File: dbtags.php

package info (click to toggle)
phpdoc 20020310-1
  • links: PTS
  • area: main
  • in suites: woody
  • size: 35,272 kB
  • ctags: 354
  • sloc: xml: 799,767; php: 1,395; cpp: 500; makefile: 200; sh: 140; awk: 51
file content (166 lines) | stat: -rw-r--r-- 4,482 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
#!/usr/bin/php -q
<?php

if ($argc > 2 || in_array($argv[1], array('--help', '-help', '-h', '-?'))) {
?>

Process XML files for used DocBook tags
and give statistics

  Usage:
  <?=$argv[0]?> [<language-code>]

  <language-code> can be a valid language code
  used in the repository, or 'all' for all
  languages. Defaults to en.

  The script will generate a tag_usage.txt
  file, containing the tags used and the numbers.
  
  Written by Gabor Hojtsy <goba@php.net>, 2001-12-28

<?php
  exit;
}

// CONFIG SECTION
$docdir = "../"; // Main directory of the PHP documentation (one dir up in cvs)

/*********************************************************************/
/* Nothing to modify below this line                                 */
/*********************************************************************/

// Long runtime
set_time_limit(0);

// Array to collect the entities
$used_tags = array();

// Default values
$langcodes = array("en");

// Parameter value copying
if ($argc == 2) { 
    $langcodes = array($argv[1]);
    if ($argv[1] === 'all') {
        $langcodes = array("ar", "cs", "de", "en", "es", "fr",
                           "hk", "hu", "it", "ja", "kr", "nl",
                           "pl", "pt_BR", "ru", "tr", "tw");
    }
}

/*********************************************************************/
/* Here starts the functions part                                    */
/*********************************************************************/

// Checks a diretory of phpdoc XML files
function check_dir($dir, &$used_tags)
{
    // Collect files and diretcories in these arrays
    $directories = array();
    $files = array();

    // Open and traverse the directory
    $handle = @opendir($dir);
    while ($file = @readdir($handle)) {

      // Collect directories and XML files
      if ($file != 'CVS' && $file != '.' &&
          $file != '..' && is_dir($dir.$file)) {
        $directories[] = $file;
      }
      elseif (strstr($file, ".xml")) {
        $files[] = $file;
      }

    }
    @closedir($handle);

    // Sort files and directories
    sort($directories);
    sort($files);

    // Files first...
    foreach ($files as $file) {
      check_file($dir.$file, $used_tags);
    }

    // than the subdirs
    foreach ($directories as $file) {
      check_dir($dir.$file."/", $used_tags);
    }
} // check_dir() function end

function check_file ($filename, &$used_tags)
{
    // Read in file contents
    $contents = preg_replace("/[\r\n]/", "", join("", file($filename)));
    
    // Drop out CDATA sections, they do not contain any DocBook tags
    $contents = preg_replace("/<!\\[CDATA\\[.+\\]\\]>/U", "", $contents);
    
    // Drop out comments, they do not contain any DocBook tags
    $contents = preg_replace("/<!--.+-->/U", "", $contents);

    // Find all tags in this file
    preg_match_all("!<([^\\s>/]+)[\\s>]!U", $contents, $tags_found);
    
    // No entities found
    if (count($tags_found[1]) == 0) { return; }
    
    // New occurances found, so increase the number
    foreach ($tags_found[1] as $tag_name) {
        $used_tags[$tag_name]++;
    }

} // check_file() function end
  
/*********************************************************************/
/* Here starts the program                                           */
/*********************************************************************/

// Chechking all languages
foreach ($langcodes as $langcode) {

    // Check for directory validity
    if (!@is_dir($docdir . $langcode)) {
        print("The $langcode language code is not valid\n");
        continue;
    } else {
        $tested_trees[] = $langcode;
    }
      
    // If directory is OK, start with the header
    echo "Searching in $docdir$langcode ...\n";
    
    // Check the requested directory
    check_dir("$docdir$langcode/", $used_tags);

}
    
echo "Generating tag_usage.txt ...\n";
    
$fp = fopen("tag_usage.txt", "w");
fwrite($fp, "TAG USAGE STATISCTICS

=========================================================
In this file you can find tag usage stats compiled
from the following tree[s] at phpdoc:\n" .
join(", ", $tested_trees) . ".

You may find some rarely used tags here, and find out
what tags others use to write documentation.
=========================================================

");

arsort($used_tags);
foreach ($used_tags as $tag_name => $number) {
    fwrite($fp, sprintf("%-30s %d", $tag_name, $number). "\n");
}

fclose($fp);

echo "Done!\n";

?>