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

Diff of /FigKernelPackages/Tracer.pm

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

revision 1.6, Mon Mar 7 02:01:51 2005 UTC revision 1.105, Wed May 14 09:09:25 2008 UTC
# Line 1  Line 1 
1    # -*- perl -*-
2    ########################################################################
3    # Copyright (c) 2003-2006 University of Chicago and Fellowship
4    # for Interpretations of Genomes. All Rights Reserved.
5    #
6    # This file is part of the SEED Toolkit.
7    #
8    # The SEED Toolkit is free software. You can redistribute
9    # it and/or modify it under the terms of the SEED Toolkit
10    # Public License.
11    #
12    # You should have received a copy of the SEED Toolkit Public License
13    # along with this program; if not write to the University of Chicago
14    # at info@ci.uchicago.edu or the Fellowship for Interpretation of
15    # Genomes at veronika@thefig.info or download a copy from
16    # http://www.theseed.org/LICENSE.TXT.
17    ########################################################################
18    
19  package Tracer;  package Tracer;
20    
21          require Exporter;          require Exporter;
22          @ISA = ('Exporter');          @ISA = ('Exporter');
23          @EXPORT = qw(Trace T TSetup QTrace Confess Cluck Min Max Assert);      @EXPORT = qw(Trace T TSetup QTrace Confess Cluck Min Max Assert Open OpenDir TICK StandardSetup EmergencyKey ETracing Constrain Insure ChDir Emergency Warn);
24          @EXPORT_OK = qw(GetFile GetOptions Merge MergeOptions ParseCommand ParseRecord UnEscape);      @EXPORT_OK = qw(GetFile GetOptions Merge MergeOptions ParseCommand ParseRecord UnEscape Escape PrintLine PutLine);
25          use strict;          use strict;
26          use Carp qw(longmess croak);      use Carp qw(longmess croak carp);
27          use CGI;          use CGI;
28        use Cwd;
29        use FIG_Config;
30        use PageBuilder;
31        use Digest::MD5;
32        use File::Basename;
33        use File::Path;
34        use File::stat;
35        use LWP::UserAgent;
36        use Time::HiRes 'gettimeofday';
37        use URI::Escape;
38        use Time::Local;
39        use POSIX qw(strftime);
40        use Time::Zone;
41    
42    
43  =head1 Tracing and Debugging Helpers  =head1 Tracing and Debugging Helpers
44    
45  =head2 Introduction  =head2 Tracing
46    
47  This package provides simple tracing for debugging and reporting purposes. To use it simply call the  This package provides simple tracing for debugging and reporting purposes. To use it simply call the
48  L</TSetup> method to set the options and call L</Trace> to write out trace messages. Each trace  L</TSetup> or L</ETracing> method to set the options and call L</Trace> to write out trace messages.
49  message has a I<trace level> and I<category> associated with it. In addition, the tracing package itself  L</TSetup> and L</ETracing> both establish a I<trace level> and a list of I<categories>. Similarly,
50  has a list of categories and a single trace level set by the B<TSetup> method. Only messages whose trace  each trace message has a I<trace level> and I<category> associated with it. Only messages whose trace
51  level is less than or equal to this package's trace level and whose category is activated will  level is less than or equal to the setup trace level and whose category is activated will
52  be written. Thus, a higher trace level on a message indicates that the message  be written. Thus, a higher trace level on a message indicates that the message
53  is less likely to be seen. A higher trace level passed to B<Setup> means more trace messages will  is less likely to be seen, while a higher trace level passed to B<TSetup> means more trace messages will
54  appear. To generate a trace message, use the following syntax.  appear.
55    
56    =head3 Putting Trace Messages in Your Code
57    
58    To generate a trace message, use the following syntax.
59    
60  C<< Trace($message) if T(errors => 4); >>      Trace($message) if T(errors => 4);
61    
62  This statement will produce a trace message if the trace level is 4 or more and the C<errors>  This statement will produce a trace message if the trace level is 4 or more and the C<errors>
63  category is active. Note that the special category C<main> is always active, so  category is active. There is a special category C<main> that is always active, so
64    
65  C<< Trace($message) if T(main => 4); >>      Trace($message) if T(main => 4);
66    
67  will trace if the trace level is 4 or more.  will trace if the trace level is 4 or more.
68    
# Line 34  Line 70 
70  following call is made in the B<Sprout> package, it will appear if the C<Sprout> category is  following call is made in the B<Sprout> package, it will appear if the C<Sprout> category is
71  active and the trace level is 2 or more.  active and the trace level is 2 or more.
72    
73  C<< Trace($message) if T(2); >>      Trace($message) if T(2);
74    
75  To set up tracing, you call the C</Setup> method. The method takes as input a trace level, a list  In scripts, where no package name is available, the category defaults to C<main>.
76  of category names, and a set of options. The trace level and list of category names are  
77    =head3 Custom Tracing
78    
79    Many programs have customized tracing configured using the L</TSetup> method. This is no longer
80    the preferred method, but a knowledge of how custom tracing works can make the more modern
81    L</Emergency Tracing> easier to understand.
82    
83    To set up custom tracing, you call the L</TSetup> method. The method takes as input a trace level,
84    a list of category names, and a destination. The trace level and list of category names are
85  specified as a space-delimited string. Thus  specified as a space-delimited string. Thus
86    
87  C<< TSetup('3 errors Sprout ERDB', 'HTML'); >>      TSetup('3 errors Sprout ERDB', 'TEXT');
88    
89    sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and
90    specifies that messages should be sent to the standard output.
91    
92  sets the trace level to 3, activated the C<errors>, C<Sprout>, and C<ERDB> categories, and  To turn on tracing for ALL categories, use an asterisk. The call below sets every category to
93  specifies that messages should be output as HTML paragraphs. The idea is to make it easier to  level 3 and writes the output to the standard error output. This sort of thing might be
94  input tracing configuration on a web form.  useful in a CGI environment.
95    
96  In addition to HTML and file output for trace messages, you can specify that the trace messages      TSetup('3 *', 'WARN');
97    
98    In addition standard error and file output for trace messages, you can specify that the trace messages
99  be queued. The messages can then be retrieved by calling the L</QTrace> method. This approach  be queued. The messages can then be retrieved by calling the L</QTrace> method. This approach
100  is useful if you are building a web page. Instead of having the trace messages interspersed with  is useful if you are building a web page. Instead of having the trace messages interspersed with
101  the page output, they can be gathered together and displayed at the end of the page. This makes  the page output, they can be gathered together and displayed at the end of the page. This makes
102  it easier to debug page formatting problems.  it easier to debug page formatting problems.
103    
104  Finally, you can specify that all trace messages be emitted as warnings.  Finally, you can specify that all trace messages be emitted to a file, or the standard output and
105    a file at the same time. To trace to a file, specify the filename with an output character in front
106    of it.
107    
108        TSetup('4 SQL', ">$fileName");
109    
110    To trace to the standard output and a file at the same time, put a C<+> in front of the angle
111    bracket.
112    
113        TSetup('3 *', "+>$fileName");
114    
115  The flexibility of tracing makes it superior to simple use of directives like C<die> and C<warn>.  The flexibility of tracing makes it superior to simple use of directives like C<die> and C<warn>.
116  Tracer calls can be left in the code with minimal overhead and then turned on only when needed.  Tracer calls can be left in the code with minimal overhead and then turned on only when needed.
117  Thus, debugging information is available and easily retrieved even when the application is  Thus, debugging information is available and easily retrieved even when the application is
118  being used out in the field.  being used out in the field.
119    
120    =head3 Trace Levels
121    
122    There is no hard and fast rule on how to use trace levels. The following is therefore only
123    a suggestion.
124    
125    =over 4
126    
127    =item Error 0
128    
129    Message indicates an error that may lead to incorrect results or that has stopped the
130    application entirely.
131    
132    =item Warning 1
133    
134    Message indicates something that is unexpected but that probably did not interfere
135    with program execution.
136    
137    =item Notice 2
138    
139    Message indicates the beginning or end of a major task.
140    
141    =item Information 3
142    
143    Message indicates a subtask. In the FIG system, a subtask generally relates to a single
144    genome. This would be a big loop that is not expected to execute more than 500 times or so.
145    
146    =item Detail 4
147    
148    Message indicates a low-level loop iteration.
149    
150    =back
151    
152    The format of trace messages is important because some utilities analyze trace files.
153    There are three fields-- the time stamp, the category name, and the text.
154    The time stamp is between square brackets and the category name between angle brackets.
155    After the category name there is a colon (C<:>) followed by the message text.
156    If the square brackets or angle brackets are missing, then the trace management
157    utilities assume that they are encountering a set of pre-formatted lines.
158    
159    Note, however, that this formatting is done automatically by the tracing functions. You
160    only need to know about it if you want to parse a trace file.
161    
162    =head3 Emergency Tracing
163    
164    Sometimes, you need a way for tracing to happen automatically without putting parameters
165    in a form or on the command line. Emergency tracing does this. You invoke emergency tracing
166    from the debug form, which is accessed from the [[DebugConsole]]. Emergency tracing requires
167    that you specify a tracing key. For command-line tools, the key is
168    taken from the C<TRACING> environment variable. For web services, the key is taken from
169    a cookie. Either way, the key tells the tracing facility who you are, so that you control
170    the tracing in your environment without stepping on other users.
171    
172    The key can be anything you want. If you don't have a key, the C<SetPassword> page will
173    generate one for you.
174    
175    You can activate and de-activate emergency tracing from the debugging control panel, as
176    well as display the trace file itself.
177    
178    To enable emergency tracing in your code, call
179    
180        ETracing($cgi)
181    
182    from a web script and
183    
184        ETracing()
185    
186    from a command-line script.
187    
188    The web script will look for the tracing key in the cookies, and the command-line
189    script will look for it in the C<TRACING> environment variable. If you are
190    using the L</StandardSetup> method or a [[WebApplication]], emergency tracing
191    will be configured automatically.
192    
193  =cut  =cut
194    
195  # Declare the configuration variables.  # Declare the configuration variables.
196    
197  my $Destination = "NONE";       # Description of where to send the trace output.  my $Destination = "WARN";   # Description of where to send the trace output.
198    my $TeeFlag = 0;            # TRUE if output is going to a file and to the
199                                # standard output
200  my %Categories = ( main => 1 );  my %Categories = ( main => 1 );
201                                                          # hash of active category names                                                          # hash of active category names
202    my @LevelNames = qw(error warn notice info detail);
203  my $TraceLevel = 0;                     # trace level; a higher trace level produces more  my $TraceLevel = 0;                     # trace level; a higher trace level produces more
204                                                          # messages                                                          # messages
205  my @Queue = ();                         # queued list of trace messages.  my @Queue = ();                         # queued list of trace messages.
206    my $LastCategory = "main";  # name of the last category interrogated
207    my $LastLevel = 0;          # level of the last test call
208    my $SetupCount = 0;         # number of times TSetup called
209    my $AllTrace = 0;           # TRUE if we are tracing all categories.
210    my $SavedCGI;               # CGI object passed to ETracing
211    my $CommandLine;            # Command line passed to StandardSetup
212    umask 2;                    # Fix the damn umask so everything is group-writable.
213    
214  =head2 Public Methods  =head2 Tracing Methods
215    
216    =head3 Setups
217    
218        my $count = Tracer::Setups();
219    
220    Return the number of times L</TSetup> has been called.
221    
222    This method allows for the creation of conditional tracing setups where, for example, we
223    may want to set up tracing if nobody else has done it before us.
224    
225    =cut
226    
227    sub Setups {
228        return $SetupCount;
229    }
230    
231  =head3 TSetup  =head3 TSetup
232    
233  C<< TSetup($categoryList, $target); >>      TSetup($categoryList, $target);
234    
235  This method is used to specify the trace options. The options are stored as package data  This method is used to specify the trace options. The options are stored as package data
236  and interrogated by the L</Trace> and L</T> methods.  and interrogated by the L</Trace> and L</T> methods.
# Line 90  Line 246 
246    
247  The destination for the trace output. To send the trace output to a file, specify the file  The destination for the trace output. To send the trace output to a file, specify the file
248  name preceded by a ">" symbol. If a double symbol is used (">>"), then the data is appended  name preceded by a ">" symbol. If a double symbol is used (">>"), then the data is appended
249  to the file. Otherwise the file is cleared before tracing begins. In addition to sending  to the file. Otherwise the file is cleared before tracing begins. Precede the first ">"
250  the trace messages to a file, you can specify a special destination. C<HTML> will cause  symbol with a C<+> to echo output to a file AND to the standard output. In addition to
251  tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>  sending the trace messages to a file, you can specify a special destination. C<HTML> will
252    cause tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>
253  will cause tracing to the standard output as ordinary text. C<ERROR> will cause trace  will cause tracing to the standard output as ordinary text. C<ERROR> will cause trace
254  messages to be sent to the standard error output as ordinary text. C<QUEUE> will cause trace  messages to be sent to the standard error output as ordinary text. C<QUEUE> will cause trace
255  messages to be stored in a queue for later retrieval by the L</QTrace> method. C<WARN> will  messages to be stored in a queue for later retrieval by the L</QTrace> method. C<WARN> will
# Line 110  Line 267 
267          my @categoryData = split /\s+/, $categoryList;          my @categoryData = split /\s+/, $categoryList;
268          # Extract the trace level.          # Extract the trace level.
269          $TraceLevel = shift @categoryData;          $TraceLevel = shift @categoryData;
270          # Build the category hash.      # Presume category-based tracing until we learn otherwise.
271        $AllTrace = 0;
272        # Build the category hash. Note that if we find a "*", we turn on non-category
273        # tracing. We must also clear away any pre-existing data.
274        %Categories = ( main => 1 );
275          for my $category (@categoryData) {          for my $category (@categoryData) {
276                  $Categories{$category} = 1;          if ($category eq '*') {
277                $AllTrace = 1;
278            } else {
279                $Categories{lc $category} = 1;
280            }
281          }          }
282          # Now we need to process the destination information. The most important special          # Now we need to process the destination information. The most important special
283          # case is the single ">", which requires we clear the file first. After doing      # case is when we're writing to a file. This is indicated by ">" (overwrite) and
284          # so, we tack on another ">" sign so that future trace messages are appended.      # ">>" (append). A leading "+" for either indicates that we are also writing to
285        # the standard output (tee mode).
286        if ($target =~ m/^\+?>>?/) {
287            if ($target =~ m/^\+/) {
288                $TeeFlag = 1;
289                $target = substr($target, 1);
290            }
291          if ($target =~ m/^>[^>]/) {          if ($target =~ m/^>[^>]/) {
292                # We need to initialize the file (which clears it).
293                  open TRACEFILE, $target;                  open TRACEFILE, $target;
294                  print TRACEFILE Now() . " Tracing initialized.\n";              print TRACEFILE "[" . Now() . "] [notice] [Tracer] Tracing initialized.\n";
295                  close TRACEFILE;                  close TRACEFILE;
296                # Set to append mode now that the file has been cleared.
297                  $Destination = ">$target";                  $Destination = ">$target";
298          } else {          } else {
299                $Destination = $target;
300            }
301        } else {
302                  $Destination = uc($target);                  $Destination = uc($target);
303          }          }
304        # Increment the setup counter.
305        $SetupCount++;
306  }  }
307    
308  =head3 SetLevel  =head3 SetLevel
309    
310  C<< Tracer::SetLevel($newLevel); >>      Tracer::SetLevel($newLevel);
311    
312  Modify the trace level. A higher trace level will cause more messages to appear.  Modify the trace level. A higher trace level will cause more messages to appear.
313    
# Line 147  Line 325 
325      $TraceLevel = $_[0];      $TraceLevel = $_[0];
326  }  }
327    
328  =head3 Now  =head3 ParseDate
   
 C<< my $string = Tracer::Now(); >>  
   
 Return a displayable time stamp containing the local time.  
   
 =cut  
   
 sub Now {  
         my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime(time);  
         my $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .  
                                  _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);  
         return $retVal;  
 }  
   
 # Pad a number to 2 digits.  
 sub _p2 {  
         my ($value) = @_;  
         $value = "0$value" if ($value < 10);  
         return $value;  
 }  
   
 =head3 LogErrors  
   
 C<< Tracer::LogErrors($fileName); >>  
   
 Route the standard error output to a log file.  
   
 =over 4  
   
 =item fileName  
   
 Name of the file to receive the error output.  
   
 =back  
329    
330  =cut      my $time = Tracer::ParseDate($dateString);
331    
332  sub LogErrors {  Convert a date into a PERL time number. This method expects a date-like string
333          # Get the file name.  and parses it into a number. The string must be vaguely date-like or it will
334          my ($fileName) = @_;  return an undefined value. Our requirement is that a month and day be
335          # Open the file as the standard error output.  present and that three pieces of the date string (time of day, month and day,
336          open STDERR, '>', $fileName;  year) be separated by likely delimiters, such as spaces, commas, and such-like.
 }  
337    
338  =head3 ReadOptions  If a time of day is present, it must be in military time with two digits for
339    everything but the hour.
340    
341  C<< my %options = Tracer::ReadOptions($fileName); >>  The year must be exactly four digits.
342    
343  Read a set of options from a file. Each option is encoded in a line of text that has the  Additional stuff can be in the string. We presume it's time zones or weekdays or something
344  format  equally innocuous. This means, however, that a sufficiently long sentence with date-like
345    parts in it may be interpreted as a date. Hopefully this will not be a problem.
346    
347  I<optionName>C<=>I<optionValue>C<; >I<comment>  It should be guaranteed that this method will parse the output of the L</Now> function.
348    
349  The option name must consist entirely of letters, digits, and the punctuation characters  The parameters are as follows.
 C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank  
 character is a semi-colon will be ignored. The return hash will map each option name to  
 the corresponding option value.  
350    
351  =over 4  =over 4
352    
353  =item fileName  =item dateString
354    
355  Name of the file containing the option data.  The date string to convert.
356    
357  =item RETURN  =item RETURN
358    
359  Returns a hash mapping the option names specified in the file to their corresponding option  Returns a PERL time, that is, a number of seconds since the epoch, or C<undef> if
360  value.  the date string is invalid. A valid date string must contain a month and day.
361    
362  =back  =back
363    
364  =cut  =cut
365    
366  sub ReadOptions {  # Universal month conversion table.
367          # Get the parameters.  use constant MONTHS => {    Jan =>  0, January   =>  0, '01' =>  0,  '1' =>  0,
368          my ($fileName) = @_;                              Feb =>  1, February  =>  1, '02' =>  1,  '2' =>  1,
369          # Open the file.                              Mar =>  2, March     =>  2, '03' =>  2,  '3' =>  2,
370          (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");                              Apr =>  3, April     =>  3, '04' =>  3,  '4' =>  3,
371          # Count the number of records read.                              May =>  4, May       =>  4, '05' =>  4,  '5' =>  4,
372          my ($records, $comments) = 0;                              Jun =>  5, June      =>  5, '06' =>  5,  '6' =>  5,
373          # Create the return hash.                              Jul =>  6, July      =>  6, '07' =>  6,  '7' =>  6,
374          my %retVal = ();                              Aug =>  7, August    =>  7, '08' =>  7,  '8' =>  7,
375          # Loop through the file, accumulating key-value pairs.                              Sep =>  8, September =>  8, '09' =>  8,  '9' =>  8,
376          while (my $line = <CONFIGFILE>) {                              Oct =>  9, October  =>   9, '10' =>  9,
377                  # Denote we've read a line.                              Nov => 10, November =>  10, '11' => 10,
378                  $records++;                              Dec => 11, December =>  11, '12' => 11
379                  # Determine the line type.                          };
                 if ($line =~ /^\s*[\n\r]/) {  
                         # A blank line is a comment.  
                         $comments++;  
                 } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {  
                         # Here we have an option assignment.  
                         retVal{$1} = $2;  
                 } elsif ($line =~ /^\s*;/) {  
                         # Here we have a text comment.  
                         $comments++;  
                 } else {  
                         # Here we have an invalid line.  
                         Trace("Invalid option statement in record $records.") if T(0);  
                 }  
         }  
         # Return the hash created.  
         return %retVal;  
 }  
   
 =head3 GetOptions  
   
 C<< Tracer::GetOptions(\%defaults, \%options); >>  
   
 Merge a specified set of options into a table of defaults. This method takes two hash references  
 as input and uses the data from the second to update the first. If the second does not exist,  
 there will be no effect. An error will be thrown if one of the entries in the second hash does not  
 exist in the first.  
   
 Consider the following example.  
   
 C<< my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options); >>  
   
 In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and  
 B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of  
 B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and  
 the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level  
 will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as  
   
 C<< {databaseType => 'Oracle'} >>  
   
 an error will occur because the B<databaseType> option does not exist.  
   
 =over 4  
   
 =item defaults  
   
 Table of default option values.  
   
 =item options  
   
 Table of overrides, if any.  
   
 =item RETURN  
   
 Returns a reference to the default table passed in as the first parameter.  
   
 =back  
   
 =cut  
380    
381  sub GetOptions {  sub ParseDate {
382          # Get the parameters.          # Get the parameters.
383          my ($defaults, $options) = @_;      my ($dateString) = @_;
384          # Check for overrides.      # Declare the return variable.
385          if ($options) {      my $retVal;
386                  # Loop through the overrides.      # Find the month and day of month. There are two ways that can happen. We check for the
387                  while (my ($option, $setting) = each %{$options}) {      # numeric style first. That way, if the user's done something like "Sun 12/22", then we
388                          # Insure this override exists.      # won't be fooled into thinking the month is Sunday.
389                          if (!exists $defaults->{$option}) {      if ($dateString =~ m#\b(\d{1,2})/(\d{1,2})\b# || $dateString =~ m#\b(\w+)\s(\d{1,2})\b#) {
390                                  croak "Unrecognized option $option encountered.";          my ($mon, $mday) = (MONTHS->{$1}, $2);
391            # Insist that the month and day are valid.
392            if (defined($mon) && $2 >= 1 && $2 <= 31) {
393                # Find the time.
394                my ($hour, $min, $sec) = (0, 0, 0);
395                if ($dateString =~ /\b(\d{1,2}):(\d{2}):(\d{2})\b/) {
396                    ($hour, $min, $sec) = ($1, $2, $3);
397                }
398                # Find the year.
399                my $year;
400                if ($dateString =~ /\b(\d{4})\b/) {
401                    $year = $1;
402                          } else {                          } else {
403                                  # Apply the override.                  # Get the default year, which is this one. Note we must convert it to
404                                  $defaults->{$option} = $setting;                  # the four-digit value expected by "timelocal".
405                    (undef, undef, undef, undef, undef, $year) = localtime();
406                    $year += 1900;
407                          }                          }
408                $retVal = timelocal($sec, $min, $hour, $mday, $mon, $year);
409                  }                  }
410          }          }
411          # Return the merged table.      # Return the result.
412          return $defaults;      return $retVal;
413  }  }
414    
415  =head3 MergeOptions  =head3 LogErrors
416    
417  C<< Tracer::MergeOptions(\%table, \%defaults); >>      Tracer::LogErrors($fileName);
418    
419  Merge default values into a hash table. This method looks at the key-value pairs in the  Route the standard error output to a log file.
 second (default) hash, and if a matching key is not found in the first hash, the default  
 pair is copied in. The process is similar to L</GetOptions>, but there is no error-  
 checking and no return value.  
420    
421  =over 4  =over 4
422    
423  =item table  =item fileName
   
 Hash table to be updated with the default values.  
   
 =item defaults  
424    
425  Default values to be merged into the first hash table if they are not already present.  Name of the file to receive the error output.
426    
427  =back  =back
428    
429  =cut  =cut
430    
431  sub MergeOptions {  sub LogErrors {
432          # Get the parameters.      # Get the file name.
433          my ($table, $defaults) = @_;      my ($fileName) = @_;
434          # Loop through the defaults.      # Open the file as the standard error output.
435          while (my ($key, $value) = each %{$defaults}) {      open STDERR, '>', $fileName;
                 if (!exists $table->{$key}) {  
                         $table->{$key} = $value;  
                 }  
         }  
436  }  }
437    
438  =head3 Trace  =head3 Trace
439    
440  C<< Trace($message); >>      Trace($message);
441    
442  Write a trace message to the target location specified in L</TSetup>. If there has not been  Write a trace message to the target location specified in L</TSetup>. If there has not been
443  any prior call to B<TSetup>.  any prior call to B<TSetup>.
# Line 368  Line 455 
455  sub Trace {  sub Trace {
456          # Get the parameters.          # Get the parameters.
457          my ($message) = @_;          my ($message) = @_;
458        # Strip off any line terminators at the end of the message. We will add
459        # new-line stuff ourselves.
460        my $stripped = Strip($message);
461        # Compute the caller information.
462        my ($callPackage, $callFile, $callLine) = caller();
463        my $callFileTitle = basename($callFile);
464        # Check the caller.
465        my $callerInfo = ($callFileTitle ne "Tracer.pm" ? " [$callFileTitle $callLine]" : "");
466          # Get the timestamp.          # Get the timestamp.
467          my $timeStamp = Now();          my $timeStamp = Now();
468        # Build the prefix.
469        my $level = $LevelNames[$LastLevel] || "($LastLevel)";
470        my $prefix = "[$timeStamp] [$level] [$LastCategory]$callerInfo";
471          # Format the message.          # Format the message.
472          my $formatted = "$timeStamp $message";      my $formatted = "$prefix $stripped";
473          # Process according to the destination.          # Process according to the destination.
474          if ($Destination eq "TEXT") {          if ($Destination eq "TEXT") {
475                  # Write the message to the standard output.                  # Write the message to the standard output.
476                  print "$formatted\n";                  print "$formatted\n";
477          } elsif ($Destination eq "ERROR") {          } elsif ($Destination eq "ERROR") {
478                  # Write the message to the error output.          # Write the message to the error output. Here, we want our prefix fields.
479                  print STDERR "$formatted\n";                  print STDERR "$formatted\n";
480        } elsif ($Destination eq "WARN") {
481            # Emit the message to the standard error output. It is presumed that the
482            # error logger will add its own prefix fields, the notable exception being
483            # the caller info.
484            print STDERR "$callerInfo$stripped\n";
485          } elsif ($Destination eq "QUEUE") {          } elsif ($Destination eq "QUEUE") {
486                  # Push the message into the queue.                  # Push the message into the queue.
487                  push @Queue, "$formatted";                  push @Queue, "$formatted";
488          } elsif ($Destination eq "HTML") {          } elsif ($Destination eq "HTML") {
489                  # Convert the message to HTML and write it to the standard output.                  # Convert the message to HTML and write it to the standard output.
490                  my $escapedMessage = CGI::escapeHTML($message);          my $escapedMessage = CGI::escapeHTML($stripped);
491                  print "<p>$formatted</p>\n";          print "<p>$timeStamp $LastCategory $LastLevel: $escapedMessage</p>\n";
     } elsif ($Destination eq "WARN") {  
        # Emit the message as a warning.  
        warn $message;  
492          } elsif ($Destination =~ m/^>>/) {          } elsif ($Destination =~ m/^>>/) {
493                  # Write the trace message to an output file.                  # Write the trace message to an output file.
494                  open TRACING, $Destination;          open(TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";
495                  print TRACING "$formatted\n";                  print TRACING "$formatted\n";
496                  close TRACING;                  close TRACING;
497            # If the Tee flag is on, echo it to the standard output.
498            if ($TeeFlag) {
499                print "$formatted\n";
500            }
501          }          }
502  }  }
503    
504  =head3 T  =head3 T
505    
506  C<< my $switch = T($category, $traceLevel); >>      my $switch = T($category, $traceLevel);
507    
508          or          or
509    
510  C<< my $switch = T($traceLevel); >>      my $switch = T($traceLevel);
511    
512  Return TRUE if the trace level is at or above a specified value and the specified category  Return TRUE if the trace level is at or above a specified value and the specified category
513  is active, else FALSE. If no category is specified, the caller's package name is used.  is active, else FALSE. If no category is specified, the caller's package name is used.
# Line 436  Line 540 
540                  my ($category, $traceLevel) = @_;                  my ($category, $traceLevel) = @_;
541                  if (!defined $traceLevel) {                  if (!defined $traceLevel) {
542                          # Here we have no category, so we need to get the calling package.                          # Here we have no category, so we need to get the calling package.
543                # The calling package is normally the first parameter. If it is
544                # omitted, the first parameter will be the tracelevel. So, the
545                # first thing we do is shift the so-called category into the
546                # $traceLevel variable where it belongs.
547                          $traceLevel = $category;                          $traceLevel = $category;
548                          my ($package, $fileName, $line) = caller;                          my ($package, $fileName, $line) = caller;
549              # If there is no calling package, we default to "main".              # If there is no calling package, we default to "main".
550                          if (!$package) {                          if (!$package) {
551                  $category = "main";                  $category = "main";
552                          } else {                          } else {
553                                  $category = $package;                  my @cats = split /::/, $package;
554                    $category = $cats[$#cats];
555                          }                          }
556                  }                  }
557                  # Use the package and tracelevel to compute the result.          # Save the category name and level.
558                  $retVal = ($traceLevel <= $TraceLevel && exists $Categories{$category});          $LastCategory = $category;
559            $LastLevel = $traceLevel;
560            # Convert it to lower case before we hash it.
561            $category = lc $category;
562            # Validate the trace level.
563            if (ref $traceLevel) {
564                Confess("Bad trace level.");
565            } elsif (ref $TraceLevel) {
566                Confess("Bad trace config.");
567            }
568            # Make the check. Note that level 0 shows even if the category is turned off.
569            $retVal = ($traceLevel <= $TraceLevel && ($traceLevel == 0 || $AllTrace || exists $Categories{$category}));
570      }      }
571          # Return the computed result.          # Return the computed result.
572      return $retVal;      return $retVal;
573  }  }
574    
575  =head3 ParseCommand  =head3 QTrace
   
 C<< my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList); >>  
   
 Parse a command line consisting of a list of parameters. The initial parameters may be option  
 specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped  
 off and merged into a table of default options. The remainder of the command line is  
 returned as a list of positional arguments. For example, consider the following invocation.  
   
 C<< my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words); >>  
   
 In this case, the list @words will be treated as a command line. There are two options available,  
 B<errors> and B<logFile>. If @words has the following format  
   
 C<< -logFile=error.log apple orange rutabaga >>  
   
 then at the end of the invocation, C<$options> will be  
   
 C<< { errors => 0, logFile => 'error.log' } >>  
   
 and C<@arguments> will contain  
576    
577  C<< apple orange rutabaga >>      my $data = QTrace($format);
578    
579  The parser allows for some escape sequences. See L</UnEscape> for a description. There is no  Return the queued trace data in the specified format.
 support for quote characters.  
580    
581  =over 4  =over 4
582    
583  =item optionTable  =item format
   
 Table of default options.  
   
 =item inputList  
   
 List of words on the command line.  
   
 =item RETURN  
584    
585  Returns a reference to the option table and a list of the positional arguments.  C<html> to format the data as an HTML list, C<text> to format it as straight text.
586    
587  =back  =back
588    
589  =cut  =cut
590    
591  sub ParseCommand {  sub QTrace {
592          # Get the parameters.      # Get the parameter.
593          my ($optionTable, @inputList) = @_;      my ($format) = @_;
594          # Process any options in the input list.      # Create the return variable.
595        my $retVal = "";
596        # Only proceed if there is an actual queue.
597        if (@Queue) {
598            # Process according to the format.
599            if ($format =~ m/^HTML$/i) {
600                # Convert the queue into an HTML list.
601                $retVal = "<ul>\n";
602                for my $line (@Queue) {
603                    my $escapedLine = CGI::escapeHTML($line);
604                    $retVal .= "<li>$escapedLine</li>\n";
605                }
606                $retVal .= "</ul>\n";
607            } elsif ($format =~ m/^TEXT$/i) {
608                # Convert the queue into a list of text lines.
609                $retVal = join("\n", @Queue) . "\n";
610            }
611            # Clear the queue.
612            @Queue = ();
613        }
614        # Return the formatted list.
615        return $retVal;
616    }
617    
618    =head3 Confess
619    
620        Confess($message);
621    
622    Trace the call stack and abort the program with the specified message. When used with
623    the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.
624    So, for example
625    
626        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
627    
628    Will abort the program with a stack trace if the value of C<$recNum> is negative.
629    
630    =over 4
631    
632    =item message
633    
634    Message to include in the trace.
635    
636    =back
637    
638    =cut
639    
640    sub Confess {
641        # Get the parameters.
642        my ($message) = @_;
643        # Set up the category and level.
644        $LastCategory = "(confess)";
645        $LastLevel = 0;
646        if (! defined($FIG_Config::no_tool_hdr)) {
647            # Here we have a tool header. Display its length so that the user can adjust the line numbers.
648            my $toolHeaderFile = "$FIG_Config::fig_disk/dist/releases/current/$FIG_Config::arch/tool_hdr";
649            # Only proceed if the tool header file is actually present.
650            if (-f $toolHeaderFile) {
651                my $fh;
652                if (open $fh, "<$toolHeaderFile") {
653                    my @lines = <$fh>;
654                    Trace("Tool header has " . scalar(@lines) . " lines.");
655                }
656            }
657        }
658        # Trace the call stack.
659        Cluck($message);
660        # Abort the program.
661        croak(">>> $message");
662    }
663    
664    =head3 Warn
665    
666        Warn($message);
667    
668    This method traces an important message. If an RSS feed is configured
669    (via I<FIG_Config::error_feed>) and the tracing destination is C<WARN>,
670    then the message will be echoed to the feed. In general, a tracing
671    destination of C<WARN> indicates that the caller is running as a web
672    service in a production environment; however, this is not a requirement.
673    
674    To force warnings into the RSS feed even when the tracing destination
675    is not C<WARN>, simply specify the C<Feed> tracing module. This can be
676    configured automatically when L</StandardSetup> is used.
677    
678    The L</Cluck> method calls this one for its final message. Since
679    L</Confess> calls L</Cluck>, this means that any error which is caught
680    and confessed will put something in the feed. This insures that someone
681    will be alerted relatively quickly when a failure occurs.
682    
683    =over 4
684    
685    =item message
686    
687    Message to be traced.
688    
689    =back
690    
691    =cut
692    
693    sub Warn {
694        # Get the parameters.
695        my ($message) = @_;
696        # Trace the message.
697        Trace($message);
698        # Check for feed forcing.
699        my $forceFeed = exists $Categories{feed};
700        # An error here would be disastrous. Note, however, that we aren't too worried
701        # about losing events. The error log is always available for the occasions where
702        # we mess up. Note that if debug mode is specified, we do this stuff even in a
703        # test environment.
704        eval {
705            # Do we need to put this in the RSS feed?
706            if ($FIG_Config::error_feed && ($Destination eq 'WARN' || $forceFeed)) {
707                # Yes. We now need to compute the date, the link, and the title.
708                # First, the date, in a very specific format.
709                my $date = strftime("%a, %02e %b %H:%M:%S %Y ", localtime) .
710                    (tz_local_offset() / 30);
711                # Environment data goes in here. We start with the date.
712                my $environment = "$date.  ";
713                # If we need to recap the message (because it's too long to be a title), we'll
714                # put it in here.
715                my $recap;
716                # Copy the message and remove excess space.
717                my $title = $message;
718                $title =~ s/\s+/ /gs;
719                # If it's too long, we have to split it up.
720                if (length $title > 60) {
721                    # Put the full message in the environment string.
722                    $recap = $title;
723                    # Excerpt it as the title.
724                    $title = substr($title, 0, 50) . "...";
725                }
726                # If we have a CGI object, then this is a web error. Otherwise, it's
727                # command-line.
728                if (defined $SavedCGI) {
729                    # We're in a web service. The environment is the user's IP, and the link
730                    # is the URL that got us here.
731                    my $key = $ENV{HTTP_X_FORWARDED_FOR} || $ENV{REMOTE_ADDR};
732                    $environment .= "Event Reported at IP address $key.";
733                    my $url = $SavedCGI->url(-full => 1, -query => 1);
734                    # We need the user agent string and (if available) the referrer.
735                    # The referrer will be the link.
736                    $environment .= "User Agent $ENV{HTTP_USER_AGENT}";
737                    if ($ENV{HTTP_REFERER}) {
738                        my $link = $ENV{HTTP_REFERER};
739                        $environment .= " referred from <a href=\"$link\">$link</a>.";
740                    } else {
741                        $environment .= " referrer unknown.";
742                    }
743                    # Close off the sentence with the original link.
744                    $environment .= " URL of error is <a href=\"$url\">$url</a>.";
745                } else {
746                    # No CGI object, so we're a command-line tool. Use the tracing
747                    # key and the PID as the user identifier, and add the command.
748                    my $key = EmergencyKey();
749                    $environment .= "Event Reported by $key Process $$.";
750                    if ($CommandLine) {
751                        # We're in a StandardSetup script, so we have the real command line.
752                        $environment .= "\n<pre>" . CGI::escapeHTML($CommandLine) . "</pre>\n";
753                    } elsif ($ENV{_}) {
754                        # We're in a BASH script, so the command has been stored in the _ variable.
755                        $environment .= "  Command = " . CGI::escapeHTML($ENV{_}) . "\n";
756                    }
757                }
758                # Build a GUID. We use the current time, the title, and the process ID,
759                # then digest the result.
760                my $guid = Digest::MD5::md5_base64(gettimeofday(), $title, $$);
761                # Finally, the description. This is a stack trace plus various environmental stuff.
762                my $stackTrace = "";
763                my @trace = LongMess();
764                # Only proceed if we got something back.
765                if (scalar(@trace) > 0) {
766                    $trace[0] =~ s/Tracer::Warn.+?called/Event occurred/;
767                    $stackTrace = "Stack trace:<pre>" . join("\n", @trace, "</pre>");
768                }
769                # We got the stack trace. Now it's time to put it all together.
770                # We have a goofy thing here in that we need to HTML-escape some sections of the description
771                # twice. They will be escaped once here, and then once when written by XML::Simple. They are
772                # unescaped once when processed by the RSS reader, and stuff in the description is treated as
773                # HTML. So, anything escaped here is treated as a literal when viewed in the RSS reader, but
774                # our <br>s and <pre>s are used to format the description.
775                $recap = (defined $recap ? "<em>" . CGI::escapeHTML($recap) . "</em><br /><br />" : "");
776                my $description = "$recap$environment  $stackTrace";
777                # Okay, we have all the pieces. Create a hash of the new event.
778                my $newItem = { title => $title,
779                                description => $description,
780                                category => $LastCategory,
781                                pubDate => $date,
782                                guid => $guid,
783                               };
784                # We need XML capability for this.
785                require XML::Simple;
786                # The RSS document goes in here.
787                my $rss;
788                # Get the name of the RSS file. It's in the FIG temporary directory.
789                my $fileName = "$FIG_Config::temp/$FIG_Config::error_feed";
790                # Does it exist?
791                if (-s $fileName) {
792                    # Slurp it in.
793                    $rss = XML::Simple::XMLin($fileName, ForceArray => ['item']);
794                } else {
795                    my $size = -s $fileName;
796                    # Create an empty channel.
797                    $rss = {
798                        channel => {
799                            title => 'NMPDR Warning Feed',
800                            link => "$FIG_Config::temp_url/$FIG_Config::error_feed",
801                            description => "Important messages regarding the status of the NMPDR.",
802                            generator => "NMPDR Trace Facility",
803                            docs => "http://blogs.law.harvard.edu/tech/rss",
804                            item => []
805                        },
806                    };
807                }
808                # Get the channel object.
809                my $channel = $rss->{channel};
810                # Update the last-build date.
811                $channel->{lastBuildDate} = $date;
812                # Get the item array.
813                my $items = $channel->{item};
814                # Insure it has only 100 entries.
815                while (scalar @{$items} > 100) {
816                    pop @{$items};
817                }
818                # Add our new item at the front.
819                unshift @{$items}, $newItem;
820                # Create the XML. Note we do not include the root or the declaration. XML Simple can't handle
821                # the requirements for those.
822                my $xml = XML::Simple::XMLout($rss, NoAttr => 1, RootName => undef, XmlDecl => '');
823                # Here we put in the root and declaration. The problem is that the root has to have the version attribute
824                # in it. So, we suppress the root and do it by hand, and that requires suppressing the declaration, too.
825                $xml = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<rss version=\"2.0\">$xml\n</rss>";
826                # We don't use Open here because we can't afford an error.
827                if (open XMLOUT, ">$fileName") {
828                    print XMLOUT $xml;
829                    close XMLOUT;
830                }
831            }
832        };
833        if ($@) {
834            # If the feed failed, we need to know why. The error will be traced, but this method will not be involved
835            # (which is a good thing).
836            my $error = $@;
837            Trace("Feed Error: $error") if T(Feed => 0);
838        }
839    }
840    
841    =head3 Assert
842    
843        Assert($condition1, $condition2, ... $conditionN);
844    
845    Return TRUE if all the conditions are true. This method can be used in conjunction with
846    the OR operator and the L</Confess> method as a debugging assert.
847    So, for example
848    
849        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
850    
851    Will abort the program with a stack trace if the value of C<$recNum> is negative.
852    
853    =cut
854    sub Assert {
855        my $retVal = 1;
856        LOOP: for my $condition (@_) {
857            if (! $condition) {
858                $retVal = 0;
859                last LOOP;
860            }
861        }
862        return $retVal;
863    }
864    
865    =head3 Cluck
866    
867        Cluck($message);
868    
869    Trace the call stack. Note that for best results, you should qualify the call with a
870    trace condition. For example,
871    
872        Cluck("Starting record parse.") if T(3);
873    
874    will only trace the stack if the trace level for the package is 3 or more.
875    
876    =over 4
877    
878    =item message
879    
880    Message to include in the trace.
881    
882    =back
883    
884    =cut
885    
886    sub Cluck {
887        # Get the parameters.
888        my ($message) = @_;
889        # Trace what's happening.
890        Trace("Stack trace for event: $message");
891        # Get the stack trace.
892        my @trace = LongMess();
893        # Convert the trace to a series of messages.
894        for my $line (@trace) {
895            # Replace the tab at the beginning with spaces.
896            $line =~ s/^\t/    /;
897            # Trace the line.
898            Trace($line);
899        }
900        # Issue a warning. This displays the event message and inserts it into the RSS error feed.
901        Warn($message);
902    }
903    
904    =head3 LongMess
905    
906        my @lines = Tracer::LongMess();
907    
908    Return a stack trace with all tracing methods removed. The return will be in the form of a list
909    of message strings.
910    
911    =cut
912    
913    sub LongMess {
914        # Declare the return variable.
915        my @retVal = ();
916        my $confession = longmess("");
917        for my $line (split /\s*\n/, $confession) {
918            unless ($line =~ /Tracer\.pm/) {
919                # Here we have a line worth keeping. Push it onto the result list.
920                push @retVal, $line;
921            }
922        }
923        # Return the result.
924        return @retVal;
925    }
926    
927    =head3 ETracing
928    
929        ETracing($parameter);
930    
931    Set up emergency tracing. Emergency tracing is tracing that is turned
932    on automatically for any program that calls this method. The emergency
933    tracing parameters are stored in a a file identified by a tracing key.
934    If this method is called with a CGI object, then the tracing key is
935    taken from a cookie. If it is called with no parameters, then the tracing
936    key is taken from an environment variable. If it is called with a string,
937    the tracing key is that string.
938    
939    =over 4
940    
941    =item parameter
942    
943    A parameter from which the tracing key is computed. If it is a scalar,
944    that scalar is used as the tracing key. If it is a CGI object, the
945    tracing key is taken from the C<IP> cookie. If it is omitted, the
946    tracing key is taken from the C<TRACING> environment variable. If it
947    is a CGI object and emergency tracing is not on, the C<Trace> and
948    C<TF> parameters will be used to determine the type of tracing.
949    
950    =back
951    
952    =cut
953    
954    sub ETracing {
955        # Get the parameter.
956        my ($parameter) = @_;
957        # Check for CGI mode.
958        if (defined $parameter && ref $parameter eq 'CGI') {
959            $SavedCGI = $parameter;
960        } else {
961            $SavedCGI = undef;
962        }
963        # Default to no tracing except errors.
964        my ($tracing, $dest) = ("0", "WARN");
965        # Check for emergency tracing.
966        my $tkey = EmergencyKey($parameter);
967        my $emergencyFile = EmergencyFileName($tkey);
968        if (-e $emergencyFile) {
969            # We have the file. Read in the data.
970            my @tracing = GetFile($emergencyFile);
971            # Pull off the time limit.
972            my $expire = shift @tracing;
973            # Convert it to seconds.
974            $expire *= 3600;
975            # Check the file data.
976            my $stat = stat($emergencyFile);
977            my ($now) = gettimeofday;
978            if ($now - $stat->mtime > $expire) {
979                # Delete the expired file.
980                unlink $emergencyFile;
981            } else {
982                # Emergency tracing is on. Pull off the destination and
983                # the trace level;
984                $dest = shift @tracing;
985                my $level = shift @tracing;
986                # Convert the destination to a real tracing destination.
987                # temp directory.
988                $dest = EmergencyTracingDest($tkey, $dest);
989                # Insure Tracer is specified.
990                my %moduleHash = map { $_ => 1 } @tracing;
991                $moduleHash{Tracer} = 1;
992                # Set the trace parameter.
993                $tracing = join(" ", $level, sort keys %moduleHash);
994            }
995        } elsif (defined $SavedCGI) {
996            # There's no emergency tracing, but we have a CGI object, so check
997            # for tracing from the form parameters.
998            if ($SavedCGI->param('Trace')) {
999                # Here the user has requested tracing via a form.
1000                $dest = ($SavedCGI->param('TF') ? ">$FIG_Config::temp/Trace$$.log" : "QUEUE");
1001                $tracing = $SavedCGI->param('Trace') . " Tracer";
1002            }
1003        }
1004        # Setup the tracing we've determined from all the stuff above.
1005        TSetup($tracing, $dest);
1006        # Check to see if we're a web script.
1007        if (defined $SavedCGI) {
1008            # Yes we are. Trace the form and environment data.
1009            TraceParms($SavedCGI);
1010            # Check for RAW mode. In raw mode, we print a fake header so that we see everything
1011            # emitted by the script in its raw form.
1012            if (T(Raw => 3)) {
1013                print CGI::header(-type => 'text/plain', -tracing => 'Raw');
1014            }
1015        }
1016    }
1017    
1018    =head3 EmergencyFileName
1019    
1020        my $fileName = Tracer::EmergencyFileName($tkey);
1021    
1022    Return the emergency tracing file name. This is the file that specifies
1023    the tracing information.
1024    
1025    =over 4
1026    
1027    =item tkey
1028    
1029    Tracing key for the current program.
1030    
1031    =item RETURN
1032    
1033    Returns the name of the file to contain the emergency tracing information.
1034    
1035    =back
1036    
1037    =cut
1038    
1039    sub EmergencyFileName {
1040        # Get the parameters.
1041        my ($tkey) = @_;
1042        # Compute the emergency tracing file name.
1043        return "$FIG_Config::temp/Emergency$tkey.txt";
1044    }
1045    
1046    =head3 EmergencyFileTarget
1047    
1048        my $fileName = Tracer::EmergencyFileTarget($tkey);
1049    
1050    Return the emergency tracing target file name. This is the file that receives
1051    the tracing output for file-based tracing.
1052    
1053    =over 4
1054    
1055    =item tkey
1056    
1057    Tracing key for the current program.
1058    
1059    =item RETURN
1060    
1061    Returns the name of the file to contain the trace output.
1062    
1063    =back
1064    
1065    =cut
1066    
1067    sub EmergencyFileTarget {
1068        # Get the parameters.
1069        my ($tkey) = @_;
1070        # Compute the emergency tracing file name.
1071        return "$FIG_Config::temp/trace$tkey.log";
1072    }
1073    
1074    =head3 EmergencyTracingDest
1075    
1076        my $dest = Tracer::EmergencyTracingDest($tkey, $myDest);
1077    
1078    This method converts an emergency tracing destination to a real
1079    tracing destination. The main difference is that if the
1080    destination is C<FILE> or C<APPEND>, we convert it to file
1081    output. If the destination is C<DUAL>, we convert it to file
1082    and standard output.
1083    
1084    =over 4
1085    
1086    =item tkey
1087    
1088    Tracing key for this environment.
1089    
1090    =item myDest
1091    
1092    Destination from the emergency tracing file.
1093    
1094    =item RETURN
1095    
1096    Returns a destination that can be passed into L</TSetup>.
1097    
1098    =back
1099    
1100    =cut
1101    
1102    sub EmergencyTracingDest {
1103        # Get the parameters.
1104        my ($tkey, $myDest) = @_;
1105        # Declare the return variable.
1106        my $retVal = $myDest;
1107        # Process according to the destination value.
1108        if ($myDest eq 'FILE') {
1109            $retVal = ">" . EmergencyFileTarget($tkey);
1110        } elsif ($myDest eq 'APPEND') {
1111            $retVal = ">>" . EmergencyFileTarget($tkey);
1112        } elsif ($myDest eq 'DUAL') {
1113            $retVal = "+>" . EmergencyFileTarget($tkey);
1114        } elsif ($myDest eq 'WARN') {
1115            $retVal = "WARN";
1116        }
1117        # Return the result.
1118        return $retVal;
1119    }
1120    
1121    =head3 Emergency
1122    
1123        Emergency($key, $hours, $dest, $level, @modules);
1124    
1125    Turn on emergency tracing. This method is normally invoked over the web from
1126    a debugging console, but it can also be called by the C<trace.pl> script.
1127    The caller specifies the duration of the emergency in hours, the desired tracing
1128    destination, the trace level, and a list of the trace modules to activate.
1129    For the length of the duration, when a program in an environment with the
1130    specified tracing key active invokes a Sprout CGI script, tracing will be
1131    turned on automatically. See L</TSetup> for more about tracing setup and
1132    L</ETracing> for more about emergency tracing.
1133    
1134    =over 4
1135    
1136    =item tkey
1137    
1138    The tracing key. This is used to identify the control file and the trace file.
1139    
1140    =item hours
1141    
1142    Number of hours to keep emergency tracing alive.
1143    
1144    =item dest
1145    
1146    Tracing destination. If no path information is specified for a file
1147    destination, it is put in the FIG temporary directory.
1148    
1149    =item level
1150    
1151    Tracing level. A higher level means more trace messages.
1152    
1153    =item modules
1154    
1155    A list of the tracing modules to activate.
1156    
1157    =back
1158    
1159    =cut
1160    
1161    sub Emergency {
1162        # Get the parameters.
1163        my ($tkey, $hours, $dest, $level, @modules) = @_;
1164        # Create the emergency file.
1165        my $specFile = EmergencyFileName($tkey);
1166        my $outHandle = Open(undef, ">$specFile");
1167        print $outHandle join("\n", $hours, $dest, $level, @modules, "");
1168    }
1169    
1170    =head3 EmergencyKey
1171    
1172        my $tkey = EmergencyKey($parameter);
1173    
1174    Return the Key to be used for emergency tracing. This could be an IP address,
1175     a session ID, or a user name, depending on the environment.
1176    
1177    =over 4
1178    
1179    =item parameter
1180    
1181    Parameter defining the method for finding the tracing key. If it is a scalar,
1182    then it is presumed to be the tracing key itself. If it is a CGI object, then
1183    the tracing key is taken from the C<IP> cookie. Otherwise, the tracing key is
1184    taken from the C<TRACING> environment variable.
1185    
1186    =item RETURN
1187    
1188    Returns the key to be used for labels in emergency tracing.
1189    
1190    =back
1191    
1192    =cut
1193    
1194    sub EmergencyKey {
1195        # Get the parameters.
1196        my ($parameter) = @_;
1197        # Declare the return variable.
1198        my $retVal;
1199        # Determine the parameter type.
1200        if (! defined $parameter) {
1201            # Here we're supposed to check the environment. If that fails, we
1202            # get the effective login ID.
1203            $retVal = $ENV{TRACING} || scalar getpwuid($<);
1204        } else {
1205            my $ptype = ref $parameter;
1206            if ($ptype eq 'CGI') {
1207                # Here we were invoked from a web page. Look for a cookie.
1208                $retVal = $parameter->cookie('IP');
1209            } elsif (! $ptype) {
1210                # Here the key was passed in.
1211                $retVal = $parameter;
1212            }
1213        }
1214        # If no luck finding a key, use the PID.
1215        if (! defined $retVal) {
1216            $retVal = $$;
1217        }
1218        # Return the result.
1219        return $retVal;
1220    }
1221    
1222    
1223    =head3 TraceParms
1224    
1225        Tracer::TraceParms($cgi);
1226    
1227    Trace the CGI parameters at trace level CGI => 3 and the environment variables
1228    at level CGI => 4. A self-referencing URL is traced at level CGI => 2.
1229    
1230    =over 4
1231    
1232    =item cgi
1233    
1234    CGI query object containing the parameters to trace.
1235    
1236    =back
1237    
1238    =cut
1239    
1240    sub TraceParms {
1241        # Get the parameters.
1242        my ($cgi) = @_;
1243        if (T(CGI => 2)) {
1244            # Here we trace the GET-style URL for the script.
1245            Trace("[URL] " . $cgi->url(-relative => 1, -query => 1));
1246        }
1247        if (T(CGI => 3)) {
1248            # Here we want to trace the parameter data.
1249            my @names = $cgi->param;
1250            for my $parmName (sort @names) {
1251                # Note we skip the Trace parameters, which are for our use only.
1252                if ($parmName ne 'Trace' && $parmName ne 'TF') {
1253                    my @values = $cgi->param($parmName);
1254                    Trace("[CGI] $parmName = " . join(", ", @values));
1255                }
1256            }
1257            # Display the request method.
1258            my $method = $cgi->request_method();
1259            Trace("Method: $method");
1260        }
1261        if (T(CGI => 4)) {
1262            # Here we want the environment data too.
1263            for my $envName (sort keys %ENV) {
1264                Trace("[ENV] $envName = $ENV{$envName}");
1265            }
1266        }
1267    }
1268    
1269    =head3 TraceImages
1270    
1271        Tracer::TraceImages($htmlString);
1272    
1273    Trace information about all of an html document's images. The tracing
1274    will be for type "IMG" at level 3. The image's source string
1275    will be displayed. This is generally either the URL of the image or
1276    raw data for the image itself. If the source is too long, only the first 300
1277    characters will be shown at trace level 3. The entire source will be shown,
1278    however, at trace level 4. This method is not very smart, and might catch
1279    Javascript code, but it is still useful when debugging the arcane
1280    behavior of images in multiple browser environments.
1281    
1282    =over 4
1283    
1284    =item htmlString
1285    
1286    HTML text for an outgoing web page.
1287    
1288    =back
1289    
1290    =cut
1291    
1292    sub TraceImages {
1293        # Only proceed if we're at the proper trace level.
1294        if (T(IMG => 3)) {
1295            # For performance reasons we're manipulating $_[0] instead of retrieving the string
1296            # into a variable called "$htmlString". This is because we expect html strings to be
1297            # long, and don't want to copy them any more than we have to.
1298            Trace(length($_[0]) . " characters in web page.");
1299            # Loop through the HTML, culling image tags.
1300            while ($_[0] =~ /<img\s+[^>]+?src="([^"]+)"/sgi) {
1301                # Extract the source string and determine whether or not it's too long.
1302                my $srcString = $1;
1303                my $pos = pos($_[0]) - length($srcString);
1304                my $excess = length($srcString) - 300;
1305                # We'll put the display string in here.
1306                my $srcDisplay = $srcString;
1307                # If it's a data string, split it at the comma.
1308                $srcDisplay =~ s/^(data[^,]+,)/$1\n/;
1309                # If there's no excess or we're at trace level 4, we're done. At level 3 with
1310                # a long string, however, we only show the first 300 characters.
1311                if ($excess > 0 && ! T(IMG => 4)) {
1312                    $srcDisplay = substr($srcDisplay,0,300) . "\nplus $excess characters.";
1313                }
1314                # Output the trace message.
1315                Trace("Image tag at position $pos:\n$srcDisplay");
1316            }
1317        }
1318    }
1319    
1320    =head2 Command-Line Utility Methods
1321    
1322    =head3 SendSMS
1323    
1324        my $msgID = Tracer::SendSMS($phoneNumber, $msg);
1325    
1326    Send a text message to a phone number using Clickatell. The FIG_Config file must contain the
1327    user name, password, and API ID for the relevant account in the hash reference variable
1328    I<$FIG_Config::phone>, using the keys C<user>, C<password>, and C<api_id>. For
1329    example, if the user name is C<BruceTheHumanPet>, the password is C<silly>, and the API ID
1330    is C<2561022>, then the FIG_Config file must contain
1331    
1332        $phone =  { user => 'BruceTheHumanPet',
1333                    password => 'silly',
1334                    api_id => '2561022' };
1335    
1336    The original purpose of this method was to insure Bruce would be notified immediately when the
1337    Sprout Load terminates. Care should be taken if you do not wish Bruce to be notified immediately
1338    when you call this method.
1339    
1340    The message ID will be returned if successful, and C<undef> if an error occurs.
1341    
1342    =over 4
1343    
1344    =item phoneNumber
1345    
1346    Phone number to receive the message, in international format. A United States phone number
1347    would be prefixed by "1". A British phone number would be prefixed by "44".
1348    
1349    =item msg
1350    
1351    Message to send to the specified phone.
1352    
1353    =item RETURN
1354    
1355    Returns the message ID if successful, and C<undef> if the message could not be sent.
1356    
1357    =back
1358    
1359    =cut
1360    
1361    sub SendSMS {
1362        # Get the parameters.
1363        my ($phoneNumber, $msg) = @_;
1364        # Declare the return variable. If we do not change it, C<undef> will be returned.
1365        my $retVal;
1366        # Only proceed if we have phone support.
1367        if (! defined $FIG_Config::phone) {
1368            Trace("Phone support not present in FIG_Config.") if T(1);
1369        } else {
1370            # Get the phone data.
1371            my $parms = $FIG_Config::phone;
1372            # Get the Clickatell URL.
1373            my $url = "http://api.clickatell.com/http/";
1374            # Create the user agent.
1375            my $ua = LWP::UserAgent->new;
1376            # Request a Clickatell session.
1377            my $resp = $ua->post("$url/sendmsg", { user => $parms->{user},
1378                                         password => $parms->{password},
1379                                         api_id => $parms->{api_id},
1380                                         to => $phoneNumber,
1381                                         text => $msg});
1382            # Check for an error.
1383            if (! $resp->is_success) {
1384                Trace("Alert failed.") if T(1);
1385            } else {
1386                # Get the message ID.
1387                my $rstring = $resp->content;
1388                if ($rstring =~ /^ID:\s+(.*)$/) {
1389                    $retVal = $1;
1390                } else {
1391                    Trace("Phone attempt failed with $rstring") if T(1);
1392                }
1393            }
1394        }
1395        # Return the result.
1396        return $retVal;
1397    }
1398    
1399    =head3 StandardSetup
1400    
1401        my ($options, @parameters) = StandardSetup(\@categories, \%options, $parmHelp, @ARGV);
1402    
1403    This method performs standard command-line parsing and tracing setup. The return
1404    values are a hash of the command-line options and a list of the positional
1405    parameters. Tracing is automatically set up and the command-line options are
1406    validated.
1407    
1408    This is a complex method that does a lot of grunt work. The parameters can
1409    be more easily understood, however, once they are examined individually.
1410    
1411    The I<categories> parameter is the most obtuse. It is a reference to a list of
1412    special-purpose tracing categories. Most tracing categories are PERL package
1413    names. So, for example, if you wanted to turn on tracing inside the B<Sprout>,
1414    B<ERDB>, and B<SproutLoad> packages, you would specify the categories
1415    
1416        ["Sprout", "SproutLoad", "ERDB"]
1417    
1418    This would cause trace messages in the specified three packages to appear in
1419    the output. There are two special tracing categories that are automatically
1420    handled by this method. In other words, if you used L</TSetup> you would need
1421    to include these categories manually, but if you use this method they are turned
1422    on automatically.
1423    
1424    =over 4
1425    
1426    =item SQL
1427    
1428    Traces SQL commands and activity.
1429    
1430    =item Tracer
1431    
1432    Traces error messages and call stacks.
1433    
1434    =back
1435    
1436    C<SQL> is only turned on if the C<-sql> option is specified in the command line.
1437    The trace level is specified using the C<-trace> command-line option. For example,
1438    the following command line for C<TransactFeatures> turns on SQL tracing and runs
1439    all tracing at level 3.
1440    
1441        TransactFeatures -trace=3 -sql register ../xacts IDs.tbl
1442    
1443    Standard tracing is output to the standard output and echoed to the file
1444    C<trace>I<$$>C<.log> in the FIG temporary directory, where I<$$> is the
1445    process ID. You can also specify the C<user> parameter to put a user ID
1446    instead of a process ID in the trace file name. So, for example
1447    
1448    The default trace level is 2. To get all messages, specify a trace level of 4.
1449    For a genome-by-genome update, use 3.
1450    
1451        TransactFeatures -trace=3 -sql -user=Bruce register ../xacts IDs.tbl
1452    
1453    would send the trace output to C<traceBruce.log> in the temporary directory.
1454    
1455    The I<options> parameter is a reference to a hash containing the command-line
1456    options, their default values, and an explanation of what they mean. Command-line
1457    options may be in the form of switches or keywords. In the case of a switch, the
1458    option value is 1 if it is specified and 0 if it is not specified. In the case
1459    of a keyword, the value is separated from the option name by an equal sign. You
1460    can see this last in the command-line example above.
1461    
1462    You can specify a different default trace level by setting C<$options->{trace}>
1463    prior to calling this method.
1464    
1465    An example at this point would help. Consider, for example, the command-line utility
1466    C<TransactFeatures>. It accepts a list of positional parameters plus the options
1467    C<safe>, C<noAlias>, C<start>, and C<tblFiles>. To start up this command, we execute
1468    the following code.
1469    
1470        my ($options, @parameters) = Tracer::StandardSetup(["DocUtils"],
1471                            { safe => [0, "use database transactions"],
1472                              noAlias => [0, "do not expect aliases in CHANGE transactions"],
1473                              start => [' ', "start with this genome"],
1474                              tblFiles => [0, "output TBL files containing the corrected IDs"] },
1475                            "<command> <transactionDirectory> <IDfile>",
1476                          @ARGV);
1477    
1478    
1479    The call to C<ParseCommand> specifies the default values for the options and
1480    stores the actual options in a hash that is returned as C<$options>. The
1481    positional parameters are returned in C<@parameters>.
1482    
1483    The following is a sample command line for C<TransactFeatures>.
1484    
1485        TransactFeatures -trace=2 -noAlias register ../xacts IDs.tbl
1486    
1487    Single and double hyphens are equivalent. So, you could also code the
1488    above command as
1489    
1490        TransactFeatures --trace=2 --noAlias register ../xacts IDs.tbl
1491    
1492    In this case, C<register>, C<../xacts>, and C<IDs.tbl> are the positional
1493    parameters, and would find themselves in I<@parameters> after executing the
1494    above code fragment. The tracing would be set to level 2, and the categories
1495    would be C<Tracer>, and <DocUtils>. C<Tracer> is standard,
1496    and C<DocUtils> was included because it came in within the first parameter
1497    to this method. The I<$options> hash would be
1498    
1499        { trace => 2, sql => 0, safe => 0,
1500          noAlias => 1, start => ' ', tblFiles => 0 }
1501    
1502    Use of C<StandardSetup> in this way provides a simple way of performing
1503    standard tracing setup and command-line parsing. Note that the caller is
1504    not even aware of the command-line switches C<-trace> and C<-sql>, which
1505    are used by this method to control the tracing. If additional tracing features
1506    need to be added in the future, they can be processed by this method without
1507    upsetting the command-line utilities.
1508    
1509    If the C<background> option is specified on the command line, then the
1510    standard and error outputs will be directed to files in the temporary
1511    directory, using the same suffix as the trace file. So, if the command
1512    line specified
1513    
1514        -user=Bruce -background
1515    
1516    then the trace output would go to C<traceBruce.log>, the standard output to
1517    C<outBruce.log>, and the error output to C<errBruce.log>. This is designed to
1518    simplify starting a command in the background.
1519    
1520    The user name is also used as the tracing key for L</Emergency Tracing>.
1521    Specifying a value of C<E> for the trace level causes emergency tracing to
1522    be used instead of custom tracing. If the user name is not specified,
1523    the tracing key is taken from the C<Tracing> environment variable. If there
1524    is no value for that variable, the tracing key will be computed from the active
1525    login ID.
1526    
1527    Since the default situation in StandardSetup is to trace to the standard
1528    output, errors that occur in command-line scripts will not generate
1529    RSS events. To force the events, use the C<warn> option.
1530    
1531        TransactFeatures -background -warn register ../xacts IDs.tbl
1532    
1533    Finally, if the special option C<-help> is specified, the option
1534    names will be traced at level 0 and the program will exit without processing.
1535    This provides a limited help capability. For example, if the user enters
1536    
1537        TransactFeatures -help
1538    
1539    he would see the following output.
1540    
1541        TransactFeatures [options] <command> <transactionDirectory> <IDfile>
1542            -trace    tracing level (default E)
1543            -sql      trace SQL commands
1544            -safe     use database transactions
1545            -noAlias  do not expect aliases in CHANGE transactions
1546            -start    start with this genome
1547            -tblFiles output TBL files containing the corrected IDs
1548    
1549    The caller has the option of modifying the tracing scheme by placing a value
1550    for C<trace> in the incoming options hash. The default value can be overridden,
1551    or the tracing to the standard output can be turned off by suffixing a minus
1552    sign to the trace level. So, for example,
1553    
1554        { trace => [0, "tracing level (default 0)"],
1555           ...
1556    
1557    would set the default trace level to 0 instead of E, while
1558    
1559        { trace => ["2-", "tracing level (default 2)"],
1560           ...
1561    
1562    would set the default to 2, but trace only to the log file, not to the
1563    standard output.
1564    
1565    The parameters to this method are as follows.
1566    
1567    =over 4
1568    
1569    =item categories
1570    
1571    Reference to a list of tracing category names. These should be names of
1572    packages whose internal workings will need to be debugged to get the
1573    command working.
1574    
1575    =item options
1576    
1577    Reference to a hash containing the legal options for the current command mapped
1578    to their default values and descriptions. The user can override the defaults
1579    by specifying the options as command-line switches prefixed by a hyphen.
1580    Tracing-related options may be added to this hash. If the C<-h> option is
1581    specified on the command line, the option descriptions will be used to
1582    explain the options. To turn off tracing to the standard output, add a
1583    minus sign to the value for C<trace> (see above).
1584    
1585    =item parmHelp
1586    
1587    A string that vaguely describes the positional parameters. This is used
1588    if the user specifies the C<-h> option.
1589    
1590    =item argv
1591    
1592    List of command line parameters, including the option switches, which must
1593    precede the positional parameters and be prefixed by a hyphen.
1594    
1595    =item RETURN
1596    
1597    Returns a list. The first element of the list is the reference to a hash that
1598    maps the command-line option switches to their values. These will either be the
1599    default values or overrides specified on the command line. The remaining
1600    elements of the list are the position parameters, in order.
1601    
1602    =back
1603    
1604    =cut
1605    
1606    sub StandardSetup {
1607        # Get the parameters.
1608        my ($categories, $options, $parmHelp, @argv) = @_;
1609        # Get the default tracing key.
1610        my $tkey = EmergencyKey();
1611        # Save the command line.
1612        $CommandLine = join(" ", $0, map { $_ =~ /\s/ ? "\"$_\"" : $_ } @argv);
1613        # Add the tracing options.
1614        if (! exists $options->{trace}) {
1615            $options->{trace} = ['2', "tracing level (E for emergency tracing)"];
1616        }
1617        $options->{sql} = [0, "turn on SQL tracing"];
1618        $options->{help} = [0, "display command-line options"];
1619        $options->{user} = [$tkey, "tracing key"];
1620        $options->{background} = [0, "spool standard and error output"];
1621        $options->{warn} = [0, "send errors to RSS feed"];
1622        # Create a parsing hash from the options hash. The parsing hash
1623        # contains the default values rather than the default value
1624        # and the description. While we're at it, we'll memorize the
1625        # length of the longest option name.
1626        my $longestName = 0;
1627        my %parseOptions = ();
1628        for my $key (keys %{$options}) {
1629            if (length $key > $longestName) {
1630                $longestName = length $key;
1631            }
1632            $parseOptions{$key} = $options->{$key}->[0];
1633        }
1634        # Parse the command line.
1635        my ($retOptions, @retParameters) = ParseCommand(\%parseOptions, @argv);
1636        # Get the logfile suffix.
1637        my $suffix = $retOptions->{user};
1638        # Check for background mode.
1639        if ($retOptions->{background}) {
1640            my $outFileName = "$FIG_Config::temp/out$suffix.log";
1641            my $errFileName = "$FIG_Config::temp/err$suffix.log";
1642            open STDOUT, ">$outFileName";
1643            open STDERR, ">$errFileName";
1644            # Check for phone support. If we have phone support and a phone number,
1645            # we want to turn it on.
1646            if ($ENV{PHONE} && defined($FIG_Config::phone)) {
1647                $retOptions->{phone} = $ENV{PHONE};
1648            }
1649        }
1650        # Now we want to set up tracing. First, we need to know if the user
1651        # wants emergency tracing.
1652        if ($retOptions->{trace} eq 'E') {
1653            ETracing($retOptions->{user});
1654        } else {
1655            # Here the tracing is controlled from the command line.
1656            my @cats = @{$categories};
1657            if ($retOptions->{sql}) {
1658                push @cats, "SQL";
1659            }
1660            if ($retOptions->{warn}) {
1661                push @cats, "Feed";
1662            }
1663            # Add the default categories.
1664            push @cats, "Tracer";
1665            # Next, we create the category string by joining the categories.
1666            my $cats = join(" ", @cats);
1667            # Check to determine whether or not the caller wants to turn off tracing
1668            # to the standard output.
1669            my $traceLevel = $retOptions->{trace};
1670            my $textOKFlag = 1;
1671            if ($traceLevel =~ /^(.)-/) {
1672                $traceLevel = $1;
1673                $textOKFlag = 0;
1674            }
1675            # Now we set up the trace mode.
1676            my $traceMode;
1677            # Verify that we can open a file in the FIG temporary directory.
1678            my $traceFileName = "$FIG_Config::temp/trace$suffix.log";
1679            if (open TESTTRACE, ">$traceFileName") {
1680                # Here we can trace to a file.
1681                $traceMode = ">$traceFileName";
1682                if ($textOKFlag) {
1683                    # Echo to standard output if the text-OK flag is set.
1684                    $traceMode = "+$traceMode";
1685                }
1686                # Close the test file.
1687                close TESTTRACE;
1688            } else {
1689                # Here we can't trace to a file. Complain about this.
1690                warn "Could not open trace file $traceFileName: $!\n";
1691                # We trace to the standard output if it's
1692                # okay, and the error log otherwise.
1693                if ($textOKFlag) {
1694                    $traceMode = "TEXT";
1695                } else {
1696                    $traceMode = "WARN";
1697                }
1698            }
1699            # Now set up the tracing.
1700            TSetup("$traceLevel $cats", $traceMode);
1701        }
1702        # Check for the "help" option. If it is specified, dump the command-line
1703        # options and exit the program.
1704        if ($retOptions->{help}) {
1705            $0 =~ m#[/\\](\w+)(\.pl)?$#i;
1706            print "$1 [options] $parmHelp\n";
1707            for my $key (sort keys %{$options}) {
1708                my $name = Pad($key, $longestName, 0, ' ');
1709                my $desc = $options->{$key}->[1];
1710                if ($options->{$key}->[0]) {
1711                    $desc .= " (default " . $options->{$key}->[0] . ")";
1712                }
1713                print "  $name $desc\n";
1714            }
1715            exit(0);
1716        }
1717        # Trace the options, if applicable.
1718        if (T(3)) {
1719            my @parms = grep { $retOptions->{$_} } keys %{$retOptions};
1720            Trace("Selected options: " . join(", ", sort @parms) . ".");
1721        }
1722        # Return the parsed parameters.
1723        return ($retOptions, @retParameters);
1724    }
1725    
1726    =head3 ReadOptions
1727    
1728        my %options = Tracer::ReadOptions($fileName);
1729    
1730    Read a set of options from a file. Each option is encoded in a line of text that has the
1731    format
1732    
1733    I<optionName>C<=>I<optionValue>C<; >I<comment>
1734    
1735    The option name must consist entirely of letters, digits, and the punctuation characters
1736    C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank
1737    character is a semi-colon will be ignored. The return hash will map each option name to
1738    the corresponding option value.
1739    
1740    =over 4
1741    
1742    =item fileName
1743    
1744    Name of the file containing the option data.
1745    
1746    =item RETURN
1747    
1748    Returns a hash mapping the option names specified in the file to their corresponding option
1749    value.
1750    
1751    =back
1752    
1753    =cut
1754    
1755    sub ReadOptions {
1756        # Get the parameters.
1757        my ($fileName) = @_;
1758        # Open the file.
1759        (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");
1760        # Count the number of records read.
1761        my ($records, $comments) = 0;
1762        # Create the return hash.
1763        my %retVal = ();
1764        # Loop through the file, accumulating key-value pairs.
1765        while (my $line = <CONFIGFILE>) {
1766            # Denote we've read a line.
1767            $records++;
1768            # Determine the line type.
1769            if ($line =~ /^\s*[\n\r]/) {
1770                # A blank line is a comment.
1771                $comments++;
1772            } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {
1773                # Here we have an option assignment.
1774                retVal{$1} = $2;
1775            } elsif ($line =~ /^\s*;/) {
1776                # Here we have a text comment.
1777                $comments++;
1778            } else {
1779                # Here we have an invalid line.
1780                Trace("Invalid option statement in record $records.") if T(0);
1781            }
1782        }
1783        # Return the hash created.
1784        return %retVal;
1785    }
1786    
1787    =head3 GetOptions
1788    
1789        Tracer::GetOptions(\%defaults, \%options);
1790    
1791    Merge a specified set of options into a table of defaults. This method takes two hash references
1792    as input and uses the data from the second to update the first. If the second does not exist,
1793    there will be no effect. An error will be thrown if one of the entries in the second hash does not
1794    exist in the first.
1795    
1796    Consider the following example.
1797    
1798        my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options);
1799    
1800    In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and
1801    B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of
1802    B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and
1803    the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level
1804    will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as
1805    
1806        {databaseType => 'Oracle'}
1807    
1808    an error will occur because the B<databaseType> option does not exist.
1809    
1810    =over 4
1811    
1812    =item defaults
1813    
1814    Table of default option values.
1815    
1816    =item options
1817    
1818    Table of overrides, if any.
1819    
1820    =item RETURN
1821    
1822    Returns a reference to the default table passed in as the first parameter.
1823    
1824    =back
1825    
1826    =cut
1827    
1828    sub GetOptions {
1829        # Get the parameters.
1830        my ($defaults, $options) = @_;
1831        # Check for overrides.
1832        if ($options) {
1833            # Loop through the overrides.
1834            while (my ($option, $setting) = each %{$options}) {
1835                # Insure this override exists.
1836                if (!exists $defaults->{$option}) {
1837                    croak "Unrecognized option $option encountered.";
1838                } else {
1839                    # Apply the override.
1840                    $defaults->{$option} = $setting;
1841                }
1842            }
1843        }
1844        # Return the merged table.
1845        return $defaults;
1846    }
1847    
1848    =head3 MergeOptions
1849    
1850        Tracer::MergeOptions(\%table, \%defaults);
1851    
1852    Merge default values into a hash table. This method looks at the key-value pairs in the
1853    second (default) hash, and if a matching key is not found in the first hash, the default
1854    pair is copied in. The process is similar to L</GetOptions>, but there is no error-
1855    checking and no return value.
1856    
1857    =over 4
1858    
1859    =item table
1860    
1861    Hash table to be updated with the default values.
1862    
1863    =item defaults
1864    
1865    Default values to be merged into the first hash table if they are not already present.
1866    
1867    =back
1868    
1869    =cut
1870    
1871    sub MergeOptions {
1872        # Get the parameters.
1873        my ($table, $defaults) = @_;
1874        # Loop through the defaults.
1875        while (my ($key, $value) = each %{$defaults}) {
1876            if (!exists $table->{$key}) {
1877                $table->{$key} = $value;
1878            }
1879        }
1880    }
1881    
1882    =head3 ParseCommand
1883    
1884        my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList);
1885    
1886    Parse a command line consisting of a list of parameters. The initial parameters may be option
1887    specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped
1888    off and merged into a table of default options. The remainder of the command line is
1889    returned as a list of positional arguments. For example, consider the following invocation.
1890    
1891        my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words);
1892    
1893    In this case, the list @words will be treated as a command line and there are two options available,
1894    B<errors> and B<logFile>. If @words has the following format
1895    
1896        -logFile=error.log apple orange rutabaga
1897    
1898    then at the end of the invocation, C<$options> will be
1899    
1900        { errors => 0, logFile => 'error.log' }
1901    
1902    and C<@arguments> will contain
1903    
1904        apple orange rutabaga
1905    
1906    The parser allows for some escape sequences. See L</UnEscape> for a description. There is no
1907    support for quote characters. Options can be specified with single or double hyphens.
1908    
1909    =over 4
1910    
1911    =item optionTable
1912    
1913    Table of default options.
1914    
1915    =item inputList
1916    
1917    List of words on the command line.
1918    
1919    =item RETURN
1920    
1921    Returns a reference to the option table and a list of the positional arguments.
1922    
1923    =back
1924    
1925    =cut
1926    
1927    sub ParseCommand {
1928        # Get the parameters.
1929        my ($optionTable, @inputList) = @_;
1930        # Process any options in the input list.
1931          my %overrides = ();          my %overrides = ();
1932          while ((@inputList > 0) && ($inputList[0] =~ /^-/)) {      while ((@inputList > 0) && ($inputList[0] =~ /^--?/)) {
1933                  # Get the current option.                  # Get the current option.
1934                  my $arg = shift @inputList;                  my $arg = shift @inputList;
1935                  # Pull out the option name.                  # Pull out the option name.
1936                  $arg =~ /^-([^=]*)/g;          $arg =~ /^--?([^=]*)/g;
1937                  my $name = $1;                  my $name = $1;
1938                  # Check for an option value.                  # Check for an option value.
1939                  if ($arg =~ /\G=(.*)$/g) {                  if ($arg =~ /\G=(.*)$/g) {
1940                          # Here we have a value for the option.                          # Here we have a value for the option.
1941                          $overrides{$name} = UnEscape($1);                          $overrides{$name} = UnEscape($1);
1942                  } else {                  } else {
1943                          # Here there is no value, so we use 1.              # Here there is no value, so we use 1.
1944                          $overrides{$name} = 1;              $overrides{$name} = 1;
1945            }
1946        }
1947        # Merge the options into the defaults.
1948        GetOptions($optionTable, \%overrides);
1949        # Translate the remaining parameters.
1950        my @retVal = ();
1951        for my $inputParm (@inputList) {
1952            push @retVal, UnEscape($inputParm);
1953        }
1954        # Return the results.
1955        return ($optionTable, @retVal);
1956    }
1957    
1958    
1959    =head2 File Utility Methods
1960    
1961    =head3 GetFile
1962    
1963        my @fileContents = Tracer::GetFile($fileName);
1964    
1965        or
1966    
1967        my $fileContents = Tracer::GetFile($fileName);
1968    
1969    Return the entire contents of a file. In list context, line-ends are removed and
1970    each line is a list element. In scalar context, line-ends are replaced by C<\n>.
1971    
1972    =over 4
1973    
1974    =item fileName
1975    
1976    Name of the file to read.
1977    
1978    =item RETURN
1979    
1980    In a list context, returns the entire file as a list with the line terminators removed.
1981    In a scalar context, returns the entire file as a string. If an error occurs opening
1982    the file, an empty list will be returned.
1983    
1984    =back
1985    
1986    =cut
1987    
1988    sub GetFile {
1989        # Get the parameters.
1990        my ($fileName) = @_;
1991        # Declare the return variable.
1992        my @retVal = ();
1993        # Open the file for input.
1994        my $handle = Open(undef, "<$fileName");
1995        # Read the whole file into the return variable, stripping off any terminator
1996        # characters.
1997        my $lineCount = 0;
1998        while (my $line = <$handle>) {
1999            $lineCount++;
2000            $line = Strip($line);
2001            push @retVal, $line;
2002        }
2003        # Close it.
2004        close $handle;
2005        my $actualLines = @retVal;
2006        Trace("$actualLines lines read from file $fileName.") if T(File => 2);
2007        # Return the file's contents in the desired format.
2008        if (wantarray) {
2009            return @retVal;
2010        } else {
2011            return join "\n", @retVal;
2012        }
2013    }
2014    
2015    =head3 PutFile
2016    
2017        Tracer::PutFile($fileName, \@lines);
2018    
2019    Write out a file from a list of lines of text.
2020    
2021    =over 4
2022    
2023    =item fileName
2024    
2025    Name of the output file.
2026    
2027    =item lines
2028    
2029    Reference to a list of text lines. The lines will be written to the file in order, with trailing
2030    new-line characters. Alternatively, may be a string, in which case the string will be written without
2031    modification.
2032    
2033    =back
2034    
2035    =cut
2036    
2037    sub PutFile {
2038        # Get the parameters.
2039        my ($fileName, $lines) = @_;
2040        # Open the output file.
2041        my $handle = Open(undef, ">$fileName");
2042        # Count the lines written.
2043        if (ref $lines ne 'ARRAY') {
2044            # Here we have a scalar, so we write it raw.
2045            print $handle $lines;
2046            Trace("Scalar put to file $fileName.") if T(File => 3);
2047        } else {
2048            # Write the lines one at a time.
2049            my $count = 0;
2050            for my $line (@{$lines}) {
2051                print $handle "$line\n";
2052                $count++;
2053            }
2054            Trace("$count lines put to file $fileName.") if T(File => 3);
2055        }
2056        # Close the output file.
2057        close $handle;
2058    }
2059    
2060    =head3 ParseRecord
2061    
2062        my @fields = Tracer::ParseRecord($line);
2063    
2064    Parse a tab-delimited data line. The data line is split into field values. Embedded tab
2065    and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.
2066    These will automatically be converted.
2067    
2068    =over 4
2069    
2070    =item line
2071    
2072    Line of data containing the tab-delimited fields.
2073    
2074    =item RETURN
2075    
2076    Returns a list of the fields found in the data line.
2077    
2078    =back
2079    
2080    =cut
2081    
2082    sub ParseRecord {
2083        # Get the parameter.
2084        my ($line) = @_;
2085        # Remove the trailing new-line, if any.
2086        chomp $line;
2087        # Split the line read into pieces using the tab character.
2088        my @retVal = split /\t/, $line;
2089        # Trim and fix the escapes in each piece.
2090        for my $value (@retVal) {
2091            # Trim leading whitespace.
2092            $value =~ s/^\s+//;
2093            # Trim trailing whitespace.
2094            $value =~ s/\s+$//;
2095            # Delete the carriage returns.
2096            $value =~ s/\r//g;
2097            # Convert the escapes into their real values.
2098            $value =~ s/\\t/"\t"/ge;
2099            $value =~ s/\\n/"\n"/ge;
2100        }
2101        # Return the result.
2102        return @retVal;
2103    }
2104    
2105    =head3 Merge
2106    
2107        my @mergedList = Tracer::Merge(@inputList);
2108    
2109    Sort a list of strings and remove duplicates.
2110    
2111    =over 4
2112    
2113    =item inputList
2114    
2115    List of scalars to sort and merge.
2116    
2117    =item RETURN
2118    
2119    Returns a list containing the same elements sorted in ascending order with duplicates
2120    removed.
2121    
2122    =back
2123    
2124    =cut
2125    
2126    sub Merge {
2127        # Get the input list in sort order.
2128        my @inputList = sort @_;
2129        # Only proceed if the list has at least two elements.
2130        if (@inputList > 1) {
2131            # Now we want to move through the list splicing out duplicates.
2132            my $i = 0;
2133            while ($i < @inputList) {
2134                # Get the current entry.
2135                my $thisEntry = $inputList[$i];
2136                # Find out how many elements duplicate the current entry.
2137                my $j = $i + 1;
2138                my $dup1 = $i + 1;
2139                while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };
2140                # If the number is nonzero, splice out the duplicates found.
2141                if ($j > $dup1) {
2142                    splice @inputList, $dup1, $j - $dup1;
2143                }
2144                # Now the element at position $dup1 is different from the element before it
2145                # at position $i. We push $i forward one position and start again.
2146                $i++;
2147            }
2148        }
2149        # Return the merged list.
2150        return @inputList;
2151    }
2152    
2153    =head3 Open
2154    
2155        my $handle = Open($fileHandle, $fileSpec, $message);
2156    
2157    Open a file.
2158    
2159    The I<$fileSpec> is essentially the second argument of the PERL C<open>
2160    function. The mode is specified using Unix-like shell information. So, for
2161    example,
2162    
2163        Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2164    
2165    would open for output appended to the specified file, and
2166    
2167        Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");
2168    
2169    would open a pipe that sorts the records written and removes duplicates. Note
2170    the use of file handle syntax in the Open call. To use anonymous file handles,
2171    code as follows.
2172    
2173        my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2174    
2175    The I<$message> parameter is used if the open fails. If it is set to C<0>, then
2176    the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a
2177    failed open will throw an exception and the third parameter will be used to construct
2178    an error message. If the parameter is omitted, a standard message is constructed
2179    using the file spec.
2180    
2181        Could not open "/usr/spool/news/twitlog"
2182    
2183    Note that the mode characters are automatically cleaned from the file name.
2184    The actual error message from the file system will be captured and appended to the
2185    message in any case.
2186    
2187        Could not open "/usr/spool/news/twitlog": file not found.
2188    
2189    In some versions of PERL the only error message we get is a number, which
2190    corresponds to the C++ C<errno> value.
2191    
2192        Could not open "/usr/spool/news/twitlog": 6.
2193    
2194    =over 4
2195    
2196    =item fileHandle
2197    
2198    File handle. If this parameter is C<undef>, a file handle will be generated
2199    and returned as the value of this method.
2200    
2201    =item fileSpec
2202    
2203    File name and mode, as per the PERL C<open> function.
2204    
2205    =item message (optional)
2206    
2207    Error message to use if the open fails. If omitted, a standard error message
2208    will be generated. In either case, the error information from the file system
2209    is appended to the message. To specify a conditional open that does not throw
2210    an error if it fails, use C<0>.
2211    
2212    =item RETURN
2213    
2214    Returns the name of the file handle assigned to the file, or C<undef> if the
2215    open failed.
2216    
2217    =back
2218    
2219    =cut
2220    
2221    sub Open {
2222        # Get the parameters.
2223        my ($fileHandle, $fileSpec, $message) = @_;
2224        # Attempt to open the file.
2225        my $rv = open $fileHandle, $fileSpec;
2226        # If the open failed, generate an error message.
2227        if (! $rv) {
2228            # Save the system error message.
2229            my $sysMessage = $!;
2230            # See if we need a default message.
2231            if (!$message) {
2232                # Clean any obvious mode characters and leading spaces from the
2233                # filename.
2234                my ($fileName) = FindNamePart($fileSpec);
2235                $message = "Could not open \"$fileName\"";
2236            }
2237            # Terminate with an error using the supplied message and the
2238            # error message from the file system.
2239            Confess("$message: $!");
2240        }
2241        # Return the file handle.
2242        return $fileHandle;
2243    }
2244    
2245    =head3 FindNamePart
2246    
2247        my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec);
2248    
2249    Extract the portion of a file specification that contains the file name.
2250    
2251    A file specification is the string passed to an C<open> call. It specifies the file
2252    mode and name. In a truly complex situation, it can specify a pipe sequence. This
2253    method assumes that the file name is whatever follows the first angle bracket
2254    sequence.  So, for example, in the following strings the file name is
2255    C</usr/fig/myfile.txt>.
2256    
2257        >>/usr/fig/myfile.txt
2258        </usr/fig/myfile.txt
2259        | sort -u > /usr/fig/myfile.txt
2260    
2261    If the method cannot find a file name using its normal methods, it will return the
2262    whole incoming string.
2263    
2264    =over 4
2265    
2266    =item fileSpec
2267    
2268    File specification string from which the file name is to be extracted.
2269    
2270    =item RETURN
2271    
2272    Returns a three-element list. The first element contains the file name portion of
2273    the specified string, or the whole string if a file name cannot be found via normal
2274    methods. The second element contains the start position of the file name portion and
2275    the third element contains the length.
2276    
2277    =back
2278    
2279    =cut
2280    #: Return Type $;
2281    sub FindNamePart {
2282        # Get the parameters.
2283        my ($fileSpec) = @_;
2284        # Default to the whole input string.
2285        my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);
2286        # Parse out the file name if we can.
2287        if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {
2288            $retVal = $2;
2289            $len = length $retVal;
2290            $pos = (length $fileSpec) - (length $3) - $len;
2291        }
2292        # Return the result.
2293        return ($retVal, $pos, $len);
2294    }
2295    
2296    =head3 OpenDir
2297    
2298        my @files = OpenDir($dirName, $filtered, $flag);
2299    
2300    Open a directory and return all the file names. This function essentially performs
2301    the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is
2302    set to TRUE, all filenames beginning with a period (C<.>), dollar sign (C<$>),
2303    or pound sign (C<#>) and all filenames ending with a tilde C<~>) will be
2304    filtered out of the return list. If the directory does not open and I<$flag> is not
2305    set, an exception is thrown. So, for example,
2306    
2307        my @files = OpenDir("/Volumes/fig/contigs", 1);
2308    
2309    is effectively the same as
2310    
2311        opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");
2312        my @files = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir(TMP);
2313    
2314    Similarly, the following code
2315    
2316        my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs", 0, 1);
2317    
2318    Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and
2319    automatically returns an empty list if the directory fails to open.
2320    
2321    =over 4
2322    
2323    =item dirName
2324    
2325    Name of the directory to open.
2326    
2327    =item filtered
2328    
2329    TRUE if files whose names begin with a period (C<.>) should be automatically removed
2330    from the list, else FALSE.
2331    
2332    =item flag
2333    
2334    TRUE if a failure to open is okay, else FALSE
2335    
2336    =back
2337    
2338    =cut
2339    #: Return Type @;
2340    sub OpenDir {
2341        # Get the parameters.
2342        my ($dirName, $filtered, $flag) = @_;
2343        # Declare the return variable.
2344        my @retVal = ();
2345        # Open the directory.
2346        if (opendir(my $dirHandle, $dirName)) {
2347            # The directory opened successfully. Get the appropriate list according to the
2348            # strictures of the filter parameter.
2349            if ($filtered) {
2350                @retVal = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir $dirHandle;
2351            } else {
2352                @retVal = readdir $dirHandle;
2353            }
2354        } elsif (! $flag) {
2355            # Here the directory would not open and it's considered an error.
2356            Confess("Could not open directory $dirName.");
2357        }
2358        # Return the result.
2359        return @retVal;
2360    }
2361    
2362    
2363    =head3 Insure
2364    
2365        Insure($dirName, $chmod);
2366    
2367    Insure a directory is present.
2368    
2369    =over 4
2370    
2371    =item dirName
2372    
2373    Name of the directory to check. If it does not exist, it will be created.
2374    
2375    =item chmod (optional)
2376    
2377    Security privileges to be given to the directory if it is created.
2378    
2379    =back
2380    
2381    =cut
2382    
2383    sub Insure {
2384        my ($dirName, $chmod) = @_;
2385        if (! -d $dirName) {
2386            Trace("Creating $dirName directory.") if T(2);
2387            eval {
2388                mkpath $dirName;
2389                # If we have permissions specified, set them here.
2390                if (defined($chmod)) {
2391                    chmod $chmod, $dirName;
2392                }
2393            };
2394            if ($@) {
2395                Confess("Error creating $dirName: $@");
2396            }
2397        }
2398    }
2399    
2400    =head3 ChDir
2401    
2402        ChDir($dirName);
2403    
2404    Change to the specified directory.
2405    
2406    =over 4
2407    
2408    =item dirName
2409    
2410    Name of the directory to which we want to change.
2411    
2412    =back
2413    
2414    =cut
2415    
2416    sub ChDir {
2417        my ($dirName) = @_;
2418        if (! -d $dirName) {
2419            Confess("Cannot change to directory $dirName: no such directory.");
2420        } else {
2421            Trace("Changing to directory $dirName.") if T(File => 4);
2422            my $okFlag = chdir $dirName;
2423            if (! $okFlag) {
2424                Confess("Error switching to directory $dirName.");
2425            }
2426        }
2427    }
2428    
2429    =head3 SetPermissions
2430    
2431        Tracer::SetPermissions($dirName, $group, $mask, %otherMasks);
2432    
2433    Set the permissions for a directory and all the files and folders inside it.
2434    In addition, the group ownership will be changed to the specified value.
2435    
2436    This method is more vulnerable than most to permission and compatability
2437    problems, so it does internal error recovery.
2438    
2439    =over 4
2440    
2441    =item dirName
2442    
2443    Name of the directory to process.
2444    
2445    =item group
2446    
2447    Name of the group to be assigned.
2448    
2449    =item mask
2450    
2451    Permission mask. Bits that are C<1> in this mask will be ORed into the
2452    permission bits of any file or directory that does not already have them
2453    set to 1.
2454    
2455    =item otherMasks
2456    
2457    Map of search patterns to permission masks. If a directory name matches
2458    one of the patterns, that directory and all its members and subdirectories
2459    will be assigned the new pattern. For example, the following would
2460    assign 01664 to most files, but would use 01777 for directories named C<tmp>.
2461    
2462        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp$' => 01777);
2463    
2464    The list is ordered, so the following would use 0777 for C<tmp1> and
2465    0666 for C<tmp>, C<tmp2>, or C<tmp3>.
2466    
2467        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp1' => 0777,
2468                                                       '^tmp' => 0666);
2469    
2470    Note that the pattern matches are all case-insensitive, and only directory
2471    names are matched, not file names.
2472    
2473    =back
2474    
2475    =cut
2476    
2477    sub SetPermissions {
2478        # Get the parameters.
2479        my ($dirName, $group, $mask, @otherMasks) = @_;
2480        # Set up for error recovery.
2481        eval {
2482            # Switch to the specified directory.
2483            ChDir($dirName);
2484            # Get the group ID.
2485            my $gid = getgrnam($group);
2486            # Get the mask for tracing.
2487            my $traceMask = sprintf("%04o", $mask) . "($mask)";
2488            Trace("Fixing permissions for directory $dirName using group $group($gid) and mask $traceMask.") if T(File => 2);
2489            my $fixCount = 0;
2490            my $lookCount = 0;
2491            # @dirs will be a stack of directories to be processed.
2492            my @dirs = (getcwd());
2493            while (scalar(@dirs) > 0) {
2494                # Get the current directory.
2495                my $dir = pop @dirs;
2496                # Check for a match to one of the specified directory names. To do
2497                # that, we need to pull the individual part of the name off of the
2498                # whole path.
2499                my $simpleName = $dir;
2500                if ($dir =~ m!/([^/]+)$!) {
2501                    $simpleName = $1;
2502                }
2503                Trace("Simple directory name for $dir is $simpleName.") if T(File => 4);
2504                # Search for a match.
2505                my $match = 0;
2506                my $i;
2507                for ($i = 0; $i < $#otherMasks && ! $match; $i += 2) {
2508                    my $pattern = $otherMasks[$i];
2509                    if ($simpleName =~ /$pattern/i) {
2510                        $match = 1;
2511                    }
2512                }
2513                # Check for a match. Note we use $i-1 because the loop added 2
2514                # before terminating due to the match.
2515                if ($match && $otherMasks[$i-1] != $mask) {
2516                    # This directory matches one of the incoming patterns, and it's
2517                    # a different mask, so we process it recursively with that mask.
2518                    SetPermissions($dir, $group, $otherMasks[$i-1], @otherMasks);
2519                } else {
2520                    # Here we can process normally. Get all of the non-hidden members.
2521                    my @submems = OpenDir($dir, 1);
2522                    for my $submem (@submems) {
2523                        # Get the full name.
2524                        my $thisMem = "$dir/$submem";
2525                        Trace("Checking member $thisMem.") if T(4);
2526                        $lookCount++;
2527                        if ($lookCount % 1000 == 0) {
2528                            Trace("$lookCount members examined. Current is $thisMem. Mask is $traceMask") if T(File => 3);
2529                        }
2530                        # Fix the group.
2531                        chown -1, $gid, $thisMem;
2532                        # Insure this member is not a symlink.
2533                        if (! -l $thisMem) {
2534                            # Get its info.
2535                            my $fileInfo = stat $thisMem;
2536                            # Only proceed if we got the info. Otherwise, it's a hard link
2537                            # and we want to skip it anyway.
2538                            if ($fileInfo) {
2539                                my $fileMode = $fileInfo->mode;
2540                                if (($fileMode & $mask) != $mask) {
2541                                    # Fix this member.
2542                                    $fileMode |= $mask;
2543                                    chmod $fileMode, $thisMem;
2544                                    $fixCount++;
2545                                }
2546                                # If it's a subdirectory, stack it.
2547                                if (-d $thisMem) {
2548                                    push @dirs, $thisMem;
2549                                }
2550                            }
2551                        }
2552                    }
2553                }
2554            }
2555            Trace("$lookCount files and directories processed, $fixCount fixed.") if T(File => 2);
2556        };
2557        # Check for an error.
2558        if ($@) {
2559            Confess("SetPermissions error: $@");
2560        }
2561    }
2562    
2563    =head3 GetLine
2564    
2565        my @data = Tracer::GetLine($handle);
2566    
2567    Read a line of data from a tab-delimited file.
2568    
2569    =over 4
2570    
2571    =item handle
2572    
2573    Open file handle from which to read.
2574    
2575    =item RETURN
2576    
2577    Returns a list of the fields in the record read. The fields are presumed to be
2578    tab-delimited. If we are at the end of the file, then an empty list will be
2579    returned. If an empty line is read, a single list item consisting of a null
2580    string will be returned.
2581    
2582    =back
2583    
2584    =cut
2585    
2586    sub GetLine {
2587        # Get the parameters.
2588        my ($handle) = @_;
2589        # Declare the return variable.
2590        my @retVal = ();
2591        Trace("File position is " . tell($handle) . ". EOF flag is " . eof($handle) . ".") if T(File => 4);
2592        # Read from the file.
2593        my $line = <$handle>;
2594        # Only proceed if we found something.
2595        if (defined $line) {
2596            # Remove the new-line. We are a bit over-cautious here because the file may be coming in via an
2597            # upload control and have a nonstandard EOL combination.
2598            $line =~ s/(\r|\n)+$//;
2599            # Here we do some fancy tracing to help in debugging complicated EOL marks.
2600            if (T(File => 4)) {
2601                my $escapedLine = $line;
2602                $escapedLine =~ s/\n/\\n/g;
2603                $escapedLine =~ s/\r/\\r/g;
2604                $escapedLine =~ s/\t/\\t/g;
2605                Trace("Line read: -->$escapedLine<--");
2606            }
2607            # If the line is empty, return a single empty string; otherwise, parse
2608            # it into fields.
2609            if ($line eq "") {
2610                push @retVal, "";
2611            } else {
2612                push @retVal, split /\t/,$line;
2613            }
2614        } else {
2615            # Trace the reason the read failed.
2616            Trace("End of file: $!") if T(File => 3);
2617        }
2618        # Return the result.
2619        return @retVal;
2620    }
2621    
2622    =head3 PutLine
2623    
2624        Tracer::PutLine($handle, \@fields, $eol);
2625    
2626    Write a line of data to a tab-delimited file. The specified field values will be
2627    output in tab-separated form, with a trailing new-line.
2628    
2629    =over 4
2630    
2631    =item handle
2632    
2633    Output file handle.
2634    
2635    =item fields
2636    
2637    List of field values.
2638    
2639    =item eol (optional)
2640    
2641    End-of-line character (default is "\n").
2642    
2643    =back
2644    
2645    =cut
2646    
2647    sub PutLine {
2648        # Get the parameters.
2649        my ($handle, $fields, $eol) = @_;
2650        # Write the data.
2651        print $handle join("\t", @{$fields}) . ($eol || "\n");
2652    }
2653    
2654    
2655    =head3 PrintLine
2656    
2657        Tracer::PrintLine($line);
2658    
2659    Print a line of text with a trailing new-line.
2660    
2661    =over 4
2662    
2663    =item line
2664    
2665    Line of text to print.
2666    
2667    =back
2668    
2669    =cut
2670    
2671    sub PrintLine {
2672        # Get the parameters.
2673        my ($line) = @_;
2674        # Print the line.
2675        print "$line\n";
2676    }
2677    
2678    
2679    =head2 Other Useful Methods
2680    
2681    =head3 ParseParm
2682    
2683        my $listValue = Tracer::ParseParm($string);
2684    
2685    Convert a parameter into a list reference. If the parameter is undefined,
2686    an undefined value will be returned. Otherwise, it will be parsed as a
2687    comma-separated list of values.
2688    
2689    =over 4
2690    
2691    =item string
2692    
2693    Incoming string.
2694    
2695    =item RETURN
2696    
2697    Returns a reference to a list of values, or C<undef> if the incoming value
2698    was undefined.
2699    
2700    =back
2701    
2702    =cut
2703    
2704    sub ParseParm {
2705        # Get the parameters.
2706        my ($string) = @_;
2707        # Declare the return variable.
2708        my $retVal;
2709        # Check for data.
2710        if (defined $string) {
2711            # We have some, so split it into a list.
2712            $retVal = [ split /\s*,\s*/, $string];
2713                  }                  }
2714        # Return the result.
2715        return $retVal;
2716          }          }
2717          # Merge the options into the defaults.  
2718          GetOptions($optionTable, \%overrides);  =head3 Now
2719          # Translate the remaining parameters.  
2720          my @retVal = ();      my $string = Tracer::Now();
2721          for my $inputParm (@inputList) {  
2722                  push @retVal, UnEscape($inputParm);  Return a displayable time stamp containing the local time. Whatever format this
2723    method produces must be parseable by L</ParseDate>.
2724    
2725    =cut
2726    
2727    sub Now {
2728        return DisplayTime(time);
2729          }          }
2730          # Return the results.  
2731          return ($optionTable, @retVal);  =head3 DisplayTime
2732    
2733        my $string = Tracer::DisplayTime($time);
2734    
2735    Convert a time value to a displayable time stamp. Whatever format this
2736    method produces must be parseable by L</ParseDate>.
2737    
2738    =over 4
2739    
2740    =item time
2741    
2742    Time to display, in seconds since the epoch, or C<undef> if the time is unknown.
2743    
2744    =item RETURN
2745    
2746    Returns a displayable time, or C<(n/a)> if the incoming time is undefined.
2747    
2748    =back
2749    
2750    =cut
2751    
2752    sub DisplayTime {
2753        my ($time) = @_;
2754        my $retVal = "(n/a)";
2755        if (defined $time) {
2756            my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($time);
2757            $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .
2758                      _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);
2759        }
2760        return $retVal;
2761    }
2762    
2763    # Pad a number to 2 digits.
2764    sub _p2 {
2765        my ($value) = @_;
2766        $value = "0$value" if ($value < 10);
2767        return $value;
2768    }
2769    
2770    =head3 Escape
2771    
2772        my $codedString = Tracer::Escape($realString);
2773    
2774    Escape a string for use in a command. Tabs will be replaced by C<\t>, new-lines
2775    replaced by C<\n>, carriage returns will be deleted, and backslashes will be doubled. The
2776    result is to reverse the effect of L</UnEscape>.
2777    
2778    =over 4
2779    
2780    =item realString
2781    
2782    String to escape.
2783    
2784    =item RETURN
2785    
2786    Escaped equivalent of the real string.
2787    
2788    =back
2789    
2790    =cut
2791    
2792    sub Escape {
2793        # Get the parameter.
2794        my ($realString) = @_;
2795        # Initialize the return variable.
2796        my $retVal = "";
2797        # Loop through the parameter string, looking for sequences to escape.
2798        while (length $realString > 0) {
2799            # Look for the first sequence to escape.
2800            if ($realString =~ /^(.*?)([\n\t\r\\])/) {
2801                # Here we found it. The text preceding the sequence is in $1. The sequence
2802                # itself is in $2. First, move the clear text to the return variable.
2803                $retVal .= $1;
2804                # Strip the processed section off the real string.
2805                $realString = substr $realString, (length $2) + (length $1);
2806                # Get the matched character.
2807                my $char = $2;
2808                # If we have a CR, we are done.
2809                if ($char ne "\r") {
2810                    # It's not a CR, so encode the escape sequence.
2811                    $char =~ tr/\t\n/tn/;
2812                    $retVal .= "\\" . $char;
2813                }
2814            } else {
2815                # Here there are no more escape sequences. The rest of the string is
2816                # transferred unmodified.
2817                $retVal .= $realString;
2818                $realString = "";
2819            }
2820        }
2821        # Return the result.
2822        return $retVal;
2823  }  }
2824    
2825  =head3 UnEscape  =head3 UnEscape
2826    
2827  C<< my $realString = Tracer::UnEscape($codedString); >>      my $realString = Tracer::UnEscape($codedString);
2828    
2829  Replace escape sequences with their actual equivalents. C<\b> will be replaced by a space,  Replace escape sequences with their actual equivalents. C<\t> will be replaced by
2830  C<\t> by a tab, C<\n> by a new-line character, and C<\\> by a back-slash.  a tab, C<\n> by a new-line character, and C<\\> by a backslash. C<\r> codes will
2831    be deleted.
2832    
2833  =over 4  =over 4
2834    
# Line 555  Line 2850 
2850          my ($codedString) = @_;          my ($codedString) = @_;
2851          # Initialize the return variable.          # Initialize the return variable.
2852          my $retVal = "";          my $retVal = "";
2853        # Only proceed if the incoming string is nonempty.
2854        if (defined $codedString) {
2855          # Loop through the parameter string, looking for escape sequences. We can't do          # Loop through the parameter string, looking for escape sequences. We can't do
2856          # translating because it causes problems with the escaped slash. ("\\b" becomes          # translating because it causes problems with the escaped slash. ("\\t" becomes
2857          # "\ " no matter what we do.)          # "\<tab>" no matter what we do.)
2858          while (length $codedString > 0) {          while (length $codedString > 0) {
2859                  # Look for the first escape sequence.                  # Look for the first escape sequence.
2860                  if ($codedString =~ /^(.*?)\\(\\|b|n|t)/) {              if ($codedString =~ /^(.*?)\\(\\|n|t|r)/) {
2861                          # Here we found it. The text preceding the sequence is in $1. The sequence                          # Here we found it. The text preceding the sequence is in $1. The sequence
2862                          # itself is in $2. First, move the clear text to the return variable.                          # itself is in $2. First, move the clear text to the return variable.
2863                          $retVal .= $1;                          $retVal .= $1;
2864                          $codedString = substr $codedString, (2 + length $1);                          $codedString = substr $codedString, (2 + length $1);
2865                          # Decode the escape sequence.                  # Get the escape value.
2866                          my $char = $2;                          my $char = $2;
2867                          $char =~ tr/\\btn/\\ \t\n/;                  # If we have a "\r", we are done.
2868                    if ($char ne 'r') {
2869                        # Here it's not an 'r', so we convert it.
2870                        $char =~ tr/\\tn/\\\t\n/;
2871                          $retVal .= $char;                          $retVal .= $char;
2872                    }
2873                } else {
2874                    # Here there are no more escape sequences. The rest of the string is
2875                    # transferred unmodified.
2876                    $retVal .= $codedString;
2877                    $codedString = "";
2878                }
2879            }
2880        }
2881        # Return the result.
2882        return $retVal;
2883    }
2884    
2885    =head3 Percent
2886    
2887        my $percent = Tracer::Percent($number, $base);
2888    
2889    Returns the percent of the base represented by the given number. If the base
2890    is zero, returns zero.
2891    
2892    =over 4
2893    
2894    =item number
2895    
2896    Percent numerator.
2897    
2898    =item base
2899    
2900    Percent base.
2901    
2902    =item RETURN
2903    
2904    Returns the percentage of the base represented by the numerator.
2905    
2906    =back
2907    
2908    =cut
2909    
2910    sub Percent {
2911        # Get the parameters.
2912        my ($number, $base) = @_;
2913        # Declare the return variable.
2914        my $retVal = 0;
2915        # Compute the percent.
2916        if ($base != 0) {
2917            $retVal = $number * 100 / $base;
2918        }
2919        # Return the result.
2920        return $retVal;
2921    }
2922    
2923    =head3 Constrain
2924    
2925        my $constrained = Constrain($value, $min, $max);
2926    
2927    Modify a numeric value to bring it to a point in between a maximum and a minimum.
2928    
2929    =over 4
2930    
2931    =item value
2932    
2933    Value to constrain.
2934    
2935    =item min (optional)
2936    
2937    Minimum permissible value. If this parameter is undefined, no minimum constraint will be applied.
2938    
2939    =item max (optional)
2940    
2941    Maximum permissible value. If this parameter is undefined, no maximum constraint will be applied.
2942    
2943    =item RETURN
2944    
2945    Returns the incoming value, constrained according to the other parameters.
2946    
2947    =back
2948    
2949    =cut
2950    
2951    sub Constrain {
2952        # Get the parameters.
2953        my ($value, $min, $max) = @_;
2954        # Declare the return variable.
2955        my $retVal = $value;
2956        # Apply the minimum constraint.
2957        if (defined $min && $retVal < $min) {
2958            $retVal = $min;
2959        }
2960        # Apply the maximum constraint.
2961        if (defined $max && $retVal > $max) {
2962            $retVal = $max;
2963        }
2964        # Return the result.
2965        return $retVal;
2966    }
2967    
2968    =head3 Min
2969    
2970        my $min = Min($value1, $value2, ... $valueN);
2971    
2972    Return the minimum argument. The arguments are treated as numbers.
2973    
2974    =over 4
2975    
2976    =item $value1, $value2, ... $valueN
2977    
2978    List of numbers to compare.
2979    
2980    =item RETURN
2981    
2982    Returns the lowest number in the list.
2983    
2984    =back
2985    
2986    =cut
2987    
2988    sub Min {
2989        # Get the parameters. Note that we prime the return value with the first parameter.
2990        my ($retVal, @values) = @_;
2991        # Loop through the remaining parameters, looking for the lowest.
2992        for my $value (@values) {
2993            if ($value < $retVal) {
2994                $retVal = $value;
2995            }
2996        }
2997        # Return the minimum found.
2998        return $retVal;
2999    }
3000    
3001    =head3 Max
3002    
3003        my $max = Max($value1, $value2, ... $valueN);
3004    
3005    Return the maximum argument. The arguments are treated as numbers.
3006    
3007    =over 4
3008    
3009    =item $value1, $value2, ... $valueN
3010    
3011    List of numbers to compare.
3012    
3013    =item RETURN
3014    
3015    Returns the highest number in the list.
3016    
3017    =back
3018    
3019    =cut
3020    
3021    sub Max {
3022        # Get the parameters. Note that we prime the return value with the first parameter.
3023        my ($retVal, @values) = @_;
3024        # Loop through the remaining parameters, looking for the highest.
3025        for my $value (@values) {
3026            if ($value > $retVal) {
3027                $retVal = $value;
3028            }
3029        }
3030        # Return the maximum found.
3031        return $retVal;
3032    }
3033    
3034    =head3 Strip
3035    
3036        my $string = Tracer::Strip($line);
3037    
3038    Strip all line terminators off a string. This is necessary when dealing with files
3039    that may have been transferred back and forth several times among different
3040    operating environments.
3041    
3042    =over 4
3043    
3044    =item line
3045    
3046    Line of text to be stripped.
3047    
3048    =item RETURN
3049    
3050    The same line of text with all the line-ending characters chopped from the end.
3051    
3052    =back
3053    
3054    =cut
3055    
3056    sub Strip {
3057        # Get a copy of the parameter string.
3058        my ($string) = @_;
3059        my $retVal = (defined $string ? $string : "");
3060        # Strip the line terminator characters.
3061        $retVal =~ s/(\r|\n)+$//g;
3062        # Return the result.
3063        return $retVal;
3064    }
3065    
3066    =head3 Pad
3067    
3068        my $paddedString = Tracer::Pad($string, $len, $left, $padChar);
3069    
3070    Pad a string to a specified length. The pad character will be a
3071    space, and the padding will be on the right side unless specified
3072    in the third parameter.
3073    
3074    =over 4
3075    
3076    =item string
3077    
3078    String to be padded.
3079    
3080    =item len
3081    
3082    Desired length of the padded string.
3083    
3084    =item left (optional)
3085    
3086    TRUE if the string is to be left-padded; otherwise it will be padded on the right.
3087    
3088    =item padChar (optional)
3089    
3090    Character to use for padding. The default is a space.
3091    
3092    =item RETURN
3093    
3094    Returns a copy of the original string with the pad character added to the
3095    specified end so that it achieves the desired length.
3096    
3097    =back
3098    
3099    =cut
3100    
3101    sub Pad {
3102        # Get the parameters.
3103        my ($string, $len, $left, $padChar) = @_;
3104        # Compute the padding character.
3105        if (! defined $padChar) {
3106            $padChar = " ";
3107        }
3108        # Compute the number of spaces needed.
3109        my $needed = $len - length $string;
3110        # Copy the string into the return variable.
3111        my $retVal = $string;
3112        # Only proceed if padding is needed.
3113        if ($needed > 0) {
3114            # Create the pad string.
3115            my $pad = $padChar x $needed;
3116            # Affix it to the return value.
3117            if ($left) {
3118                $retVal = $pad . $retVal;
3119                  } else {                  } else {
3120                          # Here there are no more escape sequences. The rest of the string is              $retVal .= $pad;
                         # transferred unmodified.  
                         $retVal .= $codedString;  
                         $codedString = "";  
3121                  }                  }
3122          }          }
3123          # Return the result.          # Return the result.
3124          return $retVal;          return $retVal;
3125  }  }
3126    
3127  =head3 ParseRecord  =head3 EOF
3128    
3129  C<< my @fields = Tracer::ParseRecord($line); >>  This is a constant that is lexically greater than any useful string.
3130    
3131  Parse a tab-delimited data line. The data line is split into field values. Embedded tab  =cut
3132  and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.  
3133  These will automatically be converted.  sub EOF {
3134        return "\xFF\xFF\xFF\xFF\xFF";
3135    }
3136    
3137    =head3 TICK
3138    
3139        my @results = TICK($commandString);
3140    
3141    Perform a back-tick operation on a command. If this is a Windows environment, any leading
3142    dot-slash (C<./> will be removed. So, for example, if you were doing
3143    
3144        `./protein.cgi`
3145    
3146    from inside a CGI script, it would work fine in Unix, but would issue an error message
3147    in Windows complaining that C<'.'> is not a valid command. If instead you code
3148    
3149        TICK("./protein.cgi")
3150    
3151    it will work correctly in both environments.
3152    
3153  =over 4  =over 4
3154    
3155  =item line  =item commandString
3156    
3157  Line of data containing the tab-delimited fields.  The command string to pass to the system.
3158    
3159  =item RETURN  =item RETURN
3160    
3161  Returns a list of the fields found in the data line.  Returns the standard output from the specified command, as a list.
3162    
3163  =back  =back
3164    
3165  =cut  =cut
3166    #: Return Type @;
3167  sub ParseRecord {  sub TICK {
3168          # Get the parameter.      # Get the parameters.
3169          my ($line) = @_;      my ($commandString) = @_;
3170          # Remove the trailing new-line, if any.      # Chop off the dot-slash if this is Windows.
3171          chomp $line;      if ($FIG_Config::win_mode) {
3172          # 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;  
                 $value =~ s/\\n/"\n"/ge;  
3173          }          }
3174          # Return the result.      # Activate the command and return the result.
3175          return @retVal;      return `$commandString`;
3176  }  }
3177    
 =head3 Merge  
3178    
3179  C<< my @mergedList = Tracer::Merge(@inputList); >>  =head3 CommaFormat
3180    
3181  Sort a list of strings and remove duplicates.      my $formatted = Tracer::CommaFormat($number);
3182    
3183    Insert commas into a number.
3184    
3185  =over 4  =over 4
3186    
3187  =item inputList  =item number
3188    
3189  List of scalars to sort and merge.  A sequence of digits.
3190    
3191  =item RETURN  =item RETURN
3192    
3193  Returns a list containing the same elements sorted in ascending order with duplicates  Returns the same digits with commas strategically inserted.
 removed.  
3194    
3195  =back  =back
3196    
3197  =cut  =cut
3198    
3199  sub Merge {  sub CommaFormat {
3200          # Get the input list in sort order.      # Get the parameters.
3201          my @inputList = sort @_;      my ($number) = @_;
3202          # Only proceed if the list has at least two elements.      # Pad the length up to a multiple of three.
3203          if (@inputList > 1) {      my $padded = "$number";
3204                  # Now we want to move through the list splicing out duplicates.      $padded = " " . $padded while length($padded) % 3 != 0;
3205                  my $i = 0;      # This is a fancy PERL trick. The parentheses in the SPLIT pattern
3206                  while ($i < @inputList) {      # cause the delimiters to be included in the output stream. The
3207                          # Get the current entry.      # GREP removes the empty strings in between the delimiters.
3208                          my $thisEntry = $inputList[$i];      my $retVal = join(",", grep { $_ ne '' } split(/(...)/, $padded));
3209                          # Find out how many elements duplicate the current entry.      # Clean out the spaces.
3210                          my $j = $i + 1;      $retVal =~ s/ //g;
3211                          my $dup1 = $i + 1;      # Return the result.
3212                          while ($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.  
                         $i++;  
                 }  
         }  
         # Return the merged list.  
         return @inputList;  
3213  }  }
3214    
 =head3 GetFile  
3215    
3216  C<< my @fileContents = Tracer::GetFile($fileName); >>  =head3 CompareLists
3217    
3218  Return the entire contents of a file.      my ($inserted, $deleted) = Tracer::CompareLists(\@newList, \@oldList, $keyIndex);
3219    
3220    Compare two lists of tuples, and return a hash analyzing the differences. The lists
3221    are presumed to be sorted alphabetically by the value in the $keyIndex column.
3222    The return value contains a list of items that are only in the new list
3223    (inserted) and only in the old list (deleted).
3224    
3225  =over 4  =over 4
3226    
3227  =item fileName  =item newList
3228    
3229  Name of the file to read.  Reference to a list of new tuples.
3230    
3231    =item oldList
3232    
3233    Reference to a list of old tuples.
3234    
3235    =item keyIndex (optional)
3236    
3237    Index into each tuple of its key field. The default is 0.
3238    
3239  =item RETURN  =item RETURN
3240    
3241  In a list context, returns the entire file as a list with the line terminators removed.  Returns a 2-tuple consisting of a reference to the list of items that are only in the new
3242  In a scalar context, returns the entire file as a string.  list (inserted) followed by a reference to the list of items that are only in the old
3243    list (deleted).
3244    
3245  =back  =back
3246    
3247  =cut  =cut
3248    
3249  sub GetFile {  sub CompareLists {
3250          # Get the parameters.          # Get the parameters.
3251          my ($fileName) = @_;      my ($newList, $oldList, $keyIndex) = @_;
3252          # Declare the return variable.      if (! defined $keyIndex) {
3253          my @retVal = ();          $keyIndex = 0;
3254          # Open the file for input.      }
3255          my $ok = open INPUTFILE, "<$fileName";      # Declare the return variables.
3256          if (!$ok) {      my ($inserted, $deleted) = ([], []);
3257                  # If we had an error, trace it. We will automatically return a null value.      # Loop through the two lists simultaneously.
3258                  Trace("Could not open \"$fileName\" for input.") if T(0);      my ($newI, $oldI) = (0, 0);
3259        my ($newN, $oldN) = (scalar @{$newList}, scalar @{$oldList});
3260        while ($newI < $newN || $oldI < $oldN) {
3261            # Get the current object in each list. Note that if one
3262            # of the lists is past the end, we'll get undef.
3263            my $newItem = $newList->[$newI];
3264            my $oldItem = $oldList->[$oldI];
3265            if (! defined($newItem) || defined($oldItem) && $newItem->[$keyIndex] gt $oldItem->[$keyIndex]) {
3266                # The old item is not in the new list, so mark it deleted.
3267                push @{$deleted}, $oldItem;
3268                $oldI++;
3269            } elsif (! defined($oldItem) || $oldItem->[$keyIndex] gt $newItem->[$keyIndex]) {
3270                # The new item is not in the old list, so mark it inserted.
3271                push @{$inserted}, $newItem;
3272                $newI++;
3273          } else {          } else {
3274                  # Read the whole file into the return variable, stripping off an terminator              # The item is in both lists, so push forward.
3275          # characters.              $oldI++;
3276          my $lineCount = 0;              $newI++;
                 while (my $line = <INPUTFILE>) {  
             $lineCount++;  
             $line =~ s/(\r|\n)+$//g;  
                         push @retVal, $line;  
                 }  
                 # Close it.  
                 close INPUTFILE;  
         my $actualLines = @retVal;  
         Trace("$lineCount lines read from $fileName. $actualLines processed.") if T(0);  
3277          }          }
         # Return the file's contents in the desired format.  
     if (wantarray) {  
             return @retVal;  
     } else {  
         return join "\n", @retVal;  
3278      }      }
3279        # Return the result.
3280        return ($inserted, $deleted);
3281  }  }
3282    
3283  =head3 QTrace  =head3 Cmp
3284    
3285  C<< my $data = QTrace($format); >>      my $cmp = Tracer::Cmp($a, $b);
3286    
3287  Return the queued trace data in the specified format.  This method performs a universal sort comparison. Each value coming in is
3288    separated into a leading text part and a trailing number part. The text
3289    part is string compared, and if both parts are equal, then the number
3290    parts are compared numerically. A stream of just numbers or a stream of
3291    just strings will sort correctly, and a mixed stream will sort with the
3292    numbers first. Strings with a label and a number will sort in the
3293    expected manner instead of lexically.
3294    
3295  =over 4  =over 4
3296    
3297  =item format  =item a
3298    
3299  C<html> to format the data as an HTML list, C<text> to format it as straight text.  First item to compare.
3300    
3301    =item b
3302    
3303    Second item to compare.
3304    
3305    =item RETURN
3306    
3307    Returns a negative number if the first item should sort first (is less), a positive
3308    number if the first item should sort second (is greater), and a zero if the items are
3309    equal.
3310    
3311  =back  =back
3312    
3313  =cut  =cut
3314    
3315  sub QTrace {  sub Cmp {
3316          # Get the parameter.      # Get the parameters.
3317          my ($format) = @_;      my ($a, $b) = @_;
3318          # Create the return variable.      # Declare the return value.
3319          my $retVal = "";      my $retVal;
3320          # Process according to the format.      # Check for nulls.
3321          if ($format =~ m/^HTML$/i) {      if (! defined($a)) {
3322                  # Convert the queue into an HTML list.          $retVal = (! defined($b) ? 0 : -1);
3323                  $retVal = "<ul>\n";      } elsif (! defined($b)) {
3324                  for my $line (@Queue) {          $retVal = 1;
3325                          my $escapedLine = CGI::escapeHTML($line);      } else {
3326                          $retVal .= "<li>$escapedLine</li>\n";          # Here we have two real values. Parse the two strings.
3327            $a =~ /^(\D*)(\d*)$/;
3328            my $aParsed = [$1, $2];
3329            $b =~ /^(\D*)(\d*)$/;
3330            my $bParsed = [$1, $2];
3331            # Compare the string parts.
3332            $retVal = $aParsed->[0] cmp $bParsed->[0];
3333            if (! $retVal) {
3334                $retVal = $aParsed->[1] <=> $bParsed->[1];
3335                  }                  }
                 $retVal .= "</ul>\n";  
         } elsif ($format =~ m/^TEXT$/i) {  
                 # Convert the queue into a list of text lines.  
                 $retVal = join("\n", @Queue) . "\n";  
3336          }          }
3337          # Clear the queue.      # Return the result.
         @Queue = ();  
         # Return the formatted list.  
3338          return $retVal;          return $retVal;
3339  }  }
3340    
3341  =head3 Confess  =head2 CGI Script Utilities
3342    
3343  C<< Confess($message); >>  =head3 ScriptSetup (deprecated)
3344    
3345  Trace the call stack and abort the program with the specified message. The stack      my ($cgi, $varHash) = ScriptSetup($noTrace);
 trace will only appear if the trace level for this package is 1 or more. When used with  
 the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.  
 So, for example  
3346    
3347  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>  Perform standard tracing and debugging setup for scripts. The value returned is
3348    the CGI object followed by a pre-built variable hash. At the end of the script,
3349    the client should call L</ScriptFinish> to output the web page.
3350    
3351  Will abort the program with a stack trace if the value of C<$recNum> is negative.  This method calls L</ETracing> to configure tracing, which allows the tracing
3352    to be configured via the emergency tracing form on the debugging control panel.
3353    Tracing will then be turned on automatically for all programs that use the L</ETracing>
3354    method, which includes every program that uses this method or L</StandardSetup>.
3355    
3356  =over 4  =over 4
3357    
3358  =item message  =item noTrace (optional)
3359    
3360  Message to include in the trace.  If specified, tracing will be suppressed. This is useful if the script wants to set up
3361    tracing manually.
3362    
3363    =item RETURN
3364    
3365    Returns a two-element list consisting of a CGI query object and a variable hash for
3366    the output page.
3367    
3368  =back  =back
3369    
3370  =cut  =cut
3371    
3372  sub Confess {  sub ScriptSetup {
3373          # Get the parameters.          # Get the parameters.
3374          my ($message) = @_;      my ($noTrace) = @_;
3375          # Trace the call stack.      # Get the CGI query object.
3376          Cluck($message) if T(1);      my $cgi = CGI->new();
3377          # Abort the program.      # Set up tracing if it's not suppressed.
3378          croak(">>> $message");      ETracing($cgi) unless $noTrace;
3379        # Create the variable hash.
3380        my $varHash = { results => '' };
3381        # Return the query object and variable hash.
3382        return ($cgi, $varHash);
3383    }
3384    
3385    =head3 ScriptFinish (deprecated)
3386    
3387        ScriptFinish($webData, $varHash);
3388    
3389    Output a web page at the end of a script. Either the string to be output or the
3390    name of a template file can be specified. If the second parameter is omitted,
3391    it is assumed we have a string to be output; otherwise, it is assumed we have the
3392    name of a template file. The template should have the variable C<DebugData>
3393    specified in any form that invokes a standard script. If debugging mode is turned
3394    on, a form field will be put in that allows the user to enter tracing data.
3395    Trace messages will be placed immediately before the terminal C<BODY> tag in
3396    the output, formatted as a list.
3397    
3398    A typical standard script would loook like the following.
3399    
3400        BEGIN {
3401            # Print the HTML header.
3402            print "CONTENT-TYPE: text/html\n\n";
3403  }  }
3404        use Tracer;
3405        use CGI;
3406        use FIG;
3407        # ... more uses ...
3408    
3409  =head3 Assert      my ($cgi, $varHash) = ScriptSetup();
3410        eval {
3411            # ... get data from $cgi, put it in $varHash ...
3412        };
3413        if ($@) {
3414            Trace("Script Error: $@") if T(0);
3415        }
3416        ScriptFinish("Html/MyTemplate.html", $varHash);
3417    
3418  C<< Assert($condition1, $condition2, ... $conditionN); >>  The idea here is that even if the script fails, you'll see trace messages and
3419    useful output.
3420    
3421  Return TRUE if all the conditions are true. This method can be used in conjunction with  =over 4
 the OR operator and the L</Confess> method, B<Assert> can function as a debugging assert.  
 So, for example  
3422    
3423  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>  =item webData
3424    
3425  Will abort the program with a stack trace if the value of C<$recNum> is negative.  A string containing either the full web page to be written to the output or the
3426    name of a template file from which the page is to be constructed. If the name
3427    of a template file is specified, then the second parameter must be present;
3428    otherwise, it must be absent.
3429    
3430    =item varHash (optional)
3431    
3432    If specified, then a reference to a hash mapping variable names for a template
3433    to their values. The template file will be read into memory, and variable markers
3434    will be replaced by data in this hash reference.
3435    
3436    =back
3437    
3438  =cut  =cut
3439  sub Assert {  
3440      my $retVal = 1;  sub ScriptFinish {
3441      LOOP: for my $condition (@_) {      # Get the parameters.
3442          if (! $condition) {      my ($webData, $varHash) = @_;
3443              $retVal = 0;      # Check for a template file situation.
3444              last LOOP;      my $outputString;
3445        if (defined $varHash) {
3446            # Here we have a template file. We need to determine the template type.
3447            my $template;
3448            if ($FIG_Config::template_url && $webData =~ /\.php$/) {
3449                $template = "$FIG_Config::template_url/$webData";
3450            } else {
3451                $template = "<<$webData";
3452            }
3453            $outputString = PageBuilder::Build($template, $varHash, "Html");
3454        } else {
3455            # Here the user gave us a raw string.
3456            $outputString = $webData;
3457        }
3458        # Check for trace messages.
3459        if ($Destination ne "NONE" && $TraceLevel > 0) {
3460            # We have trace messages, so we want to put them at the end of the body. This
3461            # is either at the end of the whole string or at the beginning of the BODY
3462            # end-tag.
3463            my $pos = length $outputString;
3464            if ($outputString =~ m#</body>#gi) {
3465                $pos = (pos $outputString) - 7;
3466            }
3467            # If the trace messages were queued, we unroll them. Otherwise, we display the
3468            # destination.
3469            my $traceHtml;
3470            if ($Destination eq "QUEUE") {
3471                $traceHtml = QTrace('Html');
3472            } elsif ($Destination =~ /^>>(.+)$/) {
3473                # Here the tracing output it to a file. We code it as a hyperlink so the user
3474                # can copy the file name into the clipboard easily.
3475                my $actualDest = $1;
3476                $traceHtml = "<p>Tracing output to $actualDest.</p>\n";
3477            } else {
3478                # Here we have one of the special destinations.
3479                $traceHtml = "<P>Tracing output type is $Destination.</p>\n";
3480          }          }
3481            substr $outputString, $pos, 0, $traceHtml;
3482      }      }
3483      return $retVal;      # Write the output string.
3484        print $outputString;
3485  }  }
3486    
3487  =head3 Cluck  =head3 GenerateURL
3488    
3489  C<< Cluck($message); >>      my $queryUrl = Tracer::GenerateURL($page, %parameters);
3490    
3491  Trace the call stack. Note that for best results, you should qualify the call with a  Generate a GET-style URL for the specified page with the specified parameter
3492  trace condition. For example,  names and values. The values will be URL-escaped automatically. So, for
3493    example
3494    
3495  C<< Cluck("Starting record parse.") if T(3); >>      Tracer::GenerateURL("form.cgi", type => 1, string => "\"high pass\" or highway")
3496    
3497  will only trace the stack if the trace level for the package is 3 or more.  would return
3498    
3499        form.cgi?type=1;string=%22high%20pass%22%20or%20highway
3500    
3501  =over 4  =over 4
3502    
3503  =item message  =item page
3504    
3505  Message to include in the trace.  Page URL.
3506    
3507    =item parameters
3508    
3509    Hash mapping parameter names to parameter values.
3510    
3511    =item RETURN
3512    
3513    Returns a GET-style URL that goes to the specified page and passes in the
3514    specified parameters and values.
3515    
3516  =back  =back
3517    
3518  =cut  =cut
3519    
3520  sub Cluck {  sub GenerateURL {
3521          # Get the parameters.          # Get the parameters.
3522          my ($message) = @_;      my ($page, %parameters) = @_;
3523      # Trace what's happening.      # Prime the return variable with the page URL.
3524      Trace("Stack trace for event: $message");      my $retVal = $page;
3525          my $confession = longmess($message);      # Loop through the parameters, creating parameter elements in a list.
3526          # Convert the confession to a series of trace messages. Note we skip any      my @parmList = map { "$_=" . uri_escape($parameters{$_}) } keys %parameters;
3527      # messages relating to calls into Tracer.      # If the list is nonempty, tack it on.
3528          for my $line (split /\s*\n/, $confession) {      if (@parmList) {
3529                  Trace($line) if ($line !~ /Tracer\.pm/);          $retVal .= "?" . join(";", @parmList);
3530          }          }
3531        # Return the result.
3532        return $retVal;
3533  }  }
3534    
3535  =head3 Min  =head3 ApplyURL
3536    
3537  C<< my $min = Min($value1, $value2, ... $valueN); >>      Tracer::ApplyURL($table, $target, $url);
3538    
3539  Return the minimum argument. The arguments are treated as numbers.  Run through a two-dimensional table (or more accurately, a list of lists), converting the
3540    I<$target> column to HTML text having a hyperlink to a URL in the I<$url> column. The
3541    URL column will be deleted by this process and the target column will be HTML-escaped.
3542    
3543    This provides a simple way to process the results of a database query into something
3544    displayable by combining a URL with text.
3545