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

Diff of /FigKernelPackages/Tracer.pm

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

revision 1.23, Tue Sep 13 05:36:12 2005 UTC revision 1.99, Wed May 7 23:00:16 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    
42    
43  =head1 Tracing and Debugging Helpers  =head1 Tracing and Debugging Helpers
44    
45  =head2 Introduction  =head2 Tracing
46    
47  This package provides simple tracing for debugging and reporting purposes. To use it simply call the  This package provides simple tracing for debugging and reporting purposes. To use it simply call the
48  L</TSetup> method to set the options and call L</Trace> to write out trace messages. Each trace  L</TSetup> or L</ETracing> method to set the options and call L</Trace> to write out trace messages.
49  message has a I<trace level> and I<category> associated with it. In addition, the tracing package itself  L</TSetup> and L</ETracing> both establish a I<trace level> and a list of I<categories>. Similarly,
50  has a list of categories and a single trace level set by the B<TSetup> method. Only messages whose trace  each trace message has a I<trace level> and I<category> associated with it. Only messages whose trace
51  level is less than or equal to this package's trace level and whose category is activated will  level is less than or equal to the setup trace level and whose category is activated will
52  be written. Thus, a higher trace level on a message indicates that the message  be written. Thus, a higher trace level on a message indicates that the message
53  is less likely to be seen. A higher trace level passed to B<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
54  appear. To generate a trace message, use the following syntax.  appear.
55    
56    =head3 Putting Trace Messages in Your Code
57    
58    To generate a trace message, use the following syntax.
59    
60  C<< Trace($message) if T(errors => 4); >>      Trace($message) if T(errors => 4);
61    
62  This statement will produce a trace message if the trace level is 4 or more and the C<errors>  This statement will produce a trace message if the trace level is 4 or more and the C<errors>
63  category is active. Note that the special category C<main> is always active, so  category is active. There is a special category C<main> that is always active, so
64    
65  C<< Trace($message) if T(main => 4); >>      Trace($message) if T(main => 4);
66    
67  will trace if the trace level is 4 or more.  will trace if the trace level is 4 or more.
68    
# Line 37  Line 70 
70  following call is made in the B<Sprout> package, it will appear if the C<Sprout> category is  following call is made in the B<Sprout> package, it will appear if the C<Sprout> category is
71  active and the trace level is 2 or more.  active and the trace level is 2 or more.
72    
73  C<< Trace($message) if T(2); >>      Trace($message) if T(2);
74    
75  To set up tracing, you call the 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>.
76  of category names, and a set of options. The trace level and list of category names are  
77    =head3 Custom Tracing
78    
79    Many programs have customized tracing configured using the L</TSetup> method. This is no longer
80    the preferred method, but a knowledge of how custom tracing works can make the more modern
81    L</Emergency Tracing> easier to understand.
82    
83    To set up custom tracing, you call the L</TSetup> method. The method takes as input a trace level,
84    a list of category names, and a destination. The trace level and list of category names are
85  specified as a space-delimited string. Thus  specified as a space-delimited string. Thus
86    
87  C<< TSetup('3 errors Sprout ERDB', 'HTML'); >>      TSetup('3 errors Sprout ERDB', 'TEXT');
88    
89  sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and  sets the trace level to 3, activates the C<errors>, C<Sprout>, and C<ERDB> categories, and
90  specifies that messages should be output as HTML paragraphs.  specifies that messages should be sent to the standard output.
91    
92  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
93  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
94  useful in a CGI environment.  useful in a CGI environment.
95    
96  C<< TSetup('3 *', 'WARN'); >>      TSetup('3 *', 'WARN');
97    
98  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
99  be queued. The messages can then be retrieved by calling the L</QTrace> method. This approach  be queued. The messages can then be retrieved by calling the L</QTrace> method. This approach
100  is useful if you are building a web page. Instead of having the trace messages interspersed with  is useful if you are building a web page. Instead of having the trace messages interspersed with
101  the page output, they can be gathered together and displayed at the end of the page. This makes  the page output, they can be gathered together and displayed at the end of the page. This makes
102  it easier to debug page formatting problems.  it easier to debug page formatting problems.
103    
104  Finally, you can specify that all trace messages be emitted as warnings.  Finally, you can specify that all trace messages be emitted to a file, or the standard output and
105    a file at the same time. To trace to a file, specify the filename with an output character in front
106    of it.
107    
108        TSetup('4 SQL', ">$fileName");
109    
110    To trace to the standard output and a file at the same time, put a C<+> in front of the angle
111    bracket.
112    
113        TSetup('3 *', "+>$fileName");
114    
115  The flexibility of tracing makes it superior to simple use of directives like C<die> and C<warn>.  The flexibility of tracing makes it superior to simple use of directives like C<die> and C<warn>.
116  Tracer calls can be left in the code with minimal overhead and then turned on only when needed.  Tracer calls can be left in the code with minimal overhead and then turned on only when needed.
117  Thus, debugging information is available and easily retrieved even when the application is  Thus, debugging information is available and easily retrieved even when the application is
118  being used out in the field.  being used out in the field.
119    
120    =head3 Trace Levels
121    
122  There is no hard and fast rule on how to use trace levels. The following is therefore only  There is no hard and fast rule on how to use trace levels. The following is therefore only
123  a suggestion.  a suggestion.
124    
125  =over 4  =over 4
126    
127  =item 0 Error  =item Error 0
128    
129  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
130  application entirely.  application entirely.
131    
132  =item 1 Warning  =item Warning 1
133    
134  Message indicates something that is unexpected but that probably did not interfere  Message indicates something that is unexpected but that probably did not interfere
135  with program execution.  with program execution.
136    
137  =item 2 Notice  =item Notice 2
138    
139  Message indicates the beginning or end of a major task.  Message indicates the beginning or end of a major task.
140    
141  =item 3 Information  =item Information 3
142    
143  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
144  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.
145    
146  =item 4 Detail  =item Detail 4
147    
148  Message indicates a low-level loop iteration.  Message indicates a low-level loop iteration.
149    
150  =back  =back
151    
152    The format of trace messages is important because some utilities analyze trace files.
153    There are three fields-- the time stamp, the category name, and the text.
154    The time stamp is between square brackets and the category name between angle brackets.
155    After the category name there is a colon (C<:>) followed by the message text.
156    If the square brackets or angle brackets are missing, then the trace management
157    utilities assume that they are encountering a set of pre-formatted lines.
158    
159    Note, however, that this formatting is done automatically by the tracing functions. You
160    only need to know about it if you want to parse a trace file.
161    
162    =head3 Emergency Tracing
163    
164    Sometimes, you need a way for tracing to happen automatically without putting parameters
165    in a form or on the command line. Emergency tracing does this. You invoke emergency tracing
166    from the debug form, which is accessed from the [[DebugConsole]]. Emergency tracing requires
167    that you specify a tracing key. For command-line tools, the key is
168    taken from the C<TRACING> environment variable. For web services, the key is taken from
169    a cookie. Either way, the key tells the tracing facility who you are, so that you control
170    the tracing in your environment without stepping on other users.
171    
172    The key can be anything you want. If you don't have a key, the C<SetPassword> page will
173    generate one for you.
174    
175    You can activate and de-activate emergency tracing from the debugging control panel, as
176    well as display the trace file itself.
177    
178    To enable emergency tracing in your code, call
179    
180        ETracing($cgi)
181    
182    from a web script and
183    
184        ETracing()
185    
186    from a command-line script.
187    
188    The web script will look for the tracing key in the cookies, and the command-line
189    script will look for it in the C<TRACING> environment variable. If you are
190    using the L</StandardSetup> method or a [[WebApplication]], emergency tracing
191    will be configured automatically.
192    
193  =cut  =cut
194    
195  # Declare the configuration variables.  # Declare the configuration variables.
196    
197  my $Destination = "NONE";   # Description of where to send the trace output.  my $Destination = "WARN";   # Description of where to send the trace output.
198  my $TeeFlag = 0;            # TRUE if output is going to a file and to the  my $TeeFlag = 0;            # TRUE if output is going to a file and to the
199                              # standard output                              # standard output
200  my %Categories = ( main => 1 );  my %Categories = ( main => 1 );
201                              # hash of active category names                              # hash of active category names
202    my @LevelNames = qw(error warn notice info detail);
203  my $TraceLevel = 0;         # trace level; a higher trace level produces more  my $TraceLevel = 0;         # trace level; a higher trace level produces more
204                              # messages                              # messages
205  my @Queue = ();             # queued list of trace messages.  my @Queue = ();             # queued list of trace messages.
206  my $LastCategory = "main";  # name of the last category interrogated  my $LastCategory = "main";  # name of the last category interrogated
207    my $LastLevel = 0;          # level of the last test call
208  my $SetupCount = 0;         # number of times TSetup called  my $SetupCount = 0;         # number of times TSetup called
209  my $AllTrace = 0;           # TRUE if we are tracing all categories.  my $AllTrace = 0;           # TRUE if we are tracing all categories.
210    my $SavedCGI;               # CGI object passed to ETracing
211    umask 2;                    # Fix the damn umask so everything is group-writable.
212    
213    =head2 Tracing Methods
214    
215    =head3 Setups
216    
217        my $count = Tracer::Setups();
218    
219    Return the number of times L</TSetup> has been called.
220    
221    This method allows for the creation of conditional tracing setups where, for example, we
222    may want to set up tracing if nobody else has done it before us.
223    
224  =head2 Public Methods  =cut
225    
226    sub Setups {
227        return $SetupCount;
228    }
229    
230  =head3 TSetup  =head3 TSetup
231    
232  C<< TSetup($categoryList, $target); >>      TSetup($categoryList, $target);
233    
234  This method is used to specify the trace options. The options are stored as package data  This method is used to specify the trace options. The options are stored as package data
235  and interrogated by the L</Trace> and L</T> methods.  and interrogated by the L</Trace> and L</T> methods.
# Line 157  Line 269 
269      # Presume category-based tracing until we learn otherwise.      # Presume category-based tracing until we learn otherwise.
270      $AllTrace = 0;      $AllTrace = 0;
271      # 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
272      # tracing.      # tracing. We must also clear away any pre-existing data.
273        %Categories = ( main => 1 );
274      for my $category (@categoryData) {      for my $category (@categoryData) {
275          if ($category eq '*') {          if ($category eq '*') {
276              $AllTrace = 1;              $AllTrace = 1;
# Line 166  Line 279 
279          }          }
280      }      }
281      # Now we need to process the destination information. The most important special      # Now we need to process the destination information. The most important special
282      # cases are the single ">", which requires we clear the file first, and the      # case is when we're writing to a file. This is indicated by ">" (overwrite) and
283      # "+" prefix which indicates a double echo.      # ">>" (append). A leading "+" for either indicates that we are also writing to
284        # the standard output (tee mode).
285      if ($target =~ m/^\+?>>?/) {      if ($target =~ m/^\+?>>?/) {
286          if ($target =~ m/^\+/) {          if ($target =~ m/^\+/) {
287              $TeeFlag = 1;              $TeeFlag = 1;
288              $target = substr($target, 1);              $target = substr($target, 1);
289          }          }
290          if ($target =~ m/^>[^>]/) {          if ($target =~ m/^>[^>]/) {
291                # We need to initialize the file (which clears it).
292              open TRACEFILE, $target;              open TRACEFILE, $target;
293              print TRACEFILE Now() . " Tracing initialized.\n";              print TRACEFILE "[" . Now() . "] [notice] [Tracer] Tracing initialized.\n";
294              close TRACEFILE;              close TRACEFILE;
295                # Set to append mode now that the file has been cleared.
296              $Destination = ">$target";              $Destination = ">$target";
297          } else {          } else {
298              $Destination = $target;              $Destination = $target;
# Line 188  Line 304 
304      $SetupCount++;      $SetupCount++;
305  }  }
306    
307  =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  
308    
309  sub Setups {      Tracer::SetLevel($newLevel);
     return $SetupCount;  
 }  
310    
311  =head3 Open  Modify the trace level. A higher trace level will cause more messages to appear.
312    
313  C<< my $handle = Open($fileHandle, $fileSpec, $message); >>  =over 4
314    
315  Open a file.  =item newLevel
316    
317  The I<$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,  
318    
319      Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");  =back
320    
321  would open for output appended to the specified file, and  =cut
322    
323      Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");  sub SetLevel {
324        $TraceLevel = $_[0];
325    }
326    
327  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.  
328    
329      my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");      my $time = Tracer::ParseDate($dateString);
330    
331  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
332  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
333  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
334  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,
335  using the file spec.  year) be separated by likely delimiters, such as spaces, commas, and such-like.
336    
337      Could not open "/usr/spool/news/twitlog"  If a time of day is present, it must be in military time with two digits for
338    everything but the hour.
339    
340  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.  
341    
342      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
343    equally innocuous. This means, however, that a sufficiently long sentence with date-like
344    parts in it may be interpreted as a date. Hopefully this will not be a problem.
345    
346  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.  
347    
348      Could not open "/usr/spool/news/twitlog": 6.  The parameters are as follows.
349    
350  =over 4  =over 4
351    
352  =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)  
353    
354  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>.  
355    
356  =item RETURN  =item RETURN
357    
358  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
359  open failed.  the date string is invalid. A valid date string must contain a month and day.
360    
361  =back  =back
362    
363  =cut  =cut
364    
365  sub Open {  # Universal month conversion table.
366    use constant MONTHS => {    Jan =>  0, January   =>  0, '01' =>  0,  '1' =>  0,
367                                Feb =>  1, February  =>  1, '02' =>  1,  '2' =>  1,
368                                Mar =>  2, March     =>  2, '03' =>  2,  '3' =>  2,
369                                Apr =>  3, April     =>  3, '04' =>  3,  '4' =>  3,
370                                May =>  4, May       =>  4, '05' =>  4,  '5' =>  4,
371                                Jun =>  5, June      =>  5, '06' =>  5,  '6' =>  5,
372                                Jul =>  6, July      =>  6, '07' =>  6,  '7' =>  6,
373                                Aug =>  7, August    =>  7, '08' =>  7,  '8' =>  7,
374                                Sep =>  8, September =>  8, '09' =>  8,  '9' =>  8,
375                                Oct =>  9, October  =>   9, '10' =>  9,
376                                Nov => 10, November =>  10, '11' => 10,
377                                Dec => 11, December =>  11, '12' => 11
378                            };
379    
380    sub ParseDate {
381      # Get the parameters.      # Get the parameters.
382      my ($fileHandle, $fileSpec, $message) = @_;      my ($dateString) = @_;
383      # Attempt to open the file.      # Declare the return variable.
384      my $rv = open $fileHandle, $fileSpec;      my $retVal;
385      # 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
386      if (! $rv) {      # numeric style first. That way, if the user's done something like "Sun 12/22", then we
387          # Save the system error message.      # won't be fooled into thinking the month is Sunday.
388          my $sysMessage = $!;      if ($dateString =~ m#\b(\d{1,2})/(\d{1,2})\b# || $dateString =~ m#\b(\w+)\s(\d{1,2})\b#) {
389          # See if we need a default message.          my ($mon, $mday) = (MONTHS->{$1}, $2);
390          if (!$message) {          # Insist that the month and day are valid.
391              # Clean any obvious mode characters and leading spaces from the          if (defined($mon) && $2 >= 1 && $2 <= 31) {
392              # filename.              # Find the time.
393              my ($fileName) = FindNamePart($fileSpec);              my ($hour, $min, $sec) = (0, 0, 0);
394              $message = "Could not open \"$fileName\"";              if ($dateString =~ /\b(\d{1,2}):(\d{2}):(\d{2})\b/) {
395                    ($hour, $min, $sec) = ($1, $2, $3);
396                }
397                # Find the year.
398                my $year;
399                if ($dateString =~ /\b(\d{4})\b/) {
400                    $year = $1;
401                } else {
402                    # Get the default year, which is this one. Note we must convert it to
403                    # the four-digit value expected by "timelocal".
404                    (undef, undef, undef, undef, undef, $year) = localtime();
405                    $year += 1900;
406          }          }
407          # 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: $!");  
408      }      }
409      # Return the file handle.      }
410      return $fileHandle;      # Return the result.
411        return $retVal;
412  }  }
413    
414  =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>.  
415    
416      >>/usr/fig/myfile.txt      Tracer::LogErrors($fileName);
     </usr/fig/myfile.txt  
     | sort -u > /usr/fig/myfile.txt  
417    
418  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.  
419    
420  =over 4  =over 4
421    
422  =item fileSpec  =item fileName
   
 File specification string from which the file name is to be extracted.  
   
 =item RETURN  
423    
424  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.  
425    
426  =back  =back
427    
428  =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);  
429    
430  is effectively the same as  sub LogErrors {
431        # Get the file name.
432      opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");      my ($fileName) = @_;
433      my @files = grep { $_ !~ /^\./ } readdir(TMP);      # Open the file as the standard error output.
434        open STDERR, '>', $fileName;
435    }
436    
437  Similarly, the following code  =head3 Trace
438    
439      my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs");      Trace($message);
440    
441  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
442  automatically throws an error if the directory fails to open.  any prior call to B<TSetup>.
443    
444  =over 4  =over 4
445    
446  =item dirName  =item message
   
 Name of the directory to open.  
   
 =item filtered  
447    
448  TRUE if files whose names begin with a period (C<.>) should be automatically removed  Message to write.
 from the list, else FALSE.  
449    
450  =back  =back
451    
452  =cut  =cut
453  #: Return Type @;  
454  sub OpenDir {  sub Trace {
455      # Get the parameters.      # Get the parameters.
456      my ($dirName, $filtered) = @_;      my ($message) = @_;
457      # Declare the return variable.      # Strip off any line terminators at the end of the message. We will add
458      my @retVal;      # new-line stuff ourselves.
459      # Open the directory.      my $stripped = Strip($message);
460      if (opendir(my $dirHandle, $dirName)) {      # Compute the caller information.
461          # The directory opened successfully. Get the appropriate list according to the      my ($callPackage, $callFile, $callLine) = caller();
462          # strictures of the filter parameter.      my $callFileTitle = basename($callFile);
463          if ($filtered) {      # Check the caller.
464              @retVal = grep { $_ !~ /^\./ } readdir $dirHandle;      my $callerInfo = ($callFileTitle ne "Tracer.pm" ? " [$callFileTitle $callLine]" : "");
465          } else {      # Get the timestamp.
466              @retVal = readdir $dirHandle;      my $timeStamp = Now();
467        # Build the prefix.
468        my $level = $LevelNames[$LastLevel] || "($LastLevel)";
469        my $prefix = "[$timeStamp] [$level] [$LastCategory]$callerInfo";
470        # Format the message.
471        my $formatted = "$prefix $stripped";
472        # Process according to the destination.
473        if ($Destination eq "TEXT") {
474            # Write the message to the standard output.
475            print "$formatted\n";
476        } elsif ($Destination eq "ERROR") {
477            # Write the message to the error output. Here, we want our prefix fields.
478            print STDERR "$formatted\n";
479        } elsif ($Destination eq "WARN") {
480            # Emit the message to the standard error output. It is presumed that the
481            # error logger will add its own prefix fields, the notable exception being
482            # the caller info.
483            print STDERR "$callerInfo$stripped\n";
484        } elsif ($Destination eq "QUEUE") {
485            # Push the message into the queue.
486            push @Queue, "$formatted";
487        } elsif ($Destination eq "HTML") {
488            # Convert the message to HTML and write it to the standard output.
489            my $escapedMessage = CGI::escapeHTML($stripped);
490            print "<p>$timeStamp $LastCategory $LastLevel: $escapedMessage</p>\n";
491        } elsif ($Destination =~ m/^>>/) {
492            # Write the trace message to an output file.
493            open(TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";
494            print TRACING "$formatted\n";
495            close TRACING;
496            # If the Tee flag is on, echo it to the standard output.
497            if ($TeeFlag) {
498                print "$formatted\n";
499          }          }
     } else {  
         # Here the directory would not open.  
         Confess("Could not open directory $dirName.");  
500      }      }
     # Return the result.  
     return @retVal;  
501  }  }
502    
503  =head3 SetLevel  =head3 T
504    
505  C<< Tracer::SetLevel($newLevel); >>      my $switch = T($category, $traceLevel);
506    
507  Modify the trace level. A higher trace level will cause more messages to appear.      or
508    
509  =over 4      my $switch = T($traceLevel);
510    
511  =item newLevel  Return TRUE if the trace level is at or above a specified value and the specified category
512    is active, else FALSE. If no category is specified, the caller's package name is used.
513    
514  Proposed new trace level.  =over 4
515    
516  =back  =item category
517    
518  =cut  Category to which the message belongs. If not specified, the caller's package name is
519    used.
520    
521  sub SetLevel {  =item traceLevel
     $TraceLevel = $_[0];  
 }  
522    
523  =head3 Now  Relevant tracing level.
524    
525    =item RETURN
526    
527    TRUE if a message at the specified trace level would appear in the trace, else FALSE.
528    
529    =back
530    
531    =cut
532    
533    sub T {
534        # Declare the return variable.
535        my $retVal = 0;
536        # Only proceed if tracing is turned on.
537        if ($Destination ne "NONE") {
538            # Get the parameters.
539            my ($category, $traceLevel) = @_;
540            if (!defined $traceLevel) {
541                # Here we have no category, so we need to get the calling package.
542                # The calling package is normally the first parameter. If it is
543                # omitted, the first parameter will be the tracelevel. So, the
544                # first thing we do is shift the so-called category into the
545                # $traceLevel variable where it belongs.
546                $traceLevel = $category;
547                my ($package, $fileName, $line) = caller;
548                # If there is no calling package, we default to "main".
549                if (!$package) {
550                    $category = "main";
551                } else {
552                    my @cats = split /::/, $package;
553                    $category = $cats[$#cats];
554                }
555            }
556            # Save the category name and level.
557            $LastCategory = $category;
558            $LastLevel = $traceLevel;
559            # Convert it to lower case before we hash it.
560            $category = lc $category;
561            # Use the category and tracelevel to compute the result.
562            if (ref $traceLevel) {
563                Confess("Bad trace level.");
564            } elsif (ref $TraceLevel) {
565                Confess("Bad trace config.");
566            }
567            $retVal = ($traceLevel <= $TraceLevel && ($AllTrace || exists $Categories{$category}));
568        }
569        # Return the computed result.
570        return $retVal;
571    }
572    
573    =head3 QTrace
574    
575        my $data = QTrace($format);
576    
577    Return the queued trace data in the specified format.
578    
579    =over 4
580    
581    =item format
582    
583    C<html> to format the data as an HTML list, C<text> to format it as straight text.
584    
585    =back
586    
587    =cut
588    
589    sub QTrace {
590        # Get the parameter.
591        my ($format) = @_;
592        # Create the return variable.
593        my $retVal = "";
594        # Only proceed if there is an actual queue.
595        if (@Queue) {
596            # Process according to the format.
597            if ($format =~ m/^HTML$/i) {
598                # Convert the queue into an HTML list.
599                $retVal = "<ul>\n";
600                for my $line (@Queue) {
601                    my $escapedLine = CGI::escapeHTML($line);
602                    $retVal .= "<li>$escapedLine</li>\n";
603                }
604                $retVal .= "</ul>\n";
605            } elsif ($format =~ m/^TEXT$/i) {
606                # Convert the queue into a list of text lines.
607                $retVal = join("\n", @Queue) . "\n";
608            }
609            # Clear the queue.
610            @Queue = ();
611        }
612        # Return the formatted list.
613        return $retVal;
614    }
615    
616    =head3 Confess
617    
618        Confess($message);
619    
620    Trace the call stack and abort the program with the specified message. When used with
621    the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.
622    So, for example
623    
624        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
625    
626    Will abort the program with a stack trace if the value of C<$recNum> is negative.
627    
628    =over 4
629    
630    =item message
631    
632    Message to include in the trace.
633    
634    =back
635    
636    =cut
637    
638    sub Confess {
639        # Get the parameters.
640        my ($message) = @_;
641        # Set up the category and level.
642        $LastCategory = "(confess)";
643        $LastLevel = 0;
644        if (! defined($FIG_Config::no_tool_hdr)) {
645            # Here we have a tool header. Display its length so that the user can adjust the line numbers.
646            my $toolHeaderFile = "$FIG_Config::fig_disk/dist/releases/current/$FIG_Config::arch/tool_hdr";
647            # Only proceed if the tool header file is actually present.
648            if (-f $toolHeaderFile) {
649                my $fh;
650                if (open $fh, "<$toolHeaderFile") {
651                    my @lines = <$fh>;
652                    Trace("Tool header has " . scalar(@lines) . " lines.");
653                }
654            }
655        }
656        # Trace the call stack.
657        Cluck($message);
658        # Abort the program.
659        croak(">>> $message");
660    }
661    
662    =head3 Warn
663    
664        Warn($message);
665    
666    This method traces an important message. If an RSS feed is configured
667    (via I<FIG_Config::error_feed>) and the tracing destination is C<WARN>,
668    then the message will be echoed to the feed. In general, a tracing
669    destination of C<WARN> indicates that the caller is running as a web
670    service in a production environment; however, this is not a requirement.
671    
672    The L</Cluck> method calls this one for its final message. Since
673    L</Confess> calls L</Cluck>, this means that any error which is caught
674    and confessed will put something in the feed. This insures that someone
675    will be alerted relatively quickly when a failure occurs.
676    
677    =over 4
678    
679    =item message
680    
681    Message to be traced.
682    
683    =back
684    
685    =cut
686    
687    sub Warn {
688        # Get the parameters.
689        my ($message) = @_;
690        # Trace the message.
691        Trace($message);
692        # An error here would be disastrous. Note, however, that we aren't too worried
693        # about losing events. The error log is always available for the occasions where
694        # we mess up.
695        eval {
696            # Do we need to put this in the RSS feed?
697            if ($FIG_Config::error_feed && $Destination eq 'WARN') {
698                # Yes. We now need to compute the date, the link, and the title.
699                # First, the date, in a very specific format.
700                my $date = strftime("%a, %02e %b %H:%M:%S %Y ", localtime) .
701                    (tz_local_offset() / 30);
702                # We'll put the link and title in here.
703                my ($link, $title);
704                # Environment data goes in here.
705                my $environment;
706                # HTML-escape the message.
707                my $escaped = CGI::escapeHTML($message);
708                # If we have a CGI object, then this is a web error. Otherwise, it's
709                # command-line.
710                if (defined $SavedCGI) {
711                    # We're in a web service. The title is the user's IP, and the link
712                    # is the URL that got us here.
713                    my $key = $ENV{HTTP_X_FORWARDED_FOR} || $ENV{REMOTE_ADDR};
714                    $title = "Event Reported at IP address $key: $escaped";
715                    $link = $SavedCGI->url(-full => 1, -query => 1);
716                    # We need the user agent string.
717                    $environment = "User Agent $ENV{HTTP_USER_AGENT}."
718                } else {
719                    # No CGI object, so we're a command-line tool. Use the tracing
720                    # key and the PID as the user identifier.
721                    my $key = EmergencyKey();
722                    $title = "Event Reported by $key Process $$: $escaped";
723                    # Set the link to the development NMPDR. There is really no good
724                    # choice here.
725                    $link = "http://$FIG_Config::dev_server";
726                    # We need the command
727                    $environment = "Command $ENV{_}.";
728                }
729                # Build a GUID. We use the current time, the title, and the process ID,
730                # then digest the result.
731                my $guid = Digest::MD5::md5_base64(gettimeofday(), $title, $$);
732                # Finally, the description. This is a stack trace plus various environmental stuff.
733                my @trace = LongMess();
734                my $trace = join "; ", @trace;
735                my $description = CGI::escapeHTML("$environment Stack trace: $trace");
736                # Okay, we have all the pieces. Create a hash of the new event.
737                my $newItem = { title => $title,
738                                description => $description,
739                                link => $link,
740                                category => $LastCategory,
741                                pubDate => $date,
742                                guid => $guid,
743                               };
744                # We need XML capability for this.
745                require XML::Simple;
746                # The RSS document goes in here.
747                my $rss;
748                # Get the name of the RSS file. It's in the FIG temporary directory.
749                my $fileName = "$FIG_Config::temp/$FIG_Config::error_feed";
750                # Does it exist?
751                if (-s $fileName) {
752                    # Slurp it in.
753                    $rss = XML::Simple::XMLin($fileName, ForceArray => ['item']);
754                } else {
755                    my $size = -s $fileName;
756                    # Create an empty channel.
757                    $rss = {
758                        channel => {
759                            title => 'NMPDR Warning Feed',
760                            link => "$FIG_Config::temp_url/$FIG_Config::error_feed",
761                            description => "Important messages regarding the status of the NMPDR.",
762                            generator => "NMPDR Trace Facility",
763                            docs => "http://blogs.law.harvard.edu/tech/rss",
764                            item => []
765                        },
766                    };
767                }
768                # Get the channel object.
769                my $channel = $rss->{channel};
770                # Update the last-build date.
771                $channel->{lastBuildDate} = $date;
772                # Get the item array.
773                my $items = $channel->{item};
774                # Insure it has only 100 entries.
775                while (scalar @{$items} > 100) {
776                    pop @{$items};
777                }
778                # Add our new item at the front.
779                unshift @{$items}, $newItem;
780                # Replace the file.
781                my $xml = XML::Simple::XMLout($rss, NoAttr => 1, RootName => 'rss', XmlDecl => '<?xml version="1.0" encoding="utf-8"?>',
782                                              NoEscape => 1);
783                # We don't use Open here because we can't afford an error.
784                if (open XMLOUT, ">$fileName") {
785                    print XMLOUT $xml;
786                    close XMLOUT;
787                }
788            }
789        };
790        # There's no "if ($@)" here, because putting an error message in the log
791        # saying that we missed putting an error message in the feed of messages
792        # in the log is not going to help anybody.
793    }
794    
795    =head3 Assert
796    
797        Assert($condition1, $condition2, ... $conditionN);
798    
799    Return TRUE if all the conditions are true. This method can be used in conjunction with
800    the OR operator and the L</Confess> method as a debugging assert.
801    So, for example
802    
803        Assert($recNum >= 0) || Confess("Invalid record number $recNum.");
804    
805    Will abort the program with a stack trace if the value of C<$recNum> is negative.
806    
807    =cut
808    sub Assert {
809        my $retVal = 1;
810        LOOP: for my $condition (@_) {
811            if (! $condition) {
812                $retVal = 0;
813                last LOOP;
814            }
815        }
816        return $retVal;
817    }
818    
819    =head3 Cluck
820    
821        Cluck($message);
822    
823    Trace the call stack. Note that for best results, you should qualify the call with a
824    trace condition. For example,
825    
826        Cluck("Starting record parse.") if T(3);
827    
828    will only trace the stack if the trace level for the package is 3 or more.
829    
830    =over 4
831    
832    =item message
833    
834    Message to include in the trace.
835    
836    =back
837    
838    =cut
839    
840    sub Cluck {
841        # Get the parameters.
842        my ($message) = @_;
843        # Trace what's happening.
844        Trace("Stack trace for event: $message");
845        # Get the stack trace.
846        my @trace = LongMess();
847        # Convert the trace to a series of messages.
848        for my $line (@trace) {
849            # Replace the tab at the beginning with spaces.
850            $line =~ s/^\t/    /;
851            # Trace the line.
852            Trace($line);
853        }
854        # Issue a warning. This displays the event message and inserts it into the RSS error feed.
855        Warn($message);
856    }
857    
858    =head3 LongMess
859    
860        my @lines = Tracer::LongMess();
861    
862    Return a stack trace with all tracing methods removed. The return will be in the form of a list
863    of message strings.
864    
865    =cut
866    
867    sub LongMess {
868        # Declare the return variable.
869        my @retVal = ();
870        my $confession = longmess("");
871        for my $line (split /\s*\n/, $confession) {
872            unless ($line =~ /Tracer\.pm/) {
873                # Here we have a line worth keeping. Push it onto the result list.
874                push @retVal, $line;
875            }
876        }
877        # Return the result.
878        return @retVal;
879    }
880    
881    =head3 ScriptSetup (deprecated)
882    
883        my ($cgi, $varHash) = ScriptSetup($noTrace);
884    
885    Perform standard tracing and debugging setup for scripts. The value returned is
886    the CGI object followed by a pre-built variable hash. At the end of the script,
887    the client should call L</ScriptFinish> to output the web page.
888    
889    This method calls L</ETracing> to configure tracing, which allows the tracing
890    to be configured via the emergency tracing form on the debugging control panel.
891    Tracing will then be turned on automatically for all programs that use the L</ETracing>
892    method, which includes every program that uses this method or L</StandardSetup>.
893    
894    =over 4
895    
896    =item noTrace (optional)
897    
898    If specified, tracing will be suppressed. This is useful if the script wants to set up
899    tracing manually.
900    
901    =item RETURN
902    
903    Returns a two-element list consisting of a CGI query object and a variable hash for
904    the output page.
905    
906    =back
907    
908    =cut
909    
910    sub ScriptSetup {
911        # Get the parameters.
912        my ($noTrace) = @_;
913        # Get the CGI query object.
914        my $cgi = CGI->new();
915        # Set up tracing if it's not suppressed.
916        ETracing($cgi) unless $noTrace;
917        # Create the variable hash.
918        my $varHash = { results => '' };
919        # Return the query object and variable hash.
920        return ($cgi, $varHash);
921    }
922    
923    =head3 ETracing
924    
925        ETracing($parameter);
926    
927    Set up emergency tracing. Emergency tracing is tracing that is turned
928    on automatically for any program that calls this method. The emergency
929    tracing parameters are stored in a a file identified by a tracing key.
930    If this method is called with a CGI object, then the tracing key is
931    taken from a cookie. If it is called with no parameters, then the tracing
932    key is taken from an environment variable. If it is called with a string,
933    the tracing key is that string.
934    
935    =over 4
936    
937    =item parameter
938    
939    A parameter from which the tracing key is computed. If it is a scalar,
940    that scalar is used as the tracing key. If it is a CGI object, the
941    tracing key is taken from the C<IP> cookie. If it is omitted, the
942    tracing key is taken from the C<TRACING> environment variable. If it
943    is a CGI object and emergency tracing is not on, the C<Trace> and
944    C<TF> parameters will be used to determine the type of tracing.
945    
946    =back
947    
948    =cut
949    
950    sub ETracing {
951        # Get the parameter.
952        my ($parameter) = @_;
953        # Check for CGI mode.
954        if (defined $parameter && ref $parameter eq 'CGI') {
955            $SavedCGI = $parameter;
956        } else {
957            $SavedCGI = undef;
958        }
959        # Default to no tracing except errors.
960        my ($tracing, $dest) = ("0", "WARN");
961        # Check for emergency tracing.
962        my $tkey = EmergencyKey($parameter);
963        my $emergencyFile = EmergencyFileName($tkey);
964        if (-e $emergencyFile) {
965            # We have the file. Read in the data.
966            my @tracing = GetFile($emergencyFile);
967            # Pull off the time limit.
968            my $expire = shift @tracing;
969            # Convert it to seconds.
970            $expire *= 3600;
971            # Check the file data.
972            my $stat = stat($emergencyFile);
973            my ($now) = gettimeofday;
974            if ($now - $stat->mtime > $expire) {
975                # Delete the expired file.
976                unlink $emergencyFile;
977            } else {
978                # Emergency tracing is on. Pull off the destination and
979                # the trace level;
980                $dest = shift @tracing;
981                my $level = shift @tracing;
982                # Convert the destination to a real tracing destination.
983                # temp directory.
984                $dest = EmergencyTracingDest($tkey, $dest);
985                # Insure Tracer is specified.
986                my %moduleHash = map { $_ => 1 } @tracing;
987                $moduleHash{Tracer} = 1;
988                # Set the trace parameter.
989                $tracing = join(" ", $level, sort keys %moduleHash);
990            }
991        } elsif (defined $SavedCGI) {
992            # There's no emergency tracing, but we have a CGI object, so check
993            # for tracing from the form parameters.
994            if ($SavedCGI->param('Trace')) {
995                # Here the user has requested tracing via a form.
996                $dest = ($SavedCGI->param('TF') ? ">$FIG_Config::temp/Trace$$.log" : "QUEUE");
997                $tracing = $SavedCGI->param('Trace') . " Tracer";
998            }
999        }
1000        # Setup the tracing we've determined from all the stuff above.
1001        TSetup($tracing, $dest);
1002        # Check to see if we're a web script.
1003        if (defined $SavedCGI) {
1004            # Yes we are. Trace the form and environment data.
1005            TraceParms($SavedCGI);
1006            # Check for RAW mode. In raw mode, we print a fake header so that we see everything
1007            # emitted by the script in its raw form.
1008            if (T(Raw => 3)) {
1009                print CGI::header(-type => 'text/plain', -tracing => 'Raw');
1010            }
1011        }
1012    }
1013    
1014    =head3 EmergencyFileName
1015    
1016        my $fileName = Tracer::EmergencyFileName($tkey);
1017    
1018    Return the emergency tracing file name. This is the file that specifies
1019    the tracing information.
1020    
1021    =over 4
1022    
1023    =item tkey
1024    
1025    Tracing key for the current program.
1026    
1027    =item RETURN
1028    
1029    Returns the name of the file to contain the emergency tracing information.
1030    
1031    =back
1032    
1033    =cut
1034    
1035    sub EmergencyFileName {
1036        # Get the parameters.
1037        my ($tkey) = @_;
1038        # Compute the emergency tracing file name.
1039        return "$FIG_Config::temp/Emergency$tkey.txt";
1040    }
1041    
1042    =head3 EmergencyFileTarget
1043    
1044        my $fileName = Tracer::EmergencyFileTarget($tkey);
1045    
1046    Return the emergency tracing target file name. This is the file that receives
1047    the tracing output for file-based tracing.
1048    
1049    =over 4
1050    
1051    =item tkey
1052    
1053    Tracing key for the current program.
1054    
1055    =item RETURN
1056    
1057    Returns the name of the file to contain the trace output.
1058    
1059    =back
1060    
1061    =cut
1062    
1063    sub EmergencyFileTarget {
1064        # Get the parameters.
1065        my ($tkey) = @_;
1066        # Compute the emergency tracing file name.
1067        return "$FIG_Config::temp/trace$tkey.log";
1068    }
1069    
1070    =head3 EmergencyTracingDest
1071    
1072        my $dest = Tracer::EmergencyTracingDest($tkey, $myDest);
1073    
1074    This method converts an emergency tracing destination to a real
1075    tracing destination. The main difference is that if the
1076    destination is C<FILE> or C<APPEND>, we convert it to file
1077    output. If the destination is C<DUAL>, we convert it to file
1078    and standard output.
1079    
1080    =over 4
1081    
1082    =item tkey
1083    
1084    Tracing key for this environment.
1085    
1086    =item myDest
1087    
1088    Destination from the emergency tracing file.
1089    
1090    =item RETURN
1091    
1092    Returns a destination that can be passed into L</TSetup>.
1093    
1094    =back
1095    
1096    =cut
1097    
1098    sub EmergencyTracingDest {
1099        # Get the parameters.
1100        my ($tkey, $myDest) = @_;
1101        # Declare the return variable.
1102        my $retVal = $myDest;
1103        # Process according to the destination value.
1104        if ($myDest eq 'FILE') {
1105            $retVal = ">" . EmergencyFileTarget($tkey);
1106        } elsif ($myDest eq 'APPEND') {
1107            $retVal = ">>" . EmergencyFileTarget($tkey);
1108        } elsif ($myDest eq 'DUAL') {
1109            $retVal = "+>" . EmergencyFileTarget($tkey);
1110        } elsif ($myDest eq 'WARN') {
1111            $retVal = "WARN";
1112        }
1113        # Return the result.
1114        return $retVal;
1115    }
1116    
1117    =head3 Emergency
1118    
1119        Emergency($key, $hours, $dest, $level, @modules);
1120    
1121    Turn on emergency tracing. This method is normally invoked over the web from
1122    a debugging console, but it can also be called by the C<trace.pl> script.
1123    The caller specifies the duration of the emergency in hours, the desired tracing
1124    destination, the trace level, and a list of the trace modules to activate.
1125    For the length of the duration, when a program in an environment with the
1126    specified tracing key active invokes a Sprout CGI script, tracing will be
1127    turned on automatically. See L</TSetup> for more about tracing setup and
1128    L</ETracing> for more about emergency tracing.
1129    
1130    =over 4
1131    
1132    =item tkey
1133    
1134    The tracing key. This is used to identify the control file and the trace file.
1135    
1136    =item hours
1137    
1138    Number of hours to keep emergency tracing alive.
1139    
1140    =item dest
1141    
1142    Tracing destination. If no path information is specified for a file
1143    destination, it is put in the FIG temporary directory.
1144    
1145    =item level
1146    
1147    Tracing level. A higher level means more trace messages.
1148    
1149    =item modules
1150    
1151    A list of the tracing modules to activate.
1152    
1153    =back
1154    
1155    =cut
1156    
1157    sub Emergency {
1158        # Get the parameters.
1159        my ($tkey, $hours, $dest, $level, @modules) = @_;
1160        # Create the emergency file.
1161        my $specFile = EmergencyFileName($tkey);
1162        my $outHandle = Open(undef, ">$specFile");
1163        print $outHandle join("\n", $hours, $dest, $level, @modules, "");
1164    }
1165    
1166    =head3 EmergencyKey
1167    
1168        my $tkey = EmergencyKey($parameter);
1169    
1170    Return the Key to be used for emergency tracing. This could be an IP address,
1171     a session ID, or a user name, depending on the environment.
1172    
1173    =over 4
1174    
1175    =item parameter
1176    
1177    Parameter defining the method for finding the tracing key. If it is a scalar,
1178    then it is presumed to be the tracing key itself. If it is a CGI object, then
1179    the tracing key is taken from the C<IP> cookie. Otherwise, the tracing key is
1180    taken from the C<TRACING> environment variable.
1181    
1182    =item RETURN
1183    
1184    Returns the key to be used for labels in emergency tracing.
1185    
1186    =back
1187    
1188    =cut
1189    
1190    sub EmergencyKey {
1191        # Get the parameters.
1192        my ($parameter) = @_;
1193        # Declare the return variable.
1194        my $retVal;
1195        # Determine the parameter type.
1196        if (! defined $parameter) {
1197            # Here we're supposed to check the environment. If that fails, we
1198            # get the effective login ID.
1199            $retVal = $ENV{TRACING} || scalar getpwuid($<);
1200        } else {
1201            my $ptype = ref $parameter;
1202            if ($ptype eq 'CGI') {
1203                # Here we were invoked from a web page. Look for a cookie.
1204                $retVal = $parameter->cookie('IP');
1205            } elsif (! $ptype) {
1206                # Here the key was passed in.
1207                $retVal = $parameter;
1208            }
1209        }
1210        # If no luck finding a key, use the PID.
1211        if (! defined $retVal) {
1212            $retVal = $$;
1213        }
1214        # Return the result.
1215        return $retVal;
1216    }
1217    
1218    
1219    =head3 TraceParms
1220    
1221        Tracer::TraceParms($cgi);
1222    
1223    Trace the CGI parameters at trace level CGI => 3 and the environment variables
1224    at level CGI => 4. A self-referencing URL is traced at level CGI => 2.
1225    
1226    =over 4
1227    
1228    =item cgi
1229    
1230    CGI query object containing the parameters to trace.
1231    
1232    =back
1233    
1234    =cut
1235    
1236    sub TraceParms {
1237        # Get the parameters.
1238        my ($cgi) = @_;
1239        if (T(CGI => 2)) {
1240            # Here we trace the GET-style URL for the script.
1241            Trace("[URL] " . $cgi->url(-relative => 1, -query => 1));
1242        }
1243        if (T(CGI => 3)) {
1244            # Here we want to trace the parameter data.
1245            my @names = $cgi->param;
1246            for my $parmName (sort @names) {
1247                # Note we skip the Trace parameters, which are for our use only.
1248                if ($parmName ne 'Trace' && $parmName ne 'TF') {
1249                    my @values = $cgi->param($parmName);
1250                    Trace("[CGI] $parmName = " . join(", ", @values));
1251                }
1252            }
1253            # Display the request method.
1254            my $method = $cgi->request_method();
1255            Trace("Method: $method");
1256        }
1257        if (T(CGI => 4)) {
1258            # Here we want the environment data too.
1259            for my $envName (sort keys %ENV) {
1260                Trace("[ENV] $envName = $ENV{$envName}");
1261            }
1262        }
1263    }
1264    
1265    =head3 TraceImages
1266    
1267        Tracer::TraceImages($htmlString);
1268    
1269    Trace information about all of an html document's images. The tracing
1270    will be for type "IMG" at level 3. The image's source string
1271    will be displayed. This is generally either the URL of the image or
1272    raw data for the image itself. If the source is too long, only the first 300
1273    characters will be shown at trace level 3. The entire source will be shown,
1274    however, at trace level 4. This method is not very smart, and might catch
1275    Javascript code, but it is still useful when debugging the arcane
1276    behavior of images in multiple browser environments.
1277    
1278    =over 4
1279    
1280    =item htmlString
1281    
1282    HTML text for an outgoing web page.
1283    
1284    =back
1285    
1286    =cut
1287    
1288    sub TraceImages {
1289        # Only proceed if we're at the proper trace level.
1290        if (T(IMG => 3)) {
1291            # For performance reasons we're manipulating $_[0] instead of retrieving the string
1292            # into a variable called "$htmlString". This is because we expect html strings to be
1293            # long, and don't want to copy them any more than we have to.
1294            Trace(length($_[0]) . " characters in web page.");
1295            # Loop through the HTML, culling image tags.
1296            while ($_[0] =~ /<img\s+[^>]+?src="([^"]+)"/sgi) {
1297                # Extract the source string and determine whether or not it's too long.
1298                my $srcString = $1;
1299                my $pos = pos($_[0]) - length($srcString);
1300                my $excess = length($srcString) - 300;
1301                # We'll put the display string in here.
1302                my $srcDisplay = $srcString;
1303                # If it's a data string, split it at the comma.
1304                $srcDisplay =~ s/^(data[^,]+,)/$1\n/;
1305                # If there's no excess or we're at trace level 4, we're done. At level 3 with
1306                # a long string, however, we only show the first 300 characters.
1307                if ($excess > 0 && ! T(IMG => 4)) {
1308                    $srcDisplay = substr($srcDisplay,0,300) . "\nplus $excess characters.";
1309                }
1310                # Output the trace message.
1311                Trace("Image tag at position $pos:\n$srcDisplay");
1312            }
1313        }
1314    }
1315    
1316    
1317    =head3 ScriptFinish (deprecated)
1318    
1319        ScriptFinish($webData, $varHash);
1320    
1321    Output a web page at the end of a script. Either the string to be output or the
1322    name of a template file can be specified. If the second parameter is omitted,
1323    it is assumed we have a string to be output; otherwise, it is assumed we have the
1324    name of a template file. The template should have the variable C<DebugData>
1325    specified in any form that invokes a standard script. If debugging mode is turned
1326    on, a form field will be put in that allows the user to enter tracing data.
1327    Trace messages will be placed immediately before the terminal C<BODY> tag in
1328    the output, formatted as a list.
1329    
1330    A typical standard script would loook like the following.
1331    
1332        BEGIN {
1333            # Print the HTML header.
1334            print "CONTENT-TYPE: text/html\n\n";
1335        }
1336        use Tracer;
1337        use CGI;
1338        use FIG;
1339        # ... more uses ...
1340    
1341        my ($cgi, $varHash) = ScriptSetup();
1342        eval {
1343            # ... get data from $cgi, put it in $varHash ...
1344        };
1345        if ($@) {
1346            Trace("Script Error: $@") if T(0);
1347        }
1348        ScriptFinish("Html/MyTemplate.html", $varHash);
1349    
1350    The idea here is that even if the script fails, you'll see trace messages and
1351    useful output.
1352    
1353    =over 4
1354    
1355    =item webData
1356    
1357    A string containing either the full web page to be written to the output or the
1358    name of a template file from which the page is to be constructed. If the name
1359    of a template file is specified, then the second parameter must be present;
1360    otherwise, it must be absent.
1361    
1362    =item varHash (optional)
1363    
1364    If specified, then a reference to a hash mapping variable names for a template
1365    to their values. The template file will be read into memory, and variable markers
1366    will be replaced by data in this hash reference.
1367    
1368    =back
1369    
1370    =cut
1371    
1372    sub ScriptFinish {
1373        # Get the parameters.
1374        my ($webData, $varHash) = @_;
1375        # Check for a template file situation.
1376        my $outputString;
1377        if (defined $varHash) {
1378            # Here we have a template file. We need to determine the template type.
1379            my $template;
1380            if ($FIG_Config::template_url && $webData =~ /\.php$/) {
1381                $template = "$FIG_Config::template_url/$webData";
1382            } else {
1383                $template = "<<$webData";
1384            }
1385            $outputString = PageBuilder::Build($template, $varHash, "Html");
1386        } else {
1387            # Here the user gave us a raw string.
1388            $outputString = $webData;
1389        }
1390        # Check for trace messages.
1391        if ($Destination ne "NONE" && $TraceLevel > 0) {
1392            # We have trace messages, so we want to put them at the end of the body. This
1393            # is either at the end of the whole string or at the beginning of the BODY
1394            # end-tag.
1395            my $pos = length $outputString;
1396            if ($outputString =~ m#</body>#gi) {
1397                $pos = (pos $outputString) - 7;
1398            }
1399            # If the trace messages were queued, we unroll them. Otherwise, we display the
1400            # destination.
1401            my $traceHtml;
1402            if ($Destination eq "QUEUE") {
1403                $traceHtml = QTrace('Html');
1404            } elsif ($Destination =~ /^>>(.+)$/) {
1405                # Here the tracing output it to a file. We code it as a hyperlink so the user
1406                # can copy the file name into the clipboard easily.
1407                my $actualDest = $1;
1408                $traceHtml = "<p>Tracing output to $actualDest.</p>\n";
1409            } else {
1410                # Here we have one of the special destinations.
1411                $traceHtml = "<P>Tracing output type is $Destination.</p>\n";
1412            }
1413            substr $outputString, $pos, 0, $traceHtml;
1414        }
1415        # Write the output string.
1416        print $outputString;
1417    }
1418    
1419    =head2 Command-Line Utility Methods
1420    
1421    =head3 SendSMS
1422    
1423        my $msgID = Tracer::SendSMS($phoneNumber, $msg);
1424    
1425    Send a text message to a phone number using Clickatell. The FIG_Config file must contain the
1426    user name, password, and API ID for the relevant account in the hash reference variable
1427    I<$FIG_Config::phone>, using the keys C<user>, C<password>, and C<api_id>. For
1428    example, if the user name is C<BruceTheHumanPet>, the password is C<silly>, and the API ID
1429    is C<2561022>, then the FIG_Config file must contain
1430    
1431        $phone =  { user => 'BruceTheHumanPet',
1432                    password => 'silly',
1433                    api_id => '2561022' };
1434    
1435    The original purpose of this method was to insure Bruce would be notified immediately when the
1436    Sprout Load terminates. Care should be taken if you do not wish Bruce to be notified immediately
1437    when you call this method.
1438    
1439    The message ID will be returned if successful, and C<undef> if an error occurs.
1440    
1441    =over 4
1442    
1443    =item phoneNumber
1444    
1445    Phone number to receive the message, in international format. A United States phone number
1446    would be prefixed by "1". A British phone number would be prefixed by "44".
1447    
1448    =item msg
1449    
1450    Message to send to the specified phone.
1451    
1452    =item RETURN
1453    
1454    Returns the message ID if successful, and C<undef> if the message could not be sent.
1455    
1456    =back
1457    
1458    =cut
1459    
1460    sub SendSMS {
1461        # Get the parameters.
1462        my ($phoneNumber, $msg) = @_;
1463        # Declare the return variable. If we do not change it, C<undef> will be returned.
1464        my $retVal;
1465        # Only proceed if we have phone support.
1466        if (! defined $FIG_Config::phone) {
1467            Trace("Phone support not present in FIG_Config.") if T(1);
1468        } else {
1469            # Get the phone data.
1470            my $parms = $FIG_Config::phone;
1471            # Get the Clickatell URL.
1472            my $url = "http://api.clickatell.com/http/";
1473            # Create the user agent.
1474            my $ua = LWP::UserAgent->new;
1475            # Request a Clickatell session.
1476            my $resp = $ua->post("$url/sendmsg", { user => $parms->{user},
1477                                         password => $parms->{password},
1478                                         api_id => $parms->{api_id},
1479                                         to => $phoneNumber,
1480                                         text => $msg});
1481            # Check for an error.
1482            if (! $resp->is_success) {
1483                Trace("Alert failed.") if T(1);
1484            } else {
1485                # Get the message ID.
1486                my $rstring = $resp->content;
1487                if ($rstring =~ /^ID:\s+(.*)$/) {
1488                    $retVal = $1;
1489                } else {
1490                    Trace("Phone attempt failed with $rstring") if T(1);
1491                }
1492            }
1493        }
1494        # Return the result.
1495        return $retVal;
1496    }
1497    
1498    =head3 StandardSetup
1499    
1500        my ($options, @parameters) = StandardSetup(\@categories, \%options, $parmHelp, @ARGV);
1501    
1502    This method performs standard command-line parsing and tracing setup. The return
1503    values are a hash of the command-line options and a list of the positional
1504    parameters. Tracing is automatically set up and the command-line options are
1505    validated.
1506    
1507    This is a complex method that does a lot of grunt work. The parameters can
1508    be more easily understood, however, once they are examined individually.
1509    
1510    The I<categories> parameter is the most obtuse. It is a reference to a list of
1511    special-purpose tracing categories. Most tracing categories are PERL package
1512    names. So, for example, if you wanted to turn on tracing inside the B<Sprout>,
1513    B<ERDB>, and B<SproutLoad> packages, you would specify the categories
1514    
1515        ["Sprout", "SproutLoad", "ERDB"]
1516    
1517    This would cause trace messages in the specified three packages to appear in
1518    the output. There are two special tracing categories that are automatically
1519    handled by this method. In other words, if you used L</TSetup> you would need
1520    to include these categories manually, but if you use this method they are turned
1521    on automatically.
1522    
1523    =over 4
1524    
1525    =item SQL
1526    
1527    Traces SQL commands and activity.
1528    
1529    =item Tracer
1530    
1531    Traces error messages and call stacks.
1532    
1533    =back
1534    
1535    C<SQL> is only turned on if the C<-sql> option is specified in the command line.
1536    The trace level is specified using the C<-trace> command-line option. For example,
1537    the following command line for C<TransactFeatures> turns on SQL tracing and runs
1538    all tracing at level 3.
1539    
1540        TransactFeatures -trace=3 -sql register ../xacts IDs.tbl
1541    
1542    Standard tracing is output to the standard output and echoed to the file
1543    C<trace>I<$$>C<.log> in the FIG temporary directory, where I<$$> is the
1544    process ID. You can also specify the C<user> parameter to put a user ID
1545    instead of a process ID in the trace file name. So, for example
1546    
1547    The default trace level is 2. To get all messages, specify a trace level of 4.
1548    For a genome-by-genome update, use 3.
1549    
1550        TransactFeatures -trace=3 -sql -user=Bruce register ../xacts IDs.tbl
1551    
1552    would send the trace output to C<traceBruce.log> in the temporary directory.
1553    
1554    The I<options> parameter is a reference to a hash containing the command-line
1555    options, their default values, and an explanation of what they mean. Command-line
1556    options may be in the form of switches or keywords. In the case of a switch, the
1557    option value is 1 if it is specified and 0 if it is not specified. In the case
1558    of a keyword, the value is separated from the option name by an equal sign. You
1559    can see this last in the command-line example above.
1560    
1561    You can specify a different default trace level by setting C<$options->{trace}>
1562    prior to calling this method.
1563    
1564    An example at this point would help. Consider, for example, the command-line utility
1565    C<TransactFeatures>. It accepts a list of positional parameters plus the options
1566    C<safe>, C<noAlias>, C<start>, and C<tblFiles>. To start up this command, we execute
1567    the following code.
1568    
1569        my ($options, @parameters) = Tracer::StandardSetup(["DocUtils"],
1570                            { safe => [0, "use database transactions"],
1571                              noAlias => [0, "do not expect aliases in CHANGE transactions"],
1572                              start => [' ', "start with this genome"],
1573                              tblFiles => [0, "output TBL files containing the corrected IDs"] },
1574                            "<command> <transactionDirectory> <IDfile>",
1575                          @ARGV);
1576    
1577    
1578    The call to C<ParseCommand> specifies the default values for the options and
1579    stores the actual options in a hash that is returned as C<$options>. The
1580    positional parameters are returned in C<@parameters>.
1581    
1582    The following is a sample command line for C<TransactFeatures>.
1583    
1584        TransactFeatures -trace=2 -noAlias register ../xacts IDs.tbl
1585    
1586    Single and double hyphens are equivalent. So, you could also code the
1587    above command as
1588    
1589        TransactFeatures --trace=2 --noAlias register ../xacts IDs.tbl
1590    
1591    In this case, C<register>, C<../xacts>, and C<IDs.tbl> are the positional
1592    parameters, and would find themselves in I<@parameters> after executing the
1593    above code fragment. The tracing would be set to level 2, and the categories
1594    would be C<Tracer>, and <DocUtils>. C<Tracer> is standard,
1595    and C<DocUtils> was included because it came in within the first parameter
1596    to this method. The I<$options> hash would be
1597    
1598        { trace => 2, sql => 0, safe => 0,
1599          noAlias => 1, start => ' ', tblFiles => 0 }
1600    
1601    Use of C<StandardSetup> in this way provides a simple way of performing
1602    standard tracing setup and command-line parsing. Note that the caller is
1603    not even aware of the command-line switches C<-trace> and C<-sql>, which
1604    are used by this method to control the tracing. If additional tracing features
1605    need to be added in the future, they can be processed by this method without
1606    upsetting the command-line utilities.
1607    
1608    If the C<background> option is specified on the command line, then the
1609    standard and error outputs will be directed to files in the temporary
1610    directory, using the same suffix as the trace file. So, if the command
1611    line specified
1612    
1613        -user=Bruce -background
1614    
1615    then the trace output would go to C<traceBruce.log>, the standard output to
1616    C<outBruce.log>, and the error output to C<errBruce.log>. This is designed to
1617    simplify starting a command in the background.
1618    
1619    The user name is also used as the tracing key for L</Emergency Tracing>.
1620    Specifying a value of C<E> for the trace level causes emergency tracing to
1621    be used instead of custom tracing. If the user name is not specified,
1622    the tracing key is taken from the C<Tracing> environment variable. If there
1623    is no value for that variable, the tracing key will be computed from the PID.
1624    
1625    Finally, if the special option C<-help> is specified, the option
1626    names will be traced at level 0 and the program will exit without processing.
1627    This provides a limited help capability. For example, if the user enters
1628    
1629        TransactFeatures -help
1630    
1631    he would see the following output.
1632    
1633        TransactFeatures [options] <command> <transactionDirectory> <IDfile>
1634            -trace    tracing level (default E)
1635            -sql      trace SQL commands
1636            -safe     use database transactions
1637            -noAlias  do not expect aliases in CHANGE transactions
1638            -start    start with this genome
1639            -tblFiles output TBL files containing the corrected IDs
1640    
1641    The caller has the option of modifying the tracing scheme by placing a value
1642    for C<trace> in the incoming options hash. The default value can be overridden,
1643    or the tracing to the standard output can be turned off by suffixing a minus
1644    sign to the trace level. So, for example,
1645    
1646        { trace => [0, "tracing level (default 0)"],
1647           ...
1648    
1649    would set the default trace level to 0 instead of E, while
1650    
1651        { trace => ["2-", "tracing level (default 2)"],
1652           ...
1653    
1654    would set the default to 2, but trace only to the log file, not to the
1655    standard output.
1656    
1657    The parameters to this method are as follows.
1658    
1659    =over 4
1660    
1661    =item categories
1662    
1663    Reference to a list of tracing category names. These should be names of
1664    packages whose internal workings will need to be debugged to get the
1665    command working.
1666    
1667    =item options
1668    
1669    Reference to a hash containing the legal options for the current command mapped
1670    to their default values and descriptions. The user can override the defaults
1671    by specifying the options as command-line switches prefixed by a hyphen.
1672    Tracing-related options may be added to this hash. If the C<-h> option is
1673    specified on the command line, the option descriptions will be used to
1674    explain the options. To turn off tracing to the standard output, add a
1675    minus sign to the value for C<trace> (see above).
1676    
1677    =item parmHelp
1678    
1679    A string that vaguely describes the positional parameters. This is used
1680    if the user specifies the C<-h> option.
1681    
1682    =item argv
1683    
1684    List of command line parameters, including the option switches, which must
1685    precede the positional parameters and be prefixed by a hyphen.
1686    
1687    =item RETURN
1688    
1689    Returns a list. The first element of the list is the reference to a hash that
1690    maps the command-line option switches to their values. These will either be the
1691    default values or overrides specified on the command line. The remaining
1692    elements of the list are the position parameters, in order.
1693    
1694    =back
1695    
1696    =cut
1697    
1698    sub StandardSetup {
1699        # Get the parameters.
1700        my ($categories, $options, $parmHelp, @argv) = @_;
1701        # Get the default tracing key.
1702        my $tkey = EmergencyKey();
1703        # Add the tracing options.
1704        if (! exists $options->{trace}) {
1705            $options->{trace} = ['2', "tracing level (E for emergency tracing)"];
1706        }
1707        $options->{sql} = [0, "turn on SQL tracing"];
1708        $options->{help} = [0, "display command-line options"];
1709        $options->{user} = [$tkey, "tracing key"];
1710        $options->{background} = [0, "spool standard and error output"];
1711        # Create a parsing hash from the options hash. The parsing hash
1712        # contains the default values rather than the default value
1713        # and the description. While we're at it, we'll memorize the
1714        # length of the longest option name.
1715        my $longestName = 0;
1716        my %parseOptions = ();
1717        for my $key (keys %{$options}) {
1718            if (length $key > $longestName) {
1719                $longestName = length $key;
1720            }
1721            $parseOptions{$key} = $options->{$key}->[0];
1722        }
1723        # Parse the command line.
1724        my ($retOptions, @retParameters) = ParseCommand(\%parseOptions, @argv);
1725        # Get the logfile suffix.
1726        my $suffix = $retOptions->{user};
1727        # Check for background mode.
1728        if ($retOptions->{background}) {
1729            my $outFileName = "$FIG_Config::temp/out$suffix.log";
1730            my $errFileName = "$FIG_Config::temp/err$suffix.log";
1731            open STDOUT, ">$outFileName";
1732            open STDERR, ">$errFileName";
1733            # Check for phone support. If we have phone support and a phone number,
1734            # we want to turn it on.
1735            if ($ENV{PHONE} && defined($FIG_Config::phone)) {
1736                $retOptions->{phone} = $ENV{PHONE};
1737            }
1738        }
1739        # Now we want to set up tracing. First, we need to know if the user
1740        # wants emergency tracing.
1741        if ($retOptions->{trace} eq 'E') {
1742            ETracing($retOptions->{user});
1743        } else {
1744            # Here the tracing is controlled from the command line.
1745            my @cats = @{$categories};
1746            if ($retOptions->{sql}) {
1747                push @cats, "SQL";
1748            }
1749            # Add the default categories.
1750            push @cats, "Tracer";
1751            # Next, we create the category string by joining the categories.
1752            my $cats = join(" ", @cats);
1753            # Check to determine whether or not the caller wants to turn off tracing
1754            # to the standard output.
1755            my $traceLevel = $retOptions->{trace};
1756            my $textOKFlag = 1;
1757            if ($traceLevel =~ /^(.)-/) {
1758                $traceLevel = $1;
1759                $textOKFlag = 0;
1760            }
1761            # Now we set up the trace mode.
1762            my $traceMode;
1763            # Verify that we can open a file in the FIG temporary directory.
1764            my $traceFileName = "$FIG_Config::temp/trace$suffix.log";
1765            if (open TESTTRACE, ">$traceFileName") {
1766                # Here we can trace to a file.
1767                $traceMode = ">$traceFileName";
1768                if ($textOKFlag) {
1769                    # Echo to standard output if the text-OK flag is set.
1770                    $traceMode = "+$traceMode";
1771                }
1772                # Close the test file.
1773                close TESTTRACE;
1774            } else {
1775                # Here we can't trace to a file. Complain about this.
1776                warn "Could not open trace file $traceFileName: $!\n";
1777                # We trace to the standard output if it's
1778                # okay, and the error log otherwise.
1779                if ($textOKFlag) {
1780                    $traceMode = "TEXT";
1781                } else {
1782                    $traceMode = "WARN";
1783                }
1784            }
1785            # Now set up the tracing.
1786            TSetup("$traceLevel $cats", $traceMode);
1787        }
1788        # Check for the "help" option. If it is specified, dump the command-line
1789        # options and exit the program.
1790        if ($retOptions->{help}) {
1791            $0 =~ m#[/\\](\w+)(\.pl)?$#i;
1792            print "$1 [options] $parmHelp\n";
1793            for my $key (sort keys %{$options}) {
1794                my $name = Pad($key, $longestName, 0, ' ');
1795                my $desc = $options->{$key}->[1];
1796                if ($options->{$key}->[0]) {
1797                    $desc .= " (default " . $options->{$key}->[0] . ")";
1798                }
1799                print "  $name $desc\n";
1800            }
1801            exit(0);
1802        }
1803        # Trace the options, if applicable.
1804        if (T(3)) {
1805            my @parms = grep { $retOptions->{$_} } keys %{$retOptions};
1806            Trace("Selected options: " . join(", ", sort @parms) . ".");
1807        }
1808        # Return the parsed parameters.
1809        return ($retOptions, @retParameters);
1810    }
1811    
1812    =head3 ReadOptions
1813    
1814        my %options = Tracer::ReadOptions($fileName);
1815    
1816    Read a set of options from a file. Each option is encoded in a line of text that has the
1817    format
1818    
1819    I<optionName>C<=>I<optionValue>C<; >I<comment>
1820    
1821    The option name must consist entirely of letters, digits, and the punctuation characters
1822    C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank
1823    character is a semi-colon will be ignored. The return hash will map each option name to
1824    the corresponding option value.
1825    
1826    =over 4
1827    
1828    =item fileName
1829    
1830    Name of the file containing the option data.
1831    
1832    =item RETURN
1833    
1834    Returns a hash mapping the option names specified in the file to their corresponding option
1835    value.
1836    
1837    =back
1838    
1839    =cut
1840    
1841    sub ReadOptions {
1842        # Get the parameters.
1843        my ($fileName) = @_;
1844        # Open the file.
1845        (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");
1846        # Count the number of records read.
1847        my ($records, $comments) = 0;
1848        # Create the return hash.
1849        my %retVal = ();
1850        # Loop through the file, accumulating key-value pairs.
1851        while (my $line = <CONFIGFILE>) {
1852            # Denote we've read a line.
1853            $records++;
1854            # Determine the line type.
1855            if ($line =~ /^\s*[\n\r]/) {
1856                # A blank line is a comment.
1857                $comments++;
1858            } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {
1859                # Here we have an option assignment.
1860                retVal{$1} = $2;
1861            } elsif ($line =~ /^\s*;/) {
1862                # Here we have a text comment.
1863                $comments++;
1864            } else {
1865                # Here we have an invalid line.
1866                Trace("Invalid option statement in record $records.") if T(0);
1867            }
1868        }
1869        # Return the hash created.
1870        return %retVal;
1871    }
1872    
1873    =head3 GetOptions
1874    
1875        Tracer::GetOptions(\%defaults, \%options);
1876    
1877    Merge a specified set of options into a table of defaults. This method takes two hash references
1878    as input and uses the data from the second to update the first. If the second does not exist,
1879    there will be no effect. An error will be thrown if one of the entries in the second hash does not
1880    exist in the first.
1881    
1882    Consider the following example.
1883    
1884        my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options);
1885    
1886    In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and
1887    B<trace>. The default database type is C<mySQL> and the default trace level is C<0>. If the value of
1888    B<$options> is C<< {dbType => 'Oracle'} >>, then the database type will be changed to C<Oracle> and
1889    the trace level will remain at 0. If B<$options> is undefined, then the database type and trace level
1890    will remain C<mySQL> and C<0>. If, on the other hand, B<$options> is defined as
1891    
1892        {databaseType => 'Oracle'}
1893    
1894    an error will occur because the B<databaseType> option does not exist.
1895    
1896    =over 4
1897    
1898    =item defaults
1899    
1900    Table of default option values.
1901    
1902    =item options
1903    
1904    Table of overrides, if any.
1905    
1906    =item RETURN
1907    
1908    Returns a reference to the default table passed in as the first parameter.
1909    
1910    =back
1911    
1912    =cut
1913    
1914    sub GetOptions {
1915        # Get the parameters.
1916        my ($defaults, $options) = @_;
1917        # Check for overrides.
1918        if ($options) {
1919            # Loop through the overrides.
1920            while (my ($option, $setting) = each %{$options}) {
1921                # Insure this override exists.
1922                if (!exists $defaults->{$option}) {
1923                    croak "Unrecognized option $option encountered.";
1924                } else {
1925                    # Apply the override.
1926                    $defaults->{$option} = $setting;
1927                }
1928            }
1929        }
1930        # Return the merged table.
1931        return $defaults;
1932    }
1933    
1934    =head3 MergeOptions
1935    
1936        Tracer::MergeOptions(\%table, \%defaults);
1937    
1938    Merge default values into a hash table. This method looks at the key-value pairs in the
1939    second (default) hash, and if a matching key is not found in the first hash, the default
1940    pair is copied in. The process is similar to L</GetOptions>, but there is no error-
1941    checking and no return value.
1942    
1943    =over 4
1944    
1945    =item table
1946    
1947    Hash table to be updated with the default values.
1948    
1949    =item defaults
1950    
1951    Default values to be merged into the first hash table if they are not already present.
1952    
1953    =back
1954    
1955    =cut
1956    
1957    sub MergeOptions {
1958        # Get the parameters.
1959        my ($table, $defaults) = @_;
1960        # Loop through the defaults.
1961        while (my ($key, $value) = each %{$defaults}) {
1962            if (!exists $table->{$key}) {
1963                $table->{$key} = $value;
1964            }
1965        }
1966    }
1967    
1968    =head3 ParseCommand
1969    
1970        my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList);
1971    
1972    Parse a command line consisting of a list of parameters. The initial parameters may be option
1973    specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped
1974    off and merged into a table of default options. The remainder of the command line is
1975    returned as a list of positional arguments. For example, consider the following invocation.
1976    
1977        my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words);
1978    
1979    In this case, the list @words will be treated as a command line and there are two options available,
1980    B<errors> and B<logFile>. If @words has the following format
1981    
1982        -logFile=error.log apple orange rutabaga
1983    
1984    then at the end of the invocation, C<$options> will be
1985    
1986        { errors => 0, logFile => 'error.log' }
1987    
1988    and C<@arguments> will contain
1989    
1990        apple orange rutabaga
1991    
1992    The parser allows for some escape sequences. See L</UnEscape> for a description. There is no
1993    support for quote characters. Options can be specified with single or double hyphens.
1994    
1995    =over 4
1996    
1997    =item optionTable
1998    
1999    Table of default options.
2000    
2001    =item inputList
2002    
2003    List of words on the command line.
2004    
2005    =item RETURN
2006    
2007    Returns a reference to the option table and a list of the positional arguments.
2008    
2009    =back
2010    
2011    =cut
2012    
2013    sub ParseCommand {
2014        # Get the parameters.
2015        my ($optionTable, @inputList) = @_;
2016        # Process any options in the input list.
2017        my %overrides = ();
2018        while ((@inputList > 0) && ($inputList[0] =~ /^--?/)) {
2019            # Get the current option.
2020            my $arg = shift @inputList;
2021            # Pull out the option name.
2022            $arg =~ /^--?([^=]*)/g;
2023            my $name = $1;
2024            # Check for an option value.
2025            if ($arg =~ /\G=(.*)$/g) {
2026                # Here we have a value for the option.
2027                $overrides{$name} = UnEscape($1);
2028            } else {
2029                # Here there is no value, so we use 1.
2030                $overrides{$name} = 1;
2031            }
2032        }
2033        # Merge the options into the defaults.
2034        GetOptions($optionTable, \%overrides);
2035        # Translate the remaining parameters.
2036        my @retVal = ();
2037        for my $inputParm (@inputList) {
2038            push @retVal, UnEscape($inputParm);
2039        }
2040        # Return the results.
2041        return ($optionTable, @retVal);
2042    }
2043    
2044    
2045    =head2 File Utility Methods
2046    
2047    =head3 GetFile
2048    
2049        my @fileContents = Tracer::GetFile($fileName);
2050    
2051        or
2052    
2053        my $fileContents = Tracer::GetFile($fileName);
2054    
2055    Return the entire contents of a file. In list context, line-ends are removed and
2056    each line is a list element. In scalar context, line-ends are replaced by C<\n>.
2057    
2058    =over 4
2059    
2060    =item fileName
2061    
2062    Name of the file to read.
2063    
2064    =item RETURN
2065    
2066    In a list context, returns the entire file as a list with the line terminators removed.
2067    In a scalar context, returns the entire file as a string. If an error occurs opening
2068    the file, an empty list will be returned.
2069    
2070    =back
2071    
2072    =cut
2073    
2074    sub GetFile {
2075        # Get the parameters.
2076        my ($fileName) = @_;
2077        # Declare the return variable.
2078        my @retVal = ();
2079        # Open the file for input.
2080        my $handle = Open(undef, "<$fileName");
2081        # Read the whole file into the return variable, stripping off any terminator
2082        # characters.
2083        my $lineCount = 0;
2084        while (my $line = <$handle>) {
2085            $lineCount++;
2086            $line = Strip($line);
2087            push @retVal, $line;
2088        }
2089        # Close it.
2090        close $handle;
2091        my $actualLines = @retVal;
2092        Trace("$actualLines lines read from file $fileName.") if T(File => 2);
2093        # Return the file's contents in the desired format.
2094        if (wantarray) {
2095            return @retVal;
2096        } else {
2097            return join "\n", @retVal;
2098        }
2099    }
2100    
2101    =head3 PutFile
2102    
2103        Tracer::PutFile($fileName, \@lines);
2104    
2105    Write out a file from a list of lines of text.
2106    
2107    =over 4
2108    
2109    =item fileName
2110    
2111    Name of the output file.
2112    
2113    =item lines
2114    
2115    Reference to a list of text lines. The lines will be written to the file in order, with trailing
2116    new-line characters. Alternatively, may be a string, in which case the string will be written without
2117    modification.
2118    
2119    =back
2120    
2121    =cut
2122    
2123    sub PutFile {
2124        # Get the parameters.
2125        my ($fileName, $lines) = @_;
2126        # Open the output file.
2127        my $handle = Open(undef, ">$fileName");
2128        # Count the lines written.
2129        if (ref $lines ne 'ARRAY') {
2130            # Here we have a scalar, so we write it raw.
2131            print $handle $lines;
2132            Trace("Scalar put to file $fileName.") if T(File => 3);
2133        } else {
2134            # Write the lines one at a time.
2135            my $count = 0;
2136            for my $line (@{$lines}) {
2137                print $handle "$line\n";
2138                $count++;
2139            }
2140            Trace("$count lines put to file $fileName.") if T(File => 3);
2141        }
2142        # Close the output file.
2143        close $handle;
2144    }
2145    
2146    =head3 ParseRecord
2147    
2148        my @fields = Tracer::ParseRecord($line);
2149    
2150    Parse a tab-delimited data line. The data line is split into field values. Embedded tab
2151    and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.
2152    These will automatically be converted.
2153    
2154    =over 4
2155    
2156    =item line
2157    
2158    Line of data containing the tab-delimited fields.
2159    
2160    =item RETURN
2161    
2162    Returns a list of the fields found in the data line.
2163    
2164    =back
2165    
2166    =cut
2167    
2168    sub ParseRecord {
2169        # Get the parameter.
2170        my ($line) = @_;
2171        # Remove the trailing new-line, if any.
2172        chomp $line;
2173        # Split the line read into pieces using the tab character.
2174        my @retVal = split /\t/, $line;
2175        # Trim and fix the escapes in each piece.
2176        for my $value (@retVal) {
2177            # Trim leading whitespace.
2178            $value =~ s/^\s+//;
2179            # Trim trailing whitespace.
2180            $value =~ s/\s+$//;
2181            # Delete the carriage returns.
2182            $value =~ s/\r//g;
2183            # Convert the escapes into their real values.
2184            $value =~ s/\\t/"\t"/ge;
2185            $value =~ s/\\n/"\n"/ge;
2186        }
2187        # Return the result.
2188        return @retVal;
2189    }
2190    
2191    =head3 Merge
2192    
2193        my @mergedList = Tracer::Merge(@inputList);
2194    
2195    Sort a list of strings and remove duplicates.
2196    
2197    =over 4
2198    
2199    =item inputList
2200    
2201    List of scalars to sort and merge.
2202    
2203    =item RETURN
2204    
2205    Returns a list containing the same elements sorted in ascending order with duplicates
2206    removed.
2207    
2208    =back
2209    
2210    =cut
2211    
2212    sub Merge {
2213        # Get the input list in sort order.
2214        my @inputList = sort @_;
2215        # Only proceed if the list has at least two elements.
2216        if (@inputList > 1) {
2217            # Now we want to move through the list splicing out duplicates.
2218            my $i = 0;
2219            while ($i < @inputList) {
2220                # Get the current entry.
2221                my $thisEntry = $inputList[$i];
2222                # Find out how many elements duplicate the current entry.
2223                my $j = $i + 1;
2224                my $dup1 = $i + 1;
2225                while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };
2226                # If the number is nonzero, splice out the duplicates found.
2227                if ($j > $dup1) {
2228                    splice @inputList, $dup1, $j - $dup1;
2229                }
2230                # Now the element at position $dup1 is different from the element before it
2231                # at position $i. We push $i forward one position and start again.
2232                $i++;
2233            }
2234        }
2235        # Return the merged list.
2236        return @inputList;
2237    }
2238    
2239    =head3 Open
2240    
2241        my $handle = Open($fileHandle, $fileSpec, $message);
2242    
2243    Open a file.
2244    
2245    The I<$fileSpec> is essentially the second argument of the PERL C<open>
2246    function. The mode is specified using Unix-like shell information. So, for
2247    example,
2248    
2249        Open(\*LOGFILE, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2250    
2251    would open for output appended to the specified file, and
2252    
2253        Open(\*DATASTREAM, "| sort -u >$outputFile", "Could not open $outputFile.");
2254    
2255    would open a pipe that sorts the records written and removes duplicates. Note
2256    the use of file handle syntax in the Open call. To use anonymous file handles,
2257    code as follows.
2258    
2259        my $logFile = Open(undef, '>>/usr/spool/news/twitlog', "Could not open twit log.");
2260    
2261    The I<$message> parameter is used if the open fails. If it is set to C<0>, then
2262    the open returns TRUE if successful and FALSE if an error occurred. Otherwise, a
2263    failed open will throw an exception and the third parameter will be used to construct
2264    an error message. If the parameter is omitted, a standard message is constructed
2265    using the file spec.
2266    
2267        Could not open "/usr/spool/news/twitlog"
2268    
2269    Note that the mode characters are automatically cleaned from the file name.
2270    The actual error message from the file system will be captured and appended to the
2271    message in any case.
2272    
2273        Could not open "/usr/spool/news/twitlog": file not found.
2274    
2275    In some versions of PERL the only error message we get is a number, which
2276    corresponds to the C++ C<errno> value.
2277    
2278        Could not open "/usr/spool/news/twitlog": 6.
2279    
2280    =over 4
2281    
2282    =item fileHandle
2283    
2284    File handle. If this parameter is C<undef>, a file handle will be generated
2285    and returned as the value of this method.
2286    
2287    =item fileSpec
2288    
2289    File name and mode, as per the PERL C<open> function.
2290    
2291    =item message (optional)
2292    
2293    Error message to use if the open fails. If omitted, a standard error message
2294    will be generated. In either case, the error information from the file system
2295    is appended to the message. To specify a conditional open that does not throw
2296    an error if it fails, use C<0>.
2297    
2298    =item RETURN
2299    
2300    Returns the name of the file handle assigned to the file, or C<undef> if the
2301    open failed.
2302    
2303    =back
2304    
2305    =cut
2306    
2307    sub Open {
2308        # Get the parameters.
2309        my ($fileHandle, $fileSpec, $message) = @_;
2310        # Attempt to open the file.
2311        my $rv = open $fileHandle, $fileSpec;
2312        # If the open failed, generate an error message.
2313        if (! $rv) {
2314            # Save the system error message.
2315            my $sysMessage = $!;
2316            # See if we need a default message.
2317            if (!$message) {
2318                # Clean any obvious mode characters and leading spaces from the
2319                # filename.
2320                my ($fileName) = FindNamePart($fileSpec);
2321                $message = "Could not open \"$fileName\"";
2322            }
2323            # Terminate with an error using the supplied message and the
2324            # error message from the file system.
2325            Confess("$message: $!");
2326        }
2327        # Return the file handle.
2328        return $fileHandle;
2329    }
2330    
2331    =head3 FindNamePart
2332    
2333        my ($fileName, $start, $len) = Tracer::FindNamePart($fileSpec);
2334    
2335    Extract the portion of a file specification that contains the file name.
2336    
2337    A file specification is the string passed to an C<open> call. It specifies the file
2338    mode and name. In a truly complex situation, it can specify a pipe sequence. This
2339    method assumes that the file name is whatever follows the first angle bracket
2340    sequence.  So, for example, in the following strings the file name is
2341    C</usr/fig/myfile.txt>.
2342    
2343        >>/usr/fig/myfile.txt
2344        </usr/fig/myfile.txt
2345        | sort -u > /usr/fig/myfile.txt
2346    
2347    If the method cannot find a file name using its normal methods, it will return the
2348    whole incoming string.
2349    
2350    =over 4
2351    
2352    =item fileSpec
2353    
2354    File specification string from which the file name is to be extracted.
2355    
2356    =item RETURN
2357    
2358    Returns a three-element list. The first element contains the file name portion of
2359    the specified string, or the whole string if a file name cannot be found via normal
2360    methods. The second element contains the start position of the file name portion and
2361    the third element contains the length.
2362    
2363    =back
2364    
2365    =cut
2366    #: Return Type $;
2367    sub FindNamePart {
2368        # Get the parameters.
2369        my ($fileSpec) = @_;
2370        # Default to the whole input string.
2371        my ($retVal, $pos, $len) = ($fileSpec, 0, length $fileSpec);
2372        # Parse out the file name if we can.
2373        if ($fileSpec =~ m/(<|>>?)(.+?)(\s*)$/) {
2374            $retVal = $2;
2375            $len = length $retVal;
2376            $pos = (length $fileSpec) - (length $3) - $len;
2377        }
2378        # Return the result.
2379        return ($retVal, $pos, $len);
2380    }
2381    
2382    =head3 OpenDir
2383    
2384        my @files = OpenDir($dirName, $filtered, $flag);
2385    
2386    Open a directory and return all the file names. This function essentially performs
2387    the functions of an C<opendir> and C<readdir>. If the I<$filtered> parameter is
2388    set to TRUE, all filenames beginning with a period (C<.>), dollar sign (C<$>),
2389    or pound sign (C<#>) and all filenames ending with a tilde C<~>) will be
2390    filtered out of the return list. If the directory does not open and I<$flag> is not
2391    set, an exception is thrown. So, for example,
2392    
2393  C<< my $string = Tracer::Now(); >>      my @files = OpenDir("/Volumes/fig/contigs", 1);
2394    
2395  Return a displayable time stamp containing the local time.  is effectively the same as
2396    
2397  =cut      opendir(TMP, "/Volumes/fig/contigs") || Confess("Could not open /Volumes/fig/contigs.");
2398        my @files = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir(TMP);
2399    
2400  sub Now {  Similarly, the following code
     my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime(time);  
     my $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .  
                  _p2($hour) . ":" . _p2($min) . ":" . _p2($sec);  
     return $retVal;  
 }  
2401    
2402  # Pad a number to 2 digits.      my @files = grep { $_ =~ /^\d/ } OpenDir("/Volumes/fig/orgs", 0, 1);
 sub _p2 {  
     my ($value) = @_;  
     $value = "0$value" if ($value < 10);  
     return $value;  
 }  
2403    
2404  =head3 LogErrors  Returns the names of all files in C</Volumes/fig/orgs> that begin with digits and
2405    automatically returns an empty list if the directory fails to open.
2406    
2407  C<< Tracer::LogErrors($fileName); >>  =over 4
2408    
2409  Route the standard error output to a log file.  =item dirName
2410    
2411  =over 4  Name of the directory to open.
2412    
2413  =item fileName  =item filtered
2414    
2415  Name of the file to receive the error output.  TRUE if files whose names begin with a period (C<.>) should be automatically removed
2416    from the list, else FALSE.
2417    
2418    =item flag
2419    
2420    TRUE if a failure to open is okay, else FALSE
2421    
2422  =back  =back
2423    
2424  =cut  =cut
2425    #: Return Type @;
2426  sub LogErrors {  sub OpenDir {
2427      # Get the file name.      # Get the parameters.
2428      my ($fileName) = @_;      my ($dirName, $filtered, $flag) = @_;
2429      # Open the file as the standard error output.      # Declare the return variable.
2430      open STDERR, '>', $fileName;      my @retVal = ();
2431        # Open the directory.
2432        if (opendir(my $dirHandle, $dirName)) {
2433            # The directory opened successfully. Get the appropriate list according to the
2434            # strictures of the filter parameter.
2435            if ($filtered) {
2436                @retVal = grep { $_ !~ /^[\.\$\#]/ && $_ !~ /~$/ } readdir $dirHandle;
2437            } else {
2438                @retVal = readdir $dirHandle;
2439            }
2440        } elsif (! $flag) {
2441            # Here the directory would not open and it's considered an error.
2442            Confess("Could not open directory $dirName.");
2443        }
2444        # Return the result.
2445        return @retVal;
2446  }  }
2447    
 =head3 ReadOptions  
   
 C<< my %options = Tracer::ReadOptions($fileName); >>  
2448    
2449  Read a set of options from a file. Each option is encoded in a line of text that has the  =head3 Insure
 format  
2450    
2451  I<optionName>C<=>I<optionValue>C<; >I<comment>      Insure($dirName, $chmod);
2452    
2453  The option name must consist entirely of letters, digits, and the punctuation characters  Insure a directory is present.
 C<.> and C<_>, and is case sensitive. Blank lines and lines in which the first nonblank  
 character is a semi-colon will be ignored. The return hash will map each option name to  
 the corresponding option value.  
2454    
2455  =over 4  =over 4
2456    
2457  =item fileName  =item dirName
2458    
2459  Name of the file containing the option data.  Name of the directory to check. If it does not exist, it will be created.
2460    
2461  =item RETURN  =item chmod (optional)
2462    
2463  Returns a hash mapping the option names specified in the file to their corresponding option  Security privileges to be given to the directory if it is created.
 value.  
2464    
2465  =back  =back
2466    
2467  =cut  =cut
2468    
2469  sub ReadOptions {  sub Insure {
2470      # Get the parameters.      my ($dirName, $chmod) = @_;
2471      my ($fileName) = @_;      if (! -d $dirName) {
2472      # Open the file.          Trace("Creating $dirName directory.") if T(2);
2473      (open CONFIGFILE, "<$fileName") || Confess("Could not open option file $fileName.");          eval {
2474      # Count the number of records read.              mkpath $dirName;
2475      my ($records, $comments) = 0;              # If we have permissions specified, set them here.
2476      # Create the return hash.              if (defined($chmod)) {
2477      my %retVal = ();                  chmod $chmod, $dirName;
2478      # Loop through the file, accumulating key-value pairs.              }
2479      while (my $line = <CONFIGFILE>) {          };
2480          # Denote we've read a line.          if ($@) {
2481          $records++;              Confess("Error creating $dirName: $@");
         # Determine the line type.  
         if ($line =~ /^\s*[\n\r]/) {  
             # A blank line is a comment.  
             $comments++;  
         } elsif ($line =~ /^\s*([A-Za-z0-9_\.]+)=([^;]*);/) {  
             # Here we have an option assignment.  
             retVal{$1} = $2;  
         } elsif ($line =~ /^\s*;/) {  
             # Here we have a text comment.  
             $comments++;  
         } else {  
             # Here we have an invalid line.  
             Trace("Invalid option statement in record $records.") if T(0);  
2482          }          }
2483      }      }
     # Return the hash created.  
     return %retVal;  
2484  }  }
2485    
2486  =head3 GetOptions  =head3 ChDir
2487    
2488  C<< Tracer::GetOptions(\%defaults, \%options); >>      ChDir($dirName);
2489    
2490  Merge a specified set of options into a table of defaults. This method takes two hash references  Change to the specified directory.
 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.  
2491    
2492  Consider the following example.  =over 4
2493    
2494  C<< my $optionTable = GetOptions({ dbType => 'mySQL', trace => 0 }, $options); >>  =item dirName
2495    
2496  In this example, the variable B<$options> is expected to contain at most two options-- B<dbType> and  Name of the directory to which we want to change.
 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<$options> is defined as  
2497    
2498  C<< {databaseType => 'Oracle'} >>  =back
2499    
2500  an error will occur because the B<databaseType> option does not exist.  =cut
2501    
2502  =over 4  sub ChDir {
2503        my ($dirName) = @_;
2504        if (! -d $dirName) {
2505            Confess("Cannot change to directory $dirName: no such directory.");
2506        } else {
2507            Trace("Changing to directory $dirName.") if T(File => 4);
2508            my $okFlag = chdir $dirName;
2509            if (! $okFlag) {
2510                Confess("Error switching to directory $dirName.");
2511            }
2512        }
2513    }
2514    
2515  =item defaults  =head3 SetPermissions
2516    
2517  Table of default option values.      Tracer::SetPermissions($dirName, $group, $mask, %otherMasks);
2518    
2519  =item options  Set the permissions for a directory and all the files and folders inside it.
2520    In addition, the group ownership will be changed to the specified value.
2521    
2522  Table of overrides, if any.  This method is more vulnerable than most to permission and compatability
2523    problems, so it does internal error recovery.
2524    
2525  =item RETURN  =over 4
2526    
2527  Returns a reference to the default table passed in as the first parameter.  =item dirName
2528    
2529  =back  Name of the directory to process.
2530    
2531  =cut  =item group
2532    
2533  sub GetOptions {  Name of the group to be assigned.
     # Get the parameters.  
     my ($defaults, $options) = @_;  
     # Check for overrides.  
     if ($options) {  
         # Loop through the overrides.  
         while (my ($option, $setting) = each %{$options}) {  
             # Insure this override exists.  
             if (!exists $defaults->{$option}) {  
                 croak "Unrecognized option $option encountered.";  
             } else {  
                 # Apply the override.  
                 $defaults->{$option} = $setting;  
             }  
         }  
     }  
     # Return the merged table.  
     return $defaults;  
 }  
2534    
2535  =head3 MergeOptions  =item mask
2536    
2537  C<< Tracer::MergeOptions(\%table, \%defaults); >>  Permission mask. Bits that are C<1> in this mask will be ORed into the
2538    permission bits of any file or directory that does not already have them
2539    set to 1.
2540    
2541  Merge default values into a hash table. This method looks at the key-value pairs in the  =item otherMasks
 second (default) hash, and if a matching key is not found in the first hash, the default  
 pair is copied in. The process is similar to L</GetOptions>, but there is no error-  
 checking and no return value.  
2542    
2543  =over 4  Map of search patterns to permission masks. If a directory name matches
2544    one of the patterns, that directory and all its members and subdirectories
2545    will be assigned the new pattern. For example, the following would
2546    assign 01664 to most files, but would use 01777 for directories named C<tmp>.
2547    
2548  =item table      Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp$' => 01777);
2549    
2550  Hash table to be updated with the default values.  The list is ordered, so the following would use 0777 for C<tmp1> and
2551    0666 for C<tmp>, C<tmp2>, or C<tmp3>.
2552    
2553  =item defaults      Tracer::SetPermissions($dirName, 'fig', 01664, '^tmp1' => 0777,
2554                                                       '^tmp' => 0666);
2555    
2556  Default values to be merged into the first hash table if they are not already present.  Note that the pattern matches are all case-insensitive, and only directory
2557    names are matched, not file names.
2558    
2559  =back  =back
2560    
2561  =cut  =cut
2562    
2563  sub MergeOptions {  sub SetPermissions {
2564      # Get the parameters.      # Get the parameters.
2565      my ($table, $defaults) = @_;      my ($dirName, $group, $mask, @otherMasks) = @_;
2566      # Loop through the defaults.      # Set up for error recovery.
2567      while (my ($key, $value) = each %{$defaults}) {      eval {
2568          if (!exists $table->{$key}) {          # Switch to the specified directory.
2569              $table->{$key} = $value;          ChDir($dirName);
2570            # Get the group ID.
2571            my $gid = getgrnam($group);
2572            # Get the mask for tracing.
2573            my $traceMask = sprintf("%04o", $mask) . "($mask)";
2574            Trace("Fixing permissions for directory $dirName using group $group($gid) and mask $traceMask.") if T(File => 2);
2575            my $fixCount = 0;
2576            my $lookCount = 0;
2577            # @dirs will be a stack of directories to be processed.
2578            my @dirs = (getcwd());
2579            while (scalar(@dirs) > 0) {
2580                # Get the current directory.
2581                my $dir = pop @dirs;
2582                # Check for a match to one of the specified directory names. To do
2583                # that, we need to pull the individual part of the name off of the
2584                # whole path.
2585                my $simpleName = $dir;
2586                if ($dir =~ m!/([^/]+)$!) {
2587                    $simpleName = $1;
2588                }
2589                Trace("Simple directory name for $dir is $simpleName.") if T(File => 4);
2590                # Search for a match.
2591                my $match = 0;
2592                my $i;
2593                for ($i = 0; $i < $#otherMasks && ! $match; $i += 2) {
2594                    my $pattern = $otherMasks[$i];
2595                    if ($simpleName =~ /$pattern/i) {
2596                        $match = 1;
2597                    }
2598                }
2599                # Check for a match. Note we use $i-1 because the loop added 2
2600                # before terminating due to the match.
2601                if ($match && $otherMasks[$i-1] != $mask) {
2602                    # This directory matches one of the incoming patterns, and it's
2603                    # a different mask, so we process it recursively with that mask.
2604                    SetPermissions($dir, $group, $otherMasks[$i-1], @otherMasks);
2605                } else {
2606                    # Here we can process normally. Get all of the non-hidden members.
2607                    my @submems = OpenDir($dir, 1);
2608                    for my $submem (@submems) {
2609                        # Get the full name.
2610                        my $thisMem = "$dir/$submem";
2611                        Trace("Checking member $thisMem.") if T(4);
2612                        $lookCount++;
2613                        if ($lookCount % 1000 == 0) {
2614                            Trace("$lookCount members examined. Current is $thisMem. Mask is $traceMask") if T(File => 3);
2615                        }
2616                        # Fix the group.
2617                        chown -1, $gid, $thisMem;
2618                        # Insure this member is not a symlink.
2619                        if (! -l $thisMem) {
2620                            # Get its info.
2621                            my $fileInfo = stat $thisMem;
2622                            # Only proceed if we got the info. Otherwise, it's a hard link
2623                            # and we want to skip it anyway.
2624                            if ($fileInfo) {
2625                                my $fileMode = $fileInfo->mode;
2626                                if (($fileMode & $mask) != $mask) {
2627                                    # Fix this member.
2628                                    $fileMode |= $mask;
2629                                    chmod $fileMode, $thisMem;
2630                                    $fixCount++;
2631                                }
2632                                # If it's a subdirectory, stack it.
2633                                if (-d $thisMem) {
2634                                    push @dirs, $thisMem;
2635                                }
2636                            }
2637                        }
2638          }          }
2639      }      }
2640  }  }
2641            Trace("$lookCount files and directories processed, $fixCount fixed.") if T(File => 2);
2642        };
2643        # Check for an error.
2644        if ($@) {
2645            Confess("SetPermissions error: $@");
2646        }
2647    }
2648    
2649  =head3 Trace  =head3 GetLine
2650    
2651  C<< Trace($message); >>      my @data = Tracer::GetLine($handle);
2652    
2653  Write a trace message to the target location specified in L</TSetup>. If there has not been  Read a line of data from a tab-delimited file.
 any prior call to B<TSetup>.  
2654    
2655  =over 4  =over 4
2656    
2657  =item message  =item handle
2658    
2659  Message to write.  Open file handle from which to read.
2660    
2661    =item RETURN
2662    
2663    Returns a list of the fields in the record read. The fields are presumed to be
2664    tab-delimited. If we are at the end of the file, then an empty list will be
2665    returned. If an empty line is read, a single list item consisting of a null
2666    string will be returned.
2667    
2668  =back  =back
2669    
2670  =cut  =cut
2671    
2672  sub Trace {  sub GetLine {
2673      # Get the parameters.      # Get the parameters.
2674      my ($message) = @_;      my ($handle) = @_;
2675      # Get the timestamp.      # Declare the return variable.
2676      my $timeStamp = Now();      my @retVal = ();
2677      # Format the message. Note we strip off any line terminators at the end.      Trace("File position is " . tell($handle) . ". EOF flag is " . eof($handle) . ".") if T(File => 4);
2678      my $formatted = "$timeStamp <$LastCategory>: " . Strip($message);      # Read from the file.
2679      # Process according to the destination.      my $line = <$handle>;
2680      if ($Destination eq "TEXT") {      # Only proceed if we found something.
2681          # Write the message to the standard output.      if (defined $line) {
2682          print "$formatted\n";          # Remove the new-line. We are a bit over-cautious here because the file may be coming in via an
2683      } elsif ($Destination eq "ERROR") {          # upload control and have a nonstandard EOL combination.
2684          # Write the message to the error output.          $line =~ s/(\r|\n)+$//;
2685          print STDERR "$formatted\n";          # Here we do some fancy tracing to help in debugging complicated EOL marks.
2686      } elsif ($Destination eq "QUEUE") {          if (T(File => 4)) {
2687          # Push the message into the queue.              my $escapedLine = $line;
2688          push @Queue, "$formatted";              $escapedLine =~ s/\n/\\n/g;
2689      } elsif ($Destination eq "HTML") {              $escapedLine =~ s/\r/\\r/g;
2690          # Convert the message to HTML and write it to the standard output.              $escapedLine =~ s/\t/\\t/g;
2691          my $escapedMessage = CGI::escapeHTML($message);              Trace("Line read: -->$escapedLine<--");
2692          print "<p>$formatted</p>\n";          }
2693      } elsif ($Destination eq "WARN") {          # If the line is empty, return a single empty string; otherwise, parse
2694         # Emit the message as a warning.          # it into fields.
2695         warn $message;          if ($line eq "") {
2696      } elsif ($Destination =~ m/^>>/) {              push @retVal, "";
2697          # Write the trace message to an output file.          } else {
2698          (open TRACING, $Destination) || die "Tracing open for \"$Destination\" failed: $!";              push @retVal, split /\t/,$line;
         print TRACING "$formatted\n";  
         close TRACING;  
         # If the Tee flag is on, echo it to the standard output.  
         if ($TeeFlag) {  
             print "$formatted\n";  
2699          }          }
2700        } else {
2701            # Trace the reason the read failed.
2702            Trace("End of file: $!") if T(File => 3);
2703      }      }
2704        # Return the result.
2705        return @retVal;
2706  }  }
2707    
2708  =head3 T  =head3 PutLine
   
 C<< my $switch = T($category, $traceLevel); >>  
   
     or  
2709    
2710  C<< my $switch = T($traceLevel); >>      Tracer::PutLine($handle, \@fields, $eol);
2711    
2712  Return TRUE if the trace level is at or above a specified value and the specified category  Write a line of data to a tab-delimited file. The specified field values will be
2713  is active, else FALSE. If no category is specified, the caller's package name is used.  output in tab-separated form, with a trailing new-line.
2714    
2715  =over 4  =over 4
2716    
2717  =item category  =item handle
2718    
2719  Category to which the message belongs. If not specified, the caller's package name is  Output file handle.
 used.  
2720    
2721  =item traceLevel  =item fields
2722    
2723  Relevant tracing level.  List of field values.
2724    
2725  =item RETURN  =item eol (optional)
2726    
2727  TRUE if a message at the specified trace level would appear in the trace, else FALSE.  End-of-line character (default is "\n").
2728    
2729  =back  =back
2730    
2731  =cut  =cut
2732    
2733  sub T {  sub PutLine {
     # Declare the return variable.  
     my $retVal = 0;  
     # Only proceed if tracing is turned on.  
     if ($Destination ne "NONE") {  
2734          # Get the parameters.          # Get the parameters.
2735          my ($category, $traceLevel) = @_;      my ($handle, $fields, $eol) = @_;
2736          if (!defined $traceLevel) {      # Write the data.
2737              # Here we have no category, so we need to get the calling package.      print $handle join("\t", @{$fields}) . ($eol || "\n");
             # The calling package is normally the first parameter. If it is  
             # omitted, the first parameter will be the tracelevel. So, the  
             # first thing we do is shift the so-called category into the  
             # $traceLevel variable where it belongs.  
             $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}));  
2738      }      }
2739      # Return the computed result.  
2740      return $retVal;  
2741    =head3 PrintLine
2742    
2743        Tracer::PrintLine($line);
2744    
2745    Print a line of text with a trailing new-line.
2746    
2747    =over 4
2748    
2749    =item line
2750    
2751    Line of text to print.
2752    
2753    =back
2754    
2755    =cut
2756    
2757    sub PrintLine {
2758        # Get the parameters.
2759        my ($line) = @_;
2760        # Print the line.
2761        print "$line\n";
2762  }  }
2763    
 =head3 ParseCommand  
2764    
2765  C<< my ($options, @arguments) = Tracer::ParseCommand(\%optionTable, @inputList); >>  =head2 Other Useful Methods
2766    
2767  Parse a command line consisting of a list of parameters. The initial parameters may be option  =head3 ParseParm
 specifiers of the form C<->I<option> or C<->I<option>C<=>I<value>. The options are stripped  
 off and merged into a table of default options. The remainder of the command line is  
 returned as a list of positional arguments. For example, consider the following invocation.  
2768    
2769  C<< my ($options, @arguments) = ParseCommand({ errors => 0, logFile => 'trace.log'}, @words); >>      my $listValue = Tracer::ParseParm($string);
2770    
2771  In this case, the list @words will be treated as a command line. There are two options available,  Convert a parameter into a list reference. If the parameter is undefined,
2772  B<errors> and B<logFile>. If @words has the following format  an undefined value will be returned. Otherwise, it will be parsed as a
2773    comma-separated list of values.
2774    
2775  C<< -logFile=error.log apple orange rutabaga >>  =over 4
2776    
2777  then at the end of the invocation, C<$options> will be  =item string
2778    
2779  C<< { errors => 0, logFile => 'error.log' } >>  Incoming string.
2780    
2781  and C<@arguments> will contain  =item RETURN
2782    
2783  C<< apple orange rutabaga >>  Returns a reference to a list of values, or C<undef> if the incoming value
2784    was undefined.
2785    
2786  The parser allows for some escape sequences. See L</UnEscape> for a description. There is no  =back
 support for quote characters.  
2787    
2788  =over 4  =cut
2789    
2790  =item optionTable  sub ParseParm {
2791        # Get the parameters.
2792        my ($string) = @_;
2793        # Declare the return variable.
2794        my $retVal;
2795        # Check for data.
2796        if (defined $string) {
2797            # We have some, so split it into a list.
2798            $retVal = [ split /\s*,\s*/, $string];
2799        }
2800        # Return the result.
2801        return $retVal;
2802    }
2803    
2804  Table of default options.  =head3 Now
2805    
2806  =item inputList      my $string = Tracer::Now();
2807    
2808  List of words on the command line.  Return a displayable time stamp containing the local time. Whatever format this
2809    method produces must be parseable by L</ParseDate>.
2810    
2811    =cut
2812    
2813    sub Now {
2814        return DisplayTime(time);
2815    }
2816    
2817    =head3 DisplayTime
2818    
2819        my $string = Tracer::DisplayTime($time);
2820    
2821    Convert a time value to a displayable time stamp. Whatever format this
2822    method produces must be parseable by L</ParseDate>.
2823    
2824    =over 4
2825    
2826    =item time
2827    
2828    Time to display, in seconds since the epoch, or C<undef> if the time is unknown.
2829    
2830  =item RETURN  =item RETURN
2831    
2832  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.
2833    
2834  =back  =back
2835    
2836  =cut  =cut
2837    
2838  sub ParseCommand {  sub DisplayTime {
2839      # Get the parameters.      my ($time) = @_;
2840      my ($optionTable, @inputList) = @_;      my $retVal = "(n/a)";
2841      # Process any options in the input list.      if (defined $time) {
2842      my %overrides = ();          my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($time);
2843      while ((@inputList > 0) && ($inputList[0] =~ /^-/)) {          $retVal = _p2($mon+1) . "/" . _p2($mday) . "/" . ($year + 1900) . " " .
2844          # 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;  
         }  
2845      }      }
2846      # Merge the options into the defaults.      return $retVal;
     GetOptions($optionTable, \%overrides);  
     # Translate the remaining parameters.  
     my @retVal = ();  
     for my $inputParm (@inputList) {  
         push @retVal, UnEscape($inputParm);  
2847      }      }
2848      # Return the results.  
2849      return ($optionTable, @retVal);  # Pad a number to 2 digits.
2850    sub _p2 {
2851        my ($value) = @_;
2852        $value = "0$value" if ($value < 10);
2853        return $value;
2854  }  }
2855    
2856  =head3 Escape  =head3 Escape
2857    
2858  C<< my $codedString = Tracer::Escape($realString); >>      my $codedString = Tracer::Escape($realString);
2859    
2860  Escape a string for use in a command length. Spaces will be replaced by C<\b>,  Escape a string for use in a command. Tabs will be replaced by C<\t>, new-lines
2861  tabs replaced by C<\t>, new-lines replaced by C<\n>, and backslashes will be  replaced by C<\n>, carriage returns will be deleted, and backslashes will be doubled. The
2862  doubled. The effect is to exactly reverse the effect of L</UnEscape>.  result is to reverse the effect of L</UnEscape>.
2863    
2864  =over 4  =over 4
2865    
# Line 850  Line 2883 
2883      # Loop through the parameter string, looking for sequences to escape.      # Loop through the parameter string, looking for sequences to escape.
2884      while (length $realString > 0) {      while (length $realString > 0) {
2885          # Look for the first sequence to escape.          # Look for the first sequence to escape.
2886          if ($realString =~ /^(.*?)([ \n\t\\])/) {          if ($realString =~ /^(.*?)([\n\t\r\\])/) {
2887              # 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
2888              # 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.
2889              $retVal .= $1;              $retVal .= $1;
2890              # Strip the processed section off the real string.              # Strip the processed section off the real string.
2891              $realString = substr $realString, (length $2) + (length $1);              $realString = substr $realString, (length $2) + (length $1);
2892              # Encode the escape sequence.              # Get the matched character.
2893              my $char = $2;              my $char = $2;
2894              $char =~ tr/ \t\n/btn/;              # If we have a CR, we are done.
2895                if ($char ne "\r") {
2896                    # It's not a CR, so encode the escape sequence.
2897                    $char =~ tr/\t\n/tn/;
2898              $retVal .= "\\" . $char;              $retVal .= "\\" . $char;
2899                }
2900          } else {          } else {
2901              # 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
2902              # transferred unmodified.              # transferred unmodified.
# Line 873  Line 2910 
2910    
2911  =head3 UnEscape  =head3 UnEscape
2912    
2913  C<< my $realString = Tracer::UnEscape($codedString); >>      my $realString = Tracer::UnEscape($codedString);
2914    
2915  Replace escape sequences with their actual equivalents. C<\b> will be replaced by a space,  Replace escape sequences with their actual equivalents. C<\t> will be replaced by
2916  C<\t> by a tab, C<\n> by a new-line character, and C<\\> by a back-slash.  a tab, C<\n> by a new-line character, and C<\\> by a backslash. C<\r> codes will
2917    be deleted.
2918    
2919  =over 4  =over 4
2920    
# Line 896  Line 2934 
2934  sub UnEscape {  sub UnEscape {
2935      # Get the parameter.      # Get the parameter.
2936      my ($codedString) = @_;      my ($codedString) = @_;
     Tracer("Coded string is \"$codedString\".") if T(4);  
2937      # Initialize the return variable.      # Initialize the return variable.
2938      my $retVal = "";      my $retVal = "";
2939      # Only proceed if the incoming string is nonempty.      # Only proceed if the incoming string is nonempty.
2940      if (defined $codedString) {      if (defined $codedString) {
2941          # Loop through the parameter string, looking for escape sequences. We can't do          # Loop through the parameter string, looking for escape sequences. We can't do
2942          # translating because it causes problems with the escaped slash. ("\\b" becomes          # translating because it causes problems with the escaped slash. ("\\t" becomes
2943          # "\ " no matter what we do.)          # "\<tab>" no matter what we do.)
2944          while (length $codedString > 0) {          while (length $codedString > 0) {
2945              # Look for the first escape sequence.              # Look for the first escape sequence.
2946              if ($codedString =~ /^(.*?)\\(\\|b|n|t)/) {              if ($codedString =~ /^(.*?)\\(\\|n|t|r)/) {
2947                  # 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
2948                  # 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.
2949                  $retVal .= $1;                  $retVal .= $1;
2950                  $codedString = substr $codedString, (2 + length $1);                  $codedString = substr $codedString, (2 + length $1);
2951                  # Decode the escape sequence.                  # Get the escape value.
2952                  my $char = $2;                  my $char = $2;
2953                  $char =~ tr/\\btn/\\ \t\n/;                  # If we have a "\r", we are done.
2954                    if ($char ne 'r') {
2955                        # Here it's not an 'r', so we convert it.
2956                        $char =~ tr/\\tn/\\\t\n/;
2957                  $retVal .= $char;                  $retVal .= $char;
2958                    }
2959              } else {              } else {
2960                  # 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
2961                  # transferred unmodified.                  # transferred unmodified.
# Line 923  Line 2964 
2964              }              }
2965          }          }
2966      }      }
2967      # Return the result.      # Return the result.
     return $retVal;  
 }  
   
 =head3 ParseRecord  
   
 C<< my @fields = Tracer::ParseRecord($line); >>  
   
 Parse a tab-delimited data line. The data line is split into field values. Embedded tab  
 and new-line characters in the data line must be represented as C<\t> and C<\n>, respectively.  
 These will automatically be converted.  
   
 =over 4  
   
 =item line  
   
 Line of data containing the tab-delimited fields.  
   
 =item RETURN  
   
 Returns a list of the fields found in the data line.  
   
 =back  
   
 =cut  
   
 sub ParseRecord {  
     # Get the parameter.  
     my ($line) = @_;  
     # Remove the trailing new-line, if any.  
     chomp $line;  
     # Split the line read into pieces using the tab character.  
     my @retVal = split /\t/, $line;  
     # Trim and fix the escapes in each piece.  
     for my $value (@retVal) {  
         # Trim leading whitespace.  
         $value =~ s/^\s+//;  
         # Trim trailing whitespace.  
         $value =~ s/\s+$//;  
         # Delete the carriage returns.  
         $value =~ s/\r//g;  
         # Convert the escapes into their real values.  
         $value =~ s/\\t/"\t"/ge;  
         $value =~ s/\\n/"\n"/ge;  
     }  
     # Return the result.  
     return @retVal;  
 }  
   
 =head3 Merge  
   
 C<< my @mergedList = Tracer::Merge(@inputList); >>  
   
 Sort a list of strings and remove duplicates.  
   
 =over 4  
   
 =item inputList  
   
 List of scalars to sort and merge.  
   
 =item RETURN  
   
 Returns a list containing the same elements sorted in ascending order with duplicates  
 removed.  
   
 =back  
   
 =cut  
   
 sub Merge {  
     # Get the input list in sort order.  
     my @inputList = sort @_;  
     # Only proceed if the list has at least two elements.  
     if (@inputList > 1) {  
         # Now we want to move through the list splicing out duplicates.  
         my $i = 0;  
         while ($i < @inputList) {  
             # Get the current entry.  
             my $thisEntry = $inputList[$i];  
             # Find out how many elements duplicate the current entry.  
             my $j = $i + 1;  
             my $dup1 = $i + 1;  
             while ($j < @inputList && $inputList[$j] eq $thisEntry) { $j++; };  
             # If the number is nonzero, splice out the duplicates found.  
             if ($j > $dup1) {  
                 splice @inputList, $dup1, $j - $dup1;  
             }  
             # Now the element at position $dup1 is different from the element before it  
             # at position $i. We push $i forward one position and start again.  
             $i++;  
         }  
     }  
     # Return the merged list.  
     return @inputList;  
 }  
   
 =head3 GetFile  
   
 C<< my @fileContents = Tracer::GetFile($fileName); >>  
   
 Return the entire contents of a file.  
   
 =over 4  
   
 =item fileName  
   
 Name of the file to read.  
   
 =item RETURN  
   
 In a list context, returns the entire file as a list with the line terminators removed.  
 In a scalar context, returns the entire file as a string.  
   
 =back  
   
 =cut  
   
 sub GetFile {  
     # Get the parameters.  
     my ($fileName) = @_;  
     # Declare the return variable.  
     my @retVal = ();  
     # Open the file for input.  
     my $ok = open INPUTFILE, "<$fileName";  
     if (!$ok) {  
         # If we had an error, trace it. We will automatically return a null value.  
         Trace("Could not open \"$fileName\" for input: $!") if T(0);  
     } else {  
         # Read the whole file into the return variable, stripping off any terminator  
         # characters.  
         my $lineCount = 0;  
         while (my $line = <INPUTFILE>) {  
             $lineCount++;  
             $line = Strip($line);  
             push @retVal, $line;  
         }  
         # Close it.  
         close INPUTFILE;  
         my $actualLines = @retVal;  
     }  
     # Return the file's contents in the desired format.  
     if (wantarray) {  
         return @retVal;  
     } else {  
         return join "\n", @retVal;  
     }  
 }  
   
 =head3 QTrace  
   
 C<< my $data = QTrace($format); >>  
   
 Return the queued trace data in the specified format.  
   
 =over 4  
   
 =item format  
   
 C<html> to format the data as an HTML list, C<text> to format it as straight text.  
   
 =back  
   
 =cut  
   
 sub QTrace {  
     # Get the parameter.  
     my ($format) = @_;  
     # Create the return variable.  
     my $retVal = "";  
     # Only proceed if there is an actual queue.  
     if (@Queue) {  
         # Process according to the format.  
         if ($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 = ();  
     }  
     # Return the formatted list.  
2968      return $retVal;      return $retVal;
2969  }  }
2970    
2971  =head3 Confess  =head3 Percent
2972    
2973  C<< Confess($message); >>      my $percent = Tracer::Percent($number, $base);
2974    
2975  Trace the call stack and abort the program with the specified message. When used with  Returns the percent of the base represented by the given number. If the base
2976  the OR operator and the L</Assert> method, B<Confess> can function as a debugging assert.  is zero, returns zero.
 So, for example  
2977    
2978  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>  =over 4
2979    
2980  Will abort the program with a stack trace if the value of C<$recNum> is negative.  =item number
2981    
2982  =over 4  Percent numerator.
2983    
2984  =item message  =item base
2985    
2986  Message to include in the trace.  Percent base.
2987    
2988    =item RETURN
2989    
2990    Returns the percentage of the base represented by the numerator.
2991    
2992  =back  =back
2993    
2994  =cut  =cut
2995    
2996  sub Confess {  sub Percent {
2997      # Get the parameters.      # Get the parameters.
2998      my ($message) = @_;      my ($number, $base) = @_;
2999      # Trace the call stack.      # Declare the return variable.
3000      Cluck($message);      my $retVal = 0;
3001      # Abort the program.      # Compute the percent.
3002      croak(">>> $message");      if ($base != 0) {
3003            $retVal = $number * 100 / $base;
3004        }
3005        # Return the result.
3006        return $retVal;
3007  }  }
3008    
3009  =head3 Assert  =head3 Constrain
   
 C<< Assert($condition1, $condition2, ... $conditionN); >>  
   
 Return TRUE if all the conditions are true. This method can be used in conjunction with  
 the OR operator and the L</Confess> method, B<Assert> can function as a debugging assert.  
 So, for example  
3010    
3011  C<< Assert($recNum >= 0) || Confess("Invalid record number $recNum."); >>      my $constrained = Constrain($value, $min, $max);
3012    
3013  Will abort the program with a stack trace if the value of C<$recNum> is negative.  Modify a numeric value to bring it to a point in between a maximum and a minimum.
3014    
3015  =cut  =over 4
 sub Assert {  
     my $retVal = 1;  
     LOOP: for my $condition (@_) {  
         if (! $condition) {  
             $retVal = 0;  
             last LOOP;  
         }  
     }  
     return $retVal;  
 }  
3016    
3017  =head3 Cluck  =item value
3018    
3019  C<< Cluck($message); >>  Value to constrain.
3020    
3021  Trace the call stack. Note that for best results, you should qualify the call with a  =item min (optional)
 trace condition. For example,  
3022    
3023  C<< Cluck("Starting record parse.") if T(3); >>  Minimum permissible value. If this parameter is undefined, no minimum constraint will be applied.
3024    
3025  will only trace the stack if the trace level for the package is 3 or more.  =item max (optional)
3026    
3027  =over 4  Maximum permissible value. If this parameter is undefined, no maximum constraint will be applied.
3028    
3029  =item message  =item RETURN
3030    
3031  Message to include in the trace.  Returns the incoming value, constrained according to the other parameters.
3032    
3033  =back  =back
3034    
3035  =cut  =cut
3036    
3037  sub Cluck {  sub Constrain {
3038      # Get the parameters.      # Get the parameters.
3039      my ($message) = @_;      my ($value, $min, $max) = @_;
3040      # Trace what's happening.      # Declare the return variable.
3041      Trace("Stack trace for event: $message");      my $retVal = $value;
3042      my $confession = longmess($message);      # Apply the minimum constraint.
3043      # Convert the confession to a series of trace messages. Note we skip any      if (defined $min && $retVal < $min) {
3044      # messages relating to calls into Tracer.          $retVal = $min;
3045      for my $line (split /\s*\n/, $confession) {      }
3046          Trace($line) if ($line !~ /Tracer\.pm/);      # Apply the maximum constraint.
3047        if (defined $max && $retVal > $max) {
3048            $retVal = $max;
3049      }      }
3050        # Return the result.
3051        return $retVal;
3052  }  }
3053    
3054  =head3 Min  =head3 Min
3055    
3056  C<< my $min = Min($value1, $value2, ... $valueN); >>      my $min = Min($value1, $value2, ... $valueN);
3057    
3058  Return the minimum argument. The arguments are treated as numbers.  Return the minimum argument. The arguments are treated as numbers.
3059    
# Line 1239  Line 3086 
3086    
3087  =head3 Max  =head3 Max
3088    
3089  C<< my $max = Max($value1, $value2, ... $valueN); >>      my $max = Max($value1, $value2, ... $valueN);
3090    
3091  Return the maximum argument. The arguments are treated as numbers.  Return the maximum argument. The arguments are treated as numbers.
3092    
# Line 1270  Line 3117 
3117      return $retVal;      return $retVal;
3118  }  }
3119    
 =head3 AddToListMap  
   
 C<< Tracer::AddToListMap(\%hash, $key, $value); >>  
   
 Add a key-value pair to a hash of lists. If no value exists for the key, a singleton list  
 is created for the key. Otherwise, the new value is pushed onto the list.  
   
 =over 4  
   
 =item hash  
   
 Reference to the target hash.  
   
 =item key  
   
 Key for which the value is to be added.  
   
 =item value  
   
 Value to add to the key's value list.  
   
 =back  
   
 =cut  
   
 sub AddToListMap {  
     # Get the parameters.  
     my ($hash, $key, $value) = @_;  
     # Process according to whether or not the key already has a value.  
     if (! exists $hash->{$key}) {  
         $hash->{$key} = [$value];  
     } else {  
         push @{$hash->{$key}}, $value;  
     }  
 }  
   
 =head3 DebugMode  
   
 C<< if (Tracer::DebugMode) { ...code... } >>  
   
 Return TRUE if debug mode has been turned on, else output an error  
 page and return FALSE.  
   
 Certain CGI scripts are too dangerous to exist in the production  
 environment. This method provides a simple way to prevent them  
 from working unless they are explicitly turned on by creating a password  
 cookie via the B<SetPassword> script.  If debugging mode  
 is not turned on, an error web page will be output directing the  
 user to enter in the correct password.  
   
 =cut  
   
 sub DebugMode {  
     # Declare the return variable.  
     my $retVal = 0;  
     # Check the debug configuration.  
     my $password = CGI::cookie("DebugMode");  
     my $encrypted = Digest::MD5::md5_hex($password);  
     if ($encrypted eq "252dec43280e0c0d6a75ffcec486e61d") {  
         $retVal = 1;  
     } else {  
         # Here debug mode is off, so we generate an error page.  
         my $pageString = PageBuilder::Build("<Html/ErrorPage.html", {}, "Html");  
         print $pageString;  
     }  
     # Return the determination indicator.  
     return $retVal;  
 }  
3120    
3121  =head3 Strip  =head3 Strip
3122    
3123  C<< my $string = Tracer::Strip($line); >>      my $string = Tracer::Strip($line);
3124    
3125  Strip all line terminators off a string. This is necessary when dealing with files  Strip all line terminators off a string. This is necessary when dealing with files
3126  that may have been transferred back and forth several times among different  that may have been transferred back and forth several times among different
# Line 1364  Line 3143 
3143  sub Strip {  sub Strip {
3144      # Get a copy of the parameter string.      # Get a copy of the parameter string.
3145      my ($string) = @_;      my ($string) = @_;
3146      my $retVal = $string;      my $retVal = (defined $string ? $string : "");
3147      # Strip the line terminator characters.      # Strip the line terminator characters.
3148      $retVal =~ s/(\r|\n)+$//g;      $retVal =~ s/(\r|\n)+$//g;
3149      # Return the result.      # Return the result.
# Line 1373  Line 3152 
3152    
3153  =head3 Pad  =head3 Pad
3154    
3155  C<< my $paddedString = Tracer::Pad($string, $len, $left, $padChar); >>      my $paddedString = Tracer::Pad($string, $len, $left, $padChar);
3156    
3157  Pad a string to a specified length. The pad character will be a  Pad a string to a specified length. The pad character will be a
3158  space, and the padding will be on the right side unless specified  space, and the padding will be on the right side unless specified
# Line 1432  Line 3211 
3211      return $retVal;      return $retVal;
3212  }  }
3213    
3214    =head3 EOF
3215    
3216    This is a constant that is lexically greater than any useful string.
3217    
3218    =cut
3219    
3220    sub EOF {
3221        return "\xFF\xFF\xFF\xFF\xFF";
3222    }
3223    
3224  =head3 TICK  =head3 TICK
3225    
3226  C<< my @results = TICK($commandString); >>      my @results = TICK($commandString);
3227    
3228  Perform a back-tick operation on a command. If this is a Windows environment, any leading  Perform a back-tick operation on a command. If this is a Windows environment, any leading
3229  dot-slash (C<./> will be removed. So, for example, if you were doing  dot-slash (C<./> will be removed. So, for example, if you were doing
# Line 1473  Line 3262 
3262      return `$commandString`;      return `$commandString`;
3263  }  }
3264    
3265    
3266    =head3 CommaFormat
3267    
3268        my $formatted = Tracer::CommaFormat($number);
3269    
3270    Insert commas into a number.
3271    
3272    =over 4
3273    
3274    =item number
3275    
3276    A sequence of digits.
3277    
3278    =item RETURN
3279    
3280    Returns the same digits with commas strategically inserted.
3281    
3282    =back
3283    
3284    =cut
3285    
3286    sub CommaFormat {
3287        # Get the parameters.
3288        my ($number) = @_;
3289        # Pad the length up to a multiple of three.
3290        my $padded = "$number";
3291        $padded = " " . $padded while length($padded) % 3 != 0;
3292        # This is a fancy PERL trick. The parentheses in the SPLIT pattern
3293        # cause the delimiters to be included in the output stream. The
3294        # GREP removes the empty strings in between the delimiters.
3295        my $retVal = join(",", grep { $_ ne '' } split(/(...)/, $padded));
3296        # Clean out the spaces.
3297        $retVal =~ s/ //g;
3298        # Return the result.
3299        return $retVal;
3300    }
3301    
3302    
3303    =head3 CompareLists
3304    
3305        my ($inserted, $deleted) = Tracer::CompareLists(\@newList, \@oldList, $keyIndex);
3306    
3307    Compare two lists of tuples, and return a hash analyzing the differences. The lists
3308    are presumed to be sorted alphabetically by the value in the $keyIndex column.
3309    The return value contains a list of items that are only in the new list
3310    (inserted) and only in the old list (deleted).
3311    
3312    =over 4
3313    
3314    =item newList
3315    
3316    Reference to a list of new tuples.
3317    
3318    =item oldList
3319    
3320    Reference to a list of old tuples.
3321    
3322    =item keyIndex (optional)
3323    
3324    Index into each tuple of its key field. The default is 0.
3325    
3326    =item RETURN
3327    
3328    Returns a 2-tuple consisting of a reference to the list of items that are only in the new
3329    list (inserted) followed by a reference to the list of items that are only in the old
3330    list (deleted).
3331    
3332    =back
3333    
3334    =cut
3335    
3336    sub CompareLists {
3337        # Get the parameters.
3338        my ($newList, $oldList, $keyIndex) = @_;
3339        if (! defined $keyIndex) {
3340            $keyIndex = 0;
3341        }
3342        # Declare the return variables.
3343        my ($inserted, $deleted) = ([], []);
3344        # Loop through the two lists simultaneously.
3345        my ($newI, $oldI) = (0, 0);
3346        my ($newN, $oldN) = (scalar @{$newList}, scalar @{$oldList});
3347        while ($newI < $newN || $oldI < $oldN) {
3348            # Get the current object in each list. Note that if one
3349            # of the lists is past the end, we'll get undef.
3350            my $newItem = $newList->[$newI];
3351            my $oldItem = $oldList->[$oldI];
3352            if (! defined($newItem) || defined($oldItem) && $newItem->[$keyIndex] gt $oldItem->[$keyIndex]) {
3353                # The old item is not in the new list, so mark it deleted.
3354                push @{$deleted}, $oldItem;
3355                $oldI++;
3356            } elsif (! defined($oldItem) || $oldItem->[$keyIndex] gt $newItem->[$keyIndex]) {
3357                # The new item is not in the old list, so mark it inserted.
3358                push @{$inserted}, $newItem;
3359                $newI++;
3360            } else {
3361                # The item is in both lists, so push forward.
3362                $oldI++;
3363                $newI++;
3364            }
3365        }
3366        # Return the result.
3367        return ($inserted, $deleted);
3368    }
3369    
3370    =head3 GenerateURL
3371    
3372        my $queryUrl = Tracer::GenerateURL($page, %parameters);
3373    
3374    Generate a GET-style URL for the specified page with the specified parameter
3375    names and values. The values will be URL-escaped automatically. So, for
3376    example
3377    
3378        Tracer::GenerateURL("form.cgi", type => 1, string => "\"high pass\" or highway")
3379    
3380    would return
3381    
3382        form.cgi?type=1;string=%22high%20pass%22%20or%20highway
3383    
3384    =over 4
3385    
3386    =item page
3387    
3388    Page URL.
3389    
3390    =item parameters
3391    
3392    Hash mapping parameter names to parameter values.
3393    
3394    =item RETURN
3395    
3396    Returns a GET-style URL that goes to the specified page and passes in the
3397    specified parameters and values.
3398    
3399    =back
3400    
3401    =cut
3402    
3403    sub GenerateURL {
3404        # Get the parameters.
3405        my ($page, %parameters) = @_;
3406        # Prime the return variable with the page URL.
3407        my $retVal = $page;
3408        # Loop through the parameters, creating parameter elements in a list.
3409        my @parmList = map { "$_=" . uri_escape($parameters{$_}) } keys %parameters;
3410        # If the list is nonempty, tack it on.
3411        if (@parmList) {
3412            $retVal .= "?" . join(";", @parmList);
3413        }
3414        # Return the result.
3415        return $retVal;
3416    }
3417    
3418    =head3 ApplyURL
3419    
3420        Tracer::ApplyURL($table, $target, $url);
3421    
3422    Run through a two-dimensional table (or more accurately, a list of lists), converting the
3423    I<$target> column to HTML text having a hyperlink to a URL in the I<$url> column. The
3424    URL column will be deleted by this process and the target column will be HTML-escaped.
3425    
3426    This provides a simple way to process the results of a database query into something
3427    displayable by combining a URL with text.
3428    
3429    =over 4
3430    
3431    =item table
3432    
3433    Reference to a list of lists. The elements in the containing list will be updated by
3434    this method.
3435    
3436    =item target
3437    
3438    The index of the column to be converted into HTML.
3439    
3440    =item url
3441    
3442    The index of the column containing the URL. Note that the URL must have a recognizable
3443    C<http:> at the beginning.
3444    
3445    =back
3446    
3447    =cut
3448    
3449    sub ApplyURL {
3450        # Get the parameters.
3451        my ($table, $target, $url) = @_;
3452        # Loop through the table.
3453        for my $row (@{$table}) {
3454            # Apply the URL to the target cell.
3455            $row->[$target] = CombineURL($row->[$target], $row->[$url]);
3456            # Delete the URL from the row.
3457            delete $row->[$url];
3458        }
3459    }
3460    
3461    =head3 CombineURL
3462    
3463        my $combinedHtml = Tracer::CombineURL($text, $url);
3464    
3465    This method will convert the specified text into HTML hyperlinked to the specified
3466    URL. The hyperlinking will only take place if the URL looks legitimate: that is, it
3467    is defined and begins with an C<http:> header.
3468    
3469    =over 4
3470    
3471    =item text
3472    
3473    Text to return. This will be HTML-escaped automatically.
3474    
3475    =item url
3476    
3477    A URL to be hyperlinked to the text. If it does not look like a URL, then the text
3478    will be returned without any hyperlinking.
3479    
3480    =item RETURN
3481    
3482    Returns the original text, HTML-escaped, with the URL hyperlinked to it. If the URL
3483    doesn't look right, the HTML-escaped text will be returned without any further
3484    modification.
3485    
3486    =back
3487    
3488    =cut
3489    
3490    sub CombineURL {
3491        # Get the parameters.
3492        my ($text, $url) = @_;
3493        # Declare the return variable.
3494        my $retVal = CGI::escapeHTML($text);
3495        # Verify the URL.
3496        if (defined($url) && $url =~ m!http://!i) {
3497            # It's good, so we apply it to the text.
3498            $retVal = "<a href=\"$url\">$retVal</a>";
3499        }
3500        # Return the result.
3501        return $retVal;
3502    }
3503    
3504    =head3 Cmp
3505    
3506        my $cmp = Tracer::Cmp($a, $b);
3507    
3508    This method performs a universal sort comparison. Each value coming in is
3509    separated into a leading text part and a trailing number part. The text
3510    part is string compared, and if both parts are equal, then the number
3511    parts are compared numerically. A stream of just numbers or a stream of
3512    just strings will sort correctly, and a mixed stream will sort with the
3513    numbers first. Strings with a label and a number will sort in the
3514    expected manner instead of lexically.
3515    
3516    =over 4
3517    
3518    =item a
3519    
3520    First item to compare.
3521    
3522    =item b
3523    
3524    Second item to compare.
3525    
3526    =item RETURN
3527    
3528    Returns a negative number if the first item should sort first (is less), a positive
3529    number if the first item should sort second (is greater), and a zero if the items are
3530    equal.
3531    
3532    =back
3533    
3534    =cut
3535    
3536    sub Cmp {
3537        # Get the parameters.
3538        my ($a, $b) = @_;
3539        # Declare the return value.
3540        my $retVal;
3541        # Check for nulls.
3542        if (! defined($a)) {
3543            $retVal = (! defined($b) ? 0 : -1);
3544        } elsif (! defined($b)) {
3545            $retVal = 1;
3546        } else {
3547            # Here we have two real values. Parse the two strings.
3548            $a =~ /^(\D*)(\d*)$/;
3549            my $aParsed = [$1, $2];
3550            $b =~ /^(\D*)(\d*)$/;
3551            my $bParsed = [$1, $2];
3552            # Compare the string parts.
3553            $retVal = $aParsed->[0] cmp $bParsed->[0];
3554            if (! $retVal) {
3555                $retVal = $aParsed->[1] <=> $bParsed->[1];
3556            }
3557        }
3558        # Return the result.
3559        return $retVal;
3560    }
3561    
3562    
3563    =head3 TrackingCode
3564    
3565        my $html = Tracer::TrackingCode();
3566    
3567    Returns the HTML code for doing web page traffic monitoring. If the
3568    current environment is a test system, then it returns a null string;
3569    otherwise, it returns a bunch of javascript containing code for turning
3570    on SiteMeter and Google Analytics.
3571    
3572    =cut
3573    
3574    sub TrackingCode {
3575        # Declare the return variable.
3576        my $retVal = "<!-- tracking off -->";
3577        # Determine if we're in production.
3578        if ($FIG_Config::site_meter) {
3579            $retVal = <<END_HTML
3580            <!-- Site Meter -->
3581            <script type="text/javascript" src="http://s20.sitemeter.com/js/counter.js?site=s20nmpdr">
3582            </script>
3583            <noscript>
3584            <a href="http://s20.sitemeter.com/stats.asp?site=s20nmpdr" target="_top">
3585            <img src="http://s20.sitemeter.com/meter.asp?site=s20nmpdr" alt="Site Meter" border="0"/></a>
3586            </noscript>
3587            <!-- Copyright (c)2006 Site Meter -->
3588    END_HTML
3589        }
3590        return $retVal;
3591    }
3592    
3593    
3594  1;  1;

Legend:
Removed from v.1.23  
changed lines
  Added in v.1.99

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3