svn commit - mysqldoc@docsrva: r6587 - in trunk: make.d tools

[mcbrown]

Author: mcbrown
Date: 2007-05-26 22:14:31 +0200 (Sat, 26 May 2007)
New Revision: 6587

Log:
Updating word count tool to support word counts by section (un-ignored only)
Updates to the makefile so that we count prepped files
New rule for doing a word count with results by section: 

make file.wcs




Modified:
   trunk/make.d/xml-format
   trunk/tools/xml-word-count.pl


Modified: trunk/make.d/xml-format
===================================================================
--- trunk/make.d/xml-format	2007-05-26 19:42:22 UTC (rev 6586)
+++ trunk/make.d/xml-format	2007-05-26 20:14:31 UTC (rev 6587)
Changed blocks: 1, Lines Added: 9, Lines Deleted: 5; 939 bytes

@@ -7,13 +7,17 @@
 %.format %.reformat:
 	$(XMLFORMAT) $*.xml
 
-%.wc: 
-	$(XMLWORDCOUNT) $*.xml
+%.wc: %-prepped.xml
+	$(XMLWORDCOUNT) $<
 
-%.wcd: 
-	$(XMLWORDCOUNT) --detailed $*.xml
+%.wcd: %-prepped.xml
+	$(XMLWORDCOUNT) --detailed $< 
 
+%.wcs: %-prepped.xml
+	$(XMLWORDCOUNT) --sectiondetail $< 
+
 help::
 	@echo "make file.format          - put file.xml in standard format"
 	@echo "make file.wc              - counts the words within XML tags"
-	@echo "make file.wcd             - counts the words within XML tags (with tag-by-tag counts"
+	@echo "make file.wcd             - counts the words within XML tags (with tag-by-tag counts)"
+	@echo "make file.wcs             - counts the words within XML tags (with section counts)"


Modified: trunk/tools/xml-word-count.pl
===================================================================
--- trunk/tools/xml-word-count.pl	2007-05-26 19:42:22 UTC (rev 6586)
+++ trunk/tools/xml-word-count.pl	2007-05-26 20:14:31 UTC (rev 6587)
Changed blocks: 8, Lines Added: 46, Lines Deleted: 3; 3028 bytes

@@ -9,6 +9,7 @@
 
 use strict;
 use Getopt::Long;
+use Data::Dumper;
 
 # Standard Tags to be excluded from the word count go here
 

@@ -39,11 +40,12 @@
     /;
 
 
-my ($addexctags,$inctags,$help,$detailed) = ('','',0,0);
+my ($addexctags,$inctags,$help,$detailed,$sectiondetail) = ('','',0,0,0);
 
 GetOptions('exclude=s' => \$addexctags,
            'include=s' => \$inctags,
            'detailed' => \$detailed,
+           'sectiondetail' => \$sectiondetail,
            'help' => \$help);
 
 if ($help)

@@ -134,7 +136,7 @@
 foreach my $file (keys %{$filemap})
 {
     ($filemap->{$file}->{wc},
-     $filemap->{$file}->{iwc}) = gen_stats($file,$detailed);
+     $filemap->{$file}->{iwc}) = gen_stats($file,$detailed,$sectiondetail);
 }
 
 my ($total,$itotal) = (0,0);

@@ -153,7 +155,7 @@
 
 sub gen_stats
 {
-    my ($file,$detailed) = @_;
+    my ($file,$detailed,$sectiondetail) = @_;
 
     my $my_handler = MySQLDocBookStats->new($tagmap);
 

@@ -172,9 +174,21 @@
         printf("%-40s %9s %9d\n", 'Total valid Words: ','',$my_handler->{totalwc});
         printf("%-40s %9s %9d\n", 'Ignored Words: ','',$my_handler->{ignorewc});
     }
+    
+    if ($sectiondetail)
+    {
+        printf("%-60s %9s\n","Section ID","Count");
+        
+        foreach my $id (sort keys %{$my_handler->{idwc}})
+        {
+            printf("%-60s %9d\n",$id,$my_handler->{idwc}->{$id});
+        }
+    }
+
     return ($my_handler->{totalwc},$my_handler->{ignorewc});
 }
 
+
 package MySQLDocBookStats;
 
 sub new

@@ -192,6 +206,9 @@
                   'currtext' => '',
                   'totalwc' => 0,
                   'ignorewc' => 0,
+                  'idmap' => [],
+                  'idwc' => {},
+                  'idcurr' => '',
                   'currtextmap' => [],
               }, $class;
 }

@@ -200,6 +217,20 @@
 {
     my ($self, $element) = @_;
 
+    if (exists($element->{Attributes}->{id}) &&
+        ($element->{Name} =~ m/^(section|chapter)$/i))
+    {
+        if (scalar @{$self->{idmap}} == 0)
+        {
+            push @{$self->{idmap}},$element->{Attributes}->{id};
+        }
+        else
+        {
+            push @{$self->{idmap}},$self->{idcurr};
+        }
+        $self->{idcurr} = $element->{Attributes}->{id};
+    }
+
     $self->{currtext} .= ' ';
     push @{$self->{currtextmap}},$self->{currtext};
     $self->{currtext} = '';

@@ -220,8 +251,20 @@
     else
     {
         $self->{totalwc} += $wc;
+        $self->{idwc}->{$self->{idcurr}} += $wc;
     }
     $self->{currtext} = pop @{$self->{currtextmap}};
+
+    if ($element->{Name} =~ m/^(section|chapter)$/i)
+    {
+        my $old = $self->{idcurr};
+        $self->{idcurr} = pop @{$self->{idmap}} || $self->{idcurr};
+        if ($old ne $self->{idcurr})
+        {
+            $self->{idwc}->{$self->{idcurr}} += $self->{idwc}->{$old};
+        }
+    }
+
 }    
 
 sub characters