kiwix/kiwix-js
1
0
Fork 0
mirror of https://github.com/kiwix/kiwix-js.git synced 2025-09-24 04:54:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

First usable version of article searching

Browse Source 
Removed possibility to list all articles (much too slow)
Added the removal of diacritics (accents etc) in the user-typed prefix
This commit is contained in:
mossroy 2012-12-28 21:48:46 +01:00
parent c598de1ac5
commit 638d2f8815
4 changed files with 80 additions and 72 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -1,2 +1,3 @@
evopedia-html5/WebContent/evopedia.html~
evopedia-html5/WebContent/evopedia.js~
evopedia-html5/WebContent/remove_diacritics.js~

9
evopedia-html5/WebContent/evopedia.html
View File

@ -31,6 +31,7 @@ License:
<title>Evopedia HTML5</title>
<script type="text/javascript" src="bzip2-antimatter15.js"></script>
<script type="text/javascript" src="remove_diacritics.js"></script>
</head>
<body>
@ -43,11 +44,9 @@ Please pick the files wikipedia_*.dat from the same dump :<br/>
<input type="file" id="dataFiles" multiple="true"/>
</div>
<br/>
Find a title : <input type="text" id="prefix" value="" />&nbsp;<input type="button" id="searchTitles" value="Search titles" onclick="searchTitlesFromPrefix(titleFile,document.getElementById('prefix').value)" />
Find titles from the prefix : <input type="text" id="prefix" value="" onkeyup="onKeyUpPrefix(event)" />&nbsp;<input type="button" id="searchTitles" value="Search titles" onclick="searchTitlesFromPrefix(titleFile,document.getElementById('prefix').value)" />
<br/>
<input type="button" id="readTitle" value="Read all title list from index" onclick="readAllTitlesFromIndex(titleFile)" />
<br/>
Choose a title : <select id="titleList" onchange="updateOffsetsFromTitle(this.value)"></select>
Choose a title from the filtered list : <select id="titleList" onchange="updateOffsetsFromTitle(this.value)"></select>
<br/>
File number : <input type="text" id="filenumber" value="0" />
<br/>
@ -62,7 +61,7 @@ Length : <input type="text" id="length" value="8866" />
<!-- TODO : add CSS styles -->
<div id="articleContent">&nbsp;</div>
<hr/>
<textarea id="rawArticleContent" cols="80" rows="20">&nbsp;</textarea>
<textarea id="debugZone" cols="80" rows="20">&nbsp;</textarea>
<script type="text/javascript" src="evopedia.js"></script>
</body>

131
evopedia-html5/WebContent/evopedia.js
View File

@ -131,6 +131,8 @@ function recursivePrefixSearch(titleFile, reader, prefix, lo, hi) {
reader.readAsArrayBuffer(blob);
}
else {
// We found the closest title
//alert ("Found the closest title near index "+lo);
readTitlesBeginningAtIndexStartingWithPrefix(titleFile,prefix,lo);
}
}
@ -142,7 +144,7 @@ function recursivePrefixSearch(titleFile, reader, prefix, lo, hi) {
function searchTitlesFromPrefix(titleFile, prefix) {
if (titleFile) {
var titleFileSize = titleFile.size;
// TODO : normalize the prefix (remove accents etc)
prefix = normalizeString(prefix);
var reader = new FileReader();
reader.onerror = errorHandler;
@ -156,77 +158,73 @@ function searchTitlesFromPrefix(titleFile, prefix) {
}
}
function readTitlesBeginningAtIndexStartingWithPrefix(titleFile,prefix,index) {
// We found the closest title
alert ("Found the closest title at index "+index);
// TODO : read the following titles, stopping when the title does not start with the prefix any more (or at a maximum number of titles)
}
/**
* Read all the titles from the index file, and populate the dropdown list
* Warning : only usable on very small dumps. It is much too long on normal dumps
* Read the titles following the given index in the title file, until one of the following conditions is reached :
* - the title does not start with the prefix anymore
* - we already read the maximum number of titles
* and populate the dropdown list
*/
function readAllTitlesFromIndex(titleFile) {
if (titleFile) {
var reader = new FileReader();
reader.onerror = errorHandler;
reader.onabort = function(e) {
alert('Title file read cancelled');
};
reader.onload = function(e) {
var binaryTitleFile = e.target.result;
var byteArray = new Uint8Array(binaryTitleFile);
function readTitlesBeginningAtIndexStartingWithPrefix(titleFile,prefix,startIndex) {
var reader = new FileReader();
reader.onerror = errorHandler;
reader.onabort = function(e) {
alert('Title file read cancelled');
};
reader.onload = function(e) {
var binaryTitleFile = e.target.result;
var byteArray = new Uint8Array(binaryTitleFile);
// Look for the index of the next NewLine
var newLineIndex=0;
while (newLineIndex<byteArray.length && byteArray[newLineIndex]!=128) {
newLineIndex++;
}
var i = newLineIndex;
var titleNumber=-1;
var comboTitleList = document.getElementById('titleList');
while (i<byteArray.length && titleNumber<50) {
var filenumber = 0;
var blockstart = 0;
var blockoffset = 0;
var length = 0;
var title = "";
// TODO : interpret escape area
var escape1 = byteArray[i];
var escape2 = byteArray[i+1];
filenumber = byteArray[i+2];
var i = 0;
var titleNumber=0;
var comboTitleList = document.getElementById('titleList');
blockstart = readIntegerFrom4Bytes(byteArray,i+3);
blockoffset = readIntegerFrom4Bytes(byteArray,i+7);
length = readIntegerFrom4Bytes(byteArray,i+11);
var newLineIndex = i+15;
while (i<byteArray.length) {
var filenumber = 0;
var blockstart = 0;
var blockoffset = 0;
var length = 0;
var title = "";
// TODO : interpret escape area
var escape1 = byteArray[i];
var escape2 = byteArray[i+1];
filenumber = byteArray[i+2];
blockstart = readIntegerFrom4Bytes(byteArray,i+3);
blockoffset = readIntegerFrom4Bytes(byteArray,i+7);
length = readIntegerFrom4Bytes(byteArray,i+11);
var newLineIndex = i+15;
// Look for the index of NewLine
while (newLineIndex<byteArray.length && byteArray[newLineIndex]!=128) {
newLineIndex++;
}
title = utf8ByteArrayToString(byteArray,i+15,newLineIndex);
if (title) {
comboTitleList.options[titleNumber] = new Option (title, filenumber+"|"+blockstart+"|"+blockoffset+"|"+length);
}
titleNumber++;
i=newLineIndex-1;
// Look for the index of the next NewLine
while (newLineIndex<byteArray.length && byteArray[newLineIndex]!=128) {
newLineIndex++;
}
};
var blob = titleFile;
// Read in the file as a binary string
reader.readAsArrayBuffer(blob);
}
else {
alert('Title file not set');
}
title = utf8ByteArrayToString(byteArray,i+15,newLineIndex);
// Skip the first title
if (titleNumber>=0 && title) {
// TODO : check if the title starts with prefix, and return if it does not
comboTitleList.options[titleNumber] = new Option (title, filenumber+"|"+blockstart+"|"+blockoffset+"|"+length);
}
titleNumber++;
i=newLineIndex-1;
}
// Run onchange on the combo, so that to read the value of the selected item (first one)
comboTitleList.onchange();
};
var blob = titleFile.slice(startIndex);
// Read in the file as a binary string
reader.readAsArrayBuffer(blob);
}
/**
* Decompress and read an article in dump files
*/
function readArticleFromHtmlForm(dataFiles) {
document.getElementById("articleContent").innerHTML="Loading article from dump...";
if (dataFiles && dataFiles.length>0) {
var filenumber = document.getElementById('filenumber').value;
var blockstart = document.getElementById('blockstart').value;
@ -289,7 +287,7 @@ function readArticleFromOffset(dataFile, blockstart, blockoffset, length) {
document.getElementById('articleContent').innerHTML = htmlArticle;
// For testing purpose
//document.getElementById('rawArticleContent').value = htmlArticle;
//document.getElementById('debugZone').value = htmlArticle;
};
// TODO : should be improved by reading the file chunks by chunks until the article is found,
@ -322,3 +320,12 @@ function handleDataFileSelect(evt) {
function handleTitleFileSelect(evt) {
titleFile = evt.target.files[0];
}
/**
* Handle Enter key in the prefix input zone
*/
function onKeyUpPrefix(evt) {
if (evt.keyCode == 13) {
document.getElementById("searchTitles").click();
}
}

11
evopedia-html5/WebContent/remove_diacritics.js
View File

@ -182,9 +182,10 @@ var diacriticsMap = [
];
for(var i=0; i<diacriticsMap.length; i++) {
permalink = stringWithDiacritics.replace(diacriticsMap[i].letters, diacriticsMap[i].base);
function normalizeString(string) {
var normalizedString=string;
for(var i=0; i<diacriticsMap.length; i++) {
normalizedString = normalizedString.replace(diacriticsMap[i].letters, diacriticsMap[i].base);
}
return normalizedString;
}