source
stringclasses 1
value | task_type
stringclasses 1
value | in_source_id
stringlengths 1
8
| prompt
stringlengths 209
40.4k
| gold_standard_solution
stringlengths 0
56.7k
| verification_info
stringclasses 1
value | metadata
stringlengths 138
225
| problem_id
stringlengths 9
10
|
|---|---|---|---|---|---|---|---|
stackexchange | llm_judgeable_groundtruth_similarity | 146555 |
Below is a question asked on the forum unix.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Can scrypt be used as the hashing algorithm for LUKS? Can I tune its parameters? How can I do this?
Now provide the response and nothing else.
| No, LUKS 1 only supports PBKDF2 as the password-based key derivation function. PBKDF2 is built on a cryptographic hash function, and you can select the hash function with --hash , as well as the iteration count via --iter-time . All supported hash functions are equally secure for this use case; a higher iteration count makes the job proportionally harder for the attacker but also make normal mounting correspondingly slower. There is a registered issue for LUKS to support scrypt. This is a significant change because there is no field in the on-disk format to indicate which key stretching is in use. This has been discussed briefly on the dm-crypt mailing list. LUKS 2 supports Argon2 , which is a memory-hard password-based key derivation function (like scrypt) that is the new standard for password hashing . | {} | {'log_upvote_score': 4, 'links': ['https://unix.stackexchange.com/questions/146555', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/-1/']} | jdg_382741 |
stackexchange | llm_judgeable_groundtruth_similarity | 11094008 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm using system.Timers.Timer to create a timer. public System.Timers.Timer timer = new System.Timers.Timer(200);private void btnAutoSend_Click(object sender, EventArgs e){ timer.Enabled = true; timer.Elapsed += new System.Timers.ElapsedEventHandler(send); timer.AutoReset = true;}public void send(object source, System.Timers.ElapsedEventArgs e){ this.rtbMsg.AppendText("psyche-->" + receiver + ": hello\n");} The receiver in send function is a parameter that I need to set when the function is used, but when I add a parameter in the send function, like: public void send(object source, System.Timers.ElapsedEventArgs e,string receiver) Then it throws an error. After I checked the MSDN, it said ElapsedEventArgs is only available for these function which won't produce data. How can I solve this problem? My program isn't the windows.Form, so I cannot use the System.Windows.Forms.Timer .
Now provide the response and nothing else.
| You can't pass extra parameters to the event handler callback, because you aren't the one calling it -- the Timer is; that's the whole point ;-) But, you can easily accomplish the same effect with a closure: private void btnAutoSend_Click(object sender, EventArgs e){ timer.Elapsed += (timerSender, timerEvent) => send(timerSender, timerEvent, receiver); timer.AutoReset = true; timer.Enabled = true;}public void send(object source, System.Timers.ElapsedEventArgs e, string receiver){ this.rtbMsg.AppendText("psyche-->" + receiver + ": hello\n");} Now the Elapsed handler is the (timerSender, timerEvent) => lambda action, which closes over the receiver variable and calls send manually with the extra parameter whenever the lambda is triggered. In your particular case you don't need the sender or arguments at all, so there's no need to forward them. The code becomes: private void btnAutoSend_Click(object sender, EventArgs e){ timer.Elapsed += (s_, e_) => OnTimerElapsed(receiver); timer.AutoReset = true; timer.Enabled = true;}private void OnTimerElapsed(string receiver){ this.rtbMsg.AppendText("psyche-->" + receiver + ": hello\n");} If you're wondering about the overhead of all this, it's pretty minimal. Lambdas are just syntactic sugar and are plain functions behind the scenes (with some automatic delegate wrapping thrown in for the event stuff). Closures are implemented using compiler-generated classes, but you won't notice any code bloat unless you truly have a ton of them. As pointed out in the comments, you seem to be accessing a UI element in the OnTimerElapsed code -- since you're not using a Windows Forms timer, there's a good chance you'll get an exception by doing this since the code will run on whatever thread the timer happens to be running in when it fires the event -- and UI controls in Windows must be accessed only from the thread that created them. You could mess around with this.Invoke to fix it manually, but it's easier to have the timer marshall the event to the right thread for you via the SynchronizingObject property : private void btnAutoSend_Click(object sender, EventArgs e){ timer.SynchronizingObject = this; // Assumes `this` implements ISynchronizeInvoke timer.Elapsed += (s_, e_) => OnTimerElapsed(receiver); timer.AutoReset = true; timer.Enabled = true;} Finally, prompted by another comment, here's another way you could store a reference to the closure so that you can unsubscribe from the event later: private void btnAutoSend_Click(object sender, EventArgs e){ timer.SynchronizingObject = this; // Assumes `this` implements ISynchronizeInvoke ElapsedEventHandler onElapsed; onElapsed = (s_, e_) => { timer.Elapsed -= onElapsed; // Clean up after firing OnTimerElapsed(receiver); }; timer.Elapsed += onElapsed; timer.AutoReset = true; timer.Enabled = true;} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/11094008', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1452694/']} | jdg_382742 |
stackexchange | llm_judgeable_groundtruth_similarity | 3305658 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
To give you a simple use case - on my website, I display the comments posted by the facebook users. For each comment I display the facebook users photo using the fb:profile-pic tag and a fb like button. This page renders properly and everything displays well. Now when the users want to read older comments, they click on the "More" link Using Jquery, I pull the older comments and in the javascript build the content adding the fb:profile-pic and the fb:like tags But these tags dont show up. Do we need to reload it or something.Thanks for your help
Now provide the response and nothing else.
| First make sure the FBML is being inserted into the DOM with an inspector. If so, all you need to do is tell Facebook to convert the FBML tags to HTML tags so your browser can render it. With the Graph API you call FB.XHTML.parse http://developers.facebook.com/docs/reference/javascript/FB.XFBML.parse using the Javascript SDK. Here's an example from my code: $('#list').append('<fb:name uid="4"></fb:name>');FB.XFBML.parse(document.getElementById('list')); | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/3305658', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/274392/']} | jdg_382743 |
stackexchange | llm_judgeable_groundtruth_similarity | 3274629 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
My WPF application is organized as a TabControl with each tab containing a different screen. One TabItem is bound to data that takes a little while to load. Since this TabItem represents a screen that users may only rarely use, I would like to not load the data until the user selects the tab. How can I do this?
Now provide the response and nothing else.
| Tab control works two ways, When we add Tab Items explicitly, each tab item is loaded and initialized immediately containing every thing. When we bind ItemsSource to list of items, and we set different data template for each data item, tab control will create only one "Content" view of selected data item, and only when the tab item is selected, "Loaded" event of content view will be fired and content will be loaded. And when different tab item is selected, "Unloaded" event will be fired for previously selected content view and "Loaded" will be fired for new selected data item. Using 2nd method is little complicated, but at runtime it will certainly reduce the resources it is using, but at time of switching tabs, it may be little slower for a while. You have to create custom data class as following class TabItemData{ public string Header {get;set;} public string ResourceKey {get;set;} public object MyBusinessObject {get;set;}} And you must create list or array of TabItemData and you must set TabControl's items source to list/array of TabItemData. Then create ItemTemplate of TabControl as data template binding "Header" property. Then create create ContentTemplate of TabControl as data template containing ContentControl with ContentTemplate of Resource key found in ResourceKey property. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3274629', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/345372/']} | jdg_382744 |
stackexchange | llm_judgeable_groundtruth_similarity | 34301579 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
As we all know, CGFloat (which is ubiquitous in CoreGraphics, UIKit etc)can be a 32-bit or 64-bit floating point number, depending on theprocessor architecture. In C, CGFloat it is a typealiasto float or double , in Swift is it defined as a struct CGFloat witha native property (which is Float or Double ). It has been observed repeatedly that a NSNumber can be created fromand converted to Float and Double , but that there exist notsimilar conversions from and to CGFloat . The general advice(e.g. in Convert CGFloat to NSNumber in Swift ) is toconvert via Double CGFloat <--> Double <--> NSNumber Example: let c1 = CGFloat(12.3)let num = NSNumber(double: Double(c1))let c2 = CGFloat(num.doubleValue) and that is simple and correct, no precision is lost.Also most platforms are 64-bit nowadays, and then the CGFloat/Double conversion is trivial and probably optimized by the compiler. However, it aroused my curiosity if a conversion can be done without promoting CGFloat to Double on 32-bit platforms. One could use a build configuration statement (as e.g. in Should conditional compilation be used to cope with difference in CGFloat on different architectures? ): extension NSNumber { convenience init(cgFloatValue value : CGFloat) { #if arch(x86_64) || arch(arm64) self.init(double: value.native) #else self.init(float: value.native) #endif }} But what if Swift is ported to other architectures which are notIntel or ARM? This does not look very future proof. One could also use the CGFLOAT_IS_DOUBLE constant (as e.g. in NSNumber from CGFloat ): if CGFLOAT_IS_DOUBLE != 0 { // ... } else { // ... } The disadvantage here is that the compiler will always emit a "Will never be executed" warning on one of the cases. So to make the long story short: How can we convert between CGFloat and NSNumber in a safe way, without compiler warnings,and without unnecessary promotion to Double ? Please note that this is meant as an "academic" problem. As mentionedabove (and in other Q&A's) one can simply convert via Double practically. I am posting a "self-answer" here in the spirit of share your knowledge, Q&A-style . Of course other answers are welcome!
Now provide the response and nothing else.
| Update: One can cast a CGFloat value to NSNumber and back: let c1 = CGFloat(12.3)let num = c1 as NSNumberlet c2 = num as CGFloat This preserves the precision of CGFloat and works with Swift 2and Swift 3. (Previous answer – far too complicated): There are two solutions that I found. The first uses the toll-free bridgingbetween NSNumber and CFNumber (as in What is most common and correct practice to get a CGFloat from an NSNumber? for Objective-C). It uses the fact that CFNumber has a dedicatedconversion mode for CGFloat values: extension NSNumber { // CGFloat -> NSNumber class func numberWithCGFloat(var value: CGFloat) -> NSNumber { return CFNumberCreate(nil , .CGFloatType, &value) } // NSNumber -> CGFloat var cgFloatValue : CGFloat { var value : CGFloat = 0 CFNumberGetValue(self, .CGFloatType, &value) return value }} That is simple and nice. The only drawback: I could not figure outhow to make the constructor an init method instead of a class method . The second possible solution is a bit longer: extension NSNumber { // CGFloat -> NSNumber private convenience init(doubleOrFloat d : Double) { self.init(double : d) } private convenience init(doubleOrFloat f : Float) { self.init(float : f) } convenience init(cgFloat : CGFloat) { self.init(doubleOrFloat: cgFloat.native) } // NSNumber -> CGFloat private func doubleOrFloatValue() -> Double { return self.doubleValue } private func doubleOrFloatValue() -> Float { return self.floatValue } var cgFloatValue : CGFloat { return CGFloat(floatLiteral: doubleOrFloatValue()) }} There are two private "helper" init methods with the same externalparameter name doubleOrFloat but different parameter types. From the actualtype of cgFloat.native the compiler determines which one to callin convenience init(cgFloat : CGFloat) { self.init(doubleOrFloat: cgFloat.native) } Same idea in the accessor method. From the type of self.native the compiler determines which of the two doubleOrFloatValue() methods to call in var cgFloatValue : CGFloat { return CGFloat(floatLiteral: doubleOrFloatValue()) } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/34301579', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1187415/']} | jdg_382745 |
stackexchange | llm_judgeable_groundtruth_similarity | 261360 |
Below is a question asked on the forum unix.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I am testing my Debian Server with some Nmap port Scanning. My Debian is a Virtual Machine running on a bridged connection. Classic port scanning using TCP SYN request works fine and detects port 80 as open (which is correct) : nmap -p 80 192.168.1.166 Starting Nmap 6.47 ( http://nmap.org ) at 2016-02-10 21:36 CETNmap scan report for 192.168.1.166Host is up (0.00014s latency).PORT STATE SERVICE80/tcp open httpMAC Address: xx:xx:xx:xx:xx:xx (Cadmus Computer Systems)Nmap done: 1 IP address (1 host up) scanned in 0.51 seconds But when running UDP port scan, it fails and my Debian server answers with an ICMP : Port unreachable error : nmap -sU -p 80 192.168.1.166Starting Nmap 6.47 ( http://nmap.org ) at 2016-02-10 21:39 CETNmap scan report for 192.168.1.166Host is up (0.00030s latency).PORT STATE SERVICE80/udp closed httpMAC Address: xx:xx:xx:xx:xx:xx (Cadmus Computer Systems)Nmap done: 1 IP address (1 host up) scanned in 0.52 seconds Wireshark record : How is that possible ? My port 80 is open, how come that Debian answers with an ICMP : Port unreachable error ? Is that a security issue?
Now provide the response and nothing else.
| Albeit TCP and UDP are part of TCP/IP, both belong to the same TCP/IP or OSI layers, and both are a layer above IP, they are different protocols. http://www.cyberciti.biz/faq/key-differences-between-tcp-and-udp-protocols/ Transmission Control Protocol (TCP) and User Datagram Protocol (UDP) are two of the core protocols of the Internet Protocol suite. Both TCP and UDP work at the transport layer TCP/IP model and both have a very different usage. TCP is a connection-oriented protocol. UDP is a connectionless protocol. (source: ml-ip.com ) Some services do indeed answer to TCP and UDP ports at the same time, as is the case of DNS and NTP services, however that is not certainly the case with web servers, which normally only answer by default to port 80/TCP (and do not work/listen at all in UDP) You can list your UDP listenning ports in a linux system with: $sudo netstat -anlpuActive Internet connections (servers and established) Proto Recv-Q Send-Q Local Address Foreign Address State PID/Program name udp 0 0 0.0.0.0:1900 0.0.0.0:* 15760/minidlnad udp 0 0 0.0.0.0:5000 0.0.0.0:* 32138/asterisk udp 0 0 0.0.0.0:4500 0.0.0.0:* 1592/charon udp 0 0 0.0.0.0:4520 0.0.0.0:* 32138/asterisk udp 0 0 0.0.0.0:5060 0.0.0.0:* 32138/asterisk udp 0 0 0.0.0.0:4569 0.0.0.0:* 32138/asterisk udp 0 0 0.0.0.0:500 0.0.0.0:* 1592/charon udp 0 0 192.168.201.1:53 0.0.0.0:* 30868/named udp 0 0 127.0.0.1:53 0.0.0.0:* 30868/named udp 0 0 0.0.0.0:67 0.0.0.0:* 2055/dhcpd udp 0 0 0.0.0.0:14403 0.0.0.0:* 1041/dhclient udp 17920 0 0.0.0.0:68 0.0.0.0:* 1592/charon udp 0 0 0.0.0.0:68 0.0.0.0:* 1041/dhclient udp 0 0 0.0.0.0:56417 0.0.0.0:* 2055/dhcpd udp 0 0 192.168.201.1:123 0.0.0.0:* 1859/ntpd udp 0 0 127.0.0.1:123 0.0.0.0:* 1859/ntpd udp 0 0 192.168.201.255:137 0.0.0.0:* 1777/nmbd udp 0 0 192.168.201.1:137 0.0.0.0:* 1777/nmbd udp 0 0 0.0.0.0:137 0.0.0.0:* 1777/nmbd udp 0 0 192.168.201.255:138 0.0.0.0:* 1777/nmbd udp 0 0 192.168.201.1:138 0.0.0.0:* 1777/nmbd udp 0 0 0.0.0.0:138 0.0.0.0:* 1777/nmbd udp 0 0 192.168.201.1:17566 0.0.0.0:* 15760/minidlnad And your listening TCP ports with the command: $sudo netstat -anlptActive Internet connections (servers and established) Proto Recv-Q Send-Q Local Address Foreign Address State PID/Program name tcp 0 0 0.0.0.0:5060 0.0.0.0:* LISTEN 32138/asterisk tcp 0 0 192.168.201.1:8200 0.0.0.0:* LISTEN 15760/minidlnad tcp 0 0 192.168.201.1:139 0.0.0.0:* LISTEN 2092/smbd tcp 0 0 0.0.0.0:2000 0.0.0.0:* LISTEN 32138/asterisk tcp 0 0 192.168.201.1:80 0.0.0.0:* LISTEN 7781/nginx tcp 0 0 192.168.201.1:53 0.0.0.0:* LISTEN 30868/named tcp 0 0 127.0.0.1:53 0.0.0.0:* LISTEN 30868/named tcp 0 0 192.168.201.1:22 0.0.0.0:* LISTEN 2023/sshd tcp 0 0 0.0.0.0:8888 0.0.0.0:* LISTEN 1919/perl tcp 0 0 127.0.0.1:953 0.0.0.0:* LISTEN 30868/named tcp 0 0 192.168.201.1:445 0.0.0.0:* LISTEN 2092/smbd tcp 0 224 192.168.201.1:22 192.168.201.12:56820 ESTABLISHED 16523/sshd: rui [pr Now normally NMAP does send a SYN to the port being scanned, and per the TCP protocol, if a daemon/service is bound to the port, it will answer with a SYN+ACK, and nmap will show it as open. TCP/IP connection negotiation: 3 way handshake To establish a connection, TCP uses a three-way handshake. Before a client attempts to connect with a server, the server must first bind to and listen at a port to open it up for connections: this is called a passive open. Once the passive open is established, a client may initiate an active open. To establish a connection, the three-way (or 3-step) handshake occurs: SYN: The active open is performed by the client sending a SYN to the server. The client sets the segment's sequence number to a random value A. SYN-ACK: In response, the server replies with a SYN-ACK. However, if a service is not running there, TCP/IP defines the kernel will send an ICMP message back with an "Port unreachable" message for UDP services, and TCP RST messages for TCP services. ICMP Destination unreachable Destination unreachable is generated by the host or its inbound gateway[3] to inform the client that the destination is unreachable for some reason. A Destination Unreachable message may be generated as a result of a TCP, UDP or another ICMP transmission. Unreachable TCP ports notably respond with TCP RST rather than a Destination Unreachable type 3 as might be expected. So indeed, your UDP scanning to port 80/UDP simply receives an ICMP unreachable message back because there is not a service listening to that combination or protocol/port. As for security considerations, those ICMP destination unreachable messages can certainly be blocked, if you define firewall/iptables rules that DROP all messages by default, and only allow in the ports that your machine serves to the outside. That way, nmap scans to all the open ports, especially in a network, will be slower, and the servers will use less resources. As an additional advantage, if a daemon/service opens additional ports, or a new service is added by mistake, it won't be serving requests until it is expressly allowed by new firewall rules. Please do note, that if instead of using DROP in iptables, you use REJECT rules, the kernel won't ignore the scanning/ TCP/IP negotiation tries, and will answer with ICMP messages of Destination unreachable, code 13: "Communication administratively prohibited (administrative filtering prevents packet from being forwarded)". Block all ports except SSH/HTTP in ipchains and iptables | {} | {'log_upvote_score': 5, 'links': ['https://unix.stackexchange.com/questions/261360', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/115216/']} | jdg_382746 |
stackexchange | llm_judgeable_groundtruth_similarity | 4469506 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I am currently juggling some integrals. In a physics textbook, Chaikin-Lubensky [1] , Chapter 6, (6.1.26), I came upon an integral that goes \begin{equation}\int_0^{1} \textrm{d} y\, \frac{1 - J_0(y)}{y} - \int_{1}^{\infty} \textrm{d} y\, \frac{J_0(y)}{y} = -.116.\end{equation} They give the result only as a floating point value without naming sources. The value looks suspiciously like $\gamma - \ln(2)$ to me ( $\gamma$ being the Euler-Mascheroni constant), which would solve a problem I have elsewhere. I am unfamiliar with the typical manipulations one uses on this kind of integrals and the various definitions of the Euler-Mascheroni constant. I fumbled around a bit with cosine integrals $\textrm{Ci}(y)$ but did not get far with it. So I am happy about suggestions.
Now provide the response and nothing else.
| A relatively elementary way is to start with known $$\gamma=\int_0^1\frac{1-\cos t}{t}\,dt-\int_1^\infty\frac{\cos t}{t}\,dt.$$ Put $t=ax$ for $a>0$ and do some rearrangements, to get $$\int_0^1\frac{1-\cos ax}{x}\,dx-\int_1^\infty\frac{\cos ax}{x}\,dx=\gamma+\log a.$$ Now the integral representation $J_0(y)=\frac2\pi\int_0^{\pi/2}\cos(y\cos x)\,dx$ yields $$\int_0^1\frac{1-J_0(y)}{y}\,dy-\int_1^\infty\frac{J_0(y)}{y}\,dy=\frac2\pi\int_0^{\pi/2}(\gamma+\log\cos x)\,dx$$ after interchanging integrations (which is not hard to justify). The result now follows from $\int_0^{\pi/2}\log\cos x\,dx\color{gray}{=\int_0^{\pi/2}\log\sin x\,dx}=-(\pi/2)\log2$ . | {} | {'log_upvote_score': 6, 'links': ['https://math.stackexchange.com/questions/4469506', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/875730/']} | jdg_382747 |
stackexchange | llm_judgeable_groundtruth_similarity | 14261118 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a concept for a special albeit simple kind of clock that would display the number of seconds since a certain point in time (which would never change). What would be the best way of storing, incrementing and displaying this persistent value?
Now provide the response and nothing else.
| Translation is done via a Translator . The translator is an object and injected for example in a view helper, so if you call that view helper, it uses the translator to translate your strings. For this answer I assume you have configured the translator just the same as the skeleton application . The best way is to use the factory to inject this as a dependency into your controller. The controller config: 'controllers' => array( 'factories' => array( 'my-controller' => function($sm) { $translator = $sm->getServiceLocator()->get('translator'); $controller = new MyModule\Controller\FooController($translator); } )) And the controller itself: namespace MyModule;use Zend\Mvc\Controller\AbstractActionController;use Zend\I18n\Translator\Translator;class FooController extends AbstractActionController{ protected $translator; public function __construct(Translator $translator) { $this->translator = $translator; }} An alternative is to pull the translator from the service manager in your action, but this is less flexible, less testable and harder to maintain: public function fooAction(){ $translator = $this->getServiceManager()->get('translator');} In both cases you can use $translator->translate('foo bar baz') to translate your strings. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/14261118', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1616217/']} | jdg_382748 |
stackexchange | llm_judgeable_groundtruth_similarity | 800804 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
The total Stiefel-Whitney class $w=1+w_1+w_2+\cdots$ is related to thetotal Wu class $u=1+u_1+u_2+\cdots$: The total Stiefel-Whitney class $w$ is the Steenrod square of the Wu class$u$: \begin{align} w=Sq(u),\ \ \ Sq=1+Sq^1+Sq^2 +\cdots .\end{align}The Wu classes can be defined through the Steenrod square (is this right? see nLab ).$$Sq^k(x) = \begin{cases}u_k x & \text{ for any } x \text{ with dim more than } k-1,\\0 & \text{ for any } x \text{ with dim less than } k.\end{cases}$$where $u_k x$ is understood as $u_k\cup x$.Thus we have (dose the second equal sign hold?)\begin{align} w_i=\sum_{k=0}^i Sq^k u_{i-k} = \sum_{k=0}^{i-k-1} u_k u_{i-k} .\end{align} Now we try to invert the relation.We first expand the above\begin{align} w_1&=u_1, \ \ \ w_2=u_2+u_1^2, \ \ \ w_3=u_3+u_1u_2, \end{align}This allows us to obtain\begin{align} u_1=w_1,\ \ \ u_2=w_2+w_1^2,\ \ \ u_3=w_3+w_1w_2+w_1^3,\ \ \\end{align} But on nLab (and several other places), it says $u_3=w_1 w_2$. I must have made an error in my calculation above, but I do not know where. Thank you for help.
Now provide the response and nothing else.
| First of all, your definition of Wu class is incorrect. If $X$ is a closed connected $n$-manifold, there is a unique class $\nu_k \in H^k(X; \mathbb{Z}_2)$ such that for any $x \in H^{n-k}(X; \mathbb{Z}_2)$, $\operatorname{Sq}^k(x) = \nu_k\cup x$. We call $\nu_k$ the $k^{\text{th}}$ Wu class. If $X$ is also smooth, then the Stiefel-Whitney classes of the tangent bundle of $X$ are related to Steenrod squares and Wu classes by the formula $$w_i = \sum_{k = 0}^i\operatorname{Sq}^k(\nu_{i-k}).$$ Note $\operatorname{Sq}^k(\nu_{i-k})$ is not simply $\nu_k\cup\nu_{i-k}$ unless $i = n$. So we have \begin{align*}w_1 &= \operatorname{Sq}^0(\nu_1) = \nu_1\\w_2 &= \operatorname{Sq}^0(\nu_2) + \operatorname{Sq}^1(\nu_1) = \nu_2 + \nu_1\cup\nu_1\\w_3 &= \operatorname{Sq}^0(\nu_3) + \operatorname{Sq}^1(\nu_2) = \nu_3 + \operatorname{Sq}^1(\nu_2)\end{align*} It follows that $\nu_1 = w_1$ and $\nu_2 = w_2 + w_1\cup w_1$. However, at this stage we can only deduce $\nu_3 = w_3 + \operatorname{Sq}^1(\nu_2)$. In order to determine $\nu_3$ in terms of Stiefel-Whitney classes, we need to compute $\operatorname{Sq}^1(\nu_2)$. First note that \begin{align*}\operatorname{Sq}^1(\nu_2) &= \operatorname{Sq}^1(w_2 + w_1\cup w_1)\\ &= \operatorname{Sq}^1(w_2) + \operatorname{Sq}^1(w_1\cup w_1)\\ &= \operatorname{Sq}^1(w_2) + \operatorname{Sq}^0(w_1)\cup\operatorname{Sq}^1(w_1) + \operatorname{Sq}^1(w_1)\cup\operatorname{Sq}^0(w_1) && \text{(by Cartan's formula)}\\&= \operatorname{Sq}^1(w_2)\end{align*} so $\nu_3 = w_3 + \operatorname{Sq}^1(w_2)$. To compute Steenrod squares of Stiefel-Whitney classes, we use Wu's formula $$\operatorname{Sq}^i(w_j) = \sum_{t=0}^k\binom{j-i+t-1}{t}w_{i-t}\cup w_{j+t}.$$ In this case, we see that $$\operatorname{Sq}^1(w_2) = \binom{0}{0}w_1\cup w_2 + \binom{1}{1}w_0\cup w_3 = w_1\cup w_2 + w_3.$$ Therefore, $\nu_3 = w_3 + \operatorname{Sq}^1(w_2) = w_3 + w_1\cup w_2 + w_3 = w_1\cup w_2$. Suppressing the cup symbol, this agrees with the identity given on nLab. See this note for more details, as well as the computations for $\nu_4$ and $\nu_5$. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/800804', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/148838/']} | jdg_382749 |
stackexchange | llm_judgeable_groundtruth_similarity | 50313296 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
How do I specify the environment to use in Angular 6+? The .angular-cli.json file seems to have changed to angular.json from previous versions and with it the structure of the json within. How/where in this file do I specify the environments to use?
Now provide the response and nothing else.
| Open angular.json file. we can see the configurations by default it will be shown for production add code snippet for your respective environments. add environment.dev.ts file in environment for dev, add environment.qa.ts for qa. Name as you prefered.use ng serve --configuration=environment_name environment_name - (dev,qa,prod) same process can be followed for ng build "configurations": { "production": { "fileReplacements": [ { "replace": "src/environments/environment.ts", "with": "src/environments/environment.prod.ts" } ], "optimization": true, "outputHashing": "all", "sourceMap": false, "extractCss": true, "namedChunks": false, "aot": true, "extractLicenses": true, "vendorChunk": false, "buildOptimizer": true }, "dev": { "fileReplacements": [ { "replace": "src/environments/environment.ts", "with": "src/environments/environment.dev.ts" } ], "optimization": true, "outputHashing": "all", "sourceMap": true, "extractCss": true, "namedChunks": false, "aot": true, "extractLicenses": true, "vendorChunk": false, "buildOptimizer": true }, "qa": { "fileReplacements": [ { "replace": "src/environments/environment.ts", "with": "src/environments/environment.qa.ts" } ], "optimization": true, "outputHashing": "all", "sourceMap": false, "extractCss": true, "namedChunks": false, "aot": true, "extractLicenses": true, "vendorChunk": false, "buildOptimizer": true } } | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/50313296', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4486146/']} | jdg_382750 |
stackexchange | llm_judgeable_groundtruth_similarity | 12081692 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
private String METHOD_NAME = "schedule";private String NAMESPACE = "http://calculate.backend.web.org";private String SOAP_ACTION = NAMESPACE + METHOD_NAME; private static final String URL = "http://192.168.0.4:8080/AndroidBackEnd/services/Calculate?wsdl"; This the code I am using to connect to my web-service from client via Ksoap.. I am hardcoding the IP address here in the URL..When ever I switch to a new network I need to change the IP address for the application to work can anyone share the solution for this please?
Now provide the response and nothing else.
| First, naming: The Task-based Asynchronous Pattern (TAP) says that all methods that are asynchronous and return Task s should be named ending with Async . So, your method should be named DoSomethingAsync . Second, the constructor of Task creates a Task that is not started, you have to Start() it manually. If your actual DoSomething method does this too, that again doesn't follow TAP and it means your code won't work well with await . Instead, you should use Task.Run(() => value) , or, even better, Task.FromResult(value) . Third, it would be better if you showed us your code that didn't work well, so that we could tell you where did you make a mistake. Now, the body of ReturnsAsync() extension method is quite simple, but most of the work for me was in figuring out the correct types (especially since I don't know Moq). The code looks like this: public static class MoqExtensions{ public static IReturnsResult<TMock> ReturnsAsync<TMock, TResult>( this IReturns<TMock, Task<TResult>> setup, TResult value) where TMock : class { return setup.Returns(Task.FromResult(value)); }} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/12081692', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1538399/']} | jdg_382751 |
stackexchange | llm_judgeable_groundtruth_similarity | 1724834 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I was wondering if someone could explain the ideas behind isomorphisms and homomorphisms and the difference between them. I understand that a linear map is an isomorphism if it is bijective, and that an isomorphism is a bijective homomorphism but I don't fully understand what a homomorphism actually is. For example, what does it mean to say that $Hom_{\mathbb{C}}\left(\mathbb{C}^2,\mathbb{C}^3\right)\simeq MAT_{\mathbb{C} }\left(3,2 \right)$ where $MAT_{\mathbb{C}}$ is the $3\times2$ matrix with complex entries. After some research, I think that this example is saying that $Hom_{\mathbb{C}}\left(\mathbb{C}^2,\mathbb{C}^3\right)$ is essentially a perfect approximation of $MAT_{\mathbb{C} }\left(3,2 \right)$ however I am struggling to understand what the notation $Hom_{\mathbb{C}}\left(\mathbb{C}^2,\mathbb{C}^3\right)$ actually means. Note: I haven't studied a course in group theory and therefore have little knowledge on it, this is for a Linear Algebra Course
Now provide the response and nothing else.
| That statement is something of a mathematical quagmire because there are lots of algebraic structures floating around, and the maps between them aren't explicitly "typed" (i.e., it's not exactly explicit what kinds of structures the homomorphisms are between)! The notation $\operatorname{Hom}_{\Bbb C}(\Bbb C^2, \Bbb C^3)$ is just the set of all $\Bbb C$-linear maps from $\Bbb C^2$ to $\Bbb C^3$ (the subscript $\Bbb C$ is what tells us the maps are $\Bbb C$-linear). Recall that a $\Bbb C$-linear map $T: \Bbb C^2 \to \Bbb C^3$ is just a map that "respects addition," so that $T(x + y) = T(x) + T(y)$ for vectors $x, y \in \Bbb C^2$, and "respects (complex) scalar multiplication" so that $T(cx) = cT(x)$ for scalars $c \in \Bbb C$ and vectors $x \in \Bbb C^2$. Another term for a linear map is a vector space homomorphism, hence the notation $\operatorname{Hom}_\Bbb C (\Bbb C^2, \Bbb C^3)$. Essentially, as other answers have pointed out, homomorphisms are just maps between algebraic structures (in this case, vector spaces) that "respect" the relevant operations (in this case, vector spaces are spaces in which we can add vectors together and multiply them by scalars, and each operation needs to be "respected"). Now, the sets $\operatorname{Hom}_\Bbb C (\Bbb C^2, \Bbb C^3)$ and $\operatorname{Mat}_\Bbb C(3, 2)$ can themselves be thought of algebraic structures (they are groups under composition/multiplication) but I would not worry about that! At least for now. I would simply view the '$\simeq$' in $\operatorname{Hom}_\Bbb C (\Bbb C^2, \Bbb C^3) \simeq \operatorname{Mat}_\Bbb C(3, 2)$ as the claim that these two sets are in bijection: If you have a linear map $T\colon \Bbb C^2 \to \Bbb C^2$, there's an easy way to write down a $3 \times 2$ matrix $M_T \in \operatorname{Mat}_\Bbb C(3, 2)$: Just make the $i$th column of $M_T$ the image $T(e_i)$ of the standard basis vector $e_i \in \Bbb C^2$. Now, if we want to consider the '$\simeq$' in $\operatorname{Hom}_\Bbb C (\Bbb C^2, \Bbb C^3) \simeq \operatorname{Mat}_\Bbb C(3, 2)$ as some kind of isomorphism of algebraic structures (not just between sets, i.e., a bijection), we would then need to worry about whether the relevant operations are preserved. If we're composing maps $S, T \in \operatorname{Hom}_\Bbb C (\Bbb C^2, \Bbb C^3)$, we'd need to verify that the corresponding matrices $M_S, M_T \in \operatorname{Mat}_\Bbb C(3, 2)$ multiply the way we'd expect. That is, $$M_T M_S = M_{T \circ S}.$$ If you show this, then you'll have shown that the groups $\operatorname{Hom}_\Bbb C (\Bbb C^2, \Bbb C^3)$ and $\operatorname{Mat}_\Bbb C(3, 2)$ are isomorphic (provided you've already shown they're in bijection). The homomorphism could be made concrete as a map $M \colon \operatorname{Hom}_\Bbb C (\Bbb C^2, \Bbb C^3) \to \operatorname{Mat}_\Bbb C(3, 2)$ that sends a $\Bbb C$-linear map $T \in \operatorname{Hom}_\Bbb C (\Bbb C^2, \Bbb C^3)$ to the matrix $M_T \in \operatorname{Mat}_\Bbb C(3, 2)$ described above. But unless your linear algebra class is way fancier than mine (and it very well may be), I would assume, not having done much group theory, that the statement is just pointing out that the two sets are in bijection, possibly "to be expanded upon later" or "plus other good stuff." | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1724834', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/236211/']} | jdg_382752 |
stackexchange | llm_judgeable_groundtruth_similarity | 9040 |
Below is a question asked on the forum dsp.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Suppose I have a $4x4$ image with the following values as its grey-level intensity for each pixel like this: I want to get its Fourier spectrum. Usually, I would just punch into Matlab and run a fft for everything to be calculated automatically. Now, if I don't have Matlab, and I have to do it by hand and with just an ordinary scientific calculator, can I still do it? I know I could do the brute force way on the Fourier transform's equation like this: In this case, $N=M=4$. So, $f(x,y)$ returns the intensity value of the above image at position $x$ and $y$. Eg, $f(1,1)=1$, $f(2, 0)=3$ But this will be insane to work out the summations so many times on paper. Most calculators can't do summations with complex numbers too. I have tried doing it with Fourier transform's separability property, but doesn't seem to work as I still have to go through the tedious summations. What other ways can I use to calculate Fourier transform on a simple image without using Matlab, particularly for the values in the first row of the example image above?
Now provide the response and nothing else.
| Your particular case can be solved without a calculator. Fourier transforms are linear operations. You can decompose your input as: $$3 \left( \begin{array}{cccc} 0 & 0 & 1 & 1 \\0 & 0 & 1 & 1 \\0 & 0 & 1 & 1 \\0 & 0 & 1 & 1 \end{array} \right) + \left( \begin{array}{cccc} 0 & 0 & 0 & 0 \\0 & 1 & 0 & 0 \\0 & 0 & 0 & 0 \\0 & 0 & 0 & 0 \end{array} \right) $$ The first matrix is constant on the Y axis, so its 2D FFT is only the 1D-FFT of one row, times 4, and 0 everywhere else. The 1D FFT of $(0, 0, 1, 1)$ is $(2, -1+j, 0, -1-j)$, so this gives you, for the first term: $$3 \times 4 \times \left( \begin{array}{cccc} 2 & -1+j & 0 & -1-j \\0 & 0 & 0 & 0 \\0 & 0 & 0 & 0 \\0 & 0 & 0 & 0 \end{array} \right)$$ As for the second term, there's only one value so there's only one component in the sum - it's just one of the basis functions, the checkerboard pattern: $$\left( \begin{array}{cccc} 1 & -j & -1 & j \\-j & -1 & j & 1 \\-1 & j & 1 & -j \\j & 1 & -j & -1 \end{array} \right)$$ Summing these two, you get: $$\left( \begin{array}{cccc} 25 & -12+11j & -1 & -12-11j \\-j & -1 & j & 1 \\-1 & j & 1 & -j \\j & 1 & -j & -1 \end{array} \right)$$ Note that this differs from Paul R's answer because of the normalization and sign conventions nobody agrees with... Divide by 4 and take the conjugate and you'll find the same result as his. | {} | {'log_upvote_score': 4, 'links': ['https://dsp.stackexchange.com/questions/9040', 'https://dsp.stackexchange.com', 'https://dsp.stackexchange.com/users/3769/']} | jdg_382753 |
stackexchange | llm_judgeable_groundtruth_similarity | 28245463 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I can't figure out how in a Google Apps Script to display this correctly. I need it to display new lines in the jsdoc output(e.g. when the function tooltip window comes up in a Spreadheet functions.) I have tried html like however it is just rendered as text and not a line break. For example: /** * Converts the prefixed value to the specified base. * Requires one of the following prefixes: * '0b' Base 2: binary * '0q' Base 4: quaternary * '0o' Base 8: octal * '0x' Base 16: hexadecimal * * @param {string} Value The prefixed value to convert. * @param {number} To The base to convert to. * @return The converted base. * @customfunction */function BASEP(Value, To) { This just renders a text blob like: Summary: Converts the prefixed value to the specified base. Requires one of the following prefixes: 0b Base 2: binary 0q Base 4: quaternary 0o Base 8: octal 0x Base 16: hexadecimal
Now provide the response and nothing else.
| Here are a few ways to control the format of your jsdoc comments in Google Apps Script: <pre> /** * Converts the prefixed value to the specified base. * Requires one of the following prefixes: * <pre> * '0b' Base 2: binary * '0q' Base 4: quaternary * '0o' Base 8: octal * '0x' Base 16: hexadecimal * </pre> * * @param {string} Value The prefixed value to convert. * @param {number} To The base to convert to. * @return The converted base. * @customfunction */function BASEP(Value, To) { } <p> paragraphs /** * Converts the prefixed value to the specified base. * Requires one of the following prefixes: * <p>'0b' Base 2: binary </p> * <p>'0q' Base 4: quaternary </p> * <p>'0o' Base 8: octal </p> * <p>'0x' Base 16: hexadecimal </p> * * @param {string} Value The prefixed value to convert. * @param {number} To The base to convert to. * @return The converted base. * @customfunction */function BASEP2(Value, To) { } List /** * Converts the prefixed value to the specified base. * Requires one of the following prefixes: * <ul style="list-style: none;"> * <li> '0b' Base 2: binary * <li> '0q' Base 4: quaternary * <li> '0o' Base 8: octal * <li> '0x' Base 16: hexadecimal * </ul> * * @param {string} Value The prefixed value to convert. * @param {number} To The base to convert to. * @return The converted base. * @customfunction */function BASEP3(Value, To) { } Table /** * Converts the prefixed value to the specified base. * Requires one of the following prefixes: * <table style="width:30%;"> * <tr><td>'0b'</td><td>Base 2:</td><td>binary</td></tr> * <tr><td>'0q'</td><td>Base 4:</td><td>quaternary</td></tr> * <tr><td>'0o'</td><td>Base 8:</td><td>octal</td></tr> * <tr><td>'0x'</td><td>Base 16:</td><td>hexadecimal</td></tr> * </table> * * @param {string} Value The prefixed value to convert. * @param {number} To The base to convert to. * @return The converted base. * @customfunction */function BASEP4(Value, To) { } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/28245463', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2511123/']} | jdg_382754 |
stackexchange | llm_judgeable_groundtruth_similarity | 82772 |
Below is a question asked on the forum raspberrypi.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Some tutorials I found are outdated, but the following answer contains a collection of notes I have used to set up home, school(enterprise), & Ad-Hoc wireless connections on my Raspberry Pi 3.
Now provide the response and nothing else.
| Raspberry Pi 3 (kernel 4.14.30-v7+) This post is a collection of notes and tutorials I have used for setting up wireless connections to the Raspberry Pi. Please let me know if you experience any issues. Headless set-up Raspbian currently looks in the boot partition for a couple files to allow a headless set-up or connect a Raspberry Pi to a network and establish an ssh connection from an external machine without a monitor, screen or mouse. After you load Raspbian OS onto an micro SD card, Ubuntu command : unzip -p 2018-03-13-raspbian-stretch-lite.zip | sudo dd of=/dev/sdX bs=4M conv=fsync status=progress Add two files to the boot partition before moving the SD card to the Pi. SSH must be enabled by placing a file named 'ssh', without any extension, onto the boot partition of the SD card. This will allow you to connect from an external device. Network connections must be defined add file named "wpa_supplicant.conf" in the boot partition and fill with network information following tutorial below. Example "wpa_supplicant.conf" for home connection: ctrl_interface=DIR=/var/run/wpa_supplicant GROUP=netdevupdate_config=1country=USnetwork={ ssid="NETWORK_NAME" psk="password"} Now what is the Pi's IP address? Search for the MAC address, all RPi 3 have the same start to their MAC address. (Won't work on enterprise network, ask admin about privliages) Ubuntu command : sudo nmap -sn 192.168.1.0/24 | grep -B 2 B8:27:EB SSH Automatically disabled during initial boot. Enable with sudo raspi-config Then select Interfacing Options → SSH → Enable Home Network Connection Easiest way: sudo raspi-config Select Network Options → Wi-fi then follow on screen instructions. Manual way: Edit wpa_suplicant.conf sudo nano /etc/wpa_supplicant/wpa_supplicant.conf Add the following: network={ ssid="NETWORK_NAME" psk="password"} Then save the file Enterprise Network Connection This is how I connect to my university wifi First create password hash and save to file (keep the single quotes around your password): echo -n 'YOUR_REAL_PASSWORD' | iconv -t utf16le | openssl md4 > hash.txt Then edit wpa_supplicant.conf sudo nano /etc/wpa_supplicant/wpa_supplicant.conf Add the following: network={ ssid="NETWORK_NAME" proto=RSN key_mgmt=WPA-EAP group=CCMP TKIP identity="YOUR_USERNAME" password=hash:5ac87xxxxxxxxxxxxxxxxxxetc phase1="peaplabel=0" phase2="auth=MSCHAPV2"} To add password hash: Move cursor to where you want to place text Press ctrl + r then insert hash.txt file hash.txt contains (stdin)= 5ac87xxxxxxxxxxxxxxxxxxetc replace "(stdin)= " with "hash:" Save the file Clear your bash history history -c Remove hash.txt rm hash.txt Managing Multiple Connections Add priority flags to each network in wpa_supplicant.conf default priority=0 (greatest priority goes first) My prioritized wpa_supplicant.conf: ctrl_interface=DIR=/var/run/wpa_supplicant GROUP=netdevupdate_config=1country=USnetwork={ priority=1 ssid="NETWORK_A" psk="password"}network={ priority=2 ssid="NETWORK_B" proto=RSN key_mgmt=WPA-EAP group=CCMP TKIP identity="YOUR_USERNAME" password=hash:5ac87xxxxxxxxxxxxxxxxxxetc phase1="peaplabel=0" phase2="auth=MSCHAPV2"} There are many more configuration options, run man wpa_supplicant.conf for info. Ad-Hoc Network / Access Point / Bridge Connection You want to wireless connect to the pi but there are no available wireless networks. Create your own! The Raspberry Pi can be set up to broadcast a wireless network. This network allows you to connect the the pi, but will not connect to the internet. Simple Pi to Pi ad-hoc setup On Each Rpi Copy the current file for backup cp /etc/network/interfaces /etc/network/interfaces.old Open file to edit sudo nano /etc/network/interfaces The only line that should be different in the following file is address everything else should be identical. And you may change the name of your network or add a password Append the following on Rpi A: auto wlan0iface wlan0 inet static address 192.168.1.1 netmask 255.255.255.0 wireless-channel 1 wireless-essid MYNETWORK wireless-mode ad-hoc Append the following Rpi B: auto wlan0iface wlan0 inet static address 192.168.1.2 ` netmask 255.255.255.0 wireless-channel 1 wireless-essid MYNETWORK wireless-mode ad-hoc Save the file and exit the editor Raise the interface: sudo ifup wlan0 Scan for ad-hoc networks: iwlist wlan0 scan You may add more devices to the network, you just must assign the device a new different static IP address. The default operating frequency/channel (2.412 GHz: channel 1) is frequently congested. Try using a different channel in the event of difficulties. Change wireless-channel to a different number Use sudo iwlist wlan0 scan to find other channels. src: https://wiki.debian.org/WiFi/AdHoc Less Simple More complicated but will connect to known networks and create ad-hoc if none are found. Follow this tutorial (no ethernet bridge, I have used this successfully) http://www.raspberryconnect.com/network/item/331-raspberry-pi-auto-wifi-hotspot-switch-no-internet-routing hostname -I Run this on Pi, Then I connected from to the second IP address listed via ssh pi@[ipaddr] from my Ubuntu host machine. With ethernet bridge (I have not tested this, but from the same tinkerers as ↑) http://www.raspberryconnect.com/network/item/330-raspberry-pi-auto-wifi-hotspot-switch-internet KNOWN ERRORS: Ssh connection fails from host machine to Pi? run with verbose output: ssh -vvvv [email protected] If the last commands before close are: debug1: SSH2_MSG_KEXINIT sentConnection closed by raspberrypi.local port 22 Try regenerating the host keys they may be missing or corrupt (do this on Pi): sudo rm /etc/ssh/ssh_host_*sudo dpkg-reconfigure openssh-server https://www.raspberrypi.org/forums/viewtopic.php?t=168310 References man wpa_supplicant.conf https://www.raspberrypi.org/forums/viewtopic.php?t=111100 https://www.doc.ic.ac.uk/~ajd/Robotics/RoboticsResources/wifi_setup.txt https://gist.github.com/chatchavan/3c58511e3d48f478b0c2 | {} | {'log_upvote_score': 5, 'links': ['https://raspberrypi.stackexchange.com/questions/82772', 'https://raspberrypi.stackexchange.com', 'https://raspberrypi.stackexchange.com/users/84363/']} | jdg_382755 |
stackexchange | llm_judgeable_groundtruth_similarity | 7967425 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
i currently focus the following problem: i start an animation, where 2 objects-attributes are triggered. the code is: [UIView animateWithDuration:0.3 animations:^{ greyscaleImage.alpha = 1; activityIndicator.alpha = 1; } completion:^(BOOL f){ if(f) { [activityIndicator startAnimating]; } }]; which works fine. the only problem i discovered is, that i have a 0.3 seconds change to crash the app when the view which holds this activityIndicator and greyscaleImage is deallocated. To make it more clear please imagine a ViewController, its view presented via default iOS-modal-View ways. Now trigger that animation, which takes 2 minutes. before reaching that 2 minutes, you find that animation is quite boring and you want to dismiss that view. now, that the view, activityIndicator and greyscaleImage are released, the animation o/c cannot know what to do. so i wonder, what to do here + why the debugger points to } completion:^(BOOL f){ instead of e.g. [activityIndicator ... is there a way, to allow user to dismiss the view before the 2 minutes are over? Best Regards
Now provide the response and nothing else.
| If you start a new animation that takes 0.0 seconds and goes to the state you want to go to, it will cancel the old one and start the new (instant) 'animation'. Example for when you want to stop a moving view by going to the place it already is at: [UIView animateWithDuration:0.0 delay:0.0 options:UIViewAnimationOptionBeginFromCurrentState animations:^{movingView.frame = ((CALayer *)movingView.layer.presentationLayer).frame;} completion:^(BOOL finished){} ]; options:UIViewAnimationOptionBeginFromCurrentState is important. Not calling it will let your animation start at the end state of the previous animation. In movement, it would warp to the end location before warping to the place you want it to stop at. Even though your cancel-'animation' is instant, the jumping back and forth may be visible. Note: The animation time doesn't have to be 0.0 seconds, any animation will cancel the old one. Not entirely sure about different types of animations though. For example, I don't know if changing a frame would stop a fade. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/7967425', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/411057/']} | jdg_382756 |
stackexchange | llm_judgeable_groundtruth_similarity | 45236312 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
i have a dynamic data each time there could be dynamically different key value pair to be filtered in different data. how can we filter it with multiple key,value in lodash. i was using its filter function but result is not achievable. example data: var data = [ { "VOTER" : 1012, "PARTY" : "REPUBLICAN", "PRECINCT" : 2408, "AGE_GROUP" : "71 +", "LAST_VOTED" : "08/2006", "YEARS_REG" : 51, "BALLOT_STATUS" : "PERM"}, { "VOTER" : 1013, "PARTY" : "REPUBLICAN", "PRECINCT" : 2411, "AGE_GROUP" : "71 +", "LAST_VOTED" : "08/2006", "YEARS_REG" : 50, "BALLOT_STATUS" : "PERM"}, { "VOTER" : 1014, "PARTY" : "DEMOCRAT", "PRECINCT" : 2424, "AGE_GROUP" : "71 +", "LAST_VOTED" : "08/2006", "YEARS_REG" : 50, "BALLOT_STATUS" : "PERM"}, { "VOTER" : 1015, "PARTY" : "DEMOCRAT", "PRECINCT" : 2418, "AGE_GROUP" : "71 +", "LAST_VOTED" : "08/2006", "YEARS_REG" : 50, "BALLOT_STATUS" : "POLL" },{ "VOTER" : 1109, "PARTY" : "AMERICAN INDEP", "PRECINCT" : 2404, "AGE_GROUP" : "71 +", "LAST_VOTED" : "08/2006", "YEARS_REG" : 34, "BALLOT_STATUS" : "POLL"},{ "VOTER" : 1111, "PARTY" : "DECLINED", "PRECINCT" : 2414, "AGE_GROUP" : "71 +", "LAST_VOTED" : "08/2006", "YEARS_REG" : 34, "BALLOT_STATUS" : "POLL"}] and filter object is: var filterby = {"PARTY":["REPUBLICAN","DEMOCRAT"],"BALLOT_STATUS":["PERM","POLL"]} Filter function from lodash: var filtered_data = _.filter(data, filterby);
Now provide the response and nothing else.
| You could use plain Javascript and iterate the keys of the filterBy and the values. var data = [{ VOTER: 1012, PARTY: "REPUBLICAN", PRECINCT: 2408, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 51, BALLOT_STATUS: "PERM" }, { VOTER: 1013, PARTY: "REPUBLICAN", PRECINCT: 2411, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 50, BALLOT_STATUS: "PERM" }, { VOTER: 1014, PARTY: "DEMOCRAT", PRECINCT: 2424, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 50, BALLOT_STATUS: "PERM" }, { VOTER: 1015, PARTY: "DEMOCRAT", PRECINCT: 2418, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 50, BALLOT_STATUS: "POLL" }, { VOTER: 1109, PARTY: "AMERICAN INDEP", PRECINCT: 2404, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 34, BALLOT_STATUS: "POLL" }, { VOTER: 1111, PARTY: "DECLINED", PRECINCT: 2414, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 34, BALLOT_STATUS: "POLL" }], filterBy = { PARTY: ["REPUBLICAN", "DEMOCRAT"], BALLOT_STATUS: ["PERM", "POLL"] }, result = data.filter(function (o) { return Object.keys(filterBy).every(function (k) { return filterBy[k].some(function (f) { return o[k] === f; }); }); });console.log(result); .as-console-wrapper { max-height: 100% !important; top: 0; } ES6 var data = [{ VOTER: 1012, PARTY: "REPUBLICAN", PRECINCT: 2408, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 51, BALLOT_STATUS: "PERM" }, { VOTER: 1013, PARTY: "REPUBLICAN", PRECINCT: 2411, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 50, BALLOT_STATUS: "PERM" }, { VOTER: 1014, PARTY: "DEMOCRAT", PRECINCT: 2424, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 50, BALLOT_STATUS: "PERM" }, { VOTER: 1015, PARTY: "DEMOCRAT", PRECINCT: 2418, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 50, BALLOT_STATUS: "POLL" }, { VOTER: 1109, PARTY: "AMERICAN INDEP", PRECINCT: 2404, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 34, BALLOT_STATUS: "POLL" }, { VOTER: 1111, PARTY: "DECLINED", PRECINCT: 2414, AGE_GROUP: "71 +", LAST_VOTED: "08/2006", YEARS_REG: 34, BALLOT_STATUS: "POLL" }], filterBy = { PARTY: ["REPUBLICAN", "DEMOCRAT"], BALLOT_STATUS: ["PERM", "POLL"] }, result = data.filter(o => Object.keys(filterBy).every(k => filterBy[k].some(f => o[k] === f)));console.log(result); .as-console-wrapper { max-height: 100% !important; top: 0; } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/45236312', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3013623/']} | jdg_382757 |
stackexchange | llm_judgeable_groundtruth_similarity | 20704 |
Below is a question asked on the forum skeptics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
The White House claims that: On average, full-time working women earn just 77 cents for every dollar a man earns. Is it the case?
Now provide the response and nothing else.
| It is not as accurate to claim that on average full-time working women earn just 77 cents for every dollar a man earns. A more accurate claim using the proper mathmatical nomenclature would be ... In 2011, the median full-time year-round* working female age 15+ earned 77 percent of what the median full-time year-round working male age 15+ earned. *[25] A full-time, year-round worker (page 20 pdf, labeled page 12) is a person who worked 35 or more hours per week (full time) and 50 or more weeks during the previous calendar year (year round). For school personnel, summer vacation is counted as weeks worked if they are scheduled to return to their job in the fall. The White House website is publishing that statistic that also shows up in their Fifty Years After the Equal Pay Act (FYAtEPA) report. This progress notwithstanding, in 2011, the average woman still earned only 77 cents for every dollar earned by men.[1] The source of the claim, according to the FYAtEPA, comes from the Census Bureau [1] U.S. Census Bureau. “Women's Earnings as a Percentage of Men's Earnings by Race and Hispanic Origin.” Historical Income Tables, Table P-40. (2011). http://www.census.gov/hhes/www/income/data/historical/people/ . Table P-40 notes that the 77.0 percent ratio is a comparison of the median full-time female to median full-time male. (Based on median earnings of full-time, year-round workers 15 years old and over as of March of the following year. [...]) The median and average (mean) are not the same thing, but sometimes the word average is used when a median value is reported for a statistic, because median values have a central tendency and are less skewed by exceptionally high/low values. The more commonly used "average" (mean) full-time working woman's earnings from the Census Bureau, Table P-37. Full-Time, Year-Round Workers by Mean Income and Sex: 1955 to 2012 . Using those figures from 2011, you would determine that a full-time year-round working woman earns on average 72.2 cents (49040 / 67913) for every dollar a full-time year-round working man earns. There is a wide range of criticism over the 77 cent figure. Some reporters even noted the White House's own pay gap , where the average women earns only 91 cents of what the average man working at the White House earns. This comparison of median/mean earnings is on a broad level and does not control for many factors that can be significant in explaining earnings differences. One factor is that women on average work fewer hours then men do. Among full-time workers (that is, those working at a job 35 hours or more per week), men are more likely than women to have a longer workweek. Twenty-six percent of men worked 41 or more hours per week in 2012, compared with 14 percent of women who did so. Women were more likely than men to work 35 to 39 hours per week: 12 percent of women worked those hours in 2012, while 5 percent of men did. There are more women in occupations with lower-pay , and less women in occupations with higher pay. While women are more likely than men to work in professional and related occupations, they are more highly represented in the lower-paying jobs within this category. For example, in 2009, professional women were more likely (nearly 70 percent) to work in the relatively low-paying education (with $887 median weekly earnings) and health care ($970 median weekly earnings) occupations, compared to 32 percent of male professionals. In 2009, only 7 percent of female professionals were employed in the relatively high paying computer ($1,253 median weekly earnings) and engineering fields ($1,266 median weekly earnings), compared to 38 percent of male professionals. Women on average have less work experience than men (page 37). on average, women at every educational level and at every age spend fewer weeks in the labor force than do men. The differences between men and women in labor force attachment are much smaller among those with a college degree or more education. 2 | {} | {'log_upvote_score': 4, 'links': ['https://skeptics.stackexchange.com/questions/20704', 'https://skeptics.stackexchange.com', 'https://skeptics.stackexchange.com/users/14975/']} | jdg_382758 |
stackexchange | llm_judgeable_groundtruth_similarity | 3883131 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
When the enhanced for loop (foreach loop) was added to Java, it was made to work with a target of either an array or Iterable . for ( T item : /*T[] or Iterable<? extends T>*/ ) { //use item} That works great for Collection classes that only implement one type of iteration, and thus have a single iterator() method. But I find myself incredibly frustrated the odd time I want to use a non-standard iterator from a Collection class. For example, I was recently trying to help somebody use a Deque as a LIFO/stack but then print the elements in FIFO order. I was forced to do this: for (Iterator<T> it = myDeque.descendingIterator(); it.hasNext(); ) { T item = it.next(); //use item} I lose the advantages of the for-each loop. It's not just about keystrokes. I don't like exposing the iterator if I don't have to, since it's easy to make the mistake of calling it.next() twice, etc. Now ideally I think the for-each loop should have accepted an Iterator as well. But it doesn't. So is there an idiomatic way of using the for-each loop in these circumstances? I'd also love to hear suggestions that use common collections libraries like Guava. The best I can come up with in absense of a helper method/class is: for ( T item : new Iterable<T>() { public Iterator<T> iterator() { return myDeque.descendingIterator(); } } ) { //use item} Which isn't worth using. I'd love to see Guava have something like Iterables.wrap to make this idiomatic, but didn't find anything like that. Obviously I could roll my own Iterator wrapper via a class or helper method. Any other ideas? Edit: As a side-note, can anybody give a valid reason for why the enhanced for-loop shouldn't have been able to just accept an Iterator ? It would probably go a long way to making me live with the current design.
Now provide the response and nothing else.
| What I'd probably do is just make a utility class called Deques which could support this, along with other utilities if desired. public class Deques { private Deques() {} public static <T> Iterable<T> asDescendingIterable(final Deque<T> deque) { return new Iterable<T>() { public Iterator<T> iterator() { return deque.descendingIterator(); } } }} This is another case where it's really too bad we don't have lambdas and method references yet. In Java 8, you'll be able to write something like this given that the method reference descendingIterator() matches the signature of Iterable : Deque<String> deque = ...for (String s : (Iterable<String>) deque::descendingIterator) { ... } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3883131', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/228171/']} | jdg_382759 |
stackexchange | llm_judgeable_groundtruth_similarity | 414357 |
Below is a question asked on the forum serverfault.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm in the process of trying to setup a couple Win2008 Server Virtual Machines on Windows Azure (using the VM Preview feature) and I'm not sure how to get my desired "architecture" setup properly. Here's what I'm trying to achieve - I want one server that will act only as my database server running MongoDB (I know they say Linux is better, but I'm restricted to Windows for various reasons at this point in time). I want a second server that will act as my webserver. This web application will be ran off node.js. The database server should only accept connections from the web server and only after a handshake has been made, and was successful. I can solve the handshake problem by having a second node.js server running on the database server that basically acts as a Rest API for my database while verifying handshakes and what not. The thing I'm having a problem figuring out is how to make the database server accept connections from only my web server? If we assume I do build the second node.js app for the DB server, is this network configuration even required considering I could build the node app to only accept connections from a certain IP address? Or would it still make sense to maintain this rule somewhere else? I know absolutely nothing about networking so this is all a little over my head right now. I would appreciate any help, guidance, links, etc anyone has to share :)
Now provide the response and nothing else.
| I'll post an answer to my own question, as I have worked out a working solution. Note: I have sacrificed all security via SSH as it wasn't needed for development in my own LAN.Changing DBus to listen on TCP instead unix sockets was also not possible. Step 1 On the remote host with an example IP address 192.168.1.100 (and to which D-Bus I'd like to have access to) I run: socat TCP-LISTEN:7272,reuseaddr,fork UNIX-CONNECT:/var/run/dbus/system_bus_socket Now socat listens for connections on 7272 port and creates a separate thread for each client. This allows multiple connections at the same time. Step 2 On local machine (which I'd like to connect to remote D-Bus) I run: socat ABSTRACT-LISTEN:/tmp/custom_dbus_name,fork TCP:192.168.1.100:7272 This connects to the port exposed remotely with socat and creates a local abstract socket to which we can connect to. Sample usage Python: import dbussysbus = dbus.bus.BusConnection("unix:abstract=/tmp/custom_dbus_name")proxy_obj = sysbus.get_object('com.some.service.name', '/com/some/service/name')my_interface = dbus.Interface(proxy_obj, dbus_interface = 'com.some.interface.name')my_interface.SomeDBusExposedMethod()my_interface.OtherRemoteMethod() D-Feet One can also use D-Feet to browse remote D-Bus services and their methods. It can be done with "File / Connect to other bus" menu option and putting your custom abstract socket name defined in second step. | {} | {'log_upvote_score': 4, 'links': ['https://serverfault.com/questions/414357', 'https://serverfault.com', 'https://serverfault.com/users/130990/']} | jdg_382760 |
stackexchange | llm_judgeable_groundtruth_similarity | 34862068 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a table where a cell can contain a number of icons, as well as text. If icons are present, they appear to the left of the text. There are a couple of possible alignment cases: Only an icon is present: The icon should be centered Only text is present: The text should be left aligned Both icons and text are present: Both the icon and text should be left aligned I thought that I could accomplish this and other more complicated alignments by wrapping everything within the table-cell with a flexbox, using justify-content: center; , and then applying margin-right: auto; to the text div. If there is text, the auto margin will push everything over to the left. If not, the justify-content style will center the icons. Here is a codepen containing my approach. .flexbox { display: flex; flex-direction: row; justify-content: center; border: 2px solid black; width: 300px; height: 17px;}.icon { height: 17px; width: 17px; background-color: red;}.text { margin-right: auto;} <div class="flexbox"> <div class="icon"></div> <div class="text">asdf</div></div> This approach works in Chrome, but the right auto margin is not applied correctly in IE 11. I'm wondering why, and how I can get around it. Extra Information It almost seems as if IE 11 first calculates the auto margins, then aligns the flex items with no regard for those margins whatsoever, and finally applies the margins as best as it can. I believe this because, when justify-content: flex-end; is set on the flexbox and the text div has margin-left: auto; , the icon is right aligned within the flexbox while the text is pushed outside of the bounds of the flexbox by almost the entire width of the flexbox (about what the auto margin should be).
Now provide the response and nothing else.
| As stated in the flexbox specification : Prior to alignment via justify-content and align-self , any positive free space is distributed to auto margins in that dimension. In other words, auto margins have precedence over justify-content . In your example, Chrome appears to be in compliance with the spec. (Firefox, as well.) But IE11 – in cases where the parent has justify-content – is ignoring margin-right: auto on the flex item. This appears to be a bug. When justify-content is removed, auto margins work. One workaround would be to remove justify-content entirely and rely solely on auto margins: Only an icon is present: The icon should be centered .icon { margin: 0 auto; } .flexbox { display: flex; flex-direction: row; border: 2px solid black; width: 300px; height: 17px;}.icon { height: 17px; width: 17px; background-color: red;}.icon { margin: 0 auto;} <div class="flexbox"> <div class="icon"></div></div> Only text is present: The text should be aligned left .text { margin-right: auto; } .flexbox { display: flex; flex-direction: row; border: 2px solid black; width: 300px; height: 17px;}.icon { height: 17px; width: 17px; background-color: red;}.text { margin-right: auto;} <div class="flexbox"> <div class="text">asdf</div></div> Both icons and text are present: Both the icon and text should be aligned left .text { margin-right: auto; } .flexbox { display: flex; flex-direction: row; border: 2px solid black; width: 300px; height: 17px;}.icon { height: 17px; width: 17px; background-color: red;}.text { margin-right: auto;} <div class="flexbox"> <div class="icon"></div> <div class="text">asdf</div></div> | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/34862068', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2577772/']} | jdg_382761 |
stackexchange | llm_judgeable_groundtruth_similarity | 16050564 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm trying to make a "line" of image thumbs, where it scrolls on mousemove. And I got it to work, but my problem now is that i wanted to make a "padding" on the sides so I doesn't have to have the mouse all the way out to the sides to see the first/last thumb. But I really really can't get it to work :/ This is the script I have now: // MouseMove scrolling on thumbsvar box = $('.thumbs-block'), innerBox = $('.thumbs'), lastElement = innerBox.find('a:last-child');var offsetPx = 100;var boxOffset = box.offset().left;var boxWidth = box.width() /* - (offsetPx*2)*/;var innerBoxWidth = (lastElement[0].offsetLeft + lastElement.outerWidth(true)) - boxOffset /* + (offsetPx*2)*/;scrollDelayTimer = null;box.mousemove(function (e) { console.log('boxWidth: ' + boxWidth + ' innerBoxWidth: ' + innerBoxWidth + ' box.scrollLeft(): ' + box.scrollLeft()); var mouseX = e.pageX; var boxMouseX = mouseX - boxOffset; if ((boxMouseX > offsetPx) && (boxMouseX < (boxWidth - offsetPx))) { var left = (boxMouseX * (innerBoxWidth - boxWidth) / boxWidth) /* - offsetPx*/; clearTimeout(scrollDelayTimer); scrollDelayTimer = setTimeout(function () { scrollDelayTimer = null; box.stop().animate({ "scrollLeft": left }, { queue: false, duration: 500, easing: 'linear' }); }, 10); }}); There are some of the places I've tried adding the offset (commented out inline), some of it gets it working in one end but not the other :/ I'm pretty sure it's a problem in the math, but I can't figure out what I should do :/ Here's a jsFiddle: http://jsfiddle.net/6CJfs/1/ I hope I made my problem clear enough, not sure how to explain it otherwise, and hope someone can help :)
Now provide the response and nothing else.
| You script is not smooth, so I modified it completely (sorry :) with a really simple approach: $(function() { const $bl = $(".thumbs-block"), $th = $(".thumbs"), blW = $bl.outerWidth(), blSW = $bl.prop("scrollWidth"), wDiff = (blSW / blW) - 1, // widths difference ratio mPadd = 60, // Mousemove Padding damp = 20; // Mousemove response softness let posX = 0, mX2 = 0, // Modified mouse position mmAA = blW - (mPadd * 2), // The mousemove available area mmAAr = (blW / mmAA), // get available mousemove fidderence ratio itv = null; const anim = () => { posX += (mX2 - posX) / damp; // zeno's paradox equation "catching delay" $th.css({ transform: `translateX(${-posX * wDiff}px)` }); }; $bl.on("mousemove", function(e) { const mouseX = e.pageX - $(this).prop("offsetLeft"); mX2 = Math.min(Math.max(0, mouseX - mPadd), mmAA) * mmAAr; }).on("mouseenter", function(e) { itv = setInterval(anim, 10); }).on("mouseleave", function() { clearInterval(itv); });}); .thumbs-block { position: relative; overflow: hidden; max-width: 100%;}.thumbs-block .thumbs { display: flex; flex-flow: row nowrap;} <div class="thumbs-block"> <div class="thumbs"> <a class="thumb"><img src="http://placehold.it/120x120/0bf&text=01" /></a> <a class="thumb"><img src="http://placehold.it/120x120/f0b&text=02" /></a> <a class="thumb"><img src="http://placehold.it/120x120/bf0&text=03" /></a> <a class="thumb"><img src="http://placehold.it/120x120/b0f&text=04" /></a> <a class="thumb"><img src="http://placehold.it/120x120/fb0&text=05" /></a> <a class="thumb"><img src="http://placehold.it/120x120/0fb&text=06" /></a> <a class="thumb"><img src="http://placehold.it/120x120/0bf&text=07" /></a> <a class="thumb"><img src="http://placehold.it/120x120/f0b&text=08" /></a> <a class="thumb"><img src="http://placehold.it/120x120/bf0&text=09" /></a> <a class="thumb"><img src="http://placehold.it/120x120/b0f&text=10" /></a> <a class="thumb"><img src="http://placehold.it/120x120/fb0&text=11" /></a> <a class="thumb"><img src="http://placehold.it/120x120/0fb&text=12" /></a> </div></div><script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script> | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/16050564', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1155596/']} | jdg_382762 |
stackexchange | llm_judgeable_groundtruth_similarity | 40112711 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have converted my codes to swift 3 and I have submitted to app store. When they open app, it crash at first time. As a result, I check my crashlog and it crash at this line. if let myLaunchOptions: NSDictionary = launchOptions as NSDictionary? { My overall code is like this. I know that launchOptions can be nil and it might not even be NSDictionary. That's why I have checked like that and it fail at that line. May I know how else to check/prevent with swift 3? func application(_ application: UIApplication, didFinishLaunchingWithOptions launchOptions: [UIApplicationLaunchOptionsKey: Any]?) -> Bool { if let myLaunchOptions: NSDictionary = launchOptions as NSDictionary? { let test = myLaunchOptions[UIApplicationLaunchOptionsKey.userActivityDictionary] as! NSDictionary let userActivity = test["UIApplicationLaunchOptionsUserActivityKey"] as! NSUserActivity NSLog("test1:" + String(describing: userActivity)) continueUserActivity(userActivity) } My crash log is here.
Now provide the response and nothing else.
| You should be checking and obtaining user activity like this: func application(_ application: UIApplication, didFinishLaunchingWithOptions launchOptions: [UIApplicationLaunchOptionsKey: Any]?) -> Bool { if let userActivityDictionary = launchOptions?[.userActivityDictionary] as? [UIApplicationLaunchOptionsKey : Any], let userActivity = userActivityDictionary[.userActivityType] as? NSUserActivity { continueUserActivity(userActivity) } return true} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/40112711', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1550974/']} | jdg_382763 |
stackexchange | llm_judgeable_groundtruth_similarity | 244243 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I ran into the problem that my primary key sequence is not in sync with my table rows. That is, when I insert a new row I get a duplicate key error because the sequence implied in the serial datatype returns a number that already exists. It seems to be caused by import/restores not maintaining the sequence properly.
Now provide the response and nothing else.
| -- Login to psql and run the following-- What is the result?SELECT MAX(id) FROM your_table;-- Then run...-- This should be higher than the last result.SELECT nextval('your_table_id_seq');-- If it's not higher... run this set the sequence last to your highest id. -- (wise to run a quick pg_dump first...)BEGIN;-- protect against concurrent inserts while you update the counterLOCK TABLE your_table IN EXCLUSIVE MODE;-- Update the sequenceSELECT setval('your_table_id_seq', COALESCE((SELECT MAX(id)+1 FROM your_table), 1), false);COMMIT; Source - Ruby Forum | {} | {'log_upvote_score': 11, 'links': ['https://Stackoverflow.com/questions/244243', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4196/']} | jdg_382764 |
stackexchange | llm_judgeable_groundtruth_similarity | 39160 |
Below is a question asked on the forum mathematica.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I want to visualize the difference between members of a set: set = {20, 36, 70, 96, 152, 301} This way I get the diffs: diffs = Select[#[[2]] - #[[1]] & /@ Tuples[{set, set}], # > 0 &]{16, 50, 76, 132, 281, 34, 60, 116, 265, 26, 82, 231, 56, 205, 149} But how can I put the diffs as a caption over graph like lines between members?
Now provide the response and nothing else.
| Borrowing some code from Kuba's: set = {20, 36, 70, 96, 152, 301}Graph[DirectedEdge @@@ #, VertexShapeFunction -> "Square", VertexSize -> {.2, .1}, VertexLabels -> Placed["Name", Center], VertexLabelStyle -> Directive[FontFamily -> "Arial", 10], GraphLayout -> "CircularEmbedding", EdgeLabels -> ((DirectedEdge[##] -> Placed[#2 - #, .85]) & @@@ #)] &@Subsets[set, {2}] Edit In fact, you could apply any nice formatting to the edges. The following applies a color proportional to its value: set = {20, 36, 70, 96, 152, 301};{min, max} = {Min@#, Max@#} &[Subtract @@@ -Subsets[set, {2}]]Graph[Property[DirectedEdge @@ #, EdgeStyle -> {Thick, ColorData["Rainbow"][ Rescale[#[[2]] - #[[1]], {min, max}]]}] & /@ #, VertexShapeFunction -> "Square", VertexSize -> {.2, .1}, VertexLabels -> Placed["Name", Center], VertexLabelStyle -> Directive[FontFamily -> "Arial", 10], GraphLayout -> "CircularEmbedding", EdgeLabels -> ((DirectedEdge[##] -> Placed[#2 - #, .85]) & @@@ #)] &@Subsets[set, {2}] | {} | {'log_upvote_score': 4, 'links': ['https://mathematica.stackexchange.com/questions/39160', 'https://mathematica.stackexchange.com', 'https://mathematica.stackexchange.com/users/4752/']} | jdg_382765 |
stackexchange | llm_judgeable_groundtruth_similarity | 60018 |
Below is a question asked on the forum biology.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I've been reading my textbook and it refers to prions as a normal protein with a helpful function but it can turn into a disease causing form. However, I look in my other textbook and it refers to the word prion as solely being a disease causing protein. I'd like to know which is the correct definition. Ie. Would I be correct in saying "The prion protein is normally involved in synaptic transmission but can turn into a disease causing form"? Thanks in advance!
Now provide the response and nothing else.
| The normal isoform of the protein is called PrP C , which stands for cellular prion protein , while the infectious isoform is called PrP SC , which stands for scrapie prion protein . According to Riesner (2003): The biochemical properties of the prion protein which is the major, if not only, component of the prion are outlined in detail. PrP is a host-encoded protein which exists as PrP C (cellular) in the non-infected host, and as PrP Sc (scrapie) as the major component of the scrapie infectious agent. (emphasis mine) If you search for "cellular prion protein" you're gonna find several papers that use the name prion protein to the normal isoform. Some examples: Prado, M., Alves-Silva, J., Magalhães, A., Prado, V., Linden, R., Martins, V. and Brentani, R. (2004). PrPc on the road: trafficking of the cellular prion protein. Journal of Neurochemistry, 88(4), pp.769-781 . Ramljak, S. (2008). Physiological function of the cellular prion protein (PrPc_1hnc). 1st ed. Berlin: Logos-Verl . Pantera, B., Bini, C., Cirri, P., Paoli, P., Camici, G., Manao, G. and Caselli, A. (2009). PrP c activation induces neurite outgrowth and differentiation in PC12 cells: role for caveolin-1 in the signal transduction pathway. Journal of Neurochemistry, 110(1), pp.194-207 . Martins, V., Mercadante, A., Cabral, A., Freitas, A. and Castro, R. (2017). Insights into the physiological function of cellular prion protein . And many others. Therefore, following this nomenclature, the answer to your question ( "Would I be correct in saying 'The prion protein is normally involved in synaptic transmission but can turn into a disease causing form'?" ) is yes . The difference is the adjective: cellular or scrapie. Finally, pay attention to this: you have two different questions here. In the title you say "Is prion a term used..." , but in the last paragraph you say ""Is the prion protein normally involved in..." . As extensively discussed in the other answer , the term prion alone (instead of prion protein ) is normally used only when referring to the abnormal isoform. More on that here: https://www.cdc.gov/prions/pdfs/public-health-impact.pdf Source: Detlev Riesner; Biochemistry and structure of PrPC and PrPSc. Br Med Bull 2003; 66 (1): 21-33 . | {} | {'log_upvote_score': 6, 'links': ['https://biology.stackexchange.com/questions/60018', 'https://biology.stackexchange.com', 'https://biology.stackexchange.com/users/32267/']} | jdg_382766 |
stackexchange | llm_judgeable_groundtruth_similarity | 8947423 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am in the process of introducing a Dependency Injection framework into an existing WebForms application (using Castle Windsor). I have pretty deep experience with DI, and tend to very strongly favor constructor injection over setter injection. If you are familiar with Webforms, you know that the ASP.Net framework handles the construction of page and control objects, making true constructor injection impossible. My current solution is to register the container in the Application_Start event of the Global.asax, and keep the container as a public static variable in Global as well. I then simply resolve each service that I need directly in the page or control when I need them. So at the top of each page, I end up with code like this: private readonly IMyService _exposureManager = Global.IoC.Resolve<IMyService>();private readonly IMyOtherService _tenCustomersExposureManager = Global.IoC.Resolve<IMyOtherService>(); Obviously, I don't like having all these references to the container scattered about my application or having my page/control dependencies be non-explicit, but I have not been able to find a better way. Is there a more elegant solution for using DI with Webforms?
Now provide the response and nothing else.
| I agree with @DarinDimitrov that MVP is an interesting option. However, when working with a legacy application, rewriting an existing page to the MVP pattern is a hell of a job. In that case it might be better to start with the Service Locator pattern (but only in your UI classes) as you are already doing. However, do change one thing. Do not expose the chosen DI container to the application, as I expect you are doing with the Global.IoC property. Instead, create a static Resolve<T> method on the Global class. This hides the container completely and allows you to swap implementations without having to change anything in your web pages. When you do this, there is no advantage in using the Common Service Locator as @Wiktor proposes. The Common Service Locator is just another abstraction for something that doesn't have to be abstracted (since you've already abstracted away the container using the Global.Resolve<T> ). Unfortunately with Web forms, there is not really any good way to do this. For Simple Injector , I wrote an integration guide for Web Forms that basically describes the use of the Global.Resolve<T> method, but also shows a way to tests if Page classes can be created. The guide can be used for other DI containers as well. BTW, please keep in mind that with Castle Windsor, everything you request must be released explicitly (the Register Resolve Release pattern ). This is a bit nasty (IMO) and differs from how other containers work and can be a source of memory leaks when you do not do this correctly. Last note. It is possible to do constructor injection with Web Forms . Well... sort of, since this will call the overloaded constructor using reflection after the Form has been created using the default constructor, so this causes Temporal Coupling . | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/8947423', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/151084/']} | jdg_382767 |
stackexchange | llm_judgeable_groundtruth_similarity | 19822700 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I've created a serial queue like this: dispatch_queue_t _serialQueue = dispatch_queue_create("com.example.name", DISPATCH_QUEUE_SERIAL); What's the difference between dispatch_async called like this dispatch_async(_serialQueue, ^{ /* TASK 1 */ }); dispatch_async(_serialQueue, ^{ /* TASK 2 */ }); And dispatch_sync called like this on this serial queue? dispatch_sync(_serialQueue, ^{ /* TASK 1 */ }); dispatch_sync(_serialQueue, ^{ /* TASK 2 */ }); My understanding is that, regardless of which dispatch method is used, TASK 1 will be executed and completed before TASK 2 , correct?
Now provide the response and nothing else.
| Yes. Using serial queue ensure the serial execution of tasks. The only difference is that dispatch_sync only return after the block is finished whereas dispatch_async return after it is added to the queue and may not finished. for this code dispatch_async(_serialQueue, ^{ printf("1"); });printf("2");dispatch_async(_serialQueue, ^{ printf("3"); });printf("4"); It may print 2413 or 2143 or 1234 but 1 always before 3 for this code dispatch_sync(_serialQueue, ^{ printf("1"); });printf("2");dispatch_sync(_serialQueue, ^{ printf("3"); });printf("4"); it always print 1234 Note: For first code, it won't print 1324 . Because printf("3") is dispatched after printf("2") is executed. And a task can only be executed after it is dispatched. The execution time of the tasks doesn't change anything. This code always print 12 dispatch_async(_serialQueue, ^{ sleep(1000);printf("1"); });dispatch_async(_serialQueue, ^{ printf("2"); }); What may happened is Thread 1: dispatch_async a time consuming task (task 1) to serial queue Thread 2: start executing task 1 Thread 1: dispatch_async another task (task 2) to serial queue Thread 2: task 1 finished. start executing task 2 Thread 2: task 2 finished. and you always see 12 | {} | {'log_upvote_score': 10, 'links': ['https://Stackoverflow.com/questions/19822700', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1648724/']} | jdg_382768 |
stackexchange | llm_judgeable_groundtruth_similarity | 1250474 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Question: I want to prove that $F_{kn}$ is a multiple of $F_n$. Approach: I have to deduce this result from the following results: $$F_{n+k} = F_{k}F_{n+1} + F_{k-1}F_{n}$$ I have shown the result by induction on $k$. I want to know if it's possible to prove it via induction on $n$ instead. I have tried but get into a mess. Is there anything I need to be careful about when choosing which variable to carry out the induction on? Thanks.
Now provide the response and nothing else.
| In fact your formula can be written:$$F_{n+k+1} = F_{k+1}F_{n+1} + F_{k}F_{n}$$ and this is symmetric on $k$ and $n$ so the same argument works also, (you can only change $k$ on $n$ and $n$ on $k$ and your first proof becomes an induction on $n$) | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1250474', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/104193/']} | jdg_382769 |
stackexchange | llm_judgeable_groundtruth_similarity | 3142283 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Find all $x$ in the interval $(0,\pi/2)$ such that $\frac{\sqrt{3}-1}{\sin x}+\frac{\sqrt{3}+1}{\cos x}=4\sqrt{2}$ . The options are (i) $\pi/9,2\pi/7$ , (ii) $\pi/36,11\pi/12$ (iii) $\pi/12,11\pi/36$ (iv) All I have been able to find one value of $x$ , $\pi/12$ . How do I find the other root(s)? My attempt : $\frac{\sqrt{3}-1}{\sin x}+\frac{\sqrt{3}+1}{\cos x}=4\sqrt{2}$ or, $\frac{\sin\pi/3-\sin\pi/6}{\sin x}+\frac{\cos\pi/6+\cos\pi/3}{\cos x}=2\sqrt{2}$ or, $\frac{\sin(\pi/4)cos(\pi/12)}{\sin x}+\frac{\cos(\pi/4)cos(\pi/12)}{\cos x}=\sqrt{2}$ or, $\sin(x+\pi/12)=\sin2x$ or, $x=\pi/12$
Now provide the response and nothing else.
| Be careful that your final equation has more potential solutions. The equation $$ \sin \left(x + \frac{\pi}{12}\right) = \sin 2x$$ implies in fact $$ x + \frac{\pi}{12} = 2x + 2k \pi$$ or $$ x + \frac{\pi}{12} = \pi - 2x + 2k \pi.$$ Also recall that you can always check the number of solutions by intersecting $$ \frac{\sqrt 3 -1}{Y} + \frac{\sqrt 3 +1}{X}=4 \sqrt 2$$ with the unit circle $$X^2+Y^2 = 1.$$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/3142283', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/351620/']} | jdg_382770 |
stackexchange | llm_judgeable_groundtruth_similarity | 25570712 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a json like this: json1 : { "field1": 111111, "field2": "someValue"} How can I wrap it in "requestBody" field into json2 like a string? json2 : { "requestBody": json1 } Something like this: { "requestBody": "{"field1": 111111,"field2": "someValue"}"}
Now provide the response and nothing else.
| JSON-encoded stuff is just a string. If you want to embed json-in-json, then the "inner" json has to be encoded into json itself. e.g. $inner = {"foo":"bar"}$outer = {"container":"{\"foo\":\"bar\"}"} Now the inner json isn't json anymore. It's just a string that happens to kinda/sorta look like JSON. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/25570712', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/495799/']} | jdg_382771 |
stackexchange | llm_judgeable_groundtruth_similarity | 13947327 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have to dump large amount of data from file to a table PostgreSQL. I know it does not support 'Ignore' 'replace' etc as done in MySql. Almost all posts regarding this in the web suggested the same thing like dumping the data to a temp table and then do a 'insert ... select ... where not exists...'. This will not help in one case, where the file data itself contained duplicate primary keys.Any body have an idea on how to handle this in PostgreSQL? P.S. I am doing this from a java program, if it helps
Now provide the response and nothing else.
| Use the same approach as you described, but DELETE (or group, or modify ...) duplicate PK in the temp table before loading to the main table. Something like: CREATE TEMP TABLE tmp_table ON COMMIT DROPASSELECT * FROM main_tableWITH NO DATA;COPY tmp_table FROM 'full/file/name/here';INSERT INTO main_tableSELECT DISTINCT ON (PK_field) *FROM tmp_tableORDER BY (some_fields) Details: CREATE TABLE AS , COPY , DISTINCT ON | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/13947327', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1579008/']} | jdg_382772 |
stackexchange | llm_judgeable_groundtruth_similarity | 66601 |
Below is a question asked on the forum emacs.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
C-h b shows the key bindings. But I can not see, which prefix is left for my own functions. Is any prefix reserved for user bindings?
Now provide the response and nothing else.
| As stated in the manual : A small number of keys are reserved for user-defined bindings, and should not be used by modes, so key bindings using those keys are safer in this regard. The reserved key sequences are those consisting of C-c followed by a letter (either upper or lower case), and function keys F5 through F9 without modifiers In practice, C-S- letter is not officially reserved but I don't remember ever seeing a mode using it. Additionally, some standard bindings on control-letter combinations tend not to be useful because you can use the arrow keys instead. This gives you C-p , C-n , C-b and C-f . Also C-a and C-e if you have Home and End keys. And all standard bindings only use the modifiers Ctrl , Shift and Meta ( C , S , M ) (or if there's any standard binding using another modifier, it duplicates another binding because those are the only three modifiers that everyone has), so if there's another modifier on your keyboard and it isn't reserved by your window manager, you can use that. You can also free Ctrl + H , Ctrl + I , Ctrl + J and Ctrl + [ by using Tab , BackSpace , Return and Escape instead, however those are trickier to use because the function keys are processed as the control-character combinations in Emacs. For example, TAB is the same thing as C-i , so if you want to give Ctrl + I its own binding, you have to re-route it to something that is not C-i . See How to bind C-i as different from TAB? | {} | {'log_upvote_score': 4, 'links': ['https://emacs.stackexchange.com/questions/66601', 'https://emacs.stackexchange.com', 'https://emacs.stackexchange.com/users/2787/']} | jdg_382773 |
stackexchange | llm_judgeable_groundtruth_similarity | 4846562 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
According to the docs, fprintf can fail and will return a negative number on failure. There are clearly many situations where it would be useful to check this value. However, I usually use fprintf to print error messages to stderr. My code will usually look something like this: rc = foo();if(rc) { fprintf(stderr, "An error occured\n"); //Sometimes stuff will need to be cleaned up here return 1;} In these cases, is it still possible for fprintf to fail? If so, is there anything that can be done to display the error message somehow or is there is a more reliable alternative to fprintf? If not, is there any need to check fprintf when it is used in this way?
Now provide the response and nothing else.
| The C standard says that the file streams stdin , stdout , and stderr shall be connected somewhere, but they don't specify where, of course.(C11 §7.21.3 Files ¶7 : At program startup, three text streams are predefined and need not be opened explicitly -- standard input (for reading conventional input), standard output (for writing conventional output), and standard error (for writing diagnostic output). As initially opened, the standard error stream is not fully buffered; the standard input and standard output streams are fully buffered if and only if the stream can be determined not to refer to an interactive device. It is perfectly feasible to run a program with the standard streams redirected: some_program_of_yours >/dev/null 2>&1 </dev/null Your writes will succeed - but the information won't go anywhere. A more brutal way of running your program is: some_program_of_yours >&- 2>&- </dev/null This time, it has been run without open file streams for stdout and stderr — in contravention of the the standard. It is still reading from /dev/null in the example, which means it doesn't get any useful data input from stdin . Many a program doesn't bother to check that the standard I/O channels are open. Many a program doesn't bother to check that the error message was successfully written. Devising a suitable fallback as outline by Tim Post and whitey04 isn't always worth the effort. If you run the ls command with its outputs suppressed, it will simply do what it can and exits with a non-zero status: $ ls; echo $?gls0$ ls >&- 2>&-; echo $?2$ (Tested RHEL Linux.) There really isn't a need for it to do more. On the other hand, if your program is supposed to run in the background and write to a log file, it probably won't write much to stderr , unless it fails to open the log file (or spots an error on the log file). Note that if you fall back on syslog(3) (or POSIX ), you have no way of knowing whether your calls were 'successful' or not; the syslog functions all return no status information. You just have to assume that they were successful. It is your last resort, therefore. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/4846562', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/236587/']} | jdg_382774 |
stackexchange | llm_judgeable_groundtruth_similarity | 7605707 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
My lower level knowledge of SQL (Server 2008) is limited, and is now being challanged by our DBAs. Let me explain (I have mentioned obvious statements in the hope that I am right, but if you see something wrong, please tell me) the scenario: We have a table which holds 'Court Orders' for people. When I created the table, (Name: CourtOrder), I created it like: CREATE TABLE dbo.CourtOrder( CourtOrderID INT NOT NULL IDENTITY(1,1), (Primary Key) PersonId INT NOT NULL, + around 20 other fields of different types.) I then applied a non-clustered index to the primary key (for efficiency). My reasons is that it is a unique field (primary key), and should be indexed, mainly for selection purposes, as we often Select from table where primary key = ... I then applied a CLUSTERED index on PersonId. The reason was to group orders for a particular person physically, as the vast majority of work is getting orders for a person. So, select from mytable where personId = ... I have been pulled up on this now. I have been told that we should put the clustered index on the primary key, and the normal index on the personId. That seems very strange to me. First off, why would you put a clustered index on a unique column? what is it clustering? Surely that's a waste of the clustered index? I'd have believed a normal index would be used on a unique column. Also, clustering the index would mean we can't cluster a different column (One per table, right?). The reasoning for me being told I have made a mistake is that they believe putting a clustered index on the PersonId would make inserts slow. For the 5% gain in speed of a select, we would be getting a 95% degradation in speed on inserts and updates. Is that correct and valid? They say that because we cluster the personId, SQL Server has to rearrange data when ever we insert or make a change to the PersonId. So then I have asked, why would SQL have the concept of a CLUSTERED INDEX, if it's so slow? Is it as slow as they're saying? How should I have setup my indexes to achieve optimum performance? I'd have thought SELECT is used more than INSERT... but they say that we're having locking issues on INSERTS... Hope someone can help me.
Now provide the response and nothing else.
| The distinction between a clustered vs. non-clustered index is that the clustered index determines the physical order of the rows in the database . In other words, applying the clustered index to PersonId means that the rows will be physically sorted by PersonId in the table, allowing an index search on this to go straight to the row (rather than a non-clustered index, which would direct you to the row's location, adding an extra step). That said, it's unusual for the primary key not to be the clustered index, but not unheard of. The issue with your scenario is actually the opposite of what you're assuming: you want unique values in a clustered index, not duplicates. Because the clustered index determines the physical order of the row, if the index is on a non-unique column, then the server has to add a background value to rows who have a duplicate key value (in your case, any rows with the same PersonId ) so that the combined value (key + background value) is unique. The only thing I would suggest is not using a surrogate key (your CourtOrderId ) column as the primary key, but instead use a compound primary key of the PersonId and some other uniquely-identifying column or set of columns. If that's not possible (or not practical), though, then put the clustered index on CourtOrderId . | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/7605707', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/560660/']} | jdg_382775 |
stackexchange | llm_judgeable_groundtruth_similarity | 13228995 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Going nuts with this issue. I have a solution with 2 projects, one of them is a plain old html with jquery ajax call while the other is a WCF service. The html page will issue a ajax call to the WCF service to get a json string and use it for display purpose. Now the issue is whenever i run in debug mode, both the html page and the WCF will be started with different port. And this has created a cross-origin issue for me when i perform testing (i.e. getting a 405 Method Not Allowed error with the calling type = OPTIONS in Firefox). I'd triple check the call method on my ajax script and the WCF service is the same (GET). I'd search google but found that either i have to install a extension or perform some configuration on IIS, which i found cumbersome since what i'm doing is something simple. Following one example, I'd add in the following configuration in my web.config but it didn't work: <system.serviceModel> <bindings> <webHttpBinding> <binding name="crossDomain" crossDomainScriptAccessEnabled="true" /> </webHttpBinding> </bindings> <behaviors> <endpointBehaviors> <behavior name="MobileService.webHttpBehavior"> <webHttp /> </behavior> </endpointBehaviors> <serviceBehaviors> <behavior name="MyServiceBehavior"> <serviceMetadata httpGetEnabled="true" /> <serviceDebug includeExceptionDetailInFaults="true"/> </behavior> </serviceBehaviors> </behaviors> <serviceHostingEnvironment aspNetCompatibilityEnabled="true" multipleSiteBindingsEnabled="true" /> <services> <service name="MobileService.SimpleMemberInfo" behaviorConfiguration="MyServiceBehavior"> <endpoint address="" binding="webHttpBinding" contract="MobileService.IMemberInfo" bindingConfiguration="crossDomain" behaviorConfiguration="MobileService.webHttpBehavior"> </endpoint> </service> </services> </system.serviceModel> <system.webServer> <httpProtocol> <customHeaders> <add name="Access-Control-Allow-Origin" value="*" /> <add name="Access-Control-Allow-Methods" value="GET" /> <add name="Access-Control-Allow-Headers" value="Content-Type, Accept" /> </customHeaders> </httpProtocol> <modules runAllManagedModulesForAllRequests="true"/> <directoryBrowse enabled="true"/> </system.webServer> Any one has any idea to get rid of this annoying issue? EDIT: Just to add, I'm running the debug with IIS Express that comes together with the VS Studio 2012 Add in WCF Code and Updated web.config [ServiceContract]public interface IMemberInfo{ [WebInvoke(Method = "GET", BodyStyle = WebMessageBodyStyle.Wrapped, ResponseFormat = WebMessageFormat.Json )] [OperationContract] string GetMemberInfoById(); // TODO: Add your service operations here} My Script: $(document).ready(function () { $.ajax("http://localhost:32972/SimpleMemberInfo.svc/GetMemberInfoById", { cache: false, beforeSend: function (xhr) { $.mobile.showPageLoadingMsg(); }, complete: function () { $.mobile.hidePageLoadingMsg(); }, contentType: 'application/json', dataType: 'json', type: 'GET', error: function () { alert('Something awful happened'); }, success: function (data) { var s = ""; s += "<li>" + data + "</li>"; $("#myList").html(s); } });});
Now provide the response and nothing else.
| You need to use JSONP for a cross-domain call to get round the browser restrictions, and to update your web.config with crossDomainScriptAccessEnabled set to true to get round server ones. There's a good example in the answer here: how to avoid cross domain policy in jquery ajax for consuming wcf service? You may also have a problem with GET requests. Try the fixes outlined here: Making a WCF Web Service work with GET requests Altogether, you want a web.config that looks something like this: <bindings> <webHttpBinding> <binding name="crossDomain" crossDomainScriptAccessEnabled="true" /> </webHttpBinding></bindings><behaviors> <endpointBehavior> <behavior name="restBehavior"> <webHttp /> </behavior> </endpointBehavior> <serviceBehavior> <behavior name="MyServiceBehavior"> <serviceMetadata httpGetEnabled="true" /> <serviceDebug includeExceptionDetailInFaults="true"/> </behavior> </serviceBehavior></behaviors><services> <service name="..." behaviorConfiguration="MyServiceBehavior"> <endpoint address="" binding="webHttpBinding" bindingConfiguration="crossDomain" contract="..." behaviorConfigurations="restBehavior" /> </service></services> (Note that both the service and the endpoint have behaviours attached, allowing webHttp calls and httpGet calls respectively, and that the binding has crossDomain access explicitly enabled). ... a service method decorated like this: [ServiceContract]public interface IMyService{ [WebGet] // Required Attribute to allow GET [OperationContract] string MyMethod(string MyParam);} ... and a client call using JSONP: <script type="text/javascript">$(document).ready(function() { var url = "..."; $.getJSON(url + "?callback=?", null, function(result) { // Note crucial ?callback=? // Process result });});</script> | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/13228995', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1158142/']} | jdg_382776 |
stackexchange | llm_judgeable_groundtruth_similarity | 52650895 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I tried to use the internal Logger of nestjs (described on https://docs.nestjs.com/techniques/logger -> but with no description of how to use it) But I had problems (tried to inject LoggerService and so on) Can anybody explain how to do this?
Now provide the response and nothing else.
| Best practice Better than accessing the Logger statically is to create an instance for your class: @Controller()export class AppController { private readonly logger = new Logger(AppController.name); @Get() async get() { this.logger.log('Getting stuff'); }} Why is this better? You can provide a context in the constructor like new Logger(AppController.name) so that the class name (or anything else) will be part of all log messages in this class. If you at some point want to extend or replace the default LoggerService , you do not need to change any of your application code besides setting the new logger. Your new logger will automatically be used. If you access it statically it will continue to take the default implementation. const app = await NestFactory.create(AppModule, {logger: new MyLogger()}); You can mock the Logger in your tests: module.useLogger(new NoOpLogger()); | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/52650895', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3463013/']} | jdg_382777 |
stackexchange | llm_judgeable_groundtruth_similarity | 81730 |
Below is a question asked on the forum datascience.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
When I add regularization techniques in my model like L1 or L2 do i need more epochs to properly converge my model. for r in (None,"L1","L2"): for max_iter in (30,45,60): classifier=SGDClassifier(loss="log",penalty=r,max_iter=max_iter,learning_rate="constant",eta0=0.01,random_state=42) print("max_iter={}".format(max_iter)) classifier.fit(X_train,Y_train) acc=classifier.score(X_test,Y_test) print("accuracy when r={} is {}".format(r,acc*100)) When r = None: max_iter = 30/45 it says ConvergenceWarning: Maximum number of iteration reached before convergence. Consider increasing max_iter to improve the fit. max_iter = 60 no warning. When r = L1: max_iter= 30 same warning. max_iter = 45/60 no warning. When r= L2: max_iter = 30/45/60 same warning Does it matter or this is random?
Now provide the response and nothing else.
| The convergence time is sensitive to the data you have and a random seed. Specifically, the convergence time is linear in expectation in all three cases. SGDClassifier uses the stochastic gradient descent for optimization. Since L1 loss is only subdifferential, the L1 penalty causes the algorithm to converge noticeably slower. Comparing with or without the L2 penalty, it is not clear what algorithm is faster. The loss function is differential. The L2 penalty may be faster in the underdetermined case. In the example below, I consider the gradient descent instead of the stochastic linear descent and regular regression to simplify the argument. Say, we aim to solve y = Xb + e, where we observe y and X only. We set the loss function to be f(b) = 0.5||y - Xb||^2. Without regularization, the solution is sol1 =(X^TX)^{-1}X^Ty and with L2 regularization, the solution is sol2 = (X^TX + lambda I)^{-1}X^Ty . In the latter case, we can guarantee that the matrix to invert is not close to singular, and, therefore, the faster convergence is expected. In short, on average, I would expect the following number of iterations requires from smallest to largest ON AVERAGE: L2 penalty No penalty (potentially, with a close tie with L2 penalty) L1 penalty You observe the opposite order. It should be very specific to your data or random seed. | {} | {'log_upvote_score': 4, 'links': ['https://datascience.stackexchange.com/questions/81730', 'https://datascience.stackexchange.com', 'https://datascience.stackexchange.com/users/98121/']} | jdg_382778 |
stackexchange | llm_judgeable_groundtruth_similarity | 508830 |
Below is a question asked on the forum serverfault.com. Provide a good and informational response to it like a helpful human would.
Question:
Im looking into the cost of putting a Cassandra cluster into a colo facility. Along these lines there would be 6-8 servers at the outset with expected growth over time. One option is just a series of Dell R320 (or similar). Another option would be blades or similarly built machines that share power. Looking at the details of an 8 node system I see it has 4x1620 watt power supplies. This gives a total of 6480 watts. If I have a rack with 208V this means I'm pulling more than 30A at peak. So I've maxed out my 42U rack in 6U of space. I realize this is 'peak load' but it seems a bit extreme. Am I misunderstanding how this calculation works? I get VA=W and I get that it won't pull this kind of load but 30A is a lot of current. I don't have the luxury of buying one and using a kill-a-watt to accurately measure it. The specs for the system don't make it sound like these are redundant but that's a tremendous amount of current. Has anyone deployed blades or multi-node servers and measured the required current? I'd love to get a Dell M1000 but the prospect of trying to budget for 40A just makes me need to lie down. EDIT If I use a kill-a-watt to measure the input current for a system with n power supplies - do I sum them? Are they all pulling 1/n?
Now provide the response and nothing else.
| Yes, blades are dense. :) You need to use a power budgeting tool to determine maximum power draw of your particular hardware configuration . Your reseller should be helping you with this. (since that's what I do :) Multiple power supplies can have quite a few possible scenarios: N+N configuration: Maximum power draw of N×Wattage power. N+1 configuration: Maximum power draw of N×Wattage power. N, non-redundant: Maximum power draw of N×Wattage power. N+X configuration, throttling allowed: Maximum power draw of N×Wattage + C Your configuration of 4×1620W is probably N+N, so maximum draw is around 3240W plus a bit. But check the documentation! It's also likely that each of the above scenarios is software-configurable, take note of that. Oh and by the way, VA=W×Power Factor . | {} | {'log_upvote_score': 4, 'links': ['https://serverfault.com/questions/508830', 'https://serverfault.com', 'https://serverfault.com/users/72780/']} | jdg_382779 |
stackexchange | llm_judgeable_groundtruth_similarity | 2615 |
Below is a question asked on the forum serverfault.com. Provide a good and informational response to it like a helpful human would.
Question:
How does one fully evaluate a RAID configuration? Pulling drives is one thing, but are there tools and techniques for more? I've considered putting a nail through a running drive (powder actuated nailgun) to see what would happen, or simulating various electrical anomalies (shorts/opens in cable, power overloads and surges, etc). What should be tested, and how? -Adam
Now provide the response and nothing else.
| In drives where hot-swap isn't an option, many raid controls (e.g. mdadm on linux) have a set-faulty command that simulates a drive failing. In drives where hot-swap is okay, yank a drive! I think your testing should cover the reasonable cases that you plan for. If you're trying to set up a server in the bush, then electrical fluctuations are reasonable test suites. If you're in a data center, the Service Agreement probably covers power. If you think a drive wildly exploding inside a rack is reasonable - then test it. Maybe you're setting up a server in a command center in Baghdad. But once again, less likely if you're in Washington State. As a general rule, your tests should cover all expected cases: Drive is old and eventually goes bad (find a drive on its last legs, get it running, then pound it till it fails) Drive fails a smart test but seems fine but you want to replace it just-in-case General drive replacement because of size/performance upgrade or you just heard the batch was bad And reasonable extreme cases. Server suddenly losing power - okay. Server itself being hit by lightning - not so much. Rack falling over - okay. Rack hit by truck - not so much. Drive being jostled - okay Drive being shot-putted - not so much. And most importantly - RAID doesn't protect against drives silently corrupting data! So make sure you're doing hashes and file verification! | {} | {'log_upvote_score': 4, 'links': ['https://serverfault.com/questions/2615', 'https://serverfault.com', 'https://serverfault.com/users/706/']} | jdg_382780 |
stackexchange | llm_judgeable_groundtruth_similarity | 18664567 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am using jquery mobile click function, however, it is not working. Here is an example of the button that I have, and it is contained within a grid: <div class="ui-block-c"><a class="request" data-role="button" data-id="\"'+json[i].num+'\" data-type="3" data-icon="plus" data-iconpos="right">Test</a></div> jQuery function: $('.request').on('click', function() { alert("hi");}); How do I fix this?
Now provide the response and nothing else.
| It looks like you are adding this element dynamically, so you'll need to use a delegated event listener: $(document).on('click', '.request', function() { alert("hi");}); Also you have an issue with your escaped quotes not matching. I don't think those are necessary: <div class="ui-block-c"><a class="request" data-role="button" data-id="'+json[i].num+'" data-type="3" data-icon="plus" data-iconpos="right">Test</a></div> | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/18664567', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2457831/']} | jdg_382781 |
stackexchange | llm_judgeable_groundtruth_similarity | 28157 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
$$\sqrt{(5+2\sqrt6)^x}+\sqrt{(5-2\sqrt6)^x}=10$$ So I have squared both sides and got: $$(5-2\sqrt6)^x+(5+2\sqrt6)^x+2\sqrt{1^x}=100$$ $$(5-2\sqrt6)^x+(5+2\sqrt6)^x+2=100$$ I don't know what to do now
Now provide the response and nothing else.
| You don't have to square the equation in the first place. Let $y = \sqrt{(5+2\sqrt{6})^x}$, then $\frac{1}{y} = \sqrt{(5-2\sqrt{6})^x}$. Hence you have $y + \frac{1}{y} = 10$ i.e. $y^2 + 1 = 10y$ i.e. $y^2-10y+1 = 0$. Hence, $(y-5)^2 =24 \Rightarrow y = 5 \pm 2 \sqrt{6}$. Hence, $$\sqrt{(5+2\sqrt{6})^x} = 5 \pm 2\sqrt{6} \Rightarrow x = \pm 2$$ (If you plug in $x = \pm 2$, you will get $5+2\sqrt{6} + 5-2\sqrt{6} $ which is nothing but $10$) | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/28157', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/7149/']} | jdg_382782 |
stackexchange | llm_judgeable_groundtruth_similarity | 2424457 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Is there a simple "Web interface" to running PHPUnit test suites? i.e. a PHP script that runs the test on the command line, and outputs a nicely formatted HTML result. I develop web applications, and the day-to-day workflow usually switches between the IDE and the browser. I would like to have the unit testing in the same environment. I'm looking for something really simple and PHP based - I am planning to get into phpUnderControl (which has the functionality I'm looking for) but not yet.
Now provide the response and nothing else.
| You can use phing to run a PHPUnitTask and then convert the output with: PHPUnitReport - This task transforms PHPUnit xml reports to HTML using XSLT. Example: <phpunitreport infile="reports/testsuites.xml" format="frames" todir="reports/tests" styledir="/home/phing/etc"/> See phpunit --help for the various output formats. The 2.3 version of PHPUnit had a chapter on this, but it is gone for some time now. You might be able to find an old copy with Google somewhere. Since you mention this is for phpUnderControl: if you are not fixed on that, consider using Jenkins and http://jenkins-php.org . On a side note: unless we are talking CI servers, most people I know don't use PHPUnit through a web interface. They either just use the command line or their IDE integration. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2424457', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/187606/']} | jdg_382783 |
stackexchange | llm_judgeable_groundtruth_similarity | 368279 |
Below is a question asked on the forum meta.stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Before I begin, I should mention that I'm not familiar with meta, and I'm not even sure if this is okay. For the time being, based on the existence of other questions with similar titles, I'm assuming that it is okay to ask for help revising a question on meta, before posting the question on the main site. Please let me know if I'm wrong, and if so, where to go for this specific type of problem. I recently wrote a question on the main site, and within the span of minutes, accrued four downvotes with no comments explaining why. The only person who commented said that the part about The Witness is irrelevant. This is information that I included because I didn't want to just spam code in a question without talking about some background first. So I deleted the question. And before I re-post it, I want to make absolutely sure that I do it right so that it won't be negatively received, hence why I am turning to meta for help. Anyway, below is the full text of the original question (followed by the revision I currently have). The help is much appreciated. Anybody who's played enough of The Witness probably knows about the puzzle where you have to sit through an hour-long monologue while a moon slowly moves from one side of the screen to the other ( full transcript ). During this bizarre and long-winded monologue about Video Game Easter Eggs, a mention is made of "Gary's Formula", which involves taking every letter of a string, multiplying its position value by six (A = 6, B = 12, C = 18, etc), and summing them together. This is used as a "proof" that Santa Claus is evil, because G(Santa Claus) = 666 . So I wrote an implementation of it, and then I wrote a 101-byte golf of it. main(c,v)char**v;{for(char*a=v[1];*a;a++)c+=6*(*a>64&&*a<91?*a-64:*a>96&&*a<123?*a-96:0);return c-2;} This is where the question comes in, essentially "why does this happen?": $ make garygolf && (./garygolf santaclaus; echo $?) # expect: 666154 If I change the code to include a call to printf , it uncovers the strange and interesting bug that is currently blowing my mind. $ cat garygolf.cmain(c,v)char**v;{for(char*a=v[1];*a;a++)c+=6*(*a>64&&*a<91?*a-64:*a>96&&*a<123?*a-96:0);printf("%u\n", c-2);return c-2;}$ make garygolf && (./garygolf santaclaus; echo $?)666154 I'm not even sure whether it's a bug in the program, a bug in the shell, or if I'm just using the shell wrong. If $? somehow wasn't the return value, or something else was modifying the return value just before exit, then adding extra arguments should result in the same return code of 154, but look: $ ./garygolf santaclaus second third; echo $? # result should be off by two668156 It's off by two. Where is 154 coming from? I feel like I'm missing something obvious. Here's some more outputs, showing how deep this unpredictable output goes: $ dogg(){ ./garygolf "$1"; echo $?; }$ dogg compute55846$ dogg computer666154$ dogg computers78012$ dogg computersa78618$ dogg computersaz942174 And as for the first paragraph, here is my second draft: I recently wrote an implementation of "Gary's Formula". Gary's Formula is described on this 58-minute diatribe about video game easter eggs (you can find the segment by searching for "santa claus"). In brief, the algorithm works as follows: for each letter in string, multiply the letter's positional value by six (A = 6, B = 12, C = 18, etc). The result is the sum of all of the letters' values. The rest, I haven't changed.
Now provide the response and nothing else.
| Your code is golfed and unreadable, and almost all of it is irrelevant. The context about the video game you were playing is also irrelevant. You need to construct a minimal reproducer for your bug - minimal in terms of complexity, not in terms of character count. For reference, assuming I understand your code correctly, the following program would have reproduced the bug: int main(void) { return 666;} You're returning an out-of-range exit code, and it's getting reduced mod 256. This is what you should have reduced your example to. No horrible golfed loop and hardcoded ASCII values and K&R-era declarations and abuse of argc as an accumulator. | {} | {'log_upvote_score': 6, 'links': ['https://meta.stackoverflow.com/questions/368279', 'https://meta.stackoverflow.com', 'https://meta.stackoverflow.com/users/1175714/']} | jdg_382784 |
stackexchange | llm_judgeable_groundtruth_similarity | 26033214 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Here is a sample action filter. We know that when we write an action filter then we need to decorate the controller with an attribute like this, to use it for any controller. I like to know whether there is any way to write an action filter which will work for all controllers in way that I do not need to decorate all the controllers with an action filter attribute. Any ideas? [LogActionFilter]public class HomeController : Controller{}public class LogActionFilter : ActionFilterAttribute { public override void OnActionExecuting(ActionExecutingContext filterContext) { Log("OnActionExecuting", filterContext.RouteData); } public override void OnActionExecuted(ActionExecutedContext filterContext) { Log("OnActionExecuted", filterContext.RouteData); } private void Log(string methodName, RouteData routeData) { var controllerName = routeData.Values["controller"]; var actionName = routeData.Values["action"]; var message = String.Format("{0} controller:{1} action:{2}", methodName, controllerName, actionName); Debug.WriteLine(message, "Action Filter Log"); } }
Now provide the response and nothing else.
| public class LogActionFilterAttribute : IActionFilter { public void OnActionExecuted(ActionExecutedContext filterContext) { Log("OnActionExecuted", filterContext.RouteData); } public void OnActionExecuting(ActionExecutingContext filterContext) { Log("OnActionExecuting", filterContext.RouteData); } private void Log(string methodName, RouteData routeData) { var controllerName = routeData.Values["controller"]; var actionName = routeData.Values["action"]; var message = String.Format("{0} controller:{1} action:{2}", methodName, controllerName, actionName); Debug.WriteLine(message, "Action Filter Log"); } }public class MvcApplication : System.Web.HttpApplication { protected void Application_Start() { GlobalFilters.Filters.Add(new LogActionFilterAttribute()); } } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/26033214', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/508127/']} | jdg_382785 |
stackexchange | llm_judgeable_groundtruth_similarity | 728415 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Can somebody give rigorous proof that the circle cannot be embedded into the real line? Obviously, if so it must be necessarily continuous and I guess this suffices in this case since there is no continuous injection by intuition...
Now provide the response and nothing else.
| It seems that you’re asking for a proof that the sphere is not homeomorphic to a subset of $\mathbb R$. This is easy: the sphere is connected, and its image in the real line would be as well. But the only connected subsets of the line are the intervals. Whether open, closed, or half-and-half, any interval is disconnected by the removal of three points, but the sphere is not. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/728415', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/79762/']} | jdg_382786 |
stackexchange | llm_judgeable_groundtruth_similarity | 22415 |
Below is a question asked on the forum physics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Once, I read that Einstein founded the special relativity theory by imagining how an observer moves at the speed of light. How does this thought experiment work? How to reach from this imagination to the relativity of time?
Now provide the response and nothing else.
| John Norton at Pitt relates the story quite nicely . In Einstein's own words: After ten years of reflection such a principle resulted from a paradox upon which I had already hit at the age of sixteen: If I pursue a beam of light with a velocity c (velocity of light in a vacuum), I should observe such a beam of light as a spatially oscillatory electromagnetic field at rest. However, there seems to be no such thing. . . on the basis of experience. . . . From the very beginning it appeared to me intuitively clear that, judged from the standpoint of such an observer, everything would have to happen according to the same laws as for an observer who, relative to the earth, was at rest. For how, otherwise, should the first observer know, that is, be able to determine, that he is in a state of fast uniform motion? In other words, assuming both (1) that all motion is relative and (2) that it's possible for an observer to travel at $C$ leads to an impossibility: (3) that there is a reference frame in which a beam of light is just a "spatially oscillatory electromagnetic field at rest" i.e, a motionless electromagnetic wave. Since he judged (3) to be impossible, then either (1) or (2) or both must be wrong. His insight was that (2) is wrong, that the speed of light is not attainable. | {} | {'log_upvote_score': 4, 'links': ['https://physics.stackexchange.com/questions/22415', 'https://physics.stackexchange.com', 'https://physics.stackexchange.com/users/8173/']} | jdg_382787 |
stackexchange | llm_judgeable_groundtruth_similarity | 142632 |
Below is a question asked on the forum mathoverflow.net. Provide a good and informational response to it like a helpful human would.
Question:
In the question Do pushouts preserve monic? it is said that monics in a topos are stable under push out. I would like a precise reference or a nice proof of this fact for elementary topoi (for Grothendieck follows since it holds in Sets, then in presheaves and then in sheaves (pointwise computation + associated sheaf).
Now provide the response and nothing else.
| Spatial weights would be relevant in non-homogeneous settings in which one expects the behaviour at different regions of space to be different. For instance, if there is an obstacle or a boundary, a weight that depends on the distance to the boundary would be natural in order to capture boundary effects. If the initial data is originally assumed to be concentrated at the origin, then weights involving the distance $|x|$ to the origin are also natural. Similarly, weights involving time $t$ are sometimes natural in evolution equations, particularly if one is trying to describe decay or blowup in time. More generally, if there is a natural singular set in physical space or frequency space, then it is natural to weight one's spaces around that set. The $X^{s.b}$ spaces mentioned in Willie's answer are a good example of this in the frequency domain (and Sobolev spaces themselves reflect the privileged nature of the frequency origin for many PDE, as the zero set for the symbol of the underlying linear operator (e.g. the Laplacian)). If one needs to prevent the solution from concentrating all its mass or energy into a ball, then Morrey or Campanato spaces are occasionally useful. As for the frequency-based refinements to Sobolev spaces (e.g. Besov and Triebel-Lizorkin, but also Hardy spaces, BMO, BV, etc.), these are "within logarithms" of Sobolev spaces, in the sense that if the ratio between the finest and coarsest spatial scale of interest (or equivalently, the ratio between the highest and lowest frequency scale of interest) is comparable to $N$, then the ratio between a Besov or Triebel-Lizorkin norm and its Sobolev counterpart (as plotted for instance on this type diagram: http://terrytao.wordpress.com/2010/03/11/a-type-diagram-for-function-spaces/ ) is at most a power of $\log N$. Because of this, Sobolev spaces generally suffice for all "subcritical" or "non-endpoint" situations in which one does not have to contend with a logarithmic pileup of contributions from each scale. If one is working in a critical setting (which is more or less the same thing as a scale-invariant or a dimensionless setting), these refinements can often be necessary to stop the logarithmic divergences caused by such things as the failure of the endpoint Sobolev inequality, e.g. $H^{n/2}({\bf R}^n) \not \subset L^\infty({\bf R}^n)$. (In this particular case, one can sometimes replace the Sobolev space $H^{n/2}$ with the smaller Besov space $B^{n/2}_1$ to recover the endpoint embedding, although there is no free lunch here and this will likely make some other estimate in one's analysis harder to prove.) In general, unless one is perturbing off of an existing method, one does not proceed by randomly picking function spaces and hoping that one's argument closes. Often the function spaces one ends up using are dictated by trying to directly estimate solutions (or approximations to solutions). For instance, if one is trying to establish a local well-posedness result for a semilinear evolution equation in some standard space, e.g. $H^s({\bf R}^n)$, one can try to expand the $H^s$ norm of that solution using a basic formula such as the Duhamel formula or the energy inequality. In trying to estimate the terms arising from that formula by harmonic analysis methods (e.g. Holder inequality, Sobolev embedding, etc.), one is naturally led to the need to control the solution in other norms as well. If all goes well, all the norms on the right-hand side can be controlled by what already has on the left-hand side plus the initial data, and then one has a good chance of closing an argument; if not, one often has to tweak the argument by either strengthening or weakening the norms one is trying to control, as dictated by what the harmonic analysis is telling you. The final norms one uses to close the argument often arise from a lengthy iteration of this procedure (which unfortunately is often hidden from view in the published version of the paper, which usually focuses on the final choice of spaces that worked, rather than the initial guesses which didn't quite work but needed to be perturbed into the final choice). Ultimately, in PDE one is usually more interested in the functions themselves, rather than the function spaces (though there are exceptions, e.g. if one is taking a dynamical systems perspective, or is relying on a fixed-point theorem exploiting the global topology of the function space). The reason that function spaces appear so prominently in PDE arguments is that functions have an infinite number of degrees of freedom, and the basic physical features of such functions (e.g. amplitude, frequency, location) are not easy to define directly in a precise and rigorous fashion. Function space norms serve as mathematically rigorous proxies for these physical statistics, but in the end they are only formal tools (with the exception of some physically natural norms or norm-like quantities, such as the mass or energy) and one should really be thinking about the physical features of the solution to the PDE directly. I discuss this point at http://terrytao.wordpress.com/2010/04/02/amplitude-frequency-dynamics-for-semilinear-dispersive-equations/ in the setting of semilinear dispersive equations (but there are similar perspectives for other PDE also). | {} | {'log_upvote_score': 5, 'links': ['https://mathoverflow.net/questions/142632', 'https://mathoverflow.net', 'https://mathoverflow.net/users/24703/']} | jdg_382788 |
stackexchange | llm_judgeable_groundtruth_similarity | 982952 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a method that uses an IList<T> as a parameter. I need to check what the type of that T object is and do something based on it. I was trying to use the T value, but the compiler does not not allow it. My solution is the following: private static string BuildClause<T>(IList<T> clause){ if (clause.Count > 0) { if (clause[0] is int || clause[0] is decimal) { //do something } else if (clause[0] is String) { //do something else } else if (...) //etc for all the types else { throw new ApplicationException("Invalid type"); } } } There has to be a better way to do this. Is there some way I can check the type of T that is passed in and then use a switch statement?
Now provide the response and nothing else.
| You could use overloads: public static string BuildClause(List<string> l){...}public static string BuildClause(List<int> l){...}public static string BuildClause<T>(List<T> l){...} Or you could inspect the type of the generic parameter: Type listType = typeof(T);if(listType == typeof(int)){...} | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/982952', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/47191/']} | jdg_382789 |
stackexchange | llm_judgeable_groundtruth_similarity | 65103 |
Below is a question asked on the forum mathoverflow.net. Provide a good and informational response to it like a helpful human would.
Question:
Suppose X is a loop space; by this we mean there is some space $Y$ with $\Omega Y \simeq X$. Under what assumptions is (the homotopy type of) $Y$ unique? As has been pointed out below, the homotopy type of $Y$ being determined uniquely is far from true in general. But for connected $Y$, are there conditions we can impose that make it so?
Now provide the response and nothing else.
| As Ryan points out, if Y is allowed to be disconnected, then there is no hope, since the loop-space construction sees only the connected component of the basepoint. But even if Y is assumed to be connected, it is not unique. For instance, let G and H be two discrete groups whose underlying sets are bijective, but which are not isomorphic. Then as (discrete) topological spaces, we have $G\simeq H$, and so both $K(G,1)$ and $K(H,1)$ are spaces Y such that $\Omega Y \simeq G \simeq H$. But $K(G,1)$ and $K(H,1)$ are not homotopy equivalent unless $G\cong H$ as groups. What is true, however, is that if we remember the "up-to-coherent-homotopy" multiplication (i.e. "$A_\infty$-structure") on a loop space $\Omega Y$, then the connected space Y is characterized up to homotopy equivalence by $\Omega Y$ and this additional data. For there is a delooping functor "B" from $A_\infty$-spaces to connected spaces, which preserves homotopy equivalence, and such that $B\Omega Y \simeq Y$. | {} | {'log_upvote_score': 5, 'links': ['https://mathoverflow.net/questions/65103', 'https://mathoverflow.net', 'https://mathoverflow.net/users/9163/']} | jdg_382790 |
stackexchange | llm_judgeable_groundtruth_similarity | 2587378 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I recently migrated a few of my Autocomplete plugins from the one produced by bassistance to the jQuery UI autocomplete . How can the "mustMatch" and "selectFirst" be implemented with just callbacks and other options without modifying the core autocomplete code itself?
Now provide the response and nothing else.
| I think I solved both features... To make things easier, I used a common custom selector: $.expr[':'].textEquals = function (a, i, m) { return $(a).text().match("^" + m[3] + "$");}; The rest of the code: $(function () { $("#tags").autocomplete({ source: '/get_my_data/', change: function (event, ui) { //if the value of the textbox does not match a suggestion, clear its value if ($(".ui-autocomplete li:textEquals('" + $(this).val() + "')").size() == 0) { $(this).val(''); } } }).live('keydown', function (e) { var keyCode = e.keyCode || e.which; //if TAB or RETURN is pressed and the text in the textbox does not match a suggestion, set the value of the textbox to the text of the first suggestion if((keyCode == 9 || keyCode == 13) && ($(".ui-autocomplete li:textEquals('" + $(this).val() + "')").size() == 0)) { $(this).val($(".ui-autocomplete li:visible:first").text()); } });}); If any of your autocomplete suggestions contain any 'special' characters used by regexp, you must escape those characters within m[3] in the custom selector: function escape_regexp(text) { return text.replace(/[-[\]{}()*+?.,\\^$|#\s]/g, "\\$&");} and change the custom selector: $.expr[':'].textEquals = function (a, i, m) { return $(a).text().match("^" + escape_regexp(m[3]) + "$");}; | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/2587378', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/234132/']} | jdg_382791 |
stackexchange | llm_judgeable_groundtruth_similarity | 647757 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
How many integers $n$ are there such that $\sqrt{n}+\sqrt{n+7259}$ is an integer? No idea on this one.
Now provide the response and nothing else.
| PERHAPS this is one approach: Let $n=t^2$ that takes care of the first square root. Then in the second square root we get $t^2+7259$. Set this square root term equal to, say $v^2$ so that we end up with $v^2-t^2=7259$ or $(v-t)(v+t)$=$7259$. Find all factors of $7259$ (which is finite) and figure out possible values of $v$ and $t$.If my approach is completely wrong, I will take it off. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/647757', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/101387/']} | jdg_382792 |
stackexchange | llm_judgeable_groundtruth_similarity | 38308067 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a code where I have two options, define lambda out of loop to save on lambda creation overhead or define it inside a loop to keep small scope. Is this choice critical and will make any significant difference? What are pros and cons of this two choices? What is best practice? #include <iostream>#include <string>#include <vector>#include <memory>int main(){ std::vector<std::function<void()>> functors; auto func = [] () { std::cout << "Hello world I am doing some action"; }; //some code here for(int i = 0; i < 100; ++i) { // some code here functors.push_back(func); // some code here }} EDITED: simplified example int main(){ auto sum = [](const int x, const int y) { return x + y; }; for(int i = 0; i < 100; ++i) { std::cout << sum(i, i + 1) << std::endl; }}
Now provide the response and nothing else.
| For each lambda expression, the compiler will create a struct with operator () overloaded for it. It won't create a struct each time the control passes through a lambda, so in terms of generated code it does not matter whether you define it inside or outside the loop. Therefore, keep things local. As a general rule, don't overthink these illusory optimization issues. Most likely, the performance bottleneck is going to be in your algorithm complexity. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/38308067', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1535428/']} | jdg_382793 |
stackexchange | llm_judgeable_groundtruth_similarity | 1536479 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
The division rule states that "There are n/d ways to do a task if it can be done using a procedure that can be carried out in n ways, and for every way w, exactly d of the n ways correspond to way w" I really can't understand this definition. Is there a easy way to explain this rule, not using math terms?
Now provide the response and nothing else.
| I guess the best way to explain this is with an example. Let's say we want to arrange $(1,1,2,3,4)$ in a row. For example, $$(1,1,2,4,3),(1,1,3,2,4)$$ Are possible arrangements. We first assume that the two $1$'s are distinct, so we have $5!$ ways to arrange: $$(1_a,1_b,2,3,4)$$ But for each of the $5!$ ways, we have over-counted some cases: $$(1,1,2,3,4)\begin{cases}(1_a,1_b,2,3,4)\\(1_b,1_a,2,3,4)\\\end{cases}$$ $$(2,1,1,3,4)\begin{cases}(2,1_a,1_b,3,4)\\(2,1_b,1_a,3,4)\\\end{cases}$$ $$\vdots $$ Every $2!$ of our initial $5!$ ways corresponds to one actual arrangement. That is why to arrange $(1,1,2,3,4)$ in a row, we have: $$\frac{5!}{2!} \space \text{ways}$$ | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/1536479', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/273597/']} | jdg_382794 |
stackexchange | llm_judgeable_groundtruth_similarity | 64953877 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm trying this Jekyll theme And I referenced this docs And This error code occurs endless!! Why this error occurs? Ah, For your information, I proceeded this & this Even if I search error message, the data doesn't come out well! I've been doing this all day, and I thought I can't cover this problem yet. Can you help me?If you need any information in the comments, I'll make up for it quickly. And this is my error code: swsui-MacBook-Pro:flexton-master sws$ bundle exec jekyll serveTraceback (most recent call last): 2: from /Users/sws/.gem/ruby/2.7.0/bin/bundle:23:in `<main>' 1: from /Users/sws/.rbenv/versions/2.7.2/lib/ruby/2.7.0/rubygems.rb:296:in `activate_bin_path'/Users/sws/.rbenv/versions/2.7.2/lib/ruby/2.7.0/rubygems.rb:277:in `find_spec_for_exe': Could not find 'bundler' (1.16.0.pre.3) required by your /Users/sws/Developer/blog/flexton-master/Gemfile.lock. (Gem::GemNotFoundException)To update to the latest version installed on your system, run `bundle update --bundler`.To install the missing version, run `gem install bundler:1.16.0.pre.3`swsui-MacBook-Pro:flexton-master sws$ bundle update --bundlerThe dependency tzinfo-data (>= 0) will be unused by any of the platforms Bundler is installing for. Bundler is installing for ruby but the dependency is only for x86-mingw32, x86-mswin32, x64-mingw32, java. To add those platforms to the bundle, run `bundle lock --add-platform x86-mingw32 x86-mswin32 x64-mingw32 java`.Fetching gem metadata from https://rubygems.org/.........Using public_suffix 3.0.2Using addressable 2.5.2Using bundler 2.1.4Using colorator 1.1.0Using concurrent-ruby 1.0.5Using eventmachine 1.2.5Using http_parser.rb 0.6.0Using em-websocket 0.5.1Fetching ffi 1.9.23Installing ffi 1.9.23 with native extensionsGem::Ext::BuildError: ERROR: Failed to build gem native extension. current directory: /Users/sws/.rbenv/versions/2.7.2/lib/ruby/gems/2.7.0/gems/ffi-1.9.23/ext/ffi_c/Users/sws/.rbenv/versions/2.7.2/bin/ruby -I /Users/sws/.rbenv/versions/2.7.2/lib/ruby/2.7.0 -r ./siteconf20201122-4218-1dxgm86.rbextconf.rbchecking for ffi_call() in -lffi... yeschecking for ffi_closure_alloc()... yeschecking for ffi_raw_call()... yeschecking for ffi_prep_raw_closure()... yeschecking for shlwapi.h... nochecking for rb_thread_blocking_region()... nochecking for rb_thread_call_with_gvl()... yeschecking for rb_thread_call_without_gvl()... yeschecking for ffi_prep_cif_var()... yescreating extconf.hcreating Makefilecurrent directory: /Users/sws/.rbenv/versions/2.7.2/lib/ruby/gems/2.7.0/gems/ffi-1.9.23/ext/ffi_cmake "DESTDIR=" cleancurrent directory: /Users/sws/.rbenv/versions/2.7.2/lib/ruby/gems/2.7.0/gems/ffi-1.9.23/ext/ffi_cmake "DESTDIR="compiling AbstractMemory.ccompiling ArrayType.ccompiling Buffer.ccompiling Call.cCall.c:334:5: error: implicit declaration of function 'rb_thread_call_without_gvl' is invalid in C99[-Werror,-Wimplicit-function-declaration] rbffi_thread_blocking_region(call_blocking_function, data, (void *) -1, NULL); ^./Thread.h:78:39: note: expanded from macro 'rbffi_thread_blocking_region'# define rbffi_thread_blocking_region rb_thread_call_without_gvl ^Call.c:388:20: warning: incompatible pointer types passing 'VALUE (void *)' (aka 'unsigned long (void *)') to parameter of type'VALUE (*)(VALUE)' (aka 'unsigned long (*)(unsigned long)') [-Wincompatible-pointer-types] rb_rescue2(rbffi_do_blocking_call, (VALUE) bc, rbffi_save_frame_exception, (VALUE) &frame, rb_eException, (VALUE) 0); ^~~~~~~~~~~~~~~~~~~~~~/Users/sws/.rbenv/versions/2.7.2/include/ruby-2.7.0/ruby/ruby.h:1988:25: note: passing argument to parameter hereVALUE rb_rescue2(VALUE(*)(VALUE),VALUE,VALUE(*)(VALUE,VALUE),VALUE,...); ^Call.c:388:56: warning: incompatible pointer types passing 'VALUE (void *, VALUE)' (aka 'unsigned long (void *, unsigned long)') toparameter of type 'VALUE (*)(VALUE, VALUE)' (aka 'unsigned long (*)(unsigned long, unsigned long)') [-Wincompatible-pointer-types] rb_rescue2(rbffi_do_blocking_call, (VALUE) bc, rbffi_save_frame_exception, (VALUE) &frame, rb_eException, (VALUE) 0); ^~~~~~~~~~~~~~~~~~~~~~~~~~/Users/sws/.rbenv/versions/2.7.2/include/ruby-2.7.0/ruby/ruby.h:1988:47: note: passing argument to parameter hereVALUE rb_rescue2(VALUE(*)(VALUE),VALUE,VALUE(*)(VALUE,VALUE),VALUE,...); ^2 warnings and 1 error generated.make: *** [Call.o] Error 1make failed, exit code 2Gem files will remain installed in /Users/sws/.rbenv/versions/2.7.2/lib/ruby/gems/2.7.0/gems/ffi-1.9.23 for inspection.Results logged to /Users/sws/.rbenv/versions/2.7.2/lib/ruby/gems/2.7.0/extensions/x86_64-darwin-20/2.7.0/ffi-1.9.23/gem_make.outAn error occurred while installing ffi (1.9.23), and Bundler cannot continue.Make sure that `gem install ffi -v '1.9.23' --source 'https://rubygems.org/'` succeeds before bundling.In Gemfile: jekyll was resolved to 3.7.3, which depends on jekyll-sass-converter was resolved to 1.5.2, which depends on sass was resolved to 3.5.5, which depends on sass-listen was resolved to 4.0.0, which depends on rb-inotify was resolved to 0.9.10, which depends on ffi And this is my environment (MacOS Big Sur 11.0.1) swsui-MacBook-Pro:flexton-master sws$ ruby -vruby 2.7.2p137 (2020-10-01 revision 5445e04352) [x86_64-darwin20]swsui-MacBook-Pro:flexton-master sws$ curl -fsSL https://github.com/rbenv/rbenv-installer/raw/master/bin/rbenv-doctor | bashChecking for `rbenv' in PATH: /usr/local/bin/rbenvChecking for rbenv shims in PATH: OKChecking `rbenv install' support: /usr/local/bin/rbenv-install (ruby-build 20201118)Counting installed Ruby versions: 1 versionsChecking RubyGems settings: OKAuditing installed plugins: OKswsui-MacBook-Pro:flexton-master sws$ gem envRubyGems Environment: - RUBYGEMS VERSION: 3.1.4 - RUBY VERSION: 2.7.2 (2020-10-01 patchlevel 137) [x86_64-darwin20] - INSTALLATION DIRECTORY: /Users/sws/.rbenv/versions/2.7.2/lib/ruby/gems/2.7.0 - USER INSTALLATION DIRECTORY: /Users/sws/.gem/ruby/2.7.0 - RUBY EXECUTABLE: /Users/sws/.rbenv/versions/2.7.2/bin/ruby - GIT EXECUTABLE: /usr/bin/git - EXECUTABLE DIRECTORY: /Users/sws/.rbenv/versions/2.7.2/bin - SPEC CACHE DIRECTORY: /Users/sws/.gem/specs - SYSTEM CONFIGURATION DIRECTORY: /Users/sws/.rbenv/versions/2.7.2/etc - RUBYGEMS PLATFORMS: - ruby - x86_64-darwin-20 - GEM PATHS: - /Users/sws/.rbenv/versions/2.7.2/lib/ruby/gems/2.7.0 - /Users/sws/.gem/ruby/2.7.0 - GEM CONFIGURATION: - :update_sources => true - :verbose => true - :backtrace => false - :bulk_threshold => 1000 - REMOTE SOURCES: - https://rubygems.org/ - SHELL PATH: - /Users/sws/.rbenv/versions/2.7.2/bin - /usr/local/Cellar/rbenv/1.1.2/libexec - /Users/sws/.gem/ruby/2.7.0/bin - /Users/sws/.rbenv/shims - /usr/local/opt/ruby/bin - %PATH - /bin - /usr/local/bin - /usr/bin And this is my .bash_profile # Setting PATH for Python 3.7# The original version is saved in .bash_profile.pysavePATH="/Library/Frameworks/Python.framework/Versions/3.7/bin:${PATH}"export PATH# Add Visual Studio Code (code)export PATH="$PATH:/Applications/Visual Studio Code.app/Contents/Resources/app/bin"export PATH=%PATH:/bin:/usr/local/bin:/usr/binexport PATH="/usr/local/opt/ruby/bin:$PATH"eval "$(rbenv init -)"export PATH="$HOME/.gem/ruby/2.7.0/bin:$PATH"
Now provide the response and nothing else.
| Have you tried this? bundle config build.ffi -- --with-cflags=-Wno-implicit-function-declaration Clang now reports an error when you use a function without an explicit declaration when building C or Objective-C code for macOS (-Werror=implicit-function-declaration flag is on). This additional error detection unifies Clang’s behavior for iOS/tvOS and macOS 64-bit targets for this diagnostic. (49917738) refs: https://developer.apple.com/documentation/xcode-release-notes/xcode-12-release-notes https://github.com/ffi/ffi/issues/840 https://github.com/tmm1/rbtrace/issues/81 | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/64953877', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/14645293/']} | jdg_382795 |
stackexchange | llm_judgeable_groundtruth_similarity | 51739509 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a controller to receive POST requests and return a JSON output. An exception handler which was implemented inside the controller class worked fine. I have tried to add Global exception handling with @ControllerAdvice annotation, but this doesn't work in my solution. I don't think the global exception handler class is being loaded. Below is my controller class: package hello;@Controller@RequestMapping("/v1")public class MyController { @RequestMapping(value = "/saveEmployee", method = RequestMethod.POST, produces = "application/json") @ResponseBody public String saveEmployee(@Valid @RequestBody Employee employee) { return "{ \"name\":\"" + employee.getEmail() + "\"}"; }} Below is Global exception handler class: package util;@ControllerAdvicepublic class MyControllerAdvice { @ExceptionHandler(MethodArgumentNotValidException.class) // @ResponseStatus(HttpStatus.BAD_REQUEST) @ResponseBody public String processValidationError(MethodArgumentNotValidException ex) { BindingResult result = ex.getBindingResult(); FieldError fieldError = result.getFieldError(); String code = fieldError.getCode(); String field = fieldError.getField(); String message = fieldError.getDefaultMessage(); message = "{ \"Code\":\"" + code + "\",\"field\":\"" + field + "\",\"Message\":\"" + message + "\"}"; return message; }} Below are my configurations: package hello;@SpringBootApplicationpublic class Application { @Bean public MessageSource messageSource() { ReloadableResourceBundleMessageSource messageSource = new ReloadableResourceBundleMessageSource(); messageSource.setBasename("classpath:messages"); messageSource.setDefaultEncoding("UTF-8"); return messageSource; } @Bean public LocalValidatorFactoryBean validator() { LocalValidatorFactoryBean bean = new LocalValidatorFactoryBean(); bean.setValidationMessageSource(messageSource()); return bean; } public static void main(String[] args) { SpringApplication.run(Application.class, args); }} Spring boot version : 2.0.3.RELEASE
Now provide the response and nothing else.
| I think the problem you have here is exactly what you identified. The MyControllerAdvice class isn't being loaded. From the code you posted, I'm inferring that your project structure looks something like: src main java hello Application.java MyController.java util MyControllerAdvice.java Because you have the SpringBootApplication annotation on your Application class, Spring Boot uses that as its starting point for creating beans, and it looks for classes annotated with things like @Controller and @ControllerAdvice (among others) to add to its context. There are many different ways to configure that, but the simplest if you're starting out or working with a relatively small project, will be to restructure it to fit Spring's recommendation here: https://docs.spring.io/spring-boot/docs/current/reference/html/using-boot-structuring-your-code.html That page is very short and worth reading to get the background, but the essence is that you want your @SpringBootApplication annotated class in the same package or a parent package as all the classes you want Spring to manage, the page above gives the following example: com +- example +- myapplication +- Application.java | +- customer | +- Customer.java | +- CustomerController.java | +- CustomerService.java | +- CustomerRepository.java | +- order +- Order.java +- OrderController.java +- OrderService.java +- OrderRepository.java So, in your case, this would mean either moving the util package under hello , like: src main java hello Application.java MyController.java util MyControllerAdvice.java Or creating a parent package for both hello and util and moving Application up to that package, like: src main java example Application.java hello MyController.java util MyControllerAdvice.java | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/51739509', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5523151/']} | jdg_382796 |
stackexchange | llm_judgeable_groundtruth_similarity | 8189384 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Possible Duplicate: Set cursor at a length of 14 onfocus of a textbox I am able to do that in firefox and IE. But for some reason its not working in Chrome and Safari :( I am simply using below line onfocus $('input:text').focus(function(){ document.getElementById('id').setSelectionRange(0, 0); }); Can someone please tell me how to do similar thing in Chrome and safari?
Now provide the response and nothing else.
| The problem is that Chrome (I haven't heard of Safari doing this as well, but I'll take you word for it) kills the selection after the focus event has fired, so you need to add a timer. The following is adapted from my answer here: How to place cursor at end of text in textarea when tabbed into However, this generally isn't good usability: it's contrary to what the user expects and removes useful functionality when using the mouse (i.e. the caret going to the location the user clicks). You can probably get around that with some handling of mousedown and mouseup events. Live demo: http://jsfiddle.net/timdown/z9DhX/1/ Code: function moveCaretToStart(el) { if (typeof el.selectionStart == "number") { el.selectionStart = el.selectionEnd = 0; } else if (typeof el.createTextRange != "undefined") { el.focus(); var range = el.createTextRange(); range.collapse(true); range.select(); }}var textBox = document.getElementById("id");textBox.onfocus = function() { moveCaretToStart(textBox); // Work around Chrome's little problem window.setTimeout(function() { moveCaretToStart(textBox); }, 1);}; | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/8189384', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/217294/']} | jdg_382797 |
stackexchange | llm_judgeable_groundtruth_similarity | 5574042 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am in search of the best way to "slugify" string what "slug" is , and my current solution is based on this recipe I have changed it a little bit to: s = 'String to slugify'slug = unicodedata.normalize('NFKD', s)slug = slug.encode('ascii', 'ignore').lower()slug = re.sub(r'[^a-z0-9]+', '-', slug).strip('-')slug = re.sub(r'[-]+', '-', slug) Anyone see any problems with this code? It is working fine, but maybe I am missing something or you know a better way?
Now provide the response and nothing else.
| There is a python package named python-slugify , which does a pretty good job of slugifying: pip install python-slugify Works like this: from slugify import slugifytxt = "This is a test ---"r = slugify(txt)self.assertEquals(r, "this-is-a-test")txt = "This -- is a ## test ---"r = slugify(txt)self.assertEquals(r, "this-is-a-test")txt = 'C\'est déjà l\'été.'r = slugify(txt)self.assertEquals(r, "cest-deja-lete")txt = 'Nín hǎo. Wǒ shì zhōng guó rén'r = slugify(txt)self.assertEquals(r, "nin-hao-wo-shi-zhong-guo-ren")txt = 'Компьютер'r = slugify(txt)self.assertEquals(r, "kompiuter")txt = 'jaja---lol-méméméoo--a'r = slugify(txt)self.assertEquals(r, "jaja-lol-mememeoo-a") See More examples This package does a bit more than what you posted (take a look at the source, it's just one file). The project is still active (got updated 2 days before I originally answered, over nine years later (last checked 2022-03-30), it still gets updated). careful : There is a second package around, named slugify . If you have both of them, you might get a problem, as they have the same name for import. The one just named slugify didn't do all I quick-checked: "Ich heiße" became "ich-heie" (should be "ich-heisse" ), so be sure to pick the right one, when using pip or easy_install . | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/5574042', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/106715/']} | jdg_382798 |
stackexchange | llm_judgeable_groundtruth_similarity | 219582 |
Below is a question asked on the forum physics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
As many books say: Temperature is (proportional, almost, etc...) average kinetic energy of particles. My question is this. "Suppose there is a body somewhere in empty space which moves at velocity v thus possessing KE not equal to 0 Joules , but has temperature equal to 0K . Can this be possible in a theoretical sense?" In my view it is possible since I think T is a measure of KE only for non-coherently moving particles. And if all particles of the body move coherently in one direction KE will not be equal to 0 Joules, but T will be 0 Kelvin . P.S. Since in the case of classical Thermodynamics, the engine (e.g. Carnot engine) does not move as a whole; it does not possess any "coherent KE", only "random KE" and thus the heuristic "temperature is average KE" works just fine. But this "rule of thumb" breaks down if the body moves as a whole. Am I right?
Now provide the response and nothing else.
| I think you are right. A perhaps more precise relation between temperature and velocity is the Maxwell–Boltzmann distribution :\begin{equation*}P(\textbf{v}) = \left( \frac{m}{2\pi k_B T} \right)^{3/2} \text{exp} \left[-\frac{m ( \textbf{v} - \textbf{v}_0)^2}{2 k_B T} \right].\end{equation*}where you see that the mean velocity $\textbf{v}_0$ and the temperature are independent. Only the variance of the velocity is related to temperature. | {} | {'log_upvote_score': 5, 'links': ['https://physics.stackexchange.com/questions/219582', 'https://physics.stackexchange.com', 'https://physics.stackexchange.com/users/76704/']} | jdg_382799 |
stackexchange | llm_judgeable_groundtruth_similarity | 306508 |
Below is a question asked on the forum stats.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
For a continuous random variable $X$ , if $E(|X|)$ is finite, is $\lim_{n\to\infty}n P(|X|>n)=0$ ? This is a problem I found on the internet, but I'm not sure whether it holds or not. I know that $n P(|X|>n)<E(|X|)$ holds by Markov inequality, but I can't show that it goes to 0 as $n$ goes to infinity.
Now provide the response and nothing else.
| Look at the sequence of random variables $\{Y_n\}$ defined by retaining only large values of $|X|$: $$Y_n:=|X|I(|X|>n).$$ It's clear that $Y_n\ge nI(|X|>n)$, so $$E(Y_n)\ge nP(|X|>n).\tag1$$ Note that $Y_n\to0$ and $|Y_n|\le |X|$ for each $n$. So the LHS of (1) tends to zero by dominated convergence . | {} | {'log_upvote_score': 4, 'links': ['https://stats.stackexchange.com/questions/306508', 'https://stats.stackexchange.com', 'https://stats.stackexchange.com/users/178816/']} | jdg_382800 |
stackexchange | llm_judgeable_groundtruth_similarity | 3350203 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I came across this question. Evaluate the limit $$ \lim_{x \to 2}\frac{\sqrt{x^3+1}-\sqrt{4x+1}}{\sqrt{x^3-2x}-\sqrt{x+2}}$$ I tried rationalizing the denominator, substitution, yet nothing seems to cancel out with the denominator. I don't think we are supposed to use squeeze theorem or L'Hopital rule for this. Can someone give me a hint in the right direction?
Now provide the response and nothing else.
| $${{\sqrt{x^3+1}-\sqrt{4x+1} \over \sqrt{x^3-2x} - \sqrt{x+2}} = \left({\sqrt{x^3+1}-\sqrt{4x+1} \over \sqrt{x^3-2x} - \sqrt{x+2}} \right)\left( {\sqrt{x^3+1}+\sqrt{4x+1} \over \sqrt{x^3+1}+\sqrt{4x+1}} \right) \left({\sqrt{x^3-2x} + \sqrt{x+2} \over \sqrt{x^3-2x} + \sqrt{x+2}} \right) =\left({x^3-4x \over x^3-3x-2}\right)\left({\sqrt{x^3-2x}+\sqrt{x+2} \over \sqrt{x^3+1}+\sqrt{4x+1}} \right) =\left({x(x+2) \over (x+1)^2}\right)\left({\sqrt{x^3-2x}+\sqrt{x+2} \over \sqrt{x^3+1}+\sqrt{4x+1}} \right)}$$ At $x=2$ , above simplified to: $\displaystyle \left({2 \times 4 \over 3 \times 3}\right) \left({2+2 \over 3+3} \right) = \left({8 \over 9}\right) \left({2 \over 3}\right) = {16 \over 27}$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/3350203', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/557123/']} | jdg_382801 |
stackexchange | llm_judgeable_groundtruth_similarity | 52398446 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Whenever I make any changes in java file, I have to restart server again and again for even small changes it. changes do not publish to server. It is really time taken process. how can I apply those changes in server without restarting server ? I tried to auto publish while saving, but still it does not work.
Now provide the response and nothing else.
| My setup: VS Code, Flutter If you don't have Podfile.lock file and pod update doesn't help, try this: Go to ios/Pods/Local Podspecs directory in your project Check every json file to find highest required ios version. Mine was "ios": "10.0" in some of them Go back to ios/ directory Open Podfile file Uncomment # platform :ios, '9.0' and replace 9.0 with version from 2. step, for example 10.0 . # platform :ios, '9.0' > platform :ios, '10.0' Run pod install and the error should be gone | {} | {'log_upvote_score': 9, 'links': ['https://Stackoverflow.com/questions/52398446', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/6403003/']} | jdg_382802 |
stackexchange | llm_judgeable_groundtruth_similarity | 1748861 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
The Archimedean property occurs in various areas of mathematics; for instance it is defined for ordered groups, ordered fields, partially ordered vector spaces and normed fields. In each of these contexts it is roughly the following property: Archimedean property. For any two (strictly) positive elements $x$ and $y$ there is some $n\in\mathbb{N}$ such that $n \cdot x$ exceeds $y$. This definition might not be adequate in each of the mentioned contexts, but at least it conveys the general idea. Indeed, in the context of normed fields we have the following definition (paraphrasing the definition given on Wikipedia): Definition. Let $F$ be a field with an absolute value $\left|\:\cdot\:\right|$, that is, a function $\left|\:\cdot\:\right| : F \to \mathbb{R}_{\geq 0}$ satisfying the following properties: $|x| = 0$ if and only if $x = 0$; For all $x,y\in F$ we have $|xy| = |x|\cdot |y|$; For all $x,y\in F$ we have $|x + y| \leq |x| + |y|$. Then $F$ is said to be Archimedean if for any non-zero $x\in F$ there exists some $n\in\mathbb{N}$ such that $$ \big|\:\underbrace{x + \cdots + x}_{n\ \text{times}}\:\big| > 1. $$ An absolute value that does not satisfy this property is called non-Archimedean . However, in the literature the term non-Archimedean absolute value is usually used as a synonym for an absolute value which satisfies the ultrametric inequality: For any $x,y\in F$ we have $|x + y| \leq \max(|x|,|y|)$. It is not so hard to see that an ultrametric absolute value can never be Archimedean: one easily proves that $|1| = 1$ holds, and then we find $|1 + 1| \leq 1$, followed by $|1 + 1 + 1| \leq 1$ and so on (repeatedly using the ultrametric inequality). It is however not so clear to me that any non-Archimedean absolute value must necessarily satisfy the ultrametric inequaltiy. Is this always true? Or is it only true for certain fields, say $\mathbb{Q}$, that happen to be the most common fields in the study of absolute values on fields?
Now provide the response and nothing else.
| Indeed, a non-Archimedean absolute value automatically satisfies the ultrametric inequality (as pointed out by Robert Israel). In my original question, I used a slightly different formulation of the Archimedean property (and the referenced lecture notes might not be online forever), so here is a full proof. Proposition. Let $F$ be a field and let $|\cdot|$ be a non-Archimedean absolute value. Then $|\cdot|$ satisfies the ultrametric inequality. Proof. Since $|\cdot|$ is non-Archimedean, we may choose some non-zero $x\in F$ such that $$ \big|\:\underbrace{x + \cdots + x}_{n\ \text{times}}\:\big| \leq 1,\tag*{for all $n\in\mathbb{N}$.} $$ We may interpret any element of $\mathbb{N}$ (or $\mathbb{Z}$ , for that matter) as an element of $F$ by identifying it with its image under the natural ring homomorphism $\mathbb{Z} \to F$ . Then the above becomes $$ |n|\cdot |x| = |n\cdot x| \leq 1,\tag*{for all $n\in\mathbb{N}$.} $$ Since $x$ is non-zero by assumption, we have $|x| \neq 0$ , hence $$ |n| \leq \frac{1}{|x|},\tag*{for all $n\in\mathbb{N}$.} $$ Now let $y,z\in F$ be given. By the binomial theorem, for all $k\in\mathbb{N}$ we have $$ (y + z)^k \: = \: \sum_{j=0}^k \binom{k}{j} y^j z^{k-j}, $$ hence $$ |y+z|^k \: = \: |(y+z)^k| \: = \: \left|\sum_{j=0}^k \binom{k}{j} y^j z^{k-j}\right| \: \leq \: \sum_{j=0}^k \frac{|y|^j\cdot |z|^{k-j}}{|x|} \: \leq \: \frac{k+1}{|x|}\cdot \max(|y|,|z|)^k. $$ Equivalently: for all $k\in\mathbb{Z}_{> 0}$ we have $$ |y+z| \: \leq \: \sqrt[k]{\frac{k+1}{|x|}}\cdot \max(|y|,|z|). $$ As $k$ increases, this factor $\sqrt[k]{\frac{k+1}{|x|}}$ converges (decreasingly) to one, so we have $$ |y + z| \: \leq \: \inf_{k\to\infty} \sqrt[k]{\frac{k+1}{|x|}}\cdot \max(|y|,|z|) \: = \: \max(|y|,|z|).\tag*{$\Box$} $$ This peculiar little trick is now standard in the literature. It is also used in many textbooks, for instance: W. Schikhof, Ultrametric Calculus: An Introduction to p-Adic Analysis , Cambridge Studies in Advanced Mathematics. Cambridge: Cambridge University Press. doi:10.1017/CBO9780511623844 (Lemma 8.2) Paulo Ribenboim, The Theory of Classical Valuations , Springer Monographs in Mathematics (section 1.2, fact E). Antonio J. Engler & Alexander Prestel, Valued Fields , Springer Monographs in Mathematics (proposition 1.1.1). Pierre Antoine Grillet, Abstract Algebra , Second Edition, Springer Graduate Texts in Mathematics 242 (chapter VI, proposition 3.2). Alain M. Robert, A Course in p-adic Analysis , Springer Graduate Texts in Mathematics 198 (chapter 2, section 1.6, first theorem). | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1748861', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/246783/']} | jdg_382803 |
stackexchange | llm_judgeable_groundtruth_similarity | 2383865 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have several .tpl.php files for nodes, CCK fields, and Views theming. These template files have a lot of logic in them to move things around, strip links, create new links, etc. I understand that this is bad development and not "The Drupal Way". If I understand correctly, "The Drupal Way" is to use preprocessor functions in your template.php file to manipulate variables and add new variables. A few questions about that: Is there a naming convention for creating a preprocessor function for a specific theme? For example, if I have a CCK field template called content-field-field_transmission_make_model.tpl , how would I name the preprocessor function? Can I use template preprocessor functions for node templates, CCK field templates, and Views templates? Do they have different methods of modifying template variables or adding new ones?
Now provide the response and nothing else.
| For a general overview, you should read up on manipulating variables within preprocess functions . Concerning the naming convention, this is normally pretty simple, but there is a catch for your current example (see below): A preprocess functions signature needs to be [yourModuleName|yourThemeName]_preprocess_[themeFunctionName](&$variables) so implementing one for the page template within a themes template.php file would result in themeName_preprocess_page(&$variables) Most of the time the name of the theme function will be the name of the *.tpl.php file, without the .tpl.php ending and with underscores instead of the hyphens. But there is a catch if the template file gets selected on the base of template suggestions , as the preprocess function can only be implemented for the base name, not for the additional suggestions! (The suggestions for alternate template files are added in preprocess functions themselves.) Your current example is one of those cases, as content-field-field_transmission_make_model.tpl.php is such a suggestion, with the base name being content-field.tpl.php , and the corresponding theme function being content_field . So you would have to implement a preprocess function named yourThemeName_preprocess_content_field(&$variables) , and within that inspect the available entries in the $variables array to check if you are actually called for the 'field_transmission_make_model', and not for a completely different CCK field, e.g.: function yourThemeName_preprocess_content_field(&$variables) { // Are we called for the right field? if ('field_transmission_make_model' == $variables['field_name']) { // Yes, add/manipulate entries within the variables array $variables['new_entry'] = 'A useless new variable'; $variables['label'] = 'A useless change of the existing label variable'; }} (Note: Untested code, beware of typos) After this, there should be a new variable $new_entry being available in your template file, and the content of the $label variable should have changed (all top level entries within the $variables array will be turned into separate variables for the template file, named after the array index). As for your second question, the basic usage of preprocess functions is the same for all template files, but be aware: Preprocess functions are only available for theme calls that use *.tpl.php files, not for theme functions The content of the $variables array varies heavily, depending on what gets themed Other modules might implement the preprocess functions as well, and they will be called one after another, so if you want to change something that gets added by another module, you can only do so if your implementation gets called after that (which will be no problem in your case, as implementations within a theme are called after all implementations within modules - just wanted to mention that there can be many implementations at once) | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/2383865', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/78093/']} | jdg_382804 |
stackexchange | llm_judgeable_groundtruth_similarity | 46214291 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have an array below: a=np.array([0.1, 0.2, 0.3, 0.7, 0.8, 0.9]) What I want is to convert this vector to a binary vector based on a threshold. take threshold=0.5 as an example, element that greater than 0.5 convert to 1, otherwise 0. The output vector should like this: a_output = [0, 0, 0, 1, 1, 1] How can I do this?
Now provide the response and nothing else.
| np.where np.where(a > 0.5, 1, 0)# array([0, 0, 0, 1, 1, 1]) Boolean basking with astype (a > .5).astype(int)# array([0, 0, 0, 1, 1, 1]) np.select np.select([a <= .5, a>.5], [np.zeros_like(a), np.ones_like(a)])# array([ 0., 0., 0., 1., 1., 1.]) Special case: np.round This is the best solution if your array values are floating values between 0 and 1 and your threshold is 0.5. a.round()# array([0., 0., 0., 1., 1., 1.]) | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/46214291', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/7326003/']} | jdg_382805 |
stackexchange | llm_judgeable_groundtruth_similarity | 67002 |
Below is a question asked on the forum dsp.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I tried for 2 signals $s_1(t) = u(t)$ and $s_2(t) = (1+i) \cdot u(t)$ . $i$ is the complex unit ( $i = (-1) ^{0.5}$ ).I got the left hand side of the inequality as $(1-i)$ and the right hand side as $(1+i)^{0.5}$ .The inequality is L.H.S $\le$ R.H.S. How is inequality established for complex signals?
Now provide the response and nothing else.
| Schwarz Inequality for continuous-time Complex valued functions is given as follows: $$\left|\int^{\infty}_{-\infty}f(t)^* \cdot g(t) dt \right|^2 \le \int^{\infty}_{-\infty}\left|f(t)\right|^2dt \cdot \int^{\infty}_{-\infty}\left|g(t)\right|^2dt$$ As you can see that, on left hand side magnitude is taken after integration making it real number and the quantity on right hand side is also real number because magnitude-squared is taken before integrating. Thus, the comparison is valid and can be done for all Complex-valued continuous time functions which are Square integrable. Meaning the Inequality exists for all functions $f(t)$ satisfying the following: $$\int^{\infty}_{-\infty}\left|f(t)\right|^2dt = c < \infty$$ | {} | {'log_upvote_score': 4, 'links': ['https://dsp.stackexchange.com/questions/67002', 'https://dsp.stackexchange.com', 'https://dsp.stackexchange.com/users/47984/']} | jdg_382806 |
stackexchange | llm_judgeable_groundtruth_similarity | 1638044 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Start with $i=\sqrt{-1}$. This will be $a_1$. $a_2$ will be $i^i$. $a_3$ will be $i^{i^{i}}$. $\vdots$ etc. In Knuth up-arrow notation : $$a_n=i\uparrow\uparrow n$$ And, amazingly, you can evaluate $\lim_{n\to\infty}a_n=\lim_{n\to\infty}i\uparrow\uparrow n=e^{-W(-\ln(i))}\approx0.4383+0.3606i$. You can check this, it does indeed converge to this value. In fact, I decided to make a graph of $a_n$ to show that it converges. (y axis is imaginary part, x axis is real part.) And, to little astonishment, I quickly noticed that there is an apparent pattern to the graph. Commonly, we define $x\uparrow\uparrow0=1$, which I have included in the graph. So the pattern seems very obvious. It follows a curved path that converges onto the point that was given above. And, if you connect the dots, starting with the first point (given on the left as the first point) and trace a nice line to the second, third, and so fourth numbers, you will find an interesting spiral. I thought that at first, this spiral was writable as an equation, but apparently, there are a few implications. You will notice that the blue dots are way closer to the converging point and that the red and black dots are a little closer. So whatever equation you can come up with should account that $a_{3n}$ is closest to the number you are trying to converge to. I want (so desperately) to see if anyone can come up with an equation that allows the computation of $a_{0.5}$ that satisfies $$i^{a_{0.5}}=a_{1.5}$$a well known identity you can find on the Wikipedia . At first glance of the graph I went on to think that perhaps, just perhaps, I (or you) could find a formula that allows us to define $i\uparrow\uparrow 0.5$. If you are familiar with De'Moivres formula, it is a formula that allows us to perform compute $$\sqrt{i}$$ with relative ease. It was derived when De'Moivre noticed an interesting pattern to $(a+bi)^n$. He proceeded to write his formula concerning the distance from zero and the angle from the positive real axis. So I must tell you that I wish for the same to occur with $i\uparrow\uparrow n$. Perhaps the answer lies in using a different coordinate system. Perhaps the answer lies in calculating the distance one of the points on one of the lines (black, red, or blue) is from the converging spot and the adding in the angle at which the next point changes. My progress on determining such a formula has gone nowhere. The most I can say is that $a_n$ is probably not chaotic and does indeed converge in a way that is most certainly not random.
Now provide the response and nothing else.
| You can find a non-trivial interpolation for the fractional iteration-height when you write down the consecutive iterates in log-polar-form (with center at the fixpoint). The nearer you come to the final fixpoint the log of the distance as well as the angle come nearer and nearer to a linear relation with the index and this suggests an obvious method of interpolation for fractional iteration-heights. I found it interesting that that type of interpolation agrees well with the solution, which you would find via the method invented by E. Schröder in the late 19 century. Although this log-polar/Schröder-interpolation gives a straightforward solution, there seems to be a better one (better in what sense? - too difficult to discuss it here) in the spirit of Kneser's analytic solution for the fractional interpolation of the $\exp()$-function (implementations available by tetrationforum). The latter can seemingly be approximated by a simple (but computationally much involved) procedure involving matrix-diagonalization and computing fractional powers of that matrix. You can find an introductory comparision of that mentioned methods (however for a different base for the exponentiation) in this small essay of mine Here is an image for an interpolation to fractional heights starting at $z_0=1$ going to $z_1=î,z_2 \approx 0.2078,...,z_\infty \approx 0.438+0.361 î$ using the Schröder-mechanism. For instance for the half-iterate we find by this method $z_{0.5} \approx 1.1667+0.734 î$. The grey dotted line indicates the integer-iterates (should be the same as that of @GEdgar) I got Sh. Levenstein's Pari/GP-program "fatou.gp" (from the tetrationforum ) for the (extended) Kneser-method working. Here is a comparision of the orbits produced by the two methods. For instance, the half-iterates differ even visually: | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/1638044', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/272831/']} | jdg_382807 |
stackexchange | llm_judgeable_groundtruth_similarity | 48450936 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'd like to create a REST API for an object which can be partially updated. On http://www.django-rest-framework.org/api-guide/serializers/#partial-updates and example is given in which partial=True is passed when instantiating the serializer: # Update `comment` with partial dataserializer = CommentSerializer(comment, data={'content': u'foo bar'}, partial=True) In my case, however, the model (which is called SessionType ) has the following viewset: class SessionTypeViewSet(viewsets.ModelViewSet): queryset = SessionType.objects.all() serializer_class = SessionTypeSerializer where the serializer is defined as class SessionTypeSerializer(serializers.ModelSerializer): class Meta: model = SessionType fields = ('title',) How can I adapt the serializer in this use case so that partial is always True ?
Now provide the response and nothing else.
| You don't need to adapt the serializer in any way. With that viewset, any call to the "detail" endpoint using the PATCH method will do a partial update. The Django Rest Framework ModelViewSet base class includes the following mixin. Here you can see how partial=True is passed when calling partial_update , which is routed to the PATCH method by default: class UpdateModelMixin(object): """ Update a model instance. """ def update(self, request, *args, **kwargs): partial = kwargs.pop('partial', False) instance = self.get_object() serializer = self.get_serializer(instance, data=request.data, partial=partial) serializer.is_valid(raise_exception=True) self.perform_update(serializer) if getattr(instance, '_prefetched_objects_cache', None): # If 'prefetch_related' has been applied to a queryset, we need to # refresh the instance from the database. instance = self.get_object() serializer = self.get_serializer(instance) return Response(serializer.data) def perform_update(self, serializer): serializer.save() def partial_update(self, request, *args, **kwargs): kwargs['partial'] = True return self.update(request, *args, **kwargs) | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/48450936', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/995862/']} | jdg_382808 |
stackexchange | llm_judgeable_groundtruth_similarity | 26049150 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I want to calculate a 32-bit CRC lookup table. One way I tried is by using the following code from this website : #include <iostream>#include <stdint.h>void make_crc_table(){ unsigned long POLYNOMIAL = 0x04c11db7; unsigned long WIDTH = 8 * sizeof(unsigned long); unsigned long TOPBIT = 1 << (WIDTH - 1); unsigned long crcTable[256]; unsigned long remainder; // Compute the remainder of each possible dividend for (int dividend = 0; dividend < 256; ++dividend) { // Start with the dividend followed by zeros remainder = dividend << (WIDTH - 8); // Perform modulo-2 division, a bit at a time for (unsigned long bit = 8; bit > 0; --bit) { // Try to divide the current data bit if (remainder & TOPBIT) { remainder = (remainder << 1) ^ POLYNOMIAL; } else { remainder = (remainder << 1); } } crcTable[dividend] = remainder; } // Print the CRC table for (int i = 0; i < 256; i++) { if (i % 4 == 0) { std::cout <<"\n"; } std::cout << std::hex << crcTable[i]; std::cout << ", "; }}int main(){ make_crc_table(); return 0;} Another way I tried is by using the following code that I found from this StackOverflow question , and the code can be downloaded from here in a file called CRC Calculator.zip #include <iostream>#include <stdint.h>#define POLYNOMIAL 0x04C11DB7uint32_t A_crcLookupTable[256] = {0};#define WIDTH (8 * sizeof(uint32_t))#define TOPBIT (((uint32_t)1) << (WIDTH - 1))#define FP_reflect_DATA(_DATO) (_DATO)#define FP_reflect_CRCTableValue(_CRCTableValue) (_CRCTableValue)uint32_t F_CRC_ObtenValorDeTabla(uint8_t VP_Pos_Tabla){ uint32_t VP_CRCTableValue = 0; uint8_t VP_Pos_bit = 0; VP_CRCTableValue = ((uint32_t) FP_reflect_DATA(VP_Pos_Tabla)) << (WIDTH - 8); for (VP_Pos_bit = 0; VP_Pos_bit < 8; VP_Pos_bit++) { if (VP_CRCTableValue & TOPBIT) { VP_CRCTableValue = (VP_CRCTableValue << 1) ^ POLYNOMIAL; } else { VP_CRCTableValue = (VP_CRCTableValue << 1); } } return (FP_reflect_CRCTableValue(VP_CRCTableValue));}void F_CRC_InicializaTabla(void){ uint16_t VP_Pos_Array = 0; for (VP_Pos_Array = 0; VP_Pos_Array < 256; VP_Pos_Array++) { A_crcLookupTable[VP_Pos_Array] = F_CRC_ObtenValorDeTabla((uint8_t)(VP_Pos_Array &0xFF)); }}void make_crc_table(){ F_CRC_InicializaTabla(); // Print the CRC table for (int i = 0; i < 256; i++) { if (i % 4 == 0) { std::cout <<"\n"; } std::cout << std::hex << A_crcLookupTable[i]; std::cout << ", "; }}int main(){ make_crc_table(); return 0;} Here is what the correct final table should be, based on this link : // The constants here are for the CRC-32 generator // polynomial, as defined in the Microsoft // Systems Journal, March 1995, pp. 107-108CONST table: ARRAY[0..255] OF DWORD = ($00000000, $77073096, $EE0E612C, $990951BA, $076DC419, $706AF48F, $E963A535, $9E6495A3, $0EDB8832, $79DCB8A4, $E0D5E91E, $97D2D988, $09B64C2B, $7EB17CBD, $E7B82D07, $90BF1D91, $1DB71064, $6AB020F2, $F3B97148, $84BE41DE, $1ADAD47D, $6DDDE4EB, $F4D4B551, $83D385C7, $136C9856, $646BA8C0, $FD62F97A, $8A65C9EC, $14015C4F, $63066CD9, $FA0F3D63, $8D080DF5, $3B6E20C8, $4C69105E, $D56041E4, $A2677172, $3C03E4D1, $4B04D447, $D20D85FD, $A50AB56B, $35B5A8FA, $42B2986C, $DBBBC9D6, $ACBCF940, $32D86CE3, $45DF5C75, $DCD60DCF, $ABD13D59, $26D930AC, $51DE003A, $C8D75180, $BFD06116, $21B4F4B5, $56B3C423, $CFBA9599, $B8BDA50F, $2802B89E, $5F058808, $C60CD9B2, $B10BE924, $2F6F7C87, $58684C11, $C1611DAB, $B6662D3D, $76DC4190, $01DB7106, $98D220BC, $EFD5102A, $71B18589, $06B6B51F, $9FBFE4A5, $E8B8D433, $7807C9A2, $0F00F934, $9609A88E, $E10E9818, $7F6A0DBB, $086D3D2D, $91646C97, $E6635C01, $6B6B51F4, $1C6C6162, $856530D8, $F262004E, $6C0695ED, $1B01A57B, $8208F4C1, $F50FC457, $65B0D9C6, $12B7E950, $8BBEB8EA, $FCB9887C, $62DD1DDF, $15DA2D49, $8CD37CF3, $FBD44C65, $4DB26158, $3AB551CE, $A3BC0074, $D4BB30E2, $4ADFA541, $3DD895D7, $A4D1C46D, $D3D6F4FB, $4369E96A, $346ED9FC, $AD678846, $DA60B8D0, $44042D73, $33031DE5, $AA0A4C5F, $DD0D7CC9, $5005713C, $270241AA, $BE0B1010, $C90C2086, $5768B525, $206F85B3, $B966D409, $CE61E49F, $5EDEF90E, $29D9C998, $B0D09822, $C7D7A8B4, $59B33D17, $2EB40D81, $B7BD5C3B, $C0BA6CAD, $EDB88320, $9ABFB3B6, $03B6E20C, $74B1D29A, $EAD54739, $9DD277AF, $04DB2615, $73DC1683, $E3630B12, $94643B84, $0D6D6A3E, $7A6A5AA8, $E40ECF0B, $9309FF9D, $0A00AE27, $7D079EB1, $F00F9344, $8708A3D2, $1E01F268, $6906C2FE, $F762575D, $806567CB, $196C3671, $6E6B06E7, $FED41B76, $89D32BE0, $10DA7A5A, $67DD4ACC, $F9B9DF6F, $8EBEEFF9, $17B7BE43, $60B08ED5, $D6D6A3E8, $A1D1937E, $38D8C2C4, $4FDFF252, $D1BB67F1, $A6BC5767, $3FB506DD, $48B2364B, $D80D2BDA, $AF0A1B4C, $36034AF6, $41047A60, $DF60EFC3, $A867DF55, $316E8EEF, $4669BE79, $CB61B38C, $BC66831A, $256FD2A0, $5268E236, $CC0C7795, $BB0B4703, $220216B9, $5505262F, $C5BA3BBE, $B2BD0B28, $2BB45A92, $5CB36A04, $C2D7FFA7, $B5D0CF31, $2CD99E8B, $5BDEAE1D, $9B64C2B0, $EC63F226, $756AA39C, $026D930A, $9C0906A9, $EB0E363F, $72076785, $05005713, $95BF4A82, $E2B87A14, $7BB12BAE, $0CB61B38, $92D28E9B, $E5D5BE0D, $7CDCEFB7, $0BDBDF21, $86D3D2D4, $F1D4E242, $68DDB3F8, $1FDA836E, $81BE16CD, $F6B9265B, $6FB077E1, $18B74777, $88085AE6, $FF0F6A70, $66063BCA, $11010B5C, $8F659EFF, $F862AE69, $616BFFD3, $166CCF45, $A00AE278, $D70DD2EE, $4E048354, $3903B3C2, $A7672661, $D06016F7, $4969474D, $3E6E77DB, $AED16A4A, $D9D65ADC, $40DF0B66, $37D83BF0, $A9BCAE53, $DEBB9EC5, $47B2CF7F, $30B5FFE9, $BDBDF21C, $CABAC28A, $53B39330, $24B4A3A6, $BAD03605, $CDD70693, $54DE5729, $23D967BF, $B3667A2E, $C4614AB8, $5D681B02, $2A6F2B94, $B40BBE37, $C30C8EA1, $5A05DF1B, $2D02EF8D); However, this is what my output is from both programs (I diffed the output, and it's the same for both of them), and it's incorrect : 0, 4c11db7, 9823b6e, d4326d9, 130476dc, 17c56b6b, 1a864db2, 1e475005, 2608edb8, 22c9f00f, 2f8ad6d6, 2b4bcb61, 350c9b64, 31cd86d3, 3c8ea00a, 384fbdbd, 4c11db70, 48d0c6c7, 4593e01e, 4152fda9, 5f15adac, 5bd4b01b, 569796c2, 52568b75, 6a1936c8, 6ed82b7f, 639b0da6, 675a1011, 791d4014, 7ddc5da3, 709f7b7a, 745e66cd, 9823b6e0, 9ce2ab57, 91a18d8e, 95609039, 8b27c03c, 8fe6dd8b, 82a5fb52, 8664e6e5, be2b5b58, baea46ef, b7a96036, b3687d81, ad2f2d84, a9ee3033, a4ad16ea, a06c0b5d, d4326d90, d0f37027, ddb056fe, d9714b49, c7361b4c, c3f706fb, ceb42022, ca753d95, f23a8028, f6fb9d9f, fbb8bb46, ff79a6f1, e13ef6f4, e5ffeb43, e8bccd9a, ec7dd02d, 34867077, 30476dc0, 3d044b19, 39c556ae, 278206ab, 23431b1c, 2e003dc5, 2ac12072, 128e9dcf, 164f8078, 1b0ca6a1, 1fcdbb16, 18aeb13, 54bf6a4, 808d07d, cc9cdca, 7897ab07, 7c56b6b0, 71159069, 75d48dde, 6b93dddb, 6f52c06c, 6211e6b5, 66d0fb02, 5e9f46bf, 5a5e5b08, 571d7dd1, 53dc6066, 4d9b3063, 495a2dd4, 44190b0d, 40d816ba, aca5c697, a864db20, a527fdf9, a1e6e04e, bfa1b04b, bb60adfc, b6238b25, b2e29692, 8aad2b2f, 8e6c3698, 832f1041, 87ee0df6, 99a95df3, 9d684044, 902b669d, 94ea7b2a, e0b41de7, e4750050, e9362689, edf73b3e, f3b06b3b, f771768c, fa325055, fef34de2, c6bcf05f, c27dede8, cf3ecb31, cbffd686, d5b88683, d1799b34, dc3abded, d8fba05a, 690ce0ee, 6dcdfd59, 608edb80, 644fc637, 7a089632, 7ec98b85, 738aad5c, 774bb0eb, 4f040d56, 4bc510e1, 46863638, 42472b8f, 5c007b8a, 58c1663d, 558240e4, 51435d53, 251d3b9e, 21dc2629, 2c9f00f0, 285e1d47, 36194d42, 32d850f5, 3f9b762c, 3b5a6b9b, 315d626, 7d4cb91, a97ed48, e56f0ff, 1011a0fa, 14d0bd4d, 19939b94, 1d528623, f12f560e, f5ee4bb9, f8ad6d60, fc6c70d7, e22b20d2, e6ea3d65, eba91bbc, ef68060b, d727bbb6, d3e6a601, dea580d8, da649d6f, c423cd6a, c0e2d0dd, cda1f604, c960ebb3, bd3e8d7e, b9ff90c9, b4bcb610, b07daba7, ae3afba2, aafbe615, a7b8c0cc, a379dd7b, 9b3660c6, 9ff77d71, 92b45ba8, 9675461f, 8832161a, 8cf30bad, 81b02d74, 857130c3, 5d8a9099, 594b8d2e, 5408abf7, 50c9b640, 4e8ee645, 4a4ffbf2, 470cdd2b, 43cdc09c, 7b827d21, 7f436096, 7200464f, 76c15bf8, 68860bfd, 6c47164a, 61043093, 65c52d24, 119b4be9, 155a565e, 18197087, 1cd86d30, 29f3d35, 65e2082, b1d065b, fdc1bec, 3793a651, 3352bbe6, 3e119d3f, 3ad08088, 2497d08d, 2056cd3a, 2d15ebe3, 29d4f654, c5a92679, c1683bce, cc2b1d17, c8ea00a0, d6ad50a5, d26c4d12, df2f6bcb, dbee767c, e3a1cbc1, e760d676, ea23f0af, eee2ed18, f0a5bd1d, f464a0aa, f9278673, fde69bc4, 89b8fd09, 8d79e0be, 803ac667, 84fbdbd0, 9abc8bd5, 9e7d9662, 933eb0bb, 97ffad0c, afb010b1, ab710d06, a6322bdf, a2f33668, bcb4666d, b8757bda, b5365d03, b1f740b4,
Now provide the response and nothing else.
| The bits are reversed. Note that the table entry for array[0x80] (0x80 is 0x01 reversed) = 0xEDB88320 , which is 0x04C11DB7 reversed. Example code: #include <iostream>#include <iomanip>void make_crc_table(unsigned long crcTable[]) { unsigned long POLYNOMIAL = 0xEDB88320; unsigned long remainder; unsigned char b = 0; do { // Start with the data byte remainder = b; for (unsigned long bit = 8; bit > 0; --bit) { if (remainder & 1) remainder = (remainder >> 1) ^ POLYNOMIAL; else remainder = (remainder >> 1); } crcTable[(size_t)b] = remainder; } while(0 != ++b);}unsigned long gen_crc(unsigned char *p, size_t n, unsigned long crcTable[]) { unsigned long crc = 0xfffffffful; size_t i; for(i = 0; i < n; i++) crc = crcTable[*p++ ^ (crc&0xff)] ^ (crc>>8); return(~crc);}int main() { unsigned long crcTable[256]; make_crc_table(crcTable); // Print the CRC table for (size_t i = 0; i < 256; i++) { std::cout << std::setfill('0') << std::setw(8) << std::hex << crcTable[i]; if (i % 4 == 3) std::cout << std::endl; else std::cout << ", "; } return 0;} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/26049150', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1625519/']} | jdg_382809 |
stackexchange | llm_judgeable_groundtruth_similarity | 28906914 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have looked around and have been unsuccessful at figuring out how take text, overlay it on an image, and then combine the two into a single UIImage . I have exhausted Google using the search terms I can think of so if anyone has a solution or at least a hint they can point to it would be greatly appreciated.
Now provide the response and nothing else.
| Ok... I figured it out: func textToImage(drawText: NSString, inImage: UIImage, atPoint: CGPoint) -> UIImage{ // Setup the font specific variables var textColor = UIColor.whiteColor() var textFont = UIFont(name: "Helvetica Bold", size: 12)! // Setup the image context using the passed image let scale = UIScreen.mainScreen().scale UIGraphicsBeginImageContextWithOptions(inImage.size, false, scale) // Setup the font attributes that will be later used to dictate how the text should be drawn let textFontAttributes = [ NSFontAttributeName: textFont, NSForegroundColorAttributeName: textColor, ] // Put the image into a rectangle as large as the original image inImage.drawInRect(CGRectMake(0, 0, inImage.size.width, inImage.size.height)) // Create a point within the space that is as bit as the image var rect = CGRectMake(atPoint.x, atPoint.y, inImage.size.width, inImage.size.height) // Draw the text into an image drawText.drawInRect(rect, withAttributes: textFontAttributes) // Create a new image out of the images we have created var newImage = UIGraphicsGetImageFromCurrentImageContext() // End the context now that we have the image we need UIGraphicsEndImageContext() //Pass the image back up to the caller return newImage} To call it, you just pass in an image: textToImage("000", inImage: UIImage(named:"thisImage.png")!, atPoint: CGPointMake(20, 20)) The following links helped me get this straight: Swift - Drawing text with drawInRect:withAttributes: How to write text on image in Objective-C (iOS)? The original goal was to create a dynamic image that I could use in an AnnotaionView such as putting a price at a given location on a map and this worked out great for it. Hope this helps someone trying to do the same thing. For Swift 3: func textToImage(drawText text: NSString, inImage image: UIImage, atPoint point: CGPoint) -> UIImage { let textColor = UIColor.white let textFont = UIFont(name: "Helvetica Bold", size: 12)! let scale = UIScreen.main.scale UIGraphicsBeginImageContextWithOptions(image.size, false, scale) let textFontAttributes = [ NSFontAttributeName: textFont, NSForegroundColorAttributeName: textColor, ] as [String : Any] image.draw(in: CGRect(origin: CGPoint.zero, size: image.size)) let rect = CGRect(origin: point, size: image.size) text.draw(in: rect, withAttributes: textFontAttributes) let newImage = UIGraphicsGetImageFromCurrentImageContext() UIGraphicsEndImageContext() return newImage! } For Swift 4: func textToImage(drawText text: String, inImage image: UIImage, atPoint point: CGPoint) -> UIImage { let textColor = UIColor.white let textFont = UIFont(name: "Helvetica Bold", size: 12)! let scale = UIScreen.main.scale UIGraphicsBeginImageContextWithOptions(image.size, false, scale) let textFontAttributes = [ NSAttributedStringKey.font: textFont, NSAttributedStringKey.foregroundColor: textColor, ] as [NSAttributedStringKey : Any] image.draw(in: CGRect(origin: CGPoint.zero, size: image.size)) let rect = CGRect(origin: point, size: image.size) text.draw(in: rect, withAttributes: textFontAttributes) let newImage = UIGraphicsGetImageFromCurrentImageContext() UIGraphicsEndImageContext() return newImage! } For Swift 5: func textToImage(drawText text: String, inImage image: UIImage, atPoint point: CGPoint) -> UIImage { let textColor = UIColor.white let textFont = UIFont(name: "Helvetica Bold", size: 12)! let scale = UIScreen.main.scale UIGraphicsBeginImageContextWithOptions(image.size, false, scale) let textFontAttributes = [ NSAttributedString.Key.font: textFont, NSAttributedString.Key.foregroundColor: textColor, ] as [NSAttributedString.Key : Any] image.draw(in: CGRect(origin: CGPoint.zero, size: image.size)) let rect = CGRect(origin: point, size: image.size) text.draw(in: rect, withAttributes: textFontAttributes) let newImage = UIGraphicsGetImageFromCurrentImageContext() UIGraphicsEndImageContext() return newImage!} | {} | {'log_upvote_score': 9, 'links': ['https://Stackoverflow.com/questions/28906914', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3750109/']} | jdg_382810 |
stackexchange | llm_judgeable_groundtruth_similarity | 3829167 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Can anyone tell me how to return multiple values from a function? Please elaborate with some example?
Now provide the response and nothing else.
| Your choices here are to either return a struct with elements of your liking, or make the function to handle the arguments with pointers. /* method 1 */struct Bar{ int x; int y;};struct Bar funct();struct Bar funct(){ struct Bar result; result.x = 1; result.y = 2; return result;}/* method 2 */void funct2(int *x, int *y);void funct2(int *x, int *y){ /* dereferencing and setting */ *x = 1; *y = 2;}int main(int argc, char* argv[]) { struct Bar dunno = funct(); int x,y; funct2(&x, &y); // dunno.x == x // dunno.y == y return 0;} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3829167', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/459184/']} | jdg_382811 |
stackexchange | llm_judgeable_groundtruth_similarity | 2842169 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Effective java says: // Potential security hole! static public final Thing[] VALUES = { ... }; Can somebody tell me what is the security hole?
Now provide the response and nothing else.
| Declaring static final public fields is usually the hallmark of a class constant. It's perfectly fine for primitive types (ints, doubles etc..), and immutable classes, like strings and java.awt.Color . With arrays, the problem is that even though the array reference is constant, the elements of the array can still be changed, and as it's a field, changes are unguarded, uncontrolled, and usually unwelcome. To combat this, the visibility of the array field can be restricted to private or package private, so you have a smaller body of code to consider when looking for suspicious modification. Alternatively, and often better, is to do away with the array together and use a 'List', or other appropriate collection type. By using a collection, you control if updates are allowed, since all updates go through methods. You can prevent updates by wrapping your collection using Collections.unmodifiableList() . But beware that even though the collection is immutable, you must also be sure that the types stored in it are also immutable, or the risk of unsolicited changes on a supposed constant will reappear. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/2842169', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/82368/']} | jdg_382812 |
stackexchange | llm_judgeable_groundtruth_similarity | 170628 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
This is I think a very simple question about infinite sequences. I thought I knew the answer but the manipulation described below worries me. Suppose I divide the interval $(0,\frac{1}{4})$ into infinitely many subintervals $S_n = (\frac{1}{(n+1)^2},\frac{1}{(n)^2})$, to wit: $S_1 = (\frac{1}{9},\frac{1}{4}),S_2 = (\frac{1}{16},\frac{1}{9})$, etc. Suppose there is a countably infinite subsequence $\{S_{n_i} \}$ of these intervals that interests me. I wish to segregate this subsequence by moving it to the left of the interval, so that the two countable sequences $\{S_n\} \setminus \{S_{n_i}\}$ and $\{S_{n_i}\}$ are segregated and remain in length-order, respectively. So we would have, $0,...S_{n_2},S_{n_1},0,...,S_2,S_1$. Are any special assumptions needed to justify this manipulation (and is the situation clear)? Thanks for any help. Edit, example: We have the line segment s: 0 _ __ _ ___ 1/4 I divide it into subintervals as described. Now suppose I want to take the subset of intervals indexed by odd n, and move them to the left of the segment. From the right at x = 1/4, I have a subsequence of intervals whose length approaches zero near (let us say) x = s, and then a new subsequence that begins at s, whose lengths approach 0 as they move towards x = 0. Does this help?
Now provide the response and nothing else.
| We will prove that $\frac{a}{\varphi(a)}=\frac{b}{\varphi(b)}$ iff the prime factorizations of $a$ and $b$ involve the same primes. If $p$ is a prime, then $\varphi(p^k)=(p-1)p^{k-1}$ for any positive integer $k$. So $\frac{p^m}{\varphi(p^m)}=\frac{p^n}{\varphi(p^n)}$ for all positive integers $m$ and $n$. Since $\varphi$ is multiplicative, it follows that if the prime factorizations of $a$ and $b$ involve the same primes, then $\frac{a}{\varphi(a)}=\frac{b}{\varphi(b)}$. Conversely, suppose that $\frac{a}{\varphi(a)}=\frac{b}{\varphi(b)}$. Then the same primes divide $a$ and $b$. This is trickier to prove. Let $p_1, p_2,\dots,p_k$ be the (distinct) primes that divide $a$, listed in decreasing order, and $q_1,q_2, \dots,q_l$ be the primes that divide $b$, again listed in decreasing order. From the fact that $\frac{a}{\varphi(a)}=\frac{b}{\varphi(b)}$, we can fairly easily conclude that$$(q_1-1)\cdots(q_l-1)p_1\cdots p_k=(p_1-1)\cdots(p_k-1)q_1\cdots q_l.\tag{$1$}$$ Suppose that $q_1 \ge p_1$. Since $q_1$ divides the right-hand side of $(1)$, it must divide the left-hand side. It cannot divide any $q_i-1$, and the only $p_i$ it can possibly divide is $p_1$, since $q_1 \ge p_1$. It follows that $q_1=p_1$. Now in Equation $(1)$, cancel the terms $q_1$ and $p_1$, also $q_1-1$ and $p_1-1$. (If $p_1 \ge q_1$, use the same argument.) We obtain an equation of the same type as $(1)$. Continue in his way, from the largest primes down. We conclude hat $k=l$, and $p_i=q_i$ for all $i$. Remark: Your post says you are interested in efficiently finding $\varphi(n)$ for large $n$. Let $n=p_1^{a_1}p_2^{a_2}\cdots p_k^{a_k}$, where the $p_i$ are distinct pimes, and the $a_i$ are $\ge 1$. Then$$\varphi(n)=(p_1-1)p_1^{a_1-1} (p_2-1)p_2^{a_2-1}\cdots (p_k-1)p_k^{a_k-1}.$$For very large $n$, the above formula is not efficient, since it involves factoring $n$, which seems to be a computationally difficult problem. It is known that if $n$ is the product of two primes, and we only know $n$ and $\varphi(n)$, we can efficiently find the two primes. So if there is an efficient way to find $\varphi(n)$ for large $n$, then the RSA encryption scheme, which is thought to be secure, is in fact not at all secure. There has been a huge amount of effort expended in trying to "break" RSA. One can probably safely say that there is known efficient way to compute $\varphi(n)$ for very large $n$. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/170628', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/18124/']} | jdg_382813 |
stackexchange | llm_judgeable_groundtruth_similarity | 48774142 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a web app that contains the meta <meta name="apple-mobile-web-app-capable" content="yes"> Before iOS 11.3, when "added to Home Screen" it would then open like a standalone app without the navigation bar. After 11.3 it now opens with the navigation bar in the browser.
Now provide the response and nothing else.
| After hours of troubleshooting I found the following that might be helpful for others. For Android/Chrome compatibility, I already had the following in my html file: <link rel="manifest" href="/manifest.json"> The manifest.json had no "display": "standalone" entry, it just had icons and name defined. It appears that before 11.3 the file was ignored by safari but now it is considered and has precedence over the meta tag apple-mobile-web-app-capable . Since the default for display: is browser , the app was opened inside a browser with a navigation bar. When I added the line "display": "standalone" in the manifest file the problem went away. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/48774142', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/718488/']} | jdg_382814 |
stackexchange | llm_judgeable_groundtruth_similarity | 6527 |
Below is a question asked on the forum earthscience.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I've only had a secondary education in physics, so bear with me, but with the greenhouse effect and all, wouldn't we be much hotter already if the ice melt-rate wasn't increasing, since more (heat) energy goes toward changing state, rather than changing temperature? My understanding of latent heat is that it is the applied heat that does not result in a dramatic temperature increase, rather it is used to change state (i.e. solid ice to liquid water). The obvious issue would be that once the ice is all melted, or it doesn't melt quick enough, we'll have proper heat problems (not just the 2 or 4 or 6 deg changes being discussed now). Are there numbers available on this? Or is this effect nonsense? Or am I looking towards a time a few orders of magnitude beyond my years?
Now provide the response and nothing else.
| Latent heat is a factor, but is completely eclipsed by the rate of global warming. For example, since 1978 the April (maximum) Arctic sea ice has decreased in volume by about $11,000$ cubic km. The latent heat absorbed by the ice to achieve this is about $3.7(10)^{18}$ Joules. Compare this to the amount of excess heat, which has been absorbed by the oceans, which is about $2.0(10)^{23}$ Joules per decade. That is, some three to four orders of magnitude more heat than the decadal heat required to melt the Arctic ice. Of course there are complications of the heat absorbed by land (much less than in the oceans), melting of Greenland and Antarctic ice sheets, and uncertainty over the depth of oceanic warming, due to sparsity of measurements, especially in the southern hemisphere. But however you cut the statistics, the latent heat is minuscule compared to the planetary heat imbalance. | {} | {'log_upvote_score': 4, 'links': ['https://earthscience.stackexchange.com/questions/6527', 'https://earthscience.stackexchange.com', 'https://earthscience.stackexchange.com/users/4481/']} | jdg_382815 |
stackexchange | llm_judgeable_groundtruth_similarity | 26433409 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
So, I just updated my codebase to Lollipop, and I'm having issues with the Action Bar. I'm using AppCompat and ActionBarActivity, and inflating a custom view. It seems that the custom view no longer takes up the whole width of the screen, leaving a thin strip on the left Way it used to look Way it looks now This is the code I'm using to set up the Action Bar. Anyone have any ideas? final ActionBar actionBar = getSupportActionBar();if(actionBar != null) { actionBar.setDisplayHomeAsUpEnabled(false); actionBar.setDisplayShowHomeEnabled(false); actionBar.setDisplayShowTitleEnabled(false); actionBar.setDisplayShowCustomEnabled(true); actionBar.setNavigationMode(ActionBar.NAVIGATION_MODE_STANDARD); actionBar.setCustomView(R.layout.action_bar_content_search_custom_view); actionBar.setBackgroundDrawable(null); // actionBar.setStackedBackgroundDrawable(null); TextView title = (TextView) actionBar.getCustomView().findViewById(R.id.action_bar_title); title.setText(R.string.youtube); ImageView back = (ImageView) actionBar.getCustomView().findViewById(R.id.action_bar_back); back.setOnClickListener(new OnClickListener() { @Override public void onClick(View v) { finish(); } });} Edit Taking out the custom view and changing the background now takes up the whole width. So the issue is, how can we make a CustomView take up the whole width of the ActionBar?
Now provide the response and nothing else.
| Looks like this is caused by the latest changes to the ActionBar in the recent appcompat-v7 update.It seems like that there are significant changes to how you should handle action bars. I faced the same issue and after reading the ActionBar documentation , and especially the following quote I found a solution. Beginning with Android L (API level 21), the action bar may be represented by any Toolbar widget within the application layout. The application may signal to the Activity which Toolbar should be treated as the Activity's action bar. Activities that use this feature should use one of the supplied .NoActionBar themes, set the windowActionBar attribute to false or otherwise not request the window feature. The way I see it, the AppCompat themes were changed and on one hand seemed to break a few things but provide much more flexibility on the other.I recommend following these steps: Use .NoActionBar style in your activity as described in the above quote Add a android.support.v7.widget.Toolbar to your Activity layout Set the app:contentInsetStart="0dp" attribute. This is the main issue with the margin that you describe in your question <android.support.v7.widget.Toolbar xmlns:android="http://schemas.android.com/apk/res/android" xmlns:app="http://schemas.android.com/apk/res-auto" android:id="@+id/actionBar" android:layout_width="match_parent" android:layout_height="wrap_content" app:contentInsetEnd="0dp" app:contentInsetStart="0dp" ></android.support.v7.widget.Toolbar> It's usually recommended that you do that in a separate layout file and use include in your activity layout so you will only need to customize the Toolbar in one place if used in multiple activities <include layout="@layout/view_action_bar" /> Use findViewById and setSupportActionBar in your Activity onCreate to signal to the Activity which Toolbar should be treated as the Activity's action bar Toolbar actionBar = (Toolbar) findViewById(R.id.actionBar);setSupportActionBar(actionBar); Once you do that, all actions added in onCreateOptionsMenu will be added to the toolbar and it will be treated as the activity action bar. Further customize the Toolbar as desired (Add child views etc.) | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/26433409', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2395376/']} | jdg_382816 |
stackexchange | llm_judgeable_groundtruth_similarity | 43242472 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a data frame that follows the following format. match team1 team2 winningTeam 1 A D A 2 B E E 3 C F C 4 D C C 5 E B B 6 F A A 7 A D D 8 D A A What I want to do is to crate variables that calculates the form of both team 1 and 2 over the last x matches. For example, I would want to create a variable called team1_form_last3_matches which for match 8 would be 0.33 (as they won 1 of their last 3 matches) and there would also be a variable called team2_form_last3_matches which would be 0.66 in match 8 (as they won 2 of their last 3 matches). Ideally I would like to be able to specify the number of previous matches to be considered when calculating the team x _form_last y variable and those variables to be automatically created. I have tried a bunch of approaches using dplyr, zoo rolling mean functions and a load of nested for / if statements. However, I have not quite cracked it and certainly not in an elegant way. I feel like I am missing a simple solution to this generic problem. Any help would be much appreciated! Cheers, Jack
Now provide the response and nothing else.
| I haven't found a way to do this elegantly, but I'm very familiar with this problem (getting data from FactSet PA reports -> Excel -> R, right?). I understand different reports have different formats, and this can be a pain. For a slightly different version of annoyingly formatted spreadsheets, I do the following. It's not the most elegant (it requires two reads of the file) but it works. I like reading the file twice, to make sure the columns are of the correct type, and with good headers. It's easy to mess up column imports, so I'd rather have my code read the file twice than go through and clean up columns myself, and the read_excel defaults, if you start at the right row, are pretty good. Also, it's worth noting that as of today (2017-04-20), readxl had an update . I installed the new version to see if that would make this very easy, but I don't believe that's the case, although I could be mistaken. library(readxl)library(stringr)library(dplyr)f_path <- file.path("whatever.xlsx")if (!file.exists(f_path)) { f_path <- file.choose()}# I read this twice, temp_read to figure out where the data actually starts...# Maybe you need something like this - # excel_sheets <- readxl::excel_sheets(f_path)# desired_sheet <- which(stringr::str_detect(excel_sheets,"2 Factor Brinson Attribution"))desired_sheet <- 1temp_read <- readxl::read_excel(f_path,sheet = desired_sheet)skip_rows <- NULLcol_skip <- 0search_string <- "Monthly Returns"max_cols_to_search <- 10max_rows_to_search <- 10# Note, for the - 0, you may need to add/subtract a row if you end up skipping too far later.while (length(skip_rows) == 0) { col_skip <- col_skip + 1 if (col_skip == max_cols_to_search) break skip_rows <- which(stringr::str_detect(temp_read[1:max_rows_to_search,col_skip][[1]],search_string)) - 0}# ... now we re-read from the known good starting point.real_data <- readxl::read_excel( f_path, sheet = desired_sheet, skip = skip_rows)# You likely don't need this if you start at the right row# But given that all weird spreadsheets are weird in their own way# You may want to operate on the col_skip, maybe like so:# real_data <- real_data %>%# select(-(1:col_skip)) | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/43242472', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4685907/']} | jdg_382817 |
stackexchange | llm_judgeable_groundtruth_similarity | 24395076 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm using Raphael to draw an object, then transferring it to an HTML canvas element with canvg so that I can use toDataURL to save it as a PNG. But when I use canvg, the resulting image is blurry. The code below, for example, produces this (raphael on top, canvg on bottom): <html> <head> <script src="lib/raphael-min.js"></script> <script type="text/javascript" src="http://canvg.googlecode.com/svn/trunk/rgbcolor.js"></script> <script type="text/javascript" src="http://canvg.googlecode.com/svn/trunk/StackBlur.js"></script> <script type="text/javascript" src="http://canvg.googlecode.com/svn/trunk/canvg.js"></script> <script src="lib/raphael.export.js"></script> </head> <body> <div id="raph_canvas"></div><br> <canvas id="html_canvas" width="50px" height="50px"></canvas> <script language="JavaScript"> var test=Raphael("raph_canvas",50,50); var rect=test.rect(0,0,50,50); rect.attr({fill: '#fff000', 'fill-opacity':1, 'stroke-width':1}) window.onload = function() { var canvas_svg = test.toSVG(); canvg('html_canvas',canvas_svg); var canvas_html = document.getElementById("html_canvas"); } </script> </body></html> The blurriness is evident in the png created by toDataURL as well. Any idea what is going on here? I don't think this has anything to do with re-sizing. I've tried setting ignoreDimensions: True and some other things. Another datapoint. If I use raphael to output some text and then use canvg, it is not only blurry but the wrong font! And here is the test.rect(0.5,0.5,50,50) suggested. Still blurry:
Now provide the response and nothing else.
| So it took me a while, but then it dawned on me. All your example images are twice the size the code claims they should be. So you're most likely on some sort of HDPI device (Retina MacBook Pro ect...) SVG is great because its resolution independent, canvas on the other hand is not. The issue you're seeing has to do with how canvas renders. To fix this, you need to prep the canvas so that your drawing will be done at the resolution of your screen. http://jsbin.com/liquxiyi/3/edit?html,js,output This jsbin example should look great on any screen. The trick: var cv = document.getElementById('box');var ctx = cv.getContext("2d");// SVG is resolution independent. Canvas is not. We need to make our canvas // High Resolution.// lets get the resolution of our device.var pixelRatio = window.devicePixelRatio || 1;// lets scale the canvas and change its CSS width/height to make it high res.cv.style.width = cv.width +'px';cv.style.height = cv.height +'px';cv.width *= pixelRatio;cv.height *= pixelRatio;// Now that its high res we need to compensate so our images can be drawn as //normal, by scaling everything up by the pixelRatio.ctx.setTransform(pixelRatio,0,0,pixelRatio,0,0);// lets draw a box// or in your case some parsed SVGctx.strokeRect(20.5,20.5,80,80);// lets convert that into a dataURLvar ur = cv.toDataURL();// result should look exactly like the canvas when using PNG (default)var result = document.getElementById('result');result.src=ur;// we need our image to match the resolution of the canvasresult.style.width = cv.style.width;result.style.height = cv.style.height; This should explain the issue you're having, and hopefully point you in a good direction to fix it. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/24395076', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3001940/']} | jdg_382818 |
stackexchange | llm_judgeable_groundtruth_similarity | 12832292 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Context: I'm trying to take a screenshot of another window to feed it into OpenCV. I found some code on the web that should be able to convert a BITMAP to something OpenCV can work with. Unfortunately I ran into some trouble. Question: Why is the bmBits attribute/member always null? (I also tried with PrintWindow instead of BitBlt the result was the same) #include <iostream>#include <string>#include <Windows.h>int main(int argc, char* argv[]){ std::wstring windowName = L"Calculator"; RECT rect; HWND hwnd = FindWindow(NULL, windowName.c_str()); if (hwnd == NULL) { return 0; } GetClientRect(hwnd, &rect); HDC hdcScreen = GetDC(NULL); HDC hdc = CreateCompatibleDC(hdcScreen); HBITMAP hbmp = CreateCompatibleBitmap(hdcScreen, rect.right - rect.left, rect.bottom - rect.top); SelectObject(hdc, hbmp); PrintWindow(hwnd, hdc, PW_CLIENTONLY); BITMAP bmp; GetObject(hbmp, sizeof(BITMAP), &bmp); return 0;}
Now provide the response and nothing else.
| The bmBits member is non-null for DIB sections. For device-dependent bitmaps (such as the one you're creating), the bmBits is not set because the pixels are on the video card, not in main memory. In your example, you need to change CreateCompatibleBitmap to CreateDIBSection if you want direct access to the bits. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/12832292', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/583833/']} | jdg_382819 |
stackexchange | llm_judgeable_groundtruth_similarity | 73387 |
Below is a question asked on the forum electronics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I want to understand how different constructs in VHDL code are synthesized in RTL. Can anyone tell me the difference between If-Else construct and Case statement constructs of a process in VHDL in terms of how the code is inferenced into RTL circuit by the synthesis tool ? Do consider the case of multiple nested if-else and mixingcase-statements with if-else construct inside a process. Also when to use which construct ? PS: I have seen a related question "Multiple if statements in process in vhdl" but that doesn't answer my question in anyway.
Now provide the response and nothing else.
| Can anyone tell me the difference between If-Else construct and Case statement constructs of a process in VHDL in terms of how the code is inferenced into RTL circuit by the synthesis tool ? The if-elsif-else construct infers a priority routing network: simulate this circuit – Schematic created using CircuitLab This corresponds to if bool_expr_1 then sig <= val_expr_1;elsif bool_expr_2 then sig <= val_expr_2;elsif bool_expr_3 then sig <= val_expr_3;else sig <= val_expr_4;end if; The case construct, on the other hand, infers a big ol' mux: This corresponds to case case_expr is when c0 => sig <= val_expr_0; when c1 => sig <= val_expr_1; when c2 => sig <= val_expr_2; ... when others => sig <= val_expr_N;end case; Obviously these are very simplified designs with only one value expression, resulting in one output. Do consider the case of multiple nested if-else and mixing case-statements with if-else construct inside a process. Per the above, you can see how they would nest/mix. Also when to use which construct ? Since if-else infers priority, it should be used when more than one input condition could occur. Using case , one the other hand, is appropriate when the inputs are mutually exclusive. | {} | {'log_upvote_score': 5, 'links': ['https://electronics.stackexchange.com/questions/73387', 'https://electronics.stackexchange.com', 'https://electronics.stackexchange.com/users/11120/']} | jdg_382820 |
stackexchange | llm_judgeable_groundtruth_similarity | 8047204 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm writing a script to import some model objects into the database my django application uses. In the past I've solved this by running ./manage.py shell and then import myscript . I'm sure there's a better way. I'd like to be able to call a script from anywhere on my HD using python scriptname.py , and in the first few lines of that script it would do whatever imports / other operations necessary so that it can access model objects and behave as though it was run using manage.py shell . What do I need to add to my script to achieve this? EDIT: Based on @Melug's answer, with addition of dynamically setting Python path to address the 'anywhere on my HD' part of the question: import syssys.path.append('c:\\my_projec_src_folder')from myproject import settingsfrom django.core.management import setup_environsetup_environ(settings)
Now provide the response and nothing else.
| Since Django 1.4 you should avoid using setup_environ(settings) (post by Melug) because it is deprecated. Use the following instead and you will be able to access your model import osos.environ.setdefault("DJANGO_SETTINGS_MODULE", "your_project_name.settings")# your imports, e.g. Django modelsfrom your_project_name.models import Location# From now onwards start your script.. Here is an example to access and modify your model: if __name__ == '__main__': # e.g. add a new location l = Location() l.name = 'Berlin' l.save() # this is an example to access your model locations = Location.objects.all() print locations # e.g. delete the location berlin = Location.objects.filter(name='Berlin') print berlin berlin.delete() Example model: class Location(models.Model): name = models.CharField(max_length=100) | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/8047204', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/193601/']} | jdg_382821 |
stackexchange | llm_judgeable_groundtruth_similarity | 17127964 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm trying to learn grunt. When I run npm init, I get a prompt in the process of creating a package.json file that asks for "test command" - I'm not sure how to utilize this, or what it's expecting. It doesn't seem to be well documented. If I leave it blank, I get this in the resulting package.json file: "scripts": { //"test": "echo \"Error: no test specified\" && exit 1" }, Can anybody shed some light on how to set up a test script?
Now provide the response and nothing else.
| at first, the scripts-property in your package.json has nothing to do with grunt itself. its just a cli-command from npm, wich will be run if you run $ npm test read more about that here: https://npmjs.org/doc/scripts.html e.g. if you test your application with the grunt & nodeunit you could just add that to the scripts-block "scripts": { "test": "grunt nodeunit"} and your nodeunit-task is run if you run 'npm test' this basically makes it easier for continuous integration and so on, if you change your underlying testframework. of course you could add an alias-task if you need more to be done before and after your tests are run (e.g. concatenation before, cleanup after) | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/17127964', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/287436/']} | jdg_382822 |
stackexchange | llm_judgeable_groundtruth_similarity | 39597952 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am working on component testing with angular2. in my html template i use the translate pipe. This is the code of the test : import { ComponentFixture, TestBed ,getTestBed} from '@angular/core/testing';import { By } from '@angular/platform-browser';import { DebugElement } from '@angular/core';import { RightComponent } from './right.component';import {TranslateService} from 'ng2-translate/ng2-translate';import {Injector} from "@angular/core";let comp: RightComponent;let fixture: ComponentFixture<RightComponent>;let el: DebugElement;let translate: TranslateService;let injector: Injector;describe('testComponent', () => {beforeEach(() => {TestBed.configureTestingModule({ declarations: [ RightComponent ]}); injector = getTestBed(); translate = injector.get(TranslateService);fixture = TestBed.createComponent(RightComponent);comp = fixture.componentInstance; // BannerComponent test instance// get title DebugElement by element nameel = fixture.debugElement.query(By.css('h2'));});it('should display original title', () => {fixture.detectChanges(); // trigger data bindingexpect(el.nativeElement.textContent).toContain('Liste des droits');});}); i got this error the the translate pipe is not known : Error: Template parse errors:The pipe 'translate' could not be found ("<h2>[ERROR ->]{{'RIGHT_TITLE' | translate}}</h2><div class="table-responsive"><table id="rightTableId" clas"): RightComponent@0:4 The pipe 'translate' could not be found (" <table id="rightTableId" class="table table-striped"> <tr> <th>[ERROR ->]{{'NAME_LABEL' | translate}}</th> </tr> <tr *ngFor="let right of rights"> "): RightComponent@4:16 The pipe 'translate' could not be found (" </tr> <tr *ngFor="let right of rights"> <td>[ERROR ->]{{right.name | translate}}</td> </tr> </table> How we resolve this problem ? Thanks.
Now provide the response and nothing else.
| it's the ng2-translate github.com/ocombe/ng2-translate You need to configure the TestBed with the library module just like you would configure the library with your real application. And looking at the documentation , it shows configuring it by importing the module imports: [ TranslateModule.forRoot()] So you should do the same in the TestBed configuration TestBed.configureTestingModule({ declarations: [ RightComponent ], imports: [TranslateModule.forRoot()]}); This is what the TestBed.configureTestingModule is for: to configure a module for the test environment. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/39597952', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3518668/']} | jdg_382823 |
stackexchange | llm_judgeable_groundtruth_similarity | 5120924 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I've got some form verification code that doesn't seem to be working correctly, and I can't figure out why. function isTextFieldEmpty(textField){ //return true or false depending on whether or not there is any text in the field console.log("Checking to see if the current field is empty..."); var val = textField.value; //val is the text from the current field console.log("The current value of 'val' is: " + val); if(val.length < 1){ return true; }else{ return false; }} The error I get is: "Uncaught TypeError: Cannot read property 'length' of undefined" . Sure enough, my console log says that the value of 'val' is undefined . I'm sure I'm missing something, but I'm still learning JS and can't figure out what it is. Any suggestions? Edit: Here is what I'm passing to the function: var uName = document.getElementById("unionname");var noUnionName = isTextFieldEmpty(uName); 'unionname' is the id of the texfield that I'm trying to validate. Here is the relevant HTML: <div class="formBox"> <label for="unionname">Union Name</label> <input type="text" name="unionname" id="unionname" value="" class="wide"/> <span class="feedback good">Sample good message</span> </div>
Now provide the response and nothing else.
| The problem is because of the operation you are using. Since DBNull.Value is not a string, you can't use the conditional operator. This is because, from the conditional operator docs : Either the type of first_expression and second_expression must be the same, or an implicit conversion must exist from one type to the other. Try doing this: if (!string.IsNullOrWhiteSpace(data[i])) row[i] = data[i];else row[i] = DBNull.Value; This bypasses the conversion requirements for both sides to be the same. Alternatively, you can cast both to a System.Object explicitly, and still use the conditional operator. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/5120924', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/615438/']} | jdg_382824 |
stackexchange | llm_judgeable_groundtruth_similarity | 14916 |
Below is a question asked on the forum linguistics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
The Ancient Greek words ἀοργησία aorgesia "a defect in the passion of anger" and ἀόριστος aoristos "without boundaries" both start with the "alpha privatum," the negative prefix cognate to English un- and Latin -in/-im/-ir/-il . However, every source that I have looked up has said that this prefix is realized as ἀν- an - when it comes before a vowel (including one that was historically preceded by a rough breathing /h/).What is the explanation for these exceptions, and do any others exist? EDIT: I kind of found the answer, so I guess I will post it in case anyone else has this problem later on. I may have follow-up questions.
Now provide the response and nothing else.
| Both of these roots originally had an initial w-. horos “boundary” is from older worwos, as attested by Mycenaean wo-wo, and dialect forms like ορϝος. In the case of orgē “anger” we do not happen to have any attested Greek dialect forms with w-, but IE *uerg- is supported by zero-grade forms like Sanskrit ūrj- “strength”. | {} | {'log_upvote_score': 4, 'links': ['https://linguistics.stackexchange.com/questions/14916', 'https://linguistics.stackexchange.com', 'https://linguistics.stackexchange.com/users/5581/']} | jdg_382825 |
stackexchange | llm_judgeable_groundtruth_similarity | 20561116 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am getting started with AngularJS, and as I understand, I can have different controllers for different sections of my web page. I am having the problem getting it work. I have two sections of my page and corresponding to each one ng-controller - JSFiddle . Only the section that come first works. For example currently, app1 works fine, but when I move it below app2 , only app2 works fine. What could be wrong? Much appreciate any explanation regarding why this behavior and any links.
Now provide the response and nothing else.
| You can have multiple controllers, but you cannot have multiple ng-app directives on the same page. This means you should only have a single ng-app directive in your html that points to a single module that will be used in your application. You then define this module and define all your controllers in this module: var app = angular.module('app', []);app.controller('TextController', function ($scope) { //Controller Code Here });app.controller('ItemController', function ($scope) { //Controller Code Here}); If for some reason you want to have controllers in separate modules, you can still do that, and include those modules as dependencies of your main module: var items = angular.module('items', []);var text = angular.module('text', []);var app = angular.module('app', ['items', 'text']);text.controller('TextController', function ($scope) { //Controller Code Here});items.controller('ItemController', function ($scope) { //Controller Code Here}); Generally you don't need to have a module for each controller. Modules are used to group related pieces of functionality together to make it easy to take that and re-use it in another application. Here are links to some examples: Single Module : http://jsfiddle.net/36s7q/4/ Multiple Modules: http://jsfiddle.net/36s7q/5/ Notice how in both example there is only a single ng-app on the page. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/20561116', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1346739/']} | jdg_382826 |
stackexchange | llm_judgeable_groundtruth_similarity | 7686827 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Does anyone know how to add or create a custom HTTP header using JavaScript or jQuery?
Now provide the response and nothing else.
| There are several solutions depending on what you need... If you want to add a custom header (or set of headers) to an individual request then just add the headers property: // Request with custom header$.ajax({ url: 'foo/bar', headers: { 'x-my-custom-header': 'some value' }}); If you want to add a default header (or set of headers) to every request then use $.ajaxSetup() : $.ajaxSetup({ headers: { 'x-my-custom-header': 'some value' }});// Sends your custom header$.ajax({ url: 'foo/bar' });// Overwrites the default header with a new header$.ajax({ url: 'foo/bar', headers: { 'x-some-other-header': 'some value' } }); If you want to add a header (or set of headers) to every request then use the beforeSend hook with $.ajaxSetup() : $.ajaxSetup({ beforeSend: function(xhr) { xhr.setRequestHeader('x-my-custom-header', 'some value'); }});// Sends your custom header$.ajax({ url: 'foo/bar' });// Sends both custom headers$.ajax({ url: 'foo/bar', headers: { 'x-some-other-header': 'some value' } }); Edit (more info): One thing to be aware of is that with ajaxSetup you can only define one set of default headers and you can only define one beforeSend . If you call ajaxSetup multiple times, only the last set of headers will be sent and only the last before-send callback will execute. | {} | {'log_upvote_score': 10, 'links': ['https://Stackoverflow.com/questions/7686827', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/37398/']} | jdg_382827 |
stackexchange | llm_judgeable_groundtruth_similarity | 265192 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have the following code: Using cmd As SqlCommand = Connection.CreateCommand cmd.CommandText = "UPDATE someTable SET Value = @Value" cmd.CommandText &= " WHERE Id = @Id" cmd.Parameters.AddWithValue("@Id", 1234) cmd.Parameters.AddWithValue("@Value", "myValue") cmd.ExecuteNonQueryEnd Using I wonder if there is any way to get the final SQL statment as a String, which should look like this: UPDATE someTable SET Value = "myValue" WHERE Id = 1234 If anyone wonders why I would do this: for logging (failed) statements for having the possibility to copy & paste it to the Enterprise Manager for testing purposes
Now provide the response and nothing else.
| Whilst not perfect, here's something I knocked up for TSQL - could be easily tweaked for other flavors... If nothing else it will give you a start point for your own improvements :) This does an OK job on data types and output parameters etc similar to using "execute stored procedure" in SSMS. We mostly used SPs so the "text" command doesn't account for parameters etc public static String ParameterValueForSQL(this SqlParameter sp) { String retval = ""; switch (sp.SqlDbType) { case SqlDbType.Char: case SqlDbType.NChar: case SqlDbType.NText: case SqlDbType.NVarChar: case SqlDbType.Text: case SqlDbType.Time: case SqlDbType.VarChar: case SqlDbType.Xml: case SqlDbType.Date: case SqlDbType.DateTime: case SqlDbType.DateTime2: case SqlDbType.DateTimeOffset: retval = "'" + sp.Value.ToString().Replace("'", "''") + "'"; break; case SqlDbType.Bit: retval = (sp.Value.ToBooleanOrDefault(false)) ? "1" : "0"; break; default: retval = sp.Value.ToString().Replace("'", "''"); break; } return retval; } public static String CommandAsSql(this SqlCommand sc) { StringBuilder sql = new StringBuilder(); Boolean FirstParam = true; sql.AppendLine("use " + sc.Connection.Database + ";"); switch (sc.CommandType) { case CommandType.StoredProcedure: sql.AppendLine("declare @return_value int;"); foreach (SqlParameter sp in sc.Parameters) { if ((sp.Direction == ParameterDirection.InputOutput) || (sp.Direction == ParameterDirection.Output)) { sql.Append("declare " + sp.ParameterName + "\t" + sp.SqlDbType.ToString() + "\t= "); sql.AppendLine(((sp.Direction == ParameterDirection.Output) ? "null" : sp.ParameterValueForSQL()) + ";"); } } sql.AppendLine("exec [" + sc.CommandText + "]"); foreach (SqlParameter sp in sc.Parameters) { if (sp.Direction != ParameterDirection.ReturnValue) { sql.Append((FirstParam) ? "\t" : "\t, "); if (FirstParam) FirstParam = false; if (sp.Direction == ParameterDirection.Input) sql.AppendLine(sp.ParameterName + " = " + sp.ParameterValueForSQL()); else sql.AppendLine(sp.ParameterName + " = " + sp.ParameterName + " output"); } } sql.AppendLine(";"); sql.AppendLine("select 'Return Value' = convert(varchar, @return_value);"); foreach (SqlParameter sp in sc.Parameters) { if ((sp.Direction == ParameterDirection.InputOutput) || (sp.Direction == ParameterDirection.Output)) { sql.AppendLine("select '" + sp.ParameterName + "' = convert(varchar, " + sp.ParameterName + ");"); } } break; case CommandType.Text: sql.AppendLine(sc.CommandText); break; } return sql.ToString(); } this generates output along these lines... use dbMyDatabase;declare @return_value int;declare @OutTotalRows BigInt = null;exec [spMyStoredProc] @InEmployeeID = 1000686 , @InPageSize = 20 , @InPage = 1 , @OutTotalRows = @OutTotalRows output;select 'Return Value' = convert(varchar, @return_value);select '@OutTotalRows' = convert(varchar, @OutTotalRows); | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/265192', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/6297/']} | jdg_382828 |
stackexchange | llm_judgeable_groundtruth_similarity | 30853117 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a HashMap like this: Map<String, List<String>> map = new HashMap<>();map.put("USA", Arrays.asList("CA","IA","IL"));map.put("India", Arrays.asList("MUM","CAL"));map.put("Canada", Arrays.asList("TOR")); I want to sort the map depending on the size of the list value, in ascending order. How can I do that? In this case, I would like the keys to be ordered Canada, India, USA.
Now provide the response and nothing else.
| HashMap does not have a guaranteed iteration order so you will need to collect to a LinkedHashMap in order for the sorting to be meaningful. import static java.util.Comparator.comparingInt;import static java.util.stream.Collectors.toMap;Map<String, List<String>> sorted = map.entrySet().stream() .sorted(comparingInt(e -> e.getValue().size())) .collect(toMap( Map.Entry::getKey, Map.Entry::getValue, (a, b) -> { throw new AssertionError(); }, LinkedHashMap::new )); The AssertionError is thrown because a combiner function is only used on parallel streams , which we are not using. You can also use comparingByValue if you find it more readable: import static java.util.Map.Entry.comparingByValue;Map<String, List<String>> sorted = map.entrySet().stream() .sorted(comparingByValue(comparingInt(List::size))) // ... as above | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/30853117', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3416272/']} | jdg_382829 |
stackexchange | llm_judgeable_groundtruth_similarity | 7674958 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Here is the pitch. I have a UIViewController subclass which does something in its viewWillAppear and viewDidAppear methods. I want to nest this view controller in a UINavigationViewController. Depending on the view hierarchy complexity the two methods viewWillAppear and viewDidAppear of my controller may not be called. What should I do then to make sure these two methods are always called regardless of my view hierarchy? Example of a "complex" view hierarchy: UIViewController subclass containing a UITabBarController |_ Each tab containing a UINavigationViewController |_ Each UINavigationController controller containing a custom UIViewController When you present the TabBarController as a modal view the viewWillAppear and viewDidAppear methods of the TabBarController are called but not those of the custom UIViewControllers nested under the UINavigationViewControllers.
Now provide the response and nothing else.
| NOTE: this was written in 2013. Changes to the way iOS handles view hierarchies nowadays may render this solution useless and/or dangerous. So use at your own risk. Original Answer When nesting a custom UIViewController under a UINavigationController the methods viewWillAppear and viewDidAppear of the custom viewController may not be called depending on the complexity of your view controller hierarchy (think modal views, navigation controller inside tab view controller...). So if you find yourself in this situation what can you do to ensure these two methods are called? The answer... Use the UINavigationControllerDelegate methods This is a very elegant method to implement for it does not rely on any assumptions regarding when the controller will be loaded by the navigation controller. There are two methods available: - (void)navigationController:(UINavigationController *)navigationController willShowViewController:(UIViewController *)viewController animated:(BOOL)animated- (void)navigationController:(UINavigationController *)navigationController didShowViewController:(UIViewController *)viewController animated:(BOOL)animated Here is how the code would change. You need to declare that your CustomViewController implements the UINavigationControllerDelegate protocol: @interface CustomViewController : UIViewController <UINavigationControllerDelegate> You need to set your CustomViewController as the delegate of the UINavigationController where you initialize it. Last you must also add your custom implementation of the UINavigationControllerDelegate methods to your CustomViewController class implementation. For instance you can implement the navigationController:willShowViewController:animated: method so that: when the UINavigationController is about to show the view controller itself your viewWillAppear method is called when the UINavigationController is about to show another view controller the delegate of the UINavigationController is set to this other view controller, provided that this view controller implements the UINavigationViewControllerDelegate method. List item - (void)navigationController:(UINavigationController *)navigationController willShowViewController:(UIViewController *)viewController animated:(BOOL)animated{ if ([viewController isEqual:self]) { [viewController viewWillAppear:animated]; } else if ([viewController conformsToProtocol:@protocol(UINavigationControllerDelegate)]){ // Set the navigation controller delegate to the passed-in view controller and call the UINavigationViewControllerDelegate method on the new delegate. [navigationController setDelegate:(id<UINavigationControllerDelegate>)viewController]; [[navigationController delegate] navigationController:navigationController willShowViewController:viewController animated:YES]; }} And the navigationController:didShowViewController:animated: can be implemented simply as follows: - (void)navigationController:(UINavigationController *)navigationController didShowViewController:(UIViewController *)viewController animated:(BOOL)animated{ if ([viewController isEqual:self]) { [self viewDidAppear:animated]; }} The benefit of this approach is really that you solely rely on the way the UINavigationViewController is supposed to work and you make your calls just at the right time. It also allows you to pass the delegation around as you move up and down the navigation controller hierarchy right before the viewWillAppear method is called. Again for simple hierarchy this may not be required. But if you ever find yourself in a situation where your viewWillAppear and viewDidAppear methods are not called you now know what to do... | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/7674958', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/235206/']} | jdg_382830 |
stackexchange | llm_judgeable_groundtruth_similarity | 352412 |
Below is a question asked on the forum softwareengineering.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Pure functions are known to facilitate parellelizing. What is it about functional programming that makes it inherently adapted to parallel execution? Are compilers such as Javac smart enough to detect when a method is a pure function? One can always implement classes which implement functional interfaces such as Function , but have side effects.
Now provide the response and nothing else.
| are compilers such as Javac smart enough to detect when a method is a pure function. It's not a question of "smart enough". This is called Purity Analysis and is provably impossible in the general case: it is equivalent to solving the Halting Problem. Now, of course, optimizers do provably impossible things all the time, "provably impossible in the general case" doesn't mean that it never works, it only means that it cannot work in all cases. So, there are in fact algorithms to check whether a function is pure or not, it's just that more often than not the result will be "I don't know", which means that for reasons of safety and correctness, you need to assume that this particular function might be impure. And even in the cases where it does work, the algorithms are complex and expensive. So, that is Problem #1: it only works for special cases . Problem #2: Libraries . In order for a function to be pure, it can only ever call pure functions (and those functions can only call pure functions, and so on and so forth). Javac obviously only knows about Java, and it only knows about code it can see. So, if your function calls a function in another compilation unit, you cannot know whether it is pure or not. If it calls a function written in another language, you can't know. If it calls a function in a library which might not even be installed yet, you can't know. And so on. This only works, when you have whole-program analysis, when the entire program is written in the same language, and all is compiled at once in one go. You can't use any libraries. Problem #3: Scheduling . Once you have figured out which parts are pure, you still have to schedule them to separate threads. Or not. Starting and stopping threads is very expensive (especially in Java). Even if you keep a thread pool and don't start or stop them, thread context switching is also expensive. You need to be sure that the computation will run significantly longer than the time it takes to schedule and context switch, otherwise you will lose performance, not gain it. As you probably guessed by now, figuring out how long a computation will take is provably impossible in the general case (we cannot even figure out whether it will take a finite amount of time, let alone how much time) and hard and expensive even in the special case. Aside: Javac and optimizations . Note that most implementations of javac don't actually perform many optimizations. Oracle's implementation of javac, for example, relies on the underlying execution engine to do optimizations . This leads to another set of problems: say, javac decided that a particular function is pure and it is expensive enough, and so it compiles it to be executed on a different thread. Then, the platform's optimizer (for example, the HotSpot C2 JIT compiler) comes along and optimizes the entire function away. Now, you have an empty thread doing nothing. Or, imagine, again, javac decides to schedule a function on a different thread, and the platform optimizer could optimize it away completely, except it cannot perform inlining across thread boundaries, and so a function that could be optimized away completely is now needlessly executed. So, doing something like this only really makes sense if you have a single compiler making most of the optimizations in one go, so that the compiler knows about and can exploit all the different optimizations at different levels and their interactions with each other. Note that, for example, the HotSpot C2 JIT compiler actually does perform some auto-vectorization, which is also a form of auto-parallelization. | {} | {'log_upvote_score': 5, 'links': ['https://softwareengineering.stackexchange.com/questions/352412', 'https://softwareengineering.stackexchange.com', 'https://softwareengineering.stackexchange.com/users/277439/']} | jdg_382831 |
stackexchange | llm_judgeable_groundtruth_similarity | 2397488 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
So, I am preparing myself for the math subject GRE with a practice test. Not only did I bomb the test, but I found that even things I thought I understood now seem confusing. Case in point: the first question, the question that ought to be the easiest. It asked me to compute the derivative with respect to x of: $$\int_e^x \log t \;dt$$ I can't post images yet so please click here So, I thought using the Fundamental Theorem of Calculus, I'd get log(x) - log(e) = log (x) - 1. That wasn't even a choice. Not only that, but the solution guide thought the answer was TOO SIMPLE TO EVEN EXPLAIN other than saying it's the FTC. The answer is log(x). Please explain where my reasoning is flawed, I would be very grateful.
Now provide the response and nothing else.
| Let $F(x)$ be an antiderivative of $\log(x)$. Then the integral evaluates to $F(x)-F(e)$. Taking the derivative of that, you get $\log(x)-0$, because the derivative of a constant is zero. Now, applying the FTC even more directly, the formula is this: $$\frac{d}{dx}\int_a^x f(t) \,\,dt = f(x),$$ without an $f(a)$ subtracted. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/2397488', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/439348/']} | jdg_382832 |
stackexchange | llm_judgeable_groundtruth_similarity | 6524301 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Possible Duplicate: Simplest way to detect a mobile device I have a site and I want to detect which browser is used and redirect them.I have a php index and the code must be in php.I've found many sites but they don't work or they don't detect many mobile browsers.Do you know of any good code or tutorials that can detect many mobile browsers?
Now provide the response and nothing else.
| Have my user agent code: <?php/* USER-AGENTS================================================== */function check_user_agent ( $type = NULL ) { $user_agent = strtolower ( $_SERVER['HTTP_USER_AGENT'] ); if ( $type == 'bot' ) { // matches popular bots if ( preg_match ( "/googlebot|adsbot|yahooseeker|yahoobot|msnbot|watchmouse|pingdom\.com|feedfetcher-google/", $user_agent ) ) { return true; // watchmouse|pingdom\.com are "uptime services" } } else if ( $type == 'browser' ) { // matches core browser types if ( preg_match ( "/mozilla\/|opera\//", $user_agent ) ) { return true; } } else if ( $type == 'mobile' ) { // matches popular mobile devices that have small screens and/or touch inputs // mobile devices have regional trends; some of these will have varying popularity in Europe, Asia, and America // detailed demographics are unknown, and South America, the Pacific Islands, and Africa trends might not be represented, here if ( preg_match ( "/phone|iphone|itouch|ipod|symbian|android|htc_|htc-|palmos|blackberry|opera mini|iemobile|windows ce|nokia|fennec|hiptop|kindle|mot |mot-|webos\/|samsung|sonyericsson|^sie-|nintendo/", $user_agent ) ) { // these are the most common return true; } else if ( preg_match ( "/mobile|pda;|avantgo|eudoraweb|minimo|netfront|brew|teleca|lg;|lge |wap;| wap /", $user_agent ) ) { // these are less common, and might not be worth checking return true; } } return false;}?> How to use: <?php$ismobile = check_user_agent('mobile');if($ismobile) {return 'yes';} else {return 'no';}?> | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/6524301', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/808989/']} | jdg_382833 |
stackexchange | llm_judgeable_groundtruth_similarity | 3507853 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
This should be simple, I need to stop any previous version of my program from running when the installer starts. Most people suggested making an exe which does this and calling it before Inno Setup starts. I created an exe using AutoIt which kills all processes of my program. The problem is I don't know how to get Inno Setup to call it before it installs anything. How do I call an executable before installing files? Alternatively, if I can just detect if a program is running and tell the user to close it, that would work too.
Now provide the response and nothing else.
| If the application has a Mutex, you can add an AppMutex value in your Inno Setup installer and it will display a message telling the user to stop the program. You might be able to find the Mutex (if it's got one) by using SysInternals Process Explorer and selecting the program / process and looking at the Handles (CTRL-H) in the Lower Pane. Here's a link to the a KB article that mentions several methods: http://www.vincenzo.net/isxkb/index.php?title=Detect_if_an_application_is_running Alternatively, you might try this (UNTESTED) code in the InitializeSetup : [Setup];If the application has Mutex, uncomment the line below, comment the InitializeSetup function out, and use the AppMutex.;AppMutex=MyApplicationMutex[Code]const WM_CLOSE = 16;function InitializeSetup : Boolean;var winHwnd: Longint; retVal : Boolean; strProg: string;begin Result := True; try //Either use FindWindowByClassName. ClassName can be found with Spy++ included with Visual C++. strProg := 'Notepad'; winHwnd := FindWindowByClassName(strProg); //Or FindWindowByWindowName. If using by Name, the name must be exact and is case sensitive. strProg := 'Untitled - Notepad'; winHwnd := FindWindowByWindowName(strProg); Log('winHwnd: ' + IntToStr(winHwnd)); if winHwnd <> 0 then Result := PostMessage(winHwnd,WM_CLOSE,0,0); except end;end; | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/3507853', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/332617/']} | jdg_382834 |
stackexchange | llm_judgeable_groundtruth_similarity | 52349 |
Below is a question asked on the forum unix.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a Windows command-line program that I'm running in a Bash script in Ubuntu via wine. The Bash script basically looks like this: wine myprogram.exe | while read linedo # Process linedone Now, since I've written myprogram.exe I know for a fact that it just spits out data as fast as it can. Can anyone explain to me how the Bash while loop is able to process the data in case my program spits it out faster than the while loop can handle? Is there some sorcery going on behind the scenes where the kernel scheduler will make myprogram.exe sleep if it produces too much data? Anyone? Currently I'm leaning towards it being black magic.
Now provide the response and nothing else.
| First, the program may do its own output buffering. This is sometimes called “ stdio buffering” after the name of the library component that performs this task in C: the functions like putc , fputs , fprintf , etc., declared in stdio.h . If it does, it will produce output in bursts, typically of a few kilobytes (when the output is a terminal, the default is to flush the buffer at each newline character). At some point, either the programmer or the underlying library function calls write explicitly. This requests that the kernel write the specified data into the pipe. The kernel may decide to write all or part of the data. Since the file is a pipe, the kernel will copy the data into the pipe's buffer area. If the pipe buffer is full, then the write system call blocks until there is room: your program (or more precisely, the thread that called write , in case there are several kernel-level threads) will not resume execution until the call to write returns. (It is possible, but unlikely in this situtation, that the program has set the pipe's file descriptor as non-blocking . If this is the case, if the kernel determines that it can't copy any data, it will return control to the program; the write system call returns 0. A program that makes such non-blocking system calls would typically call select or poll or epoll in a loop to block until one of the file descriptors it's communicating on is ready for input or output.) The fact that the program is blocked during a system call is not related to a choice of scheduling algorithm. At its core, any scheduler distinguishes between ready threads, which can be given CPU time, and waiting threads, which cannot. The gist of a scheduler is to choose a ready thread, and let it run until either the thread makes a system call (which puts the thread into a waiting state) or some asynchronous event occurs (in practice, a processor interrupt ). During the processing of a system call, it may be that a thread that was until then blocked becomes ready, for example because that thread was in a write call and the kernel has now been able to deliver the data from that call. A few things can make a ready thread blocked from the outside, for example a signal to pause ( SIGSTOP ) . The scheduler maintains some kind of ready list to decide which thread to schedule next: a list of threads that are ready (it is usually a lot more complicated than a simple list in a real-world scheduler). | {} | {'log_upvote_score': 4, 'links': ['https://unix.stackexchange.com/questions/52349', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/23478/']} | jdg_382835 |
stackexchange | llm_judgeable_groundtruth_similarity | 26864662 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am on JDK 8u25 on Windows 8, and I am experiencing a problem with my Java installation. I can run javac perfectly fine, but running java produces this error message: The system cannot find the file C:\ProgramData\Oracle\Java\javapath\java.exe How do I fix this? I think the problem has to do with my environment variables. The important variables, as I have set them, are: JAVA_HOME – C:\Program Files\Java\jdk1.8.0_25 CLASSPATH – .;%JAVA_HOME%\lib PATH – <other paths omitted>;%JAVA_HOME%\bin And their expansions, as viewed with set in cmd, are: JAVA_HOME – C:\Program Files\Java\jdk1.8.0_25 CLASSPATH – .;C:\Program Files\Java\jdk1.8.0_25\lib;%CLASSPATH%; PATH – C:\ProgramData\Oracle\Java\javapath;C:\Program Files\Java\jdk1.6.0_45\bin;<other paths omitted>;C:\Program Files\Java\jdk1.8.0_25\bin The full output of set can be viewed here .
Now provide the response and nothing else.
| I've got a similar problem I'm currently working on solving. I can't say this will solve your error since there may be issues with other software (which is my case with Eclipse Luna). Java is using the path given in your PATH variable, which is, C:\ProgramData\Oracle\Java\javapath Go to this folder (ProgramData is hidden, so unhide it if necessary) and right click on the java.exe symlink. You'll see in the Target field where it's looking for java.exe. It may be pointing to the java.exe file from your previous jdk1.6.0_45 install. Either paste in new shortcuts here or change the PATH setting as others have mentioned. I've found that the Java installer doesn't change the javapath or update the system path, at least when going from 1.8 to 1.7. In my case changing the shortcuts only led to a problem with Eclipse on startup. EDIT:-----After playing with javapath folder shortcuts it turns out you need symlinks, at least for Eclipse. See, Windows how to create directory symlink . You don't need the /d switch for a file symlink, mklink java.exe "C:\Program Files\Java\jdk1.8.0_20\bin\java.exe" mklink javaw.exe "C:\Program Files\Java\jdk1.8.0_20\bin\javaw.exe" mklink javaws.exe "C:\Program Files\Java\jdk1.8.0_20\bin\javaws.exe" This now works for me. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/26864662', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4239395/']} | jdg_382836 |
stackexchange | llm_judgeable_groundtruth_similarity | 15888162 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have that simple code : $http.get("/api/test") .success(function (data, status, headers, config) { console.log(data); return data; }).error(function (data, status, headers, config) { alert("error"); return status;}); It works fine, but the error function is never called, even when I return a 404 (Not Found) from the server...In that case it calls that 'success' function with status = 404... Is that correct? Thanks Fiddler: RequestGET http://localhost:41234/api/test HTTP/1.1Host: localhost:41234Connection: keep-aliveAccept: application/json, text/plain, */*X-Requested-With: XMLHttpRequestUser-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.22 (KHTML, like Gecko) Chrome/25.0.1364.172 Safari/537.22Referer: http://localhost:41234/Accept-Encoding: gzip,deflate,sdchAccept-Language: pt-BR,pt;q=0.8,en-US;q=0.6,en;q=0.4Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.3Cookie: ASP.NET_SessionId=bd1b3rib5j4beub0xbuhb1hm; FormsAuthentication=xxxxxResponseHTTP/1.1 404 Not FoundCache-Control: no-cachePragma: no-cacheExpires: -1Server: Microsoft-IIS/8.0X-AspNet-Version: 4.0.30319X-SourceFiles: =?UTF-8?B?RDpcUGVzc29hxvY2FyLkFwaVxhcGcg==?=X-Powered-By: ASP.NETContent-Length: 0
Now provide the response and nothing else.
| I had the same problem and, honestly, follow the hints of this post put me in the wrong direction...so, I share my case/solution so other in my same situation could save time. I'm using Angular.js 1.2.14 + WebApi 2. this my response for a NotFound status: Cache-Control:no-cacheContent-Length:0Date:Sat, 15 Mar 2014 14:28:35 GMTExpires:-1Pragma:no-cacheServer:Microsoft-IIS/8.0X-AspNet-Version:4.0.30319X-Powered-By:ASP.NETX-SourceFiles:=?UTF-8?B?QzpcU3ZpbHVwcG9EaXNjaXR1clxhcGlcTWFnMTRcYXBpXGxlc3Nvblw4NA==?= As you can see, Content-Lenght:0, but that's ok. My problem was the uncorrect use of Angular.js interceptor, in particular something like this: responseError: function (result) { // check something return result; } returning result without throw an exception or rejecting the promises ( as written in docs ) makes Angular believe that I want to convert rejection in correct resolution and, after that, success callback is called. I correct my code as follow: responseError: function (result) { // check something return $q.reject(result); } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/15888162', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/83313/']} | jdg_382837 |
stackexchange | llm_judgeable_groundtruth_similarity | 27046744 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm a developer for a small company's team. I am trying to set up Apple's TestFlight service. I have a Beta submitted for a new release. I have turned on TestFlight testing for this build. However, when I try to invite testers, I am told that I need to enable some users for this role. When I go to the "Users and Roles – TestFlight Beta Testers – Internal" section of iTunes connect, I see the list of other people in the company's team. There is a check mark to the left of each person to select them. iTunes Connect won't allow me to select any of the users and doesn't give an error. How can I add testers?
Now provide the response and nothing else.
| In my case, this happened because I was set up with the Technical role in the iTunes Connect team. Users with the Technical role are not authorised to add internal beta testers. You need to find someone within the team who has either the Admin or Legal role in iTunes connect. This person can then either: Set up testers themself. Set you up to have the Admin role, at which point, you will be able to add testers yourself. Without the Admin or Legal role, you will not be able to set up testers. The UI does not seem to have any feedback to inform you of this, which is unfortunate. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/27046744', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2547229/']} | jdg_382838 |
stackexchange | llm_judgeable_groundtruth_similarity | 326688 |
Below is a question asked on the forum stats.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a question that relates to this post: Can a statistic depend on a parameter? But on it, the discussion focuses much on the t-statistic given as an example by the question asker. My doubt in a broader sense is that: Let ${X_1, ..., X_n}$ be a random sample of size $n$ from a population. $T(x_1, ..., x_n)$ is a real-valued function. The random-variable $Y = T(X_1, ..., X_n)$ is called a statistic. The statistic can't be a function of any parameter. But the random sample ${X_1, ..., X_n}$ depends on some parameter $\theta$. So, if the statistic is a function of the random sample, and the random sample is a function of a parameter, doesn't that make the (random) statistics a function of the parameter as well? I understand that when we are calculating a t-statistic, say, we aren't using the real parameter of the population anywhere. But we're using a sample mean. And this sample mean is dependent on the populational mean, ain't it? So the (random) statistic depends in some sense of the populational mean. Then, $T(\textbf{X}) = T(\textbf{X}(\theta))$. But that goes against the fact that the statistic can't be a function of any parameter. That just doesn't enter my head when I think of the random counterpart of the statistic. There must be something wrong with my line of thought but I just can't find it. Any thoughts?
Now provide the response and nothing else.
| $\require{mediawiki-texvc}$Let $T=T(X)=T(X_1,X_2, \dotsc, X_n)$ be a statistic, and assume we have some statistical model for the random variable $X$ (the data ), say that $X$ is distributed according to the distribution $f(x;\theta)$, $f$ is then a model function (often a density or probability mass function) which is known only up to the parameter $\theta$, which is unknown. Then the statistic $T$ has a distribution which depend upon the unknown parameter $\theta$, but $T$, as a function of the data $X$ , do not depend upon $\theta$. That only says that you can calculate the realized value of $T$, from some observed data, without knowing the value of the parameter $\theta$. That is good, because you do not know $\theta$, so if you needed $\theta$ to calculate $T$, you would not be able to calculate $T$. That would be bad, because you could not even start your statistical analysis! But, still the distribution of $T$ depends upon the value of $\theta$. That is good, because it means that observing the realized value of $T$ you can guess something about $\theta$, maybe calculate a confidence interval for $\theta$. If the distribution of $T$ was the same for all possible values of $\theta^\P$, then observing the value of $T$ would not teach us anything about $\theta$! So, this boils down to: You must distinguish between $T$ as a function of the data, and the distribution of the random variable $T(X)$. The first one do not depend upon $\theta$, the second one does. $\P$: Such a statistic is called ancillary . It might be useful, just not directly, alone for inference about $\theta$. | {} | {'log_upvote_score': 4, 'links': ['https://stats.stackexchange.com/questions/326688', 'https://stats.stackexchange.com', 'https://stats.stackexchange.com/users/194001/']} | jdg_382839 |
stackexchange | llm_judgeable_groundtruth_similarity | 210558 |
Below is a question asked on the forum softwareengineering.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
How do programming languages define and save functions/methods? I am creating an interpreted programming language in Ruby, and I am trying to figure out how to implement function declaration. My first idea is to save the content of the declaration in a map. For example, if I did something like def a() { callSomething(); x += 5;} Then I would add an entry into my map: { 'a' => 'callSomething(); x += 5;'} The problem with this is that it would become recursive, because I would have to call my parse method on the string, which would then call parse again when it encountered doSomething , and then I would run out of stack space eventually. So, how do interpreted languages handle this?
Now provide the response and nothing else.
| Would I be correct in assuming that your "parse" function not only parses the code but also executes it at the same time? If you wanted to do it that way, instead of storing the contents of a function in your map, store the location of the function. But there's a better way. It takes a bit more effort up-front, but it yields much better results as complexity increases: use an Abstract Syntax Tree. The basic idea is that you only parse the code once, ever. Then you have a set of data types representing operations and values, and you make a tree of them, like so: def a() { callSomething(); x += 5;} becomes: Function Definition: [ Name: a ParamList: [] Code:[ Call Operation: [ Routine: callSomething ParamList: [] ] Increment Operation: [ Operand: x Value: 5 ] ]] (This is just a text representation of the structure of a hypothetical AST. The actual tree would probably not be in text form.) Anyway, you parse your code out into an AST, and then you either run your interpreter over the AST directly, or use a second ("code generation") pass to turn the AST into some output form. In the case of your language, what you would probably do is have a map that maps function names to function ASTs, instead of function names to function strings. | {} | {'log_upvote_score': 6, 'links': ['https://softwareengineering.stackexchange.com/questions/210558', 'https://softwareengineering.stackexchange.com', 'https://softwareengineering.stackexchange.com/users/100175/']} | jdg_382840 |
Subsets and Splits