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

Diff of /FigKernelPackages/Tracer.pm

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

revision 1.9, Wed May 4 03:05:12 2005 UTC revision 1.102, Thu May 8 22:52:30 2008 UTC
# Line 1  Line 1 
1    # -*- perl -*-
2    ########################################################################
3    # Copyright (c) 2003-2006 University of Chicago and Fellowship
4    # for Interpretations of Genomes. All Rights Reserved.
5    #
6    # This file is part of the SEED Toolkit.
7    #
8    # The SEED Toolkit is free software. You can redistribute
9    # it and/or modify it under the terms of the SEED Toolkit
10    # Public License.
11    #
12    # You should have received a copy of the SEED Toolkit Public License
13    # along with this program; if not write to the University of Chicago
14    # at info@ci.uchicago.edu or the Fellowship for Interpretation of
15    # Genomes at veronika@thefig.info or download a copy from
16    # http://www.theseed.org/LICENSE.TXT.
17    ########################################################################
18    
19  package Tracer;  package Tracer;
20    
21          require Exporter;          require Exporter;
22          @ISA = ('Exporter');          @ISA = ('Exporter');
23          @EXPORT = qw(Trace T TSetup QTrace Confess Cluck Min Max Assert);      @EXPORT = qw(Trace T TSetup QTrace Confess Cluck Min Max Assert Open OpenDir TICK StandardSetup EmergencyKey ETracing Constrain Insure ChDir Emergency Warn);
24          @EXPORT_OK = qw(GetFile GetOptions Merge MergeOptions ParseCommand ParseRecord UnEscape Escape);      @EXPORT_OK = qw(GetFile GetOptions Merge MergeOptions ParseCommand ParseRecord UnEscape Escape PrintLine PutLine);
25          use strict;          use strict;
26          use Carp qw(longmess croak);      use Carp qw(longmess croak carp);
27          use CGI;          use CGI;
28        use Cwd;
29          use FIG_Config;          use FIG_Config;
30      use PageBuilder;      use PageBuilder;
31        use Digest::MD5;
32        use File::Basename;
33        use File::Path;
34        use File::stat;
35        use LWP::UserAgent;
36        use Time::HiRes 'gettimeofday';
37        use URI::Escape;
38        use Time::Local;
39        use POSIX qw(strftime);
40        use Time::Zone;
41    
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 36  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  sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and
90  specifies that messages should be output as HTML paragraphs. The parameters are formatted  specifies that messages should be sent to the standard output.
91  to make it easier to input tracing configuration on a web form.  
92    To turn on tracing for ALL categories, use an asterisk. The call below sets every category to
93    level 3 and writes the output to the standard error output. This sort of thing might be
94    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  my $LastCategory = "main";  # name of the last category interrogated
207    my $LastLevel = 0;          # level of the last test call
208    my $SetupCount = 0;         # number of times TSetup called
209    my $AllTrace = 0;           # TRUE if we are tracing all categories.
210    my $SavedCGI;               # CGI object passed to ETracing
211    umask 2;                    # Fix the damn umask so everything is group-writable.
212    
213  =head2 Public Methods  =head2 Tracing Methods
214    
215    =head3 Setups
216    
217        my $count = Tracer::Setups();
218    
219    Return the number of times L</TSetup> has been called.
220    
221    This method allows for the creation of conditional tracing setups where, for example, we
222    may want to set up tracing if nobody else has done it before us.
223    
224    =cut
225    
226    sub Setups {
227        return $SetupCount;
228    }
229    
230  =head3 TSetup  =head3 TSetup
231    
232  C<< TSetup($categoryList, $target); >>      TSetup($categoryList, $target);
233    
234  This method is used to specify the trace options. The options are stored as package data  This method is used to specify the trace options. The options are stored as package data
235  and interrogated by the L</Trace> and L</T> methods.  and interrogated by the L</Trace> and L</T> methods.
# Line 93  Line 245 
245    
246  The destination for the trace output. To send the trace output to a file, specify the file  The destination for the trace output. To send the trace output to a file, specify the file
247  name preceded by a ">" symbol. If a double symbol is used (">>"), then the data is appended  name preceded by a ">" symbol. If a double symbol is used (">>"), then the data is appended
248  to the file. Otherwise the file is cleared before tracing begins. In addition to sending  to the file. Otherwise the file is cleared before tracing begins. Precede the first ">"
249  the trace messages to a file, you can specify a special destination. C<HTML> will cause  symbol with a C<+> to echo output to a file AND to the standard output. In addition to
250  tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>  sending the trace messages to a file, you can specify a special destination. C<HTML> will
251    cause tracing to the standard output with each line formatted as an HTML paragraph. C<TEXT>
252  will cause tracing to the standard output as ordinary text. C<ERROR> will cause trace  will cause tracing to the standard output as ordinary text. C<ERROR> will cause trace
253  messages to be sent to the standard error output as ordinary text. C<QUEUE> will cause trace  messages to be sent to the standard error output as ordinary text. C<QUEUE> will cause trace
254  messages to be stored in a queue for later retrieval by the L</QTrace> method. C<WARN> will  messages to be stored in a queue for later retrieval by the L</QTrace> method. C<WARN> will
# Line 113  Line 266 
266          my @categoryData = split /\s+/, $categoryList;          my @categoryData = split /\s+/, $categoryList;
267          # Extract the trace level.          # Extract the trace level.
268          $TraceLevel = shift @categoryData;          $TraceLevel = shift @categoryData;
269          # Build the category hash.      # Presume category-based tracing until we learn otherwise.
270        $AllTrace = 0;
271        # Build the category hash. Note that if we find a "*", we turn on non-category
272        # tracing. We must also clear away any pre-existing data.
273        %Categories = ( main => 1 );
274          for my $category (@categoryData) {          for my $category (@categoryData) {
275                  $Categories{$category} = 1;          if ($category eq '*') {
276                $AllTrace = 1;
277            } else {
278                $Categories{lc $category} = 1;
279            }
280          }          }
281          # Now we need to process the destination information. The most important special          # Now we need to process the destination information. The most important special
282          # case is the single ">", which requires we clear the file first. After doing      # case is when we're writing to a file. This is indicated by ">" (overwrite) and
283          # so, we tack on another ">" sign so that future trace messages are appended.      # ">>" (append). A leading "+" for either indicates that we are also writing to
284        # the standard output (tee mode).
285        if ($target =~ m/^\+?>>?/) {
286            if ($target =~ m/^\+/) {
287                $TeeFlag = 1;
288                $target = substr($target, 1);
289            }
290          if ($target =~ m/^>[^>]/) {          if ($target =~ m/^>[^>]/) {
291                # We need to initialize the file (which clears it).
292                  open TRACEFILE, $target;                  open TRACEFILE, $target;
293                  print TRACEFILE Now() . " Tracing initialized.\n";              print TRACEFILE "[" . Now() . "] [notice] [Tracer] Tracing initialized.\n";
294                  close TRACEFILE;                  close TRACEFILE;
295                # Set to append mode now that the file has been cleared.
296                  $Destination = ">$target";                  $Destination = ">$target";
297          } else {          } else {
298                $Destination = $target;
299            }
300        } else {
301                  $Destination = uc($target);                  $Destination = uc($target);
302          }          }
303        # Increment the setup counter.
304        $SetupCount++;
305  }  }
306    
307  =head3 SetLevel  =head3 SetLevel
308    
309  C<< Tracer::SetLevel($newLevel); >>      Tracer::SetLevel($newLevel);
310    
311  Modify the trace level. A higher trace level will cause more messages to appear.  Modify the trace level. A higher trace level will cause more messages to appear.
312    
# Line 150  Line 324 
324      $TraceLevel = $_[0];      $TraceLevel = $_[0];
325  }  }
326    
327  =head3 Now  =head3 ParseDate
   
 C<< my $string = Tracer::Now(); >>  
   
 Return a displayable time stamp containing the local time.  
   
 =cut  
   
 sub Now {  
         my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime(time);  
         my $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .  
                                  _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);  
         return $retVal;  
 }  
   
 # Pad a number to 2 digits.  
 sub _p2 {  
         my ($value) = @_;  
         $value = "0$value" if ($value < 10);  
         return $value;  
 }  
   
 =head3 LogErrors  
   
 C<< Tracer::LogErrors($fileName); >>  
   
 Route the standard error output to a log file.  
   
 =over 4  
   
 =item fileName  
   
 Name of the file to receive the error output.  
   
 =back  
328    
329  =cut      my $time = Tracer::ParseDate($dateString);
330    
331  sub LogErrors {  Convert a date into a PERL time number. This method expects a date-like string
332          # Get the file name.  and parses it into a number. The string must be vaguely date-like or it will
333          my ($fileName) = @_;  return an undefined value. Our requirement is that a month and day be
334          # Open the file as the standard error output.  present and that three pieces of the date string (time of day, month and day,
335          open STDERR, '>', $fileName;  year) be separated by likely delimiters, such as spaces, commas, and such-like.
 }  
336    
337  =head3 ReadOptions  If a time of day is present, it must be in military time with two digits for
338    everything but the hour.
339    
340  C<< my %options = Tracer::ReadOptions($fileName); >>  The year must be exactly four digits.
341    
342  Read a set of options from a file. Each option is encoded in a line of text that has the  Additional stuff can be in the string. We presume it's time zones or weekdays or something
343  format  equally innocuous. This means, however, that a sufficiently long sentence with date-like
344    parts in it may be interpreted as a date. Hopefully this will not be a problem.
345    
346  I<optionName>C<=>I<optionValue>C<; >I<comment>  It should be guaranteed that this method will parse the output of the L</Now> function.
347    
348  The option name must consist entirely of letters, digits, and the punctuation characters  The parameters are as follows.
 C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank  
 character is a semi-colon will be ignored. The return hash will map each option name to  
 the corresponding option value.  
349    
350  =over 4  =over 4
351    
352  =item fileName  =item dateString
353    
354  Name of the file containing the option data.  The date string to convert.
355    
356  =item RETURN  =item RETURN
357    
358  Returns a hash mapping the option names specified in the file to their corresponding option  Returns a PERL time, that is, a number of seconds since the epoch, or C<undef> if
359  value.  the date string is invalid. A valid date string must contain a month and day.
360    
361  =back  =back
362    
363  =cut  =cut
364    
365  sub ReadOptions {  # Universal month conversion table.
366          # Get the parameters.  use constant MONTHS => {    Jan =>  0, January   =>  0, '01' =>  0,  '1' =>  0,
367          my ($fileName) = @_;                              Feb =>  1, February  =>  1, '02' =>  1,  '2' =>  1,
368          # Open the file.                              Mar =>  2, March     =>  2, '03' =>  2,  '3' =>  2,
369          (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");                              Apr =>  3, April     =>  3, '04' =>  3,  '4' =>  3,
370          # Count the number of records read.                              May =>  4, May       =>  4, '05' =>  4,  '5' =>  4,
371          my ($records, $comments) = 0;                              Jun =>  5, June      =>  5, '06' =>  5,  '6' =>  5,
372          # Create the return hash.                              Jul =>  6, July      =>  6, '07' =>  6,  '7' =>  6,
373          my %retVal = ();                              Aug =>  7, August    =>  7, '08' =>  7,  '8' =>  7,
374          # Loop through the file, accumulating key-value pairs.                              Sep =>  8, September =>  8, '09' =>  8,  '9' =>  8,
375          while (my $line = <CONFIGFILE>) {                              Oct =>  9, October  =>   9, '10' =>  9,
376                  # Denote we've read a line.                              Nov => 10, November =>  10, '11' => 10,
377                  $records++;                              Dec => 11, December =>  11, '12' => 11
378                  # Determine the line type.                          };
                 if ($line =~ /^\s*[\n\r]/) {  
                         # A blank line is a comment.  
                         $comments++;  
                 } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {  
                         # Here we have an option assignment.  
                         retVal{$1} = $2;  
                 } elsif ($line =~ /^\s*;/) {  
                         # Here we have a text comment.  
                         $comments++;  
                 } else {  
                         # Here we have an invalid line.  
                         Trace("Invalid option statement in record $records.") if T(0);  
                 }  
         }  
         # Return the hash created.  
         return %retVal;  
 }  
   
 =head3 GetOptions  
   
 C<< Tracer::GetOptions(\%defaults, \%options); >>  
   
 Merge a specified set of options into a table of defaults. This method takes two hash references  
 as input and uses the data from the second to update the first. If the second does not exist,  
 there will be no effect. An error will be thrown if one of the entries in the second hash does not  
 exist in the first.  
   
 Consider the following example.  
   
 C<< my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options); >>  
   
 In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and  
 B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of  
 B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and  
 the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level  
 will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as  
   
 C<< {databaseType => 'Oracle'} >>  
   
 an error will occur because the B<databaseType> option does not exist.  
   
 =over 4  
   
 =item defaults  
   
 Table of default option values.  
   
 =item options  
   
 Table of overrides, if any.  
   
 =item RETURN  
   
 Returns a reference to the default table passed in as the first parameter.  
   
 =back  
   
 =cut  
379    
380  sub GetOptions {  sub ParseDate {
381          # Get the parameters.          # Get the parameters.
382          my ($defaults, $options) = @_;      my ($dateString) = @_;
383          # Check for overrides.      # Declare the return variable.
384          if ($options) {      my $retVal;
385                  # Loop through the overrides.      # Find the month and day of month. There are two ways that can happen. We check for the
386                  while (my ($option, $setting) = each %{$options}) {      # numeric style first. That way, if the user's done something like "Sun 12/22", then we
387                          # Insure this override exists.      # won't be fooled into thinking the month is Sunday.
388                          if (!exists $defaults->{$option}) {      if ($dateString =~ m#\b(\d{1,2})/(\d{1,2})\b# || $dateString =~ m#\b(\w+)\s(\d{1,2})\b#) {
389                                  croak "Unrecognized option $option encountered.";          my ($mon, $mday) = (MONTHS->{$1}, $2);
390            # Insist that the month and day are valid.
391            if (defined($mon) && $2 >= 1 && $2 <= 31) {
392                # Find the time.
393                my ($hour, $min, $sec) = (0, 0, 0);
394                if ($dateString =~ /\b(\d{1,2}):(\d{2}):(\d{2})\b/) {
395                    ($hour, $min, $sec) = ($1, $2, $3);
396                }
397                # Find the year.
398                my $year;
399                if ($dateString =~ /\b(\d{4})\b/) {
400                    $year = $1;
401                          } else {                          } else {
402                                  # Apply the override.                  # Get the default year, which is this one. Note we must convert it to
403                                  $defaults->{$option} = $setting;                  # the four-digit value expected by "timelocal".
404                    (undef, undef, undef, undef, undef, $year) = localtime();
405                    $year += 1900;
406                          }                          }
407                $retVal = timelocal($sec, $min, $hour, $mday, $mon, $year);
408                  }                  }
409          }          }
410          # Return the merged table.      # Return the result.
411          return $defaults;      return $retVal;
412  }  }
413    
414  =head3 MergeOptions  =head3 LogErrors
415    
416  C<< Tracer::MergeOptions(\%table, \%defaults); >>      Tracer::LogErrors($fileName);
417    
418  Merge default values into a hash table. This method looks at the key-value pairs in the  Route the standard error output to a log file.
 second (default) hash, and if a matching key is not found in the first hash, the default  
 pair is copied in. The process is similar to L</GetOptions>, but there is no error-  
 checking and no return value.  
419    
420  =over 4  =over 4
421    
422  =item table  =item fileName
   
 Hash table to be updated with the default values.  
   
 =item defaults  
423    
424  Default values to be merged into the first hash table if they are not already present.  Name of the file to receive the error output.
425    
426  =back  =back
427    
428  =cut  =cut
429    
430  sub MergeOptions {  sub LogErrors {
431          # Get the parameters.      # Get the file name.
432          my ($table, $defaults) = @_;      my ($fileName) = @_;
433          # Loop through the defaults.      # Open the file as the standard error output.
434          while (my ($key, $value) = each %{$defaults}) {      open STDERR, '>', $fileName;
                 if (!exists $table->{$key}) {  
                         $table->{$key} = $value;  
                 }  
         }  
435  }  }
436    
437  =head3 Trace  =head3 Trace
438    
439  C<< Trace($message); >>      Trace($message);
440    
441  Write a trace message to the target location specified in L</TSetup>. If there has not been  Write a trace message to the target location specified in L</TSetup>. If there has not been
442  any prior call to B<TSetup>.  any prior call to B<TSetup>.
# Line 371  Line 454 
454  sub Trace {  sub Trace {
455          # Get the parameters.          # Get the parameters.
456          my ($message) = @_;          my ($message) = @_;
457        # Strip off any line terminators at the end of the message. We will add
458        # new-line stuff ourselves.
459        my $stripped = Strip($message);
460        # Compute the caller information.
461        my ($callPackage, $callFile, $callLine) = caller();
462        my $callFileTitle = basename($callFile);
463        # Check the caller.
464        my $callerInfo = ($callFileTitle ne "Tracer.pm" ? " [$callFileTitle $callLine]" : "");
465          # Get the timestamp.          # Get the timestamp.
466          my $timeStamp = Now();          my $timeStamp = Now();
467          # Format the message. Note we strip off any line terminators at the end.      # Build the prefix.
468          my $formatted = "$timeStamp <$LastCategory>: " . Strip($message);      my $level = $LevelNames[$LastLevel] || "($LastLevel)";
469        my $prefix = "[$timeStamp] [$level] [$LastCategory]$callerInfo";
470        # Format the message.
471        my $formatted = "$prefix $stripped";
472          # Process according to the destination.          # Process according to the destination.
473          if ($Destination eq "TEXT") {          if ($Destination eq "TEXT") {
474                  # Write the message to the standard output.                  # Write the message to the standard output.
475                  print "$formatted\n";                  print "$formatted\n";
476          } elsif ($Destination eq "ERROR") {          } elsif ($Destination eq "ERROR") {
477                  # Write the message to the error output.          # Write the message to the error output. Here, we want our prefix fields.
478                  print STDERR "$formatted\n";                  print STDERR "$formatted\n";
479        } elsif ($Destination eq "WARN") {
480            # Emit the message to the standard error output. It is presumed that the
481            # error logger will add its own prefix fields, the notable exception being
482            # the caller info.
483            print STDERR "$callerInfo$stripped\n";
484          } elsif ($Destination eq "QUEUE") {          } elsif ($Destination eq "QUEUE") {
485                  # Push the message into the queue.                  # Push the message into the queue.
486                  push @Queue, "$formatted";                  push @Queue, "$formatted";
487          } elsif ($Destination eq "HTML") {          } elsif ($Destination eq "HTML") {
488                  # Convert the message to HTML and write it to the standard output.                  # Convert the message to HTML and write it to the standard output.
489                  my $escapedMessage = CGI::escapeHTML($message);          my $escapedMessage = CGI::escapeHTML($stripped);
490                  print "<p>$formatted</p>\n";          print "<p>$timeStamp $LastCategory $LastLevel: $escapedMessage</p>\n";
     } elsif ($Destination eq "WARN") {  
        # Emit the message as a warning.  
        warn $message;  
491          } elsif ($Destination =~ m/^>>/) {          } elsif ($Destination =~ m/^>>/) {
492                  # Write the trace message to an output file.                  # Write the trace message to an output file.
493                  open TRACING, $Destination;          open(TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";
494                  print TRACING "$formatted\n";                  print TRACING "$formatted\n";
495                  close TRACING;                  close TRACING;
496            # If the Tee flag is on, echo it to the standard output.
497            if ($TeeFlag) {
498                print "$formatted\n";
499            }
500          }          }
501  }  }
502    
503  =head3 T  =head3 T
504    
505  C<< my $switch = T($category, $traceLevel); >>      my $switch = T($category, $traceLevel);
506    
507          or          or
508    
509  C<< my $switch = T($traceLevel); >>      my $switch = T($traceLevel);
510    
511  Return TRUE if the trace level is at or above a specified value and the specified category  Return TRUE if the trace level is at or above a specified value and the specified category
512  is active, else FALSE. If no category is specified, the caller's package name is used.  is active, else FALSE. If no category is specified, the caller's package name is used.
# Line 439  Line 539 
539                  my ($category, $traceLevel) = @_;                  my ($category, $traceLevel) = @_;
540                  if (!defined $traceLevel) {                  if (!defined $traceLevel) {
541                          # Here we have no category, so we need to get the calling package.                          # Here we have no category, so we need to get the calling package.
542                # The calling package is normally the first parameter. If it is
543                # omitted, the first parameter will be the tracelevel. So, the
544                # first thing we do is shift the so-called category into the
545                # $traceLevel variable where it belongs.
546                          $traceLevel = $category;                          $traceLevel = $category;
547                          my ($package, $fileName, $line) = caller;                          my ($package, $fileName, $line) = caller;
548              # If there is no calling package, we default to "main".              # If there is no calling package, we default to "main".
549                          if (!$package) {                          if (!$package) {
550                  $category = "main";                  $category = "main";
551                          } else {                          } else {
552                                  $category = $package;                  my @cats = split /::/, $package;
553                    $category = $cats[$#cats];
554                          }                          }
555                  }                  }
556          # Save the category name.          # Save the category name and level.
557          $LastCategory = $category;          $LastCategory = $category;
558                  # Use the category and tracelevel to compute the result.          $LastLevel = $traceLevel;
559                  $retVal = ($traceLevel <= $TraceLevel && exists $Categories{$category});          # Convert it to lower case before we hash it.
560            $category = lc $category;
561            # Validate the trace level.
562            if (ref $traceLevel) {
563                Confess("Bad trace level.");
564            } elsif (ref $TraceLevel) {
565                Confess("Bad trace config.");
566            }
567            # Make the check. Note that level 0 shows even if the category is turned off.
568            $retVal = ($traceLevel <= $TraceLevel && ($traceLevel == 0 || $AllTrace || exists $Categories{$category}));
569      }      }
570          # Return the computed result.          # Return the computed result.
571      return $retVal;      return $retVal;
572  }  }
573    
574  =head3 ParseCommand  =head3 QTrace
   
 C<< my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList); >>  
   
 Parse a command line consisting of a list of parameters. The initial parameters may be option  
 specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped  
 off and merged into a table of default options. The remainder of the command line is  
 returned as a list of positional arguments. For example, consider the following invocation.  
   
 C<< my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words); >>  
   
 In this case, the list @words will be treated as a command line. There are two options available,  
 B<errors> and B<logFile>. If @words has the following format  
   
 C<< -logFile=error.log apple orange rutabaga >>  
   
 then at the end of the invocation, C<$options> will be  
   
 C<< { errors => 0, logFile => 'error.log' } >>  
   
 and C<@arguments> will contain  
575    
576  C<< apple orange rutabaga >>      my $data = QTrace($format);
577    
578  The parser allows for some escape sequences. See L</UnEscape> for a description. There is no  Return the queued trace data in the specified format.
 support for quote characters.  
579    
580  =over 4  =over 4
581    
582  =item optionTable  =item format
   
 Table of default options.  
   
 =item inputList  
   
 List of words on the command line.  
   
 =item RETURN  
583    
584  Returns a reference to the option table and a list of the positional arguments.  C<html> to format the data as an HTML list, C<text> to format it as straight text.
585    
586  =back  =back
587    
588  =cut  =cut
589    
590  sub ParseCommand {  sub QTrace {
591          # Get the parameters.      # Get the parameter.
592          my ($optionTable, @inputList) = @_;      my ($format) = @_;
593          # Process any options in the input list.      # Create the return variable.
594          my %overrides = ();      my $retVal = "";
595          while ((@inputList > 0) && ($inputList[0] =~ /^-/)) {      # Only proceed if there is an actual queue.
596                  # Get the current option.      if (@Queue) {
597                  my $arg = shift @inputList;          # Process according to the format.
598                  # Pull out the option name.          if ($format =~ m/^HTML$/i) {
599                  $arg =~ /^-([^=]*)/g;              # Convert the queue into an HTML list.
600                  my $name = $1;              $retVal = "<ul>\n";
601                  # Check for an option value.              for my $line (@Queue) {
602                  if ($arg =~ /\G=(.*)$/g) {                  my $escapedLine = CGI::escapeHTML($line);
603                          # Here we have a value for the option.                  $retVal .= "<li>$escapedLine</li>\n";
604                          $overrides{$name} = UnEscape($1);              }
605                $retVal .= "</ul>\n";
606            } elsif ($format =~ m/^TEXT$/i) {
607                # Convert the queue into a list of text lines.
608                $retVal = join("\n", @Queue) . "\n";
609            }
610            # Clear the queue.
611            @Queue = ();
612        }
613        # Return the formatted list.
614        return $retVal;
615    }
616    
617    =head3 Confess
618    
619        Confess($message);
620    
621    Trace the call stack and abort the program with the specified message. When used with
622    the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.
623    So, for example
624    
625        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
626    
627    Will abort the program with a stack trace if the value of C<$recNum> is negative.
628    
629    =over 4
630    
631    =item message
632    
633    Message to include in the trace.
634    
635    =back
636    
637    =cut
638    
639    sub Confess {
640        # Get the parameters.
641        my ($message) = @_;
642        # Set up the category and level.
643        $LastCategory = "(confess)";
644        $LastLevel = 0;
645        if (! defined($FIG_Config::no_tool_hdr)) {
646            # Here we have a tool header. Display its length so that the user can adjust the line numbers.
647            my $toolHeaderFile = "$FIG_Config::fig_disk/dist/releases/current/$FIG_Config::arch/tool_hdr";
648            # Only proceed if the tool header file is actually present.
649            if (-f $toolHeaderFile) {
650                my $fh;
651                if (open $fh, "<$toolHeaderFile") {
652                    my @lines = <$fh>;
653                    Trace("Tool header has " . scalar(@lines) . " lines.");
654                }
655            }
656        }
657        # Trace the call stack.
658        Cluck($message);
659        # Abort the program.
660        croak(">>> $message");
661    }
662    
663    =head3 Warn
664    
665        Warn($message);
666    
667    This method traces an important message. If an RSS feed is configured
668    (via I<FIG_Config::error_feed>) and the tracing destination is C<WARN>,
669    then the message will be echoed to the feed. In general, a tracing
670    destination of C<WARN> indicates that the caller is running as a web
671    service in a production environment; however, this is not a requirement.
672    
673    The L</Cluck> method calls this one for its final message. Since
674    L</Confess> calls L</Cluck>, this means that any error which is caught
675    and confessed will put something in the feed. This insures that someone
676    will be alerted relatively quickly when a failure occurs.
677    
678    =over 4
679    
680    =item message
681    
682    Message to be traced.
683    
684    =back
685    
686    =cut
687    
688    sub Warn {
689        # Get the parameters.
690        my ($message) = @_;
691        # Trace the message.
692        Trace($message);
693        # Check for debug mode.
694        my $debugMode = (exists $Categories{feed} && $TraceLevel > 0);
695        # An error here would be disastrous. Note, however, that we aren't too worried
696        # about losing events. The error log is always available for the occasions where
697        # we mess up. Note that if debug mode is specified, we do this stuff even in a
698        # test environment.
699        eval {
700            # Do we need to put this in the RSS feed?
701            if ($FIG_Config::error_feed && ($Destination eq 'WARN' || $debugMode)) {
702                # Yes. We now need to compute the date, the link, and the title.
703                # First, the date, in a very specific format.
704                my $date = strftime("%a, %02e %b %H:%M:%S %Y ", localtime) .
705                    (tz_local_offset() / 30);
706                Trace("Generating RSS feed. Date = $date.") if $debugMode;
707                # Environment data goes in here. We start with the date.
708                my $environment = "$date.  ";
709                # If we need to recap the message (because it's too long to be a title), we'll
710                # put it in here.
711                my $recap;
712                # Copy the message and remove excess space.
713                my $title = $message;
714                $title =~ s/\s+/ /gs;
715                # If it's too long, we have to split it up.
716                if (length $title > 60) {
717                    # Put the full message in the environment string.
718                    $recap = $title;
719                    # Excerpt it as the title.
720                    $title = substr($title, 0, 50) . "...";
721                }
722                # If we have a CGI object, then this is a web error. Otherwise, it's
723                # command-line.
724                if (defined $SavedCGI) {
725                    # We're in a web service. The environment is the user's IP, and the link
726                    # is the URL that got us here.
727                    my $key = $ENV{HTTP_X_FORWARDED_FOR} || $ENV{REMOTE_ADDR};
728                    $environment .= "Event Reported at IP address $key.";
729                    my $url = $SavedCGI->url(-full => 1, -query => 1);
730                    # We need the user agent string and (if available) the referrer.
731                    # The referrer will be the link.
732                    $environment .= "User Agent $ENV{HTTP_USER_AGENT}";
733                    if ($ENV{HTTP_REFERER}) {
734                        my $link = $ENV{HTTP_REFERER};
735                        $environment .= " referred from <a href=\"$link\">$link</a>.";
736                  } else {                  } else {
737                          # Here there is no value, so we use 1.                      $environment .= " referrer unknown.";
                         $overrides{$name} = 1;  
738                  }                  }
739                    # Close off the sentence with the original link.
740                    $environment .= " URL of error is <a href=\"$url\">$url</a>.";
741                } else {
742                    # No CGI object, so we're a command-line tool. Use the tracing
743                    # key and the PID as the user identifier, and add the command.
744                    my $key = EmergencyKey();
745                    $environment .= "Event Reported by $key Process $$. Command $ENV{_}.";
746                }
747                # Build a GUID. We use the current time, the title, and the process ID,
748                # then digest the result.
749                my $guid = Digest::MD5::md5_base64(gettimeofday(), $title, $$);
750                # Finally, the description. This is a stack trace plus various environmental stuff.
751                my $stackTrace = "";
752                my @trace = LongMess();
753                # Only proceed if we got something back.
754                if (scalar(@trace) > 0) {
755                    $trace[0] =~ s/Tracer::Warn.+?called/Event occurred/;
756                    $stackTrace = "Stack trace:<pre>" . join("\n", @trace, "</pre>");
757                }
758                # We got the stack trace. Now it's time to put it all together.
759                # We have a goofy thing here in that we need to HTML-escape some sections of the description
760                # twice. They will be escaped once here, and then once when written by XML::Simple. They are
761                # unescaped once when processed by the RSS reader, and stuff in the description is treated as
762                # HTML. So, anything escaped here is treated as a literal when viewed in the RSS reader, but
763                # our <br>s and <pre>s are used to format the description.
764                $recap = (defined $recap ? "<em>" . CGI::escapeHTML($recap) . "</em><br /><br />" : "");
765                my $description = "$recap$environment  $stackTrace";
766                Trace("Unescaped description is:\n$description") if $debugMode;
767                # Okay, we have all the pieces. Create a hash of the new event.
768                my $newItem = { title => $title,
769                                description => $description,
770                                category => $LastCategory,
771                                pubDate => $date,
772                                guid => $guid,
773                               };
774                # We need XML capability for this.
775                require XML::Simple;
776                # The RSS document goes in here.
777                my $rss;
778                # Get the name of the RSS file. It's in the FIG temporary directory.
779                my $fileName = "$FIG_Config::temp/$FIG_Config::error_feed";
780                # Does it exist?
781                if (-s $fileName) {
782                    # Slurp it in.
783                    $rss = XML::Simple::XMLin($fileName, ForceArray => ['item']);
784                } else {
785                    my $size = -s $fileName;
786                    # Create an empty channel.
787                    $rss = {
788                        channel => {
789                            title => 'NMPDR Warning Feed',
790                            link => "$FIG_Config::temp_url/$FIG_Config::error_feed",
791                            description => "Important messages regarding the status of the NMPDR.",
792                            generator => "NMPDR Trace Facility",
793                            docs => "http://blogs.law.harvard.edu/tech/rss",
794                            item => []
795                        },
796                    };
797                }
798                # Get the channel object.
799                my $channel = $rss->{channel};
800                # Update the last-build date.
801                $channel->{lastBuildDate} = $date;
802                # Get the item array.
803                my $items = $channel->{item};
804                # Insure it has only 100 entries.
805                while (scalar @{$items} > 100) {
806                    pop @{$items};
807                }
808                # Add our new item at the front.
809                unshift @{$items}, $newItem;
810                # Create the XML. Note we do not include the root or the declaration. XML Simple can't handle
811                # the requirements for those.
812                my $xml = XML::Simple::XMLout($rss, NoAttr => 1, RootName => undef, XmlDecl => '');
813                # Here we put in the root and declaration. The problem is that the root has to have the version attribute
814                # in it. So, we suppress the root and do it by hand, and that requires suppressing the declaration, too.
815                $xml = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<rss version=\"2.0\">$xml\n</rss>";
816                # We don't use Open here because we can't afford an error.
817                if (open XMLOUT, ">$fileName") {
818                    print XMLOUT $xml;
819                    close XMLOUT;
820                }
821            }
822        };
823        # We only worry about problems in debug mode. The loss of an error message is an annoyance, not a
824        # crisis.
825        if ($@ && $debugMode) {
826            my $error = $@;
827            Trace("Feed Error: $error");
828          }          }
829          # Merge the options into the defaults.  }
830          GetOptions($optionTable, \%overrides);  
831          # Translate the remaining parameters.  =head3 Assert
832    
833        Assert($condition1, $condition2, ... $conditionN);
834    
835    Return TRUE if all the conditions are true. This method can be used in conjunction with
836    the OR operator and the L</Confess> method as a debugging assert.
837    So, for example
838    
839        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
840    
841    Will abort the program with a stack trace if the value of C<$recNum> is negative.
842    
843    =cut
844    sub Assert {
845        my $retVal = 1;
846        LOOP: for my $condition (@_) {
847            if (! $condition) {
848                $retVal = 0;
849                last LOOP;
850            }
851        }
852        return $retVal;
853    }
854    
855    =head3 Cluck
856    
857        Cluck($message);
858    
859    Trace the call stack. Note that for best results, you should qualify the call with a
860    trace condition. For example,
861    
862        Cluck("Starting record parse.") if T(3);
863    
864    will only trace the stack if the trace level for the package is 3 or more.
865    
866    =over 4
867    
868    =item message
869    
870    Message to include in the trace.
871    
872    =back
873    
874    =cut
875    
876    sub Cluck {
877        # Get the parameters.
878        my ($message) = @_;
879        # Trace what's happening.
880        Trace("Stack trace for event: $message");
881        # Get the stack trace.
882        my @trace = LongMess();
883        # Convert the trace to a series of messages.
884        for my $line (@trace) {
885            # Replace the tab at the beginning with spaces.
886            $line =~ s/^\t/    /;
887            # Trace the line.
888            Trace($line);
889        }
890        # Issue a warning. This displays the event message and inserts it into the RSS error feed.
891        Warn($message);
892    }
893    
894    =head3 LongMess
895    
896        my @lines = Tracer::LongMess();
897    
898    Return a stack trace with all tracing methods removed. The return will be in the form of a list
899    of message strings.
900    
901    =cut
902    
903    sub LongMess {
904        # Declare the return variable.
905          my @retVal = ();          my @retVal = ();
906          for my $inputParm (@inputList) {      my $confession = longmess("");
907                  push @retVal, UnEscape($inputParm);      for my $line (split /\s*\n/, $confession) {
908            unless ($line =~ /Tracer\.pm/) {
909                # Here we have a line worth keeping. Push it onto the result list.
910                push @retVal, $line;
911          }          }
912          # Return the results.      }
913          return ($optionTable, @retVal);      # Return the result.
914        return @retVal;
915  }  }
916    
917  =head3 Escape  =head3 ScriptSetup (deprecated)
918    
919  C<< my $codedString = Tracer::Escape($realString); >>      my ($cgi, $varHash) = ScriptSetup($noTrace);
920    
921  Escape a string for use in a command length. Spaces will be replaced by C<\b>,  Perform standard tracing and debugging setup for scripts. The value returned is
922  tabs replaced by C<\t>, new-lines replaced by C<\n>, and backslashes will be  the CGI object followed by a pre-built variable hash. At the end of the script,
923  doubled. The effect is to exactly reverse the effect of L</UnEscape>.  the client should call L</ScriptFinish> to output the web page.
924    
925    This method calls L</ETracing> to configure tracing, which allows the tracing
926    to be configured via the emergency tracing form on the debugging control panel.
927    Tracing will then be turned on automatically for all programs that use the L</ETracing>
928    method, which includes every program that uses this method or L</StandardSetup>.
929    
930  =over 4  =over 4
931    
932  =item realString  =item noTrace (optional)
933    
934  String to escape.  If specified, tracing will be suppressed. This is useful if the script wants to set up
935    tracing manually.
936    
937  =item RETURN  =item RETURN
938    
939  Escaped equivalent of the real string.  Returns a two-element list consisting of a CGI query object and a variable hash for
940    the output page.
941    
942  =back  =back
943    
944  =cut  =cut
945    
946  sub Escape {  sub ScriptSetup {
947        # Get the parameters.
948        my ($noTrace) = @_;
949        # Get the CGI query object.
950        my $cgi = CGI->new();
951        # Set up tracing if it's not suppressed.
952        ETracing($cgi) unless $noTrace;
953        # Create the variable hash.
954        my $varHash = { results => '' };
955        # Return the query object and variable hash.
956        return ($cgi, $varHash);
957    }
958    
959    =head3 ETracing
960    
961        ETracing($parameter);
962    
963    Set up emergency tracing. Emergency tracing is tracing that is turned
964    on automatically for any program that calls this method. The emergency
965    tracing parameters are stored in a a file identified by a tracing key.
966    If this method is called with a CGI object, then the tracing key is
967    taken from a cookie. If it is called with no parameters, then the tracing
968    key is taken from an environment variable. If it is called with a string,
969    the tracing key is that string.
970    
971    =over 4
972    
973    =item parameter
974    
975    A parameter from which the tracing key is computed. If it is a scalar,
976    that scalar is used as the tracing key. If it is a CGI object, the
977    tracing key is taken from the C<IP> cookie. If it is omitted, the
978    tracing key is taken from the C<TRACING> environment variable. If it
979    is a CGI object and emergency tracing is not on, the C<Trace> and
980    C<TF> parameters will be used to determine the type of tracing.
981    
982    =back
983    
984    =cut
985    
986    sub ETracing {
987          # Get the parameter.          # Get the parameter.
988          my ($realString) = @_;      my ($parameter) = @_;
989          # Initialize the return variable.      # Check for CGI mode.
990          my $retVal = "";      if (defined $parameter && ref $parameter eq 'CGI') {
991          # Loop through the parameter string, looking for sequences to escape.          $SavedCGI = $parameter;
992          while (length $realString > 0) {      } else {
993                  # Look for the first sequence to escape.          $SavedCGI = undef;
994                  if ($realString =~ /^(.*?)([ \n\t\\])/) {      }
995                          # Here we found it. The text preceding the sequence is in $1. The sequence      # Default to no tracing except errors.
996                          # itself is in $2. First, move the clear text to the return variable.      my ($tracing, $dest) = ("0", "WARN");
997                          $retVal .= $1;      # Check for emergency tracing.
998                          $realString = substr $realString, (length $2 + length $1);      my $tkey = EmergencyKey($parameter);
999                          # Encode the escape sequence.      my $emergencyFile = EmergencyFileName($tkey);
1000                          my $char = $2;      if (-e $emergencyFile) {
1001                          $char =~ tr/ \t\n/btn/;          # We have the file. Read in the data.
1002                          $retVal .= "\\" . $char;          my @tracing = GetFile($emergencyFile);
1003            # Pull off the time limit.
1004            my $expire = shift @tracing;
1005            # Convert it to seconds.
1006            $expire *= 3600;
1007            # Check the file data.
1008            my $stat = stat($emergencyFile);
1009            my ($now) = gettimeofday;
1010            if ($now - $stat->mtime > $expire) {
1011                # Delete the expired file.
1012                unlink $emergencyFile;
1013            } else {
1014                # Emergency tracing is on. Pull off the destination and
1015                # the trace level;
1016                $dest = shift @tracing;
1017                my $level = shift @tracing;
1018                # Convert the destination to a real tracing destination.
1019                # temp directory.
1020                $dest = EmergencyTracingDest($tkey, $dest);
1021                # Insure Tracer is specified.
1022                my %moduleHash = map { $_ => 1 } @tracing;
1023                $moduleHash{Tracer} = 1;
1024                # Set the trace parameter.
1025                $tracing = join(" ", $level, sort keys %moduleHash);
1026            }
1027        } elsif (defined $SavedCGI) {
1028            # There's no emergency tracing, but we have a CGI object, so check
1029            # for tracing from the form parameters.
1030            if ($SavedCGI->param('Trace')) {
1031                # Here the user has requested tracing via a form.
1032                $dest = ($SavedCGI->param('TF') ? ">$FIG_Config::temp/Trace$$.log" : "QUEUE");
1033                $tracing = $SavedCGI->param('Trace') . " Tracer";
1034            }
1035        }
1036        # Setup the tracing we've determined from all the stuff above.
1037        TSetup($tracing, $dest);
1038        # Check to see if we're a web script.
1039        if (defined $SavedCGI) {
1040            # Yes we are. Trace the form and environment data.
1041            TraceParms($SavedCGI);
1042            # Check for RAW mode. In raw mode, we print a fake header so that we see everything
1043            # emitted by the script in its raw form.
1044            if (T(Raw => 3)) {
1045                print CGI::header(-type => 'text/plain', -tracing => 'Raw');
1046            }
1047        }
1048    }
1049    
1050    =head3 EmergencyFileName
1051    
1052        my $fileName = Tracer::EmergencyFileName($tkey);
1053    
1054    Return the emergency tracing file name. This is the file that specifies
1055    the tracing information.
1056    
1057    =over 4
1058    
1059    =item tkey
1060    
1061    Tracing key for the current program.
1062    
1063    =item RETURN
1064    
1065    Returns the name of the file to contain the emergency tracing information.
1066    
1067    =back
1068    
1069    =cut
1070    
1071    sub EmergencyFileName {
1072        # Get the parameters.
1073        my ($tkey) = @_;
1074        # Compute the emergency tracing file name.
1075        return "$FIG_Config::temp/Emergency$tkey.txt";
1076    }
1077    
1078    =head3 EmergencyFileTarget
1079    
1080        my $fileName = Tracer::EmergencyFileTarget($tkey);
1081    
1082    Return the emergency tracing target file name. This is the file that receives
1083    the tracing output for file-based tracing.
1084    
1085    =over 4
1086    
1087    =item tkey
1088    
1089    Tracing key for the current program.
1090    
1091    =item RETURN
1092    
1093    Returns the name of the file to contain the trace output.
1094    
1095    =back
1096    
1097    =cut
1098    
1099    sub EmergencyFileTarget {
1100        # Get the parameters.
1101        my ($tkey) = @_;
1102        # Compute the emergency tracing file name.
1103        return "$FIG_Config::temp/trace$tkey.log";
1104    }
1105    
1106    =head3 EmergencyTracingDest
1107    
1108        my $dest = Tracer::EmergencyTracingDest($tkey, $myDest);
1109    
1110    This method converts an emergency tracing destination to a real
1111    tracing destination. The main difference is that if the
1112    destination is C<FILE> or C<APPEND>, we convert it to file
1113    output. If the destination is C<DUAL>, we convert it to file
1114    and standard output.
1115    
1116    =over 4
1117    
1118    =item tkey
1119    
1120    Tracing key for this environment.
1121    
1122    =item myDest
1123    
1124    Destination from the emergency tracing file.
1125    
1126    =item RETURN
1127    
1128    Returns a destination that can be passed into L</TSetup>.
1129    
1130    =back
1131    
1132    =cut
1133    
1134    sub EmergencyTracingDest {
1135        # Get the parameters.
1136        my ($tkey, $myDest) = @_;
1137        # Declare the return variable.
1138        my $retVal = $myDest;
1139        # Process according to the destination value.
1140        if ($myDest eq 'FILE') {
1141            $retVal = ">" . EmergencyFileTarget($tkey);
1142        } elsif ($myDest eq 'APPEND') {
1143            $retVal = ">>" . EmergencyFileTarget($tkey);
1144        } elsif ($myDest eq 'DUAL') {
1145            $retVal = "+>" . EmergencyFileTarget($tkey);
1146        } elsif ($myDest eq 'WARN') {
1147            $retVal = "WARN";
1148        }
1149        # Return the result.
1150        return $retVal;
1151    }
1152    
1153    =head3 Emergency
1154    
1155        Emergency($key, $hours, $dest, $level, @modules);
1156    
1157    Turn on emergency tracing. This method is normally invoked over the web from
1158    a debugging console, but it can also be called by the C<trace.pl> script.
1159    The caller specifies the duration of the emergency in hours, the desired tracing
1160    destination, the trace level, and a list of the trace modules to activate.
1161    For the length of the duration, when a program in an environment with the
1162    specified tracing key active invokes a Sprout CGI script, tracing will be
1163    turned on automatically. See L</TSetup> for more about tracing setup and
1164    L</ETracing> for more about emergency tracing.
1165    
1166    =over 4
1167    
1168    =item tkey
1169    
1170    The tracing key. This is used to identify the control file and the trace file.
1171    
1172    =item hours
1173    
1174    Number of hours to keep emergency tracing alive.
1175    
1176    =item dest
1177    
1178    Tracing destination. If no path information is specified for a file
1179    destination, it is put in the FIG temporary directory.
1180    
1181    =item level
1182    
1183    Tracing level. A higher level means more trace messages.
1184    
1185    =item modules
1186    
1187    A list of the tracing modules to activate.
1188    
1189    =back
1190    
1191    =cut
1192    
1193    sub Emergency {
1194        # Get the parameters.
1195        my ($tkey, $hours, $dest, $level, @modules) = @_;
1196        # Create the emergency file.
1197        my $specFile = EmergencyFileName($tkey);
1198        my $outHandle = Open(undef, ">$specFile");
1199        print $outHandle join("\n", $hours, $dest, $level, @modules, "");
1200    }
1201    
1202    =head3 EmergencyKey
1203    
1204        my $tkey = EmergencyKey($parameter);
1205    
1206    Return the Key to be used for emergency tracing. This could be an IP address,
1207     a session ID, or a user name, depending on the environment.
1208    
1209    =over 4
1210    
1211    =item parameter
1212    
1213    Parameter defining the method for finding the tracing key. If it is a scalar,
1214    then it is presumed to be the tracing key itself. If it is a CGI object, then
1215    the tracing key is taken from the C<IP> cookie. Otherwise, the tracing key is
1216    taken from the C<TRACING> environment variable.
1217    
1218    =item RETURN
1219    
1220    Returns the key to be used for labels in emergency tracing.
1221    
1222    =back
1223    
1224    =cut
1225    
1226    sub EmergencyKey {
1227        # Get the parameters.
1228        my ($parameter) = @_;
1229        # Declare the return variable.
1230        my $retVal;
1231        # Determine the parameter type.
1232        if (! defined $parameter) {
1233            # Here we're supposed to check the environment. If that fails, we
1234            # get the effective login ID.
1235            $retVal = $ENV{TRACING} || scalar getpwuid($<);
1236        } else {
1237            my $ptype = ref $parameter;
1238            if ($ptype eq 'CGI') {
1239                # Here we were invoked from a web page. Look for a cookie.
1240                $retVal = $parameter->cookie('IP');
1241            } elsif (! $ptype) {
1242                # Here the key was passed in.
1243                $retVal = $parameter;
1244            }
1245        }
1246        # If no luck finding a key, use the PID.
1247        if (! defined $retVal) {
1248            $retVal = $$;
1249        }
1250        # Return the result.
1251        return $retVal;
1252    }
1253    
1254    
1255    =head3 TraceParms
1256    
1257        Tracer::TraceParms($cgi);
1258    
1259    Trace the CGI parameters at trace level CGI => 3 and the environment variables
1260    at level CGI => 4. A self-referencing URL is traced at level CGI => 2.
1261    
1262    =over 4
1263    
1264    =item cgi
1265    
1266    CGI query object containing the parameters to trace.
1267    
1268    =back
1269    
1270    =cut
1271    
1272    sub TraceParms {
1273        # Get the parameters.
1274        my ($cgi) = @_;
1275        if (T(CGI => 2)) {
1276            # Here we trace the GET-style URL for the script.
1277            Trace("[URL] " . $cgi->url(-relative => 1, -query => 1));
1278        }
1279        if (T(CGI => 3)) {
1280            # Here we want to trace the parameter data.
1281            my @names = $cgi->param;
1282            for my $parmName (sort @names) {
1283                # Note we skip the Trace parameters, which are for our use only.
1284                if ($parmName ne 'Trace' && $parmName ne 'TF') {
1285                    my @values = $cgi->param($parmName);
1286                    Trace("[CGI] $parmName = " . join(", ", @values));
1287                }
1288            }
1289            # Display the request method.
1290            my $method = $cgi->request_method();
1291            Trace("Method: $method");
1292        }
1293        if (T(CGI => 4)) {
1294            # Here we want the environment data too.
1295            for my $envName (sort keys %ENV) {
1296                Trace("[ENV] $envName = $ENV{$envName}");
1297            }
1298        }
1299    }
1300    
1301    =head3 TraceImages
1302    
1303        Tracer::TraceImages($htmlString);
1304    
1305    Trace information about all of an html document's images. The tracing
1306    will be for type "IMG" at level 3. The image's source string
1307    will be displayed. This is generally either the URL of the image or
1308    raw data for the image itself. If the source is too long, only the first 300
1309    characters will be shown at trace level 3. The entire source will be shown,
1310    however, at trace level 4. This method is not very smart, and might catch
1311    Javascript code, but it is still useful when debugging the arcane
1312    behavior of images in multiple browser environments.
1313    
1314    =over 4
1315    
1316    =item htmlString
1317    
1318    HTML text for an outgoing web page.
1319    
1320    =back
1321    
1322    =cut
1323    
1324    sub TraceImages {
1325        # Only proceed if we're at the proper trace level.
1326        if (T(IMG => 3)) {
1327            # For performance reasons we're manipulating $_[0] instead of retrieving the string
1328            # into a variable called "$htmlString". This is because we expect html strings to be
1329            # long, and don't want to copy them any more than we have to.
1330            Trace(length($_[0]) . " characters in web page.");
1331            # Loop through the HTML, culling image tags.
1332            while ($_[0] =~ /<img\s+[^>]+?src="([^"]+)"/sgi) {
1333                # Extract the source string and determine whether or not it's too long.
1334                my $srcString = $1;
1335                my $pos = pos($_[0]) - length($srcString);
1336                my $excess = length($srcString) - 300;
1337                # We'll put the display string in here.
1338                my $srcDisplay = $srcString;
1339                # If it's a data string, split it at the comma.
1340                $srcDisplay =~ s/^(data[^,]+,)/$1\n/;
1341                # If there's no excess or we're at trace level 4, we're done. At level 3 with
1342                # a long string, however, we only show the first 300 characters.
1343                if ($excess > 0 && ! T(IMG => 4)) {
1344                    $srcDisplay = substr($srcDisplay,0,300) . "\nplus $excess characters.";
1345                }
1346                # Output the trace message.
1347                Trace("Image tag at position $pos:\n$srcDisplay");
1348            }
1349        }
1350    }
1351    
1352    
1353    =head3 ScriptFinish (deprecated)
1354    
1355        ScriptFinish($webData, $varHash);
1356    
1357    Output a web page at the end of a script. Either the string to be output or the
1358    name of a template file can be specified. If the second parameter is omitted,
1359    it is assumed we have a string to be output; otherwise, it is assumed we have the
1360    name of a template file. The template should have the variable C<DebugData>
1361    specified in any form that invokes a standard script. If debugging mode is turned
1362    on, a form field will be put in that allows the user to enter tracing data.
1363    Trace messages will be placed immediately before the terminal C<BODY> tag in
1364    the output, formatted as a list.
1365    
1366    A typical standard script would loook like the following.
1367    
1368        BEGIN {
1369            # Print the HTML header.
1370            print "CONTENT-TYPE: text/html\n\n";
1371        }
1372        use Tracer;
1373        use CGI;
1374        use FIG;
1375        # ... more uses ...
1376    
1377        my ($cgi, $varHash) = ScriptSetup();
1378        eval {
1379            # ... get data from $cgi, put it in $varHash ...
1380        };
1381        if ($@) {
1382            Trace("Script Error: $@") if T(0);
1383        }
1384        ScriptFinish("Html/MyTemplate.html", $varHash);
1385    
1386    The idea here is that even if the script fails, you'll see trace messages and
1387    useful output.
1388    
1389    =over 4
1390    
1391    =item webData
1392    
1393    A string containing either the full web page to be written to the output or the
1394    name of a template file from which the page is to be constructed. If the name
1395    of a template file is specified, then the second parameter must be present;
1396    otherwise, it must be absent.
1397    
1398    =item varHash (optional)
1399    
1400    If specified, then a reference to a hash mapping variable names for a template
1401    to their values. The template file will be read into memory, and variable markers
1402    will be replaced by data in this hash reference.
1403    
1404    =back
1405    
1406    =cut
1407    
1408    sub ScriptFinish {
1409        # Get the parameters.
1410        my ($webData, $varHash) = @_;
1411        # Check for a template file situation.
1412        my $outputString;
1413        if (defined $varHash) {
1414            # Here we have a template file. We need to determine the template type.
1415            my $template;
1416            if ($FIG_Config::template_url && $webData =~ /\.php$/) {
1417                $template = "$FIG_Config::template_url/$webData";
1418            } else {
1419                $template = "<<$webData";
1420            }
1421            $outputString = PageBuilder::Build($template, $varHash, "Html");
1422        } else {
1423            # Here the user gave us a raw string.
1424            $outputString = $webData;
1425        }
1426        # Check for trace messages.
1427        if ($Destination ne "NONE" && $TraceLevel > 0) {
1428            # We have trace messages, so we want to put them at the end of the body. This
1429            # is either at the end of the whole string or at the beginning of the BODY
1430            # end-tag.
1431            my $pos = length $outputString;
1432            if ($outputString =~ m#</body>#gi) {
1433                $pos = (pos $outputString) - 7;
1434            }
1435            # If the trace messages were queued, we unroll them. Otherwise, we display the
1436            # destination.
1437            my $traceHtml;
1438            if ($Destination eq "QUEUE") {
1439                $traceHtml = QTrace('Html');
1440            } elsif ($Destination =~ /^>>(.+)$/) {
1441                # Here the tracing output it to a file. We code it as a hyperlink so the user
1442                # can copy the file name into the clipboard easily.
1443                my $actualDest = $1;
1444                $traceHtml = "<p>Tracing output to $actualDest.</p>\n";
1445            } else {
1446                # Here we have one of the special destinations.
1447                $traceHtml = "<P>Tracing output type is $Destination.</p>\n";
1448            }
1449            substr $outputString, $pos, 0, $traceHtml;
1450        }
1451        # Write the output string.
1452        print $outputString;
1453    }
1454    
1455    =head2 Command-Line Utility Methods
1456    
1457    =head3 SendSMS
1458    
1459        my $msgID = Tracer::SendSMS($phoneNumber, $msg);
1460    
1461    Send a text message to a phone number using Clickatell. The FIG_Config file must contain the
1462    user name, password, and API ID for the relevant account in the hash reference variable
1463    I<$FIG_Config::phone>, using the keys C<user>, C<password>, and C<api_id>. For
1464    example, if the user name is C<BruceTheHumanPet>, the password is C<silly>, and the API ID
1465    is C<2561022>, then the FIG_Config file must contain
1466    
1467        $phone =  { user => 'BruceTheHumanPet',
1468                    password => 'silly',
1469                    api_id => '2561022' };
1470    
1471    The original purpose of this method was to insure Bruce would be notified immediately when the
1472    Sprout Load terminates. Care should be taken if you do not wish Bruce to be notified immediately
1473    when you call this method.
1474    
1475    The message ID will be returned if successful, and C<undef> if an error occurs.
1476    
1477    =over 4
1478    
1479    =item phoneNumber
1480    
1481    Phone number to receive the message, in international format. A United States phone number
1482    would be prefixed by "1". A British phone number would be prefixed by "44".
1483    
1484    =item msg
1485    
1486    Message to send to the specified phone.
1487    
1488    =item RETURN
1489    
1490    Returns the message ID if successful, and C<undef> if the message could not be sent.
1491    
1492    =back
1493    
1494    =cut
1495    
1496    sub SendSMS {
1497        # Get the parameters.
1498        my ($phoneNumber, $msg) = @_;
1499        # Declare the return variable. If we do not change it, C<undef> will be returned.
1500        my $retVal;
1501        # Only proceed if we have phone support.
1502        if (! defined $FIG_Config::phone) {
1503            Trace("Phone support not present in FIG_Config.") if T(1);
1504        } else {
1505            # Get the phone data.
1506            my $parms = $FIG_Config::phone;
1507            # Get the Clickatell URL.
1508            my $url = "http://api.clickatell.com/http/";
1509            # Create the user agent.
1510            my $ua = LWP::UserAgent->new;
1511            # Request a Clickatell session.
1512            my $resp = $ua->post("$url/sendmsg", { user => $parms->{user},
1513                                         password => $parms->{password},
1514                                         api_id => $parms->{api_id},
1515                                         to => $phoneNumber,
1516                                         text => $msg});
1517            # Check for an error.
1518            if (! $resp->is_success) {
1519                Trace("Alert failed.") if T(1);
1520            } else {
1521                # Get the message ID.
1522                my $rstring = $resp->content;
1523                if ($rstring =~ /^ID:\s+(.*)$/) {
1524                    $retVal = $1;
1525                } else {
1526                    Trace("Phone attempt failed with $rstring") if T(1);
1527                }
1528            }
1529        }
1530        # Return the result.
1531        return $retVal;
1532    }
1533    
1534    =head3 StandardSetup
1535    
1536        my ($options, @parameters) = StandardSetup(\@categories, \%options, $parmHelp, @ARGV);
1537    
1538    This method performs standard command-line parsing and tracing setup. The return
1539    values are a hash of the command-line options and a list of the positional
1540    parameters. Tracing is automatically set up and the command-line options are
1541    validated.
1542    
1543    This is a complex method that does a lot of grunt work. The parameters can
1544    be more easily understood, however, once they are examined individually.
1545    
1546    The I<categories> parameter is the most obtuse. It is a reference to a list of
1547    special-purpose tracing categories. Most tracing categories are PERL package
1548    names. So, for example, if you wanted to turn on tracing inside the B<Sprout>,
1549    B<ERDB>, and B<SproutLoad> packages, you would specify the categories
1550    
1551        ["Sprout", "SproutLoad", "ERDB"]
1552    
1553    This would cause trace messages in the specified three packages to appear in
1554    the output. There are two special tracing categories that are automatically
1555    handled by this method. In other words, if you used L</TSetup> you would need
1556    to include these categories manually, but if you use this method they are turned
1557    on automatically.
1558    
1559    =over 4
1560    
1561    =item SQL
1562    
1563    Traces SQL commands and activity.
1564    
1565    =item Tracer
1566    
1567    Traces error messages and call stacks.
1568    
1569    =back
1570    
1571    C<SQL> is only turned on if the C<-sql> option is specified in the command line.
1572    The trace level is specified using the C<-trace> command-line option. For example,
1573    the following command line for C<TransactFeatures> turns on SQL tracing and runs
1574    all tracing at level 3.
1575    
1576        TransactFeatures -trace=3 -sql register ../xacts IDs.tbl
1577    
1578    Standard tracing is output to the standard output and echoed to the file
1579    C<trace>I<$$>C<.log> in the FIG temporary directory, where I<$$> is the
1580    process ID. You can also specify the C<user> parameter to put a user ID
1581    instead of a process ID in the trace file name. So, for example
1582    
1583    The default trace level is 2. To get all messages, specify a trace level of 4.
1584    For a genome-by-genome update, use 3.
1585    
1586        TransactFeatures -trace=3 -sql -user=Bruce register ../xacts IDs.tbl
1587    
1588    would send the trace output to C<traceBruce.log> in the temporary directory.
1589    
1590    The I<options> parameter is a reference to a hash containing the command-line
1591    options, their default values, and an explanation of what they mean. Command-line
1592    options may be in the form of switches or keywords. In the case of a switch, the
1593    option value is 1 if it is specified and 0 if it is not specified. In the case
1594    of a keyword, the value is separated from the option name by an equal sign. You
1595    can see this last in the command-line example above.
1596    
1597    You can specify a different default trace level by setting C<$options->{trace}>
1598    prior to calling this method.
1599    
1600    An example at this point would help. Consider, for example, the command-line utility
1601    C<TransactFeatures>. It accepts a list of positional parameters plus the options
1602    C<safe>, C<noAlias>, C<start>, and C<tblFiles>. To start up this command, we execute
1603    the following code.
1604    
1605        my ($options, @parameters) = Tracer::StandardSetup(["DocUtils"],
1606                            { safe => [0, "use database transactions"],
1607                              noAlias => [0, "do not expect aliases in CHANGE transactions"],
1608                              start => [' ', "start with this genome"],
1609                              tblFiles => [0, "output TBL files containing the corrected IDs"] },
1610                            "<command> <transactionDirectory> <IDfile>",
1611                          @ARGV);
1612    
1613    
1614    The call to C<ParseCommand> specifies the default values for the options and
1615    stores the actual options in a hash that is returned as C<$options>. The
1616    positional parameters are returned in C<@parameters>.
1617    
1618    The following is a sample command line for C<TransactFeatures>.
1619    
1620        TransactFeatures -trace=2 -noAlias register ../xacts IDs.tbl
1621    
1622    Single and double hyphens are equivalent. So, you could also code the
1623    above command as
1624    
1625        TransactFeatures --trace=2 --noAlias register ../xacts IDs.tbl
1626    
1627    In this case, C<register>, C<../xacts>, and C<IDs.tbl> are the positional
1628    parameters, and would find themselves in I<@parameters> after executing the
1629    above code fragment. The tracing would be set to level 2, and the categories
1630    would be C<Tracer>, and <DocUtils>. C<Tracer> is standard,
1631    and C<DocUtils> was included because it came in within the first parameter
1632    to this method. The I<$options> hash would be
1633    
1634        { trace => 2, sql => 0, safe => 0,
1635          noAlias => 1, start => ' ', tblFiles => 0 }
1636    
1637    Use of C<StandardSetup> in this way provides a simple way of performing
1638    standard tracing setup and command-line parsing. Note that the caller is
1639    not even aware of the command-line switches C<-trace> and C<-sql>, which
1640    are used by this method to control the tracing. If additional tracing features
1641    need to be added in the future, they can be processed by this method without
1642    upsetting the command-line utilities.
1643    
1644    If the C<background> option is specified on the command line, then the
1645    standard and error outputs will be directed to files in the temporary
1646    directory, using the same suffix as the trace file. So, if the command
1647    line specified
1648    
1649        -user=Bruce -background
1650    
1651    then the trace output would go to C<traceBruce.log>, the standard output to
1652    C<outBruce.log>, and the error output to C<errBruce.log>. This is designed to
1653    simplify starting a command in the background.
1654    
1655    The user name is also used as the tracing key for L</Emergency Tracing>.
1656    Specifying a value of C<E> for the trace level causes emergency tracing to
1657    be used instead of custom tracing. If the user name is not specified,
1658    the tracing key is taken from the C<Tracing> environment variable. If there
1659    is no value for that variable, the tracing key will be computed from the PID.
1660    
1661    Finally, if the special option C<-help> is specified, the option
1662    names will be traced at level 0 and the program will exit without processing.
1663    This provides a limited help capability. For example, if the user enters
1664    
1665        TransactFeatures -help
1666    
1667    he would see the following output.
1668    
1669        TransactFeatures [options] <command> <transactionDirectory> <IDfile>
1670            -trace    tracing level (default E)
1671            -sql      trace SQL commands
1672            -safe     use database transactions
1673            -noAlias  do not expect aliases in CHANGE transactions
1674            -start    start with this genome
1675            -tblFiles output TBL files containing the corrected IDs
1676    
1677    The caller has the option of modifying the tracing scheme by placing a value
1678    for C<trace> in the incoming options hash. The default value can be overridden,
1679    or the tracing to the standard output can be turned off by suffixing a minus
1680    sign to the trace level. So, for example,
1681    
1682        { trace => [0, "tracing level (default 0)"],
1683           ...
1684    
1685    would set the default trace level to 0 instead of E, while
1686    
1687        { trace => ["2-", "tracing level (default 2)"],
1688           ...
1689    
1690    would set the default to 2, but trace only to the log file, not to the
1691    standard output.
1692    
1693    The parameters to this method are as follows.
1694    
1695    =over 4
1696    
1697    =item categories
1698    
1699    Reference to a list of tracing category names. These should be names of
1700    packages whose internal workings will need to be debugged to get the
1701    command working.
1702    
1703    =item options
1704    
1705    Reference to a hash containing the legal options for the current command mapped
1706    to their default values and descriptions. The user can override the defaults
1707    by specifying the options as command-line switches prefixed by a hyphen.
1708    Tracing-related options may be added to this hash. If the C<-h> option is
1709    specified on the command line, the option descriptions will be used to
1710    explain the options. To turn off tracing to the standard output, add a
1711    minus sign to the value for C<trace> (see above).
1712    
1713    =item parmHelp
1714    
1715    A string that vaguely describes the positional parameters. This is used
1716    if the user specifies the C<-h> option.
1717    
1718    =item argv
1719    
1720    List of command line parameters, including the option switches, which must
1721    precede the positional parameters and be prefixed by a hyphen.
1722    
1723    =item RETURN
1724    
1725    Returns a list. The first element of the list is the reference to a hash that
1726    maps the command-line option switches to their values. These will either be the
1727    default values or overrides specified on the command line. The remaining
1728    elements of the list are the position parameters, in order.
1729    
1730    =back
1731    
1732    =cut
1733    
1734    sub StandardSetup {
1735        # Get the parameters.
1736        my ($categories, $options, $parmHelp, @argv) = @_;
1737        # Get the default tracing key.
1738        my $tkey = EmergencyKey();
1739        # Add the tracing options.
1740        if (! exists $options->{trace}) {
1741            $options->{trace} = ['2', "tracing level (E for emergency tracing)"];
1742        }
1743        $options->{sql} = [0, "turn on SQL tracing"];
1744        $options->{help} = [0, "display command-line options"];
1745        $options->{user} = [$tkey, "tracing key"];
1746        $options->{background} = [0, "spool standard and error output"];
1747        # Create a parsing hash from the options hash. The parsing hash
1748        # contains the default values rather than the default value
1749        # and the description. While we're at it, we'll memorize the
1750        # length of the longest option name.
1751        my $longestName = 0;
1752        my %parseOptions = ();
1753        for my $key (keys %{$options}) {
1754            if (length $key > $longestName) {
1755                $longestName = length $key;
1756            }
1757            $parseOptions{$key} = $options->{$key}->[0];
1758        }
1759        # Parse the command line.
1760        my ($retOptions, @retParameters) = ParseCommand(\%parseOptions, @argv);
1761        # Get the logfile suffix.
1762        my $suffix = $retOptions->{user};
1763        # Check for background mode.
1764        if ($retOptions->{background}) {
1765            my $outFileName = "$FIG_Config::temp/out$suffix.log";
1766            my $errFileName = "$FIG_Config::temp/err$suffix.log";
1767            open STDOUT, ">$outFileName";
1768            open STDERR, ">$errFileName";
1769            # Check for phone support. If we have phone support and a phone number,
1770            # we want to turn it on.
1771            if ($ENV{PHONE} && defined($FIG_Config::phone)) {
1772                $retOptions->{phone} = $ENV{PHONE};
1773            }
1774        }
1775        # Now we want to set up tracing. First, we need to know if the user
1776        # wants emergency tracing.
1777        if ($retOptions->{trace} eq 'E') {
1778            ETracing($retOptions->{user});
1779        } else {
1780            # Here the tracing is controlled from the command line.
1781            my @cats = @{$categories};
1782            if ($retOptions->{sql}) {
1783                push @cats, "SQL";
1784            }
1785            # Add the default categories.
1786            push @cats, "Tracer";
1787            # Next, we create the category string by joining the categories.
1788            my $cats = join(" ", @cats);
1789            # Check to determine whether or not the caller wants to turn off tracing
1790            # to the standard output.
1791            my $traceLevel = $retOptions->{trace};
1792            my $textOKFlag = 1;
1793            if ($traceLevel =~ /^(.)-/) {
1794                $traceLevel = $1;
1795                $textOKFlag = 0;
1796            }
1797            # Now we set up the trace mode.
1798            my $traceMode;
1799            # Verify that we can open a file in the FIG temporary directory.
1800            my $traceFileName = "$FIG_Config::temp/trace$suffix.log";
1801            if (open TESTTRACE, ">$traceFileName") {
1802                # Here we can trace to a file.
1803                $traceMode = ">$traceFileName";
1804                if ($textOKFlag) {
1805                    # Echo to standard output if the text-OK flag is set.
1806                    $traceMode = "+$traceMode";
1807                }
1808                # Close the test file.
1809                close TESTTRACE;
1810            } else {
1811                # Here we can't trace to a file. Complain about this.
1812                warn "Could not open trace file $traceFileName: $!\n";
1813                # We trace to the standard output if it's
1814                # okay, and the error log otherwise.
1815                if ($textOKFlag) {
1816                    $traceMode = "TEXT";
1817                } else {
1818                    $traceMode = "WARN";
1819                }
1820            }
1821            # Now set up the tracing.
1822            TSetup("$traceLevel $cats", $traceMode);
1823        }
1824        # Check for the "help" option. If it is specified, dump the command-line
1825        # options and exit the program.
1826        if ($retOptions->{help}) {
1827            $0 =~ m#[/\\](\w+)(\.pl)?$#i;
1828            print "$1 [options] $parmHelp\n";
1829            for my $key (sort keys %{$options}) {
1830                my $name = Pad($key, $longestName, 0, ' ');
1831                my $desc = $options->{$key}->[1];
1832                if ($options->{$key}->[0]) {
1833                    $desc .= " (default " . $options->{$key}->[0] . ")";
1834                }
1835                print "  $name $desc\n";
1836            }
1837            exit(0);
1838        }
1839        # Trace the options, if applicable.
1840        if (T(3)) {
1841            my @parms = grep { $retOptions->{$_} } keys %{$retOptions};
1842            Trace("Selected options: " . join(", ", sort @parms) . ".");
1843        }
1844        # Return the parsed parameters.
1845        return ($retOptions, @retParameters);
1846    }
1847    
1848    =head3 ReadOptions
1849    
1850        my %options = Tracer::ReadOptions($fileName);
1851    
1852    Read a set of options from a file. Each option is encoded in a line of text that has the
1853    format
1854    
1855    I<optionName>C<=>I<optionValue>C<; >I<comment>
1856    
1857    The option name must consist entirely of letters, digits, and the punctuation characters
1858    C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank
1859    character is a semi-colon will be ignored. The return hash will map each option name to
1860    the corresponding option value.
1861    
1862    =over 4
1863    
1864    =item fileName
1865    
1866    Name of the file containing the option data.
1867    
1868    =item RETURN
1869    
1870    Returns a hash mapping the option names specified in the file to their corresponding option
1871    value.
1872    
1873    =back
1874    
1875    =cut
1876    
1877    sub ReadOptions {
1878        # Get the parameters.
1879        my ($fileName) = @_;
1880        # Open the file.
1881        (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");
1882        # Count the number of records read.
1883        my ($records, $comments) = 0;
1884        # Create the return hash.
1885        my %retVal = ();
1886        # Loop through the file, accumulating key-value pairs.
1887        while (my $line = <CONFIGFILE>) {
1888            # Denote we've read a line.
1889            $records++;
1890            # Determine the line type.
1891            if ($line =~ /^\s*[\n\r]/) {
1892                # A blank line is a comment.
1893                $comments++;
1894            } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {
1895                # Here we have an option assignment.
1896                retVal{$1} = $2;
1897            } elsif ($line =~ /^\s*;/) {
1898                # Here we have a text comment.
1899                $comments++;
1900            } else {
1901                # Here we have an invalid line.
1902                Trace("Invalid option statement in record $records.") if T(0);
1903            }
1904        }
1905        # Return the hash created.
1906        return %retVal;
1907    }
1908    
1909    =head3 GetOptions
1910    
1911        Tracer::GetOptions(\%defaults, \%options);
1912    
1913    Merge a specified set of options into a table of defaults. This method takes two hash references
1914    as input and uses the data from the second to update the first. If the second does not exist,
1915    there will be no effect. An error will be thrown if one of the entries in the second hash does not
1916    exist in the first.
1917    
1918    Consider the following example.
1919    
1920        my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options);
1921    
1922    In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and
1923    B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of
1924    B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and
1925    the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level
1926    will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as
1927    
1928        {databaseType => 'Oracle'}
1929    
1930    an error will occur because the B<databaseType> option does not exist.
1931    
1932    =over 4
1933    
1934    =item defaults
1935    
1936    Table of default option values.
1937    
1938    =item options
1939    
1940    Table of overrides, if any.
1941    
1942    =item RETURN
1943    
1944    Returns a reference to the default table passed in as the first parameter.
1945    
1946    =back
1947    
1948    =cut
1949    
1950    sub GetOptions {
1951        # Get the parameters.
1952        my ($defaults, $options) = @_;
1953        # Check for overrides.
1954        if ($options) {
1955            # Loop through the overrides.
1956            while (my ($option, $setting) = each %{$options}) {
1957                # Insure this override exists.
1958                if (!exists $defaults->{$option}) {
1959                    croak "Unrecognized option $option encountered.";
1960                } else {
1961                    # Apply the override.
1962                    $defaults->{$option} = $setting;
1963                }
1964            }
1965        }
1966        # Return the merged table.
1967        return $defaults;
1968    }
1969    
1970    =head3 MergeOptions
1971    
1972        Tracer::MergeOptions(\%table, \%defaults);
1973    
1974    Merge default values into a hash table. This method looks at the key-value pairs in the
1975    second (default) hash, and if a matching key is not found in the first hash, the default
1976    pair is copied in. The process is similar to L</GetOptions>, but there is no error-
1977    checking and no return value.
1978    
1979    =over 4
1980    
1981    =item table
1982    
1983    Hash table to be updated with the default values.
1984    
1985    =item defaults
1986    
1987    Default values to be merged into the first hash table if they are not already present.
1988    
1989    =back
1990    
1991    =cut
1992    
1993    sub MergeOptions {
1994        # Get the parameters.
1995        my ($table, $defaults) = @_;
1996        # Loop through the defaults.
1997        while (my ($key, $value) = each %{$defaults}) {
1998            if (!exists $table->{$key}) {
1999                $table->{$key} = $value;
2000            }
2001        }
2002    }
2003    
2004    =head3 ParseCommand
2005    
2006        my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList);
2007    
2008    Parse a command line consisting of a list of parameters. The initial parameters may be option
2009    specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped
2010    off and merged into a table of default options. The remainder of the command line is
2011    returned as a list of positional arguments. For example, consider the following invocation.
2012    
2013        my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words);
2014    
2015    In this case, the list @words will be treated as a command line and there are two options available,
2016    B<errors> and B<logFile>. If @words has the following format
2017    
2018        -logFile=error.log apple orange rutabaga
2019    
2020    then at the end of the invocation, C<$options> will be
2021    
2022        { errors => 0, logFile => 'error.log' }
2023    
2024    and C<@arguments> will contain
2025    
2026        apple orange rutabaga
2027    
2028    The parser allows for some escape sequences. See L</UnEscape> for a description. There is no
2029    support for quote characters. Options can be specified with single or double hyphens.
2030    
2031    =over 4
2032    
2033    =item optionTable
2034    
2035    Table of default options.
2036    
2037    =item inputList
2038    
2039    List of words on the command line.
2040    
2041    =item RETURN
2042    
2043    Returns a reference to the option table and a list of the positional arguments.
2044    
2045    =back
2046    
2047    =cut
2048    
2049    sub ParseCommand {
2050        # Get the parameters.
2051        my ($optionTable, @inputList) = @_;
2052        # Process any options in the input list.
2053        my %overrides = ();
2054        while ((@inputList > 0) && ($inputList[0] =~ /^--?/)) {
2055            # Get the current option.
2056            my $arg = shift @inputList;
2057            # Pull out the option name.
2058            $arg =~ /^--?([^=]*)/g;
2059            my $name = $1;
2060            # Check for an option value.
2061            if ($arg =~ /\G=(.*)$/g) {
2062                # Here we have a value for the option.
2063                $overrides{$name} = UnEscape($1);
2064            } else {
2065                # Here there is no value, so we use 1.
2066                $overrides{$name} = 1;
2067            }
2068        }
2069        # Merge the options into the defaults.
2070        GetOptions($optionTable, \%overrides);
2071        # Translate the remaining parameters.
2072        my @retVal = ();
2073        for my $inputParm (@inputList) {
2074            push @retVal, UnEscape($inputParm);
2075        }
2076        # Return the results.
2077        return ($optionTable, @retVal);
2078    }
2079    
2080    
2081    =head2 File Utility Methods
2082    
2083    =head3 GetFile
2084    
2085        my @fileContents = Tracer::GetFile($fileName);
2086    
2087        or
2088    
2089        my $fileContents = Tracer::GetFile($fileName);
2090    
2091    Return the entire contents of a file. In list context, line-ends are removed and
2092    each line is a list element. In scalar context, line-ends are replaced by C<\n>.
2093    
2094    =over 4
2095    
2096    =item fileName
2097    
2098    Name of the file to read.
2099    
2100    =item RETURN
2101    
2102    In a list context, returns the entire file as a list with the line terminators removed.
2103    In a scalar context, returns the entire file as a string. If an error occurs opening
2104    the file, an empty list will be returned.
2105    
2106    =back
2107    
2108    =cut
2109    
2110    sub GetFile {
2111        # Get the parameters.
2112        my ($fileName) = @_;
2113        # Declare the return variable.
2114        my @retVal = ();
2115        # Open the file for input.
2116        my $handle = Open(undef, "<$fileName");
2117        # Read the whole file into the return variable, stripping off any terminator
2118        # characters.
2119        my $lineCount = 0;
2120        while (my $line = <$handle>) {
2121            $lineCount++;
2122            $line = Strip($line);
2123            push @retVal, $line;
2124        }
2125        # Close it.
2126        close $handle;
2127        my $actualLines = @retVal;
2128        Trace("$actualLines lines read from file $fileName.") if T(File => 2);
2129        # Return the file's contents in the desired format.
2130        if (wantarray) {
2131            return @retVal;
2132        } else {
2133            return join "\n", @retVal;
2134        }
2135    }
2136    
2137    =head3 PutFile
2138    
2139        Tracer::PutFile($fileName, \@lines);
2140    
2141    Write out a file from a list of lines of text.
2142    
2143    =over 4
2144    
2145    =item fileName
2146    
2147    Name of the output file.
2148    
2149    =item lines
2150    
2151    Reference to a list of text lines. The lines will be written to the file in order, with trailing
2152    new-line characters. Alternatively, may be a string, in which case the string will be written without
2153    modification.
2154    
2155    =back
2156    
2157    =cut
2158    
2159    sub PutFile {
2160        # Get the parameters.
2161        my ($fileName, $lines) = @_;
2162        # Open the output file.
2163        my $handle = Open(undef, ">$fileName");
2164        # Count the lines written.
2165        if (ref $lines ne 'ARRAY') {
2166            # Here we have a scalar, so we write it raw.
2167            print $handle $lines;
2168            Trace("Scalar put to file $fileName.") if T(File => 3);
2169        } else {
2170            # Write the lines one at a time.
2171            my $count = 0;
2172            for my $line (@{$lines}) {
2173                print $handle "$line\n";
2174                $count++;
2175            }
2176            Trace("$count lines put to file $fileName.") if T(File => 3);
2177        }
2178        # Close the output file.
2179        close $handle;
2180    }
2181    
2182    =head3 ParseRecord
2183    
2184        my @fields = Tracer::ParseRecord($line);
2185    
2186    Parse a tab-delimited data line. The data line is split into field values. Embedded tab
2187    and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.
2188    These will automatically be converted.
2189    
2190    =over 4
2191    
2192    =item line
2193    
2194    Line of data containing the tab-delimited fields.
2195    
2196    =item RETURN
2197    
2198    Returns a list of the fields found in the data line.
2199    
2200    =back
2201    
2202    =cut
2203    
2204    sub ParseRecord {
2205        # Get the parameter.
2206        my ($line) = @_;
2207        # Remove the trailing new-line, if any.
2208        chomp $line;
2209        # Split the line read into pieces using the tab character.
2210        my @retVal = split /\t/, $line;
2211        # Trim and fix the escapes in each piece.
2212        for my $value (@retVal) {
2213            # Trim leading whitespace.
2214            $value =~ s/^\s+//;
2215            # Trim trailing whitespace.
2216            $value =~ s/\s+$//;
2217            # Delete the carriage returns.
2218            $value =~ s/\r//g;
2219            # Convert the escapes into their real values.
2220            $value =~ s/\\t/"\t"/ge;
2221            $value =~ s/\\n/"\n"/ge;
2222        }
2223        # Return the result.
2224        return @retVal;
2225    }
2226    
2227    =head3 Merge
2228    
2229        my @mergedList = Tracer::Merge(@inputList);
2230    
2231    Sort a list of strings and remove duplicates.
2232    
2233    =over 4
2234    
2235    =item inputList
2236    
2237    List of scalars to sort and merge.
2238    
2239    =item RETURN
2240    
2241    Returns a list containing the same elements sorted in ascending order with duplicates
2242    removed.
2243    
2244    =back
2245    
2246    =cut
2247    
2248    sub Merge {
2249        # Get the input list in sort order.
2250        my @inputList = sort @_;
2251        # Only proceed if the list has at least two elements.
2252        if (@inputList > 1) {
2253            # Now we want to move through the list splicing out duplicates.
2254            my $i = 0;
2255            while ($i < @inputList) {
2256                # Get the current entry.
2257                my $thisEntry = $inputList[$i];
2258                # Find out how many elements duplicate the current entry.
2259                my $j = $i + 1;
2260                my $dup1 = $i + 1;
2261                while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };
2262                # If the number is nonzero, splice out the duplicates found.
2263                if ($j > $dup1) {
2264                    splice @inputList, $dup1, $j - $dup1;
2265                }
2266                # Now the element at position $dup1 is different from the element before it
2267                # at position $i. We push $i forward one position and start again.
2268                $i++;
2269            }
2270        }
2271        # Return the merged list.
2272        return @inputList;
2273    }
2274    
2275    =head3 Open
2276    
2277        my $handle = Open($fileHandle, $fileSpec, $message);
2278    
2279    Open a file.
2280    
2281    The I<$fileSpec> is essentially the second argument of the PERL C<open>
2282    function. The mode is specified using Unix-like shell information. So, for
2283    example,
2284    
2285        Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2286    
2287    would open for output appended to the specified file, and
2288    
2289        Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");
2290    
2291    would open a pipe that sorts the records written and removes duplicates. Note
2292    the use of file handle syntax in the Open call. To use anonymous file handles,
2293    code as follows.
2294    
2295        my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2296    
2297    The I<$message> parameter is used if the open fails. If it is set to C<0>, then
2298    the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a
2299    failed open will throw an exception and the third parameter will be used to construct
2300    an error message. If the parameter is omitted, a standard message is constructed
2301    using the file spec.
2302    
2303        Could not open "/usr/spool/news/twitlog"
2304    
2305    Note that the mode characters are automatically cleaned from the file name.
2306    The actual error message from the file system will be captured and appended to the
2307    message in any case.
2308    
2309        Could not open "/usr/spool/news/twitlog": file not found.
2310    
2311    In some versions of PERL the only error message we get is a number, which
2312    corresponds to the C++ C<errno> value.
2313    
2314        Could not open "/usr/spool/news/twitlog": 6.
2315    
2316    =over 4
2317    
2318    =item fileHandle
2319    
2320    File handle. If this parameter is C<undef>, a file handle will be generated
2321    and returned as the value of this method.
2322    
2323    =item fileSpec
2324    
2325    File name and mode, as per the PERL C<open> function.
2326    
2327    =item message (optional)
2328    
2329    Error message to use if the open fails. If omitted, a standard error message
2330    will be generated. In either case, the error information from the file system
2331    is appended to the message. To specify a conditional open that does not throw
2332    an error if it fails, use C<0>.
2333    
2334    =item RETURN
2335    
2336    Returns the name of the file handle assigned to the file, or C<undef> if the
2337    open failed.
2338    
2339    =back
2340    
2341    =cut
2342    
2343    sub Open {
2344        # Get the parameters.
2345        my ($fileHandle, $fileSpec, $message) = @_;
2346        # Attempt to open the file.
2347        my $rv = open $fileHandle, $fileSpec;
2348        # If the open failed, generate an error message.
2349        if (! $rv) {
2350            # Save the system error message.
2351            my $sysMessage = $!;
2352            # See if we need a default message.
2353            if (!$message) {
2354                # Clean any obvious mode characters and leading spaces from the
2355                # filename.
2356                my ($fileName) = FindNamePart($fileSpec);
2357                $message = "Could not open \"$fileName\"";
2358            }
2359            # Terminate with an error using the supplied message and the
2360            # error message from the file system.
2361            Confess("$message: $!");
2362        }
2363        # Return the file handle.
2364        return $fileHandle;
2365    }
2366    
2367    =head3 FindNamePart
2368    
2369        my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec);
2370    
2371    Extract the portion of a file specification that contains the file name.
2372    
2373    A file specification is the string passed to an C<open> call. It specifies the file
2374    mode and name. In a truly complex situation, it can specify a pipe sequence. This
2375    method assumes that the file name is whatever follows the first angle bracket
2376    sequence.  So, for example, in the following strings the file name is
2377    C</usr/fig/myfile.txt>.
2378    
2379        >>/usr/fig/myfile.txt
2380        </usr/fig/myfile.txt
2381        | sort -u > /usr/fig/myfile.txt
2382    
2383    If the method cannot find a file name using its normal methods, it will return the
2384    whole incoming string.
2385    
2386    =over 4
2387    
2388    =item fileSpec
2389    
2390    File specification string from which the file name is to be extracted.
2391    
2392    =item RETURN
2393    
2394    Returns a three-element list. The first element contains the file name portion of
2395    the specified string, or the whole string if a file name cannot be found via normal
2396    methods. The second element contains the start position of the file name portion and
2397    the third element contains the length.
2398    
2399    =back
2400    
2401    =cut
2402    #: Return Type $;
2403    sub FindNamePart {
2404        # Get the parameters.
2405        my ($fileSpec) = @_;
2406        # Default to the whole input string.
2407        my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);
2408        # Parse out the file name if we can.
2409        if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {
2410            $retVal = $2;
2411            $len = length $retVal;
2412            $pos = (length $fileSpec) - (length $3) - $len;
2413        }
2414        # Return the result.
2415        return ($retVal, $pos, $len);
2416    }
2417    
2418    =head3 OpenDir
2419    
2420        my @files = OpenDir($dirName, $filtered, $flag);
2421    
2422    Open a directory and return all the file names. This function essentially performs
2423    the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is
2424    set to TRUE, all filenames beginning with a period (C<.>), dollar sign (C<$>),
2425    or pound sign (C<#>) and all filenames ending with a tilde C<~>) will be
2426    filtered out of the return list. If the directory does not open and I<$flag> is not
2427    set, an exception is thrown. So, for example,
2428    
2429        my @files = OpenDir("/Volumes/fig/contigs", 1);
2430    
2431    is effectively the same as
2432    
2433        opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");
2434        my @files = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir(TMP);
2435    
2436    Similarly, the following code
2437    
2438        my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs", 0, 1);
2439    
2440    Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and
2441    automatically returns an empty list if the directory fails to open.
2442    
2443    =over 4
2444    
2445    =item dirName
2446    
2447    Name of the directory to open.
2448    
2449    =item filtered
2450    
2451    TRUE if files whose names begin with a period (C<.>) should be automatically removed
2452    from the list, else FALSE.
2453    
2454    =item flag
2455    
2456    TRUE if a failure to open is okay, else FALSE
2457    
2458    =back
2459    
2460    =cut
2461    #: Return Type @;
2462    sub OpenDir {
2463        # Get the parameters.
2464        my ($dirName, $filtered, $flag) = @_;
2465        # Declare the return variable.
2466        my @retVal = ();
2467        # Open the directory.
2468        if (opendir(my $dirHandle, $dirName)) {
2469            # The directory opened successfully. Get the appropriate list according to the
2470            # strictures of the filter parameter.
2471            if ($filtered) {
2472                @retVal = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir $dirHandle;
2473            } else {
2474                @retVal = readdir $dirHandle;
2475            }
2476        } elsif (! $flag) {
2477            # Here the directory would not open and it's considered an error.
2478            Confess("Could not open directory $dirName.");
2479        }
2480        # Return the result.
2481        return @retVal;
2482    }
2483    
2484    
2485    =head3 Insure
2486    
2487        Insure($dirName, $chmod);
2488    
2489    Insure a directory is present.
2490    
2491    =over 4
2492    
2493    =item dirName
2494    
2495    Name of the directory to check. If it does not exist, it will be created.
2496    
2497    =item chmod (optional)
2498    
2499    Security privileges to be given to the directory if it is created.
2500    
2501    =back
2502    
2503    =cut
2504    
2505    sub Insure {
2506        my ($dirName, $chmod) = @_;
2507        if (! -d $dirName) {
2508            Trace("Creating $dirName directory.") if T(2);
2509            eval {
2510                mkpath $dirName;
2511                # If we have permissions specified, set them here.
2512                if (defined($chmod)) {
2513                    chmod $chmod, $dirName;
2514                }
2515            };
2516            if ($@) {
2517                Confess("Error creating $dirName: $@");
2518            }
2519        }
2520    }
2521    
2522    =head3 ChDir
2523    
2524        ChDir($dirName);
2525    
2526    Change to the specified directory.
2527    
2528    =over 4
2529    
2530    =item dirName
2531    
2532    Name of the directory to which we want to change.
2533    
2534    =back
2535    
2536    =cut
2537    
2538    sub ChDir {
2539        my ($dirName) = @_;
2540        if (! -d $dirName) {
2541            Confess("Cannot change to directory $dirName: no such directory.");
2542        } else {
2543            Trace("Changing to directory $dirName.") if T(File => 4);
2544            my $okFlag = chdir $dirName;
2545            if (! $okFlag) {
2546                Confess("Error switching to directory $dirName.");
2547            }
2548        }
2549    }
2550    
2551    =head3 SetPermissions
2552    
2553        Tracer::SetPermissions($dirName, $group, $mask, %otherMasks);
2554    
2555    Set the permissions for a directory and all the files and folders inside it.
2556    In addition, the group ownership will be changed to the specified value.
2557    
2558    This method is more vulnerable than most to permission and compatability
2559    problems, so it does internal error recovery.
2560    
2561    =over 4
2562    
2563    =item dirName
2564    
2565    Name of the directory to process.
2566    
2567    =item group
2568    
2569    Name of the group to be assigned.
2570    
2571    =item mask
2572    
2573    Permission mask. Bits that are C<1> in this mask will be ORed into the
2574    permission bits of any file or directory that does not already have them
2575    set to 1.
2576    
2577    =item otherMasks
2578    
2579    Map of search patterns to permission masks. If a directory name matches
2580    one of the patterns, that directory and all its members and subdirectories
2581    will be assigned the new pattern. For example, the following would
2582    assign 01664 to most files, but would use 01777 for directories named C<tmp>.
2583    
2584        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp$' => 01777);
2585    
2586    The list is ordered, so the following would use 0777 for C<tmp1> and
2587    0666 for C<tmp>, C<tmp2>, or C<tmp3>.
2588    
2589        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp1' => 0777,
2590                                                       '^tmp' => 0666);
2591    
2592    Note that the pattern matches are all case-insensitive, and only directory
2593    names are matched, not file names.
2594    
2595    =back
2596    
2597    =cut
2598    
2599    sub SetPermissions {
2600        # Get the parameters.
2601        my ($dirName, $group, $mask, @otherMasks) = @_;
2602        # Set up for error recovery.
2603        eval {
2604            # Switch to the specified directory.
2605            ChDir($dirName);
2606            # Get the group ID.
2607            my $gid = getgrnam($group);
2608            # Get the mask for tracing.
2609            my $traceMask = sprintf("%04o", $mask) . "($mask)";
2610            Trace("Fixing permissions for directory $dirName using group $group($gid) and mask $traceMask.") if T(File => 2);
2611            my $fixCount = 0;
2612            my $lookCount = 0;
2613            # @dirs will be a stack of directories to be processed.
2614            my @dirs = (getcwd());
2615            while (scalar(@dirs) > 0) {
2616                # Get the current directory.
2617                my $dir = pop @dirs;
2618                # Check for a match to one of the specified directory names. To do
2619                # that, we need to pull the individual part of the name off of the
2620                # whole path.
2621                my $simpleName = $dir;
2622                if ($dir =~ m!/([^/]+)$!) {
2623                    $simpleName = $1;
2624                }
2625                Trace("Simple directory name for $dir is $simpleName.") if T(File => 4);
2626                # Search for a match.
2627                my $match = 0;
2628                my $i;
2629                for ($i = 0; $i < $#otherMasks && ! $match; $i += 2) {
2630                    my $pattern = $otherMasks[$i];
2631                    if ($simpleName =~ /$pattern/i) {
2632                        $match = 1;
2633                    }
2634                }
2635                # Check for a match. Note we use $i-1 because the loop added 2
2636                # before terminating due to the match.
2637                if ($match && $otherMasks[$i-1] != $mask) {
2638                    # This directory matches one of the incoming patterns, and it's
2639                    # a different mask, so we process it recursively with that mask.
2640                    SetPermissions($dir, $group, $otherMasks[$i-1], @otherMasks);
2641                } else {
2642                    # Here we can process normally. Get all of the non-hidden members.
2643                    my @submems = OpenDir($dir, 1);
2644                    for my $submem (@submems) {
2645                        # Get the full name.
2646                        my $thisMem = "$dir/$submem";
2647                        Trace("Checking member $thisMem.") if T(4);
2648                        $lookCount++;
2649                        if ($lookCount % 1000 == 0) {
2650                            Trace("$lookCount members examined. Current is $thisMem. Mask is $traceMask") if T(File => 3);
2651                        }
2652                        # Fix the group.
2653                        chown -1, $gid, $thisMem;
2654                        # Insure this member is not a symlink.
2655                        if (! -l $thisMem) {
2656                            # Get its info.
2657                            my $fileInfo = stat $thisMem;
2658                            # Only proceed if we got the info. Otherwise, it's a hard link
2659                            # and we want to skip it anyway.
2660                            if ($fileInfo) {
2661                                my $fileMode = $fileInfo->mode;
2662                                if (($fileMode & $mask) != $mask) {
2663                                    # Fix this member.
2664                                    $fileMode |= $mask;
2665                                    chmod $fileMode, $thisMem;
2666                                    $fixCount++;
2667                                }
2668                                # If it's a subdirectory, stack it.
2669                                if (-d $thisMem) {
2670                                    push @dirs, $thisMem;
2671                                }
2672                            }
2673                        }
2674                    }
2675                }
2676            }
2677            Trace("$lookCount files and directories processed, $fixCount fixed.") if T(File => 2);
2678        };
2679        # Check for an error.
2680        if ($@) {
2681            Confess("SetPermissions error: $@");
2682        }
2683    }
2684    
2685    =head3 GetLine
2686    
2687        my @data = Tracer::GetLine($handle);
2688    
2689    Read a line of data from a tab-delimited file.
2690    
2691    =over 4
2692    
2693    =item handle
2694    
2695    Open file handle from which to read.
2696    
2697    =item RETURN
2698    
2699    Returns a list of the fields in the record read. The fields are presumed to be
2700    tab-delimited. If we are at the end of the file, then an empty list will be
2701    returned. If an empty line is read, a single list item consisting of a null
2702    string will be returned.
2703    
2704    =back
2705    
2706    =cut
2707    
2708    sub GetLine {
2709        # Get the parameters.
2710        my ($handle) = @_;
2711        # Declare the return variable.
2712        my @retVal = ();
2713        Trace("File position is " . tell($handle) . ". EOF flag is " . eof($handle) . ".") if T(File => 4);
2714        # Read from the file.
2715        my $line = <$handle>;
2716        # Only proceed if we found something.
2717        if (defined $line) {
2718            # Remove the new-line. We are a bit over-cautious here because the file may be coming in via an
2719            # upload control and have a nonstandard EOL combination.
2720            $line =~ s/(\r|\n)+$//;
2721            # Here we do some fancy tracing to help in debugging complicated EOL marks.
2722            if (T(File => 4)) {
2723                my $escapedLine = $line;
2724                $escapedLine =~ s/\n/\\n/g;
2725                $escapedLine =~ s/\r/\\r/g;
2726                $escapedLine =~ s/\t/\\t/g;
2727                Trace("Line read: -->$escapedLine<--");
2728            }
2729            # If the line is empty, return a single empty string; otherwise, parse
2730            # it into fields.
2731            if ($line eq "") {
2732                push @retVal, "";
2733                  } else {                  } else {
2734                          # Here there are no more escape sequences. The rest of the string is              push @retVal, split /\t/,$line;
                         # transferred unmodified.  
                         $retVal .= $realString;  
                         $realString = "";  
2735                  }                  }
2736        } else {
2737            # Trace the reason the read failed.
2738            Trace("End of file: $!") if T(File => 3);
2739          }          }
2740          # Return the result.          # Return the result.
2741          return $retVal;      return @retVal;
2742  }  }
2743    
2744  =head3 UnEscape  =head3 PutLine
2745    
2746  C<< my $realString = Tracer::UnEscape($codedString); >>      Tracer::PutLine($handle, \@fields, $eol);
2747    
2748  Replace escape sequences with their actual equivalents. C<\b> will be replaced by a space,  Write a line of data to a tab-delimited file. The specified field values will be
2749  C<\t> by a tab, C<\n> by a new-line character, and C<\\> by a back-slash.  output in tab-separated form, with a trailing new-line.
2750    
2751  =over 4  =over 4
2752    
2753  =item codedString  =item handle
2754    
2755  String to un-escape.  Output file handle.
2756    
2757  =item RETURN  =item fields
2758    
2759  Returns a copy of the original string with the escape sequences converted to their actual  List of field values.
2760  values.  
2761    =item eol (optional)
2762    
2763    End-of-line character (default is "\n").
2764    
2765  =back  =back
2766    
2767  =cut  =cut
2768    
2769  sub UnEscape {  sub PutLine {
2770          # Get the parameter.      # Get the parameters.
2771          my ($codedString) = @_;      my ($handle, $fields, $eol) = @_;
2772          # Initialize the return variable.      # Write the data.
2773          my $retVal = "";      print $handle join("\t", @{$fields}) . ($eol || "\n");
         # Only proceed if the incoming string is nonempty.  
         if (defined $codedString) {  
                 # Loop through the parameter string, looking for escape sequences. We can't do  
                 # translating because it causes problems with the escaped slash. ("\\b" becomes  
                 # "\ " no matter what we do.)  
                 while (length $codedString > 0) {  
                         # Look for the first escape sequence.  
                         if ($codedString =~ /^(.*?)\\(\\|b|n|t)/) {  
                                 # Here we found it. The text preceding the sequence is in $1. The sequence  
                                 # itself is in $2. First, move the clear text to the return variable.  
                                 $retVal .= $1;  
                                 $codedString = substr $codedString, (2 + length $1);  
                                 # Decode the escape sequence.  
                                 my $char = $2;  
                                 $char =~ tr/\\btn/\\ \t\n/;  
                                 $retVal .= $char;  
                         } else {  
                                 # Here there are no more escape sequences. The rest of the string is  
                                 # transferred unmodified.  
                                 $retVal .= $codedString;  
                                 $codedString = "";  
                         }  
                 }  
         }  
         # Return the result.  
         return $retVal;  
2774  }  }
2775    
 =head3 ParseRecord  
2776    
2777  C<< my @fields = Tracer::ParseRecord($line); >>  =head3 PrintLine
2778    
2779  Parse a tab-delimited data line. The data line is split into field values. Embedded tab      Tracer::PrintLine($line);
2780  and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.  
2781  These will automatically be converted.  Print a line of text with a trailing new-line.
2782    
2783  =over 4  =over 4
2784    
2785  =item line  =item line
2786    
2787  Line of data containing the tab-delimited fields.  Line of text to print.
   
 =item RETURN  
   
 Returns a list of the fields found in the data line.  
2788    
2789  =back  =back
2790    
2791  =cut  =cut
2792    
2793  sub ParseRecord {  sub PrintLine {
2794          # Get the parameter.      # Get the parameters.
2795          my ($line) = @_;          my ($line) = @_;
2796          # Remove the trailing new-line, if any.      # Print the line.
2797          chomp $line;      print "$line\n";
         # Split the line read into pieces using the tab character.  
         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;  
         }  
         # Return the result.  
         return @retVal;  
2798  }  }
2799    
 =head3 Merge  
2800    
2801  C<< my @mergedList = Tracer::Merge(@inputList); >>  =head2 Other Useful Methods
2802    
2803  Sort a list of strings and remove duplicates.  =head3 ParseParm
2804    
2805        my $listValue = Tracer::ParseParm($string);
2806    
2807    Convert a parameter into a list reference. If the parameter is undefined,
2808    an undefined value will be returned. Otherwise, it will be parsed as a
2809    comma-separated list of values.
2810    
2811  =over 4  =over 4
2812    
2813  =item inputList  =item string
2814    
2815  List of scalars to sort and merge.  Incoming string.
2816    
2817  =item RETURN  =item RETURN
2818    
2819  Returns a list containing the same elements sorted in ascending order with duplicates  Returns a reference to a list of values, or C<undef> if the incoming value
2820  removed.  was undefined.
2821    
2822  =back  =back
2823    
2824  =cut  =cut
2825    
2826  sub Merge {  sub ParseParm {
2827          # Get the input list in sort order.      # Get the parameters.
2828          my @inputList = sort @_;      my ($string) = @_;
2829          # Only proceed if the list has at least two elements.      # Declare the return variable.
2830          if (@inputList > 1) {      my $retVal;
2831                  # Now we want to move through the list splicing out duplicates.      # Check for data.
2832                  my $i = 0;      if (defined $string) {
2833                  while ($i < @inputList) {          # We have some, so split it into a list.
2834                          # Get the current entry.          $retVal = [ split /\s*,\s*/, $string];
                         my $thisEntry = $inputList[$i];  
                         # Find out how many elements duplicate the current entry.  
                         my $j = $i + 1;  
                         my $dup1 = $i + 1;  
                         while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };  
                         # If the number is nonzero, splice out the duplicates found.  
                         if ($j > $dup1) {  
                                 splice @inputList, $dup1, $j - $dup1;  
                         }  
                         # 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++;  
2835                  }                  }
2836        # Return the result.
2837        return $retVal;
2838          }          }
2839          # Return the merged list.  
2840          return @inputList;  =head3 Now
2841    
2842        my $string = Tracer::Now();
2843    
2844    Return a displayable time stamp containing the local time. Whatever format this
2845    method produces must be parseable by L</ParseDate>.
2846    
2847    =cut
2848    
2849    sub Now {
2850        return DisplayTime(time);
2851  }  }
2852    
2853  =head3 GetFile  =head3 DisplayTime
2854    
2855  C<< my @fileContents = Tracer::GetFile($fileName); >>      my $string = Tracer::DisplayTime($time);
2856    
2857  Return the entire contents of a file.  Convert a time value to a displayable time stamp. Whatever format this
2858    method produces must be parseable by L</ParseDate>.
2859    
2860  =over 4  =over 4
2861    
2862  =item fileName  =item time
2863    
2864  Name of the file to read.  Time to display, in seconds since the epoch, or C<undef> if the time is unknown.
2865    
2866  =item RETURN  =item RETURN
2867    
2868  In a list context, returns the entire file as a list with the line terminators removed.  Returns a displayable time, or C<(n/a)> if the incoming time is undefined.
 In a scalar context, returns the entire file as a string.  
2869    
2870  =back  =back
2871    
2872  =cut  =cut
2873    
2874  sub GetFile {  sub DisplayTime {
2875          # Get the parameters.      my ($time) = @_;
2876          my ($fileName) = @_;      my $retVal = "(n/a)";
2877          # Declare the return variable.      if (defined $time) {
2878          my @retVal = ();          my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($time);
2879          # Open the file for input.          $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .
2880          my $ok = open INPUTFILE, "<$fileName";                    _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);
         if (!$ok) {  
                 # If we had an error, trace it. We will automatically return a null value.  
                 Trace("Could not open \"$fileName\" for input.") if T(0);  
         } else {  
                 # Read the whole file into the return variable, stripping off any terminator  
         # characters.  
         my $lineCount = 0;  
                 while (my $line = <INPUTFILE>) {  
             $lineCount++;  
             $line = Strip($line);  
                         push @retVal, $line;  
                 }  
                 # Close it.  
                 close INPUTFILE;  
         my $actualLines = @retVal;  
         Trace("$lineCount lines read from $fileName. $actualLines processed.") if T(3);  
2881          }          }
2882          # Return the file's contents in the desired format.      return $retVal;
     if (wantarray) {  
             return @retVal;  
     } else {  
         return join "\n", @retVal;  
2883      }      }
2884    
2885    # Pad a number to 2 digits.
2886    sub _p2 {
2887        my ($value) = @_;
2888        $value = "0$value" if ($value < 10);
2889        return $value;
2890  }  }
2891    
2892  =head3 QTrace  =head3 Escape
2893    
2894  C<< my $data = QTrace($format); >>      my $codedString = Tracer::Escape($realString);
2895    
2896  Return the queued trace data in the specified format.  Escape a string for use in a command. Tabs will be replaced by C<\t>, new-lines
2897    replaced by C<\n>, carriage returns will be deleted, and backslashes will be doubled. The
2898    result is to reverse the effect of L</UnEscape>.
2899    
2900  =over 4  =over 4
2901    
2902  =item format  =item realString
2903    
2904  C<html> to format the data as an HTML list, C<text> to format it as straight text.  String to escape.
2905    
2906    =item RETURN
2907    
2908    Escaped equivalent of the real string.
2909    
2910  =back  =back
2911    
2912  =cut  =cut
2913    
2914  sub QTrace {  sub Escape {
2915          # Get the parameter.          # Get the parameter.
2916          my ($format) = @_;      my ($realString) = @_;
2917          # Create the return variable.      # Initialize the return variable.
2918          my $retVal = "";          my $retVal = "";
2919          # Process according to the format.      # Loop through the parameter string, looking for sequences to escape.
2920          if ($format =~ m/^HTML$/i) {      while (length $realString > 0) {
2921                  # Convert the queue into an HTML list.          # Look for the first sequence to escape.
2922                  $retVal = "<ul>\n";          if ($realString =~ /^(.*?)([\n\t\r\\])/) {
2923                  for my $line (@Queue) {              # Here we found it. The text preceding the sequence is in $1. The sequence
2924                          my $escapedLine = CGI::escapeHTML($line);              # itself is in $2. First, move the clear text to the return variable.
2925                          $retVal .= "<li>$escapedLine</li>\n";              $retVal .= $1;
2926                # Strip the processed section off the real string.
2927                $realString = substr $realString, (length $2) + (length $1);
2928                # Get the matched character.
2929                my $char = $2;
2930                # If we have a CR, we are done.
2931                if ($char ne "\r") {
2932                    # It's not a CR, so encode the escape sequence.
2933                    $char =~ tr/\t\n/tn/;
2934                    $retVal .= "\\" . $char;
2935                  }                  }
2936                  $retVal .= "</ul>\n";          } else {
2937          } elsif ($format =~ m/^TEXT$/i) {              # Here there are no more escape sequences. The rest of the string is
2938                  # Convert the queue into a list of text lines.              # transferred unmodified.
2939                  $retVal = join("\n", @Queue) . "\n";              $retVal .= $realString;
2940                $realString = "";
2941          }          }
2942          # Clear the queue.      }
2943          @Queue = ();      # Return the result.
         # Return the formatted list.  
2944          return $retVal;          return $retVal;
2945  }  }
2946    
2947  =head3 Confess  =head3 UnEscape
2948    
2949  C<< Confess($message); >>      my $realString = Tracer::UnEscape($codedString);
2950    
2951  Trace the call stack and abort the program with the specified message. The stack  Replace escape sequences with their actual equivalents. C<\t> will be replaced by
2952  trace will only appear if the trace level for this package is 1 or more. When used with  a tab, C<\n> by a new-line character, and C<\\> by a backslash. C<\r> codes will
2953  the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.  be deleted.
 So, for example  
2954    
2955  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>  =over 4
2956    
2957  Will abort the program with a stack trace if the value of C<$recNum> is negative.  =item codedString
2958    
2959  =over 4  String to un-escape.
2960    
2961  =item message  =item RETURN
2962    
2963  Message to include in the trace.  Returns a copy of the original string with the escape sequences converted to their actual
2964    values.
2965    
2966  =back  =back
2967    
2968  =cut  =cut
2969    
2970  sub Confess {  sub UnEscape {
2971          # Get the parameters.      # Get the parameter.
2972          my ($message) = @_;      my ($codedString) = @_;
2973          # Trace the call stack.      # Initialize the return variable.
2974          Cluck($message) if T(1);      my $retVal = "";
2975          # Abort the program.      # Only proceed if the incoming string is nonempty.
2976          croak(">>> $message");      if (defined $codedString) {
2977            # Loop through the parameter string, looking for escape sequences. We can't do
2978            # translating because it causes problems with the escaped slash. ("\\t" becomes
2979            # "\<tab>" no matter what we do.)
2980            while (length $codedString > 0) {
2981                # Look for the first escape sequence.
2982                if ($codedString =~ /^(.*?)\\(\\|n|t|r)/) {
2983                    # Here we found it. The text preceding the sequence is in $1. The sequence
2984                    # itself is in $2. First, move the clear text to the return variable.
2985                    $retVal .= $1;
2986                    $codedString = substr $codedString, (2 + length $1);
2987                    # Get the escape value.
2988                    my $char = $2;
2989                    # If we have a "\r", we are done.
2990                    if ($char ne 'r') {
2991                        # Here it's not an 'r', so we convert it.
2992                        $char =~ tr/\\tn/\\\t\n/;
2993                        $retVal .= $char;
2994                    }
2995                } else {
2996                    # Here there are no more escape sequences. The rest of the string is
2997                    # transferred unmodified.
2998                    $retVal .= $codedString;
2999                    $codedString = "";
3000                }
3001            }
3002        }
3003        # Return the result.
3004        return $retVal;
3005  }  }
3006    
3007  =head3 Assert  =head3 Percent
3008    
3009        my $percent = Tracer::Percent($number, $base);
3010    
3011    Returns the percent of the base represented by the given number. If the base
3012    is zero, returns zero.
3013    
3014    =over 4
3015    
3016    =item number
3017    
3018    Percent numerator.
3019    
3020    =item base
3021    
3022  C<< Assert($condition1, $condition2, ... $conditionN); >>  Percent base.
3023    
3024  Return TRUE if all the conditions are true. This method can be used in conjunction with  =item RETURN
 the OR operator and the L</Confess> method, B<Assert> can function as a debugging assert.  
 So, for example  
3025    
3026  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>  Returns the percentage of the base represented by the numerator.
3027    
3028  Will abort the program with a stack trace if the value of C<$recNum> is negative.  =back
3029    
3030  =cut  =cut
3031  sub Assert {  
3032      my $retVal = 1;  sub Percent {
3033      LOOP: for my $condition (@_) {      # Get the parameters.
3034          if (! $condition) {      my ($number, $base) = @_;
3035              $retVal = 0;      # Declare the return variable.
3036              last LOOP;      my $retVal = 0;
3037          }      # Compute the percent.
3038        if ($base != 0) {
3039            $retVal = $number * 100 / $base;
3040      }      }
3041        # Return the result.
3042      return $retVal;      return $retVal;
3043  }  }
3044    
3045  =head3 Cluck  =head3 Constrain
3046    
3047  C<< Cluck($message); >>      my $constrained = Constrain($value, $min, $max);
3048    
3049  Trace the call stack. Note that for best results, you should qualify the call with a  Modify a numeric value to bring it to a point in between a maximum and a minimum.
 trace condition. For example,  
3050    
3051  C<< Cluck("Starting record parse.") if T(3); >>  =over 4
3052    
3053  will only trace the stack if the trace level for the package is 3 or more.  =item value
3054    
3055  =over 4  Value to constrain.
3056    
3057  =item message  =item min (optional)
3058    
3059  Message to include in the trace.  Minimum permissible value. If this parameter is undefined, no minimum constraint will be applied.
3060    
3061    =item max (optional)
3062    
3063    Maximum permissible value. If this parameter is undefined, no maximum constraint will be applied.
3064    
3065    =item RETURN
3066    
3067    Returns the incoming value, constrained according to the other parameters.
3068    
3069  =back  =back
3070    
3071  =cut  =cut
3072    
3073  sub Cluck {  sub Constrain {
3074          # Get the parameters.          # Get the parameters.
3075          my ($message) = @_;      my ($value, $min, $max) = @_;
3076      # Trace what's happening.      # Declare the return variable.
3077      Trace("Stack trace for event: $message");      my $retVal = $value;
3078          my $confession = longmess($message);      # Apply the minimum constraint.
3079          # Convert the confession to a series of trace messages. Note we skip any      if (defined $min && $retVal < $min) {
3080      # messages relating to calls into Tracer.          $retVal = $min;
3081          for my $line (split /\s*\n/, $confession) {      }
3082                  Trace($line) if ($line !~ /Tracer\.pm/);      # Apply the maximum constraint.
3083        if (defined $max && $retVal > $max) {
3084            $retVal = $max;
3085          }          }
3086        # Return the result.
3087        return $retVal;
3088  }  }
3089    
3090  =head3 Min  =head3 Min
3091    
3092  C<< my $min = Min($value1, $value2, ... $valueN); >>      my $min = Min($value1, $value2, ... $valueN);
3093    
3094  Return the minimum argument. The arguments are treated as numbers.  Return the minimum argument. The arguments are treated as numbers.
3095    
# Line 949  Line 3122 
3122    
3123  =head3 Max  =head3 Max
3124    
3125  C<< my $max = Max($value1, $value2, ... $valueN); >>      my $max = Max($value1, $value2, ... $valueN);
3126    
3127  Return the maximum argument. The arguments are treated as numbers.  Return the maximum argument. The arguments are treated as numbers.
3128    
# Line 980  Line 3153 
3153          return $retVal;          return $retVal;
3154  }  }
3155    
 =head3 AddToListMap  
   
 C<< Tracer::AddToListMap(\%hash, $key, $value); >>  
   
 Add a key-value pair to a hash of lists. If no value exists for the key, a singleton list  
 is created for the key. Otherwise, the new value is pushed onto the list.  
   
 =over 4  
   
 =item hash  
   
 Reference to the target hash.  
   
 =item key  
   
 Key for which the value is to be added.  
   
 =item value  
   
 Value to add to the key's value list.  
   
 =back  
   
 =cut  
   
 sub AddToListMap {  
     # Get the parameters.  
     my ($hash, $key, $value) = @_;  
     # Process according to whether or not the key already has a value.  
     if (! exists $hash->{$key}) {  
         $hash->{$key} = [$value];  
     } else {  
         push @{$hash->{$key}}, $value;  
     }  
 }  
   
 =head3 DebugMode  
   
 C<< if (Tracer::DebugMode) { ...code... } >>  
   
 Return TRUE if debug mode has been turned on in FIG_Config, else output  
 an error page and return FALSE.  
   
 Certain CGI scripts are too dangerous to exist in the production  
 environment. This method provides a simple way to prevent them  
 from working unless they are explicitly turned on in the configuration  
 file by setting C<$FIG_Config::debug_mode> to 1. If debugging mode  
 is not turned on, an error web page will be output.  
   
 =cut  
   
 sub DebugMode {  
         # Declare the return variable.  
         my $retVal;  
         # Check the debug configuration.  
         if ($FIG_Config::debug_mode) {  
                 $retVal = 1;  
         } else {  
                 # Here debug mode is off, so we generate an error page.  
         my $pageString = PageBuilder::Build("<Html/ErrorPage.html", {}, "Html");  
                 print $pageString;  
         }  
         # Return the determination indicator.  
         return $retVal;  
 }  
3156    
3157  =head3 Strip  =head3 Strip
3158    
3159  C<< my $string = Tracer::Strip($line); >>      my $string = Tracer::Strip($line);
3160    
3161  Strip all line terminators off a string. This is necessary when dealing with files  Strip all line terminators off a string. This is necessary when dealing with files
3162  that may have been transferred back and forth several times among different  that may have been transferred back and forth several times among different
# Line 1071  Line 3179 
3179  sub Strip {  sub Strip {
3180          # Get a copy of the parameter string.          # Get a copy of the parameter string.
3181          my ($string) = @_;          my ($string) = @_;
3182          my $retVal = $string;      my $retVal = (defined $string ? $string : "");
3183      # Strip the line terminator characters.      # Strip the line terminator characters.
3184      $retVal =~ s/(\r|\n)+$//g;      $retVal =~ s/(\r|\n)+$//g;
3185          # Return the result.          # Return the result.
# Line 1080  Line 3188 
3188    
3189  =head3 Pad  =head3 Pad
3190    
3191  C<< my $paddedString = Tracer::Pad($string, $len, $left, $padChar); >>      my $paddedString = Tracer::Pad($string, $len, $left, $padChar);
3192    
3193  Pad a string to a specified length. The pad character will be a  Pad a string to a specified length. The pad character will be a
3194  space, and the padding will be on the right side unless specified  space, and the padding will be on the right side unless specified
# Line 1102  Line 3210 
3210    
3211  =item padChar (optional)  =item padChar (optional)
3212    
3213    Character to use for padding. The default is a space.
3214    
3215  =item RETURN  =item RETURN
3216    
3217  Returns a copy of the original string with the spaces added to the specified end so  Returns a copy of the original string with the pad character added to the
3218  that it achieves the desired length.  specified end so that it achieves the desired length.
3219    
3220  =back  =back
3221    
# Line 1137  Line 3247 
3247          return $retVal;          return $retVal;
3248  }  }
3249    
3250    =head3 EOF
3251    
3252    This is a constant that is lexically greater than any useful string.
3253    
3254    =cut
3255    
3256    sub EOF {
3257        return "\xFF\xFF\xFF\xFF\xFF";
3258    }
3259    
3260    =head3 TICK
3261    
3262        my @results = TICK($commandString);
3263    
3264    Perform a back-tick operation on a command. If this is a Windows environment, any leading
3265    dot-slash (C<./> will be removed. So, for example, if you were doing
3266    
3267        `./protein.cgi`
3268    
3269    from inside a CGI script, it would work fine in Unix, but would issue an error message
3270    in Windows complaining that C<'.'> is not a valid command. If instead you code
3271    
3272        TICK("./protein.cgi")
3273    
3274    it will work correctly in both environments.
3275    
3276    =over 4
3277    
3278    =item commandString
3279    
3280    The command string to pass to the system.
3281    
3282    =item RETURN
3283    
3284    Returns the standard output from the specified command, as a list.
3285    
3286    =back
3287    
3288    =cut
3289    #: Return Type @;
3290    sub TICK {
3291        # Get the parameters.
3292        my ($commandString) = @_;
3293        # Chop off the dot-slash if this is Windows.
3294        if ($FIG_Config::win_mode) {
3295            $commandString =~ s!^\./!!;
3296        }
3297        # Activate the command and return the result.
3298        return `$commandString`;
3299    }
3300    
3301    
3302    =head3 CommaFormat
3303    
3304        my $formatted = Tracer::CommaFormat($number);
3305    
3306    Insert commas into a number.
3307    
3308    =over 4
3309    
3310    =item number
3311    
3312    A sequence of digits.
3313    
3314    =item RETURN
3315    
3316    Returns the same digits with commas strategically inserted.
3317    
3318    =back
3319    
3320    =cut
3321    
3322    sub CommaFormat {
3323        # Get the parameters.
3324        my ($number) = @_;
3325        # Pad the length up to a multiple of three.
3326        my $padded = "$number";
3327        $padded = " " . $padded while length($padded) % 3 != 0;
3328        # This is a fancy PERL trick. The parentheses in the SPLIT pattern
3329        # cause the delimiters to be included in the output stream. The
3330        # GREP removes the empty strings in between the delimiters.
3331        my $retVal = join(",", grep { $_ ne '' } split(/(...)/, $padded));
3332        # Clean out the spaces.
3333        $retVal =~ s/ //g;
3334        # Return the result.
3335        return $retVal;
3336    }
3337    
3338    
3339    =head3 CompareLists
3340    
3341        my ($inserted, $deleted) = Tracer::CompareLists(\@newList, \@oldList, $keyIndex);
3342    
3343    Compare two lists of tuples, and return a hash analyzing the differences. The lists
3344    are presumed to be sorted alphabetically by the value in the $keyIndex column.
3345    The return value contains a list of items that are only in the new list
3346    (inserted) and only in the old list (deleted).
3347    
3348    =over 4
3349    
3350    =item newList
3351    
3352    Reference to a list of new tuples.
3353    
3354    =item oldList
3355    
3356    Reference to a list of old tuples.
3357    
3358    =item keyIndex (optional)
3359    
3360    Index into each tuple of its key field. The default is 0.
3361    
3362    =item RETURN
3363    
3364    Returns a 2-tuple consisting of a reference to the list of items that are only in the new
3365    list (inserted) followed by a reference to the list of items that are only in the old
3366    list (deleted).
3367    
3368    =back
3369    
3370    =cut
3371    
3372    sub CompareLists {
3373        # Get the parameters.
3374        my ($newList, $oldList, $keyIndex) = @_;
3375        if (! defined $keyIndex) {
3376            $keyIndex = 0;
3377        }
3378        # Declare the return variables.
3379        my ($inserted, $deleted) = ([], []);
3380        # Loop through the two lists simultaneously.
3381        my ($newI, $oldI) = (0, 0);
3382        my ($newN, $oldN) = (scalar @{$newList}, scalar @{$oldList});
3383        while ($newI < $newN || $oldI < $oldN) {
3384            # Get the current object in each list. Note that if one
3385            # of the lists is past the end, we'll get undef.
3386            my $newItem = $newList->[$newI];
3387            my $oldItem = $oldList->[$oldI];
3388            if (! defined($newItem) || defined($oldItem) && $newItem->[$keyIndex] gt $oldItem->[$keyIndex]) {
3389                # The old item is not in the new list, so mark it deleted.
3390                push @{$deleted}, $oldItem;
3391                $oldI++;
3392            } elsif (! defined($oldItem) || $oldItem->[$keyIndex] gt $newItem->[$keyIndex]) {
3393                # The new item is not in the old list, so mark it inserted.
3394                push @{$inserted}, $newItem;
3395                $newI++;
3396            } else {
3397                # The item is in both lists, so push forward.
3398                $oldI++;
3399                $newI++;
3400            }
3401        }
3402        # Return the result.
3403        return ($inserted, $deleted);
3404    }
3405    
3406    =head3 GenerateURL
3407    
3408        my $queryUrl = Tracer::GenerateURL($page, %parameters);
3409    
3410    Generate a GET-style URL for the specified page with the specified parameter
3411    names and values. The values will be URL-escaped automatically. So, for
3412    example
3413    
3414        Tracer::GenerateURL("form.cgi", type => 1, string => "\"high pass\" or highway")
3415    
3416    would return
3417    
3418        form.cgi?type=1;string=%22high%20pass%22%20or%20highway
3419    
3420    =over 4
3421    
3422    =item page
3423    
3424    Page URL.
3425    
3426    =item parameters
3427    
3428    Hash mapping parameter names to parameter values.
3429    
3430    =item RETURN
3431    
3432    Returns a GET-style URL that goes to the specified page and passes in the
3433    specified parameters and values.
3434    
3435    =back
3436    
3437    =cut
3438    
3439    sub GenerateURL {
3440        # Get the parameters.
3441        my ($page, %parameters) = @_;
3442        # Prime the return variable with the page URL.
3443        my $retVal = $page;
3444        # Loop through the parameters, creating parameter elements in a list.
3445        my @parmList = map { "$_=" . uri_escape($parameters{$_}) } keys %parameters;
3446        # If the list is nonempty, tack it on.
3447        if (@parmList) {
3448            $retVal .= "?" . join(";", @parmList);
3449        }
3450        # Return the result.
3451        return $retVal;
3452    }
3453    
3454    =head3 ApplyURL
3455    
3456        Tracer::ApplyURL($table, $target, $url);
3457    
3458    Run through a two-dimensional table (or more accurately, a list of lists), converting the
3459    I<$target> column to HTML text having a hyperlink to a URL in the I<$url> column. The
3460    URL column will be deleted by this process and the target column will be HTML-escaped.
3461    
3462    This provides a simple way to process the results of a database query into something
3463    displayable by combining a URL with text.
3464    
3465    =over 4
3466    
3467    =item table
3468    
3469    Reference to a list of lists. The elements in the containing list will be updated by
3470    this method.
3471    
3472    =item target
3473    
3474    The index of the column to be converted into HTML.
3475    
3476    =item url
3477    
3478    The index of the column containing the URL. Note that the URL must have a recognizable
3479    C<http:> at the beginning.
3480    
3481    =back
3482    
3483    =cut
3484    
3485    sub ApplyURL {
3486        # Get the parameters.
3487        my ($table, $target, $url) = @_;
3488        # Loop through the table.
3489        for my $row (@{$table}) {
3490            # Apply the URL to the target cell.
3491            $row->[$target] = CombineURL($row->[$target], $row->[$url]);
3492            # Delete the URL from the row.
3493            delete $row->[$url];
3494        }
3495    }
3496    
3497    =head3 CombineURL
3498    
3499        my $combinedHtml = Tracer::CombineURL($text, $url);
3500    
3501    This method will convert the specified text into HTML hyperlinked to the specified
3502    URL. The hyperlinking will only take place if the URL looks legitimate: that is, it
3503    is defined and begins with an C<http:> header.
3504    
3505    =over 4
3506    
3507    =item text
3508    
3509    Text to return. This will be HTML-escaped automatically.
3510    
3511    =item url
3512    
3513    A URL to be hyperlinked to the text. If it does not look like a URL, then the text
3514    will be returned without any hyperlinking.
3515    
3516    =item RETURN
3517    
3518    Returns the original text, HTML-escaped, with the URL hyperlinked to it. If the URL
3519    doesn't look right, the HTML-escaped text will be returned without any further
3520    modification.
3521    
3522    =back
3523    
3524    =cut
3525    
3526    sub CombineURL {
3527        # Get the parameters.
3528        my ($text, $url) = @_;
3529        # Declare the return variable.
3530        my $retVal = CGI::escapeHTML($text);
3531        # Verify the URL.
3532        if (defined($url) && $url =~ m!http://!i) {
3533            # It's good, so we apply it to the text.
3534            $retVal = "<a href=\"$url\">$retVal</a>";
3535        }
3536        # Return the result.
3537        return $retVal;
3538    }
3539    
3540    =head3 Cmp
3541    
3542        my $cmp = Tracer::Cmp($a, $b);
3543    
3544    This method performs a universal sort comparison. Each value coming in is
3545    separated into a leading text part and a trailing number part. The text
3546    part is string compared, and if both parts are equal, then the number
3547    parts are compared numerically. A stream of just numbers or a stream of
3548    just strings will sort correctly, and a mixed stream will sort with the
3549    numbers first. Strings with a label and a number will sort in the
3550    expected manner instead of lexically.
3551    
3552    =over 4
3553    
3554    =item a
3555    
3556    First item to compare.
3557    
3558    =item b
3559    
3560    Second item to compare.
3561    
3562    =item RETURN
3563    
3564    Returns a negative number if the first item should sort first (is less), a positive
3565    number if the first item should sort second (is greater), and a zero if the items are
3566    equal.
3567    
3568    =back
3569    
3570    =cut
3571    
3572    sub Cmp {
3573        # Get the parameters.
3574        my ($a, $b) = @_;
3575        # Declare the return value.
3576        my $retVal;
3577        # Check for nulls.
3578        if (! defined($a)) {
3579            $retVal = (! defined($b) ? 0 : -1);
3580        } elsif (! defined($b)) {
3581            $retVal = 1;
3582        } else {
3583            # Here we have two real values. Parse the two strings.
3584            $a =~ /^(\D*)(\d*)$/;
3585            my $aParsed = [$1, $2];
3586            $b =~ /^(\D*)(\d*)$/;
3587            my $bParsed = [$1, $2];
3588            # Compare the string parts.
3589            $retVal = $aParsed->[0] cmp $bParsed->[0];
3590            if (! $retVal) {
3591                $retVal = $aParsed->[1] <=> $bParsed->[1];
3592            }
3593        }
3594        # Return the result.
3595        return $retVal;
3596    }
3597    
3598    
3599    =head3 TrackingCode
3600    
3601        my $html = Tracer::TrackingCode();
3602    
3603    Returns the HTML code for doing web page traffic monitoring. If the
3604    current environment is a test system, then it returns a null string;
3605    otherwise, it returns a bunch of javascript containing code for turning
3606    on SiteMeter and Google Analytics.
3607    
3608    =cut
3609    
3610    sub TrackingCode {
3611        # Declare the return variable.
3612        my $retVal = "<!-- tracking off -->";
3613        # Determine if we're in production.
3614        if ($FIG_Config::site_meter) {
3615            $retVal = <<END_HTML
3616            <!-- Site Meter -->
3617            <script type="text/javascript" src="http://s20.sitemeter.com/js/counter.js?site=s20nmpdr">
3618            </script>
3619            <noscript>
3620            <a href="http://s20.sitemeter.com/stats.asp?site=s20nmpdr" target="_top">
3621            <img src="http://s20.sitemeter.com/meter.asp?site=s20nmpdr" alt="Site Meter" border="0"/></a>
3622            </noscript>
3623            <!-- Copyright (c)2006 Site Meter -->
3624    END_HTML
3625        }
3626        return $retVal;
3627    }
3628    
3629    
3630  1;  1;

Legend:
Removed from v.1.9  
changed lines
  Added in v.1.102

MCS Webmaster
View