example, consider the following invocation.
2012    
2013        my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words);
2014    
2015    In this case, the list @words will be treated as a command line and there are two options available,
2016    B<errors> and B<logFile>. If @words has the following format
2017    
2018        -logFile=error.log apple orange rutabaga
2019    
2020    then at the end of the invocation, C<$options> will be
2021    
2022        { errors => 0, logFile => 'error.log' }
2023    
2024    and C<@arguments> will contain
2025    
2026        apple orange rutabaga
2027    
2028    The parser allows for some escape sequences. See L</UnEscape> for a description. There is no
2029    support for quote characters. Options can be specified with single or double hyphens.
2030    
2031    =over 4
2032    
2033    =item optionTable
2034    
2035    Table of default options.
2036    
2037    =item inputList
2038    
2039    List of words on the command line.
2040    
2041    =item RETURN
2042    
2043    Returns a reference to the option table and a list of the positional arguments.
2044    
2045    =back
2046    
2047    =cut
2048    
2049    sub ParseCommand {
2050        # Get the parameters.
2051        my ($optionTable, @inputList) = @_;
2052          # Process any options in the input list.          # Process any options in the input list.
2053          my %overrides = ();          my %overrides = ();
2054          while ((@inputList > 0) && ($inputList[0] =~ /^-/)) {      while ((@inputList > 0) && ($inputList[0] =~ /^--?/)) {
2055                  # Get the current option.                  # Get the current option.
2056                  my $arg = shift @inputList;                  my $arg = shift @inputList;
2057                  # Pull out the option name.                  # Pull out the option name.
2058                  $arg =~ /^-([^=]*)/g;          $arg =~ /^--?([^=]*)/g;
2059                  my $name = $1;                  my $name = $1;
2060                  # Check for an option value.                  # Check for an option value.
2061                  if ($arg =~ /\G=(.*)$/g) {                  if ($arg =~ /\G=(.*)$/g) {
2062                          # Here we have a value for the option.                          # Here we have a value for the option.
2063                          $overrides{$name} = UnEscape($1);                          $overrides{$name} = UnEscape($1);
2064                  } else {                  } else {
2065                          # Here there is no value, so we use 1.              # Here there is no value, so we use 1.
2066                          $overrides{$name} = 1;              $overrides{$name} = 1;
2067            }
2068        }
2069        # Merge the options into the defaults.
2070        GetOptions($optionTable, \%overrides);
2071        # Translate the remaining parameters.
2072        my @retVal = ();
2073        for my $inputParm (@inputList) {
2074            push @retVal, UnEscape($inputParm);
2075        }
2076        # Return the results.
2077        return ($optionTable, @retVal);
2078    }
2079    
2080    
2081    =head2 File Utility Methods
2082    
2083    =head3 GetFile
2084    
2085        my @fileContents = Tracer::GetFile($fileName);
2086    
2087        or
2088    
2089        my $fileContents = Tracer::GetFile($fileName);
2090    
2091    Return the entire contents of a file. In list context, line-ends are removed and
2092    each line is a list element. In scalar context, line-ends are replaced by C<\n>.
2093    
2094    =over 4
2095    
2096    =item fileName
2097    
2098    Name of the file to read.
2099    
2100    =item RETURN
2101    
2102    In a list context, returns the entire file as a list with the line terminators removed.
2103    In a scalar context, returns the entire file as a string. If an error occurs opening
2104    the file, an empty list will be returned.
2105    
2106    =back
2107    
2108    =cut
2109    
2110    sub GetFile {
2111        # Get the parameters.
2112        my ($fileName) = @_;
2113        # Declare the return variable.
2114        my @retVal = ();
2115        # Open the file for input.
2116        my $handle = Open(undef, "<$fileName");
2117        # Read the whole file into the return variable, stripping off any terminator
2118        # characters.
2119        my $lineCount = 0;
2120        while (my $line = <$handle>) {
2121            $lineCount++;
2122            $line = Strip($line);
2123            push @retVal, $line;
2124        }
2125        # Close it.
2126        close $handle;
2127        my $actualLines = @retVal;
2128        Trace("$actualLines lines read from file $fileName.") if T(File => 2);
2129        # Return the file's contents in the desired format.
2130        if (wantarray) {
2131            return @retVal;
2132        } else {
2133            return join "\n", @retVal;
2134        }
2135    }
2136    
2137    =head3 PutFile
2138    
2139        Tracer::PutFile($fileName, \@lines);
2140    
2141    Write out a file from a list of lines of text.
2142    
2143    =over 4
2144    
2145    =item fileName
2146    
2147    Name of the output file.
2148    
2149    =item lines
2150    
2151    Reference to a list of text lines. The lines will be written to the file in order, with trailing
2152    new-line characters. Alternatively, may be a string, in which case the string will be written without
2153    modification.
2154    
2155    =back
2156    
2157    =cut
2158    
2159    sub PutFile {
2160        # Get the parameters.
2161        my ($fileName, $lines) = @_;
2162        # Open the output file.
2163        my $handle = Open(undef, ">$fileName");
2164        # Count the lines written.
2165        if (ref $lines ne 'ARRAY') {
2166            # Here we have a scalar, so we write it raw.
2167            print $handle $lines;
2168            Trace("Scalar put to file $fileName.") if T(File => 3);
2169        } else {
2170            # Write the lines one at a time.
2171            my $count = 0;
2172            for my $line (@{$lines}) {
2173                print $handle "$line\n";
2174                $count++;
2175            }
2176            Trace("$count lines put to file $fileName.") if T(File => 3);
2177        }
2178        # Close the output file.
2179        close $handle;
2180    }
2181    
2182    =head3 ParseRecord
2183    
2184        my @fields = Tracer::ParseRecord($line);
2185    
2186    Parse a tab-delimited data line. The data line is split into field values. Embedded tab
2187    and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.
2188    These will automatically be converted.
2189    
2190    =over 4
2191    
2192    =item line
2193    
2194    Line of data containing the tab-delimited fields.
2195    
2196    =item RETURN
2197    
2198    Returns a list of the fields found in the data line.
2199    
2200    =back
2201    
2202    =cut
2203    
2204    sub ParseRecord {
2205        # Get the parameter.
2206        my ($line) = @_;
2207        # Remove the trailing new-line, if any.
2208        chomp $line;
2209        # Split the line read into pieces using the tab character.
2210        my @retVal = split /\t/, $line;
2211        # Trim and fix the escapes in each piece.
2212        for my $value (@retVal) {
2213            # Trim leading whitespace.
2214            $value =~ s/^\s+//;
2215            # Trim trailing whitespace.
2216            $value =~ s/\s+$//;
2217            # Delete the carriage returns.
2218            $value =~ s/\r//g;
2219            # Convert the escapes into their real values.
2220            $value =~ s/\\t/"\t"/ge;
2221            $value =~ s/\\n/"\n"/ge;
2222        }
2223        # Return the result.
2224        return @retVal;
2225    }
2226    
2227    =head3 Merge
2228    
2229        my @mergedList = Tracer::Merge(@inputList);
2230    
2231    Sort a list of strings and remove duplicates.
2232    
2233    =over 4
2234    
2235    =item inputList
2236    
2237    List of scalars to sort and merge.
2238    
2239    =item RETURN
2240    
2241    Returns a list containing the same elements sorted in ascending order with duplicates
2242    removed.
2243    
2244    =back
2245    
2246    =cut
2247    
2248    sub Merge {
2249        # Get the input list in sort order.
2250        my @inputList = sort @_;
2251        # Only proceed if the list has at least two elements.
2252        if (@inputList > 1) {
2253            # Now we want to move through the list splicing out duplicates.
2254            my $i = 0;
2255            while ($i < @inputList) {
2256                # Get the current entry.
2257                my $thisEntry = $inputList[$i];
2258                # Find out how many elements duplicate the current entry.
2259                my $j = $i + 1;
2260                my $dup1 = $i + 1;
2261                while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };
2262                # If the number is nonzero, splice out the duplicates found.
2263                if ($j > $dup1) {
2264                    splice @inputList, $dup1, $j - $dup1;
2265                }
2266                # Now the element at position $dup1 is different from the element before it
2267                # at position $i. We push $i forward one position and start again.
2268                $i++;
2269            }
2270        }
2271        # Return the merged list.
2272        return @inputList;
2273    }
2274    
2275    =head3 Open
2276    
2277        my $handle = Open($fileHandle, $fileSpec, $message);
2278    
2279    Open a file.
2280    
2281    The I<$fileSpec> is essentially the second argument of the PERL C<open>
2282    function. The mode is specified using Unix-like shell information. So, for
2283    example,
2284    
2285        Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2286    
2287    would open for output appended to the specified file, and
2288    
2289        Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");
2290    
2291    would open a pipe that sorts the records written and removes duplicates. Note
2292    the use of file handle syntax in the Open call. To use anonymous file handles,
2293    code as follows.
2294    
2295        my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2296    
2297    The I<$message> parameter is used if the open fails. If it is set to C<0>, then
2298    the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a
2299    failed open will throw an exception and the third parameter will be used to construct
2300    an error message. If the parameter is omitted, a standard message is constructed
2301    using the file spec.
2302    
2303        Could not open "/usr/spool/news/twitlog"
2304    
2305    Note that the mode characters are automatically cleaned from the file name.
2306    The actual error message from the file system will be captured and appended to the
2307    message in any case.
2308    
2309        Could not open "/usr/spool/news/twitlog": file not found.
2310    
2311    In some versions of PERL the only error message we get is a number, which
2312    corresponds to the C++ C<errno> value.
2313    
2314        Could not open "/usr/spool/news/twitlog": 6.
2315    
2316    =over 4
2317    
2318    =item fileHandle
2319    
2320    File handle. If this parameter is C<undef>, a file handle will be generated
2321    and returned as the value of this method.
2322    
2323    =item fileSpec
2324    
2325    File name and mode, as per the PERL C<open> function.
2326    
2327    =item message (optional)
2328    
2329    Error message to use if the open fails. If omitted, a standard error message
2330    will be generated. In either case, the error information from the file system
2331    is appended to the message. To specify a conditional open that does not throw
2332    an error if it fails, use C<0>.
2333    
2334    =item RETURN
2335    
2336    Returns the name of the file handle assigned to the file, or C<undef> if the
2337    open failed.
2338    
2339    =back
2340    
2341    =cut
2342    
2343    sub Open {
2344        # Get the parameters.
2345        my ($fileHandle, $fileSpec, $message) = @_;
2346        # Attempt to open the file.
2347        my $rv = open $fileHandle, $fileSpec;
2348        # If the open failed, generate an error message.
2349        if (! $rv) {
2350            # Save the system error message.
2351            my $sysMessage = $!;
2352            # See if we need a default message.
2353            if (!$message) {
2354                # Clean any obvious mode characters and leading spaces from the
2355                # filename.
2356                my ($fileName) = FindNamePart($fileSpec);
2357                $message = "Could not open \"$fileName\"";
2358            }
2359            # Terminate with an error using the supplied message and the
2360            # error message from the file system.
2361            Confess("$message: $!");
2362        }
2363        # Return the file handle.
2364        return $fileHandle;
2365    }
2366    
2367    =head3 FindNamePart
2368    
2369        my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec);
2370    
2371    Extract the portion of a file specification that contains the file name.
2372    
2373    A file specification is the string passed to an C<open> call. It specifies the file
2374    mode and name. In a truly complex situation, it can specify a pipe sequence. This
2375    method assumes that the file name is whatever follows the first angle bracket
2376    sequence.  So, for example, in the following strings the file name is
2377    C</usr/fig/myfile.txt>.
2378    
2379        >>/usr/fig/myfile.txt
2380        </usr/fig/myfile.txt
2381        | sort -u > /usr/fig/myfile.txt
2382    
2383    If the method cannot find a file name using its normal methods, it will return the
2384    whole incoming string.
2385    
2386    =over 4
2387    
2388    =item fileSpec
2389    
2390    File specification string from which the file name is to be extracted.
2391    
2392    =item RETURN
2393    
2394    Returns a three-element list. The first element contains the file name portion of
2395    the specified string, or the whole string if a file name cannot be found via normal
2396    methods. The second element contains the start position of the file name portion and
2397    the third element contains the length.
2398    
2399    =back
2400    
2401    =cut
2402    #: Return Type $;
2403    sub FindNamePart {
2404        # Get the parameters.
2405        my ($fileSpec) = @_;
2406        # Default to the whole input string.
2407        my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);
2408        # Parse out the file name if we can.
2409        if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {
2410            $retVal = $2;
2411            $len = length $retVal;
2412            $pos = (length $fileSpec) - (length $3) - $len;
2413        }
2414        # Return the result.
2415        return ($retVal, $pos, $len);
2416    }
2417    
2418    =head3 OpenDir
2419    
2420        my @files = OpenDir($dirName, $filtered, $flag);
2421    
2422    Open a directory and return all the file names. This function essentially performs
2423    the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is
2424    set to TRUE, all filenames beginning with a period (C<.>), dollar sign (C<$>),
2425    or pound sign (C<#>) and all filenames ending with a tilde C<~>) will be
2426    filtered out of the return list. If the directory does not open and I<$flag> is not
2427    set, an exception is thrown. So, for example,
2428    
2429        my @files = OpenDir("/Volumes/fig/contigs", 1);
2430    
2431    is effectively the same as
2432    
2433        opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");
2434        my @files = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir(TMP);
2435    
2436    Similarly, the following code
2437    
2438        my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs", 0, 1);
2439    
2440    Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and
2441    automatically returns an empty list if the directory fails to open.
2442    
2443    =over 4
2444    
2445    =item dirName
2446    
2447    Name of the directory to open.
2448    
2449    =item filtered
2450    
2451    TRUE if files whose names begin with a period (C<.>) should be automatically removed
2452    from the list, else FALSE.
2453    
2454    =item flag
2455    
2456    TRUE if a failure to open is okay, else FALSE
2457    
2458    =back
2459    
2460    =cut
2461    #: Return Type @;
2462    sub OpenDir {
2463        # Get the parameters.
2464        my ($dirName, $filtered, $flag) = @_;
2465        # Declare the return variable.
2466        my @retVal = ();
2467        # Open the directory.
2468        if (opendir(my $dirHandle, $dirName)) {
2469            # The directory opened successfully. Get the appropriate list according to the
2470            # strictures of the filter parameter.
2471            if ($filtered) {
2472                @retVal = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir $dirHandle;
2473            } else {
2474                @retVal = readdir $dirHandle;
2475            }
2476        } elsif (! $flag) {
2477            # Here the directory would not open and it's considered an error.
2478            Confess("Could not open directory $dirName.");
2479        }
2480        # Return the result.
2481        return @retVal;
2482    }
2483    
2484    
2485    =head3 Insure
2486    
2487        Insure($dirName, $chmod);
2488    
2489    Insure a directory is present.
2490    
2491    =over 4
2492    
2493    =item dirName
2494    
2495    Name of the directory to check. If it does not exist, it will be created.
2496    
2497    =item chmod (optional)
2498    
2499    Security privileges to be given to the directory if it is created.
2500    
2501    =back
2502    
2503    =cut
2504    
2505    sub Insure {
2506        my ($dirName, $chmod) = @_;
2507        if (! -d $dirName) {
2508            Trace("Creating $dirName directory.") if T(2);
2509            eval {
2510                mkpath $dirName;
2511                # If we have permissions specified, set them here.
2512                if (defined($chmod)) {
2513                    chmod $chmod, $dirName;
2514                }
2515            };
2516            if ($@) {
2517                Confess("Error creating $dirName: $@");
2518            }
2519        }
2520    }
2521    
2522    =head3 ChDir
2523    
2524        ChDir($dirName);
2525    
2526    Change to the specified directory.
2527    
2528    =over 4
2529    
2530    =item dirName
2531    
2532    Name of the directory to which we want to change.
2533    
2534    =back
2535    
2536    =cut
2537    
2538    sub ChDir {
2539        my ($dirName) = @_;
2540        if (! -d $dirName) {
2541            Confess("Cannot change to directory $dirName: no such directory.");
2542        } else {
2543            Trace("Changing to directory $dirName.") if T(File => 4);
2544            my $okFlag = chdir $dirName;
2545            if (! $okFlag) {
2546                Confess("Error switching to directory $dirName.");
2547            }
2548        }
2549    }
2550    
2551    =head3 SetPermissions
2552    
2553        Tracer::SetPermissions($dirName, $group, $mask, %otherMasks);
2554    
2555    Set the permissions for a directory and all the files and folders inside it.
2556    In addition, the group ownership will be changed to the specified value.
2557    
2558    This method is more vulnerable than most to permission and compatability
2559    problems, so it does internal error recovery.
2560    
2561    =over 4
2562    
2563    =item dirName
2564    
2565    Name of the directory to process.
2566    
2567    =item group
2568    
2569    Name of the group to be assigned.
2570    
2571    =item mask
2572    
2573    Permission mask. Bits that are C<1> in this mask will be ORed into the
2574    permission bits of any file or directory that does not already have them
2575    set to 1.
2576    
2577    =item otherMasks
2578    
2579    Map of search patterns to permission masks. If a directory name matches
2580    one of the patterns, that directory and all its members and subdirectories
2581    will be assigned the new pattern. For example, the following would
2582    assign 0664 to most files, but would use 0777 for directories named C<tmp>.
2583    
2584        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp$' => 01777);
2585    
2586    The list is ordered, so the following would use 0777 for C<tmp1> and
2587    0666 for C<tmp>, C<tmp2>, or C<tmp3>.
2588    
2589        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp1' => 0777,
2590                                                       '^tmp' => 0666);
2591    
2592    Note that the pattern matches are all case-insensitive, and only directory
2593    names are matched, not file names.
2594    
2595    =back
2596    
2597    =cut
2598    
2599    sub SetPermissions {
2600        # Get the parameters.
2601        my ($dirName, $group, $mask, @otherMasks) = @_;
2602        # Set up for error recovery.
2603        eval {
2604            # Switch to the specified directory.
2605            ChDir($dirName);
2606            # Get the group ID.
2607            my $gid = getgrnam($group);
2608            # Get the mask for tracing.
2609            my $traceMask = sprintf("%04o", $mask) . "($mask)";
2610            Trace("Fixing permissions for directory $dirName using group $group($gid) and mask $traceMask.") if T(File => 2);
2611            my $fixCount = 0;
2612            my $lookCount = 0;
2613            # @dirs will be a stack of directories to be processed.
2614            my @dirs = (getcwd());
2615            while (scalar(@dirs) > 0) {
2616                # Get the current directory.
2617                my $dir = pop @dirs;
2618                # Check for a match to one of the specified directory names. To do
2619                # that, we need to pull the individual part of the name off of the
2620                # whole path.
2621                my $simpleName = $dir;
2622                if ($dir =~ m!/([^/]+)$!) {
2623                    $simpleName = $1;
2624                }
2625                Trace("Simple directory name for $dir is $simpleName.") if T(File => 4);
2626                # Search for a match.
2627                my $match = 0;
2628                my $i;
2629                for ($i = 0; $i < $#otherMasks && ! $match; $i += 2) {
2630                    my $pattern = $otherMasks[$i];
2631                    if ($simpleName =~ /$pattern/i) {
2632                        $match = 1;
2633                    }
2634                }
2635                # Find out if we have a match. Note we use $i-1 because the loop added 2
2636                # before terminating due to the match.
2637                if ($match && $otherMasks[$i-1] != $mask) {
2638                    # This directory matches one of the incoming patterns, and it's
2639                    # a different mask, so we process it recursively with that mask.
2640                    SetPermissions($dir, $group, $otherMasks[$i-1], @otherMasks);
2641                } else {
2642                    # Here we can process normally. Get all of the non-hidden members.
2643                    my @submems = OpenDir($dir, 1);
2644                    for my $submem (@submems) {
2645                        # Get the full name.
2646                        my $thisMem = "$dir/$submem";
2647                        Trace("Checking member $thisMem.") if T(4);
2648                        $lookCount++;
2649                        if ($lookCount % 1000 == 0) {
2650                            Trace("$lookCount members examined. Current is $thisMem. Mask is $traceMask") if T(File => 3);
2651                        }
2652                        # Fix the group.
2653                        chown -1, $gid, $thisMem;
2654                        # Insure this member is not a symlink.
2655                        if (! -l $thisMem) {
2656                            # Get its info.
2657                            my $fileInfo = stat $thisMem;
2658                            # Only proceed if we got the info. Otherwise, it's a hard link
2659                            # and we want to skip it anyway.
2660                            if ($fileInfo) {
2661                                my $fileMode = $fileInfo->mode;
2662                                if (($fileMode & $mask) != $mask) {
2663                                    # Fix this member.
2664                                    $fileMode |= $mask;
2665                                    chmod $fileMode, $thisMem;
2666                                    $fixCount++;
2667                                }
2668                                # If it's a subdirectory, stack it.
2669                                if (-d $thisMem) {
2670                                    push @dirs, $thisMem;
2671                                }
2672                            }
2673                        }
2674                    }
2675                }
2676            }
2677            Trace("$lookCount files and directories processed, $fixCount fixed.") if T(File => 2);
2678        };
2679        # Check for an error.
2680        if ($@) {
2681            Confess("SetPermissions error: $@");
2682        }
2683    }
2684    
2685    =head3 GetLine
2686    
2687        my @data = Tracer::GetLine($handle);
2688    
2689    Read a line of data from a tab-delimited file.
2690    
2691    =over 4
2692    
2693    =item handle
2694    
2695    Open file handle from which to read.
2696    
2697    =item RETURN
2698    
2699    Returns a list of the fields in the record read. The fields are presumed to be
2700    tab-delimited. If we are at the end of the file, then an empty list will be
2701    returned. If an empty line is read, a single list item consisting of a null
2702    string will be returned.
2703    
2704    =back
2705    
2706    =cut
2707    
2708    sub GetLine {
2709        # Get the parameters.
2710        my ($handle) = @_;
2711        # Declare the return variable.
2712        my @retVal = ();
2713        Trace("File position is " . tell($handle) . ". EOF flag is " . eof($handle) . ".") if T(File => 4);
2714        # Read from the file.
2715        my $line = <$handle>;
2716        # Only proceed if we found something.
2717        if (defined $line) {
2718            # Remove the new-line. We are a bit over-cautious here because the file may be coming in via an
2719            # upload control and have a nonstandard EOL combination.
2720            $line =~ s/(\r|\n)+$//;
2721            # Here we do some fancy tracing to help in debugging complicated EOL marks.
2722            if (T(File => 4)) {
2723                my $escapedLine = $line;
2724                $escapedLine =~ s/\n/\\n/g;
2725                $escapedLine =~ s/\r/\\r/g;
2726                $escapedLine =~ s/\t/\\t/g;
2727                Trace("Line read: -->$escapedLine<--");
2728            }
2729            # If the line is empty, return a single empty string; otherwise, parse
2730            # it into fields.
2731            if ($line eq "") {
2732                push @retVal, "";
2733            } else {
2734                push @retVal, split /\t/,$line;
2735            }
2736        } else {
2737            # Trace the reason the read failed.
2738            Trace("End of file: $!") if T(File => 3);
2739        }
2740        # Return the result.
2741        return @retVal;
2742    }
2743    
2744    =head3 PutLine
2745    
2746        Tracer::PutLine($handle, \@fields, $eol);
2747    
2748    Write a line of data to a tab-delimited file. The specified field values will be
2749    output in tab-separated form, with a trailing new-line.
2750    
2751    =over 4
2752    
2753    =item handle
2754    
2755    Output file handle.
2756    
2757    =item fields
2758    
2759    List of field values.
2760    
2761    =item eol (optional)
2762    
2763    End-of-line character (default is "\n").
2764    
2765    =back
2766    
2767    =cut
2768    
2769    sub PutLine {
2770        # Get the parameters.
2771        my ($handle, $fields, $eol) = @_;
2772        # Write the data.
2773        print $handle join("\t", @{$fields}) . ($eol || "\n");
2774    }
2775    
2776    
2777    =head3 PrintLine
2778    
2779        Tracer::PrintLine($line);
2780    
2781    Print a line of text with a trailing new-line.
2782    
2783    =over 4
2784    
2785    =item line
2786    
2787    Line of text to print.
2788    
2789    =back
2790    
2791    =cut
2792    
2793    sub PrintLine {
2794        # Get the parameters.
2795        my ($line) = @_;
2796        # Print the line.
2797        print "$line\n";
2798    }
2799    
2800    
2801    =head2 Other Useful Methods
2802    
2803    =head3 ParseParm
2804    
2805        my $listValue = Tracer::ParseParm($string);
2806    
2807    Convert a parameter into a list reference. If the parameter is undefined,
2808    an undefined value will be returned. Otherwise, it will be parsed as a
2809    comma-separated list of values.
2810    
2811    =over 4
2812    
2813    =item string
2814    
2815    Incoming string.
2816    
2817    =item RETURN
2818    
2819    Returns a reference to a list of values, or C<undef> if the incoming value
2820    was undefined.
2821    
2822    =back
2823    
2824    =cut
2825    
2826    sub ParseParm {
2827        # Get the parameters.
2828        my ($string) = @_;
2829        # Declare the return variable.
2830        my $retVal;
2831        # Check for data.
2832        if (defined $string) {
2833            # We have some, so split it into a list.
2834            $retVal = [ split /\s*,\s*/, $string];
2835                  }                  }
2836        # Return the result.
2837        return $retVal;
2838    }
2839    
2840    =head3 Now
2841    
2842        my $string = Tracer::Now();
2843    
2844    Return a displayable time stamp containing the local time. Whatever format this
2845    method produces must be parseable by L</ParseDate>.
2846    
2847    =cut
2848    
2849    sub Now {
2850        return DisplayTime(time);
2851    }
2852    
2853    =head3 DisplayTime
2854    
2855        my $string = Tracer::DisplayTime($time);
2856    
2857    Convert a time value to a displayable time stamp. Whatever format this
2858    method produces must be parseable by L</ParseDate>.
2859    
2860    =over 4
2861    
2862    =item time
2863    
2864    Time to display, in seconds since the epoch, or C<undef> if the time is unknown.
2865    
2866    =item RETURN
2867    
2868    Returns a displayable time, or C<(n/a)> if the incoming time is undefined.
2869    
2870    =back
2871    
2872    =cut
2873    
2874    sub DisplayTime {
2875        my ($time) = @_;
2876        my $retVal = "(n/a)";
2877        if (defined $time) {
2878            my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($time);
2879            $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .
2880                      _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);
2881          }          }
2882          # Merge the options into the defaults.      return $retVal;
         GetOptions($optionTable, \%overrides);  
         # Translate the remaining parameters.  
         my @retVal = ();  
         for my $inputParm (@inputList) {  
                 push @retVal, UnEscape($inputParm);  
2883          }          }
2884          # Return the results.  
2885          return ($optionTable, @retVal);  # Pad a number to 2 digits.
2886    sub _p2 {
2887        my ($value) = @_;
2888        $value = "0$value" if ($value < 10);
2889        return $value;
2890  }  }
2891    
2892  =head3 Escape  =head3 Escape
2893    
2894  C<< my $codedString = Tracer::Escape($realString); >>      my $codedString = Tracer::Escape($realString);
2895    
2896  Escape a string for use in a command length. Spaces will be replaced by C<\b>,  Escape a string for use in a command. Tabs will be replaced by C<\t>, new-lines
2897  tabs replaced by C<\t>, new-lines replaced by C<\n>, and backslashes will be  replaced by C<\n>, carriage returns will be deleted, and backslashes will be doubled. The
2898  doubled. The effect is to exactly reverse the effect of L</UnEscape>.  result is to reverse the effect of L</UnEscape>.
2899    
2900  =over 4  =over 4
2901    
# Line 563  Line 2919 
2919          # Loop through the parameter string, looking for sequences to escape.          # Loop through the parameter string, looking for sequences to escape.
2920          while (length $realString > 0) {          while (length $realString > 0) {
2921                  # Look for the first sequence to escape.                  # Look for the first sequence to escape.
2922                  if ($realString =~ /^(.*?)([ \n\t\\])/) {          if ($realString =~ /^(.*?)([\n\t\r\\])/) {
2923                          # 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
2924                          # 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.
2925                          $retVal .= $1;                          $retVal .= $1;
2926                          $realString = substr $realString, (length $2 + length $1);              # Strip the processed section off the real string.
2927                          # Encode the escape sequence.              $realString = substr $realString, (length $2) + (length $1);
2928                # Get the matched character.
2929                          my $char = $2;                          my $char = $2;
2930                          $char =~ tr/ \t\n/btn/;              # If we have a CR, we are done.
2931                if ($char ne "\r") {
2932                    # It's not a CR, so encode the escape sequence.
2933                    $char =~ tr/\t\n/tn/;
2934                          $retVal .= "\\" . $char;                          $retVal .= "\\" . $char;
2935                }
2936                  } else {                  } else {
2937                          # 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
2938                          # transferred unmodified.                          # transferred unmodified.
# Line 585  Line 2946 
2946    
2947  =head3 UnEscape  =head3 UnEscape
2948    
2949  C<< my $realString = Tracer::UnEscape($codedString); >>      my $realString = Tracer::UnEscape($codedString);
2950    
2951  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
2952  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
2953    be deleted.
2954    
2955  =over 4  =over 4
2956    
# Line 613  Line 2975 
2975          # Only proceed if the incoming string is nonempty.          # Only proceed if the incoming string is nonempty.
2976          if (defined $codedString) {          if (defined $codedString) {
2977                  # 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
2978                  # translating because it causes problems with the escaped slash. ("\\b" becomes          # translating because it causes problems with the escaped slash. ("\\t" becomes
2979                  # "\ " no matter what we do.)          # "\<tab>" no matter what we do.)
2980                  while (length $codedString > 0) {                  while (length $codedString > 0) {
2981                          # Look for the first escape sequence.                          # Look for the first escape sequence.
2982                          if ($codedString =~ /^(.*?)\\(\\|b|n|t)/) {              if ($codedString =~ /^(.*?)\\(\\|n|t|r)/) {
2983                                  # 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
2984                                  # 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.
2985                                  $retVal .= $1;                                  $retVal .= $1;
2986                                  $codedString = substr $codedString, (2 + length $1);                                  $codedString = substr $codedString, (2 + length $1);
2987                                  # Decode the escape sequence.                  # Get the escape value.
2988                                  my $char = $2;                                  my $char = $2;
2989                                  $char =~ tr/\\btn/\\ \t\n/;                  # If we have a "\r", we are done.
2990                    if ($char ne 'r') {
2991                        # Here it's not an 'r', so we convert it.
2992                        $char =~ tr/\\tn/\\\t\n/;
2993                                  $retVal .= $char;                                  $retVal .= $char;
2994                    }
2995                          } else {                          } else {
2996                                  # 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
2997                                  # transferred unmodified.                                  # transferred unmodified.
# Line 638  Line 3004 
3004          return $retVal;          return $retVal;
3005  }  }
3006    
3007  =head3 ParseRecord  =head3 Percent
3008    
3009  C<< my @fields = Tracer::ParseRecord($line); >>      my $percent = Tracer::Percent($number, $base);
3010    
3011  Parse a tab-delimited data line. The data line is split into field values. Embedded tab  Returns the percent of the base represented by the given number. If the base
3012  and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.  is zero, returns zero.
 These will automatically be converted.  
3013    
3014  =over 4  =over 4
3015    
3016  =item line  =item number
3017    
3018  Line of data containing the tab-delimited fields.  Percent numerator.
3019    
3020    =item base
3021    
3022    Percent base.
3023    
3024  =item RETURN  =item RETURN
3025    
3026  Returns a list of the fields found in the data line.  Returns the percentage of the base represented by the numerator.
3027    
3028  =back  =back
3029    
3030  =cut  =cut
3031    
3032  sub ParseRecord {  sub Percent {
3033          # Get the parameter.      # Get the parameters.
3034          my ($line) = @_;      my ($number, $base) = @_;
3035          # Remove the trailing new-line, if any.      # Declare the return variable.
3036          chomp $line;      my $retVal = 0;
3037          # Split the line read into pieces using the tab character.      # Compute the percent.
3038          my @retVal = split /\t/, $line;      if ($base != 0) {
3039          # Trim and fix the escapes in each piece.          $retVal = $number * 100 / $base;
         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;  
3040          }          }
3041          # Return the result.          # Return the result.
3042          return @retVal;      return $retVal;
3043  }  }
3044    
3045  =head3 Merge  =head3 Constrain
3046    
3047  C<< my @mergedList = Tracer::Merge(@inputList); >>      my $constrained = Constrain($value, $min, $max);
3048    
3049  Sort a list of strings and remove duplicates.  Modify a numeric value to bring it to a point in between a maximum and a minimum.
3050    
3051  =over 4  =over 4
3052    
3053  =item inputList  =item value
3054    
3055  List of scalars to sort and merge.  Value to constrain.
3056    
3057    =item min (optional)
3058    
3059    Minimum permissible value. If this parameter is undefined, no minimum constraint will be applied.
3060    
3061    =item max (optional)
3062    
3063    Maximum permissible value. If this parameter is undefined, no maximum constraint will be applied.
3064    
3065  =item RETURN  =item RETURN
3066    
3067  Returns a list containing the same elements sorted in ascending order with duplicates  Returns the incoming value, constrained according to the other parameters.
 removed.  
3068    
3069  =back  =back
3070    
3071  =cut  =cut
3072    
3073  sub Merge {  sub Constrain {
3074          # Get the input list in sort order.      # Get the parameters.
3075          my @inputList = sort @_;      my ($value, $min, $max) = @_;
3076          # Only proceed if the list has at least two elements.      # Declare the return variable.
3077          if (@inputList > 1) {      my $retVal = $value;
3078                  # Now we want to move through the list splicing out duplicates.      # Apply the minimum constraint.
3079                  my $i = 0;      if (defined $min && $retVal < $min) {
3080                  while ($i < @inputList) {          $retVal = $min;
3081                          # Get the current entry.      }
3082                          my $thisEntry = $inputList[$i];      # Apply the maximum constraint.
3083                          # Find out how many elements duplicate the current entry.      if (defined $max && $retVal > $max) {
3084                          my $j = $i + 1;          $retVal = $max;
                         my $dup1 = $i + 1;  
                         while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };  
                         # If the number is nonzero, splice out the duplicates found.  
                         if ($j > $dup1) {  
                                 splice @inputList, $dup1, $j - $dup1;  
3085                          }                          }
3086                          # Now the element at position $dup1 is different from the element before it      # Return the result.
3087                          # at position $i. We push $i forward one position and start again.      return $retVal;
                         $i++;  
3088                  }                  }
3089    
3090    =head3 Min
3091    
3092        my $min = Min($value1, $value2, ... $valueN);
3093    
3094    Return the minimum argument. The arguments are treated as numbers.
3095    
3096    =over 4
3097    
3098    =item $value1, $value2, ... $valueN
3099    
3100    List of numbers to compare.
3101    
3102    =item RETURN
3103    
3104    Returns the lowest number in the list.
3105    
3106    =back
3107    
3108    =cut
3109    
3110    sub Min {
3111        # Get the parameters. Note that we prime the return value with the first parameter.
3112        my ($retVal, @values) = @_;
3113        # Loop through the remaining parameters, looking for the lowest.
3114        for my $value (@values) {
3115            if ($value < $retVal) {
3116                $retVal = $value;
3117          }          }
         # Return the merged list.  
         return @inputList;  
3118  }  }
3119        # Return the minimum found.
3120        return $retVal;
3121    }
3122    
3123    =head3 Max
3124    
3125        my $max = Max($value1, $value2, ... $valueN);
3126    
3127    Return the maximum argument. The arguments are treated as numbers.
3128    
3129    =over 4
3130    
3131    =item $value1, $value2, ... $valueN
3132    
3133    List of numbers to compare.
3134    
3135    =item RETURN
3136    
3137    Returns the highest number in the list.
3138    
3139    =back
3140    
3141    =cut
3142    
3143    sub Max {
3144        # Get the parameters. Note that we prime the return value with the first parameter.
3145        my ($retVal, @values) = @_;
3146        # Loop through the remaining parameters, looking for the highest.
3147        for my $value (@values) {
3148            if ($value > $retVal) {
3149                $retVal = $value;
3150            }
3151        }
3152        # Return the maximum found.
3153        return $retVal;
3154    }
3155    
3156    =head3 Strip
3157    
3158        my $string = Tracer::Strip($line);
3159    
3160    Strip all line terminators off a string. This is necessary when dealing with files
3161    that may have been transferred back and forth several times among different
3162    operating environments.
3163    
3164    =over 4
3165    
3166    =item line
3167    
3168    Line of text to be stripped.
3169    
3170    =item RETURN
3171    
3172    The same line of text with all the line-ending characters chopped from the end.
3173    
3174    =back
3175    
3176    =cut
3177    
3178    sub Strip {
3179        # Get a copy of the parameter string.
3180        my ($string) = @_;
3181        my $retVal = (defined $string ? $string : "");
3182        # Strip the line terminator characters.
3183        $retVal =~ s/(\r|\n)+$//g;
3184        # Return the result.
3185        return $retVal;
3186    }
3187    
3188    =head3 Pad
3189    
3190        my $paddedString = Tracer::Pad($string, $len, $left, $padChar);
3191    
3192    Pad a string to a specified length. The pad character will be a
3193    space, and the padding will be on the right side unless specified
3194    in the third parameter.
3195    
3196    =over 4
3197    
3198    =item string
3199    
3200    String to be padded.
3201    
3202    =item len
3203    
3204    Desired length of the padded string.
3205    
3206    =item left (optional)
3207    
3208    TRUE if the string is to be left-padded; otherwise it will be padded on the right.
3209    
3210    =item padChar (optional)
3211    
3212    Character to use for padding. The default is a space.
3213    
3214    =item RETURN
3215    
3216    Returns a copy of the original string with the pad character added to the
3217    specified end so that it achieves the desired length.
3218    
3219    =back
3220    
3221    =cut
3222    
3223    sub Pad {
3224        # Get the parameters.
3225        my ($string, $len, $left, $padChar) = @_;
3226        # Compute the padding character.
3227        if (! defined $padChar) {
3228            $padChar = " ";
3229        }
3230        # Compute the number of spaces needed.
3231        my $needed = $len - length $string;
3232        # Copy the string into the return variable.
3233        my $retVal = $string;
3234        # Only proceed if padding is needed.
3235        if ($needed > 0) {
3236            # Create the pad string.
3237            my $pad = $padChar x $needed;
3238            # Affix it to the return value.
3239            if ($left) {
3240                $retVal = $pad . $retVal;
3241            } else {
3242                $retVal .= $pad;
3243            }
3244        }
3245        # Return the result.
3246        return $retVal;
3247    }
3248    
3249    =head3 EOF
3250    
3251    This is a constant that is lexically greater than any useful string.
3252    
3253    =cut
3254    
3255    sub EOF {
3256        return "\xFF\xFF\xFF\xFF\xFF";
3257    }
3258    
3259    =head3 TICK
3260    
3261        my @results = TICK($commandString);
3262    
3263    Perform a back-tick operation on a command. If this is a Windows environment, any leading
3264    dot-slash (C<./> will be removed. So, for example, if you were doing
3265    
3266  =head3 GetFile      `./protein.cgi`
3267    
3268    from inside a CGI script, it would work fine in Unix, but would issue an error message
3269    in Windows complaining that C<'.'> is not a valid command. If instead you code
3270    
3271  C<< my @fileContents = Tracer::GetFile($fileName); >>      TICK("./protein.cgi")
3272    
3273  Return the entire contents of a file.  it will work correctly in both environments.
3274    
3275  =over 4  =over 4
3276    
3277  =item fileName  =item commandString
3278    
3279  Name of the file to read.  The command string to pass to the system.
3280    
3281  =item RETURN  =item RETURN
3282    
3283  In a list context, returns the entire file as a list with the line terminators removed.  Returns the standard output from the specified command, as a list.
 In a scalar context, returns the entire file as a string.  
3284    
3285  =back  =back
3286    
3287  =cut  =cut
3288    #: Return Type @;
3289  sub GetFile {  sub TICK {
3290          # Get the parameters.          # Get the parameters.
3291          my ($fileName) = @_;      my ($commandString) = @_;
3292          # Declare the return variable.      # Chop off the dot-slash if this is Windows.
3293          my @retVal = ();      if ($FIG_Config::win_mode) {
3294          # 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 any terminator  
         # characters.  
         my $lineCount = 0;  
                 while (my $line = <INPUTFILE>) {  
             $lineCount++;  
             $line = Strip($line);  
                         push @retVal, $line;  
                 }  
                 # Close it.  
                 close INPUTFILE;  
         my $actualLines = @retVal;  
         Trace("$lineCount lines read from $fileName. $actualLines processed.") if T(3);  
         }  
         # Return the file's contents in the desired format.  
     if (wantarray) {  
             return @retVal;  
     } else {  
         return join "\n", @retVal;  
3295      }      }
3296        # Activate the command and return the result.
3297        return `$commandString`;
3298  }  }
3299    
 =head3 QTrace  
3300    
3301  C<< my $data = QTrace($format); >>  =head3 CommaFormat
3302    
3303  Return the queued trace data in the specified format.      my $formatted = Tracer::CommaFormat($number);
3304    
3305    Insert commas into a number.
3306    
3307  =over 4  =over 4
3308    
3309  =item format  =item number
3310    
3311  C<html> to format the data as an HTML list, C<text> to format it as straight text.  A sequence of digits.
3312    
3313    =item RETURN
3314    
3315    Returns the same digits with commas strategically inserted.
3316    
3317  =back  =back
3318    
3319  =cut  =cut
3320    
3321  sub QTrace {  sub CommaFormat {
3322          # Get the parameter.      # Get the parameters.
3323          my ($format) = @_;      my ($number) = @_;
3324          # Create the return variable.      # Pad the length up to a multiple of three.
3325          my $retVal = "";      my $padded = "$number";
3326          # Process according to the format.      $padded = " " . $padded while length($padded) % 3 != 0;
3327          if ($format =~ m/^HTML$/i) {      # This is a fancy PERL trick. The parentheses in the SPLIT pattern
3328                  # Convert the queue into an HTML list.      # cause the delimiters to be included in the output stream. The
3329                  $retVal = "<ul>\n";      # GREP removes the empty strings in between the delimiters.
3330                  for my $line (@Queue) {      my $retVal = join(",", grep { $_ ne '' } split(/(...)/, $padded));
3331                          my $escapedLine = CGI::escapeHTML($line);      # Clean out the spaces.
3332                          $retVal .= "<li>$escapedLine</li>\n";      $retVal =~ s/ //g;
3333                  }      # 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.  
3334          return $retVal;          return $retVal;
3335  }  }
3336    
 =head3 Confess  
   
 C<< Confess($message); >>  
3337    
3338  Trace the call stack and abort the program with the specified message. The stack  =head3 CompareLists
 trace will only appear if the trace level for this package is 1 or more. When used with  
 the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.  
 So, for example  
3339    
3340  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>      my ($inserted, $deleted) = Tracer::CompareLists(\@newList, \@oldList, $keyIndex);
3341    
3342  Will abort the program with a stack trace if the value of C<$recNum> is negative.  Compare two lists of tuples, and return a hash analyzing the differences. The lists
3343    are presumed to be sorted alphabetically by the value in the $keyIndex column.
3344    The return value contains a list of items that are only in the new list
3345    (inserted) and only in the old list (deleted).
3346    
3347  =over 4  =over 4
3348    
3349  =item message  =item newList
3350    
3351  Message to include in the trace.  Reference to a list of new tuples.
3352    
3353    =item oldList
3354    
3355    Reference to a list of old tuples.
3356    
3357    =item keyIndex (optional)
3358    
3359    Index into each tuple of its key field. The default is 0.
3360    
3361    =item RETURN
3362    
3363    Returns a 2-tuple consisting of a reference to the list of items that are only in the new
3364    list (inserted) followed by a reference to the list of items that are only in the old
3365    list (deleted).
3366    
3367  =back  =back
3368    
3369  =cut  =cut
3370    
3371  sub Confess {  sub CompareLists {
3372          # Get the parameters.          # Get the parameters.
3373          my ($message) = @_;      my ($newList, $oldList, $keyIndex) = @_;
3374          # Trace the call stack.      if (! defined $keyIndex) {
3375          Cluck($message) if T(1);          $keyIndex = 0;
3376          # Abort the program.      }
3377          croak(">>> $message");      # Declare the return variables.
3378        my ($inserted, $deleted) = ([], []);
3379        # Loop through the two lists simultaneously.
3380        my ($newI, $oldI) = (0, 0);
3381        my ($newN, $oldN) = (scalar @{$newList}, scalar @{$oldList});
3382        while ($newI < $newN || $oldI < $oldN) {
3383            # Get the current object in each list. Note that if one
3384            # of the lists is past the end, we'll get undef.
3385            my $newItem = $newList->[$newI];
3386            my $oldItem = $oldList->[$oldI];
3387            if (! defined($newItem) || defined($oldItem) && $newItem->[$keyIndex] gt $oldItem->[$keyIndex]) {
3388                # The old item is not in the new list, so mark it deleted.
3389                push @{$deleted}, $oldItem;
3390                $oldI++;
3391            } elsif (! defined($oldItem) || $oldItem->[$keyIndex] gt $newItem->[$keyIndex]) {
3392                # The new item is not in the old list, so mark it inserted.
3393                push @{$inserted}, $newItem;
3394                $newI++;
3395            } else {
3396                # The item is in both lists, so push forward.
3397                $oldI++;
3398                $newI++;
3399            }
3400        }
3401        # Return the result.
3402        return ($inserted, $deleted);
3403  }  }
3404    
3405  =head3 Assert  =head3 Cmp
3406    
3407  C<< Assert($condition1, $condition2, ... $conditionN); >>      my $cmp = Tracer::Cmp($a, $b);
3408    
3409  Return TRUE if all the conditions are true. This method can be used in conjunction with  This method performs a universal sort comparison. Each value coming in is
3410  the OR operator and the L</Confess> method, B<Assert> can function as a debugging assert.  separated into a leading text part and a trailing number part. The text
3411  So, for example  part is string compared, and if both parts are equal, then the number
3412    parts are compared numerically. A stream of just numbers or a stream of
3413    just strings will sort correctly, and a mixed stream will sort with the
3414    numbers first. Strings with a label and a number will sort in the
3415    expected manner instead of lexically.
3416    
3417  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>  =over 4
3418    
3419  Will abort the program with a stack trace if the value of C<$recNum> is negative.  =item a
3420    
3421    First item to compare.
3422    
3423    =item b
3424    
3425    Second item to compare.
3426    
3427    =item RETURN
3428    
3429    Returns a negative number if the first item should sort first (is less), a positive
3430    number if the first item should sort second (is greater), and a zero if the items are
3431    equal.
3432    
3433    =back
3434    
3435  =cut  =cut
3436  sub Assert {  
3437      my $retVal = 1;  sub Cmp {
3438      LOOP: for my $condition (@_) {      # Get the parameters.
3439          if (! $condition) {      my ($a, $b) = @_;
3440              $retVal = 0;      # Declare the return value.
3441              last LOOP;      my $retVal;
3442        # Check for nulls.
3443        if (! defined($a)) {
3444            $retVal = (! defined($b) ? 0 : -1);
3445        } elsif (! defined($b)) {
3446            $retVal = 1;
3447        } else {
3448            # Here we have two real values. Parse the two strings.
3449            $a =~ /^(\D*)(\d*)$/;
3450            my $aParsed = [$1, $2];
3451            $b =~ /^(\D*)(\d*)$/;
3452            my $bParsed = [$1, $2];
3453            # Compare the string parts.
3454            $retVal = $aParsed->[0] cmp $bParsed->[0];
3455            if (! $retVal) {
3456                $retVal = $aParsed->[1] <=> $bParsed->[1];
3457          }          }
3458      }      }
3459        # Return the result.
3460      return $retVal;      return $retVal;
3461  }  }
3462    
3463  =head3 Cluck  =head3 ListEQ
3464    
3465  C<< Cluck($message); >>      my $flag = Tracer::ListEQ(\@a, \@b);
3466    
3467  Trace the call stack. Note that for best results, you should qualify the call with a  Return TRUE if the specified lists contain the same strings in the same
3468  trace condition. For example,  order, else FALSE.
3469    
3470  C<< Cluck("Starting record parse.") if T(3); >>  =over 4
3471    
3472  will only trace the stack if the trace level for the package is 3 or more.  =item a
3473    
3474  =over 4  Reference to the first list.
3475    
3476  =item message  =item b
3477    
3478  Message to include in the trace.  Reference to the second list.
3479    
3480    =item RETURN
3481    
3482    Returns TRUE if the two parameters are identical string lists, else FALSE.
3483    
3484  =back  =back
3485    
3486  =cut  =cut
3487    
3488  sub Cluck {  sub ListEQ {
3489          # Get the parameters.          # Get the parameters.
3490          my ($message) = @_;      my ($a, $b) = @_;
3491      # Trace what's happening.      # Declare the return variable. Start by checking the lengths.
3492      Trace("Stack trace for event: $message");      my $n = scalar(@$a);
3493          my $confession = longmess($message);      my $retVal = ($n == scalar(@$b));
3494          # Convert the confession to a series of trace messages. Note we skip any      # Now compare the list elements.
3495      # messages relating to calls into Tracer.      for (my $i = 0; $retVal && $i < $n; $i++) {
3496          for my $line (split /\s*\n/, $confession) {          $retVal = ($a->[$i] eq $b->[$i]);
                 Trace($line) if ($line !~ /Tracer\.pm/);  
3497          }          }
3498        # Return the result.
3499        return $retVal;
3500  }  }
3501    
3502  =head3 Min  =head2 CGI Script Utilities
3503    
3504  C<< my $min = Min($value1, $value2, ... $valueN); >>  =head3 ScriptSetup (deprecated)
3505    
3506  Return the minimum argument. The arguments are treated as numbers.      my ($cgi, $varHash) = ScriptSetup($noTrace);
3507    
3508    Perform standard tracing and debugging setup for scripts. The value returned is
3509    the CGI object followed by a pre-built variable hash. At the end of the script,
3510    the client should call L</ScriptFinish> to output the web page.
3511    
3512    This method calls L</ETracing> to configure tracing, which allows the tracing
3513    to be configured via the emergency tracing form on the debugging control panel.
3514    Tracing will then be turned on automatically for all programs that use the L</ETracing>
3515    method, which includes every program that uses this method or L</StandardSetup>.
3516    
3517  =over 4  =over 4
3518    
3519  =item $value1, $value2, ... $valueN  =item noTrace (optional)
3520    
3521  List of numbers to compare.  If specified, tracing will be suppressed. This is useful if the script wants to set up
3522    tracing manually.
3523    
3524  =item RETURN  =item RETURN
3525    
3526  Returns the lowest number in the list.  Returns a two-element list consisting of a CGI query object and a variable hash for
3527    the output page.
3528    
3529  =back  =back
3530    
3531  =cut  =cut
3532    
3533  sub Min {  sub ScriptSetup {
3534          # Get the parameters. Note that we prime the return value with the first parameter.      # Get the parameters.
3535          my ($retVal, @values) = @_;      my ($noTrace) = @_;
3536          # Loop through the remaining parameters, looking for the lowest.      # Get the CGI query object.
3537          for my $value (@values) {      my $cgi = CGI->new();
3538                  if ($value < $retVal) {      # Set up tracing if it's not suppressed.
3539                          $retVal = $value;      ETracing($cgi) unless $noTrace;
3540                  }      # Create the variable hash.
3541          }      my $varHash = { results => '' };
3542          # Return the minimum found.      # Return the query object and variable hash.
3543          return $retVal;      return ($cgi, $varHash);
3544    }
3545    
3546    =head3 ScriptFinish (deprecated)
3547    
3548        ScriptFinish($webData, $varHash);
3549    
3550    Output a web page at the end of a script. Either the string to be output or the
3551    name of a template file can be specified. If the second parameter is omitted,
3552    it is assumed we have a string to be output; otherwise, it is assumed we have the
3553    name of a template file. The template should have the variable C<DebugData>
3554    specified in any form that invokes a standard script. If debugging mode is turned
3555    on, a form field will be put in that allows the user to enter tracing data.
3556    Trace messages will be placed immediately before the terminal C<BODY> tag in
3557    the output, formatted as a list.
3558    
3559    A typical standard script would loook like the following.
3560    
3561        BEGIN {
3562            # Print the HTML header.
3563            print "CONTENT-TYPE: text/html\n\n";
3564  }  }
3565        use Tracer;
3566        use CGI;
3567        use FIG;
3568        # ... more uses ...
3569    
3570  =head3 Max      my ($cgi, $varHash) = ScriptSetup();
3571        eval {
3572  C<< my $max = Max($value1, $value2, ... $valueN); >>          # ... get data from $cgi, put it in $varHash ...
3573        };
3574        if ($@) {
3575            Trace("Script Error: $@") if T(0);
3576        }
3577        ScriptFinish("Html/MyTemplate.html", $varHash);
3578    
3579  Return the maximum argument. The arguments are treated as numbers.  The idea here is that even if the script fails, you'll see trace messages and
3580    useful output.
3581    
3582  =over 4  =over 4
3583    
3584  =item $value1, $value2, ... $valueN  =item webData
3585    
3586  List of numbers to compare.  A string containing either the full web page to be written to the output or the
3587    name of a template file from which the page is to be constructed. If the name
3588    of a template file is specified, then the second parameter must be present;
3589    otherwise, it must be absent.
3590    
3591  =item RETURN  =item varHash (optional)
3592    
3593  Returns the highest number in the list.  If specified, then a reference to a hash mapping variable names for a template
3594    to their values. The template file will be read into memory, and variable markers
3595    will be replaced by data in this hash reference.
3596    
3597  =back  =back
3598    
3599