SEARCH-154 - Initial setup for skynet branch

This commit is contained in:
Keerthi Niranjan 2017-08-17 13:15:43 +05:30 committed by Keerthi Niranjan
parent c94bc0c327
commit 86dde3c71f
3 changed files with 199 additions and 110 deletions

View File

@ -53,11 +53,11 @@
</div>
<br>
<div>
<label for="senderId">SenderId:</label><input id="senderId" size=20>
<label for="senderId">SenderId:</label><input id="senderId" placeholder='["abc", "123"]'>
</div>
<br>
<div>
<label for="threadId">ThreadId:</label><input id="threadId" size=20>
<label for="threadId">ThreadId:</label><input id="threadId" placeholder='["abc", "123"]'>
</div>
<br>
<div>
@ -67,6 +67,7 @@
<div>
<label for="var1">var1:</label><input id="var1" type="number" value="0" size=5>
</div>
<br>
<div>
<label for="realTimeIndexing">Real Time Indexing:</label><input placeholder="Pass array of messages:"
id="realTimeIndexing">
@ -80,19 +81,23 @@
</div>
<br>
<div>
<p>Results:</p>
<p id="results"></p>
<table id="table" class="hidden" style="width:100%">
<tr>
<th>ThreadId</th>
<th>SenderId</th>
<th>Text</th>
</tr>
</table>
<br>
<label for="batchNumber">Get Latest Message Timestamp</label>
<button id='getLatestMessageTimestamp'>Click</button>
<div>
<p>Results:</p>
<p id="results"></p>
<table id="table" class="hidden" style="width:100%">
<tr>
<th>ThreadId</th>
<th>SenderId</th>
<th>Text</th>
</tr>
</table>
<br>
</div>
</div>
</div>
</body>
<script>
var search = new ssf.Search("testUser1");
var buttonEl = document.getElementById('search');
@ -111,6 +116,7 @@
var sendMessage = document.getElementById('sendMessage');
var realTimeIndexing = document.getElementById('realTimeIndexing');
var batchNumber = document.getElementById('batchNumber');
var timestamp = document.getElementById('getLatestMessageTimestamp');
buttonIndex.addEventListener('click', function () {
@ -134,45 +140,71 @@
table.classList.remove('hidden');
let startDate = new Date(startEl.value);
let endDate = new Date(endEl.value);
search.searchQuery(queryEl.value, senderIdEl.value, threadIdEl.value, null, startDate, endDate, limitEl.value, offsetEl.value, 0).then(function (result) {
out = result;
var th = document.createElement('tr');
var th1 = document.createElement('td');
th1.innerText = "ThreadId";
var th2 = document.createElement('td');
th2.innerText = 'SenderId';
var th3 = document.createElement('td');
th3.innerText = 'Text';
th.appendChild(th1);
th.appendChild(th2);
th.appendChild(th3);
table.appendChild(th);
out.messages.forEach(function (msg) {
var tr = document.createElement('tr');
var t1 = document.createElement('td');
t1.innerText = msg.threadId;
var t2 = document.createElement('td');
t2.innerText = msg.senderId;
var t3 = document.createElement('td');
t3.innerText = msg.text;
tr.appendChild(t1);
tr.appendChild(t2);
tr.appendChild(t3);
table.appendChild(tr);
});
let threadIdObj, senderIdObj;
if (senderIdEl.value && senderIdEl.value !== "" && senderIdEl.value.replace(/ /g, "").length > 0) {
senderIdObj = JSON.parse(senderIdEl.value);
}
if (threadIdEl.value && threadIdEl.value !== "" && threadIdEl.value.replace(/ /g, "").length > 0) {
threadIdObj = JSON.parse(threadIdEl.value);
}
search.searchQuery(queryEl.value, senderIdObj, threadIdObj, null, startDate, endDate, limitEl.value, offsetEl.value, 0).then(function (result) {
if (result.messages.length < 1) {
resultsEl.innerHTML = "No results found"
}
if (result.messages.length > 0) {
out = result;
var th = document.createElement('tr');
var th1 = document.createElement('td');
th1.innerText = "ThreadId";
var th2 = document.createElement('td');
th2.innerText = 'SenderId';
var th3 = document.createElement('td');
th3.innerText = 'Text';
th.appendChild(th1);
th.appendChild(th2);
th.appendChild(th3);
table.appendChild(th);
out.messages.forEach(function (msg) {
var tr = document.createElement('tr');
var t1 = document.createElement('td');
t1.innerText = msg.threadId;
var t2 = document.createElement('td');
t2.innerText = msg.senderId;
var t3 = document.createElement('td');
t3.innerText = msg.text;
tr.appendChild(t1);
tr.appendChild(t2);
tr.appendChild(t3);
table.appendChild(tr);
});
}
}).catch(function (err) {
resultsEl.innerHTML = err;
resultsEl.innerHTML = 'Error: ' + err;
});
});
sendMessage.addEventListener('click', function () {
let message = JSON.parse(realTimeIndexing.value);
search.realTimeIndexing(message);
if (realTimeIndexing.value !== "") {
let message = JSON.parse(realTimeIndexing.value);
resultsEl.innerHTML = search.realTimeIndexing(message);
} else {
resultsEl.innerHTML = "Please check the entered value"
}
});
merge.addEventListener('click', function () {
search.mergeIndexBatches();
search.getLatestMessageTimestamp();
})
resultsEl.innerHTML = 'Merged';
});
timestamp.addEventListener('click', function () {
search.getLatestMessageTimestamp().then(function (res) {
resultsEl.innerHTML = res;
}).catch(function (err) {
resultsEl.innerHTML = 'Error: ' + err;
});
});
</script>
</html>
</body>
</html>

View File

@ -2,7 +2,6 @@
const fs = require('fs');
const randomString = require('randomstring');
const electron = require('electron');
const childProcess = require('child_process');
const app = electron.app;
@ -26,9 +25,7 @@ const SEARCH_PERIOD_SUBTRACTOR = 3 * 31 * 24 * 60 * 60 * 1000;//3 months
const MINIMUM_DATE = '0000000000000';
const MAXIMUM_DATE = '9999999999999';
const INDEX_VERSION = 'v1';
const INTERNATIONAL_CHARACTER_CODES = '\xAA\xB5\xBA\xC0-\xD6\xD8-\xF6\xF8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u037F\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u052F\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u08A0-\u08B2\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0980\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D\u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C39\u0C3D\u0C58\u0C59\u0C60\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D60\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0E01-\u0E30\u0E32\u0E33\u0E40-\u0E46\u0E81\u0E82\u0E84\u0E87\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA\u0EAB\u0EAD-\u0EB0\u0EB2\u0EB3\u0EBD\u0EC0-\u0EC4\u0EC6\u0EDC-\u0EDF\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u1000-\u102A\u103F\u1050-\u1055\u105A-\u105D\u1061\u1065\u1066\u106E-\u1070\u1075-\u1081\u108E\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F4\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u16F1-\u16F8\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1877\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191E\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19C1-\u19C7\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1CE9-\u1CEC\u1CEE-\u1CF1\u1CF5\u1CF6\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2CF2\u2CF3\u2D00-\u2D25\u2D27\u2D2D\u2D30-\u2D67\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u3006\u3031-\u3035\u303B\u303C\u3041-\u3096\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FCC\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA69D\uA6A0-\uA6E5\uA717-\uA71F\uA722-\uA788\uA78B-\uA78E\uA790-\uA7AD\uA7B0\uA7B1\uA7F7-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uA9E0-\uA9E4\uA9E6-\uA9EF\uA9FA-\uA9FE\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA7E-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uAB30-\uAB5A\uAB5C-\uAB5F\uAB64\uAB65\uABC0-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\uFB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC';
const INVALID_CHARACTERS_REGEX = new RegExp('[^#$_a-z0-9' + INTERNATIONAL_CHARACTER_CODES + ']+', 'gmi');
const REPLACE_COMMAS = new RegExp(',', 'g');
const SORT_BY_SCORE = 0;
const BATCH_RANDOM_INDEX_PATH_LENGTH = 20;
@ -37,9 +34,7 @@ const winArchPath = process.arch === 'ia32' ? 'library/indexvalidator-x86.exe' :
const rootPath = isMac ? 'library/indexvalidator.exec' : winArchPath;
const productionPath = path.join(execPath, isMac ? '..' : '', rootPath);
const devPath = path.join(__dirname, '..', '..', rootPath);
const libraryPath = isDevEnv ? devPath : productionPath;
let INDEX_VALIDATOR = libraryPath;
const INDEX_VALIDATOR = isDevEnv ? devPath : productionPath;
/**
* This search class communicates with the SymphonySearchEngine C library via node-ffi.
@ -49,7 +44,7 @@ class Search {
/**
* Constructor for the SymphonySearchEngine library
* @param userId
* @param userId (for the index folder name)
*/
constructor(userId) {
this.isInitialized = false;
@ -107,11 +102,18 @@ class Search {
*/
indexBatch(messages) {
return new Promise((resolve, reject) => {
if (!this.isInitialized) {
reject()
if (!Array.isArray(messages)) {
reject('Messages should be an array');
return;
}
if (!this.isInitialized) {
reject("Not initialized");
return;
}
let indexId = randomString.generate(BATCH_RANDOM_INDEX_PATH_LENGTH);
libSymphonySearch.symSECreatePartialIndexAsync(this.batchIndex, indexId, JSON.stringify(messages), function (err, res) {
libSymphonySearch.symSECreatePartialIndexAsync(this.batchIndex, indexId, JSON.stringify(messages), (err, res) => {
if (err) reject(err);
resolve(res);
});
@ -123,10 +125,9 @@ class Search {
* created from indexBatch()
*/
mergeIndexBatches() {
let self = this;
libSymphonySearch.symSEMergePartialIndexAsync(this.indexFolderName, this.batchIndex, function (err) {
libSymphonySearch.symSEMergePartialIndexAsync(this.indexFolderName, this.batchIndex, (err) => {
if (err) throw err;
libSymphonySearch.symSERemoveFolder(self.batchIndex)
libSymphonySearch.symSERemoveFolder(this.batchIndex)
});
}
@ -136,7 +137,11 @@ class Search {
* @param message
*/
realTimeIndexing(message) {
libSymphonySearch.symSEIndexRealTime(this.realTimeIndex, JSON.stringify(message));
if (!Array.isArray(message)) {
return new Error('Messages should be an array');
}
let result = libSymphonySearch.symSEIndexRealTime(this.realTimeIndex, JSON.stringify(message));
return result === 0 ? "Successful" : result
}
/**
@ -146,18 +151,17 @@ class Search {
* @returns {Promise}
*/
readJson(batch) {
let self = this;
return new Promise((resolve, reject) => {
let dirPath = path.join(execPath, isMac ? '..' : '', 'msgsjson', batch);
let messageFolderPath = isDevEnv ? path.join('./msgsjson', batch) : dirPath;
let files = fs.readdirSync(messageFolderPath);
self.messageData = [];
files.forEach(function (file) {
this.messageData = [];
files.forEach((file) => {
let tempPath = path.join(messageFolderPath, file);
let data = fs.readFileSync(tempPath, "utf8");
if (data) {
self.messageData.push(JSON.parse(data));
resolve(self.messageData);
this.messageData.push(JSON.parse(data));
resolve(this.messageData);
} else {
reject("err on reading files")
}
@ -166,7 +170,7 @@ class Search {
}
/**
* This is the magic part of this library
* This returns the search results
* which returns a char *
* @param query
* @param senderIds
@ -187,13 +191,21 @@ class Search {
let _sortOrder = sortOrder;
return new Promise((resolve, reject) => {
if (!fs.existsSync(this.indexFolderName) && !fs.existsSync(this.realTimeIndex)) {
reject('Index folder does not exist.');
return;
}
if (!this.isInitialized) {
reject(-1);
reject("Not initialized");
return;
}
let q = Search.constructQuery(query, senderIds, threadIds);
if (q === undefined) {
reject(-2);
reject("Search query error");
return;
}
let sd = new Date().getTime() - SEARCH_PERIOD_SUBTRACTOR;
@ -232,10 +244,19 @@ class Search {
});
}
/**
* returns the latest message timestamp
* from the indexed data
* @returns {Promise}
*/
getLatestMessageTimestamp() {
let self = this;
return new Promise(function (resolve, reject) {
libSymphonySearch.symSEGetLastMessageTimestampAsync(self.indexFolderName, function (err, res) {
return new Promise((resolve, reject) => {
if (!fs.existsSync(this.indexFolderName)) {
reject('Index folder does not exist.');
return;
}
libSymphonySearch.symSEGetLastMessageTimestampAsync(this.indexFolderName, (err, res) => {
if (err) {
reject(new Error(err));
}
@ -252,57 +273,94 @@ class Search {
/**
* This the query constructor
* for the query search function
* @param query
* for the search function
* @param searchQuery
* @param senderId
* @param threadId
* @returns {string}
*/
static constructQuery(query, senderId, threadId) {
static constructQuery(searchQuery, senderId, threadId) {
let query = "";
if(searchQuery !== undefined) {
query = searchQuery.trim().toLowerCase(); //to prevent injection of AND and ORs
}
let q = "";
let tokens = query.toLowerCase()
.trim()
.replace(INVALID_CHARACTERS_REGEX, ' ')
.split(' ');
let hashTags = Search.getHashTags(query);
let hashCashTagQuery = "";
let hasToken = false;
if (/"/.test(query)) {
q += (query.match(/"(.*?)"/g)).toString().replace(REPLACE_COMMAS, ' ');
q += " ";
if(hashTags.length > 0) {
hashCashTagQuery = " OR tags:(";
hashTags.forEach((item) => {
hashCashTagQuery = hashCashTagQuery + "\"" + item + "\" "
});
hashCashTagQuery += ")";
}
let hashCashTagQuery = "(";
tokens.forEach((item, i) => {
if (i > 0 && (item.startsWith('#') || item.startsWith('$')) && hasToken) {
hashCashTagQuery += " OR ";
if (query.length > 0 ) {
q = "(text:(" + query + ")" + hashCashTagQuery + ")";
}
q = Search.appendFilterQuery(q, "senderId", senderId);
q = Search.appendFilterQuery(q, "threadId", threadId);
if(q === "") {
q = undefined; //will be handled in the search function
}
return q;
}
/**
* appending the senderId
* and threadId for the query
* @param query
* @param fieldName
* @param valueArray
* @returns {string}
*/
static appendFilterQuery(query, fieldName, valueArray) {
let q = "";
if (valueArray && valueArray.length > 0 ) {
q += "(" + fieldName +":(";
valueArray.forEach((item)=>{
q+= "\"" + item + "\" ";
});
q += "))";
if(query.length > 0 ) {
q = query + " AND " + q;
}
if (item.startsWith('#') || item.startsWith('$')) {
hashCashTagQuery += ("tags:\"" + item + "\"");
hasToken = true;
} else {
q += item + " ";
}
});
hashCashTagQuery += ")";
if (q.replace(/ /g, "").length > 0 && hasToken) {
q += " OR ";
}
if (tokens.length > 0 && hasToken) {
q += hashCashTagQuery;
}
if (senderId && senderId !== "" && senderId.replace(/ /g, "").length > 0) {
q += ` AND (senderId: ${senderId})`;
}
if (threadId && threadId !== "" && threadId.replace(/ /g, "").length > 0) {
q += ` AND (threadId: ${threadId})`;
} else {
q = query;
}
return q;
}
//hashtags can have any characters(before the latest release it was
//not like this). So the only regex is splitting the search query based on
//whitespaces
/**
* return the hash cash
* tags from the query
* @param query
* @returns {Array}
*/
static getHashTags(query) {
let hashTags = [];
let tokens = query.toLowerCase()
.trim()
.replace(/\s\s+/g, ' ')
.split(' ').filter((el) => {return el.length !== 0});
tokens.forEach((item) => {
if (item.startsWith('#') || item.startsWith('$')) {
hashTags.push(item);
}
});
return hashTags;
}
/**
* Validate the index folder exist or not
* @param file
@ -318,7 +376,7 @@ class Search {
}
return new Error('Unable validate index folder')
} catch (err) {
throw (err);
throw new Error(err);
}
}
}
@ -329,4 +387,4 @@ class Search {
*/
module.exports = {
Search: Search
};
};

View File

@ -2,7 +2,6 @@
const ffi = require('ffi');
const ref = require('ref');
const electron = require('electron');
const app = electron.app;
const path = require('path');