shaba/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2.git synced 2025-01-22 22:03:34 +03:00
Code

improved HTML indexing make the queries also lookup the HTML based indexes

Browse Source 
* doc/index.py: improved HTML indexing
* doc/search.php: make the queries also lookup the HTML based indexes
Daniel
This commit is contained in:
Daniel Veillard 2002-10-07 11:13:27 +00:00
parent 141d04ba74
commit 9b00613d05
3 changed files with 71 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ChangeLog
View File

@ -1,3 +1,8 @@
Mon Oct 7 13:12:03 CEST 2002 Daniel Veillard <daniel@veillard.com>
* doc/index.py: improved HTML indexing
* doc/search.php: make the queries also lookup the HTML based indexes
Sun Oct 6 23:50:29 CEST 2002 Daniel Veillard <daniel@veillard.com>
* doc/index.py: added HTML page indexing

25
doc/index.py
View File

@ -717,6 +717,15 @@ def analyzeAPI(doc):
import glob
def analyzeHTMLText(doc, resource, p, section, id):
words = 0
try:
content = p.content
words = words + addStringHTML(content, resource, id, section, 5)
except:
return -1
return words
def analyzeHTMLPara(doc, resource, p, section, id):
words = 0
try:
@ -735,6 +744,15 @@ def analyzeHTMLPre(doc, resource, p, section, id):
return -1
return words
def analyzeHTML(doc, resource, p, section, id):
words = 0
try:
content = p.content
words = words + addStringHTML(content, resource, id, section, 5)
except:
return -1
return words
def analyzeHTML(doc, resource):
para = 0;
ctxt = doc.xpathNewContext()
@ -745,7 +763,7 @@ def analyzeHTML(doc, resource):
title = "Page %s" % (resource)
addPage(resource, title)
try:
items = ctxt.xpathEval("//h1 | //h2 | //h3 | //p | //pre")
items = ctxt.xpathEval("//h1 | //h2 | //h3 | //text()")
section = title
id = ""
for item in items:
@ -755,7 +773,10 @@ def analyzeHTML(doc, resource):
id = item.prop("id")
elif item.prop("name"):
id = item.prop("name")
elif item.name == 'p':
elif item.type == 'text':
analyzeHTMLText(doc, resource, item, section, id)
para = para + 1
elif item.name == 'text':
analyzeHTMLPara(doc, resource, item, section, id)
para = para + 1
elif item.name == 'pre':

53
doc/search.php
View File

@ -135,6 +135,20 @@ simply provide a set of keywords:
}
return array($result, $j);
}
function queryHTMLWord($word) {
$result = NULL;
$j = 0;
if ($word) {
$result = mysql_query ("SELECT relevance, name, id, resource, section FROM wordsHTML WHERE name='$word' ORDER BY relevance DESC");
if ($result) {
$j = mysql_num_rows($result);
if ($j == 0)
mysql_free_result($result);
}
logQueryWord($word);
}
return array($result, $j);
}
function resSort ($a, $b) {
list($ra,$ta,$ma,$na,$da) = $a;
list($rb,$tb,$mb,$nb,$db) = $b;
@ -162,17 +176,39 @@ simply provide a set of keywords:
$module = mysql_result($result, $i, 3);
$desc = mysql_result($result, $i, 4);
if (array_key_exists($name, $results)) {
list($r,$t,$m,$n, $d) = $results[$name];
list($r,$t,$m,$d,$w,$u) = $results[$name];
$results[$name] = array($r + $relevance + 40,
$t,$m,$n,$d);
$t,$m,$d,$w,$u);
} else {
$id = strtoupper($name);
$m = strtolower($module);
$url = "html/libxml-$m.html#$id";
$results[$name] = array($relevance,$type,
$module, $name, $desc);
$module, $desc, $name, $url);
}
}
mysql_free_result($result);
} else {
echo "<p> No symbol found for $word\n";
}
list($result, $k) = queryHTMLWord($word);
if ($k > 0) {
for ($i = 0; $i < $k; $i++) {
$relevance = mysql_result($result, $i, 0);
$name = mysql_result($result, $i, 1);
$id = mysql_result($result, $i, 2);
$module = mysql_result($result, $i, 3);
$desc = mysql_result($result, $i, 4);
$url = $module;
if ($id != "") {
$url = $url + "#$id";
}
$results[$name + "_html_" + $number+ "_" + $i ] =
array($relevance, "documentation",
$module, $desc, $word, $url);
}
mysql_free_result($result);
}
if (($j <= 0) && ($k <= 0)) {
echo "<p> No result found for $word\n";
}
}
mysql_close($link);
@ -184,11 +220,8 @@ simply provide a set of keywords:
printf("<table><tbody>\n");
printf("<tr><td>Quality</td><td>Symbol</td><td>Type</td><td>module</td><td>Description</td></tr>\n");
while (list ($name, $val) = each ($results)) {
list($r,$t,$m,$n,$d) = $val;
$upper = strtoupper($n);
$module = strtolower($m);
$url = "html/libxml-$module.html#$upper";
echo "<tr><td>$r</td><td><a href='$url'>$n</a></td><td>$t</td><td>$m</td><td>$d</td></tr>";
list($r,$t,$m,$d,$s,$u) = $val;
echo "<tr><td>$r</td><td><a href='$u'>$s</a></td><td>$t</td><td>$m</td><td>$d</td></tr>";
}
printf("</tbody></table>\n");
}