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

Diff of /FigKernelPackages/Tracer.pm

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

revision 1.26, Wed Sep 14 13:09:53 2005 UTC revision 1.111, Tue Sep 30 15:20:36 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 Open OpenDir TICK);      @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;      use Digest::MD5;
32        use File::Basename;
33        use File::Path;
34        use File::stat;
35        use LWP::UserAgent;
36        use Time::HiRes 'gettimeofday';
37        use URI::Escape;
38        use Time::Local;
39        use POSIX qw(strftime);
40        use Time::Zone;
41        use Fcntl qw(:DEFAULT :flock);
42    
43    
44  =head1 Tracing and Debugging Helpers  =head1 Tracing and Debugging Helpers
45    
46  =head2 Introduction  =head2 Tracing
47    
48  This package provides simple tracing for debugging and reporting purposes. To use it simply call the  This package provides simple tracing for debugging and reporting purposes. To use it simply call the
49  L</TSetup> method to set the options and call L</Trace> to write out trace messages. Each trace  L</TSetup> or L</ETracing> method to set the options and call L</Trace> to write out trace messages.
50  message has a I<trace level> and I<category> associated with it. In addition, the tracing package itself  L</TSetup> and L</ETracing> both establish a I<trace level> and a list of I<categories>. Similarly,
51  has a list of categories and a single trace level set by the B<TSetup> method. Only messages whose trace  each trace message has a I<trace level> and I<category> associated with it. Only messages whose trace
52  level is less than or equal to this package's trace level and whose category is activated will  level is less than or equal to the setup trace level and whose category is activated will
53  be written. Thus, a higher trace level on a message indicates that the message  be written. Thus, a higher trace level on a message indicates that the message
54  is less likely to be seen. A higher trace level passed to B<TSetup> means more trace messages will  is less likely to be seen, while a higher trace level passed to B<TSetup> means more trace messages will
55  appear. To generate a trace message, use the following syntax.  appear.
56    
57    =head3 Putting Trace Messages in Your Code
58    
59    To generate a trace message, use the following syntax.
60    
61  C<< Trace($message) if T(errors => 4); >>      Trace($message) if T(errors => 4);
62    
63  This statement will produce a trace message if the trace level is 4 or more and the C<errors>  This statement will produce a trace message if the trace level is 4 or more and the C<errors>
64  category is active. Note that the special category C<main> is always active, so  category is active. There is a special category C<main> that is always active, so
65    
66  C<< Trace($message) if T(main => 4); >>      Trace($message) if T(main => 4);
67    
68  will trace if the trace level is 4 or more.  will trace if the trace level is 4 or more.
69    
# Line 37  Line 71 
71  following call is made in the B<Sprout> package, it will appear if the C<Sprout> category is  following call is made in the B<Sprout> package, it will appear if the C<Sprout> category is
72  active and the trace level is 2 or more.  active and the trace level is 2 or more.
73    
74  C<< Trace($message) if T(2); >>      Trace($message) if T(2);
75    
76  To set up tracing, you call the L</TSetup> method. The method takes as input a trace level, a list  In scripts, where no package name is available, the category defaults to C<main>.
77  of category names, and a set of options. The trace level and list of category names are  
78    =head3 Custom Tracing
79    
80    Many programs have customized tracing configured using the L</TSetup> method. This is no longer
81    the preferred method, but a knowledge of how custom tracing works can make the more modern
82    L</Emergency Tracing> easier to understand.
83    
84    To set up custom tracing, you call the L</TSetup> method. The method takes as input a trace level,
85    a list of category names, and a destination. The trace level and list of category names are
86  specified as a space-delimited string. Thus  specified as a space-delimited string. Thus
87    
88  C<< TSetup('3 errors Sprout ERDB', 'HTML'); >>      TSetup('3 errors Sprout ERDB', 'TEXT');
89    
90  sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and  sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and
91  specifies that messages should be output as HTML paragraphs.  specifies that messages should be sent to the standard output.
92    
93  To turn on tracing for ALL categories, use an asterisk. The call below sets every category to  To turn on tracing for ALL categories, use an asterisk. The call below sets every category to
94  level 3 and writes the output to the standard error output. This sort of thing might be  level 3 and writes the output to the standard error output. This sort of thing might be
95  useful in a CGI environment.  useful in a CGI environment.
96    
97  C<< TSetup('3 *', 'WARN'); >>      TSetup('3 *', 'WARN');
98    
99  In addition to HTML and file output for trace messages, you can specify that the trace messages  In addition standard error and file output for trace messages, you can specify that the trace messages
100  be queued. The messages can then be retrieved by calling the L</QTrace> method. This approach  be queued. The messages can then be retrieved by calling the L</QTrace> method. This approach
101  is useful if you are building a web page. Instead of having the trace messages interspersed with  is useful if you are building a web page. Instead of having the trace messages interspersed with
102  the page output, they can be gathered together and displayed at the end of the page. This makes  the page output, they can be gathered together and displayed at the end of the page. This makes
103  it easier to debug page formatting problems.  it easier to debug page formatting problems.
104    
105  Finally, you can specify that all trace messages be emitted as warnings.  Finally, you can specify that all trace messages be emitted to a file, or the standard output and
106    a file at the same time. To trace to a file, specify the filename with an output character in front
107    of it.
108    
109        TSetup('4 SQL', ">$fileName");
110    
111    To trace to the standard output and a file at the same time, put a C<+> in front of the angle
112    bracket.
113    
114        TSetup('3 *', "+>$fileName");
115    
116  The flexibility of tracing makes it superior to simple use of directives like C<die> and C<warn>.  The flexibility of tracing makes it superior to simple use of directives like C<die> and C<warn>.
117  Tracer calls can be left in the code with minimal overhead and then turned on only when needed.  Tracer calls can be left in the code with minimal overhead and then turned on only when needed.
118  Thus, debugging information is available and easily retrieved even when the application is  Thus, debugging information is available and easily retrieved even when the application is
119  being used out in the field.  being used out in the field.
120    
121    =head3 Trace Levels
122    
123  There is no hard and fast rule on how to use trace levels. The following is therefore only  There is no hard and fast rule on how to use trace levels. The following is therefore only
124  a suggestion.  a suggestion.
125    
126  =over 4  =over 4
127    
128  =item 0 Error  =item Error 0
129    
130  Message indicates an error that may lead to incorrect results or that has stopped the  Message indicates an error that may lead to incorrect results or that has stopped the
131  application entirely.  application entirely.
132    
133  =item 1 Warning  =item Warning 1
134    
135  Message indicates something that is unexpected but that probably did not interfere  Message indicates something that is unexpected but that probably did not interfere
136  with program execution.  with program execution.
137    
138  =item 2 Notice  =item Notice 2
139    
140  Message indicates the beginning or end of a major task.  Message indicates the beginning or end of a major task.
141    
142  =item 3 Information  =item Information 3
143    
144  Message indicates a subtask. In the FIG system, a subtask generally relates to a single  Message indicates a subtask. In the FIG system, a subtask generally relates to a single
145  genome. This would be a big loop that is not expected to execute more than 500 times or so.  genome. This would be a big loop that is not expected to execute more than 500 times or so.
146    
147  =item 4 Detail  =item Detail 4
148    
149  Message indicates a low-level loop iteration.  Message indicates a low-level loop iteration.
150    
151  =back  =back
152    
153    The format of trace messages is important because some utilities analyze trace files.
154    There are three fields-- the time stamp, the category name, and the text.
155    The time stamp is between square brackets and the category name between angle brackets.
156    After the category name there is a colon (C<:>) followed by the message text.
157    If the square brackets or angle brackets are missing, then the trace management
158    utilities assume that they are encountering a set of pre-formatted lines.
159    
160    Note, however, that this formatting is done automatically by the tracing functions. You
161    only need to know about it if you want to parse a trace file.
162    
163    =head3 Emergency Tracing
164    
165    Sometimes, you need a way for tracing to happen automatically without putting parameters
166    in a form or on the command line. Emergency tracing does this. You invoke emergency tracing
167    from the debug form, which is accessed from the [[DebugConsole]]. Emergency tracing requires
168    that you specify a tracing key. For command-line tools, the key is
169    taken from the C<TRACING> environment variable. For web services, the key is taken from
170    a cookie. Either way, the key tells the tracing facility who you are, so that you control
171    the tracing in your environment without stepping on other users.
172    
173    The key can be anything you want. If you don't have a key, the C<SetPassword> page will
174    generate one for you.
175    
176    You can activate and de-activate emergency tracing from the debugging control panel, as
177    well as display the trace file itself.
178    
179    To enable emergency tracing in your code, call
180    
181        ETracing($cgi)
182    
183    from a web script and
184    
185        ETracing()
186    
187    from a command-line script.
188    
189    The web script will look for the tracing key in the cookies, and the command-line
190    script will look for it in the C<TRACING> environment variable. If you are
191    using the L</StandardSetup> method or a [[WebApplication]], emergency tracing
192    will be configured automatically.
193    
194  =cut  =cut
195    
196  # Declare the configuration variables.  # Declare the configuration variables.
197    
198  my $Destination = "NONE";   # Description of where to send the trace output.  my $Destination = "WARN";   # Description of where to send the trace output.
199  my $TeeFlag = 0;            # TRUE if output is going to a file and to the  my $TeeFlag = 0;            # TRUE if output is going to a file and to the
200                              # standard output                              # standard output
201  my %Categories = ( main => 1 );  my %Categories = ( main => 1 );
202                              # hash of active category names                              # hash of active category names
203    my @LevelNames = qw(error warn notice info detail);
204  my $TraceLevel = 0;         # trace level; a higher trace level produces more  my $TraceLevel = 0;         # trace level; a higher trace level produces more
205                              # messages                              # messages
206  my @Queue = ();             # queued list of trace messages.  my @Queue = ();             # queued list of trace messages.
207  my $LastCategory = "main";  # name of the last category interrogated  my $LastCategory = "main";  # name of the last category interrogated
208    my $LastLevel = 0;          # level of the last test call
209  my $SetupCount = 0;         # number of times TSetup called  my $SetupCount = 0;         # number of times TSetup called
210  my $AllTrace = 0;           # TRUE if we are tracing all categories.  my $AllTrace = 0;           # TRUE if we are tracing all categories.
211    my $SavedCGI;               # CGI object passed to ETracing
212    my $CommandLine;            # Command line passed to StandardSetup
213    umask 2;                    # Fix the damn umask so everything is group-writable.
214    
215    =head2 Tracing Methods
216    
217    =head3 Setups
218    
219        my $count = Tracer::Setups();
220    
221    Return the number of times L</TSetup> has been called.
222    
223    This method allows for the creation of conditional tracing setups where, for example, we
224    may want to set up tracing if nobody else has done it before us.
225    
226  =head2 Public Methods  =cut
227    
228    sub Setups {
229        return $SetupCount;
230    }
231    
232  =head3 TSetup  =head3 TSetup
233    
234  C<< TSetup($categoryList, $target); >>      TSetup($categoryList, $target);
235    
236  This method is used to specify the trace options. The options are stored as package data  This method is used to specify the trace options. The options are stored as package data
237  and interrogated by the L</Trace> and L</T> methods.  and interrogated by the L</Trace> and L</T> methods.
# Line 157  Line 271 
271      # Presume category-based tracing until we learn otherwise.      # Presume category-based tracing until we learn otherwise.
272      $AllTrace = 0;      $AllTrace = 0;
273      # Build the category hash. Note that if we find a "*", we turn on non-category      # Build the category hash. Note that if we find a "*", we turn on non-category
274      # tracing.      # tracing. We must also clear away any pre-existing data.
275        %Categories = ( main => 1 );
276      for my $category (@categoryData) {      for my $category (@categoryData) {
277          if ($category eq '*') {          if ($category eq '*') {
278              $AllTrace = 1;              $AllTrace = 1;
# Line 166  Line 281 
281          }          }
282      }      }
283      # Now we need to process the destination information. The most important special      # Now we need to process the destination information. The most important special
284      # cases are the single ">", which requires we clear the file first, and the      # case is when we're writing to a file. This is indicated by ">" (overwrite) and
285      # "+" prefix which indicates a double echo.      # ">>" (append). A leading "+" for either indicates that we are also writing to
286        # the standard output (tee mode).
287      if ($target =~ m/^\+?>>?/) {      if ($target =~ m/^\+?>>?/) {
288          if ($target =~ m/^\+/) {          if ($target =~ m/^\+/) {
289              $TeeFlag = 1;              $TeeFlag = 1;
290              $target = substr($target, 1);              $target = substr($target, 1);
291          }          }
292          if ($target =~ m/^>[^>]/) {          if ($target =~ m/^>[^>]/) {
293                # We need to initialize the file (which clears it).
294              open TRACEFILE, $target;              open TRACEFILE, $target;
295              print TRACEFILE Now() . " Tracing initialized.\n";              print TRACEFILE "[" . Now() . "] [notice] [Tracer] Tracing initialized.\n";
296              close TRACEFILE;              close TRACEFILE;
297                # Set to append mode now that the file has been cleared.
298              $Destination = ">$target";              $Destination = ">$target";
299          } else {          } else {
300              $Destination = $target;              $Destination = $target;
# Line 188  Line 306 
306      $SetupCount++;      $SetupCount++;
307  }  }
308    
309  =head3 Setups  =head3 SetLevel
   
 C<< my $count = Tracer::Setups(); >>  
   
 Return the number of times L</TSetup> has been called.  
   
 This method allows for the creation of conditional tracing setups where, for example, we  
 may want to set up tracing if nobody else has done it before us.  
   
 =cut  
310    
311  sub Setups {      Tracer::SetLevel($newLevel);
     return $SetupCount;  
 }  
312    
313  =head3 Open  Modify the trace level. A higher trace level will cause more messages to appear.
314    
315  C<< my $handle = Open($fileHandle, $fileSpec, $message); >>  =over 4
316    
317  Open a file.  =item newLevel
318    
319  The I<$fileSpec> is essentially the second argument of the PERL C<open>  Proposed new trace level.
 function. The mode is specified using Unix-like shell information. So, for  
 example,  
320    
321      Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");  =back
322    
323  would open for output appended to the specified file, and  =cut
324    
325      Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");  sub SetLevel {
326        $TraceLevel = $_[0];
327    }
328    
329  would open a pipe that sorts the records written and removes duplicates. Note  =head3 ParseDate
 the use of file handle syntax in the Open call. To use anonymous file handles,  
 code as follows.  
330    
331      my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");      my $time = Tracer::ParseDate($dateString);
332    
333  The I<$message> parameter is used if the open fails. If it is set to C<0>, then  Convert a date into a PERL time number. This method expects a date-like string
334  the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a  and parses it into a number. The string must be vaguely date-like or it will
335  failed open will throw an exception and the third parameter will be used to construct  return an undefined value. Our requirement is that a month and day be
336  an error message. If the parameter is omitted, a standard message is constructed  present and that three pieces of the date string (time of day, month and day,
337  using the file spec.  year) be separated by likely delimiters, such as spaces, commas, and such-like.
338    
339      Could not open "/usr/spool/news/twitlog"  If a time of day is present, it must be in military time with two digits for
340    everything but the hour.
341    
342  Note that the mode characters are automatically cleaned from the file name.  The year must be exactly four digits.
 The actual error message from the file system will be captured and appended to the  
 message in any case.  
343    
344      Could not open "/usr/spool/news/twitlog": file not found.  Additional stuff can be in the string. We presume it's time zones or weekdays or something
345    equally innocuous. This means, however, that a sufficiently long sentence with date-like
346    parts in it may be interpreted as a date. Hopefully this will not be a problem.
347    
348  In some versions of PERL the only error message we get is a number, which  It should be guaranteed that this method will parse the output of the L</Now> function.
 corresponds to the C++ C<errno> value.  
349    
350      Could not open "/usr/spool/news/twitlog": 6.  The parameters are as follows.
351    
352  =over 4  =over 4
353    
354  =item fileHandle  =item dateString
   
 File handle. If this parameter is C<undef>, a file handle will be generated  
 and returned as the value of this method.  
   
 =item fileSpec  
   
 File name and mode, as per the PERL C<open> function.  
   
 =item message (optional)  
355    
356  Error message to use if the open fails. If omitted, a standard error message  The date string to convert.
 will be generated. In either case, the error information from the file system  
 is appended to the message. To specify a conditional open that does not throw  
 an error if it fails, use C<0>.  
357    
358  =item RETURN  =item RETURN
359    
360  Returns the name of the file handle assigned to the file, or C<undef> if the  Returns a PERL time, that is, a number of seconds since the epoch, or C<undef> if
361  open failed.  the date string is invalid. A valid date string must contain a month and day.
362    
363  =back  =back
364    
365  =cut  =cut
366    
367  sub Open {  # Universal month conversion table.
368    use constant MONTHS => {    Jan =>  0, January   =>  0, '01' =>  0,  '1' =>  0,
369                                Feb =>  1, February  =>  1, '02' =>  1,  '2' =>  1,
370                                Mar =>  2, March     =>  2, '03' =>  2,  '3' =>  2,
371                                Apr =>  3, April     =>  3, '04' =>  3,  '4' =>  3,
372                                May =>  4, May       =>  4, '05' =>  4,  '5' =>  4,
373                                Jun =>  5, June      =>  5, '06' =>  5,  '6' =>  5,
374                                Jul =>  6, July      =>  6, '07' =>  6,  '7' =>  6,
375                                Aug =>  7, August    =>  7, '08' =>  7,  '8' =>  7,
376                                Sep =>  8, September =>  8, '09' =>  8,  '9' =>  8,
377                                Oct =>  9, October  =>   9, '10' =>  9,
378                                Nov => 10, November =>  10, '11' => 10,
379                                Dec => 11, December =>  11, '12' => 11
380                            };
381    
382    sub ParseDate {
383      # Get the parameters.      # Get the parameters.
384      my ($fileHandle, $fileSpec, $message) = @_;      my ($dateString) = @_;
385      # Attempt to open the file.      # Declare the return variable.
386      my $rv = open $fileHandle, $fileSpec;      my $retVal;
387      # If the open failed, generate an error message.      # Find the month and day of month. There are two ways that can happen. We check for the
388      if (! $rv) {      # numeric style first. That way, if the user's done something like "Sun 12/22", then we
389          # Save the system error message.      # won't be fooled into thinking the month is Sunday.
390          my $sysMessage = $!;      if ($dateString =~ m#\b(\d{1,2})/(\d{1,2})\b# || $dateString =~ m#\b(\w+)\s(\d{1,2})\b#) {
391          # See if we need a default message.          my ($mon, $mday) = (MONTHS->{$1}, $2);
392          if (!$message) {          # Insist that the month and day are valid.
393              # Clean any obvious mode characters and leading spaces from the          if (defined($mon) && $2 >= 1 && $2 <= 31) {
394              # filename.              # Find the time.
395              my ($fileName) = FindNamePart($fileSpec);              my ($hour, $min, $sec) = (0, 0, 0);
396              $message = "Could not open \"$fileName\"";              if ($dateString =~ /\b(\d{1,2}):(\d{2}):(\d{2})\b/) {
397                    ($hour, $min, $sec) = ($1, $2, $3);
398                }
399                # Find the year.
400                my $year;
401                if ($dateString =~ /\b(\d{4})\b/) {
402                    $year = $1;
403                } else {
404                    # Get the default year, which is this one. Note we must convert it to
405                    # the four-digit value expected by "timelocal".
406                    (undef, undef, undef, undef, undef, $year) = localtime();
407                    $year += 1900;
408          }          }
409          # Terminate with an error using the supplied message and the              $retVal = timelocal($sec, $min, $hour, $mday, $mon, $year);
         # error message from the file system.  
         Confess("$message: $!");  
410      }      }
411      # Return the file handle.      }
412      return $fileHandle;      # Return the result.
413        return $retVal;
414  }  }
415    
416  =head3 FindNamePart  =head3 LogErrors
   
 C<< my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec); >>  
   
 Extract the portion of a file specification that contains the file name.  
   
 A file specification is the string passed to an C<open> call. It specifies the file  
 mode and name. In a truly complex situation, it can specify a pipe sequence. This  
 method assumes that the file name is whatever follows the first angle bracket  
 sequence.  So, for example, in the following strings the file name is  
 C</usr/fig/myfile.txt>.  
417    
418      >>/usr/fig/myfile.txt      Tracer::LogErrors($fileName);
     </usr/fig/myfile.txt  
     | sort -u > /usr/fig/myfile.txt  
419    
420  If the method cannot find a file name using its normal methods, it will return the  Route the standard error output to a log file.
 whole incoming string.  
421    
422  =over 4  =over 4
423    
424  =item fileSpec  =item fileName
   
 File specification string from which the file name is to be extracted.  
   
 =item RETURN  
425    
426  Returns a three-element list. The first element contains the file name portion of  Name of the file to receive the error output.
 the specified string, or the whole string if a file name cannot be found via normal  
 methods. The second element contains the start position of the file name portion and  
 the third element contains the length.  
427    
428  =back  =back
429    
430  =cut  =cut
 #: Return Type $;  
 sub FindNamePart {  
     # Get the parameters.  
     my ($fileSpec) = @_;  
     # Default to the whole input string.  
     my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);  
     # Parse out the file name if we can.  
     if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {  
         $retVal = $2;  
         $len = length $retVal;  
         $pos = (length $fileSpec) - (length $3) - $len;  
     }  
     # Return the result.  
     return ($retVal, $pos, $len);  
 }  
   
 =head3 OpenDir  
   
 C<< my @files = OpenDir($dirName, $filtered); >>  
   
 Open a directory and return all the file names. This function essentially performs  
 the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is  
 set to TRUE, all filenames beginning with a period (C<.>) will be filtered out of  
 the return list. If the directory does not open, an exception is thrown. So,  
 for example,  
   
     my @files = OpenDir("/Volumes/fig/contigs", 1);  
431    
432  is effectively the same as  sub LogErrors {
433        # Get the file name.
434      opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");      my ($fileName) = @_;
435      my @files = grep { $_ !~ /^\./ } readdir(TMP);      # Open the file as the standard error output.
436        open STDERR, '>', $fileName;
437    }
438    
439  Similarly, the following code  =head3 Trace
440    
441      my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs");      Trace($message);
442    
443  Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and  Write a trace message to the target location specified in L</TSetup>. If there has not been
444  automatically throws an error if the directory fails to open.  any prior call to B<TSetup>.
445    
446  =over 4  =over 4
447    
448  =item dirName  =item message
   
 Name of the directory to open.  
   
 =item filtered  
449    
450  TRUE if files whose names begin with a period (C<.>) should be automatically removed  Message to write.
 from the list, else FALSE.  
451    
452  =back  =back
453    
454  =cut  =cut
455  #: Return Type @;  
456  sub OpenDir {  sub Trace {
457      # Get the parameters.      # Get the parameters.
458      my ($dirName, $filtered) = @_;      my ($message) = @_;
459      # Declare the return variable.      # Strip off any line terminators at the end of the message. We will add
460      my @retVal;      # new-line stuff ourselves.
461      # Open the directory.      my $stripped = Strip($message);
462      if (opendir(my $dirHandle, $dirName)) {      # Compute the caller information.
463          # The directory opened successfully. Get the appropriate list according to the      my ($callPackage, $callFile, $callLine) = caller();
464          # strictures of the filter parameter.      my $callFileTitle = basename($callFile);
465          if ($filtered) {      # Check the caller.
466              @retVal = grep { $_ !~ /^\./ } readdir $dirHandle;      my $callerInfo = ($callFileTitle ne "Tracer.pm" ? " [$callFileTitle $callLine]" : "");
467          } else {      # Get the timestamp.
468              @retVal = readdir $dirHandle;      my $timeStamp = Now();
469        # Build the prefix.
470        my $level = $LevelNames[$LastLevel] || "($LastLevel)";
471        my $prefix = "[$timeStamp] [$level] [$LastCategory]$callerInfo";
472        # Format the message.
473        my $formatted = "$prefix $stripped";
474        # Process according to the destination.
475        if ($Destination eq "TEXT") {
476            # Write the message to the standard output.
477            print "$formatted\n";
478        } elsif ($Destination eq "ERROR") {
479            # Write the message to the error output. Here, we want our prefix fields.
480            print STDERR "$formatted\n";
481        } elsif ($Destination eq "WARN") {
482            # Emit the message to the standard error output. It is presumed that the
483            # error logger will add its own prefix fields, the notable exception being
484            # the caller info.
485            print STDERR "$callerInfo$stripped\n";
486        } elsif ($Destination eq "QUEUE") {
487            # Push the message into the queue.
488            push @Queue, "$formatted";
489        } elsif ($Destination eq "HTML") {
490            # Convert the message to HTML and write it to the standard output.
491            my $escapedMessage = CGI::escapeHTML($stripped);
492            print "<p>$timeStamp $LastCategory $LastLevel: $escapedMessage</p>\n";
493        } elsif ($Destination =~ m/^>>/) {
494            # Write the trace message to an output file.
495            open(TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";
496            # Lock the file.
497            flock TRACING, LOCK_EX;
498            print TRACING "$formatted\n";
499            close TRACING;
500            # If the Tee flag is on, echo it to the standard output.
501            if ($TeeFlag) {
502                print "$formatted\n";
503          }          }
     } else {  
         # Here the directory would not open.  
         Confess("Could not open directory $dirName.");  
504      }      }
     # Return the result.  
     return @retVal;  
505  }  }
506    
507  =head3 SetLevel  =head3 T
508    
509  C<< Tracer::SetLevel($newLevel); >>      my $switch = T($category, $traceLevel);
510    
511  Modify the trace level. A higher trace level will cause more messages to appear.      or
512    
513  =over 4      my $switch = T($traceLevel);
514    
515  =item newLevel  Return TRUE if the trace level is at or above a specified value and the specified category
516    is active, else FALSE. If no category is specified, the caller's package name is used.
517    
518  Proposed new trace level.  =over 4
519    
520  =back  =item category
521    
522  =cut  Category to which the message belongs. If not specified, the caller's package name is
523    used.
524    
525  sub SetLevel {  =item traceLevel
     $TraceLevel = $_[0];  
 }  
526    
527  =head3 Now  Relevant tracing level.
528    
529    =item RETURN
530    
531  C<< my $string = Tracer::Now(); >>  TRUE if a message at the specified trace level would appear in the trace, else FALSE.
532    
533  Return a displayable time stamp containing the local time.  =back
534    
535  =cut  =cut
536    
537  sub Now {  sub T {
538      my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime(time);      # Declare the return variable.
539      my $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .      my $retVal = 0;
540                   _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);      # Only proceed if tracing is turned on.
541        if ($Destination ne "NONE") {
542            # Get the parameters.
543            my ($category, $traceLevel) = @_;
544            if (!defined $traceLevel) {
545                # Here we have no category, so we need to get the calling package.
546                # The calling package is normally the first parameter. If it is
547                # omitted, the first parameter will be the tracelevel. So, the
548                # first thing we do is shift the so-called category into the
549                # $traceLevel variable where it belongs.
550                $traceLevel = $category;
551                my ($package, $fileName, $line) = caller;
552                # If there is no calling package, we default to "main".
553                if (!$package) {
554                    $category = "main";
555                } else {
556                    my @cats = split /::/, $package;
557                    $category = $cats[$#cats];
558                }
559            }
560            # Save the category name and level.
561            $LastCategory = $category;
562            $LastLevel = $traceLevel;
563            # Convert it to lower case before we hash it.
564            $category = lc $category;
565            # Validate the trace level.
566            if (ref $traceLevel) {
567                Confess("Bad trace level.");
568            } elsif (ref $TraceLevel) {
569                Confess("Bad trace config.");
570            }
571            # Make the check. Note that level 0 shows even if the category is turned off.
572            $retVal = ($traceLevel <= $TraceLevel && ($traceLevel == 0 || $AllTrace || exists $Categories{$category}));
573        }
574        # Return the computed result.
575      return $retVal;      return $retVal;
576  }  }
577    
578  # Pad a number to 2 digits.  =head3 QTrace
579  sub _p2 {  
580      my ($value) = @_;      my $data = QTrace($format);
581      $value = "0$value" if ($value < 10);  
582      return $value;  Return the queued trace data in the specified format.
583    
584    =over 4
585    
586    =item format
587    
588    C<html> to format the data as an HTML list, C<text> to format it as straight text.
589    
590    =back
591    
592    =cut
593    
594    sub QTrace {
595        # Get the parameter.
596        my ($format) = @_;
597        # Create the return variable.
598        my $retVal = "";
599        # Only proceed if there is an actual queue.
600        if (@Queue) {
601            # Process according to the format.
602            if ($format =~ m/^HTML$/i) {
603                # Convert the queue into an HTML list.
604                $retVal = "<ul>\n";
605                for my $line (@Queue) {
606                    my $escapedLine = CGI::escapeHTML($line);
607                    $retVal .= "<li>$escapedLine</li>\n";
608                }
609                $retVal .= "</ul>\n";
610            } elsif ($format =~ m/^TEXT$/i) {
611                # Convert the queue into a list of text lines.
612                $retVal = join("\n", @Queue) . "\n";
613            }
614            # Clear the queue.
615            @Queue = ();
616        }
617        # Return the formatted list.
618        return $retVal;
619    }
620    
621    =head3 Confess
622    
623        Confess($message);
624    
625    Trace the call stack and abort the program with the specified message. When used with
626    the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.
627    So, for example
628    
629        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
630    
631    Will abort the program with a stack trace if the value of C<$recNum> is negative.
632    
633    =over 4
634    
635    =item message
636    
637    Message to include in the trace.
638    
639    =back
640    
641    =cut
642    
643    sub Confess {
644        # Get the parameters.
645        my ($message) = @_;
646        # Set up the category and level.
647        $LastCategory = "(confess)";
648        $LastLevel = 0;
649        if (! defined($FIG_Config::no_tool_hdr)) {
650            # Here we have a tool header. Display its length so that the user can adjust the line numbers.
651            my $toolHeaderFile = "$FIG_Config::fig_disk/dist/releases/current/$FIG_Config::arch/tool_hdr";
652            # Only proceed if the tool header file is actually present.
653            if (-f $toolHeaderFile) {
654                my $fh;
655                if (open $fh, "<$toolHeaderFile") {
656                    my @lines = <$fh>;
657                    Trace("Tool header has " . scalar(@lines) . " lines.");
658                }
659            }
660        }
661        # Trace the call stack.
662        Cluck($message);
663        # Abort the program.
664        croak(">>> $message");
665    }
666    
667    =head3 SaveCGI
668    
669        Tracer::SaveCGI($cgi);
670    
671    This method saves the CGI object but does not activate emergency tracing.
672    It is used to allow L</Warn> to work in situations where emergency
673    tracing is contra-indicated (e.g. the wiki).
674    
675    =over 4
676    
677    =item cgi
678    
679    Active CGI query object.
680    
681    =back
682    
683    =cut
684    
685    sub SaveCGI {
686        $SavedCGI = $_[0];
687    }
688    
689    =head3 Warn
690    
691        Warn($message, @options);
692    
693    This method traces an important message. If an RSS feed is configured
694    (via I<FIG_Config::error_feed>) and the tracing destination is C<WARN>,
695    then the message will be echoed to the feed. In general, a tracing
696    destination of C<WARN> indicates that the caller is running as a web
697    service in a production environment; however, this is not a requirement.
698    
699    To force warnings into the RSS feed even when the tracing destination
700    is not C<WARN>, simply specify the C<Feed> tracing module. This can be
701    configured automatically when L</StandardSetup> is used.
702    
703    The L</Cluck> method calls this one for its final message. Since
704    L</Confess> calls L</Cluck>, this means that any error which is caught
705    and confessed will put something in the feed. This insures that someone
706    will be alerted relatively quickly when a failure occurs.
707    
708    =over 4
709    
710    =item message
711    
712    Message to be traced.
713    
714    =item options
715    
716    A list containing zero or more options.
717    
718    =back
719    
720    The permissible options are as follows.
721    
722    =over 4
723    
724    =item noStack
725    
726    If specified, then the stack trace is not included in the output.
727    
728    =back
729    
730    =cut
731    
732    sub Warn {
733        # Get the parameters.
734        my $message = shift @_;
735        my %options = map { $_ => 1 } @_;
736        # Save $@;
737        my $savedError = $@;
738        # Trace the message.
739        Trace($message);
740        # This will contain the lock handle. If it's defined, it means we need to unlock.
741        my $lock;
742        # Check for feed forcing.
743        my $forceFeed = exists $Categories{feed};
744        # An error here would be disastrous. Note that if debug mode is specified,
745        # we do this stuff even in a test environment.
746        eval {
747            # Do we need to put this in the RSS feed?
748            if ($FIG_Config::error_feed && ($Destination eq 'WARN' || $forceFeed)) {
749                # Probably. We need to check first, however, to see if it's from an
750                # ignored IP. For non-CGI situations, we default the IP to the self-referent.
751                my $key = "127.0.0.1";
752                if (defined $SavedCGI) {
753                    # Get the IP address.
754                    $key = $ENV{HTTP_X_FORWARDED_FOR} || $ENV{REMOTE_ADDR};
755                }
756                # Is the IP address in the ignore list?
757                my $found = scalar(grep { $_ eq $key } @FIG_Config::error_ignore_ips);
758                if (! $found) {
759                    # No. We're good. We now need to compute the date, the link, and the title.
760                    # First, the date, in a very specific format.
761                    my $date = strftime("%a, %02e %b %H:%M:%S %Y ", localtime) .
762                        (tz_local_offset() / 30);
763                    # Environment data goes in here. We start with the date.
764                    my $environment = "$date.  ";
765                    # If we need to recap the message (because it's too long to be a title), we'll
766                    # put it in here.
767                    my $recap;
768                    # Copy the message and remove excess space.
769                    my $title = $message;
770                    $title =~ s/\s+/ /gs;
771                    # If it's too long, we have to split it up.
772                    if (length $title > 60) {
773                        # Put the full message in the environment string.
774                        $recap = $title;
775                        # Excerpt it as the title.
776                        $title = substr($title, 0, 50) . "...";
777                    }
778                    # If we have a CGI object, then this is a web error. Otherwise, it's
779                    # command-line.
780                    if (defined $SavedCGI) {
781                        # We're in a web service. The environment is the user's IP, and the link
782                        # is the URL that got us here.
783                        $environment .= "Event Reported at IP address $key process $$.";
784                        my $url = $SavedCGI->self_url();
785                        # We need the user agent string and (if available) the referrer.
786                        # The referrer will be the link.
787                        $environment .= " User Agent $ENV{HTTP_USER_AGENT}";
788                        if ($ENV{HTTP_REFERER}) {
789                            my $link = $ENV{HTTP_REFERER};
790                            $environment .= " referred from <a href=\"$link\">$link</a>.";
791                        } else {
792                            $environment .= " referrer unknown.";
793                        }
794                        # Close off the sentence with the original link.
795                        $environment .= " URL of event is <a href=\"$url\">$url</a>.";
796                    } else {
797                        # No CGI object, so we're a command-line tool. Use the tracing
798                        # key and the PID as the user identifier, and add the command.
799                        my $key = EmergencyKey();
800                        $environment .= "Event Reported by $key process $$.";
801                        if ($CommandLine) {
802                            # We're in a StandardSetup script, so we have the real command line.
803                            $environment .= "\n<pre>" . CGI::escapeHTML($CommandLine) . "</pre>\n";
804                        } elsif ($ENV{_}) {
805                            # We're in a BASH script, so the command has been stored in the _ variable.
806                            $environment .= "  Command = " . CGI::escapeHTML($ENV{_}) . "\n";
807                        }
808                    }
809                    # Build a GUID. We use the current time, the title, and the process ID,
810                    # then digest the result.
811                    my $guid = Digest::MD5::md5_base64(gettimeofday(), $title, $$);
812                    # Finally, the description. This is a stack trace plus various environmental stuff.
813                    # The trace is optional.
814                    my $stackTrace;
815                    if ($options{noStack}) {
816                        $stackTrace = "";
817                    } else {
818                        my @trace = LongMess();
819                        # Only proceed if we got something back.
820                        if (scalar(@trace) > 0) {
821                            $trace[0] =~ s/Tracer::Warn.+?called/Event occurred/;
822                            $stackTrace = "Stack trace:<pre>" . join("\n", @trace, "</pre>");
823                        }
824                    }
825                    # We got the stack trace. Now it's time to put it all together.
826                    # We have a goofy thing here in that we need to HTML-escape some sections of the description
827                    # twice. They will be escaped once here, and then once when written by XML::Simple. They are
828                    # unescaped once when processed by the RSS reader, and stuff in the description is treated as
829                    # HTML. So, anything escaped here is treated as a literal when viewed in the RSS reader, but
830                    # our <br>s and <pre>s are used to format the description.
831                    $recap = (defined $recap ? "<em>" . CGI::escapeHTML($recap) . "</em><br /><br />" : "");
832                    my $description = "$recap$environment  $stackTrace";
833                    # Okay, we have all the pieces. Create a hash of the new event.
834                    my $newItem = { title => $title,
835                                    description => $description,
836                                    category => $LastCategory,
837                                    pubDate => $date,
838                                    guid => $guid,
839                                  };
840                    # We need XML capability for this.
841                    require XML::Simple;
842                    # The RSS document goes in here.
843                    my $rss;
844                    # Get the name of the RSS file. It's in the FIG temporary directory.
845                    my $fileName = "$FIG_Config::temp/$FIG_Config::error_feed";
846                    # Open the config file and lock it.
847                    $lock = Open(undef, "<$FIG_Config::fig_disk/config/FIG_Config.pm");
848                    flock $lock, LOCK_EX;
849                    # Does it exist?
850                    if (-s $fileName) {
851                        # Slurp it in.
852                        $rss = XML::Simple::XMLin($fileName, ForceArray => ['item']);
853                    } else {
854                        my $size = -s $fileName;
855                        # Create an empty channel.
856                        $rss = {
857                            channel => {
858                                title => 'NMPDR Warning Feed',
859                                link => "$FIG_Config::temp_url/$FIG_Config::error_feed",
860                                description => "Important messages regarding the status of the NMPDR.",
861                                generator => "NMPDR Trace Facility",
862                                docs => "http://blogs.law.harvard.edu/tech/rss",
863                                item => []
864                            },
865                        };
866                    }
867                    # Get the channel object.
868                    my $channel = $rss->{channel};
869                    # Update the last-build date.
870                    $channel->{lastBuildDate} = $date;
871                    # Get the item array.
872                    my $items = $channel->{item};
873                    # Insure it has only 100 entries.
874                    while (scalar @{$items} > 100) {
875                        pop @{$items};
876                    }
877                    # Add our new item at the front.
878                    unshift @{$items}, $newItem;
879                    # Create the XML. Note we do not include the root or the declaration. XML Simple can't handle
880                    # the requirements for those.
881                    my $xml = XML::Simple::XMLout($channel, NoAttr => 1, RootName => 'channel', XmlDecl => '');
882                    # Here we put in the root and declaration. The problem is that the root has to have the version attribute
883                    # in it. So, we suppress the root and do it by hand, and that requires suppressing the declaration, too.
884                    $xml = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n<rss version=\"2.0\">$xml\n</rss>";
885                    # We don't use Open here because we can't afford an error.
886                    if (open XMLOUT, ">$fileName") {
887                        print XMLOUT $xml;
888                        close XMLOUT;
889                    }
890                }
891            }
892        };
893        if ($@) {
894            # If the feed failed, we need to know why. The error will be traced, but this method will not be involved
895            # (which is a good thing).
896            my $error = $@;
897            Trace("Feed Error: $error") if T(Feed => 0);
898        }
899        # Be sure to unlock.
900        if ($lock) {
901            flock $lock, LOCK_UN;
902            undef $lock;
903        }
904        # Restore the error message.
905        $@ = $savedError;
906    }
907    
908    
909    
910    
911    =head3 Assert
912    
913        Assert($condition1, $condition2, ... $conditionN);
914    
915    Return TRUE if all the conditions are true. This method can be used in conjunction with
916    the OR operator and the L</Confess> method as a debugging assert.
917    So, for example
918    
919        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
920    
921    Will abort the program with a stack trace if the value of C<$recNum> is negative.
922    
923    =cut
924    sub Assert {
925        my $retVal = 1;
926        LOOP: for my $condition (@_) {
927            if (! $condition) {
928                $retVal = 0;
929                last LOOP;
930            }
931        }
932        return $retVal;
933    }
934    
935    =head3 Cluck
936    
937        Cluck($message);
938    
939    Trace the call stack. Note that for best results, you should qualify the call with a
940    trace condition. For example,
941    
942        Cluck("Starting record parse.") if T(3);
943    
944    will only trace the stack if the trace level for the package is 3 or more.
945    
946    =over 4
947    
948    =item message
949    
950    Message to include in the trace.
951    
952    =back
953    
954    =cut
955    
956    sub Cluck {
957        # Get the parameters.
958        my ($message) = @_;
959        # Trace what's happening.
960        Trace("Stack trace for event: $message");
961        # Get the stack trace.
962        my @trace = LongMess();
963        # Convert the trace to a series of messages.
964        for my $line (@trace) {
965            # Replace the tab at the beginning with spaces.
966            $line =~ s/^\t/    /;
967            # Trace the line.
968            Trace($line);
969        }
970        # Issue a warning. This displays the event message and inserts it into the RSS error feed.
971        Warn($message);
972    }
973    
974    =head3 LongMess
975    
976        my @lines = Tracer::LongMess();
977    
978    Return a stack trace with all tracing methods removed. The return will be in the form of a list
979    of message strings.
980    
981    =cut
982    
983    sub LongMess {
984        # Declare the return variable.
985        my @retVal = ();
986        my $confession = longmess("");
987        for my $line (split /\s*\n/, $confession) {
988            unless ($line =~ /Tracer\.pm/) {
989                # Here we have a line worth keeping. Push it onto the result list.
990                push @retVal, $line;
991            }
992        }
993        # Return the result.
994        return @retVal;
995    }
996    
997    =head3 ETracing
998    
999        ETracing($parameter);
1000    
1001    Set up emergency tracing. Emergency tracing is tracing that is turned
1002    on automatically for any program that calls this method. The emergency
1003    tracing parameters are stored in a a file identified by a tracing key.
1004    If this method is called with a CGI object, then the tracing key is
1005    taken from a cookie. If it is called with no parameters, then the tracing
1006    key is taken from an environment variable. If it is called with a string,
1007    the tracing key is that string.
1008    
1009    =over 4
1010    
1011    =item parameter
1012    
1013    A parameter from which the tracing key is computed. If it is a scalar,
1014    that scalar is used as the tracing key. If it is a CGI object, the
1015    tracing key is taken from the C<IP> cookie. If it is omitted, the
1016    tracing key is taken from the C<TRACING> environment variable. If it
1017    is a CGI object and emergency tracing is not on, the C<Trace> and
1018    C<TF> parameters will be used to determine the type of tracing.
1019    
1020    =back
1021    
1022    =cut
1023    
1024    sub ETracing {
1025        # Get the parameter.
1026        my ($parameter) = @_;
1027        # Check for CGI mode.
1028        if (defined $parameter && ref $parameter eq 'CGI') {
1029            $SavedCGI = $parameter;
1030        } else {
1031            $SavedCGI = undef;
1032        }
1033        # Default to no tracing except errors.
1034        my ($tracing, $dest) = ("0", "WARN");
1035        # Check for emergency tracing.
1036        my $tkey = EmergencyKey($parameter);
1037        my $emergencyFile = EmergencyFileName($tkey);
1038        if (-e $emergencyFile) {
1039            # We have the file. Read in the data.
1040            my @tracing = GetFile($emergencyFile);
1041            # Pull off the time limit.
1042            my $expire = shift @tracing;
1043            # Convert it to seconds.
1044            $expire *= 3600;
1045            # Check the file data.
1046            my $stat = stat($emergencyFile);
1047            my ($now) = gettimeofday;
1048            if ($now - $stat->mtime > $expire) {
1049                # Delete the expired file.
1050                unlink $emergencyFile;
1051            } else {
1052                # Emergency tracing is on. Pull off the destination and
1053                # the trace level;
1054                $dest = shift @tracing;
1055                my $level = shift @tracing;
1056                # Convert the destination to a real tracing destination.
1057                # temp directory.
1058                $dest = EmergencyTracingDest($tkey, $dest);
1059                # Insure Tracer is specified.
1060                my %moduleHash = map { $_ => 1 } @tracing;
1061                $moduleHash{Tracer} = 1;
1062                # Set the trace parameter.
1063                $tracing = join(" ", $level, sort keys %moduleHash);
1064            }
1065        } elsif (defined $SavedCGI) {
1066            # There's no emergency tracing, but we have a CGI object, so check
1067            # for tracing from the form parameters.
1068            if ($SavedCGI->param('Trace')) {
1069                # Here the user has requested tracing via a form.
1070                $dest = ($SavedCGI->param('TF') ? ">$FIG_Config::temp/Trace$$.log" : "QUEUE");
1071                $tracing = $SavedCGI->param('Trace') . " Tracer";
1072            }
1073        }
1074        # Setup the tracing we've determined from all the stuff above.
1075        TSetup($tracing, $dest);
1076        # Check to see if we're a web script.
1077        if (defined $SavedCGI) {
1078            # Yes we are. Trace the form and environment data.
1079            TraceParms($SavedCGI);
1080            # Check for RAW mode. In raw mode, we print a fake header so that we see everything
1081            # emitted by the script in its raw form.
1082            if (T(Raw => 3)) {
1083                print CGI::header(-type => 'text/plain', -tracing => 'Raw');
1084            }
1085        }
1086    }
1087    
1088    =head3 EmergencyFileName
1089    
1090        my $fileName = Tracer::EmergencyFileName($tkey);
1091    
1092    Return the emergency tracing file name. This is the file that specifies
1093    the tracing information.
1094    
1095    =over 4
1096    
1097    =item tkey
1098    
1099    Tracing key for the current program.
1100    
1101    =item RETURN
1102    
1103    Returns the name of the file to contain the emergency tracing information.
1104    
1105    =back
1106    
1107    =cut
1108    
1109    sub EmergencyFileName {
1110        # Get the parameters.
1111        my ($tkey) = @_;
1112        # Compute the emergency tracing file name.
1113        return "$FIG_Config::temp/Emergency$tkey.txt";
1114    }
1115    
1116    =head3 EmergencyFileTarget
1117    
1118        my $fileName = Tracer::EmergencyFileTarget($tkey);
1119    
1120    Return the emergency tracing target file name. This is the file that receives
1121    the tracing output for file-based tracing.
1122    
1123    =over 4
1124    
1125    =item tkey
1126    
1127    Tracing key for the current program.
1128    
1129    =item RETURN
1130    
1131    Returns the name of the file to contain the trace output.
1132    
1133    =back
1134    
1135    =cut
1136    
1137    sub EmergencyFileTarget {
1138        # Get the parameters.
1139        my ($tkey) = @_;
1140        # Compute the emergency tracing file name.
1141        return "$FIG_Config::temp/trace$tkey.log";
1142    }
1143    
1144    =head3 EmergencyTracingDest
1145    
1146        my $dest = Tracer::EmergencyTracingDest($tkey, $myDest);
1147    
1148    This method converts an emergency tracing destination to a real
1149    tracing destination. The main difference is that if the
1150    destination is C<FILE> or C<APPEND>, we convert it to file
1151    output. If the destination is C<DUAL>, we convert it to file
1152    and standard output.
1153    
1154    =over 4
1155    
1156    =item tkey
1157    
1158    Tracing key for this environment.
1159    
1160    =item myDest
1161    
1162    Destination from the emergency tracing file.
1163    
1164    =item RETURN
1165    
1166    Returns a destination that can be passed into L</TSetup>.
1167    
1168    =back
1169    
1170    =cut
1171    
1172    sub EmergencyTracingDest {
1173        # Get the parameters.
1174        my ($tkey, $myDest) = @_;
1175        # Declare the return variable.
1176        my $retVal = $myDest;
1177        # Process according to the destination value.
1178        if ($myDest eq 'FILE') {
1179            $retVal = ">" . EmergencyFileTarget($tkey);
1180        } elsif ($myDest eq 'APPEND') {
1181            $retVal = ">>" . EmergencyFileTarget($tkey);
1182        } elsif ($myDest eq 'DUAL') {
1183            $retVal = "+>" . EmergencyFileTarget($tkey);
1184        } elsif ($myDest eq 'WARN') {
1185            $retVal = "WARN";
1186        }
1187        # Return the result.
1188        return $retVal;
1189    }
1190    
1191    =head3 Emergency
1192    
1193        Emergency($key, $hours, $dest, $level, @modules);
1194    
1195    Turn on emergency tracing. This method is normally invoked over the web from
1196    a debugging console, but it can also be called by the C<trace.pl> script.
1197    The caller specifies the duration of the emergency in hours, the desired tracing
1198    destination, the trace level, and a list of the trace modules to activate.
1199    For the length of the duration, when a program in an environment with the
1200    specified tracing key active invokes a Sprout CGI script, tracing will be
1201    turned on automatically. See L</TSetup> for more about tracing setup and
1202    L</ETracing> for more about emergency tracing.
1203    
1204    =over 4
1205    
1206    =item tkey
1207    
1208    The tracing key. This is used to identify the control file and the trace file.
1209    
1210    =item hours
1211    
1212    Number of hours to keep emergency tracing alive.
1213    
1214    =item dest
1215    
1216    Tracing destination. If no path information is specified for a file
1217    destination, it is put in the FIG temporary directory.
1218    
1219    =item level
1220    
1221    Tracing level. A higher level means more trace messages.
1222    
1223    =item modules
1224    
1225    A list of the tracing modules to activate.
1226    
1227    =back
1228    
1229    =cut
1230    
1231    sub Emergency {
1232        # Get the parameters.
1233        my ($tkey, $hours, $dest, $level, @modules) = @_;
1234        # Create the emergency file.
1235        my $specFile = EmergencyFileName($tkey);
1236        my $outHandle = Open(undef, ">$specFile");
1237        print $outHandle join("\n", $hours, $dest, $level, @modules, "");
1238    }
1239    
1240    =head3 EmergencyKey
1241    
1242        my $tkey = EmergencyKey($parameter);
1243    
1244    Return the Key to be used for emergency tracing. This could be an IP address,
1245     a session ID, or a user name, depending on the environment.
1246    
1247    =over 4
1248    
1249    =item parameter
1250    
1251    Parameter defining the method for finding the tracing key. If it is a scalar,
1252    then it is presumed to be the tracing key itself. If it is a CGI object, then
1253    the tracing key is taken from the C<IP> cookie. Otherwise, the tracing key is
1254    taken from the C<TRACING> environment variable.
1255    
1256    =item RETURN
1257    
1258    Returns the key to be used for labels in emergency tracing.
1259    
1260    =back
1261    
1262    =cut
1263    
1264    sub EmergencyKey {
1265        # Get the parameters.
1266        my ($parameter) = @_;
1267        # Declare the return variable.
1268        my $retVal;
1269        # Determine the parameter type.
1270        if (! defined $parameter) {
1271            # Here we're supposed to check the environment. If that fails, we
1272            # get the effective login ID.
1273            $retVal = $ENV{TRACING} || scalar getpwuid($<);
1274        } else {
1275            my $ptype = ref $parameter;
1276            if ($ptype eq 'CGI') {
1277                # Here we were invoked from a web page. Look for a cookie.
1278                $retVal = $parameter->cookie('IP');
1279            } elsif (! $ptype) {
1280                # Here the key was passed in.
1281                $retVal = $parameter;
1282            }
1283        }
1284        # If no luck finding a key, use the PID.
1285        if (! defined $retVal) {
1286            $retVal = $$;
1287        }
1288        # Return the result.
1289        return $retVal;
1290    }
1291    
1292    
1293    =head3 TraceParms
1294    
1295        Tracer::TraceParms($cgi);
1296    
1297    Trace the CGI parameters at trace level CGI => 3 and the environment variables
1298    at level CGI => 4. A self-referencing URL is traced at level CGI => 2.
1299    
1300    =over 4
1301    
1302    =item cgi
1303    
1304    CGI query object containing the parameters to trace.
1305    
1306    =back
1307    
1308    =cut
1309    
1310    sub TraceParms {
1311        # Get the parameters.
1312        my ($cgi) = @_;
1313        if (T(CGI => 2)) {
1314            # Here we trace the GET-style URL for the script.
1315            Trace("[URL] " . $cgi->url(-relative => 1, -query => 1));
1316        }
1317        if (T(CGI => 3)) {
1318            # Here we want to trace the parameter data.
1319            my @names = $cgi->param;
1320            for my $parmName (sort @names) {
1321                # Note we skip the Trace parameters, which are for our use only.
1322                if ($parmName ne 'Trace' && $parmName ne 'TF') {
1323                    my @values = $cgi->param($parmName);
1324                    Trace("[CGI] $parmName = " . join(", ", @values));
1325                }
1326            }
1327            # Display the request method.
1328            my $method = $cgi->request_method();
1329            Trace("Method: $method");
1330        }
1331        if (T(CGI => 4)) {
1332            # Here we want the environment data too.
1333            for my $envName (sort keys %ENV) {
1334                Trace("[ENV] $envName = $ENV{$envName}");
1335            }
1336        }
1337    }
1338    
1339    =head3 TraceImages
1340    
1341        Tracer::TraceImages($htmlString);
1342    
1343    Trace information about all of an html document's images. The tracing
1344    will be for type "IMG" at level 3. The image's source string
1345    will be displayed. This is generally either the URL of the image or
1346    raw data for the image itself. If the source is too long, only the first 300
1347    characters will be shown at trace level 3. The entire source will be shown,
1348    however, at trace level 4. This method is not very smart, and might catch
1349    Javascript code, but it is still useful when debugging the arcane
1350    behavior of images in multiple browser environments.
1351    
1352    =over 4
1353    
1354    =item htmlString
1355    
1356    HTML text for an outgoing web page.
1357    
1358    =back
1359    
1360    =cut
1361    
1362    sub TraceImages {
1363        # Only proceed if we're at the proper trace level.
1364        if (T(IMG => 3)) {
1365            # For performance reasons we're manipulating $_[0] instead of retrieving the string
1366            # into a variable called "$htmlString". This is because we expect html strings to be
1367            # long, and don't want to copy them any more than we have to.
1368            Trace(length($_[0]) . " characters in web page.");
1369            # Loop through the HTML, culling image tags.
1370            while ($_[0] =~ /<img\s+[^>]+?src="([^"]+)"/sgi) {
1371                # Extract the source string and determine whether or not it's too long.
1372                my $srcString = $1;
1373                my $pos = pos($_[0]) - length($srcString);
1374                my $excess = length($srcString) - 300;
1375                # We'll put the display string in here.
1376                my $srcDisplay = $srcString;
1377                # If it's a data string, split it at the comma.
1378                $srcDisplay =~ s/^(data[^,]+,)/$1\n/;
1379                # If there's no excess or we're at trace level 4, we're done. At level 3 with
1380                # a long string, however, we only show the first 300 characters.
1381                if ($excess > 0 && ! T(IMG => 4)) {
1382                    $srcDisplay = substr($srcDisplay,0,300) . "\nplus $excess characters.";
1383                }
1384                # Output the trace message.
1385                Trace("Image tag at position $pos:\n$srcDisplay");
1386            }
1387        }
1388    }
1389    
1390    =head2 Command-Line Utility Methods
1391    
1392    =head3 SendSMS
1393    
1394        my $msgID = Tracer::SendSMS($phoneNumber, $msg);
1395    
1396    Send a text message to a phone number using Clickatell. The FIG_Config file must contain the
1397    user name, password, and API ID for the relevant account in the hash reference variable
1398    I<$FIG_Config::phone>, using the keys C<user>, C<password>, and C<api_id>. For
1399    example, if the user name is C<BruceTheHumanPet>, the password is C<silly>, and the API ID
1400    is C<2561022>, then the FIG_Config file must contain
1401    
1402        $phone =  { user => 'BruceTheHumanPet',
1403                    password => 'silly',
1404                    api_id => '2561022' };
1405    
1406    The original purpose of this method was to insure Bruce would be notified immediately when the
1407    Sprout Load terminates. Care should be taken if you do not wish Bruce to be notified immediately
1408    when you call this method.
1409    
1410    The message ID will be returned if successful, and C<undef> if an error occurs.
1411    
1412    =over 4
1413    
1414    =item phoneNumber
1415    
1416    Phone number to receive the message, in international format. A United States phone number
1417    would be prefixed by "1". A British phone number would be prefixed by "44".
1418    
1419    =item msg
1420    
1421    Message to send to the specified phone.
1422    
1423    =item RETURN
1424    
1425    Returns the message ID if successful, and C<undef> if the message could not be sent.
1426    
1427    =back
1428    
1429    =cut
1430    
1431    sub SendSMS {
1432        # Get the parameters.
1433        my ($phoneNumber, $msg) = @_;
1434        # Declare the return variable. If we do not change it, C<undef> will be returned.
1435        my $retVal;
1436        # Only proceed if we have phone support.
1437        if (! defined $FIG_Config::phone) {
1438            Trace("Phone support not present in FIG_Config.") if T(1);
1439        } else {
1440            # Get the phone data.
1441            my $parms = $FIG_Config::phone;
1442            # Get the Clickatell URL.
1443            my $url = "http://api.clickatell.com/http/";
1444            # Create the user agent.
1445            my $ua = LWP::UserAgent->new;
1446            # Request a Clickatell session.
1447            my $resp = $ua->post("$url/sendmsg", { user => $parms->{user},
1448                                         password => $parms->{password},
1449                                         api_id => $parms->{api_id},
1450                                         to => $phoneNumber,
1451                                         text => $msg});
1452            # Check for an error.
1453            if (! $resp->is_success) {
1454                Trace("Alert failed.") if T(1);
1455            } else {
1456                # Get the message ID.
1457                my $rstring = $resp->content;
1458                if ($rstring =~ /^ID:\s+(.*)$/) {
1459                    $retVal = $1;
1460                } else {
1461                    Trace("Phone attempt failed with $rstring") if T(1);
1462                }
1463            }
1464        }
1465        # Return the result.
1466        return $retVal;
1467    }
1468    
1469    =head3 StandardSetup
1470    
1471        my ($options, @parameters) = StandardSetup(\@categories, \%options, $parmHelp, @ARGV);
1472    
1473    This method performs standard command-line parsing and tracing setup. The return
1474    values are a hash of the command-line options and a list of the positional
1475    parameters. Tracing is automatically set up and the command-line options are
1476    validated.
1477    
1478    This is a complex method that does a lot of grunt work. The parameters can
1479    be more easily understood, however, once they are examined individually.
1480    
1481    The I<categories> parameter is the most obtuse. It is a reference to a list of
1482    special-purpose tracing categories. Most tracing categories are PERL package
1483    names. So, for example, if you wanted to turn on tracing inside the B<Sprout>,
1484    B<ERDB>, and B<SproutLoad> packages, you would specify the categories
1485    
1486        ["Sprout", "SproutLoad", "ERDB"]
1487    
1488    This would cause trace messages in the specified three packages to appear in
1489    the output. There are two special tracing categories that are automatically
1490    handled by this method. In other words, if you used L</TSetup> you would need
1491    to include these categories manually, but if you use this method they are turned
1492    on automatically.
1493    
1494    =over 4
1495    
1496    =item SQL
1497    
1498    Traces SQL commands and activity.
1499    
1500    =item Tracer
1501    
1502    Traces error messages and call stacks.
1503    
1504    =back
1505    
1506    C<SQL> is only turned on if the C<-sql> option is specified in the command line.
1507    The trace level is specified using the C<-trace> command-line option. For example,
1508    the following command line for C<TransactFeatures> turns on SQL tracing and runs
1509    all tracing at level 3.
1510    
1511        TransactFeatures -trace=3 -sql register ../xacts IDs.tbl
1512    
1513    Standard tracing is output to the standard output and echoed to the file
1514    C<trace>I<$$>C<.log> in the FIG temporary directory, where I<$$> is the
1515    process ID. You can also specify the C<user> parameter to put a user ID
1516    instead of a process ID in the trace file name. So, for example
1517    
1518    The default trace level is 2. To get all messages, specify a trace level of 4.
1519    For a genome-by-genome update, use 3.
1520    
1521        TransactFeatures -trace=3 -sql -user=Bruce register ../xacts IDs.tbl
1522    
1523    would send the trace output to C<traceBruce.log> in the temporary directory.
1524    
1525    The I<options> parameter is a reference to a hash containing the command-line
1526    options, their default values, and an explanation of what they mean. Command-line
1527    options may be in the form of switches or keywords. In the case of a switch, the
1528    option value is 1 if it is specified and 0 if it is not specified. In the case
1529    of a keyword, the value is separated from the option name by an equal sign. You
1530    can see this last in the command-line example above.
1531    
1532    You can specify a different default trace level by setting C<$options->{trace}>
1533    prior to calling this method.
1534    
1535    An example at this point would help. Consider, for example, the command-line utility
1536    C<TransactFeatures>. It accepts a list of positional parameters plus the options
1537    C<safe>, C<noAlias>, C<start>, and C<tblFiles>. To start up this command, we execute
1538    the following code.
1539    
1540        my ($options, @parameters) = Tracer::StandardSetup(["DocUtils"],
1541                            { safe => [0, "use database transactions"],
1542                              noAlias => [0, "do not expect aliases in CHANGE transactions"],
1543                              start => [' ', "start with this genome"],
1544                              tblFiles => [0, "output TBL files containing the corrected IDs"] },
1545                            "<command> <transactionDirectory> <IDfile>",
1546                          @ARGV);
1547    
1548    
1549    The call to C<ParseCommand> specifies the default values for the options and
1550    stores the actual options in a hash that is returned as C<$options>. The
1551    positional parameters are returned in C<@parameters>.
1552    
1553    The following is a sample command line for C<TransactFeatures>.
1554    
1555        TransactFeatures -trace=2 -noAlias register ../xacts IDs.tbl
1556    
1557    Single and double hyphens are equivalent. So, you could also code the
1558    above command as
1559    
1560        TransactFeatures --trace=2 --noAlias register ../xacts IDs.tbl
1561    
1562    In this case, C<register>, C<../xacts>, and C<IDs.tbl> are the positional
1563    parameters, and would find themselves in I<@parameters> after executing the
1564    above code fragment. The tracing would be set to level 2, and the categories
1565    would be C<Tracer>, and <DocUtils>. C<Tracer> is standard,
1566    and C<DocUtils> was included because it came in within the first parameter
1567    to this method. The I<$options> hash would be
1568    
1569        { trace => 2, sql => 0, safe => 0,
1570          noAlias => 1, start => ' ', tblFiles => 0 }
1571    
1572    Use of C<StandardSetup> in this way provides a simple way of performing
1573    standard tracing setup and command-line parsing. Note that the caller is
1574    not even aware of the command-line switches C<-trace> and C<-sql>, which
1575    are used by this method to control the tracing. If additional tracing features
1576    need to be added in the future, they can be processed by this method without
1577    upsetting the command-line utilities.
1578    
1579    If the C<background> option is specified on the command line, then the
1580    standard and error outputs will be directed to files in the temporary
1581    directory, using the same suffix as the trace file. So, if the command
1582    line specified
1583    
1584        -user=Bruce -background
1585    
1586    then the trace output would go to C<traceBruce.log>, the standard output to
1587    C<outBruce.log>, and the error output to C<errBruce.log>. This is designed to
1588    simplify starting a command in the background.
1589    
1590    The user name is also used as the tracing key for L</Emergency Tracing>.
1591    Specifying a value of C<E> for the trace level causes emergency tracing to
1592    be used instead of custom tracing. If the user name is not specified,
1593    the tracing key is taken from the C<Tracing> environment variable. If there
1594    is no value for that variable, the tracing key will be computed from the active
1595    login ID.
1596    
1597    Since the default situation in StandardSetup is to trace to the standard
1598    output, errors that occur in command-line scripts will not generate
1599    RSS events. To force the events, use the C<warn> option.
1600    
1601        TransactFeatures -background -warn register ../xacts IDs.tbl
1602    
1603    Finally, if the special option C<-help> is specified, the option
1604    names will be traced at level 0 and the program will exit without processing.
1605    This provides a limited help capability. For example, if the user enters
1606    
1607        TransactFeatures -help
1608    
1609    he would see the following output.
1610    
1611        TransactFeatures [options] <command> <transactionDirectory> <IDfile>
1612            -trace    tracing level (default E)
1613            -sql      trace SQL commands
1614            -safe     use database transactions
1615            -noAlias  do not expect aliases in CHANGE transactions
1616            -start    start with this genome
1617            -tblFiles output TBL files containing the corrected IDs
1618            -forked   do not erase the trace file before tracing
1619    
1620    The caller has the option of modifying the tracing scheme by placing a value
1621    for C<trace> in the incoming options hash. The default value can be overridden,
1622    or the tracing to the standard output can be turned off by suffixing a minus
1623    sign to the trace level. So, for example,
1624    
1625        { trace => [0, "tracing level (default 0)"],
1626           ...
1627    
1628    would set the default trace level to 0 instead of E, while
1629    
1630        { trace => ["2-", "tracing level (default 2)"],
1631           ...
1632    
1633    would set the default to 2, but trace only to the log file, not to the
1634    standard output.
1635    
1636    The parameters to this method are as follows.
1637    
1638    =over 4
1639    
1640    =item categories
1641    
1642    Reference to a list of tracing category names. These should be names of
1643    packages whose internal workings will need to be debugged to get the
1644    command working.
1645    
1646    =item options
1647    
1648    Reference to a hash containing the legal options for the current command mapped
1649    to their default values and descriptions. The user can override the defaults
1650    by specifying the options as command-line switches prefixed by a hyphen.
1651    Tracing-related options may be added to this hash. If the C<-h> option is
1652    specified on the command line, the option descriptions will be used to
1653    explain the options. To turn off tracing to the standard output, add a
1654    minus sign to the value for C<trace> (see above).
1655    
1656    =item parmHelp
1657    
1658    A string that vaguely describes the positional parameters. This is used
1659    if the user specifies the C<-h> option.
1660    
1661    =item argv
1662    
1663    List of command line parameters, including the option switches, which must
1664    precede the positional parameters and be prefixed by a hyphen.
1665    
1666    =item RETURN
1667    
1668    Returns a list. The first element of the list is the reference to a hash that
1669    maps the command-line option switches to their values. These will either be the
1670    default values or overrides specified on the command line. The remaining
1671    elements of the list are the position parameters, in order.
1672    
1673    =back
1674    
1675    =cut
1676    
1677    sub StandardSetup {
1678        # Get the parameters.
1679        my ($categories, $options, $parmHelp, @argv) = @_;
1680        # Get the default tracing key.
1681        my $tkey = EmergencyKey();
1682        # Save the command line.
1683        $CommandLine = join(" ", $0, map { $_ =~ /\s/ ? "\"$_\"" : $_ } @argv);
1684        # Add the tracing options.
1685        if (! exists $options->{trace}) {
1686            $options->{trace} = ['2', "tracing level (E for emergency tracing)"];
1687        }
1688        $options->{forked} = [0, "keep old trace file"];
1689        $options->{sql} = [0, "turn on SQL tracing"];
1690        $options->{help} = [0, "display command-line options"];
1691        $options->{user} = [$tkey, "tracing key"];
1692        $options->{background} = [0, "spool standard and error output"];
1693        $options->{warn} = [0, "send errors to RSS feed"];
1694        # Create a parsing hash from the options hash. The parsing hash
1695        # contains the default values rather than the default value
1696        # and the description. While we're at it, we'll memorize the
1697        # length of the longest option name.
1698        my $longestName = 0;
1699        my %parseOptions = ();
1700        for my $key (keys %{$options}) {
1701            if (length $key > $longestName) {
1702                $longestName = length $key;
1703            }
1704            $parseOptions{$key} = $options->{$key}->[0];
1705        }
1706        # Parse the command line.
1707        my ($retOptions, @retParameters) = ParseCommand(\%parseOptions, @argv);
1708        # Get the logfile suffix.
1709        my $suffix = $retOptions->{user};
1710        # Check for background mode.
1711        if ($retOptions->{background}) {
1712            my $outFileName = "$FIG_Config::temp/out$suffix$$.log";
1713            my $errFileName = "$FIG_Config::temp/err$suffix$$.log";
1714            open STDOUT, ">$outFileName";
1715            open STDERR, ">$errFileName";
1716            # Check for phone support. If we have phone support and a phone number,
1717            # we want to turn it on.
1718            if ($ENV{PHONE} && defined($FIG_Config::phone)) {
1719                $retOptions->{phone} = $ENV{PHONE};
1720            }
1721        }
1722        # Now we want to set up tracing. First, we need to know if the user
1723        # wants emergency tracing.
1724        if ($retOptions->{trace} eq 'E') {
1725            ETracing($retOptions->{user});
1726        } else {
1727            # Here the tracing is controlled from the command line.
1728            my @cats = @{$categories};
1729            if ($retOptions->{sql}) {
1730                push @cats, "SQL";
1731            }
1732            if ($retOptions->{warn}) {
1733                push @cats, "Feed";
1734            }
1735            # Add the default categories.
1736            push @cats, "Tracer";
1737            # Next, we create the category string by joining the categories.
1738            my $cats = join(" ", @cats);
1739            # Check to determine whether or not the caller wants to turn off tracing
1740            # to the standard output.
1741            my $traceLevel = $retOptions->{trace};
1742            my $textOKFlag = 1;
1743            if ($traceLevel =~ /^(.)-/) {
1744                $traceLevel = $1;
1745                $textOKFlag = 0;
1746            }
1747            # Now we set up the trace mode.
1748            my $traceMode;
1749            # Verify that we can open a file in the FIG temporary directory.
1750            my $traceFileName = "$FIG_Config::temp/trace$suffix.log";
1751            my $traceFileSpec = ($retOptions->{forked} ? ">>$traceFileName" : ">$traceFileName");
1752            if (open TESTTRACE, "$traceFileSpec") {
1753                # Here we can trace to a file.
1754                $traceMode = ">>$traceFileName";
1755                if ($textOKFlag) {
1756                    # Echo to standard output if the text-OK flag is set.
1757                    $traceMode = "+$traceMode";
1758                }
1759                # Close the test file.
1760                close TESTTRACE;
1761            } else {
1762                # Here we can't trace to a file. Complain about this.
1763                warn "Could not open trace file $traceFileName: $!\n";
1764                # We trace to the standard output if it's
1765                # okay, and the error log otherwise.
1766                if ($textOKFlag) {
1767                    $traceMode = "TEXT";
1768                } else {
1769                    $traceMode = "WARN";
1770                }
1771            }
1772            # Now set up the tracing.
1773            TSetup("$traceLevel $cats", $traceMode);
1774        }
1775        # Check for the "help" option. If it is specified, dump the command-line
1776        # options and exit the program.
1777        if ($retOptions->{help}) {
1778            $0 =~ m#[/\\](\w+)(\.pl)?$#i;
1779            print "$1 [options] $parmHelp\n";
1780            for my $key (sort keys %{$options}) {
1781                my $name = Pad($key, $longestName, 0, ' ');
1782                my $desc = $options->{$key}->[1];
1783                if ($options->{$key}->[0]) {
1784                    $desc .= " (default " . $options->{$key}->[0] . ")";
1785                }
1786                print "  $name $desc\n";
1787            }
1788            exit(0);
1789        }
1790        # Trace the options, if applicable.
1791        if (T(3)) {
1792            my @parms = grep { $retOptions->{$_} } keys %{$retOptions};
1793            Trace("Selected options: " . join(", ", sort @parms) . ".");
1794        }
1795        # Return the parsed parameters.
1796        return ($retOptions, @retParameters);
1797    }
1798    
1799    =head3 ReadOptions
1800    
1801        my %options = Tracer::ReadOptions($fileName);
1802    
1803    Read a set of options from a file. Each option is encoded in a line of text that has the
1804    format
1805    
1806    I<optionName>C<=>I<optionValue>C<; >I<comment>
1807    
1808    The option name must consist entirely of letters, digits, and the punctuation characters
1809    C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank
1810    character is a semi-colon will be ignored. The return hash will map each option name to
1811    the corresponding option value.
1812    
1813    =over 4
1814    
1815    =item fileName
1816    
1817    Name of the file containing the option data.
1818    
1819    =item RETURN
1820    
1821    Returns a hash mapping the option names specified in the file to their corresponding option
1822    value.
1823    
1824    =back
1825    
1826    =cut
1827    
1828    sub ReadOptions {
1829        # Get the parameters.
1830        my ($fileName) = @_;
1831        # Open the file.
1832        (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");
1833        # Count the number of records read.
1834        my ($records, $comments) = 0;
1835        # Create the return hash.
1836        my %retVal = ();
1837        # Loop through the file, accumulating key-value pairs.
1838        while (my $line = <CONFIGFILE>) {
1839            # Denote we've read a line.
1840            $records++;
1841            # Determine the line type.
1842            if ($line =~ /^\s*[\n\r]/) {
1843                # A blank line is a comment.
1844                $comments++;
1845            } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {
1846                # Here we have an option assignment.
1847                retVal{$1} = $2;
1848            } elsif ($line =~ /^\s*;/) {
1849                # Here we have a text comment.
1850                $comments++;
1851            } else {
1852                # Here we have an invalid line.
1853                Trace("Invalid option statement in record $records.") if T(0);
1854            }
1855        }
1856        # Return the hash created.
1857        return %retVal;
1858    }
1859    
1860    =head3 GetOptions
1861    
1862        Tracer::GetOptions(\%defaults, \%options);
1863    
1864    Merge a specified set of options into a table of defaults. This method takes two hash references
1865    as input and uses the data from the second to update the first. If the second does not exist,
1866    there will be no effect. An error will be thrown if one of the entries in the second hash does not
1867    exist in the first.
1868    
1869    Consider the following example.
1870    
1871        my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options);
1872    
1873    In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and
1874    B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of
1875    B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and
1876    the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level
1877    will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as
1878    
1879        {databaseType => 'Oracle'}
1880    
1881    an error will occur because the B<databaseType> option does not exist.
1882    
1883    =over 4
1884    
1885    =item defaults
1886    
1887    Table of default option values.
1888    
1889    =item options
1890    
1891    Table of overrides, if any.
1892    
1893    =item RETURN
1894    
1895    Returns a reference to the default table passed in as the first parameter.
1896    
1897    =back
1898    
1899    =cut
1900    
1901    sub GetOptions {
1902        # Get the parameters.
1903        my ($defaults, $options) = @_;
1904        # Check for overrides.
1905        if ($options) {
1906            # Loop through the overrides.
1907            while (my ($option, $setting) = each %{$options}) {
1908                # Insure this override exists.
1909                if (!exists $defaults->{$option}) {
1910                    croak "Unrecognized option $option encountered.";
1911                } else {
1912                    # Apply the override.
1913                    $defaults->{$option} = $setting;
1914                }
1915            }
1916        }
1917        # Return the merged table.
1918        return $defaults;
1919    }
1920    
1921    =head3 MergeOptions
1922    
1923        Tracer::MergeOptions(\%table, \%defaults);
1924    
1925    Merge default values into a hash table. This method looks at the key-value pairs in the
1926    second (default) hash, and if a matching key is not found in the first hash, the default
1927    pair is copied in. The process is similar to L</GetOptions>, but there is no error-
1928    checking and no return value.
1929    
1930    =over 4
1931    
1932    =item table
1933    
1934    Hash table to be updated with the default values.
1935    
1936    =item defaults
1937    
1938    Default values to be merged into the first hash table if they are not already present.
1939    
1940    =back
1941    
1942    =cut
1943    
1944    sub MergeOptions {
1945        # Get the parameters.
1946        my ($table, $defaults) = @_;
1947        # Loop through the defaults.
1948        while (my ($key, $value) = each %{$defaults}) {
1949            if (!exists $table->{$key}) {
1950                $table->{$key} = $value;
1951            }
1952        }
1953    }
1954    
1955    =head3 UnparseOptions
1956    
1957        my $optionString = Tracer::UnparseOptions(\%options);
1958    
1959    Convert an option hash into a command-line string. This will not
1960    necessarily be the same text that came in, but it will nonetheless
1961    produce the same ultimate result when parsed by L</StandardSetup>.
1962    
1963    =over 4
1964    
1965    =item options
1966    
1967    Reference to a hash of options to convert into an option string.
1968    
1969    =item RETURN
1970    
1971    Returns a string that will parse to the same set of options when
1972    parsed by L</StandardSetup>.
1973    
1974    =back
1975    
1976    =cut
1977    
1978    sub UnparseOptions {
1979        # Get the parameters.
1980        my ($options) = @_;
1981        # The option segments will be put in here.
1982        my @retVal = ();
1983        # Loop through the options.
1984        for my $key (keys %$options) {
1985            # Get the option value.
1986            my $value = $options->{$key};
1987            # Only use it if it's nonempty.
1988            if (defined $value && $value ne "") {
1989                my $segment = "--$key=$value";
1990                # Quote it if necessary.
1991                if ($segment =~ /[ |<>*]/) {
1992                    $segment = '"' . $segment . '"';
1993                }
1994                # Add it to the return list.
1995                push @retVal, $segment;
1996            }
1997        }
1998        # Return the result.
1999        return join(" ", @retVal);
2000    }
2001    
2002    =head3 ParseCommand
2003    
2004        my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList);
2005    
2006    Parse a command line consisting of a list of parameters. The initial parameters may be option
2007    specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped
2008    off and merged into a table of default options. The remainder of the command line is
2009    returned as a list of positional arguments. For example, consider the following invocation.
2010    
2011        my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words);
2012    
2013    In this case, the list @words will be treated as a command line and there are two options available,
2014    B<errors> and B<logFile>. If @words has the following format
2015    
2016        -logFile=error.log apple orange rutabaga
2017    
2018    then at the end of the invocation, C<$options> will be
2019    
2020        { errors => 0, logFile => 'error.log' }
2021    
2022    and C<@arguments> will contain
2023    
2024        apple orange rutabaga
2025    
2026    The parser allows for some escape sequences. See L</UnEscape> for a description. There is no
2027    support for quote characters. Options can be specified with single or double hyphens.
2028    
2029    =over 4
2030    
2031    =item optionTable
2032    
2033    Table of default options.
2034    
2035    =item inputList
2036    
2037    List of words on the command line.
2038    
2039    =item RETURN
2040    
2041    Returns a reference to the option table and a list of the positional arguments.
2042    
2043    =back
2044    
2045    =cut
2046    
2047    sub ParseCommand {
2048        # Get the parameters.
2049        my ($optionTable, @inputList) = @_;
2050        # Process any options in the input list.
2051        my %overrides = ();
2052        while ((@inputList > 0) && ($inputList[0] =~ /^--?/)) {
2053            # Get the current option.
2054            my $arg = shift @inputList;
2055            # Pull out the option name.
2056            $arg =~ /^--?([^=]*)/g;
2057            my $name = $1;
2058            # Check for an option value.
2059            if ($arg =~ /\G=(.*)$/g) {
2060                # Here we have a value for the option.
2061                $overrides{$name} = UnEscape($1);
2062            } else {
2063                # Here there is no value, so we use 1.
2064                $overrides{$name} = 1;
2065            }
2066        }
2067        # Merge the options into the defaults.
2068        GetOptions($optionTable, \%overrides);
2069        # Translate the remaining parameters.
2070        my @retVal = ();
2071        for my $inputParm (@inputList) {
2072            push @retVal, UnEscape($inputParm);
2073        }
2074        # Return the results.
2075        return ($optionTable, @retVal);
2076    }
2077    
2078    
2079    =head2 File Utility Methods
2080    
2081    =head3 GetFile
2082    
2083        my @fileContents = Tracer::GetFile($fileName);
2084    
2085        or
2086    
2087        my $fileContents = Tracer::GetFile($fileName);
2088    
2089    Return the entire contents of a file. In list context, line-ends are removed and
2090    each line is a list element. In scalar context, line-ends are replaced by C<\n>.
2091    
2092    =over 4
2093    
2094    =item fileName
2095    
2096    Name of the file to read.
2097    
2098    =item RETURN
2099    
2100    In a list context, returns the entire file as a list with the line terminators removed.
2101    In a scalar context, returns the entire file as a string. If an error occurs opening
2102    the file, an empty list will be returned.
2103    
2104    =back
2105    
2106    =cut
2107    
2108    sub GetFile {
2109        # Get the parameters.
2110        my ($fileName) = @_;
2111        # Declare the return variable.
2112        my @retVal = ();
2113        # Open the file for input.
2114        my $handle = Open(undef, "<$fileName");
2115        # Read the whole file into the return variable, stripping off any terminator
2116        # characters.
2117        my $lineCount = 0;
2118        while (my $line = <$handle>) {
2119            $lineCount++;
2120            $line = Strip($line);
2121            push @retVal, $line;
2122        }
2123        # Close it.
2124        close $handle;
2125        my $actualLines = @retVal;
2126        Trace("$actualLines lines read from file $fileName.") if T(File => 2);
2127        # Return the file's contents in the desired format.
2128        if (wantarray) {
2129            return @retVal;
2130        } else {
2131            return join "\n", @retVal;
2132        }
2133    }
2134    
2135    =head3 PutFile
2136    
2137        Tracer::PutFile($fileName, \@lines);
2138    
2139    Write out a file from a list of lines of text.
2140    
2141    =over 4
2142    
2143    =item fileName
2144    
2145    Name of the output file.
2146    
2147    =item lines
2148    
2149    Reference to a list of text lines. The lines will be written to the file in order, with trailing
2150    new-line characters. Alternatively, may be a string, in which case the string will be written without
2151    modification.
2152    
2153    =back
2154    
2155    =cut
2156    
2157    sub PutFile {
2158        # Get the parameters.
2159        my ($fileName, $lines) = @_;
2160        # Open the output file.
2161        my $handle = Open(undef, ">$fileName");
2162        # Count the lines written.
2163        if (ref $lines ne 'ARRAY') {
2164            # Here we have a scalar, so we write it raw.
2165            print $handle $lines;
2166            Trace("Scalar put to file $fileName.") if T(File => 3);
2167        } else {
2168            # Write the lines one at a time.
2169            my $count = 0;
2170            for my $line (@{$lines}) {
2171                print $handle "$line\n";
2172                $count++;
2173            }
2174            Trace("$count lines put to file $fileName.") if T(File => 3);
2175        }
2176        # Close the output file.
2177        close $handle;
2178    }
2179    
2180    =head3 ParseRecord
2181    
2182        my @fields = Tracer::ParseRecord($line);
2183    
2184    Parse a tab-delimited data line. The data line is split into field values. Embedded tab
2185    and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.
2186    These will automatically be converted.
2187    
2188    =over 4
2189    
2190    =item line
2191    
2192    Line of data containing the tab-delimited fields.
2193    
2194    =item RETURN
2195    
2196    Returns a list of the fields found in the data line.
2197    
2198    =back
2199    
2200    =cut
2201    
2202    sub ParseRecord {
2203        # Get the parameter.
2204        my ($line) = @_;
2205        # Remove the trailing new-line, if any.
2206        chomp $line;
2207        # Split the line read into pieces using the tab character.
2208        my @retVal = split /\t/, $line;
2209        # Trim and fix the escapes in each piece.
2210        for my $value (@retVal) {
2211            # Trim leading whitespace.
2212            $value =~ s/^\s+//;
2213            # Trim trailing whitespace.
2214            $value =~ s/\s+$//;
2215            # Delete the carriage returns.
2216            $value =~ s/\r//g;
2217            # Convert the escapes into their real values.
2218            $value =~ s/\\t/"\t"/ge;
2219            $value =~ s/\\n/"\n"/ge;
2220        }
2221        # Return the result.
2222        return @retVal;
2223    }
2224    
2225    =head3 Merge
2226    
2227        my @mergedList = Tracer::Merge(@inputList);
2228    
2229    Sort a list of strings and remove duplicates.
2230    
2231    =over 4
2232    
2233    =item inputList
2234    
2235    List of scalars to sort and merge.
2236    
2237    =item RETURN
2238    
2239    Returns a list containing the same elements sorted in ascending order with duplicates
2240    removed.
2241    
2242    =back
2243    
2244    =cut
2245    
2246    sub Merge {
2247        # Get the input list in sort order.
2248        my @inputList = sort @_;
2249        # Only proceed if the list has at least two elements.
2250        if (@inputList > 1) {
2251            # Now we want to move through the list splicing out duplicates.
2252            my $i = 0;
2253            while ($i < @inputList) {
2254                # Get the current entry.
2255                my $thisEntry = $inputList[$i];
2256                # Find out how many elements duplicate the current entry.
2257                my $j = $i + 1;
2258                my $dup1 = $i + 1;
2259                while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };
2260                # If the number is nonzero, splice out the duplicates found.
2261                if ($j > $dup1) {
2262                    splice @inputList, $dup1, $j - $dup1;
2263                }
2264                # Now the element at position $dup1 is different from the element before it
2265                # at position $i. We push $i forward one position and start again.
2266                $i++;
2267            }
2268        }
2269        # Return the merged list.
2270        return @inputList;
2271    }
2272    
2273    =head3 Open
2274    
2275        my $handle = Open($fileHandle, $fileSpec, $message);
2276    
2277    Open a file.
2278    
2279    The I<$fileSpec> is essentially the second argument of the PERL C<open>
2280    function. The mode is specified using Unix-like shell information. So, for
2281    example,
2282    
2283        Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2284    
2285    would open for output appended to the specified file, and
2286    
2287        Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");
2288    
2289    would open a pipe that sorts the records written and removes duplicates. Note
2290    the use of file handle syntax in the Open call. To use anonymous file handles,
2291    code as follows.
2292    
2293        my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2294    
2295    The I<$message> parameter is used if the open fails. If it is set to C<0>, then
2296    the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a
2297    failed open will throw an exception and the third parameter will be used to construct
2298    an error message. If the parameter is omitted, a standard message is constructed
2299    using the file spec.
2300    
2301        Could not open "/usr/spool/news/twitlog"
2302    
2303    Note that the mode characters are automatically cleaned from the file name.
2304    The actual error message from the file system will be captured and appended to the
2305    message in any case.
2306    
2307        Could not open "/usr/spool/news/twitlog": file not found.
2308    
2309    In some versions of PERL the only error message we get is a number, which
2310    corresponds to the C++ C<errno> value.
2311    
2312        Could not open "/usr/spool/news/twitlog": 6.
2313    
2314    =over 4
2315    
2316    =item fileHandle
2317    
2318    File handle. If this parameter is C<undef>, a file handle will be generated
2319    and returned as the value of this method.
2320    
2321    =item fileSpec
2322    
2323    File name and mode, as per the PERL C<open> function.
2324    
2325    =item message (optional)
2326    
2327    Error message to use if the open fails. If omitted, a standard error message
2328    will be generated. In either case, the error information from the file system
2329    is appended to the message. To specify a conditional open that does not throw
2330    an error if it fails, use C<0>.
2331    
2332    =item RETURN
2333    
2334    Returns the name of the file handle assigned to the file, or C<undef> if the
2335    open failed.
2336    
2337    =back
2338    
2339    =cut
2340    
2341    sub Open {
2342        # Get the parameters.
2343        my ($fileHandle, $fileSpec, $message) = @_;
2344        # Attempt to open the file.
2345        my $rv = open $fileHandle, $fileSpec;
2346        # If the open failed, generate an error message.
2347        if (! $rv) {
2348            # Save the system error message.
2349            my $sysMessage = $!;
2350            # See if we need a default message.
2351            if (!$message) {
2352                # Clean any obvious mode characters and leading spaces from the
2353                # filename.
2354                my ($fileName) = FindNamePart($fileSpec);
2355                $message = "Could not open \"$fileName\"";
2356            }
2357            # Terminate with an error using the supplied message and the
2358            # error message from the file system.
2359            Confess("$message: $!");
2360        }
2361        # Return the file handle.
2362        return $fileHandle;
2363    }
2364    
2365    =head3 FindNamePart
2366    
2367        my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec);
2368    
2369    Extract the portion of a file specification that contains the file name.
2370    
2371    A file specification is the string passed to an C<open> call. It specifies the file
2372    mode and name. In a truly complex situation, it can specify a pipe sequence. This
2373    method assumes that the file name is whatever follows the first angle bracket
2374    sequence.  So, for example, in the following strings the file name is
2375    C</usr/fig/myfile.txt>.
2376    
2377        >>/usr/fig/myfile.txt
2378        </usr/fig/myfile.txt
2379        | sort -u > /usr/fig/myfile.txt
2380    
2381    If the method cannot find a file name using its normal methods, it will return the
2382    whole incoming string.
2383    
2384    =over 4
2385    
2386    =item fileSpec
2387    
2388    File specification string from which the file name is to be extracted.
2389    
2390    =item RETURN
2391    
2392    Returns a three-element list. The first element contains the file name portion of
2393    the specified string, or the whole string if a file name cannot be found via normal
2394    methods. The second element contains the start position of the file name portion and
2395    the third element contains the length.
2396    
2397    =back
2398    
2399    =cut
2400    #: Return Type $;
2401    sub FindNamePart {
2402        # Get the parameters.
2403        my ($fileSpec) = @_;
2404        # Default to the whole input string.
2405        my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);
2406        # Parse out the file name if we can.
2407        if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {
2408            $retVal = $2;
2409            $len = length $retVal;
2410            $pos = (length $fileSpec) - (length $3) - $len;
2411        }
2412        # Return the result.
2413        return ($retVal, $pos, $len);
2414    }
2415    
2416    =head3 OpenDir
2417    
2418        my @files = OpenDir($dirName, $filtered, $flag);
2419    
2420    Open a directory and return all the file names. This function essentially performs
2421    the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is
2422    set to TRUE, all filenames beginning with a period (C<.>), dollar sign (C<$>),
2423    or pound sign (C<#>) and all filenames ending with a tilde C<~>) will be
2424    filtered out of the return list. If the directory does not open and I<$flag> is not
2425    set, an exception is thrown. So, for example,
2426    
2427        my @files = OpenDir("/Volumes/fig/contigs", 1);
2428    
2429    is effectively the same as
2430    
2431        opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");
2432        my @files = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir(TMP);
2433    
2434    Similarly, the following code
2435    
2436        my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs", 0, 1);
2437    
2438    Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and
2439    automatically returns an empty list if the directory fails to open.
2440    
2441    =over 4
2442    
2443    =item dirName
2444    
2445    Name of the directory to open.
2446    
2447    =item filtered
2448    
2449    TRUE if files whose names begin with a period (C<.>) should be automatically removed
2450    from the list, else FALSE.
2451    
2452    =item flag
2453    
2454    TRUE if a failure to open is okay, else FALSE
2455    
2456    =back
2457    
2458    =cut
2459    #: Return Type @;
2460    sub OpenDir {
2461        # Get the parameters.
2462        my ($dirName, $filtered, $flag) = @_;
2463        # Declare the return variable.
2464        my @retVal = ();
2465        # Open the directory.
2466        if (opendir(my $dirHandle, $dirName)) {
2467            # The directory opened successfully. Get the appropriate list according to the
2468            # strictures of the filter parameter.
2469            if ($filtered) {
2470                @retVal = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir $dirHandle;
2471            } else {
2472                @retVal = readdir $dirHandle;
2473            }
2474        } elsif (! $flag) {
2475            # Here the directory would not open and it's considered an error.
2476            Confess("Could not open directory $dirName.");
2477        }
2478        # Return the result.
2479        return @retVal;
2480    }
2481    
2482    
2483    =head3 Insure
2484    
2485        Insure($dirName, $chmod);
2486    
2487    Insure a directory is present.
2488    
2489    =over 4
2490    
2491    =item dirName
2492    
2493    Name of the directory to check. If it does not exist, it will be created.
2494    
2495    =item chmod (optional)
2496    
2497    Security privileges to be given to the directory if it is created.
2498    
2499    =back
2500    
2501    =cut
2502    
2503    sub Insure {
2504        my ($dirName, $chmod) = @_;
2505        if (! -d $dirName) {
2506            Trace("Creating $dirName directory.") if T(2);
2507            eval {
2508                mkpath $dirName;
2509                # If we have permissions specified, set them here.
2510                if (defined($chmod)) {
2511                    chmod $chmod, $dirName;
2512                }
2513            };
2514            if ($@) {
2515                Confess("Error creating $dirName: $@");
2516            }
2517        }
2518  }  }
2519    
2520  =head3 LogErrors  =head3 ChDir
2521    
2522  C<< Tracer::LogErrors($fileName); >>      ChDir($dirName);
2523    
2524  Route the standard error output to a log file.  Change to the specified directory.
2525    
2526  =over 4  =over 4
2527    
2528  =item fileName  =item dirName
2529    
2530  Name of the file to receive the error output.  Name of the directory to which we want to change.
2531    
2532  =back  =back
2533    
2534  =cut  =cut
2535    
2536  sub LogErrors {  sub ChDir {
2537      # Get the file name.      my ($dirName) = @_;
2538      my ($fileName) = @_;      if (! -d $dirName) {
2539      # Open the file as the standard error output.          Confess("Cannot change to directory $dirName: no such directory.");
2540      open STDERR, '>', $fileName;      } else {
2541            Trace("Changing to directory $dirName.") if T(File => 4);
2542            my $okFlag = chdir $dirName;
2543            if (! $okFlag) {
2544                Confess("Error switching to directory $dirName.");
2545            }
2546        }
2547  }  }
2548    
2549  =head3 ReadOptions  =head3 SetPermissions
   
 C<< my %options = Tracer::ReadOptions($fileName); >>  
2550    
2551  Read a set of options from a file. Each option is encoded in a line of text that has the      Tracer::SetPermissions($dirName, $group, $mask, %otherMasks);
 format  
2552    
2553  I<optionName>C<=>I<optionValue>C<; >I<comment>  Set the permissions for a directory and all the files and folders inside it.
2554    In addition, the group ownership will be changed to the specified value.
2555    
2556  The option name must consist entirely of letters, digits, and the punctuation characters  This method is more vulnerable than most to permission and compatability
2557  C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank  problems, so it does internal error recovery.
 character is a semi-colon will be ignored. The return hash will map each option name to  
 the corresponding option value.  
2558    
2559  =over 4  =over 4
2560    
2561  =item fileName  =item dirName
2562    
2563  Name of the file containing the option data.  Name of the directory to process.
2564    
2565  =item RETURN  =item group
2566    
2567  Returns a hash mapping the option names specified in the file to their corresponding option  Name of the group to be assigned.
2568  value.  
2569    =item mask
2570    
2571    Permission mask. Bits that are C<1> in this mask will be ORed into the
2572    permission bits of any file or directory that does not already have them
2573    set to 1.
2574    
2575    =item otherMasks
2576    
2577    Map of search patterns to permission masks. If a directory name matches
2578    one of the patterns, that directory and all its members and subdirectories
2579    will be assigned the new pattern. For example, the following would
2580    assign 0664 to most files, but would use 0777 for directories named C<tmp>.
2581    
2582        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp$' => 01777);
2583    
2584    The list is ordered, so the following would use 0777 for C<tmp1> and
2585    0666 for C<tmp>, C<tmp2>, or C<tmp3>.
2586    
2587        Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp1' => 0777,
2588                                                       '^tmp' => 0666);
2589    
2590    Note that the pattern matches are all case-insensitive, and only directory
2591    names are matched, not file names.
2592    
2593  =back  =back
2594    
2595  =cut  =cut
2596    
2597  sub ReadOptions {  sub SetPermissions {
2598      # Get the parameters.      # Get the parameters.
2599      my ($fileName) = @_;      my ($dirName, $group, $mask, @otherMasks) = @_;
2600      # Open the file.      # Set up for error recovery.
2601      (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");      eval {
2602      # Count the number of records read.          # Switch to the specified directory.
2603      my ($records, $comments) = 0;          ChDir($dirName);
2604      # Create the return hash.          # Get the group ID.
2605      my %retVal = ();          my $gid = getgrnam($group);
2606      # Loop through the file, accumulating key-value pairs.          # Get the mask for tracing.
2607      while (my $line = <CONFIGFILE>) {          my $traceMask = sprintf("%04o", $mask) . "($mask)";
2608          # Denote we've read a line.          Trace("Fixing permissions for directory $dirName using group $group($gid) and mask $traceMask.") if T(File => 2);
2609          $records++;          my $fixCount = 0;
2610          # Determine the line type.          my $lookCount = 0;
2611          if ($line =~ /^\s*[\n\r]/) {          # @dirs will be a stack of directories to be processed.
2612              # A blank line is a comment.          my @dirs = (getcwd());
2613              $comments++;          while (scalar(@dirs) > 0) {
2614          } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {              # Get the current directory.
2615              # Here we have an option assignment.              my $dir = pop @dirs;
2616              retVal{$1} = $2;              # Check for a match to one of the specified directory names. To do
2617          } elsif ($line =~ /^\s*;/) {              # that, we need to pull the individual part of the name off of the
2618              # Here we have a text comment.              # whole path.
2619              $comments++;              my $simpleName = $dir;
2620                if ($dir =~ m!/([^/]+)$!) {
2621                    $simpleName = $1;
2622                }
2623                Trace("Simple directory name for $dir is $simpleName.") if T(File => 4);
2624                # Search for a match.
2625                my $match = 0;
2626                my $i;
2627                for ($i = 0; $i < $#otherMasks && ! $match; $i += 2) {
2628                    my $pattern = $otherMasks[$i];
2629                    if ($simpleName =~ /$pattern/i) {
2630                        $match = 1;
2631                    }
2632                }
2633                # Find out if we have a match. Note we use $i-1 because the loop added 2
2634                # before terminating due to the match.
2635                if ($match && $otherMasks[$i-1] != $mask) {
2636                    # This directory matches one of the incoming patterns, and it's
2637                    # a different mask, so we process it recursively with that mask.
2638                    SetPermissions($dir, $group, $otherMasks[$i-1], @otherMasks);
2639          } else {          } else {
2640              # Here we have an invalid line.                  # Here we can process normally. Get all of the non-hidden members.
2641              Trace("Invalid option statement in record $records.") if T(0);                  my @submems = OpenDir($dir, 1);
2642                    for my $submem (@submems) {
2643                        # Get the full name.
2644                        my $thisMem = "$dir/$submem";
2645                        Trace("Checking member $thisMem.") if T(4);
2646                        $lookCount++;
2647                        if ($lookCount % 1000 == 0) {
2648                            Trace("$lookCount members examined. Current is $thisMem. Mask is $traceMask") if T(File => 3);
2649          }          }
2650                        # Fix the group.
2651                        chown -1, $gid, $thisMem;
2652                        # Insure this member is not a symlink.
2653                        if (! -l $thisMem) {
2654                            # Get its info.
2655                            my $fileInfo = stat $thisMem;
2656                            # Only proceed if we got the info. Otherwise, it's a hard link
2657                            # and we want to skip it anyway.
2658                            if ($fileInfo) {
2659                                my $fileMode = $fileInfo->mode;
2660                                if (($fileMode & $mask) != $mask) {
2661                                    # Fix this member.
2662                                    $fileMode |= $mask;
2663                                    chmod $fileMode, $thisMem;
2664                                    $fixCount++;
2665                                }
2666                                # If it's a subdirectory, stack it.
2667                                if (-d $thisMem) {
2668                                    push @dirs, $thisMem;
2669                                }
2670                            }
2671                        }
2672                    }
2673                }
2674            }
2675            Trace("$lookCount files and directories processed, $fixCount fixed.") if T(File => 2);
2676        };
2677        # Check for an error.
2678        if ($@) {
2679            Confess("SetPermissions error: $@");
2680      }      }
     # Return the hash created.  
     return %retVal;  
2681  }  }
2682    
2683  =head3 GetOptions  =head3 GetLine
   
 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  
2684    
2685  C<< {databaseType => 'Oracle'} >>      my @data = Tracer::GetLine($handle);
2686    
2687  an error will occur because the B<databaseType> option does not exist.  Read a line of data from a tab-delimited file.
2688    
2689  =over 4  =over 4
2690    
2691  =item defaults  =item handle
   
 Table of default option values.  
   
 =item options  
2692    
2693  Table of overrides, if any.  Open file handle from which to read.
2694    
2695  =item RETURN  =item RETURN
2696    
2697  Returns a reference to the default table passed in as the first parameter.  Returns a list of the fields in the record read. The fields are presumed to be
2698    tab-delimited. If we are at the end of the file, then an empty list will be
2699    returned. If an empty line is read, a single list item consisting of a null
2700    string will be returned.
2701    
2702  =back  =back
2703    
2704  =cut  =cut
2705    
2706  sub GetOptions {  sub GetLine {
2707      # Get the parameters.      # Get the parameters.
2708      my ($defaults, $options) = @_;      my ($handle) = @_;
2709      # Check for overrides.      # Declare the return variable.
2710      if ($options) {      my @retVal = ();
2711          # Loop through the overrides.      Trace("File position is " . tell($handle) . ". EOF flag is " . eof($handle) . ".") if T(File => 4);
2712          while (my ($option, $setting) = each %{$options}) {      # Read from the file.
2713              # Insure this override exists.      my $line = <$handle>;
2714              if (!exists $defaults->{$option}) {      # Only proceed if we found something.
2715                  croak "Unrecognized option $option encountered.";      if (defined $line) {
2716            # Remove the new-line. We are a bit over-cautious here because the file may be coming in via an
2717            # upload control and have a nonstandard EOL combination.
2718            $line =~ s/(\r|\n)+$//;
2719            # Here we do some fancy tracing to help in debugging complicated EOL marks.
2720            if (T(File => 4)) {
2721                my $escapedLine = $line;
2722                $escapedLine =~ s/\n/\\n/g;
2723                $escapedLine =~ s/\r/\\r/g;
2724                $escapedLine =~ s/\t/\\t/g;
2725                Trace("Line read: -->$escapedLine<--");
2726            }
2727            # If the line is empty, return a single empty string; otherwise, parse
2728            # it into fields.
2729            if ($line eq "") {
2730                push @retVal, "";
2731              } else {              } else {
2732                  # Apply the override.              push @retVal, split /\t/,$line;
                 $defaults->{$option} = $setting;  
             }  
2733          }          }
2734        } else {
2735            # Trace the reason the read failed.
2736            Trace("End of file: $!") if T(File => 3);
2737      }      }
2738      # Return the merged table.      # Return the result.
2739      return $defaults;      return @retVal;
2740  }  }
2741    
2742  =head3 MergeOptions  =head3 PutLine
2743    
2744  C<< Tracer::MergeOptions(\%table, \%defaults); >>      Tracer::PutLine($handle, \@fields, $eol);
2745    
2746  Merge default values into a hash table. This method looks at the key-value pairs in the  Write a line of data to a tab-delimited file. The specified field values will be
2747  second (default) hash, and if a matching key is not found in the first hash, the default  output in tab-separated form, with a trailing new-line.
 pair is copied in. The process is similar to L</GetOptions>, but there is no error-  
 checking and no return value.  
2748    
2749  =over 4  =over 4
2750    
2751  =item table  =item handle
2752    
2753  Hash table to be updated with the default values.  Output file handle.
2754    
2755  =item defaults  =item fields
2756    
2757  Default values to be merged into the first hash table if they are not already present.  List of field values.
2758    
2759    =item eol (optional)
2760    
2761    End-of-line character (default is "\n").
2762    
2763  =back  =back
2764    
2765  =cut  =cut
2766    
2767  sub MergeOptions {  sub PutLine {
2768      # Get the parameters.      # Get the parameters.
2769      my ($table, $defaults) = @_;      my ($handle, $fields, $eol) = @_;
2770      # Loop through the defaults.      # Write the data.
2771      while (my ($key, $value) = each %{$defaults}) {      print $handle join("\t", @{$fields}) . ($eol || "\n");
         if (!exists $table->{$key}) {  
             $table->{$key} = $value;  
         }  
     }  
2772  }  }
2773    
 =head3 Trace  
2774    
2775  C<< Trace($message); >>  =head3 PrintLine
2776    
2777  Write a trace message to the target location specified in L</TSetup>. If there has not been      Tracer::PrintLine($line);
2778  any prior call to B<TSetup>.  
2779    Print a line of text with a trailing new-line.
2780    
2781  =over 4  =over 4
2782    
2783  =item message  =item line
2784    
2785  Message to write.  Line of text to print.
2786    
2787  =back  =back
2788    
2789  =cut  =cut
2790    
2791  sub Trace {  sub PrintLine {
2792      # Get the parameters.      # Get the parameters.
2793      my ($message) = @_;      my ($line) = @_;
2794      # Get the timestamp.      # Print the line.
2795      my $timeStamp = Now();      print "$line\n";
     # Format the message. Note we strip off any line terminators at the end.  
     my $formatted = "$timeStamp <$LastCategory>: " . Strip($message);  
     # Process according to the destination.  
     if ($Destination eq "TEXT") {  
         # Write the message to the standard output.  
         print "$formatted\n";  
     } elsif ($Destination eq "ERROR") {  
         # Write the message to the error output.  
         print STDERR "$formatted\n";  
     } elsif ($Destination eq "QUEUE") {  
         # Push the message into the queue.  
         push @Queue, "$formatted";  
     } elsif ($Destination eq "HTML") {  
         # Convert the message to HTML and write it to the standard output.  
         my $escapedMessage = CGI::escapeHTML($message);  
         print "<p>$formatted</p>\n";  
     } elsif ($Destination eq "WARN") {  
        # Emit the message as a warning.  
        warn $message;  
     } elsif ($Destination =~ m/^>>/) {  
         # Write the trace message to an output file.  
         (open TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";  
         print TRACING "$formatted\n";  
         close TRACING;  
         # If the Tee flag is on, echo it to the standard output.  
         if ($TeeFlag) {  
             print "$formatted\n";  
         }  
     }  
2796  }  }
2797    
 =head3 T  
2798    
2799  C<< my $switch = T($category, $traceLevel); >>  =head2 Other Useful Methods
2800    
2801      or  =head3 ParseParm
2802    
2803  C<< my $switch = T($traceLevel); >>      my $listValue = Tracer::ParseParm($string);
2804    
2805  Return TRUE if the trace level is at or above a specified value and the specified category  Convert a parameter into a list reference. If the parameter is undefined,
2806  is active, else FALSE. If no category is specified, the caller's package name is used.  an undefined value will be returned. Otherwise, it will be parsed as a
2807    comma-separated list of values.
2808    
2809  =over 4  =over 4
2810    
2811  =item category  =item string
   
 Category to which the message belongs. If not specified, the caller's package name is  
 used.  
   
 =item traceLevel  
2812    
2813  Relevant tracing level.  Incoming string.
2814    
2815  =item RETURN  =item RETURN
2816    
2817  TRUE if a message at the specified trace level would appear in the trace, else FALSE.  Returns a reference to a list of values, or C<undef> if the incoming value
2818    was undefined.
2819    
2820  =back  =back
2821    
2822  =cut  =cut
2823    
2824  sub T {  sub ParseParm {
     # Declare the return variable.  
     my $retVal = 0;  
     # Only proceed if tracing is turned on.  
     if ($Destination ne "NONE") {  
2825          # Get the parameters.          # Get the parameters.
2826          my ($category, $traceLevel) = @_;      my ($string) = @_;
2827          if (!defined $traceLevel) {      # Declare the return variable.
2828              # Here we have no category, so we need to get the calling package.      my $retVal;
2829              # The calling package is normally the first parameter. If it is      # Check for data.
2830              # omitted, the first parameter will be the tracelevel. So, the      if (defined $string) {
2831              # first thing we do is shift the so-called category into the          # We have some, so split it into a list.
2832              # $traceLevel variable where it belongs.          $retVal = [ split /\s*,\s*/, $string];
             $traceLevel = $category;  
             my ($package, $fileName, $line) = caller;  
             # If there is no calling package, we default to "main".  
             if (!$package) {  
                 $category = "main";  
             } else {  
                 $category = $package;  
             }  
         }  
         # Save the category name.  
         $LastCategory = $category;  
         # Convert it to lower case before we hash it.  
         $category = lc $category;  
         # Use the category and tracelevel to compute the result.  
         $retVal = ($traceLevel <= $TraceLevel && ($AllTrace || exists $Categories{$category}));  
2833      }      }
2834      # Return the computed result.      # Return the result.
2835      return $retVal;      return $retVal;
2836  }  }
2837    
2838  =head3 ParseCommand  =head3 Now
   
 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); >>  
2839    
2840  In this case, the list @words will be treated as a command line. There are two options available,      my $string = Tracer::Now();
 B<errors> and B<logFile>. If @words has the following format  
2841    
2842  C<< -logFile=error.log apple orange rutabaga >>  Return a displayable time stamp containing the local time. Whatever format this
2843    method produces must be parseable by L</ParseDate>.
2844    
2845  then at the end of the invocation, C<$options> will be  =cut
2846    
2847  C<< { errors => 0, logFile => 'error.log' } >>  sub Now {
2848        return DisplayTime(time);
2849    }
2850    
2851  and C<@arguments> will contain  =head3 DisplayTime
2852    
2853  C<< apple orange rutabaga >>      my $string = Tracer::DisplayTime($time);
2854    
2855  The parser allows for some escape sequences. See L</UnEscape> for a description. There is no  Convert a time value to a displayable time stamp. Whatever format this
2856  support for quote characters.  method produces must be parseable by L</ParseDate>.
2857    
2858  =over 4  =over 4
2859    
2860  =item optionTable  =item time
   
 Table of default options.  
   
 =item inputList  
2861    
2862  List of words on the command line.  Time to display, in seconds since the epoch, or C<undef> if the time is unknown.
2863    
2864  =item RETURN  =item RETURN
2865    
2866  Returns a reference to the option table and a list of the positional arguments.  Returns a displayable time, or C<(n/a)> if the incoming time is undefined.
2867    
2868  =back  =back
2869    
2870  =cut  =cut
2871    
2872  sub ParseCommand {  sub DisplayTime {
2873      # Get the parameters.      my ($time) = @_;
2874      my ($optionTable, @inputList) = @_;      my $retVal = "(n/a)";
2875      # Process any options in the input list.      if (defined $time) {
2876      my %overrides = ();          my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($time);
2877      while ((@inputList > 0) && ($inputList[0] =~ /^-/)) {          $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .
2878          # Get the current option.                    _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);
         my $arg = shift @inputList;  
         # Pull out the option name.  
         $arg =~ /^-([^=]*)/g;  
         my $name = $1;  
         # Check for an option value.  
         if ($arg =~ /\G=(.*)$/g) {  
             # Here we have a value for the option.  
             $overrides{$name} = UnEscape($1);  
         } else {  
             # Here there is no value, so we use 1.  
             $overrides{$name} = 1;  
         }  
     }  
     # Merge the options into the defaults.  
     GetOptions($optionTable, \%overrides);  
     # Translate the remaining parameters.  
     my @retVal = ();  
     for my $inputParm (@inputList) {  
         push @retVal, UnEscape($inputParm);  
2879      }      }
2880      # Return the results.      return $retVal;
2881      return ($optionTable, @retVal);  }
2882    
2883    # Pad a number to 2 digits.
2884    sub _p2 {
2885        my ($value) = @_;
2886        $value = "0$value" if ($value < 10);
2887        return $value;
2888  }  }
2889    
2890  =head3 Escape  =head3 Escape
2891    
2892  C<< my $codedString = Tracer::Escape($realString); >>      my $codedString = Tracer::Escape($realString);
2893    
2894  Escape a string for use in a command length. Tabs will be replaced by C<\t>, new-lines  Escape a string for use in a command. Tabs will be replaced by C<\t>, new-lines
2895  replaced by C<\n>, and backslashes will be doubled. The effect is to exactly reverse the  replaced by C<\n>, carriage returns will be deleted, and backslashes will be doubled. The
2896  effect of L</UnEscape>.  result is to reverse the effect of L</UnEscape>.
2897    
2898  =over 4  =over 4
2899    
# Line 850  Line 2917 
2917      # Loop through the parameter string, looking for sequences to escape.      # Loop through the parameter string, looking for sequences to escape.
2918      while (length $realString > 0) {      while (length $realString > 0) {
2919          # Look for the first sequence to escape.          # Look for the first sequence to escape.
2920          if ($realString =~ /^(.*?)([\n\t\\])/) {          if ($realString =~ /^(.*?)([\n\t\r\\])/) {
2921              # Here we found it. The text preceding the sequence is in $1. The sequence              # Here we found it. The text preceding the sequence is in $1. The sequence
2922              # itself is in $2. First, move the clear text to the return variable.              # itself is in $2. First, move the clear text to the return variable.
2923              $retVal .= $1;              $retVal .= $1;
2924              # Strip the processed section off the real string.              # Strip the processed section off the real string.
2925              $realString = substr $realString, (length $2) + (length $1);              $realString = substr $realString, (length $2) + (length $1);
2926              # Encode the escape sequence.              # Get the matched character.
2927              my $char = $2;              my $char = $2;
2928                # If we have a CR, we are done.
2929                if ($char ne "\r") {
2930                    # It's not a CR, so encode the escape sequence.
2931              $char =~ tr/\t\n/tn/;              $char =~ tr/\t\n/tn/;
2932              $retVal .= "\\" . $char;              $retVal .= "\\" . $char;
2933                }
2934          } else {          } else {
2935              # Here there are no more escape sequences. The rest of the string is              # Here there are no more escape sequences. The rest of the string is
2936              # transferred unmodified.              # transferred unmodified.
# Line 873  Line 2944 
2944    
2945  =head3 UnEscape  =head3 UnEscape
2946    
2947  C<< my $realString = Tracer::UnEscape($codedString); >>      my $realString = Tracer::UnEscape($codedString);
2948    
2949  Replace escape sequences with their actual equivalents. C<\t> will be replaced by  Replace escape sequences with their actual equivalents. C<\t> will be replaced by
2950  a tab, C<\n> by a new-line character, and C<\\> by a back-slash.  a tab, C<\n> by a new-line character, and C<\\> by a backslash. C<\r> codes will
2951    be deleted.
2952    
2953  =over 4  =over 4
2954    
# Line 905  Line 2977 
2977          # "\<tab>" no matter what we do.)          # "\<tab>" no matter what we do.)
2978          while (length $codedString > 0) {          while (length $codedString > 0) {
2979              # Look for the first escape sequence.              # Look for the first escape sequence.
2980              if ($codedString =~ /^(.*?)\\(\\|n|t)/) {              if ($codedString =~ /^(.*?)\\(\\|n|t|r)/) {
2981                  # Here we found it. The text preceding the sequence is in $1. The sequence                  # Here we found it. The text preceding the sequence is in $1. The sequence
2982                  # itself is in $2. First, move the clear text to the return variable.                  # itself is in $2. First, move the clear text to the return variable.
2983                  $retVal .= $1;                  $retVal .= $1;
2984                  $codedString = substr $codedString, (2 + length $1);                  $codedString = substr $codedString, (2 + length $1);
2985                  # Decode the escape sequence.                  # Get the escape value.
2986                  my $char = $2;                  my $char = $2;
2987                    # If we have a "\r", we are done.
2988                    if ($char ne 'r') {
2989                        # Here it's not an 'r', so we convert it.
2990                  $char =~ tr/\\tn/\\\t\n/;                  $char =~ tr/\\tn/\\\t\n/;
2991                  $retVal .= $char;                  $retVal .= $char;
2992                    }
2993              } else {              } else {
2994                  # Here there are no more escape sequences. The rest of the string is                  # Here there are no more escape sequences. The rest of the string is
2995                  # transferred unmodified.                  # transferred unmodified.
# Line 926  Line 3002 
3002      return $retVal;      return $retVal;
3003  }  }
3004    
3005  =head3 ParseRecord  =head3 Percent
3006    
3007  C<< my @fields = Tracer::ParseRecord($line); >>      my $percent = Tracer::Percent($number, $base);
3008    
3009  Parse a tab-delimited data line. The data line is split into field values. Embedded tab  Returns the percent of the base represented by the given number. If the base
3010  and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.  is zero, returns zero.
 These will automatically be converted.  
3011    
3012  =over 4  =over 4
3013    
3014  =item line  =item number
3015    
3016  Line of data containing the tab-delimited fields.  Percent numerator.
3017    
3018    =item base
3019    
3020    Percent base.
3021    
3022  =item RETURN  =item RETURN
3023    
3024  Returns a list of the fields found in the data line.  Returns the percentage of the base represented by the numerator.
3025    
3026  =back  =back
3027    
3028  =cut  =cut
3029    
3030  sub ParseRecord {  sub Percent {
3031      # Get the parameter.      # Get the parameters.
3032      my ($line) = @_;      my ($number, $base) = @_;
3033      # Remove the trailing new-line, if any.      # Declare the return variable.
3034      chomp $line;      my $retVal = 0;
3035      # Split the line read into pieces using the tab character.      # Compute the percent.
3036      my @retVal = split /\t/, $line;      if ($base != 0) {
3037      # Trim and fix the escapes in each piece.          $retVal = $number * 100 / $base;
     for my $value (@retVal) {  
         # Trim leading whitespace.  
         $value =~ s/^\s+//;  
         # Trim trailing whitespace.  
         $value =~ s/\s+$//;  
         # Delete the carriage returns.  
         $value =~ s/\r//g;  
         # Convert the escapes into their real values.  
         $value =~ s/\\t/"\t"/ge;  
         $value =~ s/\\n/"\n"/ge;  
3038      }      }
3039      # Return the result.      # Return the result.
3040      return @retVal;      return $retVal;
3041  }  }
3042    
3043  =head3 Merge  =head3 Constrain
3044    
3045  C<< my @mergedList = Tracer::Merge(@inputList); >>      my $constrained = Constrain($value, $min, $max);
3046    
3047  Sort a list of strings and remove duplicates.  Modify a numeric value to bring it to a point in between a maximum and a minimum.
3048    
3049  =over 4  =over 4
3050    
3051  =item inputList  =item value
3052    
3053  List of scalars to sort and merge.  Value to constrain.
3054    
3055    =item min (optional)
3056    
3057    Minimum permissible value. If this parameter is undefined, no minimum constraint will be applied.
3058    
3059    =item max (optional)
3060    
3061    Maximum permissible value. If this parameter is undefined, no maximum constraint will be applied.
3062    
3063  =item RETURN  =item RETURN
3064    
3065  Returns a list containing the same elements sorted in ascending order with duplicates  Returns the incoming value, constrained according to the other parameters.
 removed.  
3066    
3067  =back  =back
3068    
3069  =cut  =cut
3070    
3071  sub Merge {  sub Constrain {
3072      # Get the input list in sort order.      # Get the parameters.
3073      my @inputList = sort @_;      my ($value, $min, $max) = @_;
3074      # Only proceed if the list has at least two elements.      # Declare the return variable.
3075      if (@inputList > 1) {      my $retVal = $value;
3076          # Now we want to move through the list splicing out duplicates.      # Apply the minimum constraint.
3077          my $i = 0;      if (defined $min && $retVal < $min) {
3078          while ($i < @inputList) {          $retVal = $min;
3079              # Get the current entry.      }
3080              my $thisEntry = $inputList[$i];      # Apply the maximum constraint.
3081              # Find out how many elements duplicate the current entry.      if (defined $max && $retVal > $max) {
3082              my $j = $i + 1;          $retVal = $max;
             my $dup1 = $i + 1;  
             while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };  
             # If the number is nonzero, splice out the duplicates found.  
             if ($j > $dup1) {  
                 splice @inputList, $dup1, $j - $dup1;  
3083              }              }
3084              # Now the element at position $dup1 is different from the element before it      # Return the result.
3085              # at position $i. We push $i forward one position and start again.      return $retVal;
3086              $i++;  }
3087    
3088    =head3 Min
3089    
3090        my $min = Min($value1, $value2, ... $valueN);
3091    
3092    Return the minimum argument. The arguments are treated as numbers.
3093    
3094    =over 4
3095    
3096    =item $value1, $value2, ... $valueN
3097    
3098    List of numbers to compare.
3099    
3100    =item RETURN
3101    
3102    Returns the lowest number in the list.
3103    
3104    =back
3105    
3106    =cut
3107    
3108    sub Min {
3109        # Get the parameters. Note that we prime the return value with the first parameter.
3110        my ($retVal, @values) = @_;
3111        # Loop through the remaining parameters, looking for the lowest.
3112        for my $value (@values) {
3113            if ($value < $retVal) {
3114                $retVal = $value;
3115          }          }
3116      }      }
3117      # Return the merged list.      # Return the minimum found.
3118      return @inputList;      return $retVal;
3119  }  }
3120    
3121  =head3 GetFile  =head3 Max
3122    
3123  C<< my @fileContents = Tracer::GetFile($fileName); >>      my $max = Max($value1, $value2, ... $valueN);
3124    
3125  Return the entire contents of a file.  Return the maximum argument. The arguments are treated as numbers.
3126    
3127  =over 4  =over 4
3128    
3129  =item fileName  =item $value1, $value2, ... $valueN
3130    
3131  Name of the file to read.  List of numbers to compare.
3132    
3133  =item RETURN  =item RETURN
3134    
3135  In a list context, returns the entire file as a list with the line terminators removed.  Returns the highest number in the list.
 In a scalar context, returns the entire file as a string.  
3136    
3137  =back  =back
3138    
3139  =cut  =cut
3140    
3141  sub GetFile {  sub Max {
3142        # Get the parameters. Note that we prime the return value with the first parameter.
3143        my ($retVal, @values) = @_;
3144        # Loop through the remaining parameters, looking for the highest.
3145        for my $value (@values) {
3146            if ($value > $retVal) {
3147                $retVal = $value;
3148            }
3149        }
3150        # Return the maximum found.
3151        return $retVal;
3152    }
3153    
3154    =head3 Strip
3155    
3156        my $string = Tracer::Strip($line);
3157    
3158    Strip all line terminators off a string. This is necessary when dealing with files
3159    that may have been transferred back and forth several times among different
3160    operating environments.
3161    
3162    =over 4
3163    
3164    =item line
3165    
3166    Line of text to be stripped.
3167    
3168    =item RETURN
3169    
3170    The same line of text with all the line-ending characters chopped from the end.
3171    
3172    =back
3173    
3174    =cut
3175    
3176    sub Strip {
3177        # Get a copy of the parameter string.
3178        my ($string) = @_;
3179        my $retVal = (defined $string ? $string : "");
3180        # Strip the line terminator characters.
3181        $retVal =~ s/(\r|\n)+$//g;
3182        # Return the result.
3183        return $retVal;
3184    }
3185    
3186    =head3 Pad
3187    
3188        my $paddedString = Tracer::Pad($string, $len, $left, $padChar);
3189    
3190    Pad a string to a specified length. The pad character will be a
3191    space, and the padding will be on the right side unless specified
3192    in the third parameter.
3193    
3194    =over 4
3195    
3196    =item string
3197    
3198    String to be padded.
3199    
3200    =item len
3201    
3202    Desired length of the padded string.
3203    
3204    =item left (optional)
3205    
3206    TRUE if the string is to be left-padded; otherwise it will be padded on the right.
3207    
3208    =item padChar (optional)
3209    
3210    Character to use for padding. The default is a space.
3211    
3212    =item RETURN
3213    
3214    Returns a copy of the original string with the pad character added to the
3215    specified end so that it achieves the desired length.
3216    
3217    =back
3218    
3219    =cut
3220    
3221    sub Pad {
3222      # Get the parameters.      # Get the parameters.
3223      my ($fileName) = @_;      my ($string, $len, $left, $padChar) = @_;
3224      # Declare the return variable.      # Compute the padding character.
3225      my @retVal = ();      if (! defined $padChar) {
3226      # Open the file for input.          $padChar = " ";
3227      my $ok = open INPUTFILE, "<$fileName";      }
3228      if (!$ok) {      # Compute the number of spaces needed.
3229          # If we had an error, trace it. We will automatically return a null value.      my $needed = $len - length $string;
3230          Trace("Could not open \"$fileName\" for input: $!") if T(0);      # Copy the string into the return variable.
3231        my $retVal = $string;
3232        # Only proceed if padding is needed.
3233        if ($needed > 0) {
3234            # Create the pad string.
3235            my $pad = $padChar x $needed;
3236            # Affix it to the return value.
3237            if ($left) {
3238                $retVal = $pad . $retVal;
3239      } else {      } else {
3240          # Read the whole file into the return variable, stripping off any terminator              $retVal .= $pad;
         # characters.  
         my $lineCount = 0;  
         while (my $line = <INPUTFILE>) {  
             $lineCount++;  
             $line = Strip($line);  
             push @retVal, $line;  
3241          }          }
         # Close it.  
         close INPUTFILE;  
         my $actualLines = @retVal;  
3242      }      }
3243      # Return the file's contents in the desired format.      # Return the result.
3244      if (wantarray) {      return $retVal;
         return @retVal;  
     } else {  
         return join "\n", @retVal;  
3245      }      }
3246    
3247    =head3 EOF
3248    
3249    This is a constant that is lexically greater than any useful string.
3250    
3251    =cut
3252    
3253    sub EOF {
3254        return "\xFF\xFF\xFF\xFF\xFF";
3255  }  }
3256    
3257  =head3 QTrace  =head3 TICK
3258    
3259  C<< my $data = QTrace($format); >>      my @results = TICK($commandString);
3260    
3261  Return the queued trace data in the specified format.  Perform a back-tick operation on a command. If this is a Windows environment, any leading
3262    dot-slash (C<./> will be removed. So, for example, if you were doing
3263    
3264        `./protein.cgi`
3265    
3266    from inside a CGI script, it would work fine in Unix, but would issue an error message
3267    in Windows complaining that C<'.'> is not a valid command. If instead you code
3268    
3269        TICK("./protein.cgi")
3270    
3271    it will work correctly in both environments.
3272    
3273  =over 4  =over 4
3274    
3275  =item format  =item commandString
3276    
3277    The command string to pass to the system.
3278    
3279    =item RETURN
3280    
3281  C<html> to format the data as an HTML list, C<text> to format it as straight text.  Returns the standard output from the specified command, as a list.
3282    
3283  =back  =back
3284    
3285  =cut  =cut
3286    #: Return Type @;
3287  sub QTrace {  sub TICK {
3288      # Get the parameter.      # Get the parameters.
3289      my ($format) = @_;      my ($commandString) = @_;
3290      # Create the return variable.      # Chop off the dot-slash if this is Windows.
3291      my $retVal = "";      if ($FIG_Config::win_mode) {
3292      # Only proceed if there is an actual queue.          $commandString =~ s!^\./!!;
     if (@Queue) {  
         # Process according to the format.  
         if ($format =~ m/^HTML$/i) {  
             # Convert the queue into an HTML list.  
             $retVal = "<ul>\n";  
             for my $line (@Queue) {  
                 my $escapedLine = CGI::escapeHTML($line);  
                 $retVal .= "<li>$escapedLine</li>\n";  
             }  
             $retVal .= "</ul>\n";  
         } elsif ($format =~ m/^TEXT$/i) {  
             # Convert the queue into a list of text lines.  
             $retVal = join("\n", @Queue) . "\n";  
         }  
         # Clear the queue.  
         @Queue = ();  
3293      }      }
3294      # Return the formatted list.      # Activate the command and return the result.
3295      return $retVal;      return `$commandString`;
3296  }  }
3297    
 =head3 Confess  
   
 C<< Confess($message); >>  
3298    
3299  Trace the call stack and abort the program with the specified message. When used with  =head3 CommaFormat
 the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.  
 So, for example  
3300    
3301  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>      my $formatted = Tracer::CommaFormat($number);
3302    
3303  Will abort the program with a stack trace if the value of C<$recNum> is negative.  Insert commas into a number.
3304    
3305  =over 4  =over 4
3306    
3307  =item message  =item number
3308    
3309  Message to include in the trace.  A sequence of digits.
3310    
3311    =item RETURN
3312    
3313    Returns the same digits with commas strategically inserted.
3314    
3315  =back  =back
3316    
3317  =cut  =cut
3318    
3319  sub Confess {  sub CommaFormat {
3320      # Get the parameters.      # Get the parameters.
3321      my ($message) = @_;      my ($number) = @_;
3322      # Trace the call stack.      # Pad the length up to a multiple of three.
3323      Cluck($message);      my $padded = "$number";
3324      # Abort the program.      $padded = " " . $padded while length($padded) % 3 != 0;
3325      croak(">>> $message");      # This is a fancy PERL trick. The parentheses in the SPLIT pattern
3326        # cause the delimiters to be included in the output stream. The
3327        # GREP removes the empty strings in between the delimiters.
3328        my $retVal = join(",", grep { $_ ne '' } split(/(...)/, $padded));
3329        # Clean out the spaces.
3330        $retVal =~ s/ //g;
3331        # Return the result.
3332        return $retVal;
3333  }  }
3334    
 =head3 Assert  
   
 C<< Assert($condition1, $condition2, ... $conditionN); >>  
3335    
3336  Return TRUE if all the conditions are true. This method can be used in conjunction with  =head3 CompareLists
 the OR operator and the L</Confess> method, B<Assert> can function as a debugging assert.  
 So, for example  
3337    
3338  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>      my ($inserted, $deleted) = Tracer::CompareLists(\@newList, \@oldList, $keyIndex);
3339    
3340  Will abort the program with a stack trace if the value of C<$recNum> is negative.  Compare two lists of tuples, and return a hash analyzing the differences. The lists
3341    are presumed to be sorted alphabetically by the value in the $keyIndex column.
3342    The return value contains a list of items that are only in the new list
3343    (inserted) and only in the old list (deleted).
3344    
3345  =cut  =over 4
 sub Assert {  
     my $retVal = 1;  
     LOOP: for my $condition (@_) {  
         if (! $condition) {  
             $retVal = 0;  
             last LOOP;  
         }  
     }  
     return $retVal;  
 }  
3346    
3347  =head3 Cluck  =item newList
3348    
3349  C<< Cluck($message); >>  Reference to a list of new tuples.
3350    
3351  Trace the call stack. Note that for best results, you should qualify the call with a  =item oldList
 trace condition. For example,  
3352    
3353  C<< Cluck("Starting record parse.") if T(3); >>  Reference to a list of old tuples.
3354    
3355  will only trace the stack if the trace level for the package is 3 or more.  =item keyIndex (optional)
3356    
3357  =over 4  Index into each tuple of its key field. The default is 0.
3358    
3359  =item message  =item RETURN
3360    
3361  Message to include in the trace.  Returns a 2-tuple consisting of a reference to the list of items that are only in the new
3362    list (inserted) followed by a reference to the list of items that are only in the old
3363    list (deleted).
3364    
3365  =back  =back
3366    
3367  =cut  =cut
3368    
3369  sub Cluck {  sub CompareLists {
3370      # Get the parameters.      # Get the parameters.
3371      my ($message) = @_;      my ($newList, $oldList, $keyIndex) = @_;
3372      # Trace what's happening.      if (! defined $keyIndex) {
3373      Trace("Stack trace for event: $message");          $keyIndex = 0;
3374      my $confession = longmess($message);      }
3375      # Convert the confession to a series of trace messages. Note we skip any      # Declare the return variables.
3376      # messages relating to calls into Tracer.      my ($inserted, $deleted) = ([], []);
3377      for my $line (split /\s*\n/, $confession) {      # Loop through the two lists simultaneously.
3378          Trace($line) if ($line !~ /Tracer\.pm/);      my ($newI, $oldI) = (0, 0);
3379        my ($newN, $oldN) = (scalar @{$newList}, scalar @{$oldList});
3380        while ($newI < $newN || $oldI < $oldN) {
3381            # Get the current object in each list. Note that if one
3382            # of the lists is past the end, we'll get undef.
3383            my $newItem = $newList->[$newI];
3384            my $oldItem = $oldList->[$oldI];
3385            if (! defined($newItem) || defined($oldItem) && $newItem->[$keyIndex] gt $oldItem->[$keyIndex]) {
3386                # The old item is not in the new list, so mark it deleted.
3387                push @{$deleted}, $oldItem;
3388                $oldI++;
3389            } elsif (! defined($oldItem) || $oldItem->[$keyIndex] gt $newItem->[$keyIndex]) {
3390                # The new item is not in the old list, so mark it inserted.
3391                push @{$inserted}, $newItem;
3392                $newI++;
3393            } else {
3394                # The item is in both lists, so push forward.
3395                $oldI++;
3396                $newI++;
3397            }
3398      }      }
3399        # Return the result.
3400        return ($inserted, $deleted);
3401  }  }
3402    
3403  =head3 Min  =head3 Cmp
3404    
3405  C<< my $min = Min($value1, $value2, ... $valueN); >>      my $cmp = Tracer::Cmp($a, $b);
3406    
3407  Return the minimum argument. The arguments are treated as numbers.  This method performs a universal sort comparison. Each value coming in is
3408    separated into a leading text part and a trailing number part. The text
3409    part is string compared, and if both parts are equal, then the number
3410    parts are compared numerically. A stream of just numbers or a stream of
3411    just strings will sort correctly, and a mixed stream will sort with the
3412    numbers first. Strings with a label and a number will sort in the
3413    expected manner instead of lexically.
3414    
3415  =over 4  =over 4
3416    
3417  =item $value1, $value2, ... $valueN  =item a
3418    
3419  List of numbers to compare.  First item to compare.
3420    
3421    =item b
3422    
3423    Second item to compare.
3424    
3425  =item RETURN  =item RETURN
3426    
3427  Returns the lowest number in the list.  Returns a negative number if the first item should sort first (is less), a positive
3428    number if the first item should sort second (is greater), and a zero if the items are
3429    equal.
3430    
3431  =back  =back
3432    
3433  =cut  =cut
3434    
3435  sub Min {  sub Cmp {
3436      # Get the parameters. Note that we prime the return value with the first parameter.      # Get the parameters.
3437      my ($retVal, @values) = @_;      my ($a, $b) = @_;
3438      # Loop through the remaining parameters, looking for the lowest.      # Declare the return value.
3439      for my $value (@values) {      my $retVal;
3440          if ($value < $retVal) {      # Check for nulls.
3441              $retVal = $value;      if (! defined($a)) {
3442            $retVal = (! defined($b) ? 0 : -1);
3443        } elsif (! defined($b)) {
3444            $retVal = 1;
3445        } else {
3446            # Here we have two real values. Parse the two strings.
3447            $a =~ /^(\D*)(\d*)$/;
3448            my $aParsed = [$1, $2];
3449            $b =~ /^(\D*)(\d*)$/;
3450            my $bParsed = [$1, $2];
3451            # Compare the string parts.
3452            $retVal = $aParsed->[0] cmp $bParsed->[0];
3453            if (! $retVal) {
3454                $retVal = $aParsed->[1] <=> $bParsed->[1];
3455          }          }
3456      }      }
3457      # Return the minimum found.      # Return the result.
3458      return $retVal;      return $retVal;
3459  }  }
3460    
3461  =head3 Max  =head3 ListEQ
3462    
3463  C<< my $max = Max($value1, $value2, ... $valueN); >>      my $flag = Tracer::ListEQ(\@a, \@b);
3464    
3465  Return the maximum argument. The arguments are treated as numbers.  Return TRUE if the specified lists contain the same strings in the same
3466    order, else FALSE.
3467    
3468  =over 4  =over 4
3469    
3470  =item $value1, $value2, ... $valueN  =item a
3471    
3472  List of numbers to compare.  Reference to the first list.
3473    
3474    =item b
3475    
3476    Reference to the second list.
3477    
3478  =item RETURN  =item RETURN
3479    
3480  Returns the highest number in the list.  Returns TRUE if the two parameters are identical string lists, else FALSE.
3481    
3482  =back  =back
3483    
3484  =cut  =cut
3485    
3486  sub Max {  sub ListEQ {
3487      # Get the parameters. Note that we prime the return value with the first parameter.      # Get the parameters.
3488      my ($retVal, @values) = @_;      my ($a, $b) = @_;
3489      # Loop through the remaining parameters, looking for the highest.      # Declare the return variable. Start by checking the lengths.
3490      for my $value (@values) {      my $n = scalar(@$a);
3491          if ($value > $retVal) {      my $retVal = ($n == scalar(@$b));
3492              $retVal = $value;      # Now compare the list elements.
3493         &nb