[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 1.117, Thu Apr 2 01:13:32 2009 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    
         require Exporter;  
         @ISA = ('Exporter');  
         @EXPORT = qw(Trace T TSetup QTrace Confess Cluck Min Max Assert);  
         @EXPORT_OK = qw(GetFile GetOptions Merge MergeOptions ParseCommand ParseRecord UnEscape Escape);  
21          use strict;          use strict;
22          use Carp qw(longmess croak);      use base qw(Exporter);
23        use vars qw(@EXPORT @EXPORT_OK);
24        @EXPORT = qw(Trace T TSetup QTrace Confess MemTrace Cluck Min Max Assert Open OpenDir TICK StandardSetup EmergencyKey ETracing Constrain Insure ChDir Emergency Warn TraceDump IDHASH);
25        @EXPORT_OK = qw(GetFile GetOptions Merge MergeOptions ParseCommand ParseRecord UnEscape Escape PrintLine PutLine);
26        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        use Data::Dumper;
43    
44    
45  =head1 Tracing and Debugging Helpers  =head1 Tracing and Debugging Helpers
46    
47  =head2 Introduction  =head2 Tracing
48    
49  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
50  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.
51  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,
52  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
53  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
54  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
55  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
56  appear. To generate a trace message, use the following syntax.  appear.
57    
58    =head3 Putting Trace Messages in Your Code
59    
60    To generate a trace message, use the following syntax.
61    
62  C<< Trace($message) if T(errors => 4); >>      Trace($message) if T(errors => 4);
63    
64  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>
65  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
66    
67  C<< Trace($message) if T(main => 4); >>      Trace($message) if T(main => 4);
68    
69  will trace if the trace level is 4 or more.  will trace if the trace level is 4 or more.
70    
# Line 36  Line 72 
72  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
73  active and the trace level is 2 or more.  active and the trace level is 2 or more.
74    
75  C<< Trace($message) if T(2); >>      Trace($message) if T(2);
76    
77  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>.
78  of category names, and a set of options. The trace level and list of category names are  
79    =head3 Custom Tracing
80    
81    Many programs have customized tracing configured using the L</TSetup> method. This is no longer
82    the preferred method, but a knowledge of how custom tracing works can make the more modern
83    L</Emergency Tracing> easier to understand.
84    
85    To set up custom tracing, you call the L</TSetup> method. The method takes as input a trace level,
86    a list of category names, and a destination. The trace level and list of category names are
87  specified as a space-delimited string. Thus  specified as a space-delimited string. Thus
88    
89  C<< TSetup('3 errors Sprout ERDB', 'HTML'); >>      TSetup('3 errors Sprout ERDB', 'TEXT');
90    
91  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
92  specifies that messages should be output as HTML paragraphs. The parameters are formatted  specifies that messages should be sent to the standard output.
93  to make it easier to input tracing configuration on a web form.  
94    To turn on tracing for ALL categories, use an asterisk. The call below sets every category to
95    level 3 and writes the output to the standard error output. This sort of thing might be
96    useful in a CGI environment.
97    
98  In addition to HTML and file output for trace messages, you can specify that the trace messages      TSetup('3 *', 'WARN');
99    
100    In addition standard error and file output for trace messages, you can specify that the trace messages
101  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
102  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
103  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
104  it easier to debug page formatting problems.  it easier to debug page formatting problems.
105    
106  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
107    a file at the same time. To trace to a file, specify the filename with an output character in front
108    of it.
109    
110        TSetup('4 SQL', ">$fileName");
111    
112    To trace to the standard output and a file at the same time, put a C<+> in front of the angle
113    bracket.
114    
115        TSetup('3 *', "+>$fileName");
116    
117  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>.
118  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.
119  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
120  being used out in the field.  being used out in the field.
121    
122    =head3 Trace Levels
123    
124    There is no hard and fast rule on how to use trace levels. The following is therefore only
125    a suggestion.
126    
127    =over 4
128    
129    =item Error 0
130    
131    Message indicates an error that may lead to incorrect results or that has stopped the
132    application entirely.
133    
134    =item Warning 1
135    
136    Message indicates something that is unexpected but that probably did not interfere
137    with program execution.
138    
139    =item Notice 2
140    
141    Message indicates the beginning or end of a major task.
142    
143    =item Information 3
144    
145    Message indicates a subtask. In the FIG system, a subtask generally relates to a single
146    genome. This would be a big loop that is not expected to execute more than 500 times or so.
147    
148    =item Detail 4
149    
150    Message indicates a low-level loop iteration.
151    
152    =back
153    
154    The format of trace messages is important because some utilities analyze trace files.
155    There are three fields-- the time stamp, the category name, and the text.
156    The time stamp is between square brackets and the category name between angle brackets.
157    After the category name there is a colon (C<:>) followed by the message text.
158    If the square brackets or angle brackets are missing, then the trace management
159    utilities assume that they are encountering a set of pre-formatted lines.
160    
161    Note, however, that this formatting is done automatically by the tracing functions. You
162    only need to know about it if you want to parse a trace file.
163    
164    =head3 Emergency Tracing
165    
166    Sometimes, you need a way for tracing to happen automatically without putting parameters
167    in a form or on the command line. Emergency tracing does this. You invoke emergency tracing
168    from the debug form, which is accessed from the [[DebugConsole]]. Emergency tracing requires
169    that you specify a tracing key. For command-line tools, the key is
170    taken from the C<TRACING> environment variable. For web services, the key is taken from
171    a cookie. Either way, the key tells the tracing facility who you are, so that you control
172    the tracing in your environment without stepping on other users.
173    
174    The key can be anything you want. If you don't have a key, the C<SetPassword> page will
175    generate one for you.
176    
177    You can activate and de-activate emergency tracing from the debugging control panel, as
178    well as display the trace file itself.
179    
180    To enable emergency tracing in your code, call
181    
182        ETracing($cgi)
183    
184    from a web script and
185    
186        ETracing()
187    
188    from a command-line script.
189    
190    The web script will look for the tracing key in the cookies, and the command-line
191    script will look for it in the C<TRACING> environment variable. If you are
192    using the L</StandardSetup> method or a [[WebApplication]], emergency tracing
193    will be configured automatically.
194    
195  =cut  =cut
196    
197  # Declare the configuration variables.  # Declare the configuration variables.
198    
199  my $Destination = "NONE";       # Description of where to send the trace output.  my $Destination = "WARN";   # Description of where to send the trace output.
200    my $TeeFlag = 0;            # TRUE if output is going to a file and to the
201                                # standard output
202  my %Categories = ( main => 1 );  my %Categories = ( main => 1 );
203                                                          # hash of active category names                                                          # hash of active category names
204    my @LevelNames = qw(error warn notice info detail);
205  my $TraceLevel = 0;                     # trace level; a higher trace level produces more  my $TraceLevel = 0;                     # trace level; a higher trace level produces more
206                                                          # messages                                                          # messages
207  my @Queue = ();                         # queued list of trace messages.  my @Queue = ();                         # queued list of trace messages.
208  my $LastCategory = "main";  # name of the last category interrogated  my $LastCategory = "main";  # name of the last category interrogated
209    my $LastLevel = 0;          # level of the last test call
210    my $SetupCount = 0;         # number of times TSetup called
211    my $AllTrace = 0;           # TRUE if we are tracing all categories.
212    my $SavedCGI;               # CGI object passed to ETracing
213    my $CommandLine;            # Command line passed to StandardSetup
214    umask 2;                    # Fix the damn umask so everything is group-writable.
215    
216  =head2 Public Methods  =head2 Tracing Methods
217    
218    =head3 Setups
219    
220        my $count = Tracer::Setups();
221    
222    Return the number of times L</TSetup> has been called.
223    
224    This method allows for the creation of conditional tracing setups where, for example, we
225    may want to set up tracing if nobody else has done it before us.
226    
227    =cut
228    
229    sub Setups {
230        return $SetupCount;
231    }
232    
233  =head3 TSetup  =head3 TSetup
234    
235  C<< TSetup($categoryList, $target); >>      TSetup($categoryList, $target);
236    
237  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
238  and interrogated by the L</Trace> and L</T> methods.  and interrogated by the L</Trace> and L</T> methods.
# Line 93  Line 248 
248    
249  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
250  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
251  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 ">"
252  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
253  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
254    cause tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>
255  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
256  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
257  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 269 
269          my @categoryData = split /\s+/, $categoryList;          my @categoryData = split /\s+/, $categoryList;
270          # Extract the trace level.          # Extract the trace level.
271          $TraceLevel = shift @categoryData;          $TraceLevel = shift @categoryData;
272          # Build the category hash.      # Presume category-based tracing until we learn otherwise.
273        $AllTrace = 0;
274        # Build the category hash. Note that if we find a "*", we turn on non-category
275        # tracing. We must also clear away any pre-existing data.
276        %Categories = ( main => 1 );
277          for my $category (@categoryData) {          for my $category (@categoryData) {
278                  $Categories{$category} = 1;          if ($category eq '*') {
279                $AllTrace = 1;
280            } else {
281                $Categories{lc $category} = 1;
282            }
283          }          }
284          # Now we need to process the destination information. The most important special          # Now we need to process the destination information. The most important special
285          # case is the single ">", which requires we clear the file first. After doing      # case is when we're writing to a file. This is indicated by ">" (overwrite) and
286          # so, we tack on another ">" sign so that future trace messages are appended.      # ">>" (append). A leading "+" for either indicates that we are also writing to
287        # the standard output (tee mode).
288        if ($target =~ m/^\+?>>?/) {
289            if ($target =~ m/^\+/) {
290                $TeeFlag = 1;
291                $target = substr($target, 1);
292            }
293          if ($target =~ m/^>[^>]/) {          if ($target =~ m/^>[^>]/) {
294                # We need to initialize the file (which clears it).
295                  open TRACEFILE, $target;                  open TRACEFILE, $target;
296                  print TRACEFILE Now() . " Tracing initialized.\n";              print TRACEFILE "[" . Now() . "] [notice] [Tracer] Tracing initialized.\n";
297                  close TRACEFILE;                  close TRACEFILE;
298                # Set to append mode now that the file has been cleared.
299                  $Destination = ">$target";                  $Destination = ">$target";
300          } else {          } else {
301                $Destination = $target;
302            }
303        } else {
304                  $Destination = uc($target);                  $Destination = uc($target);
305          }          }
306        # Increment the setup counter.
307        $SetupCount++;
308  }  }
309    
310  =head3 SetLevel  =head3 SetLevel
311    
312  C<< Tracer::SetLevel($newLevel); >>      Tracer::SetLevel($newLevel);
313    
314  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.
315    
# Line 150  Line 327 
327      $TraceLevel = $_[0];      $TraceLevel = $_[0];
328  }  }
329    
330  =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  
331    
332  =cut      my $time = Tracer::ParseDate($dateString);
333    
334  sub LogErrors {  Convert a date into a PERL time number. This method expects a date-like string
335          # Get the file name.  and parses it into a number. The string must be vaguely date-like or it will
336          my ($fileName) = @_;  return an undefined value. Our requirement is that a month and day be
337          # Open the file as the standard error output.  present and that three pieces of the date string (time of day, month and day,
338          open STDERR, '>', $fileName;  year) be separated by likely delimiters, such as spaces, commas, and such-like.
 }  
339    
340  =head3 ReadOptions  If a time of day is present, it must be in military time with two digits for
341    everything but the hour.
342    
343  C<< my %options = Tracer::ReadOptions($fileName); >>  The year must be exactly four digits.
344    
345  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
346  format  equally innocuous. This means, however, that a sufficiently long sentence with date-like
347    parts in it may be interpreted as a date. Hopefully this will not be a problem.
348    
349  I<optionName>C<=>I<optionValue>C<; >I<comment>  It should be guaranteed that this method will parse the output of the L</Now> function.
350    
351  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.  
352    
353  =over 4  =over 4
354    
355  =item fileName  =item dateString
356    
357  Name of the file containing the option data.  The date string to convert.
358    
359  =item RETURN  =item RETURN
360    
361  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
362  value.  the date string is invalid. A valid date string must contain a month and day.
363    
364  =back  =back
365    
366  =cut  =cut
367    
368  sub ReadOptions {  # Universal month conversion table.
369          # Get the parameters.  use constant MONTHS => {    Jan =>  0, January   =>  0, '01' =>  0,  '1' =>  0,
370          my ($fileName) = @_;                              Feb =>  1, February  =>  1, '02' =>  1,  '2' =>  1,
371          # Open the file.                              Mar =>  2, March     =>  2, '03' =>  2,  '3' =>  2,
372          (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");                              Apr =>  3, April     =>  3, '04' =>  3,  '4' =>  3,
373          # Count the number of records read.                              May =>  4, May       =>  4, '05' =>  4,  '5' =>  4,
374          my ($records, $comments) = 0;                              Jun =>  5, June      =>  5, '06' =>  5,  '6' =>  5,
375          # Create the return hash.                              Jul =>  6, July      =>  6, '07' =>  6,  '7' =>  6,
376          my %retVal = ();                              Aug =>  7, August    =>  7, '08' =>  7,  '8' =>  7,
377          # Loop through the file, accumulating key-value pairs.                              Sep =>  8, September =>  8, '09' =>  8,  '9' =>  8,
378          while (my $line = <CONFIGFILE>) {                              Oct =>  9, October  =>   9, '10' =>  9,
379                  # Denote we've read a line.                              Nov => 10, November =>  10, '11' => 10,
380                  $records++;                              Dec => 11, December =>  11, '12' => 11
381                  # Determine the line type.                          };
                 if ($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  
382    
383  sub GetOptions {  sub ParseDate {
384          # Get the parameters.          # Get the parameters.
385          my ($defaults, $options) = @_;      my ($dateString) = @_;
386          # Check for overrides.      # Declare the return variable.
387          if ($options) {      my $retVal;
388                  # Loop through the overrides.      # Find the month and day of month. There are two ways that can happen. We check for the
389                  while (my ($option, $setting) = each %{$options}) {      # numeric style first. That way, if the user's done something like "Sun 12/22", then we
390                          # Insure this override exists.      # won't be fooled into thinking the month is Sunday.
391                          if (!exists $defaults->{$option}) {      if ($dateString =~ m#\b(\d{1,2})/(\d{1,2})\b# || $dateString =~ m#\b(\w+)\s(\d{1,2})\b#) {
392                                  croak "Unrecognized option $option encountered.";          my ($mon, $mday) = (MONTHS->{$1}, $2);
393            # Insist that the month and day are valid.
394            if (defined($mon) && $2 >= 1 && $2 <= 31) {
395                # Find the time.
396                my ($hour, $min, $sec) = (0, 0, 0);
397                if ($dateString =~ /\b(\d{1,2}):(\d{2}):(\d{2})\b/) {
398                    ($hour, $min, $sec) = ($1, $2, $3);
399                }
400                # Find the year.
401                my $year;
402                if ($dateString =~ /\b(\d{4})\b/) {
403                    $year = $1;
404                          } else {                          } else {
405                                  # Apply the override.                  # Get the default year, which is this one. Note we must convert it to
406                                  $defaults->{$option} = $setting;                  # the four-digit value expected by "timelocal".
407                    (undef, undef, undef, undef, undef, $year) = localtime();
408                    $year += 1900;
409                          }                          }
410                $retVal = timelocal($sec, $min, $hour, $mday, $mon, $year);
411                  }                  }
412          }          }
413          # Return the merged table.      # Return the result.
414          return $defaults;      return $retVal;
415  }  }
416    
417  =head3 MergeOptions  =head3 LogErrors
418    
419  C<< Tracer::MergeOptions(\%table, \%defaults); >>      Tracer::LogErrors($fileName);
420    
421  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.  
422    
423  =over 4  =over 4
424    
425  =item table  =item fileName
   
 Hash table to be updated with the default values.  
   
 =item defaults  
426    
427  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.
428    
429  =back  =back
430    
431  =cut  =cut
432    
433  sub MergeOptions {  sub LogErrors {
434          # Get the parameters.      # Get the file name.
435          my ($table, $defaults) = @_;      my ($fileName) = @_;
436          # Loop through the defaults.      # Open the file as the standard error output.
437          while (my ($key, $value) = each %{$defaults}) {      open STDERR, '>', $fileName;
                 if (!exists $table->{$key}) {  
                         $table->{$key} = $value;  
                 }  
         }  
438  }  }
439    
440  =head3 Trace  =head3 Trace
441    
442  C<< Trace($message); >>      Trace($message);
443    
444  Write a trace message to the target location specified in L</TSetup>. If there has not been  Write a trace message to the target location specified in L</TSetup>. If there has not been
445  any prior call to B<TSetup>.  any prior call to B<TSetup>.
# Line 371  Line 457 
457  sub Trace {  sub Trace {
458          # Get the parameters.          # Get the parameters.
459          my ($message) = @_;          my ($message) = @_;
460        # Strip off any line terminators at the end of the message. We will add
461        # new-line stuff ourselves.
462        my $stripped = Strip($message);
463        # Compute the caller information.
464        my ($callPackage, $callFile, $callLine) = caller();
465        my $callFileTitle = basename($callFile);
466        # Check the caller.
467        my $callerInfo = ($callFileTitle ne "Tracer.pm" ? " [$callFileTitle $callLine]" : "");
468          # Get the timestamp.          # Get the timestamp.
469          my $timeStamp = Now();          my $timeStamp = Now();
470          # Format the message. Note we strip off any line terminators at the end.      # Build the prefix.
471          my $formatted = "$timeStamp <$LastCategory>: " . Strip($message);      my $level = $LevelNames[$LastLevel] || "($LastLevel)";
472        my $prefix = "[$timeStamp] [$level] [$LastCategory]$callerInfo";
473        # Format the message.
474        my $formatted = "$prefix $stripped";
475          # Process according to the destination.          # Process according to the destination.
476          if ($Destination eq "TEXT") {          if ($Destination eq "TEXT") {
477                  # Write the message to the standard output.                  # Write the message to the standard output.
478                  print "$formatted\n";                  print "$formatted\n";
479          } elsif ($Destination eq "ERROR") {          } elsif ($Destination eq "ERROR") {
480                  # Write the message to the error output.          # Write the message to the error output. Here, we want our prefix fields.
481                  print STDERR "$formatted\n";                  print STDERR "$formatted\n";
482        } elsif ($Destination eq "WARN") {
483            # Emit the message to the standard error output. It is presumed that the
484            # error logger will add its own prefix fields, the notable exception being
485            # the caller info.
486            print STDERR "$callerInfo$stripped\n";
487          } elsif ($Destination eq "QUEUE") {          } elsif ($Destination eq "QUEUE") {
488                  # Push the message into the queue.                  # Push the message into the queue.
489                  push @Queue, "$formatted";                  push @Queue, "$formatted";
490          } elsif ($Destination eq "HTML") {          } elsif ($Destination eq "HTML") {
491                  # Convert the message to HTML and write it to the standard output.          # Convert the message to HTML.
492                  my $escapedMessage = CGI::escapeHTML($message);          my $escapedMessage = CGI::escapeHTML($stripped);
493                  print "<p>$formatted</p>\n";          # The stuff after the first line feed should be pre-formatted.
494      } elsif ($Destination eq "WARN") {          my @lines = split /\s*\n/, $escapedMessage;
495         # Emit the message as a warning.          # Get the normal portion.
496         warn $message;          my $line1 = shift @lines;
497            print "<p>$timeStamp $LastCategory $LastLevel: $line1</p>\n";
498            if (@lines) {
499                print "<pre>" . join("\n", @lines, "<pre>");
500            }
501          } elsif ($Destination =~ m/^>>/) {          } elsif ($Destination =~ m/^>>/) {
502                  # Write the trace message to an output file.                  # Write the trace message to an output file.
503                  open TRACING, $Destination;          open(TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";
504            # Lock the file.
505            flock TRACING, LOCK_EX;
506                  print TRACING "$formatted\n";                  print TRACING "$formatted\n";
507                  close TRACING;                  close TRACING;
508            # If the Tee flag is on, echo it to the standard output.
509            if ($TeeFlag) {
510                print "$formatted\n";
511            }
512        }
513    }
514    
515    =head3 MemTrace
516    
517        MemTrace($message);
518    
519    Output a trace message that includes memory size information.
520    
521    =over 4
522    
523    =item message
524    
525    Message to display. The message will be followed by a sentence about the memory size.
526    
527    =back
528    
529    =cut
530    
531    sub MemTrace {
532        # Get the parameters.
533        my ($message) = @_;
534        my $memory = GetMemorySize();
535        Trace("$message $memory in use.");
536          }          }
537    
538    
539    =head3 TraceDump
540    
541        TraceDump($title, $object);
542    
543    Dump an object to the trace log. This method simply calls the C<Dumper>
544    function, but routes the output to the trace log instead of returning it
545    as a string. The output is arranged so that it comes out monospaced when
546    it appears in an HTML trace dump.
547    
548    =over 4
549    
550    =item title
551    
552    Title to give to the object being dumped.
553    
554    =item object
555    
556    Reference to a list, hash, or object to dump.
557    
558    =back
559    
560    =cut
561    
562    sub TraceDump {
563        # Get the parameters.
564        my ($title, $object) = @_;
565        # Trace the object.
566        Trace("Object dump for $title:\n" . Dumper($object));
567  }  }
568    
569  =head3 T  =head3 T
570    
571  C<< my $switch = T($category, $traceLevel); >>      my $switch = T($category, $traceLevel);
572    
573          or          or
574    
575  C<< my $switch = T($traceLevel); >>      my $switch = T($traceLevel);
576    
577  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
578  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 605 
605                  my ($category, $traceLevel) = @_;                  my ($category, $traceLevel) = @_;
606                  if (!defined $traceLevel) {                  if (!defined $traceLevel) {
607                          # 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.
608                # The calling package is normally the first parameter. If it is
609                # omitted, the first parameter will be the tracelevel. So, the
610                # first thing we do is shift the so-called category into the
611                # $traceLevel variable where it belongs.
612                          $traceLevel = $category;                          $traceLevel = $category;
613                          my ($package, $fileName, $line) = caller;                          my ($package, $fileName, $line) = caller;
614              # If there is no calling package, we default to "main".              # If there is no calling package, we default to "main".
615                          if (!$package) {                          if (!$package) {
616                  $category = "main";                  $category = "main";
617                          } else {                          } else {
618                                  $category = $package;                  my @cats = split /::/, $package;
619                    $category = $cats[$#cats];
620                          }                          }
621                  }                  }
622          # Save the category name.          # Save the category name and level.
623          $LastCategory = $category;          $LastCategory = $category;
624                  # Use the category and tracelevel to compute the result.          $LastLevel = $traceLevel;
625                  $retVal = ($traceLevel <= $TraceLevel && exists $Categories{$category});          # Convert it to lower case before we hash it.
626            $category = lc $category;
627            # Validate the trace level.
628            if (ref $traceLevel) {
629                Confess("Bad trace level.");
630            } elsif (ref $TraceLevel) {
631                Confess("Bad trace config.");
632            }
633            # Make the check. Note that level 0 shows even if the category is turned off.
634            $retVal = ($traceLevel <= $TraceLevel && ($traceLevel == 0 || $AllTrace || exists $Categories{$category}));
635      }      }
636          # Return the computed result.          # Return the computed result.
637      return $retVal;      return $retVal;
638  }  }
639    
640    =head3 QTrace
641    
642        my $data = QTrace($format);
643    
644    Return the queued trace data in the specified format.
645    
646    =over 4
647    
648    =item format
649    
650    C<html> to format the data as an HTML list, C<text> to format it as straight text.
651    
652    =back
653    
654    =cut
655    
656    sub QTrace {
657        # Get the parameter.
658        my ($format) = @_;
659        # Create the return variable.
660        my $retVal = "";
661        # Only proceed if there is an actual queue.
662        if (@Queue) {
663            # Process according to the format.
664            if ($format =~ m/^HTML$/i) {
665                # Convert the queue into an HTML list.
666                $retVal = "<ul>\n";
667                for my $line (@Queue) {
668                    my $escapedLine = CGI::escapeHTML($line);
669                    $retVal .= "<li>$escapedLine</li>\n";
670                }
671                $retVal .= "</ul>\n";
672            } elsif ($format =~ m/^TEXT$/i) {
673                # Convert the queue into a list of text lines.
674                $retVal = join("\n", @Queue) . "\n";
675            }
676            # Clear the queue.
677            @Queue = ();
678        }
679        # Return the formatted list.
680        return $retVal;
681    }
682    
683    =head3 Confess
684    
685        Confess($message);
686    
687    Trace the call stack and abort the program with the specified message. When used with
688    the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.
689    So, for example
690    
691        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
692    
693    Will abort the program with a stack trace if the value of C<$recNum> is negative.
694    
695    =over 4
696    
697    =item message
698    
699    Message to include in the trace.
700    
701    =back
702    
703    =cut
704    
705    sub Confess {
706        # Get the parameters.
707        my ($message) = @_;
708        # Set up the category and level.
709        $LastCategory = "(confess)";
710        $LastLevel = 0;
711        # Trace the call stack.
712        Cluck($message);
713        # Abort the program.
714        croak(">>> $message");
715    }
716    
717    =head3 SaveCGI
718    
719        Tracer::SaveCGI($cgi);
720    
721    This method saves the CGI object but does not activate emergency tracing.
722    It is used to allow L</Warn> to work in situations where emergency
723    tracing is contra-indicated (e.g. the wiki).
724    
725    =over 4
726    
727    =item cgi
728    
729    Active CGI query object.
730    
731    =back
732    
733    =cut
734    
735    sub SaveCGI {
736        $SavedCGI = $_[0];
737    }
738    
739    =head3 Warn
740    
741        Warn($message, @options);
742    
743    This method traces an important message. If an RSS feed is configured
744    (via I<FIG_Config::error_feed>) and the tracing destination is C<WARN>,
745    then the message will be echoed to the feed. In general, a tracing
746    destination of C<WARN> indicates that the caller is running as a web
747    service in a production environment; however, this is not a requirement.
748    
749    To force warnings into the RSS feed even when the tracing destination
750    is not C<WARN>, simply specify the C<Feed> tracing module. This can be
751    configured automatically when L</StandardSetup> is used.
752    
753    The L</Cluck> method calls this one for its final message. Since
754    L</Confess> calls L</Cluck>, this means that any error which is caught
755    and confessed will put something in the feed. This insures that someone
756    will be alerted relatively quickly when a failure occurs.
757    
758    =over 4
759    
760    =item message
761    
762    Message to be traced.
763    
764    =item options
765    
766    A list containing zero or more options.
767    
768    =back
769    
770    The permissible options are as follows.
771    
772    =over 4
773    
774    =item noStack
775    
776    If specified, then the stack trace is not included in the output.
777    
778    =back
779    
780    =cut
781    
782    sub Warn {
783        # Get the parameters.
784        my $message = shift @_;
785        my %options = map { $_ => 1 } @_;
786        # Save $@;
787        my $savedError = $@;
788        # Trace the message.
789        Trace($message);
790        # This will contain the lock handle. If it's defined, it means we need to unlock.
791        my $lock;
792        # Check for feed forcing.
793        my $forceFeed = exists $Categories{feed};
794        # An error here would be disastrous. Note that if debug mode is specified,
795        # we do this stuff even in a test environment.
796        eval {
797            # Do we need to put this in the RSS feed?
798            if ($FIG_Config::error_feed && ($Destination eq 'WARN' || $forceFeed)) {
799                # Probably. We need to check first, however, to see if it's from an
800                # ignored IP. For non-CGI situations, we default the IP to the self-referent.
801                my $key = "127.0.0.1";
802                if (defined $SavedCGI) {
803                    # Get the IP address.
804                    $key = $ENV{HTTP_X_FORWARDED_FOR} || $ENV{REMOTE_ADDR};
805                }
806                # Is the IP address in the ignore list?
807                my $found = scalar(grep { $_ eq $key } @FIG_Config::error_ignore_ips);
808                if (! $found) {
809                    # No. We're good. We now need to compute the date, the link, and the title.
810                    # First, the date, in a very specific format.
811                    my $date = strftime("%a, %02e %b %H:%M:%S %Y ", localtime) .
812                        (tz_local_offset() / 30);
813                    # Environment data goes in here. We start with the date.
814                    my $environment = "$date.  ";
815                    # If we need to recap the message (because it's too long to be a title), we'll
816                    # put it in here.
817                    my $recap;
818                    # Copy the message and remove excess space.
819                    my $title = $message;
820                    $title =~ s/\s+/ /gs;
821                    # If it's too long, we have to split it up.
822                    if (length $title > 60) {
823                        # Put the full message in the environment string.
824                        $recap = $title;
825                        # Excerpt it as the title.
826                        $title = substr($title, 0, 50) . "...";
827                    }
828                    # If we have a CGI object, then this is a web error. Otherwise, it's
829                    # command-line.
830                    if (defined $SavedCGI) {
831                        # We're in a web service. The environment is the user's IP, and the link
832                        # is the URL that got us here.
833                        $environment .= "Event Reported at IP address $key process $$.";
834                        my $url = $SavedCGI->self_url();
835                        # We need the user agent string and (if available) the referrer.
836                        # The referrer will be the link.
837                        $environment .= " User Agent $ENV{HTTP_USER_AGENT}";
838                        if ($ENV{HTTP_REFERER}) {
839                            my $link = $ENV{HTTP_REFERER};
840                            $environment .= " referred from <a href=\"$link\">$link</a>.";
841                        } else {
842                            $environment .= " referrer unknown.";
843                        }
844                        # Close off the sentence with the original link.
845                        $environment .= " URL of event is <a href=\"$url\">$url</a>.";
846                    } else {
847                        # No CGI object, so we're a command-line tool. Use the tracing
848                        # key and the PID as the user identifier, and add the command.
849                        my $key = EmergencyKey();
850                        $environment .= "Event Reported by $key process $$.";
851                        if ($CommandLine) {
852                            # We're in a StandardSetup script, so we have the real command line.
853                            $environment .= "\n<pre>" . CGI::escapeHTML($CommandLine) . "</pre>\n";
854                        } elsif ($ENV{_}) {
855                            # We're in a BASH script, so the command has been stored in the _ variable.
856                            $environment .= "  Command = " . CGI::escapeHTML($ENV{_}) . "\n";
857                        }
858                    }
859                    # Build a GUID. We use the current time, the title, and the process ID,
860                    # then digest the result.
861                    my $guid = Digest::MD5::md5_base64(gettimeofday(), $title, $$);
862                    # Finally, the description. This is a stack trace plus various environmental stuff.
863                    # The trace is optional.
864                    my $stackTrace;
865                    if ($options{noStack}) {
866                        $stackTrace = "";
867                    } else {
868                        my @trace = LongMess();
869                        # Only proceed if we got something back.
870                        if (scalar(@trace) > 0) {
871                            $trace[0] =~ s/Tracer::Warn.+?called/Event occurred/;
872                            $stackTrace = "Stack trace:<pre>" . join("\n", @trace, "</pre>");
873                        }
874                    }
875                    # We got the stack trace. Now it's time to put it all together.
876                    # We have a goofy thing here in that we need to HTML-escape some sections of the description
877                    # twice. They will be escaped once here, and then once when written by XML::Simple. They are
878                    # unescaped once when processed by the RSS reader, and stuff in the description is treated as
879                    # HTML. So, anything escaped here is treated as a literal when viewed in the RSS reader, but
880                    # our <br>s and <pre>s are used to format the description.
881                    $recap = (defined $recap ? "<em>" . CGI::escapeHTML($recap) . "</em><br /><br />" : "");
882                    my $description = "$recap$environment  $stackTrace";
883                    # Okay, we have all the pieces. Create a hash of the new event.
884                    my $newItem = { title => $title,
885                                    description => $description,
886                                    category => $LastCategory,
887                                    pubDate => $date,
888                                    guid => $guid,
889                                  };
890                    # We need XML capability for this.
891                    require XML::Simple;
892                    # The RSS document goes in here.
893                    my $rss;
894                    # Get the name of the RSS file. It's in the FIG temporary directory.
895                    my $fileName = "$FIG_Config::temp/$FIG_Config::error_feed";
896                    # Open the config file and lock it.
897                    $lock = Open(undef, "<$FIG_Config::fig_disk/config/FIG_Config.pm");
898                    flock $lock, LOCK_EX;
899                    # Does it exist?
900                    if (-s $fileName) {
901                        # Slurp it in.
902                        $rss = XML::Simple::XMLin($fileName, ForceArray => ['item']);
903                    } else {
904                        my $size = -s $fileName;
905                        # Create an empty channel.
906                        $rss = {
907                            channel => {
908                                title => 'NMPDR Warning Feed',
909                                link => "$FIG_Config::temp_url/$FIG_Config::error_feed",
910                                description => "Important messages regarding the status of the NMPDR.",
911                                generator => "NMPDR Trace Facility",
912                                docs => "http://blogs.law.harvard.edu/tech/rss",
913                                item => []
914                            },
915                        };
916                    }
917                    # Get the channel object.
918                    my $channel = $rss->{channel};
919                    # Update the last-build date.
920                    $channel->{lastBuildDate} = $date;
921                    # Get the item array.
922                    my $items = $channel->{item};
923                    # Insure it has only 100 entries.
924                    while (scalar @{$items} > 100) {
925                        pop @{$items};
926                    }
927                    # Add our new item at the front.
928                    unshift @{$items}, $newItem;
929                    # Create the XML. Note we do not include the root or the declaration. XML Simple can't handle
930                    # the requirements for those.
931                    my $xml = XML::Simple::XMLout($channel, NoAttr => 1, RootName => 'channel', XmlDecl => '');
932                    # Here we put in the root and declaration. The problem is that the root has to have the version attribute
933                    # in it. So, we suppress the root and do it by hand, and that requires suppressing the declaration, too.
934                    $xml = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<rss version=\"2.0\">$xml\n</rss>";
935                    # We don't use Open here because we can't afford an error.
936                    if (open XMLOUT, ">$fileName") {
937                        print XMLOUT $xml;
938                        close XMLOUT;
939                    }
940                }
941            }
942        };
943        if ($@) {
944            # If the feed failed, we need to know why. The error will be traced, but this method will not be involved
945            # (which is a good thing).
946            my $error = $@;
947            Trace("Feed Error: $error") if T(Feed => 0);
948        }
949        # Be sure to unlock.
950        if ($lock) {
951            flock $lock, LOCK_UN;
952            undef $lock;
953        }
954        # Restore the error message.
955        $@ = $savedError;
956    }
957    
958    
959    
960    
961    =head3 Assert
962    
963        Assert($condition1, $condition2, ... $conditionN);
964    
965    Return TRUE if all the conditions are true. This method can be used in conjunction with
966    the OR operator and the L</Confess> method as a debugging assert.
967    So, for example
968    
969        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
970    
971    Will abort the program with a stack trace if the value of C<$recNum> is negative.
972    
973    =cut
974    sub Assert {
975        my $retVal = 1;
976        LOOP: for my $condition (@_) {
977            if (! $condition) {
978                $retVal = 0;
979                last LOOP;
980            }
981        }
982        return $retVal;
983    }
984    
985    =head3 Cluck
986    
987        Cluck($message);
988    
989    Trace the call stack. Note that for best results, you should qualify the call with a
990    trace condition. For example,
991    
992        Cluck("Starting record parse.") if T(3);
993    
994    will only trace the stack if the trace level for the package is 3 or more.
995    
996    =over 4
997    
998    =item message
999    
1000    Message to include in the trace.
1001    
1002    =back
1003    
1004    =cut
1005    
1006    sub Cluck {
1007        # Get the parameters.
1008        my ($message) = @_;
1009        # Trace what's happening.
1010        Trace("Stack trace for event: $message");
1011        # Get the stack trace.
1012        my @trace = LongMess();
1013        # Convert the trace to a series of messages.
1014        for my $line (@trace) {
1015            # Replace the tab at the beginning with spaces.
1016            $line =~ s/^\t/    /;
1017            # Trace the line.
1018            Trace($line);
1019        }
1020        # Issue a warning. This displays the event message and inserts it into the RSS error feed.
1021        Warn($message);
1022    }
1023    
1024    =head3 LongMess
1025    
1026        my @lines = Tracer::LongMess();
1027    
1028    Return a stack trace with all tracing methods removed. The return will be in the form of a list
1029    of message strings.
1030    
1031    =cut
1032    
1033    sub LongMess {
1034        # Declare the return variable.
1035        my @retVal = ();
1036        my $confession = longmess("");
1037        for my $line (split /\s*\n/, $confession) {
1038            unless ($line =~ /Tracer\.pm/) {
1039                # Here we have a line worth keeping. Push it onto the result list.
1040                push @retVal, $line;
1041            }
1042        }
1043        # Return the result.
1044        return @retVal;
1045    }
1046    
1047    =head3 ETracing
1048    
1049        ETracing($parameter);
1050    
1051    Set up emergency tracing. Emergency tracing is tracing that is turned
1052    on automatically for any program that calls this method. The emergency
1053    tracing parameters are stored in a a file identified by a tracing key.
1054    If this method is called with a CGI object, then the tracing key is
1055    taken from a cookie. If it is called with no parameters, then the tracing
1056    key is taken from an environment variable. If it is called with a string,
1057    the tracing key is that string.
1058    
1059    =over 4
1060    
1061    =item parameter
1062    
1063    A parameter from which the tracing key is computed. If it is a scalar,
1064    that scalar is used as the tracing key. If it is a CGI object, the
1065    tracing key is taken from the C<IP> cookie. If it is omitted, the
1066    tracing key is taken from the C<TRACING> environment variable. If it
1067    is a CGI object and emergency tracing is not on, the C<Trace> and
1068    C<TF> parameters will be used to determine the type of tracing.
1069    
1070    =back
1071    
1072    =cut
1073    
1074    sub ETracing {
1075        # Get the parameter.
1076        my ($parameter) = @_;
1077        # Check for CGI mode.
1078        if (defined $parameter && ref $parameter eq 'CGI') {
1079            $SavedCGI = $parameter;
1080        } else {
1081            $SavedCGI = undef;
1082        }
1083        # Default to no tracing except errors.
1084        my ($tracing, $dest) = ("0", "WARN");
1085        # Check for emergency tracing.
1086        my $tkey = EmergencyKey($parameter);
1087        my $emergencyFile = EmergencyFileName($tkey);
1088        if (-e $emergencyFile) {
1089            # We have the file. Read in the data.
1090            my @tracing = GetFile($emergencyFile);
1091            # Pull off the time limit.
1092            my $expire = shift @tracing;
1093            # Convert it to seconds.
1094            $expire *= 3600;
1095            # Check the file data.
1096            my $stat = stat($emergencyFile);
1097            my ($now) = gettimeofday;
1098            if ($now - $stat->mtime > $expire) {
1099                # Delete the expired file.
1100                unlink $emergencyFile;
1101            } else {
1102                # Emergency tracing is on. Pull off the destination and
1103                # the trace level;
1104                $dest = shift @tracing;
1105                my $level = shift @tracing;
1106                # Convert the destination to a real tracing destination.
1107                # temp directory.
1108                $dest = EmergencyTracingDest($tkey, $dest);
1109                # Insure Tracer is specified.
1110                my %moduleHash = map { $_ => 1 } @tracing;
1111                $moduleHash{Tracer} = 1;
1112                # Set the trace parameter.
1113                $tracing = join(" ", $level, sort keys %moduleHash);
1114            }
1115        } elsif (defined $SavedCGI) {
1116            # There's no emergency tracing, but we have a CGI object, so check
1117            # for tracing from the form parameters.
1118            if ($SavedCGI->param('Trace')) {
1119                # Here the user has requested tracing via a form.
1120                $dest = ($SavedCGI->param('TF') ? ">$FIG_Config::temp/Trace$$.log" : "QUEUE");
1121                $tracing = $SavedCGI->param('Trace') . " Tracer";
1122            }
1123        }
1124        # Setup the tracing we've determined from all the stuff above.
1125        TSetup($tracing, $dest);
1126        # Check to see if we're a web script.
1127        if (defined $SavedCGI) {
1128            # Yes we are. Trace the form and environment data.
1129            TraceParms($SavedCGI);
1130            # Check for RAW mode. In raw mode, we print a fake header so that we see everything
1131            # emitted by the script in its raw form.
1132            if (T(Raw => 3)) {
1133                print CGI::header(-type => 'text/plain', -tracing => 'Raw');
1134            }
1135        }
1136    }
1137    
1138    =head3 EmergencyFileName
1139    
1140        my $fileName = Tracer::EmergencyFileName($tkey);
1141    
1142    Return the emergency tracing file name. This is the file that specifies
1143    the tracing information.
1144    
1145    =over 4
1146    
1147    =item tkey
1148    
1149    Tracing key for the current program.
1150    
1151    =item RETURN
1152    
1153    Returns the name of the file to contain the emergency tracing information.
1154    
1155    =back
1156    
1157    =cut
1158    
1159    sub EmergencyFileName {
1160        # Get the parameters.
1161        my ($tkey) = @_;
1162        # Compute the emergency tracing file name.
1163        return "$FIG_Config::temp/Emergency$tkey.txt";
1164    }
1165    
1166    =head3 EmergencyFileTarget
1167    
1168        my $fileName = Tracer::EmergencyFileTarget($tkey);
1169    
1170    Return the emergency tracing target file name. This is the file that receives
1171    the tracing output for file-based tracing.
1172    
1173    =over 4
1174    
1175    =item tkey
1176    
1177    Tracing key for the current program.
1178    
1179    =item RETURN
1180    
1181    Returns the name of the file to contain the trace output.
1182    
1183    =back
1184    
1185    =cut
1186    
1187    sub EmergencyFileTarget {
1188        # Get the parameters.
1189        my ($tkey) = @_;
1190        # Compute the emergency tracing file name.
1191        return "$FIG_Config::temp/trace$tkey.log";
1192    }
1193    
1194    =head3 EmergencyTracingDest
1195    
1196        my $dest = Tracer::EmergencyTracingDest($tkey, $myDest);
1197    
1198    This method converts an emergency tracing destination to a real
1199    tracing destination. The main difference is that if the
1200    destination is C<FILE> or C<APPEND>, we convert it to file
1201    output. If the destination is C<DUAL>, we convert it to file
1202    and standard output.
1203    
1204    =over 4
1205    
1206    =item tkey
1207    
1208    Tracing key for this environment.
1209    
1210    =item myDest
1211    
1212    Destination from the emergency tracing file.
1213    
1214    =item RETURN
1215    
1216    Returns a destination that can be passed into L</TSetup>.
1217    
1218    =back
1219    
1220    =cut
1221    
1222    sub EmergencyTracingDest {
1223        # Get the parameters.
1224        my ($tkey, $myDest) = @_;
1225        # Declare the return variable.
1226        my $retVal = $myDest;
1227        # Process according to the destination value.
1228        if ($myDest eq 'FILE') {
1229            $retVal = ">" . EmergencyFileTarget($tkey);
1230        } elsif ($myDest eq 'APPEND') {
1231            $retVal = ">>" . EmergencyFileTarget($tkey);
1232        } elsif ($myDest eq 'DUAL') {
1233            $retVal = "+>" . EmergencyFileTarget($tkey);
1234        } elsif ($myDest eq 'WARN') {
1235            $retVal = "WARN";
1236        }
1237        # Return the result.
1238        return $retVal;
1239    }
1240    
1241    =head3 Emergency
1242    
1243        Emergency($key, $hours, $dest, $level, @modules);
1244    
1245    Turn on emergency tracing. This method is normally invoked over the web from
1246    a debugging console, but it can also be called by the C<trace.pl> script.
1247    The caller specifies the duration of the emergency in hours, the desired tracing
1248    destination, the trace level, and a list of the trace modules to activate.
1249    For the length of the duration, when a program in an environment with the
1250    specified tracing key active invokes a Sprout CGI script, tracing will be
1251    turned on automatically. See L</TSetup> for more about tracing setup and
1252    L</ETracing> for more about emergency tracing.
1253    
1254    =over 4
1255    
1256    =item tkey
1257    
1258    The tracing key. This is used to identify the control file and the trace file.
1259    
1260    =item hours
1261    
1262    Number of hours to keep emergency tracing alive.
1263    
1264    =item dest
1265    
1266    Tracing destination. If no path information is specified for a file
1267    destination, it is put in the FIG temporary directory.
1268    
1269    =item level
1270    
1271    Tracing level. A higher level means more trace messages.
1272    
1273    =item modules
1274    
1275    A list of the tracing modules to activate.
1276    
1277    =back
1278    
1279    =cut
1280    
1281    sub Emergency {
1282        # Get the parameters.
1283        my ($tkey, $hours, $dest, $level, @modules) = @_;
1284        # Create the emergency file.
1285        my $specFile = EmergencyFileName($tkey);
1286        my $outHandle = Open(undef, ">$specFile");
1287        print $outHandle join("\n", $hours, $dest, $level, @modules, "");
1288    }
1289    
1290    =head3 EmergencyKey
1291    
1292        my $tkey = EmergencyKey($parameter);
1293    
1294    Return the Key to be used for emergency tracing. This could be an IP address,
1295     a session ID, or a user name, depending on the environment.
1296    
1297    =over 4
1298    
1299    =item parameter
1300    
1301    Parameter defining the method for finding the tracing key. If it is a scalar,
1302    then it is presumed to be the tracing key itself. If it is a CGI object, then
1303    the tracing key is taken from the C<IP> cookie. Otherwise, the tracing key is
1304    taken from the C<TRACING> environment variable.
1305    
1306    =item RETURN
1307    
1308    Returns the key to be used for labels in emergency tracing.
1309    
1310    =back
1311    
1312    =cut
1313    
1314    sub EmergencyKey {
1315        # Get the parameters.
1316        my ($parameter) = @_;
1317        # Declare the return variable.
1318        my $retVal;
1319        # Determine the parameter type.
1320        if (! defined $parameter || defined($ENV{TRACING})) {
1321            # Here we're supposed to check the environment. If that fails, we
1322            # get the effective login ID.
1323            $retVal = $ENV{TRACING} || scalar getpwuid($<);
1324        } else {
1325            my $ptype = ref $parameter;
1326            if ($ptype eq 'CGI') {
1327                # Here we were invoked from a web page. Look for a cookie.
1328                $retVal = $parameter->cookie('IP');
1329            } elsif (! $ptype) {
1330                # Here the key was passed in.
1331                $retVal = $parameter;
1332            }
1333        }
1334        # If no luck finding a key, use the PID.
1335        if (! defined $retVal) {
1336            $retVal = $$;
1337        }
1338        # Return the result.
1339        return $retVal;
1340    }
1341    
1342    
1343    =head3 TraceParms
1344    
1345        Tracer::TraceParms($cgi);
1346    
1347    Trace the CGI parameters at trace level CGI => 3 and the environment variables
1348    at level CGI => 4. A self-referencing URL is traced at level CGI => 2.
1349    
1350    =over 4
1351    
1352    =item cgi
1353    
1354    CGI query object containing the parameters to trace.
1355    
1356    =back
1357    
1358    =cut
1359    
1360    sub TraceParms {
1361        # Get the parameters.
1362        my ($cgi) = @_;
1363        if (T(CGI => 2)) {
1364            # Here we trace the GET-style URL for the script, but only if it's
1365            # relatively small.
1366            my $url = $cgi->url(-relative => 1, -query => 1);
1367            my $len = length($url);
1368            if ($len < 500) {
1369                Trace("[URL] $url");
1370            } elsif ($len > 2048) {
1371                Trace("[URL] URL is too long to use with GET ($len characters).");
1372            } else {
1373                Trace("[URL] URL length is $len characters.");
1374            }
1375        }
1376        if (T(CGI => 3)) {
1377            # Here we want to trace the parameter data.
1378            my @names = $cgi->param;
1379            for my $parmName (sort @names) {
1380                # Note we skip the Trace parameters, which are for our use only.
1381                if ($parmName ne 'Trace' && $parmName ne 'TF') {
1382                    my @values = $cgi->param($parmName);
1383                    Trace("[CGI] $parmName = " . join(", ", @values));
1384                }
1385            }
1386            # Display the request method.
1387            my $method = $cgi->request_method();
1388            Trace("Method: $method");
1389        }
1390        if (T(CGI => 4)) {
1391            # Here we want the environment data too.
1392            for my $envName (sort keys %ENV) {
1393                Trace("[ENV] $envName = $ENV{$envName}");
1394            }
1395        }
1396    }
1397    
1398    =head3 TraceImages
1399    
1400        Tracer::TraceImages($htmlString);
1401    
1402    Trace information about all of an html document's images. The tracing
1403    will be for type "IMG" at level 3. The image's source string
1404    will be displayed. This is generally either the URL of the image or
1405    raw data for the image itself. If the source is too long, only the first 300
1406    characters will be shown at trace level 3. The entire source will be shown,
1407    however, at trace level 4. This method is not very smart, and might catch
1408    Javascript code, but it is still useful when debugging the arcane
1409    behavior of images in multiple browser environments.
1410    
1411    =over 4
1412    
1413    =item htmlString
1414    
1415    HTML text for an outgoing web page.
1416    
1417    =back
1418    
1419    =cut
1420    
1421    sub TraceImages {
1422        # Only proceed if we're at the proper trace level.
1423        if (T(IMG => 3)) {
1424            # For performance reasons we're manipulating $_[0] instead of retrieving the string
1425            # into a variable called "$htmlString". This is because we expect html strings to be
1426            # long, and don't want to copy them any more than we have to.
1427            Trace(length($_[0]) . " characters in web page.");
1428            # Loop through the HTML, culling image tags.
1429            while ($_[0] =~ /<img\s+[^>]+?src="([^"]+)"/sgi) {
1430                # Extract the source string and determine whether or not it's too long.
1431                my $srcString = $1;
1432                my $pos = pos($_[0]) - length($srcString);
1433                my $excess = length($srcString) - 300;
1434                # We'll put the display string in here.
1435                my $srcDisplay = $srcString;
1436                # If it's a data string, split it at the comma.
1437                $srcDisplay =~ s/^(data[^,]+,)/$1\n/;
1438                # If there's no excess or we're at trace level 4, we're done. At level 3 with
1439                # a long string, however, we only show the first 300 characters.
1440                if ($excess > 0 && ! T(IMG => 4)) {
1441                    $srcDisplay = substr($srcDisplay,0,300) . "\nplus $excess characters.";
1442                }
1443                # Output the trace message.
1444                Trace("Image tag at position $pos:\n$srcDisplay");
1445            }
1446        }
1447    }
1448    
1449    =head2 Command-Line Utility Methods
1450    
1451    =head3 SendSMS
1452    
1453        my $msgID = Tracer::SendSMS($phoneNumber, $msg);
1454    
1455    Send a text message to a phone number using Clickatell. The FIG_Config file must contain the
1456    user name, password, and API ID for the relevant account in the hash reference variable
1457    I<$FIG_Config::phone>, using the keys C<user>, C<password>, and C<api_id>. For
1458    example, if the user name is C<BruceTheHumanPet>, the password is C<silly>, and the API ID
1459    is C<2561022>, then the FIG_Config file must contain
1460    
1461        $phone =  { user => 'BruceTheHumanPet',
1462                    password => 'silly',
1463                    api_id => '2561022' };
1464    
1465    The original purpose of this method was to insure Bruce would be notified immediately when the
1466    Sprout Load terminates. Care should be taken if you do not wish Bruce to be notified immediately
1467    when you call this method.
1468    
1469    The message ID will be returned if successful, and C<undef> if an error occurs.
1470    
1471    =over 4
1472    
1473    =item phoneNumber
1474    
1475    Phone number to receive the message, in international format. A United States phone number
1476    would be prefixed by "1". A British phone number would be prefixed by "44".
1477    
1478    =item msg
1479    
1480    Message to send to the specified phone.
1481    
1482    =item RETURN
1483    
1484    Returns the message ID if successful, and C<undef> if the message could not be sent.
1485    
1486    =back
1487    
1488    =cut
1489    
1490    sub SendSMS {
1491        # Get the parameters.
1492        my ($phoneNumber, $msg) = @_;
1493        # Declare the return variable. If we do not change it, C<undef> will be returned.
1494        my $retVal;
1495        # Only proceed if we have phone support.
1496        if (! defined $FIG_Config::phone) {
1497            Trace("Phone support not present in FIG_Config.") if T(1);
1498        } else {
1499            # Get the phone data.
1500            my $parms = $FIG_Config::phone;
1501            # Get the Clickatell URL.
1502            my $url = "http://api.clickatell.com/http/";
1503            # Create the user agent.
1504            my $ua = LWP::UserAgent->new;
1505            # Request a Clickatell session.
1506            my $resp = $ua->post("$url/sendmsg", { user => $parms->{user},
1507                                         password => $parms->{password},
1508                                         api_id => $parms->{api_id},
1509                                         to => $phoneNumber,
1510                                         text => $msg});
1511            # Check for an error.
1512            if (! $resp->is_success) {
1513                Trace("Alert failed.") if T(1);
1514            } else {
1515                # Get the message ID.
1516                my $rstring = $resp->content;
1517                if ($rstring =~ /^ID:\s+(.*)$/) {
1518                    $retVal = $1;
1519                } else {
1520                    Trace("Phone attempt failed with $rstring") if T(1);
1521                }
1522            }
1523        }
1524        # Return the result.
1525        return $retVal;
1526    }
1527    
1528    =head3 StandardSetup
1529    
1530        my ($options, @parameters) = StandardSetup(\@categories, \%options, $parmHelp, @ARGV);
1531    
1532    This method performs standard command-line parsing and tracing setup. The return
1533    values are a hash of the command-line options and a list of the positional
1534    parameters. Tracing is automatically set up and the command-line options are
1535    validated.
1536    
1537    This is a complex method that does a lot of grunt work. The parameters can
1538    be more easily understood, however, once they are examined individually.
1539    
1540    The I<categories> parameter is the most obtuse. It is a reference to a list of
1541    special-purpose tracing categories. Most tracing categories are PERL package
1542    names. So, for example, if you wanted to turn on tracing inside the B<Sprout>,
1543    B<ERDB>, and B<SproutLoad> packages, you would specify the categories
1544    
1545        ["Sprout", "SproutLoad", "ERDB"]
1546    
1547    This would cause trace messages in the specified three packages to appear in
1548    the output. There are two special tracing categories that are automatically
1549    handled by this method. In other words, if you used L</TSetup> you would need
1550    to include these categories manually, but if you use this method they are turned
1551    on automatically.
1552    
1553    =over 4
1554    
1555    =item SQL
1556    
1557    Traces SQL commands and activity.
1558    
1559    =item Tracer
1560    
1561    Traces error messages and call stacks.
1562    
1563    =back
1564    
1565    C<SQL> is only turned on if the C<-sql> option is specified in the command line.
1566    The trace level is specified using the C<-trace> command-line option. For example,
1567    the following command line for C<TransactFeatures> turns on SQL tracing and runs
1568    all tracing at level 3.
1569    
1570        TransactFeatures -trace=3 -sql register ../xacts IDs.tbl
1571    
1572    Standard tracing is output to the standard output and echoed to the file
1573    C<trace>I<$$>C<.log> in the FIG temporary directory, where I<$$> is the
1574    process ID. You can also specify the C<user> parameter to put a user ID
1575    instead of a process ID in the trace file name. So, for example
1576    
1577    The default trace level is 2. To get all messages, specify a trace level of 4.
1578    For a genome-by-genome update, use 3.
1579    
1580        TransactFeatures -trace=3 -sql -user=Bruce register ../xacts IDs.tbl
1581    
1582    would send the trace output to C<traceBruce.log> in the temporary directory.
1583    
1584    The I<options> parameter is a reference to a hash containing the command-line
1585    options, their default values, and an explanation of what they mean. Command-line
1586    options may be in the form of switches or keywords. In the case of a switch, the
1587    option value is 1 if it is specified and 0 if it is not specified. In the case
1588    of a keyword, the value is separated from the option name by an equal sign. You
1589    can see this last in the command-line example above.
1590    
1591    You can specify a different default trace level by setting C<$options->{trace}>
1592    prior to calling this method.
1593    
1594    An example at this point would help. Consider, for example, the command-line utility
1595    C<TransactFeatures>. It accepts a list of positional parameters plus the options
1596    C<safe>, C<noAlias>, C<start>, and C<tblFiles>. To start up this command, we execute
1597    the following code.
1598    
1599        my ($options, @parameters) = Tracer::StandardSetup(["DocUtils"],
1600                            { safe => [0, "use database transactions"],
1601                              noAlias => [0, "do not expect aliases in CHANGE transactions"],
1602                              start => [' ', "start with this genome"],
1603                              tblFiles => [0, "output TBL files containing the corrected IDs"] },
1604                            "<command> <transactionDirectory> <IDfile>",
1605                          @ARGV);
1606    
1607    
1608    The call to C<ParseCommand> specifies the default values for the options and
1609    stores the actual options in a hash that is returned as C<$options>. The
1610    positional parameters are returned in C<@parameters>.
1611    
1612    The following is a sample command line for C<TransactFeatures>.
1613    
1614        TransactFeatures -trace=2 -noAlias register ../xacts IDs.tbl
1615    
1616    Single and double hyphens are equivalent. So, you could also code the
1617    above command as
1618    
1619        TransactFeatures --trace=2 --noAlias register ../xacts IDs.tbl
1620    
1621    In this case, C<register>, C<../xacts>, and C<IDs.tbl> are the positional
1622    parameters, and would find themselves in I<@parameters> after executing the
1623    above code fragment. The tracing would be set to level 2, and the categories
1624    would be C<Tracer>, and <DocUtils>. C<Tracer> is standard,
1625    and C<DocUtils> was included because it came in within the first parameter
1626    to this method. The I<$options> hash would be
1627    
1628        { trace => 2, sql => 0, safe => 0,
1629          noAlias => 1, start => ' ', tblFiles => 0 }
1630    
1631    Use of C<StandardSetup> in this way provides a simple way of performing
1632    standard tracing setup and command-line parsing. Note that the caller is
1633    not even aware of the command-line switches C<-trace> and C<-sql>, which
1634    are used by this method to control the tracing. If additional tracing features
1635    need to be added in the future, they can be processed by this method without
1636    upsetting the command-line utilities.
1637    
1638    If the C<background> option is specified on the command line, then the
1639    standard and error outputs will be directed to files in the temporary
1640    directory, using the same suffix as the trace file. So, if the command
1641    line specified
1642    
1643        -user=Bruce -background
1644    
1645    then the trace output would go to C<traceBruce.log>, the standard output to
1646    C<outBruce.log>, and the error output to C<errBruce.log>. This is designed to
1647    simplify starting a command in the background.
1648    
1649    The user name is also used as the tracing key for L</Emergency Tracing>.
1650    Specifying a value of C<E> for the trace level causes emergency tracing to
1651    be used instead of custom tracing. If the user name is not specified,
1652    the tracing key is taken from the C<Tracing> environment variable. If there
1653    is no value for that variable, the tracing key will be computed from the active
1654    login ID.
1655    
1656    Since the default situation in StandardSetup is to trace to the standard
1657    output, errors that occur in command-line scripts will not generate
1658    RSS events. To force the events, use the C<warn> option.
1659    
1660        TransactFeatures -background -warn register ../xacts IDs.tbl
1661    
1662    Finally, if the special option C<-help> is specified, the option
1663    names will be traced at level 0 and the program will exit without processing.
1664    This provides a limited help capability. For example, if the user enters
1665    
1666        TransactFeatures -help
1667    
1668    he would see the following output.
1669    
1670        TransactFeatures [options] <command> <transactionDirectory> <IDfile>
1671            -trace    tracing level (default E)
1672            -sql      trace SQL commands
1673            -safe     use database transactions
1674            -noAlias  do not expect aliases in CHANGE transactions
1675            -start    start with this genome
1676            -tblFiles output TBL files containing the corrected IDs
1677            -forked   do not erase the trace file before tracing
1678    
1679    The caller has the option of modifying the tracing scheme by placing a value
1680    for C<trace> in the incoming options hash. The default value can be overridden,
1681    or the tracing to the standard output can be turned off by suffixing a minus
1682    sign to the trace level. So, for example,
1683    
1684        { trace => [0, "tracing level (default 0)"],
1685           ...
1686    
1687    would set the default trace level to 0 instead of E, while
1688    
1689        { trace => ["2-", "tracing level (default 2)"],
1690           ...
1691    
1692    would set the default to 2, but trace only to the log file, not to the
1693    standard output.
1694    
1695    The parameters to this method are as follows.
1696    
1697    =over 4
1698    
1699    =item categories
1700    
1701    Reference to a list of tracing category names. These should be names of
1702    packages whose internal workings will need to be debugged to get the
1703    command working.
1704    
1705    =item options
1706    
1707    Reference to a hash containing the legal options for the current command mapped
1708    to their default values and descriptions. The user can override the defaults
1709    by specifying the options as command-line switches prefixed by a hyphen.
1710    Tracing-related options may be added to this hash. If the C<-h> option is
1711    specified on the command line, the option descriptions will be used to
1712    explain the options. To turn off tracing to the standard output, add a
1713    minus sign to the value for C<trace> (see above).
1714    
1715    =item parmHelp
1716    
1717    A string that vaguely describes the positional parameters. This is used
1718    if the user specifies the C<-h> option.
1719    
1720    =item argv
1721    
1722    List of command line parameters, including the option switches, which must
1723    precede the positional parameters and be prefixed by a hyphen.
1724    
1725    =item RETURN
1726    
1727    Returns a list. The first element of the list is the reference to a hash that
1728    maps the command-line option switches to their values. These will either be the
1729    default values or overrides specified on the command line. The remaining
1730    elements of the list are the position parameters, in order.
1731    
1732    =back
1733    
1734    =cut
1735    
1736    sub StandardSetup {
1737        # Get the parameters.
1738        my ($categories, $options, $parmHelp, @argv) = @_;
1739        # Get the default tracing key.
1740        my $tkey = EmergencyKey();
1741        # Save the command line.
1742        $CommandLine = join(" ", $0, map { $_ =~ /\s/ ? "\"$_\"" : $_ } @argv);
1743        # Add the tracing options.
1744        if (! exists $options->{trace}) {
1745            $options->{trace} = ['2', "tracing level (E for emergency tracing)"];
1746        }
1747        if (! exists $options->{forked}) {
1748            $options->{forked} = [0, "keep old trace file"];
1749        }
1750        $options->{sql} = [0, "turn on SQL tracing"];
1751        $options->{help} = [0, "display command-line options"];
1752        $options->{user} = [$tkey, "tracing key"];
1753        $options->{background} = [0, "spool standard and error output"];
1754        $options->{warn} = [0, "send errors to RSS feed"];
1755        $options->{moreTracing} = ["", "comma-delimited list of additional trace modules for debugging"];
1756        # Create a parsing hash from the options hash. The parsing hash
1757        # contains the default values rather than the default value
1758        # and the description. While we're at it, we'll memorize the
1759        # length of the longest option name.
1760        my $longestName = 0;
1761        my %parseOptions = ();
1762        for my $key (keys %{$options}) {
1763            if (length $key > $longestName) {
1764                $longestName = length $key;
1765            }
1766            $parseOptions{$key} = $options->{$key}->[0];
1767        }
1768        # Parse the command line.
1769        my ($retOptions, @retParameters) = ParseCommand(\%parseOptions, @argv);
1770        # Get the logfile suffix.
1771        my $suffix = $retOptions->{user};
1772        # We'll put the trace file name in here. We need it later if background
1773        # mode is on.
1774        my $traceFileName;
1775        # Now we want to set up tracing. First, we need to know if the user
1776        # wants emergency tracing.
1777        if ($retOptions->{trace} eq 'E') {
1778            ETracing($retOptions->{user});
1779        } else {
1780            # Here the tracing is controlled from the command line.
1781            my @cats = @{$categories};
1782            if ($retOptions->{sql}) {
1783                push @cats, "SQL";
1784            }
1785            if ($retOptions->{warn}) {
1786                push @cats, "Feed";
1787            }
1788            # Add the default categories.
1789            push @cats, "Tracer";
1790            # Check for more tracing groups.
1791            if ($retOptions->{moreTracing}) {
1792                push @cats, split /,/, $retOptions->{moreTracing};
1793            }
1794            # Next, we create the category string by joining the categories.
1795            my $cats = join(" ", @cats);
1796            # Check to determine whether or not the caller wants to turn off tracing
1797            # to the standard output.
1798            my $traceLevel = $retOptions->{trace};
1799            my $textOKFlag = 1;
1800            if ($traceLevel =~ /^(.)-/) {
1801                $traceLevel = $1;
1802                $textOKFlag = 0;
1803            }
1804            # Now we set up the trace mode.
1805            my $traceMode;
1806            # Verify that we can open a file in the FIG temporary directory.
1807            my $traceFileName = "$FIG_Config::temp/trace$suffix.log";
1808            my $traceFileSpec = ($retOptions->{forked} ? ">>$traceFileName" : ">$traceFileName");
1809            if (open TESTTRACE, "$traceFileSpec") {
1810                # Here we can trace to a file.
1811                $traceMode = ">>$traceFileName";
1812                if ($textOKFlag) {
1813                    # Echo to standard output if the text-OK flag is set.
1814                    $traceMode = "+$traceMode";
1815                }
1816                # Close the test file.
1817                close TESTTRACE;
1818            } else {
1819                # Here we can't trace to a file. Complain about this.
1820                warn "Could not open trace file $traceFileName: $!\n";
1821                # We trace to the standard output if it's
1822                # okay, and the error log otherwise.
1823                if ($textOKFlag) {
1824                    $traceMode = "TEXT";
1825                } else {
1826                    $traceMode = "WARN";
1827                }
1828            }
1829            # Now set up the tracing.
1830            TSetup("$traceLevel $cats", $traceMode);
1831        }
1832        # Check for background mode.
1833        if ($retOptions->{background}) {
1834            my $outFileName = "$FIG_Config::temp/out$suffix$$.log";
1835            my $errFileName = "$FIG_Config::temp/err$suffix$$.log";
1836            # Spool the output.
1837            open STDOUT, ">$outFileName";
1838            # If we have a trace file, trace the errors to the log. Otherwise,
1839            # spool the errors.
1840            if (defined $traceFileName) {
1841                open STDERR, "| Tracer $traceFileName";
1842            } else {
1843                open STDERR, ">$errFileName";
1844            }
1845            # Check for phone support. If we have phone support and a phone number,
1846            # we want to turn it on.
1847            if ($ENV{PHONE} && defined($FIG_Config::phone)) {
1848                $retOptions->{phone} = $ENV{PHONE};
1849            }
1850        }
1851        # Check for the "help" option. If it is specified, dump the command-line
1852        # options and exit the program.
1853        if ($retOptions->{help}) {
1854            $0 =~ m#[/\\](\w+)(\.pl)?$#i;
1855            print "$1 [options] $parmHelp\n";
1856            for my $key (sort keys %{$options}) {
1857                my $name = Pad($key, $longestName, 0, ' ');
1858                my $desc = $options->{$key}->[1];
1859                if ($options->{$key}->[0]) {
1860                    $desc .= " (default " . $options->{$key}->[0] . ")";
1861                }
1862                print "  $name $desc\n";
1863            }
1864            exit(0);
1865        }
1866        # Trace the options, if applicable.
1867        if (T(3)) {
1868            my @parms = grep { $retOptions->{$_} } keys %{$retOptions};
1869            Trace("Selected options: " . join(", ", sort @parms) . ".");
1870        }
1871        # Return the parsed parameters.
1872        return ($retOptions, @retParameters);
1873    }
1874    
1875    =head3 ReadOptions
1876    
1877        my %options = Tracer::ReadOptions($fileName);
1878    
1879    Read a set of options from a file. Each option is encoded in a line of text that has the
1880    format
1881    
1882    I<optionName>C<=>I<optionValue>C<; >I<comment>
1883    
1884    The option name must consist entirely of letters, digits, and the punctuation characters
1885    C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank
1886    character is a semi-colon will be ignored. The return hash will map each option name to
1887    the corresponding option value.
1888    
1889    =over 4
1890    
1891    =item fileName
1892    
1893    Name of the file containing the option data.
1894    
1895    =item RETURN
1896    
1897    Returns a hash mapping the option names specified in the file to their corresponding option
1898    value.
1899    
1900    =back
1901    
1902    =cut
1903    
1904    sub ReadOptions {
1905        # Get the parameters.
1906        my ($fileName) = @_;
1907        # Open the file.
1908        (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");
1909        # Count the number of records read.
1910        my ($records, $comments) = 0;
1911        # Create the return hash.
1912        my %retVal = ();
1913        # Loop through the file, accumulating key-value pairs.
1914        while (my $line = <CONFIGFILE>) {
1915            # Denote we've read a line.
1916            $records++;
1917            # Determine the line type.
1918            if ($line =~ /^\s*[\n\r]/) {
1919                # A blank line is a comment.
1920                $comments++;
1921            } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {
1922                # Here we have an option assignment.
1923                retVal{$1} = $2;
1924            } elsif ($line =~ /^\s*;/) {
1925                # Here we have a text comment.
1926                $comments++;
1927            } else {
1928                # Here we have an invalid line.
1929                Trace("Invalid option statement in record $records.") if T(0);
1930            }
1931        }
1932        # Return the hash created.
1933        return %retVal;
1934    }
1935    
1936    =head3 GetOptions
1937    
1938        Tracer::GetOptions(\%defaults, \%options);
1939    
1940    Merge a specified set of options into a table of defaults. This method takes two hash references
1941    as input and uses the data from the second to update the first. If the second does not exist,
1942    there will be no effect. An error will be thrown if one of the entries in the second hash does not
1943    exist in the first.
1944    
1945    Consider the following example.
1946    
1947        my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options);
1948    
1949    In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and
1950    B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of
1951    B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and
1952    the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level
1953    will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as
1954    
1955        {databaseType => 'Oracle'}
1956    
1957    an error will occur because the B<databaseType> option does not exist.
1958    
1959    =over 4
1960    
1961    =item defaults
1962    
1963    Table of default option values.
1964    
1965    =item options
1966    
1967    Table of overrides, if any.
1968    
1969    =item RETURN
1970    
1971    Returns a reference to the default table passed in as the first parameter.
1972    
1973    =back
1974    
1975    =cut
1976    
1977    sub GetOptions {
1978        # Get the parameters.
1979        my ($defaults, $options) = @_;
1980        # Check for overrides.
1981        if ($options) {
1982            # Loop through the overrides.
1983            while (my ($option, $setting) = each %{$options}) {
1984                # Insure this override exists.
1985                if (!exists $defaults->{$option}) {
1986                    croak "Unrecognized option $option encountered.";
1987                } else {
1988                    # Apply the override.
1989                    $defaults->{$option} = $setting;
1990                }
1991            }
1992        }
1993        # Return the merged table.
1994        return $defaults;
1995    }
1996    
1997    =head3 MergeOptions
1998    
1999        Tracer::MergeOptions(\%table, \%defaults);
2000    
2001    Merge default values into a hash table. This method looks at the key-value pairs in the
2002    second (default) hash, and if a matching key is not found in the first hash, the default
2003    pair is copied in. The process is similar to L</GetOptions>, but there is no error-
2004    checking and no return value.
2005    
2006    =over 4
2007    
2008    =item table
2009    
2010    Hash table to be updated with the default values.
2011    
2012    =item defaults
2013    
2014    Default values to be merged into the first hash table if they are not already present.
2015    
2016    =back
2017    
2018    =cut
2019    
2020    sub MergeOptions {
2021        # Get the parameters.
2022        my ($table, $defaults) = @_;
2023        # Loop through the defaults.
2024        while (my ($key, $value) = each %{$defaults}) {
2025            if (!exists $table->{$key}) {
2026                $table->{$key} = $value;
2027            }
2028        }
2029    }
2030    
2031    =head3 UnparseOptions
2032    
2033        my $optionString = Tracer::UnparseOptions(\%options);
2034    
2035    Convert an option hash into a command-line string. This will not
2036    necessarily be the same text that came in, but it will nonetheless
2037    produce the same ultimate result when parsed by L</StandardSetup>.
2038    
2039    =over 4
2040    
2041    =item options
2042    
2043    Reference to a hash of options to convert into an option string.
2044    
2045    =item RETURN
2046    
2047    Returns a string that will parse to the same set of options when
2048    parsed by L</StandardSetup>.
2049    
2050    =back
2051    
2052    =cut
2053    
2054    sub UnparseOptions {
2055        # Get the parameters.
2056        my ($options) = @_;
2057        # The option segments will be put in here.
2058        my @retVal = ();
2059        # Loop through the options.
2060        for my $key (keys %$options) {
2061            # Get the option value.
2062            my $value = $options->{$key};
2063            # Only use it if it's nonempty.
2064            if (defined $value && $value ne "") {
2065                my $segment = "--$key=$value";
2066                # Quote it if necessary.
2067                if ($segment =~ /[ |<>*]/) {
2068                    $segment = '"' . $segment . '"';
2069                }
2070                # Add it to the return list.
2071                push @retVal, $segment;
2072            }
2073        }
2074        # Return the result.
2075        return join(" ", @retVal);
2076    }
2077    
2078  =head3 ParseCommand  =head3 ParseCommand
2079    
2080  C<< my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList); >>      my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList);
2081    
2082    Parse a command line consisting of a list of parameters. The initial parameters may be option
2083    specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped
2084    off and merged into a table of default options. The remainder of the command line is
2085    returned as a list of positional arguments. For example, consider the following invocation.
2086    
2087        my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words);
2088    
2089    In this case, the list @words will be treated as a command line and there are two options available,
2090    B<errors> and B<logFile>. If @words has the following format
2091    
2092        -logFile=error.log apple orange rutabaga
2093    
2094    then at the end of the invocation, C<$options> will be
2095    
2096        { errors => 0, logFile => 'error.log' }
2097    
2098    and C<@arguments> will contain
2099    
2100        apple orange rutabaga
2101    
2102    The parser allows for some escape sequences. See L</UnEscape> for a description. There is no
2103    support for quote characters. Options can be specified with single or double hyphens.
2104    
2105    =over 4
2106    
2107    =item optionTable
2108    
2109    Table of default options.
2110    
2111    =item inputList
2112    
2113    List of words on the command line.
2114    
2115    =item RETURN
2116    
2117    Returns a reference to the option table and a list of the positional arguments.
2118    
2119    =back
2120    
2121    =cut
2122    
2123    sub ParseCommand {
2124        # Get the parameters.
2125        my ($optionTable, @inputList) = @_;
2126        # Process any options in the input list.
2127        my %overrides = ();
2128        while ((@inputList > 0) && ($inputList[0] =~ /^--?/)) {
2129            # Get the current option.
2130            my $arg = shift @inputList;
2131            # Pull out the option name.
2132            $arg =~ /^--?([^=]*)/g;
2133            my $name = $1;
2134            # Check for an option value.
2135            if ($arg =~ /\G=(.*)$/g) {
2136                # Here we have a value for the option.
2137                $overrides{$name} = UnEscape($1);
2138            } else {
2139                # Here there is no value, so we use 1.
2140                $overrides{$name} = 1;
2141            }
2142        }
2143        # Merge the options into the defaults.
2144        GetOptions($optionTable, \%overrides);
2145        # Translate the remaining parameters.
2146        my @retVal = ();
2147        for my $inputParm (@inputList) {
2148            push @retVal, UnEscape($inputParm);
2149        }
2150        # Return the results.
2151        return ($optionTable, @retVal);
2152    }
2153    
2154    
2155    =head2 File Utility Methods
2156    
2157    =head3 GetFile
2158    
2159        my @fileContents = Tracer::GetFile($fileName);
2160    
2161        or
2162    
2163        my $fileContents = Tracer::GetFile($fileName);
2164    
2165    Return the entire contents of a file. In list context, line-ends are removed and
2166    each line is a list element. In scalar context, line-ends are replaced by C<\n>.
2167    
2168    =over 4
2169    
2170    =item fileName
2171    
2172    Name of the file to read.
2173    
2174    =item RETURN
2175    
2176    In a list context, returns the entire file as a list with the line terminators removed.
2177    In a scalar context, returns the entire file as a string. If an error occurs opening
2178    the file, an empty list will be returned.
2179    
2180    =back
2181    
2182    =cut
2183    
2184    sub GetFile {
2185        # Get the parameters.
2186        my ($fileName) = @_;
2187        # Declare the return variable.
2188        my @retVal = ();
2189        # Open the file for input.
2190        my $handle = Open(undef, "<$fileName");
2191        # Read the whole file into the return variable, stripping off any terminator
2192        # characters.
2193        my $lineCount = 0;
2194        while (my $line = <$handle>) {
2195            $lineCount++;
2196            $line = Strip($line);
2197            push @retVal, $line;
2198        }
2199        # Close it.
2200        close $handle;
2201        my $actualLines = @retVal;
2202        Trace("$actualLines lines read from file $fileName.") if T(File => 2);
2203        # Return the file's contents in the desired format.
2204        if (wantarray) {
2205            return @retVal;
2206        } else {
2207            return join "\n", @retVal;
2208        }
2209    }
2210    
2211    =head3 PutFile
2212    
2213        Tracer::PutFile($fileName, \@lines);
2214    
2215    Write out a file from a list of lines of text.
2216    
2217    =over 4
2218    
2219    =item fileName
2220    
2221    Name of the output file.
2222    
2223    =item lines
2224    
2225    Reference to a list of text lines. The lines will be written to the file in order, with trailing
2226    new-line characters. Alternatively, may be a string, in which case the string will be written without
2227    modification.
2228    
2229    =back
2230    
2231    =cut
2232    
2233    sub PutFile {
2234        # Get the parameters.
2235        my ($fileName, $lines) = @_;
2236        # Open the output file.
2237        my $handle = Open(undef, ">$fileName");
2238        # Count the lines written.
2239        if (ref $lines ne 'ARRAY') {
2240            # Here we have a scalar, so we write it raw.
2241            print $handle $lines;
2242            Trace("Scalar put to file $fileName.") if T(File => 3);
2243        } else {
2244            # Write the lines one at a time.
2245            my $count = 0;
2246            for my $line (@{$lines}) {
2247                print $handle "$line\n";
2248                $count++;
2249            }
2250            Trace("$count lines put to file $fileName.") if T(File => 3);
2251        }
2252        # Close the output file.
2253        close $handle;
2254    }
2255    
2256    =head3 ParseRecord
2257    
2258        my @fields = Tracer::ParseRecord($line);
2259    
2260    Parse a tab-delimited data line. The data line is split into field values. Embedded tab
2261    and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.
2262    These will automatically be converted.
2263    
2264    =over 4
2265    
2266    =item line
2267    
2268    Line of data containing the tab-delimited fields.
2269    
2270    =item RETURN
2271    
2272    Returns a list of the fields found in the data line.
2273    
2274    =back
2275    
2276    =cut
2277    
2278    sub ParseRecord {
2279        # Get the parameter.
2280        my ($line) = @_;
2281        # Remove the trailing new-line, if any.
2282        chomp $line;
2283        # Split the line read into pieces using the tab character.
2284        my @retVal = split /\t/, $line;
2285        # Trim and fix the escapes in each piece.
2286        for my $value (@retVal) {
2287            # Trim leading whitespace.
2288            $value =~ s/^\s+//;
2289            # Trim trailing whitespace.
2290            $value =~ s/\s+$//;
2291            # Delete the carriage returns.
2292            $value =~ s/\r//g;
2293            # Convert the escapes into their real values.
2294            $value =~ s/\\t/"\t"/ge;
2295            $value =~ s/\\n/"\n"/ge;
2296        }
2297        # Return the result.
2298        return @retVal;
2299    }
2300    
2301    =head3 Merge
2302    
2303        my @mergedList = Tracer::Merge(@inputList);
2304    
2305    Sort a list of strings and remove duplicates.
2306    
2307    =over 4
2308    
2309    =item inputList
2310    
2311    List of scalars to sort and merge.
2312    
2313    =item RETURN
2314    
2315    Returns a list containing the same elements sorted in ascending order with duplicates
2316    removed.
2317    
2318    =back
2319    
2320    =cut
2321    
2322    sub Merge {
2323        # Get the input list in sort order.
2324        my @inputList = sort @_;
2325        # Only proceed if the list has at least two elements.
2326        if (@inputList > 1) {
2327            # Now we want to move through the list splicing out duplicates.
2328            my $i = 0;
2329            while ($i < @inputList) {
2330                # Get the current entry.
2331                my $thisEntry = $inputList[$i];
2332                # Find out how many elements duplicate the current entry.
2333                my $j = $i + 1;
2334                my $dup1 = $i + 1;
2335                while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };
2336                # If the number is nonzero, splice out the duplicates found.
2337                if ($j > $dup1) {
2338                    splice @inputList, $dup1, $j - $dup1;
2339                }
2340                # Now the element at position $dup1 is different from the element before it
2341                # at position $i. We push $i forward one position and start again.
2342                $i++;
2343            }
2344        }
2345        # Return the merged list.
2346        return @inputList;
2347    }
2348    
2349    =head3 Open
2350    
2351        my $handle = Open($fileHandle, $fileSpec, $message);
2352    
2353    Open a file.
2354    
2355    The I<$fileSpec> is essentially the second argument of the PERL C<open>
2356    function. The mode is specified using Unix-like shell information. So, for
2357    example,
2358    
2359        Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2360    
2361    would open for output appended to the specified file, and
2362    
2363        Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");
2364    
2365    would open a pipe that sorts the records written and removes duplicates. Note
2366    the use of file handle syntax in the Open call. To use anonymous file handles,
2367    code as follows.
2368    
2369        my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2370    
2371    The I<$message> parameter is used if the open fails. If it is set to C<0>, then
2372    the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a
2373    failed open will throw an exception and the third parameter will be used to construct
2374    an error message. If the parameter is omitted, a standard message is constructed
2375    using the file spec.
2376    
2377        Could not open "/usr/spool/news/twitlog"
2378    
2379    Note that the mode characters are automatically cleaned from the file name.
2380    The actual error message from the file system will be captured and appended to the
2381    message in any case.
2382    
2383        Could not open "/usr/spool/news/twitlog": file not found.
2384    
2385    In some versions of PERL the only error message we get is a number, which
2386    corresponds to the C++ C<errno> value.
2387    
2388        Could not open "/usr/spool/news/twitlog": 6.
2389    
2390    =over 4
2391    
2392    =item fileHandle
2393    
2394    File handle. If this parameter is C<undef>, a file handle will be generated
2395    and returned as the value of this method.
2396    
2397    =item fileSpec
2398    
2399    File name and mode, as per the PERL C<open> function.
2400    
2401    =item message (optional)
2402    
2403    Error message to use if the open fails. If omitted, a standard error message
2404    will be generated. In either case, the error information from the file system
2405    is appended to the message. To specify a conditional open that does not throw
2406    an error if it fails, use C<0>.
2407    
2408    =item RETURN
2409    
2410    Returns the name of the file handle assigned to the file, or C<undef> if the
2411    open failed.
2412    
2413    =back
2414    
2415    =cut
2416    
2417    sub Open {
2418        # Get the parameters.
2419        my ($fileHandle, $fileSpec, $message) = @_;
2420        # Attempt to open the file.
2421        my $rv = open $fileHandle, $fileSpec;
2422        # If the open failed, generate an error message.
2423        if (! $rv) {
2424            # Save the system error message.
2425            my $sysMessage = $!;
2426            # See if we need a default message.
2427            if (!$message) {
2428                # Clean any obvious mode characters and leading spaces from the
2429                # filename.
2430                my ($fileName) = FindNamePart($fileSpec);
2431                $message = "Could not open \"$fileName\"";
2432            }
2433            # Terminate with an error using the supplied message and the
2434            # error message from the file system.
2435            Confess("$message: $!");
2436        }
2437        # Return the file handle.
2438        return $fileHandle;
2439    }
2440    
2441    =head3 FindNamePart
2442    
2443        my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec);
2444    
2445    Extract the portion of a file specification that contains the file name.
2446    
2447    A file specification is the string passed to an C<open> call. It specifies the file
2448    mode and name. In a truly complex situation, it can specify a pipe sequence. This
2449    method assumes that the file name is whatever follows the first angle bracket
2450    sequence.  So, for example, in the following strings the file name is
2451    C</usr/fig/myfile.txt>.
2452    
2453        >>/usr/fig/myfile.txt
2454        </usr/fig/myfile.txt
2455        | sort -u > /usr/fig/myfile.txt
2456    
2457    If the method cannot find a file name using its normal methods, it will return the
2458    whole incoming string.
2459    
2460    =over 4
2461    
2462    =item fileSpec
2463    
2464    File specification string from which the file name is to be extracted.
2465    
2466    =item RETURN
2467    
2468    Returns a three-element list. The first element contains the file name portion of
2469    the specified string, or the whole string if a file name cannot be found via normal
2470    methods. The second element contains the start position of the file name portion and
2471    the third element contains the length.
2472    
2473    =back
2474    
2475    =cut
2476    #: Return Type $;
2477    sub FindNamePart {
2478        # Get the parameters.
2479        my ($fileSpec) = @_;
2480        # Default to the whole input string.
2481        my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);
2482        # Parse out the file name if we can.
2483        if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {
2484            $retVal = $2;
2485            $len = length $retVal;
2486            $pos = (length $fileSpec) - (length $3) - $len;
2487        }
2488        # Return the result.
2489        return ($retVal, $pos, $len);
2490    }
2491    
2492    =head3 OpenDir
2493    
2494        my @files = OpenDir($dirName, $filtered, $flag);
2495    
2496    Open a directory and return all the file names. This function essentially performs
2497    the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is
2498    set to TRUE, all filenames beginning with a period (C<.>), dollar sign (C<$>),
2499    or pound sign (C<#>) and all filenames ending with a tilde C<~>) will be
2500    filtered out of the return list. If the directory does not open and I<$flag> is not
2501    set, an exception is thrown. So, for example,
2502    
2503        my @files = OpenDir("/Volumes/fig/contigs", 1);
2504    
2505    is effectively the same as
2506    
2507        opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");
2508        my @files = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir(TMP);
2509    
2510    Similarly, the following code
2511    
2512        my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs", 0, 1);
2513    
2514    Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and
2515    automatically returns an empty list if the directory fails to open.
2516    
2517    =over 4
2518    
2519    =item dirName
2520    
2521    Name of the directory to open.
2522    
2523    =item filtered
2524    
2525    TRUE if files whose names begin with a period (C<.>) should be automatically removed
2526    from the list, else FALSE.
2527    
2528    =item flag
2529    
2530    TRUE if a failure to open is okay, else FALSE
2531    
2532    =back
2533    
2534    =cut
2535    #: Return Type @;
2536    sub OpenDir {
2537        # Get the parameters.
2538        my ($dirName, $filtered, $flag) = @_;
2539        # Declare the return variable.
2540        my @retVal = ();
2541        # Open the directory.
2542        if (opendir(my $dirHandle, $dirName)) {
2543            # The directory opened successfully. Get the appropriate list according to the
2544            # strictures of the filter parameter.
2545            if ($filtered) {
2546                @retVal = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir $dirHandle;
2547            } else {
2548                @retVal = readdir $dirHandle;
2549            }
2550            closedir $dirHandle;
2551        } elsif (! $flag) {
2552            # Here the directory would not open and it's considered an error.
2553            Confess("Could not open directory $dirName.");
2554        }
2555        # Return the result.
2556        return @retVal;
2557    }
2558    
2559    
2560    =head3 Insure
2561    
2562        Insure($dirName, $chmod);
2563    
2564    Insure a directory is present.
2565    
2566    =over 4
2567    
2568    =item dirName
2569    
2570    Name of the directory to check. If it does not exist, it will be created.
2571    
2572    =item chmod (optional)
2573    
2574    Security privileges to be given to the directory if it is created.
2575    
2576    =back
2577    
2578    =cut
2579    
2580    sub Insure {
2581        my ($dirName, $chmod) = @_;
2582        if (! -d $dirName) {
2583            Trace("Creating $dirName directory.") if T(2);
2584            eval {
2585                mkpath $dirName;
2586                # If we have permissions specified, set them here.
2587                if (defined($chmod)) {
2588                    chmod $chmod, $dirName;
2589                }
2590            };
2591            if ($@) {
2592                Confess("Error creating $dirName: $@");
2593            }
2594        }
2595    }
2596    
2597    =head3 ChDir
2598    
2599        ChDir($dirName);
2600    
2601    Change to the specified directory.
2602    
2603    =over 4
2604    
2605    =item dirName
2606    
2607    Name of the directory to which we want to change.
2608    
2609    =back
2610    
2611    =cut
2612    
2613    sub ChDir {
2614        my ($dirName) = @_;
2615        if (! -d $dirName) {
2616            Confess("Cannot change to directory $dirName: no such directory.");
2617        } else {
2618            Trace("Changing to directory $dirName.") if T(File => 4);
2619            my $okFlag = chdir $dirName;
2620            if (! $okFlag) {
2621                Confess("Error switching to directory $dirName.");
2622            }
2623        }
2624    }
2625    
2626    =head3 SetPermissions
2627    
2628        Tracer::SetPermissions($dirName, $group, $mask, %otherMasks);
2629    
2630    Set the permissions for a directory and all the files and folders inside it.
2631    In addition, the group ownership will be changed to the specified value.
2632    
2633    This method is more vulnerable than most to permission and compatability
2634    problems, so it does internal error recovery.
2635    
2636    =over 4
2637    
2638    =item dirName
2639    
2640    Name of the directory to process.
2641    
2642    =item group
2643    
2644    Name of the group to be assigned.
2645    
2646    =item mask
2647    
2648    Permission mask. Bits that are C<1> in this mask will be ORed into the
2649    permission bits of any file or directory that does not already have them
2650    set to 1.
2651    
2652    =item otherMasks
2653    
2654    Map of search patterns to permission masks. If a directory name matches
2655    one of the patterns, that directory and all its members and subdirectories
2656    will be assigned the new pattern. For example, the following would
2657    assign 0664 to most files, but would use 0777 for directories named C<tmp>.
2658    
2659        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp$' => 01777);
2660    
2661    The list is ordered, so the following would use 0777 for C<tmp1> and
2662    0666 for C<tmp>, C<tmp2>, or C<tmp3>.
2663    
2664        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp1' => 0777,
2665                                                       '^tmp' => 0666);
2666    
2667    Note that the pattern matches are all case-insensitive, and only directory
2668    names are matched, not file names.
2669    
2670    =back
2671    
2672    =cut
2673    
2674    sub SetPermissions {
2675        # Get the parameters.
2676        my ($dirName, $group, $mask, @otherMasks) = @_;
2677        # Set up for error recovery.
2678        eval {
2679            # Switch to the specified directory.
2680            ChDir($dirName);
2681            # Get the group ID.
2682            my $gid = getgrnam($group);
2683            # Get the mask for tracing.
2684            my $traceMask = sprintf("%04o", $mask) . "($mask)";
2685            Trace("Fixing permissions for directory $dirName using group $group($gid) and mask $traceMask.") if T(File => 2);
2686            my $fixCount = 0;
2687            my $lookCount = 0;
2688            # @dirs will be a stack of directories to be processed.
2689            my @dirs = (getcwd());
2690            while (scalar(@dirs) > 0) {
2691                # Get the current directory.
2692                my $dir = pop @dirs;
2693                # Check for a match to one of the specified directory names. To do
2694                # that, we need to pull the individual part of the name off of the
2695                # whole path.
2696                my $simpleName = $dir;
2697                if ($dir =~ m!/([^/]+)$!) {
2698                    $simpleName = $1;
2699                }
2700                Trace("Simple directory name for $dir is $simpleName.") if T(File => 4);
2701                # Search for a match.
2702                my $match = 0;
2703                my $i;
2704                for ($i = 0; $i < $#otherMasks && ! $match; $i += 2) {
2705                    my $pattern = $otherMasks[$i];
2706                    if ($simpleName =~ /$pattern/i) {
2707                        $match = 1;
2708                    }
2709                }
2710                # Find out if we have a match. Note we use $i-1 because the loop added 2
2711                # before terminating due to the match.
2712                if ($match && $otherMasks[$i-1] != $mask) {
2713                    # This directory matches one of the incoming patterns, and it's
2714                    # a different mask, so we process it recursively with that mask.
2715                    SetPermissions($dir, $group, $otherMasks[$i-1], @otherMasks);
2716                } else {
2717                    # Here we can process normally. Get all of the non-hidden members.
2718                    my @submems = OpenDir($dir, 1);
2719                    for my $submem (@submems) {
2720                        # Get the full name.
2721                        my $thisMem = "$dir/$submem";
2722                        Trace("Checking member $thisMem.") if T(4);
2723                        $lookCount++;
2724                        if ($lookCount % 1000 == 0) {
2725                            Trace("$lookCount members examined. Current is $thisMem. Mask is $traceMask") if T(File => 3);
2726                        }
2727                        # Fix the group.
2728                        chown -1, $gid, $thisMem;
2729                        # Insure this member is not a symlink.
2730                        if (! -l $thisMem) {
2731                            # Get its info.
2732                            my $fileInfo = stat $thisMem;
2733                            # Only proceed if we got the info. Otherwise, it's a hard link
2734                            # and we want to skip it anyway.
2735                            if ($fileInfo) {
2736                                my $fileMode = $fileInfo->mode;
2737                                if (($fileMode & $mask) != $mask) {
2738                                    # Fix this member.
2739                                    $fileMode |= $mask;
2740                                    chmod $fileMode, $thisMem;
2741                                    $fixCount++;
2742                                }
2743                                # If it's a subdirectory, stack it.
2744                                if (-d $thisMem) {
2745                                    push @dirs, $thisMem;
2746                                }
2747                            }
2748                        }
2749                    }
2750                }
2751            }
2752            Trace("$lookCount files and directories processed, $fixCount fixed.") if T(File => 2);
2753        };
2754        # Check for an error.
2755        if ($@) {
2756            Confess("SetPermissions error: $@");
2757        }
2758    }
2759    
2760    =head3 GetLine
2761    
2762        my @data = Tracer::GetLine($handle);
2763    
2764    Read a line of data from a tab-delimited file.
2765    
2766    =over 4
2767    
2768    =item handle
2769    
2770    Open file handle from which to read.
2771    
2772    =item RETURN
2773    
2774    Returns a list of the fields in the record read. The fields are presumed to be
2775    tab-delimited. If we are at the end of the file, then an empty list will be
2776    returned. If an empty line is read, a single list item consisting of a null
2777    string will be returned.
2778    
2779    =back
2780    
2781    =cut
2782    
2783    sub GetLine {
2784        # Get the parameters.
2785        my ($handle) = @_;
2786        # Declare the return variable.
2787        my @retVal = ();
2788        Trace("File position is " . tell($handle) . ". EOF flag is " . eof($handle) . ".") if T(File => 4);
2789        # Read from the file.
2790        my $line = <$handle>;
2791        # Only proceed if we found something.
2792        if (defined $line) {
2793            # Remove the new-line. We are a bit over-cautious here because the file may be coming in via an
2794            # upload control and have a nonstandard EOL combination.
2795            $line =~ s/(\r|\n)+$//;
2796            # Here we do some fancy tracing to help in debugging complicated EOL marks.
2797            if (T(File => 4)) {
2798                my $escapedLine = $line;
2799                $escapedLine =~ s/\n/\\n/g;
2800                $escapedLine =~ s/\r/\\r/g;
2801                $escapedLine =~ s/\t/\\t/g;
2802                Trace("Line read: -->$escapedLine<--");
2803            }
2804            # If the line is empty, return a single empty string; otherwise, parse
2805            # it into fields.
2806            if ($line eq "") {
2807                push @retVal, "";
2808            } else {
2809                push @retVal, split /\t/,$line;
2810            }
2811        } else {
2812            # Trace the reason the read failed.
2813            Trace("End of file: $!") if T(File => 3);
2814        }
2815        # Return the result.
2816        return @retVal;
2817    }
2818    
2819    =head3 PutLine
2820    
2821        Tracer::PutLine($handle, \@fields, $eol);
2822    
2823    Write a line of data to a tab-delimited file. The specified field values will be
2824    output in tab-separated form, with a trailing new-line.
2825    
2826    =over 4
2827    
2828    =item handle
2829    
2830    Output file handle.
2831    
2832    =item fields
2833    
2834    List of field values.
2835    
2836    =item eol (optional)
2837    
2838    End-of-line character (default is "\n").
2839    
2840    =back
2841    
2842    =cut
2843    
2844    sub PutLine {
2845        # Get the parameters.
2846        my ($handle, $fields, $eol) = @_;
2847        # Write the data.
2848        print $handle join("\t", @{$fields}) . ($eol || "\n");
2849    }
2850    
2851    
2852    =head3 PrintLine
2853    
2854        Tracer::PrintLine($line);
2855    
2856    Print a line of text with a trailing new-line.
2857    
2858    =over 4
2859    
2860    =item line
2861    
2862    Line of text to print.
2863    
2864    =back
2865    
2866    =cut
2867    
2868    sub PrintLine {
2869        # Get the parameters.
2870        my ($line) = @_;
2871        # Print the line.
2872        print "$line\n";
2873    }
2874    
2875    
2876    =head2 Other Useful Methods
2877    
2878    =head3 IDHASH
2879    
2880        my $hash = SHTargetSearch::IDHASH(@keys);
2881    
2882    This is a dinky little method that converts a list of values to a reference
2883    to hash of values to labels. The values and labels are the same.
2884    
2885    =cut
2886    
2887    sub IDHASH {
2888        my %retVal = map { $_ => $_ } @_;
2889        return \%retVal;
2890    }
2891    
2892    =head3 Pluralize
2893    
2894        my $plural = Tracer::Pluralize($word);
2895    
2896    This is a very simple pluralization utility. It adds an C<s> at the end
2897    of the input word unless it already ends in an C<s>, in which case it
2898    adds C<es>.
2899    
2900    =over 4
2901    
2902    =item word
2903    
2904    Singular word to pluralize.
2905    
2906    =item RETURN
2907    
2908    Returns the probable plural form of the word.
2909    
2910    =back
2911    
2912    =cut
2913    
2914  Parse a command line consisting of a list of parameters. The initial parameters may be option  sub Pluralize {
2915  specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped      # Get the parameters.
2916  off and merged into a table of default options. The remainder of the command line is      my ($word) = @_;
2917  returned as a list of positional arguments. For example, consider the following invocation.      # Declare the return variable.
2918        my $retVal;
2919        if ($word =~ /s$/) {
2920            $retVal = $word . 'es';
2921        } else {
2922            $retVal = $word . 's';
2923        }
2924        # Return the result.
2925        return $retVal;
2926    }
2927    
2928    =head3 Numeric
2929    
2930        my $okFlag = Tracer::Numeric($string);
2931    
2932    Return the value of the specified string if it is numeric, or an undefined value
2933    if it is not numeric.
2934    
2935    =over 4
2936    
2937    =item string
2938    
2939    String to check.
2940    
2941    =item RETURN
2942    
2943    Returns the numeric value of the string if successful, or C<undef> if the string
2944    is not numeric.
2945    
2946    =back
2947    
2948    =cut
2949    
2950    sub Numeric {
2951        # Get the parameters.
2952        my ($string) = @_;
2953        # We'll put the value in here if we succeed.
2954        my $retVal;
2955        # Get a working copy of the string.
2956        my $copy = $string;
2957        # Trim leading and trailing spaces.
2958        $copy =~ s/^\s+//;
2959        $copy =~ s/\s+$//;
2960        # Check the result.
2961        if ($copy =~ /^[+-]?\d+$/) {
2962            $retVal = $copy;
2963        } elsif ($copy =~ /^([+-]\d+|\d*)[eE][+-]?\d+$/) {
2964            $retVal = $copy;
2965        } elsif ($copy =~ /^([+-]\d+|\d*)\.\d*([eE][+-]?\d+)?$/) {
2966            $retVal = $copy;
2967        }
2968        # Return the result.
2969        return $retVal;
2970    }
2971    
2972    
2973    =head3 ParseParm
2974    
2975        my $listValue = Tracer::ParseParm($string);
2976    
2977    Convert a parameter into a list reference. If the parameter is undefined,
2978    an undefined value will be returned. Otherwise, it will be parsed as a
2979    comma-separated list of values.
2980    
2981    =over 4
2982    
2983    =item string
2984    
2985    Incoming string.
2986    
2987    =item RETURN
2988    
2989    Returns a reference to a list of values, or C<undef> if the incoming value
2990    was undefined.
2991    
2992    =back
2993    
2994    =cut
2995    
2996    sub ParseParm {
2997        # Get the parameters.
2998        my ($string) = @_;
2999        # Declare the return variable.
3000        my $retVal;
3001        # Check for data.
3002        if (defined $string) {
3003            # We have some, so split it into a list.
3004            $retVal = [ split /\s*,\s*/, $string];
3005        }
3006        # Return the result.
3007        return $retVal;
3008    }
3009    
3010    =head3 Now
3011    
3012        my $string = Tracer::Now();
3013    
3014    Return a displayable time stamp containing the local time. Whatever format this
3015    method produces must be parseable by L</ParseDate>.
3016    
3017    =cut
3018    
3019    sub Now {
3020        return DisplayTime(time);
3021    }
3022    
3023    =head3 DisplayTime
3024    
3025        my $string = Tracer::DisplayTime($time);
3026    
3027    Convert a time value to a displayable time stamp. Whatever format this
3028    method produces must be parseable by L</ParseDate>.
3029    
3030    =over 4
3031    
3032    =item time
3033    
3034    Time to display, in seconds since the epoch, or C<undef> if the time is unknown.
3035    
3036    =item RETURN
3037    
3038    Returns a displayable time, or C<(n/a)> if the incoming time is undefined.
3039    
3040    =back
3041    
3042    =cut
3043    
3044    sub DisplayTime {
3045        my ($time) = @_;
3046        my $retVal = "(n/a)";
3047        if (defined $time) {
3048            my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($time);
3049            $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .
3050                      _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);
3051        }
3052        return $retVal;
3053    }
3054    
3055    # Pad a number to 2 digits.
3056    sub _p2 {
3057        my ($value) = @_;
3058        $value = "0$value" if ($value < 10);
3059        return $value;
3060    }
3061    
3062    =head3 Escape
3063    
3064        my $codedString = Tracer::Escape($realString);
3065    
3066    Escape a string for use in a command. Tabs will be replaced by C<\t>, new-lines
3067    replaced by C<\n>, carriage returns will be deleted, and backslashes will be doubled. The
3068    result is to reverse the effect of L</UnEscape>.
3069    
3070    =over 4
3071    
3072    =item realString
3073    
3074    String to escape.
3075    
3076    =item RETURN
3077    
3078    Escaped equivalent of the real string.
3079    
3080    =back
3081    
3082    =cut
3083    
3084    sub Escape {
3085        # Get the parameter.
3086        my ($realString) = @_;
3087        # Initialize the return variable.
3088        my $retVal = "";
3089        # Loop through the parameter string, looking for sequences to escape.
3090        while (length $realString > 0) {
3091            # Look for the first sequence to escape.
3092            if ($realString =~ /^(.*?)([\n\t\r\\])/) {
3093                # Here we found it. The text preceding the sequence is in $1. The sequence
3094                # itself is in $2. First, move the clear text to the return variable.
3095                $retVal .= $1;
3096                # Strip the processed section off the real string.
3097                $realString = substr $realString, (length $2) + (length $1);
3098                # Get the matched character.
3099                my $char = $2;
3100                # If we have a CR, we are done.
3101                if ($char ne "\r") {
3102                    # It's not a CR, so encode the escape sequence.
3103                    $char =~ tr/\t\n/tn/;
3104                    $retVal .= "\\" . $char;
3105                }
3106            } else {
3107                # Here there are no more escape sequences. The rest of the string is
3108                # transferred unmodified.
3109                $retVal .= $realString;
3110                $realString = "";
3111            }
3112        }
3113        # Return the result.
3114        return $retVal;
3115    }
3116    
3117    =head3 UnEscape
3118    
3119        my $realString = Tracer::UnEscape($codedString);
3120    
3121    Replace escape sequences with their actual equivalents. C<\t> will be replaced by
3122    a tab, C<\n> by a new-line character, and C<\\> by a backslash. C<\r> codes will
3123    be deleted.
3124    
3125    =over 4
3126    
3127    =item codedString
3128    
3129    String to un-escape.
3130    
3131    =item RETURN
3132    
3133    Returns a copy of the original string with the escape sequences converted to their actual
3134    values.
3135    
3136    =back
3137    
3138    =cut
3139    
3140    sub UnEscape {
3141        # Get the parameter.
3142        my ($codedString) = @_;
3143        # Initialize the return variable.
3144        my $retVal = "";
3145        # Only proceed if the incoming string is nonempty.
3146        if (defined $codedString) {
3147            # Loop through the parameter string, looking for escape sequences. We can't do
3148            # translating because it causes problems with the escaped slash. ("\\t" becomes
3149            # "\<tab>" no matter what we do.)
3150            while (length $codedString > 0) {
3151                # Look for the first escape sequence.
3152                if ($codedString =~ /^(.*?)\\(\\|n|t|r)/) {
3153                    # Here we found it. The text preceding the sequence is in $1. The sequence
3154                    # itself is in $2. First, move the clear text to the return variable.
3155                    $retVal .= $1;
3156                    $codedString = substr $codedString, (2 + length $1);
3157                    # Get the escape value.
3158                    my $char = $2;
3159                    # If we have a "\r", we are done.
3160                    if ($char ne 'r') {
3161                        # Here it's not an 'r', so we convert it.
3162                        $char =~ tr/\\tn/\\\t\n/;
3163                        $retVal .= $char;
3164                    }
3165                } else {
3166                    # Here there are no more escape sequences. The rest of the string is
3167                    # transferred unmodified.
3168                    $retVal .= $codedString;
3169                    $codedString = "";
3170                }
3171            }
3172        }
3173        # Return the result.
3174        return $retVal;
3175    }
3176    
3177    =head3 Percent
3178    
3179        my $percent = Tracer::Percent($number, $base);
3180    
3181    Returns the percent of the base represented by the given number. If the base
3182    is zero, returns zero.
3183    
3184    =over 4
3185    
3186    =item number
3187    
3188    Percent numerator.
3189    
3190    =item base
3191    
3192    Percent base.
3193    
3194    =item RETURN
3195    
3196    Returns the percentage of the base represented by the numerator.
3197    
3198    =back
3199    
3200    =cut
3201    
3202    sub Percent {
3203        # Get the parameters.
3204        my ($number, $base) = @_;
3205        # Declare the return variable.
3206        my $retVal = 0;
3207        # Compute the percent.
3208        if ($base != 0) {
3209            $retVal = $number * 100 / $base;
3210        }
3211        # Return the result.
3212        return $retVal;
3213    }
3214    
3215    =head3 In
3216    
3217        my $flag = Tracer::In($value, $min, $max);
3218    
3219    Return TRUE if the value is between the minimum and the maximum, else FALSE.
3220    
3221    =cut
3222    
3223    sub In {
3224        return ($_[0] <= $_[2] && $_[0] >= $_[1]);
3225    }
3226    
3227    
3228    =head3 Constrain
3229    
3230        my $constrained = Constrain($value, $min, $max);
3231    
3232    Modify a numeric value to bring it to a point in between a maximum and a minimum.
3233    
3234    =over 4
3235    
3236    =item value
3237    
3238    Value to constrain.
3239    
3240    =item min (optional)
3241    
3242    Minimum permissible value. If this parameter is undefined, no minimum constraint will be applied.
3243    
3244    =item max (optional)
3245    
3246    Maximum permissible value. If this parameter is undefined, no maximum constraint will be applied.
3247    
3248    =item RETURN
3249    
3250    Returns the incoming value, constrained according to the other parameters.
3251    
3252    =back
3253    
3254    =cut
3255    
3256    sub Constrain {
3257        # Get the parameters.
3258        my ($value, $min, $max) = @_;
3259        # Declare the return variable.
3260        my $retVal = $value;
3261        # Apply the minimum constraint.
3262        if (defined $min && $retVal < $min) {
3263            $retVal = $min;
3264        }
3265        # Apply the maximum constraint.
3266        if (defined $max && $retVal > $max) {
3267            $retVal = $max;
3268        }
3269        # Return the result.
3270        return $retVal;
3271    }
3272    
3273    =head3 Min
3274    
3275        my $min = Min($value1, $value2, ... $valueN);
3276    
3277    Return the minimum argument. The arguments are treated as numbers.
3278    
3279    =over 4
3280    
3281    =item $value1, $value2, ... $valueN
3282    
3283    List of numbers to compare.
3284    
3285  C<< my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words); >>  =item RETURN
3286    
3287  In this case, the list @words will be treated as a command line. There are two options available,  Returns the lowest number in the list.
 B<errors> and B<logFile>. If @words has the following format  
3288    
3289  C<< -logFile=error.log apple orange rutabaga >>  =back
3290    
3291  then at the end of the invocation, C<$options> will be  =cut
3292    
3293  C<< { errors => 0, logFile => 'error.log' } >>  sub Min {
3294        # Get the parameters. Note that we prime the return value with the first parameter.
3295        my ($retVal, @values) = @_;
3296        # Loop through the remaining parameters, looking for the lowest.
3297        for my $value (@values) {
3298            if ($value < $retVal) {
3299                $retVal = $value;
3300            }
3301        }
3302        # Return the minimum found.
3303        return $retVal;
3304    }
3305    
3306  and C<@arguments> will contain  =head3 Max
3307    
3308  C<< apple orange rutabaga >>      my $max = Max($value1, $value2, ... $valueN);
3309    
3310  The parser allows for some escape sequences. See L</UnEscape> for a description. There is no  Return the maximum argument. The arguments are treated as numbers.
 support for quote characters.  
3311    
3312  =over 4  =over 4
3313    
3314  =item optionTable  =item $value1, $value2, ... $valueN
   
 Table of default options.  
   
 =item inputList  
3315    
3316  List of words on the command line.  List of numbers to compare.
3317    
3318  =item RETURN  =item RETURN
3319    
3320  Returns a reference to the option table and a list of the positional arguments.  Returns the highest number in the list.
3321    
3322  =back  =back
3323    
3324  =cut  =cut
3325    
3326  sub ParseCommand {  sub Max {
3327          # Get the parameters.      # Get the parameters. Note that we prime the return value with the first parameter.
3328          my ($optionTable, @inputList) = @_;      my ($retVal, @values) = @_;
3329          # Process any options in the input list.      # Loop through the remaining parameters, looking for the highest.
3330          my %overrides = ();      for my $value (@values) {
3331          while ((@inputList > 0) && ($inputList[0] =~ /^-/)) {          if ($value > $retVal) {
3332                  # Get the current option.              $retVal = $value;
                 my $arg = shift @inputList;  
                 # Pull out the option name.  
                 $arg =~ /^-([^=]*)/g;  
                 my $name = $1;  
                 # Check for an option value.  
                 if ($arg =~ /\G=(.*)$/g) {  
                         # Here we have a value for the option.  
                         $overrides{$name} = UnEscape($1);  
                 } else {  
                         # Here there is no value, so we use 1.  
                         $overrides{$name} = 1;  
                 }  
3333          }          }
         # Merge the options into the defaults.  
         GetOptions($optionTable, \%overrides);  
         # Translate the remaining parameters.  
         my @retVal = ();  
         for my $inputParm (@inputList) {  
                 push @retVal, UnEscape($inputParm);  
3334          }          }
3335          # Return the results.      # Return the maximum found.
3336          return ($optionTable, @retVal);      return $retVal;
3337  }  }
3338    
3339  =head3 Escape  =head3 Strip
3340    
3341  C<< my $codedString = Tracer::Escape($realString); >>      my $string = Tracer::Strip($line);
3342    
3343  Escape a string for use in a command length. Spaces will be replaced by C<\b>,  Strip all line terminators off a string. This is necessary when dealing with files
3344  tabs replaced by C<\t>, new-lines replaced by C<\n>, and backslashes will be  that may have been transferred back and forth several times among different
3345  doubled. The effect is to exactly reverse the effect of L</UnEscape>.  operating environments.
3346    
3347  =over 4  =over 4
3348    
3349  =item realString  =item line
3350    
3351  String to escape.  Line of text to be stripped.
3352    
3353  =item RETURN  =item RETURN
3354    
3355  Escaped equivalent of the real string.  The same line of text with all the line-ending characters chopped from the end.
3356    
3357  =back  =back
3358    
3359  =cut  =cut
3360    
3361  sub Escape {  sub Strip {
3362          # Get the parameter.      # Get a copy of the parameter string.
3363          my ($realString) = @_;      my ($string) = @_;
3364          # Initialize the return variable.      my $retVal = (defined $string ? $string : "");
3365          my $retVal = "";      # Strip the line terminator characters.
3366          # Loop through the parameter string, looking for sequences to escape.      $retVal =~ s/(\r|\n)+$//g;
3367          while (length $realString > 0) {      # Return the result.
3368                  # Look for the first sequence to escape.      return $retVal;
                 if ($realString =~ /^(.*?)([ \n\t\\])/) {  
                         # Here we found it. The text preceding the sequence is in $1. The sequence  
                         # itself is in $2. First, move the clear text to the return variable.  
                         $retVal .= $1;  
                         $realString = substr $realString, (length $2 + length $1);  
                         # Encode the escape sequence.  
                         my $char = $2;  
                         $char =~ tr/ \t\n/btn/;  
                         $retVal .= "\\" . $char;  
                 } else {  
                         # Here there are no more escape sequences. The rest of the string is  
                         # transferred unmodified.  
                         $retVal .= $realString;  
                         $realString = "";  
                 }  
3369          }          }
3370    
3371    =head3 Trim
3372    
3373        my $string = Tracer::Trim($line);
3374    
3375    Trim all spaces from the beginning and ending of a string.
3376    
3377    =over 4
3378    
3379    =item line
3380    
3381    Line of text to be trimmed.
3382    
3383    =item RETURN
3384    
3385    The same line of text with all whitespace chopped off either end.
3386    
3387    =back
3388    
3389    =cut
3390    
3391    sub Trim {
3392        # Get a copy of the parameter string.
3393        my ($string) = @_;
3394        my $retVal = (defined $string ? $string : "");
3395        # Strip the front spaces.
3396        $retVal =~ s/^\s+//;
3397        # Strip the back spaces.
3398        $retVal =~ s/\s+$//;
3399          # Return the result.          # Return the result.
3400          return $retVal;          return $retVal;
3401  }  }
3402    
3403  =head3 UnEscape  =head3 Pad
3404    
3405  C<< my $realString = Tracer::UnEscape($codedString); >>      my $paddedString = Tracer::Pad($string, $len, $left, $padChar);
3406    
3407  Replace escape sequences with their actual equivalents. C<\b> will be replaced by a space,  Pad a string to a specified length. The pad character will be a
3408  C<\t> by a tab, C<\n> by a new-line character, and C<\\> by a back-slash.  space, and the padding will be on the right side unless specified
3409    in the third parameter.
3410    
3411  =over 4  =over 4
3412    
3413  =item codedString  =item string
3414    
3415  String to un-escape.  String to be padded.
3416    
3417    =item len
3418    
3419    Desired length of the padded string.
3420    
3421    =item left (optional)
3422    
3423    TRUE if the string is to be left-padded; otherwise it will be padded on the right.
3424    
3425    =item padChar (optional)
3426    
3427    Character to use for padding. The default is a space.
3428    
3429  =item RETURN  =item RETURN
3430    
3431  Returns a copy of the original string with the escape sequences converted to their actual  Returns a copy of the original string with the pad character added to the
3432  values.  specified end so that it achieves the desired length.
3433    
3434  =back  =back
3435    
3436  =cut  =cut
3437    
3438  sub UnEscape {  sub Pad {
3439          # Get the parameter.      # Get the parameters.
3440          my ($codedString) = @_;      my ($string, $len, $left, $padChar) = @_;
3441          # Initialize the return variable.      # Compute the padding character.
3442          my $retVal = "";      if (! defined $padChar) {
3443          # Only proceed if the incoming string is nonempty.          $padChar = " ";
         if (defined $codedString) {  
                 # Loop through the parameter string, looking for escape sequences. We can't do  
                 # translating because it causes problems with the escaped slash. ("\\b" becomes  
                 # "\ " no matter what we do.)  
                 while (length $codedString > 0) {  
                         # Look for the first escape sequence.  
                         if ($codedString =~ /^(.*?)\\(\\|b|n|t)/) {  
                                 # Here we found it. The text preceding the sequence is in $1. The sequence  
                                 # itself is in $2. First, move the clear text to the return variable.  
                                 $retVal .= $1;  
                                 $codedString = substr $codedString, (2 + length $1);  
                                 # Decode the escape sequence.  
                                 my $char = $2;  
                                 $char =~ tr/\\btn/\\ \t\n/;  
                                 $retVal .= $char;  
                         } else {  
                                 # Here there are no more escape sequences. The rest of the string is  
                                 # transferred unmodified.  
                                 $retVal .= $codedString;  
                                 $codedString = "";  
3444                          }                          }
3445        # Compute the number of spaces needed.
3446        my $needed = $len - length $string;
3447        # Copy the string into the return variable.
3448        my $retVal = $string;
3449        # Only proceed if padding is needed.
3450        if ($needed > 0) {
3451            # Create the pad string.
3452            my $pad = $padChar x $needed;
3453            # Affix it to the return value.
3454            if ($left) {
3455                $retVal = $pad . $retVal;
3456            } else {
3457                $retVal .= $pad;
3458                  }                  }
3459          }          }
3460          # Return the result.          # Return the result.
3461          return $retVal;          return $retVal;
3462  }  }
3463    
3464  =head3 ParseRecord  =head3 EOF
3465    
3466  C<< my @fields = Tracer::ParseRecord($line); >>  This is a constant that is lexically greater than any useful string.
3467    
3468  Parse a tab-delimited data line. The data line is split into field values. Embedded tab  =cut
3469  and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.  
3470  These will automatically be converted.  sub EOF {
3471        return "\xFF\xFF\xFF\xFF\xFF";
3472    }
3473    
3474    =head3 TICK
3475    
3476        my @results = TICK($commandString);
3477    
3478    Perform a back-tick operation on a command. If this is a Windows environment, any leading
3479    dot-slash (C<./> will be removed. So, for example, if you were doing
3480    
3481        `./protein.cgi`
3482    
3483    from inside a CGI script, it would work fine in Unix, but would issue an error message
3484    in Windows complaining that C<'.'> is not a valid command. If instead you code
3485    
3486        TICK("./protein.cgi")
3487    
3488    it will work correctly in both environments.
3489    
3490  =over 4  =over 4
3491    
3492  =item line  =item commandString
3493    
3494  Line of data containing the tab-delimited fields.  The command string to pass to the system.
3495    
3496  =item RETURN  =item RETURN
3497    
3498  Returns a list of the fields found in the data line.  Returns the standard output from the specified command, as a list.
3499    
3500  =back  =back
3501    
3502  =cut  =cut
3503    #: Return Type @;
3504  sub ParseRecord {  sub TICK {
3505          # Get the parameter.      # Get the parameters.
3506          my ($line) = @_;      my ($commandString) = @_;
3507          # Remove the trailing new-line, if any.      # Chop off the dot-slash if this is Windows.
3508          chomp $line;      if ($FIG_Config::win_mode) {
3509          # Split the line read into pieces using the tab character.          $commandString =~ s!^\./!!;
         my @retVal = split /\t/, $line;  
         # Trim and fix the escapes in each piece.  
         for my $value (@retVal) {  
                 # Trim leading whitespace.  
                 $value =~ s/^\s+//;  
                 # Trim trailing whitespace.  
                 $value =~ s/\s+$//;  
                 # Delete the carriage returns.  
                 $value =~ s/\r//g;  
                 # Convert the escapes into their real values.  
                 $value =~ s/\\t/"\t"/ge;  
                 $value =~ s/\\n/"\n"/ge;  
3510          }          }
3511          # Return the result.      # Activate the command and return the result.
3512          return @retVal;      return `$commandString`;
3513  }  }
3514    
 =head3 Merge  
3515    
3516  C<< my @mergedList = Tracer::Merge(@inputList); >>  =head3 CommaFormat
3517    
3518  Sort a list of strings and remove duplicates.      my $formatted = Tracer::CommaFormat($number);
3519    
3520    Insert commas into a number.
3521    
3522  =over 4  =over 4
3523    
3524  =item inputList  =item number
3525    
3526  List of scalars to sort and merge.  A sequence of digits.
3527    
3528  =item RETURN  =item RETURN
3529    
3530  Returns a list containing the same elements sorted in ascending order with duplicates  Returns the same digits with commas strategically inserted.
 removed.  
3531    
3532  =back  =back
3533    
3534  =cut  =cut
3535    
3536  sub Merge {  sub CommaFormat {
3537          # Get the input list in sort order.      # Get the parameters.
3538          my @inputList = sort @_;      my ($number) = @_;
3539          # Only proceed if the list has at least two elements.      # Pad the length up to a multiple of three.
3540          if (@inputList > 1) {      my $padded = "$number";
3541                  # Now we want to move through the list splicing out duplicates.      $padded = " " . $padded while length($padded) % 3 != 0;
3542                  my $i = 0;      # This is a fancy PERL trick. The parentheses in the SPLIT pattern
3543                  while ($i < @inputList) {      # cause the delimiters to be included in the output stream. The
3544                          # Get the current entry.      # GREP removes the empty strings in between the delimiters.
3545                          my $thisEntry = $inputList[$i];      my $retVal = join(",", grep { $_ ne '' } split(/(...)/, $padded));
3546                          # Find out how many elements duplicate the current entry.      # Clean out the spaces.
3547                          my $j = $i + 1;      $retVal =~ s/ //g;
3548                          my $dup1 = $i + 1;      # Return the result.
3549                          while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };      return $retVal;
                         # If the number is nonzero, splice out the duplicates found.  
                         if ($j > $dup1) {  
                                 splice @inputList, $dup1, $j - $dup1;  
                         }  
                         # Now the element at position $dup1 is different from the element before it  
                         # at position $i. We push $i forward one position and start again.  
                         $i++;  
                 }  
         }  
         # Return the merged list.  
         return @inputList;  
3550  }  }
3551    
 =head3 GetFile  
3552    
3553  C<< my @fileContents = Tracer::GetFile($fileName); >>  =head3 GetMemorySize
3554    
3555        my $string = Tracer::GetMemorySize();
3556    
3557    Return a memory size string for the current process. The string will be
3558    in comma format, with a size indicator (K, M, G) at the end.
3559    
3560  Return the entire contents of a file.  =cut
3561    
3562    sub GetMemorySize {
3563        # Get the memory size from Unix.
3564        my ($retVal) = `ps h -o vsz $$`;
3565        # Remove the ending new-line.
3566        chomp $retVal;
3567        # Format and return the result.
3568        return CommaFormat($retVal) . "K";
3569    }
3570    
3571    =head3 CompareLists
3572    
3573        my ($inserted, $deleted) = Tracer::CompareLists(\@newList, \@oldList, $keyIndex);
3574    
3575    Compare two lists of tuples, and return a hash analyzing the differences. The lists
3576    are presumed to be sorted alphabetically by the value in the $keyIndex column.
3577    The return value contains a list of items that are only in the new list
3578    (inserted) and only in the old list (deleted).
3579    
3580  =over 4  =over 4
3581    
3582  =item fileName  =item newList
3583    
3584  Name of the file to read.  Reference to a list of new tuples.
3585    
3586    =item oldList
3587    
3588    Reference to a list of old tuples.
3589    
3590    =item keyIndex (optional)
3591    
3592    Index into each tuple of its key field. The default is 0.
3593    
3594  =item RETURN  =item RETURN
3595    
3596  In a list context, returns the entire file as a list with the line terminators removed.  Returns a 2-tuple consisting of a reference to the list of items that are only in the new
3597  In a scalar context, returns the entire file as a string.  list (inserted) followed by a reference to the list of items that are only in the old
3598    list (deleted).
3599    
3600  =back  =back
3601    
3602  =cut  =cut
3603    
3604  sub GetFile {  sub CompareLists {
3605          # Get the parameters.          # Get the parameters.
3606          my ($fileName) = @_;      my ($newList, $oldList, $keyIndex) = @_;
3607          # Declare the return variable.      if (! defined $keyIndex) {
3608          my @retVal = ();          $keyIndex = 0;
3609          # Open the file for input.      }
3610          my $ok = open INPUTFILE, "<$fileName";      # Declare the return variables.
3611          if (!$ok) {      my ($inserted, $deleted) = ([], []);
3612                  # If we had an error, trace it. We will automatically return a null value.      # Loop through the two lists simultaneously.
3613                  Trace("Could not open \"$fileName\" for input.") if T(0);      my ($newI, $oldI) = (0, 0);
3614        my ($newN, $oldN) = (scalar @{$newList}, scalar @{$oldList});
3615        while ($newI < $newN || $oldI < $oldN) {
3616            # Get the current object in each list. Note that if one
3617            # of the lists is past the end, we'll get undef.
3618            my $newItem = $newList->[$newI];
3619            my $oldItem = $oldList->[$oldI];
3620            if (! defined($newItem) || defined($oldItem) && $newItem->[$keyIndex] gt $oldItem->[$keyIndex]) {
3621                # The old item is not in the new list, so mark it deleted.
3622                push @{$deleted}, $oldItem;
3623                $oldI++;
3624            } elsif (! defined($oldItem) || $oldItem->[$keyIndex] gt $newItem->[$keyIndex]) {
3625                # The new item is not in the old list, so mark it inserted.
3626                push @{$inserted}, $newItem;
3627                $newI++;
3628          } else {          } else {
3629                  # Read the whole file into the return variable, stripping off any terminator              # The item is in both lists, so push forward.
3630          # characters.              $oldI++;
3631          my $lineCount = 0;              $newI++;
                 while (my $line = <INPUTFILE>) {  
             $lineCount++;  
             $line = Strip($line);  
                         push @retVal, $line;  
3632                  }                  }
                 # Close it.  
                 close INPUTFILE;  
         my $actualLines = @retVal;  
         Trace("$lineCount lines read from $fileName. $actualLines processed.") if T(3);  
         }  
         # Return the file's contents in the desired format.  
     if (wantarray) {  
             return @retVal;  
     } else {  
         return join "\n", @retVal;  
3633      }      }
3634        # Return the result.
3635        return ($inserted, $deleted);
3636  }  }
3637    
3638  =head3 QTrace  =head3 Cmp
3639    
3640  C<< my $data = QTrace($format); >>      my $cmp = Tracer::Cmp($a, $b);
3641    
3642  Return the queued trace data in the specified format.  This method performs a universal sort comparison. Each value coming in is
3643    separated into a leading text part and a trailing number part. The text
3644    part is string compared, and if both parts are equal, then the number
3645    parts are compared numerically. A stream of just numbers or a stream of
3646    just strings will sort correctly, and a mixed stream will sort with the
3647    numbers first. Strings with a label and a number will sort in the
3648    expected manner instead of lexically.
3649    
3650  =over 4  =over 4
3651    
3652  =item format  =item a
3653    
3654  C<html> to format the data as an HTML list, C<text> to format it as straight text.  First item to compare.
3655    
3656    =item b
3657    
3658    Second item to compare.
3659    
3660    =item RETURN
3661    
3662    Returns a negative number if the first item should sort first (is less), a positive
3663    number if the first item should sort second (is greater), and a zero if the items are
3664    equal.
3665    
3666  =back  =back
3667    
3668  =cut  =cut
3669    
3670  sub QTrace {  sub Cmp {
3671          # Get the parameter.      # Get the parameters.
3672          my ($format) = @_;      my ($a, $b) = @_;
3673          # Create the return variable.      # Declare the return value.